From 9807a54cd74149988f5d20088bf7a7957c205bfb Mon Sep 17 00:00:00 2001 From: Jarno Rajahalme Date: Mon, 7 Jan 2013 09:54:31 -0800 Subject: linux/openvswitch.h: Make OVSP_LOCAL 32-bit. OVS ports are now 32-bit, so OVSP_LOCAL should be too. (Internally, kernel module still keeps port numbers 16-bit, though.) Signed-off-by: Jarno Rajahalme Signed-off-by: Jesse Gross --- include/linux/openvswitch.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/openvswitch.h b/include/linux/openvswitch.h index d42e174bd0c8..99e6414a40d9 100644 --- a/include/linux/openvswitch.h +++ b/include/linux/openvswitch.h @@ -94,7 +94,7 @@ struct ovs_vport_stats { }; /* Fixed logical ports. */ -#define OVSP_LOCAL ((__u16)0) +#define OVSP_LOCAL ((__u32)0) /* Packet transfer. */ -- cgit v1.2.3 From 345046673449b5c35840e5cc34a60059cbec9305 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:00:53 +0000 Subject: slab: Move kmalloc related function defs Move these functions higher up in slab.h so that they are grouped with other generic kmalloc related definitions. Acked-by: Glauber Costa Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 5d168d7e0a28..ccbb37685c6c 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -147,6 +147,15 @@ void kmem_cache_free(struct kmem_cache *, void *); sizeof(struct __struct), __alignof__(struct __struct),\ (__flags), NULL) +/* + * Common kmalloc functions provided by all allocators + */ +void * __must_check __krealloc(const void *, size_t, gfp_t); +void * __must_check krealloc(const void *, size_t, gfp_t); +void kfree(const void *); +void kzfree(const void *); +size_t ksize(const void *); + /* * The largest kmalloc size supported by the slab allocators is * 32 megabyte (2^25) or the maximum allocatable page order if that is @@ -224,15 +233,6 @@ struct seq_file; int cache_show(struct kmem_cache *s, struct seq_file *m); void print_slabinfo_header(struct seq_file *m); -/* - * Common kmalloc functions provided by all allocators - */ -void * __must_check __krealloc(const void *, size_t, gfp_t); -void * __must_check krealloc(const void *, size_t, gfp_t); -void kfree(const void *); -void kzfree(const void *); -size_t ksize(const void *); - /* * Allocator specific definitions. These are mainly used to establish optimized * ways to convert kmalloc() calls to kmem_cache_alloc() invocations by -- cgit v1.2.3 From ce6a50263d4ddeba1f0d08f16716a82770c03690 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:14:19 +0000 Subject: slab: Common kmalloc slab index determination Extract the function to determine the index of the slab within the array of kmalloc caches as well as a function to determine maximum object size from the nr of the kmalloc slab. This is used here only to simplify slub bootstrap but will be used later also for SLAB. Acked-by: Glauber Costa Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 172 +++++++++++++++++++++++++++++++++-------------- include/linux/slub_def.h | 63 ----------------- 2 files changed, 122 insertions(+), 113 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index ccbb37685c6c..c97fe92532d1 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -94,29 +94,6 @@ #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \ (unsigned long)ZERO_SIZE_PTR) -/* - * Common fields provided in kmem_cache by all slab allocators - * This struct is either used directly by the allocator (SLOB) - * or the allocator must include definitions for all fields - * provided in kmem_cache_common in their definition of kmem_cache. - * - * Once we can do anonymous structs (C11 standard) we could put a - * anonymous struct definition in these allocators so that the - * separate allocations in the kmem_cache structure of SLAB and - * SLUB is no longer needed. - */ -#ifdef CONFIG_SLOB -struct kmem_cache { - unsigned int object_size;/* The original size of the object */ - unsigned int size; /* The aligned/padded/added on size */ - unsigned int align; /* Alignment as calculated */ - unsigned long flags; /* Active flags on the slab */ - const char *name; /* Slab name for sysfs */ - int refcount; /* Use counter */ - void (*ctor)(void *); /* Called on object slot creation */ - struct list_head list; /* List of all slab caches on the system */ -}; -#endif struct mem_cgroup; /* @@ -156,6 +133,35 @@ void kfree(const void *); void kzfree(const void *); size_t ksize(const void *); +#ifdef CONFIG_SLOB +/* + * Common fields provided in kmem_cache by all slab allocators + * This struct is either used directly by the allocator (SLOB) + * or the allocator must include definitions for all fields + * provided in kmem_cache_common in their definition of kmem_cache. + * + * Once we can do anonymous structs (C11 standard) we could put a + * anonymous struct definition in these allocators so that the + * separate allocations in the kmem_cache structure of SLAB and + * SLUB is no longer needed. + */ +struct kmem_cache { + unsigned int object_size;/* The original size of the object */ + unsigned int size; /* The aligned/padded/added on size */ + unsigned int align; /* Alignment as calculated */ + unsigned long flags; /* Active flags on the slab */ + const char *name; /* Slab name for sysfs */ + int refcount; /* Use counter */ + void (*ctor)(void *); /* Called on object slot creation */ + struct list_head list; /* List of all slab caches on the system */ +}; + +#define KMALLOC_MAX_SIZE (1UL << 30) + +#include + +#else /* CONFIG_SLOB */ + /* * The largest kmalloc size supported by the slab allocators is * 32 megabyte (2^25) or the maximum allocatable page order if that is @@ -171,6 +177,99 @@ size_t ksize(const void *); #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_HIGH) #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_HIGH - PAGE_SHIFT) +/* + * Kmalloc subsystem. + */ +#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 +#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN +#else +#ifdef CONFIG_SLAB +#define KMALLOC_MIN_SIZE 32 +#else +#define KMALLOC_MIN_SIZE 8 +#endif +#endif + +#define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) + +/* + * Figure out which kmalloc slab an allocation of a certain size + * belongs to. + * 0 = zero alloc + * 1 = 65 .. 96 bytes + * 2 = 120 .. 192 bytes + * n = 2^(n-1) .. 2^n -1 + */ +static __always_inline int kmalloc_index(size_t size) +{ + if (!size) + return 0; + + if (size <= KMALLOC_MIN_SIZE) + return KMALLOC_SHIFT_LOW; + + if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96) + return 1; + if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192) + return 2; + if (size <= 8) return 3; + if (size <= 16) return 4; + if (size <= 32) return 5; + if (size <= 64) return 6; + if (size <= 128) return 7; + if (size <= 256) return 8; + if (size <= 512) return 9; + if (size <= 1024) return 10; + if (size <= 2 * 1024) return 11; + if (size <= 4 * 1024) return 12; + if (size <= 8 * 1024) return 13; + if (size <= 16 * 1024) return 14; + if (size <= 32 * 1024) return 15; + if (size <= 64 * 1024) return 16; + if (size <= 128 * 1024) return 17; + if (size <= 256 * 1024) return 18; + if (size <= 512 * 1024) return 19; + if (size <= 1024 * 1024) return 20; + if (size <= 2 * 1024 * 1024) return 21; + if (size <= 4 * 1024 * 1024) return 22; + if (size <= 8 * 1024 * 1024) return 23; + if (size <= 16 * 1024 * 1024) return 24; + if (size <= 32 * 1024 * 1024) return 25; + if (size <= 64 * 1024 * 1024) return 26; + BUG(); + + /* Will never be reached. Needed because the compiler may complain */ + return -1; +} + +#ifdef CONFIG_SLAB +#include +#elif defined(CONFIG_SLUB) +#include +#else +#error "Unknown slab allocator" +#endif + +/* + * Determine size used for the nth kmalloc cache. + * return size or 0 if a kmalloc cache for that + * size does not exist + */ +static __always_inline int kmalloc_size(int n) +{ + if (n > 2) + return 1 << n; + + if (n == 1 && KMALLOC_MIN_SIZE <= 32) + return 96; + + if (n == 2 && KMALLOC_MIN_SIZE <= 64) + return 192; + + return 0; +} +#endif /* !CONFIG_SLOB */ + /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. @@ -233,33 +332,6 @@ struct seq_file; int cache_show(struct kmem_cache *s, struct seq_file *m); void print_slabinfo_header(struct seq_file *m); -/* - * Allocator specific definitions. These are mainly used to establish optimized - * ways to convert kmalloc() calls to kmem_cache_alloc() invocations by - * selecting the appropriate general cache at compile time. - * - * Allocators must define at least: - * - * kmem_cache_alloc() - * __kmalloc() - * kmalloc() - * - * Those wishing to support NUMA must also define: - * - * kmem_cache_alloc_node() - * kmalloc_node() - * - * See each allocator definition file for additional comments and - * implementation notes. - */ -#ifdef CONFIG_SLUB -#include -#elif defined(CONFIG_SLOB) -#include -#else -#include -#endif - /** * kmalloc_array - allocate memory for an array. * @n: number of elements. diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 9db4825cd393..99c3e05ff1f0 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -115,17 +115,6 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -/* - * Kmalloc subsystem. - */ -#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 -#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN -#else -#define KMALLOC_MIN_SIZE 8 -#endif - -#define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) - /* * Maximum kmalloc object size handled by SLUB. Larger object allocations * are passed through to the page allocator. The page allocator "fastpath" @@ -152,58 +141,6 @@ struct kmem_cache { */ extern struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT]; -/* - * Sorry that the following has to be that ugly but some versions of GCC - * have trouble with constant propagation and loops. - */ -static __always_inline int kmalloc_index(size_t size) -{ - if (!size) - return 0; - - if (size <= KMALLOC_MIN_SIZE) - return KMALLOC_SHIFT_LOW; - - if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96) - return 1; - if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192) - return 2; - if (size <= 8) return 3; - if (size <= 16) return 4; - if (size <= 32) return 5; - if (size <= 64) return 6; - if (size <= 128) return 7; - if (size <= 256) return 8; - if (size <= 512) return 9; - if (size <= 1024) return 10; - if (size <= 2 * 1024) return 11; - if (size <= 4 * 1024) return 12; -/* - * The following is only needed to support architectures with a larger page - * size than 4k. We need to support 2 * PAGE_SIZE here. So for a 64k page - * size we would have to go up to 128k. - */ - if (size <= 8 * 1024) return 13; - if (size <= 16 * 1024) return 14; - if (size <= 32 * 1024) return 15; - if (size <= 64 * 1024) return 16; - if (size <= 128 * 1024) return 17; - if (size <= 256 * 1024) return 18; - if (size <= 512 * 1024) return 19; - if (size <= 1024 * 1024) return 20; - if (size <= 2 * 1024 * 1024) return 21; - BUG(); - return -1; /* Will never be reached */ - -/* - * What we really wanted to do and cannot do because of compiler issues is: - * int i; - * for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) - * if (size <= (1 << i)) - * return i; - */ -} - /* * Find the slab cache for a given combination of allocation flags and size. * -- cgit v1.2.3 From e33660165c901d18e7d3df2290db070d3e4b46df Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:14:18 +0000 Subject: slab: Use common kmalloc_index/kmalloc_size functions Make slab use the common functions. We can get rid of a lot of old ugly stuff as a results. Among them the sizes array and the weird include/linux/kmalloc_sizes file and some pretty bad #include statements in slab_def.h. The one thing that is different in slab is that the 32 byte cache will also be created for arches that have page sizes larger than 4K. There are numerous smaller allocations that SLOB and SLUB can handle better because of their support for smaller allocation sizes so lets keep the 32 byte slab also for arches with > 4K pages. Reviewed-by: Glauber Costa Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/kmalloc_sizes.h | 45 ----------------------------------------- include/linux/slab_def.h | 47 +++++++++++-------------------------------- 2 files changed, 12 insertions(+), 80 deletions(-) delete mode 100644 include/linux/kmalloc_sizes.h (limited to 'include/linux') diff --git a/include/linux/kmalloc_sizes.h b/include/linux/kmalloc_sizes.h deleted file mode 100644 index e576b848ce10..000000000000 --- a/include/linux/kmalloc_sizes.h +++ /dev/null @@ -1,45 +0,0 @@ -#if (PAGE_SIZE == 4096) - CACHE(32) -#endif - CACHE(64) -#if L1_CACHE_BYTES < 64 - CACHE(96) -#endif - CACHE(128) -#if L1_CACHE_BYTES < 128 - CACHE(192) -#endif - CACHE(256) - CACHE(512) - CACHE(1024) - CACHE(2048) - CACHE(4096) - CACHE(8192) - CACHE(16384) - CACHE(32768) - CACHE(65536) - CACHE(131072) -#if KMALLOC_MAX_SIZE >= 262144 - CACHE(262144) -#endif -#if KMALLOC_MAX_SIZE >= 524288 - CACHE(524288) -#endif -#if KMALLOC_MAX_SIZE >= 1048576 - CACHE(1048576) -#endif -#if KMALLOC_MAX_SIZE >= 2097152 - CACHE(2097152) -#endif -#if KMALLOC_MAX_SIZE >= 4194304 - CACHE(4194304) -#endif -#if KMALLOC_MAX_SIZE >= 8388608 - CACHE(8388608) -#endif -#if KMALLOC_MAX_SIZE >= 16777216 - CACHE(16777216) -#endif -#if KMALLOC_MAX_SIZE >= 33554432 - CACHE(33554432) -#endif diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 8bb6e0eaf3c6..e0f30ef9525d 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -11,8 +11,6 @@ */ #include -#include /* kmalloc_sizes.h needs PAGE_SIZE */ -#include /* kmalloc_sizes.h needs L1_CACHE_BYTES */ #include /* @@ -104,15 +102,8 @@ struct kmem_cache { */ }; -/* Size description struct for general caches. */ -struct cache_sizes { - size_t cs_size; - struct kmem_cache *cs_cachep; -#ifdef CONFIG_ZONE_DMA - struct kmem_cache *cs_dmacachep; -#endif -}; -extern struct cache_sizes malloc_sizes[]; +extern struct kmem_cache *kmalloc_caches[PAGE_SHIFT + MAX_ORDER]; +extern struct kmem_cache *kmalloc_dma_caches[PAGE_SHIFT + MAX_ORDER]; void *kmem_cache_alloc(struct kmem_cache *, gfp_t); void *__kmalloc(size_t size, gfp_t flags); @@ -133,26 +124,19 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) void *ret; if (__builtin_constant_p(size)) { - int i = 0; + int i; if (!size) return ZERO_SIZE_PTR; -#define CACHE(x) \ - if (size <= x) \ - goto found; \ - else \ - i++; -#include -#undef CACHE - return NULL; -found: + i = kmalloc_index(size); + #ifdef CONFIG_ZONE_DMA if (flags & GFP_DMA) - cachep = malloc_sizes[i].cs_dmacachep; + cachep = kmalloc_dma_caches[i]; else #endif - cachep = malloc_sizes[i].cs_cachep; + cachep = kmalloc_caches[i]; ret = kmem_cache_alloc_trace(cachep, flags, size); @@ -186,26 +170,19 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) struct kmem_cache *cachep; if (__builtin_constant_p(size)) { - int i = 0; + int i; if (!size) return ZERO_SIZE_PTR; -#define CACHE(x) \ - if (size <= x) \ - goto found; \ - else \ - i++; -#include -#undef CACHE - return NULL; -found: + i = kmalloc_index(size); + #ifdef CONFIG_ZONE_DMA if (flags & GFP_DMA) - cachep = malloc_sizes[i].cs_dmacachep; + cachep = kmalloc_dma_caches[i]; else #endif - cachep = malloc_sizes[i].cs_cachep; + cachep = kmalloc_caches[i]; return kmem_cache_alloc_node_trace(cachep, flags, node, size); } -- cgit v1.2.3 From 6744f087ba2a49f6d6935d9daa0b20a0f03567b5 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:12:17 +0000 Subject: slab: Common name for the per node structures Rename the structure used for the per node structures in slab to have a name that expresses that fact. Acked-by: Glauber Costa Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab_def.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index e0f30ef9525d..8b5b2f6b36d3 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -95,7 +95,7 @@ struct kmem_cache { * pointer for each node since "nodelists" uses the remainder of * available pointers. */ - struct kmem_list3 **nodelists; + struct kmem_cache_node **nodelists; struct array_cache *array[NR_CPUS + MAX_NUMNODES]; /* * Do not add fields after array[] -- cgit v1.2.3 From 6a67368c36e2c0c2578ba62f6264ab739af08cce Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:14:19 +0000 Subject: slab: Rename nodelists to node Have a common naming between both slab caches for future changes. Acked-by: Glauber Costa Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab_def.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 8b5b2f6b36d3..4ff50e8d1a2c 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -95,7 +95,7 @@ struct kmem_cache { * pointer for each node since "nodelists" uses the remainder of * available pointers. */ - struct kmem_cache_node **nodelists; + struct kmem_cache_node **node; struct array_cache *array[NR_CPUS + MAX_NUMNODES]; /* * Do not add fields after array[] -- cgit v1.2.3 From 95a05b428cc675694321c8f762591984f3fd2b1e Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:14:19 +0000 Subject: slab: Common constants for kmalloc boundaries Standardize the constants that describe the smallest and largest object kept in the kmalloc arrays for SLAB and SLUB. Differentiate between the maximum size for which a slab cache is used (KMALLOC_MAX_CACHE_SIZE) and the maximum allocatable size (KMALLOC_MAX_SIZE, KMALLOC_MAX_ORDER). Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 34 ++++++++++++++++++++++++---------- include/linux/slub_def.h | 19 +++---------------- 2 files changed, 27 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index c97fe92532d1..c01780540054 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -163,7 +163,12 @@ struct kmem_cache { #else /* CONFIG_SLOB */ /* - * The largest kmalloc size supported by the slab allocators is + * Kmalloc array related definitions + */ + +#ifdef CONFIG_SLAB +/* + * The largest kmalloc size supported by the SLAB allocators is * 32 megabyte (2^25) or the maximum allocatable page order if that is * less than 32 MB. * @@ -173,9 +178,24 @@ struct kmem_cache { */ #define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \ (MAX_ORDER + PAGE_SHIFT - 1) : 25) +#define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH +#define KMALLOC_SHIFT_LOW 5 +#else +/* + * SLUB allocates up to order 2 pages directly and otherwise + * passes the request to the page allocator. + */ +#define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) +#define KMALLOC_SHIFT_LOW 3 +#endif -#define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_HIGH) -#define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_HIGH - PAGE_SHIFT) +/* Maximum allocatable size */ +#define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) +/* Maximum size for which we actually use a slab cache */ +#define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH) +/* Maximum order allocatable via the slab allocagtor */ +#define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT) /* * Kmalloc subsystem. @@ -183,15 +203,9 @@ struct kmem_cache { #if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 #define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN #else -#ifdef CONFIG_SLAB -#define KMALLOC_MIN_SIZE 32 -#else -#define KMALLOC_MIN_SIZE 8 -#endif +#define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif -#define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) - /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 99c3e05ff1f0..032028ef9a34 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -115,19 +115,6 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -/* - * Maximum kmalloc object size handled by SLUB. Larger object allocations - * are passed through to the page allocator. The page allocator "fastpath" - * is relatively slow so we need this value sufficiently high so that - * performance critical objects are allocated through the SLUB fastpath. - * - * This should be dropped to PAGE_SIZE / 2 once the page allocator - * "fastpath" becomes competitive with the slab allocator fastpaths. - */ -#define SLUB_MAX_SIZE (2 * PAGE_SIZE) - -#define SLUB_PAGE_SHIFT (PAGE_SHIFT + 2) - #ifdef CONFIG_ZONE_DMA #define SLUB_DMA __GFP_DMA #else @@ -139,7 +126,7 @@ struct kmem_cache { * We keep the general caches in an array of slab caches that are used for * 2^x bytes of allocations. */ -extern struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT]; +extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; /* * Find the slab cache for a given combination of allocation flags and size. @@ -211,7 +198,7 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { - if (size > SLUB_MAX_SIZE) + if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); if (!(flags & SLUB_DMA)) { @@ -247,7 +234,7 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && - size <= SLUB_MAX_SIZE && !(flags & SLUB_DMA)) { + size <= KMALLOC_MAX_CACHE_SIZE && !(flags & SLUB_DMA)) { struct kmem_cache *s = kmalloc_slab(size); if (!s) -- cgit v1.2.3 From 9425c58e5445277699ff3c2a87bac1cfebc1b48d Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:12:17 +0000 Subject: slab: Common definition for the array of kmalloc caches Have a common definition fo the kmalloc cache arrays in SLAB and SLUB Acked-by: Glauber Costa Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 5 +++++ include/linux/slab_def.h | 3 --- include/linux/slub_def.h | 6 ------ 3 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index c01780540054..f2327a898a85 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -206,6 +206,11 @@ struct kmem_cache { #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif +extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; +#ifdef CONFIG_ZONE_DMA +extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1]; +#endif + /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 4ff50e8d1a2c..113ec080313f 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -102,9 +102,6 @@ struct kmem_cache { */ }; -extern struct kmem_cache *kmalloc_caches[PAGE_SHIFT + MAX_ORDER]; -extern struct kmem_cache *kmalloc_dma_caches[PAGE_SHIFT + MAX_ORDER]; - void *kmem_cache_alloc(struct kmem_cache *, gfp_t); void *__kmalloc(size_t size, gfp_t flags); diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 032028ef9a34..3701896f7f8a 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -122,12 +122,6 @@ struct kmem_cache { #define SLUB_DMA (__force gfp_t)0 #endif -/* - * We keep the general caches in an array of slab caches that are used for - * 2^x bytes of allocations. - */ -extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; - /* * Find the slab cache for a given combination of allocation flags and size. * -- cgit v1.2.3 From 2c59dd6544212faa5ce761920d2251f4152f408d Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:14:19 +0000 Subject: slab: Common Kmalloc cache determination Extract the optimized lookup functions from slub and put them into slab_common.c. Then make slab use these functions as well. Joonsoo notes that this fixes some issues with constant folding which also reduces the code size for slub. https://lkml.org/lkml/2012/10/20/82 Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 41 ++++++++++------------------------------- 1 file changed, 10 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 3701896f7f8a..16341e5316de 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -115,29 +115,6 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -#ifdef CONFIG_ZONE_DMA -#define SLUB_DMA __GFP_DMA -#else -/* Disable DMA functionality */ -#define SLUB_DMA (__force gfp_t)0 -#endif - -/* - * Find the slab cache for a given combination of allocation flags and size. - * - * This ought to end up with a global pointer to the right cache - * in kmalloc_caches. - */ -static __always_inline struct kmem_cache *kmalloc_slab(size_t size) -{ - int index = kmalloc_index(size); - - if (index == 0) - return NULL; - - return kmalloc_caches[index]; -} - void *kmem_cache_alloc(struct kmem_cache *, gfp_t); void *__kmalloc(size_t size, gfp_t flags); @@ -195,13 +172,14 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); - if (!(flags & SLUB_DMA)) { - struct kmem_cache *s = kmalloc_slab(size); + if (!(flags & GFP_DMA)) { + int index = kmalloc_index(size); - if (!s) + if (!index) return ZERO_SIZE_PTR; - return kmem_cache_alloc_trace(s, flags, size); + return kmem_cache_alloc_trace(kmalloc_caches[index], + flags, size); } } return __kmalloc(size, flags); @@ -228,13 +206,14 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && - size <= KMALLOC_MAX_CACHE_SIZE && !(flags & SLUB_DMA)) { - struct kmem_cache *s = kmalloc_slab(size); + size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) { + int index = kmalloc_index(size); - if (!s) + if (!index) return ZERO_SIZE_PTR; - return kmem_cache_alloc_node_trace(s, flags, node, size); + return kmem_cache_alloc_node_trace(kmalloc_caches[index], + flags, node, size); } return __kmalloc_node(size, flags, node); } -- cgit v1.2.3 From ca34956b804b7554fc4e88826773380d9d5122a8 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 10 Jan 2013 19:14:19 +0000 Subject: slab: Common definition for kmem_cache_node Put the definitions for the kmem_cache_node structures together so that we have one structure. That will allow us to create more common fields in the future which could yield more opportunities to share code. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 16341e5316de..027276fa8713 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -53,17 +53,6 @@ struct kmem_cache_cpu { #endif }; -struct kmem_cache_node { - spinlock_t list_lock; /* Protect partial list and nr_partial */ - unsigned long nr_partial; - struct list_head partial; -#ifdef CONFIG_SLUB_DEBUG - atomic_long_t nr_slabs; - atomic_long_t total_objects; - struct list_head full; -#endif -}; - /* * Word size structure that can be atomically updated or read and that * contains both the order and the number of objects that a slab of the -- cgit v1.2.3 From c601fd6956e92b0eb268d4af754073c76155b99d Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Tue, 5 Feb 2013 16:36:47 +0000 Subject: slab: Handle ARCH_DMA_MINALIGN correctly James Hogan hit boot problems in next-20130204 on Meta: META213-Thread0 DSP [LogF] kobject (4fc03980): tried to init an initialized object, something is seriously wrong. META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] Call trace: META213-Thread0 DSP [LogF] [<4000888c>] _show_stack+0x68/0x7c META213-Thread0 DSP [LogF] [<400088b4>] _dump_stack+0x14/0x28 META213-Thread0 DSP [LogF] [<40103794>] _kobject_init+0x58/0x9c META213-Thread0 DSP [LogF] [<40103810>] _kobject_create+0x38/0x64 META213-Thread0 DSP [LogF] [<40103eac>] _kobject_create_and_add+0x14/0x8c META213-Thread0 DSP [LogF] [<40190ac4>] _mnt_init+0xd8/0x220 META213-Thread0 DSP [LogF] [<40190508>] _vfs_caches_init+0xb0/0x160 META213-Thread0 DSP [LogF] [<401851f4>] _start_kernel+0x274/0x340 META213-Thread0 DSP [LogF] [<40188424>] _metag_start_kernel+0x58/0x6c META213-Thread0 DSP [LogF] [<40000044>] __start+0x44/0x48 META213-Thread0 DSP [LogF] META213-Thread0 DSP [LogF] devtmpfs: initialized META213-Thread0 DSP [LogF] L2 Cache: Not present META213-Thread0 DSP [LogF] BUG: failure at fs/sysfs/dir.c:736/sysfs_read_ns_type()! META213-Thread0 DSP [LogF] Kernel panic - not syncing: BUG! META213-Thread0 DSP [Thread Exit] Thread has exited - return code = 4294967295 And bisected the problem to commit 95a05b4 ("slab: Common constants for kmalloc boundaries"). As it turns out, a fixed KMALLOC_SHIFT_LOW does not work for arches with higher alignment requirements. Determine KMALLOC_SHIFT_LOW from ARCH_DMA_MINALIGN instead. Reported-and-tested-by: James Hogan Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index f2327a898a85..0c621752caa6 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -133,6 +133,19 @@ void kfree(const void *); void kzfree(const void *); size_t ksize(const void *); +/* + * Some archs want to perform DMA into kmalloc caches and need a guaranteed + * alignment larger than the alignment of a 64-bit integer. + * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. + */ +#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 +#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN +#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN +#define KMALLOC_SHIFT_LOW ilog2(ARCH_DMA_MINALIGN) +#else +#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) +#endif + #ifdef CONFIG_SLOB /* * Common fields provided in kmem_cache by all slab allocators @@ -179,7 +192,9 @@ struct kmem_cache { #define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \ (MAX_ORDER + PAGE_SHIFT - 1) : 25) #define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH +#ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 5 +#endif #else /* * SLUB allocates up to order 2 pages directly and otherwise @@ -187,8 +202,10 @@ struct kmem_cache { */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) +#ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif +#endif /* Maximum allocatable size */ #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) @@ -200,9 +217,7 @@ struct kmem_cache { /* * Kmalloc subsystem. */ -#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 -#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN -#else +#ifndef KMALLOC_MIN_SIZE #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif @@ -289,17 +304,6 @@ static __always_inline int kmalloc_size(int n) } #endif /* !CONFIG_SLOB */ -/* - * Some archs want to perform DMA into kmalloc caches and need a guaranteed - * alignment larger than the alignment of a 64-bit integer. - * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. - */ -#ifdef ARCH_DMA_MINALIGN -#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -#else -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) -#endif - /* * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. * Intended for arches that get misalignment faults even for 64 bit integer -- cgit v1.2.3 From f43f627d2f17e95c78647eeddf968d12f5c286b1 Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Mon, 4 Feb 2013 13:37:20 +0000 Subject: PM: make VT switching to the suspend console optional v3 KMS drivers can potentially restore the display configuration without userspace help. Such drivers can can call a new funciton, pm_vt_switch_required(false) if they support this feature. In that case, the PM layer won't VT switch to the suspend console at suspend time and then back to the original VT on resume, but rather leave things alone for a nicer looking suspend and resume sequence. v2: make a function so we can handle multiple drivers (Alan) v3: use a list to track device requests (Rafael) v4: Squash in build fix from Jesse for CONFIG_VT_CONSOLE_SLEEP=n v5: Squash in patch from Wu Fengguang to add a few missing static qualifiers. v6: Add missing EXPORT_SYMBOL. Signed-off-by: Jesse Barnes Reviewed-by: Rafael J. Wysocki (v3) Signed-off-by: Daniel Vetter --- include/linux/pm.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 03d7bb145311..e5da2f353e8f 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -35,6 +35,19 @@ extern void (*pm_idle)(void); extern void (*pm_power_off)(void); extern void (*pm_power_off_prepare)(void); +struct device; /* we have a circular dep with device.h */ +#ifdef CONFIG_VT_CONSOLE_SLEEP +extern void pm_vt_switch_required(struct device *dev, bool required); +extern void pm_vt_switch_unregister(struct device *dev); +#else +static inline void pm_vt_switch_required(struct device *dev, bool required) +{ +} +static inline void pm_vt_switch_unregister(struct device *dev) +{ +} +#endif /* CONFIG_VT_CONSOLE_SLEEP */ + /* * Device power management */ -- cgit v1.2.3 From 3cf2667b9f8b2c2fe298a427deb399e52321da6b Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Mon, 4 Feb 2013 13:37:21 +0000 Subject: fb: add support for drivers not needing VT switch at suspend/resume time Use the new PM routines to indicate whether we need to VT switch at suspend and resume time. When a new driver is bound, set its flag accordingly, and when unbound, remove it from the PM's console tracking list. Signed-off-by: Jesse Barnes Acked-by: Rafael J. Wysocki Signed-off-by: Daniel Vetter --- include/linux/fb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 58b98606ac26..d49c60f5aa4c 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -501,6 +501,8 @@ struct fb_info { resource_size_t size; } ranges[0]; } *apertures; + + bool skip_vt_switch; /* no VT switch on suspend/resume required */ }; static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { -- cgit v1.2.3 From 4490108b4a5ada14c7be712260829faecc814ae5 Mon Sep 17 00:00:00 2001 From: Ben Pfaff Date: Fri, 15 Feb 2013 17:29:22 -0800 Subject: openvswitch: Allow OVS_USERSPACE_ATTR_USERDATA to be variable length. Until now, the optional OVS_USERSPACE_ATTR_USERDATA attribute had to be exactly 64 bits long, if it was present. However, 64 bits is not enough space to associate as much information with a flow as would be convenient for some userspace features now under development. This commit generalizes the attribute, allowing it to be any length. This generalization is backward-compatible: if userspace only uses 64-bit attributes, then it will not see any change in behavior. CC: Romain Lenglet Signed-off-by: Ben Pfaff Signed-off-by: Jesse Gross --- include/linux/openvswitch.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/openvswitch.h b/include/linux/openvswitch.h index 99e6414a40d9..67d6c7b03581 100644 --- a/include/linux/openvswitch.h +++ b/include/linux/openvswitch.h @@ -127,7 +127,8 @@ enum ovs_packet_cmd { * for %OVS_PACKET_CMD_EXECUTE. It has nested %OVS_ACTION_ATTR_* attributes. * @OVS_PACKET_ATTR_USERDATA: Present for an %OVS_PACKET_CMD_ACTION * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an - * %OVS_USERSPACE_ATTR_USERDATA attribute. + * %OVS_USERSPACE_ATTR_USERDATA attribute, with the same length and content + * specified there. * * These attributes follow the &struct ovs_header within the Generic Netlink * payload for %OVS_PACKET_* commands. @@ -137,7 +138,7 @@ enum ovs_packet_attr { OVS_PACKET_ATTR_PACKET, /* Packet data. */ OVS_PACKET_ATTR_KEY, /* Nested OVS_KEY_ATTR_* attributes. */ OVS_PACKET_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */ - OVS_PACKET_ATTR_USERDATA, /* u64 OVS_ACTION_ATTR_USERSPACE arg. */ + OVS_PACKET_ATTR_USERDATA, /* OVS_ACTION_ATTR_USERSPACE arg. */ __OVS_PACKET_ATTR_MAX }; @@ -389,13 +390,13 @@ enum ovs_sample_attr { * enum ovs_userspace_attr - Attributes for %OVS_ACTION_ATTR_USERSPACE action. * @OVS_USERSPACE_ATTR_PID: u32 Netlink PID to which the %OVS_PACKET_CMD_ACTION * message should be sent. Required. - * @OVS_USERSPACE_ATTR_USERDATA: If present, its u64 argument is copied to the - * %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA, + * @OVS_USERSPACE_ATTR_USERDATA: If present, its variable-length argument is + * copied to the %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA. */ enum ovs_userspace_attr { OVS_USERSPACE_ATTR_UNSPEC, OVS_USERSPACE_ATTR_PID, /* u32 Netlink PID to receive upcalls. */ - OVS_USERSPACE_ATTR_USERDATA, /* u64 optional user-specified cookie. */ + OVS_USERSPACE_ATTR_USERDATA, /* Optional user-specified cookie. */ __OVS_USERSPACE_ATTR_MAX }; -- cgit v1.2.3 From 27cef8b47cfb27fa2955a8577637794f1f275db2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Heiko=20St=C3=BCbner?= Date: Sat, 23 Feb 2013 12:06:44 -0800 Subject: Input: auo-pixcir-ts - handle reset gpio directly Devicetree based platforms don't handle device callbacks very well and until now no board has come along that needs more extended hwinit than pulling the rst gpio high. Therefore pull the reset handling directly into the driver and remove the callbacks from the driver. If extended device setup is needed at some later point, power-sequences would probably be the solution of choice. Signed-off-by: Heiko Stuebner Signed-off-by: Dmitry Torokhov --- include/linux/input/auo-pixcir-ts.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/input/auo-pixcir-ts.h b/include/linux/input/auo-pixcir-ts.h index 75d4be717714..5049f21928e4 100644 --- a/include/linux/input/auo-pixcir-ts.h +++ b/include/linux/input/auo-pixcir-ts.h @@ -43,12 +43,10 @@ */ struct auo_pixcir_ts_platdata { int gpio_int; + int gpio_rst; int int_setting; - void (*init_hw)(struct i2c_client *); - void (*exit_hw)(struct i2c_client *); - unsigned int x_max; unsigned int y_max; }; -- cgit v1.2.3 From e90a6df80dc45ab53d2f4f4db297434e48c0208e Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Mon, 25 Feb 2013 11:31:43 +0100 Subject: HID: Extend the interface with report requests Some drivers send reports directly to underlying device, creating an unwanted dependency on the underlying transport layer. This patch adds hid_hw_request() to the interface, thereby removing usbhid from the lion share of the drivers. Signed-off-by: Henrik Rydberg Signed-off-by: Benjamin Tissoires Reviewed-by: Mika Westerberg Signed-off-by: Jiri Kosina --- include/linux/hid.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index e14b465b1146..261c713d4842 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -662,6 +662,7 @@ struct hid_driver { * @hidinput_input_event: event input event (e.g. ff or leds) * @parse: this method is called only once to parse the device data, * shouldn't allocate anything to not leak memory + * @request: send report request to device (e.g. feature report) */ struct hid_ll_driver { int (*start)(struct hid_device *hdev); @@ -676,6 +677,10 @@ struct hid_ll_driver { unsigned int code, int value); int (*parse)(struct hid_device *hdev); + + void (*request)(struct hid_device *hdev, + struct hid_report *report, int reqtype); + }; #define PM_HINT_FULLON 1<<5 @@ -883,6 +888,21 @@ static inline int hid_hw_power(struct hid_device *hdev, int level) return hdev->ll_driver->power ? hdev->ll_driver->power(hdev, level) : 0; } + +/** + * hid_hw_request - send report request to device + * + * @hdev: hid device + * @report: report to send + * @reqtype: hid request type + */ +static inline void hid_hw_request(struct hid_device *hdev, + struct hid_report *report, int reqtype) +{ + if (hdev->ll_driver->request) + hdev->ll_driver->request(hdev, report, reqtype); +} + int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, int size, int interrupt); -- cgit v1.2.3 From 3373443befa73ee60e4275e7699b26058b01455a Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Mon, 25 Feb 2013 11:31:44 +0100 Subject: HID: Extend the interface with wait io request Some drivers need to wait for an io from the underlying device, creating an unwanted dependency on the underlying transport layer. This patch adds wait() to the interface, thereby removing usbhid from the lion share of the drivers. Signed-off-by: Henrik Rydberg Signed-off-by: Benjamin Tissoires Reviewed-by: Mika Westerberg Signed-off-by: Jiri Kosina --- include/linux/hid.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 261c713d4842..7071eb3d36c7 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -663,6 +663,7 @@ struct hid_driver { * @parse: this method is called only once to parse the device data, * shouldn't allocate anything to not leak memory * @request: send report request to device (e.g. feature report) + * @wait: wait for buffered io to complete (send/recv reports) */ struct hid_ll_driver { int (*start)(struct hid_device *hdev); @@ -681,6 +682,8 @@ struct hid_ll_driver { void (*request)(struct hid_device *hdev, struct hid_report *report, int reqtype); + int (*wait)(struct hid_device *hdev); + }; #define PM_HINT_FULLON 1<<5 @@ -903,6 +906,17 @@ static inline void hid_hw_request(struct hid_device *hdev, hdev->ll_driver->request(hdev, report, reqtype); } +/** + * hid_hw_wait - wait for buffered io to complete + * + * @hdev: hid device + */ +static inline void hid_hw_wait(struct hid_device *hdev) +{ + if (hdev->ll_driver->wait) + hdev->ll_driver->wait(hdev); +} + int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, int size, int interrupt); -- cgit v1.2.3 From d6b0c58048d2c8c6f4955c37f670125b2792cd14 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sat, 23 Feb 2013 13:11:14 -0800 Subject: devres: allow adding custom actions to the stack Sometimes drivers need to execute one-off actions in their error handling or device teardown paths. An example would be toggling a GPIO line to reset the controlled device into predefined state. To allow performing such actions when using managed resources let's allow adding them to stack/group of devres resources. Acked-by: Tejun Heo Acked-by: Greg Kroah-Hartman Signed-off-by: Dmitry Torokhov --- include/linux/device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 86ef6ab553b1..854b247bf5f9 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -567,6 +567,10 @@ extern void devm_kfree(struct device *dev, void *p); void __iomem *devm_request_and_ioremap(struct device *dev, struct resource *res); +/* allows to add/remove a custom action to devres stack */ +int devm_add_action(struct device *dev, void (*action)(void *), void *data); +void devm_remove_action(struct device *dev, void (*action)(void *), void *data); + struct device_dma_parameters { /* * a low level driver may set these to teach IOMMU code about -- cgit v1.2.3 From c849a6143bec520aff2a6646518b0d041402428b Mon Sep 17 00:00:00 2001 From: Andrew de los Reyes Date: Mon, 18 Feb 2013 09:20:21 -0800 Subject: HID: Separate struct hid_device's driver_lock into two locks. This patch separates struct hid_device's driver_lock into two. The goal is to allow hid device drivers to receive input during their probe() or remove() function calls. This is necessary because some drivers need to communicate with the device to determine parameters needed during probe (e.g., size of a multi-touch surface), and if possible, may perfer to communicate with a device on host-initiated disconnect (e.g., to put it into a low-power state). Historically, three functions used driver_lock: - hid_device_probe: blocks to acquire lock - hid_device_remove: blocks to acquire lock - hid_input_report: if locked returns -EBUSY, else acquires lock This patch adds another lock (driver_input_lock) which is used to block input from occurring. The lock behavior is now: - hid_device_probe: blocks to acq. driver_lock, then driver_input_lock - hid_device_remove: blocks to acq. driver_lock, then driver_input_lock - hid_input_report: if driver_input_lock locked returns -EBUSY, else acquires driver_input_lock This patch also adds two helper functions to be called during probe() or remove(): hid_device_io_start() and hid_device_io_stop(). These functions lock and unlock, respectively, driver_input_lock; they also make a note of whether they did so that hid-core knows if a driver has changed the lock state. This patch results in no behavior change for existing devices and drivers. However, during a probe() or remove() function call in a driver, that driver may now selectively call hid_device_io_start() to let input events come through, then optionally call hid_device_io_stop() to stop them. Signed-off-by: Andrew de los Reyes Signed-off-by: Jiri Kosina --- include/linux/hid.h | 46 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 45 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index e14b465b1146..895b85639dec 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -456,7 +456,8 @@ struct hid_device { /* device report descriptor */ unsigned country; /* HID country */ struct hid_report_enum report_enum[HID_REPORT_TYPES]; - struct semaphore driver_lock; /* protects the current driver */ + struct semaphore driver_lock; /* protects the current driver, except during input */ + struct semaphore driver_input_lock; /* protects the current driver */ struct device dev; /* device */ struct hid_driver *driver; struct hid_ll_driver *ll_driver; @@ -477,6 +478,7 @@ struct hid_device { /* device report descriptor */ unsigned int status; /* see STAT flags above */ unsigned claimed; /* Claimed by hidinput, hiddev? */ unsigned quirks; /* Various quirks the device can pull on us */ + bool io_started; /* Protected by driver_lock. If IO has started */ struct list_head inputs; /* The list of inputs */ void *hiddev; /* The hiddev structure */ @@ -599,6 +601,10 @@ struct hid_usage_id { * @resume: invoked on resume if device was not reset (NULL means nop) * @reset_resume: invoked on resume if device was reset (NULL means nop) * + * probe should return -errno on error, or 0 on success. During probe, + * input will not be passed to raw_event unless hid_device_io_start is + * called. + * * raw_event and event should return 0 on no action performed, 1 when no * further processing should be done and negative on error * @@ -737,6 +743,44 @@ const struct hid_device_id *hid_match_id(struct hid_device *hdev, const struct hid_device_id *id); s32 hid_snto32(__u32 value, unsigned n); +/** + * hid_device_io_start - enable HID input during probe, remove + * + * @hid - the device + * + * This should only be called during probe or remove and only be + * called by the thread calling probe or remove. It will allow + * incoming packets to be delivered to the driver. + */ +static inline void hid_device_io_start(struct hid_device *hid) { + if (hid->io_started) { + dev_warn(&hid->dev, "io already started"); + return; + } + hid->io_started = true; + up(&hid->driver_input_lock); +} + +/** + * hid_device_io_stop - disable HID input during probe, remove + * + * @hid - the device + * + * Should only be called after hid_device_io_start. It will prevent + * incoming packets from going to the driver for the duration of + * probe, remove. If called during probe, packets will still go to the + * driver after probe is complete. This function should only be called + * by the thread calling probe or remove. + */ +static inline void hid_device_io_stop(struct hid_device *hid) { + if (!hid->io_started) { + dev_warn(&hid->dev, "io already stopped"); + return; + } + hid->io_started = false; + down(&hid->driver_input_lock); +} + /** * hid_map_usage - map usage input bits * -- cgit v1.2.3 From c8801a8e715d7793e1e7bcd2f6fe132234741753 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 19 Mar 2012 16:35:48 +0000 Subject: regulator: core: Mark all get and enable calls as __must_check It's generally important that devices have power when they expect it so drivers really ought to be checking for errors on the power up paths. Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 7bc732ce6e50..145022a83085 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -141,18 +141,18 @@ void regulator_put(struct regulator *regulator); void devm_regulator_put(struct regulator *regulator); /* regulator output control and status */ -int regulator_enable(struct regulator *regulator); +int __must_check regulator_enable(struct regulator *regulator); int regulator_disable(struct regulator *regulator); int regulator_force_disable(struct regulator *regulator); int regulator_is_enabled(struct regulator *regulator); int regulator_disable_deferred(struct regulator *regulator, int ms); -int regulator_bulk_get(struct device *dev, int num_consumers, - struct regulator_bulk_data *consumers); -int devm_regulator_bulk_get(struct device *dev, int num_consumers, - struct regulator_bulk_data *consumers); -int regulator_bulk_enable(int num_consumers, - struct regulator_bulk_data *consumers); +int __must_check regulator_bulk_get(struct device *dev, int num_consumers, + struct regulator_bulk_data *consumers); +int __must_check devm_regulator_bulk_get(struct device *dev, int num_consumers, + struct regulator_bulk_data *consumers); +int __must_check regulator_bulk_enable(int num_consumers, + struct regulator_bulk_data *consumers); int regulator_bulk_disable(int num_consumers, struct regulator_bulk_data *consumers); int regulator_bulk_force_disable(int num_consumers, -- cgit v1.2.3 From f19b00da8ed37db4e3891fe534fcf3a605a0e562 Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Mon, 18 Feb 2013 06:50:39 +0000 Subject: regulator: core: support shared enable GPIO concept A Regulator can be enabled by external GPIO pin. This is configurable in the regulator_config. At this moment, the GPIO can be owned by only one regulator device. In some devices, multiple regulators are enabled by shared one GPIO pin. This patch extends this limitation, enabling shared enable GPIO of regulators. New list for enable GPIO: 'regulator_ena_gpio_list' This manages enable GPIO list. New structure for supporting shared enable GPIO: 'regulator_enable_gpio' The enable count is used for balancing GPIO control count. This count is incremented when GPIO is enabled. On the other hand, it's decremented when GPIO is disabled. Reference count: 'request_count' The reference count, 'request_count' is incremented/decremented on requesting/freeing the GPIO. This count makes sure only free the GPIO when it has no users. How it works If the GPIO is already used, skip requesting new GPIO usage. The GPIO is new one, request GPIO function and add it to the list of enable GPIO. This list is used for balancing enable GPIO count and pin control. Updating a GPIO and invert code moved 'ena_gpio' and 'ena_gpio_invert' of the regulator_config were moved to new function, regulator_ena_gpio_request(). Use regulator_enable_pin structure rather than regulator_dev. Signed-off-by: Milo(Woogyom) Kim Reviewed-by: Axel Lin Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 23070fd83872..a467d11dd67d 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -22,6 +22,7 @@ struct regmap; struct regulator_dev; struct regulator_init_data; +struct regulator_enable_gpio; enum regulator_status { REGULATOR_STATUS_OFF, @@ -300,6 +301,7 @@ struct regulator_dev { struct dentry *debugfs; + struct regulator_enable_gpio *ena_pin; int ena_gpio; unsigned int ena_gpio_invert:1; unsigned int ena_gpio_state:1; -- cgit v1.2.3 From 7b74d149247c8972da1cec3e4c70b67049aaeb69 Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Mon, 18 Feb 2013 06:50:55 +0000 Subject: regulator: core: use regulator_ena_pin member The regulator_dev has regulator_enable_gpio structure. 'ena_gpio' and 'ena_gpio_invert' were moved to in regulator_enable_gpio. regulator_dev ---> regulator_enable_gpio .ena_gpio .gpio .ena_gpio_invert .ena_gpio_invert Pointer, 'ena_pin' is used for checking valid enable GPIO pin. Signed-off-by: Milo(Woogyom) Kim Reviewed-by: Axel Lin Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index a467d11dd67d..7b7aeec04f86 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -302,8 +302,6 @@ struct regulator_dev { struct dentry *debugfs; struct regulator_enable_gpio *ena_pin; - int ena_gpio; - unsigned int ena_gpio_invert:1; unsigned int ena_gpio_state:1; }; -- cgit v1.2.3 From 07fe6e00f6cca6fef85a14a1dc3ed4f2e35d3f0b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 21 Jan 2013 15:03:44 -0500 Subject: get rid of duplicate logics in __SC_....[1-6] definitions All those guys have the same form - "take a list of type/name pairs, apply some macro to each of them". Abstract that part away, convert all __SC_FOO##x(__VA_ARGS__) to __MAP(x,__SC_FOO,__VA_ARGS__). Signed-off-by: Al Viro --- include/linux/compat.h | 18 ++++------- include/linux/syscalls.h | 82 +++++++++++++++++++----------------------------- 2 files changed, 38 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 76a87fb57ac2..8c1dfc8d830d 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -27,12 +27,6 @@ #define __SC_DELOUSE(t,v) ((t)(unsigned long)(v)) #endif -#define __SC_CCAST1(t1, a1) __SC_DELOUSE(t1,a1) -#define __SC_CCAST2(t2, a2, ...) __SC_DELOUSE(t2,a2), __SC_CCAST1(__VA_ARGS__) -#define __SC_CCAST3(t3, a3, ...) __SC_DELOUSE(t3,a3), __SC_CCAST2(__VA_ARGS__) -#define __SC_CCAST4(t4, a4, ...) __SC_DELOUSE(t4,a4), __SC_CCAST3(__VA_ARGS__) -#define __SC_CCAST5(t5, a5, ...) __SC_DELOUSE(t5,a5), __SC_CCAST4(__VA_ARGS__) -#define __SC_CCAST6(t6, a6, ...) __SC_DELOUSE(t6,a6), __SC_CCAST5(__VA_ARGS__) #define COMPAT_SYSCALL_DEFINE1(name, ...) \ COMPAT_SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE2(name, ...) \ @@ -49,19 +43,19 @@ #ifdef CONFIG_HAVE_SYSCALL_WRAPPERS #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ - asmlinkage long compat_sys##name(__SC_DECL##x(__VA_ARGS__)); \ - static inline long C_SYSC##name(__SC_DECL##x(__VA_ARGS__)); \ - asmlinkage long compat_SyS##name(__SC_LONG##x(__VA_ARGS__)) \ + asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ + static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ + asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))\ { \ - return (long) C_SYSC##name(__SC_CCAST##x(__VA_ARGS__)); \ + return C_SYSC##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \ } \ SYSCALL_ALIAS(compat_sys##name, compat_SyS##name); \ - static inline long C_SYSC##name(__SC_DECL##x(__VA_ARGS__)) + static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #else /* CONFIG_HAVE_SYSCALL_WRAPPERS */ #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ - asmlinkage long compat_sys##name(__SC_DECL##x(__VA_ARGS__)) + asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* CONFIG_HAVE_SYSCALL_WRAPPERS */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 313a8e0a6553..f9411f0c1c80 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -78,49 +78,31 @@ struct sigaltstack; #include #include -#define __SC_DECL1(t1, a1) t1 a1 -#define __SC_DECL2(t2, a2, ...) t2 a2, __SC_DECL1(__VA_ARGS__) -#define __SC_DECL3(t3, a3, ...) t3 a3, __SC_DECL2(__VA_ARGS__) -#define __SC_DECL4(t4, a4, ...) t4 a4, __SC_DECL3(__VA_ARGS__) -#define __SC_DECL5(t5, a5, ...) t5 a5, __SC_DECL4(__VA_ARGS__) -#define __SC_DECL6(t6, a6, ...) t6 a6, __SC_DECL5(__VA_ARGS__) - -#define __SC_LONG1(t1, a1) long a1 -#define __SC_LONG2(t2, a2, ...) long a2, __SC_LONG1(__VA_ARGS__) -#define __SC_LONG3(t3, a3, ...) long a3, __SC_LONG2(__VA_ARGS__) -#define __SC_LONG4(t4, a4, ...) long a4, __SC_LONG3(__VA_ARGS__) -#define __SC_LONG5(t5, a5, ...) long a5, __SC_LONG4(__VA_ARGS__) -#define __SC_LONG6(t6, a6, ...) long a6, __SC_LONG5(__VA_ARGS__) - -#define __SC_CAST1(t1, a1) (t1) a1 -#define __SC_CAST2(t2, a2, ...) (t2) a2, __SC_CAST1(__VA_ARGS__) -#define __SC_CAST3(t3, a3, ...) (t3) a3, __SC_CAST2(__VA_ARGS__) -#define __SC_CAST4(t4, a4, ...) (t4) a4, __SC_CAST3(__VA_ARGS__) -#define __SC_CAST5(t5, a5, ...) (t5) a5, __SC_CAST4(__VA_ARGS__) -#define __SC_CAST6(t6, a6, ...) (t6) a6, __SC_CAST5(__VA_ARGS__) - -#define __SC_TEST(type) BUILD_BUG_ON(sizeof(type) > sizeof(long)) -#define __SC_TEST1(t1, a1) __SC_TEST(t1) -#define __SC_TEST2(t2, a2, ...) __SC_TEST(t2); __SC_TEST1(__VA_ARGS__) -#define __SC_TEST3(t3, a3, ...) __SC_TEST(t3); __SC_TEST2(__VA_ARGS__) -#define __SC_TEST4(t4, a4, ...) __SC_TEST(t4); __SC_TEST3(__VA_ARGS__) -#define __SC_TEST5(t5, a5, ...) __SC_TEST(t5); __SC_TEST4(__VA_ARGS__) -#define __SC_TEST6(t6, a6, ...) __SC_TEST(t6); __SC_TEST5(__VA_ARGS__) +/* + * __MAP - apply a macro to syscall arguments + * __MAP(n, m, t1, a1, t2, a2, ..., tn, an) will expand to + * m(t1, a1), m(t2, a2), ..., m(tn, an) + * The first argument must be equal to the amount of type/name + * pairs given. Note that this list of pairs (i.e. the arguments + * of __MAP starting at the third one) is in the same format as + * for SYSCALL_DEFINE/COMPAT_SYSCALL_DEFINE + */ +#define __MAP1(m,t,a) m(t,a) +#define __MAP2(m,t,a,...) m(t,a), __MAP1(m,__VA_ARGS__) +#define __MAP3(m,t,a,...) m(t,a), __MAP2(m,__VA_ARGS__) +#define __MAP4(m,t,a,...) m(t,a), __MAP3(m,__VA_ARGS__) +#define __MAP5(m,t,a,...) m(t,a), __MAP4(m,__VA_ARGS__) +#define __MAP6(m,t,a,...) m(t,a), __MAP5(m,__VA_ARGS__) +#define __MAP(n,...) __MAP##n(__VA_ARGS__) + +#define __SC_DECL(t, a) t a +#define __SC_LONG(t, a) long a +#define __SC_CAST(t, a) (t) a +#define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(sizeof(type) > sizeof(long)) #ifdef CONFIG_FTRACE_SYSCALLS -#define __SC_STR_ADECL1(t, a) #a -#define __SC_STR_ADECL2(t, a, ...) #a, __SC_STR_ADECL1(__VA_ARGS__) -#define __SC_STR_ADECL3(t, a, ...) #a, __SC_STR_ADECL2(__VA_ARGS__) -#define __SC_STR_ADECL4(t, a, ...) #a, __SC_STR_ADECL3(__VA_ARGS__) -#define __SC_STR_ADECL5(t, a, ...) #a, __SC_STR_ADECL4(__VA_ARGS__) -#define __SC_STR_ADECL6(t, a, ...) #a, __SC_STR_ADECL5(__VA_ARGS__) - -#define __SC_STR_TDECL1(t, a) #t -#define __SC_STR_TDECL2(t, a, ...) #t, __SC_STR_TDECL1(__VA_ARGS__) -#define __SC_STR_TDECL3(t, a, ...) #t, __SC_STR_TDECL2(__VA_ARGS__) -#define __SC_STR_TDECL4(t, a, ...) #t, __SC_STR_TDECL3(__VA_ARGS__) -#define __SC_STR_TDECL5(t, a, ...) #t, __SC_STR_TDECL4(__VA_ARGS__) -#define __SC_STR_TDECL6(t, a, ...) #t, __SC_STR_TDECL5(__VA_ARGS__) +#define __SC_STR_ADECL(t, a) #a +#define __SC_STR_TDECL(t, a) #t extern struct ftrace_event_class event_class_syscall_enter; extern struct ftrace_event_class event_class_syscall_exit; @@ -217,10 +199,10 @@ extern struct trace_event_functions exit_syscall_print_funcs; #ifdef CONFIG_FTRACE_SYSCALLS #define SYSCALL_DEFINEx(x, sname, ...) \ static const char *types_##sname[] = { \ - __SC_STR_TDECL##x(__VA_ARGS__) \ + __MAP(x,__SC_STR_TDECL,__VA_ARGS__) \ }; \ static const char *args_##sname[] = { \ - __SC_STR_ADECL##x(__VA_ARGS__) \ + __MAP(x,__SC_STR_ADECL,__VA_ARGS__) \ }; \ SYSCALL_METADATA(sname, x); \ __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) @@ -234,21 +216,21 @@ extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_DEFINE(name) static inline long SYSC_##name #define __SYSCALL_DEFINEx(x, name, ...) \ - asmlinkage long sys##name(__SC_DECL##x(__VA_ARGS__)); \ - static inline long SYSC##name(__SC_DECL##x(__VA_ARGS__)); \ - asmlinkage long SyS##name(__SC_LONG##x(__VA_ARGS__)) \ + asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ - __SC_TEST##x(__VA_ARGS__); \ - return (long) SYSC##name(__SC_CAST##x(__VA_ARGS__)); \ + __MAP(x,__SC_TEST,__VA_ARGS__); \ + return SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ } \ SYSCALL_ALIAS(sys##name, SyS##name); \ - static inline long SYSC##name(__SC_DECL##x(__VA_ARGS__)) + static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #else /* CONFIG_HAVE_SYSCALL_WRAPPERS */ #define SYSCALL_DEFINE(name) asmlinkage long sys_##name #define __SYSCALL_DEFINEx(x, name, ...) \ - asmlinkage long sys##name(__SC_DECL##x(__VA_ARGS__)) + asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* CONFIG_HAVE_SYSCALL_WRAPPERS */ -- cgit v1.2.3 From 4a0fd5bf0fd0795af8f1be3b261f5cf146a4cb9b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 21 Jan 2013 15:16:58 -0500 Subject: teach SYSCALL_DEFINE how to deal with long long/unsigned long long ... and convert a bunch of SYSCALL_DEFINE ones to SYSCALL_DEFINE, killing the boilerplate crap around them. Signed-off-by: Al Viro --- include/linux/syscalls.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f9411f0c1c80..3e07b92efbf6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -96,9 +96,10 @@ struct sigaltstack; #define __MAP(n,...) __MAP##n(__VA_ARGS__) #define __SC_DECL(t, a) t a -#define __SC_LONG(t, a) long a +#define __TYPE_IS_LL(t) (__same_type((t)0, 0LL) || __same_type((t)0, 0ULL)) +#define __SC_LONG(t, a) __typeof(__builtin_choose_expr(__TYPE_IS_LL(t), 0LL, 0L)) a #define __SC_CAST(t, a) (t) a -#define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(sizeof(type) > sizeof(long)) +#define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(!__TYPE_IS_LL(t) && sizeof(t) > sizeof(long)) #ifdef CONFIG_FTRACE_SYSCALLS #define __SC_STR_ADECL(t, a) #a -- cgit v1.2.3 From e1b5bb6d1236d4ad2084c53aa83dde7cdf6f8eea Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 21 Jan 2013 17:16:07 -0500 Subject: consolidate cond_syscall and SYSCALL_ALIAS declarations take them to asm/linkage.h, with default in linux/linkage.h Signed-off-by: Al Viro --- include/linux/linkage.h | 21 +++++++++++++++++++++ include/linux/syscalls.h | 14 -------------- 2 files changed, 21 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 807f1e533226..829d66c67fc2 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -2,6 +2,7 @@ #define _LINUX_LINKAGE_H #include +#include #include #ifdef __cplusplus @@ -14,6 +15,26 @@ #define asmlinkage CPP_ASMLINKAGE #endif +#ifndef SYMBOL_NAME +#ifdef CONFIG_SYMBOL_PREFIX +#define SYMBOL_NAME(x) CONFIG_SYMBOL_PREFIX ## x +#else +#define SYMBOL_NAME(x) x +#endif +#endif +#define __SYMBOL_NAME(x) __stringify(SYMBOL_NAME(x)) + +#ifndef cond_syscall +#define cond_syscall(x) asm(".weak\t" __SYMBOL_NAME(x) \ + "\n\t.set\t" __SYMBOL_NAME(x) "," __SYMBOL_NAME(sys_ni_syscall)); +#endif + +#ifndef SYSCALL_ALIAS +#define SYSCALL_ALIAS(alias, name) \ + asm ("\t.globl " __SYMBOL_NAME(alias) \ + "\n\t.set\t" __SYMBOL_NAME(alias) "," __SYMBOL_NAME(name)) +#endif + #define __page_aligned_data __section(.data..page_aligned) __aligned(PAGE_SIZE) #define __page_aligned_bss __section(.bss..page_aligned) __aligned(PAGE_SIZE) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3e07b92efbf6..87584373305d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -183,20 +183,6 @@ extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_DEFINE5(name, ...) SYSCALL_DEFINEx(5, _##name, __VA_ARGS__) #define SYSCALL_DEFINE6(name, ...) SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) -#ifdef CONFIG_PPC64 -#define SYSCALL_ALIAS(alias, name) \ - asm ("\t.globl " #alias "\n\t.set " #alias ", " #name "\n" \ - "\t.globl ." #alias "\n\t.set ." #alias ", ." #name) -#else -#if defined(CONFIG_ALPHA) || defined(CONFIG_MIPS) -#define SYSCALL_ALIAS(alias, name) \ - asm ( #alias " = " #name "\n\t.globl " #alias) -#else -#define SYSCALL_ALIAS(alias, name) \ - asm ("\t.globl " #alias "\n\t.set " #alias ", " #name) -#endif -#endif - #ifdef CONFIG_FTRACE_SYSCALLS #define SYSCALL_DEFINEx(x, sname, ...) \ static const char *types_##sname[] = { \ -- cgit v1.2.3 From 22d1a35da0e247a006c286842a1846acb4ffed4f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 21 Jan 2013 17:18:07 -0500 Subject: make HAVE_SYSCALL_WRAPPERS unconditional Signed-off-by: Al Viro --- include/linux/compat.h | 9 --------- include/linux/syscalls.h | 10 ---------- 2 files changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 8c1dfc8d830d..110132527e4c 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -40,8 +40,6 @@ #define COMPAT_SYSCALL_DEFINE6(name, ...) \ COMPAT_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS - #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ @@ -52,13 +50,6 @@ SYSCALL_ALIAS(compat_sys##name, compat_SyS##name); \ static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) -#else /* CONFIG_HAVE_SYSCALL_WRAPPERS */ - -#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ - asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) - -#endif /* CONFIG_HAVE_SYSCALL_WRAPPERS */ - #ifndef compat_user_stack_pointer #define compat_user_stack_pointer() current_user_stack_pointer() #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 87584373305d..3b6fc13cb46a 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -198,8 +198,6 @@ extern struct trace_event_functions exit_syscall_print_funcs; __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) #endif -#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS - #define SYSCALL_DEFINE(name) static inline long SYSC_##name #define __SYSCALL_DEFINEx(x, name, ...) \ @@ -213,14 +211,6 @@ extern struct trace_event_functions exit_syscall_print_funcs; SYSCALL_ALIAS(sys##name, SyS##name); \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) -#else /* CONFIG_HAVE_SYSCALL_WRAPPERS */ - -#define SYSCALL_DEFINE(name) asmlinkage long sys_##name -#define __SYSCALL_DEFINEx(x, name, ...) \ - asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) - -#endif /* CONFIG_HAVE_SYSCALL_WRAPPERS */ - asmlinkage long sys_time(time_t __user *tloc); asmlinkage long sys_stime(time_t __user *tptr); asmlinkage long sys_gettimeofday(struct timeval __user *tv, -- cgit v1.2.3 From 2cf0966683430b6468f36ca20515a33ca7f2403c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 21 Jan 2013 15:25:54 -0500 Subject: make SYSCALL_DEFINE-generated wrappers do asmlinkage_protect ... and switch i386 to HAVE_SYSCALL_WRAPPERS, killing open-coded uses of asmlinkage_protect() in a bunch of syscalls. Signed-off-by: Al Viro --- include/linux/syscalls.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3b6fc13cb46a..9660a8bdcbbe 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -99,6 +99,7 @@ struct sigaltstack; #define __TYPE_IS_LL(t) (__same_type((t)0, 0LL) || __same_type((t)0, 0ULL)) #define __SC_LONG(t, a) __typeof(__builtin_choose_expr(__TYPE_IS_LL(t), 0LL, 0L)) a #define __SC_CAST(t, a) (t) a +#define __SC_ARGS(t, a) a #define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(!__TYPE_IS_LL(t) && sizeof(t) > sizeof(long)) #ifdef CONFIG_FTRACE_SYSCALLS @@ -200,13 +201,16 @@ extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_DEFINE(name) static inline long SYSC_##name +#define __PROTECT(...) asmlinkage_protect(__VA_ARGS__) #define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ + long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ __MAP(x,__SC_TEST,__VA_ARGS__); \ - return SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ + return ret; \ } \ SYSCALL_ALIAS(sys##name, SyS##name); \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) -- cgit v1.2.3 From 19f4fc3aee180000fe45952691bbe69dde1d9e95 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 24 Feb 2013 02:17:03 -0500 Subject: convert sendfile{,64} to COMPAT_SYSCALL_DEFINE Signed-off-by: Al Viro --- include/linux/compat.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 110132527e4c..ad299afcd488 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -670,6 +670,8 @@ asmlinkage ssize_t compat_sys_process_vm_writev(compat_pid_t pid, asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, compat_size_t count); +asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, + compat_loff_t __user *offset, compat_size_t count); asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, compat_stack_t __user *uoss_ptr); -- cgit v1.2.3 From 35280bd4a3fa841897e2638437607fdec6c34f31 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 24 Feb 2013 14:52:17 -0500 Subject: switch epoll_pwait to COMPAT_SYSCALL_DEFINE Signed-off-by: Al Viro --- include/linux/compat.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index ad299afcd488..cdec8f2e9e21 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -432,10 +432,9 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, /* * epoll (fs/eventpoll.c) compat bits follow ... */ -struct epoll_event; -#define compat_epoll_event epoll_event +struct epoll_event; /* fortunately, this one is fixed-layout */ asmlinkage long compat_sys_epoll_pwait(int epfd, - struct compat_epoll_event __user *events, + struct epoll_event __user *events, int maxevents, int timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); -- cgit v1.2.3 From d5dc77bfeeab0b03a32e3db5e31e2f64605634ab Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 25 Feb 2013 18:42:04 -0500 Subject: consolidate compat lookup_dcookie() Signed-off-by: Al Viro --- include/linux/compat.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index cdec8f2e9e21..482c9e65b5bf 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -429,6 +429,7 @@ extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request, asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, compat_long_t addr, compat_long_t data); +asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, size_t); /* * epoll (fs/eventpoll.c) compat bits follow ... */ -- cgit v1.2.3 From 56e41d3c5aa84d679eebdb3cb8a70b03c5fbd6c3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 21 Jan 2013 23:15:25 -0500 Subject: merge compat sys_ipc instances Signed-off-by: Al Viro --- include/linux/compat.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 482c9e65b5bf..79a4781ac502 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -318,6 +318,7 @@ long compat_sys_msgrcv(int first, int second, int msgtyp, int third, int version, void __user *uptr); long compat_sys_shmat(int first, int second, compat_uptr_t third, int version, void __user *uptr); +asmlinkage long compat_sys_ipc(u32, int, int, u32, compat_uptr_t, u32); #else long compat_sys_semctl(int semid, int semnum, int cmd, int arg); long compat_sys_msgsnd(int msqid, struct compat_msgbuf __user *msgp, -- cgit v1.2.3 From 0e65a81b105a3f646793d46740ad90fa5c067986 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 3 Feb 2013 14:36:44 -0500 Subject: get rid of compat_sys_semctl() and friends in case of ARCH_WANT_OLD_COMPAT_IPC Signed-off-by: Al Viro --- include/linux/compat.h | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 79a4781ac502..2bfe67329dc4 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -311,22 +311,13 @@ asmlinkage long compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, compat_size_t __user *len_ptr); -#ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC -long compat_sys_semctl(int first, int second, int third, void __user *uptr); -long compat_sys_msgsnd(int first, int second, int third, void __user *uptr); -long compat_sys_msgrcv(int first, int second, int msgtyp, int third, - int version, void __user *uptr); -long compat_sys_shmat(int first, int second, compat_uptr_t third, int version, - void __user *uptr); asmlinkage long compat_sys_ipc(u32, int, int, u32, compat_uptr_t, u32); -#else -long compat_sys_semctl(int semid, int semnum, int cmd, int arg); -long compat_sys_msgsnd(int msqid, struct compat_msgbuf __user *msgp, +asmlinkage long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg); +asmlinkage long compat_sys_semctl(int semid, int semnum, int cmd, int arg); +asmlinkage long compat_sys_msgsnd(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, int msgflg); -long compat_sys_msgrcv(int msqid, struct compat_msgbuf __user *msgp, +asmlinkage long compat_sys_msgrcv(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, long msgtyp, int msgflg); -long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg); -#endif long compat_sys_msgctl(int first, int second, void __user *uptr); long compat_sys_shmctl(int first, int second, void __user *uptr); long compat_sys_semtimedop(int semid, struct sembuf __user *tsems, -- cgit v1.2.3 From 4b377bab29e6a241db42f27541e7fb63713ee178 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 4 Mar 2013 10:47:59 -0500 Subject: make do_mremap() static The extern in sys_sparc_64.c was a rudiment of time when do_mremap() used to exist in MMU case (it doesn't anymore). As for !MMU one, nothing uses it outside of mm/nommu.c... Signed-off-by: Al Viro --- include/linux/mm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7acc9dc73c9f..f4c8aa990442 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1079,9 +1079,6 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, bool need_rmap_locks); -extern unsigned long do_mremap(unsigned long addr, - unsigned long old_len, unsigned long new_len, - unsigned long flags, unsigned long new_addr); extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, int dirty_accountable, int prot_numa); -- cgit v1.2.3 From 45d9550a0e7e9230606ca3c4c6f4dc6297848b2f Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 19 Feb 2013 12:17:01 -0800 Subject: workqueue: allow more off-queue flag space When a work item is off-queue, its work->data contains WORK_STRUCT_* and WORK_OFFQ_* flags. As WORK_OFFQ_* flags are used only while a work item is off-queue, it can occupy bits of work->data which aren't used while off-queue. WORK_OFFQ_* currently only use bits used by on-queue CWQ pointer. As color bits aren't used while off-queue, there's no reason to not use them. Lower WORK_OFFQ_FLAG_BASE from WORK_STRUCT_FLAG_BITS to WORK_STRUCT_COLOR_SHIFT thus giving 4 more bits to off-queue flag space which is also used to record worker_pool ID while off-queue. This doesn't introduce any visible behavior difference. tj: Rewrote the description. Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 8afab27cdbc2..5bd030f630a9 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -68,7 +68,7 @@ enum { WORK_STRUCT_COLOR_BITS, /* data contains off-queue information when !WORK_STRUCT_PWQ */ - WORK_OFFQ_FLAG_BASE = WORK_STRUCT_FLAG_BITS, + WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, WORK_OFFQ_CANCELING = (1 << WORK_OFFQ_FLAG_BASE), -- cgit v1.2.3 From 65dff759d2948cf18e2029fc5c0c595b8b7da3a5 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 1 Mar 2013 15:01:56 +0800 Subject: cgroup: fix cgroup_path() vs rename() race rename() will change dentry->d_name. The result of this race can be worse than seeing partially rewritten name, but we might access a stale pointer because rename() will re-allocate memory to hold a longer name. As accessing dentry->name must be protected by dentry->d_lock or parent inode's i_mutex, while on the other hand cgroup-path() can be called with some irq-safe spinlocks held, we can't generate cgroup path using dentry->d_name. Alternatively we make a copy of dentry->d_name and save it in cgrp->name when a cgroup is created, and update cgrp->name at rename(). v5: use flexible array instead of zero-size array. v4: - allocate root_cgroup_name and all root_cgroup->name points to it. - add cgroup_name() wrapper. v3: use kfree_rcu() instead of synchronize_rcu() in user-visible path. v2: make cgrp->name RCU safe. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 900af5964f55..75c6ec1ba1ba 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -150,6 +150,11 @@ enum { CGRP_CPUSET_CLONE_CHILDREN, }; +struct cgroup_name { + struct rcu_head rcu_head; + char name[]; +}; + struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ @@ -172,6 +177,19 @@ struct cgroup { struct cgroup *parent; /* my parent */ struct dentry *dentry; /* cgroup fs entry, RCU protected */ + /* + * This is a copy of dentry->d_name, and it's needed because + * we can't use dentry->d_name in cgroup_path(). + * + * You must acquire rcu_read_lock() to access cgrp->name, and + * the only place that can change it is rename(), which is + * protected by parent dir's i_mutex. + * + * Normally you should use cgroup_name() wrapper rather than + * access it directly. + */ + struct cgroup_name __rcu *name; + /* Private pointers for each registered subsystem */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; @@ -404,6 +422,12 @@ struct cgroup_scanner { void *data; }; +/* Caller should hold rcu_read_lock() */ +static inline const char *cgroup_name(const struct cgroup *cgrp) +{ + return rcu_dereference(cgrp->name)->name; +} + int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); -- cgit v1.2.3 From 462fce46065ec4b200c08619c047b9e5a8fd154a Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 27 Feb 2013 19:41:56 +0900 Subject: KVM: set_memory_region: Drop user_alloc from prepare/commit_memory_region() X86 does not use this any more. The remaining user, s390's !user_alloc check, can be simply removed since KVM_SET_MEMORY_REGION ioctl is no longer supported. Note: fixed powerpc's indentations with spaces to suppress checkpatch errors. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index cad77fe09d77..b4757a1cc4c4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -464,12 +464,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages); int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_memory_slot old, - struct kvm_userspace_memory_region *mem, - bool user_alloc); + struct kvm_userspace_memory_region *mem); void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old, - bool user_alloc); + struct kvm_memory_slot old); bool kvm_largepages_enabled(void); void kvm_disable_largepages(void); /* flush all memory translations */ -- cgit v1.2.3 From 47ae31e257c548abdb199e0d26723139a9a967ba Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 27 Feb 2013 19:43:00 +0900 Subject: KVM: set_memory_region: Drop user_alloc from set_memory_region() Except ia64's stale code, KVM_SET_MEMORY_REGION support, this is only used for sanity checks in __kvm_set_memory_region() which can easily be changed to use slot id instead. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b4757a1cc4c4..84a994c7a5c5 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -453,11 +453,9 @@ id_to_memslot(struct kvm_memslots *slots, int id) } int kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - bool user_alloc); + struct kvm_userspace_memory_region *mem); int __kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, - bool user_alloc); + struct kvm_userspace_memory_region *mem); void kvm_arch_free_memslot(struct kvm_memory_slot *free, struct kvm_memory_slot *dont); int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages); @@ -553,9 +551,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log); int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, - struct - kvm_userspace_memory_region *mem, - bool user_alloc); + struct kvm_userspace_memory_region *mem); int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level); long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); -- cgit v1.2.3 From 74d0727cb7aaaea48a6353209093be26abc8d160 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 27 Feb 2013 19:43:44 +0900 Subject: KVM: set_memory_region: Make kvm_mr_change available to arch code This will be used for cleaning up prepare/commit_memory_region() later. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 84a994c7a5c5..8eaf61f7b02d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -452,6 +452,24 @@ id_to_memslot(struct kvm_memslots *slots, int id) return slot; } +/* + * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: + * - create a new memory slot + * - delete an existing memory slot + * - modify an existing memory slot + * -- move it in the guest physical memory space + * -- just change its flags + * + * Since flags can be changed by some of these operations, the following + * differentiation is the best we can do for __kvm_set_memory_region(): + */ +enum kvm_mr_change { + KVM_MR_CREATE, + KVM_MR_DELETE, + KVM_MR_MOVE, + KVM_MR_FLAGS_ONLY, +}; + int kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem); int __kvm_set_memory_region(struct kvm *kvm, -- cgit v1.2.3 From 7b6195a91d60909a2834ab7181e2b9476e6fe749 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 27 Feb 2013 19:44:34 +0900 Subject: KVM: set_memory_region: Refactor prepare_memory_region() This patch drops the parameter old, a copy of the old memory slot, and adds a new parameter named change to know the change being requested. This not only cleans up the code but also removes extra copying of the memory slot structure. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8eaf61f7b02d..caa72cf7e8e7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -479,8 +479,8 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free, int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages); int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_memory_slot old, - struct kvm_userspace_memory_region *mem); + struct kvm_userspace_memory_region *mem, + enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, struct kvm_memory_slot old); -- cgit v1.2.3 From 8482644aea11e0647867732319ccf35879a9acc2 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 27 Feb 2013 19:45:25 +0900 Subject: KVM: set_memory_region: Refactor commit_memory_region() This patch makes the parameter old a const pointer to the old memory slot and adds a new parameter named change to know the change being requested: the former is for removing extra copying and the latter is for cleaning up the code. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index caa72cf7e8e7..ac584cc53581 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -483,7 +483,8 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot old); + const struct kvm_memory_slot *old, + enum kvm_mr_change change); bool kvm_largepages_enabled(void); void kvm_disable_largepages(void); /* flush all memory translations */ -- cgit v1.2.3 From 51dcdafcb720a9d1fd73b597d0ccf48837abc59f Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Tue, 5 Mar 2013 14:16:00 +0800 Subject: regulator: core: Add enable_is_inverted flag to indicate set enable_mask bits to disable Add enable_is_inverted flag to indicate set enable_mask bits to disable when using regulator_enable_regmap and friends APIs. Signed-off-by: Axel Lin Reviewed-by: Haojian Zhuang Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 7df93f52db08..07ea8f1a127e 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -199,6 +199,8 @@ enum regulator_type { * output when using regulator_set_voltage_sel_regmap * @enable_reg: Register for control when using regmap enable/disable ops * @enable_mask: Mask for control when using regmap enable/disable ops + * @enable_is_inverted: A flag to indicate set enable_mask bits to disable + * when using regulator_enable_regmap and friends APIs. * @bypass_reg: Register for control when using regmap set_bypass * @bypass_mask: Mask for control when using regmap set_bypass * @@ -228,6 +230,7 @@ struct regulator_desc { unsigned int apply_bit; unsigned int enable_reg; unsigned int enable_mask; + bool enable_is_inverted; unsigned int bypass_reg; unsigned int bypass_mask; -- cgit v1.2.3 From 7d8e0bf56a66bab08d2f316dd87e56c08cecb899 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 10:57:03 +0800 Subject: cgroup: avoid accessing modular cgroup subsys structure without locking subsys[i] is set to NULL in cgroup_unload_subsys() at modular unload, and that's protected by cgroup_mutex, and then the memory *subsys[i] resides will be freed. So this is unsafe without any locking: if (!ss || ss->module) ... v2: - add a comment for enum cgroup_subsys_id - simplify the comment in cgroup_exit() Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 75c6ec1ba1ba..5f76829dd75e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -44,14 +44,25 @@ extern void cgroup_unload_subsys(struct cgroup_subsys *ss); extern const struct file_operations proc_cgroup_operations; -/* Define the enumeration of all builtin cgroup subsystems */ +/* + * Define the enumeration of all cgroup subsystems. + * + * We define ids for builtin subsystems and then modular ones. + */ #define SUBSYS(_x) _x ## _subsys_id, -#define IS_SUBSYS_ENABLED(option) IS_ENABLED(option) enum cgroup_subsys_id { +#define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option) +#include +#undef IS_SUBSYS_ENABLED + CGROUP_BUILTIN_SUBSYS_COUNT, + + __CGROUP_SUBSYS_TEMP_PLACEHOLDER = CGROUP_BUILTIN_SUBSYS_COUNT - 1, + +#define IS_SUBSYS_ENABLED(option) IS_MODULE(option) #include +#undef IS_SUBSYS_ENABLED CGROUP_SUBSYS_COUNT, }; -#undef IS_SUBSYS_ENABLED #undef SUBSYS /* Per-subsystem/per-cgroup state maintained by the system. */ -- cgit v1.2.3 From 9259826ccb8165f797e4c2c9d17925b41af5f6ae Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 11:37:50 +0800 Subject: res_counter: remove include of cgroup.h from res_counter.h It's not needed at all. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/res_counter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 5ae8456d9670..a83a849bf1d3 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -13,7 +13,7 @@ * info about what this counter is. */ -#include +#include /* * The core object. the cgroup that wishes to account for some -- cgit v1.2.3 From ff794dea52eaaa09017efea688a1d7f92ab0818e Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 11:37:56 +0800 Subject: cpuset: remove include of cgroup.h from cpuset.h We don't need to include cgroup.h in cpuset.h. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cpuset.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 8c8a60d29407..ccd1de8ad822 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -11,7 +11,6 @@ #include #include #include -#include #include #ifdef CONFIG_CPUSETS -- cgit v1.2.3 From e1fd1f490fa4213bd3060efa823a39d299538f72 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 5 Mar 2013 15:04:55 -0500 Subject: get rid of union semop in sys_semctl(2) arguments just have the bugger take unsigned long and deal with SETVAL case (when we use an int member in the union) explicitly. Signed-off-by: Al Viro --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 9660a8bdcbbe..65c001f7fa0b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -657,7 +657,7 @@ asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf); asmlinkage long sys_semget(key_t key, int nsems, int semflg); asmlinkage long sys_semop(int semid, struct sembuf __user *sops, unsigned nsops); -asmlinkage long sys_semctl(int semid, int semnum, int cmd, union semun arg); +asmlinkage long sys_semctl(int semid, int semnum, int cmd, unsigned long arg); asmlinkage long sys_semtimedop(int semid, struct sembuf __user *sops, unsigned nsops, const struct timespec __user *timeout); -- cgit v1.2.3 From 99e621f796d7f0341a51e8cdf32b81663b10b448 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 5 Mar 2013 15:36:40 -0500 Subject: syscalls.h: slightly reduce the jungles of macros a) teach __MAP(num, m, ) to take empty list (with num being 0, of course) b) fold types__... and args__... declaration and initialization into SYSCALL_METADATA(num, ...), making their use conditional on num != 0. That allows to use the SYSCALL_METADATA instead of its near-duplicate in SYSCALL_DEFINE0. c) make SYSCALL_METADATA expand to nothing in case if CONFIG_FTRACE_SYSCALLS is not defined; that allows to make SYSCALL_DEFINE0 and SYSCALL_DEFINEx definitions independent from CONFIG_FTRACE_SYSCALLS. d) kill SYSCALL_DEFINE - no users left (SYSCALL_DEFINE[0-6] is, of course, still alive and well). Signed-off-by: Al Viro --- include/linux/syscalls.h | 49 +++++++++++++++--------------------------------- 1 file changed, 15 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 65c001f7fa0b..4147d700a293 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -87,6 +87,7 @@ struct sigaltstack; * of __MAP starting at the third one) is in the same format as * for SYSCALL_DEFINE/COMPAT_SYSCALL_DEFINE */ +#define __MAP0(m,...) #define __MAP1(m,t,a) m(t,a) #define __MAP2(m,t,a,...) m(t,a), __MAP1(m,__VA_ARGS__) #define __MAP3(m,t,a,...) m(t,a), __MAP2(m,__VA_ARGS__) @@ -139,7 +140,13 @@ extern struct trace_event_functions exit_syscall_print_funcs; __attribute__((section("_ftrace_events"))) \ *__event_exit_##sname = &event_exit_##sname; -#define SYSCALL_METADATA(sname, nb) \ +#define SYSCALL_METADATA(sname, nb, ...) \ + static const char *types_##sname[] = { \ + __MAP(nb,__SC_STR_TDECL,__VA_ARGS__) \ + }; \ + static const char *args_##sname[] = { \ + __MAP(nb,__SC_STR_ADECL,__VA_ARGS__) \ + }; \ SYSCALL_TRACE_ENTER_EVENT(sname); \ SYSCALL_TRACE_EXIT_EVENT(sname); \ static struct syscall_metadata __used \ @@ -147,8 +154,8 @@ extern struct trace_event_functions exit_syscall_print_funcs; .name = "sys"#sname, \ .syscall_nr = -1, /* Filled in at boot */ \ .nb_args = nb, \ - .types = types_##sname, \ - .args = args_##sname, \ + .types = nb ? types_##sname : NULL, \ + .args = nb ? args_##sname : NULL, \ .enter_event = &event_enter_##sname, \ .exit_event = &event_exit_##sname, \ .enter_fields = LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \ @@ -156,26 +163,13 @@ extern struct trace_event_functions exit_syscall_print_funcs; static struct syscall_metadata __used \ __attribute__((section("__syscalls_metadata"))) \ *__p_syscall_meta_##sname = &__syscall_meta_##sname; +#else +#define SYSCALL_METADATA(sname, nb, ...) +#endif #define SYSCALL_DEFINE0(sname) \ - SYSCALL_TRACE_ENTER_EVENT(_##sname); \ - SYSCALL_TRACE_EXIT_EVENT(_##sname); \ - static struct syscall_metadata __used \ - __syscall_meta__##sname = { \ - .name = "sys_"#sname, \ - .syscall_nr = -1, /* Filled in at boot */ \ - .nb_args = 0, \ - .enter_event = &event_enter__##sname, \ - .exit_event = &event_exit__##sname, \ - .enter_fields = LIST_HEAD_INIT(__syscall_meta__##sname.enter_fields), \ - }; \ - static struct syscall_metadata __used \ - __attribute__((section("__syscalls_metadata"))) \ - *__p_syscall_meta_##sname = &__syscall_meta__##sname; \ + SYSCALL_METADATA(_##sname, 0); \ asmlinkage long sys_##sname(void) -#else -#define SYSCALL_DEFINE0(name) asmlinkage long sys_##name(void) -#endif #define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) #define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__) @@ -184,22 +178,9 @@ extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_DEFINE5(name, ...) SYSCALL_DEFINEx(5, _##name, __VA_ARGS__) #define SYSCALL_DEFINE6(name, ...) SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) -#ifdef CONFIG_FTRACE_SYSCALLS #define SYSCALL_DEFINEx(x, sname, ...) \ - static const char *types_##sname[] = { \ - __MAP(x,__SC_STR_TDECL,__VA_ARGS__) \ - }; \ - static const char *args_##sname[] = { \ - __MAP(x,__SC_STR_ADECL,__VA_ARGS__) \ - }; \ - SYSCALL_METADATA(sname, x); \ + SYSCALL_METADATA(sname, x, __VA_ARGS__) \ __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) -#else -#define SYSCALL_DEFINEx(x, sname, ...) \ - __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) -#endif - -#define SYSCALL_DEFINE(name) static inline long SYSC_##name #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__) #define __SYSCALL_DEFINEx(x, name, ...) \ -- cgit v1.2.3 From a0f155e9646d5f1c263f6f9aae880151100243bb Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 28 Feb 2013 12:33:18 +0100 Subject: KVM: Initialize irqfd from kvm_init(). Currently, eventfd introduces module_init/module_exit functions to initialize/cleanup the irqfd workqueue. This only works, however, if no other module_init/module_exit functions are built into the same module. Let's just move the initialization and cleanup to kvm_init and kvm_exit. This way, it is also clearer where kvm startup may fail. Signed-off-by: Cornelia Huck Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ac584cc53581..d50fe173028b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -424,6 +424,19 @@ void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); int __must_check vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); +#ifdef __KVM_HAVE_IOAPIC +int kvm_irqfd_init(void); +void kvm_irqfd_exit(void); +#else +static inline int kvm_irqfd_init(void) +{ + return 0; +} + +static inline void kvm_irqfd_exit(void) +{ +} +#endif int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, struct module *module); void kvm_exit(void); -- cgit v1.2.3 From 060f0ce6ff975decd1e0ee318c08e228bccbee1e Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 28 Feb 2013 12:33:19 +0100 Subject: KVM: Introduce KVM_VIRTIO_CCW_NOTIFY_BUS. Add a new bus type for virtio-ccw devices on s390. Signed-off-by: Cornelia Huck Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d50fe173028b..9fa13ebc3381 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -149,6 +149,7 @@ struct kvm_io_bus { enum kvm_bus { KVM_MMIO_BUS, KVM_PIO_BUS, + KVM_VIRTIO_CCW_NOTIFY_BUS, KVM_NR_BUSES }; -- cgit v1.2.3 From 82dc3c63c692b1e1d59378ecee948ac88e034aad Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Mar 2013 15:57:22 +0000 Subject: net: introduce NAPI_POLL_WEIGHT Some drivers use a too big NAPI poll weight. This patch adds a NAPI_POLL_WEIGHT default value and issues an error message if a driver attempts to use a bigger weight. Signed-off-by: Eric Dumazet Cc: Eilon Greenstein Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b3d00fa4b314..896eb4985f97 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1475,6 +1475,11 @@ static inline void *netdev_priv(const struct net_device *dev) */ #define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype)) +/* Default NAPI poll() weight + * Device drivers are strongly advised to not use bigger value + */ +#define NAPI_POLL_WEIGHT 64 + /** * netif_napi_add - initialize a napi context * @dev: network device -- cgit v1.2.3 From 1fd9c467b4f7e08beee41f9771396f39265f4c08 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 5 Mar 2013 11:51:55 +0800 Subject: mfd: arizona: Define additional FLL control registers Signed-off-by: Mark Brown --- include/linux/mfd/arizona/registers.h | 40 +++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h index 340355136069..a61ce90ecd3f 100644 --- a/include/linux/mfd/arizona/registers.h +++ b/include/linux/mfd/arizona/registers.h @@ -85,12 +85,14 @@ #define ARIZONA_FLL1_CONTROL_6 0x176 #define ARIZONA_FLL1_LOOP_FILTER_TEST_1 0x177 #define ARIZONA_FLL1_NCO_TEST_0 0x178 +#define ARIZONA_FLL1_CONTROL_7 0x179 #define ARIZONA_FLL1_SYNCHRONISER_1 0x181 #define ARIZONA_FLL1_SYNCHRONISER_2 0x182 #define ARIZONA_FLL1_SYNCHRONISER_3 0x183 #define ARIZONA_FLL1_SYNCHRONISER_4 0x184 #define ARIZONA_FLL1_SYNCHRONISER_5 0x185 #define ARIZONA_FLL1_SYNCHRONISER_6 0x186 +#define ARIZONA_FLL1_SYNCHRONISER_7 0x187 #define ARIZONA_FLL1_SPREAD_SPECTRUM 0x189 #define ARIZONA_FLL1_GPIO_CLOCK 0x18A #define ARIZONA_FLL2_CONTROL_1 0x191 @@ -101,12 +103,14 @@ #define ARIZONA_FLL2_CONTROL_6 0x196 #define ARIZONA_FLL2_LOOP_FILTER_TEST_1 0x197 #define ARIZONA_FLL2_NCO_TEST_0 0x198 +#define ARIZONA_FLL2_CONTROL_7 0x199 #define ARIZONA_FLL2_SYNCHRONISER_1 0x1A1 #define ARIZONA_FLL2_SYNCHRONISER_2 0x1A2 #define ARIZONA_FLL2_SYNCHRONISER_3 0x1A3 #define ARIZONA_FLL2_SYNCHRONISER_4 0x1A4 #define ARIZONA_FLL2_SYNCHRONISER_5 0x1A5 #define ARIZONA_FLL2_SYNCHRONISER_6 0x1A6 +#define ARIZONA_FLL2_SYNCHRONISER_7 0x1A7 #define ARIZONA_FLL2_SPREAD_SPECTRUM 0x1A9 #define ARIZONA_FLL2_GPIO_CLOCK 0x1AA #define ARIZONA_MIC_CHARGE_PUMP_1 0x200 @@ -1677,6 +1681,13 @@ #define ARIZONA_FLL1_FRC_INTEG_VAL_SHIFT 0 /* FLL1_FRC_INTEG_VAL - [11:0] */ #define ARIZONA_FLL1_FRC_INTEG_VAL_WIDTH 12 /* FLL1_FRC_INTEG_VAL - [11:0] */ +/* + * R377 (0x179) - FLL1 Control 7 + */ +#define ARIZONA_FLL1_GAIN_MASK 0x003c /* FLL1_GAIN */ +#define ARIZONA_FLL1_GAIN_SHIFT 2 /* FLL1_GAIN */ +#define ARIZONA_FLL1_GAIN_WIDTH 4 /* FLL1_GAIN */ + /* * R385 (0x181) - FLL1 Synchroniser 1 */ @@ -1723,6 +1734,17 @@ #define ARIZONA_FLL1_CLK_SYNC_SRC_SHIFT 0 /* FLL1_CLK_SYNC_SRC - [3:0] */ #define ARIZONA_FLL1_CLK_SYNC_SRC_WIDTH 4 /* FLL1_CLK_SYNC_SRC - [3:0] */ +/* + * R391 (0x187) - FLL1 Synchroniser 7 + */ +#define ARIZONA_FLL1_SYNC_GAIN_MASK 0x003c /* FLL1_SYNC_GAIN */ +#define ARIZONA_FLL1_SYNC_GAIN_SHIFT 2 /* FLL1_SYNC_GAIN */ +#define ARIZONA_FLL1_SYNC_GAIN_WIDTH 4 /* FLL1_SYNC_GAIN */ +#define ARIZONA_FLL1_SYNC_BW 0x0001 /* FLL1_SYNC_BW */ +#define ARIZONA_FLL1_SYNC_BW_MASK 0x0001 /* FLL1_SYNC_BW */ +#define ARIZONA_FLL1_SYNC_BW_SHIFT 0 /* FLL1_SYNC_BW */ +#define ARIZONA_FLL1_SYNC_BW_WIDTH 1 /* FLL1_SYNC_BW */ + /* * R393 (0x189) - FLL1 Spread Spectrum */ @@ -1815,6 +1837,13 @@ #define ARIZONA_FLL2_FRC_INTEG_VAL_SHIFT 0 /* FLL2_FRC_INTEG_VAL - [11:0] */ #define ARIZONA_FLL2_FRC_INTEG_VAL_WIDTH 12 /* FLL2_FRC_INTEG_VAL - [11:0] */ +/* + * R409 (0x199) - FLL2 Control 7 + */ +#define ARIZONA_FLL2_GAIN_MASK 0x003c /* FLL2_GAIN */ +#define ARIZONA_FLL2_GAIN_SHIFT 2 /* FLL2_GAIN */ +#define ARIZONA_FLL2_GAIN_WIDTH 4 /* FLL2_GAIN */ + /* * R417 (0x1A1) - FLL2 Synchroniser 1 */ @@ -1861,6 +1890,17 @@ #define ARIZONA_FLL2_CLK_SYNC_SRC_SHIFT 0 /* FLL2_CLK_SYNC_SRC - [3:0] */ #define ARIZONA_FLL2_CLK_SYNC_SRC_WIDTH 4 /* FLL2_CLK_SYNC_SRC - [3:0] */ +/* + * R423 (0x1A7) - FLL2 Synchroniser 7 + */ +#define ARIZONA_FLL2_SYNC_GAIN_MASK 0x003c /* FLL2_SYNC_GAIN */ +#define ARIZONA_FLL2_SYNC_GAIN_SHIFT 2 /* FLL2_SYNC_GAIN */ +#define ARIZONA_FLL2_SYNC_GAIN_WIDTH 4 /* FLL2_SYNC_GAIN */ +#define ARIZONA_FLL2_SYNC_BW_MASK 0x0001 /* FLL2_SYNC_BW */ +#define ARIZONA_FLL2_SYNC_BW_MASK 0x0001 /* FLL2_SYNC_BW */ +#define ARIZONA_FLL2_SYNC_BW_SHIFT 0 /* FLL2_SYNC_BW */ +#define ARIZONA_FLL2_SYNC_BW_WIDTH 1 /* FLL2_SYNC_BW */ + /* * R425 (0x1A9) - FLL2 Spread Spectrum */ -- cgit v1.2.3 From 19a37d1cd5465c10d669a296a2ea24b4c985363b Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:05:28 +0800 Subject: sched: Remove some dummy functions No one will call those functions if CONFIG_SCHED_DEBUG=n. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A748.3050206@huawei.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6ddbfb..2715fbb9ea85 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -127,18 +127,6 @@ extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); extern void proc_sched_set_task(struct task_struct *p); extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); -#else -static inline void -proc_sched_show_task(struct task_struct *p, struct seq_file *m) -{ -} -static inline void proc_sched_set_task(struct task_struct *p) -{ -} -static inline void -print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) -{ -} #endif /* -- cgit v1.2.3 From 090b582f27ac7b6714661020033160130e5297bd Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:05:51 +0800 Subject: sched: Remove test_sd_parent() It's unused. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A75F.4070202@huawei.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2715fbb9ea85..e880d7d115ef 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -959,15 +959,6 @@ extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], cpumask_var_t *alloc_sched_domains(unsigned int ndoms); void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); -/* Test a flag in parent sched domain */ -static inline int test_sd_parent(struct sched_domain *sd, int flag) -{ - if (sd->parent && (sd->parent->flags & flag)) - return 1; - - return 0; -} - unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu); unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu); -- cgit v1.2.3 From cc1f4b1f3faed9f2040eff2a75f510b424b3cf18 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:06:09 +0800 Subject: sched: Move SCHED_LOAD_SHIFT macros to kernel/sched/sched.h They are used internally only. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A771.4070104@huawei.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index e880d7d115ef..f8826d04fb12 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -755,31 +755,6 @@ enum cpu_idle_type { CPU_MAX_IDLE_TYPES }; -/* - * Increase resolution of nice-level calculations for 64-bit architectures. - * The extra resolution improves shares distribution and load balancing of - * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup - * hierarchies, especially on larger systems. This is not a user-visible change - * and does not change the user-interface for setting shares/weights. - * - * We increase resolution only if we have enough bits to allow this increased - * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution - * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the - * increased costs. - */ -#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */ -# define SCHED_LOAD_RESOLUTION 10 -# define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION) -# define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION) -#else -# define SCHED_LOAD_RESOLUTION 0 -# define scale_load(w) (w) -# define scale_load_down(w) (w) -#endif - -#define SCHED_LOAD_SHIFT (10 + SCHED_LOAD_RESOLUTION) -#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) - /* * Increase resolution of cpu_power calculations */ -- cgit v1.2.3 From 5e6521eaa1ee581a13b904f35b80c5efeb2baccb Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:06:23 +0800 Subject: sched: Move struct sched_group to kernel/sched/sched.h Move struct sched_group_power and sched_group and related inline functions to kernel/sched/sched.h, as they are used internally only. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A77F.2010705@huawei.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 58 ++------------------------------------------------- 1 file changed, 2 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index f8826d04fb12..0d641304c0ff 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -780,62 +780,6 @@ enum cpu_idle_type { extern int __weak arch_sd_sibiling_asym_packing(void); -struct sched_group_power { - atomic_t ref; - /* - * CPU power of this group, SCHED_LOAD_SCALE being max power for a - * single CPU. - */ - unsigned int power, power_orig; - unsigned long next_update; - /* - * Number of busy cpus in this group. - */ - atomic_t nr_busy_cpus; - - unsigned long cpumask[0]; /* iteration mask */ -}; - -struct sched_group { - struct sched_group *next; /* Must be a circular list */ - atomic_t ref; - - unsigned int group_weight; - struct sched_group_power *sgp; - - /* - * The CPUs this group covers. - * - * NOTE: this field is variable length. (Allocated dynamically - * by attaching extra space to the end of the structure, - * depending on how many CPUs the kernel has booted up with) - */ - unsigned long cpumask[0]; -}; - -static inline struct cpumask *sched_group_cpus(struct sched_group *sg) -{ - return to_cpumask(sg->cpumask); -} - -/* - * cpumask masking which cpus in the group are allowed to iterate up the domain - * tree. - */ -static inline struct cpumask *sched_group_mask(struct sched_group *sg) -{ - return to_cpumask(sg->sgp->cpumask); -} - -/** - * group_first_cpu - Returns the first cpu in the cpumask of a sched_group. - * @group: The group whose first cpu is to be returned. - */ -static inline unsigned int group_first_cpu(struct sched_group *group) -{ - return cpumask_first(sched_group_cpus(group)); -} - struct sched_domain_attr { int relax_domain_level; }; @@ -846,6 +790,8 @@ struct sched_domain_attr { extern int sched_domain_level_max; +struct sched_group; + struct sched_domain { /* These fields must be setup */ struct sched_domain *parent; /* top domain must be null terminated */ -- cgit v1.2.3 From b13095f07f25464de65f5ce5ea94e16813d67488 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:06:38 +0800 Subject: sched: Move wake flags to kernel/sched/sched.h They are used internally only. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A78E.7040609@huawei.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 0d641304c0ff..863b505ac48e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -920,13 +920,6 @@ struct uts_namespace; struct rq; struct sched_domain; -/* - * wake flags - */ -#define WF_SYNC 0x01 /* waker goes to sleep after wakup */ -#define WF_FORK 0x02 /* child wakeup after fork */ -#define WF_MIGRATED 0x04 /* internal use, task got migrated */ - #define ENQUEUE_WAKEUP 1 #define ENQUEUE_HEAD 2 #ifdef CONFIG_SMP -- cgit v1.2.3 From c82ba9fa7588dfd02d4dc99ad1af486304bc424c Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:06:55 +0800 Subject: sched: Move struct sched_class to kernel/sched/sched.h It's used internally only. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A79F.8090502@huawei.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 59 --------------------------------------------------- 1 file changed, 59 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 863b505ac48e..04b834fa14bc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -917,65 +917,6 @@ struct mempolicy; struct pipe_inode_info; struct uts_namespace; -struct rq; -struct sched_domain; - -#define ENQUEUE_WAKEUP 1 -#define ENQUEUE_HEAD 2 -#ifdef CONFIG_SMP -#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */ -#else -#define ENQUEUE_WAKING 0 -#endif - -#define DEQUEUE_SLEEP 1 - -struct sched_class { - const struct sched_class *next; - - void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags); - void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags); - void (*yield_task) (struct rq *rq); - bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt); - - void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags); - - struct task_struct * (*pick_next_task) (struct rq *rq); - void (*put_prev_task) (struct rq *rq, struct task_struct *p); - -#ifdef CONFIG_SMP - int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags); - void (*migrate_task_rq)(struct task_struct *p, int next_cpu); - - void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); - void (*post_schedule) (struct rq *this_rq); - void (*task_waking) (struct task_struct *task); - void (*task_woken) (struct rq *this_rq, struct task_struct *task); - - void (*set_cpus_allowed)(struct task_struct *p, - const struct cpumask *newmask); - - void (*rq_online)(struct rq *rq); - void (*rq_offline)(struct rq *rq); -#endif - - void (*set_curr_task) (struct rq *rq); - void (*task_tick) (struct rq *rq, struct task_struct *p, int queued); - void (*task_fork) (struct task_struct *p); - - void (*switched_from) (struct rq *this_rq, struct task_struct *task); - void (*switched_to) (struct rq *this_rq, struct task_struct *task); - void (*prio_changed) (struct rq *this_rq, struct task_struct *task, - int oldprio); - - unsigned int (*get_rr_interval) (struct rq *rq, - struct task_struct *task); - -#ifdef CONFIG_FAIR_GROUP_SCHED - void (*task_move_group) (struct task_struct *p, int on_rq); -#endif -}; - struct load_weight { unsigned long weight, inv_weight; }; -- cgit v1.2.3 From 15f803c94bd92b17708aad9e74226fd0b2c9130c Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:07:11 +0800 Subject: sched: Make default_scale_freq_power() static As default_scale_{freq,smt}_power() and update_rt_power() are used in kernel/sched/fair.c only, annotate them as static functions. Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A7AF.8010900@huawei.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 04b834fa14bc..eadd113e1eb2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -880,9 +880,6 @@ extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], cpumask_var_t *alloc_sched_domains(unsigned int ndoms); void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); -unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu); -unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu); - bool cpus_share_cache(int this_cpu, int that_cpu); #else /* CONFIG_SMP */ -- cgit v1.2.3 From 25cc7da7e6336d3bb6a5bad3d3fa96fce9a81d5b Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 16:07:33 +0800 Subject: sched: Move group scheduling functions out of include/linux/sched.h - Make sched_group_{set_,}runtime(), sched_group_{set_,}period() and sched_rt_can_attach() static. - Move sched_{create,destroy,online,offline}_group() to kernel/sched/sched.h. - Remove declaration of sched_group_shares(). Signed-off-by: Li Zefan Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/5135A7C5.3000708@huawei.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index eadd113e1eb2..fc039ceccbea 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2512,28 +2512,7 @@ extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #ifdef CONFIG_CGROUP_SCHED - extern struct task_group root_task_group; - -extern struct task_group *sched_create_group(struct task_group *parent); -extern void sched_online_group(struct task_group *tg, - struct task_group *parent); -extern void sched_destroy_group(struct task_group *tg); -extern void sched_offline_group(struct task_group *tg); -extern void sched_move_task(struct task_struct *tsk); -#ifdef CONFIG_FAIR_GROUP_SCHED -extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); -extern unsigned long sched_group_shares(struct task_group *tg); -#endif -#ifdef CONFIG_RT_GROUP_SCHED -extern int sched_group_set_rt_runtime(struct task_group *tg, - long rt_runtime_us); -extern long sched_group_rt_runtime(struct task_group *tg); -extern int sched_group_set_rt_period(struct task_group *tg, - long rt_period_us); -extern long sched_group_rt_period(struct task_group *tg); -extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk); -#endif #endif /* CONFIG_CGROUP_SCHED */ extern int task_can_switch_user(struct user_struct *up, -- cgit v1.2.3 From 877c685607925238e302cd3aa38788dca6c1b226 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 5 Mar 2013 11:38:08 +0800 Subject: perf: Remove include of cgroup.h from perf_event.h Move struct perf_cgroup_info and perf_cgroup to kernel/perf/core.c, and then we can remove include of cgroup.h. Signed-off-by: Li Zefan Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Tejun Heo Link: http://lkml.kernel.org/r/513568A0.6020804@huawei.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 18 +----------------- 1 file changed, 1 insertion(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e47ee462c2f2..8737e1cee8b2 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -21,7 +21,6 @@ */ #ifdef CONFIG_PERF_EVENTS -# include # include # include #endif @@ -299,22 +298,7 @@ struct swevent_hlist { #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 -#ifdef CONFIG_CGROUP_PERF -/* - * perf_cgroup_info keeps track of time_enabled for a cgroup. - * This is a per-cpu dynamically allocated data structure. - */ -struct perf_cgroup_info { - u64 time; - u64 timestamp; -}; - -struct perf_cgroup { - struct cgroup_subsys_state css; - struct perf_cgroup_info *info; /* timing info, one per cpu */ -}; -#endif - +struct perf_cgroup; struct ring_buffer; /** -- cgit v1.2.3 From 9a886586c82aa02cb49f8c85e961595716884545 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 15 Feb 2013 19:25:00 +0100 Subject: wireless: move sequence number arithmetic to ieee80211.h Move the sequence number arithmetic code from mac80211 to ieee80211.h so others can use it. Also rename the functions from _seq to _sn, they operate on the sequence number, not the sequence_control field. Also move macros to convert the sequence control to/from the sequence number value from various drivers. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 7e24fe0cfbcd..a0c550fb65a6 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -113,6 +113,34 @@ #define IEEE80211_CTL_EXT_SSW_FBACK 0x9000 #define IEEE80211_CTL_EXT_SSW_ACK 0xa000 + +#define IEEE80211_SN_MASK ((IEEE80211_SCTL_SEQ) >> 4) +#define IEEE80211_MAX_SN IEEE80211_SN_MASK +#define IEEE80211_SN_MODULO (IEEE80211_MAX_SN + 1) + +static inline int ieee80211_sn_less(u16 sn1, u16 sn2) +{ + return ((sn1 - sn2) & IEEE80211_SN_MASK) > (IEEE80211_SN_MODULO >> 1); +} + +static inline u16 ieee80211_sn_add(u16 sn1, u16 sn2) +{ + return (sn1 + sn2) & IEEE80211_SN_MASK; +} + +static inline u16 ieee80211_sn_inc(u16 sn) +{ + return ieee80211_sn_add(sn, 1); +} + +static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) +{ + return (sn1 - sn2) & IEEE80211_SN_MASK; +} + +#define IEEE80211_SEQ_TO_SN(seq) (((seq) & IEEE80211_SCTL_SEQ) >> 4) +#define IEEE80211_SN_TO_SEQ(ssn) (((ssn) << 4) & IEEE80211_SCTL_SEQ) + /* miscellaneous IEEE 802.11 constants */ #define IEEE80211_MAX_FRAG_THRESHOLD 2352 #define IEEE80211_MAX_RTS_THRESHOLD 2353 -- cgit v1.2.3 From b8a31c9a5afff257cc5dd637cda5fef03e12d67b Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Fri, 22 Feb 2013 17:28:49 +0100 Subject: ieee80211: mark 802.11 related structs as being 2-byte aligned Regardless of what header features they use, or if they align the IP header or not, 802.11 packets from all drivers guarantee a 2-byte alignment (and there's a debug WARN_ON in case they don't). Annotate packet structs with __aligned(2) to allow the compiler to use 16-bit load/store operations on platforms with extremely inefficient unaligned access (e.g. MIPS). This reduces code size and improves performance on affected platforms and causes no binary code change on others. Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a0c550fb65a6..6e352c31fee0 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -213,7 +213,7 @@ struct ieee80211_hdr { u8 addr3[6]; __le16 seq_ctrl; u8 addr4[6]; -} __packed; +} __packed __aligned(2); struct ieee80211_hdr_3addr { __le16 frame_control; @@ -222,7 +222,7 @@ struct ieee80211_hdr_3addr { u8 addr2[6]; u8 addr3[6]; __le16 seq_ctrl; -} __packed; +} __packed __aligned(2); struct ieee80211_qos_hdr { __le16 frame_control; @@ -232,7 +232,7 @@ struct ieee80211_qos_hdr { u8 addr3[6]; __le16 seq_ctrl; __le16 qos_ctrl; -} __packed; +} __packed __aligned(2); /** * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set @@ -609,7 +609,7 @@ struct ieee80211s_hdr { __le32 seqnum; u8 eaddr1[6]; u8 eaddr2[6]; -} __packed; +} __packed __aligned(2); /* Mesh flags */ #define MESH_FLAGS_AE_A4 0x1 @@ -903,7 +903,7 @@ struct ieee80211_mgmt { } u; } __packed action; } u; -} __packed; +} __packed __aligned(2); /* Supported Rates value encodings in 802.11n-2009 7.3.2.2 */ #define BSS_MEMBERSHIP_SELECTOR_HT_PHY 127 @@ -934,20 +934,20 @@ struct ieee80211_rts { __le16 duration; u8 ra[6]; u8 ta[6]; -} __packed; +} __packed __aligned(2); struct ieee80211_cts { __le16 frame_control; __le16 duration; u8 ra[6]; -} __packed; +} __packed __aligned(2); struct ieee80211_pspoll { __le16 frame_control; __le16 aid; u8 bssid[6]; u8 ta[6]; -} __packed; +} __packed __aligned(2); /* TDLS */ -- cgit v1.2.3 From c8bb93f5f5d478a01db66127844d1d2dd30abec7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 21 Feb 2013 17:26:44 +0100 Subject: wireless: remove unused VHT MCS defines There's an enum with the same values (but slightly different names except for NOT_SUPPORTED) that is actually used, so remove the defines. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 6e352c31fee0..35c1f96d9365 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1318,11 +1318,6 @@ struct ieee80211_vht_operation { } __packed; -#define IEEE80211_VHT_MCS_ZERO_TO_SEVEN_SUPPORT 0 -#define IEEE80211_VHT_MCS_ZERO_TO_EIGHT_SUPPORT 1 -#define IEEE80211_VHT_MCS_ZERO_TO_NINE_SUPPORT 2 -#define IEEE80211_VHT_MCS_NOT_SUPPORTED 3 - /* 802.11ac VHT Capabilities */ #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 -- cgit v1.2.3 From 55d942f4246c79a8f3f17f92c224e641c5c26125 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 1 Mar 2013 13:07:48 +0100 Subject: mac80211: restrict peer's VHT capabilities to own Implement restricting peer VHT capabilities to the device's own capabilities. This is useful when a single driver supports more than one device and the devices have different capabilities (often they will differ in the number of spatial streams), but in particular is also necessary for VHT capability overrides to work correctly -- otherwise it'd be possible to e.g. advertise, due to overrides, that TX-STBC is not supported, but then still use it to TX to the AP because it supports RX-STBC. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 35c1f96d9365..4cf0c9e4dd99 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1333,10 +1333,11 @@ struct ieee80211_vht_operation { #define IEEE80211_VHT_CAP_RXSTBC_2 0x00000200 #define IEEE80211_VHT_CAP_RXSTBC_3 0x00000300 #define IEEE80211_VHT_CAP_RXSTBC_4 0x00000400 +#define IEEE80211_VHT_CAP_RXSTBC_MASK 0x00000700 #define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE 0x00000800 #define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE 0x00001000 #define IEEE80211_VHT_CAP_BEAMFORMER_ANTENNAS_MAX 0x00006000 -#define IEEE80211_VHT_CAP_SOUNDING_DIMENTION_MAX 0x00030000 +#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MAX 0x00030000 #define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE 0x00080000 #define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE 0x00100000 #define IEEE80211_VHT_CAP_VHT_TXOP_PS 0x00200000 -- cgit v1.2.3 From acbba0d0f88e2577b9d92b61b136d13f65831a52 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 6 Mar 2013 01:31:12 +0000 Subject: team: introduce two default team_modeop functions and use them in modes No need to duplicate code for this. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_team.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index cfd21e3d5506..3283def74483 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -112,6 +112,10 @@ struct team_mode_ops { void (*port_disabled)(struct team *team, struct team_port *port); }; +extern int team_modeop_port_enter(struct team *team, struct team_port *port); +extern void team_modeop_port_change_dev_addr(struct team *team, + struct team_port *port); + enum team_option_type { TEAM_OPTION_TYPE_U32, TEAM_OPTION_TYPE_STRING, @@ -236,7 +240,6 @@ static inline struct team_port *team_get_port_by_index_rcu(struct team *team, return NULL; } -extern int team_port_set_team_dev_addr(struct team_port *port); extern int team_options_register(struct team *team, const struct team_option *option, size_t option_count); -- cgit v1.2.3 From 753f993911b32e479b4fab5d228dc07c11d1e7e7 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 6 Mar 2013 01:31:13 +0000 Subject: team: introduce random mode As suggested by Eric Dumazet, allow user to select mode which chooses TX port randomly. Functionality should be more of less similar to round-robin mode with even lower overhead. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_team.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 3283def74483..4474557904f6 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -240,6 +240,26 @@ static inline struct team_port *team_get_port_by_index_rcu(struct team *team, return NULL; } +static inline struct team_port * +team_get_first_port_txable_rcu(struct team *team, struct team_port *port) +{ + struct team_port *cur; + + if (likely(team_port_txable(port))) + return port; + cur = port; + list_for_each_entry_continue_rcu(cur, &team->port_list, list) + if (team_port_txable(port)) + return cur; + list_for_each_entry_rcu(cur, &team->port_list, list) { + if (cur == port) + break; + if (team_port_txable(port)) + return cur; + } + return NULL; +} + extern int team_options_register(struct team *team, const struct team_option *option, size_t option_count); -- cgit v1.2.3 From 8524982847ff00b66ffb89314c342c51f4138ee7 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Mon, 18 Feb 2013 21:47:45 +0100 Subject: ssb: fix unaligned access to mac address The mac address should be aligned to u16 to prevent an unaligned access in drivers/ssb/pci.c where it is casted to __be16. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 22958d68ecfe..8b1322296fed 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -26,9 +26,9 @@ struct ssb_sprom_core_pwr_info { struct ssb_sprom { u8 revision; - u8 il0mac[6]; /* MAC address for 802.11b/g */ - u8 et0mac[6]; /* MAC address for Ethernet */ - u8 et1mac[6]; /* MAC address for 802.11a */ + u8 il0mac[6] __aligned(sizeof(u16)); /* MAC address for 802.11b/g */ + u8 et0mac[6] __aligned(sizeof(u16)); /* MAC address for Ethernet */ + u8 et1mac[6] __aligned(sizeof(u16)); /* MAC address for 802.11a */ u8 et0phyaddr; /* MII address for enet0 */ u8 et1phyaddr; /* MII address for enet1 */ u8 et0mdcport; /* MDIO for enet0 */ -- cgit v1.2.3 From f04a9d8adf766c480353c0f2427e641251c9b059 Mon Sep 17 00:00:00 2001 From: Rajkumar Kasirajan Date: Wed, 30 May 2012 16:32:37 +0530 Subject: mfd: ab8500-sysctrl: Update correct turn on status In L9540, turn_on_status register is not updated correctly if the device is rebooted with AC/USB charger connected. Due to this, the device boots android instead of entering into charge only mode. Read the AC/USB status register to detect the charger presence and update the turn on status manually. Signed-off-by: Rajkumar Kasirajan Signed-off-by: Per Forlin Signed-off-by: Lee Jones Reviewed-by: Rupesh KUMAR Reviewed-by: Philippe LANGLAIS Tested-by: Rupesh KUMAR Tested-by: Philippe LANGLAIS Acked-by: Samuel Ortiz --- include/linux/mfd/abx500/ab8500.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index 9db0bda446a0..fdd8be64feeb 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -512,6 +512,8 @@ static inline int is_ab9540_2p0_or_earlier(struct ab8500 *ab) return (is_ab9540(ab) && (ab->chip_id < AB8500_CUT2P0)); } +void ab8500_override_turn_on_stat(u8 mask, u8 set); + #ifdef CONFIG_AB8500_DEBUG void ab8500_dump_all_banks(struct device *dev); void ab8500_debug_register_interrupt(int line); -- cgit v1.2.3 From 734823462590335cbf5c6a1fa5cae84a881dcb43 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 26 Feb 2013 10:06:55 +0000 Subject: mfd: ab8500-gpadc: Add gpadc hw conversion Add the support of gpacd hw conversion and make the number of sample configurable. Signed-off-by: M'boumba Cedric Madianga Signed-off-by: Lee Jones Reviewed-by: Mattias WALLIN Tested-by: Michel JAOUEN Acked-by: Samuel Ortiz --- include/linux/mfd/abx500/ab8500-gpadc.h | 30 ++++++++++++++++++++++++++---- 1 file changed, 26 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500-gpadc.h b/include/linux/mfd/abx500/ab8500-gpadc.h index 252966769d93..7694e7ab1880 100644 --- a/include/linux/mfd/abx500/ab8500-gpadc.h +++ b/include/linux/mfd/abx500/ab8500-gpadc.h @@ -4,12 +4,14 @@ * * Author: Arun R Murthy * Author: Daniel Willerud + * Author: M'boumba Cedric Madianga */ #ifndef _AB8500_GPADC_H #define _AB8500_GPADC_H -/* GPADC source: From datasheet(ADCSwSel[4:0] in GPADCCtrl2) */ +/* GPADC source: From datasheet(ADCSwSel[4:0] in GPADCCtrl2 + * and ADCHwSel[4:0] in GPADCCtrl3 ) */ #define BAT_CTRL 0x01 #define BTEMP_BALL 0x02 #define MAIN_CHARGER_V 0x03 @@ -24,12 +26,32 @@ #define BK_BAT_V 0x0C #define DIE_TEMP 0x0D +#define SAMPLE_1 1 +#define SAMPLE_4 4 +#define SAMPLE_8 8 +#define SAMPLE_16 16 +#define RISING_EDGE 0 +#define FALLING_EDGE 1 + +/* Arbitrary ADC conversion type constants */ +#define ADC_SW 0 +#define ADC_HW 1 + + struct ab8500_gpadc; struct ab8500_gpadc *ab8500_gpadc_get(char *name); -int ab8500_gpadc_convert(struct ab8500_gpadc *gpadc, u8 channel); -int ab8500_gpadc_read_raw(struct ab8500_gpadc *gpadc, u8 channel); +int ab8500_gpadc_sw_hw_convert(struct ab8500_gpadc *gpadc, u8 channel, + u8 avg_sample, u8 trig_edge, u8 trig_timer, u8 conv_type); +static inline int ab8500_gpadc_convert(struct ab8500_gpadc *gpadc, u8 channel) +{ + return ab8500_gpadc_sw_hw_convert(gpadc, channel, + SAMPLE_16, 0, 0, ADC_SW); +} + +int ab8500_gpadc_read_raw(struct ab8500_gpadc *gpadc, u8 channel, + u8 avg_sample, u8 trig_edge, u8 trig_timer, u8 conv_type); int ab8500_gpadc_ad_to_voltage(struct ab8500_gpadc *gpadc, - u8 channel, int ad_value); + u8 channel, int ad_value); #endif /* _AB8500_GPADC_H */ -- cgit v1.2.3 From 022ab148d28e8466e45d28552224e3029f1cccd8 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Sat, 16 Feb 2013 10:25:07 +0100 Subject: pinctrl: Declare operation structures as const The pinconf, pinctrl and pinmux operation structures hold function pointers that are never modified. Declare them as const. Signed-off-by: Laurent Pinchart Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinctrl.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index 778804df293f..2c2a9e8d8578 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -118,9 +118,9 @@ struct pinctrl_desc { const char *name; struct pinctrl_pin_desc const *pins; unsigned int npins; - struct pinctrl_ops *pctlops; - struct pinmux_ops *pmxops; - struct pinconf_ops *confops; + const struct pinctrl_ops *pctlops; + const struct pinmux_ops *pmxops; + const struct pinconf_ops *confops; struct module *owner; }; -- cgit v1.2.3 From 3e1a498f2728476535571d270081a17fdfceaf26 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 25 Feb 2013 14:57:35 +0000 Subject: mfd: ab8500-core: Add Interrupt support for ab8540 ITSource/ITLatch 7, 8, 9 and 10 don't exist on AB8540. This patch replaces them with '-1' in the interrupt list, and handles the '-1' in the code accordingly. Signed-off-by: Lee Jones Acked-by: Samuel Ortiz --- include/linux/mfd/abx500/ab8500.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index fdd8be64feeb..b5780fd40fe4 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -362,6 +362,7 @@ struct ab8500 { u8 *oldmask; int mask_size; const int *irq_reg_offset; + int it_latchhier_num; }; struct regulator_reg_init; -- cgit v1.2.3 From 75932094601b404fc9ef28f7b6c0aa83dd619af0 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 12 Feb 2013 15:11:19 +0000 Subject: mfd: ab8500-sysctrl: Add new reset function Add a new reset function which uses the AB WD with 0 timeout. Signed-off-by: Lee Jones Acked-by: Samuel Ortiz --- include/linux/mfd/abx500/ab8500-sysctrl.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500-sysctrl.h b/include/linux/mfd/abx500/ab8500-sysctrl.h index ebf12e793db9..990bc93f46e1 100644 --- a/include/linux/mfd/abx500/ab8500-sysctrl.h +++ b/include/linux/mfd/abx500/ab8500-sysctrl.h @@ -12,6 +12,7 @@ int ab8500_sysctrl_read(u16 reg, u8 *value); int ab8500_sysctrl_write(u16 reg, u8 mask, u8 value); +void ab8500_restart(char mode, const char *cmd); #else @@ -40,6 +41,7 @@ static inline int ab8500_sysctrl_clear(u16 reg, u8 bits) /* Configuration data for SysClkReq1RfClkBuf - SysClkReq8RfClkBuf */ struct ab8500_sysctrl_platform_data { u8 initial_req_buf_config[8]; + u16 (*reboot_reason_code)(const char *cmd); }; /* Registers */ @@ -299,4 +301,8 @@ struct ab8500_sysctrl_platform_data { #define AB9540_SYSCLK12BUF4VALID_SYSCLK12BUF4VALID_MASK 0xFF #define AB9540_SYSCLK12BUF4VALID_SYSCLK12BUF4VALID_SHIFT 0 +#define AB8500_ENABLE_WD 0x1 +#define AB8500_KICK_WD 0x2 +#define AB8500_WD_RESTART_ON_EXPIRE 0x10 + #endif /* __AB8500_SYSCTRL_H */ -- cgit v1.2.3 From e4bffe8d8ad9856143b6e941a17870aee37413d7 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 11 Feb 2013 10:38:00 +0000 Subject: mfd: ab8500-gpadc: Add support for the AB8540 This patch enables the GPADC to work on AB8540 based platforms. Signed-off-by: Lee Jones Acked-by: Samuel Ortiz --- include/linux/mfd/abx500/ab8500-gpadc.h | 43 ++++++++++++++++++++++----------- 1 file changed, 29 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500-gpadc.h b/include/linux/mfd/abx500/ab8500-gpadc.h index 7694e7ab1880..4131437ace4b 100644 --- a/include/linux/mfd/abx500/ab8500-gpadc.h +++ b/include/linux/mfd/abx500/ab8500-gpadc.h @@ -12,19 +12,32 @@ /* GPADC source: From datasheet(ADCSwSel[4:0] in GPADCCtrl2 * and ADCHwSel[4:0] in GPADCCtrl3 ) */ -#define BAT_CTRL 0x01 -#define BTEMP_BALL 0x02 -#define MAIN_CHARGER_V 0x03 -#define ACC_DETECT1 0x04 -#define ACC_DETECT2 0x05 -#define ADC_AUX1 0x06 -#define ADC_AUX2 0x07 -#define MAIN_BAT_V 0x08 -#define VBUS_V 0x09 -#define MAIN_CHARGER_C 0x0A -#define USB_CHARGER_C 0x0B -#define BK_BAT_V 0x0C -#define DIE_TEMP 0x0D +#define BAT_CTRL 0x01 +#define BTEMP_BALL 0x02 +#define MAIN_CHARGER_V 0x03 +#define ACC_DETECT1 0x04 +#define ACC_DETECT2 0x05 +#define ADC_AUX1 0x06 +#define ADC_AUX2 0x07 +#define MAIN_BAT_V 0x08 +#define VBUS_V 0x09 +#define MAIN_CHARGER_C 0x0A +#define USB_CHARGER_C 0x0B +#define BK_BAT_V 0x0C +#define DIE_TEMP 0x0D +#define USB_ID 0x0E +#define XTAL_TEMP 0x12 +#define VBAT_TRUE_MEAS 0x13 +#define BAT_CTRL_AND_IBAT 0x1C +#define VBAT_MEAS_AND_IBAT 0x1D +#define VBAT_TRUE_MEAS_AND_IBAT 0x1E +#define BAT_TEMP_AND_IBAT 0x1F + +/* Virtual channel used only for ibat convertion to ampere + * Battery current conversion (ibat) cannot be requested as a single conversion + * but it is always in combination with other input requests + */ +#define IBAT_VIRTUAL_CHANNEL 0xFF #define SAMPLE_1 1 #define SAMPLE_4 4 @@ -37,7 +50,6 @@ #define ADC_SW 0 #define ADC_HW 1 - struct ab8500_gpadc; struct ab8500_gpadc *ab8500_gpadc_get(char *name); @@ -51,6 +63,9 @@ static inline int ab8500_gpadc_convert(struct ab8500_gpadc *gpadc, u8 channel) int ab8500_gpadc_read_raw(struct ab8500_gpadc *gpadc, u8 channel, u8 avg_sample, u8 trig_edge, u8 trig_timer, u8 conv_type); +int ab8500_gpadc_double_read_raw(struct ab8500_gpadc *gpadc, u8 channel, + u8 avg_sample, u8 trig_edge, u8 trig_timer, u8 conv_type, + int *ibat); int ab8500_gpadc_ad_to_voltage(struct ab8500_gpadc *gpadc, u8 channel, int ad_value); -- cgit v1.2.3 From bc6b4132bcae4b8e59766ba2dae8f377009b26d0 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 26 Feb 2013 14:02:31 +0000 Subject: mfd: ab8500-debug: Add support for the AB8540 Allow GPADC debug information to be shown when executing on an AB8540 based platform. Signed-off-by: Alexandre Bourdiol Reviewed-by: Marcus COOPER Reviewed-by: Philippe LANGLAIS Acked-by: Samuel Ortiz --- include/linux/mfd/abx500/ab8500-gpadc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500-gpadc.h b/include/linux/mfd/abx500/ab8500-gpadc.h index 4131437ace4b..49ded001049b 100644 --- a/include/linux/mfd/abx500/ab8500-gpadc.h +++ b/include/linux/mfd/abx500/ab8500-gpadc.h @@ -68,5 +68,8 @@ int ab8500_gpadc_double_read_raw(struct ab8500_gpadc *gpadc, u8 channel, int *ibat); int ab8500_gpadc_ad_to_voltage(struct ab8500_gpadc *gpadc, u8 channel, int ad_value); +void ab8540_gpadc_get_otp(struct ab8500_gpadc *gpadc, + u16 *vmain_l, u16 *vmain_h, u16 *btemp_l, u16 *btemp_h, + u16 *vbat_l, u16 *vbat_h, u16 *ibat_l, u16 *ibat_h); #endif /* _AB8500_GPADC_H */ -- cgit v1.2.3 From 93ff722e88530b9719cbf53be4f3197722461394 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 31 May 2012 16:16:36 +0200 Subject: ab8500-fg: Add power cut feature for ab8505 and ab8540 Add support for a power cut feature which allows user to configure when ab8505 and ab8540 based platforms should shut down system due to low battery. Signed-off-by: Lee Jones --- include/linux/mfd/abx500.h | 10 ++++++++++ include/linux/mfd/abx500/ab8500-bm.h | 18 ++++++++++++++++++ 2 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h index 9ead60bc66b7..188aedc322c2 100644 --- a/include/linux/mfd/abx500.h +++ b/include/linux/mfd/abx500.h @@ -89,6 +89,11 @@ struct abx500_fg; * points. * @maint_thres This is the threshold where we stop reporting * battery full while in maintenance, in per cent + * @pcut_enable: Enable power cut feature in ab8505 + * @pcut_max_time: Max time threshold + * @pcut_flag_time: Flagtime threshold + * @pcut_max_restart: Max number of restarts + * @pcut_debounce_time: Sets battery debounce time */ struct abx500_fg_parameters { int recovery_sleep_timer; @@ -106,6 +111,11 @@ struct abx500_fg_parameters { int battok_raising_th_sel1; int user_cap_limit; int maint_thres; + bool pcut_enable; + u8 pcut_max_time; + u8 pcut_flag_time; + u8 pcut_max_restart; + u8 pcut_debounce_time; }; /** diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h index 8d35bfe164c8..0efbe0efee7f 100644 --- a/include/linux/mfd/abx500/ab8500-bm.h +++ b/include/linux/mfd/abx500/ab8500-bm.h @@ -235,6 +235,14 @@ /* Battery type */ #define BATTERY_UNKNOWN 00 +/* Registers for pcut feature in ab8505 and ab9540 */ +#define AB8505_RTC_PCUT_CTL_STATUS_REG 0x12 +#define AB8505_RTC_PCUT_TIME_REG 0x13 +#define AB8505_RTC_PCUT_MAX_TIME_REG 0x14 +#define AB8505_RTC_PCUT_FLAG_TIME_REG 0x15 +#define AB8505_RTC_PCUT_RESTART_REG 0x16 +#define AB8505_RTC_PCUT_DEBOUNCE_REG 0x17 + /** * struct res_to_temp - defines one point in a temp to res curve. To * be used in battery packs that combines the identification resistor with a @@ -283,6 +291,11 @@ struct ab8500_fg; * points. * @maint_thres This is the threshold where we stop reporting * battery full while in maintenance, in per cent + * @pcut_enable: Enable power cut feature in ab8505 + * @pcut_max_time: Max time threshold + * @pcut_flag_time: Flagtime threshold + * @pcut_max_restart: Max number of restarts + * @pcut_debunce_time: Sets battery debounce time */ struct ab8500_fg_parameters { int recovery_sleep_timer; @@ -299,6 +312,11 @@ struct ab8500_fg_parameters { int battok_raising_th_sel1; int user_cap_limit; int maint_thres; + bool pcut_enable; + u8 pcut_max_time; + u8 pcut_flag_time; + u8 pcut_max_restart; + u8 pcut_debunce_time; }; /** -- cgit v1.2.3 From 0f4aa401853e07885707aedfc68c608051b0d6e4 Mon Sep 17 00:00:00 2001 From: Yang QU Date: Tue, 26 Jun 2012 19:25:52 +0800 Subject: ab8500-charger: Add backup battery charge voltages on the ab8540 Add 2.7v, 2.9v, 3.0v, 3.2v and 3.3v charging voltages for backup battery. Before that only 2.5v, 2.6v, 2.8v, 3.1v were available. Signed-off-by: Yang QU Signed-off-by: Lee Jones Reviewed-by: Maxime COQUELIN Reviewed-by: Marcus COOPER Tested-by: Xiao Mei ZHANG --- include/linux/mfd/abx500/ab8500-bm.h | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h index 0efbe0efee7f..a73e05a0441b 100644 --- a/include/linux/mfd/abx500/ab8500-bm.h +++ b/include/linux/mfd/abx500/ab8500-bm.h @@ -105,6 +105,7 @@ #define AB8500_RTC_BACKUP_CHG_REG 0x0C #define AB8500_RTC_CC_CONF_REG 0x01 #define AB8500_RTC_CTRL_REG 0x0B +#define AB8500_RTC_CTRL1_REG 0x11 /* * OTP register offsets @@ -179,10 +180,25 @@ #define BUP_ICH_SEL_300UA 0x08 #define BUP_ICH_SEL_700UA 0x0C -#define BUP_VCH_SEL_2P5V 0x00 -#define BUP_VCH_SEL_2P6V 0x01 -#define BUP_VCH_SEL_2P8V 0x02 -#define BUP_VCH_SEL_3P1V 0x03 +enum bup_vch_sel { + BUP_VCH_SEL_2P5V, + BUP_VCH_SEL_2P6V, + BUP_VCH_SEL_2P8V, + BUP_VCH_SEL_3P1V, + /* + * Note that the following 5 values 2.7v, 2.9v, 3.0v, 3.2v, 3.3v + * are only available on ab8540. You can't choose these 5 + * voltage on ab8500/ab8505/ab9540. + */ + BUP_VCH_SEL_2P7V, + BUP_VCH_SEL_2P9V, + BUP_VCH_SEL_3P0V, + BUP_VCH_SEL_3P2V, + BUP_VCH_SEL_3P3V, +}; + +#define BUP_VCH_RANGE 0x02 +#define VBUP33_VRTCN 0x01 /* Battery OVV constants */ #define BATT_OVV_ENA 0x02 -- cgit v1.2.3 From 4dcdf57773fd45b483fc7613b9e51b89a57d655c Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 14 Feb 2013 09:24:10 +0000 Subject: ab8500-bm: Quick re-attach charging behaviour Due to a bug in some AB8500 ASICs charger removal cannot always be detected if the removal and reinsertion is done to close in time. This patch detects above described case and handles the situation so that charging will be kept turned on. Signed-off-by: Lee Jones --- include/linux/mfd/abx500/ux500_chargalg.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ux500_chargalg.h b/include/linux/mfd/abx500/ux500_chargalg.h index d43ac0f35526..110d12f09548 100644 --- a/include/linux/mfd/abx500/ux500_chargalg.h +++ b/include/linux/mfd/abx500/ux500_chargalg.h @@ -17,6 +17,7 @@ struct ux500_charger; struct ux500_charger_ops { int (*enable) (struct ux500_charger *, int, int, int); + int (*check_enable) (struct ux500_charger *, int, int); int (*kick_wd) (struct ux500_charger *); int (*update_curr) (struct ux500_charger *, int); }; -- cgit v1.2.3 From 8891716e24d7b0f4b1c3b4fdff641bcb1fb282c4 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Wed, 13 Feb 2013 11:39:19 +0000 Subject: ab8500-bm: Charge only mode fixes for the ab9540 Fix for charging not getting enabled in charge only mode by external charger. Signed-off-by: Lee Jones --- include/linux/mfd/abx500/ux500_chargalg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ux500_chargalg.h b/include/linux/mfd/abx500/ux500_chargalg.h index 110d12f09548..fa831f1e8cf8 100644 --- a/include/linux/mfd/abx500/ux500_chargalg.h +++ b/include/linux/mfd/abx500/ux500_chargalg.h @@ -41,4 +41,6 @@ struct ux500_charger { bool external; }; +extern struct blocking_notifier_head charger_notifier_list; + #endif -- cgit v1.2.3 From db43e6c473b57d4e7a55c4bd6edef71f40f13eae Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 14 Feb 2013 12:39:15 +0000 Subject: ab8500-bm: Add usb power path support AB8540 supports power path function in USB charging mode for fast power up with dead and weak battery, and it could extend the battery age. When USB charging starts, if the Vbattrue is below than SW cut off voltage, power path and pre-charge should be enabled. If Vbattrue is higher than SW cut off voltage, power path and pre-charge should be disabled. This is to make sure full current to battery charge. At the end of charge, power path should be enable again to reduce charging the battery again. Signed-off-by: Lee Jones --- include/linux/mfd/abx500.h | 1 + include/linux/mfd/abx500/ab8500-bm.h | 12 ++++++++++++ include/linux/mfd/abx500/ux500_chargalg.h | 4 ++++ 3 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h index 188aedc322c2..cd71d8eadf50 100644 --- a/include/linux/mfd/abx500.h +++ b/include/linux/mfd/abx500.h @@ -267,6 +267,7 @@ struct abx500_bm_data { bool autopower_cfg; bool ac_enabled; bool usb_enabled; + bool usb_power_path; bool no_maintenance; bool capacity_scaling; bool chg_unknown_bat; diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h index a73e05a0441b..0ebf0c5d1f88 100644 --- a/include/linux/mfd/abx500/ab8500-bm.h +++ b/include/linux/mfd/abx500/ab8500-bm.h @@ -69,6 +69,8 @@ #define AB8500_USBCH_CTRL1_REG 0xC0 #define AB8500_USBCH_CTRL2_REG 0xC1 #define AB8500_USBCH_IPT_CRNTLVL_REG 0xC2 +#define AB8540_USB_PP_MODE_REG 0xC5 +#define AB8540_USB_PP_CHR_REG 0xC6 /* * Gas Gauge register offsets @@ -259,6 +261,16 @@ enum bup_vch_sel { #define AB8505_RTC_PCUT_RESTART_REG 0x16 #define AB8505_RTC_PCUT_DEBOUNCE_REG 0x17 +/* USB Power Path constants for ab8540 */ +#define BUS_VSYS_VOL_SELECT_MASK 0x06 +#define BUS_VSYS_VOL_SELECT_3P6V 0x00 +#define BUS_VSYS_VOL_SELECT_3P325V 0x02 +#define BUS_VSYS_VOL_SELECT_3P9V 0x04 +#define BUS_VSYS_VOL_SELECT_4P3V 0x06 +#define BUS_POWER_PATH_MODE_ENA 0x01 +#define BUS_PP_PRECHG_CURRENT_MASK 0x0E +#define BUS_POWER_PATH_PRECHG_ENA 0x01 + /** * struct res_to_temp - defines one point in a temp to res curve. To * be used in battery packs that combines the identification resistor with a diff --git a/include/linux/mfd/abx500/ux500_chargalg.h b/include/linux/mfd/abx500/ux500_chargalg.h index fa831f1e8cf8..234c99143bf7 100644 --- a/include/linux/mfd/abx500/ux500_chargalg.h +++ b/include/linux/mfd/abx500/ux500_chargalg.h @@ -20,6 +20,8 @@ struct ux500_charger_ops { int (*check_enable) (struct ux500_charger *, int, int); int (*kick_wd) (struct ux500_charger *); int (*update_curr) (struct ux500_charger *, int); + int (*pp_enable) (struct ux500_charger *, bool); + int (*pre_chg_enable) (struct ux500_charger *, bool); }; /** @@ -30,6 +32,7 @@ struct ux500_charger_ops { * @max_out_curr maximum output charger current in mA * @enabled indicates if this charger is used or not * @external external charger unit (pm2xxx) + * @power_path USB power path support */ struct ux500_charger { struct power_supply psy; @@ -39,6 +42,7 @@ struct ux500_charger { int wdt_refresh; bool enabled; bool external; + bool power_path; }; extern struct blocking_notifier_head charger_notifier_list; -- cgit v1.2.3 From 861a30da53e2c5b9823b5390c1757baaf8f6e356 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Wed, 29 Aug 2012 20:36:51 +0800 Subject: ab8500-bm: Add support for the new ab8540 platform Provide AB8540 platform specific information required to run the Battery Management subsystem on AB8540 based devices. For this to happen we see the introduction of separate platform specific data structures and a means in which to process them. Signed-off-by: Lee Jones --- include/linux/mfd/abx500.h | 10 +++++++++- include/linux/mfd/abx500/ab8500-bm.h | 5 ++++- 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h index cd71d8eadf50..33b0253569a3 100644 --- a/include/linux/mfd/abx500.h +++ b/include/linux/mfd/abx500.h @@ -246,7 +246,11 @@ struct abx500_bm_charger_parameters { * @interval_not_charging charge alg cycle period time when not charging (sec) * @temp_hysteresis temperature hysteresis * @gnd_lift_resistance Battery ground to phone ground resistance (mOhm) - * @maxi: maximization parameters + * @n_chg_out_curr number of elements in array chg_output_curr + * @n_chg_in_curr number of elements in array chg_input_curr + * @chg_output_curr charger output current level map + * @chg_input_curr charger input current level map + * @maxi maximization parameters * @cap_levels capacity in percent for the different capacity levels * @bat_type table of supported battery types * @chg_params charger parameters @@ -281,6 +285,10 @@ struct abx500_bm_data { int interval_not_charging; int temp_hysteresis; int gnd_lift_resistance; + int n_chg_out_curr; + int n_chg_in_curr; + int *chg_output_curr; + int *chg_input_curr; const struct abx500_maxim_parameters *maxi; const struct abx500_bm_capacity_levels *cap_levels; struct abx500_battery_type *bat_type; diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h index 0ebf0c5d1f88..ee1c1626c886 100644 --- a/include/linux/mfd/abx500/ab8500-bm.h +++ b/include/linux/mfd/abx500/ab8500-bm.h @@ -33,7 +33,7 @@ #define AB8500_CH_STATUS2_REG 0x01 #define AB8500_CH_USBCH_STAT1_REG 0x02 #define AB8500_CH_USBCH_STAT2_REG 0x03 -#define AB8500_CH_FSM_STAT_REG 0x04 +#define AB8540_CH_USBCH_STAT3_REG 0x04 #define AB8500_CH_STAT_REG 0x05 /* @@ -157,6 +157,7 @@ #define CH_OP_CUR_LVL_1P4 0x0D #define CH_OP_CUR_LVL_1P5 0x0E #define CH_OP_CUR_LVL_1P6 0x0F +#define CH_OP_CUR_LVL_2P 0x3F /* BTEMP High thermal limits */ #define BTEMP_HIGH_TH_57_0 0x00 @@ -246,6 +247,8 @@ enum bup_vch_sel { #define BAT_CTRL_20U_ENA 0x02 #define BAT_CTRL_18U_ENA 0x01 #define BAT_CTRL_16U_ENA 0x02 +#define BAT_CTRL_60U_ENA 0x01 +#define BAT_CTRL_120U_ENA 0x02 #define BAT_CTRL_CMP_ENA 0x04 #define FORCE_BAT_CTRL_CMP_HIGH 0x08 #define BAT_CTRL_PULL_UP_ENA 0x10 -- cgit v1.2.3 From b3ea5f451e4e435b650e34142f8552002dc21297 Mon Sep 17 00:00:00 2001 From: Marcus Cooper Date: Wed, 29 Aug 2012 17:56:19 +0200 Subject: ab8500-charger: Add UsbLineCtrl2 reference When the state of USB Charge detection is changed then the calls use a define for another register in other bank. This change creates a new define for the correct register and removes the magic numbers that are present. Signed-off-by: Marcus Cooper Signed-off-by: Lee Jones Reviewed-by: Hakan BERG Reviewed-by: Jonas ABERG --- include/linux/mfd/abx500/ab8500-bm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h index ee1c1626c886..f5214dc651f9 100644 --- a/include/linux/mfd/abx500/ab8500-bm.h +++ b/include/linux/mfd/abx500/ab8500-bm.h @@ -23,6 +23,7 @@ * Bank : 0x5 */ #define AB8500_USB_LINE_STAT_REG 0x80 +#define AB8500_USB_LINE_CTRL2_REG 0x82 #define AB8500_USB_LINK1_STAT_REG 0x94 /* -- cgit v1.2.3 From f4095a0f06476e5914f2c58b4e96258b2e2ba6b7 Mon Sep 17 00:00:00 2001 From: M BenZoubeir Date: Thu, 13 Sep 2012 10:34:18 +0200 Subject: pm2301-charger: Adjust interrupt handler behavior Signed-off-by: M BenZoubeir Signed-off-by: Lee Jones Reviewed-by: Philippe LANGLAIS --- include/linux/pm2301_charger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm2301_charger.h b/include/linux/pm2301_charger.h index fc3f026922ae..85c16defe11a 100644 --- a/include/linux/pm2301_charger.h +++ b/include/linux/pm2301_charger.h @@ -48,7 +48,7 @@ struct pm2xxx_charger_platform_data { size_t num_supplicants; int i2c_bus; const char *label; - int irq_number; + int gpio_irq_number; unsigned int lpn_gpio; int irq_type; }; -- cgit v1.2.3 From 9684819b5a29e62acd8265a92d8f3454de9bb71e Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Wed, 27 Feb 2013 16:38:17 +0100 Subject: HID: ll_driver: Extend the interface with idle requests Some drivers send the idle command directly to underlying device, creating an unwanted dependency on the underlying transport layer. This patch adds hid_hw_idle() to the interface, thereby removing usbhid from the lion share of the drivers. Signed-off-by: Benjamin Tissoires Reviewed-by: David Herrmann Signed-off-by: Jiri Kosina --- include/linux/hid.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 7071eb3d36c7..863744c38ddc 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -664,6 +664,7 @@ struct hid_driver { * shouldn't allocate anything to not leak memory * @request: send report request to device (e.g. feature report) * @wait: wait for buffered io to complete (send/recv reports) + * @idle: send idle request to device */ struct hid_ll_driver { int (*start)(struct hid_device *hdev); @@ -683,6 +684,7 @@ struct hid_ll_driver { struct hid_report *report, int reqtype); int (*wait)(struct hid_device *hdev); + int (*idle)(struct hid_device *hdev, int report, int idle, int reqtype); }; @@ -906,6 +908,23 @@ static inline void hid_hw_request(struct hid_device *hdev, hdev->ll_driver->request(hdev, report, reqtype); } +/** + * hid_hw_idle - send idle request to device + * + * @hdev: hid device + * @report: report to control + * @idle: idle state + * @reqtype: hid request type + */ +static inline int hid_hw_idle(struct hid_device *hdev, int report, int idle, + int reqtype) +{ + if (hdev->ll_driver->idle) + return hdev->ll_driver->idle(hdev, report, idle, reqtype); + + return 0; +} + /** * hid_hw_wait - wait for buffered io to complete * -- cgit v1.2.3 From d2348fb6fdc6d671ad45b62db237f76c8c115603 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Sat, 2 Mar 2013 11:10:11 +0100 Subject: tick: Dynamically set broadcast irq affinity When a cpu goes to a deep idle state where its local timer is shutdown, it notifies the time frame work to use the broadcast timer instead. Unfortunately, the broadcast device could wake up any CPU, including an idle one which is not concerned by the wake up at all. So in the worst case an idle CPU will wake up to send an IPI to the CPU whose timer expired. Provide an opt-in feature CLOCK_EVT_FEAT_DYNIRQ which tells the core that is should set the interrupt affinity of the broadcast interrupt to the cpu which has the earliest expiry time. This avoids unnecessary spurious wakeups and IPIs. [ tglx: Adopted to cpumask rework, silenced an uninitialized warning, massaged changelog ] Signed-off-by: Daniel Lezcano Cc: viresh.kumar@linaro.org Cc: jacob.jun.pan@linux.intel.com Cc: linux-arm-kernel@lists.infradead.org Cc: santosh.shilimkar@ti.com Cc: linaro-kernel@lists.linaro.org Cc: patches@linaro.org Cc: rickard.andersson@stericsson.com Cc: vincent.guittot@linaro.org Cc: linus.walleij@stericsson.com Cc: john.stultz@linaro.org Link: http://lkml.kernel.org/r/1362219013-18173-3-git-send-email-daniel.lezcano@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 66346521cb65..494d33ea78f8 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -55,6 +55,11 @@ enum clock_event_nofitiers { #define CLOCK_EVT_FEAT_C3STOP 0x000008 #define CLOCK_EVT_FEAT_DUMMY 0x000010 +/* + * Core shall set the interrupt affinity dynamically in broadcast mode + */ +#define CLOCK_EVT_FEAT_DYNIRQ 0x000020 + /** * struct clock_event_device - clock event device descriptor * @event_handler: Assigned by the framework to be called by the low -- cgit v1.2.3 From 56dd9470d7c8734f055da2a6bac553caf4a468eb Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 24 Feb 2013 00:23:25 +0100 Subject: context_tracking: Move exception handling to generic code Exceptions handling on context tracking should share common treatment: on entry we exit user mode if the exception triggered in that context. Then on exception exit we return to that previous context. Generalize this to avoid duplication across archs. Signed-off-by: Frederic Weisbecker Cc: Li Zhong Cc: Kevin Hilman Cc: Mats Liljegren Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Steven Rostedt Cc: Namhyung Kim Cc: Andrew Morton Cc: Thomas Gleixner Cc: Paul E. McKenney --- include/linux/context_tracking.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index b28d161c1091..5a69273e93e6 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -1,10 +1,11 @@ #ifndef _LINUX_CONTEXT_TRACKING_H #define _LINUX_CONTEXT_TRACKING_H -#ifdef CONFIG_CONTEXT_TRACKING #include #include +#include +#ifdef CONFIG_CONTEXT_TRACKING struct context_tracking { /* * When active is false, probes are unset in order @@ -33,12 +34,26 @@ static inline bool context_tracking_active(void) extern void user_enter(void); extern void user_exit(void); + +static inline void exception_enter(struct pt_regs *regs) +{ + user_exit(); +} + +static inline void exception_exit(struct pt_regs *regs) +{ + if (user_mode(regs)) + user_enter(); +} + extern void context_tracking_task_switch(struct task_struct *prev, struct task_struct *next); #else static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } +static inline void exception_enter(struct pt_regs *regs) { } +static inline void exception_exit(struct pt_regs *regs) { } static inline void context_tracking_task_switch(struct task_struct *prev, struct task_struct *next) { } #endif /* !CONFIG_CONTEXT_TRACKING */ -- cgit v1.2.3 From 6c1e0256fad84a843d915414e4b5973b7443d48d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 24 Feb 2013 01:19:14 +0100 Subject: context_tracking: Restore correct previous context state on exception exit On exception exit, we restore the previous context tracking state based on the regs of the interrupted frame. Iff that frame is in user mode as stated by user_mode() helper, we restore the context tracking user mode. However there is a tiny chunck of low level arch code after we pass through user_enter() and until the CPU eventually resumes userspace. If an exception happens in this tiny area, exception_enter() correctly exits the context tracking user mode but exception_exit() won't restore it because of the value returned by user_mode(regs). As a result we may return to userspace with the wrong context tracking state. To fix this, change exception_enter() to return the context tracking state prior to its call and pass this saved state to exception_exit(). This restores the real context tracking state of the interrupted frame. (May be this patch was suggested to me, I don't recall exactly. If so, sorry for the missing credit). Signed-off-by: Frederic Weisbecker Cc: Li Zhong Cc: Kevin Hilman Cc: Mats Liljegren Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Steven Rostedt Cc: Namhyung Kim Cc: Andrew Morton Cc: Thomas Gleixner Cc: Paul E. McKenney --- include/linux/context_tracking.h | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 5a69273e93e6..365f4a61bf04 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -5,7 +5,6 @@ #include #include -#ifdef CONFIG_CONTEXT_TRACKING struct context_tracking { /* * When active is false, probes are unset in order @@ -14,12 +13,13 @@ struct context_tracking { * may be further optimized using static keys. */ bool active; - enum { + enum ctx_state { IN_KERNEL = 0, IN_USER, } state; }; +#ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); static inline bool context_tracking_in_user(void) @@ -35,14 +35,19 @@ static inline bool context_tracking_active(void) extern void user_enter(void); extern void user_exit(void); -static inline void exception_enter(struct pt_regs *regs) +static inline enum ctx_state exception_enter(void) { + enum ctx_state prev_ctx; + + prev_ctx = this_cpu_read(context_tracking.state); user_exit(); + + return prev_ctx; } -static inline void exception_exit(struct pt_regs *regs) +static inline void exception_exit(enum ctx_state prev_ctx) { - if (user_mode(regs)) + if (prev_ctx == IN_USER) user_enter(); } @@ -52,8 +57,8 @@ extern void context_tracking_task_switch(struct task_struct *prev, static inline bool context_tracking_in_user(void) { return false; } static inline void user_enter(void) { } static inline void user_exit(void) { } -static inline void exception_enter(struct pt_regs *regs) { } -static inline void exception_exit(struct pt_regs *regs) { } +static inline enum ctx_state exception_enter(void) { return 0; } +static inline void exception_exit(enum ctx_state prev_ctx) { } static inline void context_tracking_task_switch(struct task_struct *prev, struct task_struct *next) { } #endif /* !CONFIG_CONTEXT_TRACKING */ -- cgit v1.2.3 From 9fbc42eac1f6917081dc3b39922b2f1c57fdff28 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 25 Feb 2013 17:25:39 +0100 Subject: cputime: Dynamically scale cputime for full dynticks accounting The full dynticks cputime accounting is able to account either using the tick or the context tracking subsystem. This way the housekeeping CPU can keep the low overhead tick based solution. This latter mode has a low jiffies resolution granularity and need to be scaled against CFS precise runtime accounting to improve its result. We are doing this for CONFIG_TICK_CPU_ACCOUNTING, now we also need to expand it to full dynticks accounting dynamic off-case as well. Signed-off-by: Frederic Weisbecker Cc: Li Zhong Cc: Kevin Hilman Cc: Mats Liljegren Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Steven Rostedt Cc: Namhyung Kim Cc: Andrew Morton Cc: Thomas Gleixner Cc: Paul E. McKenney --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6ddbfb..8d1b6034d80b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -570,7 +570,7 @@ struct signal_struct { cputime_t utime, stime, cutime, cstime; cputime_t gtime; cputime_t cgtime; -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE struct cputime prev_cputime; #endif unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; @@ -1327,7 +1327,7 @@ struct task_struct { cputime_t utime, stime, utimescaled, stimescaled; cputime_t gtime; -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE struct cputime prev_cputime; #endif #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -- cgit v1.2.3 From 090096bf3db1c281ddd034573260045888a68fea Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 6 Mar 2013 15:39:42 +0000 Subject: net: generic fdb support for drivers without ndo_fdb_ If the driver does not support the ndo_op use the generic handler for it. This should work in the majority of cases. Eventually the fdb_dflt_add call gets translated into a __dev_set_rx_mode() call which should handle hardware support for filtering via the IFF_UNICAST_FLT flag. Namely IFF_UNICAST_FLT indicates if the hardware can do unicast address filtering. If no support is available the device is put into promisc mode. Signed-off-by: Vlad Yasevich Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 489dd7bb28ec..f28544b2f9af 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -69,6 +69,15 @@ extern int ndo_dflt_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, int idx); +extern int ndo_dflt_fdb_add(struct ndmsg *ndm, + struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, + u16 flags); +extern int ndo_dflt_fdb_del(struct ndmsg *ndm, + struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr); extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u16 mode); -- cgit v1.2.3 From c031e234ee304b507b79f76a7677ea0a7a8890e8 Mon Sep 17 00:00:00 2001 From: Andy King Date: Thu, 7 Mar 2013 05:26:13 +0000 Subject: VSOCK: Split vm_sockets.h into kernel/uapi Split the vSockets header into kernel and UAPI parts. The former gets the bits that used to be in __KERNEL__ guards, while the latter gets everything that is user-visible. Tested by compiling vsock (+transport) and a simple user-mode vSockets application. Reported-by: David Howells Acked-by: Dmitry Torokhov Signed-off-by: Andy King Acked-by: David Howells Signed-off-by: David S. Miller --- include/linux/vm_sockets.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 include/linux/vm_sockets.h (limited to 'include/linux') diff --git a/include/linux/vm_sockets.h b/include/linux/vm_sockets.h new file mode 100644 index 000000000000..0805eecba8f7 --- /dev/null +++ b/include/linux/vm_sockets.h @@ -0,0 +1,23 @@ +/* + * VMware vSockets Driver + * + * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef _VM_SOCKETS_H +#define _VM_SOCKETS_H + +#include + +int vm_sockets_get_local_cid(void); + +#endif /* _VM_SOCKETS_H */ -- cgit v1.2.3 From ec5f061564238892005257c83565a0b58ec79295 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 7 Mar 2013 09:28:01 +0000 Subject: net: Kill link between CSUM and SG features. Earlier SG was unset if CSUM was not available for given device to force skb copy to avoid sending inconsistent csum. Commit c9af6db4c11c (net: Fix possible wrong checksum generation) added explicit flag to force copy to fix this issue. Therefore there is no need to link SG and CSUM, following patch kills this link between there two features. This patch is also required following patch in series. Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/netdevice.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 896eb4985f97..e1ebeffa6b35 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2683,6 +2683,19 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) { return __skb_gso_segment(skb, features, true); } +__be16 skb_network_protocol(struct sk_buff *skb); + +static inline bool can_checksum_protocol(netdev_features_t features, + __be16 protocol) +{ + return ((features & NETIF_F_GEN_CSUM) || + ((features & NETIF_F_V4_CSUM) && + protocol == htons(ETH_P_IP)) || + ((features & NETIF_F_V6_CSUM) && + protocol == htons(ETH_P_IPV6)) || + ((features & NETIF_F_FCOE_CRC) && + protocol == htons(ETH_P_FCOE))); +} #ifdef CONFIG_BUG extern void netdev_rx_csum_fault(struct net_device *dev); -- cgit v1.2.3 From aefbd2b3c2a9c657605e4337f9919d6c6273e8e6 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 7 Mar 2013 13:21:46 +0000 Subject: tunneling: Capture inner mac header during encapsulation. This patch adds inner mac header. This will be used in next patch to find tunner header length. Header len is required to copy tunnel header to each gso segment. This patch does not change any functionality. Signed-off-by: Pravin B Shelar Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/skbuff.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 821c7f45d2a7..d7f96ff68f77 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -387,6 +387,7 @@ typedef unsigned char *sk_buff_data_t; * @vlan_tci: vlan tag control information * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) + * @inner_mac_header: Link layer header (encapsulation) * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header @@ -505,6 +506,7 @@ struct sk_buff { sk_buff_data_t inner_transport_header; sk_buff_data_t inner_network_header; + sk_buff_data_t inner_mac_header; sk_buff_data_t transport_header; sk_buff_data_t network_header; sk_buff_data_t mac_header; @@ -1466,6 +1468,7 @@ static inline void skb_reserve(struct sk_buff *skb, int len) static inline void skb_reset_inner_headers(struct sk_buff *skb) { + skb->inner_mac_header = skb->mac_header; skb->inner_network_header = skb->network_header; skb->inner_transport_header = skb->transport_header; } @@ -1511,6 +1514,22 @@ static inline void skb_set_inner_network_header(struct sk_buff *skb, skb->inner_network_header += offset; } +static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) +{ + return skb->head + skb->inner_mac_header; +} + +static inline void skb_reset_inner_mac_header(struct sk_buff *skb) +{ + skb->inner_mac_header = skb->data - skb->head; +} + +static inline void skb_set_inner_mac_header(struct sk_buff *skb, + const int offset) +{ + skb_reset_inner_mac_header(skb); + skb->inner_mac_header += offset; +} static inline bool skb_transport_header_was_set(const struct sk_buff *skb) { return skb->transport_header != ~0U; @@ -1604,6 +1623,21 @@ static inline void skb_set_inner_network_header(struct sk_buff *skb, skb->inner_network_header = skb->data + offset; } +static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) +{ + return skb->inner_mac_header; +} + +static inline void skb_reset_inner_mac_header(struct sk_buff *skb) +{ + skb->inner_mac_header = skb->data; +} + +static inline void skb_set_inner_mac_header(struct sk_buff *skb, + const int offset) +{ + skb->inner_mac_header = skb->data + offset; +} static inline bool skb_transport_header_was_set(const struct sk_buff *skb) { return skb->transport_header != NULL; -- cgit v1.2.3 From 731362674580cb0c696cd1b1a03d8461a10cf90a Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 7 Mar 2013 13:21:51 +0000 Subject: tunneling: Add generic Tunnel segmentation. Adds generic tunneling offloading support for IPv4-UDP based tunnels. GSO type is added to request this offload for a skb. netdev feature NETIF_F_UDP_TUNNEL is added for hardware offloaded udp-tunnel support. Currently no device supports this feature, software offload is used. This can be used by tunneling protocols like VXLAN. CC: Jesse Gross Signed-off-by: Pravin B Shelar Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 7 ++++--- include/linux/skbuff.h | 2 ++ 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 3dd39340430e..f5e797c0c2a4 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -42,9 +42,9 @@ enum { NETIF_F_TSO6_BIT, /* ... TCPv6 segmentation */ NETIF_F_FSO_BIT, /* ... FCoE segmentation */ NETIF_F_GSO_GRE_BIT, /* ... GRE with TSO */ - /**/NETIF_F_GSO_LAST, /* [can't be last bit, see GSO_MASK] */ - NETIF_F_GSO_RESERVED2 /* ... free (fill GSO_MASK to 8 bits) */ - = NETIF_F_GSO_LAST, + NETIF_F_GSO_UDP_TUNNEL_BIT, /* ... UDP TUNNEL with TSO */ + /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ + NETIF_F_GSO_UDP_TUNNEL_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CSUM_BIT, /* SCTP checksum offload */ @@ -103,6 +103,7 @@ enum { #define NETIF_F_RXFCS __NETIF_F(RXFCS) #define NETIF_F_RXALL __NETIF_F(RXALL) #define NETIF_F_GRE_GSO __NETIF_F(GSO_GRE) +#define NETIF_F_UDP_TUNNEL __NETIF_F(UDP_TUNNEL) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d7f96ff68f77..eb2106fe3bb4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -316,6 +316,8 @@ enum { SKB_GSO_FCOE = 1 << 5, SKB_GSO_GRE = 1 << 6, + + SKB_GSO_UDP_TUNNEL = 1 << 7, }; #if BITS_PER_LONG > 32 -- cgit v1.2.3 From 6150f3bc0b4f94f0eea3e32b4e7462025e4bd972 Mon Sep 17 00:00:00 2001 From: Nicolas Royer Date: Wed, 20 Feb 2013 17:10:23 +0100 Subject: ARM: AT91SAM9G45: same platform data structure for all crypto peripherals MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Only AES use DMA in AT91SAM9G45 (TDES and SHA use PDC). However latest Atmel TDES and SHA IP releases use DMA instead of PDC. --> Atmel TDES and SHA drivers need DMA platform data for those IP releases. Goal of this patch is to use the same platform data structure for all Atmel crypto peripherals. This structure contains information about DMA interface. Signed-off-by: Nicolas Royer Acked-by: Nicolas Ferre Acked-by: Eric Bénard Tested-by: Eric Bénard Signed-off-by: Herbert Xu --- include/linux/platform_data/atmel-aes.h | 22 ---------------------- include/linux/platform_data/crypto-atmel.h | 22 ++++++++++++++++++++++ 2 files changed, 22 insertions(+), 22 deletions(-) delete mode 100644 include/linux/platform_data/atmel-aes.h create mode 100644 include/linux/platform_data/crypto-atmel.h (limited to 'include/linux') diff --git a/include/linux/platform_data/atmel-aes.h b/include/linux/platform_data/atmel-aes.h deleted file mode 100644 index ab68082fbcb0..000000000000 --- a/include/linux/platform_data/atmel-aes.h +++ /dev/null @@ -1,22 +0,0 @@ -#ifndef __LINUX_ATMEL_AES_H -#define __LINUX_ATMEL_AES_H - -#include - -/** - * struct aes_dma_data - DMA data for AES - */ -struct aes_dma_data { - struct at_dma_slave txdata; - struct at_dma_slave rxdata; -}; - -/** - * struct aes_platform_data - board-specific AES configuration - * @dma_slave: DMA slave interface to use in data transfers. - */ -struct aes_platform_data { - struct aes_dma_data *dma_slave; -}; - -#endif /* __LINUX_ATMEL_AES_H */ diff --git a/include/linux/platform_data/crypto-atmel.h b/include/linux/platform_data/crypto-atmel.h new file mode 100644 index 000000000000..b46e0d9062a0 --- /dev/null +++ b/include/linux/platform_data/crypto-atmel.h @@ -0,0 +1,22 @@ +#ifndef __LINUX_CRYPTO_ATMEL_H +#define __LINUX_CRYPTO_ATMEL_H + +#include + +/** + * struct crypto_dma_data - DMA data for AES/TDES/SHA + */ +struct crypto_dma_data { + struct at_dma_slave txdata; + struct at_dma_slave rxdata; +}; + +/** + * struct crypto_platform_data - board-specific AES/TDES/SHA configuration + * @dma_slave: DMA slave interface to use in data transfers. + */ +struct crypto_platform_data { + struct crypto_dma_data *dma_slave; +}; + +#endif /* __LINUX_CRYPTO_ATMEL_H */ -- cgit v1.2.3 From e61667af2f77d481411f2ccd307fed2247d785a8 Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Sun, 10 Mar 2013 05:18:39 +0000 Subject: tcp: Remove unused tw_cookie_values from tcp_timewait_sock tw_cookie_values is never used in the TCP-stack. It was added by 435cf559f (TCPCT part 1d: define TCP cookie option, extend existing struct's), but already at that time it was not used at all, nor mentioned in the commit-message. Signed-off-by: Christoph Paasch Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index f28408c07dc2..515c3746b675 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -361,10 +361,6 @@ struct tcp_timewait_sock { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tw_md5_key; #endif - /* Few sockets in timewait have cookies; in that case, then this - * object holds a reference to them (tw_cookie_values->kref). - */ - struct tcp_cookie_values *tw_cookie_values; }; static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) -- cgit v1.2.3 From 26fd76cab2e61cedc5c25f7151fb31b57ddc53c7 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Fri, 22 Feb 2013 10:53:25 +0100 Subject: NFC: llcp: Implement socket options Some LLCP services (e.g. the validation ones) require some control over the LLCP link parameters like the receive window (RW) or the MIU extension (MIUX). This can only be done through socket options. Signed-off-by: Samuel Ortiz --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 2b9f74b0ffea..428c37a1f95c 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -298,6 +298,7 @@ struct ucred { #define SOL_IUCV 277 #define SOL_CAIF 278 #define SOL_ALG 279 +#define SOL_NFC 280 /* IPX options */ #define IPX_TYPE 1 -- cgit v1.2.3 From 3a08a8f9f0936e182d387afd85fdc5d303381521 Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Mon, 4 Mar 2013 23:32:07 +0530 Subject: kvm: Record the preemption status of vcpus using preempt notifiers Note that we mark as preempted only when vcpu's task state was Running during preemption. Thanks Jiannan, Avi for preemption notifier ideas. Thanks Gleb, PeterZ for their precious suggestions. Thanks Srikar for an idea on avoiding rcu lock while checking task state that improved overcommit numbers. Reviewed-by: Chegu Vinod Reviewed-by: Marcelo Tosatti Signed-off-by: Raghavendra K T Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9fa13ebc3381..0f4941a9c9c8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -253,6 +253,7 @@ struct kvm_vcpu { bool dy_eligible; } spin_loop; #endif + bool preempted; struct kvm_vcpu_arch arch; }; -- cgit v1.2.3 From e0c25362384f4be9c755c98560cd4b1cdb2ec79c Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Sun, 10 Mar 2013 21:52:53 -0500 Subject: clocksource: add empty version of clocksource_of_init Add an empty clocksource_of_init when !CLKSRC_OF. This is needed for builds where no timer has selected CLKSRC_OF. Signed-off-by: Rob Herring Cc: John Stultz Cc: Thomas Gleixner --- include/linux/clocksource.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 27cfda427dd9..08ed5e19d8c6 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -340,6 +340,7 @@ extern void clocksource_of_init(void); __used __section(__clksrc_of_table) \ = { .compatible = compat, .data = fn }; #else +static inline void clocksource_of_init(void) {} #define CLOCKSOURCE_OF_DECLARE(name, compat, fn) #endif -- cgit v1.2.3 From 44f507163d9e51238458ee6904b4d71fb0723723 Mon Sep 17 00:00:00 2001 From: Vijay Mohan Pandarathil Date: Mon, 11 Mar 2013 09:28:44 -0600 Subject: VFIO: Wrapper for getting reference to vfio_device - Added vfio_device_get_from_dev() as wrapper to get reference to vfio_device from struct device. - Added vfio_device_data() as a wrapper to get device_data from vfio_device. Signed-off-by: Vijay Mohan Pandarathil Signed-off-by: Alex Williamson --- include/linux/vfio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index ab9e86224c54..ac8d488e4372 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -45,6 +45,9 @@ extern int vfio_add_group_dev(struct device *dev, void *device_data); extern void *vfio_del_group_dev(struct device *dev); +extern struct vfio_device *vfio_device_get_from_dev(struct device *dev); +extern void vfio_device_put(struct vfio_device *device); +extern void *vfio_device_data(struct vfio_device *device); /** * struct vfio_iommu_driver_ops - VFIO IOMMU driver callbacks -- cgit v1.2.3 From b818d1a7f72575eef17e00dc4085512c9cc8897d Mon Sep 17 00:00:00 2001 From: Hector Palacios Date: Sun, 10 Mar 2013 22:50:02 +0000 Subject: phy/micrel: Add support for KSZ8031 Micrel PHY KSZ8031 is similar to KSZ8021 and also requires the special initialization of "Operation Mode Strap Override" in reg 0x16 introduced in 212ea99 (phy/micrel: Implement support for KSZ8021). Signed-off-by: Hector Palacios Reviewed-by: Marek Vasut Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 9dbb41a4e250..8752dbbc6135 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -19,6 +19,7 @@ #define PHY_ID_KSZ9021 0x00221610 #define PHY_ID_KS8737 0x00221720 #define PHY_ID_KSZ8021 0x00221555 +#define PHY_ID_KSZ8031 0x00221556 #define PHY_ID_KSZ8041 0x00221510 #define PHY_ID_KSZ8051 0x00221550 /* same id: ks8001 Rev. A/B, and ks8721 Rev 3. */ -- cgit v1.2.3 From 6ba8a3b19e764b6a65e4030ab0999be50c291e6c Mon Sep 17 00:00:00 2001 From: Nandita Dukkipati Date: Mon, 11 Mar 2013 10:00:43 +0000 Subject: tcp: Tail loss probe (TLP) This patch series implement the Tail loss probe (TLP) algorithm described in http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01. The first patch implements the basic algorithm. TLP's goal is to reduce tail latency of short transactions. It achieves this by converting retransmission timeouts (RTOs) occuring due to tail losses (losses at end of transactions) into fast recovery. TLP transmits one packet in two round-trips when a connection is in Open state and isn't receiving any ACKs. The transmitted packet, aka loss probe, can be either new or a retransmission. When there is tail loss, the ACK from a loss probe triggers FACK/early-retransmit based fast recovery, thus avoiding a costly RTO. In the absence of loss, there is no change in the connection state. PTO stands for probe timeout. It is a timer event indicating that an ACK is overdue and triggers a loss probe packet. The PTO value is set to max(2*SRTT, 10ms) and is adjusted to account for delayed ACK timer when there is only one oustanding packet. TLP Algorithm On transmission of new data in Open state: -> packets_out > 1: schedule PTO in max(2*SRTT, 10ms). -> packets_out == 1: schedule PTO in max(2*RTT, 1.5*RTT + 200ms) -> PTO = min(PTO, RTO) Conditions for scheduling PTO: -> Connection is in Open state. -> Connection is either cwnd limited or no new data to send. -> Number of probes per tail loss episode is limited to one. -> Connection is SACK enabled. When PTO fires: new_segment_exists: -> transmit new segment. -> packets_out++. cwnd remains same. no_new_packet: -> retransmit the last segment. Its ACK triggers FACK or early retransmit based recovery. ACK path: -> rearm RTO at start of ACK processing. -> reschedule PTO if need be. In addition, the patch includes a small variation to the Early Retransmit (ER) algorithm, such that ER and TLP together can in principle recover any N-degree of tail loss through fast recovery. TLP is controlled by the same sysctl as ER, tcp_early_retrans sysctl. tcp_early_retrans==0; disables TLP and ER. ==1; enables RFC5827 ER. ==2; delayed ER. ==3; TLP and delayed ER. [DEFAULT] ==4; TLP only. The TLP patch series have been extensively tested on Google Web servers. It is most effective for short Web trasactions, where it reduced RTOs by 15% and improved HTTP response time (average by 6%, 99th percentile by 10%). The transmitted probes account for <0.5% of the overall transmissions. Signed-off-by: Nandita Dukkipati Acked-by: Neal Cardwell Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 515c3746b675..01860d74555c 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -201,7 +201,6 @@ struct tcp_sock { unused : 1; u8 repair_queue; u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */ - early_retrans_delayed:1, /* Delayed ER timer installed */ syn_data:1, /* SYN includes data */ syn_fastopen:1, /* SYN includes Fast Open option */ syn_data_acked:1;/* data in SYN is acked by SYN-ACK */ -- cgit v1.2.3 From 9b717a8d245075ffb8e95a2dfb4ee97ce4747457 Mon Sep 17 00:00:00 2001 From: Nandita Dukkipati Date: Mon, 11 Mar 2013 10:00:44 +0000 Subject: tcp: TLP loss detection. This is the second of the TLP patch series; it augments the basic TLP algorithm with a loss detection scheme. This patch implements a mechanism for loss detection when a Tail loss probe retransmission plugs a hole thereby masking packet loss from the sender. The loss detection algorithm relies on counting TLP dupacks as outlined in Sec. 3 of: http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01 The basic idea is: Sender keeps track of TLP "episode" upon retransmission of a TLP packet. An episode ends when the sender receives an ACK above the SND.NXT (tracked by tlp_high_seq) at the time of the episode. We want to make sure that before the episode ends the sender receives a "TLP dupack", indicating that the TLP retransmission was unnecessary, so there was no loss/hole that needed plugging. If the sender gets no TLP dupack before the end of the episode, then it reduces ssthresh and the congestion window, because the TLP packet arriving at the receiver probably plugged a hole. Signed-off-by: Nandita Dukkipati Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 01860d74555c..763c108ee03d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -204,6 +204,7 @@ struct tcp_sock { syn_data:1, /* SYN includes data */ syn_fastopen:1, /* SYN includes Fast Open option */ syn_data_acked:1;/* data in SYN is acked by SYN-ACK */ + u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ /* RTT measurement */ u32 srtt; /* smoothed round trip time << 3 */ -- cgit v1.2.3 From 42e836eb4527fb635cb799a701fe4c9fe741c03a Mon Sep 17 00:00:00 2001 From: Michael Stapelberg Date: Mon, 11 Mar 2013 13:56:44 +0000 Subject: phy: add set_wol/get_wol functions This allows ethernet drivers (such as the mv643xx_eth) to support Wake on LAN on platforms where PHY registers have to be configured for Wake on LAN (e.g. the Marvell Kirkwood based qnap TS-119P II). Signed-off-by: Michael Stapelberg Signed-off-by: David S. Miller --- include/linux/phy.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 33999adbf8c8..9e11039dd7a3 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -455,6 +455,14 @@ struct phy_driver { */ void (*txtstamp)(struct phy_device *dev, struct sk_buff *skb, int type); + /* Some devices (e.g. qnap TS-119P II) require PHY register changes to + * enable Wake on LAN, so set_wol is provided to be called in the + * ethernet driver's set_wol function. */ + int (*set_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); + + /* See set_wol, but for checking whether Wake on LAN is enabled. */ + void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); + struct device_driver driver; }; #define to_phy_driver(d) container_of(d, struct phy_driver, driver) @@ -560,6 +568,8 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); int phy_get_eee_err(struct phy_device *phydev); int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data); int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data); +int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); +void phy_ethtool_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); int __init mdio_bus_init(void); void mdio_bus_exit(void); -- cgit v1.2.3 From d84ff0512f1bfc0d8c864efadb4523fce68919cc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:29:59 -0700 Subject: workqueue: consistently use int for @cpu variables Workqueue is mixing unsigned int and int for @cpu variables. There's no point in using unsigned int for cpus - many of cpu related APIs take int anyway. Consistently use int for @cpu variables so that we can use negative values to mark special ones. This patch doesn't introduce any visible behavior changes. Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- include/linux/workqueue.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 5bd030f630a9..899be6636d20 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -435,7 +435,7 @@ extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); -extern bool workqueue_congested(unsigned int cpu, struct workqueue_struct *wq); +extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); /* @@ -466,12 +466,12 @@ static inline bool __deprecated flush_delayed_work_sync(struct delayed_work *dwo } #ifndef CONFIG_SMP -static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg) +static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } #else -long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg); +long work_on_cpu(int cpu, long (*fn)(void *), void *arg); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER -- cgit v1.2.3 From 7a4e344c5675eefbde93ed9a98ef45e0e4957bc2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:00 -0700 Subject: workqueue: introduce workqueue_attrs Introduce struct workqueue_attrs which carries worker attributes - currently the nice level and allowed cpumask along with helper routines alloc_workqueue_attrs() and free_workqueue_attrs(). Each worker_pool now carries ->attrs describing the attributes of its workers. All functions dealing with cpumask and nice level of workers are updated to follow worker_pool->attrs instead of determining them from other characteristics of the worker_pool, and init_workqueues() is updated to set worker_pool->attrs appropriately for all standard pools. Note that create_worker() is updated to always perform set_user_nice() and use set_cpus_allowed_ptr() combined with manual assertion of PF_THREAD_BOUND instead of kthread_bind(). This simplifies handling random attributes without affecting the outcome. This patch doesn't introduce any behavior changes. v2: Missing cpumask_var_t definition caused build failure on some archs. linux/cpumask.h included. Signed-off-by: Tejun Heo Reported-by: kbuild test robot Reviewed-by: Lai Jiangshan --- include/linux/workqueue.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 899be6636d20..00c1b9ba8252 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -11,6 +11,7 @@ #include #include #include +#include struct workqueue_struct; @@ -115,6 +116,15 @@ struct delayed_work { int cpu; }; +/* + * A struct for workqueue attributes. This can be used to change + * attributes of an unbound workqueue. + */ +struct workqueue_attrs { + int nice; /* nice level */ + cpumask_var_t cpumask; /* allowed CPUs */ +}; + static inline struct delayed_work *to_delayed_work(struct work_struct *work) { return container_of(work, struct delayed_work, work); @@ -399,6 +409,9 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, extern void destroy_workqueue(struct workqueue_struct *wq); +struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask); +void free_workqueue_attrs(struct workqueue_attrs *attrs); + extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_work(struct workqueue_struct *wq, struct work_struct *work); -- cgit v1.2.3 From 493008a8e475771a2126e0ce95a73e35b371d277 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:03 -0700 Subject: workqueue: drop WQ_RESCUER and test workqueue->rescuer for NULL instead WQ_RESCUER is superflous. WQ_MEM_RECLAIM indicates that the user wants a rescuer and testing wq->rescuer for NULL can answer whether a given workqueue has a rescuer or not. Drop WQ_RESCUER and test wq->rescuer directly. This will help simplifying __alloc_workqueue_key() failure path by allowing it to use destroy_workqueue() on a partially constructed workqueue, which in turn will help implementing dynamic management of pool_workqueues. While at it, clear wq->rescuer after freeing it in destroy_workqueue(). This is a precaution as scheduled changes will make destruction more complex. This patch doesn't introduce any functional changes. Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- include/linux/workqueue.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 00c1b9ba8252..c270b4eedf16 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -295,7 +295,6 @@ enum { WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ WQ_DRAINING = 1 << 6, /* internal: workqueue is draining */ - WQ_RESCUER = 1 << 7, /* internal: workqueue has rescuer */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ -- cgit v1.2.3 From 9e8cd2f5898ab6710ad81f4583fada08bf8049a4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:04 -0700 Subject: workqueue: implement apply_workqueue_attrs() Implement apply_workqueue_attrs() which applies workqueue_attrs to the specified unbound workqueue by creating a new pwq (pool_workqueue) linked to worker_pool with the specified attributes. A new pwq is linked at the head of wq->pwqs instead of tail and __queue_work() verifies that the first unbound pwq has positive refcnt before choosing it for the actual queueing. This is to cover the case where creation of a new pwq races with queueing. As base ref on a pwq won't be dropped without making another pwq the first one, __queue_work() is guaranteed to make progress and not add work item to a dead pwq. init_and_link_pwq() is updated to return the last first pwq the new pwq replaced, which is put by apply_workqueue_attrs(). Note that apply_workqueue_attrs() is almost identical to unbound pwq part of alloc_and_link_pwqs(). The only difference is that there is no previous first pwq. apply_workqueue_attrs() is implemented to handle such cases and replaces unbound pwq handling in alloc_and_link_pwqs(). Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- include/linux/workqueue.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index c270b4eedf16..e152394fa7eb 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -410,6 +410,8 @@ extern void destroy_workqueue(struct workqueue_struct *wq); struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask); void free_workqueue_attrs(struct workqueue_attrs *attrs); +int apply_workqueue_attrs(struct workqueue_struct *wq, + const struct workqueue_attrs *attrs); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); -- cgit v1.2.3 From 618b01eb426dd2d73a4b5e5ebc6379e4eee3b123 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:04 -0700 Subject: workqueue: make it clear that WQ_DRAINING is an internal flag We're gonna add another internal WQ flag. Let's make the distinction clear. Prefix WQ_DRAINING with __ and move it to bit 16. Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- include/linux/workqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index e152394fa7eb..1751ec4c47c9 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -294,7 +294,7 @@ enum { WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ - WQ_DRAINING = 1 << 6, /* internal: workqueue is draining */ + __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ -- cgit v1.2.3 From 8719dceae2f98a578507c0f6b49c93f320bd729c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:04 -0700 Subject: workqueue: reject adjusting max_active or applying attrs to ordered workqueues Adjusting max_active of or applying new workqueue_attrs to an ordered workqueue breaks its ordering guarantee. The former is obvious. The latter is because applying attrs creates a new pwq (pool_workqueue) and there is no ordering constraint between the old and new pwqs. Make apply_workqueue_attrs() and workqueue_set_max_active() trigger WARN_ON() if those operations are requested on an ordered workqueue and fail / ignore respectively. Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- include/linux/workqueue.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 1751ec4c47c9..5668ab249af5 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -295,6 +295,7 @@ enum { WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ + __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ @@ -397,7 +398,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue(fmt, flags, args...) \ - alloc_workqueue(fmt, WQ_UNBOUND | (flags), 1, ##args) + alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args) #define create_workqueue(name) \ alloc_workqueue((name), WQ_MEM_RECLAIM, 1) -- cgit v1.2.3 From ba630e4940924ad1962883c207a62890778ced63 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:04 -0700 Subject: cpumask: implement cpumask_parse() We have cpulist_parse() but not cpumask_parse(). Implement it using bitmap_parse(). bitmap_parse() is weird in that it takes @len for a string in kernel-memory which also is inconsistent with bitmap_parselist(). Make cpumask_parse() calculate the length and don't expose the inconsistency to cpumask users. Maybe we can fix up bitmap_parse() later. This will be used to expose workqueue cpumask knobs to userland via sysfs. Signed-off-by: Tejun Heo Cc: Rusty Russell --- include/linux/cpumask.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 032560295fcb..d08e4d2a9b92 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -590,6 +590,21 @@ static inline int cpulist_scnprintf(char *buf, int len, nr_cpumask_bits); } +/** + * cpumask_parse - extract a cpumask from from a string + * @buf: the buffer to extract from + * @dstp: the cpumask to set. + * + * Returns -errno, or 0 for success. + */ +static inline int cpumask_parse(const char *buf, struct cpumask *dstp) +{ + char *nl = strchr(buf, '\n'); + int len = nl ? nl - buf : strlen(buf); + + return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits); +} + /** * cpulist_parse - extract a cpumask from a user string of ranges * @buf: the buffer to extract from -- cgit v1.2.3 From d73ce004225a7b2ed75f4340bb63721d55552265 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:05 -0700 Subject: driver/base: implement subsys_virtual_register() Kay tells me the most appropriate place to expose workqueues to userland would be /sys/devices/virtual/workqueues/WQ_NAME which is symlinked to /sys/bus/workqueue/devices/WQ_NAME and that we're lacking a way to do that outside of driver core as virtual_device_parent() isn't exported and there's no inteface to conveniently create a virtual subsystem. This patch implements subsys_virtual_register() by factoring out subsys_register() from subsys_system_register() and using it with virtual_device_parent() as the origin directory. It's identical to subsys_system_register() other than the origin directory but we aren't gonna restrict the device names which should be used under it. This will be used to expose workqueue attributes to userland. Signed-off-by: Tejun Heo Acked-by: Greg Kroah-Hartman Cc: Kay Sievers --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 9d6464ea99c6..ee10d4e7be1a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -302,6 +302,8 @@ void subsys_interface_unregister(struct subsys_interface *sif); int subsys_system_register(struct bus_type *subsys, const struct attribute_group **groups); +int subsys_virtual_register(struct bus_type *subsys, + const struct attribute_group **groups); /** * struct class - device classes -- cgit v1.2.3 From 226223ab3c4118ddd10688cc2c131135848371ab Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 11:30:05 -0700 Subject: workqueue: implement sysfs interface for workqueues There are cases where workqueue users want to expose control knobs to userland. e.g. Unbound workqueues with custom attributes are scheduled to be used for writeback workers and depending on configuration it can be useful to allow admins to tinker with the priority or allowed CPUs. This patch implements workqueue_sysfs_register(), which makes the workqueue visible under /sys/bus/workqueue/devices/WQ_NAME. There currently are two attributes common to both per-cpu and unbound pools and extra attributes for unbound pools including nice level and cpumask. If alloc_workqueue*() is called with WQ_SYSFS, workqueue_sysfs_register() is called automatically as part of workqueue creation. This is the preferred method unless the workqueue user wants to apply workqueue_attrs before making the workqueue visible to userland. v2: Disallow exposing ordered workqueues as ordered workqueues can't be tuned in any way. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 5668ab249af5..7f6d29a417c0 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -293,6 +293,7 @@ enum { WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ + WQ_SYSFS = 1 << 6, /* visible in sysfs, see wq_sysfs_register() */ __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ @@ -495,4 +496,11 @@ extern bool freeze_workqueues_busy(void); extern void thaw_workqueues(void); #endif /* CONFIG_FREEZER */ +#ifdef CONFIG_SYSFS +int workqueue_sysfs_register(struct workqueue_struct *wq); +#else /* CONFIG_SYSFS */ +static inline int workqueue_sysfs_register(struct workqueue_struct *wq) +{ return 0; } +#endif /* CONFIG_SYSFS */ + #endif -- cgit v1.2.3 From cc2a8b1a5595a435191fb197d92d1f3e193c9a6d Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 12 Mar 2013 13:59:14 -0700 Subject: async: remove unused @node from struct async_domain The @node in struct async_domain is unused after we introduce async_global_pending, remove it. tj: Unnecessary whitespace adjustments dropped. Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo Cc: Arjan van de Ven --- include/linux/async.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/async.h b/include/linux/async.h index a2e3f18b2ad6..98ea0fef30d5 100644 --- a/include/linux/async.h +++ b/include/linux/async.h @@ -18,7 +18,6 @@ typedef u64 async_cookie_t; typedef void (async_func_ptr) (void *data, async_cookie_t cookie); struct async_domain { - struct list_head node; struct list_head pending; unsigned registered:1; }; @@ -27,8 +26,7 @@ struct async_domain { * domain participates in global async_synchronize_full */ #define ASYNC_DOMAIN(_name) \ - struct async_domain _name = { .node = LIST_HEAD_INIT(_name.node), \ - .pending = LIST_HEAD_INIT(_name.pending), \ + struct async_domain _name = { .pending = LIST_HEAD_INIT(_name.pending), \ .registered = 1 } /* @@ -36,8 +34,7 @@ struct async_domain { * complete, this domain does not participate in async_synchronize_full */ #define ASYNC_DOMAIN_EXCLUSIVE(_name) \ - struct async_domain _name = { .node = LIST_HEAD_INIT(_name.node), \ - .pending = LIST_HEAD_INIT(_name.pending), \ + struct async_domain _name = { .pending = LIST_HEAD_INIT(_name.pending), \ .registered = 0 } extern async_cookie_t async_schedule(async_func_ptr *ptr, void *data); -- cgit v1.2.3 From 362f2b098b188ede9c4350cc20e58040dbfa515e Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 12 Mar 2013 13:59:14 -0700 Subject: async: rename and redefine async_func_ptr A function type is typically defined as typedef ret_type (*func)(args..) but async_func_ptr is not. Redefine it. Also rename async_func_ptr to async_func_t for _func_t suffix is more generic. Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo Cc: Arjan van de Ven --- include/linux/async.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/async.h b/include/linux/async.h index 98ea0fef30d5..6b0226bdaadc 100644 --- a/include/linux/async.h +++ b/include/linux/async.h @@ -16,7 +16,7 @@ #include typedef u64 async_cookie_t; -typedef void (async_func_ptr) (void *data, async_cookie_t cookie); +typedef void (*async_func_t) (void *data, async_cookie_t cookie); struct async_domain { struct list_head pending; unsigned registered:1; @@ -37,8 +37,8 @@ struct async_domain { struct async_domain _name = { .pending = LIST_HEAD_INIT(_name.pending), \ .registered = 0 } -extern async_cookie_t async_schedule(async_func_ptr *ptr, void *data); -extern async_cookie_t async_schedule_domain(async_func_ptr *ptr, void *data, +extern async_cookie_t async_schedule(async_func_t func, void *data); +extern async_cookie_t async_schedule_domain(async_func_t func, void *data, struct async_domain *domain); void async_unregister_domain(struct async_domain *domain); extern void async_synchronize_full(void); -- cgit v1.2.3 From 49d0de082c31de34cc896c14eec5f1c2ade0415a Mon Sep 17 00:00:00 2001 From: Steven Whitehouse Date: Thu, 14 Feb 2013 16:42:34 -0800 Subject: rcu: Fix hlist_bl_set_first_rcu() annotation Abhi noticed that we were getting a complaint from the RCU subsystem about access of an RCU protected list under the write side bit lock. This commit adds additional annotation to check both the RCU read lock and the write side bit lock before printing a message. Reported by: Abhijith Das Signed-off-by: Steven Whitehouse Tested-by: Abhijith Das Signed-off-by: Paul E. McKenney --- include/linux/list_bl.h | 5 +++++ include/linux/rculist_bl.h | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h index 31f9d75adc5b..2eb88556c5c5 100644 --- a/include/linux/list_bl.h +++ b/include/linux/list_bl.h @@ -125,6 +125,11 @@ static inline void hlist_bl_unlock(struct hlist_bl_head *b) __bit_spin_unlock(0, (unsigned long *)b); } +static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) +{ + return bit_spin_is_locked(0, (unsigned long *)b); +} + /** * hlist_bl_for_each_entry - iterate over list of given type * @tpos: the type * to use as a loop cursor. diff --git a/include/linux/rculist_bl.h b/include/linux/rculist_bl.h index cf1244fbf3b6..4f216c59e7db 100644 --- a/include/linux/rculist_bl.h +++ b/include/linux/rculist_bl.h @@ -20,7 +20,7 @@ static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h, static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h) { return (struct hlist_bl_node *) - ((unsigned long)rcu_dereference(h->first) & ~LIST_BL_LOCKMASK); + ((unsigned long)rcu_dereference_check(h->first, hlist_bl_is_locked(h)) & ~LIST_BL_LOCKMASK); } /** -- cgit v1.2.3 From e7b2dcc52b0e2d598a469f01cc460ccdde6869f2 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 12 Mar 2013 15:35:58 -0700 Subject: cgroup: remove cgroup_is_descendant() It was used by ns cgroup, and ns cgroup was removed long ago. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 5f76829dd75e..7e818a3ef60a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -448,9 +448,6 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen); int cgroup_task_count(const struct cgroup *cgrp); -/* Return true if cgrp is a descendant of the task's cgroup */ -int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task); - /* * Control Group taskset, used to pass around set of tasks to cgroup_subsys * methods. -- cgit v1.2.3 From e62676169118bc2d42e5008b3f8872646313f077 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Mar 2013 17:41:37 -0700 Subject: workqueue: implement current_is_workqueue_rescuer() Implement a function which queries whether it currently is running off a workqueue rescuer. This will be used to convert writeback to workqueue. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 7f6d29a417c0..df30763c8682 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -451,6 +451,7 @@ extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); +extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); -- cgit v1.2.3 From e86ac13b031cf71d8f40ff513e627aac80e6b765 Mon Sep 17 00:00:00 2001 From: Mugunthan V N Date: Mon, 11 Mar 2013 23:16:35 +0000 Subject: drivers: net: ethernet: cpsw: change cpts_active_slave to active_slave Change cpts_active_slave to active_slave so that the same DT property can be used to ethtool and SIOCGMIIPHY. CC: Richard Cochran Signed-off-by: Mugunthan V N Signed-off-by: David S. Miller --- include/linux/platform_data/cpsw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/cpsw.h b/include/linux/platform_data/cpsw.h index 798fb80b024b..bb3cd58d71e3 100644 --- a/include/linux/platform_data/cpsw.h +++ b/include/linux/platform_data/cpsw.h @@ -30,7 +30,7 @@ struct cpsw_platform_data { u32 channels; /* number of cpdma channels (symmetric) */ u32 slaves; /* number of slave cpgmac ports */ struct cpsw_slave_data *slave_data; - u32 cpts_active_slave; /* time stamping slave */ + u32 active_slave; /* time stamping, ethtool and SIOCGMIIPHY slave */ u32 cpts_clock_mult; /* convert input clock ticks to nanoseconds */ u32 cpts_clock_shift; /* convert input clock ticks to nanoseconds */ u32 ale_entries; /* ale table size */ -- cgit v1.2.3 From eaa907c546f76222227dfc41784b22588af1e3d7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 6 Mar 2013 11:18:36 +0000 Subject: tick: Provide a check for a forced broadcast pending On the CPU which gets woken along with the target CPU of the broadcast the following happens: deep_idle() <-- spurious wakeup broadcast_exit() set forced bit enable interrupts <-- Nothing happens disable interrupts broadcast_enter() <-- Here we observe the forced bit is set deep_idle() Now after that the target CPU of the broadcast runs the broadcast handler and finds the other CPU in both the broadcast and the forced mask, sends the IPI and stuff gets back to normal. So it's not actually harmful, just more evidence for the theory, that hardware designers have access to very special drug supplies. Now there is no point in going back to deep idle just to wake up again right away via an IPI. Provide a check which allows the idle code to avoid the deep idle transition. Signed-off-by: Thomas Gleixner Cc: LAK Cc: John Stultz Cc: Arjan van de Veen Cc: Lorenzo Pieralisi Tested-by: Santosh Shilimkar Cc: Jason Liu Link: http://lkml.kernel.org/r/20130306111537.565418308@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 494d33ea78f8..646aac136eed 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -175,6 +175,12 @@ extern void tick_broadcast(const struct cpumask *mask); extern int tick_receive_broadcast(void); #endif +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) +extern int tick_check_broadcast_expired(void); +#else +static inline int tick_check_broadcast_expired(void) { return 0; } +#endif + #ifdef CONFIG_GENERIC_CLOCKEVENTS extern void clockevents_notify(unsigned long reason, void *arg); #else -- cgit v1.2.3 From be871b7e54711479d3b9d3617d49898770830db2 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 12 Mar 2013 17:21:19 +0100 Subject: device: separate all subsys mutexes ca22e56d (driver-core: implement 'sysdev' functionality for regular devices and buses) has introduced bus_register macro with a static key to distinguish different subsys mutex classes. This however doesn't work for different subsys which use a common registering function. One example is subsys_system_register (and mce_device and cpu_device). In the end this leads to the following lockdep splat: [ 207.271924] ====================================================== [ 207.271932] [ INFO: possible circular locking dependency detected ] [ 207.271942] 3.9.0-rc1-0.7-default+ #34 Not tainted [ 207.271948] ------------------------------------------------------- [ 207.271957] bash/10493 is trying to acquire lock: [ 207.271963] (subsys mutex){+.+.+.}, at: [] bus_remove_device+0x37/0x1c0 [ 207.271987] [ 207.271987] but task is already holding lock: [ 207.271995] (cpu_hotplug.lock){+.+.+.}, at: [] cpu_hotplug_begin+0x2f/0x60 [ 207.272012] [ 207.272012] which lock already depends on the new lock. [ 207.272012] [ 207.272023] [ 207.272023] the existing dependency chain (in reverse order) is: [ 207.272033] [ 207.272033] -> #4 (cpu_hotplug.lock){+.+.+.}: [ 207.272044] [] lock_acquire+0xe9/0x120 [ 207.272056] [] mutex_lock_nested+0x37/0x360 [ 207.272069] [] get_online_cpus+0x29/0x40 [ 207.272082] [] drain_all_stock+0x30/0x150 [ 207.272094] [] mem_cgroup_reclaim+0xaa/0xe0 [ 207.272104] [] __mem_cgroup_try_charge+0x51e/0xcf0 [ 207.272114] [] mem_cgroup_charge_common+0x36/0x60 [ 207.272125] [] mem_cgroup_newpage_charge+0x2a/0x30 [ 207.272135] [] do_wp_page+0x231/0x830 [ 207.272147] [] handle_pte_fault+0x19e/0x8d0 [ 207.272157] [] handle_mm_fault+0x158/0x1e0 [ 207.272166] [] do_page_fault+0x2a3/0x4e0 [ 207.272178] [] page_fault+0x28/0x30 [ 207.272189] [ 207.272189] -> #3 (&mm->mmap_sem){++++++}: [ 207.272199] [] lock_acquire+0xe9/0x120 [ 207.272208] [] might_fault+0x6d/0x90 [ 207.272218] [] filldir64+0xb3/0x120 [ 207.272229] [] call_filldir+0x89/0x130 [ext3] [ 207.272248] [] ext3_readdir+0x6b7/0x7e0 [ext3] [ 207.272263] [] vfs_readdir+0xa9/0xc0 [ 207.272273] [] sys_getdents64+0x9b/0x110 [ 207.272284] [] system_call_fastpath+0x16/0x1b [ 207.272296] [ 207.272296] -> #2 (&type->i_mutex_dir_key#3){+.+.+.}: [ 207.272309] [] lock_acquire+0xe9/0x120 [ 207.272319] [] mutex_lock_nested+0x37/0x360 [ 207.272329] [] link_path_walk+0x6f4/0x9a0 [ 207.272339] [] path_openat+0xba/0x470 [ 207.272349] [] do_filp_open+0x48/0xa0 [ 207.272358] [] file_open_name+0xdc/0x110 [ 207.272369] [] filp_open+0x35/0x40 [ 207.272378] [] _request_firmware+0x52e/0xb20 [ 207.272389] [] request_firmware+0x16/0x20 [ 207.272399] [] request_microcode_fw+0x61/0xd0 [microcode] [ 207.272416] [] microcode_init_cpu+0x104/0x150 [microcode] [ 207.272431] [] mc_device_add+0x7c/0xb0 [microcode] [ 207.272444] [] subsys_interface_register+0xc9/0x100 [ 207.272457] [] 0xffffffffa04fc0f4 [ 207.272472] [] do_one_initcall+0x42/0x180 [ 207.272485] [] load_module+0x19df/0x1b70 [ 207.272499] [] sys_init_module+0xe6/0x130 [ 207.272511] [] system_call_fastpath+0x16/0x1b [ 207.272523] [ 207.272523] -> #1 (umhelper_sem){++++.+}: [ 207.272537] [] lock_acquire+0xe9/0x120 [ 207.272548] [] down_read+0x34/0x50 [ 207.272559] [] usermodehelper_read_trylock+0x4f/0x100 [ 207.272575] [] _request_firmware+0x59d/0xb20 [ 207.272587] [] request_firmware+0x16/0x20 [ 207.272599] [] request_microcode_fw+0x61/0xd0 [microcode] [ 207.272613] [] microcode_init_cpu+0x104/0x150 [microcode] [ 207.272627] [] mc_device_add+0x7c/0xb0 [microcode] [ 207.272641] [] subsys_interface_register+0xc9/0x100 [ 207.272654] [] 0xffffffffa04fc0f4 [ 207.272666] [] do_one_initcall+0x42/0x180 [ 207.272678] [] load_module+0x19df/0x1b70 [ 207.272690] [] sys_init_module+0xe6/0x130 [ 207.272702] [] system_call_fastpath+0x16/0x1b [ 207.272715] [ 207.272715] -> #0 (subsys mutex){+.+.+.}: [ 207.272729] [] __lock_acquire+0x13b2/0x15f0 [ 207.272740] [] lock_acquire+0xe9/0x120 [ 207.272751] [] mutex_lock_nested+0x37/0x360 [ 207.272763] [] bus_remove_device+0x37/0x1c0 [ 207.272775] [] device_del+0x134/0x1f0 [ 207.272786] [] device_unregister+0x22/0x60 [ 207.272798] [] mce_cpu_callback+0x15e/0x1ad [ 207.272812] [] notifier_call_chain+0x72/0x130 [ 207.272824] [] __raw_notifier_call_chain+0xe/0x10 [ 207.272839] [] _cpu_down+0x1d6/0x350 [ 207.272851] [] cpu_down+0x40/0x60 [ 207.272862] [] store_online+0x75/0xe0 [ 207.272874] [] dev_attr_store+0x20/0x30 [ 207.272886] [] sysfs_write_file+0xd9/0x150 [ 207.272900] [] vfs_write+0xcb/0x130 [ 207.272911] [] sys_write+0x64/0xa0 [ 207.272923] [] system_call_fastpath+0x16/0x1b [ 207.272936] [ 207.272936] other info that might help us debug this: [ 207.272936] [ 207.272952] Chain exists of: [ 207.272952] subsys mutex --> &mm->mmap_sem --> cpu_hotplug.lock [ 207.272952] [ 207.272973] Possible unsafe locking scenario: [ 207.272973] [ 207.272984] CPU0 CPU1 [ 207.272992] ---- ---- [ 207.273000] lock(cpu_hotplug.lock); [ 207.273009] lock(&mm->mmap_sem); [ 207.273020] lock(cpu_hotplug.lock); [ 207.273031] lock(subsys mutex); [ 207.273040] [ 207.273040] *** DEADLOCK *** [ 207.273040] [ 207.273055] 5 locks held by bash/10493: [ 207.273062] #0: (&buffer->mutex){+.+.+.}, at: [] sysfs_write_file+0x49/0x150 [ 207.273080] #1: (s_active#150){.+.+.+}, at: [] sysfs_write_file+0xc2/0x150 [ 207.273099] #2: (x86_cpu_hotplug_driver_mutex){+.+.+.}, at: [] cpu_hotplug_driver_lock+0x17/0x20 [ 207.273121] #3: (cpu_add_remove_lock){+.+.+.}, at: [] cpu_down+0x2c/0x60 [ 207.273140] #4: (cpu_hotplug.lock){+.+.+.}, at: [] cpu_hotplug_begin+0x2f/0x60 [ 207.273158] [ 207.273158] stack backtrace: [ 207.273170] Pid: 10493, comm: bash Not tainted 3.9.0-rc1-0.7-default+ #34 [ 207.273180] Call Trace: [ 207.273192] [] print_circular_bug+0x223/0x310 [ 207.273204] [] __lock_acquire+0x13b2/0x15f0 [ 207.273216] [] ? sysfs_hash_and_remove+0x60/0xc0 [ 207.273227] [] lock_acquire+0xe9/0x120 [ 207.273239] [] ? bus_remove_device+0x37/0x1c0 [ 207.273251] [] mutex_lock_nested+0x37/0x360 [ 207.273263] [] ? bus_remove_device+0x37/0x1c0 [ 207.273274] [] ? sysfs_hash_and_remove+0x60/0xc0 [ 207.273286] [] bus_remove_device+0x37/0x1c0 [ 207.273298] [] device_del+0x134/0x1f0 [ 207.273309] [] device_unregister+0x22/0x60 [ 207.273321] [] mce_cpu_callback+0x15e/0x1ad [ 207.273332] [] notifier_call_chain+0x72/0x130 [ 207.273344] [] __raw_notifier_call_chain+0xe/0x10 [ 207.273356] [] _cpu_down+0x1d6/0x350 [ 207.273368] [] ? cpu_hotplug_driver_lock+0x17/0x20 [ 207.273380] [] cpu_down+0x40/0x60 [ 207.273391] [] store_online+0x75/0xe0 [ 207.273402] [] dev_attr_store+0x20/0x30 [ 207.273413] [] sysfs_write_file+0xd9/0x150 [ 207.273425] [] vfs_write+0xcb/0x130 [ 207.273436] [] sys_write+0x64/0xa0 [ 207.273447] [] system_call_fastpath+0x16/0x1b Which reports a false possitive deadlock because it sees: 1) load_module -> subsys_interface_register -> mc_deveice_add (*) -> subsys->p->mutex -> link_path_walk -> lookup_slow -> i_mutex 2) sys_write -> _cpu_down -> cpu_hotplug_begin -> cpu_hotplug.lock -> mce_cpu_callback -> mce_device_remove(**) -> device_unregister -> bus_remove_device -> subsys mutex 3) vfs_readdir -> i_mutex -> filldir64 -> might_fault -> might_lock_read(mmap_sem) -> page_fault -> mmap_sem -> drain_all_stock -> cpu_hotplug.lock but 1) takes cpu_subsys subsys (*) but 2) takes mce_device subsys (**) so the deadlock is not possible AFAICS. The fix is quite simple. We can pull the key inside bus_type structure because they are defined per device so the pointer will be unique as well. bus_register doesn't need to be a macro anymore so change it to the inline. We could get rid of __bus_register as there is no other caller but maybe somebody will want to use a different key so keep it around for now. Reported-by: Li Zefan Signed-off-by: Michal Hocko Signed-off-by: Jiri Kosina Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 9d6464ea99c6..4a7c4a84afee 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -111,17 +111,11 @@ struct bus_type { struct iommu_ops *iommu_ops; struct subsys_private *p; + struct lock_class_key lock_key; }; -/* This is a #define to keep the compiler from merging different - * instances of the __key variable */ -#define bus_register(subsys) \ -({ \ - static struct lock_class_key __key; \ - __bus_register(subsys, &__key); \ -}) -extern int __must_check __bus_register(struct bus_type *bus, - struct lock_class_key *key); +extern int __must_check bus_register(struct bus_type *bus); + extern void bus_unregister(struct bus_type *bus); extern int __must_check bus_rescan_devices(struct bus_type *bus); -- cgit v1.2.3 From f792685006274a850e6cc0ea9ade275ccdfc90bc Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 5 Mar 2013 18:05:46 +0100 Subject: math64: New div64_u64_rem helper Provide an extended version of div64_u64() that also returns the remainder of the division. We are going to need this to refine the cputime scaling code. Signed-off-by: Frederic Weisbecker Cc: Stanislaw Gruszka Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Andrew Morton --- include/linux/math64.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index b8ba85544721..931a619407bf 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -29,6 +29,15 @@ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder) return dividend / divisor; } +/** + * div64_u64_rem - unsigned 64bit divide with 64bit divisor + */ +static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder) +{ + *remainder = dividend % divisor; + return dividend / divisor; +} + /** * div64_u64 - unsigned 64bit divide with 64bit divisor */ @@ -61,8 +70,16 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) extern s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder); #endif +#ifndef div64_u64_rem +extern u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder); +#endif + #ifndef div64_u64 -extern u64 div64_u64(u64 dividend, u64 divisor); +static inline u64 div64_u64(u64 dividend, u64 divisor) +{ + u64 remainder; + return div64_u64_rem(dividend, divisor, &remainder); +} #endif #ifndef div64_s64 -- cgit v1.2.3 From 8425e3d5bdbe8e741d2c73cf3189ed59b4038b84 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 13 Mar 2013 16:51:36 -0700 Subject: workqueue: inline trivial wrappers There's no reason to make these trivial wrappers full (exported) functions. Inline the followings. queue_work() queue_delayed_work() mod_delayed_work() schedule_work_on() schedule_work() schedule_delayed_work_on() schedule_delayed_work() keventd_up() Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 123 +++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 111 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index df30763c8682..835d12b76960 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -417,28 +417,16 @@ int apply_workqueue_attrs(struct workqueue_struct *wq, extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); -extern bool queue_work(struct workqueue_struct *wq, struct work_struct *work); extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); -extern bool queue_delayed_work(struct workqueue_struct *wq, - struct delayed_work *work, unsigned long delay); extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); -extern bool mod_delayed_work(struct workqueue_struct *wq, - struct delayed_work *dwork, unsigned long delay); extern void flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern void flush_scheduled_work(void); -extern bool schedule_work_on(int cpu, struct work_struct *work); -extern bool schedule_work(struct work_struct *work); -extern bool schedule_delayed_work_on(int cpu, struct delayed_work *work, - unsigned long delay); -extern bool schedule_delayed_work(struct delayed_work *work, - unsigned long delay); extern int schedule_on_each_cpu(work_func_t func); -extern int keventd_up(void); int execute_in_process_context(work_func_t fn, struct execute_work *); @@ -455,6 +443,117 @@ extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); +/** + * queue_work - queue work on a workqueue + * @wq: workqueue to use + * @work: work to queue + * + * Returns %false if @work was already on a queue, %true otherwise. + * + * We queue the work to the CPU on which it was submitted, but if the CPU dies + * it can be processed by another CPU. + */ +static inline bool queue_work(struct workqueue_struct *wq, + struct work_struct *work) +{ + return queue_work_on(WORK_CPU_UNBOUND, wq, work); +} + +/** + * queue_delayed_work - queue work on a workqueue after delay + * @wq: workqueue to use + * @dwork: delayable work to queue + * @delay: number of jiffies to wait before queueing + * + * Equivalent to queue_delayed_work_on() but tries to use the local CPU. + */ +static inline bool queue_delayed_work(struct workqueue_struct *wq, + struct delayed_work *dwork, + unsigned long delay) +{ + return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); +} + +/** + * mod_delayed_work - modify delay of or queue a delayed work + * @wq: workqueue to use + * @dwork: work to queue + * @delay: number of jiffies to wait before queueing + * + * mod_delayed_work_on() on local CPU. + */ +static inline bool mod_delayed_work(struct workqueue_struct *wq, + struct delayed_work *dwork, + unsigned long delay) +{ + return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); +} + +/** + * schedule_work_on - put work task on a specific cpu + * @cpu: cpu to put the work task on + * @work: job to be done + * + * This puts a job on a specific cpu + */ +static inline bool schedule_work_on(int cpu, struct work_struct *work) +{ + return queue_work_on(cpu, system_wq, work); +} + +/** + * schedule_work - put work task in global workqueue + * @work: job to be done + * + * Returns %false if @work was already on the kernel-global workqueue and + * %true otherwise. + * + * This puts a job in the kernel-global workqueue if it was not already + * queued and leaves it in the same position on the kernel-global + * workqueue otherwise. + */ +static inline bool schedule_work(struct work_struct *work) +{ + return queue_work(system_wq, work); +} + +/** + * schedule_delayed_work_on - queue work in global workqueue on CPU after delay + * @cpu: cpu to use + * @dwork: job to be done + * @delay: number of jiffies to wait + * + * After waiting for a given time this puts a job in the kernel-global + * workqueue on the specified CPU. + */ +static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, + unsigned long delay) +{ + return queue_delayed_work_on(cpu, system_wq, dwork, delay); +} + +/** + * schedule_delayed_work - put work task in global workqueue after delay + * @dwork: job to be done + * @delay: number of jiffies to wait or 0 for immediate execution + * + * After waiting for a given time this puts a job in the kernel-global + * workqueue. + */ +static inline bool schedule_delayed_work(struct delayed_work *dwork, + unsigned long delay) +{ + return queue_delayed_work(system_wq, dwork, delay); +} + +/** + * keventd_up - is workqueue initialized yet? + */ +static inline bool keventd_up(void) +{ + return system_wq != NULL; +} + /* * Like above, but uses del_timer() instead of del_timer_sync(). This means, * if it returns 0 the timer function may be running and the queueing is in -- cgit v1.2.3 From ae63b31e4d0e2ec09c569306ea46f664508ef717 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 3 May 2012 23:09:03 -0400 Subject: tracing: Separate out trace events from global variables The trace events for ftrace are all defined via global variables. The arrays of events and event systems are linked to a global list. This prevents multiple users of the event system (what to enable and what not to). By adding descriptors to represent the event/file relation, as well as to which trace_array descriptor they are associated with, allows for more than one set of events to be defined. Once the trace events files have a link between the trace event and the trace_array they are associated with, we can create multiple trace_arrays that can record separate events in separate buffers. Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 51 ++++++++++++++++++++++++++++++++++---------- 1 file changed, 40 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 13a54d0bdfa8..c7191d482f98 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -182,18 +182,20 @@ extern int ftrace_event_reg(struct ftrace_event_call *event, enum trace_reg type, void *data); enum { - TRACE_EVENT_FL_ENABLED_BIT, TRACE_EVENT_FL_FILTERED_BIT, - TRACE_EVENT_FL_RECORDED_CMD_BIT, TRACE_EVENT_FL_CAP_ANY_BIT, TRACE_EVENT_FL_NO_SET_FILTER_BIT, TRACE_EVENT_FL_IGNORE_ENABLE_BIT, }; +/* + * Event flags: + * FILTERED - The event has a filter attached + * CAP_ANY - Any user can enable for perf + * NO_SET_FILTER - Set when filter has error and is to be ignored + */ enum { - TRACE_EVENT_FL_ENABLED = (1 << TRACE_EVENT_FL_ENABLED_BIT), TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), - TRACE_EVENT_FL_RECORDED_CMD = (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT), TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), TRACE_EVENT_FL_NO_SET_FILTER = (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT), TRACE_EVENT_FL_IGNORE_ENABLE = (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT), @@ -203,12 +205,44 @@ struct ftrace_event_call { struct list_head list; struct ftrace_event_class *class; char *name; - struct dentry *dir; struct trace_event event; const char *print_fmt; struct event_filter *filter; + struct list_head *files; void *mod; void *data; + int flags; /* static flags of different events */ + +#ifdef CONFIG_PERF_EVENTS + int perf_refcount; + struct hlist_head __percpu *perf_events; +#endif +}; + +struct trace_array; +struct ftrace_subsystem_dir; + +enum { + FTRACE_EVENT_FL_ENABLED_BIT, + FTRACE_EVENT_FL_RECORDED_CMD_BIT, +}; + +/* + * Ftrace event file flags: + * ENABELD - The event is enabled + * RECORDED_CMD - The comms should be recorded at sched_switch + */ +enum { + FTRACE_EVENT_FL_ENABLED = (1 << FTRACE_EVENT_FL_ENABLED_BIT), + FTRACE_EVENT_FL_RECORDED_CMD = (1 << FTRACE_EVENT_FL_RECORDED_CMD_BIT), +}; + +struct ftrace_event_file { + struct list_head list; + struct ftrace_event_call *event_call; + struct dentry *dir; + struct trace_array *tr; + struct ftrace_subsystem_dir *system; /* * 32 bit flags: @@ -223,17 +257,12 @@ struct ftrace_event_call { * * Note: Reads of flags do not hold the event_mutex since * they occur in critical sections. But the way flags - * is currently used, these changes do no affect the code + * is currently used, these changes do not affect the code * except that when a change is made, it may have a slight * delay in propagating the changes to other CPUs due to * caching and such. */ unsigned int flags; - -#ifdef CONFIG_PERF_EVENTS - int perf_refcount; - struct hlist_head __percpu *perf_events; -#endif }; #define __TRACE_EVENT_FLAGS(name, value) \ -- cgit v1.2.3 From ccb469a198cffac94a7eea0b69f715f06e2ddf15 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 2 Aug 2012 10:32:10 -0400 Subject: tracing: Pass the ftrace_file to the buffer lock reserve code Pass the struct ftrace_event_file *ftrace_file to the trace_event_buffer_lock_reserve() (new function that replaces the trace_current_buffer_lock_reserver()). The ftrace_file holds a pointer to the trace_array that is in use. In the case of multiple buffers with different trace_arrays, this allows different events to be recorded into different buffers. Also fixed some of the stale comments in include/trace/ftrace.h Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index c7191d482f98..fd28c170c597 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -128,6 +128,13 @@ enum print_line_t { void tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, int pc); +struct ftrace_event_file; + +struct ring_buffer_event * +trace_event_buffer_lock_reserve(struct ring_buffer **current_buffer, + struct ftrace_event_file *ftrace_file, + int type, unsigned long len, + unsigned long flags, int pc); struct ring_buffer_event * trace_current_buffer_lock_reserve(struct ring_buffer **current_buffer, int type, unsigned long len, -- cgit v1.2.3 From 15693458c4bc0693fd63a50d60f35b628fcf4e29 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Thu, 28 Feb 2013 19:59:17 -0500 Subject: tracing/ring-buffer: Move poll wake ups into ring buffer code Move the logic to wake up on ring buffer data into the ring buffer code itself. This simplifies the tracing code a lot and also has the added benefit that waiters on one of the instance buffers can be woken only when data is added to that instance instead of data added to any instance. Signed-off-by: Steven Rostedt --- include/linux/ring_buffer.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 1342e69542f3..d69cf637a15a 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -4,6 +4,7 @@ #include #include #include +#include struct ring_buffer; struct ring_buffer_iter; @@ -96,6 +97,11 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) +void ring_buffer_wait(struct ring_buffer *buffer, int cpu); +int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, + struct file *filp, poll_table *poll_table); + + #define RING_BUFFER_ALL_CPUS -1 void ring_buffer_free(struct ring_buffer *buffer); -- cgit v1.2.3 From f71130de5c7fba92faf3901784714e37a234c08f Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Thu, 21 Feb 2013 10:32:38 +0800 Subject: tracing: Add a helper function for event print functions Move duplicate code in event print functions to a helper function. This shrinks the size of the kernel by ~13K. text data bss dec hex filename 6596137 1743966 10138672 18478775 119f6b7 vmlinux.o.old 6583002 1743849 10138672 18465523 119c2f3 vmlinux.o.new Link: http://lkml.kernel.org/r/51258746.2060304@huawei.com Signed-off-by: Li Zefan Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index fd28c170c597..4d79d2dc189c 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -38,6 +38,12 @@ const char *ftrace_print_symbols_seq_u64(struct trace_seq *p, const char *ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int len); +struct trace_iterator; +struct trace_event; + +int ftrace_raw_output_prep(struct trace_iterator *iter, + struct trace_event *event); + /* * The trace entry - the most basic unit of tracing. This is what * is printed in the end as a single line in the trace output, such as: @@ -95,8 +101,6 @@ enum trace_iter_flags { }; -struct trace_event; - typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter, int flags, struct trace_event *event); -- cgit v1.2.3 From 2a30c11f6a037e2475f3c651bc57e697e79fa963 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 4 Mar 2013 22:27:04 -0500 Subject: tracing: Add comment for trace event flag IGNORE_ENABLE All the trace event flags have comments but the IGNORE_ENABLE flag which is set for ftrace internal events that should not be enabled via the debugfs "enable" file. That is, if the top level enable file is set, it will enable all events. It use to just check the ftrace event call descriptor "reg" field and skip those whithout it, but now some ftrace internal events have a reg field but still need to be skipped. The flag was created to ignore those events. Now document it. Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 4d79d2dc189c..0b0814d90164 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -204,6 +204,7 @@ enum { * FILTERED - The event has a filter attached * CAP_ANY - Any user can enable for perf * NO_SET_FILTER - Set when filter has error and is to be ignored + * IGNORE_ENABLE - For ftrace internal events, do not enable with debugfs file */ enum { TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), -- cgit v1.2.3 From 575380da8b46969a2c6a7e14a51056a63b30fe2e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 4 Mar 2013 23:05:12 -0500 Subject: tracing: Only clear trace buffer on module unload if event was traced Currently, when a module with events is unloaded, the trace buffer is cleared. This is just a safety net in case the module might have some strange callback when its event is outputted. But there's no reason to reset the buffer if the module didn't have any of its events traced. Add a flag to the event "call" structure called WAS_ENABLED and gets set when the event is ever enabled, and this flag never gets cleared. When a module gets unloaded, if any of its events have this flag set, then the trace buffer will get cleared. Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 0b0814d90164..d6964244e567 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -197,6 +197,7 @@ enum { TRACE_EVENT_FL_CAP_ANY_BIT, TRACE_EVENT_FL_NO_SET_FILTER_BIT, TRACE_EVENT_FL_IGNORE_ENABLE_BIT, + TRACE_EVENT_FL_WAS_ENABLED_BIT, }; /* @@ -205,12 +206,16 @@ enum { * CAP_ANY - Any user can enable for perf * NO_SET_FILTER - Set when filter has error and is to be ignored * IGNORE_ENABLE - For ftrace internal events, do not enable with debugfs file + * WAS_ENABLED - Set and stays set when an event was ever enabled + * (used for module unloading, if a module event is enabled, + * it is best to clear the buffers that used it). */ enum { TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), TRACE_EVENT_FL_NO_SET_FILTER = (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT), TRACE_EVENT_FL_IGNORE_ENABLE = (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT), + TRACE_EVENT_FL_WAS_ENABLED = (1 << TRACE_EVENT_FL_WAS_ENABLED_BIT), }; struct ftrace_event_call { -- cgit v1.2.3 From 12883efb670c28dff57dcd7f4f995a1ffe153b2d Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 5 Mar 2013 09:24:35 -0500 Subject: tracing: Consolidate max_tr into main trace_array structure Currently, the way the latency tracers and snapshot feature works is to have a separate trace_array called "max_tr" that holds the snapshot buffer. For latency tracers, this snapshot buffer is used to swap the running buffer with this buffer to save the current max latency. The only items needed for the max_tr is really just a copy of the buffer itself, the per_cpu data pointers, the time_start timestamp that states when the max latency was triggered, and the cpu that the max latency was triggered on. All other fields in trace_array are unused by the max_tr, making the max_tr mostly bloat. This change removes the max_tr completely, and adds a new structure called trace_buffer, that holds the buffer pointer, the per_cpu data pointers, the time_start timestamp, and the cpu where the latency occurred. The trace_array, now has two trace_buffers, one for the normal trace and one for the max trace or snapshot. By doing this, not only do we remove the bloat from the max_trace but the instances of traces can now use their own snapshot feature and not have just the top level global_trace have the snapshot feature and latency tracers for itself. Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index d6964244e567..d84c4a575514 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -8,6 +8,7 @@ #include struct trace_array; +struct trace_buffer; struct tracer; struct dentry; @@ -67,6 +68,7 @@ struct trace_entry { struct trace_iterator { struct trace_array *tr; struct tracer *trace; + struct trace_buffer *trace_buffer; void *private; int cpu_file; struct mutex mutex; -- cgit v1.2.3 From ad909e21bbe69f1d39055d346540abd827190eca Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 6 Mar 2013 21:45:37 -0500 Subject: tracing: Add internal tracing_snapshot() functions The new snapshot feature is quite handy. It's a way for the user to take advantage of the spare buffer that, until then, only the latency tracers used to "snapshot" the buffer when it hit a max latency. Now users can trigger a "snapshot" manually when some condition is hit in a program. But a snapshot currently can not be triggered by a condition inside the kernel. With the addition of tracing_snapshot() and tracing_snapshot_alloc(), snapshots can now be taking when a condition is hit, and the developer wants to snapshot the case without stopping the trace. Note, any snapshot will overwrite the old one, so take care in how this is done. These new functions are to be used like tracing_on(), tracing_off() and trace_printk() are. That is, they should never be called in the mainline Linux kernel. They are solely for the purpose of debugging. The tracing_snapshot() will not allocate a buffer, but it is safe to be called from any context (except NMIs). But if a snapshot buffer isn't allocated when it is called, it will write to the live buffer, complaining about the lack of a snapshot buffer, and then stop tracing (giving you the "permanent snapshot"). tracing_snapshot_alloc() will allocate the snapshot buffer if it was not already allocated and then take the snapshot. This routine *may sleep*, and must be called from context that can sleep. The allocation is done with GFP_KERNEL and not atomic. If you need a snapshot in an atomic context, say in early boot, then it is best to call the tracing_snapshot_alloc() before then, where it will allocate the buffer, and then you can use the tracing_snapshot() anywhere you want and still get snapshots. Cc: Hiraku Toyooka Cc: Thomas Gleixner Cc: Peter Zijlstra Signed-off-by: Steven Rostedt --- include/linux/kernel.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index c566927efcbd..bc5392a326ab 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -483,6 +483,8 @@ enum ftrace_dump_mode { void tracing_on(void); void tracing_off(void); int tracing_is_on(void); +void tracing_snapshot(void); +void tracing_snapshot_alloc(void); extern void tracing_start(void); extern void tracing_stop(void); @@ -570,6 +572,8 @@ static inline void trace_dump_stack(void) { } static inline void tracing_on(void) { } static inline void tracing_off(void) { } static inline int tracing_is_on(void) { return 0; } +static inline void tracing_snapshot(void) { } +static inline void tracing_snapshot_alloc(void) { } static inline __printf(1, 2) int trace_printk(const char *fmt, ...) -- cgit v1.2.3 From 09ae72348eccb60e304cf8ce94653f4a78fcd407 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 8 Mar 2013 21:02:34 -0500 Subject: tracing: Add trace_puts() for even faster trace_printk() tracing The trace_printk() is extremely fast and is very handy as it can be used in any context (including NMIs!). But it still requires scanning the fmt string for parsing the args. Even the trace_bprintk() requires a scan to know what args will be saved, although it doesn't copy the format string itself. Several times trace_printk() has no args, and wastes cpu cycles scanning the fmt string. Adding trace_puts() allows the developer to use an even faster tracing method that only saves the pointer to the string in the ring buffer without doing any format parsing at all. This will help remove even more of the "Heisenbug" effect, when debugging. Also fixed up the F_printk()s for the ftrace internal bprint and print events. Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Frederic Weisbecker Signed-off-by: Steven Rostedt --- include/linux/kernel.h | 41 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 40 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index bc5392a326ab..a3a5574a61fc 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -514,7 +514,8 @@ do { \ * * This is intended as a debugging tool for the developer only. * Please refrain from leaving trace_printks scattered around in - * your code. + * your code. (Extra memory is used for special buffers that are + * allocated when trace_printk() is used) */ #define trace_printk(fmt, args...) \ @@ -537,6 +538,44 @@ int __trace_bprintk(unsigned long ip, const char *fmt, ...); extern __printf(2, 3) int __trace_printk(unsigned long ip, const char *fmt, ...); +/** + * trace_puts - write a string into the ftrace buffer + * @str: the string to record + * + * Note: __trace_bputs is an internal function for trace_puts and + * the @ip is passed in via the trace_puts macro. + * + * This is similar to trace_printk() but is made for those really fast + * paths that a developer wants the least amount of "Heisenbug" affects, + * where the processing of the print format is still too much. + * + * This function allows a kernel developer to debug fast path sections + * that printk is not appropriate for. By scattering in various + * printk like tracing in the code, a developer can quickly see + * where problems are occurring. + * + * This is intended as a debugging tool for the developer only. + * Please refrain from leaving trace_puts scattered around in + * your code. (Extra memory is used for special buffers that are + * allocated when trace_puts() is used) + * + * Returns: 0 if nothing was written, positive # if string was. + * (1 when __trace_bputs is used, strlen(str) when __trace_puts is used) + */ + +extern int __trace_bputs(unsigned long ip, const char *str); +extern int __trace_puts(unsigned long ip, const char *str, int size); +#define trace_puts(str) ({ \ + static const char *trace_printk_fmt \ + __attribute__((section("__trace_printk_fmt"))) = \ + __builtin_constant_p(str) ? str : NULL; \ + \ + if (__builtin_constant_p(str)) \ + __trace_bputs(_THIS_IP_, trace_printk_fmt); \ + else \ + __trace_puts(_THIS_IP_, str, strlen(str)); \ +}) + extern void trace_dump_stack(void); /* -- cgit v1.2.3 From 9d3c752c062e3266f1051ba0825276ea1e2777da Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 8 Mar 2013 22:11:57 -0500 Subject: tracing: Optimize trace_printk() with one arg to use trace_puts() Although trace_printk() is extremely fast, especially when it uses trace_bprintk() (writes args straight to buffer instead of inserting into string), it still has the overhead of calling one of the printf sprintf() functions, that need to scan the fmt string to determine what, if any args it has. This is a waste of precious CPU cycles if the printk format has no args but a single constant string. It is better to use trace_puts() which does not have the overhead of the fmt scanning. But wouldn't it be nice if the developer didn't have to think about such things, and the compile would just do it for them? trace_printk("this string has no args\n"); [...] trace_printk("this sting does %p %d\n", foo, bar); As tracing is critical to have the least amount of overhead, especially when dealing with race conditions, and you want to eliminate any "Heisenbugs", you want the trace_printk() to use the fastest possible means of tracing. Currently the macro magic determines if it will use trace_bprintk() or if the fmt is a dynamic string (a variable), it will fall back to the slow trace_printk() method that does a full snprintf() before copying it into the buffer, where as trace_bprintk() only copys the pointer to the fmt and the args into the buffer. Well, now there's a way to spend some more Hogwarts cash and come up with new fancy macro magic. #define trace_printk(fmt, ...) \ do { \ char _______STR[] = __stringify((__VA_ARGS__)); \ if (sizeof(_______STR) > 3) \ do_trace_printk(fmt, ##__VA_ARGS__); \ else \ trace_puts(fmt); \ } while (0) The above needs a bit of explaining (both here and in the comments). By stringifying the __VA_ARGS__, we can, at compile time, determine the number of args that are being passed to trace_printk(). The extra parenthesis are required, otherwise the compiler complains about too many parameters for __stringify if there is more than one arg. When there are no args, the __stringify((__VA_ARGS__)) converts into "()\0", a string of 3 characters. Anything else, will be a string containing more than 3 characters. Now we assign that string to a dynamic char array, and then take the sizeof() of that array. If it is greater than 3 characters, we know trace_printk() has args and we need to do the full "do_trace_printk()" on them, otherwise it was only passed a single arg and we can optimize to use trace_puts(). Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Frederic Weisbecker Signed-off-by: Steven "The King of Nasty Macros!" Rostedt --- include/linux/kernel.h | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index a3a5574a61fc..d0a16fe03fef 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -516,9 +516,30 @@ do { \ * Please refrain from leaving trace_printks scattered around in * your code. (Extra memory is used for special buffers that are * allocated when trace_printk() is used) + * + * A little optization trick is done here. If there's only one + * argument, there's no need to scan the string for printf formats. + * The trace_puts() will suffice. But how can we take advantage of + * using trace_puts() when trace_printk() has only one argument? + * By stringifying the args and checking the size we can tell + * whether or not there are args. __stringify((__VA_ARGS__)) will + * turn into "()\0" with a size of 3 when there are no args, anything + * else will be bigger. All we need to do is define a string to this, + * and then take its size and compare to 3. If it's bigger, use + * do_trace_printk() otherwise, optimize it to trace_puts(). Then just + * let gcc optimize the rest. */ -#define trace_printk(fmt, args...) \ +#define trace_printk(fmt, ...) \ +do { \ + char _______STR[] = __stringify((__VA_ARGS__)); \ + if (sizeof(_______STR) > 3) \ + do_trace_printk(fmt, ##__VA_ARGS__); \ + else \ + trace_puts(fmt); \ +} while (0) + +#define do_trace_printk(fmt, args...) \ do { \ static const char *trace_printk_fmt \ __attribute__((section("__trace_printk_fmt"))) = \ -- cgit v1.2.3 From 57d01ad09721fb7719c4c8c72b434398186f35a0 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 12 Mar 2013 12:38:06 -0400 Subject: tracing: Fix comments for ftrace_event_file/call flags Most of the flags for the struct ftrace_event_file were moved over to the flags of the struct ftrace_event_call, but the comments were never updated. Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index d84c4a575514..4cb6cd8338a4 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -230,6 +230,13 @@ struct ftrace_event_call { struct list_head *files; void *mod; void *data; + /* + * bit 0: filter_active + * bit 1: allow trace by non root (cap any) + * bit 2: failed to apply filter + * bit 3: ftrace internal event (do not enable) + * bit 4: Event was enabled by module + */ int flags; /* static flags of different events */ #ifdef CONFIG_PERF_EVENTS @@ -248,7 +255,7 @@ enum { /* * Ftrace event file flags: - * ENABELD - The event is enabled + * ENABLED - The event is enabled * RECORDED_CMD - The comms should be recorded at sched_switch */ enum { @@ -265,12 +272,8 @@ struct ftrace_event_file { /* * 32 bit flags: - * bit 1: enabled - * bit 2: filter_active - * bit 3: enabled cmd record - * bit 4: allow trace by non root (cap any) - * bit 5: failed to apply filter - * bit 6: ftrace internal event (do not enable) + * bit 0: enabled + * bit 1: enabled cmd record * * Changes to flags must hold the event_mutex. * -- cgit v1.2.3 From e67efb93f0e9130174293ffaa5975f87b301b531 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 12 Mar 2013 15:07:59 -0400 Subject: ftrace: Clean up function probe methods When a function probe is created, each function that the probe is attached to, a "callback" method is called. On release of the probe, each function entry calls the "free" method. First, "callback" is a confusing name and does not really match what it does. Callback sounds like it will be called when the probe triggers. But that's not the case. This is really an "init" function, so lets rename it as such. Secondly, both "init" and "free" do not pass enough information back to the handlers. Pass back the ops, ip and data for each time the method is called. We have the information, might as well use it. Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e5ca8ef50e9b..832422d706f4 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -259,8 +259,10 @@ struct ftrace_probe_ops { void (*func)(unsigned long ip, unsigned long parent_ip, void **data); - int (*callback)(unsigned long ip, void **data); - void (*free)(void **data); + int (*init)(struct ftrace_probe_ops *ops, + unsigned long ip, void **data); + void (*free)(struct ftrace_probe_ops *ops, + unsigned long ip, void **data); int (*print)(struct seq_file *m, unsigned long ip, struct ftrace_probe_ops *ops, -- cgit v1.2.3 From 417944c4c7a0f657158d0515f3b8e8c043fd788f Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 12 Mar 2013 13:26:18 -0400 Subject: tracing: Add a way to soft disable trace events In order to let triggers enable or disable events, we need a 'soft' method for doing so. For example, if a function probe is added that lets a user enable or disable events when a function is called, that change must be done without taking locks or a mutex, and definitely it can't sleep. But the full enabling of a tracepoint is expensive. By adding a 'SOFT_DISABLE' flag, and converting the flags to be updated without the protection of a mutex (using set/clear_bit()), this soft disable flag can be used to allow critical sections to enable or disable events from being traced (after the event has been placed into "SOFT_MODE"). Some caveats though: The comm recorder (to map pids with a comm) can not be soft disabled (yet). If you disable an event with with a "soft" disable and wait a while before reading the trace, the comm cache may be replaced and you'll get a bunch of <...> for comms in the trace. Reading the "enable" file for an event that is disabled will now give you "0*" where the '*' denotes that the tracepoint is still active but the event itself is "disabled". [ fixed _BIT used in & operation : thanks to Dan Carpenter and smatch ] Cc: Dan Carpenter Cc: Tom Zanussi Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 4cb6cd8338a4..4e28b011e63b 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -251,16 +251,23 @@ struct ftrace_subsystem_dir; enum { FTRACE_EVENT_FL_ENABLED_BIT, FTRACE_EVENT_FL_RECORDED_CMD_BIT, + FTRACE_EVENT_FL_SOFT_MODE_BIT, + FTRACE_EVENT_FL_SOFT_DISABLED_BIT, }; /* * Ftrace event file flags: * ENABLED - The event is enabled * RECORDED_CMD - The comms should be recorded at sched_switch + * SOFT_MODE - The event is enabled/disabled by SOFT_DISABLED + * SOFT_DISABLED - When set, do not trace the event (even though its + * tracepoint may be enabled) */ enum { FTRACE_EVENT_FL_ENABLED = (1 << FTRACE_EVENT_FL_ENABLED_BIT), FTRACE_EVENT_FL_RECORDED_CMD = (1 << FTRACE_EVENT_FL_RECORDED_CMD_BIT), + FTRACE_EVENT_FL_SOFT_MODE = (1 << FTRACE_EVENT_FL_SOFT_MODE_BIT), + FTRACE_EVENT_FL_SOFT_DISABLED = (1 << FTRACE_EVENT_FL_SOFT_DISABLED_BIT), }; struct ftrace_event_file { @@ -274,17 +281,18 @@ struct ftrace_event_file { * 32 bit flags: * bit 0: enabled * bit 1: enabled cmd record + * bit 2: enable/disable with the soft disable bit + * bit 3: soft disabled * - * Changes to flags must hold the event_mutex. - * - * Note: Reads of flags do not hold the event_mutex since - * they occur in critical sections. But the way flags + * Note: The bits must be set atomically to prevent races + * from other writers. Reads of flags do not need to be in + * sync as they occur in critical sections. But the way flags * is currently used, these changes do not affect the code * except that when a change is made, it may have a slight * delay in propagating the changes to other CPUs due to - * caching and such. + * caching and such. Which is mostly OK ;-) */ - unsigned int flags; + unsigned long flags; }; #define __TRACE_EVENT_FLAGS(name, value) \ -- cgit v1.2.3 From c142be8ebe0b7bf73c8a0063925623f3e4b980c0 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 13 Mar 2013 09:55:57 -0400 Subject: tracing: Add skip argument to trace_dump_stack() Altough the trace_dump_stack() already skips three functions in the call to stack trace, which gets the stack trace to start at the caller of the function, the caller may want to skip some more too (as it may have helper functions). Add a skip argument to the trace_dump_stack() that lets the caller skip back tracing functions that it doesn't care about. Signed-off-by: Steven Rostedt --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d0a16fe03fef..239dbb9627ca 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -597,7 +597,7 @@ extern int __trace_puts(unsigned long ip, const char *str, int size); __trace_puts(_THIS_IP_, str, strlen(str)); \ }) -extern void trace_dump_stack(void); +extern void trace_dump_stack(int skip); /* * The double __builtin_constant_p is because gcc will give us an error -- cgit v1.2.3 From 8aacf017b065a805d27467843490c976835eb4a5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Thu, 14 Mar 2013 13:13:45 -0400 Subject: tracing: Add "uptime" trace clock that uses jiffies Add a simple trace clock called "uptime" for those that are interested in the uptime of the trace. It uses jiffies as that's the safest method, as other uptime clocks grab seq locks, which could cause a deadlock if taken from an event or function tracer. Requested-by: Mauro Carvalho Chehab Cc: Thomas Gleixner Cc: Frederic Weisbecker Signed-off-by: Steven Rostedt --- include/linux/trace_clock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/trace_clock.h b/include/linux/trace_clock.h index d563f37e1a1d..1d7ca2739272 100644 --- a/include/linux/trace_clock.h +++ b/include/linux/trace_clock.h @@ -16,6 +16,7 @@ extern u64 notrace trace_clock_local(void); extern u64 notrace trace_clock(void); +extern u64 notrace trace_clock_jiffies(void); extern u64 notrace trace_clock_global(void); extern u64 notrace trace_clock_counter(void); -- cgit v1.2.3 From b92021b09df70c1609e3547f3d6128dd560be97f Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 15 Mar 2013 15:04:17 +1030 Subject: CONFIG_SYMBOL_PREFIX: cleanup. We have CONFIG_SYMBOL_PREFIX, which three archs define to the string "_". But Al Viro broke this in "consolidate cond_syscall and SYSCALL_ALIAS declarations" (in linux-next), and he's not the first to do so. Using CONFIG_SYMBOL_PREFIX is awkward, since we usually just want to prefix it so something. So various places define helpers which are defined to nothing if CONFIG_SYMBOL_PREFIX isn't set: 1) include/asm-generic/unistd.h defines __SYMBOL_PREFIX. 2) include/asm-generic/vmlinux.lds.h defines VMLINUX_SYMBOL(sym) 3) include/linux/export.h defines MODULE_SYMBOL_PREFIX. 4) include/linux/kernel.h defines SYMBOL_PREFIX (which differs from #7) 5) kernel/modsign_certificate.S defines ASM_SYMBOL(sym) 6) scripts/modpost.c defines MODULE_SYMBOL_PREFIX 7) scripts/Makefile.lib defines SYMBOL_PREFIX on the commandline if CONFIG_SYMBOL_PREFIX is set, so that we have a non-string version for pasting. (arch/h8300/include/asm/linkage.h defines SYMBOL_NAME(), too). Let's solve this properly: 1) No more generic prefix, just CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX. 2) Make linux/export.h usable from asm. 3) Define VMLINUX_SYMBOL() and VMLINUX_SYMBOL_STR(). 4) Make everyone use them. Signed-off-by: Rusty Russell Reviewed-by: James Hogan Tested-by: James Hogan (metag) --- include/linux/export.h | 20 ++++++++++++++------ include/linux/kernel.h | 7 ------- include/linux/module.h | 4 ++-- 3 files changed, 16 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/export.h b/include/linux/export.h index 696c0f48afc7..412cd509effe 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -5,17 +5,24 @@ * to reduce the amount of pointless cruft we feed to gcc when only * exporting a simple symbol or two. * - * If you feel the need to add #include to this file - * then you are doing something wrong and should go away silently. + * Try not to add #includes here. It slows compilation and makes kernel + * hackers place grumpy comments in header files. */ /* Some toolchains use a `_' prefix for all user symbols. */ -#ifdef CONFIG_SYMBOL_PREFIX -#define MODULE_SYMBOL_PREFIX CONFIG_SYMBOL_PREFIX +#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX +#define __VMLINUX_SYMBOL(x) _##x +#define __VMLINUX_SYMBOL_STR(x) "_" #x #else -#define MODULE_SYMBOL_PREFIX "" +#define __VMLINUX_SYMBOL(x) x +#define __VMLINUX_SYMBOL_STR(x) #x #endif +/* Indirect, so macros are expanded before pasting. */ +#define VMLINUX_SYMBOL(x) __VMLINUX_SYMBOL(x) +#define VMLINUX_SYMBOL_STR(x) __VMLINUX_SYMBOL_STR(x) + +#ifndef __ASSEMBLY__ struct kernel_symbol { unsigned long value; @@ -51,7 +58,7 @@ extern struct module __this_module; __CRC_SYMBOL(sym, sec) \ static const char __kstrtab_##sym[] \ __attribute__((section("__ksymtab_strings"), aligned(1))) \ - = MODULE_SYMBOL_PREFIX #sym; \ + = VMLINUX_SYMBOL_STR(sym); \ static const struct kernel_symbol __ksymtab_##sym \ __used \ __attribute__((section("___ksymtab" sec "+" #sym), unused)) \ @@ -85,5 +92,6 @@ extern struct module __this_module; #define EXPORT_UNUSED_SYMBOL_GPL(sym) #endif /* CONFIG_MODULES */ +#endif /* !__ASSEMBLY__ */ #endif /* _LINUX_EXPORT_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 80d36874689b..e13e992eae8a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -723,13 +723,6 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } /* Trap pasters of __FUNCTION__ at compile-time */ #define __FUNCTION__ (__func__) -/* This helps us to avoid #ifdef CONFIG_SYMBOL_PREFIX */ -#ifdef CONFIG_SYMBOL_PREFIX -#define SYMBOL_PREFIX CONFIG_SYMBOL_PREFIX -#else -#define SYMBOL_PREFIX "" -#endif - /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD diff --git a/include/linux/module.h b/include/linux/module.h index ead1b5719a12..46f1ea01e6f6 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -190,7 +190,7 @@ extern int modules_disabled; /* for sysctl */ /* Get/put a kernel symbol (calls must be symmetric) */ void *__symbol_get(const char *symbol); void *__symbol_get_gpl(const char *symbol); -#define symbol_get(x) ((typeof(&x))(__symbol_get(MODULE_SYMBOL_PREFIX #x))) +#define symbol_get(x) ((typeof(&x))(__symbol_get(VMLINUX_SYMBOL_STR(x)))) /* modules using other modules: kdb wants to see this. */ struct module_use { @@ -453,7 +453,7 @@ extern void __module_put_and_exit(struct module *mod, long code) #ifdef CONFIG_MODULE_UNLOAD unsigned long module_refcount(struct module *mod); void __symbol_put(const char *symbol); -#define symbol_put(x) __symbol_put(MODULE_SYMBOL_PREFIX #x) +#define symbol_put(x) __symbol_put(VMLINUX_SYMBOL_STR(x)) void symbol_put_addr(void *addr); /* Sometimes we know we already have a refcount, and it's easier not -- cgit v1.2.3 From 8a7fbfab4be39b8690543f3d29b26860d2f6c576 Mon Sep 17 00:00:00 2001 From: "nikolay@redhat.com" Date: Tue, 12 Mar 2013 02:49:01 +0000 Subject: netxen: write IP address to firmware when using bonding This patch allows LRO aggregation on bonded devices that contain an NX3031 device. It also adds a for_each_netdev_in_bond_rcu(bond, slave) macro which executes for each slave that has bond as master. V3: After testing and discussing this with Rajesh, I decided to keep the vlan ip cache and just rename it to ip_cache since it will store bond ip addresses too. A new master flag has been added to the ip cache to denote that the address has been added because of a master device. I've taken care of the enslave/release cases by checking for various combinations of events and flags (e.g. netxen has a master, it's a bond master and it's not marked as a slave means it is being enslaved and is dev_open()ed in bond_enslave). I've changed netxen_free_ip_list() to have a "master" parameter which causes all IP addresses marked as master to be deleted (used when a netxen is being released). I've made the patch use the new upper device API as well. The following cases were tested: - bond -> netxen - vlan -> netxen - vlan -> bond -> netxen V2: Remove local ip caching, retrieve addresses dynamically and restore them if necessary. Note: Tested with NX3031 adapter. Tested-by: Rajesh Borundia Signed-off-by: Andy Gospodarek Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e1ebeffa6b35..9fc1ab0c8914 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1617,6 +1617,9 @@ extern seqcount_t devnet_rename_seq; /* Device rename seq */ list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue_rcu(net, d) \ list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list) +#define for_each_netdev_in_bond_rcu(bond, slave) \ + for_each_netdev_rcu(&init_net, slave) \ + if (netdev_master_upper_dev_get_rcu(slave) == bond) #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) static inline struct net_device *next_net_device(struct net_device *dev) @@ -2774,6 +2777,11 @@ static inline void netif_set_gso_max_size(struct net_device *dev, dev->gso_max_size = size; } +static inline bool netif_is_bond_master(struct net_device *dev) +{ + return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING; +} + static inline bool netif_is_bond_slave(struct net_device *dev) { return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING; -- cgit v1.2.3 From 764444f5a324ad5a272773f078192819084388ce Mon Sep 17 00:00:00 2001 From: Fernando Luis Vazquez Cao Date: Wed, 13 Mar 2013 16:57:25 +0000 Subject: net: clean leftover of COMPAT_NET_DEV_OPS removal COMPAT_NET_DEV_OPS was removed a while back and with it the definition of netdev_resync_ops() went away. Let's finish the clean-up. Signed-off-by: Fernando Luis Vazquez Cao Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9fc1ab0c8914..56e3e0665272 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1692,7 +1692,6 @@ extern int netdev_refcnt_read(const struct net_device *dev); extern void free_netdev(struct net_device *dev); extern void synchronize_net(void); extern int init_dummy_netdev(struct net_device *dev); -extern void netdev_resync_ops(struct net_device *dev); extern struct net_device *dev_get_by_index(struct net *net, int ifindex); extern struct net_device *__dev_get_by_index(struct net *net, int ifindex); -- cgit v1.2.3 From dad3cab3e063110b3ae3dc82a00e7aacd09b91ec Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Mon, 4 Mar 2013 16:52:49 -0600 Subject: USB: fix trivial usb_device kernel-doc errors Fix trivial kernel-doc warnings: Warning(include/linux/usb.h:574): No description found for parameter 'usb3_lpm_enabled' Warning(include/linux/usb.h:574): Excess struct/union/enum/typedef member 'usb_classdev' description in 'usb_device' Warning(include/linux/usb.h:574): Excess struct/union/enum/typedef member 'usbfs_dentry' description in 'usb_device' Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Jiri Kosina Cc: linux-usb@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Nishanth Menon Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 4d22d0f6167a..52464fb2389b 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -469,14 +469,12 @@ struct usb3_lpm_parameters { * @lpm_capable: device supports LPM * @usb2_hw_lpm_capable: device can perform USB2 hardware LPM * @usb2_hw_lpm_enabled: USB2 hardware LPM enabled + * @usb3_lpm_enabled: USB3 hardware LPM enabled * @string_langid: language ID for strings * @product: iProduct string, if present (static) * @manufacturer: iManufacturer string, if present (static) * @serial: iSerialNumber string, if present (static) * @filelist: usbfs files that are open to this device - * @usb_classdev: USB class device that was created for usbfs device - * access from userspace - * @usbfs_dentry: usbfs dentry entry for the device * @maxchild: number of ports if hub * @quirks: quirks of the whole device * @urbnum: number of URBs submitted for the whole device -- cgit v1.2.3 From 96dd86fa588169b745a71aedf2070e80f4943623 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Fri, 15 Mar 2013 12:30:06 -0700 Subject: Drivers: hv: Add a new driver to support host initiated backup This driver supports host initiated backup of the guest. On Windows guests, the host can generate application consistent backups using the Windows VSS framework. On Linux, we ensure that the backup will be file system consistent. This driver allows the host to initiate a "Freeze" operation on all the mounted file systems in the guest. Once the mounted file systems in the guest are frozen, the host snapshots the guest's file systems. Once this is done, the guest's file systems are "thawed". This driver has a user-level component (daemon) that invokes the appropriate operation on all the mounted file systems in response to the requests from the host. The duration for which the guest is frozen is very short - a few seconds. During this interval, the diff disk is comitted. In this version of the patch I have addressed the feedback from Olaf Herring. Also, some of the connector related issues have been fixed. Signed-off-by: K. Y. Srinivasan Reviewed-by: Haiyang Zhang Cc: Evgeniy Polyakov Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index df77ba9a8166..95d0850584da 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -27,6 +27,63 @@ #include + +/* + * Implementation of host controlled snapshot of the guest. + */ + +#define VSS_OP_REGISTER 128 + +enum hv_vss_op { + VSS_OP_CREATE = 0, + VSS_OP_DELETE, + VSS_OP_HOT_BACKUP, + VSS_OP_GET_DM_INFO, + VSS_OP_BU_COMPLETE, + /* + * Following operations are only supported with IC version >= 5.0 + */ + VSS_OP_FREEZE, /* Freeze the file systems in the VM */ + VSS_OP_THAW, /* Unfreeze the file systems */ + VSS_OP_AUTO_RECOVER, + VSS_OP_COUNT /* Number of operations, must be last */ +}; + + +/* + * Header for all VSS messages. + */ +struct hv_vss_hdr { + __u8 operation; + __u8 reserved[7]; +} __attribute__((packed)); + + +/* + * Flag values for the hv_vss_check_feature. Linux supports only + * one value. + */ +#define VSS_HBU_NO_AUTO_RECOVERY 0x00000005 + +struct hv_vss_check_feature { + __u32 flags; +} __attribute__((packed)); + +struct hv_vss_check_dm_info { + __u32 flags; +} __attribute__((packed)); + +struct hv_vss_msg { + union { + struct hv_vss_hdr vss_hdr; + int error; + }; + union { + struct hv_vss_check_feature vss_cf; + struct hv_vss_check_dm_info dm_info; + }; +} __attribute__((packed)); + /* * An implementation of HyperV key value pair (KVP) functionality for Linux. * @@ -1252,6 +1309,14 @@ void vmbus_driver_unregister(struct hv_driver *hv_driver); 0xb9, 0x8b, 0x8b, 0xa1, 0xa1, 0xf3, 0xf9, 0x5a \ } +/* + * VSS (Backup/Restore) GUID + */ +#define HV_VSS_GUID \ + .guid = { \ + 0x29, 0x2e, 0xfa, 0x35, 0x23, 0xea, 0x36, 0x42, \ + 0x96, 0xae, 0x3a, 0x6e, 0xba, 0xcb, 0xa4, 0x40 \ + } /* * Common header for Hyper-V ICs */ @@ -1356,6 +1421,10 @@ int hv_kvp_init(struct hv_util_service *); void hv_kvp_deinit(void); void hv_kvp_onchannelcallback(void *); +int hv_vss_init(struct hv_util_service *); +void hv_vss_deinit(void); +void hv_vss_onchannelcallback(void *); + /* * Negotiated version with the Host. */ -- cgit v1.2.3 From fa882867ae5f8543eb304a1667563f1c99514475 Mon Sep 17 00:00:00 2001 From: Samuel Iglesias Gonsalvez Date: Fri, 8 Mar 2013 09:21:46 +0100 Subject: ipack: add ipack_get_device() ipack_put_device() Prepare everything for later use. Signed-off-by: Samuel Iglesias Gonsalvez Signed-off-by: Greg Kroah-Hartman --- include/linux/ipack.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipack.h b/include/linux/ipack.h index fea12cbb2aeb..def91fd996f4 100644 --- a/include/linux/ipack.h +++ b/include/linux/ipack.h @@ -221,6 +221,9 @@ void ipack_driver_unregister(struct ipack_driver *edrv); int ipack_device_register(struct ipack_device *dev); void ipack_device_unregister(struct ipack_device *dev); +void ipack_get_device(struct ipack_device *dev); +void ipack_put_device(struct ipack_device *dev); + /** * DEFINE_IPACK_DEVICE_TABLE - macro used to describe a IndustryPack table * @_table: device table name -- cgit v1.2.3 From e926301b39a07f587ff8c66354a2e2ee4c29162c Mon Sep 17 00:00:00 2001 From: Samuel Iglesias Gonsalvez Date: Fri, 8 Mar 2013 09:21:47 +0100 Subject: ipack: split ipack_device_register() in several functions One function is ipack_device_init(). If it fails, the caller should execute ipack_put_device(). The second function is ipack_device_add that only adds the device. If it fails, the caller should execute ipack_put_device(). Then the device is removed with refcount = 0, as device_register() kernel documentation says. ipack_device_del() is added to remove the device. Signed-off-by: Samuel Iglesias Gonsalvez Signed-off-by: Greg Kroah-Hartman --- include/linux/ipack.h | 39 +++++++++++++++++++++++++++++---------- 1 file changed, 29 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipack.h b/include/linux/ipack.h index def91fd996f4..1888e06ddf64 100644 --- a/include/linux/ipack.h +++ b/include/linux/ipack.h @@ -207,19 +207,38 @@ int ipack_driver_register(struct ipack_driver *edrv, struct module *owner, void ipack_driver_unregister(struct ipack_driver *edrv); /** - * ipack_device_register -- register an IPack device with the kernel - * @dev: the new device to register. + * ipack_device_init -- initialize an IPack device + * @dev: the new device to initialize. * - * Register a new IPack device ("module" in IndustryPack jargon). The call - * is done by the carrier driver. The carrier should populate the fields - * bus and slot as well as the region array of @dev prior to calling this - * function. The rest of the fields will be allocated and populated - * during registration. + * Initialize a new IPack device ("module" in IndustryPack jargon). The call + * is done by the carrier driver. The carrier should populate the fields + * bus and slot as well as the region array of @dev prior to calling this + * function. The rest of the fields will be allocated and populated + * during initalization. * - * Return zero on success or error code on failure. + * Return zero on success or error code on failure. + * + * NOTE: _Never_ directly free @dev after calling this function, even + * if it returned an error! Always use ipack_put_device() to give up the + * reference initialized in this function instead. + */ +int ipack_device_init(struct ipack_device *dev); + +/** + * ipack_device_add -- Add an IPack device + * @dev: the new device to add. + * + * Add a new IPack device. The call is done by the carrier driver + * after calling ipack_device_init(). + * + * Return zero on success or error code on failure. + * + * NOTE: _Never_ directly free @dev after calling this function, even + * if it returned an error! Always use ipack_put_device() to give up the + * reference initialized in this function instead. */ -int ipack_device_register(struct ipack_device *dev); -void ipack_device_unregister(struct ipack_device *dev); +int ipack_device_add(struct ipack_device *dev); +void ipack_device_del(struct ipack_device *dev); void ipack_get_device(struct ipack_device *dev); void ipack_put_device(struct ipack_device *dev); -- cgit v1.2.3 From 5caf4636259ae3af0efbb9bfc4cd97874b547c7d Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Tue, 12 Mar 2013 11:56:46 +0800 Subject: clocksource: Add new feature flag CLOCK_SOURCE_SUSPEND_NONSTOP Some x86 processors have a TSC clocksource, which continues to run even when system is suspended. Also most OMAP platforms have a 32 KHz timer which has similar capability. Add a feature flag so that it could be utilized. Signed-off-by: Feng Tang Signed-off-by: John Stultz --- include/linux/clocksource.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 27cfda427dd9..aa7032c7238f 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -206,6 +206,7 @@ struct clocksource { #define CLOCK_SOURCE_WATCHDOG 0x10 #define CLOCK_SOURCE_VALID_FOR_HRES 0x20 #define CLOCK_SOURCE_UNSTABLE 0x40 +#define CLOCK_SOURCE_SUSPEND_NONSTOP 0x80 /* simplify initialization of mask field */ #define CLOCKSOURCE_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1) -- cgit v1.2.3 From a362db3d6c8a952cbde510b1fa35d0ee001b347e Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 16 Mar 2013 04:47:55 +0000 Subject: net: fix some typos in netif features Cc: Pravin B Shelar Cc: "David S. Miller" Signed-off-by: Cong Wang Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index f5e797c0c2a4..d6ee2d008ee4 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -102,8 +102,8 @@ enum { #define NETIF_F_VLAN_CHALLENGED __NETIF_F(VLAN_CHALLENGED) #define NETIF_F_RXFCS __NETIF_F(RXFCS) #define NETIF_F_RXALL __NETIF_F(RXALL) -#define NETIF_F_GRE_GSO __NETIF_F(GSO_GRE) -#define NETIF_F_UDP_TUNNEL __NETIF_F(UDP_TUNNEL) +#define NETIF_F_GSO_GRE __NETIF_F(GSO_GRE) +#define NETIF_F_GSO_UDP_TUNNEL __NETIF_F(GSO_UDP_TUNNEL) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ -- cgit v1.2.3 From 1a2c6181c4a1922021b4d7df373bba612c3e5f04 Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Sun, 17 Mar 2013 08:23:34 +0000 Subject: tcp: Remove TCPCT TCPCT uses option-number 253, reserved for experimental use and should not be used in production environments. Further, TCPCT does not fully implement RFC 6013. As a nice side-effect, removing TCPCT increases TCP's performance for very short flows: Doing an apache-benchmark with -c 100 -n 100000, sending HTTP-requests for files of 1KB size. before this patch: average (among 7 runs) of 20845.5 Requests/Second after: average (among 7 runs) of 21403.6 Requests/Second Signed-off-by: Christoph Paasch Signed-off-by: David S. Miller --- include/linux/tcp.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 763c108ee03d..ed6a7456eecd 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -90,9 +90,6 @@ struct tcp_options_received { sack_ok : 4, /* SACK seen on SYN packet */ snd_wscale : 4, /* Window scaling received from sender */ rcv_wscale : 4; /* Window scaling to send to receiver */ - u8 cookie_plus:6, /* bytes in authenticator/cookie option */ - cookie_out_never:1, - cookie_in_always:1; u8 num_sacks; /* Number of SACK blocks */ u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ @@ -102,7 +99,6 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt) { rx_opt->tstamp_ok = rx_opt->sack_ok = 0; rx_opt->wscale_ok = rx_opt->snd_wscale = 0; - rx_opt->cookie_plus = 0; } /* This is the max number of SACKS that we'll generate and process. It's safe @@ -320,12 +316,6 @@ struct tcp_sock { struct tcp_md5sig_info __rcu *md5sig_info; #endif - /* When the cookie options are generated and exchanged, then this - * object holds a reference to them (cookie_values->kref). Also - * contains related tcp_cookie_transactions fields. - */ - struct tcp_cookie_values *cookie_values; - /* TCP fastopen related information */ struct tcp_fastopen_request *fastopen_req; /* fastopen_rsk points to request_sock that resulted in this big -- cgit v1.2.3 From 8655cc490e83f66476de8c1294411860325c3531 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Tue, 19 Feb 2013 21:10:30 +0000 Subject: iio: Add broken out info_mask fields for shared_by_type and separate This simplifies the code, removes an extensive layer of 'helper' macros and gives us twice as much room to play with in these masks before we have any need to be clever. Signed-off-by: Jonathan Cameron Acked-by: Lars-Peter Clausen --- include/linux/iio/iio.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index da8c776ba0bd..76976509d628 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -218,6 +218,10 @@ ssize_t iio_enum_write(struct iio_dev *indio_dev, * endianness: little or big endian * @info_mask: What information is to be exported about this channel. * This includes calibbias, scale etc. + * @info_mask_separate: What information is to be exported that is specific to + * this channel. + * @info_mask_shared_by_type: What information is to be exported that is shared +* by all channels of the same type. * @event_mask: What events can this channel produce. * @ext_info: Array of extended info attributes for this channel. * The array is NULL terminated, the last element should @@ -253,6 +257,8 @@ struct iio_chan_spec { enum iio_endian endianness; } scan_type; long info_mask; + long info_mask_separate; + long info_mask_shared_by_type; long event_mask; const struct iio_chan_spec_ext_info *ext_info; const char *extend_name; @@ -275,7 +281,9 @@ struct iio_chan_spec { static inline bool iio_channel_has_info(const struct iio_chan_spec *chan, enum iio_chan_info_enum type) { - return chan->info_mask & IIO_CHAN_INFO_BITS(type); + return (chan->info_mask & IIO_CHAN_INFO_BITS(type)) | + (chan->info_mask_separate & type) | + (chan->info_mask_shared_by_type & type); } #define IIO_ST(si, rb, sb, sh) \ -- cgit v1.2.3 From 5ea864940e8ab63c2669902650b807d0507c390d Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Wed, 27 Feb 2013 19:41:59 +0000 Subject: iio:st_sensors move to info_mask_(shared_by_type/separate) The original info_mask is going away in favour of the broken out versions. Signed-off-by: Jonathan Cameron Acked-by: Denis Ciocca --- include/linux/iio/common/st_sensors.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 1f86a97ab2e2..7c0c0d3aef35 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -15,6 +15,7 @@ #include #include #include +#include #define ST_SENSORS_TX_MAX_LENGTH 2 #define ST_SENSORS_RX_MAX_LENGTH 6 @@ -45,8 +46,8 @@ { \ .type = device_type, \ .modified = 1, \ - .info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \ - IIO_CHAN_INFO_SCALE_SEPARATE_BIT, \ + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ + BIT(IIO_CHAN_INFO_SCALE), \ .scan_index = index, \ .channel2 = mod, \ .address = addr, \ -- cgit v1.2.3 From ea0c68006321eea78a3702a9d68ff9395e06da38 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Wed, 27 Feb 2013 19:42:39 +0000 Subject: iio:adc:ad_sigma_delta move to info_mask_(shared_by_type/separate) The original info_mask is going away in favour of the broken out versions. Signed-off-by: Jonathan Cameron Acked-by: Lars-Peter Clausen --- include/linux/iio/adc/ad_sigma_delta.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 2e4eab9868a3..e7fdec4db9da 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -133,9 +133,9 @@ int ad_sd_validate_trigger(struct iio_dev *indio_dev, struct iio_trigger *trig); .channel2 = (_channel2), \ .address = (_address), \ .extend_name = (_extend_name), \ - .info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \ - IIO_CHAN_INFO_SCALE_SHARED_BIT | \ - IIO_CHAN_INFO_OFFSET_SEPARATE_BIT, \ + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ + BIT(IIO_CHAN_INFO_OFFSET), \ + .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \ .scan_index = (_si), \ .scan_type = { \ .sign = 'u', \ -- cgit v1.2.3 From b841f8abc27466026ecf4e5590c6c737c2e86e7e Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Wed, 27 Feb 2013 19:35:55 +0000 Subject: staging:iio:accel:adis move to info_mask_(shared_by_type/separate) The original info_mask is going away in favour of the broken out versions. Signed-off-by: Jonathan Cameron Acked-by: Lars-Peter Clausen --- include/linux/iio/imu/adis.h | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index ff781dca2e9a..b665dc7f017b 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -162,8 +162,8 @@ int adis_single_conversion(struct iio_dev *indio_dev, .indexed = 1, \ .channel = (chan), \ .extend_name = name, \ - .info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \ - IIO_CHAN_INFO_SCALE_SEPARATE_BIT, \ + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ + BIT(IIO_CHAN_INFO_SCALE), \ .address = (addr), \ .scan_index = (si), \ .scan_type = { \ @@ -184,9 +184,9 @@ int adis_single_conversion(struct iio_dev *indio_dev, .type = IIO_TEMP, \ .indexed = 1, \ .channel = 0, \ - .info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \ - IIO_CHAN_INFO_SCALE_SEPARATE_BIT | \ - IIO_CHAN_INFO_OFFSET_SEPARATE_BIT, \ + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ + BIT(IIO_CHAN_INFO_SCALE) | \ + BIT(IIO_CHAN_INFO_OFFSET), \ .address = (addr), \ .scan_index = (si), \ .scan_type = { \ @@ -197,13 +197,13 @@ int adis_single_conversion(struct iio_dev *indio_dev, }, \ } -#define ADIS_MOD_CHAN(_type, mod, addr, si, info, bits) { \ +#define ADIS_MOD_CHAN(_type, mod, addr, si, info_sep, bits) { \ .type = (_type), \ .modified = 1, \ .channel2 = IIO_MOD_ ## mod, \ - .info_mask = IIO_CHAN_INFO_RAW_SEPARATE_BIT | \ - IIO_CHAN_INFO_SCALE_SHARED_BIT | \ - info, \ + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ + info_sep, \ + .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \ .address = (addr), \ .scan_index = (si), \ .scan_type = { \ @@ -214,17 +214,17 @@ int adis_single_conversion(struct iio_dev *indio_dev, }, \ } -#define ADIS_ACCEL_CHAN(mod, addr, si, info, bits) \ - ADIS_MOD_CHAN(IIO_ACCEL, mod, addr, si, info, bits) +#define ADIS_ACCEL_CHAN(mod, addr, si, info_sep, bits) \ + ADIS_MOD_CHAN(IIO_ACCEL, mod, addr, si, info_sep, bits) -#define ADIS_GYRO_CHAN(mod, addr, si, info, bits) \ - ADIS_MOD_CHAN(IIO_ANGL_VEL, mod, addr, si, info, bits) +#define ADIS_GYRO_CHAN(mod, addr, si, info_sep, bits) \ + ADIS_MOD_CHAN(IIO_ANGL_VEL, mod, addr, si, info_sep, bits) -#define ADIS_INCLI_CHAN(mod, addr, si, info, bits) \ - ADIS_MOD_CHAN(IIO_INCLI, mod, addr, si, info, bits) +#define ADIS_INCLI_CHAN(mod, addr, si, info_sep, bits) \ + ADIS_MOD_CHAN(IIO_INCLI, mod, addr, si, info_sep, bits) -#define ADIS_ROT_CHAN(mod, addr, si, info, bits) \ - ADIS_MOD_CHAN(IIO_ROT, mod, addr, si, info, bits) +#define ADIS_ROT_CHAN(mod, addr, si, info_sep, bits) \ + ADIS_MOD_CHAN(IIO_ROT, mod, addr, si, info_sep, bits) #ifdef CONFIG_IIO_ADIS_LIB_BUFFER -- cgit v1.2.3 From b9606e2aa97d3d831d1236c0e789a33a2f867a8a Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Wed, 27 Feb 2013 19:43:52 +0000 Subject: iio:core drop info_mask from struct iio_info This has been replaced by the pair of masks info_mask_separate and info_mask_shared_by_type. Other variants may follow. Signed-off-by: Jonathan Cameron Acked-by: Lars-Peter Clausen --- include/linux/iio/iio.h | 73 +------------------------------------------------ 1 file changed, 1 insertion(+), 72 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 76976509d628..8d171f427632 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -38,76 +38,6 @@ enum iio_chan_info_enum { IIO_CHAN_INFO_HYSTERESIS, }; -#define IIO_CHAN_INFO_SHARED_BIT(type) BIT(type*2) -#define IIO_CHAN_INFO_SEPARATE_BIT(type) BIT(type*2 + 1) -#define IIO_CHAN_INFO_BITS(type) (IIO_CHAN_INFO_SHARED_BIT(type) | \ - IIO_CHAN_INFO_SEPARATE_BIT(type)) - -#define IIO_CHAN_INFO_RAW_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_RAW) -#define IIO_CHAN_INFO_PROCESSED_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_PROCESSED) -#define IIO_CHAN_INFO_SCALE_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_SCALE) -#define IIO_CHAN_INFO_SCALE_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT(IIO_CHAN_INFO_SCALE) -#define IIO_CHAN_INFO_OFFSET_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_OFFSET) -#define IIO_CHAN_INFO_OFFSET_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT(IIO_CHAN_INFO_OFFSET) -#define IIO_CHAN_INFO_CALIBSCALE_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_CALIBSCALE) -#define IIO_CHAN_INFO_CALIBSCALE_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT(IIO_CHAN_INFO_CALIBSCALE) -#define IIO_CHAN_INFO_CALIBBIAS_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_CALIBBIAS) -#define IIO_CHAN_INFO_CALIBBIAS_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT(IIO_CHAN_INFO_CALIBBIAS) -#define IIO_CHAN_INFO_PEAK_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_PEAK) -#define IIO_CHAN_INFO_PEAK_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT(IIO_CHAN_INFO_PEAK) -#define IIO_CHAN_INFO_PEAKSCALE_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_PEAKSCALE) -#define IIO_CHAN_INFO_PEAKSCALE_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT(IIO_CHAN_INFO_PEAKSCALE) -#define IIO_CHAN_INFO_QUADRATURE_CORRECTION_RAW_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT( \ - IIO_CHAN_INFO_QUADRATURE_CORRECTION_RAW) -#define IIO_CHAN_INFO_QUADRATURE_CORRECTION_RAW_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT( \ - IIO_CHAN_INFO_QUADRATURE_CORRECTION_RAW) -#define IIO_CHAN_INFO_AVERAGE_RAW_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_AVERAGE_RAW) -#define IIO_CHAN_INFO_AVERAGE_RAW_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT(IIO_CHAN_INFO_AVERAGE_RAW) -#define IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT( \ - IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY) -#define IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT( \ - IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY) -#define IIO_CHAN_INFO_SAMP_FREQ_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_SAMP_FREQ) -#define IIO_CHAN_INFO_SAMP_FREQ_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT(IIO_CHAN_INFO_SAMP_FREQ) -#define IIO_CHAN_INFO_FREQUENCY_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_FREQUENCY) -#define IIO_CHAN_INFO_FREQUENCY_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT(IIO_CHAN_INFO_FREQUENCY) -#define IIO_CHAN_INFO_PHASE_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_PHASE) -#define IIO_CHAN_INFO_PHASE_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT(IIO_CHAN_INFO_PHASE) -#define IIO_CHAN_INFO_HARDWAREGAIN_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_HARDWAREGAIN) -#define IIO_CHAN_INFO_HARDWAREGAIN_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT(IIO_CHAN_INFO_HARDWAREGAIN) -#define IIO_CHAN_INFO_HYSTERESIS_SEPARATE_BIT \ - IIO_CHAN_INFO_SEPARATE_BIT(IIO_CHAN_INFO_HYSTERESIS) -#define IIO_CHAN_INFO_HYSTERESIS_SHARED_BIT \ - IIO_CHAN_INFO_SHARED_BIT(IIO_CHAN_INFO_HYSTERESIS) - enum iio_endian { IIO_CPU, IIO_BE, @@ -281,8 +211,7 @@ struct iio_chan_spec { static inline bool iio_channel_has_info(const struct iio_chan_spec *chan, enum iio_chan_info_enum type) { - return (chan->info_mask & IIO_CHAN_INFO_BITS(type)) | - (chan->info_mask_separate & type) | + return (chan->info_mask_separate & type) | (chan->info_mask_shared_by_type & type); } -- cgit v1.2.3 From 717bfb5f46f0ee809f6ce04ebdf44521730fff05 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Sun, 17 Mar 2013 20:07:25 +0800 Subject: ALSA: snd-usb: handle raw data format of UAC2 devices UAC2 compliant audio devices may announce the capability to transport raw audio data on their endpoints. Catch this and handle it as 'special' stream on the ALSA side. Signed-off-by: Daniel Mack Reported-by: Andreas Koch Signed-off-by: Takashi Iwai --- include/linux/usb/audio-v2.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/audio-v2.h b/include/linux/usb/audio-v2.h index ed13053153f4..c5f2158ab00e 100644 --- a/include/linux/usb/audio-v2.h +++ b/include/linux/usb/audio-v2.h @@ -170,6 +170,8 @@ struct uac2_as_header_descriptor { __u8 iChannelNames; } __attribute__((packed)); +#define UAC2_FORMAT_TYPE_I_RAW_DATA (1 << 31) + /* 4.10.1.2 Class-Specific AS Isochronous Audio Data Endpoint Descriptor */ struct uac2_iso_endpoint_descriptor { -- cgit v1.2.3 From 1f0972f5b05a674d73e4eb314fa1b6c78e37aef1 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Tue, 12 Mar 2013 13:24:19 +0200 Subject: usb: phy: nop: Add some parameters to platform data Add clk_rate parameter to platform data. If supplied, the NOP phy driver will program the clock to that rate during probe. Also add 2 flags, needs_vcc and needs_reset. If the flag is set and the regulator couldn't be found then the driver will bail out with -EPROBE_DEFER. Signed-off-by: Roger Quadros Acked-by: Felipe Balbi Signed-off-by: Felipe Balbi --- include/linux/usb/nop-usb-xceiv.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/nop-usb-xceiv.h b/include/linux/usb/nop-usb-xceiv.h index 28884c717411..148d35171aac 100644 --- a/include/linux/usb/nop-usb-xceiv.h +++ b/include/linux/usb/nop-usb-xceiv.h @@ -5,6 +5,11 @@ struct nop_usb_xceiv_platform_data { enum usb_phy_type type; + unsigned long clk_rate; + + /* if set fails with -EPROBE_DEFER if can't get regulator */ + unsigned int needs_vcc:1; + unsigned int needs_reset:1; }; #if defined(CONFIG_NOP_USB_XCEIV) || (defined(CONFIG_NOP_USB_XCEIV_MODULE) && defined(MODULE)) -- cgit v1.2.3 From 4495afcf713adb5bdb16504052952bdd0d11f90a Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 26 Feb 2013 20:03:28 +0530 Subject: usb: dwc3: omap: remove platform data associated with dwc3-omap omap5 is not going to have support for non-dt boot making the platform data associated with dwc3 useless. Removed it here. Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Felipe Balbi --- include/linux/platform_data/dwc3-omap.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/dwc3-omap.h b/include/linux/platform_data/dwc3-omap.h index ada401244e0b..1d36ca874cc8 100644 --- a/include/linux/platform_data/dwc3-omap.h +++ b/include/linux/platform_data/dwc3-omap.h @@ -41,7 +41,3 @@ enum dwc3_omap_utmi_mode { DWC3_OMAP_UTMI_MODE_HW, DWC3_OMAP_UTMI_MODE_SW, }; - -struct dwc3_omap_data { - enum dwc3_omap_utmi_mode utmi_mode; -}; -- cgit v1.2.3 From f07bd56bbdaa2340ebf46af9a37e7b2d1b4578e3 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 24 Jan 2013 14:52:24 +0200 Subject: usb: gadget: udc-core: allow udc class register gadget device Currently all UDC drivers are calling device_register() before calling usb_add_gadget_udc(). In order to avoid code duplication, we can allow udc-core.c register that device. However that would become a really large patch, so to cope with the meanwhile and allow us to write bite-sized patches, we're adding a flag which will be set by UDC driver once it removes the code for registering the gadget device. Once all are converted, the new flag will be removed. Reviewed-by: Tomasz Figa Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 2e297e80d59a..fcd9ef8d3f70 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -494,6 +494,9 @@ struct usb_gadget_ops { * only supports HNP on a different root port. * @b_hnp_enable: OTG device feature flag, indicating that the A-Host * enabled HNP support. + * @register_my_device: Flag telling udc-core that UDC driver didn't + * register the gadget device to the driver model. Temporary until + * all UDC drivers are fixed up properly. * @name: Identifies the controller hardware type. Used in diagnostics * and sometimes configuration. * @dev: Driver model state for this abstract device. @@ -531,6 +534,7 @@ struct usb_gadget { unsigned b_hnp_enable:1; unsigned a_hnp_support:1; unsigned a_alt_hnp_support:1; + unsigned register_my_device:1; const char *name; struct device dev; unsigned out_epnum; -- cgit v1.2.3 From 7bce401cc6db5508ef2517e45bd8caf7ce0a15ee Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 24 Jan 2013 17:41:00 +0200 Subject: usb: gadget: drop now unnecessary flag We don't need the ->register_my_device flag anymore because all UDC drivers have been properly converted. Let's remove every history of it. Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index fcd9ef8d3f70..2e297e80d59a 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -494,9 +494,6 @@ struct usb_gadget_ops { * only supports HNP on a different root port. * @b_hnp_enable: OTG device feature flag, indicating that the A-Host * enabled HNP support. - * @register_my_device: Flag telling udc-core that UDC driver didn't - * register the gadget device to the driver model. Temporary until - * all UDC drivers are fixed up properly. * @name: Identifies the controller hardware type. Used in diagnostics * and sometimes configuration. * @dev: Driver model state for this abstract device. @@ -534,7 +531,6 @@ struct usb_gadget { unsigned b_hnp_enable:1; unsigned a_hnp_support:1; unsigned a_alt_hnp_support:1; - unsigned register_my_device:1; const char *name; struct device dev; unsigned out_epnum; -- cgit v1.2.3 From d1e3d757f7aa91f15db347fc05ffd7ef7f413091 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 24 Jan 2013 22:29:48 +0200 Subject: usb: common: introduce usb_state_string() this function will receive enum usb_device_state and return a human-readable string from it or, case an unknown value is passed as argument, the string "UNKNOWN". Signed-off-by: Felipe Balbi --- include/linux/usb/ch9.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index 9c210f2283df..27603bcbb9b9 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -43,4 +43,13 @@ */ extern const char *usb_speed_string(enum usb_device_speed speed); + +/** + * usb_state_string - Returns human readable name for the state. + * @state: The state to return a human-readable name for. If it's not + * any of the states devices in usb_device_state_string enum, + * the string UNKNOWN will be returned. + */ +extern const char *usb_state_string(enum usb_device_state state); + #endif /* __LINUX_USB_CH9_H */ -- cgit v1.2.3 From 49401f4169c0e5a1b38f1a676d6f12eecaf77485 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Mon, 19 Dec 2011 12:57:04 +0200 Subject: usb: gadget: introduce gadget state tracking that's useful information to expose to userland. Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 2e297e80d59a..32b734d88d6b 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -482,6 +482,7 @@ struct usb_gadget_ops { * @speed: Speed of current connection to USB host. * @max_speed: Maximal speed the UDC can handle. UDC must support this * and all slower speeds. + * @state: the state we are now (attached, suspended, configured, etc) * @sg_supported: true if we can handle scatter-gather * @is_otg: True if the USB device port uses a Mini-AB jack, so that the * gadget driver must provide a USB OTG descriptor. @@ -525,6 +526,7 @@ struct usb_gadget { struct list_head ep_list; /* of usb_ep */ enum usb_device_speed speed; enum usb_device_speed max_speed; + enum usb_device_state state; unsigned sg_supported:1; unsigned is_otg:1; unsigned is_a_peripheral:1; @@ -959,6 +961,13 @@ extern void usb_gadget_unmap_request(struct usb_gadget *gadget, /*-------------------------------------------------------------------------*/ +/* utility to set gadget state properly */ + +extern void usb_gadget_set_state(struct usb_gadget *gadget, + enum usb_device_state state); + +/*-------------------------------------------------------------------------*/ + /* utility wrapping a simple endpoint selection policy */ extern struct usb_ep *usb_ep_autoconfig(struct usb_gadget *, -- cgit v1.2.3 From 792bfcf7a1cd7913fa5d55f2b3a40e3275e98f6f Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Tue, 26 Feb 2013 14:47:44 +0200 Subject: usb: gadget: udc-core: introduce usb_add_gadget_udc_release() not all UDC drivers need a proper release function, for those which don't need it, we udc-core will provide a no-op release method so we can remove "redefinition" of such methods in almost every UDC driver. Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 32b734d88d6b..c454a88abf2e 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -874,6 +874,8 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver); */ int usb_gadget_unregister_driver(struct usb_gadget_driver *driver); +extern int usb_add_gadget_udc_release(struct device *parent, + struct usb_gadget *gadget, void (*release)(struct device *dev)); extern int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget); extern void usb_del_gadget_udc(struct usb_gadget *gadget); extern int udc_attach_driver(const char *name, -- cgit v1.2.3 From 42c0bf1ce7c067bbc3e77d5626f102a16bc4fb6b Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 7 Mar 2013 10:39:57 +0200 Subject: usb: otg: prefix otg_state_string with usb_ all other functions under drivers/usb/ start with usb_, let's do the same thing. This patch is in preparation for moving otg_state_string to usb-common.c and deleting otg.c completely. Signed-off-by: Felipe Balbi --- include/linux/usb/otg.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h index e8a5fe87c6bd..9f9fb3927b0a 100644 --- a/include/linux/usb/otg.h +++ b/include/linux/usb/otg.h @@ -37,9 +37,9 @@ struct usb_otg { }; #ifdef CONFIG_USB_OTG_UTILS -extern const char *otg_state_string(enum usb_otg_state state); +extern const char *usb_otg_state_string(enum usb_otg_state state); #else -static inline const char *otg_state_string(enum usb_otg_state state) +static inline const char *usb_otg_state_string(enum usb_otg_state state) { return NULL; } -- cgit v1.2.3 From 7009bdd7f31ed6e769af0f76e2368bb6033be572 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 7 Mar 2013 10:45:56 +0200 Subject: usb: otg: move usb_otg_state_string to usb-common.c otg.c only had a single function definition which might make more sense to be placed in usb-common.c. While doing that, we also delete otg.c since it's now empty. Signed-off-by: Felipe Balbi --- include/linux/usb/otg.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h index 9f9fb3927b0a..291e01ba32e5 100644 --- a/include/linux/usb/otg.h +++ b/include/linux/usb/otg.h @@ -36,14 +36,7 @@ struct usb_otg { }; -#ifdef CONFIG_USB_OTG_UTILS extern const char *usb_otg_state_string(enum usb_otg_state state); -#else -static inline const char *usb_otg_state_string(enum usb_otg_state state) -{ - return NULL; -} -#endif /* Context: can sleep */ static inline int -- cgit v1.2.3 From edc7cb2e955f222fe51cd44c1cf9c94d58017344 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 7 Mar 2013 11:13:43 +0200 Subject: usb: phy: make it a menuconfig We already have a considerable amount of USB PHY drivers, making it a menuconfig just prevents us from adding too much churn to USB's menuconfig. While at that, also select USB_OTG_UTILS from this new menuconfig just to keep backwards compatibility until we manage to remove that symbol. Signed-off-by: Felipe Balbi --- include/linux/usb/phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index 15847cbdb512..b001dc3d6354 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -161,7 +161,7 @@ usb_phy_shutdown(struct usb_phy *x) } /* for usb host and peripheral controller drivers */ -#ifdef CONFIG_USB_OTG_UTILS +#if IS_ENABLED(CONFIG_USB_PHY) extern struct usb_phy *usb_get_phy(enum usb_phy_type type); extern struct usb_phy *devm_usb_get_phy(struct device *dev, enum usb_phy_type type); -- cgit v1.2.3 From b774212ea5f13911a5e0211a7088e42dad46b4c8 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Fri, 8 Mar 2013 13:22:58 +0200 Subject: usb: phy: introduce ->set_vbus() method this method will be used to enable or disable the charge pump. Whenever we have DRD devices, we need to be able to turn VBUS on or off whenever we want. Note that in the ideal case, this would be controlled by the ID-pin Interrupt, but not all devices have ID-pin properly routed since manufacturers can choose to save that trace if they're building a host-only product out of a DRD IP. This is also useful during debugging where we might not have the proper cable hanging around. Signed-off-by: Felipe Balbi --- include/linux/usb/phy.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index b001dc3d6354..b7c2217c585f 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -91,6 +91,9 @@ struct usb_phy { int (*init)(struct usb_phy *x); void (*shutdown)(struct usb_phy *x); + /* enable/disable VBUS */ + int (*set_vbus)(struct usb_phy *x, int on); + /* effective for B devices, ignored for A-peripheral */ int (*set_power)(struct usb_phy *x, unsigned mA); @@ -160,6 +163,24 @@ usb_phy_shutdown(struct usb_phy *x) x->shutdown(x); } +static inline int +usb_phy_vbus_on(struct usb_phy *x) +{ + if (!x->set_vbus) + return 0; + + return x->set_vbus(x, true); +} + +static inline int +usb_phy_vbus_off(struct usb_phy *x) +{ + if (!x->set_vbus) + return 0; + + return x->set_vbus(x, false); +} + /* for usb host and peripheral controller drivers */ #if IS_ENABLED(CONFIG_USB_PHY) extern struct usb_phy *usb_get_phy(enum usb_phy_type type); -- cgit v1.2.3 From 2ba7943af0f0cca5a069cd3aff807815bc76fff1 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Thu, 7 Mar 2013 18:51:44 +0530 Subject: usb: dwc3: dwc3-omap: return -EPROBE_DEFER if probe has not yet executed return -EPROBE_DEFER from dwc3_omap_mailbox in dwc3-omap.c, if the probe of dwc3-omap has not yet been executed or failed. Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Felipe Balbi --- include/linux/usb/dwc3-omap.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/dwc3-omap.h b/include/linux/usb/dwc3-omap.h index 51eae14477f7..5615f4d82724 100644 --- a/include/linux/usb/dwc3-omap.h +++ b/include/linux/usb/dwc3-omap.h @@ -19,11 +19,11 @@ enum omap_dwc3_vbus_id_status { }; #if (defined(CONFIG_USB_DWC3) || defined(CONFIG_USB_DWC3_MODULE)) -extern void dwc3_omap_mailbox(enum omap_dwc3_vbus_id_status status); +extern int dwc3_omap_mailbox(enum omap_dwc3_vbus_id_status status); #else -static inline void dwc3_omap_mailbox(enum omap_dwc3_vbus_id_status status) +static inline int dwc3_omap_mailbox(enum omap_dwc3_vbus_id_status status) { - return; + return -ENODEV; } #endif -- cgit v1.2.3 From b7fa5c2aec5be083eb2719b405089703608e9bc6 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 14 Mar 2013 17:59:06 +0200 Subject: usb: phy: return -ENXIO when PHY layer isn't enabled in cases where PHY layer isn't enabled, we want to still return an error code (actually an error pointer) so that our users don't need to cope with either error pointer of NULL. This will simplify users as below: - return IS_ERR(phy) ? PTR_ERR(phy) : -ENODEV; + return PTR_ERR(phy); Acked-by: Kishon Vijay Abraham I Reported-by: Alan Stern Signed-off-by: Felipe Balbi --- include/linux/usb/phy.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index b7c2217c585f..6b5978f57633 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -197,29 +197,29 @@ extern int usb_bind_phy(const char *dev_name, u8 index, #else static inline struct usb_phy *usb_get_phy(enum usb_phy_type type) { - return NULL; + return ERR_PTR(-ENXIO); } static inline struct usb_phy *devm_usb_get_phy(struct device *dev, enum usb_phy_type type) { - return NULL; + return ERR_PTR(-ENXIO); } static inline struct usb_phy *usb_get_phy_dev(struct device *dev, u8 index) { - return NULL; + return ERR_PTR(-ENXIO); } static inline struct usb_phy *devm_usb_get_phy_dev(struct device *dev, u8 index) { - return NULL; + return ERR_PTR(-ENXIO); } static inline struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev, const char *phandle, u8 index) { - return NULL; + return ERR_PTR(-ENXIO); } static inline void usb_put_phy(struct usb_phy *x) -- cgit v1.2.3 From e6251fc244a18a53830f38de84e4fcaee2f58662 Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Fri, 15 Mar 2013 16:32:05 +0100 Subject: itg3200: fix incorrect ifdef comment Signed-off-by: Paul Bolle Signed-off-by: Jiri Kosina --- include/linux/iio/gyro/itg3200.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/gyro/itg3200.h b/include/linux/iio/gyro/itg3200.h index c53f16914b77..2a820850f284 100644 --- a/include/linux/iio/gyro/itg3200.h +++ b/include/linux/iio/gyro/itg3200.h @@ -149,6 +149,6 @@ static inline void itg3200_buffer_unconfigure(struct iio_dev *indio_dev) { } -#endif /* CONFIG_IIO_RING_BUFFER */ +#endif /* CONFIG_IIO_BUFFER */ #endif /* ITG3200_H_ */ -- cgit v1.2.3 From 5a20d339c785d98d8b050b9afc098e4184a6098c Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Sun, 3 Mar 2013 13:58:05 +0900 Subject: f2fs: align f2fs maximum name length to linux based filesystem The maximum filename length supported in linux is 255 characters. So let's follow that. Signed-off-by: Namjae Jeon Signed-off-by: Amit Sahrawat Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index f9a12f6243a5..df6fab82f87e 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -139,7 +139,7 @@ struct f2fs_extent { __le32 len; /* lengh of the extent */ } __packed; -#define F2FS_MAX_NAME_LEN 256 +#define F2FS_NAME_LEN 255 #define ADDRS_PER_INODE 923 /* Address Pointers in an Inode */ #define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ #define NIDS_PER_BLOCK 1018 /* Node IDs in an Indirect Block */ @@ -165,7 +165,8 @@ struct f2fs_inode { __le32 i_flags; /* file attributes */ __le32 i_pino; /* parent inode number */ __le32 i_namelen; /* file name length */ - __u8 i_name[F2FS_MAX_NAME_LEN]; /* file name for SPOR */ + __u8 i_name[F2FS_NAME_LEN]; /* file name for SPOR */ + __u8 i_reserved2; /* for backward compatibility */ struct f2fs_extent i_ext; /* caching a largest extent */ @@ -362,10 +363,10 @@ struct f2fs_summary_block { typedef __le32 f2fs_hash_t; /* One directory entry slot covers 8bytes-long file name */ -#define F2FS_NAME_LEN 8 -#define F2FS_NAME_LEN_BITS 3 +#define F2FS_SLOT_LEN 8 +#define F2FS_SLOT_LEN_BITS 3 -#define GET_DENTRY_SLOTS(x) ((x + F2FS_NAME_LEN - 1) >> F2FS_NAME_LEN_BITS) +#define GET_DENTRY_SLOTS(x) ((x + F2FS_SLOT_LEN - 1) >> F2FS_SLOT_LEN_BITS) /* the number of dentry in a block */ #define NR_DENTRY_IN_BLOCK 214 @@ -377,10 +378,10 @@ typedef __le32 f2fs_hash_t; #define SIZE_OF_DENTRY_BITMAP ((NR_DENTRY_IN_BLOCK + BITS_PER_BYTE - 1) / \ BITS_PER_BYTE) #define SIZE_OF_RESERVED (PAGE_SIZE - ((SIZE_OF_DIR_ENTRY + \ - F2FS_NAME_LEN) * \ + F2FS_SLOT_LEN) * \ NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP)) -/* One directory entry slot representing F2FS_NAME_LEN-sized file name */ +/* One directory entry slot representing F2FS_SLOT_LEN-sized file name */ struct f2fs_dir_entry { __le32 hash_code; /* hash code of file name */ __le32 ino; /* inode number */ @@ -394,7 +395,7 @@ struct f2fs_dentry_block { __u8 dentry_bitmap[SIZE_OF_DENTRY_BITMAP]; __u8 reserved[SIZE_OF_RESERVED]; struct f2fs_dir_entry dentry[NR_DENTRY_IN_BLOCK]; - __u8 filename[NR_DENTRY_IN_BLOCK][F2FS_NAME_LEN]; + __u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN]; } __packed; /* file types used in inode_info->flags */ -- cgit v1.2.3 From 443580486e3b96578928c1c91e8fbdcf0c9c9c7f Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Mon, 18 Feb 2013 23:28:34 +0900 Subject: irqchip: Renesas INTC External IRQ pin driver This patch adds a driver for external IRQ pins connected to the INTC block on recent SoCs from Renesas. The INTC hardware block usually contains a rather wide range of features ranging from external IRQ pin handling to legacy interrupt controller support. On older SoCs the INTC is used as a general purpose interrupt controller both for external IRQ pins and on-chip devices. On more recent ARM based SoCs with Cortex-A9 the main interrupt controller is the GIC, but IRQ trigger setup still need to happen in the INTC hardware block. This driver implements the glue code needed to configure IRQ trigger and also handle mask/unmask and demux of external IRQ pins hooked up from the INTC to the GIC. Tested on sh73a0 and r8a7779. The hardware varies quite a bit with SoC model, for instance register width and bitfield widths vary wildly. The driver requires one GIC SPI per external IRQ pin to operate. Each driver instance will handle up to 8 external IRQ pins. The SoCs using this driver are currently mainly used together with regular platform devices so this driver allows configuration via platform data to support things like static interrupt base address. DT support will be added incrementally in the not so distant future. Signed-off-by: Magnus Damm Acked-by: Thomas Gleixner Signed-off-by: Simon Horman --- include/linux/platform_data/irq-renesas-intc-irqpin.h | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 include/linux/platform_data/irq-renesas-intc-irqpin.h (limited to 'include/linux') diff --git a/include/linux/platform_data/irq-renesas-intc-irqpin.h b/include/linux/platform_data/irq-renesas-intc-irqpin.h new file mode 100644 index 000000000000..00ccac34dac8 --- /dev/null +++ b/include/linux/platform_data/irq-renesas-intc-irqpin.h @@ -0,0 +1,10 @@ +#ifndef __IRQ_RENESAS_INTC_IRQPIN_H__ +#define __IRQ_RENESAS_INTC_IRQPIN_H__ + +struct renesas_intc_irqpin_config { + unsigned int sense_bitfield_width; + unsigned int irq_base; + bool control_parent; +}; + +#endif /* __IRQ_RENESAS_INTC_IRQPIN_H__ */ -- cgit v1.2.3 From 0ca8712285e9e762ce4f5faf9f803b52e48c6837 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Tue, 26 Feb 2013 20:59:23 +0900 Subject: irqchip: intc-irqpin: GPL header for platform data Add GPL header to platform data include file. Signed-off-by: Magnus Damm Reviewed-by: Thomas Gleixner Tested-by: Guennadi Liakhovetski Signed-off-by: Simon Horman --- include/linux/platform_data/irq-renesas-intc-irqpin.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/irq-renesas-intc-irqpin.h b/include/linux/platform_data/irq-renesas-intc-irqpin.h index 00ccac34dac8..e4cb911066a6 100644 --- a/include/linux/platform_data/irq-renesas-intc-irqpin.h +++ b/include/linux/platform_data/irq-renesas-intc-irqpin.h @@ -1,3 +1,22 @@ +/* + * Renesas INTC External IRQ Pin Driver + * + * Copyright (C) 2013 Magnus Damm + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + #ifndef __IRQ_RENESAS_INTC_IRQPIN_H__ #define __IRQ_RENESAS_INTC_IRQPIN_H__ -- cgit v1.2.3 From fbc83b7f59dd8ed1154286b6de00b6d03c24a3c4 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Wed, 27 Feb 2013 17:15:01 +0900 Subject: irqchip: Renesas IRQC driver This patch adds a driver for external IRQ pins connected to the IRQC hardware block on recent SoCs from Renesas. The IRQC hardware block is used together with more recent ARM based SoCs using the GIC. As usual the GIC requires external IRQ trigger setup somewhere else which in this particular case happens to be IRQC. This driver implements the glue code needed to configure IRQ trigger and also handle mask/unmask and demux of external IRQ pins hooked up from the IRQC to the GIC. Tested on r8a73a4 but is designed to work with a wide range of SoCs. The driver requires one GIC SPI per external IRQ pin to operate. Each driver instance will handle up to 32 external IRQ pins. The SoCs using this driver are currently mainly used together with regular platform devices so this driver allows configuration via platform data to support things like static interrupt base address. DT support will be added incrementally in the not so distant future. Signed-off-by: Magnus Damm Tested-by: Guennadi Liakhovetski Signed-off-by: Simon Horman --- include/linux/platform_data/irq-renesas-irqc.h | 27 ++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) create mode 100644 include/linux/platform_data/irq-renesas-irqc.h (limited to 'include/linux') diff --git a/include/linux/platform_data/irq-renesas-irqc.h b/include/linux/platform_data/irq-renesas-irqc.h new file mode 100644 index 000000000000..3ae17b3e00ed --- /dev/null +++ b/include/linux/platform_data/irq-renesas-irqc.h @@ -0,0 +1,27 @@ +/* + * Renesas IRQC Driver + * + * Copyright (C) 2013 Magnus Damm + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef __IRQ_RENESAS_IRQC_H__ +#define __IRQ_RENESAS_IRQC_H__ + +struct renesas_irqc_config { + unsigned int irq_base; +}; + +#endif /* __IRQ_RENESAS_IRQC_H__ */ -- cgit v1.2.3 From af6882be363d3a7bf0f72dd17ac2a639c4da0059 Mon Sep 17 00:00:00 2001 From: Fabio Baltieri Date: Fri, 8 Mar 2013 10:27:09 +0800 Subject: usb: phy: ab8500-usb: update irq handling code Update irq handling code to notify all possible link status changes of AB8500 and AB8505 to the ux500-musb glue driver. The additional event codes will be used for pm-runtime implementation, and are defined in a separate ux500-specific header. This also modify the irq registration code to use devm_* helpers and drop all non necessary fail path code. Acked-by: Linus Walleij Signed-off-by: Fabio Baltieri Signed-off-by: Felipe Balbi --- include/linux/usb/musb-ux500.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/linux/usb/musb-ux500.h (limited to 'include/linux') diff --git a/include/linux/usb/musb-ux500.h b/include/linux/usb/musb-ux500.h new file mode 100644 index 000000000000..1e2c7130f6e1 --- /dev/null +++ b/include/linux/usb/musb-ux500.h @@ -0,0 +1,31 @@ +/* + * Copyright (C) 2013 ST-Ericsson AB + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __MUSB_UX500_H__ +#define __MUSB_UX500_H__ + +enum ux500_musb_vbus_id_status { + UX500_MUSB_NONE = 0, + UX500_MUSB_VBUS, + UX500_MUSB_ID, + UX500_MUSB_CHARGER, + UX500_MUSB_ENUMERATED, + UX500_MUSB_RIDA, + UX500_MUSB_RIDB, + UX500_MUSB_RIDC, + UX500_MUSB_PREPARE, + UX500_MUSB_CLEAN, +}; + +#endif /* __MUSB_UX500_H__ */ -- cgit v1.2.3 From 70bc126471af30bb115e635512dcf6d86fe6e29a Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Wed, 6 Mar 2013 08:20:52 -0500 Subject: tty: Add safe tty throttle/unthrottle functions The tty driver can become stuck throttled due to race conditions between throttle and unthrottle, when the decision to throttle or unthrottle is conditional. The following example helps to illustrate the race: CPU 0 | CPU 1 | if (condition A) | | | if (!condition A) | unthrottle() throttle() | | Note the converse is also possible; ie., CPU 0 | CPU 1 | | if (!condition A) | if (condition A) | throttle() | | unthrottle() | Add new throttle/unthrottle functions based on the familiar model of task state and schedule/wake. For example, while (1) { tty_set_flow_change(tty, TTY_THROTTLE_SAFE); if (!condition) break; if (!tty_throttle_safe(tty)) break; } __tty_set_flow_change(tty, 0); In this example, if an unthrottle occurs after the condition is evaluated but before tty_throttle_safe(), then tty_throttle_safe() will return non-zero, looping and forcing the re-evaluation of condition. Reported-by: Vincent Pillet Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index c75d886b0307..189ca80494d1 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -258,6 +258,7 @@ struct tty_struct { unsigned char warned:1; unsigned char ctrl_status; /* ctrl_lock */ unsigned int receive_room; /* Bytes free for queue */ + int flow_change; struct tty_struct *link; struct fasync_struct *fasync; @@ -318,6 +319,21 @@ struct tty_file_private { #define TTY_WRITE_FLUSH(tty) tty_write_flush((tty)) +/* Values for tty->flow_change */ +#define TTY_THROTTLE_SAFE 1 +#define TTY_UNTHROTTLE_SAFE 2 + +static inline void __tty_set_flow_change(struct tty_struct *tty, int val) +{ + tty->flow_change = val; +} + +static inline void tty_set_flow_change(struct tty_struct *tty, int val) +{ + tty->flow_change = val; + smp_mb(); +} + #ifdef CONFIG_TTY extern void console_init(void); extern void tty_kref_put(struct tty_struct *tty); @@ -400,6 +416,8 @@ extern int tty_write_room(struct tty_struct *tty); extern void tty_driver_flush_buffer(struct tty_struct *tty); extern void tty_throttle(struct tty_struct *tty); extern void tty_unthrottle(struct tty_struct *tty); +extern int tty_throttle_safe(struct tty_struct *tty); +extern int tty_unthrottle_safe(struct tty_struct *tty); extern int tty_do_resize(struct tty_struct *tty, struct winsize *ws); extern void tty_driver_remove_tty(struct tty_driver *driver, struct tty_struct *tty); -- cgit v1.2.3 From 6be06e7273c4682a15ca1f4adf1aeae510823530 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Wed, 6 Mar 2013 08:38:21 -0500 Subject: tty: Fix checkpatch errors in tty_ldisc.h Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_ldisc.h | 132 +++++++++++++++++++++++----------------------- 1 file changed, 66 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 455a0d7bf220..58390c73df8b 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -9,89 +9,89 @@ * * int (*open)(struct tty_struct *); * - * This function is called when the line discipline is associated - * with the tty. The line discipline can use this as an - * opportunity to initialize any state needed by the ldisc routines. - * + * This function is called when the line discipline is associated + * with the tty. The line discipline can use this as an + * opportunity to initialize any state needed by the ldisc routines. + * * void (*close)(struct tty_struct *); * * This function is called when the line discipline is being - * shutdown, either because the tty is being closed or because - * the tty is being changed to use a new line discipline - * + * shutdown, either because the tty is being closed or because + * the tty is being changed to use a new line discipline + * * void (*flush_buffer)(struct tty_struct *tty); * - * This function instructs the line discipline to clear its - * buffers of any input characters it may have queued to be - * delivered to the user mode process. - * + * This function instructs the line discipline to clear its + * buffers of any input characters it may have queued to be + * delivered to the user mode process. + * * ssize_t (*chars_in_buffer)(struct tty_struct *tty); * - * This function returns the number of input characters the line + * This function returns the number of input characters the line * discipline may have queued up to be delivered to the user mode * process. - * + * * ssize_t (*read)(struct tty_struct * tty, struct file * file, * unsigned char * buf, size_t nr); * - * This function is called when the user requests to read from - * the tty. The line discipline will return whatever characters - * it has buffered up for the user. If this function is not - * defined, the user will receive an EIO error. - * + * This function is called when the user requests to read from + * the tty. The line discipline will return whatever characters + * it has buffered up for the user. If this function is not + * defined, the user will receive an EIO error. + * * ssize_t (*write)(struct tty_struct * tty, struct file * file, - * const unsigned char * buf, size_t nr); - * - * This function is called when the user requests to write to the - * tty. The line discipline will deliver the characters to the - * low-level tty device for transmission, optionally performing - * some processing on the characters first. If this function is - * not defined, the user will receive an EIO error. - * + * const unsigned char * buf, size_t nr); + * + * This function is called when the user requests to write to the + * tty. The line discipline will deliver the characters to the + * low-level tty device for transmission, optionally performing + * some processing on the characters first. If this function is + * not defined, the user will receive an EIO error. + * * int (*ioctl)(struct tty_struct * tty, struct file * file, - * unsigned int cmd, unsigned long arg); + * unsigned int cmd, unsigned long arg); * * This function is called when the user requests an ioctl which - * is not handled by the tty layer or the low-level tty driver. - * It is intended for ioctls which affect line discpline - * operation. Note that the search order for ioctls is (1) tty - * layer, (2) tty low-level driver, (3) line discpline. So a - * low-level driver can "grab" an ioctl request before the line - * discpline has a chance to see it. - * + * is not handled by the tty layer or the low-level tty driver. + * It is intended for ioctls which affect line discpline + * operation. Note that the search order for ioctls is (1) tty + * layer, (2) tty low-level driver, (3) line discpline. So a + * low-level driver can "grab" an ioctl request before the line + * discpline has a chance to see it. + * * long (*compat_ioctl)(struct tty_struct * tty, struct file * file, - * unsigned int cmd, unsigned long arg); + * unsigned int cmd, unsigned long arg); * - * Process ioctl calls from 32-bit process on 64-bit system + * Process ioctl calls from 32-bit process on 64-bit system * * void (*set_termios)(struct tty_struct *tty, struct ktermios * old); * - * This function notifies the line discpline that a change has - * been made to the termios structure. - * + * This function notifies the line discpline that a change has + * been made to the termios structure. + * * int (*poll)(struct tty_struct * tty, struct file * file, - * poll_table *wait); + * poll_table *wait); * - * This function is called when a user attempts to select/poll on a - * tty device. It is solely the responsibility of the line - * discipline to handle poll requests. + * This function is called when a user attempts to select/poll on a + * tty device. It is solely the responsibility of the line + * discipline to handle poll requests. * * void (*receive_buf)(struct tty_struct *, const unsigned char *cp, - * char *fp, int count); - * - * This function is called by the low-level tty driver to send - * characters received by the hardware to the line discpline for - * processing. is a pointer to the buffer of input - * character received by the device. is a pointer to a - * pointer of flag bytes which indicate whether a character was - * received with a parity error, etc. - * + * char *fp, int count); + * + * This function is called by the low-level tty driver to send + * characters received by the hardware to the line discpline for + * processing. is a pointer to the buffer of input + * character received by the device. is a pointer to a + * pointer of flag bytes which indicate whether a character was + * received with a parity error, etc. + * * void (*write_wakeup)(struct tty_struct *); * - * This function is called by the low-level tty driver to signal - * that line discpline should try to send more characters to the - * low-level driver for transmission. If the line discpline does - * not have any more data to send, it can just return. + * This function is called by the low-level tty driver to signal + * that line discpline should try to send more characters to the + * low-level driver for transmission. If the line discpline does + * not have any more data to send, it can just return. * * int (*hangup)(struct tty_struct *) * @@ -115,7 +115,7 @@ struct tty_ldisc_ops { char *name; int num; int flags; - + /* * The following routines are called from above. */ @@ -123,19 +123,19 @@ struct tty_ldisc_ops { void (*close)(struct tty_struct *); void (*flush_buffer)(struct tty_struct *tty); ssize_t (*chars_in_buffer)(struct tty_struct *tty); - ssize_t (*read)(struct tty_struct * tty, struct file * file, - unsigned char __user * buf, size_t nr); - ssize_t (*write)(struct tty_struct * tty, struct file * file, - const unsigned char * buf, size_t nr); - int (*ioctl)(struct tty_struct * tty, struct file * file, + ssize_t (*read)(struct tty_struct *tty, struct file *file, + unsigned char __user *buf, size_t nr); + ssize_t (*write)(struct tty_struct *tty, struct file *file, + const unsigned char *buf, size_t nr); + int (*ioctl)(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); - long (*compat_ioctl)(struct tty_struct * tty, struct file * file, + long (*compat_ioctl)(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); - void (*set_termios)(struct tty_struct *tty, struct ktermios * old); + void (*set_termios)(struct tty_struct *tty, struct ktermios *old); unsigned int (*poll)(struct tty_struct *, struct file *, struct poll_table_struct *); int (*hangup)(struct tty_struct *tty); - + /* * The following routines are called from below. */ @@ -145,7 +145,7 @@ struct tty_ldisc_ops { void (*dcd_change)(struct tty_struct *, unsigned int); struct module *owner; - + int refcount; }; -- cgit v1.2.3 From 6865ff222ccab371c04afce17aec1f7d70b17dbc Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 7 Mar 2013 13:12:27 +0100 Subject: TTY: do not warn about setting speed via SPD_* The warning is there since 2.1.69 and we have not seen anybody reporting it in the past decade. Remove the warning now. tty_get_baud_rate can now be inline. This gives us one less EXPORT_SYMBOL. Signed-off-by: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 189ca80494d1..63b62865c8e9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -255,7 +255,6 @@ struct tty_struct { int count; struct winsize winsize; /* termios mutex */ unsigned char stopped:1, hw_stopped:1, flow_stopped:1, packet:1; - unsigned char warned:1; unsigned char ctrl_status; /* ctrl_lock */ unsigned int receive_room; /* Bytes free for queue */ int flow_change; @@ -437,13 +436,28 @@ extern void tty_flush_to_ldisc(struct tty_struct *tty); extern void tty_buffer_free_all(struct tty_port *port); extern void tty_buffer_flush(struct tty_struct *tty); extern void tty_buffer_init(struct tty_port *port); -extern speed_t tty_get_baud_rate(struct tty_struct *tty); extern speed_t tty_termios_baud_rate(struct ktermios *termios); extern speed_t tty_termios_input_baud_rate(struct ktermios *termios); extern void tty_termios_encode_baud_rate(struct ktermios *termios, speed_t ibaud, speed_t obaud); extern void tty_encode_baud_rate(struct tty_struct *tty, speed_t ibaud, speed_t obaud); + +/** + * tty_get_baud_rate - get tty bit rates + * @tty: tty to query + * + * Returns the baud rate as an integer for this terminal. The + * termios lock must be held by the caller and the terminal bit + * flags may be updated. + * + * Locking: none + */ +static inline speed_t tty_get_baud_rate(struct tty_struct *tty) +{ + return tty_termios_baud_rate(&tty->termios); +} + extern void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old); extern int tty_termios_hw_change(struct ktermios *a, struct ktermios *b); extern int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); -- cgit v1.2.3 From 6aad04f21374633bd8cecf25024553d1e11a9522 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 7 Mar 2013 13:12:29 +0100 Subject: TTY: add tty_port_tty_wakeup helper It allows for cleaning up on a considerable amount of places. They did port_get, wakeup, kref_put. Now the only thing needed is to call tty_port_tty_wakeup which does exactly that. One exception is ifx6x60 where tty_wakeup was open-coded. We now call tty_wakeup properly there. Signed-off-by: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 63b62865c8e9..b6e890a87eb1 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -534,6 +534,7 @@ extern int tty_port_carrier_raised(struct tty_port *port); extern void tty_port_raise_dtr_rts(struct tty_port *port); extern void tty_port_lower_dtr_rts(struct tty_port *port); extern void tty_port_hangup(struct tty_port *port); +extern void tty_port_tty_wakeup(struct tty_port *port); extern int tty_port_block_til_ready(struct tty_port *port, struct tty_struct *tty, struct file *filp); extern int tty_port_close_start(struct tty_port *port, -- cgit v1.2.3 From aa27a094e2c2e0cc59914e56113b860f524f4479 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 7 Mar 2013 13:12:30 +0100 Subject: TTY: add tty_port_tty_hangup helper It allows for cleaning up on a considerable amount of places. They did port_get, hangup, kref_put. Now the only thing needed is to call tty_port_tty_hangup which does exactly that. And they can also decide whether to consider CLOCAL or completely ignore that. Signed-off-by: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index b6e890a87eb1..d3548f871968 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -534,6 +534,7 @@ extern int tty_port_carrier_raised(struct tty_port *port); extern void tty_port_raise_dtr_rts(struct tty_port *port); extern void tty_port_lower_dtr_rts(struct tty_port *port); extern void tty_port_hangup(struct tty_port *port); +extern void tty_port_tty_hangup(struct tty_port *port, bool check_clocal); extern void tty_port_tty_wakeup(struct tty_port *port); extern int tty_port_block_til_ready(struct tty_port *port, struct tty_struct *tty, struct file *filp); -- cgit v1.2.3 From 21622939fc452c7fb739464b8e49368c3ceaa0ee Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Mon, 11 Mar 2013 16:44:21 -0400 Subject: tty: Add diagnostic for halted line discipline Flip buffer work must not be scheduled by the line discipline after the line discipline has been halted; issue warning. Note: drivers can still schedule flip buffer work. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index d3548f871968..66ae020e8a98 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -315,6 +315,7 @@ struct tty_file_private { #define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */ #define TTY_HUPPED 18 /* Post driver->hangup() */ #define TTY_HUPPING 21 /* ->hangup() in progress */ +#define TTY_LDISC_HALTED 22 /* Line discipline is halted */ #define TTY_WRITE_FLUSH(tty) tty_write_flush((tty)) -- cgit v1.2.3 From d912156605b0eb3b3070dc7eabc43db6379aa43b Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Mon, 11 Mar 2013 16:44:33 -0400 Subject: tty: Don't reenable already enabled ldisc tty_ldisc_hangup() guarantees the ldisc is enabled (or that there is no ldisc). Since __tty_hangup() was the only user, re-define tty_ldisc_enable() in file-scope. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 66ae020e8a98..367a9dfc4ea2 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -561,8 +561,6 @@ extern void tty_ldisc_release(struct tty_struct *tty, struct tty_struct *o_tty); extern void tty_ldisc_init(struct tty_struct *tty); extern void tty_ldisc_deinit(struct tty_struct *tty); extern void tty_ldisc_begin(void); -/* This last one is just for the tty layer internals and shouldn't be used elsewhere */ -extern void tty_ldisc_enable(struct tty_struct *tty); /* n_tty.c */ -- cgit v1.2.3 From 6f8da5df8c451103e0043f73a00c90676da6be9e Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Tue, 12 Mar 2013 18:08:09 -0400 Subject: power_supply: Add support for tps65090-charger This patch adds support for the tps65090 charger driver. This driver is responsible for controlling the charger aspect of the tps65090 mfd. Currently, this mainly consists of turning on and off the charger, but some features of the charger can be supported through this driver including: - Enable Auto Recharge based on Battery voltage - Fast Charge Safety Timer - Maximum battery discharge current - Maximum battery adapter current - Enable External Charge - Disable charging termination based on low charger current (supported) Once the driver is accepted, later patches can add support for the features above which are not yet supported. Based on work by: Syed Rafiuddin Laxman Dewangan Signed-off-by: Rhyland Klein Signed-off-by: Anton Vorontsov --- include/linux/mfd/tps65090.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65090.h b/include/linux/mfd/tps65090.h index 6694cf43e8b8..998628a2b08b 100644 --- a/include/linux/mfd/tps65090.h +++ b/include/linux/mfd/tps65090.h @@ -86,6 +86,11 @@ struct tps65090_regulator_plat_data { struct tps65090_platform_data { int irq_base; + + char **supplied_to; + size_t num_supplicants; + int enable_low_current_chrg; + struct tps65090_regulator_plat_data *reg_pdata[TPS65090_REGULATOR_MAX]; }; -- cgit v1.2.3 From 3d6ee287a3e341c88eafd0b4620b12d640b3736b Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 12 Mar 2013 20:26:02 +0100 Subject: clk: Introduce optional is_prepared callback To reflect whether a clk_hw is prepared the clk_hw may implement the optional is_prepared callback. If not implemented we fall back to use the software prepare counter. Signed-off-by: Ulf Hansson Acked-by: Linus Walleij Signed-off-by: Mike Turquette --- include/linux/clk-provider.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 7f197d7addb0..ee946862e058 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -45,6 +45,10 @@ struct clk_hw; * undo any work done in the @prepare callback. Called with * prepare_lock held. * + * @is_prepared: Queries the hardware to determine if the clock is prepared. + * This function is allowed to sleep. Optional, if this op is not + * set then the prepare count will be used. + * * @enable: Enable the clock atomically. This must not return until the * clock is generating a valid clock signal, usable by consumer * devices. Called with enable_lock held. This function must not @@ -108,6 +112,7 @@ struct clk_hw; struct clk_ops { int (*prepare)(struct clk_hw *hw); void (*unprepare)(struct clk_hw *hw); + int (*is_prepared)(struct clk_hw *hw); int (*enable)(struct clk_hw *hw); void (*disable)(struct clk_hw *hw); int (*is_enabled)(struct clk_hw *hw); @@ -351,6 +356,7 @@ unsigned int __clk_get_enable_count(struct clk *clk); unsigned int __clk_get_prepare_count(struct clk *clk); unsigned long __clk_get_rate(struct clk *clk); unsigned long __clk_get_flags(struct clk *clk); +bool __clk_is_prepared(struct clk *clk); bool __clk_is_enabled(struct clk *clk); struct clk *__clk_lookup(const char *name); -- cgit v1.2.3 From 3cc8247f1dce79511de8bf0f69ab02a46cc315b7 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 12 Mar 2013 20:26:04 +0100 Subject: clk: Introduce optional unprepare_unused callback An unprepare_unused callback is introduced due to the same reasons to why the disable_unused callback was added. During the clk_disable_unused sequence, those clk_hw that needs specific treatment with regards to being unprepared, shall implement the unprepare_unused callback. Signed-off-by: Ulf Hansson Acked-by: Linus Walleij Signed-off-by: Mike Turquette --- include/linux/clk-provider.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index ee946862e058..56e6cc12c796 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -49,6 +49,10 @@ struct clk_hw; * This function is allowed to sleep. Optional, if this op is not * set then the prepare count will be used. * + * @unprepare_unused: Unprepare the clock atomically. Only called from + * clk_disable_unused for prepare clocks with special needs. + * Called with prepare mutex held. This function may sleep. + * * @enable: Enable the clock atomically. This must not return until the * clock is generating a valid clock signal, usable by consumer * devices. Called with enable_lock held. This function must not @@ -113,6 +117,7 @@ struct clk_ops { int (*prepare)(struct clk_hw *hw); void (*unprepare)(struct clk_hw *hw); int (*is_prepared)(struct clk_hw *hw); + void (*unprepare_unused)(struct clk_hw *hw); int (*enable)(struct clk_hw *hw); void (*disable)(struct clk_hw *hw); int (*is_enabled)(struct clk_hw *hw); -- cgit v1.2.3 From 14a40ffccd6163bbcd1d6f32b28a88ffe6149fc6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 19 Mar 2013 13:45:20 -0700 Subject: sched: replace PF_THREAD_BOUND with PF_NO_SETAFFINITY PF_THREAD_BOUND was originally used to mark kernel threads which were bound to a specific CPU using kthread_bind() and a task with the flag set allows cpus_allowed modifications only to itself. Workqueue is currently abusing it to prevent userland from meddling with cpus_allowed of workqueue workers. What we need is a flag to prevent userland from messing with cpus_allowed of certain kernel tasks. In kernel, anyone can (incorrectly) squash the flag, and, for worker-type usages, restricting cpus_allowed modification to the task itself doesn't provide meaningful extra proection as other tasks can inject work items to the task anyway. This patch replaces PF_THREAD_BOUND with PF_NO_SETAFFINITY. sched_setaffinity() checks the flag and return -EINVAL if set. set_cpus_allowed_ptr() is no longer affected by the flag. This will allow simplifying workqueue worker CPU affinity management. Signed-off-by: Tejun Heo Acked-by: Ingo Molnar Reviewed-by: Lai Jiangshan Cc: Peter Zijlstra Cc: Thomas Gleixner --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6ddbfb..e5c64f7b8c1d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1793,7 +1793,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ #define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */ #define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */ -#define PF_THREAD_BOUND 0x04000000 /* Thread bound to specific cpu */ +#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ -- cgit v1.2.3 From 4d10f054f7df600ec8a388091c93b2d976920de0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 19 Mar 2013 15:38:50 +0100 Subject: clocksource: make CLOCKSOURCE_OF_DECLARE type safe This ensures that a function pointer passed into CLOCKSOURCE_OF_DECLARE takes the same arguments that we use for calling that function later. Also fix the extraneous semicolon at end of the CLOCKSOURCE_OF_DECLARE definition. Signed-off-by: Arnd Bergmann Acked-by: Rob Herring --- include/linux/clocksource.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 08ed5e19d8c6..ac33184b14fd 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -332,16 +332,23 @@ extern int clocksource_mmio_init(void __iomem *, const char *, extern int clocksource_i8253_init(void); +struct device_node; +typedef void(*clocksource_of_init_fn)(struct device_node *); #ifdef CONFIG_CLKSRC_OF extern void clocksource_of_init(void); #define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \ static const struct of_device_id __clksrc_of_table_##name \ __used __section(__clksrc_of_table) \ - = { .compatible = compat, .data = fn }; + = { .compatible = compat, \ + .data = (fn == (clocksource_of_init_fn)NULL) ? fn : fn } #else static inline void clocksource_of_init(void) {} -#define CLOCKSOURCE_OF_DECLARE(name, compat, fn) +#define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \ + static const struct of_device_id __clksrc_of_table_##name \ + __unused __section(__clksrc_of_table) \ + = { .compatible = compat, \ + .data = (fn == (clocksource_of_init_fn)NULL) ? fn : fn } #endif #endif /* _LINUX_CLOCKSOURCE_H */ -- cgit v1.2.3 From a9a0fef779074838230e04a322fd2bdc921f4f4f Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 18 Mar 2013 13:22:19 +1030 Subject: virtio_ring: expose virtio barriers for use in vringh. The host side of ring needs this logic too. Signed-off-by: Rusty Russell --- include/linux/virtio_ring.h | 57 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 63c6ea199519..ca3ad41c2c82 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -4,6 +4,63 @@ #include #include +/* + * Barriers in virtio are tricky. Non-SMP virtio guests can't assume + * they're not on an SMP host system, so they need to assume real + * barriers. Non-SMP virtio hosts could skip the barriers, but does + * anyone care? + * + * For virtio_pci on SMP, we don't need to order with respect to MMIO + * accesses through relaxed memory I/O windows, so smp_mb() et al are + * sufficient. + * + * For using virtio to talk to real devices (eg. other heterogeneous + * CPUs) we do need real barriers. In theory, we could be using both + * kinds of virtio, so it's a runtime decision, and the branch is + * actually quite cheap. + */ + +#ifdef CONFIG_SMP +static inline void virtio_mb(bool weak_barriers) +{ + if (weak_barriers) + smp_mb(); + else + mb(); +} + +static inline void virtio_rmb(bool weak_barriers) +{ + if (weak_barriers) + smp_rmb(); + else + rmb(); +} + +static inline void virtio_wmb(bool weak_barriers) +{ + if (weak_barriers) + smp_wmb(); + else + wmb(); +} +#else +static inline void virtio_mb(bool weak_barriers) +{ + mb(); +} + +static inline void virtio_rmb(bool weak_barriers) +{ + rmb(); +} + +static inline void virtio_wmb(bool weak_barriers) +{ + wmb(); +} +#endif + struct virtio_device; struct virtqueue; -- cgit v1.2.3 From f87d0fbb579818fed3eeb0923cc253163ab93039 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 20 Mar 2013 13:50:14 +1030 Subject: vringh: host-side implementation of virtio rings. Getting use of virtio rings correct is tricky, and a recent patch saw an implementation of in-kernel rings (as separate from userspace). This abstracts the business of dealing with the virtio ring layout from the access (userspace or direct); to do this, we use function pointers, which gcc inlines correctly. Signed-off-by: Rusty Russell Acked-by: Michael S. Tsirkin --- include/linux/vringh.h | 196 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 196 insertions(+) create mode 100644 include/linux/vringh.h (limited to 'include/linux') diff --git a/include/linux/vringh.h b/include/linux/vringh.h new file mode 100644 index 000000000000..b8f086625c49 --- /dev/null +++ b/include/linux/vringh.h @@ -0,0 +1,196 @@ +/* + * Linux host-side vring helpers; for when the kernel needs to access + * someone else's vring. + * + * Copyright IBM Corporation, 2013. + * Parts taken from drivers/vhost/vhost.c Copyright 2009 Red Hat, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Written by: Rusty Russell + */ +#ifndef _LINUX_VRINGH_H +#define _LINUX_VRINGH_H +#include +#include +#include +#include + +/* virtio_ring with information needed for host access. */ +struct vringh { + /* Guest publishes used event idx (note: we always do). */ + bool event_indices; + + /* Can we get away with weak barriers? */ + bool weak_barriers; + + /* Last available index we saw (ie. where we're up to). */ + u16 last_avail_idx; + + /* Last index we used. */ + u16 last_used_idx; + + /* How many descriptors we've completed since last need_notify(). */ + u32 completed; + + /* The vring (note: it may contain user pointers!) */ + struct vring vring; +}; + +/* The memory the vring can access, and what offset to apply. */ +struct vringh_range { + u64 start, end_incl; + u64 offset; +}; + +/** + * struct vringh_iov - iovec mangler. + * + * Mangles iovec in place, and restores it. + * Remaining data is iov + i, of used - i elements. + */ +struct vringh_iov { + struct iovec *iov; + size_t consumed; /* Within iov[i] */ + unsigned i, used, max_num; +}; + +/** + * struct vringh_iov - kvec mangler. + * + * Mangles kvec in place, and restores it. + * Remaining data is iov + i, of used - i elements. + */ +struct vringh_kiov { + struct kvec *iov; + size_t consumed; /* Within iov[i] */ + unsigned i, used, max_num; +}; + +/* Flag on max_num to indicate we're kmalloced. */ +#define VRINGH_IOV_ALLOCATED 0x8000000 + +/* Helpers for userspace vrings. */ +int vringh_init_user(struct vringh *vrh, u32 features, + unsigned int num, bool weak_barriers, + struct vring_desc __user *desc, + struct vring_avail __user *avail, + struct vring_used __user *used); + +static inline void vringh_iov_init(struct vringh_iov *iov, + struct iovec *iovec, unsigned num) +{ + iov->used = iov->i = 0; + iov->consumed = 0; + iov->max_num = num; + iov->iov = iovec; +} + +static inline void vringh_iov_reset(struct vringh_iov *iov) +{ + iov->iov[iov->i].iov_len += iov->consumed; + iov->iov[iov->i].iov_base -= iov->consumed; + iov->consumed = 0; + iov->i = 0; +} + +static inline void vringh_iov_cleanup(struct vringh_iov *iov) +{ + if (iov->max_num & VRINGH_IOV_ALLOCATED) + kfree(iov->iov); + iov->max_num = iov->used = iov->i = iov->consumed = 0; + iov->iov = NULL; +} + +/* Convert a descriptor into iovecs. */ +int vringh_getdesc_user(struct vringh *vrh, + struct vringh_iov *riov, + struct vringh_iov *wiov, + bool (*getrange)(struct vringh *vrh, + u64 addr, struct vringh_range *r), + u16 *head); + +/* Copy bytes from readable vsg, consuming it (and incrementing wiov->i). */ +ssize_t vringh_iov_pull_user(struct vringh_iov *riov, void *dst, size_t len); + +/* Copy bytes into writable vsg, consuming it (and incrementing wiov->i). */ +ssize_t vringh_iov_push_user(struct vringh_iov *wiov, + const void *src, size_t len); + +/* Mark a descriptor as used. */ +int vringh_complete_user(struct vringh *vrh, u16 head, u32 len); +int vringh_complete_multi_user(struct vringh *vrh, + const struct vring_used_elem used[], + unsigned num_used); + +/* Pretend we've never seen descriptor (for easy error handling). */ +void vringh_abandon_user(struct vringh *vrh, unsigned int num); + +/* Do we need to fire the eventfd to notify the other side? */ +int vringh_need_notify_user(struct vringh *vrh); + +bool vringh_notify_enable_user(struct vringh *vrh); +void vringh_notify_disable_user(struct vringh *vrh); + +/* Helpers for kernelspace vrings. */ +int vringh_init_kern(struct vringh *vrh, u32 features, + unsigned int num, bool weak_barriers, + struct vring_desc *desc, + struct vring_avail *avail, + struct vring_used *used); + +static inline void vringh_kiov_init(struct vringh_kiov *kiov, + struct kvec *kvec, unsigned num) +{ + kiov->used = kiov->i = 0; + kiov->consumed = 0; + kiov->max_num = num; + kiov->iov = kvec; +} + +static inline void vringh_kiov_reset(struct vringh_kiov *kiov) +{ + kiov->iov[kiov->i].iov_len += kiov->consumed; + kiov->iov[kiov->i].iov_base -= kiov->consumed; + kiov->consumed = 0; + kiov->i = 0; +} + +static inline void vringh_kiov_cleanup(struct vringh_kiov *kiov) +{ + if (kiov->max_num & VRINGH_IOV_ALLOCATED) + kfree(kiov->iov); + kiov->max_num = kiov->used = kiov->i = kiov->consumed = 0; + kiov->iov = NULL; +} + +int vringh_getdesc_kern(struct vringh *vrh, + struct vringh_kiov *riov, + struct vringh_kiov *wiov, + u16 *head, + gfp_t gfp); + +ssize_t vringh_iov_pull_kern(struct vringh_kiov *riov, void *dst, size_t len); +ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov, + const void *src, size_t len); +void vringh_abandon_kern(struct vringh *vrh, unsigned int num); +int vringh_complete_kern(struct vringh *vrh, u16 head, u32 len); + +bool vringh_notify_enable_kern(struct vringh *vrh); +void vringh_notify_disable_kern(struct vringh *vrh); + +int vringh_need_notify_kern(struct vringh *vrh); + +#endif /* _LINUX_VRINGH_H */ -- cgit v1.2.3 From 3beee86a4b9374e38dba36b44e81f1423a0d6b54 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sjur=20Br=C3=A6ndeland?= Date: Wed, 20 Mar 2013 13:51:24 +1030 Subject: virtio: Introduce vringh wrappers in virtio_config MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add wrappers for the host vrings to support loose coupling between the virtio device and driver. A new struct vringh_config_ops with the functions find_vrhs() and del_vrhs() is added to the virtio_device struct. This enables virtio drivers to manage virtio host rings without detailed knowledge of how the vrings are created and deleted. The function vringh_notify() is added so vringh clients can notify the other side that buffers are added to the used-ring. Cc: Ohad Ben-Cohen Signed-off-by: Sjur Brændeland Signed-off-by: Rusty Russell (constified vringh_config) --- include/linux/virtio.h | 3 +++ include/linux/vringh.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index ff6714e6d0f5..5d5b3abc283d 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -8,6 +8,7 @@ #include #include #include +#include /** * virtqueue - a queue to register buffers for sending or receiving. @@ -70,6 +71,7 @@ static inline unsigned int virtqueue_get_queue_index(struct virtqueue *vq) * @dev: underlying device. * @id: the device type identification (used to match it with a driver). * @config: the configuration ops for this device. + * @vringh_config: configuration ops for host vrings. * @vqs: the list of virtqueues for this device. * @features: the features supported by both driver and device. * @priv: private pointer for the driver's use. @@ -79,6 +81,7 @@ struct virtio_device { struct device dev; struct virtio_device_id id; const struct virtio_config_ops *config; + const struct vringh_config_ops *vringh_config; struct list_head vqs; /* Note that this is a Linux set_bit-style bitmap. */ unsigned long features[1]; diff --git a/include/linux/vringh.h b/include/linux/vringh.h index b8f086625c49..749cde28728b 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -47,6 +47,28 @@ struct vringh { /* The vring (note: it may contain user pointers!) */ struct vring vring; + + /* The function to call to notify the guest about added buffers */ + void (*notify)(struct vringh *); +}; + +/** + * struct vringh_config_ops - ops for creating a host vring from a virtio driver + * @find_vrhs: find the host vrings and instantiate them + * vdev: the virtio_device + * nhvrs: the number of host vrings to find + * hvrs: on success, includes new host vrings + * callbacks: array of driver callbacks, for each host vring + * include a NULL entry for vqs that do not need a callback + * Returns 0 on success or error status + * @del_vrhs: free the host vrings found by find_vrhs(). + */ +struct virtio_device; +typedef void vrh_callback_t(struct virtio_device *, struct vringh *); +struct vringh_config_ops { + int (*find_vrhs)(struct virtio_device *vdev, unsigned nhvrs, + struct vringh *vrhs[], vrh_callback_t *callbacks[]); + void (*del_vrhs)(struct virtio_device *vdev); }; /* The memory the vring can access, and what offset to apply. */ @@ -193,4 +215,11 @@ void vringh_notify_disable_kern(struct vringh *vrh); int vringh_need_notify_kern(struct vringh *vrh); +/* Notify the guest about buffers added to the used ring */ +static inline void vringh_notify(struct vringh *vrh) +{ + if (vrh->notify) + vrh->notify(vrh); +} + #endif /* _LINUX_VRINGH_H */ -- cgit v1.2.3 From 0d2e1a2926b1839a4b74519e660739b2566c9386 Mon Sep 17 00:00:00 2001 From: Erwan Yvin Date: Wed, 20 Mar 2013 13:52:24 +1030 Subject: caif_virtio: Introduce caif over virtio Add the CAIF Virtio shared memory driver for talking to a modem. This CAIF Link layer communicates to the modem over shared memory. It is implemented as a virtio_driver. The underlying virtio device is managed by the remoteproc framework. The Virtio queue is used for transmitting data to the modem, and the new vringh is used for receiving data. Genalloc is used for managing the shared memory used for TX data. The default dma-alloc-coherent allocator can only allocate whole pages, and this wastes too much shared memory. Flow control is implemented by stopping the TX-queues if the virtio queues go full or we run out of memory. Queued are reopened when queues are below the watermark. NAPI is used in RX path, and a dedicated tasklet is used for releasing TX buffers. Signed-off-by: Erwan Yvin Acked-by: David S. Miller Signed-off-by: Rusty Russell (minor fixes) --- include/linux/virtio_caif.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) create mode 100644 include/linux/virtio_caif.h (limited to 'include/linux') diff --git a/include/linux/virtio_caif.h b/include/linux/virtio_caif.h new file mode 100644 index 000000000000..5d2d3124ca3d --- /dev/null +++ b/include/linux/virtio_caif.h @@ -0,0 +1,24 @@ +/* + * Copyright (C) ST-Ericsson AB 2012 + * Author: Sjur Brændeland + * + * This header is BSD licensed so + * anyone can use the definitions to implement compatible remote processors + */ + +#ifndef VIRTIO_CAIF_H +#define VIRTIO_CAIF_H + +#include +struct virtio_caif_transf_config { + u16 headroom; + u16 tailroom; + u32 mtu; + u8 reserved[4]; +}; + +struct virtio_caif_config { + struct virtio_caif_transf_config uplink, downlink; + u8 reserved[8]; +}; +#endif -- cgit v1.2.3 From c8164d8931fdee9ac5314708c4071adf1d997425 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 20 Mar 2013 15:37:08 +1030 Subject: scatterlist: introduce sg_unmark_end This is useful in places that recycle the same scatterlist multiple times, and do not want to incur the cost of sg_init_table every time in hot paths. Acked-by: Jens Axboe Signed-off-by: Paolo Bonzini Signed-off-by: Rusty Russell --- include/linux/scatterlist.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 2d8bdaef9611..bfc47e0de81c 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -171,6 +171,22 @@ static inline void sg_mark_end(struct scatterlist *sg) sg->page_link &= ~0x01; } +/** + * sg_unmark_end - Undo setting the end of the scatterlist + * @sg: SG entryScatterlist + * + * Description: + * Removes the termination marker from the given entry of the scatterlist. + * + **/ +static inline void sg_unmark_end(struct scatterlist *sg) +{ +#ifdef CONFIG_DEBUG_SG + BUG_ON(sg->sg_magic != SG_MAGIC); +#endif + sg->page_link &= ~0x02; +} + /** * sg_phys - Return physical address of an sg entry * @sg: SG entry -- cgit v1.2.3 From 13816c768d46586e925b22736992258d6105ad2c Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 20 Mar 2013 15:37:09 +1030 Subject: virtio_ring: virtqueue_add_sgs, to add multiple sgs. virtio_scsi can really use this, to avoid the current hack of copying the whole sg array. Some other things get slightly neater, too. This causes a slowdown in virtqueue_add_buf(), which is implemented as a wrapper. This is addressed in the next patches. for i in `seq 50`; do /usr/bin/time -f 'Wall time:%e' ./vringh_test --indirect --eventidx --parallel --fast-vringh; done 2>&1 | stats --trim-outliers: Before: Using CPUS 0 and 3 Guest: notified 0, pinged 39009-39063(39062) Host: notified 39009-39063(39062), pinged 0 Wall time:1.700000-1.950000(1.723542) After: Using CPUS 0 and 3 Guest: notified 0, pinged 39062-39063(39063) Host: notified 39062-39063(39063), pinged 0 Wall time:1.760000-2.220000(1.789167) Signed-off-by: Rusty Russell Reviewed-by: Wanlong Gao Reviewed-by: Asias He --- include/linux/virtio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 5d5b3abc283d..ac80288b2920 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -41,6 +41,13 @@ int virtqueue_add_buf(struct virtqueue *vq, void *data, gfp_t gfp); +int virtqueue_add_sgs(struct virtqueue *vq, + struct scatterlist *sgs[], + unsigned int out_sgs, + unsigned int in_sgs, + void *data, + gfp_t gfp); + void virtqueue_kick(struct virtqueue *vq); bool virtqueue_kick_prepare(struct virtqueue *vq); -- cgit v1.2.3 From 282edb36499042a92b71f052f51754ae7ed936e4 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 20 Mar 2013 15:44:26 +1030 Subject: virtio_ring: virtqueue_add_outbuf / virtqueue_add_inbuf. These are specialized versions of virtqueue_add_buf(), which cover over 80% of cases and are far clearer. In particular, the scatterlists passed to these functions don't have to be clean (ie. we ignore end markers). Signed-off-by: Rusty Russell --- include/linux/virtio.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index ac80288b2920..833f17b6a743 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -41,6 +41,16 @@ int virtqueue_add_buf(struct virtqueue *vq, void *data, gfp_t gfp); +int virtqueue_add_outbuf(struct virtqueue *vq, + struct scatterlist sg[], unsigned int num, + void *data, + gfp_t gfp); + +int virtqueue_add_inbuf(struct virtqueue *vq, + struct scatterlist sg[], unsigned int num, + void *data, + gfp_t gfp); + int virtqueue_add_sgs(struct virtqueue *vq, struct scatterlist *sgs[], unsigned int out_sgs, -- cgit v1.2.3 From 081aa458c38ba576bdd4265fc807fa95b48b9e79 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 13 Mar 2013 09:17:09 +0800 Subject: cgroup: consolidate cgroup_attach_task() and cgroup_attach_proc() These two functions share most of the code. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 7e818a3ef60a..01c48c6806d6 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -693,7 +693,8 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp, struct cgroup_iter *it); void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); -int cgroup_attach_task(struct cgroup *, struct task_struct *); +int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk, + bool threadgroup); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); /* -- cgit v1.2.3 From f77668dc25b27270fe589031b22c432c3462b1d8 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 19 Mar 2013 06:39:30 +0000 Subject: net: flow_dissector: add __skb_get_poff to get a start offset to payload __skb_get_poff() returns the offset to the payload as far as it could be dissected. The main user is currently BPF, so that we can dynamically truncate packets without needing to push actual payload to the user space and instead can analyze headers only. Suggested-by: Eric Dumazet Signed-off-by: Daniel Borkmann Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b66ecc6ef102..497412165b1c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2840,6 +2840,8 @@ static inline void skb_checksum_none_assert(const struct sk_buff *skb) bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); +u32 __skb_get_poff(const struct sk_buff *skb); + /** * skb_head_is_locked - Determine if the skb->head is locked down * @skb: skb to check -- cgit v1.2.3 From 3e5289d5e3f98b7b5b8cac32e9e5a7004c067436 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 19 Mar 2013 06:39:31 +0000 Subject: filter: add ANC_PAY_OFFSET instruction for loading payload start offset It is very useful to do dynamic truncation of packets. In particular, we're interested to push the necessary header bytes to the user space and cut off user payload that should probably not be transferred for some reasons (e.g. privacy, speed, or others). With the ancillary extension PAY_OFFSET, we can load it into the accumulator, and return it. E.g. in bpfc syntax ... ld #poff ; { 0x20, 0, 0, 0xfffff034 }, ret a ; { 0x16, 0, 0, 0x00000000 }, ... as a filter will accomplish this without having to do a big hackery in a BPF filter itself. Follow-up JIT implementations are welcome. Thanks to Eric Dumazet for suggesting and discussing this during the Netfilter Workshop in Copenhagen. Suggested-by: Eric Dumazet Signed-off-by: Daniel Borkmann Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index c45eabc135e1..d2059cb4e465 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -126,6 +126,7 @@ enum { BPF_S_ANC_SECCOMP_LD_W, BPF_S_ANC_VLAN_TAG, BPF_S_ANC_VLAN_TAG_PRESENT, + BPF_S_ANC_PAY_OFFSET, }; #endif /* __LINUX_FILTER_H__ */ -- cgit v1.2.3 From 2b5faa4c553f90ee2dde1d976b220b1ca9741ef0 Mon Sep 17 00:00:00 2001 From: Jesper Derehag Date: Tue, 19 Mar 2013 20:50:05 +0000 Subject: connector: Added coredumping event to the process connector Process connector can now also detect coredumping events. Main aim of patch is get notified at start of coredumping, instead of having to wait for it to finish and then being notified through EXIT event. Could be used for instance by process-managers that want to get notified as soon as possible about process failures, and not necessarily beeing notified after coredump, which could be in the order of minutes depending on size of coredump, piping and so on. Signed-off-by: Jesper Derehag Signed-off-by: David S. Miller --- include/linux/cn_proc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cn_proc.h b/include/linux/cn_proc.h index 2c1bc1ea04ee..1d5b02a96c46 100644 --- a/include/linux/cn_proc.h +++ b/include/linux/cn_proc.h @@ -26,6 +26,7 @@ void proc_id_connector(struct task_struct *task, int which_id); void proc_sid_connector(struct task_struct *task); void proc_ptrace_connector(struct task_struct *task, int which_id); void proc_comm_connector(struct task_struct *task); +void proc_coredump_connector(struct task_struct *task); void proc_exit_connector(struct task_struct *task); #else static inline void proc_fork_connector(struct task_struct *task) @@ -48,6 +49,9 @@ static inline void proc_ptrace_connector(struct task_struct *task, int ptrace_id) {} +static inline void proc_coredump_connector(struct task_struct *task) +{} + static inline void proc_exit_connector(struct task_struct *task) {} #endif /* CONFIG_PROC_EVENTS */ -- cgit v1.2.3 From a831881be220358a1d28c5d95d69449fb6d623ca Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 18 Dec 2012 17:32:19 +0100 Subject: nohz: Basic full dynticks interface For extreme usecases such as Real Time or HPC, having the ability to shutdown the tick when a single task runs on a CPU is a desired feature: * Reducing the amount of interrupts improves throughput for CPU-bound tasks. The CPU is less distracted from its real job, from an execution time and from the cache point of views. * This also improve latency response as we have less critical sections. Start with introducing a very simple interface to define full dynticks CPU: use a boot time option defined cpumask through the "nohz_extended=" kernel parameter. CPUs that are part of this range will have their tick shutdown whenever possible: provided they run a single task and they don't do kernel activity that require the periodic tick. These details will be later documented in Documentation/* An online CPU must be kept outside this range to handle the timekeeping. Suggested-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- include/linux/tick.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 553272e6af55..44bfa8aa439f 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -157,6 +157,13 @@ static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } # endif /* !NO_HZ */ +#ifdef CONFIG_NO_HZ_EXTENDED +extern int tick_nohz_extended_cpu(int cpu); +#else +static inline int tick_nohz_extended_cpu(int cpu) { return 0; } +#endif + + # ifdef CONFIG_CPU_IDLE_GOV_MENU extern void menu_hrtimer_cancel(void); # else -- cgit v1.2.3 From 1c20091e77fc5a9b7d7d905176443b4822a23cdb Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Aug 2011 23:21:01 +0200 Subject: nohz: Wake up full dynticks CPUs when a timer gets enqueued Wake up a CPU when a timer list timer is enqueued there and the target is part of the full dynticks range. Sending an IPI to it makes it reconsidering the next timer to program on top of recent updates. This may later be improved by checking if the tick is really stopped on the target. This would need some careful synchronization though. So deal with such optimization later and start simple. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9004f6e19eac..10626e2ee688 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1851,9 +1851,9 @@ static inline void idle_task_exit(void) {} #endif #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) -extern void wake_up_idle_cpu(int cpu); +extern void wake_up_nohz_cpu(int cpu); #else -static inline void wake_up_idle_cpu(int cpu) { } +static inline void wake_up_nohz_cpu(int cpu) { } #endif #ifdef CONFIG_SCHED_AUTOGROUP -- cgit v1.2.3 From 65deb782858128cde598ac4a9150ab7cdd29dafa Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Thu, 28 Feb 2013 16:43:19 +0000 Subject: arm: vexpress: Decouple vexpress-poweroff implementation from machine_desc This patch adds the pm_power_off and arm_pm_restart variable settings to the vexpress-poweroff.c driver to decouple it from the machine_desc definition. Signed-off-by: Catalin Marinas Acked-by: Pawel Moll --- include/linux/vexpress.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h index 75818744ab59..ea7168a68081 100644 --- a/include/linux/vexpress.h +++ b/include/linux/vexpress.h @@ -115,9 +115,6 @@ unsigned __vexpress_get_site(struct device *dev, struct device_node *node); void vexpress_sysreg_early_init(void __iomem *base); void vexpress_sysreg_of_early_init(void); -void vexpress_power_off(void); -void vexpress_restart(char str, const char *cmd); - /* Clocks */ struct clk *vexpress_osc_setup(struct device *dev); -- cgit v1.2.3 From 9b44190dc114c1720b34975b5bfc65aece112ced Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 20 Mar 2013 13:32:58 +0000 Subject: tcp: refactor F-RTO The patch series refactor the F-RTO feature (RFC4138/5682). This is to simplify the loss recovery processing. Existing F-RTO was developed during the experimental stage (RFC4138) and has many experimental features. It takes a separate code path from the traditional timeout processing by overloading CA_Disorder instead of using CA_Loss state. This complicates CA_Disorder state handling because it's also used for handling dubious ACKs and undos. While the algorithm in the RFC does not change the congestion control, the implementation intercepts congestion control in various places (e.g., frto_cwnd in tcp_ack()). The new code implements newer F-RTO RFC5682 using CA_Loss processing path. F-RTO becomes a small extension in the timeout processing and interfaces with congestion control and Eifel undo modules. It lets congestion control (module) determines how many to send independently. F-RTO only chooses what to send in order to detect spurious retranmission. If timeout is found spurious it invokes existing Eifel undo algorithms like DSACK or TCP timestamp based detection. The first patch removes all F-RTO code except the sysctl_tcp_frto is left for the new implementation. Since CA_EVENT_FRTO is removed, TCP westwood now computes ssthresh on regular timeout CA_EVENT_LOSS event. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index ed6a7456eecd..f5f203b36379 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -187,14 +187,12 @@ struct tcp_sock { u32 window_clamp; /* Maximal window to advertise */ u32 rcv_ssthresh; /* Current window clamp */ - u32 frto_highmark; /* snd_nxt when RTO occurred */ u16 advmss; /* Advertised MSS */ - u8 frto_counter; /* Number of new acks after RTO */ + u8 unused; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ thin_dupack : 1,/* Fast retransmit on first dupack */ - repair : 1, - unused : 1; + repair : 1; u8 repair_queue; u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */ syn_data:1, /* SYN includes data */ -- cgit v1.2.3 From e33099f96d99c391b3325caa9c44258de04aae86 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 20 Mar 2013 13:33:00 +0000 Subject: tcp: implement RFC5682 F-RTO This patch implements F-RTO (foward RTO recovery): When the first retransmission after timeout is acknowledged, F-RTO sends new data instead of old data. If the next ACK acknowledges some never-retransmitted data, then the timeout was spurious and the congestion state is reverted. Otherwise if the next ACK selectively acknowledges the new data, then the timeout was genuine and the loss recovery continues. This idea applies to recurring timeouts as well. While F-RTO sends different data during timeout recovery, it does not (and should not) change the congestion control. The implementaion follows the three steps of SACK enhanced algorithm (section 3) in RFC5682. Step 1 is in tcp_enter_loss(). Step 2 and 3 are in tcp_process_loss(). The basic version is not supported because SACK enhanced version also works for non-SACK connections. The new implementation is functionally in parity with the old F-RTO implementation except the one case where it increases undo events: In addition to the RFC algorithm, a spurious timeout may be detected without sending data in step 2, as long as the SACK confirms not all the original data are dropped. When this happens, the sender will undo the cwnd and perhaps enter fast recovery instead. This additional check increases the F-RTO undo events by 5x compared to the prior implementation on Google Web servers, since the sender often does not have new data to send for HTTP. Note F-RTO may detect spurious timeout before Eifel with timestamps does so. Signed-off-by: Yuchung Cheng Acked-by: Eric Dumazet Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index f5f203b36379..5adbc33d1ab3 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -192,7 +192,8 @@ struct tcp_sock { u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ thin_dupack : 1,/* Fast retransmit on first dupack */ - repair : 1; + repair : 1, + frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */ u8 repair_queue; u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */ syn_data:1, /* SYN includes data */ -- cgit v1.2.3 From 3cf956eebe54cdb7cf1701642085507f0354e56a Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 20 Mar 2013 10:12:10 +0100 Subject: ASoC: wm8994: Support constraining the maximum number of channels clocked Some systems use the audio CODEC to clock a DAI with multiple data lines in parallel, meaning that bit clocks are only required for a smaller number of channels than data is sent for. In some cases providing the extra bit clocks can take the other devices on the audio bus out of spec. Support such systems by allowing a maximum number of channels to be specified. Signed-off-by: Mark Brown --- include/linux/mfd/wm8994/pdata.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8994/pdata.h b/include/linux/mfd/wm8994/pdata.h index 8e21a094836d..68e776594889 100644 --- a/include/linux/mfd/wm8994/pdata.h +++ b/include/linux/mfd/wm8994/pdata.h @@ -17,6 +17,7 @@ #define WM8994_NUM_LDO 2 #define WM8994_NUM_GPIO 11 +#define WM8994_NUM_AIF 3 struct wm8994_ldo_pdata { /** GPIOs to enable regulator, 0 or less if not available */ @@ -215,6 +216,13 @@ struct wm8994_pdata { * system. */ bool spkmode_pu; + + /** + * Maximum number of channels clocks will be generated for, + * useful for systems where and I2S bus with multiple data + * lines is mastered. + */ + int max_channels_clocked[WM8994_NUM_AIF]; }; #endif -- cgit v1.2.3 From 4f1b07581613bf076b0dacdd9a3fb290d3caa227 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 10 Jan 2013 15:38:48 +0000 Subject: mfd: wm5102: Add additional speaker control registers Signed-off-by: Mark Brown --- include/linux/mfd/arizona/registers.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h index a61ce90ecd3f..a47fd358016f 100644 --- a/include/linux/mfd/arizona/registers.h +++ b/include/linux/mfd/arizona/registers.h @@ -217,6 +217,8 @@ #define ARIZONA_PDM_SPK1_CTRL_2 0x491 #define ARIZONA_PDM_SPK2_CTRL_1 0x492 #define ARIZONA_PDM_SPK2_CTRL_2 0x493 +#define ARIZONA_SPK_CTRL_2 0x4B5 +#define ARIZONA_SPK_CTRL_3 0x4B6 #define ARIZONA_DAC_COMP_1 0x4DC #define ARIZONA_DAC_COMP_2 0x4DD #define ARIZONA_DAC_COMP_3 0x4DE -- cgit v1.2.3 From 79617801ea0c0e6664cb497d4c1892c2ff407364 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 21 Mar 2013 22:22:03 +0100 Subject: filter: bpf_jit_comp: refactor and unify BPF JIT image dump output If bpf_jit_enable > 1, then we dump the emitted JIT compiled image after creation. Currently, only SPARC and PowerPC has similar output as in the reference implementation on x86_64. Make a small helper function in order to reduce duplicated code and make the dump output uniform across architectures x86_64, SPARC, PPC, ARM (e.g. on ARM flen, pass and proglen are currently not shown, but would be interesting to know as well), also for future BPF JIT implementations on other archs. Cc: Mircea Gherzan Cc: Matt Evans Cc: Eric Dumazet Cc: David S. Miller Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/filter.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index d2059cb4e465..d7d25083130b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -50,6 +50,16 @@ extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, uns #ifdef CONFIG_BPF_JIT extern void bpf_jit_compile(struct sk_filter *fp); extern void bpf_jit_free(struct sk_filter *fp); + +static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, + u32 pass, void *image) +{ + pr_err("flen=%u proglen=%u pass=%u image=%p\n", + flen, proglen, pass, image); + if (image) + print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_ADDRESS, + 16, 1, image, proglen, false); +} #define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns) #else static inline void bpf_jit_compile(struct sk_filter *fp) -- cgit v1.2.3 From f58b082aed43400c03e53beacc50a9f9eb23ac91 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 6 Mar 2013 23:46:20 +0100 Subject: ACPI / scan: Add special handler for Intel Lynxpoint LPSS devices Devices on the Intel Lynxpoint Low Power Subsystem (LPSS) have some common features that aren't shared with any other platform devices, including the clock and LTR (Latency Tolerance Reporting) registers. It is better to handle those features in common code than to bother device drivers with doing that (I/O functionality-wise the LPSS devices are generally compatible with other devices that don't have those special registers and may be handled by the same drivers). The clock registers of the LPSS devices are now taken care of by the special clk-x86-lpss driver, but the MMIO mappings used for accessing those registers can also be used for accessing the LTR registers on those devices (LTR support for the Lynxpoint LPSS is going to be added by a subsequent patch). Thus it is convenient to add a special ACPI scan handler for the Lynxpoint LPSS devices that will create the MMIO mappings for accessing the clock (and LTR in the future) registers and will register the LPSS devices' clocks, so the clk-x86-lpss driver will only need to take care of the main Lynxpoint LPSS clock. Introduce a special ACPI scan handler for Intel Lynxpoint LPSS devices as described above. This also reduces overhead related to browsing the ACPI namespace in search of the LPSS devices before the registration of their clocks, removes some LPSS-specific (and somewhat ugly) code from acpi_platform.c and shrinks the overall code size slightly. Signed-off-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki Acked-by: Mike Turquette --- include/linux/platform_data/clk-lpss.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/platform_data/clk-lpss.h (limited to 'include/linux') diff --git a/include/linux/platform_data/clk-lpss.h b/include/linux/platform_data/clk-lpss.h new file mode 100644 index 000000000000..528e73ce46d2 --- /dev/null +++ b/include/linux/platform_data/clk-lpss.h @@ -0,0 +1,18 @@ +/* + * Intel Low Power Subsystem clocks. + * + * Copyright (C) 2013, Intel Corporation + * Authors: Mika Westerberg + * Rafael J. Wysocki + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __CLK_LPSS_H +#define __CLK_LPSS_H + +extern int lpt_clk_init(void); + +#endif /* __CLK_LPSS_H */ -- cgit v1.2.3 From 19919226c3f20e6bf5de3df96432ce80ffd63ff2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 22 Mar 2013 10:48:33 +0100 Subject: clockevents: Add missing tick_check_broadcast_expired() for CLOCKEVENTS=n Fengs build robot reports: arch/arm/kernel/process.c: In function 'cpu_idle': arch/arm/kernel/process.c:211:4: error: implicit declaration of function 'tick_check_broadcast_expired' [-Werror=implicit-function-declaration] Add the missing inline function for non clockevent builds Reported-by: Wu Fengguang Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 646aac136eed..464e229e7d84 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -193,6 +193,7 @@ static inline void clockevents_suspend(void) {} static inline void clockevents_resume(void) {} #define clockevents_notify(reason, arg) do { } while (0) +static inline int tick_check_broadcast_expired(void) { return 0; } #endif -- cgit v1.2.3 From 19dde0bd71e3dffb03ddc509019e22250f4e20c0 Mon Sep 17 00:00:00 2001 From: Janusz Dziedzic Date: Thu, 21 Mar 2013 15:47:54 +0100 Subject: cfg80211: add P2P Notice of Absence attribute Add P2P Notice of Absence attribute structure. Signed-off-by: Janusz Dziedzic Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 4cf0c9e4dd99..d10b5bba3268 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1027,6 +1027,26 @@ enum ieee80211_p2p_attr_id { IEEE80211_P2P_ATTR_MAX }; +/* Notice of Absence attribute - described in P2P spec 4.1.14 */ +/* Typical max value used here */ +#define IEEE80211_P2P_NOA_DESC_MAX 4 + +struct ieee80211_p2p_noa_desc { + u8 count; + __le32 duration; + __le32 interval; + __le32 start_time; +} __packed; + +struct ieee80211_p2p_noa_attr { + u8 index; + u8 oppps_ctwindow; + struct ieee80211_p2p_noa_desc desc[IEEE80211_P2P_NOA_DESC_MAX]; +} __packed; + +#define IEEE80211_P2P_OPPPS_ENABLE_BIT BIT(7) +#define IEEE80211_P2P_OPPPS_CTWINDOW_MASK 0x7F + /** * struct ieee80211_bar - HT Block Ack Request * -- cgit v1.2.3 From d79df329d0bd425c00856915b7b12f54dd100154 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 21 Mar 2013 15:58:58 +0000 Subject: regulator: ab8500: Further populate initialisation registers This patch supplies access to some extra settings provided by the AB8500 regulator device. We also update some of the existing initialisation values in accordance with internal ST-Ericsson code submissions. This single patch was originally a collection of updates which have been squashed together to aid with clarity. Signed-off-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 7bd73bbdfd1b..2c6c9625013c 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -86,7 +86,15 @@ enum ab8500_regulator_reg { AB8500_REGUCTRL2SPARE, AB8500_REGUCTRLDISCH, AB8500_REGUCTRLDISCH2, + AB8500_ARMREGU2, /* NOTE! PRCMU register */ + AB8500_VBBSEL1, /* NOTE! PRCMU register */ + AB8500_VBBSEL2, /* NOTE! PRCMU register */ + AB8500_VSMPS1REGU, + AB8500_VSMPS2REGU, + AB8500_VSMPS3REGU, /* NOTE! PRCMU register */ AB8500_VSMPS1SEL1, + AB8500_VSMPS3SEL1, /* NOTE! PRCMU register */ + AB8500_VSMPS3SEL2, /* NOTE! PRCMU register */ AB8500_NUM_REGULATOR_REGISTERS, }; -- cgit v1.2.3 From 3c1b8438d4bc99269aba560739e3e6cb640584f4 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 21 Mar 2013 15:59:01 +0000 Subject: ARM: ux500: regulators: Add mask for configuration There is already before a register mask in the regulator driver to allow some bits of a register to be initialized. The register value is defined in the board configuration. This patch puts a mask in the board configuration to specify which bits should actually be altered. The purpose with this patch is to avoid future mistakes when updating the allowed bits in the regulator driver. Signed-off-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 2c6c9625013c..a1d245f13d9c 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -48,13 +48,15 @@ enum ab9540_regulator_id { /* AB8500 and AB9540 register initialization */ struct ab8500_regulator_reg_init { int id; + u8 mask; u8 value; }; -#define INIT_REGULATOR_REGISTER(_id, _value) \ - { \ - .id = _id, \ - .value = _value, \ +#define INIT_REGULATOR_REGISTER(_id, _mask, _value) \ + { \ + .id = _id, \ + .mask = _mask, \ + .value = _value, \ } /* AB8500 registers */ -- cgit v1.2.3 From 33bc8f46a8ee3fc1836def9713933435b7ff0b90 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 21 Mar 2013 15:59:02 +0000 Subject: regulator: ab8500: Another push to synchronise recent AB8500 developments This patch ensures that many of the recent developments pertaining to the AB8500 regulator device are propagated out into the public arena. It aims to update some of the existing initialisation values in accordance with internal ST-Ericsson code submissions. This single patch was originally a collection of updates which have been squashed together to aid with clarity. Signed-off-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index a1d245f13d9c..dd7944f735d8 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -61,6 +61,7 @@ struct ab8500_regulator_reg_init { /* AB8500 registers */ enum ab8500_regulator_reg { + AB8500_REGUREQUESTCTRL1, AB8500_REGUREQUESTCTRL2, AB8500_REGUREQUESTCTRL3, AB8500_REGUREQUESTCTRL4, @@ -77,26 +78,28 @@ enum ab8500_regulator_reg { AB8500_REGUMISC1, AB8500_VAUDIOSUPPLY, AB8500_REGUCTRL1VAMIC, + AB8500_VSMPS1REGU, + AB8500_VSMPS2REGU, + AB8500_VSMPS3REGU, /* NOTE! PRCMU register */ AB8500_VPLLVANAREGU, AB8500_VREFDDR, AB8500_EXTSUPPLYREGU, AB8500_VAUX12REGU, AB8500_VRF1VAUX3REGU, + AB8500_VSMPS1SEL1, + AB8500_VSMPS1SEL2, + AB8500_VSMPS1SEL3, + AB8500_VSMPS2SEL1, + AB8500_VSMPS2SEL2, + AB8500_VSMPS2SEL3, + AB8500_VSMPS3SEL1, /* NOTE! PRCMU register */ + AB8500_VSMPS3SEL2, /* NOTE! PRCMU register */ AB8500_VAUX1SEL, AB8500_VAUX2SEL, AB8500_VRF1VAUX3SEL, AB8500_REGUCTRL2SPARE, AB8500_REGUCTRLDISCH, AB8500_REGUCTRLDISCH2, - AB8500_ARMREGU2, /* NOTE! PRCMU register */ - AB8500_VBBSEL1, /* NOTE! PRCMU register */ - AB8500_VBBSEL2, /* NOTE! PRCMU register */ - AB8500_VSMPS1REGU, - AB8500_VSMPS2REGU, - AB8500_VSMPS3REGU, /* NOTE! PRCMU register */ - AB8500_VSMPS1SEL1, - AB8500_VSMPS3SEL1, /* NOTE! PRCMU register */ - AB8500_VSMPS3SEL2, /* NOTE! PRCMU register */ AB8500_NUM_REGULATOR_REGISTERS, }; -- cgit v1.2.3 From 732805a563617aafc7405409c03182afafb3943b Mon Sep 17 00:00:00 2001 From: Bengt Jonsson Date: Thu, 21 Mar 2013 15:59:03 +0000 Subject: regulator: ab8500: Separate regulator and MFD platform data The ab8500 MFD should not have knowledge about regulator- specific platform data like number of regulators and regulator registers. As the regulator platform data is about to grow with external regulators, this information is moved to a new structure provided by the regulator driver. Signed-off-by: Bengt Jonsson Signed-off-by: Lee Jones Reviewed-by: Yvan FILLION Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index dd7944f735d8..3a8e02687f7b 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -152,4 +152,11 @@ enum ab9540_regulator_reg { AB9540_NUM_REGULATOR_REGISTERS, }; +struct ab8500_regulator_platform_data { + int num_reg_init; + struct ab8500_regulator_reg_init *reg_init; + int num_regulator; + struct regulator_init_data *regulator; +}; + #endif -- cgit v1.2.3 From 9d0ca6ed6f2f12eb488f450d5d38d047aa402a53 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 21 Mar 2013 14:17:34 +0000 Subject: virtio: remove obsolete virtqueue_get_queue_index() You can access it directly now, since 3.8: v3.7-rc1-13-g06ca287 'virtio: move queue_index and num_free fields into core struct virtqueue.' Cc: Cornelia Huck Signed-off-by: Rusty Russell Acked-by: Cornelia Huck Signed-off-by: David S. Miller --- include/linux/virtio.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index ff6714e6d0f5..2d7a5e045908 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -58,12 +58,6 @@ void *virtqueue_detach_unused_buf(struct virtqueue *vq); unsigned int virtqueue_get_vring_size(struct virtqueue *vq); -/* FIXME: Obsolete accessor, but required for virtio_net merge. */ -static inline unsigned int virtqueue_get_queue_index(struct virtqueue *vq) -{ - return vq->index; -} - /** * virtio_device - representation of a device using virtio * @index: unique position on the virtio bus -- cgit v1.2.3 From c3a07134e6aa5b93a37f72ffa3d11fadf72bf757 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 22 Mar 2013 03:39:28 +0000 Subject: mv643xx_eth: convert to use the Marvell Orion MDIO driver This patch converts the Marvell MV643XX ethernet driver to use the Marvell Orion MDIO driver. As a result, PowerPC and ARM platforms registering the Marvell MV643XX ethernet driver are also updated to register a Marvell Orion MDIO driver. This driver voluntarily overlaps with the Marvell Ethernet shared registers because it will use a subset of this shared register (shared_base + 0x4 to shared_base + 0x84). The Ethernet driver is also updated to look up for a PHY device using the Orion MDIO bus driver. For ARM and PowerPC we register a single instance of the "mvmdio" driver in the system like it used to be done with the use of the "shared_smi" platform_data cookie on ARM. Note that it is safe to register the mvmdio driver only for the "ge00" instance of the driver because this "ge00" interface is guaranteed to always be explicitely registered by consumers of arch/arm/plat-orion/common.c and other instances (ge01, ge10 and ge11) were all pointing their shared_smi to ge00. For PowerPC the in-tree Device Tree Source files mention only one MV643XX ethernet MAC instance so the MDIO bus driver is registered only when id == 0. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mv643xx_eth.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mv643xx_eth.h b/include/linux/mv643xx_eth.h index 49258e0ed1c6..141d395bbb5f 100644 --- a/include/linux/mv643xx_eth.h +++ b/include/linux/mv643xx_eth.h @@ -19,7 +19,6 @@ struct mv643xx_eth_shared_platform_data { struct mbus_dram_target_info *dram; - struct platform_device *shared_smi; /* * Max packet size for Tx IP/Layer 4 checksum, when set to 0, default * limit of 9KiB will be used. -- cgit v1.2.3 From 51e7e8b632d8e564ba494dfa61358ac1a97e4ceb Mon Sep 17 00:00:00 2001 From: Bernie Thompson Date: Wed, 27 Feb 2013 12:19:17 -0800 Subject: mmc: core: Add in support to expose PRV for v4 MMCs The JEDEC MMC v4 spec defines a new PRV value in place of the original fwrev and hwrev specified in v1. We can expose this in the kernel to enable user space to more easily determine the product revision of a given MMC. Signed-off-by: Bernie Thompson Reviewed-by: Ulf Hansson Signed-off-by: Chris Ball --- include/linux/mmc/card.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 61b2c30c903b..f31725ba49f3 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -17,6 +17,7 @@ struct mmc_cid { unsigned int manfid; char prod_name[8]; + unsigned char prv; unsigned int serial; unsigned short oemid; unsigned short year; -- cgit v1.2.3 From eed222aca8d077af3600b651176f6fd04d95cce1 Mon Sep 17 00:00:00 2001 From: Aaron Lu Date: Tue, 5 Mar 2013 11:24:52 +0800 Subject: mmc: sdio: bind acpi with sdio function device ACPI spec 5 defined the _ADR encoding for sdio bus as: High word - slot number (0 based) Low word - function number This patch adds support for binding sdio function device with acpi node, and if successful, involve acpi into its power management. Signed-off-by: Aaron Lu Reviewed-by: Adrian Hunter Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index d6f20cc6415e..17d714801e94 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -361,6 +361,8 @@ struct mmc_host { unsigned int actual_clock; /* Actual HC clock rate */ + unsigned int slotno; /* used for sdio acpi binding */ + unsigned long private[0] ____cacheline_aligned; }; -- cgit v1.2.3 From ce4f3313b05c836c21a91ac89f87dccf84ce9561 Mon Sep 17 00:00:00 2001 From: Peter De Schrijver Date: Fri, 22 Mar 2013 14:07:53 +0200 Subject: clk: add table lookup to mux Add a table lookup feature to the mux clock. Also allow arbitrary masks instead of the width. This will be used by some clocks on Tegra114. Also adapt the tegra periph clk because it uses struct clk_mux directly. Signed-off-by: Peter De Schrijver Tested-by: Stephen Warren Signed-off-by: Mike Turquette --- include/linux/clk-private.h | 2 +- include/linux/clk-provider.h | 9 ++++++++- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-private.h b/include/linux/clk-private.h index 9c7f5807824b..dd7adff76e81 100644 --- a/include/linux/clk-private.h +++ b/include/linux/clk-private.h @@ -152,7 +152,7 @@ struct clk { }, \ .reg = _reg, \ .shift = _shift, \ - .width = _width, \ + .mask = BIT(_width) - 1, \ .flags = _mux_flags, \ .lock = _lock, \ }; \ diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 56e6cc12c796..63ba3b740794 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -297,8 +297,9 @@ struct clk *clk_register_divider_table(struct device *dev, const char *name, struct clk_mux { struct clk_hw hw; void __iomem *reg; + u32 *table; + u32 mask; u8 shift; - u8 width; u8 flags; spinlock_t *lock; }; @@ -307,11 +308,17 @@ struct clk_mux { #define CLK_MUX_INDEX_BIT BIT(1) extern const struct clk_ops clk_mux_ops; + struct clk *clk_register_mux(struct device *dev, const char *name, const char **parent_names, u8 num_parents, unsigned long flags, void __iomem *reg, u8 shift, u8 width, u8 clk_mux_flags, spinlock_t *lock); +struct clk *clk_register_mux_table(struct device *dev, const char *name, + const char **parent_names, u8 num_parents, unsigned long flags, + void __iomem *reg, u8 shift, u32 mask, + u8 clk_mux_flags, u32 *table, spinlock_t *lock); + /** * struct clk_fixed_factor - fixed multiplier and divider clock * -- cgit v1.2.3 From cc244ddae6d4c6902ac9d7d64023534f8c44a7eb Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 3 May 2012 12:30:07 -0700 Subject: timekeeping: Move TAI managment into timekeeping core from ntp Currently NTP manages the TAI offset. Since there's plans for a CLOCK_TAI clockid, push the TAI management into the timekeeping core. CC: Thomas Gleixner CC: Eric Dumazet CC: Richard Cochran Signed-off-by: John Stultz --- include/linux/time.h | 2 ++ include/linux/timekeeper_internal.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index d4835dfdf25e..47210a175e78 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -181,6 +181,8 @@ extern struct timespec timespec_trunc(struct timespec t, unsigned gran); extern int timekeeping_valid_for_hres(void); extern u64 timekeeping_max_deferment(void); extern int timekeeping_inject_offset(struct timespec *ts); +extern s32 timekeeping_get_tai_offset(void); +extern void timekeeping_set_tai_offset(s32 tai_offset); struct tms; extern void do_sys_times(struct tms *); diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index e1d558e237ec..ff94f436f8b7 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -62,6 +62,9 @@ struct timekeeper { ktime_t offs_boot; /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ struct timespec raw_time; + /* The current UTC to TAI offset in seconds */ + s32 tai_offset; + /* Seqlock for all timekeeper values */ seqlock_t lock; }; -- cgit v1.2.3 From 1ff3c9677bff7e468e0c487d0ffefe4e901d33f4 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 3 May 2012 12:43:40 -0700 Subject: timekeeping: Add CLOCK_TAI clockid This add a CLOCK_TAI clockid and the needed accessors. CC: Thomas Gleixner CC: Eric Dumazet CC: Richard Cochran Signed-off-by: John Stultz --- include/linux/time.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 47210a175e78..22d81b3c955b 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -183,6 +183,7 @@ extern u64 timekeeping_max_deferment(void); extern int timekeeping_inject_offset(struct timespec *ts); extern s32 timekeeping_get_tai_offset(void); extern void timekeeping_set_tai_offset(s32 tai_offset); +extern void timekeeping_clocktai(struct timespec *ts); struct tms; extern void do_sys_times(struct tms *); -- cgit v1.2.3 From 90adda98b89aaf68b06014ecf805b6c477daa19b Mon Sep 17 00:00:00 2001 From: John Stultz Date: Mon, 21 Jan 2013 17:00:11 -0800 Subject: hrtimer: Add hrtimer support for CLOCK_TAI Add hrtimer support for CLOCK_TAI, as well as posix timer interfaces. Signed-off-by: John Stultz --- include/linux/hrtimer.h | 5 ++++- include/linux/timekeeper_internal.h | 2 ++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index cc07d2777bbe..d19a5c2d2270 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -157,6 +157,7 @@ enum hrtimer_base_type { HRTIMER_BASE_MONOTONIC, HRTIMER_BASE_REALTIME, HRTIMER_BASE_BOOTTIME, + HRTIMER_BASE_TAI, HRTIMER_MAX_CLOCK_BASES, }; @@ -327,7 +328,9 @@ extern ktime_t ktime_get(void); extern ktime_t ktime_get_real(void); extern ktime_t ktime_get_boottime(void); extern ktime_t ktime_get_monotonic_offset(void); -extern ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot); +extern ktime_t ktime_get_clocktai(void); +extern ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot, + ktime_t *offs_tai); DECLARE_PER_CPU(struct tick_device, tick_cpu_device); diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index ff94f436f8b7..26700d870506 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -64,6 +64,8 @@ struct timekeeper { struct timespec raw_time; /* The current UTC to TAI offset in seconds */ s32 tai_offset; + /* Offset clock monotonic -> clock tai */ + ktime_t offs_tai; /* Seqlock for all timekeeper values */ seqlock_t lock; -- cgit v1.2.3 From eb93e4d93093615c60cb7dd3dcb24e46bd7d62d4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 Feb 2013 22:51:36 +0000 Subject: timekeeping: Make jiffies_lock internal Nothing outside of the timekeeping core needs that lock. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/jiffies.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 82ed068b1ebe..8fb8edf12417 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -75,7 +75,6 @@ extern int register_refined_jiffies(long clock_tick_rate); */ extern u64 __jiffy_data jiffies_64; extern unsigned long volatile __jiffy_data jiffies; -extern seqlock_t jiffies_lock; #if (BITS_PER_LONG < 64) u64 get_jiffies_64(void); -- cgit v1.2.3 From 7e40672d930b369c1984457233ec5557aa53bfb8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 Feb 2013 22:51:37 +0000 Subject: timekeeping: Move lock out of timekeeper struct Make the lock a separate entity. Preparatory patch for shadow timekeeper structure. Signed-off-by: Thomas Gleixner [Merged with CLOCK_TAI changes] Signed-off-by: John Stultz --- include/linux/timekeeper_internal.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 26700d870506..a151bd70e52b 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -67,8 +67,6 @@ struct timekeeper { /* Offset clock monotonic -> clock tai */ ktime_t offs_tai; - /* Seqlock for all timekeeper values */ - seqlock_t lock; }; static inline struct timespec tk_xtime(struct timekeeper *tk) -- cgit v1.2.3 From cbe5e6109538ddab57764a88d9f0c2accd0c7d48 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Fri, 22 Mar 2013 22:17:36 -0600 Subject: lru_cache: introduce lc_get_cumulative() New helper to be able to consolidate more updates into a single transaction. Without this, we can only grab a single refcount on an updated element while preparing a transaction. lc_get_cumulative - like lc_get; also finds to-be-changed elements @lc: the lru cache to operate on @enr: the label to look up Unlike lc_get this also returns the element for @enr, if it is belonging to a pending transaction, so the return values are like for lc_get(), plus: pointer to an element already on the "to_be_changed" list. In this case, the cache was already marked %LC_DIRTY. Caller needs to make sure that the pending transaction is completed, before proceeding to actually use this element. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Fixed up by Jens to export lc_get_cumulative(). Signed-off-by: Jens Axboe --- include/linux/lru_cache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h index 4019013c6593..46262284de47 100644 --- a/include/linux/lru_cache.h +++ b/include/linux/lru_cache.h @@ -256,6 +256,7 @@ extern void lc_destroy(struct lru_cache *lc); extern void lc_set(struct lru_cache *lc, unsigned int enr, int index); extern void lc_del(struct lru_cache *lc, struct lc_element *element); +extern struct lc_element *lc_get_cumulative(struct lru_cache *lc, unsigned int enr); extern struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr); extern struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr); extern struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr); -- cgit v1.2.3 From 5bbcf5e6abe97485748b51ea0713cc3012b4a8f0 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Tue, 19 Mar 2013 18:16:59 +0100 Subject: drbd: adjust upper limit for activity log extents Now that the on-disk activity-log ring buffer size is adjustable, the maximum active set can become larger, and is now limited by the use of 16bit "labels". This increases the maximum working set from 6433 to 65534 extents, each of which covers an area of 4MiB. Which means that if you use the maximum, you'd have to resync more than 250 GiB after an unclean Primary shutdown. With capable backend storage and replication links, this is entirely feasible. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd_limits.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index 1fa19c5f5e64..1fedf2b17cc8 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -126,13 +126,12 @@ #define DRBD_RESYNC_RATE_DEF 250 #define DRBD_RESYNC_RATE_SCALE 'k' /* kilobytes */ - /* less than 7 would hit performance unnecessarily. - * 919 slots context information per transaction, - * 32k activity log, 4k transaction size, - * one transaction in flight: - * 919 * 7 = 6433 */ + /* less than 7 would hit performance unnecessarily. */ #define DRBD_AL_EXTENTS_MIN 7 -#define DRBD_AL_EXTENTS_MAX 6433 + /* we use u16 as "slot number", (u16)~0 is "FREE". + * If you use >= 292 kB on-disk ring buffer, + * this is the maximum you can use: */ +#define DRBD_AL_EXTENTS_MAX 0xfffe #define DRBD_AL_EXTENTS_DEF 1237 #define DRBD_AL_EXTENTS_SCALE '1' -- cgit v1.2.3 From 66311274691ec65972cad3626057fa8d00c146d8 Mon Sep 17 00:00:00 2001 From: Lin Ming Date: Sat, 23 Mar 2013 11:42:24 +0800 Subject: block: add a flag to identify PM request Add a flag REQ_PM to identify the request is PM related, such requests will not change the device request queue's runtime status. It is intended to be used in driver's runtime PM callback, so that driver can perform some IO to the device there with the queue's runtime status unaffected. e.g. in SCSI disk's runtime suspend callback, the disk will be put into stopped power state, and this require sending a command to the device. Such command processing should not change the disk's runtime status. Signed-off-by: Lin Ming Signed-off-by: Aaron Lu Acked-by: Alan Stern Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index cdf11191e645..fcc1ce28d5ca 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -175,6 +175,7 @@ enum rq_flag_bits { __REQ_IO_STAT, /* account I/O stat */ __REQ_MIXED_MERGE, /* merge of different types, fail separately */ __REQ_KERNEL, /* direct IO to kernel pages */ + __REQ_PM, /* runtime pm request */ __REQ_NR_BITS, /* stops here */ }; @@ -223,5 +224,6 @@ enum rq_flag_bits { #define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) #define REQ_SECURE (1 << __REQ_SECURE) #define REQ_KERNEL (1 << __REQ_KERNEL) +#define REQ_PM (1 << __REQ_PM) #endif /* __LINUX_BLK_TYPES_H */ -- cgit v1.2.3 From 6c9546675864f51506af69eca388e5d922942c56 Mon Sep 17 00:00:00 2001 From: Lin Ming Date: Sat, 23 Mar 2013 11:42:26 +0800 Subject: block: add runtime pm helpers Add runtime pm helper functions: void blk_pm_runtime_init(struct request_queue *q, struct device *dev) - Initialization function for drivers to call. int blk_pre_runtime_suspend(struct request_queue *q) - If any requests are in the queue, mark last busy and return -EBUSY. Otherwise set q->rpm_status to RPM_SUSPENDING and return 0. void blk_post_runtime_suspend(struct request_queue *q, int err) - If the suspend succeeded then set q->rpm_status to RPM_SUSPENDED. Otherwise set it to RPM_ACTIVE and mark last busy. void blk_pre_runtime_resume(struct request_queue *q) - Set q->rpm_status to RPM_RESUMING. void blk_post_runtime_resume(struct request_queue *q, int err) - If the resume succeeded then set q->rpm_status to RPM_ACTIVE and call __blk_run_queue, then mark last busy and autosuspend. Otherwise set q->rpm_status to RPM_SUSPENDED. The idea and API is designed by Alan Stern and described here: http://marc.info/?l=linux-scsi&m=133727953625963&w=2 Signed-off-by: Lin Ming Signed-off-by: Aaron Lu Acked-by: Alan Stern Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 78feda9bbae2..89d89c7162aa 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -361,6 +361,12 @@ struct request_queue { */ struct kobject kobj; +#ifdef CONFIG_PM_RUNTIME + struct device *dev; + int rpm_status; + unsigned int nr_pending; +#endif + /* * queue settings */ @@ -960,6 +966,27 @@ struct request_queue *blk_alloc_queue(gfp_t); struct request_queue *blk_alloc_queue_node(gfp_t, int); extern void blk_put_queue(struct request_queue *); +/* + * block layer runtime pm functions + */ +#ifdef CONFIG_PM_RUNTIME +extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev); +extern int blk_pre_runtime_suspend(struct request_queue *q); +extern void blk_post_runtime_suspend(struct request_queue *q, int err); +extern void blk_pre_runtime_resume(struct request_queue *q); +extern void blk_post_runtime_resume(struct request_queue *q, int err); +#else +static inline void blk_pm_runtime_init(struct request_queue *q, + struct device *dev) {} +static inline int blk_pre_runtime_suspend(struct request_queue *q) +{ + return -ENOSYS; +} +static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {} +static inline void blk_pre_runtime_resume(struct request_queue *q) {} +static inline void blk_post_runtime_resume(struct request_queue *q, int err) {} +#endif + /* * blk_plug permits building a queue of related requests by holding the I/O * fragments for a short period. This allows merging of sequential requests -- cgit v1.2.3 From 57fb233f078beb5d0437a4ae575fbd4d9eb9c738 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 24 Aug 2012 04:56:11 -0700 Subject: block: Reorder struct bio_set This is prep work for the next patch, which embeds a struct bio_list in struct bio_set. Signed-off-by: Kent Overstreet CC: Jens Axboe --- include/linux/bio.h | 66 ++++++++++++++++++++++++++--------------------------- 1 file changed, 33 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 820e7aaad4fd..93d3d17a300d 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -298,39 +298,6 @@ static inline int bio_associate_current(struct bio *bio) { return -ENOENT; } static inline void bio_disassociate_task(struct bio *bio) { } #endif /* CONFIG_BLK_CGROUP */ -/* - * bio_set is used to allow other portions of the IO system to - * allocate their own private memory pools for bio and iovec structures. - * These memory pools in turn all allocate from the bio_slab - * and the bvec_slabs[]. - */ -#define BIO_POOL_SIZE 2 -#define BIOVEC_NR_POOLS 6 -#define BIOVEC_MAX_IDX (BIOVEC_NR_POOLS - 1) - -struct bio_set { - struct kmem_cache *bio_slab; - unsigned int front_pad; - - mempool_t *bio_pool; -#if defined(CONFIG_BLK_DEV_INTEGRITY) - mempool_t *bio_integrity_pool; -#endif - mempool_t *bvec_pool; -}; - -struct biovec_slab { - int nr_vecs; - char *name; - struct kmem_cache *slab; -}; - -/* - * a small number of entries is fine, not going to be performance critical. - * basically we just need to survive - */ -#define BIO_SPLIT_ENTRIES 2 - #ifdef CONFIG_HIGHMEM /* * remember never ever reenable interrupts between a bvec_kmap_irq and @@ -527,6 +494,39 @@ static inline struct bio *bio_list_get(struct bio_list *bl) return bio; } +/* + * bio_set is used to allow other portions of the IO system to + * allocate their own private memory pools for bio and iovec structures. + * These memory pools in turn all allocate from the bio_slab + * and the bvec_slabs[]. + */ +#define BIO_POOL_SIZE 2 +#define BIOVEC_NR_POOLS 6 +#define BIOVEC_MAX_IDX (BIOVEC_NR_POOLS - 1) + +struct bio_set { + struct kmem_cache *bio_slab; + unsigned int front_pad; + + mempool_t *bio_pool; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + mempool_t *bio_integrity_pool; +#endif + mempool_t *bvec_pool; +}; + +struct biovec_slab { + int nr_vecs; + char *name; + struct kmem_cache *slab; +}; + +/* + * a small number of entries is fine, not going to be performance critical. + * basically we just need to survive + */ +#define BIO_SPLIT_ENTRIES 2 + #if defined(CONFIG_BLK_DEV_INTEGRITY) #define bip_vec_idx(bip, idx) (&(bip->bip_vec[(idx)])) -- cgit v1.2.3 From df2cb6daa4cbc34406bc4b1ac9b9335df1083a72 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 10 Sep 2012 14:33:46 -0700 Subject: block: Avoid deadlocks with bio allocation by stacking drivers Previously, if we ever try to allocate more than once from the same bio set while running under generic_make_request() (i.e. a stacking block driver), we risk deadlock. This is because of the code in generic_make_request() that converts recursion to iteration; any bios we submit won't actually be submitted (so they can complete and eventually be freed) until after we return - this means if we allocate a second bio, we're blocking the first one from ever being freed. Thus if enough threads call into a stacking block driver at the same time with bios that need multiple splits, and the bio_set's reserve gets used up, we deadlock. This can be worked around in the driver code - we could check if we're running under generic_make_request(), then mask out __GFP_WAIT when we go to allocate a bio, and if the allocation fails punt to workqueue and retry the allocation. But this is tricky and not a generic solution. This patch solves it for all users by inverting the previously described technique. We allocate a rescuer workqueue for each bio_set, and then in the allocation code if there are bios on current->bio_list we would be blocking, we punt them to the rescuer workqueue to be submitted. This guarantees forward progress for bio allocations under generic_make_request() provided each bio is submitted before allocating the next, and provided the bios are freed after they complete. Note that this doesn't do anything for allocation from other mempools. Instead of allocating per bio data structures from a mempool, code should use bio_set's front_pad. Tested it by forcing the rescue codepath to be taken (by disabling the first GFP_NOWAIT) attempt, and then ran it with bcache (which does a lot of arbitrary bio splitting) and verified that the rescuer was being invoked. Signed-off-by: Kent Overstreet CC: Jens Axboe Acked-by: Tejun Heo Reviewed-by: Muthukumar Ratty --- include/linux/bio.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 93d3d17a300d..b31036ff779f 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -513,6 +513,15 @@ struct bio_set { mempool_t *bio_integrity_pool; #endif mempool_t *bvec_pool; + + /* + * Deadlock avoidance for stacking block drivers: see comments in + * bio_alloc_bioset() for details + */ + spinlock_t rescue_lock; + struct bio_list rescue_list; + struct work_struct rescue_work; + struct workqueue_struct *rescue_workqueue; }; struct biovec_slab { -- cgit v1.2.3 From 6fda981cafbf908acd11e1e636fec50e99d56a47 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 12 Oct 2012 13:18:27 -0700 Subject: block: Fix a buffer overrun in bio_integrity_split() bio_integrity_split() seemed to be confusing pointers and arrays - bip_vec in bio_integrity_payload was an array appended to the end of the payload, so the bio_vecs in struct bio_pair should have come after the bio_integrity_payload they're for. Fix it by making bip_vec a pointer to the inline vecs - a later patch is going to make more use of this pointer. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: Martin K. Petersen --- include/linux/bio.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index b31036ff779f..81004fdcc277 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -182,7 +182,9 @@ struct bio_integrity_payload { unsigned short bip_idx; /* current bip_vec index */ struct work_struct bip_work; /* I/O completion */ - struct bio_vec bip_vec[0]; /* embedded bvec array */ + + struct bio_vec *bip_vec; + struct bio_vec bip_inline_vecs[0];/* embedded bvec array */ }; #endif /* CONFIG_BLK_DEV_INTEGRITY */ -- cgit v1.2.3 From 9f060e2231ca96ca94f2ffcff730acd72606b280 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 12 Oct 2012 15:29:33 -0700 Subject: block: Convert integrity to bvec_alloc_bs() This adds a pointer to the bvec array to struct bio_integrity_payload, instead of the bvecs always being inline; then the bvecs are allocated with bvec_alloc_bs(). Changed bvec_alloc_bs() and bvec_free_bs() to take a pointer to a mempool instead of the bioset, so that bio integrity can use a different mempool for its bvecs, and thus avoid a potential deadlock. This is eventually for immutable bio vecs - immutable bvecs aren't useful if we still have to copy them, hence the need for the pointer. Less code is always nice too, though. Also, bio_integrity_alloc() was using fs_bio_set if no bio_set was specified. This was wrong - using the bio_set doesn't protect us from memory allocation failures, because we just used kmalloc for the bio_integrity_payload. But it does introduce the possibility of deadlock, if for some reason we weren't supposed to be using fs_bio_set. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: Martin K. Petersen --- include/linux/bio.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 81004fdcc277..669b1cb18fee 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -213,6 +213,7 @@ extern void bio_pair_release(struct bio_pair *dbio); extern struct bio_set *bioset_create(unsigned int, unsigned int); extern void bioset_free(struct bio_set *); +extern mempool_t *biovec_create_pool(struct bio_set *bs, int pool_entries); extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *); extern void bio_put(struct bio *); @@ -288,8 +289,8 @@ extern struct bio *bio_copy_user_iov(struct request_queue *, int, int, gfp_t); extern int bio_uncopy_user(struct bio *); void zero_fill_bio(struct bio *bio); -extern struct bio_vec *bvec_alloc_bs(gfp_t, int, unsigned long *, struct bio_set *); -extern void bvec_free_bs(struct bio_set *, struct bio_vec *, unsigned int); +extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *); +extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); #ifdef CONFIG_BLK_CGROUP @@ -511,10 +512,11 @@ struct bio_set { unsigned int front_pad; mempool_t *bio_pool; + mempool_t *bvec_pool; #if defined(CONFIG_BLK_DEV_INTEGRITY) mempool_t *bio_integrity_pool; + mempool_t *bvec_integrity_pool; #endif - mempool_t *bvec_pool; /* * Deadlock avoidance for stacking block drivers: see comments in -- cgit v1.2.3 From 054bdf646e36c2f7dc1bf6bc6209dbbb5909164b Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 28 Sep 2012 13:17:55 -0700 Subject: block: Add bio_advance() This is prep work for immutable bio vecs; we first want to centralize where bvecs are modified. Next two patches convert some existing code to use this function. Signed-off-by: Kent Overstreet CC: Jens Axboe --- include/linux/bio.h | 2 ++ include/linux/blk_types.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 669b1cb18fee..fcb4dba2d8ea 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -248,6 +248,8 @@ extern void bio_endio(struct bio *, int); struct request_queue; extern int bio_phys_segments(struct request_queue *, struct bio *); +extern void bio_advance(struct bio *, unsigned); + extern void bio_init(struct bio *); extern void bio_reset(struct bio *); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index cdf11191e645..c178d25e588b 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -197,6 +197,8 @@ enum rq_flag_bits { REQ_SECURE) #define REQ_CLONE_MASK REQ_COMMON_MASK +#define BIO_NO_ADVANCE_ITER_MASK (REQ_DISCARD|REQ_WRITE_SAME) + /* This mask is used for both bio and request merge checking */ #define REQ_NOMERGE_FLAGS \ (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA) -- cgit v1.2.3 From f73a1c7d117d07a96d89475066188a2b79e53c48 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 25 Sep 2012 15:05:12 -0700 Subject: block: Add bio_end_sector() Just a little convenience macro - main reason to add it now is preparing for immutable bio vecs, it'll reduce the size of the patch that puts bi_sector/bi_size/bi_idx into a struct bvec_iter. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: Lars Ellenberg CC: Jiri Kosina CC: Alasdair Kergon CC: dm-devel@redhat.com CC: Neil Brown CC: Martin Schwidefsky CC: Heiko Carstens CC: linux-s390@vger.kernel.org CC: Chris Mason CC: Steven Whitehouse Acked-by: Steven Whitehouse --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index fcb4dba2d8ea..20507eb7c979 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -67,6 +67,7 @@ #define bio_offset(bio) bio_iovec((bio))->bv_offset #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) #define bio_sectors(bio) ((bio)->bi_size >> 9) +#define bio_end_sector(bio) ((bio)->bi_sector + bio_sectors((bio))) static inline unsigned int bio_cur_bytes(struct bio *bio) { -- cgit v1.2.3 From 9e882242c6193ae6f416f2d8d8db0d9126bd996b Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 10 Sep 2012 14:41:12 -0700 Subject: block: Add submit_bio_wait(), remove from md Random cleanup - this code was duplicated and it's not really specific to md. Also added the ability to return the actual error code. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: NeilBrown Acked-by: Tejun Heo --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 20507eb7c979..b20a9cd776dd 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -249,6 +249,7 @@ extern void bio_endio(struct bio *, int); struct request_queue; extern int bio_phys_segments(struct request_queue *, struct bio *); +extern int submit_bio_wait(int rw, struct bio *bio); extern void bio_advance(struct bio *, unsigned); extern void bio_init(struct bio *); -- cgit v1.2.3 From 16ac3d63e74f3d6e34e42d6e523b6a61de0020f0 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 10 Sep 2012 13:57:51 -0700 Subject: block: Add bio_copy_data() This gets open coded quite a bit and it's tricky to get right, so make a generic version and convert some existing users over to it instead. Signed-off-by: Kent Overstreet CC: Jens Axboe --- include/linux/bio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index b20a9cd776dd..90d36c65cb70 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -286,6 +286,8 @@ static inline void bio_flush_dcache_pages(struct bio *bi) } #endif +extern void bio_copy_data(struct bio *dst, struct bio *src); + extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *, unsigned long, unsigned int, int, gfp_t); extern struct bio *bio_copy_user_iov(struct request_queue *, -- cgit v1.2.3 From d74c6d514fe314b8bdab58b487b25992291577ec Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 6 Feb 2013 12:23:11 -0800 Subject: block: Add bio_for_each_segment_all() __bio_for_each_segment() iterates bvecs from the specified index instead of bio->bv_idx. Currently, the only usage is to walk all the bvecs after the bio has been advanced by specifying 0 index. For immutable bvecs, we need to split these apart; bio_for_each_segment() is going to have a different implementation. This will also help document the intent of code that's using it - bio_for_each_segment_all() is only legal to use for code that owns the bio. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: Neil Brown CC: Boaz Harrosh --- include/linux/bio.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 90d36c65cb70..be2efa09f9bf 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -137,16 +137,27 @@ static inline int bio_has_allocated_vec(struct bio *bio) #define bio_io_error(bio) bio_endio((bio), -EIO) /* - * drivers should not use the __ version unless they _really_ want to - * run through the entire bio and not just pending pieces + * drivers should not use the __ version unless they _really_ know what + * they're doing */ #define __bio_for_each_segment(bvl, bio, i, start_idx) \ for (bvl = bio_iovec_idx((bio), (start_idx)), i = (start_idx); \ i < (bio)->bi_vcnt; \ bvl++, i++) +/* + * drivers should _never_ use the all version - the bio may have been split + * before it got to the driver and the driver won't own all of it + */ +#define bio_for_each_segment_all(bvl, bio, i) \ + for (i = 0; \ + bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt; \ + i++) + #define bio_for_each_segment(bvl, bio, i) \ - __bio_for_each_segment(bvl, bio, i, (bio)->bi_idx) + for (i = (bio)->bi_idx; \ + bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt; \ + i++) /* * get a reference to a bio, so it won't disappear. the intended use is -- cgit v1.2.3 From a07876064a0b73ab5ef1ebcf14b1cf0231c07858 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Mon, 10 Sep 2012 14:03:28 -0700 Subject: block: Add bio_alloc_pages() More utility code to replace stuff that's getting open coded. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: NeilBrown --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index be2efa09f9bf..e25378f2f408 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -298,6 +298,7 @@ static inline void bio_flush_dcache_pages(struct bio *bi) #endif extern void bio_copy_data(struct bio *dst, struct bio *src); +extern int bio_alloc_pages(struct bio *bio, gfp_t gfp); extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *, unsigned long, unsigned int, int, gfp_t); -- cgit v1.2.3 From a38352e0ac02dbbd4fa464dc22d1352b5fbd06fd Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 25 May 2012 13:03:11 -0700 Subject: block: Add an explicit bio flag for bios that own their bvec This is for the new bio splitting code. When we split a bio, if the split occured on a bvec boundry we reuse the bvec for the new bio. But that means bio_free() can't free it, hence the explicit flag. Signed-off-by: Kent Overstreet CC: Jens Axboe Acked-by: Tejun Heo --- include/linux/bio.h | 5 ----- include/linux/blk_types.h | 1 + 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index e25378f2f408..794bcd0c5039 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -85,11 +85,6 @@ static inline void *bio_data(struct bio *bio) return NULL; } -static inline int bio_has_allocated_vec(struct bio *bio) -{ - return bio->bi_io_vec && bio->bi_io_vec != bio->bi_inline_vecs; -} - /* * will die */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index c178d25e588b..538289ffc704 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -117,6 +117,7 @@ struct bio { * BIO_POOL_IDX() */ #define BIO_RESET_BITS 12 +#define BIO_OWNS_VEC 12 /* bio_free() should free bvec */ #define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag))) -- cgit v1.2.3 From 29ed7813ce5c4661261aeebddb1b8660e0860223 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 4 Sep 2012 09:54:22 -0700 Subject: bio-integrity: Add explicit field for owner of bip_buf This was the only real user of BIO_CLONED, which didn't have very clear semantics. Convert to its own flag so we can get rid of BIO_CLONED. Signed-off-by: Kent Overstreet CC: Jens Axboe CC: Martin K. Petersen --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 794bcd0c5039..ef24466d8f82 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -187,6 +187,7 @@ struct bio_integrity_payload { unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_idx; /* current bip_vec index */ + unsigned bip_owns_buf:1; /* should free bip_buf */ struct work_struct bip_work; /* I/O completion */ -- cgit v1.2.3 From 84759c6d18c5144432781ddca037d929ee9db8a5 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 21 Sep 2011 21:43:05 -0700 Subject: Revert "rw_semaphore: remove up/down_read_non_owner" This reverts commit 11b80f459adaf91a712f95e7734a17655a36bf30. Bcache needs rw semaphores for cache coherency in writeback mode - writes have to take a read lock on a per cache device rw sem, and release it when the bio completes. But since this is for bios it's naturally not in the context of the process that originally took the lock. Signed-off-by: Kent Overstreet CC: Christoph Hellwig CC: David Howells --- include/linux/rwsem.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 8da67d625e13..0616ffe45702 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -133,10 +133,20 @@ do { \ _down_write_nest_lock(sem, &(nest_lock)->dep_map); \ } while (0); +/* + * Take/release a lock when not the owner will release it. + * + * [ This API should be avoided as much as possible - the + * proper abstraction for this case is completions. ] + */ +extern void down_read_non_owner(struct rw_semaphore *sem); +extern void up_read_non_owner(struct rw_semaphore *sem); #else # define down_read_nested(sem, subclass) down_read(sem) # define down_write_nest_lock(sem, nest_lock) down_write(sem) # define down_write_nested(sem, subclass) down_write(sem) +# define down_read_non_owner(sem) down_read(sem) +# define up_read_non_owner(sem) up_read(sem) #endif #endif /* _LINUX_RWSEM_H */ -- cgit v1.2.3 From cafe563591446cf80bfbc2fe3bc72a2e36cf1060 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 23 Mar 2013 16:11:31 -0700 Subject: bcache: A block layer cache Does writethrough and writeback caching, handles unclean shutdown, and has a bunch of other nifty features motivated by real world usage. See the wiki at http://bcache.evilpiepirate.org for more. Signed-off-by: Kent Overstreet --- include/linux/cgroup_subsys.h | 6 ++++++ include/linux/sched.h | 4 ++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index f204a7a9cf38..6e7ec64b69ab 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -78,3 +78,9 @@ SUBSYS(hugetlb) #endif /* */ + +#ifdef CONFIG_CGROUP_BCACHE +SUBSYS(bcache) +#endif + +/* */ diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6ddbfb..a8482d063bc3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1576,6 +1576,10 @@ struct task_struct { #ifdef CONFIG_UPROBES struct uprobe_task *utask; #endif +#if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE) + unsigned int sequential_io; + unsigned int sequential_io_avg; +#endif }; /* Future-safe accessor for struct task_struct's cpus_allowed. */ -- cgit v1.2.3 From 5f9296ba21b3c395e53dd84e7ff9578f97f24295 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 28 Feb 2012 18:26:31 +0530 Subject: i2c: Add bus recovery infrastructure Add i2c bus recovery infrastructure to i2c adapters as specified in the i2c protocol Rev. 03 section 3.1.16 titled "Bus clear". http://www.nxp.com/documents/user_manual/UM10204.pdf Sometimes during operation i2c bus hangs and we need to give dummy clocks to slave device to start the transfer again. Now we may have capability in the bus controller to generate these clocks or platform may have gpio pins which can be toggled to generate dummy clocks. This patch supports both. This patch also adds in generic bus recovery routines gpio or scl line based which can be used by bus controller. In addition controller driver may provide its own version of the bus recovery routine. This doesn't support multi-master recovery for now. Signed-off-by: Viresh Kumar [wsa: changed gpio type to int and minor reformatting] Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index d0c4db7b4872..2eca3860b77f 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -370,6 +370,45 @@ struct i2c_algorithm { u32 (*functionality) (struct i2c_adapter *); }; +/** + * struct i2c_bus_recovery_info - I2C bus recovery information + * @recover_bus: Recover routine. Either pass driver's recover_bus() routine, or + * i2c_generic_scl_recovery() or i2c_generic_gpio_recovery(). + * @get_scl: This gets current value of SCL line. Mandatory for generic SCL + * recovery. Used internally for generic GPIO recovery. + * @set_scl: This sets/clears SCL line. Mandatory for generic SCL recovery. Used + * internally for generic GPIO recovery. + * @get_sda: This gets current value of SDA line. Optional for generic SCL + * recovery. Used internally, if sda_gpio is a valid GPIO, for generic GPIO + * recovery. + * @prepare_recovery: This will be called before starting recovery. Platform may + * configure padmux here for SDA/SCL line or something else they want. + * @unprepare_recovery: This will be called after completing recovery. Platform + * may configure padmux here for SDA/SCL line or something else they want. + * @scl_gpio: gpio number of the SCL line. Only required for GPIO recovery. + * @sda_gpio: gpio number of the SDA line. Only required for GPIO recovery. + */ +struct i2c_bus_recovery_info { + int (*recover_bus)(struct i2c_adapter *); + + int (*get_scl)(struct i2c_adapter *); + void (*set_scl)(struct i2c_adapter *, int val); + int (*get_sda)(struct i2c_adapter *); + + void (*prepare_recovery)(struct i2c_bus_recovery_info *bri); + void (*unprepare_recovery)(struct i2c_bus_recovery_info *bri); + + /* gpio recovery */ + int scl_gpio; + int sda_gpio; +}; + +int i2c_recover_bus(struct i2c_adapter *adap); + +/* Generic recovery routines */ +int i2c_generic_gpio_recovery(struct i2c_adapter *adap); +int i2c_generic_scl_recovery(struct i2c_adapter *adap); + /* * i2c_adapter is the structure used to identify a physical i2c bus along * with the access algorithms necessary to access it. @@ -393,6 +432,8 @@ struct i2c_adapter { struct mutex userspace_clients_lock; struct list_head userspace_clients; + + struct i2c_bus_recovery_info *bus_recovery_info; }; #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev) -- cgit v1.2.3 From 49a64ac555f1dabd2b94325553187d0db6ecac16 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Thu, 21 Mar 2013 08:08:46 +0000 Subject: i2c: tegra: assume CONFIG_OF, remove platform data Tegra only supports, and always enables, device tree. Remove all ifdefs and runtime checks for DT support from the driver. Platform data is therefore no longer required. Delete the header that defines it. Signed-off-by: Stephen Warren Signed-off-by: Wolfram Sang --- include/linux/i2c-tegra.h | 25 ------------------------- 1 file changed, 25 deletions(-) delete mode 100644 include/linux/i2c-tegra.h (limited to 'include/linux') diff --git a/include/linux/i2c-tegra.h b/include/linux/i2c-tegra.h deleted file mode 100644 index 9c85da49857a..000000000000 --- a/include/linux/i2c-tegra.h +++ /dev/null @@ -1,25 +0,0 @@ -/* - * drivers/i2c/busses/i2c-tegra.c - * - * Copyright (C) 2010 Google, Inc. - * Author: Colin Cross - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ - -#ifndef _LINUX_I2C_TEGRA_H -#define _LINUX_I2C_TEGRA_H - -struct tegra_i2c_platform_data { - unsigned long bus_clk_rate; -}; - -#endif /* _LINUX_I2C_TEGRA_H */ -- cgit v1.2.3 From d4e1a692e9e85f9cbee090ea8d6158b133d32157 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Mon, 4 Mar 2013 21:30:41 +0000 Subject: ACPI: Remove acpi_device dependency in acpi_device_set_id() This patch updates the internal operations of acpi_device_set_id() to setup acpi_device_pnp without using acpi_device. There is no functional change to acpi_device_set_id() in this patch. acpi_pnp_type is added to acpi_device_pnp, so that PNPID type is self-contained within acpi_device_pnp. acpi_add_id(), acpi_bay_match(), acpi_dock_match(), acpi_ibm_smbus_match() and acpi_is_video_device() are changed to take acpi_handle as an argument, instead of acpi_device. Signed-off-by: Toshi Kani Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index bcbdd7484e58..edaf311473e5 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -204,7 +204,7 @@ extern bool wmi_has_guid(const char *guid); #if defined(CONFIG_ACPI_VIDEO) || defined(CONFIG_ACPI_VIDEO_MODULE) extern long acpi_video_get_capabilities(acpi_handle graphics_dev_handle); -extern long acpi_is_video_device(struct acpi_device *device); +extern long acpi_is_video_device(acpi_handle handle); extern void acpi_video_dmi_promote_vendor(void); extern void acpi_video_dmi_demote_vendor(void); extern int acpi_video_backlight_support(void); @@ -217,7 +217,7 @@ static inline long acpi_video_get_capabilities(acpi_handle graphics_dev_handle) return 0; } -static inline long acpi_is_video_device(struct acpi_device *device) +static inline long acpi_is_video_device(acpi_handle handle) { return 0; } -- cgit v1.2.3 From c58c844187df61ef7cc103d0abb5dd6198bcfcd6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 18 Mar 2013 19:45:14 -0400 Subject: NFS: Don't accept more reads/writes if the open context recovery failed If the state recovery failed, we want to ensure that the application doesn't try to use the same file descriptor for more reads or writes. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 1cc25682b20b..f6b1956f3c86 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -77,6 +77,7 @@ struct nfs_open_context { unsigned long flags; #define NFS_CONTEXT_ERROR_WRITE (0) #define NFS_CONTEXT_RESEND_WRITES (1) +#define NFS_CONTEXT_BAD (2) int error; struct list_head list; -- cgit v1.2.3 From 9b20614988199fb03580b335a28250922e902098 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 17 Mar 2013 15:52:00 -0400 Subject: NFSv4: The stateid must remain the same for replayed RPC calls If we replay a READ or WRITE call, we should not be changing the stateid. Currently, we may end up doing so, because the stateid is only selected at xdr encode time. This patch ensures that we select the stateid after we get an NFSv4.1 session slot, and that we keep that same stateid across retries. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 4b993d358dad..90a4aa190b43 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -486,6 +486,7 @@ struct nfs_readargs { struct nfs_fh * fh; struct nfs_open_context *context; struct nfs_lock_context *lock_context; + nfs4_stateid stateid; __u64 offset; __u32 count; unsigned int pgbase; @@ -507,6 +508,7 @@ struct nfs_writeargs { struct nfs_fh * fh; struct nfs_open_context *context; struct nfs_lock_context *lock_context; + nfs4_stateid stateid; __u64 offset; __u32 count; enum nfs3_stable_how stable; -- cgit v1.2.3 From 3b66486c4c7136f8d4bbe1306d581fadc6bce4c7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 17 Mar 2013 15:31:15 -0400 Subject: NFSv4.1: Select the "most recent locking state" for read/write/setattr stateids Follow the practice described in section 8.2.2 of RFC5661: When sending a read/write or setattr stateid, set the seqid field to zero in order to signal that the NFS server should apply the most recent locking state. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 6c6ed153a9b4..74c9e52c9338 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -197,5 +197,6 @@ struct nfs_server { #define NFS_CAP_MTIME (1U << 13) #define NFS_CAP_POSIX_LOCK (1U << 14) #define NFS_CAP_UIDGID_NOMAP (1U << 15) +#define NFS_CAP_STATEID_NFSV41 (1U << 16) #endif -- cgit v1.2.3 From 49f9a0fafd844c32f2abada047c0b9a5ba0d6255 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 15 Mar 2013 16:44:28 -0400 Subject: NFSv4.1: Enable open-by-filehandle Sometimes, we actually _want_ to do open-by-filehandle, for instance when recovering opens after a network partition, or when called from nfs4_file_open. Enable that functionality using a new capability NFS_CAP_ATOMIC_OPEN_V1, and which is only enabled for NFSv4.1 servers that support it. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 74c9e52c9338..d8fdfdc7a8fe 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -198,5 +198,6 @@ struct nfs_server { #define NFS_CAP_POSIX_LOCK (1U << 14) #define NFS_CAP_UIDGID_NOMAP (1U << 15) #define NFS_CAP_STATEID_NFSV41 (1U << 16) +#define NFS_CAP_ATOMIC_OPEN_V1 (1U << 17) #endif -- cgit v1.2.3 From e44b0ceee4cc2a926225e73ac1e20b9a5bb22c2d Mon Sep 17 00:00:00 2001 From: Kenneth Heitke Date: Tue, 12 Mar 2013 11:41:46 -0700 Subject: add single-wire serial bus interface (SSBI) driver SSBI is the Qualcomm single-wire serial bus interface used to connect the MSM devices to the PMIC and other devices. Since SSBI only supports a single slave, the driver gets the name of the slave device passed in from the board file through the master device's platform data. SSBI registers pretty early (postcore), so that the PMIC can come up before the board init. This is useful if the board init requires the use of gpios that are connected through the PMIC. Based on a patch by Dima Zavin that can be found at: http://android.git.kernel.org/?p=kernel/msm.git;a=commitdiff;h=eb060bac4 This patch adds PMIC Arbiter support for the MSM8660. The PMIC Arbiter is a hardware wrapper around the SSBI 2.0 controller that is designed to overcome concurrency issues and security limitations. A controller_type field is added to the platform data to specify the type of the SSBI controller (1.0, 2.0, or PMIC Arbiter). [davidb@codeaurora.org: I've moved this driver into drivers/ssbi/ and added an include for linux/module.h so that it will compile] Signed-off-by: Kenneth Heitke Signed-off-by: David Brown Signed-off-by: Greg Kroah-Hartman --- include/linux/msm_ssbi.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) create mode 100644 include/linux/msm_ssbi.h (limited to 'include/linux') diff --git a/include/linux/msm_ssbi.h b/include/linux/msm_ssbi.h new file mode 100644 index 000000000000..cfa47df6d003 --- /dev/null +++ b/include/linux/msm_ssbi.h @@ -0,0 +1,49 @@ +/* Copyright (C) 2010 Google, Inc. + * Copyright (c) 2011, Code Aurora Forum. All rights reserved. + * Author: Dima Zavin + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _LINUX_MSM_SSBI_H +#define _LINUX_MSM_SSBI_H + +#include + +struct msm_ssbi_slave_info { + const char *name; + void *platform_data; +}; + +enum msm_ssbi_controller_type { + MSM_SBI_CTRL_SSBI = 0, + MSM_SBI_CTRL_SSBI2, + MSM_SBI_CTRL_PMIC_ARBITER, +}; + +struct msm_ssbi_platform_data { + struct msm_ssbi_slave_info slave; + enum msm_ssbi_controller_type controller_type; +}; + +#ifdef CONFIG_MSM_SSBI +int msm_ssbi_write(struct device *dev, u16 addr, u8 *buf, int len); +int msm_ssbi_read(struct device *dev, u16 addr, u8 *buf, int len); +#else +static inline int msm_ssbi_write(struct device *dev, u16 addr, u8 *buf, int len) +{ + return -ENXIO; +} +static inline int msm_ssbi_read(struct device *dev, u16 addr, u8 *buf, int len) +{ + return -ENXIO; +} +#endif +#endif -- cgit v1.2.3 From 4a6692e2ac4c6b09235a9568468dd83a380c271d Mon Sep 17 00:00:00 2001 From: David Brown Date: Tue, 12 Mar 2013 11:41:49 -0700 Subject: ssbi: Allow compilation as a module The ssbi driver's read/write entry points are protected with wrappers in the case when the driver isn't enabled. These wrappers don't make any sense, since a client of the SSBI bus won't work without it. Make these just regular functions, so that the SSBI driver can be built as a module. Signed-off-by: David Brown Signed-off-by: Greg Kroah-Hartman --- include/linux/msm_ssbi.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msm_ssbi.h b/include/linux/msm_ssbi.h index cfa47df6d003..0fe245bb2940 100644 --- a/include/linux/msm_ssbi.h +++ b/include/linux/msm_ssbi.h @@ -33,17 +33,6 @@ struct msm_ssbi_platform_data { enum msm_ssbi_controller_type controller_type; }; -#ifdef CONFIG_MSM_SSBI int msm_ssbi_write(struct device *dev, u16 addr, u8 *buf, int len); int msm_ssbi_read(struct device *dev, u16 addr, u8 *buf, int len); -#else -static inline int msm_ssbi_write(struct device *dev, u16 addr, u8 *buf, int len) -{ - return -ENXIO; -} -static inline int msm_ssbi_read(struct device *dev, u16 addr, u8 *buf, int len) -{ - return -ENXIO; -} -#endif #endif -- cgit v1.2.3 From ce44bf5b5544cbe6358abb01f039361a99b80901 Mon Sep 17 00:00:00 2001 From: David Brown Date: Tue, 12 Mar 2013 11:41:54 -0700 Subject: SSBI: Remove MSM_ prefix from SSBI drivers Although the SSBI sub is currently only used on MSM SoCs, it is still a bus in its own right. Remove this msm_ prefix from the driver and it's symbols. Clients can now refer directly to ssbi_write() and ssbi_read(). Signed-off-by: David Brown Signed-off-by: Greg Kroah-Hartman --- include/linux/msm_ssbi.h | 38 -------------------------------------- include/linux/ssbi.h | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+), 38 deletions(-) delete mode 100644 include/linux/msm_ssbi.h create mode 100644 include/linux/ssbi.h (limited to 'include/linux') diff --git a/include/linux/msm_ssbi.h b/include/linux/msm_ssbi.h deleted file mode 100644 index 0fe245bb2940..000000000000 --- a/include/linux/msm_ssbi.h +++ /dev/null @@ -1,38 +0,0 @@ -/* Copyright (C) 2010 Google, Inc. - * Copyright (c) 2011, Code Aurora Forum. All rights reserved. - * Author: Dima Zavin - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 and - * only version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#ifndef _LINUX_MSM_SSBI_H -#define _LINUX_MSM_SSBI_H - -#include - -struct msm_ssbi_slave_info { - const char *name; - void *platform_data; -}; - -enum msm_ssbi_controller_type { - MSM_SBI_CTRL_SSBI = 0, - MSM_SBI_CTRL_SSBI2, - MSM_SBI_CTRL_PMIC_ARBITER, -}; - -struct msm_ssbi_platform_data { - struct msm_ssbi_slave_info slave; - enum msm_ssbi_controller_type controller_type; -}; - -int msm_ssbi_write(struct device *dev, u16 addr, u8 *buf, int len); -int msm_ssbi_read(struct device *dev, u16 addr, u8 *buf, int len); -#endif diff --git a/include/linux/ssbi.h b/include/linux/ssbi.h new file mode 100644 index 000000000000..44ef5da21470 --- /dev/null +++ b/include/linux/ssbi.h @@ -0,0 +1,38 @@ +/* Copyright (C) 2010 Google, Inc. + * Copyright (c) 2011, Code Aurora Forum. All rights reserved. + * Author: Dima Zavin + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _LINUX_SSBI_H +#define _LINUX_SSBI_H + +#include + +struct ssbi_slave_info { + const char *name; + void *platform_data; +}; + +enum ssbi_controller_type { + MSM_SBI_CTRL_SSBI = 0, + MSM_SBI_CTRL_SSBI2, + MSM_SBI_CTRL_PMIC_ARBITER, +}; + +struct ssbi_platform_data { + struct ssbi_slave_info slave; + enum ssbi_controller_type controller_type; +}; + +int ssbi_write(struct device *dev, u16 addr, u8 *buf, int len); +int ssbi_read(struct device *dev, u16 addr, u8 *buf, int len); +#endif -- cgit v1.2.3 From 303f0847925ece27129487a2bfc05199ab2a0b51 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 15 Mar 2013 12:08:53 +0800 Subject: USB: adds comment on suspend callback This patch adds comments on interface driver suspend callback to emphasize that the failure return value is ignored by USB core in system sleep context, so do not try to recover device for this case and let resume/reset_resume callback handle the suspend failure if needed. Also kerneldoc for usb_suspend_both() is updated with the fact. Acked-by: Alan Stern Signed-off-by: Ming Lei Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 52464fb2389b..8d4bc173d66a 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -976,7 +976,12 @@ struct usbdrv_wrap { * the "usbfs" filesystem. This lets devices provide ways to * expose information to user space regardless of where they * do (or don't) show up otherwise in the filesystem. - * @suspend: Called when the device is going to be suspended by the system. + * @suspend: Called when the device is going to be suspended by the + * system either from system sleep or runtime suspend context. The + * return value will be ignored in system sleep context, so do NOT + * try to continue using the device if suspend fails in this case. + * Instead, let the resume or reset-resume routine recover from + * the failure. * @resume: Called when the device is being resumed by the system. * @reset_resume: Called when the suspended device has been reset instead * of being resumed. -- cgit v1.2.3 From f91a595d0b813c3a2f3b848c165e865ca4c5b8cc Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Sat, 16 Mar 2013 11:46:44 +0530 Subject: memory: emif: Handle devices which are not rated for >85C As per JESD209-2E specification for LPDDR2, http://www.jedec.org/standards-documents/results/jesd209-2E Table 73, LPDDR2 memories come in two flavors - Standard and Extended. The Standard types can operate from -25C to +85C However, beyond that and upto +105C can only be supported by Extended types. Unfortunately, it seems there is no info in MR0(device info) or MR[1,2](device feature) for run time detection of this capability as far as seen on the spec. Hence, we provide a custom_config flag to be populated by platforms which have these "extended" type memories. For the "Standard" memories, we need to consider MR4 notifications of temperature triggers >85C as equivalent to thermal shutdown events (equivalent to Spec specified thermal shutdown events for "extended" parts). Reported-by: Richard Woodruff Signed-off-by: Nishanth Menon Signed-off-by: Lokesh Vutla Acked-by: Santosh Shilimkar Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/emif_plat.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/emif_plat.h b/include/linux/platform_data/emif_plat.h index 03378ca84061..5c19a2a647c4 100644 --- a/include/linux/platform_data/emif_plat.h +++ b/include/linux/platform_data/emif_plat.h @@ -40,6 +40,7 @@ /* Custom config requests */ #define EMIF_CUSTOM_CONFIG_LPMODE 0x00000001 #define EMIF_CUSTOM_CONFIG_TEMP_ALERT_POLL_INTERVAL 0x00000002 +#define EMIF_CUSTOM_CONFIG_EXTENDED_TEMP_PART 0x00000004 #ifndef __ASSEMBLY__ /** -- cgit v1.2.3 From 3edce1cf813aa6a087df7730cec0e67d57288300 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Sun, 17 Mar 2013 21:00:06 +0100 Subject: USB: cdc-wdm: implement IOCTL_WDM_MAX_COMMAND MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Userspace applications need to know the maximum supported message size. The cdc-wdm driver translates between a character device stream and a message based protocol. Each message is transported as a usb control message with no further encapsulation or syncronization. Each read or write on the character device should translate to exactly one usb control message to ensure that message boundaries are kept intact. That means that the userspace application must know the maximum message size supported by the device and driver, making this size a vital part of the cdc-wdm character device API. CDC WDM and CDC MBIM functions export the maximum supported message size through CDC functional descriptors. The cdc-wdm and cdc_mbim drivers will parse these descriptors and use the value chosen by the device. The only current way for a userspace application to retrive the value is by duplicating the descriptor parsing. This is an unnecessary complex task, and application writers are likely to postpone it, using a fixed value and adding a "todo" item. QMI functions have no way to tell the host what message size they support. The qmi_wwan driver use a fixed value based on protocol recommendations and observed device behaviour. Userspace applications must know and hard code the same value. This scheme will break if we ever encounter a QMI device needing a device specific message size quirk. We are currently unable to support such a device because using a non default size would break the implicit userspace API. The message size is currently a hidden attribute of the cdc-wdm userspace API. Retrieving it is unnecessarily complex, increasing the possibility of drivers and applications using different limits. The resulting errors are hard to debug, and can only be replicated on identical hardware. Exporting the maximum message size from the driver simplifies the task for the userspace application, and creates a unified information source independent of device and function class. It also serves to document that the message size is part of the cdc-wdm userspace API. This proposed API extension has been presented for the authors of userspace applications and libraries using the current API: libmbim, libqmi, uqmi, oFono and ModemManager. The replies were: Aleksander Morgado: "We do really need max message size for MBIM; and as you say, it may be good to have the max message size info also for QMI, so the new ioctl seems a good addition. So +1 from my side, for what it's worth." Dan Williams: "Yeah, +1 here. I'd prefer the sysfs file, but the fact that that doesn't work for fd passing pretty much kills it." No negative replies are so far received. Cc: Aleksander Morgado Cc: Dan Williams Signed-off-by: Bjørn Mork Acked-by: Oliver Neukum Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/cdc-wdm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/cdc-wdm.h b/include/linux/usb/cdc-wdm.h index 719c332620fa..0b3f4295c025 100644 --- a/include/linux/usb/cdc-wdm.h +++ b/include/linux/usb/cdc-wdm.h @@ -11,6 +11,8 @@ #ifndef __LINUX_USB_CDC_WDM_H #define __LINUX_USB_CDC_WDM_H +#include + extern struct usb_driver *usb_cdc_wdm_register(struct usb_interface *intf, struct usb_endpoint_descriptor *ep, int bufsize, -- cgit v1.2.3 From c5116e9d8d2de324f13a91fe5afc308cd6b0ca93 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 19 Mar 2013 16:58:58 +0100 Subject: ssb: define more board types MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 54 ++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 51 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 8b1322296fed..c64999fd1660 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -340,13 +340,61 @@ enum ssb_bustype { #define SSB_BOARDVENDOR_DELL 0x1028 /* Dell */ #define SSB_BOARDVENDOR_HP 0x0E11 /* HP */ /* board_type */ +#define SSB_BOARD_BCM94301CB 0x0406 +#define SSB_BOARD_BCM94301MP 0x0407 +#define SSB_BOARD_BU4309 0x040A +#define SSB_BOARD_BCM94309CB 0x040B +#define SSB_BOARD_BCM4309MP 0x040C +#define SSB_BOARD_BU4306 0x0416 #define SSB_BOARD_BCM94306MP 0x0418 #define SSB_BOARD_BCM4309G 0x0421 #define SSB_BOARD_BCM4306CB 0x0417 -#define SSB_BOARD_BCM4309MP 0x040C +#define SSB_BOARD_BCM94306PC 0x0425 /* pcmcia 3.3v 4306 card */ +#define SSB_BOARD_BCM94306CBSG 0x042B /* with SiGe PA */ +#define SSB_BOARD_PCSG94306 0x042D /* with SiGe PA */ +#define SSB_BOARD_BU4704SD 0x042E /* with sdram */ +#define SSB_BOARD_BCM94704AGR 0x042F /* dual 11a/11g Router */ +#define SSB_BOARD_BCM94308MP 0x0430 /* 11a-only minipci */ +#define SSB_BOARD_BU4318 0x0447 +#define SSB_BOARD_CB4318 0x0448 +#define SSB_BOARD_MPG4318 0x0449 #define SSB_BOARD_MP4318 0x044A -#define SSB_BOARD_BU4306 0x0416 -#define SSB_BOARD_BU4309 0x040A +#define SSB_BOARD_SD4318 0x044B +#define SSB_BOARD_BCM94306P 0x044C /* with SiGe */ +#define SSB_BOARD_BCM94303MP 0x044E +#define SSB_BOARD_BCM94306MPM 0x0450 +#define SSB_BOARD_BCM94306MPL 0x0453 +#define SSB_BOARD_PC4303 0x0454 /* pcmcia */ +#define SSB_BOARD_BCM94306MPLNA 0x0457 +#define SSB_BOARD_BCM94306MPH 0x045B +#define SSB_BOARD_BCM94306PCIV 0x045C +#define SSB_BOARD_BCM94318MPGH 0x0463 +#define SSB_BOARD_BU4311 0x0464 +#define SSB_BOARD_BCM94311MC 0x0465 +#define SSB_BOARD_BCM94311MCAG 0x0466 +/* 4321 boards */ +#define SSB_BOARD_BU4321 0x046B +#define SSB_BOARD_BU4321E 0x047C +#define SSB_BOARD_MP4321 0x046C +#define SSB_BOARD_CB2_4321 0x046D +#define SSB_BOARD_CB2_4321_AG 0x0066 +#define SSB_BOARD_MC4321 0x046E +/* 4325 boards */ +#define SSB_BOARD_BCM94325DEVBU 0x0490 +#define SSB_BOARD_BCM94325BGABU 0x0491 +#define SSB_BOARD_BCM94325SDGWB 0x0492 +#define SSB_BOARD_BCM94325SDGMDL 0x04AA +#define SSB_BOARD_BCM94325SDGMDL2 0x04C6 +#define SSB_BOARD_BCM94325SDGMDL3 0x04C9 +#define SSB_BOARD_BCM94325SDABGWBA 0x04E1 +/* 4322 boards */ +#define SSB_BOARD_BCM94322MC 0x04A4 +#define SSB_BOARD_BCM94322USB 0x04A8 /* dualband */ +#define SSB_BOARD_BCM94322HM 0x04B0 +#define SSB_BOARD_BCM94322USB2D 0x04Bf /* single band discrete front end */ +/* 4312 boards */ +#define SSB_BOARD_BU4312 0x048A +#define SSB_BOARD_BCM4312MCGSG 0x04B5 /* chip_package */ #define SSB_CHIPPACK_BCM4712S 1 /* Small 200pin 4712 */ #define SSB_CHIPPACK_BCM4712M 2 /* Medium 225pin 4712 */ -- cgit v1.2.3 From 3e6998574fde0ab7a3329c9229394dd80462ead2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 19 Mar 2013 16:58:59 +0100 Subject: bcma: define board types MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Using that IDs we can write workarounds for various cards Signed-off-by: Rafał Miłecki Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 54 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index e0ce311011c0..0ab6712fd76b 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -173,6 +173,60 @@ struct bcma_host_ops { #define BCMA_CHIP_ID_BCM53572 53572 #define BCMA_PKG_ID_BCM47188 9 +/* Board types (on PCI usually equals to the subsystem dev id) */ +/* BCM4313 */ +#define BCMA_BOARD_TYPE_BCM94313BU 0X050F +#define BCMA_BOARD_TYPE_BCM94313HM 0X0510 +#define BCMA_BOARD_TYPE_BCM94313EPA 0X0511 +#define BCMA_BOARD_TYPE_BCM94313HMG 0X051C +/* BCM4716 */ +#define BCMA_BOARD_TYPE_BCM94716NR2 0X04CD +/* BCM43224 */ +#define BCMA_BOARD_TYPE_BCM943224X21 0X056E +#define BCMA_BOARD_TYPE_BCM943224X21_FCC 0X00D1 +#define BCMA_BOARD_TYPE_BCM943224X21B 0X00E9 +#define BCMA_BOARD_TYPE_BCM943224M93 0X008B +#define BCMA_BOARD_TYPE_BCM943224M93A 0X0090 +#define BCMA_BOARD_TYPE_BCM943224X16 0X0093 +#define BCMA_BOARD_TYPE_BCM94322X9 0X008D +#define BCMA_BOARD_TYPE_BCM94322M35E 0X008E +/* BCM43228 */ +#define BCMA_BOARD_TYPE_BCM943228BU8 0X0540 +#define BCMA_BOARD_TYPE_BCM943228BU9 0X0541 +#define BCMA_BOARD_TYPE_BCM943228BU 0X0542 +#define BCMA_BOARD_TYPE_BCM943227HM4L 0X0543 +#define BCMA_BOARD_TYPE_BCM943227HMB 0X0544 +#define BCMA_BOARD_TYPE_BCM943228HM4L 0X0545 +#define BCMA_BOARD_TYPE_BCM943228SD 0X0573 +/* BCM4331 */ +#define BCMA_BOARD_TYPE_BCM94331X19 0X00D6 +#define BCMA_BOARD_TYPE_BCM94331X28 0X00E4 +#define BCMA_BOARD_TYPE_BCM94331X28B 0X010E +#define BCMA_BOARD_TYPE_BCM94331PCIEBT3AX 0X00E4 +#define BCMA_BOARD_TYPE_BCM94331X12_2G 0X00EC +#define BCMA_BOARD_TYPE_BCM94331X12_5G 0X00ED +#define BCMA_BOARD_TYPE_BCM94331X29B 0X00EF +#define BCMA_BOARD_TYPE_BCM94331CSAX 0X00EF +#define BCMA_BOARD_TYPE_BCM94331X19C 0X00F5 +#define BCMA_BOARD_TYPE_BCM94331X33 0X00F4 +#define BCMA_BOARD_TYPE_BCM94331BU 0X0523 +#define BCMA_BOARD_TYPE_BCM94331S9BU 0X0524 +#define BCMA_BOARD_TYPE_BCM94331MC 0X0525 +#define BCMA_BOARD_TYPE_BCM94331MCI 0X0526 +#define BCMA_BOARD_TYPE_BCM94331PCIEBT4 0X0527 +#define BCMA_BOARD_TYPE_BCM94331HM 0X0574 +#define BCMA_BOARD_TYPE_BCM94331PCIEDUAL 0X059B +#define BCMA_BOARD_TYPE_BCM94331MCH5 0X05A9 +#define BCMA_BOARD_TYPE_BCM94331CS 0X05C6 +#define BCMA_BOARD_TYPE_BCM94331CD 0X05DA +/* BCM53572 */ +#define BCMA_BOARD_TYPE_BCM953572BU 0X058D +#define BCMA_BOARD_TYPE_BCM953572NR2 0X058E +#define BCMA_BOARD_TYPE_BCM947188NR2 0X058F +#define BCMA_BOARD_TYPE_BCM953572SDRNR2 0X0590 +/* BCM43142 */ +#define BCMA_BOARD_TYPE_BCM943142HM 0X05E0 + struct bcma_device { struct bcma_bus *bus; struct bcma_device_id id; -- cgit v1.2.3 From 12bef78f0a806639daef58b1770be6ea19b2e94d Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Thu, 21 Mar 2013 16:26:19 +0100 Subject: ssb: fix sprom constant for ant_available_{bg,a} This was done accordingly to new specs. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/ssb/ssb_regs.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h index 6ecfa02ddbac..3a7256955b10 100644 --- a/include/linux/ssb/ssb_regs.h +++ b/include/linux/ssb/ssb_regs.h @@ -289,11 +289,11 @@ #define SSB_SPROM4_ETHPHY_ET1A_SHIFT 5 #define SSB_SPROM4_ETHPHY_ET0M (1<<14) /* MDIO for enet0 */ #define SSB_SPROM4_ETHPHY_ET1M (1<<15) /* MDIO for enet1 */ -#define SSB_SPROM4_ANTAVAIL 0x005D /* Antenna available bitfields */ -#define SSB_SPROM4_ANTAVAIL_A 0x00FF /* A-PHY bitfield */ -#define SSB_SPROM4_ANTAVAIL_A_SHIFT 0 -#define SSB_SPROM4_ANTAVAIL_BG 0xFF00 /* B-PHY and G-PHY bitfield */ -#define SSB_SPROM4_ANTAVAIL_BG_SHIFT 8 +#define SSB_SPROM4_ANTAVAIL 0x005C /* Antenna available bitfields */ +#define SSB_SPROM4_ANTAVAIL_BG 0x00FF /* B-PHY and G-PHY bitfield */ +#define SSB_SPROM4_ANTAVAIL_BG_SHIFT 0 +#define SSB_SPROM4_ANTAVAIL_A 0xFF00 /* A-PHY bitfield */ +#define SSB_SPROM4_ANTAVAIL_A_SHIFT 8 #define SSB_SPROM4_AGAIN01 0x005E /* Antenna Gain (in dBm Q5.2) */ #define SSB_SPROM4_AGAIN0 0x00FF /* Antenna 0 */ #define SSB_SPROM4_AGAIN0_SHIFT 0 -- cgit v1.2.3 From 0f16cfe39eeef47c91aa3c3bf2b49954d5313a58 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 21 Mar 2013 12:36:42 +0100 Subject: USB: serial: remove generic disconnect callback Remove the now empty generic disconnect callback and make the disconnect callback non-mandatory. Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/serial.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 1819b59aab2a..437dfd6787f9 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -329,7 +329,6 @@ extern void usb_serial_generic_read_bulk_callback(struct urb *urb); extern void usb_serial_generic_write_bulk_callback(struct urb *urb); extern void usb_serial_generic_throttle(struct tty_struct *tty); extern void usb_serial_generic_unthrottle(struct tty_struct *tty); -extern void usb_serial_generic_disconnect(struct usb_serial *serial); extern void usb_serial_generic_release(struct usb_serial *serial); extern int usb_serial_generic_register(void); extern void usb_serial_generic_deregister(void); -- cgit v1.2.3 From 79b80b8a1141ba0605e917a6fc12d44383ab29b8 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 21 Mar 2013 12:36:43 +0100 Subject: USB: serial: remove generic release callback Remove empty generic release implementation and make the release callback non-mandatory (like attach, probe and disconnect). Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/serial.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 437dfd6787f9..3f8f5e3c76d5 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -329,7 +329,6 @@ extern void usb_serial_generic_read_bulk_callback(struct urb *urb); extern void usb_serial_generic_write_bulk_callback(struct urb *urb); extern void usb_serial_generic_throttle(struct tty_struct *tty); extern void usb_serial_generic_unthrottle(struct tty_struct *tty); -extern void usb_serial_generic_release(struct usb_serial *serial); extern int usb_serial_generic_register(void); extern void usb_serial_generic_deregister(void); extern int usb_serial_generic_submit_read_urbs(struct usb_serial_port *port, -- cgit v1.2.3 From 143d9d961608b737d90a813deaaf91affb41c83c Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 21 Mar 2013 12:36:51 +0100 Subject: USB: serial: add tiocmiwait subdriver operation Add tiocmiwait operation to struct usb_serial_driver. Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/serial.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 3f8f5e3c76d5..9c8b53f80f48 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -272,6 +272,7 @@ struct usb_serial_driver { int (*tiocmget)(struct tty_struct *tty); int (*tiocmset)(struct tty_struct *tty, unsigned int set, unsigned int clear); + int (*tiocmiwait)(struct tty_struct *tty, unsigned long arg); int (*get_icount)(struct tty_struct *tty, struct serial_icounter_struct *icount); /* Called by the tty layer for port level work. There may or may not -- cgit v1.2.3 From 980373b7918b8023be6b7df03857f494ae124d0b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 21 Mar 2013 12:36:52 +0100 Subject: USB: serial: add generic TIOCMIWAIT implementation Add generic TIOCMIWAIT implementation which correctly handles hangup, USB-device disconnect, does not rely on the deprecated sleep_on functions and hence does not suffer from the races currently affecting several usb-serial drivers. This makes it much easier to add TIOCMIWAIT support to subdrivers as the tricky details related to hangup and disconnect (e.g. atomicity, that the private port data may have been freed when woken up, and waking up processes at disconnect) have been handled once and for all. To add support to a subdriver, simply set the tiocmiwait-port-operation field, update the port icount fields and wake up any process sleeping on the tty-port modem-status-change wait queue on changes. Note that the tty-port initialised flag can be used to detect disconnected as the port will be hung up as part of disconnect (and cannot be reactivated due to the disconnected flag). However, as the tty-port implementation currently wakes up processes before calling port shutdown, the tty-hupping flag must also be checked to detect hangup for now. Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/serial.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 9c8b53f80f48..47c8d2c506c8 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -15,6 +15,7 @@ #include #include +#include #include #include @@ -61,6 +62,7 @@ * @bulk_out_buffers: pointers to the bulk out buffers for this port * @write_urbs: pointers to the bulk out urbs for this port * @write_urbs_free: status bitmap the for bulk out urbs + * @icount: interrupt counters * @tx_bytes: number of bytes currently in host stack queues * @bulk_out_endpointAddress: endpoint address for the bulk out pipe for this * port. @@ -109,6 +111,7 @@ struct usb_serial_port { unsigned long write_urbs_free; __u8 bulk_out_endpointAddress; + struct async_icount icount; int tx_bytes; unsigned long flags; @@ -330,6 +333,8 @@ extern void usb_serial_generic_read_bulk_callback(struct urb *urb); extern void usb_serial_generic_write_bulk_callback(struct urb *urb); extern void usb_serial_generic_throttle(struct tty_struct *tty); extern void usb_serial_generic_unthrottle(struct tty_struct *tty); +extern int usb_serial_generic_tiocmiwait(struct tty_struct *tty, + unsigned long arg); extern int usb_serial_generic_register(void); extern void usb_serial_generic_deregister(void); extern int usb_serial_generic_submit_read_urbs(struct usb_serial_port *port, -- cgit v1.2.3 From befefcda4bddc52d29248931801961a72aeef28b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 21 Mar 2013 12:36:54 +0100 Subject: USB: serial: add generic get_icount implementation Add generic get_icount implementation that subdrivers relying on the port interrupt counters can use. Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/serial.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 47c8d2c506c8..c786ee7fca8f 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -335,6 +335,8 @@ extern void usb_serial_generic_throttle(struct tty_struct *tty); extern void usb_serial_generic_unthrottle(struct tty_struct *tty); extern int usb_serial_generic_tiocmiwait(struct tty_struct *tty, unsigned long arg); +extern int usb_serial_generic_get_icount(struct tty_struct *tty, + struct serial_icounter_struct *icount); extern int usb_serial_generic_register(void); extern void usb_serial_generic_deregister(void); extern int usb_serial_generic_submit_read_urbs(struct usb_serial_port *port, -- cgit v1.2.3 From 53ab34dc50ad99366257d34cdb8a84f24250d611 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 21 Mar 2013 12:37:35 +0100 Subject: USB: serial: remove unused MSR-wait queue Remove the port MSR-wait queue now that all drivers have been migrated to the tty-port queue. Signed-off-by: Johan Hovold Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/serial.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index c786ee7fca8f..b9b0f7b4e43b 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -68,7 +68,6 @@ * port. * @flags: usb serial port flags * @write_wait: a wait_queue_head_t used by the port. - * @delta_msr_wait: modem-status-change wait queue * @work: work queue entry for the line discipline waking up. * @throttled: nonzero if the read urb is inactive to throttle the device * @throttle_req: nonzero if the tty wants to throttle us @@ -116,7 +115,6 @@ struct usb_serial_port { unsigned long flags; wait_queue_head_t write_wait; - wait_queue_head_t delta_msr_wait; struct work_struct work; char throttled; char throttle_req; -- cgit v1.2.3 From 1e9663c62b32f695af37fec4afc473b59f5ca9b4 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 25 Mar 2013 08:58:00 +0000 Subject: iio:trigger: Introduce iio_tigger_{set,get}_drvdata Introduce iio_tigger_{set,get}_drvdata which allows to attach driver specific data to a trigger. The functions wrap access to the triggers private_data field and all current users are updated to use iio_tigger_{set,get}_drvdata instead of directly accessing the private_data field. This is the first step towards removing the private_data field from the iio_trigger struct. The following coccinelle script has been used to update the drivers: @@ struct iio_trigger *trigger; expression priv; @@ -trigger->private_data = priv +iio_trigger_set_drv_data(trigger, priv) @@ struct iio_trigger *trigger; @@ -trigger->private_data +iio_trigger_get_drv_data(trigger) Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- include/linux/iio/trigger.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index c66e0a96f6e8..b81948aba1d6 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -91,6 +91,30 @@ static inline void iio_trigger_get(struct iio_trigger *trig) __module_get(trig->ops->owner); } +/** + * iio_device_set_drvdata() - Set trigger driver data + * @trig: IIO trigger structure + * @data: Driver specific data + * + * Allows to attach an arbitrary pointer to an IIO trigger, which can later be + * retrieved by iio_trigger_get_drvdata(). + */ +static inline void iio_trigger_set_drvdata(struct iio_trigger *trig, void *data) +{ + trig->private_data = data; +} + +/** + * iio_trigger_get_drvdata() - Get trigger driver data + * @trig: IIO trigger structure + * + * Returns the data previously set with iio_trigger_set_drvdata() + */ +static inline void *iio_trigger_get_drvdata(struct iio_trigger *trig) +{ + return trig->private_data; +} + /** * iio_trigger_register() - register a trigger with the IIO core * @trig_info: trigger to be registered -- cgit v1.2.3 From 5034bfc976928b447cb6decd311d35161107a72f Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 25 Mar 2013 08:58:00 +0000 Subject: iio:trigger: Use dev_{set,get}_drvdata for private data management Use dev_{set,get}_drvdata for managing private data attached to a trigger instead of using a custom field in the iio_trigger struct. Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- include/linux/iio/trigger.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index b81948aba1d6..3869c525b052 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -44,7 +44,6 @@ struct iio_trigger_ops { * @id: [INTERN] unique id number * @name: [DRIVER] unique name * @dev: [DRIVER] associated device (if relevant) - * @private_data: [DRIVER] device specific data * @list: [INTERN] used in maintenance of global trigger list * @alloc_list: [DRIVER] used for driver specific trigger list * @use_count: use count for the trigger @@ -60,7 +59,6 @@ struct iio_trigger { const char *name; struct device dev; - void *private_data; struct list_head list; struct list_head alloc_list; int use_count; @@ -101,7 +99,7 @@ static inline void iio_trigger_get(struct iio_trigger *trig) */ static inline void iio_trigger_set_drvdata(struct iio_trigger *trig, void *data) { - trig->private_data = data; + dev_set_drvdata(&trig->dev, data); } /** @@ -112,7 +110,7 @@ static inline void iio_trigger_set_drvdata(struct iio_trigger *trig, void *data) */ static inline void *iio_trigger_get_drvdata(struct iio_trigger *trig) { - return trig->private_data; + return dev_get_drvdata(&trig->dev); } /** -- cgit v1.2.3 From 57df8106932b57427df1eaaa13871857f75b1194 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Fri, 8 Feb 2013 14:52:06 +0800 Subject: Thermal: exynos: fix cooling state translation Signed-off-by: Zhang Rui Tested-by: Amit Daniel kachhap --- include/linux/cpu_cooling.h | 7 +++++++ include/linux/thermal.h | 5 ++++- 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index 40b4ef54cc7d..bc479b1e0fd9 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -42,6 +42,8 @@ struct thermal_cooling_device *cpufreq_cooling_register( * @cdev: thermal cooling device pointer. */ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); + +unsigned long cpufreq_cooling_get_level(unsigned int, unsigned int); #else /* !CONFIG_CPU_THERMAL */ static inline struct thermal_cooling_device *cpufreq_cooling_register( const struct cpumask *clip_cpus) @@ -53,6 +55,11 @@ static inline void cpufreq_cooling_unregister( { return; } +static inline unsigned long cpufreq_cooling_get_level(unsigned int, + unsigned int) +{ + return THERMAL_CSTATE_INVALID; +} #endif /* CONFIG_CPU_THERMAL */ #endif /* __CPU_COOLING_H__ */ diff --git a/include/linux/thermal.h b/include/linux/thermal.h index f0bd7f90a90d..5a3b428daaab 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -33,8 +33,11 @@ #define THERMAL_MAX_TRIPS 12 #define THERMAL_NAME_LENGTH 20 +/* invalid cooling state */ +#define THERMAL_CSTATE_INVALID -1UL + /* No upper/lower limit requirement */ -#define THERMAL_NO_LIMIT -1UL +#define THERMAL_NO_LIMIT THERMAL_CSTATE_INVALID /* Unit conversion macros */ #define KELVIN_TO_CELSIUS(t) (long)(((long)t-2732 >= 0) ? \ -- cgit v1.2.3 From f8b587055a793c7719f0d4f41b7b4aeeef43aa2d Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Wed, 20 Mar 2013 21:38:07 +0000 Subject: thermal: Fix compiler warning The following warning is obtained when CONFIG_NET is not defined: In file included from drivers/thermal/mvebu_thermal.c:27:0: include/linux/thermal.h:254:12: warning: 'thermal_generate_netlink_event' defined but not used [-Wunused-function] This patch fixes the warning by properly inlining thermal_generate_netlink_event(). Signed-off-by: Ezequiel Garcia Signed-off-by: Zhang Rui --- include/linux/thermal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index f0bd7f90a90d..fd7b8f3e6f42 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -251,7 +251,7 @@ void thermal_unregister_governor(struct thermal_governor *); extern int thermal_generate_netlink_event(struct thermal_zone_device *tz, enum events event); #else -static int thermal_generate_netlink_event(struct thermal_zone_device *tz, +static inline int thermal_generate_netlink_event(struct thermal_zone_device *tz, enum events event) { return 0; -- cgit v1.2.3 From c0f4dfd4f90f1667d234d21f15153ea09a2eaa66 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 28 Dec 2012 11:30:36 -0800 Subject: rcu: Make RCU_FAST_NO_HZ take advantage of numbered callbacks Because RCU callbacks are now associated with the number of the grace period that they must wait for, CPUs can now take advance callbacks corresponding to grace periods that ended while a given CPU was in dyntick-idle mode. This eliminates the need to try forcing the RCU state machine while entering idle, thus reducing the CPU intensiveness of RCU_FAST_NO_HZ, which should increase its energy efficiency. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index b758ce17b309..9ed2c9a4de45 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -80,6 +80,7 @@ extern void do_trace_rcu_torture_read(char *rcutorturename, #define UINT_CMP_LT(a, b) (UINT_MAX / 2 < (a) - (b)) #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) +#define ulong2long(a) (*(long *)(&(a))) /* Exported common interfaces */ -- cgit v1.2.3 From f607e31ce3963327f749b56c65dfec2642aa623c Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 22 Feb 2013 18:36:53 +0000 Subject: ASoC: arizona: Fix interaction between headphone outputs and identification Running HPDET while the headphone outputs are enabled can disrupt the operation of HPDET. In order to avoid this HPDET needs to disable the headphone outputs and ASoC needs to not enable them while HPDET is running. Do the ASoC side of this by storing the enable state in the core driver structure and only writing to the device if a flag indicating that the accessory detection side is in a state where it can have the headphone output stage enabled. Signed-off-by: Mark Brown --- include/linux/mfd/arizona/core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/core.h b/include/linux/mfd/arizona/core.h index a710255528d7..cc281368dc55 100644 --- a/include/linux/mfd/arizona/core.h +++ b/include/linux/mfd/arizona/core.h @@ -100,6 +100,9 @@ struct arizona { struct regmap_irq_chip_data *aod_irq_chip; struct regmap_irq_chip_data *irq_chip; + bool hpdet_magic; + unsigned int hp_ena; + struct mutex clk_lock; int clk32k_ref; -- cgit v1.2.3 From de88cbb7b244f3bcd61d49fd6dec35c19192545a Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Fri, 18 Jan 2013 15:31:37 +0000 Subject: arm: Move chained_irq_(enter|exit) to a generic file These functions have been introduced by commit 10a8c383 (irq: introduce entry and exit functions for chained handlers) in asm/mach/irq.h. This patch moves them to linux/irqchip/chained_irq.h so that generic irqchip drivers do not rely on architecture specific header files. Signed-off-by: Catalin Marinas Tested-by: Marc Zyngier Cc: Russell King Cc: Thomas Gleixner Cc: Rob Herring --- include/linux/irqchip/chained_irq.h | 52 +++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) create mode 100644 include/linux/irqchip/chained_irq.h (limited to 'include/linux') diff --git a/include/linux/irqchip/chained_irq.h b/include/linux/irqchip/chained_irq.h new file mode 100644 index 000000000000..adf4c30f3af6 --- /dev/null +++ b/include/linux/irqchip/chained_irq.h @@ -0,0 +1,52 @@ +/* + * Chained IRQ handlers support. + * + * Copyright (C) 2011 ARM Ltd. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ +#ifndef __IRQCHIP_CHAINED_IRQ_H +#define __IRQCHIP_CHAINED_IRQ_H + +#include + +/* + * Entry/exit functions for chained handlers where the primary IRQ chip + * may implement either fasteoi or level-trigger flow control. + */ +static inline void chained_irq_enter(struct irq_chip *chip, + struct irq_desc *desc) +{ + /* FastEOI controllers require no action on entry. */ + if (chip->irq_eoi) + return; + + if (chip->irq_mask_ack) { + chip->irq_mask_ack(&desc->irq_data); + } else { + chip->irq_mask(&desc->irq_data); + if (chip->irq_ack) + chip->irq_ack(&desc->irq_data); + } +} + +static inline void chained_irq_exit(struct irq_chip *chip, + struct irq_desc *desc) +{ + if (chip->irq_eoi) + chip->irq_eoi(&desc->irq_data); + else + chip->irq_unmask(&desc->irq_data); +} + +#endif /* __IRQCHIP_CHAINED_IRQ_H */ -- cgit v1.2.3 From c0114709ed85a5693eb74acdfa03d94f7f12e5b8 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 14 Jan 2013 18:05:37 +0000 Subject: irqchip: gic: Perform the gic_secondary_init() call via CPU notifier All the calls to gic_secondary_init() pass 0 as the first argument. Since this function is called on each CPU when starting, it can be done in a platform-independent way via a CPU notifier registered by the GIC code. Signed-off-by: Catalin Marinas Acked-by: Stephen Warren Acked-by: Viresh Kumar Acked-by: Santosh Shilimkar Acked-by: Rob Herring Acked-by: Simon Horman Tested-by: Simon Horman Acked-by: Srinidhi Kasagar Tested-by: Dinh Nguyen Acked-by: Nicolas Pitre Tested-by: Marc Zyngier Cc: Russell King Cc: Thomas Gleixner Cc: Kukjin Kim Cc: Sascha Hauer Cc: David Brown Cc: Bryan Huntsman Cc: Tony Lindgren Cc: Magnus Damm Cc: Shiraz Hashim Cc: Linus Walleij Cc: Will Deacon Cc: Kukjin Kim Cc: Barry Song --- include/linux/irqchip/arm-gic.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index 3fd8e4290a1c..3e203eb23cc7 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -65,7 +65,6 @@ extern struct irq_chip gic_arch_extn; void gic_init_bases(unsigned int, int, void __iomem *, void __iomem *, u32 offset, struct device_node *); -void gic_secondary_init(unsigned int); void gic_cascade_irq(unsigned int gic_nr, unsigned int irq); static inline void gic_init(unsigned int nr, int start, -- cgit v1.2.3 From 6752c8db8e0cfedb44ba62806dd15b383ed64000 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?YOSHIFUJI=20Hideaki=20/=20=E5=90=89=E8=97=A4=E8=8B=B1?= =?UTF-8?q?=E6=98=8E?= Date: Mon, 25 Mar 2013 08:26:16 +0000 Subject: firewire net, ipv4 arp: Extend hardware address and remove driver-level packet inspection. Inspection of upper layer protocol is considered harmful, especially if it is about ARP or other stateful upper layer protocol; driver cannot (and should not) have full state of them. IPv4 over Firewire module used to inspect ARP (both in sending path and in receiving path), and record peer's GUID, max packet size, max speed and fifo address. This patch removes such inspection by extending our "hardware address" definition to include other information as well: max packet size, max speed and fifo. By doing this, The neighbour module in networking subsystem can cache them. Note: As we have started ignoring sspd and max_rec in ARP/NDP, those information will not be used in the driver when sending. When a packet is being sent, the IP layer fills our pseudo header with the extended "hardware address", including GUID and fifo. The driver can look-up node-id (the real but rather volatile low-level address) by GUID, and then the module can send the packet to the wire using parameters provided in the extendedn hardware address. This approach is realistic because IP over IEEE1394 (RFC2734) and IPv6 over IEEE1394 (RFC3146) share same "hardware address" format in their address resolution protocols. Here, extended "hardware address" is defined as follows: union fwnet_hwaddr { u8 u[16]; struct { __be64 uniq_id; /* EUI-64 */ u8 max_rec; /* max packet size */ u8 sspd; /* max speed */ __be16 fifo_hi; /* hi 16bits of FIFO addr */ __be32 fifo_lo; /* lo 32bits of FIFO addr */ } __packed uc; }; Note that Hardware address is declared as union, so that we can map full IP address into this, when implementing MCAP (Multicast Cannel Allocation Protocol) for IPv6, but IP and ARP subsystem do not need to know this format in detail. One difference between original ARP (RFC826) and 1394 ARP (RFC2734) is that 1394 ARP Request/Reply do not contain the target hardware address field (aka ar$tha). This difference is handled in the ARP subsystem. CC: Stephan Gatzka Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/if_arp.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index 89b4614a4722..f563907ed776 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -33,7 +33,15 @@ static inline struct arphdr *arp_hdr(const struct sk_buff *skb) static inline int arp_hdr_len(struct net_device *dev) { - /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ - return sizeof(struct arphdr) + (dev->addr_len + sizeof(u32)) * 2; + switch (dev->type) { +#if IS_ENABLED(CONFIG_FIREWIRE_NET) + case ARPHRD_IEEE1394: + /* ARP header, device address and 2 IP addresses */ + return sizeof(struct arphdr) + dev->addr_len + sizeof(u32) * 2; +#endif + default: + /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ + return sizeof(struct arphdr) + (dev->addr_len + sizeof(u32)) * 2; + } } #endif /* _LINUX_IF_ARP_H */ -- cgit v1.2.3 From 0e5e4f0e56aca0df1d5648db0be9028bd573b25c Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 9 Nov 2012 16:33:05 -0700 Subject: NVMe: Add discard support for capable devices This adds discard support to block queues if the nvme device is capable of deallocating blocks as indicated by the controller's optional command support. A discard flagged bio request will submit an NVMe deallocate Data Set Management command for the requested blocks. Signed-off-by: Keith Busch Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 4fa3b0b9b071..bde44c1fd213 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -107,6 +107,12 @@ struct nvme_id_ctrl { __u8 vs[1024]; }; +enum { + NVME_CTRL_ONCS_COMPARE = 1 << 0, + NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, + NVME_CTRL_ONCS_DSM = 1 << 2, +}; + struct nvme_lbaf { __le16 ms; __u8 ds; @@ -246,6 +252,31 @@ enum { NVME_RW_DSM_COMPRESSED = 1 << 7, }; +struct nvme_dsm_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + __le64 prp1; + __le64 prp2; + __le32 nr; + __le32 attributes; + __u32 rsvd12[4]; +}; + +enum { + NVME_DSMGMT_IDR = 1 << 0, + NVME_DSMGMT_IDW = 1 << 1, + NVME_DSMGMT_AD = 1 << 2, +}; + +struct nvme_dsm_range { + __le32 cattr; + __le32 nlb; + __le64 slba; +}; + /* Admin commands */ enum nvme_admin_opcode { @@ -372,6 +403,7 @@ struct nvme_command { struct nvme_create_sq create_sq; struct nvme_delete_queue delete_queue; struct nvme_download_firmware dlfw; + struct nvme_dsm_cmd dsm; }; }; -- cgit v1.2.3 From ece70094f6ab2107d4313fa1802b13dab0234ac5 Mon Sep 17 00:00:00 2001 From: Prashant Gaikwad Date: Wed, 20 Mar 2013 17:30:34 +0530 Subject: clk: Add composite clock type Not all clocks are required to be decomposed into basic clock types but at the same time want to use the functionality provided by these basic clock types instead of duplicating. For example, Tegra SoC has ~100 clocks which can be decomposed into Mux -> Div -> Gate clock types making the clock count to ~300. Also, parent change operation can not be performed on gate clock which forces to use mux clock in driver if want to change the parent. Instead aggregate the basic clock types functionality into one clock and just use this clock for all operations. This clock type re-uses the functionality of basic clock types and not limited to basic clock types but any hardware-specific implementation. Signed-off-by: Prashant Gaikwad Signed-off-by: Mike Turquette --- include/linux/clk-provider.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 63ba3b740794..1f0352802794 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -342,6 +342,37 @@ struct clk *clk_register_fixed_factor(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned int mult, unsigned int div); +/*** + * struct clk_composite - aggregate clock of mux, divider and gate clocks + * + * @hw: handle between common and hardware-specific interfaces + * @mux_hw: handle between composite and hardware-specifix mux clock + * @div_hw: handle between composite and hardware-specifix divider clock + * @gate_hw: handle between composite and hardware-specifix gate clock + * @mux_ops: clock ops for mux + * @div_ops: clock ops for divider + * @gate_ops: clock ops for gate + */ +struct clk_composite { + struct clk_hw hw; + struct clk_ops ops; + + struct clk_hw *mux_hw; + struct clk_hw *div_hw; + struct clk_hw *gate_hw; + + const struct clk_ops *mux_ops; + const struct clk_ops *div_ops; + const struct clk_ops *gate_ops; +}; + +struct clk *clk_register_composite(struct device *dev, const char *name, + const char **parent_names, int num_parents, + struct clk_hw *mux_hw, const struct clk_ops *mux_ops, + struct clk_hw *div_hw, const struct clk_ops *div_ops, + struct clk_hw *gate_hw, const struct clk_ops *gate_ops, + unsigned long flags); + /** * clk_register - allocate a new clock, register it and return an opaque cookie * @dev: device that is registering this clock -- cgit v1.2.3 From 3a54aaa0a3ddb2cf2ec1b94a94024e9a8a8af962 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 24 Jan 2013 16:10:26 +0100 Subject: perf/x86: Improve sysfs event mapping with event string This patch extends Jiri's changes to make generic events mapping visible via sysfs. The patch extends the mechanism to non-generic events by allowing the mappings to be hardcoded in strings. This mechanism will be used by the PEBS-LL patch later on. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: ak@linux.intel.com Cc: acme@redhat.com Cc: jolsa@redhat.com Cc: namhyung.kim@lge.com Link: http://lkml.kernel.org/r/1359040242-8269-3-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar [ fixed up conflict with 2663960 "perf: Make EVENT_ATTR global" ] Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8737e1cee8b2..1c592114c437 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -809,6 +809,7 @@ do { \ struct perf_pmu_events_attr { struct device_attribute attr; u64 id; + const char *event_str; }; #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ -- cgit v1.2.3 From 85467136cdcc674f30beb0e5b79f048fe3a6a76f Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Wed, 27 Feb 2013 17:06:45 -0700 Subject: PCI: Add PCI_BUS_NUM() and PCI_DEVID() interfaces PCI defines PCI_DEVFN(), PCI_SLOT(), and PCI_FUNC() interfaces; however, it doesn't have interfaces to return PCI bus and PCI device id. Drivers (AMD IOMMU, and AER) implement module specific definitions for PCI_BUS() and AMD_IOMMU driver also has a module specific interface to calculate PCI device id from bus number and devfn. Add PCI_BUS_NUM and PCI_DEVID interfaces to return PCI bus number and PCI device id respectively to avoid the need for duplicate definitions in other modules. AER driver code and AMD IOMMU driver define PCI_BUS. AMD IOMMU driver defines an interface to calculate device id from bus number, and devfn pair. PCI_DEVFN(), PCI_SLOT(), and PCI_FUNC() interfaces are exported to user-space via uapi/linux/pci.h. However, in the interest to keep the new interfaces as kernel only and not export them to user-space unnecessarily, added them to linux/pci.h instead. Signed-off-by: Shuah Khan Signed-off-by: Bjorn Helgaas Acked-by: Joerg Roedel --- include/linux/pci.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 2461033a7987..849a336e149c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -35,6 +35,21 @@ /* Include the ID list */ #include +/* + * The PCI interface treats multi-function devices as independent + * devices. The slot/function address of each device is encoded + * in a single byte as follows: + * + * 7:3 = slot + * 2:0 = function + * PCI_DEVFN(), PCI_SLOT(), and PCI_FUNC() are defined uapi/linux/pci.h + * In the interest of not exposing interfaces to user-space unnecessarily, + * the following kernel only defines are being added here. + */ +#define PCI_DEVID(bus, devfn) ((((u16)bus) << 8) | devfn) +/* return bus from PCI devid = ((u16)bus_number) << 8) | devfn */ +#define PCI_BUS_NUM(x) (((x) >> 8) & 0xff) + /* pci_slot represents a physical slot */ struct pci_slot { struct pci_bus *bus; /* The bus this slot is on */ -- cgit v1.2.3 From 13c3b0fcc8e33ba49f252378f6e7290b146042af Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Mon, 4 Mar 2013 18:40:57 -0700 Subject: NVMe: Move structures & definitions to header file nvme-scsi.c uses several data structures and definitions that were previously private to nvme-core.c. Move the definitions to nvme.h, protected by __KERNEL__. Signed-off-by: Vishal Verma Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index bde44c1fd213..6f899add14ab 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -493,4 +493,64 @@ struct nvme_admin_cmd { #define NVME_IOCTL_ADMIN_CMD _IOWR('N', 0x41, struct nvme_admin_cmd) #define NVME_IOCTL_SUBMIT_IO _IOW('N', 0x42, struct nvme_user_io) +#ifdef __KERNEL__ +#include + +#define NVME_IO_TIMEOUT (5 * HZ) + +/* + * Represents an NVM Express device. Each nvme_dev is a PCI function. + */ +struct nvme_dev { + struct list_head node; + struct nvme_queue **queues; + u32 __iomem *dbs; + struct pci_dev *pci_dev; + struct dma_pool *prp_page_pool; + struct dma_pool *prp_small_pool; + int instance; + int queue_count; + int db_stride; + u32 ctrl_config; + struct msix_entry *entry; + struct nvme_bar __iomem *bar; + struct list_head namespaces; + char serial[20]; + char model[40]; + char firmware_rev[8]; + u32 max_hw_sectors; + u16 oncs; +}; + +/* + * An NVM Express namespace is equivalent to a SCSI LUN + */ +struct nvme_ns { + struct list_head list; + + struct nvme_dev *dev; + struct request_queue *queue; + struct gendisk *disk; + + int ns_id; + int lba_shift; +}; + +/* + * The nvme_iod describes the data in an I/O, including the list of PRP + * entries. You can't see it in this data structure because C doesn't let + * me express that. Use nvme_alloc_iod to ensure there's enough space + * allocated to store the PRP list. + */ +struct nvme_iod { + void *private; /* For the use of the submitter of the I/O */ + int npages; /* In the PRP list. 0 means small pool in use */ + int offset; /* Of PRP list */ + int nents; /* Used in scatterlist */ + int length; /* Of data, in bytes */ + dma_addr_t first_dma; + struct scatterlist sg[0]; +}; +#endif + #endif /* _LINUX_NVME_H */ -- cgit v1.2.3 From f8ebf8409abfdaeeb8c847381629a2a8b8e3d816 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Wed, 27 Mar 2013 07:13:41 -0400 Subject: NVMe: Add definitions for format command The SCSI emulation has the ability to send format commands, so we need to add the definition of the command. Also add a missing error code. Signed-off-by: Vishal Verma Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 6f899add14ab..f1974cab60cf 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -393,6 +393,16 @@ struct nvme_download_firmware { __u32 rsvd12[4]; }; +struct nvme_format_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[4]; + __le32 cdw10; + __u32 rsvd11[5]; +}; + struct nvme_command { union { struct nvme_common_command common; @@ -403,6 +413,7 @@ struct nvme_command { struct nvme_create_sq create_sq; struct nvme_delete_queue delete_queue; struct nvme_download_firmware dlfw; + struct nvme_format_cmd format; struct nvme_dsm_cmd dsm; }; }; @@ -420,6 +431,7 @@ enum { NVME_SC_FUSED_FAIL = 0x9, NVME_SC_FUSED_MISSING = 0xa, NVME_SC_INVALID_NS = 0xb, + NVME_SC_CMD_SEQ_ERROR = 0xc, NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, NVME_SC_NS_NOT_READY = 0x82, -- cgit v1.2.3 From e05a4f4fc9ddf7a8633c368786a115b3111d36fd Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Mon, 25 Mar 2013 21:12:27 +0100 Subject: Remove spurious _H suffixes from ifdef comments Signed-off-by: Paul Bolle Signed-off-by: Jiri Kosina --- include/linux/evm.h | 2 +- include/linux/ima.h | 4 ++-- include/linux/integrity.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h index 9fc13a760928..1fcb88ca88de 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -96,5 +96,5 @@ static inline int evm_inode_init_security(struct inode *inode, return 0; } -#endif /* CONFIG_EVM_H */ +#endif /* CONFIG_EVM */ #endif /* LINUX_EVM_H */ diff --git a/include/linux/ima.h b/include/linux/ima.h index 86c361e947b9..1b7f268cddce 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -46,7 +46,7 @@ static inline int ima_module_check(struct file *file) return 0; } -#endif /* CONFIG_IMA_H */ +#endif /* CONFIG_IMA */ #ifdef CONFIG_IMA_APPRAISE extern void ima_inode_post_setattr(struct dentry *dentry); @@ -72,5 +72,5 @@ static inline int ima_inode_removexattr(struct dentry *dentry, { return 0; } -#endif /* CONFIG_IMA_APPRAISE_H */ +#endif /* CONFIG_IMA_APPRAISE */ #endif /* _LINUX_IMA_H */ diff --git a/include/linux/integrity.h b/include/linux/integrity.h index 66c5fe9550a5..83222cebd47b 100644 --- a/include/linux/integrity.h +++ b/include/linux/integrity.h @@ -36,5 +36,5 @@ static inline void integrity_inode_free(struct inode *inode) { return; } -#endif /* CONFIG_INTEGRITY_H */ +#endif /* CONFIG_INTEGRITY */ #endif /* _LINUX_INTEGRITY_H */ -- cgit v1.2.3 From 4f22decf9b6329acfe59091c5cba6b378b9b31db Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Fri, 22 Mar 2013 18:38:28 +0100 Subject: HID: input: don't register unmapped input devices There is no need to register an input device containing no events. This allows drivers using the quirk MULTI_INPUT to register one input per report effectively used. For backward compatibility, we need to add a quirk to request this behavior. Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 863744c38ddc..fffa06bc4880 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -282,6 +282,7 @@ struct hid_item { #define HID_QUIRK_BADPAD 0x00000020 #define HID_QUIRK_MULTI_INPUT 0x00000040 #define HID_QUIRK_HIDINPUT_FORCE 0x00000080 +#define HID_QUIRK_NO_EMPTY_INPUT 0x00000100 #define HID_QUIRK_SKIP_OUTPUT_REPORTS 0x00010000 #define HID_QUIRK_FULLSPEED_INTERVAL 0x10000000 #define HID_QUIRK_NO_INIT_REPORTS 0x20000000 -- cgit v1.2.3 From 221ad7f2df7c54b3f05471a3599ea7368366aaeb Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 26 Mar 2013 21:24:20 +0000 Subject: regmap: core: Provide regmap_can_raw_write() operation Mainly useful internally but exported since this is a public API that's being checked for. Signed-off-by: Mark Brown --- include/linux/regmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index bf77dfdabef9..02d84e24b7c2 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -389,6 +389,7 @@ int regmap_update_bits_check(struct regmap *map, unsigned int reg, bool *change); int regmap_get_val_bytes(struct regmap *map); int regmap_async_complete(struct regmap *map); +bool regmap_can_raw_write(struct regmap *map); int regcache_sync(struct regmap *map); int regcache_sync_region(struct regmap *map, unsigned int min, -- cgit v1.2.3 From 8761e31c227f9751327196f170eba2b519eab48f Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Tue, 26 Mar 2013 10:30:44 -0700 Subject: mmzone: correct "pags" to "pages" in comment. Signed-off-by: Cody P Schafer Signed-off-by: Jiri Kosina --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ede274957e05..2570216b844a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -450,7 +450,7 @@ struct zone { * * present_pages is physical pages existing within the zone, which * is calculated as: - * present_pages = spanned_pages - absent_pages(pags in holes); + * present_pages = spanned_pages - absent_pages(pages in holes); * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the -- cgit v1.2.3 From e874a6697710f52fa8ab29487a99034d5d96fdcc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Emilio=20L=C3=B3pez?= Date: Mon, 25 Feb 2013 11:44:26 -0300 Subject: clk: arm: sunxi: Add a new clock driver for sunxi SOCs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This commit implements the base CPU clocks for sunxi devices. It has been tested using a slightly modified cpufreq driver from the linux-sunxi 3.0 tree. Additionally, document the new bindings introduced by this patch. Idling: / # cat /sys/kernel/debug/clk/clk_summary clock enable_cnt prepare_cnt rate --------------------------------------------------------------------- osc32k 0 0 32768 osc24M_fixed 0 0 24000000 osc24M 0 0 24000000 apb1_mux 0 0 24000000 apb1 0 0 24000000 pll1 0 0 60000000 cpu 0 0 60000000 axi 0 0 60000000 ahb 0 0 60000000 apb0 0 0 30000000 dummy 0 0 0 After "yes >/dev/null &": / # cat /sys/kernel/debug/clk/clk_summary clock enable_cnt prepare_cnt rate --------------------------------------------------------------------- osc32k 0 0 32768 osc24M_fixed 0 0 24000000 osc24M 0 0 24000000 apb1_mux 0 0 24000000 apb1 0 0 24000000 pll1 0 0 1008000000 cpu 0 0 1008000000 axi 0 0 336000000 ahb 0 0 168000000 apb0 0 0 84000000 dummy 0 0 0 Signed-off-by: Emilio López Acked-by: Maxime Ripard Signed-off-by: Mike Turquette --- include/linux/clk/sunxi.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 include/linux/clk/sunxi.h (limited to 'include/linux') diff --git a/include/linux/clk/sunxi.h b/include/linux/clk/sunxi.h new file mode 100644 index 000000000000..e074fdd5a236 --- /dev/null +++ b/include/linux/clk/sunxi.h @@ -0,0 +1,22 @@ +/* + * Copyright 2012 Maxime Ripard + * + * Maxime Ripard + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_CLK_SUNXI_H_ +#define __LINUX_CLK_SUNXI_H_ + +void __init sunxi_init_clocks(void); + +#endif -- cgit v1.2.3 From 2db76d7c3c6db93058f983c8240f7c7c25e87ee6 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Tue, 26 Mar 2013 15:14:18 +0200 Subject: lib/scatterlist: sg_page_iter: support sg lists w/o backing pages The i915 driver uses sg lists for memory without backing 'struct page' pages, similarly to other IO memory regions, setting only the DMA address for these. It does this, so that it can program the HW MMU tables in a uniform way both for sg lists with and without backing pages. Without a valid page pointer we can't call nth_page to get the current page in __sg_page_iter_next, so add a helper that relevant users can call separately. Also add a helper to get the DMA address of the current page (idea from Daniel). Convert all places in i915, to use the new API. Signed-off-by: Imre Deak Reviewed-by: Damien Lespiau Signed-off-by: Daniel Vetter --- include/linux/scatterlist.h | 28 +++++++++++++++++++++++----- 1 file changed, 23 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 2d8bdaef9611..e96b9546c4c6 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -235,13 +235,13 @@ size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents, * sg page iterator * * Iterates over sg entries page-by-page. On each successful iteration, - * @piter->page points to the current page, @piter->sg to the sg holding this - * page and @piter->sg_pgoffset to the page's page offset within the sg. The - * iteration will stop either when a maximum number of sg entries was reached - * or a terminating sg (sg_last(sg) == true) was reached. + * you can call sg_page_iter_page(@piter) and sg_page_iter_dma_address(@piter) + * to get the current page and its dma address. @piter->sg will point to the + * sg holding this page and @piter->sg_pgoffset to the page's page offset + * within the sg. The iteration will stop either when a maximum number of sg + * entries was reached or a terminating sg (sg_last(sg) == true) was reached. */ struct sg_page_iter { - struct page *page; /* current page */ struct scatterlist *sg; /* sg holding the page */ unsigned int sg_pgoffset; /* page offset within the sg */ @@ -255,6 +255,24 @@ bool __sg_page_iter_next(struct sg_page_iter *piter); void __sg_page_iter_start(struct sg_page_iter *piter, struct scatterlist *sglist, unsigned int nents, unsigned long pgoffset); +/** + * sg_page_iter_page - get the current page held by the page iterator + * @piter: page iterator holding the page + */ +static inline struct page *sg_page_iter_page(struct sg_page_iter *piter) +{ + return nth_page(sg_page(piter->sg), piter->sg_pgoffset); +} + +/** + * sg_page_iter_dma_address - get the dma address of the current page held by + * the page iterator. + * @piter: page iterator holding the page + */ +static inline dma_addr_t sg_page_iter_dma_address(struct sg_page_iter *piter) +{ + return sg_dma_address(piter->sg) + (piter->sg_pgoffset << PAGE_SHIFT); +} /** * for_each_sg_page - iterate over the pages of the given sg list -- cgit v1.2.3 From 5203cd28db6dc05c3618a602cf4cf81203d00257 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 26 Mar 2013 23:11:21 +0000 Subject: net: core: introduce skb_probe_transport_header() Sometimes, we need probe and set the transport header for packets (e.g from untrusted source). This patch introduces a new helper skb_probe_transport_header() which tries to probe and set the l4 header through skb_flow_dissect(), if not just set the transport header to the hint passed by caller. Cc: Eric Dumazet Signed-off-by: Jason Wang Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 497412165b1c..fa88b966cb8e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -32,6 +32,7 @@ #include #include #include +#include /* Don't change this without changing skb_csum_unnecessary! */ #define CHECKSUM_NONE 0 @@ -1559,6 +1560,19 @@ static inline void skb_set_transport_header(struct sk_buff *skb, skb->transport_header += offset; } +static inline void skb_probe_transport_header(struct sk_buff *skb, + const int offset_hint) +{ + struct flow_keys keys; + + if (skb_transport_header_was_set(skb)) + return; + else if (skb_flow_dissect(skb, &keys)) + skb_set_transport_header(skb, keys.thoff); + else + skb_set_transport_header(skb, offset_hint); +} + static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; -- cgit v1.2.3 From d6b688cf2f7ca3e168acc73597f4d7102ae663fa Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Wed, 27 Mar 2013 17:23:10 +0100 Subject: bcma: handle more devices in bcma_pmu_get_alp_clock() Add some more chip IDs to bcma_pmu_get_alp_clock() Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_chipcommon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 8390c474f69a..1db4c6de372e 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -104,6 +104,7 @@ #define BCMA_CC_CHIPST_4706_MIPS_BENDIAN BIT(3) /* 0: little, 1: big endian */ #define BCMA_CC_CHIPST_4706_PCIE1_DISABLE BIT(5) /* PCIE1 enable strap pin */ #define BCMA_CC_CHIPST_5357_NAND_BOOT BIT(4) /* NAND boot, valid for CC rev 38 and/or BCM5357 */ +#define BCMA_CC_CHIPST_4360_XTAL_40MZ 0x00000001 #define BCMA_CC_JCMD 0x0030 /* Rev >= 10 only */ #define BCMA_CC_JCMD_START 0x80000000 #define BCMA_CC_JCMD_BUSY 0x80000000 -- cgit v1.2.3 From 6951618b4b0bb022429ab17d49f2fa3650f21cb4 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Wed, 27 Mar 2013 17:23:11 +0100 Subject: bcma: export bcma_chipco_get_alp_clock() This function will be used by brcmsmac. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_chipcommon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 1db4c6de372e..453fcc914683 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -608,6 +608,8 @@ void bcma_chipco_bcm4331_ext_pa_lines_ctl(struct bcma_drv_cc *cc, bool enable); extern u32 bcma_chipco_watchdog_timer_set(struct bcma_drv_cc *cc, u32 ticks); +extern u32 bcma_chipco_get_alp_clock(struct bcma_drv_cc *cc); + void bcma_chipco_irq_mask(struct bcma_drv_cc *cc, u32 mask, u32 value); u32 bcma_chipco_irq_status(struct bcma_drv_cc *cc, u32 mask); -- cgit v1.2.3 From 43a5911b3dcec81add87d833cd8c7ddaaa205a47 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 21 Mar 2013 15:59:15 +0000 Subject: regulator: ab8500: Clean out SoC registers Clean out initialisation that is handled by SoC. Regulator settings for Vpll (partly), Vsmps1, Vsmps2, Vsmps3 (partly), Vrf1, Varm, Vape, Vbb, Vmod are cleaned out. They should not be touched by the kernel. We also update many of the initialisation values to be more in-line with the current development efforts of ST-Ericsson internal engineers. Signed-off-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 3a8e02687f7b..26792ff360be 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -61,7 +61,6 @@ struct ab8500_regulator_reg_init { /* AB8500 registers */ enum ab8500_regulator_reg { - AB8500_REGUREQUESTCTRL1, AB8500_REGUREQUESTCTRL2, AB8500_REGUREQUESTCTRL3, AB8500_REGUREQUESTCTRL4, @@ -78,22 +77,11 @@ enum ab8500_regulator_reg { AB8500_REGUMISC1, AB8500_VAUDIOSUPPLY, AB8500_REGUCTRL1VAMIC, - AB8500_VSMPS1REGU, - AB8500_VSMPS2REGU, - AB8500_VSMPS3REGU, /* NOTE! PRCMU register */ AB8500_VPLLVANAREGU, AB8500_VREFDDR, AB8500_EXTSUPPLYREGU, AB8500_VAUX12REGU, AB8500_VRF1VAUX3REGU, - AB8500_VSMPS1SEL1, - AB8500_VSMPS1SEL2, - AB8500_VSMPS1SEL3, - AB8500_VSMPS2SEL1, - AB8500_VSMPS2SEL2, - AB8500_VSMPS2SEL3, - AB8500_VSMPS3SEL1, /* NOTE! PRCMU register */ - AB8500_VSMPS3SEL2, /* NOTE! PRCMU register */ AB8500_VAUX1SEL, AB8500_VAUX2SEL, AB8500_VRF1VAUX3SEL, -- cgit v1.2.3 From fbbdb8f096e0e5d8244e1ffa46e364146ab9a440 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Wed, 27 Mar 2013 16:46:06 +0000 Subject: net: fix compile error of implicit declaration of skb_probe_transport_header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The commit 40893fd(net: switch to use skb_probe_transport_header()) involes a new error accidently. When NET_SKBUFF_DATA_USES_OFFSE is not enabled, below compile error happens: CC net/packet/af_packet.o net/packet/af_packet.c: In function ‘packet_sendmsg_spkt’: net/packet/af_packet.c:1516:2: error: implicit declaration of function ‘skb_probe_transport_header’ [-Werror=implicit-function-declaration] cc1: some warnings being treated as errors make[2]: *** [net/packet/af_packet.o] Error 1 make[1]: *** [net/packet] Error 2 make: *** [net] Error 2 As it seems skb_probe_transport_header() is not related to NET_SKBUFF_DATA_USES_OFFSE, we should move the definition of skb_probe_transport_header() out of scope of NET_SKBUFF_DATA_USES_OFFSE macro. Cc: Jason Wang Cc: Eric Dumazet Signed-off-by: Ying Xue Acked-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fa88b966cb8e..878e0ee81068 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1560,19 +1560,6 @@ static inline void skb_set_transport_header(struct sk_buff *skb, skb->transport_header += offset; } -static inline void skb_probe_transport_header(struct sk_buff *skb, - const int offset_hint) -{ - struct flow_keys keys; - - if (skb_transport_header_was_set(skb)) - return; - else if (skb_flow_dissect(skb, &keys)) - skb_set_transport_header(skb, keys.thoff); - else - skb_set_transport_header(skb, offset_hint); -} - static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; @@ -1716,6 +1703,19 @@ static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ +static inline void skb_probe_transport_header(struct sk_buff *skb, + const int offset_hint) +{ + struct flow_keys keys; + + if (skb_transport_header_was_set(skb)) + return; + else if (skb_flow_dissect(skb, &keys)) + skb_set_transport_header(skb, keys.thoff); + else + skb_set_transport_header(skb, offset_hint); +} + static inline void skb_mac_header_rebuild(struct sk_buff *skb) { if (skb_mac_header_was_set(skb)) { -- cgit v1.2.3 From f3d4039242af92a9d93dee2fd9ae47066b20ca29 Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Wed, 27 Mar 2013 10:52:28 +0000 Subject: tokenring: delete last holdout of CONFIG_TR Tokenring support was deleted in v3.5. One last holdout of the macro CONFIG_TR escaped that fate. Until now. Signed-off-by: Paul Bolle Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 56e3e0665272..1dbb02c98946 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -144,8 +144,6 @@ static inline bool dev_xmit_complete(int rc) # else # define LL_MAX_HEADER 96 # endif -#elif IS_ENABLED(CONFIG_TR) -# define LL_MAX_HEADER 48 #else # define LL_MAX_HEADER 32 #endif -- cgit v1.2.3 From e5c5d22e8dcf7c2d430336cbf8e180bd38e8daf1 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 28 Mar 2013 13:38:25 +0900 Subject: net: add ETH_P_802_3_MIN Add a new constant ETH_P_802_3_MIN, the minimum ethernet type for an 802.3 frame. Frames with a lower value in the ethernet type field are Ethernet II. Also update all the users of this value that David Miller and I could find to use the new constant. Also correct a bug in util.c. The comparison with ETH_P_802_3_MIN should be >= not >. As suggested by Jesse Gross. Compile tested only. Cc: David Miller Cc: Jesse Gross Cc: Karsten Keil Cc: John W. Linville Cc: Johannes Berg Cc: Bart De Schuymer Cc: Stephen Hemminger Cc: Patrick McHardy Cc: Marcel Holtmann Cc: Gustavo Padovan Cc: Johan Hedberg Cc: linux-bluetooth@vger.kernel.org Cc: netfilter-devel@vger.kernel.org Cc: bridge@lists.linux-foundation.org Cc: linux-wireless@vger.kernel.org Cc: linux1394-devel@lists.sourceforge.net Cc: linux-media@vger.kernel.org Cc: netdev@vger.kernel.org Cc: dev@openvswitch.org Acked-by: Mauro Carvalho Chehab Acked-by: Stefan Richter Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 218a3b686d90..70962f3fdb79 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -339,7 +339,7 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, */ proto = vhdr->h_vlan_encapsulated_proto; - if (ntohs(proto) >= 1536) { + if (ntohs(proto) >= ETH_P_802_3_MIN) { skb->protocol = proto; return; } -- cgit v1.2.3 From 3d5a96582303e28c48699f3faaf920ef7d43e6f2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 19 Mar 2013 15:38:50 +0100 Subject: clocksource: make CLOCKSOURCE_OF_DECLARE type safe This ensures that a function pointer passed into CLOCKSOURCE_OF_DECLARE takes the same arguments that we use for calling that function later. Also fix the extraneous semicolon at end of the CLOCKSOURCE_OF_DECLARE definition. Signed-off-by: Arnd Bergmann Acked-by: Rob Herring --- include/linux/clocksource.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 08ed5e19d8c6..192d6d1771ee 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -332,16 +332,23 @@ extern int clocksource_mmio_init(void __iomem *, const char *, extern int clocksource_i8253_init(void); +struct device_node; +typedef void(*clocksource_of_init_fn)(struct device_node *); #ifdef CONFIG_CLKSRC_OF extern void clocksource_of_init(void); #define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \ static const struct of_device_id __clksrc_of_table_##name \ __used __section(__clksrc_of_table) \ - = { .compatible = compat, .data = fn }; + = { .compatible = compat, \ + .data = (fn == (clocksource_of_init_fn)NULL) ? fn : fn } #else static inline void clocksource_of_init(void) {} -#define CLOCKSOURCE_OF_DECLARE(name, compat, fn) +#define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \ + static const struct of_device_id __clksrc_of_table_##name \ + __attribute__((unused)) \ + = { .compatible = compat, \ + .data = (fn == (clocksource_of_init_fn)NULL) ? fn : fn } #endif #endif /* _LINUX_CLOCKSOURCE_H */ -- cgit v1.2.3 From b949be5857a4033e00fed67b707774f52619ce60 Mon Sep 17 00:00:00 2001 From: George Spelvin Date: Wed, 27 Mar 2013 14:08:33 +0100 Subject: idr: document exit conditions on idr_for_each_entry better And some manual common subexpression elimination which may help the compiler produce smaller code. Signed-off-by: George Spelvin Signed-off-by: Philipp Reisner Signed-off-by: Jens Axboe --- include/linux/idr.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 2640c7e99e51..6ece0583362a 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -122,11 +122,13 @@ static inline void *idr_find(struct idr *idr, int id) * @idp: idr handle * @entry: the type * to use as cursor * @id: id entry's key + * + * @entry and @id do not need to be initialized before the loop, and + * after normal terminatinon @entry is left with the value NULL. This + * is convenient for a "not found" value. */ -#define idr_for_each_entry(idp, entry, id) \ - for (id = 0, entry = (typeof(entry))idr_get_next((idp), &(id)); \ - entry != NULL; \ - ++id, entry = (typeof(entry))idr_get_next((idp), &(id))) +#define idr_for_each_entry(idp, entry, id) \ + for (id = 0; ((entry) = idr_get_next(idp, &(id))) != NULL; ++id) /* * Don't use the following functions. These exist only to suppress -- cgit v1.2.3 From 2bd5ed5d6713594eb2b4d234d01217d506279c7d Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Wed, 27 Mar 2013 14:08:40 +0100 Subject: drbd: Fix disconnect to keep the peer disk state if connection breaks during operation The issue was that if the connection broke while we did the gracefull state change to C_DISCONNECTING (C_TEARDOWN), then we returned a success code from the state engine. (SS_CW_NO_NEED) The result of that is that we missed to call the fence-peer script in such a case. Fixed that by introducing a new error code (SS_OUTDATE_WO_CONN). This one should never reach back into user space. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 0c5a18ec322c..316330705fd7 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -319,7 +319,8 @@ enum drbd_state_rv { SS_IN_TRANSIENT_STATE = -18, /* Retry after the next state change */ SS_CONCURRENT_ST_CHG = -19, /* Concurrent cluster side state change! */ SS_O_VOL_PEER_PRI = -20, - SS_AFTER_LAST_ERROR = -21, /* Keep this at bottom */ + SS_OUTDATE_WO_CONN = -21, + SS_AFTER_LAST_ERROR = -22, /* Keep this at bottom */ }; /* from drbd_strings.c */ -- cgit v1.2.3 From 3990e04df085e0561ab34f84731dc5929585c526 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Wed, 27 Mar 2013 14:08:48 +0100 Subject: drbd: use sched_setscheduler() It was unnoticed for some time that assigning to current->policy is no longer sufficient to set a real time priority for a kernel thread. Reported-by: Charlie Suffin Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 316330705fd7..1b4d4ee1168f 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -52,7 +52,7 @@ #endif extern const char *drbd_buildtag(void); -#define REL_VERSION "8.4.2" +#define REL_VERSION "8.4.3" #define API_VERSION 1 #define PRO_VERSION_MIN 86 #define PRO_VERSION_MAX 101 -- cgit v1.2.3 From 84ebc10294a3d7be4c66f51070b7aedbaa24de9b Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 27 Mar 2013 16:14:46 -0400 Subject: USB: remove CONFIG_USB_SUSPEND option This patch (as1675) removes the CONFIG_USB_SUSPEND option, essentially replacing it everywhere with CONFIG_PM_RUNTIME (except for one place in hub.c, where it is replaced with CONFIG_PM because the code needs to be used in both runtime and system PM). The net result is code shrinkage and simplification. There's very little point in keeping CONFIG_USB_SUSPEND because almost everybody enables it. The few that don't will find that the usbcore module has gotten somewhat bigger and they will have to take active measures if they want to prevent hubs from being runtime suspended. Signed-off-by: Alan Stern CC: Peter Chen Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 +- include/linux/usb/hcd.h | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 8d4bc173d66a..a0bee5a28d1a 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -617,7 +617,7 @@ static inline bool usb_acpi_power_manageable(struct usb_device *hdev, int index) #endif /* USB autosuspend and autoresume */ -#ifdef CONFIG_USB_SUSPEND +#ifdef CONFIG_PM_RUNTIME extern void usb_enable_autosuspend(struct usb_device *udev); extern void usb_disable_autosuspend(struct usb_device *udev); diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 59694b5e5e90..f5f5c7dfda90 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -84,7 +84,7 @@ struct usb_hcd { struct timer_list rh_timer; /* drives root-hub polling */ struct urb *status_urb; /* the current status urb */ -#ifdef CONFIG_USB_SUSPEND +#ifdef CONFIG_PM_RUNTIME struct work_struct wakeup_work; /* for remote wakeup */ #endif @@ -593,14 +593,14 @@ extern int hcd_bus_suspend(struct usb_device *rhdev, pm_message_t msg); extern int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg); #endif /* CONFIG_PM */ -#ifdef CONFIG_USB_SUSPEND +#ifdef CONFIG_PM_RUNTIME extern void usb_hcd_resume_root_hub(struct usb_hcd *hcd); #else static inline void usb_hcd_resume_root_hub(struct usb_hcd *hcd) { return; } -#endif /* CONFIG_USB_SUSPEND */ +#endif /* CONFIG_PM_RUNTIME */ /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From 5d0f6131a79adfa1fb51309c5f81a2a4ef879dd4 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Mon, 4 Mar 2013 18:40:58 -0700 Subject: NVMe: Add nvme-scsi.c Translates SCSI commands in SG_IO ioctl to NVMe commands. Uses the scsi-nvme translation spec from nvmexpress.org as reference. Signed-off-by: Vishal Verma Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f1974cab60cf..aa575033dbe7 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -546,6 +546,8 @@ struct nvme_ns { int ns_id; int lba_shift; + u64 mode_select_num_blocks; + u32 mode_select_block_len; }; /* @@ -563,6 +565,39 @@ struct nvme_iod { dma_addr_t first_dma; struct scatterlist sg[0]; }; + +/** + * nvme_free_iod - frees an nvme_iod + * @dev: The device that the I/O was submitted to + * @iod: The memory to free + */ +void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod); + +int nvme_setup_prps(struct nvme_dev *dev, struct nvme_common_command *cmd, + struct nvme_iod *iod, int total_len, gfp_t gfp); +struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write, + unsigned long addr, unsigned length); +void nvme_unmap_user_pages(struct nvme_dev *dev, int write, + struct nvme_iod *iod); +struct nvme_queue *get_nvmeq(struct nvme_dev *dev); +void put_nvmeq(struct nvme_queue *nvmeq); +int nvme_submit_sync_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd, + u32 *result, unsigned timeout); +int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns); +int nvme_submit_admin_cmd(struct nvme_dev *, struct nvme_command *, + u32 *result); +int nvme_identify(struct nvme_dev *, unsigned nsid, unsigned cns, + dma_addr_t dma_addr); +int nvme_get_features(struct nvme_dev *dev, unsigned fid, unsigned nsid, + dma_addr_t dma_addr, u32 *result); +int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11, + dma_addr_t dma_addr, u32 *result); + +struct sg_io_hdr; + +int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr); +int nvme_sg_get_version_num(int __user *ip); + #endif #endif /* _LINUX_NVME_H */ -- cgit v1.2.3 From fddddb52a6c4e2438f4514ed979183653ca0732a Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Thu, 21 Mar 2013 17:59:14 +0100 Subject: bus: introduce an Marvell EBU MBus driver The Marvell EBU SoCs have a configurable physical address space layout: the physical ranges of memory used to address PCI(e) interfaces, NOR flashes, SRAM and various other types of memory are configurable by software, through a mechanism of so-called 'address decoding windows'. This new driver mvebu-mbus consolidates the existing code to address the configuration of these memory ranges, which is spread into mach-mvebu, mach-orion5x, mach-mv78xx0, mach-dove and mach-kirkwood. Following patches convert each Marvell EBU SoC family to use this driver, therefore removing the old code that was configuring the address decoding windows. It is worth mentioning that the MVEBU_MBUS Kconfig option is intentionally added as a blind option. The new driver implements and exports the mv_mbus_dram_info() function, which is used by various Marvell drivers throughout the tree to get access to window configuration parameters that they require. This function is also implemented in arch/arm/plat-orion/addr-map.c, which ultimately gets removed at the end of this patch series. So, in order to preserve bisectability, we want to ensure that *either* this new driver, *or* the legacy code in plat-orion/addr-map.c gets compiled in. By making MVEBU_MBUS a blind option, we are sure that only a platform that does 'select MVEBU_MBUS' will get this new driver compiled in. Therefore, throughout the next patches that convert the Marvell sub-architectures one after the other to this new driver, we add the 'select MVEBU_MBUS' and also ensure to remove plat-orion/addr-map.c from the build for this specific sub-architecture. This ensures that bisectability is preserved. Ealier versions of this driver had a DT binding, but since those were not yet agreed upon, they were removed. The driver still uses of_device_id to find the SoC specific details according to the string passed to mvebu_mbus_init(). The plan is to re-introduce a proper DT binding as a followup set of patches. Signed-off-by: Thomas Petazzoni Acked-by: Arnd Bergmann Signed-off-by: Jason Cooper --- include/linux/mbus.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mbus.h b/include/linux/mbus.h index efa1a6d7aca8..462eb9791012 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -32,6 +32,17 @@ struct mbus_dram_target_info } cs[4]; }; +/* Flags for PCI/PCIe address decoding regions */ +#define MVEBU_MBUS_PCI_IO 0x1 +#define MVEBU_MBUS_PCI_MEM 0x2 +#define MVEBU_MBUS_PCI_WA 0x3 + +/* + * Magic value that explicits that we don't need a remapping-capable + * address decoding window. + */ +#define MVEBU_MBUS_NO_REMAP (0xffffffff) + /* * The Marvell mbus is to be found only on SOCs from the Orion family * at the moment. Provide a dummy stub for other architectures. @@ -44,4 +55,15 @@ static inline const struct mbus_dram_target_info *mv_mbus_dram_info(void) return NULL; } #endif -#endif + +int mvebu_mbus_add_window_remap_flags(const char *devname, phys_addr_t base, + size_t size, phys_addr_t remap, + unsigned int flags); +int mvebu_mbus_add_window(const char *devname, phys_addr_t base, + size_t size); +int mvebu_mbus_del_window(phys_addr_t base, size_t size); +int mvebu_mbus_init(const char *soc, phys_addr_t mbus_phys_base, + size_t mbus_size, phys_addr_t sdram_phys_base, + size_t sdram_size); + +#endif /* __LINUX_MBUS_H */ -- cgit v1.2.3 From e5354107e14755991da82e0d2a4791db92908d9d Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Wed, 27 Mar 2013 17:29:53 +0200 Subject: mei: bus: Initial MEI Client bus type implementation mei client bus will present some of the mei clients as devices for other standard subsystems Implement the probe, remove, match, device addtion routines, along with the sysfs and uevent ones. mei_cl_device_id is also added to mod_devicetable.h A mei-cleint-bus.txt document describing the rationale and the API usage is also added while ABI/testing/sysfs-bus-mei describeis the modalias ABI. Signed-off-by: Samuel Ortiz Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- include/linux/mei_cl_bus.h | 20 ++++++++++++++++++++ include/linux/mod_devicetable.h | 9 +++++++++ 2 files changed, 29 insertions(+) create mode 100644 include/linux/mei_cl_bus.h (limited to 'include/linux') diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h new file mode 100644 index 000000000000..4e7351de7eca --- /dev/null +++ b/include/linux/mei_cl_bus.h @@ -0,0 +1,20 @@ +#ifndef _LINUX_MEI_CL_BUS_H +#define _LINUX_MEI_CL_BUS_H + +#include +#include + +struct mei_cl_device; + +struct mei_cl_driver { + struct device_driver driver; + const char *name; + + const struct mei_cl_device_id *id_table; + + int (*probe)(struct mei_cl_device *dev, + const struct mei_cl_device_id *id); + int (*remove)(struct mei_cl_device *dev); +}; + +#endif /* _LINUX_MEI_CL_BUS_H */ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 779cf7c4a3d1..b508016fb76d 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -9,6 +9,7 @@ #ifdef __KERNEL__ #include +#include typedef unsigned long kernel_ulong_t; #endif @@ -568,4 +569,12 @@ struct ipack_device_id { __u32 device; /* Device ID or IPACK_ANY_ID */ }; +#define MEI_CL_MODULE_PREFIX "mei:" +#define MEI_CL_NAME_SIZE 32 + +struct mei_cl_device_id { + char name[MEI_CL_NAME_SIZE]; + kernel_ulong_t driver_info; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ -- cgit v1.2.3 From 333e4ee0781bd0b5938da263c4bb7ab66a0d1b57 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Wed, 27 Mar 2013 17:29:54 +0200 Subject: mei: bus: Implement driver registration Signed-off-by: Samuel Ortiz Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- include/linux/mei_cl_bus.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index 4e7351de7eca..ba2aa3b66f30 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -17,4 +17,11 @@ struct mei_cl_driver { int (*remove)(struct mei_cl_device *dev); }; +int __mei_cl_driver_register(struct mei_cl_driver *driver, + struct module *owner); +#define mei_cl_driver_register(driver) \ + __mei_cl_driver_register(driver, THIS_MODULE) + +void mei_cl_driver_unregister(struct mei_cl_driver *driver); + #endif /* _LINUX_MEI_CL_BUS_H */ -- cgit v1.2.3 From 3e8332952dedd2c17bb497e3909e3b6fbac10ce7 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Wed, 27 Mar 2013 17:29:55 +0200 Subject: mei: bus: Initial implementation for I/O routines Signed-off-by: Samuel Ortiz Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- include/linux/mei_cl_bus.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index ba2aa3b66f30..d9958c3960a2 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -24,4 +24,15 @@ int __mei_cl_driver_register(struct mei_cl_driver *driver, void mei_cl_driver_unregister(struct mei_cl_driver *driver); +int mei_cl_send(struct mei_cl_device *device, u8 *buf, size_t length); +int mei_cl_recv(struct mei_cl_device *device, u8 *buf, size_t length); + +typedef void (*mei_cl_event_cb_t)(struct mei_cl_device *device, + u32 events, void *context); +int mei_cl_register_event_cb(struct mei_cl_device *device, + mei_cl_event_cb_t read_cb, void *context); + +#define MEI_CL_EVENT_RX 0 +#define MEI_CL_EVENT_TX 1 + #endif /* _LINUX_MEI_CL_BUS_H */ -- cgit v1.2.3 From aa6aef216f8aea1a00b56aafc29b8745237a9b62 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Wed, 27 Mar 2013 17:29:59 +0200 Subject: mei: bus: Implement bus driver data setter/getter MEI drivers should be able to carry their private data around. Signed-off-by: Samuel Ortiz Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- include/linux/mei_cl_bus.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index d9958c3960a2..1bece18825ba 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -35,4 +35,7 @@ int mei_cl_register_event_cb(struct mei_cl_device *device, #define MEI_CL_EVENT_RX 0 #define MEI_CL_EVENT_TX 1 +void *mei_cl_get_drvdata(const struct mei_cl_device *device); +void mei_cl_set_drvdata(struct mei_cl_device *device, void *data); + #endif /* _LINUX_MEI_CL_BUS_H */ -- cgit v1.2.3 From 6ae07f27ab202069bd567967a0099070eb7f77d5 Mon Sep 17 00:00:00 2001 From: Fabio Porcedda Date: Tue, 26 Mar 2013 10:35:17 +0100 Subject: driver core: platform_device.h: fix checkpatch errors and warnings Signed-off-by: Fabio Porcedda Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_device.h | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index c082c71f7225..9abf1db6aea6 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -20,12 +20,12 @@ struct mfd_cell; struct platform_device { - const char * name; + const char *name; int id; bool id_auto; struct device dev; u32 num_resources; - struct resource * resource; + struct resource *resource; const struct platform_device_id *id_entry; @@ -47,9 +47,12 @@ extern struct bus_type platform_bus_type; extern struct device platform_bus; extern void arch_setup_pdev_archdata(struct platform_device *); -extern struct resource *platform_get_resource(struct platform_device *, unsigned int, unsigned int); +extern struct resource *platform_get_resource(struct platform_device *, + unsigned int, unsigned int); extern int platform_get_irq(struct platform_device *, unsigned int); -extern struct resource *platform_get_resource_byname(struct platform_device *, unsigned int, const char *); +extern struct resource *platform_get_resource_byname(struct platform_device *, + unsigned int, + const char *); extern int platform_get_irq_byname(struct platform_device *, const char *); extern int platform_add_devices(struct platform_device **, int); @@ -161,7 +164,8 @@ extern struct platform_device *platform_device_alloc(const char *name, int id); extern int platform_device_add_resources(struct platform_device *pdev, const struct resource *res, unsigned int num); -extern int platform_device_add_data(struct platform_device *pdev, const void *data, size_t size); +extern int platform_device_add_data(struct platform_device *pdev, + const void *data, size_t size); extern int platform_device_add(struct platform_device *pdev); extern void platform_device_del(struct platform_device *pdev); extern void platform_device_put(struct platform_device *pdev); @@ -190,7 +194,8 @@ static inline void *platform_get_drvdata(const struct platform_device *pdev) return dev_get_drvdata(&pdev->dev); } -static inline void platform_set_drvdata(struct platform_device *pdev, void *data) +static inline void platform_set_drvdata(struct platform_device *pdev, + void *data) { dev_set_drvdata(&pdev->dev, data); } @@ -222,10 +227,10 @@ static void __exit __platform_driver##_exit(void) \ } \ module_exit(__platform_driver##_exit); -extern struct platform_device *platform_create_bundle(struct platform_driver *driver, - int (*probe)(struct platform_device *), - struct resource *res, unsigned int n_res, - const void *data, size_t size); +extern struct platform_device *platform_create_bundle( + struct platform_driver *driver, int (*probe)(struct platform_device *), + struct resource *res, unsigned int n_res, + const void *data, size_t size); /* early platform driver interface */ struct early_platform_driver { -- cgit v1.2.3 From cb06ff102e2d79a82cf780aa5e6947b2e0529ac0 Mon Sep 17 00:00:00 2001 From: Chanho Min Date: Wed, 27 Mar 2013 18:38:11 +0900 Subject: ARM: PL011: Add support for Rx DMA buffer polling. In DMA support, The received data is not pushed to tty until the DMA buffer is filled. But some megabyte rate chips such as BT expect fast response and data should be pushed immediately. In order to fix this issue, We suggest the use of the timer for polling DMA buffer. In our test, no data loss occurred at high-baudrate as compared with interrupt- driven (We tested with 3Mbps). We changes: - We add timer for polling. If we set poll_timer to 10, every 10ms, timer handler checks the residue in the dma buffer and transfer data to the tty. Also, last_residue is updated for the next polling. - poll_timeout is used to prevent the timer's system cost. If poll_timeout is set to 3000 and no data is received in 3 seconds, we inactivate poll timer and driver falls back to interrupt-driven. When data is received again in FIFO and UART irq is occurred, we switch back to DMA mode and start polling. - We use consistent DMA mappings to avoid from the frequent cache operation of the timer function for default. - pl011_dma_rx_chars is modified. the pending size is recalculated because data can be taken by polling. - the polling time is adjusted if dma rx poll is enabled but no rate is specified. Ideal polling interval to push 1 character at every interval is the reciprocal of 'baud rate / 10 line bits per character / 1000 ms per sec'. But It is very aggressive to system. Experimentally, '10000000 / baud' is suitable to receive dozens of characters. the poll rate can be specified statically by dma_rx_poll_rate of the platform data as well. Changes compared to v1: - Use of consistent DMA mappings. - Added dma_rx_poll_rate in platform data to specify the polling interval. - Added dma_rx_poll_timeout in platform data to specify the polling timeout. Changes compared to v2: - Use of consistent DMA mappings for default. - Added dma_rx_poll_enable in platform data to adjust the polling time according to the baud rate. - remove unnecessary lock from the polling function. Signed-off-by: Chanho Min Signed-off-by: Greg Kroah-Hartman --- include/linux/amba/serial.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h index f612c783170f..62d9303c2837 100644 --- a/include/linux/amba/serial.h +++ b/include/linux/amba/serial.h @@ -203,6 +203,9 @@ struct amba_pl011_data { bool (*dma_filter)(struct dma_chan *chan, void *filter_param); void *dma_rx_param; void *dma_tx_param; + bool dma_rx_poll_enable; + unsigned int dma_rx_poll_rate; + unsigned int dma_rx_poll_timeout; void (*init) (void); void (*exit) (void); }; -- cgit v1.2.3 From d1a820011b2fbc11d5af80d1a961fe66c613fa4b Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 28 Mar 2013 16:11:01 +0000 Subject: regulator: ab8500-ext: New driver to control external regulators The ABx500 is capable of controlling three external regulator supplies. Most commonly on and off are supported, but if an external regulator chipset or power supply supports high-power and low-power mode settings, we can control those too. Signed-off-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 26792ff360be..4e92e5b879a5 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -10,6 +10,8 @@ #ifndef __LINUX_MFD_AB8500_REGULATOR_H #define __LINUX_MFD_AB8500_REGULATOR_H +#include + /* AB8500 regulators */ enum ab8500_regulator_id { AB8500_LDO_AUX1, @@ -140,11 +142,37 @@ enum ab9540_regulator_reg { AB9540_NUM_REGULATOR_REGISTERS, }; +/* AB8500 external regulators */ +enum ab8500_ext_regulator_id { + AB8500_EXT_SUPPLY1, + AB8500_EXT_SUPPLY2, + AB8500_EXT_SUPPLY3, + AB8500_NUM_EXT_REGULATORS, +}; + +/* AB8500 regulator platform data */ struct ab8500_regulator_platform_data { int num_reg_init; struct ab8500_regulator_reg_init *reg_init; int num_regulator; struct regulator_init_data *regulator; + int num_ext_regulator; + struct regulator_init_data *ext_regulator; }; +/* AB8500 external regulator functions (internal) */ +#ifdef CONFIG_REGULATOR_AB8500_EXT +int ab8500_ext_regulator_init(struct platform_device *pdev); +int ab8500_ext_regulator_exit(struct platform_device *pdev); +#else +inline int ab8500_ext_regulator_init(struct platform_device *pdev) +{ + return 0; +} +inline int ab8500_ext_regulator_exit(struct platform_device *pdev) +{ + return 0; +} +#endif + #endif -- cgit v1.2.3 From 18bc2b39307b45527efc6c84836953c7a8f2181e Mon Sep 17 00:00:00 2001 From: Bengt Jonsson Date: Thu, 28 Mar 2013 16:11:06 +0000 Subject: regulator: ab8500-ext: Add HW request support Support for HW request is added in the external regulator driver. A flag in the board configuration can be set to let HW control the regulator when there is no SW request. This means that the regulator will be put in high power mode when there is a SW request and in HW-request mode otherwise. Signed-off-by: Bengt Jonsson Signed-off-by: Lee Jones Reviewed-by: Mattias NILSSON Reviewed-by: Jonas ABERG Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 4e92e5b879a5..cf496e93c0cf 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -143,6 +143,10 @@ enum ab9540_regulator_reg { }; /* AB8500 external regulators */ +struct ab8500_ext_regulator_cfg { + bool hwreq; /* requires hw mode or high power mode */ +}; + enum ab8500_ext_regulator_id { AB8500_EXT_SUPPLY1, AB8500_EXT_SUPPLY2, -- cgit v1.2.3 From 41a06aa738ad889cf96f56024ddf84ecf4a18a6f Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 28 Mar 2013 16:11:08 +0000 Subject: regulator: ab8500: Remove USB regulator The USB regulator is controlled by hardware. The software support was only needed for early hardware (ED) which is no longer supported. Signed-off-by: Bengt Jonsson Signed-off-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index cf496e93c0cf..b86e089195ea 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -19,7 +19,6 @@ enum ab8500_regulator_id { AB8500_LDO_AUX3, AB8500_LDO_INTCORE, AB8500_LDO_TVOUT, - AB8500_LDO_USB, AB8500_LDO_AUDIO, AB8500_LDO_ANAMIC1, AB8500_LDO_ANAMIC2, -- cgit v1.2.3 From da0b0c47dcfd92317e2ece4c3434e1f82b55cf8a Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 28 Mar 2013 16:11:09 +0000 Subject: regulator: ab8500: Init debug from regulator driver The purpose of this patch is to guarantee that ab8500-debug will record the regulator registers before they are modified by the ab8500 regulator driver. Signed-off-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index b86e089195ea..592a3f3994c0 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -178,4 +178,18 @@ inline int ab8500_ext_regulator_exit(struct platform_device *pdev) } #endif +#ifdef CONFIG_REGULATOR_AB8500_DEBUG +int ab8500_regulator_debug_init(struct platform_device *pdev); +int ab8500_regulator_debug_exit(struct platform_device *pdev); +#else +static inline int ab8500_regulator_debug_init(struct platform_device *pdev) +{ + return 0; +} +static inline int ab8500_regulator_debug_exit(struct platform_device *pdev) +{ + return 0; +} +#endif + #endif -- cgit v1.2.3 From a3f109bd793dfe5c611220ca5ab6c72f1aed479e Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Thu, 28 Mar 2013 11:51:31 +0000 Subject: sh_eth: add R-Car support for real Commit d0418bb7123f44b23d69ac349eec7daf9103472f (net: sh_eth: Add eth support for R8A7779 device) was a failed attempt to add support for one of members of the R-Car SoC family. That's for three reasons: it treated R8A7779 the same as SH7724 except including quite dirty hack adding ECMR_ELB bit to the mask in sh_eth_set_rate() while not removing ECMR_RTM bit (despite it's reserved in R-Car Ether), and it didn't add a new register offset array despite the closest SH_ETH_REG_FAST_SH4 mapping differs by 0x200 to the offsets all the R-Car Ether registers have, and also some of the registers in this old mapping don't exist on R-Car Ether (due to this, SH7724's 'sh_eth_my_cpu_data' structure is not adequeate for R-Car too). Fix all these shortcomings, restoring the SH7724 related section to its pristine state... Signed-off-by: Sergei Shtylyov Signed-off-by: David S. Miller --- include/linux/sh_eth.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sh_eth.h b/include/linux/sh_eth.h index b17d765ded84..fc305713fc6d 100644 --- a/include/linux/sh_eth.h +++ b/include/linux/sh_eth.h @@ -6,6 +6,7 @@ enum {EDMAC_LITTLE_ENDIAN, EDMAC_BIG_ENDIAN}; enum { SH_ETH_REG_GIGABIT, + SH_ETH_REG_FAST_RCAR, SH_ETH_REG_FAST_SH4, SH_ETH_REG_FAST_SH3_SH2 }; -- cgit v1.2.3 From 72f4dc117b57e05120aaac6e218b8abc09a5c350 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 16 Mar 2013 15:54:25 -0400 Subject: NFS: Remove unneeded forward declaration I've built with NFSv4 enabled and disabled. This forward declaration does not seem to be required. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 90a4aa190b43..c1ca1f3f4935 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -14,9 +14,6 @@ #define NFS_DEF_FILE_IO_SIZE (4096U) #define NFS_MIN_FILE_IO_SIZE (1024U) -/* Forward declaration for NFS v3 */ -struct nfs4_secinfo_flavors; - struct nfs4_string { unsigned int len; char *data; -- cgit v1.2.3 From fb15b26f8ba3ff629a052faf3f4a4744585ca2dc Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 16 Mar 2013 15:54:34 -0400 Subject: SUNRPC: Define rpcsec_gss_info structure The NFSv4 SECINFO procedure returns a list of security flavors. Any GSS flavor also has a GSS tuple containing an OID, a quality-of- protection value, and a service value, which specifies a particular GSS pseudoflavor. For simplicity and efficiency, I'd like to return each GSS tuple from the NFSv4 SECINFO XDR decoder and pass it straight into the RPC client. Define a data structure that is visible to both the NFS client and the RPC client. Take structure and field names from the relevant standards to avoid confusion. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 21 +++++---------------- include/linux/sunrpc/gss_api.h | 14 ++++++++++++-- 2 files changed, 17 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index c1ca1f3f4935..b759467741eb 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1049,25 +1049,14 @@ struct nfs4_fs_locations_res { struct nfs4_fs_locations *fs_locations; }; -struct nfs4_secinfo_oid { - unsigned int len; - char data[GSS_OID_MAX_LEN]; -}; - -struct nfs4_secinfo_gss { - struct nfs4_secinfo_oid sec_oid4; - unsigned int qop4; - unsigned int service; -}; - -struct nfs4_secinfo_flavor { - unsigned int flavor; - struct nfs4_secinfo_gss gss; +struct nfs4_secinfo4 { + u32 flavor; + struct rpcsec_gss_info flavor_info; }; struct nfs4_secinfo_flavors { - unsigned int num_flavors; - struct nfs4_secinfo_flavor flavors[0]; + unsigned int num_flavors; + struct nfs4_secinfo4 flavors[0]; }; struct nfs4_secinfo_arg { diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index a19e2547ae6a..98950e5a8877 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -25,10 +25,20 @@ struct gss_ctx { #define GSS_C_NO_BUFFER ((struct xdr_netobj) 0) #define GSS_C_NO_CONTEXT ((struct gss_ctx *) 0) -#define GSS_C_NULL_OID ((struct xdr_netobj) 0) /*XXX arbitrary length - is this set somewhere? */ #define GSS_OID_MAX_LEN 32 +struct rpcsec_gss_oid { + unsigned int len; + u8 data[GSS_OID_MAX_LEN]; +}; + +/* From RFC 3530 */ +struct rpcsec_gss_info { + struct rpcsec_gss_oid oid; + u32 qop; + u32 service; +}; /* gss-api prototypes; note that these are somewhat simplified versions of * the prototypes specified in RFC 2744. */ @@ -76,7 +86,7 @@ struct pf_desc { struct gss_api_mech { struct list_head gm_list; struct module *gm_owner; - struct xdr_netobj gm_oid; + struct rpcsec_gss_oid gm_oid; char *gm_name; const struct gss_api_ops *gm_ops; /* pseudoflavors supported by this mechanism: */ -- cgit v1.2.3 From 9568c5e9a61de49f67f524404a27a1014a8d7f1e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 16 Mar 2013 15:54:43 -0400 Subject: SUNRPC: Introduce rpcauth_get_pseudoflavor() A SECINFO reply may contain flavors whose kernel module is not yet loaded by the client's kernel. A new RPC client API, called rpcauth_get_pseudoflavor(), is introduced to do proper checking for support of a security flavor. When this API is invoked, the RPC client now tries to load the module for each flavor first before performing the "is this supported?" check. This means if a module is available on the client, but has not been loaded yet, it will be loaded and registered automatically when the SECINFO reply is processed. The new API can take a full GSS tuple (OID, QoP, and service). Previously only the OID and service were considered. nfs_find_best_sec() is updated to verify all flavors requested in a SECINFO reply, including AUTH_NULL and AUTH_UNIX. Previously these two flavors were simply assumed to be supported without consulting the RPC client. Note that the replaced version of nfs_find_best_sec() can return RPC_AUTH_MAXFLAVOR if the server returns a recognized OID but an unsupported "service" value. nfs_find_best_sec() now returns RPC_AUTH_UNIX in this case. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 5 +++++ include/linux/sunrpc/gss_api.h | 5 ++--- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 58fda1c3c783..6851da4cb416 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -22,6 +22,8 @@ /* size of the nodename buffer */ #define UNX_MAXNODENAME 32 +struct rpcsec_gss_info; + /* Work around the lack of a VFS credential */ struct auth_cred { kuid_t uid; @@ -103,6 +105,7 @@ struct rpc_authops { int (*pipes_create)(struct rpc_auth *); void (*pipes_destroy)(struct rpc_auth *); int (*list_pseudoflavors)(rpc_authflavor_t *, int); + rpc_authflavor_t (*info2flavor)(struct rpcsec_gss_info *); }; struct rpc_credops { @@ -137,6 +140,8 @@ int rpcauth_register(const struct rpc_authops *); int rpcauth_unregister(const struct rpc_authops *); struct rpc_auth * rpcauth_create(rpc_authflavor_t, struct rpc_clnt *); void rpcauth_release(struct rpc_auth *); +rpc_authflavor_t rpcauth_get_pseudoflavor(rpc_authflavor_t, + struct rpcsec_gss_info *); int rpcauth_list_flavors(rpc_authflavor_t *, int); struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int); void rpcauth_init_cred(struct rpc_cred *, const struct auth_cred *, struct rpc_auth *, const struct rpc_credops *); diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index 98950e5a8877..aba7687ca884 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -127,9 +127,8 @@ struct gss_api_ops { int gss_mech_register(struct gss_api_mech *); void gss_mech_unregister(struct gss_api_mech *); -/* returns a mechanism descriptor given an OID, and increments the mechanism's - * reference count. */ -struct gss_api_mech * gss_mech_get_by_OID(struct xdr_netobj *); +/* Given a GSS security tuple, look up a pseudoflavor */ +rpc_authflavor_t gss_mech_info2flavor(struct rpcsec_gss_info *); /* Returns a reference to a mechanism, given a name like "krb5" etc. */ struct gss_api_mech *gss_mech_get_by_name(const char *); -- cgit v1.2.3 From 83523d083a045a2069e5f3443d2e4f810a6e6d9a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 16 Mar 2013 15:55:01 -0400 Subject: SUNRPC: Consider qop when looking up pseudoflavors The NFSv4 SECINFO operation returns a list of security flavors that the server supports for a particular share. An NFSv4 client is supposed to pick a pseudoflavor it supports that corresponds to one of the flavors returned by the server. GSS flavors in this list have a GSS tuple that identify a specific GSS pseudoflavor. Currently our client ignores the GSS tuple's "qop" value. A matching pseudoflavor is chosen based only on the OID and service value. So far this omission has not had much effect on Linux. The NFSv4 protocol currently supports only one qop value: GSS_C_QOP_DEFAULT, also known as zero. However, if an NFSv4 server happens to return something other than zero in the qop field, our client won't notice. This could cause the client to behave in incorrect ways that could have security implications. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_api.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index aba7687ca884..96e5a81a54d7 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -25,6 +25,7 @@ struct gss_ctx { #define GSS_C_NO_BUFFER ((struct xdr_netobj) 0) #define GSS_C_NO_CONTEXT ((struct gss_ctx *) 0) +#define GSS_C_QOP_DEFAULT (0) /*XXX arbitrary length - is this set somewhere? */ #define GSS_OID_MAX_LEN 32 @@ -68,12 +69,14 @@ u32 gss_unwrap( u32 gss_delete_sec_context( struct gss_ctx **ctx_id); -u32 gss_svc_to_pseudoflavor(struct gss_api_mech *, u32 service); +rpc_authflavor_t gss_svc_to_pseudoflavor(struct gss_api_mech *, u32 qop, + u32 service); u32 gss_pseudoflavor_to_service(struct gss_api_mech *, u32 pseudoflavor); char *gss_service_to_auth_domain_name(struct gss_api_mech *, u32 service); struct pf_desc { u32 pseudoflavor; + u32 qop; u32 service; char *name; char *auth_domain_name; -- cgit v1.2.3 From a77c806fb9d097bb7733b64207cf52fc2c6438bb Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 16 Mar 2013 15:55:10 -0400 Subject: SUNRPC: Refactor nfsd4_do_encode_secinfo() Clean up. This matches a similar API for the client side, and keeps ULP fingers out the of the GSS mech switch. Signed-off-by: Chuck Lever Acked-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 4 ++++ include/linux/sunrpc/gss_api.h | 3 +++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 6851da4cb416..0dd00f4f6810 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -106,6 +106,8 @@ struct rpc_authops { void (*pipes_destroy)(struct rpc_auth *); int (*list_pseudoflavors)(rpc_authflavor_t *, int); rpc_authflavor_t (*info2flavor)(struct rpcsec_gss_info *); + int (*flavor2info)(rpc_authflavor_t, + struct rpcsec_gss_info *); }; struct rpc_credops { @@ -142,6 +144,8 @@ struct rpc_auth * rpcauth_create(rpc_authflavor_t, struct rpc_clnt *); void rpcauth_release(struct rpc_auth *); rpc_authflavor_t rpcauth_get_pseudoflavor(rpc_authflavor_t, struct rpcsec_gss_info *); +int rpcauth_get_gssinfo(rpc_authflavor_t, + struct rpcsec_gss_info *); int rpcauth_list_flavors(rpc_authflavor_t *, int); struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int); void rpcauth_init_cred(struct rpc_cred *, const struct auth_cred *, struct rpc_auth *, const struct rpc_credops *); diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index 96e5a81a54d7..fca23380e667 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -133,6 +133,9 @@ void gss_mech_unregister(struct gss_api_mech *); /* Given a GSS security tuple, look up a pseudoflavor */ rpc_authflavor_t gss_mech_info2flavor(struct rpcsec_gss_info *); +/* Given a pseudoflavor, look up a GSS security tuple */ +int gss_mech_flavor2info(rpc_authflavor_t, struct rpcsec_gss_info *); + /* Returns a reference to a mechanism, given a name like "krb5" etc. */ struct gss_api_mech *gss_mech_get_by_name(const char *); -- cgit v1.2.3 From 6599c0acae10e929b5315821c1d064cd13fe7648 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 16 Mar 2013 15:55:19 -0400 Subject: SUNRPC: Make gss_mech_get() static gss_mech_get() is no longer used outside of gss_mech_switch.c. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_api.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index fca23380e667..f32b7a47e13f 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -145,9 +145,6 @@ struct gss_api_mech *gss_mech_get_by_pseudoflavor(u32); /* Fill in an array with a list of supported pseudoflavors */ int gss_mech_list_pseudoflavors(rpc_authflavor_t *, int); -/* Just increments the mechanism's reference count and returns its input: */ -struct gss_api_mech * gss_mech_get(struct gss_api_mech *); - /* For every successful gss_mech_get or gss_mech_get_by_* call there must be a * corresponding call to gss_mech_put. */ void gss_mech_put(struct gss_api_mech *); -- cgit v1.2.3 From e4bcda28344cc4762c57ad7333f0472a39e83479 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Fri, 29 Mar 2013 17:38:18 -0600 Subject: ARM: tegra: move to This is required so that code such as Tegra's PCIe and clock drivers can still access this header file once Tegra is converted to multiplatform, and no longer exists. Signed-off-by: Stephen Warren --- include/linux/tegra-powergate.h | 49 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) create mode 100644 include/linux/tegra-powergate.h (limited to 'include/linux') diff --git a/include/linux/tegra-powergate.h b/include/linux/tegra-powergate.h new file mode 100644 index 000000000000..55c29a8d5015 --- /dev/null +++ b/include/linux/tegra-powergate.h @@ -0,0 +1,49 @@ +/* + * Copyright (c) 2010 Google, Inc + * + * Author: + * Colin Cross + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef _MACH_TEGRA_POWERGATE_H_ +#define _MACH_TEGRA_POWERGATE_H_ + +struct clk; + +#define TEGRA_POWERGATE_CPU 0 +#define TEGRA_POWERGATE_3D 1 +#define TEGRA_POWERGATE_VENC 2 +#define TEGRA_POWERGATE_PCIE 3 +#define TEGRA_POWERGATE_VDEC 4 +#define TEGRA_POWERGATE_L2 5 +#define TEGRA_POWERGATE_MPE 6 +#define TEGRA_POWERGATE_HEG 7 +#define TEGRA_POWERGATE_SATA 8 +#define TEGRA_POWERGATE_CPU1 9 +#define TEGRA_POWERGATE_CPU2 10 +#define TEGRA_POWERGATE_CPU3 11 +#define TEGRA_POWERGATE_CELP 12 +#define TEGRA_POWERGATE_3D1 13 + +#define TEGRA_POWERGATE_CPU0 TEGRA_POWERGATE_CPU +#define TEGRA_POWERGATE_3D0 TEGRA_POWERGATE_3D + +int tegra_powergate_is_powered(int id); +int tegra_powergate_power_on(int id); +int tegra_powergate_power_off(int id); +int tegra_powergate_remove_clamping(int id); + +/* Must be called with clk disabled, and returns with clk enabled */ +int tegra_powergate_sequence_power_up(int id, struct clk *clk); + +#endif /* _MACH_TEGRA_POWERGATE_H_ */ -- cgit v1.2.3 From 14b57a10553b5b768f77b247e6dd285c65816064 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 29 Mar 2013 14:46:51 +0100 Subject: openvswitch: Use ETH_ALEN to define ethernet addresses Signed-off-by: Thomas Graf Signed-off-by: Jesse Gross --- include/linux/openvswitch.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/openvswitch.h b/include/linux/openvswitch.h index 67d6c7b03581..8b9d7217eddc 100644 --- a/include/linux/openvswitch.h +++ b/include/linux/openvswitch.h @@ -20,6 +20,7 @@ #define _LINUX_OPENVSWITCH_H 1 #include +#include /** * struct ovs_header - header for OVS Generic Netlink messages. @@ -269,8 +270,8 @@ enum ovs_frag_type { #define OVS_FRAG_TYPE_MAX (__OVS_FRAG_TYPE_MAX - 1) struct ovs_key_ethernet { - __u8 eth_src[6]; - __u8 eth_dst[6]; + __u8 eth_src[ETH_ALEN]; + __u8 eth_dst[ETH_ALEN]; }; struct ovs_key_ipv4 { @@ -316,14 +317,14 @@ struct ovs_key_arp { __be32 arp_sip; __be32 arp_tip; __be16 arp_op; - __u8 arp_sha[6]; - __u8 arp_tha[6]; + __u8 arp_sha[ETH_ALEN]; + __u8 arp_tha[ETH_ALEN]; }; struct ovs_key_nd { __u32 nd_target[4]; - __u8 nd_sll[6]; - __u8 nd_tll[6]; + __u8 nd_sll[ETH_ALEN]; + __u8 nd_tll[ETH_ALEN]; }; /** -- cgit v1.2.3 From 22e3880a76bb9a0c4fa5c8fefdc8697a36a4dae1 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 29 Mar 2013 14:46:52 +0100 Subject: openvswitch: Expose to userspace It contains the public netlink interface bits required by userspace to make use of the interface. Signed-off-by: Thomas Graf Signed-off-by: Jesse Gross --- include/linux/openvswitch.h | 433 +------------------------------------------- 1 file changed, 1 insertion(+), 432 deletions(-) (limited to 'include/linux') diff --git a/include/linux/openvswitch.h b/include/linux/openvswitch.h index 8b9d7217eddc..e6b240b6196c 100644 --- a/include/linux/openvswitch.h +++ b/include/linux/openvswitch.h @@ -19,437 +19,6 @@ #ifndef _LINUX_OPENVSWITCH_H #define _LINUX_OPENVSWITCH_H 1 -#include -#include - -/** - * struct ovs_header - header for OVS Generic Netlink messages. - * @dp_ifindex: ifindex of local port for datapath (0 to make a request not - * specific to a datapath). - * - * Attributes following the header are specific to a particular OVS Generic - * Netlink family, but all of the OVS families use this header. - */ - -struct ovs_header { - int dp_ifindex; -}; - -/* Datapaths. */ - -#define OVS_DATAPATH_FAMILY "ovs_datapath" -#define OVS_DATAPATH_MCGROUP "ovs_datapath" -#define OVS_DATAPATH_VERSION 0x1 - -enum ovs_datapath_cmd { - OVS_DP_CMD_UNSPEC, - OVS_DP_CMD_NEW, - OVS_DP_CMD_DEL, - OVS_DP_CMD_GET, - OVS_DP_CMD_SET -}; - -/** - * enum ovs_datapath_attr - attributes for %OVS_DP_* commands. - * @OVS_DP_ATTR_NAME: Name of the network device that serves as the "local - * port". This is the name of the network device whose dp_ifindex is given in - * the &struct ovs_header. Always present in notifications. Required in - * %OVS_DP_NEW requests. May be used as an alternative to specifying - * dp_ifindex in other requests (with a dp_ifindex of 0). - * @OVS_DP_ATTR_UPCALL_PID: The Netlink socket in userspace that is initially - * set on the datapath port (for OVS_ACTION_ATTR_MISS). Only valid on - * %OVS_DP_CMD_NEW requests. A value of zero indicates that upcalls should - * not be sent. - * @OVS_DP_ATTR_STATS: Statistics about packets that have passed through the - * datapath. Always present in notifications. - * - * These attributes follow the &struct ovs_header within the Generic Netlink - * payload for %OVS_DP_* commands. - */ -enum ovs_datapath_attr { - OVS_DP_ATTR_UNSPEC, - OVS_DP_ATTR_NAME, /* name of dp_ifindex netdev */ - OVS_DP_ATTR_UPCALL_PID, /* Netlink PID to receive upcalls */ - OVS_DP_ATTR_STATS, /* struct ovs_dp_stats */ - __OVS_DP_ATTR_MAX -}; - -#define OVS_DP_ATTR_MAX (__OVS_DP_ATTR_MAX - 1) - -struct ovs_dp_stats { - __u64 n_hit; /* Number of flow table matches. */ - __u64 n_missed; /* Number of flow table misses. */ - __u64 n_lost; /* Number of misses not sent to userspace. */ - __u64 n_flows; /* Number of flows present */ -}; - -struct ovs_vport_stats { - __u64 rx_packets; /* total packets received */ - __u64 tx_packets; /* total packets transmitted */ - __u64 rx_bytes; /* total bytes received */ - __u64 tx_bytes; /* total bytes transmitted */ - __u64 rx_errors; /* bad packets received */ - __u64 tx_errors; /* packet transmit problems */ - __u64 rx_dropped; /* no space in linux buffers */ - __u64 tx_dropped; /* no space available in linux */ -}; - -/* Fixed logical ports. */ -#define OVSP_LOCAL ((__u32)0) - -/* Packet transfer. */ - -#define OVS_PACKET_FAMILY "ovs_packet" -#define OVS_PACKET_VERSION 0x1 - -enum ovs_packet_cmd { - OVS_PACKET_CMD_UNSPEC, - - /* Kernel-to-user notifications. */ - OVS_PACKET_CMD_MISS, /* Flow table miss. */ - OVS_PACKET_CMD_ACTION, /* OVS_ACTION_ATTR_USERSPACE action. */ - - /* Userspace commands. */ - OVS_PACKET_CMD_EXECUTE /* Apply actions to a packet. */ -}; - -/** - * enum ovs_packet_attr - attributes for %OVS_PACKET_* commands. - * @OVS_PACKET_ATTR_PACKET: Present for all notifications. Contains the entire - * packet as received, from the start of the Ethernet header onward. For - * %OVS_PACKET_CMD_ACTION, %OVS_PACKET_ATTR_PACKET reflects changes made by - * actions preceding %OVS_ACTION_ATTR_USERSPACE, but %OVS_PACKET_ATTR_KEY is - * the flow key extracted from the packet as originally received. - * @OVS_PACKET_ATTR_KEY: Present for all notifications. Contains the flow key - * extracted from the packet as nested %OVS_KEY_ATTR_* attributes. This allows - * userspace to adapt its flow setup strategy by comparing its notion of the - * flow key against the kernel's. - * @OVS_PACKET_ATTR_ACTIONS: Contains actions for the packet. Used - * for %OVS_PACKET_CMD_EXECUTE. It has nested %OVS_ACTION_ATTR_* attributes. - * @OVS_PACKET_ATTR_USERDATA: Present for an %OVS_PACKET_CMD_ACTION - * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an - * %OVS_USERSPACE_ATTR_USERDATA attribute, with the same length and content - * specified there. - * - * These attributes follow the &struct ovs_header within the Generic Netlink - * payload for %OVS_PACKET_* commands. - */ -enum ovs_packet_attr { - OVS_PACKET_ATTR_UNSPEC, - OVS_PACKET_ATTR_PACKET, /* Packet data. */ - OVS_PACKET_ATTR_KEY, /* Nested OVS_KEY_ATTR_* attributes. */ - OVS_PACKET_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */ - OVS_PACKET_ATTR_USERDATA, /* OVS_ACTION_ATTR_USERSPACE arg. */ - __OVS_PACKET_ATTR_MAX -}; - -#define OVS_PACKET_ATTR_MAX (__OVS_PACKET_ATTR_MAX - 1) - -/* Virtual ports. */ - -#define OVS_VPORT_FAMILY "ovs_vport" -#define OVS_VPORT_MCGROUP "ovs_vport" -#define OVS_VPORT_VERSION 0x1 - -enum ovs_vport_cmd { - OVS_VPORT_CMD_UNSPEC, - OVS_VPORT_CMD_NEW, - OVS_VPORT_CMD_DEL, - OVS_VPORT_CMD_GET, - OVS_VPORT_CMD_SET -}; - -enum ovs_vport_type { - OVS_VPORT_TYPE_UNSPEC, - OVS_VPORT_TYPE_NETDEV, /* network device */ - OVS_VPORT_TYPE_INTERNAL, /* network device implemented by datapath */ - __OVS_VPORT_TYPE_MAX -}; - -#define OVS_VPORT_TYPE_MAX (__OVS_VPORT_TYPE_MAX - 1) - -/** - * enum ovs_vport_attr - attributes for %OVS_VPORT_* commands. - * @OVS_VPORT_ATTR_PORT_NO: 32-bit port number within datapath. - * @OVS_VPORT_ATTR_TYPE: 32-bit %OVS_VPORT_TYPE_* constant describing the type - * of vport. - * @OVS_VPORT_ATTR_NAME: Name of vport. For a vport based on a network device - * this is the name of the network device. Maximum length %IFNAMSIZ-1 bytes - * plus a null terminator. - * @OVS_VPORT_ATTR_OPTIONS: Vport-specific configuration information. - * @OVS_VPORT_ATTR_UPCALL_PID: The Netlink socket in userspace that - * OVS_PACKET_CMD_MISS upcalls will be directed to for packets received on - * this port. A value of zero indicates that upcalls should not be sent. - * @OVS_VPORT_ATTR_STATS: A &struct ovs_vport_stats giving statistics for - * packets sent or received through the vport. - * - * These attributes follow the &struct ovs_header within the Generic Netlink - * payload for %OVS_VPORT_* commands. - * - * For %OVS_VPORT_CMD_NEW requests, the %OVS_VPORT_ATTR_TYPE and - * %OVS_VPORT_ATTR_NAME attributes are required. %OVS_VPORT_ATTR_PORT_NO is - * optional; if not specified a free port number is automatically selected. - * Whether %OVS_VPORT_ATTR_OPTIONS is required or optional depends on the type - * of vport. - * and other attributes are ignored. - * - * For other requests, if %OVS_VPORT_ATTR_NAME is specified then it is used to - * look up the vport to operate on; otherwise dp_idx from the &struct - * ovs_header plus %OVS_VPORT_ATTR_PORT_NO determine the vport. - */ -enum ovs_vport_attr { - OVS_VPORT_ATTR_UNSPEC, - OVS_VPORT_ATTR_PORT_NO, /* u32 port number within datapath */ - OVS_VPORT_ATTR_TYPE, /* u32 OVS_VPORT_TYPE_* constant. */ - OVS_VPORT_ATTR_NAME, /* string name, up to IFNAMSIZ bytes long */ - OVS_VPORT_ATTR_OPTIONS, /* nested attributes, varies by vport type */ - OVS_VPORT_ATTR_UPCALL_PID, /* u32 Netlink PID to receive upcalls */ - OVS_VPORT_ATTR_STATS, /* struct ovs_vport_stats */ - __OVS_VPORT_ATTR_MAX -}; - -#define OVS_VPORT_ATTR_MAX (__OVS_VPORT_ATTR_MAX - 1) - -/* Flows. */ - -#define OVS_FLOW_FAMILY "ovs_flow" -#define OVS_FLOW_MCGROUP "ovs_flow" -#define OVS_FLOW_VERSION 0x1 - -enum ovs_flow_cmd { - OVS_FLOW_CMD_UNSPEC, - OVS_FLOW_CMD_NEW, - OVS_FLOW_CMD_DEL, - OVS_FLOW_CMD_GET, - OVS_FLOW_CMD_SET -}; - -struct ovs_flow_stats { - __u64 n_packets; /* Number of matched packets. */ - __u64 n_bytes; /* Number of matched bytes. */ -}; - -enum ovs_key_attr { - OVS_KEY_ATTR_UNSPEC, - OVS_KEY_ATTR_ENCAP, /* Nested set of encapsulated attributes. */ - OVS_KEY_ATTR_PRIORITY, /* u32 skb->priority */ - OVS_KEY_ATTR_IN_PORT, /* u32 OVS dp port number */ - OVS_KEY_ATTR_ETHERNET, /* struct ovs_key_ethernet */ - OVS_KEY_ATTR_VLAN, /* be16 VLAN TCI */ - OVS_KEY_ATTR_ETHERTYPE, /* be16 Ethernet type */ - OVS_KEY_ATTR_IPV4, /* struct ovs_key_ipv4 */ - OVS_KEY_ATTR_IPV6, /* struct ovs_key_ipv6 */ - OVS_KEY_ATTR_TCP, /* struct ovs_key_tcp */ - OVS_KEY_ATTR_UDP, /* struct ovs_key_udp */ - OVS_KEY_ATTR_ICMP, /* struct ovs_key_icmp */ - OVS_KEY_ATTR_ICMPV6, /* struct ovs_key_icmpv6 */ - OVS_KEY_ATTR_ARP, /* struct ovs_key_arp */ - OVS_KEY_ATTR_ND, /* struct ovs_key_nd */ - OVS_KEY_ATTR_SKB_MARK, /* u32 skb mark */ - __OVS_KEY_ATTR_MAX -}; - -#define OVS_KEY_ATTR_MAX (__OVS_KEY_ATTR_MAX - 1) - -/** - * enum ovs_frag_type - IPv4 and IPv6 fragment type - * @OVS_FRAG_TYPE_NONE: Packet is not a fragment. - * @OVS_FRAG_TYPE_FIRST: Packet is a fragment with offset 0. - * @OVS_FRAG_TYPE_LATER: Packet is a fragment with nonzero offset. - * - * Used as the @ipv4_frag in &struct ovs_key_ipv4 and as @ipv6_frag &struct - * ovs_key_ipv6. - */ -enum ovs_frag_type { - OVS_FRAG_TYPE_NONE, - OVS_FRAG_TYPE_FIRST, - OVS_FRAG_TYPE_LATER, - __OVS_FRAG_TYPE_MAX -}; - -#define OVS_FRAG_TYPE_MAX (__OVS_FRAG_TYPE_MAX - 1) - -struct ovs_key_ethernet { - __u8 eth_src[ETH_ALEN]; - __u8 eth_dst[ETH_ALEN]; -}; - -struct ovs_key_ipv4 { - __be32 ipv4_src; - __be32 ipv4_dst; - __u8 ipv4_proto; - __u8 ipv4_tos; - __u8 ipv4_ttl; - __u8 ipv4_frag; /* One of OVS_FRAG_TYPE_*. */ -}; - -struct ovs_key_ipv6 { - __be32 ipv6_src[4]; - __be32 ipv6_dst[4]; - __be32 ipv6_label; /* 20-bits in least-significant bits. */ - __u8 ipv6_proto; - __u8 ipv6_tclass; - __u8 ipv6_hlimit; - __u8 ipv6_frag; /* One of OVS_FRAG_TYPE_*. */ -}; - -struct ovs_key_tcp { - __be16 tcp_src; - __be16 tcp_dst; -}; - -struct ovs_key_udp { - __be16 udp_src; - __be16 udp_dst; -}; - -struct ovs_key_icmp { - __u8 icmp_type; - __u8 icmp_code; -}; - -struct ovs_key_icmpv6 { - __u8 icmpv6_type; - __u8 icmpv6_code; -}; - -struct ovs_key_arp { - __be32 arp_sip; - __be32 arp_tip; - __be16 arp_op; - __u8 arp_sha[ETH_ALEN]; - __u8 arp_tha[ETH_ALEN]; -}; - -struct ovs_key_nd { - __u32 nd_target[4]; - __u8 nd_sll[ETH_ALEN]; - __u8 nd_tll[ETH_ALEN]; -}; - -/** - * enum ovs_flow_attr - attributes for %OVS_FLOW_* commands. - * @OVS_FLOW_ATTR_KEY: Nested %OVS_KEY_ATTR_* attributes specifying the flow - * key. Always present in notifications. Required for all requests (except - * dumps). - * @OVS_FLOW_ATTR_ACTIONS: Nested %OVS_ACTION_ATTR_* attributes specifying - * the actions to take for packets that match the key. Always present in - * notifications. Required for %OVS_FLOW_CMD_NEW requests, optional for - * %OVS_FLOW_CMD_SET requests. - * @OVS_FLOW_ATTR_STATS: &struct ovs_flow_stats giving statistics for this - * flow. Present in notifications if the stats would be nonzero. Ignored in - * requests. - * @OVS_FLOW_ATTR_TCP_FLAGS: An 8-bit value giving the OR'd value of all of the - * TCP flags seen on packets in this flow. Only present in notifications for - * TCP flows, and only if it would be nonzero. Ignored in requests. - * @OVS_FLOW_ATTR_USED: A 64-bit integer giving the time, in milliseconds on - * the system monotonic clock, at which a packet was last processed for this - * flow. Only present in notifications if a packet has been processed for this - * flow. Ignored in requests. - * @OVS_FLOW_ATTR_CLEAR: If present in a %OVS_FLOW_CMD_SET request, clears the - * last-used time, accumulated TCP flags, and statistics for this flow. - * Otherwise ignored in requests. Never present in notifications. - * - * These attributes follow the &struct ovs_header within the Generic Netlink - * payload for %OVS_FLOW_* commands. - */ -enum ovs_flow_attr { - OVS_FLOW_ATTR_UNSPEC, - OVS_FLOW_ATTR_KEY, /* Sequence of OVS_KEY_ATTR_* attributes. */ - OVS_FLOW_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */ - OVS_FLOW_ATTR_STATS, /* struct ovs_flow_stats. */ - OVS_FLOW_ATTR_TCP_FLAGS, /* 8-bit OR'd TCP flags. */ - OVS_FLOW_ATTR_USED, /* u64 msecs last used in monotonic time. */ - OVS_FLOW_ATTR_CLEAR, /* Flag to clear stats, tcp_flags, used. */ - __OVS_FLOW_ATTR_MAX -}; - -#define OVS_FLOW_ATTR_MAX (__OVS_FLOW_ATTR_MAX - 1) - -/** - * enum ovs_sample_attr - Attributes for %OVS_ACTION_ATTR_SAMPLE action. - * @OVS_SAMPLE_ATTR_PROBABILITY: 32-bit fraction of packets to sample with - * @OVS_ACTION_ATTR_SAMPLE. A value of 0 samples no packets, a value of - * %UINT32_MAX samples all packets and intermediate values sample intermediate - * fractions of packets. - * @OVS_SAMPLE_ATTR_ACTIONS: Set of actions to execute in sampling event. - * Actions are passed as nested attributes. - * - * Executes the specified actions with the given probability on a per-packet - * basis. - */ -enum ovs_sample_attr { - OVS_SAMPLE_ATTR_UNSPEC, - OVS_SAMPLE_ATTR_PROBABILITY, /* u32 number */ - OVS_SAMPLE_ATTR_ACTIONS, /* Nested OVS_ACTION_ATTR_* attributes. */ - __OVS_SAMPLE_ATTR_MAX, -}; - -#define OVS_SAMPLE_ATTR_MAX (__OVS_SAMPLE_ATTR_MAX - 1) - -/** - * enum ovs_userspace_attr - Attributes for %OVS_ACTION_ATTR_USERSPACE action. - * @OVS_USERSPACE_ATTR_PID: u32 Netlink PID to which the %OVS_PACKET_CMD_ACTION - * message should be sent. Required. - * @OVS_USERSPACE_ATTR_USERDATA: If present, its variable-length argument is - * copied to the %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA. - */ -enum ovs_userspace_attr { - OVS_USERSPACE_ATTR_UNSPEC, - OVS_USERSPACE_ATTR_PID, /* u32 Netlink PID to receive upcalls. */ - OVS_USERSPACE_ATTR_USERDATA, /* Optional user-specified cookie. */ - __OVS_USERSPACE_ATTR_MAX -}; - -#define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1) - -/** - * struct ovs_action_push_vlan - %OVS_ACTION_ATTR_PUSH_VLAN action argument. - * @vlan_tpid: Tag protocol identifier (TPID) to push. - * @vlan_tci: Tag control identifier (TCI) to push. The CFI bit must be set - * (but it will not be set in the 802.1Q header that is pushed). - * - * The @vlan_tpid value is typically %ETH_P_8021Q. The only acceptable TPID - * values are those that the kernel module also parses as 802.1Q headers, to - * prevent %OVS_ACTION_ATTR_PUSH_VLAN followed by %OVS_ACTION_ATTR_POP_VLAN - * from having surprising results. - */ -struct ovs_action_push_vlan { - __be16 vlan_tpid; /* 802.1Q TPID. */ - __be16 vlan_tci; /* 802.1Q TCI (VLAN ID and priority). */ -}; - -/** - * enum ovs_action_attr - Action types. - * - * @OVS_ACTION_ATTR_OUTPUT: Output packet to port. - * @OVS_ACTION_ATTR_USERSPACE: Send packet to userspace according to nested - * %OVS_USERSPACE_ATTR_* attributes. - * @OVS_ACTION_ATTR_SET: Replaces the contents of an existing header. The - * single nested %OVS_KEY_ATTR_* attribute specifies a header to modify and its - * value. - * @OVS_ACTION_ATTR_PUSH_VLAN: Push a new outermost 802.1Q header onto the - * packet. - * @OVS_ACTION_ATTR_POP_VLAN: Pop the outermost 802.1Q header off the packet. - * @OVS_ACTION_ATTR_SAMPLE: Probabilitically executes actions, as specified in - * the nested %OVS_SAMPLE_ATTR_* attributes. - * - * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all - * fields within a header are modifiable, e.g. the IPv4 protocol and fragment - * type may not be changed. - */ - -enum ovs_action_attr { - OVS_ACTION_ATTR_UNSPEC, - OVS_ACTION_ATTR_OUTPUT, /* u32 port number. */ - OVS_ACTION_ATTR_USERSPACE, /* Nested OVS_USERSPACE_ATTR_*. */ - OVS_ACTION_ATTR_SET, /* One nested OVS_KEY_ATTR_*. */ - OVS_ACTION_ATTR_PUSH_VLAN, /* struct ovs_action_push_vlan. */ - OVS_ACTION_ATTR_POP_VLAN, /* No argument. */ - OVS_ACTION_ATTR_SAMPLE, /* Nested OVS_SAMPLE_ATTR_*. */ - __OVS_ACTION_ATTR_MAX -}; - -#define OVS_ACTION_ATTR_MAX (__OVS_ACTION_ATTR_MAX - 1) +#include #endif /* _LINUX_OPENVSWITCH_H */ -- cgit v1.2.3 From a691ce7fe451363d2f1fa48d30c8f4b87c2475d4 Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Thu, 28 Mar 2013 15:24:53 +0000 Subject: include/linux: printk is needed in filter.h when CONFIG_BPF_JIT is defined for make V=1 EXTRA_CFLAGS=-W ARCH=arm allmodconfig printk is need when CONFIG_BPF_JIT is defined or it will report pr_err and print_hex_dump are implicit declaration Signed-off-by: Chen Gang Signed-off-by: David S. Miller --- include/linux/filter.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index d7d25083130b..d1248f401a56 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -48,6 +48,9 @@ extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen); extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len); #ifdef CONFIG_BPF_JIT +#include +#include + extern void bpf_jit_compile(struct sk_filter *fp); extern void bpf_jit_free(struct sk_filter *fp); -- cgit v1.2.3 From 4c3d5e7b41dda1b1372bfc2545ef092a1bc5ad33 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 30 Mar 2013 06:31:03 +0000 Subject: net: reorder some fields of net_device As time passed, some fields were added in net_device, and not at sensible offsets. Lets reorder some fields to reduce number of cache lines in RX path. Fields not used in data path should be moved out of this critical cache line. In particular, move broadcast[] to the end of the rx section, as it is less used, and ethernet uses only the beginning of the 32bytes field. Before patch : offsetof(struct net_device,dev_addr)=0x258 offsetof(struct net_device,rx_handler)=0x2b8 offsetof(struct net_device,ingress_queue)=0x2c8 offsetof(struct net_device,broadcast)=0x278 After : offsetof(struct net_device,dev_addr)=0x280 offsetof(struct net_device,rx_handler)=0x298 offsetof(struct net_device,ingress_queue)=0x2a8 offsetof(struct net_device,broadcast)=0x2b0 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1dbb02c98946..4491414a9218 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1071,6 +1071,8 @@ struct net_device { struct list_head dev_list; struct list_head napi_list; struct list_head unreg_list; + struct list_head upper_dev_list; /* List of upper devices */ + /* currently active device features */ netdev_features_t features; @@ -1143,6 +1145,13 @@ struct net_device { spinlock_t addr_list_lock; struct netdev_hw_addr_list uc; /* Unicast mac addresses */ struct netdev_hw_addr_list mc; /* Multicast mac addresses */ + struct netdev_hw_addr_list dev_addrs; /* list of device + * hw addresses + */ +#ifdef CONFIG_SYSFS + struct kset *queues_kset; +#endif + bool uc_promisc; unsigned int promiscuity; unsigned int allmulti; @@ -1175,21 +1184,11 @@ struct net_device { * avoid dirtying this cache line. */ - struct list_head upper_dev_list; /* List of upper devices */ - /* Interface address info used in eth_type_trans() */ unsigned char *dev_addr; /* hw address, (before bcast because most packets are unicast) */ - struct netdev_hw_addr_list dev_addrs; /* list of device - hw addresses */ - - unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ - -#ifdef CONFIG_SYSFS - struct kset *queues_kset; -#endif #ifdef CONFIG_RPS struct netdev_rx_queue *_rx; @@ -1200,18 +1199,14 @@ struct net_device { /* Number of RX queues currently active in device */ unsigned int real_num_rx_queues; -#ifdef CONFIG_RFS_ACCEL - /* CPU reverse-mapping for RX completion interrupts, indexed - * by RX queue number. Assigned by driver. This must only be - * set if the ndo_rx_flow_steer operation is defined. */ - struct cpu_rmap *rx_cpu_rmap; -#endif #endif rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; struct netdev_queue __rcu *ingress_queue; + unsigned char broadcast[MAX_ADDR_LEN]; /* hw bcast add */ + /* * Cache lines mostly used on transmit path @@ -1233,6 +1228,12 @@ struct net_device { #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_maps; #endif +#ifdef CONFIG_RFS_ACCEL + /* CPU reverse-mapping for RX completion interrupts, indexed + * by RX queue number. Assigned by driver. This must only be + * set if the ndo_rx_flow_steer operation is defined. */ + struct cpu_rmap *rx_cpu_rmap; +#endif /* These may be needed for future network-power-down code. */ -- cgit v1.2.3 From b60e6a0eb0273132cbb60a9806abf5f47a4aee1c Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 21 Mar 2013 12:21:31 +0000 Subject: cpuidle : handle clockevent notify from the cpuidle framework When a cpu enters a deep idle state, the local timers are stopped and the time framework falls back to the timer device used as a broadcast timer. The different cpuidle drivers are calling clockevents_notify ENTER/EXIT when the idle state stops the local timer. Add a new flag CPUIDLE_FLAG_TIMER_STOP which can be set by the cpuidle drivers. If the flag is set, the cpuidle core code takes care of the notification on behalf of the driver to avoid pointless code duplication. Signed-off-by: Daniel Lezcano Reviewed-by: Thomas Gleixner Acked-by: Santosh Shilimkar Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 480c14dc1ddd..a837b332df65 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -57,6 +57,7 @@ struct cpuidle_state { /* Idle State Flags */ #define CPUIDLE_FLAG_TIME_VALID (0x01) /* is residency time measurable? */ #define CPUIDLE_FLAG_COUPLED (0x02) /* state applies to multiple cpus */ +#define CPUIDLE_FLAG_TIMER_STOP (0x04) /* timer is stopped on this state */ #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) -- cgit v1.2.3 From 4dbad816febb6cb7340e36af4f5c0dc86e55a2ca Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 27 Mar 2013 10:22:09 +0000 Subject: timer: move enum definition out of ifdef section The next patch will setup automatically the broadcast timer for the different cpuidle driver when one idle state stops its timer. This will be part of the generic code. But some ARM boards, like s3c64xx, uses cpuidle but without the CONFIG_GENERIC_CLOCKEVENTS_BUILD set. Hence the cpuidle framework will be compiled with the code supposed to be generic, that is with clockevents_notify and the different enum. Also the function clockevents_notify is a noop macro, this is fine except the usual code is: int cpu = smp_processor_id(); clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ON, &cpu); and that raises a warning for the variable cpu which is not used. Move the clock_event_nofitiers enum definition out of the CONFIG_GENERIC_CLOCKEVENTS_BUILD section to prevent a compilation error when these are used in the code. Change the clockevents_notify macro to a static inline noop function to prevent a compilation warning. Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- include/linux/clockchips.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 66346521cb65..f9fd93758333 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -8,6 +8,20 @@ #ifndef _LINUX_CLOCKCHIPS_H #define _LINUX_CLOCKCHIPS_H +/* Clock event notification values */ +enum clock_event_nofitiers { + CLOCK_EVT_NOTIFY_ADD, + CLOCK_EVT_NOTIFY_BROADCAST_ON, + CLOCK_EVT_NOTIFY_BROADCAST_OFF, + CLOCK_EVT_NOTIFY_BROADCAST_FORCE, + CLOCK_EVT_NOTIFY_BROADCAST_ENTER, + CLOCK_EVT_NOTIFY_BROADCAST_EXIT, + CLOCK_EVT_NOTIFY_SUSPEND, + CLOCK_EVT_NOTIFY_RESUME, + CLOCK_EVT_NOTIFY_CPU_DYING, + CLOCK_EVT_NOTIFY_CPU_DEAD, +}; + #ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD #include @@ -26,20 +40,6 @@ enum clock_event_mode { CLOCK_EVT_MODE_RESUME, }; -/* Clock event notification values */ -enum clock_event_nofitiers { - CLOCK_EVT_NOTIFY_ADD, - CLOCK_EVT_NOTIFY_BROADCAST_ON, - CLOCK_EVT_NOTIFY_BROADCAST_OFF, - CLOCK_EVT_NOTIFY_BROADCAST_FORCE, - CLOCK_EVT_NOTIFY_BROADCAST_ENTER, - CLOCK_EVT_NOTIFY_BROADCAST_EXIT, - CLOCK_EVT_NOTIFY_SUSPEND, - CLOCK_EVT_NOTIFY_RESUME, - CLOCK_EVT_NOTIFY_CPU_DYING, - CLOCK_EVT_NOTIFY_CPU_DEAD, -}; - /* * Clock event features */ @@ -173,7 +173,7 @@ extern int tick_receive_broadcast(void); #ifdef CONFIG_GENERIC_CLOCKEVENTS extern void clockevents_notify(unsigned long reason, void *arg); #else -# define clockevents_notify(reason, arg) do { } while (0) +static inline void clockevents_notify(unsigned long reason, void *arg) {} #endif #else /* CONFIG_GENERIC_CLOCKEVENTS_BUILD */ @@ -181,7 +181,7 @@ extern void clockevents_notify(unsigned long reason, void *arg); static inline void clockevents_suspend(void) {} static inline void clockevents_resume(void) {} -#define clockevents_notify(reason, arg) do { } while (0) +static inline void clockevents_notify(unsigned long reason, void *arg) {} #endif -- cgit v1.2.3 From a06df062a189a8d5588babb8bf0bb78672497798 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 27 Mar 2013 10:22:10 +0000 Subject: cpuidle: initialize the broadcast timer framework The commit 89878baa73f0f1c679355006bd8632e5d78f96c2 introduced the CPUIDLE_FLAG_TIMER_STOP flag where we specify a specific idle state stops the local timer. Now use this flag to check at init time if one state will need the broadcast timer and, in this case, setup the broadcast timer framework. That prevents multiple code duplication in the drivers. Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index a837b332df65..fc3e5808b7ff 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -107,6 +107,8 @@ struct cpuidle_driver { /* set to 1 to use the core cpuidle time keeping (for all states). */ unsigned int en_core_tk_irqen:1; + /* used by the cpuidle framework to setup the broadcast timer */ + unsigned int bctimer:1; /* states array must be ordered in decreasing power consumption */ struct cpuidle_state states[CPUIDLE_STATE_MAX]; int state_count; -- cgit v1.2.3 From 7bd353a995d9049262661d85811d6109140582a3 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 27 Mar 2013 15:58:57 +0000 Subject: cpufreq: Add per policy governor-init/exit infrastructure Currently, there can't be multiple instances of single governor_type. If we have a multi-package system, where we have multiple instances of struct policy (per package), we can't have multiple instances of same governor. i.e. We can't have multiple instances of ondemand governor for multiple packages. Governors directory in sysfs is created at /sys/devices/system/cpu/cpufreq/ governor-name/. Which again reflects that there can be only one instance of a governor_type in the system. This is a bottleneck for multicluster system, where we want different packages to use same governor type, but with different tunables. This patch is inclined towards providing this infrastructure. Because we are required to allocate governor's resources dynamically now, we must do it at policy creation and end. And so got CPUFREQ_GOV_POLICY_INIT/EXIT. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index a22944ca0526..b7393b56f552 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -106,6 +106,7 @@ struct cpufreq_policy { * governors are used */ unsigned int policy; /* see above */ struct cpufreq_governor *governor; /* see below */ + void *governor_data; struct work_struct update; /* if update_policy() needs to be * called, but you're in IRQ context */ @@ -178,9 +179,11 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div, u_int mu * CPUFREQ GOVERNORS * *********************************************************************/ -#define CPUFREQ_GOV_START 1 -#define CPUFREQ_GOV_STOP 2 -#define CPUFREQ_GOV_LIMITS 3 +#define CPUFREQ_GOV_START 1 +#define CPUFREQ_GOV_STOP 2 +#define CPUFREQ_GOV_LIMITS 3 +#define CPUFREQ_GOV_POLICY_INIT 4 +#define CPUFREQ_GOV_POLICY_EXIT 5 struct cpufreq_governor { char name[CPUFREQ_NAME_LEN]; -- cgit v1.2.3 From 4d5dcc4211f9def4281eafb54b8ed483862e8135 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 27 Mar 2013 15:58:58 +0000 Subject: cpufreq: governor: Implement per policy instances of governors Currently, there can't be multiple instances of single governor_type. If we have a multi-package system, where we have multiple instances of struct policy (per package), we can't have multiple instances of same governor. i.e. We can't have multiple instances of ondemand governor for multiple packages. Governors directory in sysfs is created at /sys/devices/system/cpu/cpufreq/ governor-name/. Which again reflects that there can be only one instance of a governor_type in the system. This is a bottleneck for multicluster system, where we want different packages to use same governor type, but with different tunables. This patch uses the infrastructure provided by earlier patch and implements init/exit routines for ondemand and conservative governors. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index b7393b56f552..4bbc572dd521 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -232,6 +232,13 @@ struct cpufreq_driver { struct module *owner; char name[CPUFREQ_NAME_LEN]; u8 flags; + /* + * This should be set by platforms having multiple clock-domains, i.e. + * supporting multiple policies. With this sysfs directories of governor + * would be created in cpu/cpu/cpufreq/ directory and so they can + * use the same governor with different tunables for different clusters. + */ + bool have_governor_per_policy; /* needed by all drivers */ int (*init) (struct cpufreq_policy *policy); @@ -332,6 +339,7 @@ const char *cpufreq_get_current_driver(void); *********************************************************************/ int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); int cpufreq_update_policy(unsigned int cpu); +bool have_governor_per_policy(void); #ifdef CONFIG_CPU_FREQ /* query the current CPU frequency (in kHz). If zero, cpufreq couldn't detect it */ -- cgit v1.2.3 From 6a8e95b071ecf7357d294782b6ef4e707ce0fbbd Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Mon, 25 Mar 2013 21:34:51 +0800 Subject: ARM: mxs: move icoll driver into drivers/irqchip Move icoll.c into drivers/irqchip as irq-mxs.c, and along with the renaming, change the driver to use IRQCHIP_DECLARE. Signed-off-by: Shawn Guo --- include/linux/irqchip/mxs.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 include/linux/irqchip/mxs.h (limited to 'include/linux') diff --git a/include/linux/irqchip/mxs.h b/include/linux/irqchip/mxs.h new file mode 100644 index 000000000000..9039a538a919 --- /dev/null +++ b/include/linux/irqchip/mxs.h @@ -0,0 +1,14 @@ +/* + * Copyright (C) 2013 Freescale Semiconductor, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_IRQCHIP_MXS_H +#define __LINUX_IRQCHIP_MXS_H + +extern void icoll_handle_irq(struct pt_regs *); + +#endif -- cgit v1.2.3 From 547f384f33dbd6171607f925ab246e25e315961e Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 28 Mar 2013 16:11:14 +0000 Subject: regulator: ab8500: add support for ab8505 To obtain full AB8505 regulator support, the AB8500 regulator driver first needs to know its register layout and their initialisation values for each. That information is provided via a couple of large data structures which we provide here. Signed-off-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 75 ++++++++++++++++++++++++++++++++++++++-- 1 file changed, 73 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 592a3f3994c0..9a7cf97e5040 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -5,6 +5,7 @@ * * Authors: Sundar Iyer for ST-Ericsson * Bengt Jonsson for ST-Ericsson + * Daniel Willerud for ST-Ericsson */ #ifndef __LINUX_MFD_AB8500_REGULATOR_H @@ -27,7 +28,28 @@ enum ab8500_regulator_id { AB8500_NUM_REGULATORS, }; -/* AB9450 regulators */ +/* AB8505 regulators */ +enum ab8505_regulator_id { + AB8505_LDO_AUX1, + AB8505_LDO_AUX2, + AB8505_LDO_AUX3, + AB8505_LDO_AUX4, + AB8505_LDO_AUX5, + AB8505_LDO_AUX6, + AB8505_LDO_INTCORE, + AB8505_LDO_ADC, + AB8505_LDO_USB, + AB8505_LDO_AUDIO, + AB8505_LDO_ANAMIC1, + AB8505_LDO_ANAMIC2, + AB8505_LDO_AUX8, + AB8505_LDO_ANA, + AB8505_SYSCLKREQ_2, + AB8505_SYSCLKREQ_4, + AB8505_NUM_REGULATORS, +}; + +/* AB9540 regulators */ enum ab9540_regulator_id { AB9540_LDO_AUX1, AB9540_LDO_AUX2, @@ -46,7 +68,7 @@ enum ab9540_regulator_id { AB9540_NUM_REGULATORS, }; -/* AB8500 and AB9540 register initialization */ +/* AB8500, AB8505, and AB9540 register initialization */ struct ab8500_regulator_reg_init { int id; u8 mask; @@ -92,6 +114,55 @@ enum ab8500_regulator_reg { AB8500_NUM_REGULATOR_REGISTERS, }; +/* AB8505 registers */ +enum ab8505_regulator_reg { + AB8505_REGUREQUESTCTRL1, + AB8505_REGUREQUESTCTRL2, + AB8505_REGUREQUESTCTRL3, + AB8505_REGUREQUESTCTRL4, + AB8505_REGUSYSCLKREQ1HPVALID1, + AB8505_REGUSYSCLKREQ1HPVALID2, + AB8505_REGUHWHPREQ1VALID1, + AB8505_REGUHWHPREQ1VALID2, + AB8505_REGUHWHPREQ2VALID1, + AB8505_REGUHWHPREQ2VALID2, + AB8505_REGUSWHPREQVALID1, + AB8505_REGUSWHPREQVALID2, + AB8505_REGUSYSCLKREQVALID1, + AB8505_REGUSYSCLKREQVALID2, + AB8505_REGUVAUX4REQVALID, + AB8505_REGUMISC1, + AB8505_VAUDIOSUPPLY, + AB8505_REGUCTRL1VAMIC, + AB8505_VSMPSAREGU, + AB8505_VSMPSBREGU, + AB8505_VSAFEREGU, /* NOTE! PRCMU register */ + AB8505_VPLLVANAREGU, + AB8505_EXTSUPPLYREGU, + AB8505_VAUX12REGU, + AB8505_VRF1VAUX3REGU, + AB8505_VSMPSASEL1, + AB8505_VSMPSASEL2, + AB8505_VSMPSASEL3, + AB8505_VSMPSBSEL1, + AB8505_VSMPSBSEL2, + AB8505_VSMPSBSEL3, + AB8505_VSAFESEL1, /* NOTE! PRCMU register */ + AB8505_VSAFESEL2, /* NOTE! PRCMU register */ + AB8505_VSAFESEL3, /* NOTE! PRCMU register */ + AB8505_VAUX1SEL, + AB8505_VAUX2SEL, + AB8505_VRF1VAUX3SEL, + AB8505_VAUX4REQCTRL, + AB8505_VAUX4REGU, + AB8505_VAUX4SEL, + AB8505_REGUCTRLDISCH, + AB8505_REGUCTRLDISCH2, + AB8505_REGUCTRLDISCH3, + AB8505_CTRLVAUX5, + AB8505_CTRLVAUX6, + AB8505_NUM_REGULATOR_REGISTERS, +}; /* AB9540 registers */ enum ab9540_regulator_reg { -- cgit v1.2.3 From ae0a9a3efce22e77b5f0f2b266646431f492f7ed Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 28 Mar 2013 16:11:16 +0000 Subject: regulator: ab8500: Add support for the ab8540 To obtain full AB8540 regulator support, the AB8500 regulator driver first needs to know its register layout and their initialisation values for each. That information is provided via a couple of large data structures which we provide here. Signed-off-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 86 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 9a7cf97e5040..bb0140c9d4f4 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -68,6 +68,25 @@ enum ab9540_regulator_id { AB9540_NUM_REGULATORS, }; +/* AB8540 regulators */ +enum ab8540_regulator_id { + AB8540_LDO_AUX1, + AB8540_LDO_AUX2, + AB8540_LDO_AUX3, + AB8540_LDO_AUX4, + AB8540_LDO_INTCORE, + AB8540_LDO_TVOUT, + AB8540_LDO_AUDIO, + AB8540_LDO_ANAMIC1, + AB8540_LDO_ANAMIC2, + AB8540_LDO_DMIC, + AB8540_LDO_ANA, + AB8540_LDO_SDIO, + AB8540_SYSCLKREQ_2, + AB8540_SYSCLKREQ_4, + AB8540_NUM_REGULATORS, +}; + /* AB8500, AB8505, and AB9540 register initialization */ struct ab8500_regulator_reg_init { int id; @@ -212,6 +231,73 @@ enum ab9540_regulator_reg { AB9540_NUM_REGULATOR_REGISTERS, }; +/* AB8540 registers */ +enum ab8540_regulator_reg { + AB8540_REGUREQUESTCTRL1, + AB8540_REGUREQUESTCTRL2, + AB8540_REGUREQUESTCTRL3, + AB8540_REGUREQUESTCTRL4, + AB8540_REGUSYSCLKREQ1HPVALID1, + AB8540_REGUSYSCLKREQ1HPVALID2, + AB8540_REGUHWHPREQ1VALID1, + AB8540_REGUHWHPREQ1VALID2, + AB8540_REGUHWHPREQ2VALID1, + AB8540_REGUHWHPREQ2VALID2, + AB8540_REGUSWHPREQVALID1, + AB8540_REGUSWHPREQVALID2, + AB8540_REGUSYSCLKREQVALID1, + AB8540_REGUSYSCLKREQVALID2, + AB8540_REGUVAUX4REQVALID, + AB8540_REGUVAUX5REQVALID, + AB8540_REGUVAUX6REQVALID, + AB8540_REGUVCLKBREQVALID, + AB8540_REGUVRF1REQVALID, + AB8540_REGUMISC1, + AB8540_VAUDIOSUPPLY, + AB8540_REGUCTRL1VAMIC, + AB8540_VHSIC, + AB8540_VSDIO, + AB8540_VSMPS1REGU, + AB8540_VSMPS2REGU, + AB8540_VSMPS3REGU, + AB8540_VPLLVANAREGU, + AB8540_EXTSUPPLYREGU, + AB8540_VAUX12REGU, + AB8540_VRF1VAUX3REGU, + AB8540_VSMPS1SEL1, + AB8540_VSMPS1SEL2, + AB8540_VSMPS1SEL3, + AB8540_VSMPS2SEL1, + AB8540_VSMPS2SEL2, + AB8540_VSMPS2SEL3, + AB8540_VSMPS3SEL1, + AB8540_VSMPS3SEL2, + AB8540_VAUX1SEL, + AB8540_VAUX2SEL, + AB8540_VRF1VAUX3SEL, + AB8540_REGUCTRL2SPARE, + AB8540_VAUX4REQCTRL, + AB8540_VAUX4REGU, + AB8540_VAUX4SEL, + AB8540_VAUX5REQCTRL, + AB8540_VAUX5REGU, + AB8540_VAUX5SEL, + AB8540_VAUX6REQCTRL, + AB8540_VAUX6REGU, + AB8540_VAUX6SEL, + AB8540_VCLKBREQCTRL, + AB8540_VCLKBREGU, + AB8540_VCLKBSEL, + AB8540_VRF1REQCTRL, + AB8540_REGUCTRLDISCH, + AB8540_REGUCTRLDISCH2, + AB8540_REGUCTRLDISCH3, + AB8540_REGUCTRLDISCH4, + AB8540_VSIMSYSCLKCTRL, + AB8540_VANAVPLLSEL, + AB8540_NUM_REGULATOR_REGISTERS, +}; + /* AB8500 external regulators */ struct ab8500_ext_regulator_cfg { bool hwreq; /* requires hw mode or high power mode */ -- cgit v1.2.3 From 3cb7825bdc84d1d6c81ac9a2be201fe5bea5de05 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Fri, 29 Mar 2013 13:36:05 +0800 Subject: ARM: mxs: remove common.h All three remaining functions declared in common.h are implemented by clock driver. Create header include/linux/clk/mxs.h to contain them and remove common.h. Signed-off-by: Shawn Guo --- include/linux/clk/mxs.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/linux/clk/mxs.h (limited to 'include/linux') diff --git a/include/linux/clk/mxs.h b/include/linux/clk/mxs.h new file mode 100644 index 000000000000..90c30dc3efc7 --- /dev/null +++ b/include/linux/clk/mxs.h @@ -0,0 +1,16 @@ +/* + * Copyright (C) 2013 Freescale Semiconductor, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_CLK_MXS_H +#define __LINUX_CLK_MXS_H + +int mx23_clocks_init(void); +int mx28_clocks_init(void); +int mxs_saif_clkmux_select(unsigned int clkmux); + +#endif -- cgit v1.2.3 From 543bb255a1987836e64f5b7a63664ead8b32b042 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Tue, 26 Mar 2013 20:37:57 -0600 Subject: spi: add ability to validate xfer->bits_per_word in SPI core Allow SPI masters to define the set of bits_per_word values they support. If they do this, then the SPI core will reject transfers that attempt to use an unsupported bits_per_word value. This eliminates the need for each SPI driver to implement this checking in most cases. Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 38c2b925923d..733eb5ee31c5 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -228,6 +228,11 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * every chipselect is connected to a slave. * @dma_alignment: SPI controller constraint on DMA buffers alignment. * @mode_bits: flags understood by this controller driver + * @bits_per_word_mask: A mask indicating which values of bits_per_word are + * supported by the driver. Bit n indicates that a bits_per_word n+1 is + * suported. If set, the SPI core will reject any transfer with an + * unsupported bits_per_word. If not set, this value is simply ignored, + * and it's up to the individual driver to perform any validation. * @flags: other constraints relevant to this driver * @bus_lock_spinlock: spinlock for SPI bus locking * @bus_lock_mutex: mutex for SPI bus locking @@ -301,6 +306,9 @@ struct spi_master { /* spi_device.mode flags understood by this controller driver */ u16 mode_bits; + /* bitmask of supported bits_per_word for transfers */ + u32 bits_per_word_mask; + /* other constraints relevant to this driver */ u16 flags; #define SPI_MASTER_HALF_DUPLEX BIT(0) /* can't do full duplex */ -- cgit v1.2.3 From 9fac2cf316b070ae43d2ae2525e381ff2d1d68aa Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 24 Jan 2013 16:10:27 +0100 Subject: perf/x86: Add flags to event constraints This patch adds a flags field to each event constraint. It can be used to store event specific features which can then later be used by scheduling code or low-level x86 code. The flags are propagated into event->hw.flags during the get_event_constraint() call. They are cleared during the put_event_constraint() call. This mechanism is going to be used by the PEBS-LL patches. It avoids defining yet another table to hold event specific information. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: ak@linux.intel.com Cc: jolsa@redhat.com Cc: namhyung.kim@lge.com Link: http://lkml.kernel.org/r/1359040242-8269-4-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1c592114c437..cd3bb2cd9494 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -127,6 +127,7 @@ struct hw_perf_event { int event_base_rdpmc; int idx; int last_cpu; + int flags; struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; -- cgit v1.2.3 From c3feedf2aaf9ac8bad6f19f5d21e4ee0b4b87e9c Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 24 Jan 2013 16:10:28 +0100 Subject: perf/core: Add weighted samples For some events it's useful to weight sample with a hardware provided number. This expresses how expensive the action the sample represent was. This allows the profiler to scale the samples to be more informative to the programmer. There is already the period which is used similarly, but it means something different, so I chose to not overload it. Instead a new sample type for WEIGHT is added. Can be used for multiple things. Initially it is used for TSX abort costs and profiling by memory latencies (so to make expensive load appear higher up in the histograms). The concept is quite generic and can be extended to many other kinds of events or architectures, as long as the hardware provides suitable auxillary values. In principle it could be also used for software tracepoints. This adds the generic glue. A new optional sample format for a 64-bit weight value. Signed-off-by: Andi Kleen Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: acme@redhat.com Cc: jolsa@redhat.com Cc: namhyung.kim@lge.com Link: http://lkml.kernel.org/r/1359040242-8269-5-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index cd3bb2cd9494..7ce0b37b155b 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -573,6 +573,7 @@ struct perf_sample_data { struct perf_branch_stack *br_stack; struct perf_regs_user regs_user; u64 stack_user_size; + u64 weight; }; static inline void perf_sample_data_init(struct perf_sample_data *data, @@ -586,6 +587,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE; data->regs_user.regs = NULL; data->stack_user_size = 0; + data->weight = 0; } extern void perf_output_sample(struct perf_output_handle *handle, -- cgit v1.2.3 From d6be9ad6c960f43800a6f118932bc8a5a4eadcd1 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 24 Jan 2013 16:10:31 +0100 Subject: perf: Add generic memory sampling interface This patch adds PERF_SAMPLE_DATA_SRC. PERF_SAMPLE_DATA_SRC collects the data source, i.e., where did the data associated with the sampled instruction come from. Information is stored in a perf_mem_data_src structure. It contains opcode, mem level, tlb, snoop, lock information, subject to availability in hardware. Signed-off-by: Stephane Eranian Cc: peterz@infradead.org Cc: ak@linux.intel.com Cc: acme@redhat.com Cc: jolsa@redhat.com Cc: namhyung.kim@lge.com Link: http://lkml.kernel.org/r/1359040242-8269-8-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 7ce0b37b155b..42a6daaf4e0a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -568,6 +568,7 @@ struct perf_sample_data { u32 reserved; } cpu_entry; u64 period; + union perf_mem_data_src data_src; struct perf_callchain_entry *callchain; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; @@ -588,6 +589,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, data->regs_user.regs = NULL; data->stack_user_size = 0; data->weight = 0; + data->data_src.val = 0; } extern void perf_output_sample(struct perf_output_handle *handle, -- cgit v1.2.3 From ff45262a85dbf1bc74463c5dcea1d71a406d4d8e Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Mon, 18 Feb 2013 21:10:14 -0800 Subject: leds: add new LP5562 LED driver LP5562 can drive up to 4 channels, RGB and White. LEDs can be controlled directly via the led class control interface. LP55xx common driver LP5562 is one of LP55xx family device, so LP55xx common code are used. On the other hand, chip specific configuration is defined in the structure 'lp55xx_device_config' LED pattern data LP5562 has also internal program memory which is used for running various LED patterns. LP5562 driver supports the firmware interface and the predefined pattern data as well. LP5562 device attributes: 'led_pattern' and 'engine_mux' A 'led_pattern' is an index code which runs the predefined pattern data. And 'engine_mux' is updated with the firmware interface is activated. Detailed description has been updated in the documentation files, 'leds-lp55xx.txt' and 'leds-lp5562.txt'. Changes on the header file LP5562 configurable definitions are added. Pattern RGB data is fixed as constant value. (No side effect on other devices, LP5521 or LP5523.) (cooloney@gmail.com: remove redundant mutex_unlock(). Reported by Dan Carpenter ) Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Bryan Wu --- include/linux/platform_data/leds-lp55xx.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/leds-lp55xx.h b/include/linux/platform_data/leds-lp55xx.h index 1509570d5a3f..1f1041e8b4fc 100644 --- a/include/linux/platform_data/leds-lp55xx.h +++ b/include/linux/platform_data/leds-lp55xx.h @@ -32,6 +32,13 @@ #define LP5521_CLK_INT 1 /* Internal clock */ #define LP5521_CLK_AUTO 2 /* Automatic clock selection */ +/* Bits in LP5562 CONFIG register */ +#define LP5562_PWM_HF LP5521_PWM_HF +#define LP5562_PWRSAVE_EN LP5521_PWRSAVE_EN +#define LP5562_CLK_SRC_EXT LP5521_CLK_SRC_EXT +#define LP5562_CLK_INT LP5521_CLK_INT +#define LP5562_CLK_AUTO LP5521_CLK_AUTO + struct lp55xx_led_config { const char *name; u8 chan_nr; @@ -40,9 +47,9 @@ struct lp55xx_led_config { }; struct lp55xx_predef_pattern { - u8 *r; - u8 *g; - u8 *b; + const u8 *r; + const u8 *g; + const u8 *b; u8 size_r; u8 size_g; u8 size_b; -- cgit v1.2.3 From 39f7e08af3fd9ca1cb94a8270354afb2ea5cfcd3 Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Thu, 14 Mar 2013 04:29:19 -0700 Subject: leds: trigger: use inline functions instead of macros Macros are used in case that an inline function doesn't work. Otherwise, use an empty inline function. (a) Case of !CONFIG_LEDS_TRIGGERS Following macros are replaced with inline functions. led_trigger_register_simple() led_trigger_unregister_simple() led_trigger_event() To make inline types, the structure, 'led_trigger' should be defined. This structure has no member at all. (b) Case of !CONFIG_LEDS_TRIGGER_IDE_DISK ledtrig_ide_activity() macro is replaced with an inline function as well. (c) DEFINE_LED_TRIGGER() and DEFINE_LED_TRIGGER_GLOBAL() Struct 'led_trigger' is defined both cases, with CONFIG_LEDS_TRIGGERS and without CONFIG_LEDS_TRIGGERS. Those macros are moved out of CONFIG_LED_TRIGGERS because of no-dependency on CONFIG_LEDS_TRIGGERS. (d) Fix build errors in mmc-core driver After replacing macros with inline functions, following build errors occur. (condition: CONFIG_LEDS_TRIGGERS is not set) drivers/mmc/core/core.c: In function 'mmc_request_done': drivers/mmc/core/core.c:164:25: error: 'struct mmc_host' has no member named 'led' drivers/mmc/core/core.c: In function 'mmc_start_request': drivers/mmc/core/core.c:254:24: error: 'struct mmc_host' has no member named 'led' make[3]: *** [drivers/mmc/core/core.o] Error 1 The reason of these errors is non-existent member variable, 'led'. It is only valid when CONFIG_LEDS_TRIGGERS is set. But now, it can be used without this dependency. To fix build errors, member 'led' is always used without its config option in 'include/linux/mmc/host.h'. Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Bryan Wu --- include/linux/leds.h | 25 ++++++++++++++----------- include/linux/mmc/host.h | 2 -- 2 files changed, 14 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 0d9b5eed714e..2d8c0b4f2f76 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -142,6 +142,10 @@ extern void led_set_brightness(struct led_classdev *led_cdev, /* * LED Triggers */ +/* Registration functions for simple triggers */ +#define DEFINE_LED_TRIGGER(x) static struct led_trigger *x; +#define DEFINE_LED_TRIGGER_GLOBAL(x) struct led_trigger *x; + #ifdef CONFIG_LEDS_TRIGGERS #define TRIG_NAME_MAX 50 @@ -164,9 +168,6 @@ struct led_trigger { extern int led_trigger_register(struct led_trigger *trigger); extern void led_trigger_unregister(struct led_trigger *trigger); -/* Registration functions for simple triggers */ -#define DEFINE_LED_TRIGGER(x) static struct led_trigger *x; -#define DEFINE_LED_TRIGGER_GLOBAL(x) struct led_trigger *x; extern void led_trigger_register_simple(const char *name, struct led_trigger **trigger); extern void led_trigger_unregister_simple(struct led_trigger *trigger); @@ -199,20 +200,22 @@ extern void led_trigger_rename_static(const char *name, #else -/* Triggers aren't active - null macros */ -#define DEFINE_LED_TRIGGER(x) -#define DEFINE_LED_TRIGGER_GLOBAL(x) -#define led_trigger_register_simple(x, y) do {} while(0) -#define led_trigger_unregister_simple(x) do {} while(0) -#define led_trigger_event(x, y) do {} while(0) +/* Trigger has no members */ +struct led_trigger {}; -#endif +/* Trigger inline empty functions */ +static inline void led_trigger_register_simple(const char *name, + struct led_trigger **trigger) {} +static inline void led_trigger_unregister_simple(struct led_trigger *trigger) {} +static inline void led_trigger_event(struct led_trigger *trigger, + enum led_brightness event) {} +#endif /* CONFIG_LEDS_TRIGGERS */ /* Trigger specific functions */ #ifdef CONFIG_LEDS_TRIGGER_IDE_DISK extern void ledtrig_ide_activity(void); #else -#define ledtrig_ide_activity() do {} while(0) +static inline void ledtrig_ide_activity(void) {} #endif /* diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index d6f20cc6415e..357e80efcde0 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -341,9 +341,7 @@ struct mmc_host { mmc_pm_flag_t pm_flags; /* requested pm features */ -#ifdef CONFIG_LEDS_TRIGGERS struct led_trigger *led; /* activity led */ -#endif #ifdef CONFIG_REGULATOR bool regulator_enabled; /* regulator state */ -- cgit v1.2.3 From 48a1d032c954b9b06c3adbf35ef4735dd70ab757 Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Thu, 14 Mar 2013 04:29:24 -0700 Subject: leds: add camera LED triggers Some LED devices support flash/torch functionality through the LED subsystem. This patch enables direct LED trigger controls by the driver. Flash on/off and torch on/off can be done simply by other driver space. Two trigger APIs are added, ledtrig_flash_ctrl() and ledtrig_torch_ctrl(). Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Bryan Wu --- include/linux/leds.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 2d8c0b4f2f76..0287ab296689 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -218,6 +218,14 @@ extern void ledtrig_ide_activity(void); static inline void ledtrig_ide_activity(void) {} #endif +#if defined(CONFIG_LEDS_TRIGGER_CAMERA) || defined(CONFIG_LEDS_TRIGGER_CAMERA_MODULE) +extern void ledtrig_flash_ctrl(bool on); +extern void ledtrig_torch_ctrl(bool on); +#else +static inline void ledtrig_flash_ctrl(bool on) {} +static inline void ledtrig_torch_ctrl(bool on) {} +#endif + /* * Generic LED platform data for describing LED names and default triggers. */ -- cgit v1.2.3 From 81f2a5b4a0570a662efd629c176fc1d67e56f7e3 Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Wed, 20 Mar 2013 17:37:04 -0700 Subject: leds: lp55xx: configure the clock detection Now LP55xx provides automatic clock detection API, lp55xx_is_extclk_used(). The clock configuration can be done by the driver itself. (a) Concept The default value is set by each driver with clock selection. The internal clock selection bit is updated in case that the external clock is not detected or clock rate is not 32KHz. (b) Change on LP55xx platform data The clock configuration is done automatically, so no need to define 'update_config' in the platform side. Correlated information are removed in the documentations and header. (c) Definitions moved from header to driver files CONFIG register values are moved each driver, LP5521 and LP5562. Not necessary definitions are removed also. Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Bryan Wu --- include/linux/platform_data/leds-lp55xx.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/leds-lp55xx.h b/include/linux/platform_data/leds-lp55xx.h index 1f1041e8b4fc..202e290faea8 100644 --- a/include/linux/platform_data/leds-lp55xx.h +++ b/include/linux/platform_data/leds-lp55xx.h @@ -20,25 +20,6 @@ #define LP55XX_CLOCK_INT 1 #define LP55XX_CLOCK_EXT 2 -/* Bits in LP5521 CONFIG register. 'update_config' in lp55xx_platform_data */ -#define LP5521_PWM_HF 0x40 /* PWM: 0 = 256Hz, 1 = 558Hz */ -#define LP5521_PWRSAVE_EN 0x20 /* 1 = Power save mode */ -#define LP5521_CP_MODE_OFF 0 /* Charge pump (CP) off */ -#define LP5521_CP_MODE_BYPASS 8 /* CP forced to bypass mode */ -#define LP5521_CP_MODE_1X5 0x10 /* CP forced to 1.5x mode */ -#define LP5521_CP_MODE_AUTO 0x18 /* Automatic mode selection */ -#define LP5521_R_TO_BATT 4 /* R out: 0 = CP, 1 = Vbat */ -#define LP5521_CLK_SRC_EXT 0 /* Ext-clk source (CLK_32K) */ -#define LP5521_CLK_INT 1 /* Internal clock */ -#define LP5521_CLK_AUTO 2 /* Automatic clock selection */ - -/* Bits in LP5562 CONFIG register */ -#define LP5562_PWM_HF LP5521_PWM_HF -#define LP5562_PWRSAVE_EN LP5521_PWRSAVE_EN -#define LP5562_CLK_SRC_EXT LP5521_CLK_SRC_EXT -#define LP5562_CLK_INT LP5521_CLK_INT -#define LP5562_CLK_AUTO LP5521_CLK_AUTO - struct lp55xx_led_config { const char *name; u8 chan_nr; @@ -86,9 +67,6 @@ struct lp55xx_platform_data { /* Predefined pattern data */ struct lp55xx_predef_pattern *patterns; unsigned int num_patterns; - - /* _CONFIG register */ - u8 update_config; }; #endif /* _LEDS_LP55XX_H */ -- cgit v1.2.3 From d55262c4d164759a8debe772da6c9b16059dec47 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 1 Apr 2013 11:23:38 -0700 Subject: workqueue: update sysfs interface to reflect NUMA awareness and a kernel param to disable NUMA affinity Unbound workqueues are now NUMA aware. Let's add some control knobs and update sysfs interface accordingly. * Add kernel param workqueue.numa_disable which disables NUMA affinity globally. * Replace sysfs file "pool_id" with "pool_ids" which contain node:pool_id pairs. This change is userland-visible but "pool_id" hasn't seen a release yet, so this is okay. * Add a new sysf files "numa" which can toggle NUMA affinity on individual workqueues. This is implemented as attrs->no_numa whichn is special in that it isn't part of a pool's attributes. It only affects how apply_workqueue_attrs() picks which pools to use. After "pool_ids" change, first_pwq() doesn't have any user left. Removed. Signed-off-by: Tejun Heo Reviewed-by: Lai Jiangshan --- include/linux/workqueue.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 835d12b76960..717975639378 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -119,10 +119,15 @@ struct delayed_work { /* * A struct for workqueue attributes. This can be used to change * attributes of an unbound workqueue. + * + * Unlike other fields, ->no_numa isn't a property of a worker_pool. It + * only modifies how apply_workqueue_attrs() select pools and thus doesn't + * participate in pool hash calculations or equality comparisons. */ struct workqueue_attrs { int nice; /* nice level */ cpumask_var_t cpumask; /* allowed CPUs */ + bool no_numa; /* disable NUMA affinity */ }; static inline struct delayed_work *to_delayed_work(struct work_struct *work) -- cgit v1.2.3 From 253b5374f08f3908cc380c5665470a5b7609be1c Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 11 Dec 2012 13:14:09 +0900 Subject: mfd: wm5102: Add registers for microphone detection level configuration Signed-off-by: Mark Brown --- include/linux/mfd/arizona/registers.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h index 340355136069..f43aa7c8d040 100644 --- a/include/linux/mfd/arizona/registers.h +++ b/include/linux/mfd/arizona/registers.h @@ -124,6 +124,10 @@ #define ARIZONA_MIC_DETECT_1 0x2A3 #define ARIZONA_MIC_DETECT_2 0x2A4 #define ARIZONA_MIC_DETECT_3 0x2A5 +#define ARIZONA_MIC_DETECT_LEVEL_1 0x2A6 +#define ARIZONA_MIC_DETECT_LEVEL_2 0x2A7 +#define ARIZONA_MIC_DETECT_LEVEL_3 0x2A8 +#define ARIZONA_MIC_DETECT_LEVEL_4 0x2A9 #define ARIZONA_MIC_NOISE_MIX_CONTROL_1 0x2C3 #define ARIZONA_ISOLATION_CONTROL 0x2CB #define ARIZONA_JACK_DETECT_ANALOGUE 0x2D3 -- cgit v1.2.3 From 932bc4d7a53ba418de67fdab533248df5b36c752 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 21 Mar 2013 11:57:58 +0200 Subject: net: add skb_dst_set_noref_force Rename skb_dst_set_noref to __skb_dst_set_noref and add force flag as suggested by David Miller. The new wrapper skb_dst_set_noref_force will force dst entries that are not cached to be attached as skb dst without taking reference as long as provided dst is reclaimed after RCU grace period. Signed-off-by: Julian Anastasov Signed-off by: Hans Schillstrom Acked-by: David S. Miller Signed-off-by: Simon Horman --- include/linux/skbuff.h | 35 ++++++++++++++++++++++++++++++++++- 1 file changed, 34 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 878e0ee81068..364e2440a7ee 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -575,7 +575,40 @@ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) skb->_skb_refdst = (unsigned long)dst; } -extern void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst); +extern void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst, + bool force); + +/** + * skb_dst_set_noref - sets skb dst, hopefully, without taking reference + * @skb: buffer + * @dst: dst entry + * + * Sets skb dst, assuming a reference was not taken on dst. + * If dst entry is cached, we do not take reference and dst_release + * will be avoided by refdst_drop. If dst entry is not cached, we take + * reference, so that last dst_release can destroy the dst immediately. + */ +static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) +{ + __skb_dst_set_noref(skb, dst, false); +} + +/** + * skb_dst_set_noref_force - sets skb dst, without taking reference + * @skb: buffer + * @dst: dst entry + * + * Sets skb dst, assuming a reference was not taken on dst. + * No reference is taken and no dst_release will be called. While for + * cached dsts deferred reclaim is a basic feature, for entries that are + * not cached it is caller's job to guarantee that last dst_release for + * provided dst happens when nobody uses it, eg. after a RCU grace period. + */ +static inline void skb_dst_set_noref_force(struct sk_buff *skb, + struct dst_entry *dst) +{ + __skb_dst_set_noref(skb, dst, true); +} /** * skb_dst_is_noref - Test if skb dst isn't refcounted -- cgit v1.2.3 From 094f7b69ea738d7d619cba449d2af97159949459 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 1 Apr 2013 08:14:24 -0400 Subject: selinux: make security_sb_clone_mnt_opts return an error on context mismatch I had the following problem reported a while back. If you mount the same filesystem twice using NFSv4 with different contexts, then the second context= option is ignored. For instance: # mount server:/export /mnt/test1 # mount server:/export /mnt/test2 -o context=system_u:object_r:tmp_t:s0 # ls -dZ /mnt/test1 drwxrwxrwt. root root system_u:object_r:nfs_t:s0 /mnt/test1 # ls -dZ /mnt/test2 drwxrwxrwt. root root system_u:object_r:nfs_t:s0 /mnt/test2 When we call into SELinux to set the context of a "cloned" superblock, it will currently just bail out when it notices that we're reusing an existing superblock. Since the existing superblock is already set up and presumably in use, we can't go overwriting its context with the one from the "original" sb. Because of this, the second context= option in this case cannot take effect. This patch fixes this by turning security_sb_clone_mnt_opts into an int return operation. When it finds that the "new" superblock that it has been handed is already set up, it checks to see whether the contexts on the old superblock match it. If it does, then it will just return success, otherwise it'll return -EBUSY and emit a printk to tell the admin why the second mount failed. Note that this patch may cause casualties. The NFSv4 code relies on being able to walk down to an export from the pseudoroot. If you mount filesystems that are nested within one another with different contexts, then this patch will make those mounts fail in new and "exciting" ways. For instance, suppose that /export is a separate filesystem on the server: # mount server:/ /mnt/test1 # mount salusa:/export /mnt/test2 -o context=system_u:object_r:tmp_t:s0 mount.nfs: an incorrect mount option was specified ...with the printk in the ring buffer. Because we *might* eventually walk down to /mnt/test1/export, the mount is denied due to this patch. The second mount needs the pseudoroot superblock, but that's already present with the wrong context. OTOH, if we mount these in the reverse order, then both mounts work, because the pseudoroot superblock created when mounting /export is discarded once that mount is done. If we then however try to walk into that directory, the automount fails for the similar reasons: # cd /mnt/test1/scratch/ -bash: cd: /mnt/test1/scratch: Device or resource busy The story I've gotten from the SELinux folks that I've talked to is that this is desirable behavior. In SELinux-land, mounting the same data under different contexts is wrong -- there can be only one. Cc: Steve Dickson Cc: Stephen Smalley Signed-off-by: Jeff Layton Acked-by: Eric Paris Signed-off-by: James Morris --- include/linux/security.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index eee7478cda70..4c7058dc5514 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1436,7 +1436,7 @@ struct security_operations { struct path *new_path); int (*sb_set_mnt_opts) (struct super_block *sb, struct security_mnt_opts *opts); - void (*sb_clone_mnt_opts) (const struct super_block *oldsb, + int (*sb_clone_mnt_opts) (const struct super_block *oldsb, struct super_block *newsb); int (*sb_parse_opts_str) (char *options, struct security_mnt_opts *opts); @@ -1721,7 +1721,7 @@ int security_sb_mount(const char *dev_name, struct path *path, int security_sb_umount(struct vfsmount *mnt, int flags); int security_sb_pivotroot(struct path *old_path, struct path *new_path); int security_sb_set_mnt_opts(struct super_block *sb, struct security_mnt_opts *opts); -void security_sb_clone_mnt_opts(const struct super_block *oldsb, +int security_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb); int security_sb_parse_opts_str(char *options, struct security_mnt_opts *opts); @@ -2011,9 +2011,11 @@ static inline int security_sb_set_mnt_opts(struct super_block *sb, return 0; } -static inline void security_sb_clone_mnt_opts(const struct super_block *oldsb, +static inline int security_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb) -{ } +{ + return 0; +} static inline int security_sb_parse_opts_str(char *options, struct security_mnt_opts *opts) { -- cgit v1.2.3 From 181387da2d64c3129e5b5186c4dd388bc5041d53 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 1 Apr 2013 19:08:06 -0700 Subject: writeback: remove unused bdi_pending_list There's no user left. Remove it. Signed-off-by: Tejun Heo Reviewed-by: Jan Kara Cc: Jens Axboe Cc: Fengguang Wu --- include/linux/backing-dev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 350459910fe1..a5ef27f5411a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -130,7 +130,6 @@ void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2); extern spinlock_t bdi_lock; extern struct list_head bdi_list; -extern struct list_head bdi_pending_list; static inline int wb_has_dirty_io(struct bdi_writeback *wb) { -- cgit v1.2.3 From 839a8e8660b6777e7fe4e80af1a048aebe2b5977 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 1 Apr 2013 19:08:06 -0700 Subject: writeback: replace custom worker pool implementation with unbound workqueue Writeback implements its own worker pool - each bdi can be associated with a worker thread which is created and destroyed dynamically. The worker thread for the default bdi is always present and serves as the "forker" thread which forks off worker threads for other bdis. there's no reason for writeback to implement its own worker pool when using unbound workqueue instead is much simpler and more efficient. This patch replaces custom worker pool implementation in writeback with an unbound workqueue. The conversion isn't too complicated but the followings are worth mentioning. * bdi_writeback->last_active, task and wakeup_timer are removed. delayed_work ->dwork is added instead. Explicit timer handling is no longer necessary. Everything works by either queueing / modding / flushing / canceling the delayed_work item. * bdi_writeback_thread() becomes bdi_writeback_workfn() which runs off bdi_writeback->dwork. On each execution, it processes bdi->work_list and reschedules itself if there are more things to do. The function also handles low-mem condition, which used to be handled by the forker thread. If the function is running off a rescuer thread, it only writes out limited number of pages so that the rescuer can serve other bdis too. This preserves the flusher creation failure behavior of the forker thread. * INIT_LIST_HEAD(&bdi->bdi_list) is used to tell bdi_writeback_workfn() about on-going bdi unregistration so that it always drains work_list even if it's running off the rescuer. Note that the original code was broken in this regard. Under memory pressure, a bdi could finish unregistration with non-empty work_list. * The default bdi is no longer special. It now is treated the same as any other bdi and bdi_cap_flush_forker() is removed. * BDI_pending is no longer used. Removed. * Some tracepoints become non-applicable. The following TPs are removed - writeback_nothread, writeback_wake_thread, writeback_wake_forker_thread, writeback_thread_start, writeback_thread_stop. Everything, including devices coming and going away and rescuer operation under simulated memory pressure, seems to work fine in my test setup. Signed-off-by: Tejun Heo Reviewed-by: Jan Kara Cc: Jens Axboe Cc: Fengguang Wu Cc: Jeff Moyer --- include/linux/backing-dev.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index a5ef27f5411a..c3881553f7d1 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -18,6 +18,7 @@ #include #include #include +#include struct page; struct device; @@ -27,7 +28,6 @@ struct dentry; * Bits in backing_dev_info.state */ enum bdi_state { - BDI_pending, /* On its way to being activated */ BDI_wb_alloc, /* Default embedded wb allocated */ BDI_async_congested, /* The async (write) queue is getting full */ BDI_sync_congested, /* The sync queue is getting full */ @@ -53,10 +53,8 @@ struct bdi_writeback { unsigned int nr; unsigned long last_old_flush; /* last old data flush */ - unsigned long last_active; /* last time bdi thread was active */ - struct task_struct *task; /* writeback thread */ - struct timer_list wakeup_timer; /* used for delayed bdi thread wakeup */ + struct delayed_work dwork; /* work item used for writeback */ struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ @@ -123,7 +121,7 @@ int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, enum wb_reason reason); void bdi_start_background_writeback(struct backing_dev_info *bdi); -int bdi_writeback_thread(void *data); +void bdi_writeback_workfn(struct work_struct *work); int bdi_has_dirty_io(struct backing_dev_info *bdi); void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2); @@ -131,6 +129,8 @@ void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2); extern spinlock_t bdi_lock; extern struct list_head bdi_list; +extern struct workqueue_struct *bdi_wq; + static inline int wb_has_dirty_io(struct bdi_writeback *wb) { return !list_empty(&wb->b_dirty) || @@ -335,11 +335,6 @@ static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi) return bdi->capabilities & BDI_CAP_SWAP_BACKED; } -static inline bool bdi_cap_flush_forker(struct backing_dev_info *bdi) -{ - return bdi == &default_backing_dev_info; -} - static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) { return bdi_cap_writeback_dirty(mapping->backing_dev_info); -- cgit v1.2.3 From 19baba4cb6843bbe3dfde87e1e913f6a9cd27da9 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sat, 9 Mar 2013 08:16:44 +0000 Subject: i2c: Remove detach_adapter The detach_adapter callback has been deprecated for quite some time and has no user left. Keeping it alive blocks other cleanups, so remove it. Signed-off-by: Lars-Peter Clausen Reviewed-by: Jean Delvare Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 2eca3860b77f..f2bcd46ce194 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -125,7 +125,6 @@ extern s32 i2c_smbus_write_i2c_block_data(const struct i2c_client *client, * struct i2c_driver - represent an I2C device driver * @class: What kind of i2c device we instantiate (for detect) * @attach_adapter: Callback for bus addition (deprecated) - * @detach_adapter: Callback for bus removal (deprecated) * @probe: Callback for device binding * @remove: Callback for device unbinding * @shutdown: Callback for device shutdown @@ -162,12 +161,10 @@ extern s32 i2c_smbus_write_i2c_block_data(const struct i2c_client *client, struct i2c_driver { unsigned int class; - /* Notifies the driver that a new bus has appeared or is about to be - * removed. You should avoid using this, it will be removed in a - * near future. + /* Notifies the driver that a new bus has appeared. You should avoid + * using this, it will be removed in a near future. */ int (*attach_adapter)(struct i2c_adapter *) __deprecated; - int (*detach_adapter)(struct i2c_adapter *) __deprecated; /* Standard driver model interfaces */ int (*probe)(struct i2c_client *, const struct i2c_device_id *); -- cgit v1.2.3 From 71546300c8684eb69286604c79624582c16f2f5b Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sat, 9 Mar 2013 08:16:47 +0000 Subject: i2c: Make return type of i2c_del_adapter() void i2c_del_adapter() is usually called from a drivers remove callback. The Linux device driver model does not allow the remove callback to fail and all resources allocated in the probe callback need to be freed, as well as all resources which have been provided to the rest of the kernel(for example a I2C adapter) need to be revoked. So any function revoking such resources isn't allowed to fail either. i2c_del_adapter() adheres to this requirement and will never fail. But i2c_del_adapter()'s return type is int, which may cause driver authors to think that it can fail. This led to code constructs like: ret = i2c_del_adapter(...); BUG_ON(ret); Since i2c_del_adapter() always returns 0 the BUG_ON is never hit and essentially becomes dead code, which means it can be removed. Making the return type of i2c_del_adapter() void makes it explicit that the function will never fail and should prevent constructs like the above from re-appearing in the kernel code. All callers of i2c_del_adapter() have already been updated in a previous patch to ignore the return value, so the conversion of the return type from int to void can be done without causing any build failures. Signed-off-by: Lars-Peter Clausen Reviewed-by: Jean Delvare Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index f2bcd46ce194..e988fa935b3c 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -488,7 +488,7 @@ void i2c_unlock_adapter(struct i2c_adapter *); */ #if defined(CONFIG_I2C) || defined(CONFIG_I2C_MODULE) extern int i2c_add_adapter(struct i2c_adapter *); -extern int i2c_del_adapter(struct i2c_adapter *); +extern void i2c_del_adapter(struct i2c_adapter *); extern int i2c_add_numbered_adapter(struct i2c_adapter *); extern int i2c_register_driver(struct module *, struct i2c_driver *); -- cgit v1.2.3 From 51d95709dddf7fdf6769a547de37a9c98edf8df9 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sat, 9 Mar 2013 08:16:49 +0000 Subject: i2c: Make the return type of i2c_del_mux_adapter() void i2c_del_mux_adapter always returns 0 and none of it current users check its return value anyway. It is also an essential requirement of the Linux device driver model, that functions which may be called from a device's remove callback to free resources provided by the device, are not allowed to fail. This is the case for i2c_del_mux_adapter(), so make its return type void to make the fact that it won't fail explicit. Signed-off-by: Lars-Peter Clausen Reviewed-by: Jean Delvare Signed-off-by: Wolfram Sang --- include/linux/i2c-mux.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c-mux.h b/include/linux/i2c-mux.h index 40cb05a97b46..b5f9a007a3ab 100644 --- a/include/linux/i2c-mux.h +++ b/include/linux/i2c-mux.h @@ -42,7 +42,7 @@ struct i2c_adapter *i2c_add_mux_adapter(struct i2c_adapter *parent, int (*deselect) (struct i2c_adapter *, void *mux_dev, u32 chan_id)); -int i2c_del_mux_adapter(struct i2c_adapter *adap); +void i2c_del_mux_adapter(struct i2c_adapter *adap); #endif /* __KERNEL__ */ -- cgit v1.2.3 From ef096542642874de10909f02686447a96a66ad14 Mon Sep 17 00:00:00 2001 From: Chao Xie Date: Mon, 25 Mar 2013 03:06:57 -0400 Subject: usb: mv_usb: remove clock name from pdata Using pdata to pass clock name is not correct. Directly get clock from usb drivers. Signed-off-by: Chao Xie Signed-off-by: Felipe Balbi --- include/linux/platform_data/mv_usb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mv_usb.h b/include/linux/platform_data/mv_usb.h index 944b01dd103e..98b7925f1a2d 100644 --- a/include/linux/platform_data/mv_usb.h +++ b/include/linux/platform_data/mv_usb.h @@ -34,8 +34,6 @@ struct mv_usb_addon_irq { }; struct mv_usb_platform_data { - unsigned int clknum; - char **clkname; struct mv_usb_addon_irq *id; /* Only valid for OTG. ID pin change*/ struct mv_usb_addon_irq *vbus; /* valid for OTG/UDC. VBUS change*/ -- cgit v1.2.3 From 225da3e3cb1f0db9e4cb7fa2a7dc3a360d1cf788 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Sun, 31 Mar 2013 18:34:43 -0700 Subject: usb: renesas_usbhs: fixup sparse errors for common.c This patch fixup below sparse errors CHECK ${RENESAS_USB}/common.c ${RENESAS_USB}/common.c:313:17: error: incompatible types in conditional expression (different base types) ${RENESAS_USB}/common.c:322:17: error: incompatible types in conditional expression (different base types) ${RENESAS_USB}/common.c:384:17: error: incompatible types in conditional expression (different base types) ${RENESAS_USB}/common.c:524:9: error: incompatible types in conditional expression (different base types) ${RENESAS_USB}/common.c:545:9: error: incompatible types in conditional expression (different base types) ${RENESAS_USB}/common.c:574:9: error: incompatible types in conditional expression (different base types) ${RENESAS_USB}/common.c:606:9: error: incompatible types in conditional expression (different base types) ${RENESAS_USB}/mod_gadget.c:233:28: warning: symbol 'req_clear_feature' was not declared. Should it be static? ${RENESAS_USB}/mod_gadget.c:274:28: warning: symbol 'req_set_feature' was not declared. Should it be static? ${RENESAS_USB}/mod_gadget.c:375:28: warning: symbol 'req_get_status' was not declared. Should it be static? [ balbi@ti.com : added three sparse fixes to mod_gadget.c ] Signed-off-by: Kuninori Morimoto Signed-off-by: Felipe Balbi --- include/linux/usb/renesas_usbhs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/renesas_usbhs.h b/include/linux/usb/renesas_usbhs.h index c5d36c65c33b..e452ba6ec6bd 100644 --- a/include/linux/usb/renesas_usbhs.h +++ b/include/linux/usb/renesas_usbhs.h @@ -62,14 +62,14 @@ struct renesas_usbhs_platform_callback { * Hardware exit function for platform. * it is called when driver was removed */ - void (*hardware_exit)(struct platform_device *pdev); + int (*hardware_exit)(struct platform_device *pdev); /* * option: * * for board specific clock control */ - void (*power_ctrl)(struct platform_device *pdev, + int (*power_ctrl)(struct platform_device *pdev, void __iomem *base, int enable); /* @@ -77,7 +77,7 @@ struct renesas_usbhs_platform_callback { * * Phy reset for platform */ - void (*phy_reset)(struct platform_device *pdev); + int (*phy_reset)(struct platform_device *pdev); /* * get USB ID function -- cgit v1.2.3 From 6fed4d869a11fdbb4c6a5e444dfb2c22f92c3e46 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 1 Apr 2013 22:03:06 +0100 Subject: extcon: arizona: Allow configuration of button detection The Arizona button detection circuit is configurable, allowing the system integrator to program a range of thresholds for the buttons supported on the accessory but currently the driver uses the default button ranges and does not provide any flexibility in how this is exposed to the application layer. Provide platform data allowing the user to control this and to map the buttons to keys in the input subsystem. Signed-off-by: Mark Brown --- include/linux/mfd/arizona/pdata.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 455c51d22d6b..eb11a8ac6db2 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -86,6 +86,11 @@ struct arizona_micd_config { bool gpio; }; +struct arizona_micd_range { + int max; /** Ohms */ + int key; /** Key to report to input layer */ +}; + struct arizona_pdata { int reset; /** GPIO controlling /RESET, if any */ int ldoena; /** GPIO controlling LODENA, if any */ @@ -138,6 +143,10 @@ struct arizona_pdata { /** Force MICBIAS on for mic detect */ bool micd_force_micbias; + /** Mic detect level parameters */ + const struct arizona_micd_range *micd_ranges; + int num_micd_ranges; + /** Headset polarity configurations */ struct arizona_micd_config *micd_configs; int num_micd_configs; -- cgit v1.2.3 From e56a0a572be150c79cdbf62ff98f4a63419e1c0b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 1 Apr 2013 19:03:52 +0100 Subject: extcon: arizona: Allow pull to be disabled on GPIO5 when used for JACKET In some designs an external pull won't be needed. Signed-off-by: Mark Brown --- include/linux/mfd/arizona/pdata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index eb11a8ac6db2..008b8c40549f 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -122,6 +122,9 @@ struct arizona_pdata { /** GPIO5 is used for jack detection */ bool jd_gpio5; + /** Internal pull on GPIO5 is disabled when used for jack detection */ + bool jd_gpio5_nopull; + /** Use the headphone detect circuit to identify the accessory */ bool hpdet_acc_id; -- cgit v1.2.3 From 9c2ba270eaa227c999af451e1c2c9bf0d24aa8e5 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 25 Feb 2013 23:42:31 +0000 Subject: extcon: arizona: Simplify HPDET based identification Rather than measuring both HP channels we can simply directly measure the microphone impedance and then rely on MICDET for final confirmation of the presence of a suitable microphone. This improves the overall performance of the identification process. Signed-off-by: Mark Brown --- include/linux/mfd/arizona/pdata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 008b8c40549f..45c84777c624 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -128,6 +128,9 @@ struct arizona_pdata { /** Use the headphone detect circuit to identify the accessory */ bool hpdet_acc_id; + /** Check for line output with HPDET method */ + bool hpdet_acc_id_line; + /** GPIO used for mic isolation with HPDET */ int hpdet_id_gpio; -- cgit v1.2.3 From cd59e79656f4e7137909166248a935d422b1245a Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 1 Apr 2013 19:21:48 +0100 Subject: extcon: arizona: Allow additional debounce during microphone detection Help mitigate against mechanical bounce during the initial detection by allowing the configuration of an additional debounce on top of that the hardware does during the initial phase of microphone detection operation. Signed-off-by: Mark Brown --- include/linux/mfd/arizona/pdata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 45c84777c624..3ef300baa2e6 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -134,6 +134,9 @@ struct arizona_pdata { /** GPIO used for mic isolation with HPDET */ int hpdet_id_gpio; + /** Extra debounce timeout used during initial mic detection (ms) */ + int micd_detect_debounce; + /** GPIO for mic detection polarity */ int micd_pol_gpio; -- cgit v1.2.3 From 7abd4e2a8f1c3e534da44c35e2d3d6353573e51f Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 1 Apr 2013 19:25:55 +0100 Subject: extcon: arizona: Make mic detection timeout configurable Signed-off-by: Mark Brown --- include/linux/mfd/arizona/pdata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 3ef300baa2e6..a0f940987a3e 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -149,6 +149,9 @@ struct arizona_pdata { /** Mic detect debounce level */ int micd_dbtime; + /** Mic detect timeout (ms) */ + int micd_timeout; + /** Force MICBIAS on for mic detect */ bool micd_force_micbias; -- cgit v1.2.3 From b43a7ffbf33be7e4d3b10b7714ee663ea2c52fe2 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Sun, 24 Mar 2013 11:56:43 +0530 Subject: cpufreq: Notify all policy->cpus in cpufreq_notify_transition() policy->cpus contains all online cpus that have single shared clock line. And their frequencies are always updated together. Many SMP system's cpufreq drivers take care of this in individual drivers but the best place for this code is in cpufreq core. This patch modifies cpufreq_notify_transition() to notify frequency change for all cpus in policy->cpus and hence updates all users of this API. Signed-off-by: Viresh Kumar Acked-by: Stephen Warren Tested-by: Stephen Warren Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 4bbc572dd521..037d36ae63e5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -278,8 +278,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); -void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state); - +void cpufreq_notify_transition(struct cpufreq_policy *policy, + struct cpufreq_freqs *freqs, unsigned int state); static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy, unsigned int min, unsigned int max) { -- cgit v1.2.3 From bb5547acfcd842950b8a22aa83f84af93388b9f2 Mon Sep 17 00:00:00 2001 From: Varun Sethi Date: Fri, 29 Mar 2013 01:23:58 +0530 Subject: iommu/fsl: Make iova dma_addr_t in the iommu_iova_to_phys API. This is required in case of PAMU, as it can support a window size of up to 64G (even on 32bit). Signed-off-by: Varun Sethi Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index ba3b8a98a049..bb0a0fc26729 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -91,8 +91,7 @@ struct iommu_ops { phys_addr_t paddr, size_t size, int prot); size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, size_t size); - phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, - unsigned long iova); + phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); int (*domain_has_cap)(struct iommu_domain *domain, unsigned long cap); int (*add_device)(struct device *dev); @@ -134,8 +133,7 @@ extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size); -extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, - unsigned long iova); +extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova); extern int iommu_domain_has_cap(struct iommu_domain *domain, unsigned long cap); extern void iommu_set_fault_handler(struct iommu_domain *domain, @@ -267,8 +265,7 @@ static inline void iommu_domain_window_disable(struct iommu_domain *domain, { } -static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, - unsigned long iova) +static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { return 0; } -- cgit v1.2.3 From 80f97f0f73b82444f714651ea053838d27779dca Mon Sep 17 00:00:00 2001 From: Varun Sethi Date: Fri, 29 Mar 2013 01:24:00 +0530 Subject: iommu/fsl: Add the window permission flag as a parameter to iommu_window_enable API. Each iommu window can have access permissions associated with it. Extended the window_enable API to incorporate window access permissions. In case of PAMU each window can have its specific set of permissions. Signed-off-by: Varun Sethi Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index bb0a0fc26729..272781073110 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -104,7 +104,7 @@ struct iommu_ops { /* Window handling functions */ int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, - phys_addr_t paddr, u64 size); + phys_addr_t paddr, u64 size, int prot); void (*domain_window_disable)(struct iommu_domain *domain, u32 wnd_nr); /* Set the numer of window per domain */ int (*domain_set_windows)(struct iommu_domain *domain, u32 w_count); @@ -169,7 +169,8 @@ extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr, /* Window handling function prototypes */ extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, - phys_addr_t offset, u64 size); + phys_addr_t offset, u64 size, + int prot); extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr); /** * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework @@ -255,7 +256,7 @@ static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova, static inline int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, - u64 size) + u64 size, int prot) { return -ENODEV; } -- cgit v1.2.3 From 65b3841b9cb5fe1b239f12dbf033f9827d73d032 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 2 Apr 2013 09:35:07 +0000 Subject: of_net.h: Provide empty functions if OF_NET is not configured of_get_mac_address() and of_get_phy_mode() are only provided if OF_NET is configured. While most callers check for the define, not all do, and those who do require #ifdef around the code. For those who don't, the missing check can result in errors such as arch/powerpc/sysdev/tsi108_dev.c:107:3: error: implicit declaration of function 'of_get_mac_address' [-Werror=implicit-function-declaration] arch/powerpc/sysdev/mv64x60_dev.c:253:2: error: implicit declaration of function 'of_get_mac_address' [-Werror=implicit-function-declaration] Provide empty functions if OF_NET is not configured. This is safe because all callers do check the return values. Cc: David Daney Signed-off-by: Guenter Roeck Acked-by: Rob Herring Signed-off-by: David S. Miller --- include/linux/of_net.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_net.h b/include/linux/of_net.h index f47464188710..61bf53b02779 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -11,6 +11,16 @@ #include extern const int of_get_phy_mode(struct device_node *np); extern const void *of_get_mac_address(struct device_node *np); +#else +static inline const int of_get_phy_mode(struct device_node *np) +{ + return -ENODEV; +} + +static inline const void *of_get_mac_address(struct device_node *np) +{ + return NULL; +} #endif #endif /* __LINUX_OF_NET_H */ -- cgit v1.2.3 From 35e1d5f6344ed1bb2fab61ac7934aa0f19908b2c Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 2 Apr 2013 13:24:05 +0100 Subject: regulator: ab8500-ext: Remove unused REGULATOR_AB8500_EXT guard Before the AB8500 External Regulator driver was Mainlined, it used to be conditionally compiled in using the CONFIG_REGULATOR_AB8500_EXT flag. During the review process that capability was removed, but the guard controlling prototyping slipped though the net. This patch cleans it up. Signed-off-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index bb0140c9d4f4..44f67e8f1a6d 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -320,21 +320,6 @@ struct ab8500_regulator_platform_data { struct regulator_init_data *ext_regulator; }; -/* AB8500 external regulator functions (internal) */ -#ifdef CONFIG_REGULATOR_AB8500_EXT -int ab8500_ext_regulator_init(struct platform_device *pdev); -int ab8500_ext_regulator_exit(struct platform_device *pdev); -#else -inline int ab8500_ext_regulator_init(struct platform_device *pdev) -{ - return 0; -} -inline int ab8500_ext_regulator_exit(struct platform_device *pdev) -{ - return 0; -} -#endif - #ifdef CONFIG_REGULATOR_AB8500_DEBUG int ab8500_regulator_debug_init(struct platform_device *pdev); int ab8500_regulator_debug_exit(struct platform_device *pdev); @@ -349,4 +334,8 @@ static inline int ab8500_regulator_debug_exit(struct platform_device *pdev) } #endif +/* AB8500 external regulator functions. */ +int ab8500_ext_regulator_init(struct platform_device *pdev); +int ab8500_ext_regulator_exit(struct platform_device *pdev); + #endif -- cgit v1.2.3 From 3566d40c1a4617461b38c82059bdc41d622faa8b Mon Sep 17 00:00:00 2001 From: James Hogan Date: Mon, 25 Mar 2013 14:35:07 +0000 Subject: clk: fix clk_mux::flags kerneldoc The kerneldoc comment for struct clk_mux documented the non-existent num_clks instead of flags. Correct this. Signed-off-by: James Hogan Signed-off-by: Mike Turquette --- include/linux/clk-provider.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 1f0352802794..b1675074fe7c 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -284,7 +284,7 @@ struct clk *clk_register_divider_table(struct device *dev, const char *name, * @reg: register controlling multiplexer * @shift: shift to multiplexer bit field * @width: width of mutliplexer bit field - * @num_clks: number of parent clocks + * @flags: hardware-specific flags * @lock: register lock * * Clock with multiple selectable parents. Implements .get_parent, .set_parent -- cgit v1.2.3 From 119f5e448d32c11faf22fe81f6f2d78467a47149 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Wed, 13 Mar 2013 20:32:13 +0900 Subject: gpio: Renesas R-Car GPIO driver V3 This patch is V3 of a GPIO driver for the R-Car series of SoCs from Renesas. This driver is designed to be reusable between multiple SoCs that share the same basic building block, but so far it has only been used on R-Car H1 (r8a7779). Each driver instance handles 32 GPIOs with individually maskable IRQs. The driver operates on a single I/O memory range and the 32 GPIOs are hooked up a single interrupt. In the case of R-Car H1 either external IRQ pins or GPIOs with interrupts can be used for on-board interupts. For external IRQs 4 pins are supported, and in the case of GPIO there are 202 GPIOS as 202 interrupts hooked up via 6 driver instances and to the GIC and the Cortex-A9 Quad. At this point this driver is interfacing as a regular platform device driver. In the future DT support will be submitted as an incremental feature patch. Signed-off-by: Magnus Damm Reviewed-by: Linus Walleij Signed-off-by: Simon Horman --- include/linux/platform_data/gpio-rcar.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/linux/platform_data/gpio-rcar.h (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-rcar.h b/include/linux/platform_data/gpio-rcar.h new file mode 100644 index 000000000000..bebfcd86fb80 --- /dev/null +++ b/include/linux/platform_data/gpio-rcar.h @@ -0,0 +1,25 @@ +/* + * Renesas R-Car GPIO Support + * + * Copyright (C) 2013 Magnus Damm + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __GPIO_RCAR_H__ +#define __GPIO_RCAR_H__ + +struct gpio_rcar_config { + unsigned int gpio_base; + unsigned int irq_base; + unsigned int number_of_pins; +}; + +#endif /* __GPIO_RCAR_H__ */ -- cgit v1.2.3 From dc3465a943ed2dd5de37d3d60df5c4e11c49efcb Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Sun, 10 Mar 2013 03:27:00 +0100 Subject: gpio-rcar: Add pinctrl support Register the GPIO pin range, and request and free GPIO pins using the pinctrl API. Signed-off-by: Laurent Pinchart Acked-by: Linus Walleij Signed-off-by: Simon Horman --- include/linux/platform_data/gpio-rcar.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-rcar.h b/include/linux/platform_data/gpio-rcar.h index bebfcd86fb80..b253f77a7ddf 100644 --- a/include/linux/platform_data/gpio-rcar.h +++ b/include/linux/platform_data/gpio-rcar.h @@ -20,6 +20,7 @@ struct gpio_rcar_config { unsigned int gpio_base; unsigned int irq_base; unsigned int number_of_pins; + const char *pctl_name; }; #endif /* __GPIO_RCAR_H__ */ -- cgit v1.2.3 From d7ca4c755a82eda8f0fc4f72c52130056b28c7d2 Mon Sep 17 00:00:00 2001 From: "Manjunathappa, Prakash" Date: Thu, 28 Mar 2013 18:41:59 +0530 Subject: ARM: davinci: mmc: derive version information from device name Remove specifying mmc controller IP version information via platform data, instead specify device name so that driver derives it from platform_device_id table. Also change the clock node name to match the changed dev_id. Tested on da850-evm to make sure driver loads without clk_get failures. Signed-off-by: Manjunathappa, Prakash Reviewed-by: Sekhar Nori Acked-by: Arnd Bergmann Acked-by: Chris Ball Signed-off-by: Sekhar Nori --- include/linux/platform_data/mmc-davinci.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mmc-davinci.h b/include/linux/platform_data/mmc-davinci.h index 5ba6b22ce338..9cea4ee377b5 100644 --- a/include/linux/platform_data/mmc-davinci.h +++ b/include/linux/platform_data/mmc-davinci.h @@ -23,9 +23,6 @@ struct davinci_mmc_config { /* any additional host capabilities: OR'd in to mmc->f_caps */ u32 caps; - /* Version of the MMC/SD controller */ - u8 version; - /* Number of sg segments */ u8 nr_sg; }; -- cgit v1.2.3 From 88af8bbe4ef781031ad3370847553f3b42ba0076 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sun, 23 Dec 2012 21:10:24 +0100 Subject: usb: gadget: the start of the configfs interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit |# modprobe dummy_hcd num=2 |# modprobe libcomposite |# lsmod |Module Size Used by |libcomposite 31648 0 |dummy_hcd 19871 0 |# mkdir /sys/kernel/config/usb_gadget/oha |# cd /sys/kernel/config/usb_gadget/oha |# mkdir configs/def.1 |# mkdir configs/def.2 |# mkdir functions/acm.ttyS1 |# mkdir strings/0x1 |mkdir: cannot create directory `strings/0x1': Invalid argument |# mkdir strings/0x409 |# mkdir strings/1033 |mkdir: cannot create directory `strings/1033': File exists |# mkdir strings/1032 |# mkdir configs/def.1/strings/0x409 |# mkdir configs/def.2/strings/0x409 |#find . -ls | 975 0 drwxr-xr-x 5 root root 0 Dec 23 17:40 . | 978 0 drwxr-xr-x 4 root root 0 Dec 23 17:43 ./strings | 4100 0 drwxr-xr-x 2 root root 0 Dec 23 17:43 ./strings/1032 | 995 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./strings/1032/serialnumber | 996 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./strings/1032/product | 997 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./strings/1032/manufacturer | 2002 0 drwxr-xr-x 2 root root 0 Dec 23 17:41 ./strings/0x409 | 998 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./strings/0x409/serialnumber | 999 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./strings/0x409/product | 1000 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./strings/0x409/manufacturer | 977 0 drwxr-xr-x 4 root root 0 Dec 23 17:41 ./configs | 4081 0 drwxr-xr-x 3 root root 0 Dec 23 17:41 ./configs/def.2 | 4082 0 drwxr-xr-x 3 root root 0 Dec 23 17:42 ./configs/def.2/strings | 2016 0 drwxr-xr-x 2 root root 0 Dec 23 17:42 ./configs/def.2/strings/0x409 | 1001 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./configs/def.2/strings/0x409/configuration | 1002 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./configs/def.2/bmAttributes | 1003 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./configs/def.2/MaxPower | 979 0 drwxr-xr-x 3 root root 0 Dec 23 17:42 ./configs/def.1 | 980 0 drwxr-xr-x 3 root root 0 Dec 23 17:42 ./configs/def.1/strings | 5122 0 drwxr-xr-x 2 root root 0 Dec 23 17:42 ./configs/def.1/strings/0x409 | 1004 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./configs/def.1/strings/0x409/configuration | 1005 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./configs/def.1/bmAttributes | 1006 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./configs/def.1/MaxPower | 976 0 drwxr-xr-x 3 root root 0 Dec 23 17:41 ./functions | 981 0 drwxr-xr-x 2 root root 0 Dec 23 17:41 ./functions/acm.ttyS1 | 1007 0 -r--r--r-- 1 root root 4096 Dec 23 17:43 ./functions/acm.ttyS1/port_num | 1008 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./UDC | 1009 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./bcdUSB | 1010 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./bcdDevice | 1011 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./idProduct | 1012 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./idVendor | 1013 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./bMaxPacketSize0 | 1014 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./bDeviceProtocol | 1015 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./bDeviceSubClass | 1016 0 -rw-r--r-- 1 root root 4096 Dec 23 17:43 ./bDeviceClass |# cat functions/acm.ttyS1/port_num |0 |# ls -lah /dev/ttyGS* |crw-rw---T 1 root dialout 252, 0 Dec 23 17:41 /dev/ttyGS0 | |# echo 0x1234 > idProduct |# echo 0xabcd > idVendor |# echo 1122 > strings/0x409/serialnumber |# echo "The manufacturer" > strings/0x409/manufacturer |# echo 1 > strings/1032/manufacturer |# echo 1sa > strings/1032/product |# echo tada > strings/1032/serialnumber |echo "Primary configuration" > configs/def.1/strings/0x409/configuration |# echo "Secondary configuration" > configs/def.2/strings/0x409/configuration |# ln -s functions/acm.ttyS1 configs/def.1/ |# ln -s functions/acm.ttyS1 configs/def.2/ |find configs/def.1/ -ls | 979 0 drwxr-xr-x 3 root root 0 Dec 23 17:49 configs/def.1/ | 6264 0 lrwxrwxrwx 1 root root 0 Dec 23 17:48 configs/def.1/acm.ttyS1 -> ../../../../usb_gadget/oha/functions/acm.ttyS1 | 980 0 drwxr-xr-x 3 root root 0 Dec 23 17:42 configs/def.1/strings | 5122 0 drwxr-xr-x 2 root root 0 Dec 23 17:49 configs/def.1/strings/0x409 | 6284 0 -rw-r--r-- 1 root root 4096 Dec 23 17:47 configs/def.1/strings/0x409/configuration | 6285 0 -rw-r--r-- 1 root root 4096 Dec 23 17:49 configs/def.1/bmAttributes | 6286 0 -rw-r--r-- 1 root root 4096 Dec 23 17:49 configs/def.1/MaxPower | |echo 120 > configs/def.1/MaxPower | |# ls -lh /sys/class/udc/ |total 0 |lrwxrwxrwx 1 root root 0 Dec 23 17:50 dummy_udc.0 -> ../../devices/platform/dummy_udc.0/udc/dummy_udc.0 |lrwxrwxrwx 1 root root 0 Dec 23 17:50 dummy_udc.1 -> ../../devices/platform/dummy_udc.1/udc/dummy_udc.1 |# echo dummy_udc.0 > UDC |# lsusb |Bus 001 Device 002: ID abcd:1234 Unknown | |lsusb -d abcd:1234 -v |Device Descriptor: … | idVendor 0xabcd Unknown | idProduct 0x1234 | bcdDevice 3.06 | iManufacturer 1 The manufacturer | iProduct 2 | iSerial 3 1122 | bNumConfigurations 2 … |echo "" > UDC v5…v6 - wired up strings with usb_gstrings_attach() - add UDC attribe. Write "udc-name" will bind the gadget. Write an empty string (it should contain \n since 0 bytes write get optimzed away) will unbind the UDC from the gadget. The name of available UDCs can be obtained from /sys/class/udc/ v4…v5 - string rework. This will add a strings folder incl. language code like strings/409/manufacturer as suggested by Alan. - rebased ontop reworked functions.c which has usb_function_instance which is used prior after "mkdir acm.instance" and can be directly used for configuration via configfs. v3…v4 - moved functions from the root folde down to the gadget as suggested by Michał - configs have now their own configs folder as suggested by Michał. The folder is still name.bConfigurationValue where name becomes the sConfiguration. Is this usefull should we just stilc configs/bConfigurationValue/ ? - added configfs support to the ACM function. The port_num attribute is exported by f_acm. An argument has been added to the USB alloc function to distinguish between "old" (use facm_configure() to configure and configfs interface (expose a config_node). The port_num is currently a dumb counter. It will require some function re-work to make it work. scheduled for v5: - sym linking function into config. v2…v3 - replaced one ifndef by ifdef as suggested by Micahał - strstr()/strchr() function_make as suggested by Micahł - replace [iSerialNumber|iProduct|iManufacturer] with [sSerialNumber|sProduct|sManufacturer] as suggested by Alan - added creation of config descriptors v1…v2 - moved gadgets from configfs' root directory into /udcs/ within our "usb_gadget" folder. Requested by Andrzej & Michał - use a dot as a delimiter between function's name and its instance's name as suggested by Michał - renamed all config_item_type, configfs_group_operations, make_group, drop_item as suggested by suggested by Andrzej to remain consisten within this file and within other configfs users - Since configfs.c and functions.c are now part of the udc-core module, the module itself is now called udc. Also added a tiny ifdef around init code becuase udc-core is subsys init and this is too early for configfs in the built-in case. In the module case, we can only have one init function. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Felipe Balbi --- include/linux/usb/composite.h | 3 + include/linux/usb/gadget_configfs.h | 110 ++++++++++++++++++++++++++++++++++++ 2 files changed, 113 insertions(+) create mode 100644 include/linux/usb/gadget_configfs.h (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 8860594d6364..5e61589fc166 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -39,6 +39,7 @@ #include #include #include +#include /* * USB function drivers should return USB_GADGET_DELAYED_STATUS if they @@ -464,6 +465,8 @@ struct usb_function_driver { }; struct usb_function_instance { + struct config_group group; + struct list_head cfs_list; struct usb_function_driver *fd; void (*free_func_inst)(struct usb_function_instance *inst); }; diff --git a/include/linux/usb/gadget_configfs.h b/include/linux/usb/gadget_configfs.h new file mode 100644 index 000000000000..d74c0ae989d5 --- /dev/null +++ b/include/linux/usb/gadget_configfs.h @@ -0,0 +1,110 @@ +#ifndef __GADGET_CONFIGFS__ +#define __GADGET_CONFIGFS__ + +#include + +int check_user_usb_string(const char *name, + struct usb_gadget_strings *stringtab_dev); + +#define GS_STRINGS_W(__struct, __name) \ + static ssize_t __struct##_##__name##_store(struct __struct *gs, \ + const char *page, size_t len) \ +{ \ + int ret; \ + \ + ret = usb_string_copy(page, &gs->__name); \ + if (ret) \ + return ret; \ + return len; \ +} + +#define GS_STRINGS_R(__struct, __name) \ + static ssize_t __struct##_##__name##_show(struct __struct *gs, \ + char *page) \ +{ \ + return sprintf(page, "%s\n", gs->__name ?: ""); \ +} + +#define GS_STRING_ITEM_ATTR(struct_name, name) \ + static struct struct_name##_attribute struct_name##_##name = \ + __CONFIGFS_ATTR(name, S_IRUGO | S_IWUSR, \ + struct_name##_##name##_show, \ + struct_name##_##name##_store) + +#define GS_STRINGS_RW(struct_name, _name) \ + GS_STRINGS_R(struct_name, _name) \ + GS_STRINGS_W(struct_name, _name) \ + GS_STRING_ITEM_ATTR(struct_name, _name) + +#define USB_CONFIG_STRING_RW_OPS(struct_in) \ + CONFIGFS_ATTR_OPS(struct_in); \ + \ +static struct configfs_item_operations struct_in##_langid_item_ops = { \ + .release = struct_in##_attr_release, \ + .show_attribute = struct_in##_attr_show, \ + .store_attribute = struct_in##_attr_store, \ +}; \ + \ +static struct config_item_type struct_in##_langid_type = { \ + .ct_item_ops = &struct_in##_langid_item_ops, \ + .ct_attrs = struct_in##_langid_attrs, \ + .ct_owner = THIS_MODULE, \ +} + +#define USB_CONFIG_STRINGS_LANG(struct_in, struct_member) \ + static struct config_group *struct_in##_strings_make( \ + struct config_group *group, \ + const char *name) \ + { \ + struct struct_member *gi; \ + struct struct_in *gs; \ + struct struct_in *new; \ + int langs = 0; \ + int ret; \ + \ + new = kzalloc(sizeof(*new), GFP_KERNEL); \ + if (!new) \ + return ERR_PTR(-ENOMEM); \ + \ + ret = check_user_usb_string(name, &new->stringtab_dev); \ + if (ret) \ + goto err; \ + config_group_init_type_name(&new->group, name, \ + &struct_in##_langid_type); \ + \ + gi = container_of(group, struct struct_member, strings_group); \ + ret = -EEXIST; \ + list_for_each_entry(gs, &gi->string_list, list) { \ + if (gs->stringtab_dev.language == new->stringtab_dev.language) \ + goto err; \ + langs++; \ + } \ + ret = -EOVERFLOW; \ + if (langs >= MAX_USB_STRING_LANGS) \ + goto err; \ + \ + list_add_tail(&new->list, &gi->string_list); \ + return &new->group; \ +err: \ + kfree(new); \ + return ERR_PTR(ret); \ +} \ + \ +static void struct_in##_strings_drop( \ + struct config_group *group, \ + struct config_item *item) \ +{ \ + config_item_put(item); \ +} \ + \ +static struct configfs_group_operations struct_in##_strings_ops = { \ + .make_group = &struct_in##_strings_make, \ + .drop_item = &struct_in##_strings_drop, \ +}; \ + \ +static struct config_item_type struct_in##_strings_type = { \ + .ct_group_ops = &struct_in##_strings_ops, \ + .ct_owner = THIS_MODULE, \ +} + +#endif -- cgit v1.2.3 From 3451d0243c3cdfd729b36f9684a14659d4895ca3 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Aug 2011 23:21:01 +0200 Subject: nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- include/linux/sched.h | 8 ++++---- include/linux/tick.h | 8 ++++---- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 10626e2ee688..1ff9e0a5de27 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -230,7 +230,7 @@ extern void init_idle_bootup_task(struct task_struct *idle); extern int runqueue_is_locked(int cpu); -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void nohz_balance_enter_idle(int cpu); extern void set_cpu_sd_state_idle(void); extern int get_nohz_timer_target(void); @@ -1758,13 +1758,13 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, } #endif -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON void calc_load_enter_idle(void); void calc_load_exit_idle(void); #else static inline void calc_load_enter_idle(void) { } static inline void calc_load_exit_idle(void) { } -#endif /* CONFIG_NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ #ifndef CONFIG_CPUMASK_OFFSTACK static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) @@ -1850,7 +1850,7 @@ extern void idle_task_exit(void); static inline void idle_task_exit(void) {} #endif -#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) +#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) extern void wake_up_nohz_cpu(int cpu); #else static inline void wake_up_nohz_cpu(int cpu) { } diff --git a/include/linux/tick.h b/include/linux/tick.h index 44bfa8aa439f..5e403339ee14 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -82,7 +82,7 @@ extern int tick_program_event(ktime_t expires, int force); extern void tick_setup_sched_timer(void); # endif -# if defined CONFIG_NO_HZ || defined CONFIG_HIGH_RES_TIMERS +# if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS extern void tick_cancel_sched_timer(int cpu); # else static inline void tick_cancel_sched_timer(int cpu) { } @@ -123,7 +123,7 @@ static inline void tick_check_idle(int cpu) { } static inline int tick_oneshot_mode_active(void) { return 0; } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ -# ifdef CONFIG_NO_HZ +# ifdef CONFIG_NO_HZ_COMMON DECLARE_PER_CPU(struct tick_sched, tick_cpu_sched); static inline int tick_nohz_tick_stopped(void) @@ -138,7 +138,7 @@ extern ktime_t tick_nohz_get_sleep_length(void); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); -# else /* !CONFIG_NO_HZ */ +# else /* !CONFIG_NO_HZ_COMMON */ static inline int tick_nohz_tick_stopped(void) { return 0; @@ -155,7 +155,7 @@ static inline ktime_t tick_nohz_get_sleep_length(void) } static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } -# endif /* !NO_HZ */ +# endif /* !CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_EXTENDED extern int tick_nohz_extended_cpu(int cpu); -- cgit v1.2.3 From 684d5ce4afafddb2ad08f36ea30ca7d7adc88ebe Mon Sep 17 00:00:00 2001 From: Zhenhua HUANG Date: Tue, 2 Apr 2013 13:24:15 +0100 Subject: regulator: ab8500: Introduce aux5, aux6 regulators for AB8540 Introduce aux5, aux6 into ab8540 regulator framework. Signed-off-by: Zhenhua HUANG Signed-off-by: Lee Jones Reviewed-by: Maxime COQUELIN Reviewed-by: David PARIS Reviewed-by: Philippe LANGLAIS Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 44f67e8f1a6d..90b8b5ae9a4e 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -74,6 +74,8 @@ enum ab8540_regulator_id { AB8540_LDO_AUX2, AB8540_LDO_AUX3, AB8540_LDO_AUX4, + AB8540_LDO_AUX5, + AB8540_LDO_AUX6, AB8540_LDO_INTCORE, AB8540_LDO_TVOUT, AB8540_LDO_AUDIO, -- cgit v1.2.3 From c4e67bbc99ce661808c3ee77b0bb5779d0df11ca Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 2 Apr 2013 13:24:19 +0100 Subject: ARM: ux500: Pass regulator platform data using the new format Regulator platform data is now passed though a single structure as opposed to the old way where four separate struct elements were required. This patch makes use of the new format. Signed-off-by: Lee Jones Signed-off-by: Mark Brown --- include/linux/mfd/abx500/ab8500.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index 9db0bda446a0..84f449475c25 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -364,8 +364,7 @@ struct ab8500 { const int *irq_reg_offset; }; -struct regulator_reg_init; -struct regulator_init_data; +struct ab8500_regulator_platform_data; struct ab8500_gpio_platform_data; struct ab8500_codec_platform_data; struct ab8500_sysctrl_platform_data; @@ -375,19 +374,13 @@ struct ab8500_sysctrl_platform_data; * @irq_base: start of AB8500 IRQs, AB8500_NR_IRQS will be used * @pm_power_off: Should machine pm power off hook be registered or not * @init: board-specific initialization after detection of ab8500 - * @num_regulator_reg_init: number of regulator init registers - * @regulator_reg_init: regulator init registers - * @num_regulator: number of regulators * @regulator: machine-specific constraints for regulators */ struct ab8500_platform_data { int irq_base; bool pm_power_off; void (*init) (struct ab8500 *); - int num_regulator_reg_init; - struct ab8500_regulator_reg_init *regulator_reg_init; - int num_regulator; - struct regulator_init_data *regulator; + struct ab8500_regulator_platform_data *regulator; struct abx500_gpio_platform_data *gpio; struct ab8500_codec_platform_data *codec; struct ab8500_sysctrl_platform_data *sysctrl; -- cgit v1.2.3 From 056b205316cc3dcf8a67cf813a26ff8a72bf3cb9 Mon Sep 17 00:00:00 2001 From: Soren Brinkmann Date: Tue, 2 Apr 2013 15:36:56 -0700 Subject: clk: divider: Introduce CLK_DIVIDER_ALLOW_ZERO flag Dividers which have CLK_DIVIDER_ONE_BASED set have a redundant state, being a divider value of zero. Some hardware implementations allow a zero divider which simply doesn't alter the frequency. I.e. it acts like a divide by one or bypassing the divider. This flag is used to handle such HW in the clk-divider model. Signed-off-by: Soren Brinkmann Signed-off-by: Mike Turquette --- include/linux/clk-provider.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index b1675074fe7c..9fdfae74d669 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -249,9 +249,14 @@ struct clk_div_table { * CLK_DIVIDER_ONE_BASED - by default the divisor is the value read from the * register plus one. If CLK_DIVIDER_ONE_BASED is set then the divider is * the raw value read from the register, with the value of zero considered - * invalid + * invalid, unless CLK_DIVIDER_ALLOW_ZERO is set. * CLK_DIVIDER_POWER_OF_TWO - clock divisor is 2 raised to the value read from * the hardware register + * CLK_DIVIDER_ALLOW_ZERO - Allow zero divisors. For dividers which have + * CLK_DIVIDER_ONE_BASED set, it is possible to end up with a zero divisor. + * Some hardware implementations gracefully handle this case and allow a + * zero divisor by not modifying their input clock + * (divide by one / bypass). */ struct clk_divider { struct clk_hw hw; @@ -265,6 +270,7 @@ struct clk_divider { #define CLK_DIVIDER_ONE_BASED BIT(0) #define CLK_DIVIDER_POWER_OF_TWO BIT(1) +#define CLK_DIVIDER_ALLOW_ZERO BIT(2) extern const struct clk_ops clk_divider_ops; struct clk *clk_register_divider(struct device *dev, const char *name, -- cgit v1.2.3 From d8668fcb0b257d9fdcfbe5c172a99b8d85e1cd82 Mon Sep 17 00:00:00 2001 From: Shan Hai Date: Mon, 18 Mar 2013 10:30:43 +0800 Subject: libata: Use integer return value for atapi_command_packet_set The function returns type of ATAPI drives so it should return integer value. The commit 4dce8ba94c7 (libata: Use 'bool' return value for ata_id_XXX) since v2.6.39 changed the type of return value from int to bool, the change would cause all of the ATAPI class drives to be treated as TYPE_TAPE and the max_sectors of the drives to be set to 65535 because of the commit f8d8e5799b7(libata: increase 128 KB / cmd limit for ATAPI tape drives), for the function would return true for all ATAPI class drives and the TYPE_TAPE is defined as 0x01. Cc: stable@vger.kernel.org Signed-off-by: Shan Hai Signed-off-by: Jeff Garzik --- include/linux/ata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index 8f7a3d68371a..ee0bd9524055 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -954,7 +954,7 @@ static inline int atapi_cdb_len(const u16 *dev_id) } } -static inline bool atapi_command_packet_set(const u16 *dev_id) +static inline int atapi_command_packet_set(const u16 *dev_id) { return (dev_id[ATA_ID_CONFIG] >> 8) & 0x1f; } -- cgit v1.2.3 From a32450e127fc6e5ca6d958ceb3cfea4d30a00846 Mon Sep 17 00:00:00 2001 From: Shan Hai Date: Mon, 18 Mar 2013 10:30:44 +0800 Subject: libata: Set max sector to 65535 for Slimtype DVD A DS8A8SH drive The Slimtype DVD A DS8A8SH drive locks up when max sector is smaller than 65535, and the blow backtrace is observed on locking up: INFO: task flush-8:32:1130 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. flush-8:32 D ffffffff8180cf60 0 1130 2 0x00000000 ffff880273aef618 0000000000000046 0000000000000005 ffff880273aee000 ffff880273aee000 ffff880273aeffd8 ffff880273aee010 ffff880273aee000 ffff880273aeffd8 ffff880273aee000 ffff88026e842ea0 ffff880274a10000 Call Trace: [] schedule+0x5d/0x70 [] io_schedule+0x8c/0xd0 [] get_request+0x731/0x7d0 [] ? cfq_allow_merge+0x50/0x90 [] ? wake_up_bit+0x40/0x40 [] ? bio_attempt_back_merge+0x33/0x110 [] blk_queue_bio+0x23a/0x3f0 [] generic_make_request+0xc6/0x120 [] submit_bio+0x138/0x160 [] ? bio_alloc_bioset+0x96/0x120 [] submit_bh+0x1f1/0x220 [] __block_write_full_page+0x228/0x340 [] ? attach_nobh_buffers+0xc0/0xc0 [] ? I_BDEV+0x10/0x10 [] ? I_BDEV+0x10/0x10 [] block_write_full_page_endio+0xe6/0x100 [] block_write_full_page+0x15/0x20 [] blkdev_writepage+0x18/0x20 [] __writepage+0x17/0x40 [] write_cache_pages+0x34a/0x4a0 [] ? set_page_dirty+0x70/0x70 [] generic_writepages+0x51/0x80 [] do_writepages+0x20/0x50 [] __writeback_single_inode+0xa6/0x2b0 [] writeback_sb_inodes+0x311/0x4d0 [] __writeback_inodes_wb+0x86/0xd0 [] wb_writeback+0x1a3/0x330 [] ? _raw_spin_lock_irqsave+0x3f/0x50 [] ? get_nr_inodes+0x52/0x70 [] wb_do_writeback+0x1dc/0x260 [] ? schedule_timeout+0x204/0x240 [] bdi_writeback_thread+0x102/0x2b0 [] ? wb_do_writeback+0x260/0x260 [] kthread+0xc0/0xd0 [] ? kthread_worker_fn+0x1b0/0x1b0 [] ret_from_fork+0x7c/0xb0 [] ? kthread_worker_fn+0x1b0/0x1b0 The above trace was triggered by "dd if=/dev/zero of=/dev/sr0 bs=2048 count=32768" It was previously working by accident, since another bug introduced by 4dce8ba94c7 (libata: Use 'bool' return value for ata_id_XXX) caused all drives to use maxsect=65535. Cc: stable@vger.kernel.org Signed-off-by: Shan Hai Signed-off-by: Jeff Garzik --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 91c9d109e5f1..eae7a053dc51 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -398,6 +398,7 @@ enum { ATA_HORKAGE_NOSETXFER = (1 << 14), /* skip SETXFER, SATA only */ ATA_HORKAGE_BROKEN_FPDMA_AA = (1 << 15), /* skip AA */ ATA_HORKAGE_DUMP_ID = (1 << 16), /* dump IDENTIFY data */ + ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17), /* Set max sects to 65535 */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From d76a3a77113db020d9bb1e894822869410450bd9 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 3 Apr 2013 22:02:52 -0400 Subject: ext4/jbd2: don't wait (forever) for stale tid caused by wraparound In the case where an inode has a very stale transaction id (tid) in i_datasync_tid or i_sync_tid, it's possible that after a very large (2**31) number of transactions, that the tid number space might wrap, causing tid_geq()'s calculations to fail. Commit deeeaf13 "jbd2: fix fsync() tid wraparound bug", later modified by commit e7b04ac0 "jbd2: don't wake kjournald unnecessarily", attempted to fix this problem, but it only avoided kjournald spinning forever by fixing the logic in jbd2_log_start_commit(). Unfortunately, in the codepaths in fs/ext4/fsync.c and fs/ext4/inode.c that might call jbd2_log_start_commit() with a stale tid, those functions will subsequently call jbd2_log_wait_commit() with the same stale tid, and then wait for a very long time. To fix this, we replace the calls to jbd2_log_start_commit() and jbd2_log_wait_commit() with a call to a new function, jbd2_complete_transaction(), which will correctly handle stale tid's. As a bonus, jbd2_complete_transaction() will avoid locking j_state_lock for writing unless a commit needs to be started. This should have a small (but probably not measurable) improvement for ext4's scalability. Signed-off-by: "Theodore Ts'o" Reported-by: Ben Hutchings Reported-by: George Barnett Cc: stable@vger.kernel.org --- include/linux/jbd2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 50e5a5e6a712..f0289754b464 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1200,6 +1200,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); int jbd2_journal_force_commit_nested(journal_t *journal); int jbd2_log_wait_commit(journal_t *journal, tid_t tid); +int jbd2_complete_transaction(journal_t *journal, tid_t tid); int jbd2_log_do_checkpoint(journal_t *journal); int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid); -- cgit v1.2.3 From 794446c6946513c684d448205fbd76fa35f38b72 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Wed, 3 Apr 2013 22:06:52 -0400 Subject: jbd2: fix race between jbd2_journal_remove_checkpoint and ->j_commit_callback The following race is possible: [kjournald2] other_task jbd2_journal_commit_transaction() j_state = T_FINISHED; spin_unlock(&journal->j_list_lock); ->jbd2_journal_remove_checkpoint() ->jbd2_journal_free_transaction(); ->kmem_cache_free(transaction) ->j_commit_callback(journal, transaction); -> USE_AFTER_FREE WARNING: at lib/list_debug.c:62 __list_del_entry+0x1c0/0x250() Hardware name: list_del corruption. prev->next should be ffff88019a4ec198, but was 6b6b6b6b6b6b6b6b Modules linked in: cpufreq_ondemand acpi_cpufreq freq_table mperf coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode sg xhci_hcd button sd_mod crc_t10dif aesni_intel ablk_helper cryptd lrw aes_x86_64 xts gf128mul ahci libahci pata_acpi ata_generic dm_mirror dm_region_hash dm_log dm_mod Pid: 16400, comm: jbd2/dm-1-8 Tainted: G W 3.8.0-rc3+ #107 Call Trace: [] warn_slowpath_common+0xad/0xf0 [] warn_slowpath_fmt+0x46/0x50 [] ? ext4_journal_commit_callback+0x99/0xc0 [] __list_del_entry+0x1c0/0x250 [] ext4_journal_commit_callback+0x6f/0xc0 [] jbd2_journal_commit_transaction+0x23a6/0x2570 [] ? try_to_del_timer_sync+0x82/0xa0 [] ? del_timer_sync+0x91/0x1e0 [] kjournald2+0x19f/0x6a0 [] ? wake_up_bit+0x40/0x40 [] ? bit_spin_lock+0x80/0x80 [] kthread+0x10e/0x120 [] ? __init_kthread_worker+0x70/0x70 [] ret_from_fork+0x7c/0xb0 [] ? __init_kthread_worker+0x70/0x70 In order to demonstrace this issue one should mount ext4 with mount -o discard option on SSD disk. This makes callback longer and race window becomes wider. In order to fix this we should mark transaction as finished only after callbacks have completed Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" Cc: stable@vger.kernel.org --- include/linux/jbd2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index f0289754b464..f9fe88957b7a 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -480,6 +480,7 @@ struct transaction_s T_COMMIT, T_COMMIT_DFLUSH, T_COMMIT_JFLUSH, + T_COMMIT_CALLBACK, T_FINISHED } t_state; -- cgit v1.2.3 From c31ad081e8734aab3fb45d2f32e9969994dd076e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Arve=20Hj=C3=B8nnev=C3=A5g?= Date: Tue, 22 May 2012 16:33:23 -0700 Subject: pstore/ram: Allow specifying ecc parameters in platform data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allow specifying ecc parameters in platform data Signed-off-by: Arve Hjønnevåg [jstultz: Tweaked commit subject & add commit message] Signed-off-by: John Stultz Acked-by: Kees Cook Signed-off-by: Anton Vorontsov --- include/linux/pstore_ram.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index cb6ab5feab67..9974975d40db 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -26,6 +26,13 @@ struct persistent_ram_buffer; struct rs_control; +struct persistent_ram_ecc_info { + int block_size; + int ecc_size; + int symsize; + int poly; +}; + struct persistent_ram_zone { phys_addr_t paddr; size_t size; @@ -39,15 +46,14 @@ struct persistent_ram_zone { struct rs_control *rs_decoder; int corrected_bytes; int bad_blocks; - int ecc_block_size; - int ecc_size; + struct persistent_ram_ecc_info ecc_info; char *old_log; size_t old_log_size; }; struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, - u32 sig, int ecc_size); + u32 sig, struct persistent_ram_ecc_info *ecc_info); void persistent_ram_free(struct persistent_ram_zone *prz); void persistent_ram_zap(struct persistent_ram_zone *prz); @@ -74,7 +80,7 @@ struct ramoops_platform_data { unsigned long console_size; unsigned long ftrace_size; int dump_oops; - int ecc_size; + struct persistent_ram_ecc_info ecc_info; }; #endif -- cgit v1.2.3 From 3daf37260e965aa4bb060db99c2ed10b28109e04 Mon Sep 17 00:00:00 2001 From: Tony Prisk Date: Sat, 23 Mar 2013 17:02:15 +1300 Subject: of: Add support for reading a u32 from a multi-value property. This patch adds an of_property_read_u32_index() function to allow reading a single indexed u32 value from a property containing multiple u32 values. Signed-off-by: Tony Prisk Reviewed-by: Stephen Warren Acked-by: Linus Walleij Acked-by: Rob Herring --- include/linux/of.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index a0f129284948..c0747a44eaff 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -235,6 +235,9 @@ extern struct device_node *of_find_node_with_property( extern struct property *of_find_property(const struct device_node *np, const char *name, int *lenp); +extern int of_property_read_u32_index(const struct device_node *np, + const char *propname, + u32 index, u32 *out_value); extern int of_property_read_u8_array(const struct device_node *np, const char *propname, u8 *out_values, size_t sz); extern int of_property_read_u16_array(const struct device_node *np, @@ -394,6 +397,12 @@ static inline struct device_node *of_find_compatible_node( return NULL; } +static inline int of_property_read_u32_index(const struct device_node *np, + const char *propname, u32 index, u32 *out_value) +{ + return -ENOSYS; +} + static inline int of_property_read_u8_array(const struct device_node *np, const char *propname, u8 *out_values, size_t sz) { -- cgit v1.2.3 From 3af4ae1e4b57a663fff9cfe711c84fefb6ec966f Mon Sep 17 00:00:00 2001 From: Tony Prisk Date: Wed, 3 Apr 2013 07:20:34 +1300 Subject: video: vt8500: Remove unused platform_data/video-vt8500lcdfb.h With the conversion to devicetree only for arch-vt8500, this header is no longer required. This patch removes the #include from the two framebuffer drivers that used it, and the header file. Signed-off-by: Tony Prisk Reviewed-by: Jean-Christophe Plagniol-Villard Signed-off-by: Tomi Valkeinen --- include/linux/platform_data/video-vt8500lcdfb.h | 31 ------------------------- 1 file changed, 31 deletions(-) delete mode 100644 include/linux/platform_data/video-vt8500lcdfb.h (limited to 'include/linux') diff --git a/include/linux/platform_data/video-vt8500lcdfb.h b/include/linux/platform_data/video-vt8500lcdfb.h deleted file mode 100644 index 7f399c370fe0..000000000000 --- a/include/linux/platform_data/video-vt8500lcdfb.h +++ /dev/null @@ -1,31 +0,0 @@ -/* - * VT8500/WM8505 Frame Buffer platform data definitions - * - * Copyright (C) 2010 Ed Spiridonov - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#ifndef _VT8500FB_H -#define _VT8500FB_H - -#include - -struct vt8500fb_platform_data { - struct fb_videomode mode; - u32 xres_virtual; - u32 yres_virtual; - u32 bpp; - unsigned long video_mem_phys; - void *video_mem_virt; - unsigned long video_mem_len; -}; - -#endif /* _VT8500FB_H */ -- cgit v1.2.3 From 0908ad6e56b5a6e86745680bc324bdbfac64d0b6 Mon Sep 17 00:00:00 2001 From: Ananth N Mavinakayanahalli Date: Fri, 22 Mar 2013 20:46:27 +0530 Subject: uprobes: Add trap variant helper Some architectures like powerpc have multiple variants of the trap instruction. Introduce an additional helper is_trap_insn() for run-time handling of non-uprobe traps on such architectures. While there, change is_swbp_at_addr() to is_trap_at_addr() for reading clarity. With this change, the uprobe registration path will supercede any trap instruction inserted at the requested location, while taking care of delivering the SIGTRAP for cases where the trap notification came in for an address without a uprobe. See [1] for a more detailed explanation. [1] https://lists.ozlabs.org/pipermail/linuxppc-dev/2013-March/104771.html This change was suggested by Oleg Nesterov. Signed-off-by: Ananth N Mavinakayanahalli Acked-by: Srikar Dronamraju Signed-off-by: Oleg Nesterov --- include/linux/uprobes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 02b83db8e2c5..19612881399a 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -100,6 +100,7 @@ struct uprobes_state { extern int __weak set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); extern bool __weak is_swbp_insn(uprobe_opcode_t *insn); +extern bool __weak is_trap_insn(uprobe_opcode_t *insn); extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); -- cgit v1.2.3 From 4aa02c7cbb6816913554dc18ff750a70a4ace796 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Wed, 13 Mar 2013 14:03:12 +0800 Subject: video: mxsfb: remove fb_phys/fb_size from platform_data There is no in-tree users of mxsfb_platform_data fb_phys/fb_size. With CMA support in the kernel, there is no real need for platform to reserve memory and pass address and size into driver via platform_data. So let's remove fb_phys/fb_size from mxsfb_platform_data to ease full device tree adoption. Signed-off-by: Shawn Guo --- include/linux/mxsfb.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mxsfb.h b/include/linux/mxsfb.h index f80af8674342..93696404ee55 100644 --- a/include/linux/mxsfb.h +++ b/include/linux/mxsfb.h @@ -35,15 +35,6 @@ struct mxsfb_platform_data { unsigned dotclk_delay; /* refer manual HW_LCDIF_VDCTRL4 register */ unsigned ld_intf_width; /* refer STMLCDIF_* macros */ - - unsigned fb_size; /* Size of the video memory. If zero a - * default will be used - */ - unsigned long fb_phys; /* physical address for the video memory. If - * zero the framebuffer memory will be dynamically - * allocated. If specified,fb_size must also be specified. - * fb_phys must be unused by Linux. - */ u32 sync; /* sync mask, contains MXSFB specifics not * carried in fb_info->var.sync */ -- cgit v1.2.3 From 36f3e99649baa77b2d22e385b2ea09e8f308c905 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Wed, 13 Mar 2013 14:28:19 +0800 Subject: video: mxsfb: remove dotclk_delay from platform_data There is no in-tree mxsfb users using mxsfb_platform_data dotclk_delay. Let's remove it from mxsfb_platform_data to ease full device tree adoption of mxsfb driver. If later we have platform/board need to configure this parameter, we can add it into device tree bindings. Signed-off-by: Shawn Guo --- include/linux/mxsfb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mxsfb.h b/include/linux/mxsfb.h index 93696404ee55..b78465cdb26e 100644 --- a/include/linux/mxsfb.h +++ b/include/linux/mxsfb.h @@ -33,7 +33,6 @@ struct mxsfb_platform_data { unsigned default_bpp; - unsigned dotclk_delay; /* refer manual HW_LCDIF_VDCTRL4 register */ unsigned ld_intf_width; /* refer STMLCDIF_* macros */ u32 sync; /* sync mask, contains MXSFB specifics not * carried in fb_info->var.sync -- cgit v1.2.3 From c8b5cfc8797203d5e952592be00a5acacf5cef6a Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Thu, 14 Mar 2013 13:21:56 +0800 Subject: video: mxsfb: remove mxsfb_platform_data None of mxsfb users uses mxsfb_platform_data now. Let's remove it from mxsfb driver. As the result, include/linux/mxsfb.h gets deleted with a few macros moved into mxsfb.c. Along with the change, the typo "FAILING" in macro name is fixed to be "FALLING". Signed-off-by: Shawn Guo --- include/linux/mxsfb.h | 42 ------------------------------------------ 1 file changed, 42 deletions(-) delete mode 100644 include/linux/mxsfb.h (limited to 'include/linux') diff --git a/include/linux/mxsfb.h b/include/linux/mxsfb.h deleted file mode 100644 index b78465cdb26e..000000000000 --- a/include/linux/mxsfb.h +++ /dev/null @@ -1,42 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301, USA. - */ - -#ifndef __LINUX_MXSFB_H -#define __LINUX_MXSFB_H - -#include - -#define STMLCDIF_8BIT 1 /** pixel data bus to the display is of 8 bit width */ -#define STMLCDIF_16BIT 0 /** pixel data bus to the display is of 16 bit width */ -#define STMLCDIF_18BIT 2 /** pixel data bus to the display is of 18 bit width */ -#define STMLCDIF_24BIT 3 /** pixel data bus to the display is of 24 bit width */ - -#define MXSFB_SYNC_DATA_ENABLE_HIGH_ACT (1 << 6) -#define MXSFB_SYNC_DOTCLK_FAILING_ACT (1 << 7) /* failing/negtive edge sampling */ - -struct mxsfb_platform_data { - struct fb_videomode *mode_list; - unsigned mode_count; - - unsigned default_bpp; - - unsigned ld_intf_width; /* refer STMLCDIF_* macros */ - u32 sync; /* sync mask, contains MXSFB specifics not - * carried in fb_info->var.sync - */ -}; - -#endif /* __LINUX_MXSFB_H */ -- cgit v1.2.3 From 26aafa77df61c4190eae80646211ee6f07c88eaf Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Tue, 26 Feb 2013 11:07:32 +0800 Subject: spi: mxs-spi: move to use generic DMA helper With the generic DMA device tree helper supported by mxs-dma driver, client devices only need to call dma_request_slave_channel() for requesting a DMA channel from dmaengine. Since mxs is a DT only platform now, along with the changes, the non-DT case handling in probe function also gets removed. Signed-off-by: Shawn Guo Acked-by: Grant Likely Reviewed-by: Arnd Bergmann --- include/linux/spi/mxs-spi.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/mxs-spi.h b/include/linux/spi/mxs-spi.h index 61ae1306db23..4835486f58e5 100644 --- a/include/linux/spi/mxs-spi.h +++ b/include/linux/spi/mxs-spi.h @@ -24,7 +24,7 @@ #ifndef __LINUX_SPI_MXS_SPI_H__ #define __LINUX_SPI_MXS_SPI_H__ -#include +#include #define ssp_is_old(host) ((host)->devid == IMX23_SSP) @@ -137,9 +137,7 @@ struct mxs_ssp { unsigned int clk_rate; enum mxs_ssp_id devid; - int dma_channel; struct dma_chan *dmach; - struct mxs_dma_data dma_data; unsigned int dma_dir; enum dma_transfer_direction slave_dirn; u32 ssp_pio_words[SSP_PIO_NUM]; -- cgit v1.2.3 From aa6f9c595d857328e5d815e5b94c0e7cd31a6b59 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Fri, 22 Mar 2013 11:31:29 -0700 Subject: ntp: Move do_adjtimex() and hardpps() functions to timekeeping.c In preparation for changing the ntp locking rules, move do_adjtimex and hardpps accessor functions to timekeeping.c, but keep the code logic in ntp.c. This patch also introduces a ntp_internal.h file so timekeeping specific interfaces of ntp.c can be more limitedly shared with timekeeping.c. Cc: Thomas Gleixner Cc: Richard Cochran Cc: Prarit Bhargava Signed-off-by: John Stultz --- include/linux/timex.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index 5ec87c60b97c..b3726e61368e 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -125,9 +125,6 @@ extern unsigned long tick_usec; /* USER_HZ period (usec) */ extern unsigned long tick_nsec; /* SHIFTED_HZ period (nsec) */ -extern void ntp_init(void); -extern void ntp_clear(void); - /* Required to safely shift negative values */ #define shift_right(x, s) ({ \ __typeof__(x) __x = (x); \ @@ -140,10 +137,6 @@ extern void ntp_clear(void); #define NTP_INTERVAL_FREQ (HZ) #define NTP_INTERVAL_LENGTH (NSEC_PER_SEC/NTP_INTERVAL_FREQ) -/* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */ -extern u64 ntp_tick_length(void); - -extern int second_overflow(unsigned long secs); extern int do_adjtimex(struct timex *); extern void hardpps(const struct timespec *, const struct timespec *); -- cgit v1.2.3 From 14a3b6abe98c8f53a13522610c257accef7321df Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 Feb 2013 22:51:38 +0000 Subject: timekeeping: Store cycle_last value in timekeeper struct as well For implementing a shadow timekeeper and a split calculation/update region we need to store the cycle_last value in the timekeeper and update the value in the clocksource struct only in the update region. Add the extra storage to the timekeeper. Signed-off-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timekeeper_internal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index a151bd70e52b..c1825eb436ed 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -20,6 +20,8 @@ struct timekeeper { u32 shift; /* Number of clock cycles in one NTP interval. */ cycle_t cycle_interval; + /* Last cycle value (also stored in clock->cycle_last) */ + cycle_t cycle_last; /* Number of clock shifted nano seconds in one NTP interval. */ u64 xtime_interval; /* shifted nano seconds left over when rounding cycle_interval */ -- cgit v1.2.3 From 441f199a37cfd66c5dd8dd45490bd3ea6971117d Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Mon, 25 Mar 2013 13:22:24 -0600 Subject: clk: tegra: defer application of init table The Tegra clock driver is initialized during the ARM machine descriptor's .init_irq() hook. It can't be initialized earlier, since dynamic memory usage is required. It can't be initialized later, since the .init_timer() hook needs the clocks initialized. However, at this time, udelay() doesn't work. The Tegra clock initialization table may enable some PLLs. Enabling a PLL may require usage of udelay(). Hence, this can't happen right when the clock driver is initialized. To solve this, separate the clock driver initialization from the clock table processing, so they can execute at separate times. Signed-off-by: Stephen Warren --- include/linux/clk/tegra.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index 404d6f940872..642789baec74 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -123,5 +123,6 @@ static inline void tegra_cpu_clock_resume(void) void tegra_periph_reset_deassert(struct clk *c); void tegra_periph_reset_assert(struct clk *c); void tegra_clocks_init(void); +void tegra_clocks_apply_init_table(void); #endif /* __LINUX_CLK_TEGRA_H_ */ -- cgit v1.2.3 From deaf39efbc0829f26ae0b8fbe5de820588982f72 Mon Sep 17 00:00:00 2001 From: Simon Glass Date: Mon, 25 Feb 2013 14:08:36 -0800 Subject: mfd: Add ChromeOS EC messages header This file is included verbatim from the ChromeOS EC respository. Ideally we would prefer to avoid changing it, to make it easier to track this rapidly-changing file. Signed-off-by: Simon Glass Signed-off-by: Che-Liang Chiou Signed-off-by: Vincent Palatin Signed-off-by: Samuel Ortiz --- include/linux/mfd/cros_ec_commands.h | 1369 ++++++++++++++++++++++++++++++++++ 1 file changed, 1369 insertions(+) create mode 100644 include/linux/mfd/cros_ec_commands.h (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h new file mode 100644 index 000000000000..86fd06953bcd --- /dev/null +++ b/include/linux/mfd/cros_ec_commands.h @@ -0,0 +1,1369 @@ +/* + * Host communication command constants for ChromeOS EC + * + * Copyright (C) 2012 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * The ChromeOS EC multi function device is used to mux all the requests + * to the EC device for its multiple features: keyboard controller, + * battery charging and regulator control, firmware update. + * + * NOTE: This file is copied verbatim from the ChromeOS EC Open Source + * project in an attempt to make future updates easy to make. + */ + +#ifndef __CROS_EC_COMMANDS_H +#define __CROS_EC_COMMANDS_H + +/* + * Protocol overview + * + * request: CMD [ P0 P1 P2 ... Pn S ] + * response: ERR [ P0 P1 P2 ... Pn S ] + * + * where the bytes are defined as follow : + * - CMD is the command code. (defined by EC_CMD_ constants) + * - ERR is the error code. (defined by EC_RES_ constants) + * - Px is the optional payload. + * it is not sent if the error code is not success. + * (defined by ec_params_ and ec_response_ structures) + * - S is the checksum which is the sum of all payload bytes. + * + * On LPC, CMD and ERR are sent/received at EC_LPC_ADDR_KERNEL|USER_CMD + * and the payloads are sent/received at EC_LPC_ADDR_KERNEL|USER_PARAM. + * On I2C, all bytes are sent serially in the same message. + */ + +/* Current version of this protocol */ +#define EC_PROTO_VERSION 0x00000002 + +/* Command version mask */ +#define EC_VER_MASK(version) (1UL << (version)) + +/* I/O addresses for ACPI commands */ +#define EC_LPC_ADDR_ACPI_DATA 0x62 +#define EC_LPC_ADDR_ACPI_CMD 0x66 + +/* I/O addresses for host command */ +#define EC_LPC_ADDR_HOST_DATA 0x200 +#define EC_LPC_ADDR_HOST_CMD 0x204 + +/* I/O addresses for host command args and params */ +#define EC_LPC_ADDR_HOST_ARGS 0x800 +#define EC_LPC_ADDR_HOST_PARAM 0x804 +#define EC_HOST_PARAM_SIZE 0x0fc /* Size of param area in bytes */ + +/* I/O addresses for host command params, old interface */ +#define EC_LPC_ADDR_OLD_PARAM 0x880 +#define EC_OLD_PARAM_SIZE 0x080 /* Size of param area in bytes */ + +/* EC command register bit functions */ +#define EC_LPC_CMDR_DATA (1 << 0) /* Data ready for host to read */ +#define EC_LPC_CMDR_PENDING (1 << 1) /* Write pending to EC */ +#define EC_LPC_CMDR_BUSY (1 << 2) /* EC is busy processing a command */ +#define EC_LPC_CMDR_CMD (1 << 3) /* Last host write was a command */ +#define EC_LPC_CMDR_ACPI_BRST (1 << 4) /* Burst mode (not used) */ +#define EC_LPC_CMDR_SCI (1 << 5) /* SCI event is pending */ +#define EC_LPC_CMDR_SMI (1 << 6) /* SMI event is pending */ + +#define EC_LPC_ADDR_MEMMAP 0x900 +#define EC_MEMMAP_SIZE 255 /* ACPI IO buffer max is 255 bytes */ +#define EC_MEMMAP_TEXT_MAX 8 /* Size of a string in the memory map */ + +/* The offset address of each type of data in mapped memory. */ +#define EC_MEMMAP_TEMP_SENSOR 0x00 /* Temp sensors */ +#define EC_MEMMAP_FAN 0x10 /* Fan speeds */ +#define EC_MEMMAP_TEMP_SENSOR_B 0x18 /* Temp sensors (second set) */ +#define EC_MEMMAP_ID 0x20 /* 'E' 'C' */ +#define EC_MEMMAP_ID_VERSION 0x22 /* Version of data in 0x20 - 0x2f */ +#define EC_MEMMAP_THERMAL_VERSION 0x23 /* Version of data in 0x00 - 0x1f */ +#define EC_MEMMAP_BATTERY_VERSION 0x24 /* Version of data in 0x40 - 0x7f */ +#define EC_MEMMAP_SWITCHES_VERSION 0x25 /* Version of data in 0x30 - 0x33 */ +#define EC_MEMMAP_EVENTS_VERSION 0x26 /* Version of data in 0x34 - 0x3f */ +#define EC_MEMMAP_HOST_CMD_FLAGS 0x27 /* Host command interface flags */ +#define EC_MEMMAP_SWITCHES 0x30 +#define EC_MEMMAP_HOST_EVENTS 0x34 +#define EC_MEMMAP_BATT_VOLT 0x40 /* Battery Present Voltage */ +#define EC_MEMMAP_BATT_RATE 0x44 /* Battery Present Rate */ +#define EC_MEMMAP_BATT_CAP 0x48 /* Battery Remaining Capacity */ +#define EC_MEMMAP_BATT_FLAG 0x4c /* Battery State, defined below */ +#define EC_MEMMAP_BATT_DCAP 0x50 /* Battery Design Capacity */ +#define EC_MEMMAP_BATT_DVLT 0x54 /* Battery Design Voltage */ +#define EC_MEMMAP_BATT_LFCC 0x58 /* Battery Last Full Charge Capacity */ +#define EC_MEMMAP_BATT_CCNT 0x5c /* Battery Cycle Count */ +#define EC_MEMMAP_BATT_MFGR 0x60 /* Battery Manufacturer String */ +#define EC_MEMMAP_BATT_MODEL 0x68 /* Battery Model Number String */ +#define EC_MEMMAP_BATT_SERIAL 0x70 /* Battery Serial Number String */ +#define EC_MEMMAP_BATT_TYPE 0x78 /* Battery Type String */ + +/* Number of temp sensors at EC_MEMMAP_TEMP_SENSOR */ +#define EC_TEMP_SENSOR_ENTRIES 16 +/* + * Number of temp sensors at EC_MEMMAP_TEMP_SENSOR_B. + * + * Valid only if EC_MEMMAP_THERMAL_VERSION returns >= 2. + */ +#define EC_TEMP_SENSOR_B_ENTRIES 8 +#define EC_TEMP_SENSOR_NOT_PRESENT 0xff +#define EC_TEMP_SENSOR_ERROR 0xfe +#define EC_TEMP_SENSOR_NOT_POWERED 0xfd +#define EC_TEMP_SENSOR_NOT_CALIBRATED 0xfc +/* + * The offset of temperature value stored in mapped memory. This allows + * reporting a temperature range of 200K to 454K = -73C to 181C. + */ +#define EC_TEMP_SENSOR_OFFSET 200 + +#define EC_FAN_SPEED_ENTRIES 4 /* Number of fans at EC_MEMMAP_FAN */ +#define EC_FAN_SPEED_NOT_PRESENT 0xffff /* Entry not present */ +#define EC_FAN_SPEED_STALLED 0xfffe /* Fan stalled */ + +/* Battery bit flags at EC_MEMMAP_BATT_FLAG. */ +#define EC_BATT_FLAG_AC_PRESENT 0x01 +#define EC_BATT_FLAG_BATT_PRESENT 0x02 +#define EC_BATT_FLAG_DISCHARGING 0x04 +#define EC_BATT_FLAG_CHARGING 0x08 +#define EC_BATT_FLAG_LEVEL_CRITICAL 0x10 + +/* Switch flags at EC_MEMMAP_SWITCHES */ +#define EC_SWITCH_LID_OPEN 0x01 +#define EC_SWITCH_POWER_BUTTON_PRESSED 0x02 +#define EC_SWITCH_WRITE_PROTECT_DISABLED 0x04 +/* Recovery requested via keyboard */ +#define EC_SWITCH_KEYBOARD_RECOVERY 0x08 +/* Recovery requested via dedicated signal (from servo board) */ +#define EC_SWITCH_DEDICATED_RECOVERY 0x10 +/* Was fake developer mode switch; now unused. Remove in next refactor. */ +#define EC_SWITCH_IGNORE0 0x20 + +/* Host command interface flags */ +/* Host command interface supports LPC args (LPC interface only) */ +#define EC_HOST_CMD_FLAG_LPC_ARGS_SUPPORTED 0x01 + +/* Wireless switch flags */ +#define EC_WIRELESS_SWITCH_WLAN 0x01 +#define EC_WIRELESS_SWITCH_BLUETOOTH 0x02 + +/* + * This header file is used in coreboot both in C and ACPI code. The ACPI code + * is pre-processed to handle constants but the ASL compiler is unable to + * handle actual C code so keep it separate. + */ +#ifndef __ACPI__ + +/* LPC command status byte masks */ +/* EC has written a byte in the data register and host hasn't read it yet */ +#define EC_LPC_STATUS_TO_HOST 0x01 +/* Host has written a command/data byte and the EC hasn't read it yet */ +#define EC_LPC_STATUS_FROM_HOST 0x02 +/* EC is processing a command */ +#define EC_LPC_STATUS_PROCESSING 0x04 +/* Last write to EC was a command, not data */ +#define EC_LPC_STATUS_LAST_CMD 0x08 +/* EC is in burst mode. Unsupported by Chrome EC, so this bit is never set */ +#define EC_LPC_STATUS_BURST_MODE 0x10 +/* SCI event is pending (requesting SCI query) */ +#define EC_LPC_STATUS_SCI_PENDING 0x20 +/* SMI event is pending (requesting SMI query) */ +#define EC_LPC_STATUS_SMI_PENDING 0x40 +/* (reserved) */ +#define EC_LPC_STATUS_RESERVED 0x80 + +/* + * EC is busy. This covers both the EC processing a command, and the host has + * written a new command but the EC hasn't picked it up yet. + */ +#define EC_LPC_STATUS_BUSY_MASK \ + (EC_LPC_STATUS_FROM_HOST | EC_LPC_STATUS_PROCESSING) + +/* Host command response codes */ +enum ec_status { + EC_RES_SUCCESS = 0, + EC_RES_INVALID_COMMAND = 1, + EC_RES_ERROR = 2, + EC_RES_INVALID_PARAM = 3, + EC_RES_ACCESS_DENIED = 4, + EC_RES_INVALID_RESPONSE = 5, + EC_RES_INVALID_VERSION = 6, + EC_RES_INVALID_CHECKSUM = 7, + EC_RES_IN_PROGRESS = 8, /* Accepted, command in progress */ + EC_RES_UNAVAILABLE = 9, /* No response available */ + EC_RES_TIMEOUT = 10, /* We got a timeout */ + EC_RES_OVERFLOW = 11, /* Table / data overflow */ +}; + +/* + * Host event codes. Note these are 1-based, not 0-based, because ACPI query + * EC command uses code 0 to mean "no event pending". We explicitly specify + * each value in the enum listing so they won't change if we delete/insert an + * item or rearrange the list (it needs to be stable across platforms, not + * just within a single compiled instance). + */ +enum host_event_code { + EC_HOST_EVENT_LID_CLOSED = 1, + EC_HOST_EVENT_LID_OPEN = 2, + EC_HOST_EVENT_POWER_BUTTON = 3, + EC_HOST_EVENT_AC_CONNECTED = 4, + EC_HOST_EVENT_AC_DISCONNECTED = 5, + EC_HOST_EVENT_BATTERY_LOW = 6, + EC_HOST_EVENT_BATTERY_CRITICAL = 7, + EC_HOST_EVENT_BATTERY = 8, + EC_HOST_EVENT_THERMAL_THRESHOLD = 9, + EC_HOST_EVENT_THERMAL_OVERLOAD = 10, + EC_HOST_EVENT_THERMAL = 11, + EC_HOST_EVENT_USB_CHARGER = 12, + EC_HOST_EVENT_KEY_PRESSED = 13, + /* + * EC has finished initializing the host interface. The host can check + * for this event following sending a EC_CMD_REBOOT_EC command to + * determine when the EC is ready to accept subsequent commands. + */ + EC_HOST_EVENT_INTERFACE_READY = 14, + /* Keyboard recovery combo has been pressed */ + EC_HOST_EVENT_KEYBOARD_RECOVERY = 15, + + /* Shutdown due to thermal overload */ + EC_HOST_EVENT_THERMAL_SHUTDOWN = 16, + /* Shutdown due to battery level too low */ + EC_HOST_EVENT_BATTERY_SHUTDOWN = 17, + + /* + * The high bit of the event mask is not used as a host event code. If + * it reads back as set, then the entire event mask should be + * considered invalid by the host. This can happen when reading the + * raw event status via EC_MEMMAP_HOST_EVENTS but the LPC interface is + * not initialized on the EC, or improperly configured on the host. + */ + EC_HOST_EVENT_INVALID = 32 +}; +/* Host event mask */ +#define EC_HOST_EVENT_MASK(event_code) (1UL << ((event_code) - 1)) + +/* Arguments at EC_LPC_ADDR_HOST_ARGS */ +struct ec_lpc_host_args { + uint8_t flags; + uint8_t command_version; + uint8_t data_size; + /* + * Checksum; sum of command + flags + command_version + data_size + + * all params/response data bytes. + */ + uint8_t checksum; +} __packed; + +/* Flags for ec_lpc_host_args.flags */ +/* + * Args are from host. Data area at EC_LPC_ADDR_HOST_PARAM contains command + * params. + * + * If EC gets a command and this flag is not set, this is an old-style command. + * Command version is 0 and params from host are at EC_LPC_ADDR_OLD_PARAM with + * unknown length. EC must respond with an old-style response (that is, + * withouth setting EC_HOST_ARGS_FLAG_TO_HOST). + */ +#define EC_HOST_ARGS_FLAG_FROM_HOST 0x01 +/* + * Args are from EC. Data area at EC_LPC_ADDR_HOST_PARAM contains response. + * + * If EC responds to a command and this flag is not set, this is an old-style + * response. Command version is 0 and response data from EC is at + * EC_LPC_ADDR_OLD_PARAM with unknown length. + */ +#define EC_HOST_ARGS_FLAG_TO_HOST 0x02 + +/* + * Notes on commands: + * + * Each command is an 8-byte command value. Commands which take params or + * return response data specify structs for that data. If no struct is + * specified, the command does not input or output data, respectively. + * Parameter/response length is implicit in the structs. Some underlying + * communication protocols (I2C, SPI) may add length or checksum headers, but + * those are implementation-dependent and not defined here. + */ + +/*****************************************************************************/ +/* General / test commands */ + +/* + * Get protocol version, used to deal with non-backward compatible protocol + * changes. + */ +#define EC_CMD_PROTO_VERSION 0x00 + +struct ec_response_proto_version { + uint32_t version; +} __packed; + +/* + * Hello. This is a simple command to test the EC is responsive to + * commands. + */ +#define EC_CMD_HELLO 0x01 + +struct ec_params_hello { + uint32_t in_data; /* Pass anything here */ +} __packed; + +struct ec_response_hello { + uint32_t out_data; /* Output will be in_data + 0x01020304 */ +} __packed; + +/* Get version number */ +#define EC_CMD_GET_VERSION 0x02 + +enum ec_current_image { + EC_IMAGE_UNKNOWN = 0, + EC_IMAGE_RO, + EC_IMAGE_RW +}; + +struct ec_response_get_version { + /* Null-terminated version strings for RO, RW */ + char version_string_ro[32]; + char version_string_rw[32]; + char reserved[32]; /* Was previously RW-B string */ + uint32_t current_image; /* One of ec_current_image */ +} __packed; + +/* Read test */ +#define EC_CMD_READ_TEST 0x03 + +struct ec_params_read_test { + uint32_t offset; /* Starting value for read buffer */ + uint32_t size; /* Size to read in bytes */ +} __packed; + +struct ec_response_read_test { + uint32_t data[32]; +} __packed; + +/* + * Get build information + * + * Response is null-terminated string. + */ +#define EC_CMD_GET_BUILD_INFO 0x04 + +/* Get chip info */ +#define EC_CMD_GET_CHIP_INFO 0x05 + +struct ec_response_get_chip_info { + /* Null-terminated strings */ + char vendor[32]; + char name[32]; + char revision[32]; /* Mask version */ +} __packed; + +/* Get board HW version */ +#define EC_CMD_GET_BOARD_VERSION 0x06 + +struct ec_response_board_version { + uint16_t board_version; /* A monotonously incrementing number. */ +} __packed; + +/* + * Read memory-mapped data. + * + * This is an alternate interface to memory-mapped data for bus protocols + * which don't support direct-mapped memory - I2C, SPI, etc. + * + * Response is params.size bytes of data. + */ +#define EC_CMD_READ_MEMMAP 0x07 + +struct ec_params_read_memmap { + uint8_t offset; /* Offset in memmap (EC_MEMMAP_*) */ + uint8_t size; /* Size to read in bytes */ +} __packed; + +/* Read versions supported for a command */ +#define EC_CMD_GET_CMD_VERSIONS 0x08 + +struct ec_params_get_cmd_versions { + uint8_t cmd; /* Command to check */ +} __packed; + +struct ec_response_get_cmd_versions { + /* + * Mask of supported versions; use EC_VER_MASK() to compare with a + * desired version. + */ + uint32_t version_mask; +} __packed; + +/* + * Check EC communcations status (busy). This is needed on i2c/spi but not + * on lpc since it has its own out-of-band busy indicator. + * + * lpc must read the status from the command register. Attempting this on + * lpc will overwrite the args/parameter space and corrupt its data. + */ +#define EC_CMD_GET_COMMS_STATUS 0x09 + +/* Avoid using ec_status which is for return values */ +enum ec_comms_status { + EC_COMMS_STATUS_PROCESSING = 1 << 0, /* Processing cmd */ +}; + +struct ec_response_get_comms_status { + uint32_t flags; /* Mask of enum ec_comms_status */ +} __packed; + + +/*****************************************************************************/ +/* Flash commands */ + +/* Get flash info */ +#define EC_CMD_FLASH_INFO 0x10 + +struct ec_response_flash_info { + /* Usable flash size, in bytes */ + uint32_t flash_size; + /* + * Write block size. Write offset and size must be a multiple + * of this. + */ + uint32_t write_block_size; + /* + * Erase block size. Erase offset and size must be a multiple + * of this. + */ + uint32_t erase_block_size; + /* + * Protection block size. Protection offset and size must be a + * multiple of this. + */ + uint32_t protect_block_size; +} __packed; + +/* + * Read flash + * + * Response is params.size bytes of data. + */ +#define EC_CMD_FLASH_READ 0x11 + +struct ec_params_flash_read { + uint32_t offset; /* Byte offset to read */ + uint32_t size; /* Size to read in bytes */ +} __packed; + +/* Write flash */ +#define EC_CMD_FLASH_WRITE 0x12 + +struct ec_params_flash_write { + uint32_t offset; /* Byte offset to write */ + uint32_t size; /* Size to write in bytes */ + /* + * Data to write. Could really use EC_PARAM_SIZE - 8, but tidiest to + * use a power of 2 so writes stay aligned. + */ + uint8_t data[64]; +} __packed; + +/* Erase flash */ +#define EC_CMD_FLASH_ERASE 0x13 + +struct ec_params_flash_erase { + uint32_t offset; /* Byte offset to erase */ + uint32_t size; /* Size to erase in bytes */ +} __packed; + +/* + * Get/set flash protection. + * + * If mask!=0, sets/clear the requested bits of flags. Depending on the + * firmware write protect GPIO, not all flags will take effect immediately; + * some flags require a subsequent hard reset to take effect. Check the + * returned flags bits to see what actually happened. + * + * If mask=0, simply returns the current flags state. + */ +#define EC_CMD_FLASH_PROTECT 0x15 +#define EC_VER_FLASH_PROTECT 1 /* Command version 1 */ + +/* Flags for flash protection */ +/* RO flash code protected when the EC boots */ +#define EC_FLASH_PROTECT_RO_AT_BOOT (1 << 0) +/* + * RO flash code protected now. If this bit is set, at-boot status cannot + * be changed. + */ +#define EC_FLASH_PROTECT_RO_NOW (1 << 1) +/* Entire flash code protected now, until reboot. */ +#define EC_FLASH_PROTECT_ALL_NOW (1 << 2) +/* Flash write protect GPIO is asserted now */ +#define EC_FLASH_PROTECT_GPIO_ASSERTED (1 << 3) +/* Error - at least one bank of flash is stuck locked, and cannot be unlocked */ +#define EC_FLASH_PROTECT_ERROR_STUCK (1 << 4) +/* + * Error - flash protection is in inconsistent state. At least one bank of + * flash which should be protected is not protected. Usually fixed by + * re-requesting the desired flags, or by a hard reset if that fails. + */ +#define EC_FLASH_PROTECT_ERROR_INCONSISTENT (1 << 5) +/* Entile flash code protected when the EC boots */ +#define EC_FLASH_PROTECT_ALL_AT_BOOT (1 << 6) + +struct ec_params_flash_protect { + uint32_t mask; /* Bits in flags to apply */ + uint32_t flags; /* New flags to apply */ +} __packed; + +struct ec_response_flash_protect { + /* Current value of flash protect flags */ + uint32_t flags; + /* + * Flags which are valid on this platform. This allows the caller + * to distinguish between flags which aren't set vs. flags which can't + * be set on this platform. + */ + uint32_t valid_flags; + /* Flags which can be changed given the current protection state */ + uint32_t writable_flags; +} __packed; + +/* + * Note: commands 0x14 - 0x19 version 0 were old commands to get/set flash + * write protect. These commands may be reused with version > 0. + */ + +/* Get the region offset/size */ +#define EC_CMD_FLASH_REGION_INFO 0x16 +#define EC_VER_FLASH_REGION_INFO 1 + +enum ec_flash_region { + /* Region which holds read-only EC image */ + EC_FLASH_REGION_RO, + /* Region which holds rewritable EC image */ + EC_FLASH_REGION_RW, + /* + * Region which should be write-protected in the factory (a superset of + * EC_FLASH_REGION_RO) + */ + EC_FLASH_REGION_WP_RO, +}; + +struct ec_params_flash_region_info { + uint32_t region; /* enum ec_flash_region */ +} __packed; + +struct ec_response_flash_region_info { + uint32_t offset; + uint32_t size; +} __packed; + +/* Read/write VbNvContext */ +#define EC_CMD_VBNV_CONTEXT 0x17 +#define EC_VER_VBNV_CONTEXT 1 +#define EC_VBNV_BLOCK_SIZE 16 + +enum ec_vbnvcontext_op { + EC_VBNV_CONTEXT_OP_READ, + EC_VBNV_CONTEXT_OP_WRITE, +}; + +struct ec_params_vbnvcontext { + uint32_t op; + uint8_t block[EC_VBNV_BLOCK_SIZE]; +} __packed; + +struct ec_response_vbnvcontext { + uint8_t block[EC_VBNV_BLOCK_SIZE]; +} __packed; + +/*****************************************************************************/ +/* PWM commands */ + +/* Get fan target RPM */ +#define EC_CMD_PWM_GET_FAN_TARGET_RPM 0x20 + +struct ec_response_pwm_get_fan_rpm { + uint32_t rpm; +} __packed; + +/* Set target fan RPM */ +#define EC_CMD_PWM_SET_FAN_TARGET_RPM 0x21 + +struct ec_params_pwm_set_fan_target_rpm { + uint32_t rpm; +} __packed; + +/* Get keyboard backlight */ +#define EC_CMD_PWM_GET_KEYBOARD_BACKLIGHT 0x22 + +struct ec_response_pwm_get_keyboard_backlight { + uint8_t percent; + uint8_t enabled; +} __packed; + +/* Set keyboard backlight */ +#define EC_CMD_PWM_SET_KEYBOARD_BACKLIGHT 0x23 + +struct ec_params_pwm_set_keyboard_backlight { + uint8_t percent; +} __packed; + +/* Set target fan PWM duty cycle */ +#define EC_CMD_PWM_SET_FAN_DUTY 0x24 + +struct ec_params_pwm_set_fan_duty { + uint32_t percent; +} __packed; + +/*****************************************************************************/ +/* + * Lightbar commands. This looks worse than it is. Since we only use one HOST + * command to say "talk to the lightbar", we put the "and tell it to do X" part + * into a subcommand. We'll make separate structs for subcommands with + * different input args, so that we know how much to expect. + */ +#define EC_CMD_LIGHTBAR_CMD 0x28 + +struct rgb_s { + uint8_t r, g, b; +}; + +#define LB_BATTERY_LEVELS 4 +/* List of tweakable parameters. NOTE: It's __packed so it can be sent in a + * host command, but the alignment is the same regardless. Keep it that way. + */ +struct lightbar_params { + /* Timing */ + int google_ramp_up; + int google_ramp_down; + int s3s0_ramp_up; + int s0_tick_delay[2]; /* AC=0/1 */ + int s0a_tick_delay[2]; /* AC=0/1 */ + int s0s3_ramp_down; + int s3_sleep_for; + int s3_ramp_up; + int s3_ramp_down; + + /* Oscillation */ + uint8_t new_s0; + uint8_t osc_min[2]; /* AC=0/1 */ + uint8_t osc_max[2]; /* AC=0/1 */ + uint8_t w_ofs[2]; /* AC=0/1 */ + + /* Brightness limits based on the backlight and AC. */ + uint8_t bright_bl_off_fixed[2]; /* AC=0/1 */ + uint8_t bright_bl_on_min[2]; /* AC=0/1 */ + uint8_t bright_bl_on_max[2]; /* AC=0/1 */ + + /* Battery level thresholds */ + uint8_t battery_threshold[LB_BATTERY_LEVELS - 1]; + + /* Map [AC][battery_level] to color index */ + uint8_t s0_idx[2][LB_BATTERY_LEVELS]; /* AP is running */ + uint8_t s3_idx[2][LB_BATTERY_LEVELS]; /* AP is sleeping */ + + /* Color palette */ + struct rgb_s color[8]; /* 0-3 are Google colors */ +} __packed; + +struct ec_params_lightbar { + uint8_t cmd; /* Command (see enum lightbar_command) */ + union { + struct { + /* no args */ + } dump, off, on, init, get_seq, get_params; + + struct num { + uint8_t num; + } brightness, seq, demo; + + struct reg { + uint8_t ctrl, reg, value; + } reg; + + struct rgb { + uint8_t led, red, green, blue; + } rgb; + + struct lightbar_params set_params; + }; +} __packed; + +struct ec_response_lightbar { + union { + struct dump { + struct { + uint8_t reg; + uint8_t ic0; + uint8_t ic1; + } vals[23]; + } dump; + + struct get_seq { + uint8_t num; + } get_seq; + + struct lightbar_params get_params; + + struct { + /* no return params */ + } off, on, init, brightness, seq, reg, rgb, demo, set_params; + }; +} __packed; + +/* Lightbar commands */ +enum lightbar_command { + LIGHTBAR_CMD_DUMP = 0, + LIGHTBAR_CMD_OFF = 1, + LIGHTBAR_CMD_ON = 2, + LIGHTBAR_CMD_INIT = 3, + LIGHTBAR_CMD_BRIGHTNESS = 4, + LIGHTBAR_CMD_SEQ = 5, + LIGHTBAR_CMD_REG = 6, + LIGHTBAR_CMD_RGB = 7, + LIGHTBAR_CMD_GET_SEQ = 8, + LIGHTBAR_CMD_DEMO = 9, + LIGHTBAR_CMD_GET_PARAMS = 10, + LIGHTBAR_CMD_SET_PARAMS = 11, + LIGHTBAR_NUM_CMDS +}; + +/*****************************************************************************/ +/* Verified boot commands */ + +/* + * Note: command code 0x29 version 0 was VBOOT_CMD in Link EVT; it may be + * reused for other purposes with version > 0. + */ + +/* Verified boot hash command */ +#define EC_CMD_VBOOT_HASH 0x2A + +struct ec_params_vboot_hash { + uint8_t cmd; /* enum ec_vboot_hash_cmd */ + uint8_t hash_type; /* enum ec_vboot_hash_type */ + uint8_t nonce_size; /* Nonce size; may be 0 */ + uint8_t reserved0; /* Reserved; set 0 */ + uint32_t offset; /* Offset in flash to hash */ + uint32_t size; /* Number of bytes to hash */ + uint8_t nonce_data[64]; /* Nonce data; ignored if nonce_size=0 */ +} __packed; + +struct ec_response_vboot_hash { + uint8_t status; /* enum ec_vboot_hash_status */ + uint8_t hash_type; /* enum ec_vboot_hash_type */ + uint8_t digest_size; /* Size of hash digest in bytes */ + uint8_t reserved0; /* Ignore; will be 0 */ + uint32_t offset; /* Offset in flash which was hashed */ + uint32_t size; /* Number of bytes hashed */ + uint8_t hash_digest[64]; /* Hash digest data */ +} __packed; + +enum ec_vboot_hash_cmd { + EC_VBOOT_HASH_GET = 0, /* Get current hash status */ + EC_VBOOT_HASH_ABORT = 1, /* Abort calculating current hash */ + EC_VBOOT_HASH_START = 2, /* Start computing a new hash */ + EC_VBOOT_HASH_RECALC = 3, /* Synchronously compute a new hash */ +}; + +enum ec_vboot_hash_type { + EC_VBOOT_HASH_TYPE_SHA256 = 0, /* SHA-256 */ +}; + +enum ec_vboot_hash_status { + EC_VBOOT_HASH_STATUS_NONE = 0, /* No hash (not started, or aborted) */ + EC_VBOOT_HASH_STATUS_DONE = 1, /* Finished computing a hash */ + EC_VBOOT_HASH_STATUS_BUSY = 2, /* Busy computing a hash */ +}; + +/* + * Special values for offset for EC_VBOOT_HASH_START and EC_VBOOT_HASH_RECALC. + * If one of these is specified, the EC will automatically update offset and + * size to the correct values for the specified image (RO or RW). + */ +#define EC_VBOOT_HASH_OFFSET_RO 0xfffffffe +#define EC_VBOOT_HASH_OFFSET_RW 0xfffffffd + +/*****************************************************************************/ +/* USB charging control commands */ + +/* Set USB port charging mode */ +#define EC_CMD_USB_CHARGE_SET_MODE 0x30 + +struct ec_params_usb_charge_set_mode { + uint8_t usb_port_id; + uint8_t mode; +} __packed; + +/*****************************************************************************/ +/* Persistent storage for host */ + +/* Maximum bytes that can be read/written in a single command */ +#define EC_PSTORE_SIZE_MAX 64 + +/* Get persistent storage info */ +#define EC_CMD_PSTORE_INFO 0x40 + +struct ec_response_pstore_info { + /* Persistent storage size, in bytes */ + uint32_t pstore_size; + /* Access size; read/write offset and size must be a multiple of this */ + uint32_t access_size; +} __packed; + +/* + * Read persistent storage + * + * Response is params.size bytes of data. + */ +#define EC_CMD_PSTORE_READ 0x41 + +struct ec_params_pstore_read { + uint32_t offset; /* Byte offset to read */ + uint32_t size; /* Size to read in bytes */ +} __packed; + +/* Write persistent storage */ +#define EC_CMD_PSTORE_WRITE 0x42 + +struct ec_params_pstore_write { + uint32_t offset; /* Byte offset to write */ + uint32_t size; /* Size to write in bytes */ + uint8_t data[EC_PSTORE_SIZE_MAX]; +} __packed; + +/*****************************************************************************/ +/* Real-time clock */ + +/* RTC params and response structures */ +struct ec_params_rtc { + uint32_t time; +} __packed; + +struct ec_response_rtc { + uint32_t time; +} __packed; + +/* These use ec_response_rtc */ +#define EC_CMD_RTC_GET_VALUE 0x44 +#define EC_CMD_RTC_GET_ALARM 0x45 + +/* These all use ec_params_rtc */ +#define EC_CMD_RTC_SET_VALUE 0x46 +#define EC_CMD_RTC_SET_ALARM 0x47 + +/*****************************************************************************/ +/* Port80 log access */ + +/* Get last port80 code from previous boot */ +#define EC_CMD_PORT80_LAST_BOOT 0x48 + +struct ec_response_port80_last_boot { + uint16_t code; +} __packed; + +/*****************************************************************************/ +/* Thermal engine commands */ + +/* Set thershold value */ +#define EC_CMD_THERMAL_SET_THRESHOLD 0x50 + +struct ec_params_thermal_set_threshold { + uint8_t sensor_type; + uint8_t threshold_id; + uint16_t value; +} __packed; + +/* Get threshold value */ +#define EC_CMD_THERMAL_GET_THRESHOLD 0x51 + +struct ec_params_thermal_get_threshold { + uint8_t sensor_type; + uint8_t threshold_id; +} __packed; + +struct ec_response_thermal_get_threshold { + uint16_t value; +} __packed; + +/* Toggle automatic fan control */ +#define EC_CMD_THERMAL_AUTO_FAN_CTRL 0x52 + +/* Get TMP006 calibration data */ +#define EC_CMD_TMP006_GET_CALIBRATION 0x53 + +struct ec_params_tmp006_get_calibration { + uint8_t index; +} __packed; + +struct ec_response_tmp006_get_calibration { + float s0; + float b0; + float b1; + float b2; +} __packed; + +/* Set TMP006 calibration data */ +#define EC_CMD_TMP006_SET_CALIBRATION 0x54 + +struct ec_params_tmp006_set_calibration { + uint8_t index; + uint8_t reserved[3]; /* Reserved; set 0 */ + float s0; + float b0; + float b1; + float b2; +} __packed; + +/*****************************************************************************/ +/* MKBP - Matrix KeyBoard Protocol */ + +/* + * Read key state + * + * Returns raw data for keyboard cols; see ec_response_mkbp_info.cols for + * expected response size. + */ +#define EC_CMD_MKBP_STATE 0x60 + +/* Provide information about the matrix : number of rows and columns */ +#define EC_CMD_MKBP_INFO 0x61 + +struct ec_response_mkbp_info { + uint32_t rows; + uint32_t cols; + uint8_t switches; +} __packed; + +/* Simulate key press */ +#define EC_CMD_MKBP_SIMULATE_KEY 0x62 + +struct ec_params_mkbp_simulate_key { + uint8_t col; + uint8_t row; + uint8_t pressed; +} __packed; + +/* Configure keyboard scanning */ +#define EC_CMD_MKBP_SET_CONFIG 0x64 +#define EC_CMD_MKBP_GET_CONFIG 0x65 + +/* flags */ +enum mkbp_config_flags { + EC_MKBP_FLAGS_ENABLE = 1, /* Enable keyboard scanning */ +}; + +enum mkbp_config_valid { + EC_MKBP_VALID_SCAN_PERIOD = 1 << 0, + EC_MKBP_VALID_POLL_TIMEOUT = 1 << 1, + EC_MKBP_VALID_MIN_POST_SCAN_DELAY = 1 << 3, + EC_MKBP_VALID_OUTPUT_SETTLE = 1 << 4, + EC_MKBP_VALID_DEBOUNCE_DOWN = 1 << 5, + EC_MKBP_VALID_DEBOUNCE_UP = 1 << 6, + EC_MKBP_VALID_FIFO_MAX_DEPTH = 1 << 7, +}; + +/* Configuration for our key scanning algorithm */ +struct ec_mkbp_config { + uint32_t valid_mask; /* valid fields */ + uint8_t flags; /* some flags (enum mkbp_config_flags) */ + uint8_t valid_flags; /* which flags are valid */ + uint16_t scan_period_us; /* period between start of scans */ + /* revert to interrupt mode after no activity for this long */ + uint32_t poll_timeout_us; + /* + * minimum post-scan relax time. Once we finish a scan we check + * the time until we are due to start the next one. If this time is + * shorter this field, we use this instead. + */ + uint16_t min_post_scan_delay_us; + /* delay between setting up output and waiting for it to settle */ + uint16_t output_settle_us; + uint16_t debounce_down_us; /* time for debounce on key down */ + uint16_t debounce_up_us; /* time for debounce on key up */ + /* maximum depth to allow for fifo (0 = no keyscan output) */ + uint8_t fifo_max_depth; +} __packed; + +struct ec_params_mkbp_set_config { + struct ec_mkbp_config config; +} __packed; + +struct ec_response_mkbp_get_config { + struct ec_mkbp_config config; +} __packed; + +/* Run the key scan emulation */ +#define EC_CMD_KEYSCAN_SEQ_CTRL 0x66 + +enum ec_keyscan_seq_cmd { + EC_KEYSCAN_SEQ_STATUS = 0, /* Get status information */ + EC_KEYSCAN_SEQ_CLEAR = 1, /* Clear sequence */ + EC_KEYSCAN_SEQ_ADD = 2, /* Add item to sequence */ + EC_KEYSCAN_SEQ_START = 3, /* Start running sequence */ + EC_KEYSCAN_SEQ_COLLECT = 4, /* Collect sequence summary data */ +}; + +enum ec_collect_flags { + /* + * Indicates this scan was processed by the EC. Due to timing, some + * scans may be skipped. + */ + EC_KEYSCAN_SEQ_FLAG_DONE = 1 << 0, +}; + +struct ec_collect_item { + uint8_t flags; /* some flags (enum ec_collect_flags) */ +}; + +struct ec_params_keyscan_seq_ctrl { + uint8_t cmd; /* Command to send (enum ec_keyscan_seq_cmd) */ + union { + struct { + uint8_t active; /* still active */ + uint8_t num_items; /* number of items */ + /* Current item being presented */ + uint8_t cur_item; + } status; + struct { + /* + * Absolute time for this scan, measured from the + * start of the sequence. + */ + uint32_t time_us; + uint8_t scan[0]; /* keyscan data */ + } add; + struct { + uint8_t start_item; /* First item to return */ + uint8_t num_items; /* Number of items to return */ + } collect; + }; +} __packed; + +struct ec_result_keyscan_seq_ctrl { + union { + struct { + uint8_t num_items; /* Number of items */ + /* Data for each item */ + struct ec_collect_item item[0]; + } collect; + }; +} __packed; + +/*****************************************************************************/ +/* Temperature sensor commands */ + +/* Read temperature sensor info */ +#define EC_CMD_TEMP_SENSOR_GET_INFO 0x70 + +struct ec_params_temp_sensor_get_info { + uint8_t id; +} __packed; + +struct ec_response_temp_sensor_get_info { + char sensor_name[32]; + uint8_t sensor_type; +} __packed; + +/*****************************************************************************/ + +/* + * Note: host commands 0x80 - 0x87 are reserved to avoid conflict with ACPI + * commands accidentally sent to the wrong interface. See the ACPI section + * below. + */ + +/*****************************************************************************/ +/* Host event commands */ + +/* + * Host event mask params and response structures, shared by all of the host + * event commands below. + */ +struct ec_params_host_event_mask { + uint32_t mask; +} __packed; + +struct ec_response_host_event_mask { + uint32_t mask; +} __packed; + +/* These all use ec_response_host_event_mask */ +#define EC_CMD_HOST_EVENT_GET_B 0x87 +#define EC_CMD_HOST_EVENT_GET_SMI_MASK 0x88 +#define EC_CMD_HOST_EVENT_GET_SCI_MASK 0x89 +#define EC_CMD_HOST_EVENT_GET_WAKE_MASK 0x8d + +/* These all use ec_params_host_event_mask */ +#define EC_CMD_HOST_EVENT_SET_SMI_MASK 0x8a +#define EC_CMD_HOST_EVENT_SET_SCI_MASK 0x8b +#define EC_CMD_HOST_EVENT_CLEAR 0x8c +#define EC_CMD_HOST_EVENT_SET_WAKE_MASK 0x8e +#define EC_CMD_HOST_EVENT_CLEAR_B 0x8f + +/*****************************************************************************/ +/* Switch commands */ + +/* Enable/disable LCD backlight */ +#define EC_CMD_SWITCH_ENABLE_BKLIGHT 0x90 + +struct ec_params_switch_enable_backlight { + uint8_t enabled; +} __packed; + +/* Enable/disable WLAN/Bluetooth */ +#define EC_CMD_SWITCH_ENABLE_WIRELESS 0x91 + +struct ec_params_switch_enable_wireless { + uint8_t enabled; +} __packed; + +/*****************************************************************************/ +/* GPIO commands. Only available on EC if write protect has been disabled. */ + +/* Set GPIO output value */ +#define EC_CMD_GPIO_SET 0x92 + +struct ec_params_gpio_set { + char name[32]; + uint8_t val; +} __packed; + +/* Get GPIO value */ +#define EC_CMD_GPIO_GET 0x93 + +struct ec_params_gpio_get { + char name[32]; +} __packed; +struct ec_response_gpio_get { + uint8_t val; +} __packed; + +/*****************************************************************************/ +/* I2C commands. Only available when flash write protect is unlocked. */ + +/* Read I2C bus */ +#define EC_CMD_I2C_READ 0x94 + +struct ec_params_i2c_read { + uint16_t addr; + uint8_t read_size; /* Either 8 or 16. */ + uint8_t port; + uint8_t offset; +} __packed; +struct ec_response_i2c_read { + uint16_t data; +} __packed; + +/* Write I2C bus */ +#define EC_CMD_I2C_WRITE 0x95 + +struct ec_params_i2c_write { + uint16_t data; + uint16_t addr; + uint8_t write_size; /* Either 8 or 16. */ + uint8_t port; + uint8_t offset; +} __packed; + +/*****************************************************************************/ +/* Charge state commands. Only available when flash write protect unlocked. */ + +/* Force charge state machine to stop in idle mode */ +#define EC_CMD_CHARGE_FORCE_IDLE 0x96 + +struct ec_params_force_idle { + uint8_t enabled; +} __packed; + +/*****************************************************************************/ +/* Console commands. Only available when flash write protect is unlocked. */ + +/* Snapshot console output buffer for use by EC_CMD_CONSOLE_READ. */ +#define EC_CMD_CONSOLE_SNAPSHOT 0x97 + +/* + * Read next chunk of data from saved snapshot. + * + * Response is null-terminated string. Empty string, if there is no more + * remaining output. + */ +#define EC_CMD_CONSOLE_READ 0x98 + +/*****************************************************************************/ + +/* + * Cut off battery power output if the battery supports. + * + * For unsupported battery, just don't implement this command and lets EC + * return EC_RES_INVALID_COMMAND. + */ +#define EC_CMD_BATTERY_CUT_OFF 0x99 + +/*****************************************************************************/ +/* Temporary debug commands. TODO: remove this crosbug.com/p/13849 */ + +/* + * Dump charge state machine context. + * + * Response is a binary dump of charge state machine context. + */ +#define EC_CMD_CHARGE_DUMP 0xa0 + +/* + * Set maximum battery charging current. + */ +#define EC_CMD_CHARGE_CURRENT_LIMIT 0xa1 + +struct ec_params_current_limit { + uint32_t limit; +} __packed; + +/*****************************************************************************/ +/* System commands */ + +/* + * TODO: this is a confusing name, since it doesn't necessarily reboot the EC. + * Rename to "set image" or something similar. + */ +#define EC_CMD_REBOOT_EC 0xd2 + +/* Command */ +enum ec_reboot_cmd { + EC_REBOOT_CANCEL = 0, /* Cancel a pending reboot */ + EC_REBOOT_JUMP_RO = 1, /* Jump to RO without rebooting */ + EC_REBOOT_JUMP_RW = 2, /* Jump to RW without rebooting */ + /* (command 3 was jump to RW-B) */ + EC_REBOOT_COLD = 4, /* Cold-reboot */ + EC_REBOOT_DISABLE_JUMP = 5, /* Disable jump until next reboot */ + EC_REBOOT_HIBERNATE = 6 /* Hibernate EC */ +}; + +/* Flags for ec_params_reboot_ec.reboot_flags */ +#define EC_REBOOT_FLAG_RESERVED0 (1 << 0) /* Was recovery request */ +#define EC_REBOOT_FLAG_ON_AP_SHUTDOWN (1 << 1) /* Reboot after AP shutdown */ + +struct ec_params_reboot_ec { + uint8_t cmd; /* enum ec_reboot_cmd */ + uint8_t flags; /* See EC_REBOOT_FLAG_* */ +} __packed; + +/* + * Get information on last EC panic. + * + * Returns variable-length platform-dependent panic information. See panic.h + * for details. + */ +#define EC_CMD_GET_PANIC_INFO 0xd3 + +/*****************************************************************************/ +/* + * ACPI commands + * + * These are valid ONLY on the ACPI command/data port. + */ + +/* + * ACPI Read Embedded Controller + * + * This reads from ACPI memory space on the EC (EC_ACPI_MEM_*). + * + * Use the following sequence: + * + * - Write EC_CMD_ACPI_READ to EC_LPC_ADDR_ACPI_CMD + * - Wait for EC_LPC_CMDR_PENDING bit to clear + * - Write address to EC_LPC_ADDR_ACPI_DATA + * - Wait for EC_LPC_CMDR_DATA bit to set + * - Read value from EC_LPC_ADDR_ACPI_DATA + */ +#define EC_CMD_ACPI_READ 0x80 + +/* + * ACPI Write Embedded Controller + * + * This reads from ACPI memory space on the EC (EC_ACPI_MEM_*). + * + * Use the following sequence: + * + * - Write EC_CMD_ACPI_WRITE to EC_LPC_ADDR_ACPI_CMD + * - Wait for EC_LPC_CMDR_PENDING bit to clear + * - Write address to EC_LPC_ADDR_ACPI_DATA + * - Wait for EC_LPC_CMDR_PENDING bit to clear + * - Write value to EC_LPC_ADDR_ACPI_DATA + */ +#define EC_CMD_ACPI_WRITE 0x81 + +/* + * ACPI Query Embedded Controller + * + * This clears the lowest-order bit in the currently pending host events, and + * sets the result code to the 1-based index of the bit (event 0x00000001 = 1, + * event 0x80000000 = 32), or 0 if no event was pending. + */ +#define EC_CMD_ACPI_QUERY_EVENT 0x84 + +/* Valid addresses in ACPI memory space, for read/write commands */ +/* Memory space version; set to EC_ACPI_MEM_VERSION_CURRENT */ +#define EC_ACPI_MEM_VERSION 0x00 +/* + * Test location; writing value here updates test compliment byte to (0xff - + * value). + */ +#define EC_ACPI_MEM_TEST 0x01 +/* Test compliment; writes here are ignored. */ +#define EC_ACPI_MEM_TEST_COMPLIMENT 0x02 +/* Keyboard backlight brightness percent (0 - 100) */ +#define EC_ACPI_MEM_KEYBOARD_BACKLIGHT 0x03 + +/* Current version of ACPI memory address space */ +#define EC_ACPI_MEM_VERSION_CURRENT 1 + + +/*****************************************************************************/ +/* + * Special commands + * + * These do not follow the normal rules for commands. See each command for + * details. + */ + +/* + * Reboot NOW + * + * This command will work even when the EC LPC interface is busy, because the + * reboot command is processed at interrupt level. Note that when the EC + * reboots, the host will reboot too, so there is no response to this command. + * + * Use EC_CMD_REBOOT_EC to reboot the EC more politely. + */ +#define EC_CMD_REBOOT 0xd1 /* Think "die" */ + +/* + * Resend last response (not supported on LPC). + * + * Returns EC_RES_UNAVAILABLE if there is no response available - for example, + * there was no previous command, or the previous command's response was too + * big to save. + */ +#define EC_CMD_RESEND_RESPONSE 0xdb + +/* + * This header byte on a command indicate version 0. Any header byte less + * than this means that we are talking to an old EC which doesn't support + * versioning. In that case, we assume version 0. + * + * Header bytes greater than this indicate a later version. For example, + * EC_CMD_VERSION0 + 1 means we are using version 1. + * + * The old EC interface must not use commands 0dc or higher. + */ +#define EC_CMD_VERSION0 0xdc + +#endif /* !__ACPI__ */ + +#endif /* __CROS_EC_COMMANDS_H */ -- cgit v1.2.3 From 4ab6174e8cdb007cf500e484bdf454b8d14d524a Mon Sep 17 00:00:00 2001 From: Simon Glass Date: Mon, 25 Feb 2013 14:08:37 -0800 Subject: mfd: Add ChromeOS EC implementation This is the base EC implementation, which provides a high level interface to the EC for use by the rest of the kernel. The actual communcations is dealt with by a separate protocol driver which registers itself with this interface. Interrupts are passed on through a notifier. A simple message structure is used to pass messages to the protocol driver. Signed-off-by: Simon Glass Signed-off-by: Che-Liang Chiou Signed-off-by: Jonathan Kliegman Signed-off-by: Luigi Semenzato Signed-off-by: Olof Johansson Signed-off-by: Vincent Palatin Signed-off-by: Samuel Ortiz --- include/linux/mfd/cros_ec.h | 170 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 170 insertions(+) create mode 100644 include/linux/mfd/cros_ec.h (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h new file mode 100644 index 000000000000..032af7fc5b2e --- /dev/null +++ b/include/linux/mfd/cros_ec.h @@ -0,0 +1,170 @@ +/* + * ChromeOS EC multi-function device + * + * Copyright (C) 2012 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_MFD_CROS_EC_H +#define __LINUX_MFD_CROS_EC_H + +#include + +/* + * Command interface between EC and AP, for LPC, I2C and SPI interfaces. + */ +enum { + EC_MSG_TX_HEADER_BYTES = 3, + EC_MSG_TX_TRAILER_BYTES = 1, + EC_MSG_TX_PROTO_BYTES = EC_MSG_TX_HEADER_BYTES + + EC_MSG_TX_TRAILER_BYTES, + EC_MSG_RX_PROTO_BYTES = 3, + + /* Max length of messages */ + EC_MSG_BYTES = EC_HOST_PARAM_SIZE + EC_MSG_TX_PROTO_BYTES, + +}; + +/** + * struct cros_ec_msg - A message sent to the EC, and its reply + * + * @version: Command version number (often 0) + * @cmd: Command to send (EC_CMD_...) + * @out_buf: Outgoing payload (to EC) + * @outlen: Outgoing length + * @in_buf: Incoming payload (from EC) + * @in_len: Incoming length + */ +struct cros_ec_msg { + u8 version; + u8 cmd; + uint8_t *out_buf; + int out_len; + uint8_t *in_buf; + int in_len; +}; + +/** + * struct cros_ec_device - Information about a ChromeOS EC device + * + * @name: Name of this EC interface + * @priv: Private data + * @irq: Interrupt to use + * @din: input buffer (from EC) + * @dout: output buffer (to EC) + * \note + * These two buffers will always be dword-aligned and include enough + * space for up to 7 word-alignment bytes also, so we can ensure that + * the body of the message is always dword-aligned (64-bit). + * + * We use this alignment to keep ARM and x86 happy. Probably word + * alignment would be OK, there might be a small performance advantage + * to using dword. + * @din_size: size of din buffer + * @dout_size: size of dout buffer + * @command_send: send a command + * @command_recv: receive a command + * @ec_name: name of EC device (e.g. 'chromeos-ec') + * @phys_name: name of physical comms layer (e.g. 'i2c-4') + * @parent: pointer to parent device (e.g. i2c or spi device) + * @dev: Device pointer + * dev_lock: Lock to prevent concurrent access + * @wake_enabled: true if this device can wake the system from sleep + * @was_wake_device: true if this device was set to wake the system from + * sleep at the last suspend + * @event_notifier: interrupt event notifier for transport devices + */ +struct cros_ec_device { + const char *name; + void *priv; + int irq; + uint8_t *din; + uint8_t *dout; + int din_size; + int dout_size; + int (*command_send)(struct cros_ec_device *ec, + uint16_t cmd, void *out_buf, int out_len); + int (*command_recv)(struct cros_ec_device *ec, + uint16_t cmd, void *in_buf, int in_len); + int (*command_sendrecv)(struct cros_ec_device *ec, + uint16_t cmd, void *out_buf, int out_len, + void *in_buf, int in_len); + int (*command_xfer)(struct cros_ec_device *ec, + struct cros_ec_msg *msg); + + const char *ec_name; + const char *phys_name; + struct device *parent; + + /* These are --private-- fields - do not assign */ + struct device *dev; + struct mutex dev_lock; + bool wake_enabled; + bool was_wake_device; + struct blocking_notifier_head event_notifier; +}; + +/** + * cros_ec_suspend - Handle a suspend operation for the ChromeOS EC device + * + * This can be called by drivers to handle a suspend event. + * + * ec_dev: Device to suspend + * @return 0 if ok, -ve on error + */ +int cros_ec_suspend(struct cros_ec_device *ec_dev); + +/** + * cros_ec_resume - Handle a resume operation for the ChromeOS EC device + * + * This can be called by drivers to handle a resume event. + * + * @ec_dev: Device to resume + * @return 0 if ok, -ve on error + */ +int cros_ec_resume(struct cros_ec_device *ec_dev); + +/** + * cros_ec_prepare_tx - Prepare an outgoing message in the output buffer + * + * This is intended to be used by all ChromeOS EC drivers, but at present + * only SPI uses it. Once LPC uses the same protocol it can start using it. + * I2C could use it now, with a refactor of the existing code. + * + * @ec_dev: Device to register + * @msg: Message to write + */ +int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, + struct cros_ec_msg *msg); + +/** + * cros_ec_remove - Remove a ChromeOS EC + * + * Call this to deregister a ChromeOS EC. After this you should call + * cros_ec_free(). + * + * @ec_dev: Device to register + * @return 0 if ok, -ve on error + */ +int cros_ec_remove(struct cros_ec_device *ec_dev); + +/** + * cros_ec_register - Register a new ChromeOS EC, using the provided info + * + * Before calling this, allocate a pointer to a new device and then fill + * in all the fields up to the --private-- marker. + * + * @ec_dev: Device to register + * @return 0 if ok, -ve on error + */ +int cros_ec_register(struct cros_ec_device *ec_dev); + +#endif /* __LINUX_MFD_CROS_EC_H */ -- cgit v1.2.3 From 43840415339f1600f281211cfb5400fab696536e Mon Sep 17 00:00:00 2001 From: Simon Glass Date: Mon, 25 Feb 2013 14:08:40 -0800 Subject: input: matrix-keymap: Add function to read the new DT binding We now have a binding which adds two parameters to the matrix keypad DT node. This is separate from the GPIO-driven matrix keypad binding, and unfortunately incompatible, since that uses row-gpios/col-gpios for the row and column counts. So the easiest option here is to provide a function for non-GPIO drivers to use to decode the binding. Note: We could in fact create an entirely separate structure to hold these two fields, but it does not seem worth it, yet. If we have more parameters then we can add this, and then refactor each driver to hold such a structure. Signed-off-by: Simon Glass Acked-by: Dmitry Torokhov Tested-by: Sourav Poddar (v2) Signed-off-by: Samuel Ortiz --- include/linux/input/matrix_keypad.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h index 5f3aa6b11bfa..27e06acc509a 100644 --- a/include/linux/input/matrix_keypad.h +++ b/include/linux/input/matrix_keypad.h @@ -81,4 +81,23 @@ int matrix_keypad_build_keymap(const struct matrix_keymap_data *keymap_data, unsigned short *keymap, struct input_dev *input_dev); +#ifdef CONFIG_OF +/** + * matrix_keypad_parse_of_params() - Read parameters from matrix-keypad node + * + * @dev: Device containing of_node + * @rows: Returns number of matrix rows + * @cols: Returns number of matrix columns + * @return 0 if OK, <0 on error + */ +int matrix_keypad_parse_of_params(struct device *dev, + unsigned int *rows, unsigned int *cols); +#else +static inline int matrix_keypad_parse_of_params(struct device *dev, + unsigned int *rows, unsigned int *cols) +{ + return -ENOSYS; +} +#endif /* CONFIG_OF */ + #endif /* _MATRIX_KEYPAD_H */ -- cgit v1.2.3 From 3ec6eb9cc2dbfa5b626f813ab8077eb71da60af2 Mon Sep 17 00:00:00 2001 From: Tomasz Figa Date: Thu, 4 Apr 2013 18:17:19 +0200 Subject: regulator: max8952: Separate constraints from platform data struct This patch modifies platform data structure of max8952 driver to use pointer to regulator_init_data struct instead of embedding it. This is a prerequisite for adding Device Tree support for the driver. Signed-off-by: Tomasz Figa Signed-off-by: Kyungmin Park Signed-off-by: Mark Brown --- include/linux/regulator/max8952.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/max8952.h b/include/linux/regulator/max8952.h index 45e42855ad05..c13aa34d9019 100644 --- a/include/linux/regulator/max8952.h +++ b/include/linux/regulator/max8952.h @@ -128,7 +128,7 @@ struct max8952_platform_data { u8 sync_freq; u8 ramp_speed; - struct regulator_init_data reg_data; + struct regulator_init_data *reg_data; }; -- cgit v1.2.3 From 3ff4aa95b3cd960a1c2e1422bc3dbd604f88271b Mon Sep 17 00:00:00 2001 From: Tomasz Figa Date: Thu, 4 Apr 2013 18:17:20 +0200 Subject: regulator: max8952: Add Device Tree support This patch adds Device Tree support to max8952 regulator driver. Signed-off-by: Tomasz Figa Signed-off-by: Kyungmin Park Signed-off-by: Mark Brown --- include/linux/regulator/max8952.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/max8952.h b/include/linux/regulator/max8952.h index c13aa34d9019..4dbb63a1d4ab 100644 --- a/include/linux/regulator/max8952.h +++ b/include/linux/regulator/max8952.h @@ -122,11 +122,11 @@ struct max8952_platform_data { int gpio_vid1; int gpio_en; - u8 default_mode; - u8 dvs_mode[MAX8952_NUM_DVS_MODE]; /* MAX8952_DVS_MODEx_XXXXmV */ + u32 default_mode; + u32 dvs_mode[MAX8952_NUM_DVS_MODE]; /* MAX8952_DVS_MODEx_XXXXmV */ - u8 sync_freq; - u8 ramp_speed; + u32 sync_freq; + u32 ramp_speed; struct regulator_init_data *reg_data; }; -- cgit v1.2.3 From 14c6578683367b1e7af0c3c09e872b45a45183a7 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 14:21:34 +0200 Subject: mtd: nand: remove AG-AND support We have only one AG-AND driver and it was not touched since 2005. It looks like AG-AND was not really make it to mass-production and can be considered a dead technology. Along with the AG-AND support, this patch removes the BBT_AUTO_REFRESH feature, because the only user of this feature is AG-AND. And even though it is implemented as a generic feature, I prefer to remove it because NAND flashes do not really need it in this form. Signed-off-by: Artem Bityutskiy Acked-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index ef52d9c91459..7cc299436f94 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -171,22 +171,6 @@ typedef enum { #define NAND_CACHEPRG 0x00000008 /* Chip has copy back function */ #define NAND_COPYBACK 0x00000010 -/* - * AND Chip which has 4 banks and a confusing page / block - * assignment. See Renesas datasheet for further information. - */ -#define NAND_IS_AND 0x00000020 -/* - * Chip has a array of 4 pages which can be read without - * additional ready /busy waits. - */ -#define NAND_4PAGE_ARRAY 0x00000040 -/* - * Chip requires that BBT is periodically rewritten to prevent - * bits from adjacent blocks from 'leaking' in altering data. - * This happens with the Renesas AG-AND chips, possibly others. - */ -#define BBT_AUTO_REFRESH 0x00000080 /* * Chip requires ready check on read (for auto-incremented sequential read). * True only for small page devices; large page devices do not support -- cgit v1.2.3 From 0be718e5525a73557e76ea1c05b8001dde507049 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 14:35:56 +0200 Subject: mtd: nand: remove a bunch of unused commands Signed-off-by: Artem Bityutskiy Acked-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 7cc299436f94..e5d6160a4511 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -86,7 +86,6 @@ extern int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); #define NAND_CMD_READOOB 0x50 #define NAND_CMD_ERASE1 0x60 #define NAND_CMD_STATUS 0x70 -#define NAND_CMD_STATUS_MULTI 0x71 #define NAND_CMD_SEQIN 0x80 #define NAND_CMD_RNDIN 0x85 #define NAND_CMD_READID 0x90 @@ -105,25 +104,6 @@ extern int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); #define NAND_CMD_RNDOUTSTART 0xE0 #define NAND_CMD_CACHEDPROG 0x15 -/* Extended commands for AG-AND device */ -/* - * Note: the command for NAND_CMD_DEPLETE1 is really 0x00 but - * there is no way to distinguish that from NAND_CMD_READ0 - * until the remaining sequence of commands has been completed - * so add a high order bit and mask it off in the command. - */ -#define NAND_CMD_DEPLETE1 0x100 -#define NAND_CMD_DEPLETE2 0x38 -#define NAND_CMD_STATUS_MULTI 0x71 -#define NAND_CMD_STATUS_ERROR 0x72 -/* multi-bank error status (banks 0-3) */ -#define NAND_CMD_STATUS_ERROR0 0x73 -#define NAND_CMD_STATUS_ERROR1 0x74 -#define NAND_CMD_STATUS_ERROR2 0x75 -#define NAND_CMD_STATUS_ERROR3 0x76 -#define NAND_CMD_STATUS_RESET 0x7f -#define NAND_CMD_STATUS_CLEAR 0xff - #define NAND_CMD_NONE -1 /* Status bits */ -- cgit v1.2.3 From 96dca4c29c5e4fc158f8f31513994408c90c6818 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 14:50:43 +0200 Subject: mtd: nand: remove NAND_NO_PADDING macro It is not used anywhere. Signed-off-by: Artem Bityutskiy Acked-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index e5d6160a4511..10fd7df07b5e 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -145,8 +145,6 @@ typedef enum { */ /* Buswidth is 16 bit */ #define NAND_BUSWIDTH_16 0x00000002 -/* Device supports partial programming without padding */ -#define NAND_NO_PADDING 0x00000004 /* Chip has cache program function */ #define NAND_CACHEPRG 0x00000008 /* Chip has copy back function */ @@ -171,11 +169,9 @@ typedef enum { #define NAND_SUBPAGE_READ 0x00001000 /* Options valid for Samsung large page devices */ -#define NAND_SAMSUNG_LP_OPTIONS \ - (NAND_NO_PADDING | NAND_CACHEPRG | NAND_COPYBACK) +#define NAND_SAMSUNG_LP_OPTIONS (NAND_CACHEPRG | NAND_COPYBACK) /* Macros to identify the above */ -#define NAND_MUST_PAD(chip) (!(chip->options & NAND_NO_PADDING)) #define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) #define NAND_HAS_COPYBACK(chip) ((chip->options & NAND_COPYBACK)) #define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) -- cgit v1.2.3 From 88ad4b162adb3821815d0098987040fca26c7d80 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 14:52:25 +0200 Subject: mtd: nand: remove NAND_COPYBACK macro It is unused. Signed-off-by: Artem Bityutskiy Acked-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 10fd7df07b5e..ec0a74877714 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -147,8 +147,6 @@ typedef enum { #define NAND_BUSWIDTH_16 0x00000002 /* Chip has cache program function */ #define NAND_CACHEPRG 0x00000008 -/* Chip has copy back function */ -#define NAND_COPYBACK 0x00000010 /* * Chip requires ready check on read (for auto-incremented sequential read). * True only for small page devices; large page devices do not support @@ -169,11 +167,10 @@ typedef enum { #define NAND_SUBPAGE_READ 0x00001000 /* Options valid for Samsung large page devices */ -#define NAND_SAMSUNG_LP_OPTIONS (NAND_CACHEPRG | NAND_COPYBACK) +#define NAND_SAMSUNG_LP_OPTIONS (NAND_CACHEPRG) /* Macros to identify the above */ #define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) -#define NAND_HAS_COPYBACK(chip) ((chip->options & NAND_COPYBACK)) #define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) /* Non chip related options */ -- cgit v1.2.3 From 3239a6cdef0be60ec2dadc501cf385dc419d7452 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 14:56:18 +0200 Subject: mtd: nand: use NAND_HAS_CACHEPROG We have this unused macro, let's use it and justify its existence. Signed-off-by: Artem Bityutskiy Acked-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index ec0a74877714..07d7a3dc5582 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -167,7 +167,7 @@ typedef enum { #define NAND_SUBPAGE_READ 0x00001000 /* Options valid for Samsung large page devices */ -#define NAND_SAMSUNG_LP_OPTIONS (NAND_CACHEPRG) +#define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG /* Macros to identify the above */ #define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) -- cgit v1.2.3 From 68aa352de28235bccdcee96ddf49f7628e93ec6f Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 16:05:00 +0200 Subject: mtd: nand: rename the id field of 'struct nand_flash_dev' The 'id' is a bit confusing name because NAND IDs are multi-byte. Re-name it to 'dev_id' to make it clear that this is the "device ID" part (the second byte). While on it, clean-up the commentary for 'struct nand_flash_dev'. Signed-off-by: Artem Bityutskiy Acked-by: Brian Norris Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 07d7a3dc5582..9aed31a49af1 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -548,19 +548,18 @@ struct nand_chip { /** * struct nand_flash_dev - NAND Flash Device ID Structure - * @name: Identify the device type - * @id: device ID code - * @pagesize: Pagesize in bytes. Either 256 or 512 or 0 - * If the pagesize is 0, then the real pagesize - * and the eraseize are determined from the - * extended id bytes in the chip - * @erasesize: Size of an erase block in the flash device. - * @chipsize: Total chipsize in Mega Bytes - * @options: Bitfield to store chip relevant options + * @name: a human-readable name of the NAND chip + * @dev_id: the device ID (the second byte of the full chip ID array) + * @pagesize: size of the NAND page in bytes; if 0, then the real page size (as + * well as the eraseblock size) is determined from the extended NAND + * chip ID array) + * @erasesize: eraseblock size in bytes (determined from the extended ID if 0) + * @chipsize: total chip size in MiB + * @options: stores various chip bit options */ struct nand_flash_dev { char *name; - int id; + int dev_id; unsigned long pagesize; unsigned long chipsize; unsigned long erasesize; -- cgit v1.2.3 From 8dbfae1ef04311ba19d6b6c9a4d8fdddbb90ab0f Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 15:39:18 +0200 Subject: mtd: nand_ids: introduce helper macros Introduce helper macros for defining NAND chips. These macros do not really add much value in the current code-base. However, we are going to add full ID support which adds some more complexity to the table, and helper macros become useful for readability. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 9aed31a49af1..63b319a6f98c 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -546,6 +546,30 @@ struct nand_chip { #define NAND_MFR_MACRONIX 0xc2 #define NAND_MFR_EON 0x92 +/* + * A helper for defining older NAND chips where the second ID byte fully + * defined the chip, including the geometry (chip size, eraseblock size, page + * size). + */ +#define LEGACY_ID_NAND(nm, devid, pagesz, chipsz, erasesz, opts) \ + { .name = (nm), .dev_id = (devid), .pagesize = (pagesz), \ + .chipsize = (chipsz), .erasesize = (erasesz), \ + .options = (opts) } + +/* + * A helper for defining newer chips which report their page size and + * eraseblock size via the extended ID bytes. + * + * The real difference between LEGACY_ID_NAND and EXTENDED_ID_NAND is that with + * EXTENDED_ID_NAND, manufacturers overloaded the same device ID so that the + * device ID now only represented a particular total chip size (and voltage, + * buswidth), and the page size, eraseblock size, and OOB size could vary while + * using the same device ID. + */ +#define EXTENDED_ID_NAND(nm, devid, chipsz, opts) \ + { .name = (nm), .dev_id = (devid), .chipsize = (chipsz), \ + .options = (opts) } + /** * struct nand_flash_dev - NAND Flash Device ID Structure * @name: a human-readable name of the NAND chip -- cgit v1.2.3 From 8e12b474f9a2349bcaebda65bdc38e8398ff408e Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Mar 2013 16:26:56 +0200 Subject: mtd: nand: provision full ID support Up until now we identified NAND chips by the 'device ID' part of the full chip ID array, which is the second full ID array byte. However, the newest flashes use the same device ID for chips with identical page and eraseblock sizes, but different OOB sizes. And unfortunately, it is not clear if there is a "standard" way to fetch the OOB size from chip's full ID array. Here is an example: Toshiba TC58NVG2S0F: 0x98, 0xdc, 0x90, 0x26, 0x76, 0x15, 0x01, 0x08 Toshiba TC58NVG3S0F: 0x98, 0xd3, 0x90, 0x26, 0x76, 0x15, 0x02, 0x08 The first one is a 512MiB NAND chip with 4KiB NAND pages, 256KiB eraseblock size and 224 bytes OOB. The second one is a 1GiB NAND chip with the same page and eraseblock sizes, but with 232 bytes OOB. This means that we have to store full ID in our NAND flashes table in order to distinguish between these 2. This patch adds the 'id[8]' field to the 'struct nand_flash_dev' structure, and it makes it to be a part of anonymous union, where the second member is a structure containing the 'mfr_id' and 'dev_id' bytes. The union makes sure that 'mfr_id' refers the same RAM address as 'id[0]' and 'dev_id' refers the same RAM address as 'id[1]'. The only motivation for the union is an assumption that 'type->dev_id' is more readable than 'type->id[1]'. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 63b319a6f98c..9a1b74c85044 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -551,9 +551,9 @@ struct nand_chip { * defined the chip, including the geometry (chip size, eraseblock size, page * size). */ -#define LEGACY_ID_NAND(nm, devid, pagesz, chipsz, erasesz, opts) \ - { .name = (nm), .dev_id = (devid), .pagesize = (pagesz), \ - .chipsize = (chipsz), .erasesize = (erasesz), \ +#define LEGACY_ID_NAND(nm, devid, pagesz, chipsz, erasesz, opts) \ + { .name = (nm), {{ .dev_id = (devid) }}, .pagesize = (pagesz), \ + .chipsize = (chipsz), .erasesize = (erasesz), \ .options = (opts) } /* @@ -566,14 +566,19 @@ struct nand_chip { * buswidth), and the page size, eraseblock size, and OOB size could vary while * using the same device ID. */ -#define EXTENDED_ID_NAND(nm, devid, chipsz, opts) \ - { .name = (nm), .dev_id = (devid), .chipsize = (chipsz), \ +#define EXTENDED_ID_NAND(nm, devid, chipsz, opts) \ + { .name = (nm), {{ .dev_id = (devid) }}, .chipsize = (chipsz), \ .options = (opts) } /** * struct nand_flash_dev - NAND Flash Device ID Structure * @name: a human-readable name of the NAND chip * @dev_id: the device ID (the second byte of the full chip ID array) + * @mfr_id: manufecturer ID part of the full chip ID array (refers the same + * memory address as @id[0]) + * @dev_id: device ID part of the full chip ID array (refers the same memory + * address as @id[1]) + * @id: full device ID array * @pagesize: size of the NAND page in bytes; if 0, then the real page size (as * well as the eraseblock size) is determined from the extended NAND * chip ID array) @@ -583,7 +588,13 @@ struct nand_chip { */ struct nand_flash_dev { char *name; - int dev_id; + union { + struct { + uint8_t mfr_id; + uint8_t dev_id; + }; + uint8_t id[8]; + }; unsigned long pagesize; unsigned long chipsize; unsigned long erasesize; -- cgit v1.2.3 From ad2457894c272279bf73ca46ae5ea5de4876d2a0 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Mon, 4 Mar 2013 00:57:20 +0100 Subject: mtd: devices: elm: check for device's presence before configuration In case the driver is not probed - due to config mismatches or errors in the DTS files - dev_get_drvdata() returns NULL, leading to an Ooops during boot. Make elm_config() return an error in such cases to propagate the error up to the user, so it can fall back to software mode. Signed-off-by: Daniel Mack Acked-by: Peter Korsgaard Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/platform_data/elm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h index 1bd5244d1dcd..bf0a83b7ed9d 100644 --- a/include/linux/platform_data/elm.h +++ b/include/linux/platform_data/elm.h @@ -50,5 +50,5 @@ struct elm_errorvec { void elm_decode_bch_error_page(struct device *dev, u8 *ecc_calc, struct elm_errorvec *err_vec); -void elm_config(struct device *dev, enum bch_ecc bch_type); +int elm_config(struct device *dev, enum bch_ecc bch_type); #endif /* __ELM_H */ -- cgit v1.2.3 From 26a4734623e4f06752014336b05cf3ae77158892 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 11 Mar 2013 15:38:48 +0200 Subject: mtd: add 'const' qualifier to a couple of register functions 'mtd_device_parse_register()' and 'parse_mtd_partitions()' functions accept a an array of character pointers. These functions modify neither the pointers nor the characters they point to. The characters are actually names of the MTD parsers. At the moment, the argument type is 'const char **', which means that only the names of the parsers are constant. Let's turn the argument type into 'const char * const *', which means that both names and the pointers which point to them are constant. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/mtd.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index f9ac2897b86b..a5cf4e8d6818 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -362,10 +362,10 @@ struct mtd_partition; struct mtd_part_parser_data; extern int mtd_device_parse_register(struct mtd_info *mtd, - const char **part_probe_types, - struct mtd_part_parser_data *parser_data, - const struct mtd_partition *defparts, - int defnr_parts); + const char * const *part_probe_types, + struct mtd_part_parser_data *parser_data, + const struct mtd_partition *defparts, + int defnr_parts); #define mtd_device_register(master, parts, nr_parts) \ mtd_device_parse_register(master, NULL, NULL, parts, nr_parts) extern int mtd_device_unregister(struct mtd_info *master); -- cgit v1.2.3 From d50dcb1d0e1f8ebe11db1719aad5753cd1b4c4f8 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Tue, 12 Mar 2013 10:28:31 +0200 Subject: mtd: plat-ram: add const quilifiers Be a bit stricter and add few more 'const' qualifiers. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/plat-ram.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/plat-ram.h b/include/linux/mtd/plat-ram.h index e07890aff1cf..44212d65aa97 100644 --- a/include/linux/mtd/plat-ram.h +++ b/include/linux/mtd/plat-ram.h @@ -20,8 +20,8 @@ struct platdata_mtd_ram { const char *mapname; - const char **map_probes; - const char **probes; + const char * const *map_probes; + const char * const *probes; struct mtd_partition *partitions; int nr_partitions; int bankwidth; -- cgit v1.2.3 From f39cf6c7d472349a9907955ef213db1f26618ba0 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Tue, 12 Mar 2013 10:32:52 +0200 Subject: mtd: physmap: add const qualifiers Be a bit stricter and add few more 'const' qualifiers. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/physmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/physmap.h b/include/linux/mtd/physmap.h index d2887e76b7f6..aa6a2633c2da 100644 --- a/include/linux/mtd/physmap.h +++ b/include/linux/mtd/physmap.h @@ -30,7 +30,7 @@ struct physmap_flash_data { unsigned int pfow_base; char *probe_type; struct mtd_partition *parts; - const char **part_probe_types; + const char * const *part_probe_types; }; #endif /* __LINUX_MTD_PHYSMAP__ */ -- cgit v1.2.3 From ecb42fea59cf2d1e7160c5c7e707120e0e6714db Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 13 Mar 2013 13:45:00 +0200 Subject: mtd: nand: use more reasonable integer types Use 'unsigned int' instead of 'unsigned long' in the NAND chip description data structure, because 32-bits is more than enough for our purposes. We do not need 64-bits, which is what we end up on 64-bit architectures. We declare many instances of this data structure, so this should help saving some amount of memory. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 9a1b74c85044..d5903c0a0fe7 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -582,8 +582,8 @@ struct nand_chip { * @pagesize: size of the NAND page in bytes; if 0, then the real page size (as * well as the eraseblock size) is determined from the extended NAND * chip ID array) - * @erasesize: eraseblock size in bytes (determined from the extended ID if 0) * @chipsize: total chip size in MiB + * @erasesize: eraseblock size in bytes (determined from the extended ID if 0) * @options: stores various chip bit options */ struct nand_flash_dev { @@ -595,10 +595,10 @@ struct nand_flash_dev { }; uint8_t id[8]; }; - unsigned long pagesize; - unsigned long chipsize; - unsigned long erasesize; - unsigned long options; + unsigned int pagesize; + unsigned int chipsize; + unsigned int erasesize; + unsigned int options; }; /** -- cgit v1.2.3 From 53552d22bfe1f83f69f18eddae2f1d96249440f3 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Thu, 14 Mar 2013 09:57:23 +0200 Subject: mtd: introduce a macro for max NAND ID sequence length Introduce a helpful macro for the maximum NAND ID sequence length instead of using the "8" magic number. Signed-off-by: Artem Bityutskiy Acked-by: Huang Shijie Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index d5903c0a0fe7..0f78d19303c5 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -546,6 +546,9 @@ struct nand_chip { #define NAND_MFR_MACRONIX 0xc2 #define NAND_MFR_EON 0x92 +/* The maximum expected count of bytes in the NAND ID sequence */ +#define NAND_MAX_ID_LEN 8 + /* * A helper for defining older NAND chips where the second ID byte fully * defined the chip, including the geometry (chip size, eraseblock size, page @@ -593,7 +596,7 @@ struct nand_flash_dev { uint8_t mfr_id; uint8_t dev_id; }; - uint8_t id[8]; + uint8_t id[NAND_MAX_ID_LEN]; }; unsigned int pagesize; unsigned int chipsize; -- cgit v1.2.3 From f22d5f638b0ea40e7cceb4639a608bd2c3eff97c Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Fri, 15 Mar 2013 11:00:59 +0800 Subject: mtd: add new fields to nand_flash_dev{} As time goes on, we begin to meet the situation that we can not get enough information from some nand chips's id data. Take some Toshiba's nand chips for example. I have 4 Toshiba's nand chips in my hand: TC58NVG2S0F, TC58NVG3S0F, TC58NVG5D2, TC58NVG6D2 When we read these chips' datasheets, we will get the geometry of these chips: TC58NVG2S0F : 4096 + 224 TC58NVG3S0F : 4096 + 232 TC58NVG5D2 : 8192 + 640 TC58NVG6D2 : 8192 + 640 But we can not parse out the correct oob size for these chips from the id data. This patch adds some new fields to the nand_flash_dev{}: @id_len: the valid length of the id data. See the comments in nand_id_has_period() @oobsize: the oob size. Signed-off-by: Huang Shijie Reviewed-by: Brian Norris Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 0f78d19303c5..13786f0ae12a 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -588,6 +588,8 @@ struct nand_chip { * @chipsize: total chip size in MiB * @erasesize: eraseblock size in bytes (determined from the extended ID if 0) * @options: stores various chip bit options + * @id_len: The valid length of the @id. + * @oobsize: OOB size */ struct nand_flash_dev { char *name; @@ -602,6 +604,8 @@ struct nand_flash_dev { unsigned int chipsize; unsigned int erasesize; unsigned int options; + uint16_t id_len; + uint16_t oobsize; }; /** -- cgit v1.2.3 From 5bfa9b71a2d6642506e2dfdf49a66620f54f1d92 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Tue, 19 Mar 2013 10:29:26 +0200 Subject: mtd: nand_ids: improve LEGACY_ID_NAND macro a bit Notice that all the flashes belonging to the "legacy ID" class have 512 bytes NAND page. This means we may simplify the 'LEGACY_ID_NAND()' macro as well as the NAND ID table a little. Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 13786f0ae12a..ebf970e11428 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -552,12 +552,11 @@ struct nand_chip { /* * A helper for defining older NAND chips where the second ID byte fully * defined the chip, including the geometry (chip size, eraseblock size, page - * size). + * size). All these chips have 512 bytes NAND page size. */ -#define LEGACY_ID_NAND(nm, devid, pagesz, chipsz, erasesz, opts) \ - { .name = (nm), {{ .dev_id = (devid) }}, .pagesize = (pagesz), \ - .chipsize = (chipsz), .erasesize = (erasesz), \ - .options = (opts) } +#define LEGACY_ID_NAND(nm, devid, chipsz, erasesz, opts) \ + { .name = (nm), {{ .dev_id = (devid) }}, .pagesize = 512, \ + .chipsize = (chipsz), .erasesize = (erasesz), .options = (opts) } /* * A helper for defining newer chips which report their page size and -- cgit v1.2.3 From 837a6ba4f3b6d23026674e6af6b6849a4634fff9 Mon Sep 17 00:00:00 2001 From: "Gupta, Pekon" Date: Fri, 15 Mar 2013 17:55:53 +0530 Subject: mtd: nand: subpage write support for hardware based ECC schemes This patch adds support for subpage (partial-page) writes when using hardware based ECC schemes. Advantages: (1) reduces storage overhead when using file-systems like UBIFS, which store LEB header at page-size granularity. (2) allows independent subpage writes, thereby increasing NAND storage efficiency for non-page aligned data. + updated cafe_nand and lpc32xx_mlc NAND drivers for change in chip->write_page interface. Signed-off-by: Gupta, Pekon Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index ebf970e11428..ab6363443ce8 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -318,6 +318,7 @@ struct nand_hw_control { * any single ECC step, 0 if bitflips uncorrectable, -EIO hw error * @read_subpage: function to read parts of the page covered by ECC; * returns same as read_page() + * @write_subpage: function to write parts of the page covered by ECC. * @write_page: function to write a page according to the ECC generator * requirements. * @write_oob_raw: function to write chip OOB data without ECC @@ -349,6 +350,9 @@ struct nand_ecc_ctrl { uint8_t *buf, int oob_required, int page); int (*read_subpage)(struct mtd_info *mtd, struct nand_chip *chip, uint32_t offs, uint32_t len, uint8_t *buf); + int (*write_subpage)(struct mtd_info *mtd, struct nand_chip *chip, + uint32_t offset, uint32_t data_len, + const uint8_t *data_buf, int oob_required); int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, const uint8_t *buf, int oob_required); int (*write_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, @@ -484,8 +488,8 @@ struct nand_chip { int (*errstat)(struct mtd_info *mtd, struct nand_chip *this, int state, int status, int page); int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page, - int cached, int raw); + uint32_t offset, int data_len, const uint8_t *buf, + int oob_required, int page, int cached, int raw); int (*onfi_set_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip, -- cgit v1.2.3 From 5ab3a89a741fa4c331f42dec17fde59586dc59e6 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Wed, 13 Mar 2013 21:34:20 +0400 Subject: mfd: syscon: Add non-DT support This patch allow using syscon driver from the platform data, i.e. possibility using driver on systems without oftree support. For search syscon device from the client drivers, "syscon_regmap_lookup_by_pdevname" function was added. Signed-off-by: Alexander Shiyan Acked-by: Arnd Bergmann Signed-off-by: Samuel Ortiz --- include/linux/mfd/syscon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h index 6aeb6b8da64d..5c9ee6ee7960 100644 --- a/include/linux/mfd/syscon.h +++ b/include/linux/mfd/syscon.h @@ -17,6 +17,7 @@ extern struct regmap *syscon_node_to_regmap(struct device_node *np); extern struct regmap *syscon_regmap_lookup_by_compatible(const char *s); +extern struct regmap *syscon_regmap_lookup_by_pdevname(const char *s); extern struct regmap *syscon_regmap_lookup_by_phandle( struct device_node *np, const char *property); -- cgit v1.2.3 From 12202fa7573d32aa0915cde6e8fab4c86b63ca2c Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 5 Apr 2013 19:40:10 +0200 Subject: netfilter: remove unneeded variable proc_net_netfilter Now that this supports net namespace for nflog and nfqueue, we can remove the global proc_net_netfilter which has no clients anymore. Based on patch from Gao feng. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index ee142846f56a..0060fde3160e 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -289,11 +289,6 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #endif } -#ifdef CONFIG_PROC_FS -#include -extern struct proc_dir_entry *proc_net_netfilter; -#endif - #else /* !CONFIG_NETFILTER */ #define NF_HOOK(pf, hook, skb, indev, outdev, okfn) (okfn)(skb) #define NF_HOOK_COND(pf, hook, skb, indev, outdev, okfn, cond) (okfn)(skb) -- cgit v1.2.3 From 5e49035e26abf557737c1281439548f33b41578e Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Fri, 15 Feb 2013 15:03:50 -0700 Subject: spi/tegra: remove unused Tegra platform data header The platform data header is no longer used. Delete it. Signed-off-by: Stephen Warren Signed-off-by: Grant Likely --- include/linux/spi/spi-tegra.h | 40 ---------------------------------------- 1 file changed, 40 deletions(-) delete mode 100644 include/linux/spi/spi-tegra.h (limited to 'include/linux') diff --git a/include/linux/spi/spi-tegra.h b/include/linux/spi/spi-tegra.h deleted file mode 100644 index 786932c62edb..000000000000 --- a/include/linux/spi/spi-tegra.h +++ /dev/null @@ -1,40 +0,0 @@ -/* - * spi-tegra.h: SPI interface for Nvidia Tegra20 SLINK controller. - * - * Copyright (C) 2011 NVIDIA Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - */ - -#ifndef _LINUX_SPI_TEGRA_H -#define _LINUX_SPI_TEGRA_H - -struct tegra_spi_platform_data { - int dma_req_sel; - unsigned int spi_max_frequency; -}; - -/* - * Controller data from device to pass some info like - * hw based chip select can be used or not and if yes - * then CS hold and setup time. - */ -struct tegra_spi_device_controller_data { - bool is_hw_based_cs; - int cs_setup_clk_count; - int cs_hold_clk_count; -}; - -#endif /* _LINUX_SPI_TEGRA_H */ -- cgit v1.2.3 From a2b950ac7b1e6442919ee9e79c4963e134698869 Mon Sep 17 00:00:00 2001 From: Ohad Ben-Cohen Date: Sun, 7 Apr 2013 14:06:07 +0300 Subject: remoteproc: perserve resource table data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Copy resource table from first to second firmware loading. After firmware is loaded to memory, update the vdevs resource pointer to the resource table kept in device memory. Signed-off-by: Sjur Brændeland Acked-by: Ido Yariv [rebase, terminology and style changes] Signed-off-by: Ohad Ben-Cohen --- include/linux/remoteproc.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index faf33324c78f..b4cef16460f8 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -401,6 +401,9 @@ enum rproc_crash_type { * @crash_comp: completion used to sync crash handler and the rproc reload * @recovery_disabled: flag that state if recovery was disabled * @max_notifyid: largest allocated notify id. + * @table_ptr: pointer to the resource table in effect + * @cached_table: copy of the resource table + * @table_csum: checksum of the resource table */ struct rproc { struct klist_node node; @@ -429,9 +432,13 @@ struct rproc { struct completion crash_comp; bool recovery_disabled; int max_notifyid; + struct resource_table *table_ptr; + struct resource_table *cached_table; + u32 table_csum; }; /* we currently support only two vrings per rvdev */ + #define RVDEV_NUM_VRINGS 2 /** @@ -464,6 +471,7 @@ struct rproc_vring { * @vring: the vrings for this vdev * @dfeatures: virtio device features * @gfeatures: virtio guest features + * @rsc_offset: offset of the vdev's resource entry */ struct rproc_vdev { struct list_head node; @@ -472,6 +480,7 @@ struct rproc_vdev { struct rproc_vring vring[RVDEV_NUM_VRINGS]; unsigned long dfeatures; unsigned long gfeatures; + u32 rsc_offset; }; struct rproc *rproc_alloc(struct device *dev, const char *name, -- cgit v1.2.3 From 92b38f851470f8d8ea7ed638d546f83b5268bc12 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sjur=20Br=C3=A6ndeland?= Date: Thu, 21 Feb 2013 18:15:39 +0100 Subject: remoteproc: support virtio config space. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Support virtio configuration space and device status. The virtio device can now access the resource table in shared memory. Signed-off-by: Sjur Brændeland Acked-by: Ido Yariv [rebase and style changes] Signed-off-by: Ohad Ben-Cohen --- include/linux/remoteproc.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index b4cef16460f8..9e7e745dac55 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -469,8 +469,6 @@ struct rproc_vring { * @rproc: the rproc handle * @vdev: the virio device * @vring: the vrings for this vdev - * @dfeatures: virtio device features - * @gfeatures: virtio guest features * @rsc_offset: offset of the vdev's resource entry */ struct rproc_vdev { @@ -478,8 +476,6 @@ struct rproc_vdev { struct rproc *rproc; struct virtio_device vdev; struct rproc_vring vring[RVDEV_NUM_VRINGS]; - unsigned long dfeatures; - unsigned long gfeatures; u32 rsc_offset; }; -- cgit v1.2.3 From 8cc9934520e7f752fe45d5199664d741ba24a932 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 7 Apr 2013 09:29:50 -0700 Subject: cgroup, cpuset: replace move_member_tasks_to_cpuset() with cgroup_transfer_tasks() When a cpuset becomes empty (no CPU or memory), its tasks are transferred with the nearest ancestor with execution resources. This is implemented using cgroup_scan_tasks() with a callback which grabs cgroup_mutex and invokes cgroup_attach_task() on each task. Both cgroup_mutex and cgroup_attach_task() are scheduled to be unexported. Implement cgroup_transfer_tasks() in cgroup proper which is essentially the same as move_member_tasks_to_cpuset() except that it takes cgroups instead of cpusets and @to comes before @from like normal functions with those arguments, and replace move_member_tasks_to_cpuset() with it. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 01c48c6806d6..f8eb01d75ddc 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -696,6 +696,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk, bool threadgroup); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); +int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); /* * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works -- cgit v1.2.3 From b9777cf8d7c7854c3c38bd6621d993b85c2afcdf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 7 Apr 2013 09:29:51 -0700 Subject: cgroup: unexport locking interface and cgroup_attach_task() Now that all external cgroup_lock() users are gone, we can finally unexport the locking interface and prevent future abuse of cgroup_mutex. Make cgroup_[un]lock() and cgroup_lock_live_group() static. Also, cgroup_attach_task() doesn't have any user left and can't be used without locking interface anyway. Make it static too. Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f8eb01d75ddc..63deb70f3149 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -30,10 +30,7 @@ struct css_id; extern int cgroup_init_early(void); extern int cgroup_init(void); -extern void cgroup_lock(void); extern int cgroup_lock_is_held(void); -extern bool cgroup_lock_live_group(struct cgroup *cgrp); -extern void cgroup_unlock(void); extern void cgroup_fork(struct task_struct *p); extern void cgroup_post_fork(struct task_struct *p); extern void cgroup_exit(struct task_struct *p, int run_callbacks); @@ -693,8 +690,6 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp, struct cgroup_iter *it); void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); -int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk, - bool threadgroup); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); -- cgit v1.2.3 From 2219449a65ace0290cd9c2260ff337e326b8be8a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 7 Apr 2013 09:29:51 -0700 Subject: cgroup: remove cgroup_lock_is_held() We don't want controllers to assume that the information is officially available and do funky things with it. The only user is task_subsys_state_check() which uses it to verify RCU access context. We can move cgroup_lock_is_held() inside CONFIG_PROVE_RCU but that doesn't add meaningful protection compared to conditionally exposing cgroup_mutex. Remove cgroup_lock_is_held(), export cgroup_mutex iff CONFIG_PROVE_RCU and use lockdep_is_held() directly on the mutex in task_subsys_state_check(). While at it, add parentheses around macro arguments in task_subsys_state_check(). Signed-off-by: Tejun Heo Acked-by: Li Zefan --- include/linux/cgroup.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 63deb70f3149..515927eebb37 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -30,7 +30,6 @@ struct css_id; extern int cgroup_init_early(void); extern int cgroup_init(void); -extern int cgroup_lock_is_held(void); extern void cgroup_fork(struct task_struct *p); extern void cgroup_post_fork(struct task_struct *p); extern void cgroup_exit(struct task_struct *p, int run_callbacks); @@ -552,10 +551,16 @@ static inline struct cgroup_subsys_state *cgroup_subsys_state( * rcu_dereference_check() conditions, such as locks used during the * cgroup_subsys::attach() methods. */ +#ifdef CONFIG_PROVE_RCU +extern struct mutex cgroup_mutex; #define task_subsys_state_check(task, subsys_id, __c) \ - rcu_dereference_check(task->cgroups->subsys[subsys_id], \ - lockdep_is_held(&task->alloc_lock) || \ - cgroup_lock_is_held() || (__c)) + rcu_dereference_check((task)->cgroups->subsys[(subsys_id)], \ + lockdep_is_held(&(task)->alloc_lock) || \ + lockdep_is_held(&cgroup_mutex) || (__c)) +#else +#define task_subsys_state_check(task, subsys_id, __c) \ + rcu_dereference((task)->cgroups->subsys[(subsys_id)]) +#endif static inline struct cgroup_subsys_state * task_subsys_state(struct task_struct *task, int subsys_id) -- cgit v1.2.3 From 540b3a39eea0056d305f17dda47eb185c4d56ddc Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Sun, 7 Apr 2013 03:44:07 +0000 Subject: net/mlx4_en: Enable DCB ETS ops only when supported by the firmware Enable the DCB ETS ops only when supported by the firmware. For older firmware/cards which don't support ETS, advertize only PFC DCB ops. Signed-off-by: Eugenia Emantayev Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 811f91cf5e8c..1bc5a750b330 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -140,6 +140,7 @@ enum { MLX4_DEV_CAP_FLAG_VEP_UC_STEER = 1LL << 41, MLX4_DEV_CAP_FLAG_VEP_MC_STEER = 1LL << 42, MLX4_DEV_CAP_FLAG_COUNTERS = 1LL << 48, + MLX4_DEV_CAP_FLAG_SET_ETH_SCHED = 1LL << 53, MLX4_DEV_CAP_FLAG_SENSE_SUPPORT = 1LL << 55, MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV = 1LL << 59, MLX4_DEV_CAP_FLAG_64B_EQE = 1LL << 61, -- cgit v1.2.3 From a0ef6a348a47bdb3896c468608f9cd19c1c26949 Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Sun, 7 Apr 2013 20:52:22 -0700 Subject: Input: MT - handle semi-mt devices in core Most semi-mt drivers use the slots in a manual way, but really only need to treat the finger count manually. With this patch, a semi-mt driver may use the input-mt core for everything else. Signed-off-by: Henrik Rydberg Signed-off-by: Dmitry Torokhov --- include/linux/input/mt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h index 2e86bd0bfba1..1b1dfa80d9ff 100644 --- a/include/linux/input/mt.h +++ b/include/linux/input/mt.h @@ -19,6 +19,7 @@ #define INPUT_MT_DIRECT 0x0002 /* direct device, e.g. touchscreen */ #define INPUT_MT_DROP_UNUSED 0x0004 /* drop contacts not seen in frame */ #define INPUT_MT_TRACK 0x0008 /* use in-kernel tracking */ +#define INPUT_MT_SEMI_MT 0x0010 /* semi-mt device, finger count handled manually */ /** * struct input_mt_slot - represents the state of an input MT slot -- cgit v1.2.3 From 9e8269de100dd0be1199778dc175ff22417aebd2 Mon Sep 17 00:00:00 2001 From: Naveen Krishna Chatradhi Date: Wed, 13 Mar 2013 09:38:20 +0530 Subject: hwmon: (ntc_thermistor) Add DT with IIO support to NTC thermistor driver This patch adds DT support to NTC driver to parse the platform data. Also adds the support to work as an iio device client. During the probe ntc driver gets the respective channels of ADC and uses iio_raw_read calls to get the ADC converted value. Signed-off-by: Naveen Krishna Chatradhi [Guenter Roeck: fixed Kconfig dependencies; use ERR_CAST] Tested-by: Doug Anderson Signed-off-by: Guenter Roeck --- include/linux/platform_data/ntc_thermistor.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/ntc_thermistor.h b/include/linux/platform_data/ntc_thermistor.h index 88734e871e3a..fa95f9cbe7ea 100644 --- a/include/linux/platform_data/ntc_thermistor.h +++ b/include/linux/platform_data/ntc_thermistor.h @@ -21,6 +21,8 @@ #ifndef _LINUX_NTC_H #define _LINUX_NTC_H +struct iio_channel; + enum ntc_thermistor_type { TYPE_NCPXXWB473, TYPE_NCPXXWL333, @@ -39,13 +41,17 @@ struct ntc_thermistor_platform_data { * described at Documentation/hwmon/ntc_thermistor * * pullup/down_ohm: 0 for infinite / not-connected + * + * chan: iio_channel pointer to communicate with the ADC which the + * thermistor is using for conversion of the analog values. */ - int (*read_uV)(void); + int (*read_uV)(struct ntc_thermistor_platform_data *); unsigned int pullup_uV; unsigned int pullup_ohm; unsigned int pulldown_ohm; enum { NTC_CONNECTED_POSITIVE, NTC_CONNECTED_GROUND } connect; + struct iio_channel *chan; int (*read_ohm)(void); }; -- cgit v1.2.3 From 088ce2ac9ebac5c74faf4d39083627875fa6f0f0 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 13 Mar 2013 16:40:39 -0700 Subject: hwmon: Fix CamelCase checkpatch warnings Signed-off-by: Guenter Roeck --- include/linux/platform_data/ntc_thermistor.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/ntc_thermistor.h b/include/linux/platform_data/ntc_thermistor.h index fa95f9cbe7ea..c7285b575462 100644 --- a/include/linux/platform_data/ntc_thermistor.h +++ b/include/linux/platform_data/ntc_thermistor.h @@ -45,8 +45,8 @@ struct ntc_thermistor_platform_data { * chan: iio_channel pointer to communicate with the ADC which the * thermistor is using for conversion of the analog values. */ - int (*read_uV)(struct ntc_thermistor_platform_data *); - unsigned int pullup_uV; + int (*read_uv)(struct ntc_thermistor_platform_data *); + unsigned int pullup_uv; unsigned int pullup_ohm; unsigned int pulldown_ohm; -- cgit v1.2.3 From 79ba1d8910f517c3bd39d794ddb1a5b4c03795c4 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 27 Mar 2013 14:38:07 +0100 Subject: mac80211: parse Timeout Interval Element using a struct Instead of open-coding the accesses and length check do the length check in the IE parser and assign a struct pointer for use in the remaining code. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d10b5bba3268..e46fea8b972e 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1955,6 +1955,16 @@ enum ieee80211_timeout_interval_type { WLAN_TIMEOUT_ASSOC_COMEBACK = 3 /* 802.11w */, }; +/** + * struct ieee80211_timeout_interval_ie - Timeout Interval element + * @type: type, see &enum ieee80211_timeout_interval_type + * @value: timeout interval value + */ +struct ieee80211_timeout_interval_ie { + u8 type; + __le32 value; +} __packed; + /* BACK action code */ enum ieee80211_back_actioncode { WLAN_ACTION_ADDBA_REQ = 0, -- cgit v1.2.3 From fc1b74925f87f6aca5432eb73f6a57eff30afde7 Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Fri, 5 Apr 2013 19:20:30 +0000 Subject: KVM: Move vm_list kvm_lock declarations out of x86 The variables vm_list and kvm_lock are common to all architectures, so move the declarations from arch/x86/include/asm/kvm_host.h to include/linux/kvm_host.h. Fixes sparse warnings like these when building for arm64: virt/kvm/kvm_main.c: warning: symbol 'kvm_lock' was not declared. Should it be static? virt/kvm/kvm_main.c: warning: symbol 'vm_list' was not declared. Should it be static? Signed-off-by: Geoff Levand Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1c0be23f874d..71fed38c7200 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -135,6 +135,9 @@ struct kvm; struct kvm_vcpu; extern struct kmem_cache *kvm_vcpu_cache; +extern raw_spinlock_t kvm_lock; +extern struct list_head vm_list; + struct kvm_io_range { gpa_t addr; int len; -- cgit v1.2.3 From 8b415dcd762607379cf0a69c9dd25940da1d174e Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Fri, 5 Apr 2013 19:20:30 +0000 Subject: KVM: Move kvm_rebooting declaration out of x86 The variable kvm_rebooting is a common kvm variable, so move its declaration from arch/x86/include/asm/kvm_host.h to include/asm/kvm_host.h. Fixes this sparse warning when building on arm64: virt/kvm/kvm_main.c:warning: symbol 'kvm_rebooting' was not declared. Should it be static? Signed-off-by: Geoff Levand Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 71fed38c7200..20d77d24d764 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1061,6 +1061,8 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) } } +extern bool kvm_rebooting; + #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) -- cgit v1.2.3 From 9a47a8dccf8866b497bd80809da1c665e7b07c2c Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 21 Mar 2013 12:27:25 +0100 Subject: mfd: prcmu: pass a base and size with the early initcall This patch will make an early remapping of the PRCMU, to be used when setting up the clocks, that will call down into parts of the PRCMU driver before it is probed. Going forward this will be removed like this: - The mailbox subsystem need to be merged. http://marc.info/?l=linux-kernel&m=136314559201983&w=2 - At this point the PRCMU clock code can be moved over to the ux500 clock driver in drivers/clk/ux500/* and maintained there in a decentralized manner. - This early initcall and PRCMU base parameters become part of the ux500_clk_init() call instead. Cc: Suman Anna Cc: Loic Pallardy Acked-by: Samuel Ortiz Acked-by: Arnd Bergmann Acked-by: Ulf Hansson Signed-off-by: Linus Walleij --- include/linux/mfd/db8500-prcmu.h | 4 ++-- include/linux/mfd/dbx500-prcmu.h | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/db8500-prcmu.h b/include/linux/mfd/db8500-prcmu.h index 77a46ae2fc17..ac943df93489 100644 --- a/include/linux/mfd/db8500-prcmu.h +++ b/include/linux/mfd/db8500-prcmu.h @@ -489,7 +489,7 @@ struct prcmu_auto_pm_config { #ifdef CONFIG_MFD_DB8500_PRCMU -void db8500_prcmu_early_init(void); +void db8500_prcmu_early_init(u32 phy_base, u32 size); int prcmu_set_rc_a2p(enum romcode_write); enum romcode_read prcmu_get_rc_p2a(void); enum ap_pwrst prcmu_get_xp70_current_state(void); @@ -553,7 +553,7 @@ void db8500_prcmu_write_masked(unsigned int reg, u32 mask, u32 value); #else /* !CONFIG_MFD_DB8500_PRCMU */ -static inline void db8500_prcmu_early_init(void) {} +static inline void db8500_prcmu_early_init(u32 phy_base, u32 size) {} static inline int prcmu_set_rc_a2p(enum romcode_write code) { diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h index 3abcca91eecd..8c546cbcb9a6 100644 --- a/include/linux/mfd/dbx500-prcmu.h +++ b/include/linux/mfd/dbx500-prcmu.h @@ -276,9 +276,9 @@ struct prcmu_fw_version { #if defined(CONFIG_UX500_SOC_DB8500) -static inline void __init prcmu_early_init(void) +static inline void prcmu_early_init(u32 phy_base, u32 size) { - return db8500_prcmu_early_init(); + return db8500_prcmu_early_init(phy_base, size); } static inline int prcmu_set_power_state(u8 state, bool keep_ulp_clk, @@ -500,7 +500,7 @@ static inline int prcmu_config_a9wdog(u8 num, bool sleep_auto_off) } #else -static inline void __init prcmu_early_init(void) {} +static inline void prcmu_early_init(u32 phy_base, u32 size) {} static inline int prcmu_set_power_state(u8 state, bool keep_ulp_clk, bool keep_ap_pll) -- cgit v1.2.3 From 1e22a8c614a5d8c29d0882de21ce327673b71fca Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 19 Mar 2013 15:36:12 +0100 Subject: ARM: ux500: move PM-related PRCMU functions to machine We are trying to decompose and decentralize the code in the DB8500 PRCMU out into subdrivers. The code moved in this patch concerns a group of functions used for decoupling and recoupling the IRQs from the GIC. During sleep and idle the Ux500 system will transfer all IRQ handling to the PRCMU using these functions. Basically we are left with the two alternatives of code placement as: - arch/arm/mach-ux500/pm.c - this because the code is closely related to the GIC, and takes ownership of some of the registers from the PRCMU related to this PM functionality. - drivers/mfd/db8500-prcmu-pm.c - because the code is affecting stuff in the PRCMU register range. But then this code needs to remap and handle GIC registers. This patch implementation is taking the first approach. Currently the cpuidle driver is the only piece of code using this set of functions, but it will later also be used by the suspend/resume code which is currently under review. The header file is moved to: The function prototypes need to be placed in a globally visible header since the CPUidle code is planned to move out to drivers/cpuidle. Acked-by: Samuel Ortiz Acked-by: Rickard Andersson Acked-by: Daniel Lezcano Signed-off-by: Linus Walleij --- include/linux/mfd/db8500-prcmu.h | 6 ------ include/linux/mfd/dbx500-prcmu.h | 30 ------------------------------ include/linux/platform_data/arm-ux500-pm.h | 21 +++++++++++++++++++++ 3 files changed, 21 insertions(+), 36 deletions(-) create mode 100644 include/linux/platform_data/arm-ux500-pm.h (limited to 'include/linux') diff --git a/include/linux/mfd/db8500-prcmu.h b/include/linux/mfd/db8500-prcmu.h index ac943df93489..0bd69446bb05 100644 --- a/include/linux/mfd/db8500-prcmu.h +++ b/include/linux/mfd/db8500-prcmu.h @@ -522,12 +522,6 @@ int db8500_prcmu_load_a9wdog(u8 id, u32 val); void db8500_prcmu_system_reset(u16 reset_code); int db8500_prcmu_set_power_state(u8 state, bool keep_ulp_clk, bool keep_ap_pll); u8 db8500_prcmu_get_power_state_result(void); -int db8500_prcmu_gic_decouple(void); -int db8500_prcmu_gic_recouple(void); -int db8500_prcmu_copy_gic_settings(void); -bool db8500_prcmu_gic_pending_irq(void); -bool db8500_prcmu_pending_irq(void); -bool db8500_prcmu_is_cpu_in_wfi(int cpu); void db8500_prcmu_enable_wakeups(u32 wakeups); int db8500_prcmu_set_epod(u16 epod_id, u8 epod_state); int db8500_prcmu_request_clock(u8 clock, bool enable); diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h index 8c546cbcb9a6..fc43cecc9449 100644 --- a/include/linux/mfd/dbx500-prcmu.h +++ b/include/linux/mfd/dbx500-prcmu.h @@ -293,36 +293,6 @@ static inline u8 prcmu_get_power_state_result(void) return db8500_prcmu_get_power_state_result(); } -static inline int prcmu_gic_decouple(void) -{ - return db8500_prcmu_gic_decouple(); -} - -static inline int prcmu_gic_recouple(void) -{ - return db8500_prcmu_gic_recouple(); -} - -static inline bool prcmu_gic_pending_irq(void) -{ - return db8500_prcmu_gic_pending_irq(); -} - -static inline bool prcmu_is_cpu_in_wfi(int cpu) -{ - return db8500_prcmu_is_cpu_in_wfi(cpu); -} - -static inline int prcmu_copy_gic_settings(void) -{ - return db8500_prcmu_copy_gic_settings(); -} - -static inline bool prcmu_pending_irq(void) -{ - return db8500_prcmu_pending_irq(); -} - static inline int prcmu_set_epod(u16 epod_id, u8 epod_state) { return db8500_prcmu_set_epod(epod_id, epod_state); diff --git a/include/linux/platform_data/arm-ux500-pm.h b/include/linux/platform_data/arm-ux500-pm.h new file mode 100644 index 000000000000..8dff64b29ec0 --- /dev/null +++ b/include/linux/platform_data/arm-ux500-pm.h @@ -0,0 +1,21 @@ +/* + * Copyright (C) ST-Ericsson SA 2010-2013 + * Author: Rickard Andersson for + * ST-Ericsson. + * Author: Daniel Lezcano for Linaro. + * License terms: GNU General Public License (GPL) version 2 + * + */ + +#ifndef ARM_UX500_PM_H +#define ARM_UX500_PM_H + +int prcmu_gic_decouple(void); +int prcmu_gic_recouple(void); +bool prcmu_gic_pending_irq(void); +bool prcmu_pending_irq(void); +bool prcmu_is_cpu_in_wfi(int cpu); +int prcmu_copy_gic_settings(void); +void ux500_pm_init(u32 phy_base, u32 size); + +#endif /* ARM_UX500_PM_H */ -- cgit v1.2.3 From 55b175d7e6327939df82592ef279c534da323354 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 21 Mar 2013 22:51:07 +0100 Subject: ARM: ux500: split out prcmu initialization This untangles the final bits of the prcmu code from the platform code: * The IRQ_PRCMU_* definitions move from irqs-db8500.h into prcmu.c because they are only of local significance. * u8500_thsens_device goes into the prcmu, because it uses a PRCMU IRQ that the platform does not see. * IRQ_DB8500_AB8500 and IRQ_PRCMU_BASE go into the platform data because the PRCMU does not see it. Acked-by: Samuel Ortiz Signed-off-by: Arnd Bergmann [Fixed a oneliner bug] Signed-off-by: Linus Walleij --- include/linux/mfd/dbx500-prcmu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h index fc43cecc9449..689e6a0d9c99 100644 --- a/include/linux/mfd/dbx500-prcmu.h +++ b/include/linux/mfd/dbx500-prcmu.h @@ -237,6 +237,8 @@ struct prcmu_pdata bool enable_set_ddr_opp; bool enable_ape_opp_100_voltage; struct ab8500_platform_data *ab_platdata; + int ab_irq; + int irq_base; u32 version_offset; u32 legacy_offset; u32 adt_offset; -- cgit v1.2.3 From 9b819060d349e2247c471d8f055c91a597560da0 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 19 Mar 2013 11:21:56 +0100 Subject: clk: ux500: pass clock base adresses in init call The ux500 clock driver was including which will not work when building for multiplatform support since is going away. Pass the base adresses in the init call instead. Cc: Ulf Hansson Cc: Mike Turquette Acked-by: Arnd Bergmann Acked-by: Ulf Hansson Acked-by: Mike Turquette Signed-off-by: Linus Walleij --- include/linux/platform_data/clk-ux500.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/clk-ux500.h b/include/linux/platform_data/clk-ux500.h index 3af0da1f3be5..320d9c39ea0a 100644 --- a/include/linux/platform_data/clk-ux500.h +++ b/include/linux/platform_data/clk-ux500.h @@ -10,7 +10,8 @@ #ifndef __CLK_UX500_H #define __CLK_UX500_H -void u8500_clk_init(void); +void u8500_clk_init(u32 clkrst1_base, u32 clkrst2_base, u32 clkrst3_base, + u32 clkrst5_base, u32 clkrst6_base); void u9540_clk_init(void); void u8540_clk_init(void); -- cgit v1.2.3 From ab0fc6ce4825311e1842bb3c46611d0f02d189df Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 21 Mar 2013 22:51:06 +0100 Subject: ARM: ux500: move mach/msp.h to This header file only contains platform data structure definitions, so it's straightforward to move. Signed-off-by: Arnd Bergmann [Delete one include rather than move it] Signed-off-by: Linus Walleij --- include/linux/platform_data/asoc-ux500-msp.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) create mode 100644 include/linux/platform_data/asoc-ux500-msp.h (limited to 'include/linux') diff --git a/include/linux/platform_data/asoc-ux500-msp.h b/include/linux/platform_data/asoc-ux500-msp.h new file mode 100644 index 000000000000..9991aea3d577 --- /dev/null +++ b/include/linux/platform_data/asoc-ux500-msp.h @@ -0,0 +1,27 @@ +/* + * Copyright (C) ST-Ericsson SA 2010 + * + * Author: Rabin Vincent for ST-Ericsson + * License terms: GNU General Public License (GPL), version 2. + */ + +#ifndef __MSP_H +#define __MSP_H + +#include + +enum msp_i2s_id { + MSP_I2S_0 = 0, + MSP_I2S_1, + MSP_I2S_2, + MSP_I2S_3, +}; + +/* Platform data structure for a MSP I2S-device */ +struct msp_i2s_platform_data { + enum msp_i2s_id id; + struct stedma40_chan_cfg *msp_i2s_dma_rx; + struct stedma40_chan_cfg *msp_i2s_dma_tx; +}; + +#endif -- cgit v1.2.3 From b82718565c74a4f313163da8e1ce12af4bc9d34e Mon Sep 17 00:00:00 2001 From: Jingoo Han Date: Tue, 12 Feb 2013 15:29:15 -0800 Subject: ARM: EXYNOS: change the name of USB ohci header This patch changes the name of USB ohci header from 'usb-exynos.h' to 'usb-ohci-exynos.h'. This is because this header file has the platdata for only EXYNOS OHCI. Signed-off-by: Jingoo Han Acked-by: Alan Stern Signed-off-by: Kukjin Kim --- include/linux/platform_data/usb-exynos.h | 21 --------------------- include/linux/platform_data/usb-ohci-exynos.h | 21 +++++++++++++++++++++ 2 files changed, 21 insertions(+), 21 deletions(-) delete mode 100644 include/linux/platform_data/usb-exynos.h create mode 100644 include/linux/platform_data/usb-ohci-exynos.h (limited to 'include/linux') diff --git a/include/linux/platform_data/usb-exynos.h b/include/linux/platform_data/usb-exynos.h deleted file mode 100644 index c256c595be5e..000000000000 --- a/include/linux/platform_data/usb-exynos.h +++ /dev/null @@ -1,21 +0,0 @@ -/* - * Copyright (C) 2011 Samsung Electronics Co.Ltd - * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#ifndef __MACH_EXYNOS_OHCI_H -#define __MACH_EXYNOS_OHCI_H - -struct exynos4_ohci_platdata { - int (*phy_init)(struct platform_device *pdev, int type); - int (*phy_exit)(struct platform_device *pdev, int type); -}; - -extern void exynos4_ohci_set_platdata(struct exynos4_ohci_platdata *pd); - -#endif /* __MACH_EXYNOS_OHCI_H */ diff --git a/include/linux/platform_data/usb-ohci-exynos.h b/include/linux/platform_data/usb-ohci-exynos.h new file mode 100644 index 000000000000..c256c595be5e --- /dev/null +++ b/include/linux/platform_data/usb-ohci-exynos.h @@ -0,0 +1,21 @@ +/* + * Copyright (C) 2011 Samsung Electronics Co.Ltd + * http://www.samsung.com/ + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __MACH_EXYNOS_OHCI_H +#define __MACH_EXYNOS_OHCI_H + +struct exynos4_ohci_platdata { + int (*phy_init)(struct platform_device *pdev, int type); + int (*phy_exit)(struct platform_device *pdev, int type); +}; + +extern void exynos4_ohci_set_platdata(struct exynos4_ohci_platdata *pd); + +#endif /* __MACH_EXYNOS_OHCI_H */ -- cgit v1.2.3 From f8a0941f1bbdbaa68441142675986501b48da8f5 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 22 Mar 2013 12:59:33 +0100 Subject: mfd: arizona: Basic support for edge triggered IRQs Allow the user to configure edge triggered IRQs, though we do not yet fully handle new interrupts occurring while an interrupt is being handled. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/arizona/pdata.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 455c51d22d6b..84fefede3a23 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -99,7 +99,8 @@ struct arizona_pdata { /** If a direct 32kHz clock is provided on an MCLK specify it here */ int clk32k_src; - bool irq_active_high; /** IRQ polarity */ + /** Mode for primary IRQ (defaults to active low) */ + unsigned int irq_flags; /* Base GPIO */ int gpio_base; -- cgit v1.2.3 From 3092f8050eccce8463afe771f0910634a433e24b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sun, 24 Mar 2013 23:05:58 +0000 Subject: mfd: arizona: Allow GPIO to be specified for IRQ line If a GPIO is specified for the chip IRQ line then request it. This improves support for systems that do not put pins into input mode when used as interrupts. Also use this GPIO when the primary IRQ is in edge triggered mode to detect if we have handled pending interrupts in order to improve robustness. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/arizona/pdata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 84fefede3a23..8755dd05ab78 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -163,6 +163,9 @@ struct arizona_pdata { /** Haptic actuator type */ unsigned int hap_act; + + /** GPIO for primary IRQ (used for edge triggered emulation) */ + int irq_gpio; }; #endif -- cgit v1.2.3 From 544c7aadd7d4309ed01fcd787d393db67eb7eaea Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 29 Jan 2013 18:44:41 +0800 Subject: mfd: arizona: Support configuring MICBIASes into bypass mode Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/arizona/pdata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 8755dd05ab78..554d903cdf41 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -78,6 +78,7 @@ struct arizona_micbias { unsigned int ext_cap:1; /** External capacitor fitted */ unsigned int discharge:1; /** Actively discharge */ unsigned int fast_start:1; /** Enable aggressive startup ramp rate */ + unsigned int bypass:1; /** Use bypass mode */ }; struct arizona_micd_config { -- cgit v1.2.3 From a5055d5d683605210f77d46614bbdb389c1e4a07 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Fri, 15 Feb 2013 23:56:49 +0100 Subject: mfd: twl4030-madc: Add support for raw value in twl4030_madc_conversion MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Driver twl4030-madc has hardcoded channel types (10 - battery current, 1 - battery temperature) and also conversation data in variable twl4030_divider_ratios. These hardcoded channels are incorrect for Nokia RX-51 board (where is channel 0 - battery temperature). For Nokia RX-51 there is rx51_battery power_supply driver which reporting battery information via twl4030_madc_conversion. But this driver needs raw values (not converted via some hardcoded functions). So this patch adding new parameter "raw" to struct twl4030_madc_request which tell twl4030-madc driver to not convert values, but rather return raw. Signed-off-by: Pali Rohár Reviewed-by: Anton Vorontsov Signed-off-by: Samuel Ortiz --- include/linux/i2c/twl4030-madc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c/twl4030-madc.h b/include/linux/i2c/twl4030-madc.h index 530e11ba0738..01f595107048 100644 --- a/include/linux/i2c/twl4030-madc.h +++ b/include/linux/i2c/twl4030-madc.h @@ -39,6 +39,7 @@ struct twl4030_madc_conversion_method { * @do_avgP: sample the input channel for 4 consecutive cycles * @method: RT, SW1, SW2 * @type: Polling or interrupt based method + * @raw: Return raw value, do not convert it */ struct twl4030_madc_request { @@ -48,6 +49,7 @@ struct twl4030_madc_request { u16 type; bool active; bool result_pending; + bool raw; int rbuf[TWL4030_MADC_MAX_CHANNELS]; void (*func_cb)(int len, int channels, int *buf); }; -- cgit v1.2.3 From 3c2670e6515cf584810f417db9b00992c8b2d75a Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sat, 6 Apr 2013 09:56:00 -0700 Subject: driver core: add uid and gid to devtmpfs Some drivers want to tell userspace what uid and gid should be used for their device nodes, so allow that information to percolate through the driver core to userspace in order to make this happen. This means that some systems (i.e. Android and friends) will not need to even run a udev-like daemon for their device node manager and can just rely in devtmpfs fully, reducing their footprint even more. Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 4a7c4a84afee..851b85c7101e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -25,6 +25,7 @@ #include #include #include +#include #include struct device; @@ -465,7 +466,8 @@ struct device_type { const char *name; const struct attribute_group **groups; int (*uevent)(struct device *dev, struct kobj_uevent_env *env); - char *(*devnode)(struct device *dev, umode_t *mode); + char *(*devnode)(struct device *dev, umode_t *mode, + uid_t *uid, gid_t *gid); void (*release)(struct device *dev); const struct dev_pm_ops *pm; @@ -843,7 +845,8 @@ extern int device_rename(struct device *dev, const char *new_name); extern int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); extern const char *device_get_devnode(struct device *dev, - umode_t *mode, const char **tmp); + umode_t *mode, uid_t *uid, gid_t *gid, + const char **tmp); extern void *dev_get_drvdata(const struct device *dev); extern int dev_set_drvdata(struct device *dev, void *data); -- cgit v1.2.3 From 324670b620ab1ed00ba160e435686bd2ae4a59ce Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 4 Apr 2013 19:40:50 +0900 Subject: kprobes: Move __kprobes definition into compiler.h Currently, __kprobes is defined in linux/kprobes.h which is too big to be included in small or basic headers that want to make use of this simple attribute. So move __kprobes definition into linux/compiler.h in which other compiler attributes are defined. Signed-off-by: Masami Hiramatsu Cc: Timo Juhani Lindfors Cc: Ananth N Mavinakayanahalli Cc: Pavel Emelyanov Cc: Jiri Kosina Cc: Nadia Yvette Chambers Cc: yrl.pp-manager.tt@hitachi.com Cc: David S. Miller Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20130404104049.21071.20908.stgit@mhiramat-M0-7522 [ Improved the attribute explanation a bit. ] Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 6 ++++++ include/linux/kprobes.h | 6 +----- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 10b8f23fab0f..92669cd182a6 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -351,4 +351,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); */ #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x)) +/* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */ +#ifdef CONFIG_KPROBES +# define __kprobes __attribute__((__section__(".kprobes.text"))) +#else +# define __kprobes +#endif #endif /* __LINUX_COMPILER_H */ diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 4b6ef4d33cc2..ca1d27a0d6a6 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -29,6 +29,7 @@ * and Prasanna S Panchamukhi * added function-return probes. */ +#include /* for __kprobes */ #include #include #include @@ -49,16 +50,11 @@ #define KPROBE_REENTER 0x00000004 #define KPROBE_HIT_SSDONE 0x00000008 -/* Attach to insert probes on any functions which should be ignored*/ -#define __kprobes __attribute__((__section__(".kprobes.text"))) - #else /* CONFIG_KPROBES */ typedef int kprobe_opcode_t; struct arch_specific_insn { int dummy; }; -#define __kprobes - #endif /* CONFIG_KPROBES */ struct kprobe; -- cgit v1.2.3 From ee761f629d598579594d7e1eb8c552f3c5f71e4d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 Mar 2013 22:49:32 +0100 Subject: arch: Consolidate tsk_is_polling() Move it to a common place. Preparatory patch for implementing set/clear for the idle need_resched poll implementation. Signed-off-by: Thomas Gleixner Cc: Linus Torvalds Cc: Rusty Russell Cc: Paul McKenney Cc: Peter Zijlstra Reviewed-by: Cc: Srivatsa S. Bhat Cc: Magnus Damm Link: http://lkml.kernel.org/r/20130321215233.446034505@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6ddbfb..6709a5813f27 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2621,6 +2621,26 @@ static inline int spin_needbreak(spinlock_t *lock) #endif } +/* + * Idle thread specific functions to determine the need_resched + * polling state. We have two versions, one based on TS_POLLING in + * thread_info.status and one based on TIF_POLLING_NRFLAG in + * thread_info.flags + */ +#ifdef TS_POLLING +static inline int tsk_is_polling(struct task_struct *p) +{ + return task_thread_info(p)->status & TS_POLLING; +} +#elif defined(TIF_POLLING_NRFLAG) +static inline int tsk_is_polling(struct task_struct *p) +{ + return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG); +} +#else +static inline int tsk_is_polling(struct task_struct *p) { return 0; } +#endif + /* * Thread group CPU time accounting. */ -- cgit v1.2.3 From 3a98f871ecaf44806e188184332c3fec27c8f08c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 Mar 2013 22:49:33 +0100 Subject: idle: Implement set/clr functions for need_resched poll Implement set/clear functions for the idle need_resched poll implementation. Signed-off-by: Thomas Gleixner Cc: Linus Torvalds Cc: Rusty Russell Cc: Paul McKenney Cc: Peter Zijlstra Reviewed-by: Cc: Srivatsa S. Bhat Cc: Magnus Damm Link: http://lkml.kernel.org/r/20130321215233.518839807@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6709a5813f27..21fe9a142e51 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2632,13 +2632,34 @@ static inline int tsk_is_polling(struct task_struct *p) { return task_thread_info(p)->status & TS_POLLING; } +static inline void current_set_polling(void) +{ + current_thread_info()->status |= TS_POLLING; +} + +static inline void current_clr_polling(void) +{ + current_thread_info()->status &= ~TS_POLLING; + smp_mb__after_clear_bit(); +} #elif defined(TIF_POLLING_NRFLAG) static inline int tsk_is_polling(struct task_struct *p) { return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG); } +static inline void current_set_polling(void) +{ + set_thread_flag(TIF_POLLING_NRFLAG); +} + +static inline void current_clr_polling(void) +{ + clear_thread_flag(TIF_POLLING_NRFLAG); +} #else static inline int tsk_is_polling(struct task_struct *p) { return 0; } +static inline void current_set_polling(void) { } +static inline void current_clr_polling(void) { } #endif /* -- cgit v1.2.3 From a1a04ec3c7c27a682473fd9beb2c996316a64649 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 Mar 2013 22:49:34 +0100 Subject: idle: Provide a generic entry point for the idle code For now this calls cpu_idle(), but in the long run we want to move the cpu bringup code to the core and therefor we add a state argument. Signed-off-by: Thomas Gleixner Cc: Linus Torvalds Cc: Rusty Russell Cc: Paul McKenney Cc: Peter Zijlstra Reviewed-by: Cc: Srivatsa S. Bhat Cc: Magnus Damm Link: http://lkml.kernel.org/r/20130321215233.583190032@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpu.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ce7a074f2519..7419e30c55fb 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -212,4 +212,12 @@ static inline int disable_nonboot_cpus(void) { return 0; } static inline void enable_nonboot_cpus(void) {} #endif /* !CONFIG_PM_SLEEP_SMP */ +enum cpuhp_state { + CPUHP_OFFLINE, + CPUHP_ONLINE, +}; + +void cpu_startup_entry(enum cpuhp_state state); +void cpu_idle(void); + #endif /* _LINUX_CPU_H_ */ -- cgit v1.2.3 From d166991234347215dc23fc9dc15a63a83a1a54e1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 Mar 2013 22:49:35 +0100 Subject: idle: Implement generic idle function All idle functions in arch/* are more or less the same, plus minus a few bugs and extra instrumentation, tickless support and other optional items. Implement a generic idle function which resembles the functionality found in arch/. Provide weak arch_cpu_idle_* functions which can be overridden by the architecture code if needed. Signed-off-by: Thomas Gleixner Cc: Linus Torvalds Cc: Rusty Russell Cc: Paul McKenney Cc: Peter Zijlstra Reviewed-by: Cc: Srivatsa S. Bhat Cc: Magnus Damm Link: http://lkml.kernel.org/r/20130321215233.646635455@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpu.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 7419e30c55fb..c6f6e0839b61 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -220,4 +220,12 @@ enum cpuhp_state { void cpu_startup_entry(enum cpuhp_state state); void cpu_idle(void); +void cpu_idle_poll_ctrl(bool enable); + +void arch_cpu_idle(void); +void arch_cpu_idle_prepare(void); +void arch_cpu_idle_enter(void); +void arch_cpu_idle_exit(void); +void arch_cpu_idle_dead(void); + #endif /* _LINUX_CPU_H_ */ -- cgit v1.2.3 From 654003e98213991e4d534487907baad2afd9828d Mon Sep 17 00:00:00 2001 From: Ian Lartey Date: Fri, 22 Mar 2013 14:55:12 +0000 Subject: mfd: palmas: is_palmas_charger needed by multiple drivers is_palmas_charger checks for the presence of charging functionality in the device Signed-off-by: Graeme Gregory Signed-off-by: Ian Lartey Acked-by: Laxman Dewangani Signed-off-by: Samuel Ortiz --- include/linux/mfd/palmas.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 3bbda22721ea..4a066d0caf44 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -1,9 +1,10 @@ /* * TI Palmas * - * Copyright 2011 Texas Instruments Inc. + * Copyright 2011-2013 Texas Instruments Inc. * * Author: Graeme Gregory + * Author: Ian Lartey * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -22,6 +23,15 @@ #define PALMAS_NUM_CLIENTS 3 +/* The ID_REVISION NUMBERS */ +#define PALMAS_CHIP_OLD_ID 0x0000 +#define PALMAS_CHIP_ID 0xC035 +#define PALMAS_CHIP_CHARGER_ID 0xC036 + +#define is_palmas(a) (((a) == PALMAS_CHIP_OLD_ID) || \ + ((a) == PALMAS_CHIP_ID)) +#define is_palmas_charger(a) ((a) == PALMAS_CHIP_CHARGER_ID) + struct palmas_pmic; struct palmas_gpadc; struct palmas_resource; -- cgit v1.2.3 From 751391c74f3d41a8d5c5dd5100385f723660c368 Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Tue, 12 Mar 2013 18:08:06 -0400 Subject: mfd: tps65090: Fix enum in header file The enum is missing the definition for the first bit, which makes all the rest off by one. Add definition for the TPS65090_IRQ_INTERRUPT bit which at 0. Signed-off-by: Rhyland Klein Signed-off-by: Samuel Ortiz --- include/linux/mfd/tps65090.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65090.h b/include/linux/mfd/tps65090.h index 6694cf43e8b8..9ce231fda74f 100644 --- a/include/linux/mfd/tps65090.h +++ b/include/linux/mfd/tps65090.h @@ -27,6 +27,7 @@ /* TPS65090 IRQs */ enum { + TPS65090_IRQ_INTERRUPT, TPS65090_IRQ_VAC_STATUS_CHANGE, TPS65090_IRQ_VSYS_STATUS_CHANGE, TPS65090_IRQ_BAT_STATUS_CHANGE, -- cgit v1.2.3 From 57e1b48805a92304e4f50ebf5b885e627731a444 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 6 Mar 2013 14:28:13 +0800 Subject: mfd: arizona: Define additional FLL control registers Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/arizona/registers.h | 40 +++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h index 340355136069..a61ce90ecd3f 100644 --- a/include/linux/mfd/arizona/registers.h +++ b/include/linux/mfd/arizona/registers.h @@ -85,12 +85,14 @@ #define ARIZONA_FLL1_CONTROL_6 0x176 #define ARIZONA_FLL1_LOOP_FILTER_TEST_1 0x177 #define ARIZONA_FLL1_NCO_TEST_0 0x178 +#define ARIZONA_FLL1_CONTROL_7 0x179 #define ARIZONA_FLL1_SYNCHRONISER_1 0x181 #define ARIZONA_FLL1_SYNCHRONISER_2 0x182 #define ARIZONA_FLL1_SYNCHRONISER_3 0x183 #define ARIZONA_FLL1_SYNCHRONISER_4 0x184 #define ARIZONA_FLL1_SYNCHRONISER_5 0x185 #define ARIZONA_FLL1_SYNCHRONISER_6 0x186 +#define ARIZONA_FLL1_SYNCHRONISER_7 0x187 #define ARIZONA_FLL1_SPREAD_SPECTRUM 0x189 #define ARIZONA_FLL1_GPIO_CLOCK 0x18A #define ARIZONA_FLL2_CONTROL_1 0x191 @@ -101,12 +103,14 @@ #define ARIZONA_FLL2_CONTROL_6 0x196 #define ARIZONA_FLL2_LOOP_FILTER_TEST_1 0x197 #define ARIZONA_FLL2_NCO_TEST_0 0x198 +#define ARIZONA_FLL2_CONTROL_7 0x199 #define ARIZONA_FLL2_SYNCHRONISER_1 0x1A1 #define ARIZONA_FLL2_SYNCHRONISER_2 0x1A2 #define ARIZONA_FLL2_SYNCHRONISER_3 0x1A3 #define ARIZONA_FLL2_SYNCHRONISER_4 0x1A4 #define ARIZONA_FLL2_SYNCHRONISER_5 0x1A5 #define ARIZONA_FLL2_SYNCHRONISER_6 0x1A6 +#define ARIZONA_FLL2_SYNCHRONISER_7 0x1A7 #define ARIZONA_FLL2_SPREAD_SPECTRUM 0x1A9 #define ARIZONA_FLL2_GPIO_CLOCK 0x1AA #define ARIZONA_MIC_CHARGE_PUMP_1 0x200 @@ -1677,6 +1681,13 @@ #define ARIZONA_FLL1_FRC_INTEG_VAL_SHIFT 0 /* FLL1_FRC_INTEG_VAL - [11:0] */ #define ARIZONA_FLL1_FRC_INTEG_VAL_WIDTH 12 /* FLL1_FRC_INTEG_VAL - [11:0] */ +/* + * R377 (0x179) - FLL1 Control 7 + */ +#define ARIZONA_FLL1_GAIN_MASK 0x003c /* FLL1_GAIN */ +#define ARIZONA_FLL1_GAIN_SHIFT 2 /* FLL1_GAIN */ +#define ARIZONA_FLL1_GAIN_WIDTH 4 /* FLL1_GAIN */ + /* * R385 (0x181) - FLL1 Synchroniser 1 */ @@ -1723,6 +1734,17 @@ #define ARIZONA_FLL1_CLK_SYNC_SRC_SHIFT 0 /* FLL1_CLK_SYNC_SRC - [3:0] */ #define ARIZONA_FLL1_CLK_SYNC_SRC_WIDTH 4 /* FLL1_CLK_SYNC_SRC - [3:0] */ +/* + * R391 (0x187) - FLL1 Synchroniser 7 + */ +#define ARIZONA_FLL1_SYNC_GAIN_MASK 0x003c /* FLL1_SYNC_GAIN */ +#define ARIZONA_FLL1_SYNC_GAIN_SHIFT 2 /* FLL1_SYNC_GAIN */ +#define ARIZONA_FLL1_SYNC_GAIN_WIDTH 4 /* FLL1_SYNC_GAIN */ +#define ARIZONA_FLL1_SYNC_BW 0x0001 /* FLL1_SYNC_BW */ +#define ARIZONA_FLL1_SYNC_BW_MASK 0x0001 /* FLL1_SYNC_BW */ +#define ARIZONA_FLL1_SYNC_BW_SHIFT 0 /* FLL1_SYNC_BW */ +#define ARIZONA_FLL1_SYNC_BW_WIDTH 1 /* FLL1_SYNC_BW */ + /* * R393 (0x189) - FLL1 Spread Spectrum */ @@ -1815,6 +1837,13 @@ #define ARIZONA_FLL2_FRC_INTEG_VAL_SHIFT 0 /* FLL2_FRC_INTEG_VAL - [11:0] */ #define ARIZONA_FLL2_FRC_INTEG_VAL_WIDTH 12 /* FLL2_FRC_INTEG_VAL - [11:0] */ +/* + * R409 (0x199) - FLL2 Control 7 + */ +#define ARIZONA_FLL2_GAIN_MASK 0x003c /* FLL2_GAIN */ +#define ARIZONA_FLL2_GAIN_SHIFT 2 /* FLL2_GAIN */ +#define ARIZONA_FLL2_GAIN_WIDTH 4 /* FLL2_GAIN */ + /* * R417 (0x1A1) - FLL2 Synchroniser 1 */ @@ -1861,6 +1890,17 @@ #define ARIZONA_FLL2_CLK_SYNC_SRC_SHIFT 0 /* FLL2_CLK_SYNC_SRC - [3:0] */ #define ARIZONA_FLL2_CLK_SYNC_SRC_WIDTH 4 /* FLL2_CLK_SYNC_SRC - [3:0] */ +/* + * R423 (0x1A7) - FLL2 Synchroniser 7 + */ +#define ARIZONA_FLL2_SYNC_GAIN_MASK 0x003c /* FLL2_SYNC_GAIN */ +#define ARIZONA_FLL2_SYNC_GAIN_SHIFT 2 /* FLL2_SYNC_GAIN */ +#define ARIZONA_FLL2_SYNC_GAIN_WIDTH 4 /* FLL2_SYNC_GAIN */ +#define ARIZONA_FLL2_SYNC_BW_MASK 0x0001 /* FLL2_SYNC_BW */ +#define ARIZONA_FLL2_SYNC_BW_MASK 0x0001 /* FLL2_SYNC_BW */ +#define ARIZONA_FLL2_SYNC_BW_SHIFT 0 /* FLL2_SYNC_BW */ +#define ARIZONA_FLL2_SYNC_BW_WIDTH 1 /* FLL2_SYNC_BW */ + /* * R425 (0x1A9) - FLL2 Spread Spectrum */ -- cgit v1.2.3 From 395b97a3aeff0b8d949ee3e67bf8c11c5ffd6861 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 27 Mar 2013 09:31:28 -0400 Subject: ftrace: Do not call stub functions in control loop The function tracing control loop used by perf spits out a warning if the called function is not a control function. This is because the control function references a per cpu allocated data structure on struct ftrace_ops that is not allocated for other types of functions. commit 0a016409e42 "ftrace: Optimize the function tracer list loop" Had an optimization done to all function tracing loops to optimize for a single registered ops. Unfortunately, this allows for a slight race when tracing starts or ends, where the stub function might be called after the current registered ops is removed. In this case we get the following dump: root# perf stat -e ftrace:function sleep 1 [ 74.339105] WARNING: at include/linux/ftrace.h:209 ftrace_ops_control_func+0xde/0xf0() [ 74.349522] Hardware name: PRIMERGY RX200 S6 [ 74.357149] Modules linked in: sg igb iTCO_wdt ptp pps_core iTCO_vendor_support i7core_edac dca lpc_ich i2c_i801 coretemp edac_core crc32c_intel mfd_core ghash_clmulni_intel dm_multipath acpi_power_meter pcspk r microcode vhost_net tun macvtap macvlan nfsd kvm_intel kvm auth_rpcgss nfs_acl lockd sunrpc uinput xfs libcrc32c sd_mod crc_t10dif sr_mod cdrom mgag200 i2c_algo_bit drm_kms_helper ttm qla2xxx mptsas ahci drm li bahci scsi_transport_sas mptscsih libata scsi_transport_fc i2c_core mptbase scsi_tgt dm_mirror dm_region_hash dm_log dm_mod [ 74.446233] Pid: 1377, comm: perf Tainted: G W 3.9.0-rc1 #1 [ 74.453458] Call Trace: [ 74.456233] [] warn_slowpath_common+0x7f/0xc0 [ 74.462997] [] ? rcu_note_context_switch+0xa0/0xa0 [ 74.470272] [] ? __unregister_ftrace_function+0xa2/0x1a0 [ 74.478117] [] warn_slowpath_null+0x1a/0x20 [ 74.484681] [] ftrace_ops_control_func+0xde/0xf0 [ 74.491760] [] ftrace_call+0x5/0x2f [ 74.497511] [] ? ftrace_call+0x5/0x2f [ 74.503486] [] ? ftrace_call+0x5/0x2f [ 74.509500] [] ? synchronize_sched+0x5/0x50 [ 74.516088] [] ? _cond_resched+0x5/0x40 [ 74.522268] [] ? synchronize_sched+0x5/0x50 [ 74.528837] [] ? __unregister_ftrace_function+0xa2/0x1a0 [ 74.536696] [] ? _cond_resched+0x5/0x40 [ 74.542878] [] ? mutex_lock+0x1d/0x50 [ 74.548869] [] unregister_ftrace_function+0x27/0x50 [ 74.556243] [] perf_ftrace_event_register+0x9f/0x140 [ 74.563709] [] ? _cond_resched+0x5/0x40 [ 74.569887] [] ? mutex_lock+0x1d/0x50 [ 74.575898] [] perf_trace_destroy+0x2e/0x50 [ 74.582505] [] tp_perf_event_destroy+0x9/0x10 [ 74.589298] [] free_event+0x70/0x1a0 [ 74.595208] [] perf_event_release_kernel+0x69/0xa0 [ 74.602460] [] ? _cond_resched+0x5/0x40 [ 74.608667] [] put_event+0x90/0xc0 [ 74.614373] [] perf_release+0x10/0x20 [ 74.620367] [] __fput+0xf4/0x280 [ 74.625894] [] ____fput+0xe/0x10 [ 74.631387] [] task_work_run+0xa7/0xe0 [ 74.637452] [] do_notify_resume+0x71/0xb0 [ 74.643843] [] int_signal+0x12/0x17 To fix this a new ftrace_ops flag is added that denotes the ftrace_list_end ftrace_ops stub as just that, a stub. This flag is now checked in the control loop and the function is not called if the flag is set. Thanks to Jovi for not just reporting the bug, but also pointing out where the bug was in the code. Link: http://lkml.kernel.org/r/514A8855.7090402@redhat.com Link: http://lkml.kernel.org/r/1364377499-1900-15-git-send-email-jovi.zhangwei@huawei.com Tested-by: WANG Chao Reported-by: WANG Chao Reported-by: zhangwei(Jovi) Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e5ca8ef50e9b..167abf907802 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -89,6 +89,7 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, * that the call back has its own recursion protection. If it does * not set this, then the ftrace infrastructure will add recursion * protection for the caller. + * STUB - The ftrace_ops is just a place holder. */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, @@ -98,6 +99,7 @@ enum { FTRACE_OPS_FL_SAVE_REGS = 1 << 4, FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 5, FTRACE_OPS_FL_RECURSION_SAFE = 1 << 6, + FTRACE_OPS_FL_STUB = 1 << 7, }; struct ftrace_ops { -- cgit v1.2.3 From ea71d9a600e769ca669f4ba3e25ffdecdeede240 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Sun, 24 Mar 2013 00:01:48 +0100 Subject: clocksource: sunxi: make use of CLKSRC_OF Using CLKSRC_OF allows to remove the SoC specific sunxi_timer.h header, and instead of using a custom init function in the machine definition use the standard clocksource_of_init function. Signed-off-by: Maxime Ripard --- include/linux/sunxi_timer.h | 24 ------------------------ 1 file changed, 24 deletions(-) delete mode 100644 include/linux/sunxi_timer.h (limited to 'include/linux') diff --git a/include/linux/sunxi_timer.h b/include/linux/sunxi_timer.h deleted file mode 100644 index 18081787e5f3..000000000000 --- a/include/linux/sunxi_timer.h +++ /dev/null @@ -1,24 +0,0 @@ -/* - * Copyright 2012 Maxime Ripard - * - * Maxime Ripard - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#ifndef __SUNXI_TIMER_H -#define __SUNXI_TIMER_H - -#include - -void sunxi_timer_init(void); - -#endif -- cgit v1.2.3 From f1dc6c4f77678979868fe220c6913890e13473d8 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Sun, 10 Mar 2013 15:54:46 +0100 Subject: irqchip: sunxi: Make use of the IRQCHIP_DECLARE macro This allows to remove some boilerplate code. At the same time, call the set_handle_irq function in the initialization function of the irqchip, so that we can remove it from the machine declaration. Signed-off-by: Maxime Ripard --- include/linux/irqchip/sunxi.h | 27 --------------------------- 1 file changed, 27 deletions(-) delete mode 100644 include/linux/irqchip/sunxi.h (limited to 'include/linux') diff --git a/include/linux/irqchip/sunxi.h b/include/linux/irqchip/sunxi.h deleted file mode 100644 index 1fe2c2260e2b..000000000000 --- a/include/linux/irqchip/sunxi.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * Copyright 2012 Maxime Ripard - * - * Maxime Ripard - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#ifndef __LINUX_IRQCHIP_SUNXI_H -#define __LINUX_IRQCHIP_SUNXI_H - -#include - -extern void sunxi_init_irq(void); - -extern asmlinkage void __exception_irq_entry sunxi_handle_irq( - struct pt_regs *regs); - -#endif -- cgit v1.2.3 From e46980a10a76ec3282dd6832c1974b880acd23d3 Mon Sep 17 00:00:00 2001 From: Samuel Ortiz Date: Tue, 9 Apr 2013 01:51:38 +0300 Subject: mei: bus: Add device enabling and disabling API It should be left to the drivers to enable and disable the device on the MEI bus when e.g getting probed. For drivers to be able to safely call the enable and disable hooks, the mei_cl_ops must be set before it's probed and thus this should happen before registering the device on the MEI bus. Hence the mei_cl_add_device() prototype change. Signed-off-by: Samuel Ortiz Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- include/linux/mei_cl_bus.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index 1bece18825ba..d14af7b722ef 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -38,4 +38,7 @@ int mei_cl_register_event_cb(struct mei_cl_device *device, void *mei_cl_get_drvdata(const struct mei_cl_device *device); void mei_cl_set_drvdata(struct mei_cl_device *device, void *data); +int mei_cl_enable_device(struct mei_cl_device *device); +int mei_cl_disable_device(struct mei_cl_device *device); + #endif /* _LINUX_MEI_CL_BUS_H */ -- cgit v1.2.3 From 577b42327d707fbe7166aad6902c2eeee6a65015 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 8 Apr 2013 21:38:12 -0400 Subject: NFS: Add functionality to allow waiting on all outstanding reads to complete This will later allow NFS locking code to wait for readahead to complete before releasing byte range locks. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f6b1956f3c86..fc01d5cb4cf1 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -59,11 +59,18 @@ struct nfs_lockowner { pid_t l_pid; }; +#define NFS_IO_INPROGRESS 0 +struct nfs_io_counter { + unsigned long flags; + atomic_t io_count; +}; + struct nfs_lock_context { atomic_t count; struct list_head list; struct nfs_open_context *open_context; struct nfs_lockowner lockowner; + struct nfs_io_counter io_count; }; struct nfs4_state; -- cgit v1.2.3 From 5fb1c2dd8f9e9f3fd4ecbaefc75b83ab0ec40cfa Mon Sep 17 00:00:00 2001 From: Sylwester Nawrocki Date: Mon, 25 Mar 2013 17:56:23 +0100 Subject: mfd: syscon: Add missing struct device_node declaration MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit syscon.h header uses struct device_node in functions' declarations without declaring it. This causes compilation warnings like: include/linux/mfd/syscon.h:20: warning: ‘struct device_node’ declared inside parameter list include/linux/mfd/syscon.h:20: warning: its scope is only this definition or declaration, which is probably not what you want Fix it by adding a forward declaration of struct device_node. Signed-off-by: Sylwester Nawrocki Signed-off-by: Kyungmin Park Acked-by: Dong Aisheng Signed-off-by: Samuel Ortiz --- include/linux/mfd/syscon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h index 5c9ee6ee7960..b473577f36db 100644 --- a/include/linux/mfd/syscon.h +++ b/include/linux/mfd/syscon.h @@ -15,6 +15,8 @@ #ifndef __LINUX_MFD_SYSCON_H__ #define __LINUX_MFD_SYSCON_H__ +struct device_node; + extern struct regmap *syscon_node_to_regmap(struct device_node *np); extern struct regmap *syscon_regmap_lookup_by_compatible(const char *s); extern struct regmap *syscon_regmap_lookup_by_pdevname(const char *s); -- cgit v1.2.3 From a6e4d5a03e9e3587e88aba687d8f225f4f04c792 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Mon, 25 Mar 2013 09:14:30 +0000 Subject: x86, efivars: firmware bug workarounds should be in platform code Let's not burden ia64 with checks in the common efivars code that we're not writing too much data to the variable store. That kind of thing is an x86 firmware bug, plain and simple. efi_query_variable_store() provides platforms with a wrapper in which they can perform checks and workarounds for EFI variable storage bugs. Cc: H. Peter Anvin Cc: Matthew Garrett Signed-off-by: Matt Fleming --- include/linux/efi.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 9bf2f1fcae27..3d7df3d32c66 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -333,6 +333,7 @@ typedef efi_status_t efi_query_capsule_caps_t(efi_capsule_header_t **capsules, unsigned long count, u64 *max_size, int *reset_type); +typedef efi_status_t efi_query_variable_store_t(u32 attributes, unsigned long size); /* * EFI Configuration Table and GUID definitions @@ -575,9 +576,15 @@ extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if pos #ifdef CONFIG_X86 extern void efi_late_init(void); extern void efi_free_boot_services(void); +extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size); #else static inline void efi_late_init(void) {} static inline void efi_free_boot_services(void) {} + +static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) +{ + return EFI_SUCCESS; +} #endif extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr); extern u64 efi_get_iobase (void); @@ -731,7 +738,7 @@ struct efivar_operations { efi_get_variable_t *get_variable; efi_get_next_variable_t *get_next_variable; efi_set_variable_t *set_variable; - efi_query_variable_info_t *query_variable_info; + efi_query_variable_store_t *query_variable_store; }; struct efivars { -- cgit v1.2.3 From 230f13a5035fd4725a6623af83953623fd51173a Mon Sep 17 00:00:00 2001 From: Jean-Nicolas Graux Date: Tue, 9 Apr 2013 10:35:19 +0200 Subject: mfd: support stmpe1801 18 bits enhanced port expander Provides support for 1801 variant of stmpe gpio port expanders. This chip has 18 gpios configurable as GPI, GPO, keypad matrix, special key or dedicated key function. Note that special/dedicated key function is not supported yet. Signed-off-by: Jean-Nicolas Graux Acked-by: Linus Walleij Signed-off-by: Samuel Ortiz --- include/linux/mfd/stmpe.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index 383ac1512a39..48395a69a7e9 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -26,6 +26,7 @@ enum stmpe_partnum { STMPE801, STMPE811, STMPE1601, + STMPE1801, STMPE2401, STMPE2403, STMPE_NBR_PARTS @@ -39,6 +40,7 @@ enum { STMPE_IDX_CHIP_ID, STMPE_IDX_ICR_LSB, STMPE_IDX_IER_LSB, + STMPE_IDX_ISR_LSB, STMPE_IDX_ISR_MSB, STMPE_IDX_GPMR_LSB, STMPE_IDX_GPSR_LSB, @@ -49,6 +51,7 @@ enum { STMPE_IDX_GPFER_LSB, STMPE_IDX_GPAFR_U_MSB, STMPE_IDX_IEGPIOR_LSB, + STMPE_IDX_ISGPIOR_LSB, STMPE_IDX_ISGPIOR_MSB, STMPE_IDX_MAX, }; -- cgit v1.2.3 From 1b8664341100716202c29d67f24d67094a82971e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 9 Apr 2013 05:54:01 +0000 Subject: net: sctp: introduce uapi header for sctp This patch introduces an UAPI header for the SCTP protocol, so that we can facilitate the maintenance and development of user land applications or libraries, in particular in terms of header synchronization. To not break compatibility, some fragments from lksctp-tools' netinet/sctp.h have been carefully included, while taking care that neither kernel nor user land breaks, so both compile fine with this change (for lksctp-tools I tested with the old netinet/sctp.h header and with a newly adapted one that includes the uapi sctp header). lksctp-tools smoke test run through successfully as well in both cases. Suggested-by: Neil Horman Cc: Neil Horman Cc: Vlad Yasevich Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index c11a28706fa4..3bfe8d6ee248 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -53,7 +53,9 @@ #include /* We need in_addr. */ #include /* We need in6_addr. */ +#include +#include /* Section 3.1. SCTP Common Header Format */ typedef struct sctphdr { @@ -63,14 +65,10 @@ typedef struct sctphdr { __le32 checksum; } __packed sctp_sctphdr_t; -#ifdef __KERNEL__ -#include - static inline struct sctphdr *sctp_hdr(const struct sk_buff *skb) { return (struct sctphdr *)skb_transport_header(skb); } -#endif /* Section 3.2. Chunk Field Descriptions. */ typedef struct sctp_chunkhdr { -- cgit v1.2.3 From ca10b9e9a8ca7342ee07065289cbe74ac128c169 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 8 Apr 2013 17:58:11 +0000 Subject: selinux: add a skb_owned_by() hook Commit 90ba9b1986b5ac (tcp: tcp_make_synack() can use alloc_skb()) broke certain SELinux/NetLabel configurations by no longer correctly assigning the sock to the outgoing SYNACK packet. Cost of atomic operations on the LISTEN socket is quite big, and we would like it to happen only if really needed. This patch introduces a new security_ops->skb_owned_by() method, that is a void operation unless selinux is active. Reported-by: Miroslav Vadkerti Diagnosed-by: Paul Moore Signed-off-by: Eric Dumazet Cc: "David S. Miller" Cc: linux-security-module@vger.kernel.org Acked-by: James Morris Tested-by: Paul Moore Acked-by: Paul Moore Signed-off-by: David S. Miller --- include/linux/security.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index eee7478cda70..6c3a78ace051 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1638,6 +1638,7 @@ struct security_operations { int (*tun_dev_attach_queue) (void *security); int (*tun_dev_attach) (struct sock *sk, void *security); int (*tun_dev_open) (void *security); + void (*skb_owned_by) (struct sk_buff *skb, struct sock *sk); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -2588,6 +2589,8 @@ int security_tun_dev_attach_queue(void *security); int security_tun_dev_attach(struct sock *sk, void *security); int security_tun_dev_open(void *security); +void security_skb_owned_by(struct sk_buff *skb, struct sock *sk); + #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, struct sock *other, @@ -2779,6 +2782,11 @@ static inline int security_tun_dev_open(void *security) { return 0; } + +static inline void security_skb_owned_by(struct sk_buff *skb, struct sock *sk) +{ +} + #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_NETWORK_XFRM -- cgit v1.2.3 From 386afc91144b36b42117b0092893f15bc8798a80 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 9 Apr 2013 10:48:33 -0700 Subject: spinlocks and preemption points need to be at least compiler barriers In UP and non-preempt respectively, the spinlocks and preemption disable/enable points are stubbed out entirely, because there is no regular code that can ever hit the kind of concurrency they are meant to protect against. However, while there is no regular code that can cause scheduling, we _do_ end up having some exceptional (literally!) code that can do so, and that we need to make sure does not ever get moved into the critical region by the compiler. In particular, get_user() and put_user() is generally implemented as inline asm statements (even if the inline asm may then make a call instruction to call out-of-line), and can obviously cause a page fault and IO as a result. If that inline asm has been scheduled into the middle of a preemption-safe (or spinlock-protected) code region, we obviously lose. Now, admittedly this is *very* unlikely to actually ever happen, and we've not seen examples of actual bugs related to this. But partly exactly because it's so hard to trigger and the resulting bug is so subtle, we should be extra careful to get this right. So make sure that even when preemption is disabled, and we don't have to generate any actual *code* to explicitly tell the system that we are in a preemption-disabled region, we need to at least tell the compiler not to move things around the critical region. This patch grew out of the same discussion that caused commits 79e5f05edcbf ("ARC: Add implicit compiler barrier to raw_local_irq* functions") and 3e2e0d2c222b ("tile: comment assumption about __insn_mtspr for ") to come about. Note for stable: use discretion when/if applying this. As mentioned, this bug may never have actually bitten anybody, and gcc may never have done the required code motion for it to possibly ever trigger in practice. Cc: stable@vger.kernel.org Cc: Steven Rostedt Cc: Peter Zijlstra Signed-off-by: Linus Torvalds --- include/linux/preempt.h | 22 ++++++++++++++-------- include/linux/spinlock_up.h | 29 ++++++++++++++++++----------- 2 files changed, 32 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 5a710b9c578e..87a03c746f17 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -93,14 +93,20 @@ do { \ #else /* !CONFIG_PREEMPT_COUNT */ -#define preempt_disable() do { } while (0) -#define sched_preempt_enable_no_resched() do { } while (0) -#define preempt_enable_no_resched() do { } while (0) -#define preempt_enable() do { } while (0) - -#define preempt_disable_notrace() do { } while (0) -#define preempt_enable_no_resched_notrace() do { } while (0) -#define preempt_enable_notrace() do { } while (0) +/* + * Even if we don't have any preemption, we need preempt disable/enable + * to be barriers, so that we don't have things like get_user/put_user + * that can cause faults and scheduling migrate into our preempt-protected + * region. + */ +#define preempt_disable() barrier() +#define sched_preempt_enable_no_resched() barrier() +#define preempt_enable_no_resched() barrier() +#define preempt_enable() barrier() + +#define preempt_disable_notrace() barrier() +#define preempt_enable_no_resched_notrace() barrier() +#define preempt_enable_notrace() barrier() #endif /* CONFIG_PREEMPT_COUNT */ diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index a26e2fb604e6..e2369c167dbd 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -16,7 +16,10 @@ * In the debug case, 1 means unlocked, 0 means locked. (the values * are inverted, to catch initialization bugs) * - * No atomicity anywhere, we are on UP. + * No atomicity anywhere, we are on UP. However, we still need + * the compiler barriers, because we do not want the compiler to + * move potentially faulting instructions (notably user accesses) + * into the locked sequence, resulting in non-atomic execution. */ #ifdef CONFIG_DEBUG_SPINLOCK @@ -25,6 +28,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) { lock->slock = 0; + barrier(); } static inline void @@ -32,6 +36,7 @@ arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) { local_irq_save(flags); lock->slock = 0; + barrier(); } static inline int arch_spin_trylock(arch_spinlock_t *lock) @@ -39,32 +44,34 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) char oldval = lock->slock; lock->slock = 0; + barrier(); return oldval > 0; } static inline void arch_spin_unlock(arch_spinlock_t *lock) { + barrier(); lock->slock = 1; } /* * Read-write spinlocks. No debug version. */ -#define arch_read_lock(lock) do { (void)(lock); } while (0) -#define arch_write_lock(lock) do { (void)(lock); } while (0) -#define arch_read_trylock(lock) ({ (void)(lock); 1; }) -#define arch_write_trylock(lock) ({ (void)(lock); 1; }) -#define arch_read_unlock(lock) do { (void)(lock); } while (0) -#define arch_write_unlock(lock) do { (void)(lock); } while (0) +#define arch_read_lock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_write_lock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_read_trylock(lock) ({ barrier(); (void)(lock); 1; }) +#define arch_write_trylock(lock) ({ barrier(); (void)(lock); 1; }) +#define arch_read_unlock(lock) do { barrier(); (void)(lock); } while (0) +#define arch_write_unlock(lock) do { barrier(); (void)(lock); } while (0) #else /* DEBUG_SPINLOCK */ #define arch_spin_is_locked(lock) ((void)(lock), 0) /* for sched.c and kernel_lock.c: */ -# define arch_spin_lock(lock) do { (void)(lock); } while (0) -# define arch_spin_lock_flags(lock, flags) do { (void)(lock); } while (0) -# define arch_spin_unlock(lock) do { (void)(lock); } while (0) -# define arch_spin_trylock(lock) ({ (void)(lock); 1; }) +# define arch_spin_lock(lock) do { barrier(); (void)(lock); } while (0) +# define arch_spin_lock_flags(lock, flags) do { barrier(); (void)(lock); } while (0) +# define arch_spin_unlock(lock) do { barrier(); (void)(lock); } while (0) +# define arch_spin_trylock(lock) ({ barrier(); (void)(lock); 1; }) #endif /* DEBUG_SPINLOCK */ #define arch_spin_is_contended(lock) (((void)(lock), 0)) -- cgit v1.2.3 From 8ce584c7416d8a85a6f3edc17d1cddefe331e87e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 30 Mar 2013 20:13:46 -0400 Subject: procfs: add proc_remove_subtree() just what it sounds like; do that only to procfs subtrees you've created - doing that to something shared with another driver is not only antisocial, but might cause interesting races with proc_create() and its ilk. Signed-off-by: Al Viro --- include/linux/proc_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 8307f2f94d86..94dfb2aa5533 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -117,6 +117,7 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, const struct file_operations *proc_fops, void *data); extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent); +extern int remove_proc_subtree(const char *name, struct proc_dir_entry *parent); struct pid_namespace; @@ -202,6 +203,7 @@ static inline struct proc_dir_entry *proc_create_data(const char *name, return NULL; } #define remove_proc_entry(name, parent) do {} while (0) +#define remove_proc_subtree(name, parent) do {} while (0) static inline struct proc_dir_entry *proc_symlink(const char *name, struct proc_dir_entry *parent,const char *dest) {return NULL;} -- cgit v1.2.3 From 8d71db4f0890605d44815a2b2da4ca003f1bb142 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 19 Mar 2013 21:01:03 -0400 Subject: lift sb_start_write/sb_end_write out of ->aio_write() Signed-off-by: Al Viro --- include/linux/fs.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2c28271ab9d4..578a66e6ee72 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2223,6 +2223,20 @@ static inline struct inode *file_inode(struct file *f) return f->f_inode; } +static inline void file_start_write(struct file *file) +{ + if (!S_ISREG(file_inode(file)->i_mode)) + return; + __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); +} + +static inline void file_end_write(struct file *file) +{ + if (!S_ISREG(file_inode(file)->i_mode)) + return; + __sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE); +} + /* * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. -- cgit v1.2.3 From 599a0ac14e065b7c08471ef2e75a504b7dec9267 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 12 Mar 2013 09:58:10 -0400 Subject: pipe: fold file_operations instances in one Signed-off-by: Al Viro --- include/linux/fs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 578a66e6ee72..b1f28b02ede6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2080,7 +2080,6 @@ extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; extern const struct file_operations bad_sock_fops; -extern const struct file_operations def_fifo_fops; #ifdef CONFIG_BLOCK extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); @@ -2152,10 +2151,6 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern int is_bad_inode(struct inode *); -extern const struct file_operations read_pipefifo_fops; -extern const struct file_operations write_pipefifo_fops; -extern const struct file_operations rdwr_pipefifo_fops; - #ifdef CONFIG_BLOCK /* * return READ, READA, or WRITE -- cgit v1.2.3 From ba5bb147330a8737b6b5a812cc774c79c070704b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 21 Mar 2013 02:21:19 -0400 Subject: pipe: take allocation and freeing of pipe_inode_info out of ->i_mutex * new field - pipe->files; number of struct file over that pipe (all sharing the same inode, of course); protected by inode->i_lock. * pipe_release() decrements pipe->files, clears inode->i_pipe when if the counter has reached 0 (all under ->i_lock) and, in that case, frees pipe after having done pipe_unlock() * fifo_open() starts with grabbing ->i_lock, and either bumps pipe->files if ->i_pipe was non-NULL or allocates a new pipe (dropping and regaining ->i_lock) and rechecks ->i_pipe; if it's still NULL, inserts new pipe there, otherwise bumps ->i_pipe->files and frees the one we'd allocated. At that point we know that ->i_pipe is non-NULL and won't go away, so we can do pipe_lock() on it and proceed as we used to. If we end up failing, decrement pipe->files and if it reaches 0 clear ->i_pipe and free the sucker after pipe_unlock(). Signed-off-by: Al Viro --- include/linux/pipe_fs_i.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index ad1a427b5267..59778e1c9c08 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -34,6 +34,7 @@ struct pipe_buffer { * @tmp_page: cached released page * @readers: number of current readers of this pipe * @writers: number of current writers of this pipe + * @files: number of struct file refering this pipe (protected by ->i_lock) * @waiting_writers: number of writers blocked waiting for room * @r_counter: reader counter * @w_counter: writer counter @@ -47,6 +48,7 @@ struct pipe_inode_info { unsigned int nrbufs, curbuf, buffers; unsigned int readers; unsigned int writers; + unsigned int files; unsigned int waiting_writers; unsigned int r_counter; unsigned int w_counter; -- cgit v1.2.3 From 72b0d9aacb89f3759931ec440e1b535671145bb4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 21 Mar 2013 02:32:24 -0400 Subject: pipe: don't use ->i_mutex now it can be done - put mutex into pipe_inode_info, use it instead of ->i_mutex Signed-off-by: Al Viro --- include/linux/pipe_fs_i.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 59778e1c9c08..d803a85a64b6 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -27,6 +27,7 @@ struct pipe_buffer { /** * struct pipe_inode_info - a linux kernel pipe + * @mutex: mutex protecting the whole thing * @wait: reader/writer wait point in case of empty/full pipe * @nrbufs: the number of non-empty pipe buffers in this pipe * @buffers: total number of buffers (should be a power of 2) @@ -44,6 +45,7 @@ struct pipe_buffer { * @bufs: the circular array of pipe buffers **/ struct pipe_inode_info { + struct mutex mutex; wait_queue_head_t wait; unsigned int nrbufs, curbuf, buffers; unsigned int readers; -- cgit v1.2.3 From 6447a3cf19da8c4653283d1c491e2e775633f348 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 21 Mar 2013 11:01:38 -0400 Subject: get rid of pipe->inode it's used only as a flag to distinguish normal pipes/FIFOs from the internal per-task one used by file-to-file splice. And pipe->files would work just as well for that purpose... Signed-off-by: Al Viro --- include/linux/pipe_fs_i.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index d803a85a64b6..ed8eeeb10811 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -41,7 +41,6 @@ struct pipe_buffer { * @w_counter: writer counter * @fasync_readers: reader side fasync * @fasync_writers: writer side fasync - * @inode: inode this pipe is attached to * @bufs: the circular array of pipe buffers **/ struct pipe_inode_info { @@ -57,7 +56,6 @@ struct pipe_inode_info { struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; - struct inode *inode; struct pipe_buffer *bufs; }; -- cgit v1.2.3 From 7bee130e222dfb3a7a70c0404dc09f104cddd7d6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 21 Mar 2013 11:04:15 -0400 Subject: get rid of alloc_pipe_info() argument not used anymore Signed-off-by: Al Viro --- include/linux/pipe_fs_i.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index ed8eeeb10811..765114f16243 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -146,7 +146,7 @@ int pipe_proc_fn(struct ctl_table *, int, void __user *, size_t *, loff_t *); /* Drop the inode semaphore and wait for a pipe event, atomically */ void pipe_wait(struct pipe_inode_info *pipe); -struct pipe_inode_info * alloc_pipe_info(struct inode * inode); +struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct inode * inode); void __free_pipe_info(struct pipe_inode_info *); -- cgit v1.2.3 From 4b8a8f1e4f94fd87747e6e3acef74cf0b4dc0dae Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 21 Mar 2013 11:06:46 -0400 Subject: get rid of the last free_pipe_info() callers and rename __free_pipe_info() to free_pipe_info() Signed-off-by: Al Viro --- include/linux/pipe_fs_i.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 765114f16243..b8809fef61f5 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -147,8 +147,7 @@ int pipe_proc_fn(struct ctl_table *, int, void __user *, size_t *, loff_t *); void pipe_wait(struct pipe_inode_info *pipe); struct pipe_inode_info *alloc_pipe_info(void); -void free_pipe_info(struct inode * inode); -void __free_pipe_info(struct pipe_inode_info *); +void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ void *generic_pipe_buf_map(struct pipe_inode_info *, struct pipe_buffer *, int); -- cgit v1.2.3 From 021ada7dff22d0d9540ff596cb0f8bb866755ee1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 29 Mar 2013 19:27:05 -0400 Subject: procfs: switch /proc/self away from proc_dir_entry Just have it pinned in dcache all along and let procfs ->kill_sb() drop it before kill_anon_super(). Signed-off-by: Al Viro --- include/linux/pid_namespace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 215e5e3dda10..5524f8cfa950 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -28,6 +28,7 @@ struct pid_namespace { struct pid_namespace *parent; #ifdef CONFIG_PROC_FS struct vfsmount *proc_mnt; + struct dentry *proc_self; #endif #ifdef CONFIG_BSD_PROCESS_ACCT struct bsd_acct_struct *bacct; -- cgit v1.2.3 From 2043f495c7c1a06f7748b5bcd17656d93c95e1a6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 31 Mar 2013 13:43:23 -0400 Subject: new helper: single_open_size() Same as single_open(), but preallocates the buffer of given size. Doesn't make any sense for sizes up to PAGE_SIZE and doesn't make sense if output of show() exceeds PAGE_SIZE only rarely - seq_read() will take care of growing the buffer and redoing show(). If you _know_ that it will be large, it might make more sense to look into saner iterator, rather than go with single-shot one. If that's impossible, single_open_size() might be for you. Again, don't use that without a good reason; occasionally that's really the best way to go, but very often there are better solutions. Signed-off-by: Al Viro --- include/linux/seq_file.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 68a04a343cad..2da29ac178fc 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -123,6 +123,7 @@ static inline int seq_nodemask_list(struct seq_file *m, nodemask_t *mask) } int single_open(struct file *, int (*)(struct seq_file *, void *), void *); +int single_open_size(struct file *, int (*)(struct seq_file *, void *), void *, size_t); int single_release(struct inode *, struct file *); void *__seq_open_private(struct file *, const struct seq_operations *, int); int seq_open_private(struct file *, const struct seq_operations *, int); -- cgit v1.2.3 From ee21ed0afc2f47007fbd8b22928ecb17316e13e2 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 31 Mar 2013 15:30:40 -0400 Subject: procfs: kill ->write_proc() Signed-off-by: Al Viro --- include/linux/proc_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 94dfb2aa5533..4f4137a0bd8a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -72,7 +72,6 @@ struct proc_dir_entry { struct proc_dir_entry *next, *parent, *subdir; void *data; read_proc_t *read_proc; - write_proc_t *write_proc; atomic_t count; /* use count */ int pde_users; /* number of callers into module in progress */ struct completion *pde_unload_completion; -- cgit v1.2.3 From d9dda78bad879595d8c4220a067fc029d6484a16 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 31 Mar 2013 18:16:14 -0400 Subject: procfs: new helper - PDE_DATA(inode) The only part of proc_dir_entry the code outside of fs/proc really cares about is PDE(inode)->data. Provide a helper for that; static inline for now, eventually will be moved to fs/proc, along with the knowledge of struct proc_dir_entry layout. Signed-off-by: Al Viro --- include/linux/proc_fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 4f4137a0bd8a..5ae73e273e7e 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -306,6 +306,11 @@ static inline struct proc_dir_entry *PDE(const struct inode *inode) return PROC_I(inode)->pde; } +static inline void *PDE_DATA(const struct inode *inode) +{ + return PROC_I(inode)->pde->data; +} + static inline struct net *PDE_NET(struct proc_dir_entry *pde) { return pde->parent->data; -- cgit v1.2.3 From fbd387aea0cb98c9d6e534c55d3d2ac83153348d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 1 Apr 2013 20:48:34 -0400 Subject: create_proc_cpu_mask() doesn't need an argument... Signed-off-by: Al Viro --- include/linux/profile.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/profile.h b/include/linux/profile.h index 21123902366d..aaad3861beb8 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -18,10 +18,10 @@ struct pt_regs; struct notifier_block; #if defined(CONFIG_PROFILING) && defined(CONFIG_PROC_FS) -void create_prof_cpu_mask(struct proc_dir_entry *de); +void create_prof_cpu_mask(void); int create_proc_profile(void); #else -static inline void create_prof_cpu_mask(struct proc_dir_entry *de) +static inline void create_prof_cpu_mask(void) { } -- cgit v1.2.3 From 80e928f7ebb958f4d79d4099d1c5c0a015a23b93 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 4 Apr 2013 17:02:03 +0100 Subject: proc: Kill create_proc_entry() Kill create_proc_entry() in favour of create_proc_read_entry(), proc_create() and proc_create_data(). Signed-off-by: David Howells --- include/linux/proc_fs.h | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 5ae73e273e7e..bcc0e10ef1df 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -109,8 +109,6 @@ extern void proc_root_init(void); void proc_flush_task(struct task_struct *task); -extern struct proc_dir_entry *create_proc_entry(const char *name, umode_t mode, - struct proc_dir_entry *parent); struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct file_operations *proc_fops, @@ -164,17 +162,9 @@ static inline struct proc_dir_entry *proc_create(const char *name, umode_t mode, return proc_create_data(name, mode, parent, proc_fops, NULL); } -static inline struct proc_dir_entry *create_proc_read_entry(const char *name, +extern struct proc_dir_entry *create_proc_read_entry(const char *name, umode_t mode, struct proc_dir_entry *base, - read_proc_t *read_proc, void * data) -{ - struct proc_dir_entry *res=create_proc_entry(name,mode,base); - if (res) { - res->read_proc=read_proc; - res->data=data; - } - return res; -} + read_proc_t *read_proc, void *data); extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name, struct proc_dir_entry *parent); @@ -190,9 +180,6 @@ static inline void proc_flush_task(struct task_struct *task) { } -static inline struct proc_dir_entry *create_proc_entry(const char *name, - umode_t mode, struct proc_dir_entry *parent) { return NULL; } - #define proc_create(name, mode, parent, fops) ({ (void)(mode), NULL; }) static inline struct proc_dir_entry *proc_create_data(const char *name, -- cgit v1.2.3 From 6eb4c7e96e19fd2c38a103472048fc0e0e0a3ec3 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 9 Apr 2013 08:57:20 +0000 Subject: netfilter: ipset: hash:*net*: nomatch flag not excluded on set resize If a resize is triggered the nomatch flag is not excluded at hashing, which leads to the element missed at lookup in the resized set. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_ahash.h | 30 +++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index 01d25e6fc792..0214c4c146fa 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -291,6 +291,7 @@ ip_set_hash_destroy(struct ip_set *set) #define type_pf_data_tlist TOKEN(TYPE, PF, _data_tlist) #define type_pf_data_next TOKEN(TYPE, PF, _data_next) #define type_pf_data_flags TOKEN(TYPE, PF, _data_flags) +#define type_pf_data_reset_flags TOKEN(TYPE, PF, _data_reset_flags) #ifdef IP_SET_HASH_WITH_NETS #define type_pf_data_match TOKEN(TYPE, PF, _data_match) #else @@ -385,9 +386,9 @@ type_pf_resize(struct ip_set *set, bool retried) struct ip_set_hash *h = set->data; struct htable *t, *orig = h->table; u8 htable_bits = orig->htable_bits; - const struct type_pf_elem *data; + struct type_pf_elem *data; struct hbucket *n, *m; - u32 i, j; + u32 i, j, flags = 0; int ret; retry: @@ -412,9 +413,16 @@ retry: n = hbucket(orig, i); for (j = 0; j < n->pos; j++) { data = ahash_data(n, j); +#ifdef IP_SET_HASH_WITH_NETS + flags = 0; + type_pf_data_reset_flags(data, &flags); +#endif m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_add(m, data, AHASH_MAX(h), 0); + ret = type_pf_elem_add(m, data, AHASH_MAX(h), flags); if (ret < 0) { +#ifdef IP_SET_HASH_WITH_NETS + type_pf_data_flags(data, flags); +#endif read_unlock_bh(&set->lock); ahash_destroy(t); if (ret == -EAGAIN) @@ -836,9 +844,9 @@ type_pf_tresize(struct ip_set *set, bool retried) struct ip_set_hash *h = set->data; struct htable *t, *orig = h->table; u8 htable_bits = orig->htable_bits; - const struct type_pf_elem *data; + struct type_pf_elem *data; struct hbucket *n, *m; - u32 i, j; + u32 i, j, flags = 0; int ret; /* Try to cleanup once */ @@ -873,10 +881,17 @@ retry: n = hbucket(orig, i); for (j = 0; j < n->pos; j++) { data = ahash_tdata(n, j); +#ifdef IP_SET_HASH_WITH_NETS + flags = 0; + type_pf_data_reset_flags(data, &flags); +#endif m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), 0, - ip_set_timeout_get(type_pf_data_timeout(data))); + ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), flags, + ip_set_timeout_get(type_pf_data_timeout(data))); if (ret < 0) { +#ifdef IP_SET_HASH_WITH_NETS + type_pf_data_flags(data, flags); +#endif read_unlock_bh(&set->lock); ahash_destroy(t); if (ret == -EAGAIN) @@ -1187,6 +1202,7 @@ type_pf_gc_init(struct ip_set *set) #undef type_pf_data_tlist #undef type_pf_data_next #undef type_pf_data_flags +#undef type_pf_data_reset_flags #undef type_pf_data_match #undef type_pf_elem -- cgit v1.2.3 From 866ad9a747bbf5461739fcae6d0a41c8971bbe1d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 3 Apr 2013 19:07:30 -0400 Subject: procfs: preparations for remove_proc_entry() race fixes * leave ->proc_fops alone; make ->pde_users negative instead * trim pde_opener * move relevant code in fs/proc/inode.c Signed-off-by: Al Viro --- include/linux/proc_fs.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index bcc0e10ef1df..947ae7eb63ef 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -60,20 +60,13 @@ struct proc_dir_entry { kgid_t gid; loff_t size; const struct inode_operations *proc_iops; - /* - * NULL ->proc_fops means "PDE is going away RSN" or - * "PDE is just created". In either case, e.g. ->read_proc won't be - * called because it's too late or too early, respectively. - * - * If you're allocating ->proc_fops dynamically, save a pointer - * somewhere. - */ const struct file_operations *proc_fops; struct proc_dir_entry *next, *parent, *subdir; void *data; read_proc_t *read_proc; atomic_t count; /* use count */ - int pde_users; /* number of callers into module in progress */ + int pde_users; /* number of callers into module in progress; */ + /* negative -> it's going away RSN */ struct completion *pde_unload_completion; struct list_head pde_openers; /* who did ->open, but not ->release */ spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */ -- cgit v1.2.3 From 05c0ae21c034a6f7c6f4c0c63a31167ebb4b061f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 4 Apr 2013 16:28:47 -0400 Subject: try a saner locking for pde_opener... Signed-off-by: Al Viro --- include/linux/proc_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 947ae7eb63ef..2781e498f709 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -65,7 +65,7 @@ struct proc_dir_entry { void *data; read_proc_t *read_proc; atomic_t count; /* use count */ - int pde_users; /* number of callers into module in progress; */ + atomic_t in_use; /* number of callers into module in progress; */ /* negative -> it's going away RSN */ struct completion *pde_unload_completion; struct list_head pde_openers; /* who did ->open, but not ->release */ -- cgit v1.2.3 From 066ec1dd44e84a911fe04556e4a9b89f1c83b0cb Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Tue, 9 Apr 2013 19:47:40 +0400 Subject: of: Add stub of_get_parent for non-OF builds Fixes build error on x86_64 allmodconfig, introduced by commit 5ab3a89a741f ("mfd: syscon: Add non-DT support"). drivers/regulator/anatop-regulator.c: In function 'anatop_regulator_probe': drivers/regulator/anatop-regulator.c:134:2: error: implicit declaration of function 'of_get_parent' [-Werror=implicit-function-declaration] Signed-off-by: Alexander Shiyan Acked-by: Rob Herring Signed-off-by: Samuel Ortiz --- include/linux/of.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index a0f129284948..9f5923fc0775 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -353,6 +353,11 @@ static inline struct device_node *of_find_node_by_name(struct device_node *from, return NULL; } +static inline struct device_node *of_get_parent(const struct device_node *node) +{ + return NULL; +} + static inline bool of_have_populated_dt(void) { return false; -- cgit v1.2.3 From 06b332a52293a45324320b6b446a7fa677fb6702 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 9 Apr 2013 11:34:36 -0400 Subject: nfsd4: check backchannel attributes on create_session Make sure the client gives us an adequate backchannel. Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/msg_prot.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index c68a147939a6..aadc6a04e1ac 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -138,6 +138,9 @@ typedef __be32 rpc_fraghdr; #define RPC_MAX_HEADER_WITH_AUTH \ (RPC_CALLHDRSIZE + 2*(2+RPC_MAX_AUTH_SIZE/4)) +#define RPC_MAX_REPHEADER_WITH_AUTH \ + (RPC_REPHDRSIZE + (2 + RPC_MAX_AUTH_SIZE/4)) + /* * RFC1833/RFC3530 rpcbind (v3+) well-known netid's. */ -- cgit v1.2.3 From 479f614110b889d5783acdaec865ede3cdb96b97 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 29 Mar 2013 14:44:42 +0800 Subject: cgroup: Kill subsys.active flag The only user was cpuacct. Acked-by: Tejun Heo Signed-off-by: Li Zefan Acked-by: Peter Zijlstra Link: http://lkml.kernel.org/r/5155385A.4040207@huawei.com Signed-off-by: Ingo Molnar --- include/linux/cgroup.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 900af5964f55..95c02c0e35b3 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -458,7 +458,6 @@ struct cgroup_subsys { void (*bind)(struct cgroup *root); int subsys_id; - int active; int disabled; int early_init; /* -- cgit v1.2.3 From 46fc4c909339f5a84d1679045297d9d2fb596987 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 2 Apr 2013 15:57:26 +0200 Subject: ssb: implement spurious tone avoidance MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit And make use of it in b43. This fixes a regression introduced with 49d55cef5b1925a5c1efb6aaddaa40fc7c693335 b43: N-PHY: implement spurious tone avoidance This commit made BCM4322 use only MCS 0 on channel 13, which of course resulted in performance drop (down to 0.7Mb/s). Reported-by: Stefan Brüns Signed-off-by: Rafał Miłecki Cc: Stable Signed-off-by: John W. Linville --- include/linux/ssb/ssb_driver_chipcommon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb_driver_chipcommon.h b/include/linux/ssb/ssb_driver_chipcommon.h index 9e492be5244b..6fcfe99bd999 100644 --- a/include/linux/ssb/ssb_driver_chipcommon.h +++ b/include/linux/ssb/ssb_driver_chipcommon.h @@ -219,6 +219,7 @@ #define SSB_CHIPCO_PMU_CTL 0x0600 /* PMU control */ #define SSB_CHIPCO_PMU_CTL_ILP_DIV 0xFFFF0000 /* ILP div mask */ #define SSB_CHIPCO_PMU_CTL_ILP_DIV_SHIFT 16 +#define SSB_CHIPCO_PMU_CTL_PLL_UPD 0x00000400 #define SSB_CHIPCO_PMU_CTL_NOILPONW 0x00000200 /* No ILP on wait */ #define SSB_CHIPCO_PMU_CTL_HTREQEN 0x00000100 /* HT req enable */ #define SSB_CHIPCO_PMU_CTL_ALPREQEN 0x00000080 /* ALP req enable */ @@ -667,5 +668,6 @@ enum ssb_pmu_ldo_volt_id { void ssb_pmu_set_ldo_voltage(struct ssb_chipcommon *cc, enum ssb_pmu_ldo_volt_id id, u32 voltage); void ssb_pmu_set_ldo_paref(struct ssb_chipcommon *cc, bool on); +void ssb_pmu_spuravoid_pllupdate(struct ssb_chipcommon *cc, int spuravoid); #endif /* LINUX_SSB_CHIPCO_H_ */ -- cgit v1.2.3 From 10629d711ed780470937ecda50d9ffa0e925a4ee Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 10 Apr 2013 09:56:54 -0600 Subject: PCI: Remove __weak annotation from pcibios_get_phb_of_node decl The __weak annotation on the pcibios_get_phb_of_node() declaration causes *every* definition to be marked "weak." The linker then selects one based on link order, which may be the wrong one. Gabor found that on MIPS, the linker selected the generic implementation from drivers/pci even though arch/mips supplied a definition without the __weak annotation: $ mipsel-openwrt-linux-readelf -s arch/mips/pci/built-in.o \ drivers/pci/built-in.o vmlinux.o | grep pcibios_get_phb_of_node 86: 0000046c 12 FUNC WEAK DEFAULT 2 pcibios_get_phb_of_node 1430: 00012e2c 104 FUNC WEAK DEFAULT 2 pcibios_get_phb_of_node 31898: 0017e4ec 104 FUNC WEAK DEFAULT 2 pcibios_get_phb_of_node This removes the __weak annotation from the pcibios_get_phb_of_node() declaration so arch-specific non-weak implementations work reliably. Suggested-by: Gabor Juhos Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 2461033a7987..67734407fc7f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1823,7 +1823,7 @@ extern void pci_set_bus_of_node(struct pci_bus *bus); extern void pci_release_bus_of_node(struct pci_bus *bus); /* Arch may override this (weak) */ -extern struct device_node * __weak pcibios_get_phb_of_node(struct pci_bus *bus); +extern struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus); static inline struct device_node * pci_device_to_OF_node(const struct pci_dev *pdev) -- cgit v1.2.3 From cdee3904b4ce7c03d1013ed6dd704b43ae7fc2e9 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 9 Jan 2013 10:46:17 +1100 Subject: audit: Syscall rules are not applied to existing processes on non-x86 Commit b05d8447e782 (audit: inline audit_syscall_entry to reduce burden on archs) changed audit_syscall_entry to check for a dummy context before calling __audit_syscall_entry. Unfortunately the dummy context state is maintained in __audit_syscall_entry so once set it never gets cleared, even if the audit rules change. As a result, if there are no auditing rules when a process starts then it will never be subject to any rules added later. x86 doesn't see this because it has an assembly fast path that calls directly into __audit_syscall_entry. I noticed this issue when working on audit performance optimisations. I wrote a set of simple test cases available at: http://ozlabs.org/~anton/junkcode/audit_tests.tar.gz 02_new_rule.py fails without the patch and passes with it. The test case clears all rules, starts a process, adds a rule then verifies the process produces a syscall audit record. Signed-off-by: Anton Blanchard Cc: # 3.3+ Signed-off-by: Eric Paris --- include/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 5a6d718adf34..37464c592c92 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -120,7 +120,7 @@ static inline void audit_syscall_entry(int arch, int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { - if (unlikely(!audit_dummy_context())) + if (unlikely(current->audit_context)) __audit_syscall_entry(arch, major, a0, a1, a2, a3); } static inline void audit_syscall_exit(void *pt_regs) -- cgit v1.2.3 From 2950fa9d3291b90e9b7663b6a409ea37a97a5e35 Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Sun, 7 Apr 2013 16:55:23 +0800 Subject: kernel: audit: beautify code, for extern function, better to check its parameters by itself __audit_socketcall is an extern function. better to check its parameters by itself. also can return error code, when fail (find invalid parameters). also use macro instead of real hard code number also give related comments for it. Signed-off-by: Chen Gang [eparis: fix the return value when !CONFIG_AUDIT] Signed-off-by: Eric Paris --- include/linux/audit.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 37464c592c92..8f92e1dea966 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -84,6 +84,9 @@ extern int audit_classify_arch(int arch); #define AUDIT_TYPE_CHILD_DELETE 3 /* a child being deleted */ #define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ +/* maximized args number that audit_socketcall can process */ +#define AUDITSC_ARGS 6 + struct filename; #ifdef CONFIG_AUDITSYSCALL @@ -190,7 +193,7 @@ extern void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern int __audit_bprm(struct linux_binprm *bprm); -extern void __audit_socketcall(int nargs, unsigned long *args); +extern int __audit_socketcall(int nargs, unsigned long *args); extern int __audit_sockaddr(int len, void *addr); extern void __audit_fd_pair(int fd1, int fd2); extern void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr); @@ -224,10 +227,11 @@ static inline int audit_bprm(struct linux_binprm *bprm) return __audit_bprm(bprm); return 0; } -static inline void audit_socketcall(int nargs, unsigned long *args) +static inline int audit_socketcall(int nargs, unsigned long *args) { if (unlikely(!audit_dummy_context())) - __audit_socketcall(nargs, args); + return __audit_socketcall(nargs, args); + return 0; } static inline int audit_sockaddr(int len, void *addr) { @@ -354,8 +358,10 @@ static inline int audit_bprm(struct linux_binprm *bprm) { return 0; } -static inline void audit_socketcall(int nargs, unsigned long *args) -{ } +static inline int audit_socketcall(int nargs, unsigned long *args) +{ + return 0; +} static inline void audit_fd_pair(int fd1, int fd2) { } static inline int audit_sockaddr(int len, void *addr) -- cgit v1.2.3 From 84cfb6ab484b442d5115eb3baf9db7d74a3ea626 Mon Sep 17 00:00:00 2001 From: Rami Rosen Date: Wed, 10 Apr 2013 14:41:17 +0300 Subject: cgroup: remove bind() method from cgroup_subsys. The bind() method of cgroup_subsys is not used in any of the controllers (cpuset, freezer, blkio, net_cls, memcg, net_prio, devices, perf, hugetlb, cpu and cpuacct) tj: Removed the entry on ->bind() from Documentation/cgroups/cgroups.txt. Also updated a couple paragraphs which were suggesting that dynamic re-binding may be implemented. It's not gonna. Signed-off-by: Rami Rosen Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 515927eebb37..92acf8601ae0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -483,8 +483,6 @@ struct cgroup_subsys { void (*fork)(struct task_struct *task); void (*exit)(struct cgroup *cgrp, struct cgroup *old_cgrp, struct task_struct *task); - void (*bind)(struct cgroup *root); - int subsys_id; int active; int disabled; -- cgit v1.2.3 From 78574cf981cd3d9ae9f6adbd466a772310ec24ff Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 8 Apr 2013 19:00:38 -0700 Subject: cgroup: implement cgroup_is_descendant() A couple controllers want to determine whether two cgroups are in ancestor/descendant relationship. As it's more likely that the descendant is the primary subject of interest and there are other operations focusing on the descendants, let's ask is_descendent rather than is_ancestor. Implementation is trivial as the previous patch guarantees that all ancestors of a cgroup stay accessible as long as the cgroup is accessible. tj: Removed depth optimization, renamed from cgroup_is_ancestor(), rewrote descriptions. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 92acf8601ae0..a2b9d4b13369 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -439,6 +439,7 @@ int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_is_removed(const struct cgroup *cgrp); +bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen); -- cgit v1.2.3 From 6b07a24fc38476e04f591cc17594bc1835b9efdd Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 10 Apr 2013 15:34:14 -0400 Subject: lsm: add the missing documentation for the security_skb_owned_by() hook Unfortunately we didn't catch the missing comments earlier when the patch was merged. Signed-off-by: Paul Moore Signed-off-by: David S. Miller --- include/linux/security.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 6c3a78ace051..032c366ef1c6 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1012,6 +1012,10 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * This hook can be used by the module to update any security state * associated with the TUN device's security structure. * @security pointer to the TUN devices's security structure. + * @skb_owned_by: + * This hook sets the packet's owning sock. + * @skb is the packet. + * @sk the sock which owns the packet. * * Security hooks for XFRM operations. * -- cgit v1.2.3 From 2b78f1e1389aef263071b9edf41c0980b092e601 Mon Sep 17 00:00:00 2001 From: Andreas Larsson Date: Fri, 15 Mar 2013 14:45:38 +0100 Subject: gpio: gpio-generic: Add 16 and 32 bit big endian byte order support There is no general support for 64-bit big endian accesses, so that is left unsupported. Signed-off-by: Andreas Larsson Acked-by: Anton Vorontsov Signed-off-by: Linus Walleij --- include/linux/basic_mmio_gpio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/basic_mmio_gpio.h b/include/linux/basic_mmio_gpio.h index 1c504ca5bdb3..d8a97ec0e2b8 100644 --- a/include/linux/basic_mmio_gpio.h +++ b/include/linux/basic_mmio_gpio.h @@ -72,5 +72,6 @@ int bgpio_init(struct bgpio_chip *bgc, struct device *dev, #define BGPIOF_BIG_ENDIAN BIT(0) #define BGPIOF_UNREADABLE_REG_SET BIT(1) /* reg_set is unreadable */ #define BGPIOF_UNREADABLE_REG_DIR BIT(2) /* reg_dir is unreadable */ +#define BGPIOF_BIG_ENDIAN_BYTE_ORDER BIT(3) #endif /* __BASIC_MMIO_GPIO_H */ -- cgit v1.2.3 From 7fc7acb9a0b0ff3ffdf21818fe0735ebaf4fecb8 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 9 Apr 2013 15:57:25 +0200 Subject: gpio / ACPI: Handle ACPI events in accordance with the spec Commit 0d1c28a (gpiolib-acpi: Add ACPI5 event model support to gpio.) that added support for ACPI events signalled through GPIO interrupts covered only GPIO pins whose numbers are less than or equal to 255. However, there may be GPIO pins with numbers greater than 255 and the ACPI spec (ACPI 5.0, Section 5.6.5.1) requires the _EVT method to be used for handling events corresponding to those pins. Moreover, according to the spec, _EVT is the default mechanism for handling all ACPI events signalled through GPIO interrupts, so if the _Exx/_Lxx method is not present for the given pin, _EVT should be used instead. If present, though, _Exx/_Lxx take precedence over _EVT which shouldn't be executed in that case (ACPI 5.0, Section 5.6.5.3). Modify acpi_gpiochip_request_interrupts() to follow the spec as described above and add acpi_gpiochip_free_interrupts() needed to free interrupts associated with _EVT. Signed-off-by: Rafael J. Wysocki Acked-by: Mika Westerberg Signed-off-by: Linus Walleij --- include/linux/acpi_gpio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi_gpio.h b/include/linux/acpi_gpio.h index b76ebd08ff8e..213135f44333 100644 --- a/include/linux/acpi_gpio.h +++ b/include/linux/acpi_gpio.h @@ -8,6 +8,7 @@ int acpi_get_gpio(char *path, int pin); void acpi_gpiochip_request_interrupts(struct gpio_chip *chip); +void acpi_gpiochip_free_interrupts(struct gpio_chip *chip); #else /* CONFIG_GPIO_ACPI */ @@ -17,6 +18,7 @@ static inline int acpi_get_gpio(char *path, int pin) } static inline void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) { } +static inline void acpi_gpiochip_free_interrupts(struct gpio_chip *chip) { } #endif /* CONFIG_GPIO_ACPI */ -- cgit v1.2.3 From fb72a0590b770f7da6a02bde6b8a147a3d9f6168 Mon Sep 17 00:00:00 2001 From: Soren Brinkmann Date: Wed, 3 Apr 2013 12:17:12 -0700 Subject: clk: Properly handle notifier return values Notifiers may return NOTIFY_(OK|DONE|STOP|BAD). The CCF uses an inconsistent mix of checking against NOTIFY_STOP or NOTIFY_BAD. This inconsistency leaves errors undetected in some cases: clk_set_parent() calls __clk_speculate_rates(), which stops when it hits a NOTIFIER_BAD (STOP is ignored), and passes this value back to the caller. clk_set_parent() compares this return value against NOTIFY_STOP only, ignoring NOTIFY_BAD returns. Use NOTIFY_STOP_MASK to detect a negative notifier return value and document all four return value options. Signed-off-by: Soren Brinkmann Signed-off-by: Mike Turquette --- include/linux/clk.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index b3ac22d0fc1f..9a6d04524b1a 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -28,16 +28,16 @@ struct clk; * PRE_RATE_CHANGE - called immediately before the clk rate is changed, * to indicate that the rate change will proceed. Drivers must * immediately terminate any operations that will be affected by the - * rate change. Callbacks may either return NOTIFY_DONE or - * NOTIFY_STOP. + * rate change. Callbacks may either return NOTIFY_DONE, NOTIFY_OK, + * NOTIFY_STOP or NOTIFY_BAD. * * ABORT_RATE_CHANGE: called if the rate change failed for some reason * after PRE_RATE_CHANGE. In this case, all registered notifiers on * the clk will be called with ABORT_RATE_CHANGE. Callbacks must - * always return NOTIFY_DONE. + * always return NOTIFY_DONE or NOTIFY_OK. * * POST_RATE_CHANGE - called after the clk rate change has successfully - * completed. Callbacks must always return NOTIFY_DONE. + * completed. Callbacks must always return NOTIFY_DONE or NOTIFY_OK. * */ #define PRE_RATE_CHANGE BIT(0) -- cgit v1.2.3 From b8f649f1f531914a30ecb420e7565ee04dccc2ad Mon Sep 17 00:00:00 2001 From: Haojian Zhuang Date: Tue, 9 Apr 2013 18:12:04 +0800 Subject: ARM: pxa: move PXA_GPIO_TO_IRQ macro Since PXA_GPIO_TO_IRQ() & MMP_GPIO_TO_IRQ() macro are depended on arch code, move them from gpio driver to platform driver instead. Signed-off-by: Haojian Zhuang Acked-by: Linus Walleij --- include/linux/gpio-pxa.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/gpio-pxa.h b/include/linux/gpio-pxa.h index d755b28ba635..d90ebbe02ca4 100644 --- a/include/linux/gpio-pxa.h +++ b/include/linux/gpio-pxa.h @@ -14,6 +14,7 @@ extern int pxa_last_gpio; extern int pxa_irq_to_gpio(int irq); struct pxa_gpio_platform_data { + int irq_base; int (*gpio_set_wake)(unsigned int gpio, unsigned int on); }; -- cgit v1.2.3 From bbfce37b3ea11d13a984063a162c898a5fb23b1e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 11 Apr 2013 02:04:55 +0200 Subject: video/s3c: move platform_data out of arch/arm The s3c-fb driver requires header files from the samsung platforms to find its platform_data definition, but this no longer works on multiplatform kernels, so let's move the data into a new header file under include/linux/platform_data. Signed-off-by: Arnd Bergmann Cc: linux-fbdev@vger.kernel.org Acked-by: Jingoo Han Signed-off-by: Tomi Valkeinen --- include/linux/platform_data/video_s3c.h | 54 +++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) create mode 100644 include/linux/platform_data/video_s3c.h (limited to 'include/linux') diff --git a/include/linux/platform_data/video_s3c.h b/include/linux/platform_data/video_s3c.h new file mode 100644 index 000000000000..48883995f47f --- /dev/null +++ b/include/linux/platform_data/video_s3c.h @@ -0,0 +1,54 @@ +#ifndef __PLATFORM_DATA_VIDEO_S3C +#define __PLATFORM_DATA_VIDEO_S3C + +/* S3C_FB_MAX_WIN + * Set to the maximum number of windows that any of the supported hardware + * can use. Since the platform data uses this for an array size, having it + * set to the maximum of any version of the hardware can do is safe. + */ +#define S3C_FB_MAX_WIN (5) + +/** + * struct s3c_fb_pd_win - per window setup data + * @xres : The window X size. + * @yres : The window Y size. + * @virtual_x: The virtual X size. + * @virtual_y: The virtual Y size. + */ +struct s3c_fb_pd_win { + unsigned short default_bpp; + unsigned short max_bpp; + unsigned short xres; + unsigned short yres; + unsigned short virtual_x; + unsigned short virtual_y; +}; + +/** + * struct s3c_fb_platdata - S3C driver platform specific information + * @setup_gpio: Setup the external GPIO pins to the right state to transfer + * the data from the display system to the connected display + * device. + * @vidcon0: The base vidcon0 values to control the panel data format. + * @vidcon1: The base vidcon1 values to control the panel data output. + * @vtiming: Video timing when connected to a RGB type panel. + * @win: The setup data for each hardware window, or NULL for unused. + * @display_mode: The LCD output display mode. + * + * The platform data supplies the video driver with all the information + * it requires to work with the display(s) attached to the machine. It + * controls the initial mode, the number of display windows (0 is always + * the base framebuffer) that are initialised etc. + * + */ +struct s3c_fb_platdata { + void (*setup_gpio)(void); + + struct s3c_fb_pd_win *win[S3C_FB_MAX_WIN]; + struct fb_videomode *vtiming; + + u32 vidcon0; + u32 vidcon1; +}; + +#endif -- cgit v1.2.3 From 3480c0cab6e1a25fdeb63147b0b643b7825a36fb Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Thu, 11 Apr 2013 12:04:18 +0800 Subject: regulator: ab8500-ext: Make the return type of ab8500_ext_regulator_exit() void ab8500_ext_regulator_exit() never fails. Signed-off-by: Axel Lin Acked-by: Bengt Jonsson Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 90b8b5ae9a4e..7c5ff0c55773 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -338,6 +338,6 @@ static inline int ab8500_regulator_debug_exit(struct platform_device *pdev) /* AB8500 external regulator functions. */ int ab8500_ext_regulator_init(struct platform_device *pdev); -int ab8500_ext_regulator_exit(struct platform_device *pdev); +void ab8500_ext_regulator_exit(struct platform_device *pdev); #endif -- cgit v1.2.3 From 4e4098a3e08783cfd75f9fcdab276dc1d46931da Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 11 Apr 2013 11:43:29 -0700 Subject: driver core: handle user namespaces properly with the uid/gid devtmpfs change Now that devtmpfs is caring about uid/gid, we need to use the correct internal types so users who have USER_NS enabled will have things work properly for them. Thanks to Eric for pointing this out, and the patch review. Reported-by: Eric W. Biederman Cc: Kay Sievers Cc: Ming Lei Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 851b85c7101e..88615ccaf23a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -467,7 +467,7 @@ struct device_type { const struct attribute_group **groups; int (*uevent)(struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(struct device *dev, umode_t *mode, - uid_t *uid, gid_t *gid); + kuid_t *uid, kgid_t *gid); void (*release)(struct device *dev); const struct dev_pm_ops *pm; @@ -845,7 +845,7 @@ extern int device_rename(struct device *dev, const char *new_name); extern int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); extern const char *device_get_devnode(struct device *dev, - umode_t *mode, uid_t *uid, gid_t *gid, + umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp); extern void *dev_get_drvdata(const struct device *dev); extern int dev_set_drvdata(struct device *dev, void *data); -- cgit v1.2.3 From ac64995da872c8ae6f74a5556fdad565829985b0 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 11 Apr 2013 04:40:30 +0000 Subject: usbnet: introduce usbnet_link_change API This patch introduces the API of usbnet_link_change, so that usbnet can handle link change centrally, which may help to implement killing traffic URBs for saving USB bus bandwidth and host controller power. Signed-off-by: Ming Lei Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 0e5ac93bab10..eb021b8f53bd 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -245,5 +245,6 @@ extern void usbnet_get_drvinfo(struct net_device *, struct ethtool_drvinfo *); extern int usbnet_nway_reset(struct net_device *net); extern int usbnet_manage_power(struct usbnet *, int); +extern void usbnet_link_change(struct usbnet *, bool, bool); #endif /* __LINUX_USB_USBNET_H */ -- cgit v1.2.3 From 4b49f58fff00e6e9b24eaa31d4c6324393d76b0a Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 11 Apr 2013 04:40:40 +0000 Subject: usbnet: handle link change The link change is detected via the interrupt pipe, and bulk pipes are responsible for transfering packets, so it is reasonable to stop bulk transfer after link is reported as off. Two adavantages may be obtained with stopping bulk transfer after link becomes off: - USB bus bandwidth is saved(USB bus is shared bus except for USB3.0), for example, lots of 'IN' token packets and 'NYET' handshake packets is transfered on 2.0 bus. - probabaly power might be saved for usb host controller since cancelling bulk transfer may disable the asynchronous schedule of host controller. With this patch, when link becomes off, about ~10% performance boost can be found on bulk transfer of anther usb device which is attached to same bus with the usbnet device, see below test on next-20130410: - read from usb mass storage(Sandisk Extreme USB 3.0) on pandaboard with below command after unplugging ethernet cable: dd if=/dev/sda iflag=direct of=/dev/null bs=1M count=800 - without the patch 1, 838860800 bytes (839 MB) copied, 36.2216 s, 23.2 MB/s 2, 838860800 bytes (839 MB) copied, 35.8368 s, 23.4 MB/s 3, 838860800 bytes (839 MB) copied, 35.823 s, 23.4 MB/s 4, 838860800 bytes (839 MB) copied, 35.937 s, 23.3 MB/s 5, 838860800 bytes (839 MB) copied, 35.7365 s, 23.5 MB/s average: 23.6MB/s - with the patch 1, 838860800 bytes (839 MB) copied, 32.3817 s, 25.9 MB/s 2, 838860800 bytes (839 MB) copied, 31.7389 s, 26.4 MB/s 3, 838860800 bytes (839 MB) copied, 32.438 s, 25.9 MB/s 4, 838860800 bytes (839 MB) copied, 32.5492 s, 25.8 MB/s 5, 838860800 bytes (839 MB) copied, 31.6178 s, 26.5 MB/s average: 26.1MB/s Signed-off-by: Ming Lei Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index eb021b8f53bd..da46327fca17 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -72,6 +72,7 @@ struct usbnet { # define EVENT_DEVICE_REPORT_IDLE 8 # define EVENT_NO_RUNTIME_PM 9 # define EVENT_RX_KILL 10 +# define EVENT_LINK_CHANGE 11 }; static inline struct usb_driver *driver_of(struct usb_interface *intf) -- cgit v1.2.3 From d71956960c9dafaafeb19ea010c234abe9d25f10 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 20 Mar 2013 16:56:18 -0500 Subject: OF: add empty of_device_is_available for !OF Add an empty version of of_device_is_available. Signed-off-by: Rob Herring --- include/linux/of.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index a0f129284948..95c8583688bd 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -379,6 +379,11 @@ static inline int of_device_is_compatible(const struct device_node *device, return 0; } +static inline int of_device_is_available(const struct device_node *device) +{ + return 0; +} + static inline struct property *of_find_property(const struct device_node *np, const char *name, int *lenp) -- cgit v1.2.3 From 9ee51f01eee84a108510ac2794b9a9dff8be6d3f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 11 Apr 2013 02:04:48 +0200 Subject: tty: serial/samsung: make register definitions global The registers for the Samsung S3C serial port are currently defined in the platform specific arch/arm/plat-samsung/include/plat/regs-serial.h file, which is not visible to multiplatform capable drivers. Unfortunately, it is not possible to move the file into a more local place as we should normally try to, because the same registers may be used in one of four places: * In the driver itself * In platform-independent ARM code for early debug output * In platform_data definitions * In the Samsung platform power management code I have also found no way to logically split out a platform_data file, other than possibly move everything into include/linux/platform_data, which also felt wrong. The only part of this file that makes sense to keep specific to the s3c24xx platform are the virtual and physical addresses defined here, which are needed in no other location. Signed-off-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_s3c.h | 260 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 260 insertions(+) create mode 100644 include/linux/serial_s3c.h (limited to 'include/linux') diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h new file mode 100644 index 000000000000..907d9d1d56cf --- /dev/null +++ b/include/linux/serial_s3c.h @@ -0,0 +1,260 @@ +/* + * Internal header file for Samsung S3C2410 serial ports (UART0-2) + * + * Copyright (C) 2002 Shane Nay (shane@minirl.com) + * + * Additional defines, Copyright 2003 Simtec Electronics (linux@simtec.co.uk) + * + * Adapted from: + * + * Internal header file for MX1ADS serial ports (UART1 & 2) + * + * Copyright (C) 2002 Shane Nay (shane@minirl.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +*/ + +#ifndef __ASM_ARM_REGS_SERIAL_H +#define __ASM_ARM_REGS_SERIAL_H + +#define S3C2410_URXH (0x24) +#define S3C2410_UTXH (0x20) +#define S3C2410_ULCON (0x00) +#define S3C2410_UCON (0x04) +#define S3C2410_UFCON (0x08) +#define S3C2410_UMCON (0x0C) +#define S3C2410_UBRDIV (0x28) +#define S3C2410_UTRSTAT (0x10) +#define S3C2410_UERSTAT (0x14) +#define S3C2410_UFSTAT (0x18) +#define S3C2410_UMSTAT (0x1C) + +#define S3C2410_LCON_CFGMASK ((0xF<<3)|(0x3)) + +#define S3C2410_LCON_CS5 (0x0) +#define S3C2410_LCON_CS6 (0x1) +#define S3C2410_LCON_CS7 (0x2) +#define S3C2410_LCON_CS8 (0x3) +#define S3C2410_LCON_CSMASK (0x3) + +#define S3C2410_LCON_PNONE (0x0) +#define S3C2410_LCON_PEVEN (0x5 << 3) +#define S3C2410_LCON_PODD (0x4 << 3) +#define S3C2410_LCON_PMASK (0x7 << 3) + +#define S3C2410_LCON_STOPB (1<<2) +#define S3C2410_LCON_IRM (1<<6) + +#define S3C2440_UCON_CLKMASK (3<<10) +#define S3C2440_UCON_CLKSHIFT (10) +#define S3C2440_UCON_PCLK (0<<10) +#define S3C2440_UCON_UCLK (1<<10) +#define S3C2440_UCON_PCLK2 (2<<10) +#define S3C2440_UCON_FCLK (3<<10) +#define S3C2443_UCON_EPLL (3<<10) + +#define S3C6400_UCON_CLKMASK (3<<10) +#define S3C6400_UCON_CLKSHIFT (10) +#define S3C6400_UCON_PCLK (0<<10) +#define S3C6400_UCON_PCLK2 (2<<10) +#define S3C6400_UCON_UCLK0 (1<<10) +#define S3C6400_UCON_UCLK1 (3<<10) + +#define S3C2440_UCON2_FCLK_EN (1<<15) +#define S3C2440_UCON0_DIVMASK (15 << 12) +#define S3C2440_UCON1_DIVMASK (15 << 12) +#define S3C2440_UCON2_DIVMASK (7 << 12) +#define S3C2440_UCON_DIVSHIFT (12) + +#define S3C2412_UCON_CLKMASK (3<<10) +#define S3C2412_UCON_CLKSHIFT (10) +#define S3C2412_UCON_UCLK (1<<10) +#define S3C2412_UCON_USYSCLK (3<<10) +#define S3C2412_UCON_PCLK (0<<10) +#define S3C2412_UCON_PCLK2 (2<<10) + +#define S3C2410_UCON_CLKMASK (1 << 10) +#define S3C2410_UCON_CLKSHIFT (10) +#define S3C2410_UCON_UCLK (1<<10) +#define S3C2410_UCON_SBREAK (1<<4) + +#define S3C2410_UCON_TXILEVEL (1<<9) +#define S3C2410_UCON_RXILEVEL (1<<8) +#define S3C2410_UCON_TXIRQMODE (1<<2) +#define S3C2410_UCON_RXIRQMODE (1<<0) +#define S3C2410_UCON_RXFIFO_TOI (1<<7) +#define S3C2443_UCON_RXERR_IRQEN (1<<6) +#define S3C2443_UCON_LOOPBACK (1<<5) + +#define S3C2410_UCON_DEFAULT (S3C2410_UCON_TXILEVEL | \ + S3C2410_UCON_RXILEVEL | \ + S3C2410_UCON_TXIRQMODE | \ + S3C2410_UCON_RXIRQMODE | \ + S3C2410_UCON_RXFIFO_TOI) + +#define S3C2410_UFCON_FIFOMODE (1<<0) +#define S3C2410_UFCON_TXTRIG0 (0<<6) +#define S3C2410_UFCON_RXTRIG8 (1<<4) +#define S3C2410_UFCON_RXTRIG12 (2<<4) + +/* S3C2440 FIFO trigger levels */ +#define S3C2440_UFCON_RXTRIG1 (0<<4) +#define S3C2440_UFCON_RXTRIG8 (1<<4) +#define S3C2440_UFCON_RXTRIG16 (2<<4) +#define S3C2440_UFCON_RXTRIG32 (3<<4) + +#define S3C2440_UFCON_TXTRIG0 (0<<6) +#define S3C2440_UFCON_TXTRIG16 (1<<6) +#define S3C2440_UFCON_TXTRIG32 (2<<6) +#define S3C2440_UFCON_TXTRIG48 (3<<6) + +#define S3C2410_UFCON_RESETBOTH (3<<1) +#define S3C2410_UFCON_RESETTX (1<<2) +#define S3C2410_UFCON_RESETRX (1<<1) + +#define S3C2410_UFCON_DEFAULT (S3C2410_UFCON_FIFOMODE | \ + S3C2410_UFCON_TXTRIG0 | \ + S3C2410_UFCON_RXTRIG8 ) + +#define S3C2410_UMCOM_AFC (1<<4) +#define S3C2410_UMCOM_RTS_LOW (1<<0) + +#define S3C2412_UMCON_AFC_63 (0<<5) /* same as s3c2443 */ +#define S3C2412_UMCON_AFC_56 (1<<5) +#define S3C2412_UMCON_AFC_48 (2<<5) +#define S3C2412_UMCON_AFC_40 (3<<5) +#define S3C2412_UMCON_AFC_32 (4<<5) +#define S3C2412_UMCON_AFC_24 (5<<5) +#define S3C2412_UMCON_AFC_16 (6<<5) +#define S3C2412_UMCON_AFC_8 (7<<5) + +#define S3C2410_UFSTAT_TXFULL (1<<9) +#define S3C2410_UFSTAT_RXFULL (1<<8) +#define S3C2410_UFSTAT_TXMASK (15<<4) +#define S3C2410_UFSTAT_TXSHIFT (4) +#define S3C2410_UFSTAT_RXMASK (15<<0) +#define S3C2410_UFSTAT_RXSHIFT (0) + +/* UFSTAT S3C2443 same as S3C2440 */ +#define S3C2440_UFSTAT_TXFULL (1<<14) +#define S3C2440_UFSTAT_RXFULL (1<<6) +#define S3C2440_UFSTAT_TXSHIFT (8) +#define S3C2440_UFSTAT_RXSHIFT (0) +#define S3C2440_UFSTAT_TXMASK (63<<8) +#define S3C2440_UFSTAT_RXMASK (63) + +#define S3C2410_UTRSTAT_TXE (1<<2) +#define S3C2410_UTRSTAT_TXFE (1<<1) +#define S3C2410_UTRSTAT_RXDR (1<<0) + +#define S3C2410_UERSTAT_OVERRUN (1<<0) +#define S3C2410_UERSTAT_FRAME (1<<2) +#define S3C2410_UERSTAT_BREAK (1<<3) +#define S3C2443_UERSTAT_PARITY (1<<1) + +#define S3C2410_UERSTAT_ANY (S3C2410_UERSTAT_OVERRUN | \ + S3C2410_UERSTAT_FRAME | \ + S3C2410_UERSTAT_BREAK) + +#define S3C2410_UMSTAT_CTS (1<<0) +#define S3C2410_UMSTAT_DeltaCTS (1<<2) + +#define S3C2443_DIVSLOT (0x2C) + +/* S3C64XX interrupt registers. */ +#define S3C64XX_UINTP 0x30 +#define S3C64XX_UINTSP 0x34 +#define S3C64XX_UINTM 0x38 + +#define S3C64XX_UINTM_RXD (0) +#define S3C64XX_UINTM_TXD (2) +#define S3C64XX_UINTM_RXD_MSK (1 << S3C64XX_UINTM_RXD) +#define S3C64XX_UINTM_TXD_MSK (1 << S3C64XX_UINTM_TXD) + +/* Following are specific to S5PV210 */ +#define S5PV210_UCON_CLKMASK (1<<10) +#define S5PV210_UCON_CLKSHIFT (10) +#define S5PV210_UCON_PCLK (0<<10) +#define S5PV210_UCON_UCLK (1<<10) + +#define S5PV210_UFCON_TXTRIG0 (0<<8) +#define S5PV210_UFCON_TXTRIG4 (1<<8) +#define S5PV210_UFCON_TXTRIG8 (2<<8) +#define S5PV210_UFCON_TXTRIG16 (3<<8) +#define S5PV210_UFCON_TXTRIG32 (4<<8) +#define S5PV210_UFCON_TXTRIG64 (5<<8) +#define S5PV210_UFCON_TXTRIG128 (6<<8) +#define S5PV210_UFCON_TXTRIG256 (7<<8) + +#define S5PV210_UFCON_RXTRIG1 (0<<4) +#define S5PV210_UFCON_RXTRIG4 (1<<4) +#define S5PV210_UFCON_RXTRIG8 (2<<4) +#define S5PV210_UFCON_RXTRIG16 (3<<4) +#define S5PV210_UFCON_RXTRIG32 (4<<4) +#define S5PV210_UFCON_RXTRIG64 (5<<4) +#define S5PV210_UFCON_RXTRIG128 (6<<4) +#define S5PV210_UFCON_RXTRIG256 (7<<4) + +#define S5PV210_UFSTAT_TXFULL (1<<24) +#define S5PV210_UFSTAT_RXFULL (1<<8) +#define S5PV210_UFSTAT_TXMASK (255<<16) +#define S5PV210_UFSTAT_TXSHIFT (16) +#define S5PV210_UFSTAT_RXMASK (255<<0) +#define S5PV210_UFSTAT_RXSHIFT (0) + +#define S3C2410_UCON_CLKSEL0 (1 << 0) +#define S3C2410_UCON_CLKSEL1 (1 << 1) +#define S3C2410_UCON_CLKSEL2 (1 << 2) +#define S3C2410_UCON_CLKSEL3 (1 << 3) + +/* Default values for s5pv210 UCON and UFCON uart registers */ +#define S5PV210_UCON_DEFAULT (S3C2410_UCON_TXILEVEL | \ + S3C2410_UCON_RXILEVEL | \ + S3C2410_UCON_TXIRQMODE | \ + S3C2410_UCON_RXIRQMODE | \ + S3C2410_UCON_RXFIFO_TOI | \ + S3C2443_UCON_RXERR_IRQEN) + +#define S5PV210_UFCON_DEFAULT (S3C2410_UFCON_FIFOMODE | \ + S5PV210_UFCON_TXTRIG4 | \ + S5PV210_UFCON_RXTRIG4) + +#ifndef __ASSEMBLY__ + +/* configuration structure for per-machine configurations for the + * serial port + * + * the pointer is setup by the machine specific initialisation from the + * arch/arm/mach-s3c2410/ directory. +*/ + +struct s3c2410_uartcfg { + unsigned char hwport; /* hardware port number */ + unsigned char unused; + unsigned short flags; + upf_t uart_flags; /* default uart flags */ + unsigned int clk_sel; + + unsigned int has_fracval; + + unsigned long ucon; /* value of ucon for port */ + unsigned long ulcon; /* value of ulcon for port */ + unsigned long ufcon; /* value of ufcon for port */ +}; + +#endif /* __ASSEMBLY__ */ + +#endif /* __ASM_ARM_REGS_SERIAL_H */ + -- cgit v1.2.3 From 12028d2d216220618f76284af5f8ed510b11da55 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 3 Apr 2013 13:56:54 +0300 Subject: gpiolib-acpi: introduce acpi_get_gpio_by_index() helper Instead of open-coding ACPI GPIO resource lookup in each driver, we provide a helper function analogous to Device Tree version that allows drivers to specify which GPIO resource they are interested (using an index to the GPIO resources). The function then finds out the correct resource, translates the ACPI GPIO number to the corresponding Linux GPIO number and returns that. Signed-off-by: Mika Westerberg Acked-by: Rafael J. Wysocki Signed-off-by: Linus Walleij --- include/linux/acpi_gpio.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi_gpio.h b/include/linux/acpi_gpio.h index 213135f44333..4c120a1e0ca3 100644 --- a/include/linux/acpi_gpio.h +++ b/include/linux/acpi_gpio.h @@ -1,12 +1,23 @@ #ifndef _LINUX_ACPI_GPIO_H_ #define _LINUX_ACPI_GPIO_H_ +#include #include #include +/** + * struct acpi_gpio_info - ACPI GPIO specific information + * @gpioint: if %true this GPIO is of type GpioInt otherwise type is GpioIo + */ +struct acpi_gpio_info { + bool gpioint; +}; + #ifdef CONFIG_GPIO_ACPI int acpi_get_gpio(char *path, int pin); +int acpi_get_gpio_by_index(struct device *dev, int index, + struct acpi_gpio_info *info); void acpi_gpiochip_request_interrupts(struct gpio_chip *chip); void acpi_gpiochip_free_interrupts(struct gpio_chip *chip); @@ -17,6 +28,12 @@ static inline int acpi_get_gpio(char *path, int pin) return -ENODEV; } +static inline int acpi_get_gpio_by_index(struct device *dev, int index, + struct acpi_gpio_info *info) +{ + return -ENODEV; +} + static inline void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) { } static inline void acpi_gpiochip_free_interrupts(struct gpio_chip *chip) { } -- cgit v1.2.3 From ae4647fb7654676fc44a97e86eb35f9f06b99f66 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 12 Apr 2013 00:03:42 -0400 Subject: jbd2: reduce journal_head size Remove unused t_cow_tid field (ext4 copy-on-write support doesn't seem to be happening) and change b_modified and b_jlist to bitfields thus saving 8 bytes in the structure. Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" Reviewed-by: Zheng Liu --- include/linux/journal-head.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/journal-head.h b/include/linux/journal-head.h index c18b46f8aeeb..13a3da25ff07 100644 --- a/include/linux/journal-head.h +++ b/include/linux/journal-head.h @@ -31,21 +31,14 @@ struct journal_head { /* * Journalling list for this buffer [jbd_lock_bh_state()] */ - unsigned b_jlist; + unsigned b_jlist:4; /* * This flag signals the buffer has been modified by * the currently running transaction * [jbd_lock_bh_state()] */ - unsigned b_modified; - - /* - * This feild tracks the last transaction id in which this buffer - * has been cowed - * [jbd_lock_bh_state()] - */ - tid_t b_cow_tid; + unsigned b_modified:1; /* * Copy of the buffer data frozen for writing to the log. -- cgit v1.2.3 From 9b89f6ba2ab56e4d9c00e7e591d6bc333137895e Mon Sep 17 00:00:00 2001 From: Andrei Epure Date: Thu, 11 Apr 2013 20:30:29 +0300 Subject: sched: Document task_struct::personality field Signed-off-by: Andrei Epure Cc: Linus Torvalds Cc: Andrew Morton Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1365701429-4721-1-git-send-email-epure.andrei@gmail.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9004f6e19eac..6bdaa73ede13 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1105,8 +1105,10 @@ struct task_struct { int exit_code, exit_signal; int pdeath_signal; /* The signal sent when the parent dies */ unsigned int jobctl; /* JOBCTL_*, siglock protected */ - /* ??? */ + + /* Used for emulating ABI behavior of previous Linux versions */ unsigned int personality; + unsigned did_exec:1; unsigned in_execve:1; /* Tell the LSMs that the process is doing an * execve */ -- cgit v1.2.3 From 61fc41317666be400802ac793f47de816ef7bd57 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 19 Nov 2012 17:23:13 +0100 Subject: reset: Add reset controller API This adds a simple API for devices to request being reset by separate reset controller hardware and implements the reset signal device tree binding. Signed-off-by: Philipp Zabel Reviewed-by: Stephen Warren Reviewed-by: Shawn Guo Reviewed-by: Marek Vasut Reviewed-by: Pavel Machek --- include/linux/reset-controller.h | 51 ++++++++++++++++++++++++++++++++++++++++ include/linux/reset.h | 17 ++++++++++++++ 2 files changed, 68 insertions(+) create mode 100644 include/linux/reset-controller.h create mode 100644 include/linux/reset.h (limited to 'include/linux') diff --git a/include/linux/reset-controller.h b/include/linux/reset-controller.h new file mode 100644 index 000000000000..2f61311ae3e0 --- /dev/null +++ b/include/linux/reset-controller.h @@ -0,0 +1,51 @@ +#ifndef _LINUX_RESET_CONTROLLER_H_ +#define _LINUX_RESET_CONTROLLER_H_ + +#include + +struct reset_controller_dev; + +/** + * struct reset_control_ops + * + * @reset: for self-deasserting resets, does all necessary + * things to reset the device + * @assert: manually assert the reset line, if supported + * @deassert: manually deassert the reset line, if supported + */ +struct reset_control_ops { + int (*reset)(struct reset_controller_dev *rcdev, unsigned long id); + int (*assert)(struct reset_controller_dev *rcdev, unsigned long id); + int (*deassert)(struct reset_controller_dev *rcdev, unsigned long id); +}; + +struct module; +struct device_node; + +/** + * struct reset_controller_dev - reset controller entity that might + * provide multiple reset controls + * @ops: a pointer to device specific struct reset_control_ops + * @owner: kernel module of the reset controller driver + * @list: internal list of reset controller devices + * @of_node: corresponding device tree node as phandle target + * @of_reset_n_cells: number of cells in reset line specifiers + * @of_xlate: translation function to translate from specifier as found in the + * device tree to id as given to the reset control ops + * @nr_resets: number of reset controls in this reset controller device + */ +struct reset_controller_dev { + struct reset_control_ops *ops; + struct module *owner; + struct list_head list; + struct device_node *of_node; + int of_reset_n_cells; + int (*of_xlate)(struct reset_controller_dev *rcdev, + const struct of_phandle_args *reset_spec); + unsigned int nr_resets; +}; + +int reset_controller_register(struct reset_controller_dev *rcdev); +void reset_controller_unregister(struct reset_controller_dev *rcdev); + +#endif diff --git a/include/linux/reset.h b/include/linux/reset.h new file mode 100644 index 000000000000..6082247feab1 --- /dev/null +++ b/include/linux/reset.h @@ -0,0 +1,17 @@ +#ifndef _LINUX_RESET_H_ +#define _LINUX_RESET_H_ + +struct device; +struct reset_control; + +int reset_control_reset(struct reset_control *rstc); +int reset_control_assert(struct reset_control *rstc); +int reset_control_deassert(struct reset_control *rstc); + +struct reset_control *reset_control_get(struct device *dev, const char *id); +void reset_control_put(struct reset_control *rstc); +struct reset_control *devm_reset_control_get(struct device *dev, const char *id); + +int device_reset(struct device *dev); + +#endif -- cgit v1.2.3 From f2530dc71cf0822f90bb63ea4600caaef33a66bb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 9 Apr 2013 09:33:34 +0200 Subject: kthread: Prevent unpark race which puts threads on the wrong cpu The smpboot threads rely on the park/unpark mechanism which binds per cpu threads on a particular core. Though the functionality is racy: CPU0 CPU1 CPU2 unpark(T) wake_up_process(T) clear(SHOULD_PARK) T runs leave parkme() due to !SHOULD_PARK bind_to(CPU2) BUG_ON(wrong CPU) We cannot let the tasks move themself to the target CPU as one of those tasks is actually the migration thread itself, which requires that it starts running on the target cpu right away. The solution to this problem is to prevent wakeups in park mode which are not from unpark(). That way we can guarantee that the association of the task to the target cpu is working correctly. Add a new task state (TASK_PARKED) which prevents other wakeups and use this state explicitly for the unpark wakeup. Peter noticed: Also, since the task state is visible to userspace and all the parked tasks are still in the PID space, its a good hint in ps and friends that these tasks aren't really there for the moment. The migration thread has another related issue. CPU0 CPU1 Bring up CPU2 create_thread(T) park(T) wait_for_completion() parkme() complete() sched_set_stop_task() schedule(TASK_PARKED) The sched_set_stop_task() call is issued while the task is on the runqueue of CPU1 and that confuses the hell out of the stop_task class on that cpu. So we need the same synchronizaion before sched_set_stop_task(). Reported-by: Dave Jones Reported-and-tested-by: Dave Hansen Reported-and-tested-by: Borislav Petkov Acked-by: Peter Ziljstra Cc: Srivatsa S. Bhat Cc: dhillf@gmail.com Cc: Ingo Molnar Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304091635430.21884@ionos Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6ddbfb..e692a022527b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -163,9 +163,10 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) #define TASK_DEAD 64 #define TASK_WAKEKILL 128 #define TASK_WAKING 256 -#define TASK_STATE_MAX 512 +#define TASK_PARKED 512 +#define TASK_STATE_MAX 1024 -#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW" +#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP" extern char ___assert_task_state[1 - 2*!!( sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)]; -- cgit v1.2.3 From 788437273fa8b824810ea9a23f7ed4d7fdb2949a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 11 Apr 2013 22:42:03 +0200 Subject: spi: s3c64xx: move to generic dmaengine API The spi-s3c64xx uses a Samsung proprietary interface for talking to the DMA engine, which does not work with multiplatform kernels. This version of the patch leaves the old code in place, behind an #ifdef. This can be removed in the future, after the s3c64xx platform start supporting the regular dmaengine interface. An earlier version of this patch was tested successfully on exynos5250 by Padma Venkat. The conversion was rather mechanical, since the samsung interface is just a shallow wrapper around the dmaengine interface. Signed-off-by: Arnd Bergmann --- include/linux/platform_data/spi-s3c64xx.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h index ceba18d23a5a..8447f634c7f5 100644 --- a/include/linux/platform_data/spi-s3c64xx.h +++ b/include/linux/platform_data/spi-s3c64xx.h @@ -11,6 +11,8 @@ #ifndef __S3C64XX_PLAT_SPI_H #define __S3C64XX_PLAT_SPI_H +#include + struct platform_device; /** @@ -38,6 +40,7 @@ struct s3c64xx_spi_info { int src_clk_nr; int num_cs; int (*cfg_gpio)(void); + dma_filter_fn filter; }; /** -- cgit v1.2.3 From 26d5bbe5ba2073fc7ef9e69a55543b2376f5bad0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 12 Apr 2013 10:29:04 -0700 Subject: Revert "cgroup: remove bind() method from cgroup_subsys." This reverts commit 84cfb6ab484b442d5115eb3baf9db7d74a3ea626. There are scheduled changes which make use of the removed callback. Signed-off-by: Tejun Heo Cc: Rami Rosen Cc: Li Zefan --- include/linux/cgroup.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index a2b9d4b13369..45aee0fc6b98 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -484,6 +484,8 @@ struct cgroup_subsys { void (*fork)(struct task_struct *task); void (*exit)(struct cgroup *cgrp, struct cgroup *old_cgrp, struct task_struct *task); + void (*bind)(struct cgroup *root); + int subsys_id; int active; int disabled; -- cgit v1.2.3 From 79b16641efabd14944dbfc2fde2ae1e8ae8413bc Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Fri, 12 Apr 2013 13:57:44 +0200 Subject: clk: add device tree fixed-factor-clock binding support Add support for DT "fixed-factor-clock" binding to the common fixed factor clock support. Signed-off-by: Gregory CLEMENT Tested-by: Christian Ruppert Signed-off-by: Mike Turquette --- include/linux/clk-provider.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 9fdfae74d669..e7b7cbc53815 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -325,6 +325,8 @@ struct clk *clk_register_mux_table(struct device *dev, const char *name, void __iomem *reg, u8 shift, u32 mask, u8 clk_mux_flags, u32 *table, spinlock_t *lock); +void of_fixed_factor_clk_setup(struct device_node *node); + /** * struct clk_fixed_factor - fixed multiplier and divider clock * -- cgit v1.2.3 From 9abd5f0555df6cd36130feb742f1def6d99c60fe Mon Sep 17 00:00:00 2001 From: Sebastian Hesselbarth Date: Thu, 11 Apr 2013 21:42:29 +0200 Subject: clk: add si5351 i2c common clock driver This patch adds a common clock driver for Silicon Labs Si5351a/b/c i2c programmable clock generators. Currently, the driver does not support VXCO feature of si5351b. Passing platform_data or DT bindings selectively allows to overwrite stored Si5351 configuration which is very helpful for clock generators with empty eeprom configuration. Corresponding device tree binding documentation is also added. Signed-off-by: Sebastian Hesselbarth Tested-by: Daniel Mack Acked-by: Guenter Roeck Tested-by: Michal Bachraty Signed-off-by: Mike Turquette --- include/linux/platform_data/si5351.h | 114 +++++++++++++++++++++++++++++++++++ 1 file changed, 114 insertions(+) create mode 100644 include/linux/platform_data/si5351.h (limited to 'include/linux') diff --git a/include/linux/platform_data/si5351.h b/include/linux/platform_data/si5351.h new file mode 100644 index 000000000000..92dabcaf6499 --- /dev/null +++ b/include/linux/platform_data/si5351.h @@ -0,0 +1,114 @@ +/* + * Si5351A/B/C programmable clock generator platform_data. + */ + +#ifndef __LINUX_PLATFORM_DATA_SI5351_H__ +#define __LINUX_PLATFORM_DATA_SI5351_H__ + +struct clk; + +/** + * enum si5351_variant - SiLabs Si5351 chip variant + * @SI5351_VARIANT_A: Si5351A (8 output clocks, XTAL input) + * @SI5351_VARIANT_A3: Si5351A MSOP10 (3 output clocks, XTAL input) + * @SI5351_VARIANT_B: Si5351B (8 output clocks, XTAL/VXCO input) + * @SI5351_VARIANT_C: Si5351C (8 output clocks, XTAL/CLKIN input) + */ +enum si5351_variant { + SI5351_VARIANT_A = 1, + SI5351_VARIANT_A3 = 2, + SI5351_VARIANT_B = 3, + SI5351_VARIANT_C = 4, +}; + +/** + * enum si5351_pll_src - Si5351 pll clock source + * @SI5351_PLL_SRC_DEFAULT: default, do not change eeprom config + * @SI5351_PLL_SRC_XTAL: pll source clock is XTAL input + * @SI5351_PLL_SRC_CLKIN: pll source clock is CLKIN input (Si5351C only) + */ +enum si5351_pll_src { + SI5351_PLL_SRC_DEFAULT = 0, + SI5351_PLL_SRC_XTAL = 1, + SI5351_PLL_SRC_CLKIN = 2, +}; + +/** + * enum si5351_multisynth_src - Si5351 multisynth clock source + * @SI5351_MULTISYNTH_SRC_DEFAULT: default, do not change eeprom config + * @SI5351_MULTISYNTH_SRC_VCO0: multisynth source clock is VCO0 + * @SI5351_MULTISYNTH_SRC_VCO1: multisynth source clock is VCO1/VXCO + */ +enum si5351_multisynth_src { + SI5351_MULTISYNTH_SRC_DEFAULT = 0, + SI5351_MULTISYNTH_SRC_VCO0 = 1, + SI5351_MULTISYNTH_SRC_VCO1 = 2, +}; + +/** + * enum si5351_clkout_src - Si5351 clock output clock source + * @SI5351_CLKOUT_SRC_DEFAULT: default, do not change eeprom config + * @SI5351_CLKOUT_SRC_MSYNTH_N: clkout N source clock is multisynth N + * @SI5351_CLKOUT_SRC_MSYNTH_0_4: clkout N source clock is multisynth 0 (N<4) + * or 4 (N>=4) + * @SI5351_CLKOUT_SRC_XTAL: clkout N source clock is XTAL + * @SI5351_CLKOUT_SRC_CLKIN: clkout N source clock is CLKIN (Si5351C only) + */ +enum si5351_clkout_src { + SI5351_CLKOUT_SRC_DEFAULT = 0, + SI5351_CLKOUT_SRC_MSYNTH_N = 1, + SI5351_CLKOUT_SRC_MSYNTH_0_4 = 2, + SI5351_CLKOUT_SRC_XTAL = 3, + SI5351_CLKOUT_SRC_CLKIN = 4, +}; + +/** + * enum si5351_drive_strength - Si5351 clock output drive strength + * @SI5351_DRIVE_DEFAULT: default, do not change eeprom config + * @SI5351_DRIVE_2MA: 2mA clock output drive strength + * @SI5351_DRIVE_4MA: 4mA clock output drive strength + * @SI5351_DRIVE_6MA: 6mA clock output drive strength + * @SI5351_DRIVE_8MA: 8mA clock output drive strength + */ +enum si5351_drive_strength { + SI5351_DRIVE_DEFAULT = 0, + SI5351_DRIVE_2MA = 2, + SI5351_DRIVE_4MA = 4, + SI5351_DRIVE_6MA = 6, + SI5351_DRIVE_8MA = 8, +}; + +/** + * struct si5351_clkout_config - Si5351 clock output configuration + * @clkout: clkout number + * @multisynth_src: multisynth source clock + * @clkout_src: clkout source clock + * @pll_master: if true, clkout can also change pll rate + * @drive: output drive strength + * @rate: initial clkout rate, or default if 0 + */ +struct si5351_clkout_config { + enum si5351_multisynth_src multisynth_src; + enum si5351_clkout_src clkout_src; + enum si5351_drive_strength drive; + bool pll_master; + unsigned long rate; +}; + +/** + * struct si5351_platform_data - Platform data for the Si5351 clock driver + * @variant: Si5351 chip variant + * @clk_xtal: xtal input clock + * @clk_clkin: clkin input clock + * @pll_src: array of pll source clock setting + * @clkout: array of clkout configuration + */ +struct si5351_platform_data { + enum si5351_variant variant; + struct clk *clk_xtal; + struct clk *clk_clkin; + enum si5351_pll_src pll_src[2]; + struct si5351_clkout_config clkout[8]; +}; + +#endif -- cgit v1.2.3 From 0d3e3350d5871c53464be4c92d57198744247005 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 4 Apr 2013 16:41:06 +0300 Subject: mmc: core: fix performance regression initializing MMC host controllers Commit fa5501890d8974301042e0202d342a6cbe8609f4 introduced a performance regression by adding mmc_power_up() to mmc_start_host(). mmc_power_up() is not necessary to host controller initialization, it is part of card initialization and is performed anyway asynchronously. This patch allows a driver to leave the power up in asynchronous code (as it was before). On my current target platform this reduces driver initialization from: [ 1.313220] initcall sdhci_acpi_driver_init+0x0/0x12 returned 0 after 102008 usecs to this: [ 1.217209] initcall sdhci_acpi_driver_init+0x0/0x12 returned 0 after 8331 usecs Signed-off-by: Adrian Hunter Acked-by: Ulf Hansson Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 17d714801e94..8873e8349597 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -280,6 +280,7 @@ struct mmc_host { #define MMC_CAP2_PACKED_WR (1 << 13) /* Allow packed write */ #define MMC_CAP2_PACKED_CMD (MMC_CAP2_PACKED_RD | \ MMC_CAP2_PACKED_WR) +#define MMC_CAP2_NO_PRESCAN_POWERUP (1 << 14) /* Don't power up before scan */ mmc_pm_flag_t pm_caps; /* supported pm features */ -- cgit v1.2.3 From d3a1c7be8361e2fbb6affbdb19de47ca48d6c402 Mon Sep 17 00:00:00 2001 From: Mike Turquette Date: Thu, 11 Apr 2013 11:31:36 -0700 Subject: clk: composite: rename 'div' references to 'rate' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename all div_hw and div_ops related variables and functions to use rate_hw, rate_ops, etc. This is to make the rate-change portion of the composite clk implementation more generic. A patch following this one will allow for fixed-rate clocks to reuse this infrastructure. Signed-off-by: Mike Turquette Reviewed-by: Prashant Gaikwad Tested-by: Emilio López Cc: Gregory CLEMENT --- include/linux/clk-provider.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index e7b7cbc53815..11860985fecb 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -354,11 +354,11 @@ struct clk *clk_register_fixed_factor(struct device *dev, const char *name, * struct clk_composite - aggregate clock of mux, divider and gate clocks * * @hw: handle between common and hardware-specific interfaces - * @mux_hw: handle between composite and hardware-specifix mux clock - * @div_hw: handle between composite and hardware-specifix divider clock - * @gate_hw: handle between composite and hardware-specifix gate clock + * @mux_hw: handle between composite and hardware-specific mux clock + * @rate_hw: handle between composite and hardware-specific rate clock + * @gate_hw: handle between composite and hardware-specific gate clock * @mux_ops: clock ops for mux - * @div_ops: clock ops for divider + * @rate_ops: clock ops for rate * @gate_ops: clock ops for gate */ struct clk_composite { @@ -366,18 +366,18 @@ struct clk_composite { struct clk_ops ops; struct clk_hw *mux_hw; - struct clk_hw *div_hw; + struct clk_hw *rate_hw; struct clk_hw *gate_hw; const struct clk_ops *mux_ops; - const struct clk_ops *div_ops; + const struct clk_ops *rate_ops; const struct clk_ops *gate_ops; }; struct clk *clk_register_composite(struct device *dev, const char *name, const char **parent_names, int num_parents, struct clk_hw *mux_hw, const struct clk_ops *mux_ops, - struct clk_hw *div_hw, const struct clk_ops *div_ops, + struct clk_hw *rate_hw, const struct clk_ops *rate_ops, struct clk_hw *gate_hw, const struct clk_ops *gate_ops, unsigned long flags); -- cgit v1.2.3 From 1640f28f6b839637d9b82a3c4a19120601e59c66 Mon Sep 17 00:00:00 2001 From: Franky Lin Date: Thu, 11 Apr 2013 13:28:51 +0200 Subject: brcmfmac: add support for dongle ARM CR4 core Newer WiFi chip use ARM CR4 core to achieve higher performance. Add necessary code for host driver in order to support CR4 core. Reviewed-by: Arend van Spriel Reviewed-by: Pieter-Paul Giesberts Signed-off-by: Franky Lin Signed-off-by: Arend van Spriel Signed-off-by: John W. Linville --- include/linux/bcma/bcma.h | 1 + include/linux/bcma/bcma_regs.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index 0ab6712fd76b..f14a98a79c9d 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -134,6 +134,7 @@ struct bcma_host_ops { #define BCMA_CORE_I2S 0x834 #define BCMA_CORE_SDR_DDR1_MEM_CTL 0x835 /* SDR/DDR1 memory controller core */ #define BCMA_CORE_SHIM 0x837 /* SHIM component in ubus/6362 */ +#define BCMA_CORE_ARM_CR4 0x83e #define BCMA_CORE_DEFAULT 0xFFF #define BCMA_MAX_NR_CORES 16 diff --git a/include/linux/bcma/bcma_regs.h b/include/linux/bcma/bcma_regs.h index 7e8104bb7a7e..917dcd7965e7 100644 --- a/include/linux/bcma/bcma_regs.h +++ b/include/linux/bcma/bcma_regs.h @@ -37,6 +37,7 @@ #define BCMA_IOST_BIST_DONE 0x8000 #define BCMA_RESET_CTL 0x0800 #define BCMA_RESET_CTL_RESET 0x0001 +#define BCMA_RESET_ST 0x0804 /* BCMA PCI config space registers. */ #define BCMA_PCI_PMCSR 0x44 -- cgit v1.2.3 From 1e9ab4dd258ecbb0f1c377fd4dbe227cdb93d9bd Mon Sep 17 00:00:00 2001 From: Piotr Haber Date: Thu, 11 Apr 2013 13:28:52 +0200 Subject: brcmfmac: setup SDIO reset behavior Set device in a manner that SDIO I/O card reset will lead to WLAN backplane and PMU state reset. Reviewed-by: Hante Meuleman Reviewed-by: Arend van Spriel Reviewed-by: Pieter-Paul Giesberts Reviewed-by: Franky (Zhenhui) Lin Signed-off-by: Piotr Haber Signed-off-by: Arend van Spriel Signed-off-by: John W. Linville --- include/linux/bcma/bcma_driver_chipcommon.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 453fcc914683..b8b09eac60a4 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -316,6 +316,9 @@ #define BCMA_CC_PMU_CTL 0x0600 /* PMU control */ #define BCMA_CC_PMU_CTL_ILP_DIV 0xFFFF0000 /* ILP div mask */ #define BCMA_CC_PMU_CTL_ILP_DIV_SHIFT 16 +#define BCMA_CC_PMU_CTL_RES 0x00006000 /* reset control mask */ +#define BCMA_CC_PMU_CTL_RES_SHIFT 13 +#define BCMA_CC_PMU_CTL_RES_RELOAD 0x2 /* reload POR values */ #define BCMA_CC_PMU_CTL_PLL_UPD 0x00000400 #define BCMA_CC_PMU_CTL_NOILPONW 0x00000200 /* No ILP on wait */ #define BCMA_CC_PMU_CTL_HTREQEN 0x00000100 /* HT req enable */ -- cgit v1.2.3 From 668761ac01d6f5a36b8e5a24d4e154550e2c4c3b Mon Sep 17 00:00:00 2001 From: Hante Meuleman Date: Fri, 12 Apr 2013 10:55:55 +0200 Subject: brcmfmac: define and use platform specific data for SDIO. This patch adds support for platform specific data for SDIO fullmac devices. Currently OOB interrupts are configured by Kconfig BRCMFMAC_SDIO_OOB but that is now determined dynamically by checking availibility of platform data. Cc: Hauke Mehrtens Reviewed-by: Arend Van Spriel Reviewed-by: Franky (Zhenhui) Lin Reviewed-by: Pieter-Paul Giesberts Reviewed-by: Piotr Haber Signed-off-by: Hante Meuleman Signed-off-by: Arend van Spriel Signed-off-by: John W. Linville --- include/linux/platform_data/brcmfmac-sdio.h | 124 ++++++++++++++++++++++++++++ 1 file changed, 124 insertions(+) create mode 100644 include/linux/platform_data/brcmfmac-sdio.h (limited to 'include/linux') diff --git a/include/linux/platform_data/brcmfmac-sdio.h b/include/linux/platform_data/brcmfmac-sdio.h new file mode 100644 index 000000000000..1ade657d5fc1 --- /dev/null +++ b/include/linux/platform_data/brcmfmac-sdio.h @@ -0,0 +1,124 @@ +/* + * Copyright (c) 2013 Broadcom Corporation + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY + * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION + * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN + * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ + +#ifndef _LINUX_BRCMFMAC_PLATFORM_H +#define _LINUX_BRCMFMAC_PLATFORM_H + +/* + * Platform specific driver functions and data. Through the platform specific + * device data functions can be provided to help the brcmfmac driver to + * operate with the device in combination with the used platform. + * + * Use the platform data in the following (similar) way: + * + * +#include + + +static void brcmfmac_power_on(void) +{ +} + +static void brcmfmac_power_off(void) +{ +} + +static void brcmfmac_reset(void) +{ +} + +static struct brcmfmac_sdio_platform_data brcmfmac_sdio_pdata = { + .power_on = brcmfmac_power_on, + .power_off = brcmfmac_power_off, + .reset = brcmfmac_reset +}; + +static struct platform_device brcmfmac_device = { + .name = BRCMFMAC_SDIO_PDATA_NAME, + .id = PLATFORM_DEVID_NONE, + .dev.platform_data = &brcmfmac_sdio_pdata +}; + +void __init brcmfmac_init_pdata(void) +{ + brcmfmac_sdio_pdata.oob_irq_supported = true; + brcmfmac_sdio_pdata.oob_irq_nr = gpio_to_irq(GPIO_BRCMF_SDIO_OOB); + brcmfmac_sdio_pdata.oob_irq_flags = IORESOURCE_IRQ | + IORESOURCE_IRQ_HIGHLEVEL; + platform_device_register(&brcmfmac_device); +} + * + * + * Note: the brcmfmac can be loaded as module or be statically built-in into + * the kernel. If built-in then do note that it uses module_init (and + * module_exit) routines which equal device_initcall. So if you intend to + * create a module with the platform specific data for the brcmfmac and have + * it built-in to the kernel then use a higher initcall then device_initcall + * (see init.h). If this is not done then brcmfmac will load without problems + * but will not pickup the platform data. + * + * When the driver does not "detect" platform driver data then it will continue + * without reporting anything and just assume there is no data needed. Which is + * probably true for most platforms. + * + * Explanation of the platform_data fields: + * + * drive_strength: is the preferred drive_strength to be used for the SDIO + * pins. If 0 then a default value will be used. This is the target drive + * strength, the exact drive strength which will be used depends on the + * capabilities of the device. + * + * oob_irq_supported: does the board have support for OOB interrupts. SDIO + * in-band interrupts are relatively slow and for having less overhead on + * interrupt processing an out of band interrupt can be used. If the HW + * supports this then enable this by setting this field to true and configure + * the oob related fields. + * + * oob_irq_nr, oob_irq_flags: the OOB interrupt information. The values are + * used for registering the irq using request_irq function. + * + * power_on: This function is called by the brcmfmac when the module gets + * loaded. This can be particularly useful for low power devices. The platform + * spcific routine may for example decide to power up the complete device. + * If there is no use-case for this function then provide NULL. + * + * power_off: This function is called by the brcmfmac when the module gets + * unloaded. At this point the device can be powered down or otherwise be reset. + * So if an actual power_off is not supported but reset is then reset the device + * when this function gets called. This can be particularly useful for low power + * devices. If there is no use-case for this function (either power-down or + * reset) then provide NULL. + * + * reset: This function can get called if the device communication broke down. + * This functionality is particularly useful in case of SDIO type devices. It is + * possible to reset a dongle via sdio data interface, but it requires that + * this is fully functional. This function is chip/module specific and this + * function should return only after the complete reset has completed. + */ + +#define BRCMFMAC_SDIO_PDATA_NAME "brcmfmac_sdio" + +struct brcmfmac_sdio_platform_data { + unsigned int drive_strength; + bool oob_irq_supported; + unsigned int oob_irq_nr; + unsigned long oob_irq_flags; + void (*power_on)(void); + void (*power_off)(void); + void (*reset)(void); +}; + +#endif /* _LINUX_BRCMFMAC_PLATFORM_H */ -- cgit v1.2.3 From 6a76f8c0ab19f215af2a3442870eeb5f0e81998d Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 11 Apr 2013 15:55:01 +0900 Subject: tracing: Fix possible NULL pointer dereferences Currently set_ftrace_pid and set_graph_function files use seq_lseek for their fops. However seq_open() is called only for FMODE_READ in the fops->open() so that if an user tries to seek one of those file when she open it for writing, it sees NULL seq_file and then panic. It can be easily reproduced with following command: $ cd /sys/kernel/debug/tracing $ echo 1234 | sudo tee -a set_ftrace_pid In this example, GNU coreutils' tee opens the file with fopen(, "a") and then the fopen() internally calls lseek(). Link: http://lkml.kernel.org/r/1365663302-2170-1-git-send-email-namhyung@kernel.org Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Namhyung Kim Cc: stable@vger.kernel.org Signed-off-by: Namhyung Kim Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 167abf907802..eb3ce327b975 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -396,7 +396,7 @@ ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); -loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int whence); +loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence); int ftrace_regex_release(struct inode *inode, struct file *file); void __init -- cgit v1.2.3 From 7f49ef69db6bbf756c0abca7e9b65b32e999eec8 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 12 Apr 2013 16:40:13 -0400 Subject: ftrace: Move ftrace_filter_lseek out of CONFIG_DYNAMIC_FTRACE section As ftrace_filter_lseek is now used with ftrace_pid_fops, it needs to be moved out of the #ifdef CONFIG_DYNAMIC_FTRACE section as the ftrace_pid_fops is defined when DYNAMIC_FTRACE is not. Cc: stable@vger.kernel.org Cc: Namhyung Kim Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index eb3ce327b975..52da2a250795 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -396,7 +396,6 @@ ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos); -loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence); int ftrace_regex_release(struct inode *inode, struct file *file); void __init @@ -569,6 +568,8 @@ static inline int ftrace_regex_release(struct inode *inode, struct file *file) { return -ENODEV; } #endif /* CONFIG_DYNAMIC_FTRACE */ +loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence); + /* totally disable ftrace - can not re-enable after this */ void ftrace_kill(void); -- cgit v1.2.3 From 10a9574756201fbbdd0cac11f370f00d3d02bfa1 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Fri, 12 Apr 2013 05:44:20 +0000 Subject: PCI: Add pcibios hooks for adding and removing PCI buses On ACPI-based platforms, the pci_slot driver creates PCI slot devices according to information from ACPI tables by registering an ACPI PCI subdriver. The ACPI PCI subdriver will only be called when creating/ destroying PCI root buses, and it won't be called when hot-plugging P2P bridges. It may cause stale PCI slot devices after hot-removing a P2P bridge if that bridge has associated PCI slots. And the acpiphp driver has the same issue too. This patch introduces two hook points into the PCI core, which will be invoked when creating/destroying PCI buses for PCI host and P2P bridges. They could be used to setup/destroy platform dependent stuff in a unified way, both at boot time and for PCI hotplug operations. Signed-off-by: Jiang Liu Signed-off-by: Yijing Wang Signed-off-by: Bjorn Helgaas Reviewed-by: Yinghai Lu Cc: "Rafael J. Wysocki" Cc: Toshi Kani Cc: Tony Luck Cc: Fenghua Yu Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Myron Stowe --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 2461033a7987..be9399452133 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -678,6 +678,8 @@ extern struct list_head pci_root_buses; /* list of all known PCI buses */ extern int no_pci_devices(void); void pcibios_resource_survey_bus(struct pci_bus *bus); +void pcibios_add_bus(struct pci_bus *bus); +void pcibios_remove_bus(struct pci_bus *bus); void pcibios_fixup_bus(struct pci_bus *); int __must_check pcibios_enable_device(struct pci_dev *, int mask); /* Architecture specific versions may override this (weak) */ -- cgit v1.2.3 From 5090d4a6a1f150ec593ac5f2a755b5a3e878b21e Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Fri, 12 Apr 2013 05:44:21 +0000 Subject: PCI/ACPI: Prepare stub functions to handle ACPI PCI (hotplug) slots Prepare two stub functions to handle ACPI PCI slots and ACPI PCI hotplug slots, which will be invoked by the PCI core when creating/destroying PCI buses. It will be used to get rid of ACPI PCI subdrivers for pci_slot and acpiphp, and eventually remove the ACPI PCI subdriver mechanism. And it will also be used to handle ACPI PCI (hotplug) slots in a unified way, both at boot time and for PCI hotplug operations. Signed-off-by: Jiang Liu Signed-off-by: Yijing Wang Signed-off-by: Bjorn Helgaas Reviewed-by: Yinghai Lu Cc: "Rafael J. Wysocki" Cc: Toshi Kani Cc: Tony Luck Cc: Fenghua Yu Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Myron Stowe --- include/linux/pci-acpi.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 9a22b5efb384..2b1743cc3186 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -41,7 +41,13 @@ static inline acpi_handle acpi_pci_get_bridge_handle(struct pci_bus *pbus) return DEVICE_ACPI_HANDLE(dev); } -#endif + +void acpi_pci_add_bus(struct pci_bus *bus); +void acpi_pci_remove_bus(struct pci_bus *bus); +#else /* CONFIG_ACPI */ +static inline void acpi_pci_add_bus(struct pci_bus *bus) { } +static inline void acpi_pci_remove_bus(struct pci_bus *bus) { } +#endif /* CONFIG_ACPI */ #ifdef CONFIG_ACPI_APEI extern bool aer_acpi_firmware_first(void); -- cgit v1.2.3 From 5c0b04e3d913c91aee6e48e567e20a3f67849618 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Fri, 12 Apr 2013 05:44:24 +0000 Subject: PCI/ACPI: Handle PCI slot devices when creating/destroying PCI buses Currently the pci_slot driver doesn't update PCI slot devices when PCI device hotplug event happens, which may cause memory leak and returning stale information to user. Now the pci_slot driver has been changed as built-in driver, so invoke PCI slot enumeration and destroy routines directly from the PCI core. And remove ACPI PCI sub-driver related code because it isn't needed any more. [bhelgas: removed "extern" from function declarations] Signed-off-by: Jiang Liu Signed-off-by: Yijing Wang Signed-off-by: Bjorn Helgaas Reviewed-by: Yinghai Lu Acked-by: Rafael J. Wysocki Cc: Toshi Kani --- include/linux/pci-acpi.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 2b1743cc3186..23cd40abba4f 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -44,6 +44,18 @@ static inline acpi_handle acpi_pci_get_bridge_handle(struct pci_bus *pbus) void acpi_pci_add_bus(struct pci_bus *bus); void acpi_pci_remove_bus(struct pci_bus *bus); + +#ifdef CONFIG_ACPI_PCI_SLOT +void acpi_pci_slot_init(void); +void acpi_pci_slot_enumerate(struct pci_bus *bus, acpi_handle handle); +void acpi_pci_slot_remove(struct pci_bus *bus); +#else +static inline void acpi_pci_slot_init(void) { } +static inline void acpi_pci_slot_enumerate(struct pci_bus *bus, + acpi_handle handle) { } +static inline void acpi_pci_slot_remove(struct pci_bus *bus) { } +#endif + #else /* CONFIG_ACPI */ static inline void acpi_pci_add_bus(struct pci_bus *bus) { } static inline void acpi_pci_remove_bus(struct pci_bus *bus) { } -- cgit v1.2.3 From 3b63aaa70e1ccc4b66d60acc78da09700706a703 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Fri, 12 Apr 2013 05:44:26 +0000 Subject: PCI: acpiphp: Do not use ACPI PCI subdriver mechanism Previously the acpiphp driver registered itself as an ACPI PCI subdriver, so its callbacks were invoked when creating/destroying PCI root buses to manage ACPI-based PCI hotplug slots. But it doesn't handle P2P bridge hotplug events, so it will cause strange behaviour if there are hotplug slots associated with a hot-removed P2P bridge. This patch fixes this issue by: 1) Directly hooking into PCI core to update hotplug slot devices when creating/destroying PCI buses through: pci_{add|remove}_bus() -> acpi_pci_{add|remove}_bus() 2) Getting rid of unused ACPI PCI subdriver-related code It also cleans up unused code in the acpiphp driver. [bhelgaas: keep acpi_pci_add_bus() stub for CONFIG_ACPI=n] Signed-off-by: Jiang Liu Signed-off-by: Yijing Wang Signed-off-by: Bjorn Helgaas Reviewed-by: Yinghai Lu Cc: "Rafael J. Wysocki" Cc: Toshi Kani --- include/linux/pci-acpi.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 23cd40abba4f..81b31613eb25 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -56,6 +56,17 @@ static inline void acpi_pci_slot_enumerate(struct pci_bus *bus, static inline void acpi_pci_slot_remove(struct pci_bus *bus) { } #endif +#ifdef CONFIG_HOTPLUG_PCI_ACPI +void acpiphp_init(void); +void acpiphp_enumerate_slots(struct pci_bus *bus, acpi_handle handle); +void acpiphp_remove_slots(struct pci_bus *bus); +#else +static inline void acpiphp_init(void) { } +static inline void acpiphp_enumerate_slots(struct pci_bus *bus, + acpi_handle handle) { } +static inline void acpiphp_remove_slots(struct pci_bus *bus) { } +#endif + #else /* CONFIG_ACPI */ static inline void acpi_pci_add_bus(struct pci_bus *bus) { } static inline void acpi_pci_remove_bus(struct pci_bus *bus) { } -- cgit v1.2.3 From ea024870cf10687b3fded66a9deb6253888f30b7 Mon Sep 17 00:00:00 2001 From: Anton Arapov Date: Wed, 3 Apr 2013 18:00:31 +0200 Subject: uretprobes: Introduce uprobe_consumer->ret_handler() Enclose return probes implementation, introduce ->ret_handler() and update existing code to rely on ->handler() *and* ->ret_handler() for uprobe and uretprobe respectively. Signed-off-by: Anton Arapov Acked-by: Srikar Dronamraju Signed-off-by: Oleg Nesterov --- include/linux/uprobes.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 19612881399a..5c8d3290df41 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -46,6 +46,9 @@ enum uprobe_filter_ctx { struct uprobe_consumer { int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs); + int (*ret_handler)(struct uprobe_consumer *self, + unsigned long func, + struct pt_regs *regs); bool (*filter)(struct uprobe_consumer *self, enum uprobe_filter_ctx ctx, struct mm_struct *mm); -- cgit v1.2.3 From 0dfd0eb8e4d72ded8b21f4fee74ba5547408cbe9 Mon Sep 17 00:00:00 2001 From: Anton Arapov Date: Wed, 3 Apr 2013 18:00:35 +0200 Subject: uretprobes: Return probe entry, prepare_uretprobe() When a uprobe with return probe consumer is hit, prepare_uretprobe() function is invoked. It creates return_instance, hijacks return address and replaces it with the trampoline. * Return instances are kept as stack per uprobed task. * Return instance is chained, when the original return address is trampoline's page vaddr (e.g. recursive call of the probed function). Signed-off-by: Anton Arapov Acked-by: Srikar Dronamraju Signed-off-by: Oleg Nesterov --- include/linux/uprobes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 5c8d3290df41..b0507f24eeb0 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -71,6 +71,7 @@ struct uprobe_task { enum uprobe_task_state state; struct arch_uprobe_task autask; + struct return_instance *return_instances; struct uprobe *active_uprobe; unsigned long xol_vaddr; -- cgit v1.2.3 From ded49c55309a37129dc30a5f0e85b8a64e5c1716 Mon Sep 17 00:00:00 2001 From: Anton Arapov Date: Wed, 3 Apr 2013 18:00:37 +0200 Subject: uretprobes: Limit the depth of return probe nestedness Unlike the kretprobes we can't trust userspace, thus must have protection from user space attacks. User-space have "unlimited" stack, and this patch limits the return probes nestedness as a simple remedy for it. Note that this implementation leaks return_instance on siglongjmp until exit()/exec(). The intention is to have KISS and bare minimum solution for the initial implementation in order to not complicate the uretprobes code. In the future we may come up with more sophisticated solution that remove this depth limitation. It is not easy task and lays beyond this patchset. Signed-off-by: Anton Arapov Acked-by: Srikar Dronamraju Signed-off-by: Oleg Nesterov --- include/linux/uprobes.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index b0507f24eeb0..06f28beed7c2 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -38,6 +38,8 @@ struct inode; #define UPROBE_HANDLER_REMOVE 1 #define UPROBE_HANDLER_MASK 1 +#define MAX_URETPROBE_DEPTH 64 + enum uprobe_filter_ctx { UPROBE_FILTER_REGISTER, UPROBE_FILTER_UNREGISTER, @@ -72,6 +74,7 @@ struct uprobe_task { struct arch_uprobe_task autask; struct return_instance *return_instances; + unsigned int depth; struct uprobe *active_uprobe; unsigned long xol_vaddr; -- cgit v1.2.3 From 80a26a5c22b90a82b8696cb72c1d09d525ada53e Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Tue, 26 Mar 2013 16:38:29 +0800 Subject: Thermal: build thermal governors into thermal_sys module The thermal governors are part of the thermal framework, rather than a seperate feature/module. Because the generic thermal layer can not work without thermal governors, and it must load the thermal governors during its initialization. Build them into one module in this patch. This also fix a problem that the generic thermal layer does not work when CONFIG_THERMAL=m and CONFIG_THERMAL_GOV_XXX=y. Signed-off-by: Zhang Rui Acked-by: Eduardo Valentin Acked-by: Durgadoss R --- include/linux/thermal.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 5a3b428daaab..4445b951b57e 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -187,7 +187,6 @@ struct thermal_governor { char name[THERMAL_NAME_LENGTH]; int (*throttle)(struct thermal_zone_device *tz, int trip); struct list_head governor_list; - struct module *owner; }; /* Structure that holds binding parameters for a zone */ @@ -247,9 +246,6 @@ struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, void thermal_cdev_update(struct thermal_cooling_device *); void notify_thermal_framework(struct thermal_zone_device *, int); -int thermal_register_governor(struct thermal_governor *); -void thermal_unregister_governor(struct thermal_governor *); - #ifdef CONFIG_NET extern int thermal_generate_netlink_event(struct thermal_zone_device *tz, enum events event); -- cgit v1.2.3 From bbf7fc88c78f7317e2cdcf77e974c8a9a8312641 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Tue, 26 Mar 2013 23:57:01 +0800 Subject: Thermal: build cpu_cooling code into thermal_sys module Signed-off-by: Zhang Rui Acked-by: Eduardo Valentin Acked-by: Durgadoss R --- include/linux/cpu_cooling.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index bc479b1e0fd9..77c87c9d0193 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -29,7 +29,7 @@ #define CPUFREQ_COOLING_START 0 #define CPUFREQ_COOLING_STOP 1 -#if defined(CONFIG_CPU_THERMAL) || defined(CONFIG_CPU_THERMAL_MODULE) +#ifdef CONFIG_CPU_THERMAL /** * cpufreq_cooling_register - function to create cpufreq cooling device. * @clip_cpus: cpumask of cpus where the frequency constraints will happen -- cgit v1.2.3 From ba60eb25ff6be6f8e60488cdfd454e5c612bce60 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 14 Apr 2013 10:49:37 -0400 Subject: SUNRPC: Fix a livelock problem in the xprt->backlog queue This patch ensures that we throttle new RPC requests if there are requests already waiting in the xprt->backlog queue. The reason for doing this is to fix livelock issues that can occur when an existing (high priority) task is waiting in the backlog queue, gets woken up by xprt_free_slot(), but a new task then steals the slot. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 30834be03011..12815f66a9c4 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -279,6 +279,7 @@ struct xprt_class { struct rpc_xprt *xprt_create_transport(struct xprt_create *args); void xprt_connect(struct rpc_task *task); void xprt_reserve(struct rpc_task *task); +void xprt_retry_reserve(struct rpc_task *task); int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task); int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); @@ -334,6 +335,7 @@ int xs_swapper(struct rpc_xprt *xprt, int enable); #define XPRT_CLOSING (6) #define XPRT_CONNECTION_ABORT (7) #define XPRT_CONNECTION_CLOSE (8) +#define XPRT_CONGESTED (9) static inline void xprt_set_connected(struct rpc_xprt *xprt) { -- cgit v1.2.3 From b7993cebb841b0da7a33e9d5ce301a9fd3209165 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 14 Apr 2013 11:42:00 -0400 Subject: SUNRPC: Allow rpc_create() to request that TCP slots be unlimited This is mainly for use by NFSv4.1, where the session negotiation ultimately wants to decide how many RPC slots we can fill. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 + include/linux/sunrpc/xprt.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 2cf4ffaa3cd4..e7d492ce7c18 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -124,6 +124,7 @@ struct rpc_create_args { #define RPC_CLNT_CREATE_NOPING (1UL << 4) #define RPC_CLNT_CREATE_DISCRTRY (1UL << 5) #define RPC_CLNT_CREATE_QUIET (1UL << 6) +#define RPC_CLNT_CREATE_INFINITE_SLOTS (1UL << 7) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 12815f66a9c4..ff5392421cb2 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -255,6 +255,8 @@ static inline int bc_prealloc(struct rpc_rqst *req) } #endif /* CONFIG_SUNRPC_BACKCHANNEL */ +#define XPRT_CREATE_INFINITE_SLOTS (1U) + struct xprt_create { int ident; /* XPRT_TRANSPORT identifier */ struct net * net; @@ -263,6 +265,7 @@ struct xprt_create { size_t addrlen; const char *servername; struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ + unsigned int flags; }; struct xprt_class { -- cgit v1.2.3 From 98f98cf571b7b1f34683455a61dae9f35e7222a1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 14 Apr 2013 11:49:51 -0400 Subject: NFSv4.1: Set the RPC_CLNT_CREATE_INFINITE_SLOTS flag for NFSv4.1 transports This ensures that the RPC layer doesn't override the NFS session negotiation. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index d8fdfdc7a8fe..3b7fa2abecca 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -40,6 +40,7 @@ struct nfs_client { #define NFS_CS_NORESVPORT 0 /* - use ephemeral src port */ #define NFS_CS_DISCRTRY 1 /* - disconnect on RPC retry */ #define NFS_CS_MIGRATION 2 /* - transparent state migr */ +#define NFS_CS_INFINITE_SLOTS 3 /* - don't limit TCP slots */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ -- cgit v1.2.3 From 935d8aabd4331f47a89c3e1daa5779d23cf244ee Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 14 Apr 2013 10:06:31 -0700 Subject: Add file_ns_capable() helper function for open-time capability checking Nothing is using it yet, but this will allow us to delay the open-time checks to use time, without breaking the normal UNIX permission semantics where permissions are determined by the opener (and the file descriptor can then be passed to a different process, or the process can drop capabilities). Signed-off-by: Linus Torvalds --- include/linux/capability.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index 98503b792369..d9a4f7f40f32 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -35,6 +35,7 @@ struct cpu_vfs_cap_data { #define _KERNEL_CAP_T_SIZE (sizeof(kernel_cap_t)) +struct file; struct inode; struct dentry; struct user_namespace; @@ -211,6 +212,7 @@ extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); extern bool nsown_capable(int cap); extern bool inode_capable(const struct inode *inode, int cap); +extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); -- cgit v1.2.3 From 63c4d919cf66b1b3ffa7861bddb50a697914af5b Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Fri, 5 Apr 2013 12:32:28 +0000 Subject: thermal: introduce thermal_zone_get_zone_by_name helper function This patch adds a helper function to get a reference of a thermal zone, based on the zone type name. It will perform a zone name lookup and return a reference to a thermal zone device that matches the name requested. In case the zone is not found or when several zones match same name or if the required parameters are invalid, it will return the corresponding error code (ERR_PTR). Cc: Durgadoss R Signed-off-by: Eduardo Valentin Acked-by: Durgadoss R Signed-off-by: Zhang Rui --- include/linux/thermal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 3bda306f7a50..9af2f3a99658 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -239,6 +239,7 @@ void thermal_zone_device_update(struct thermal_zone_device *); struct thermal_cooling_device *thermal_cooling_device_register(char *, void *, const struct thermal_cooling_device_ops *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); +struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name); int get_tz_trend(struct thermal_zone_device *, int); struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, -- cgit v1.2.3 From 837b26bb2e4a83d224e725f07a1d9ca824bf905c Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Fri, 5 Apr 2013 12:32:29 +0000 Subject: thermal: expose thermal_zone_get_temp API This patch exports the thermal_zone_get_temp API so that driver writers can fetch temperature of thermal zones managed by other drivers. Acked-by: Durgadoss R Signed-off-by: Eduardo Valentin Signed-off-by: Zhang Rui --- include/linux/thermal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 9af2f3a99658..ec2b886f9d96 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -240,6 +240,7 @@ struct thermal_cooling_device *thermal_cooling_device_register(char *, void *, const struct thermal_cooling_device_ops *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name); +int thermal_zone_get_temp(struct thermal_zone_device *tz, unsigned long *temp); int get_tz_trend(struct thermal_zone_device *, int); struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, -- cgit v1.2.3 From 25a7e6848db76e22677aff202d9c4ef3503be15b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 14 Apr 2013 20:15:25 -0700 Subject: move cgroupfs_root to include/linux/cgroup.h While controllers shouldn't be accessing cgroupfs_root directly, it being hidden inside kern/cgroup.c makes somethings pretty silly. This makes routing hierarchy-wide settings which need to be visible to controllers cumbersome. We're gonna add another hierarchy-wide setting which needs to be accessed from controllers. Move cgroupfs_root and its flags to the header file so that we can access root settings with inline helpers. Signed-off-by: Tejun Heo Acked-by: Serge E. Hallyn Acked-by: Li Zefan --- include/linux/cgroup.h | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 45aee0fc6b98..b21881e1ea08 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -19,6 +19,7 @@ #include #include #include +#include #ifdef CONFIG_CGROUPS @@ -238,6 +239,62 @@ struct cgroup { struct simple_xattrs xattrs; }; +#define MAX_CGROUP_ROOT_NAMELEN 64 + +/* cgroupfs_root->flags */ +enum { + CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ + CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ +}; + +/* + * A cgroupfs_root represents the root of a cgroup hierarchy, and may be + * associated with a superblock to form an active hierarchy. This is + * internal to cgroup core. Don't access directly from controllers. + */ +struct cgroupfs_root { + struct super_block *sb; + + /* + * The bitmask of subsystems intended to be attached to this + * hierarchy + */ + unsigned long subsys_mask; + + /* Unique id for this hierarchy. */ + int hierarchy_id; + + /* The bitmask of subsystems currently attached to this hierarchy */ + unsigned long actual_subsys_mask; + + /* A list running through the attached subsystems */ + struct list_head subsys_list; + + /* The root cgroup for this hierarchy */ + struct cgroup top_cgroup; + + /* Tracks how many cgroups are currently defined in hierarchy.*/ + int number_of_cgroups; + + /* A list running through the active hierarchies */ + struct list_head root_list; + + /* All cgroups on this root, cgroup_mutex protected */ + struct list_head allcg_list; + + /* Hierarchy-specific flags */ + unsigned long flags; + + /* IDs for cgroups in this hierarchy */ + struct ida cgroup_ida; + + /* The path to use for release notifications. */ + char release_agent_path[PATH_MAX]; + + /* The name for this hierarchy - may be empty */ + char name[MAX_CGROUP_ROOT_NAMELEN]; +}; + /* * A css_set is a structure holding pointers to a set of * cgroup_subsys_state objects. This saves space in the task struct -- cgit v1.2.3 From 873fe09ea5df6ccf6bb34811d8c9992aacb67598 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 14 Apr 2013 20:15:26 -0700 Subject: cgroup: introduce sane_behavior mount option It's a sad fact that at this point various cgroup controllers are carrying so many idiosyncrasies and pure insanities that it simply isn't possible to reach any sort of sane consistent behavior while maintaining staying fully compatible with what already has been exposed to userland. As we can't break exposed userland interface, transitioning to sane behaviors can only be done in steps while maintaining backwards compatibility. This patch introduces a new mount option - __DEVEL__sane_behavior - which disables crazy features and enforces consistent behaviors in cgroup core proper and various controllers. As exactly which behaviors it changes are still being determined, the mount option, at this point, is useful only for development of the new behaviors. As such, the mount option is prefixed with __DEVEL__ and generates a warning message when used. Eventually, once we get to the point where all controller's behaviors are consistent enough to implement unified hierarchy, the __DEVEL__ prefix will be dropped, and more importantly, unified-hierarchy will enforce sane_behavior by default. Maybe we'll able to completely drop the crazy stuff after a while, maybe not, but we at least have a strategy to move on to saner behaviors. This patch introduces the mount option and changes the following behaviors in cgroup core. * Mount options "noprefix" and "clone_children" are disallowed. Also, cgroupfs file cgroup.clone_children is not created. * When mounting an existing superblock, mount options should match. This is currently pretty crazy. If one mounts a cgroup, creates a subdirectory, unmounts it and then mount it again with different option, it looks like the new options are applied but they aren't. * Remount is disallowed. The behaviors changes are documented in the comment above CGRP_ROOT_SANE_BEHAVIOR enum and will be expanded as different controllers are converted and planned improvements progress. v2: Dropped unnecessary explicit file permission setting sane_behavior cftype entry as suggested by Li Zefan. Signed-off-by: Tejun Heo Acked-by: Serge E. Hallyn Acked-by: Li Zefan Cc: Michal Hocko Cc: Vivek Goyal --- include/linux/cgroup.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b21881e1ea08..9c300ad9a911 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -156,6 +156,8 @@ enum { * specified at mount time and thus is implemented here. */ CGRP_CPUSET_CLONE_CHILDREN, + /* see the comment above CGRP_ROOT_SANE_BEHAVIOR for details */ + CGRP_SANE_BEHAVIOR, }; struct cgroup_name { @@ -243,6 +245,37 @@ struct cgroup { /* cgroupfs_root->flags */ enum { + /* + * Unfortunately, cgroup core and various controllers are riddled + * with idiosyncrasies and pointless options. The following flag, + * when set, will force sane behavior - some options are forced on, + * others are disallowed, and some controllers will change their + * hierarchical or other behaviors. + * + * The set of behaviors affected by this flag are still being + * determined and developed and the mount option for this flag is + * prefixed with __DEVEL__. The prefix will be dropped once we + * reach the point where all behaviors are compatible with the + * planned unified hierarchy, which will automatically turn on this + * flag. + * + * The followings are the behaviors currently affected this flag. + * + * - Mount options "noprefix" and "clone_children" are disallowed. + * Also, cgroupfs file cgroup.clone_children is not created. + * + * - When mounting an existing superblock, mount options should + * match. + * + * - Remount is disallowed. + * + * The followings are planned changes. + * + * - release_agent will be disallowed once replacement notification + * mechanism is implemented. + */ + CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), + CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ }; @@ -360,6 +393,7 @@ struct cgroup_map_cb { /* cftype->flags */ #define CFTYPE_ONLY_ON_ROOT (1U << 0) /* only create on root cg */ #define CFTYPE_NOT_ON_ROOT (1U << 1) /* don't create on root cg */ +#define CFTYPE_INSANE (1U << 2) /* don't create if sane_behavior */ #define MAX_CFTYPE_NAME 64 @@ -486,6 +520,15 @@ struct cgroup_scanner { void *data; }; +/* + * See the comment above CGRP_ROOT_SANE_BEHAVIOR for details. This + * function can be called as long as @cgrp is accessible. + */ +static inline bool cgroup_sane_behavior(const struct cgroup *cgrp) +{ + return cgrp->root->flags & CGRP_ROOT_SANE_BEHAVIOR; +} + /* Caller should hold rcu_read_lock() */ static inline const char *cgroup_name(const struct cgroup *cgrp) { -- cgit v1.2.3 From a53e28da574a40bcc9f78f5d0b0b60570182595b Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 25 Mar 2013 13:23:52 +0100 Subject: dma: Make the 'mask' parameter of __dma_request_channel const The 'mask' parameter is not modified in __dma_request_channel and really shouldn't be. Make this explicit by making the parameter const. Signed-off-by: Lars-Peter Clausen Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 91ac8da25020..dd6d21b335c8 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -967,7 +967,8 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); #ifdef CONFIG_DMA_ENGINE enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); void dma_issue_pending_all(void); -struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param); +struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param); struct dma_chan *dma_request_slave_channel(struct device *dev, char *name); void dma_release_channel(struct dma_chan *chan); #else @@ -978,7 +979,7 @@ static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descript static inline void dma_issue_pending_all(void) { } -static inline struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, +static inline struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param) { return NULL; @@ -1005,9 +1006,9 @@ struct dma_chan *net_dma_find_channel(void); __dma_request_slave_channel_compat(&(mask), x, y, dev, name) static inline struct dma_chan -*__dma_request_slave_channel_compat(dma_cap_mask_t *mask, dma_filter_fn fn, - void *fn_param, struct device *dev, - char *name) +*__dma_request_slave_channel_compat(const dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param, + struct device *dev, char *name) { struct dma_chan *chan; -- cgit v1.2.3 From bef29ec508e58bf8b9ec0915de5b0739fb800c91 Mon Sep 17 00:00:00 2001 From: Markus Pargmann Date: Sun, 24 Feb 2013 16:36:09 +0100 Subject: DMA: of: Constant names No DMA of-function alters the name, so this patch changes the name arguments to be constant. Most drivers will probably request DMA channels using a constant name. Signed-off-by: Markus Pargmann Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 4 ++-- include/linux/of_dma.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 91ac8da25020..274071ca6f04 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -968,7 +968,7 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); void dma_issue_pending_all(void); struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param); -struct dma_chan *dma_request_slave_channel(struct device *dev, char *name); +struct dma_chan *dma_request_slave_channel(struct device *dev, const char *name); void dma_release_channel(struct dma_chan *chan); #else static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) @@ -984,7 +984,7 @@ static inline struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, return NULL; } static inline struct dma_chan *dma_request_slave_channel(struct device *dev, - char *name) + const char *name) { return NULL; } diff --git a/include/linux/of_dma.h b/include/linux/of_dma.h index d15073e080dd..ce6a8ab3d2bb 100644 --- a/include/linux/of_dma.h +++ b/include/linux/of_dma.h @@ -40,7 +40,7 @@ extern int of_dma_controller_register(struct device_node *np, void *data); extern int of_dma_controller_free(struct device_node *np); extern struct dma_chan *of_dma_request_slave_channel(struct device_node *np, - char *name); + const char *name); extern struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma); #else @@ -58,7 +58,7 @@ static inline int of_dma_controller_free(struct device_node *np) } static inline struct dma_chan *of_dma_request_slave_channel(struct device_node *np, - char *name) + const char *name) { return NULL; } -- cgit v1.2.3 From 05fb22ec5456a472a5eadcaacb3e51eca1f8c79c Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 15 Apr 2013 14:25:05 +0800 Subject: cgroup: remove cgrp->top_cgroup It's not used, and it can be retrieved via cgrp->root->top_cgroup. Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 9c300ad9a911..64047ae7fde1 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -204,7 +204,6 @@ struct cgroup { struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; struct cgroupfs_root *root; - struct cgroup *top_cgroup; /* * List of cg_cgroup_links pointing at css_sets with -- cgit v1.2.3 From 95b80e0a9ab3c1c8b41af5f2863801708f8f7288 Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Thu, 21 Mar 2013 17:59:19 +0100 Subject: arm: mach-mv78xx0: convert to use the mvebu-mbus driver This commit convers the mach-mv78xx0 sub-architecture to use the mvebu-mbus driver. We simply have to call mvebu_mbus_init() in the ->init_early() function, and modify the PCIe code so that it uses the new functions provided by mvebu-mbus to create the needed PCIe windows. Signed-off-by: Thomas Petazzoni Acked-by: Arnd Bergmann Signed-off-by: Jason Cooper --- include/linux/mbus.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mbus.h b/include/linux/mbus.h index 462eb9791012..dba482e31a13 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -43,6 +43,9 @@ struct mbus_dram_target_info */ #define MVEBU_MBUS_NO_REMAP (0xffffffff) +/* Maximum size of a mbus window name */ +#define MVEBU_MBUS_MAX_WINNAME_SZ 32 + /* * The Marvell mbus is to be found only on SOCs from the Orion family * at the moment. Provide a dummy stub for other architectures. -- cgit v1.2.3 From 1b2e98bc1e35ebe1f65c3db62c8317096ad7f2c8 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 9 Apr 2013 14:05:43 +0300 Subject: dma: acpi-dma: introduce ACPI DMA helpers There is a new generic API to get a DMA channel for a slave device (commit 9a6cecc8 "dmaengine: add helper function to request a slave DMA channel"). In similar fashion to the DT case (commit aa3da644 "of: Add generic device tree DMA helpers") we introduce helpers to the DMAC drivers which are enumerated by ACPI. The proposed extension provides the following API calls: acpi_dma_controller_register(), devm_acpi_dma_controller_register() acpi_dma_controller_free(), devm_acpi_dma_controller_free() acpi_dma_simple_xlate() acpi_dma_request_slave_chan_by_index() acpi_dma_request_slave_chan_by_name() The first two should be used, for example, at probe() and remove() of the corresponding DMAC driver. At the register stage the DMAC driver supplies a custom xlate() function to translate a struct dma_spec into struct dma_chan. Accordingly to the ACPI Fixed DMA resource specification the only two pieces of information the slave device has are the channel id and the request line (slave id). Those two are represented by struct dma_spec. The acpi_dma_request_slave_chan_by_index() provides access to the specifix FixedDMA resource by its index. Whereas dma_request_slave_channel() takes a string parameter to identify the DMA resources required by the slave device. To make a slave device driver work with both DeviceTree and ACPI enumeration a simple convention is established: "tx" corresponds to the index 0 and "rx" to the index 1. In case of robust configuration the slave device driver unfortunately needs to call acpi_dma_request_slave_chan_by_index() directly. Additionally the patch provides "managed" version of the register/free pair i.e. devm_acpi_dma_controller_register() and devm_acpi_dma_controller_free(). Usually, the driver uses only devm_acpi_dma_controller_register(). Signed-off-by: Andy Shevchenko Reviewed-by: Mika Westerberg Acked-by: Rafael J. Wysocki Signed-off-by: Vinod Koul --- include/linux/acpi_dma.h | 116 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) create mode 100644 include/linux/acpi_dma.h (limited to 'include/linux') diff --git a/include/linux/acpi_dma.h b/include/linux/acpi_dma.h new file mode 100644 index 000000000000..d09deabc7bf6 --- /dev/null +++ b/include/linux/acpi_dma.h @@ -0,0 +1,116 @@ +/* + * ACPI helpers for DMA request / controller + * + * Based on of_dma.h + * + * Copyright (C) 2013, Intel Corporation + * Author: Andy Shevchenko + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_ACPI_DMA_H +#define __LINUX_ACPI_DMA_H + +#include +#include +#include + +/** + * struct acpi_dma_spec - slave device DMA resources + * @chan_id: channel unique id + * @slave_id: request line unique id + * @dev: struct device of the DMA controller to be used in the filter + * function + */ +struct acpi_dma_spec { + int chan_id; + int slave_id; + struct device *dev; +}; + +/** + * struct acpi_dma - representation of the registered DMAC + * @dma_controllers: linked list node + * @dev: struct device of this controller + * @acpi_dma_xlate: callback function to find a suitable channel + * @data: private data used by a callback function + */ +struct acpi_dma { + struct list_head dma_controllers; + struct device *dev; + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *); + void *data; +}; + +/* Used with acpi_dma_simple_xlate() */ +struct acpi_dma_filter_info { + dma_cap_mask_t dma_cap; + dma_filter_fn filter_fn; +}; + +#ifdef CONFIG_DMA_ACPI + +int acpi_dma_controller_register(struct device *dev, + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *), + void *data); +int acpi_dma_controller_free(struct device *dev); +int devm_acpi_dma_controller_register(struct device *dev, + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *), + void *data); +void devm_acpi_dma_controller_free(struct device *dev); + +struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev, + size_t index); +struct dma_chan *acpi_dma_request_slave_chan_by_name(struct device *dev, + const char *name); + +struct dma_chan *acpi_dma_simple_xlate(struct acpi_dma_spec *dma_spec, + struct acpi_dma *adma); +#else + +static inline int acpi_dma_controller_register(struct device *dev, + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *), + void *data) +{ + return -ENODEV; +} +static inline int acpi_dma_controller_free(struct device *dev) +{ + return -ENODEV; +} +static inline int devm_acpi_dma_controller_register(struct device *dev, + struct dma_chan *(*acpi_dma_xlate) + (struct acpi_dma_spec *, struct acpi_dma *), + void *data) +{ + return -ENODEV; +} +static inline void devm_acpi_dma_controller_free(struct device *dev) +{ +} + +static inline struct dma_chan *acpi_dma_request_slave_chan_by_index( + struct device *dev, size_t index) +{ + return NULL; +} +static inline struct dma_chan *acpi_dma_request_slave_chan_by_name( + struct device *dev, const char *name) +{ + return NULL; +} + +#define acpi_dma_simple_xlate NULL + +#endif + +#define acpi_dma_request_slave_channel acpi_dma_request_slave_chan_by_index + +#endif /* __LINUX_ACPI_DMA_H */ -- cgit v1.2.3 From e6a90810559cc3755a5b1629d1fd0b914462f98c Mon Sep 17 00:00:00 2001 From: Bastian Hecht Date: Mon, 15 Apr 2013 09:31:00 -0700 Subject: Input: st1232 - add reset pin handling We add the possibility to hand over a GPIO number for the reset pin. This way we can remove existing board code that takes care of it and group this information properly in the platform data or in the device tree configuration. Signed-off-by: Bastian Hecht Acked-by: Laurent Pinchart Signed-off-by: Dmitry Torokhov --- include/linux/platform_data/st1232_pdata.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/linux/platform_data/st1232_pdata.h (limited to 'include/linux') diff --git a/include/linux/platform_data/st1232_pdata.h b/include/linux/platform_data/st1232_pdata.h new file mode 100644 index 000000000000..cac3e7b4c454 --- /dev/null +++ b/include/linux/platform_data/st1232_pdata.h @@ -0,0 +1,13 @@ +#ifndef _LINUX_ST1232_PDATA_H +#define _LINUX_ST1232_PDATA_H + +/* + * Optional platform data + * + * Use this if you want the driver to drive the reset pin. + */ +struct st1232_pdata { + int reset_gpio; +}; + +#endif -- cgit v1.2.3 From c5bfece2d6129131b4ade985e63bc35ddf5868d4 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Apr 2013 16:45:34 +0200 Subject: nohz: Switch from "extended nohz" to "full nohz" based naming "Extended nohz" was used as a naming base for the full dynticks API and Kconfig symbols. It reflects the fact the system tries to stop the tick in more places than just idle. But that "extended" name is a bit opaque and vague. Rename it to "full" makes it clearer what the system tries to do under this config: try to shutdown the tick anytime it can. The various constraints that prevent that to happen shouldn't be considered as fundamental properties of this feature but rather technical issues that may be solved in the future. Reported-by: Ingo Molnar Signed-off-by: Frederic Weisbecker Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- include/linux/tick.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 5e403339ee14..b4e3b0c9639e 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -157,10 +157,10 @@ static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } # endif /* !CONFIG_NO_HZ_COMMON */ -#ifdef CONFIG_NO_HZ_EXTENDED -extern int tick_nohz_extended_cpu(int cpu); +#ifdef CONFIG_NO_HZ_FULL +extern int tick_nohz_full_cpu(int cpu); #else -static inline int tick_nohz_extended_cpu(int cpu) { return 0; } +static inline int tick_nohz_full_cpu(int cpu) { return 0; } #endif -- cgit v1.2.3 From 31815c08fc90f44d6165034fd473f23df5d31449 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Sat, 13 Apr 2013 08:46:58 +0400 Subject: serial: sccnxp: Replace pdata.init/exit with regulator API Typical usage of pdata.init/exit is enable/disable power and/or toggle reset for the target chip. This patch replaces these callbacks with regulator API. Signed-off-by: Alexander Shiyan Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/serial-sccnxp.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/serial-sccnxp.h b/include/linux/platform_data/serial-sccnxp.h index 215574d1e81d..bdc510d03245 100644 --- a/include/linux/platform_data/serial-sccnxp.h +++ b/include/linux/platform_data/serial-sccnxp.h @@ -86,10 +86,6 @@ struct sccnxp_pdata { const u32 mctrl_cfg[SCCNXP_MAX_UARTS]; /* Timer value for polling mode (usecs) */ const unsigned int poll_time_us; - /* Called during startup */ - void (*init)(void); - /* Called before finish */ - void (*exit)(void); }; #endif -- cgit v1.2.3 From 4cd729b04285b7330edaf5a7080aa795d6d15ff3 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Mon, 15 Apr 2013 09:54:25 +0000 Subject: net: add dev_uc_sync_multiple() and dev_mc_sync_multiple() api The current implementation of dev_uc_sync/unsync() assumes that there is a strict 1-to-1 relationship between the source and destination of the sync. In other words, once an address has been synced to a destination device, it will not be synced to any other device through the sync API. However, there are some virtual devices that aggreate a number of lower devices and need to sync addresses to all of them. The current API falls short there. This patch introduces a new dev_uc_sync_multiple() api that can be called in the above circumstances and allows sync to work for every invocation. CC: Jiri Pirko Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 53d3939358a7..623b57b52195 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -209,6 +209,7 @@ struct netdev_hw_addr { #define NETDEV_HW_ADDR_T_UNICAST 4 #define NETDEV_HW_ADDR_T_MULTICAST 5 bool global_use; + int sync_cnt; int refcount; int synced; struct rcu_head rcu_head; @@ -2627,6 +2628,7 @@ extern int dev_uc_add(struct net_device *dev, const unsigned char *addr); extern int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr); extern int dev_uc_del(struct net_device *dev, const unsigned char *addr); extern int dev_uc_sync(struct net_device *to, struct net_device *from); +extern int dev_uc_sync_multiple(struct net_device *to, struct net_device *from); extern void dev_uc_unsync(struct net_device *to, struct net_device *from); extern void dev_uc_flush(struct net_device *dev); extern void dev_uc_init(struct net_device *dev); @@ -2638,6 +2640,7 @@ extern int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr); extern int dev_mc_del(struct net_device *dev, const unsigned char *addr); extern int dev_mc_del_global(struct net_device *dev, const unsigned char *addr); extern int dev_mc_sync(struct net_device *to, struct net_device *from); +extern int dev_mc_sync_multiple(struct net_device *to, struct net_device *from); extern void dev_mc_unsync(struct net_device *to, struct net_device *from); extern void dev_mc_flush(struct net_device *dev); extern void dev_mc_init(struct net_device *dev); -- cgit v1.2.3 From 0635eb8a54cf0fea64b174bb68bc36b9c3d622db Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 15 Apr 2013 13:09:45 -0700 Subject: Move utf16 functions to kernel core and rename We want to be able to use the utf16 functions that are currently present in the EFI variables code in platform-specific code as well. Move them to the kernel core, and in the process rename them to accurately describe what they do - they don't handle UTF16, only UCS2. Signed-off-by: Matthew Garrett Signed-off-by: Matt Fleming --- include/linux/ucs2_string.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 include/linux/ucs2_string.h (limited to 'include/linux') diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h new file mode 100644 index 000000000000..cbb20afdbc01 --- /dev/null +++ b/include/linux/ucs2_string.h @@ -0,0 +1,14 @@ +#ifndef _LINUX_UCS2_STRING_H_ +#define _LINUX_UCS2_STRING_H_ + +#include /* for size_t */ +#include /* for NULL */ + +typedef u16 ucs2_char_t; + +unsigned long ucs2_strnlen(const ucs2_char_t *s, size_t maxlength); +unsigned long ucs2_strlen(const ucs2_char_t *s); +unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength); +int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len); + +#endif /* _LINUX_UCS2_STRING_H_ */ -- cgit v1.2.3 From 8e7ee6f5dfb56a32da760d990be908ed35b1c5bf Mon Sep 17 00:00:00 2001 From: Xiangliang Yu Date: Wed, 20 Mar 2013 22:34:56 -0600 Subject: PCI: Define macro for Marvell vendor ID Define PCI_VENDOR_ID_MARVELL_EXT macro for 0x1b4b vendor ID Signed-off-by: Xiangliang Yu Signed-off-by: Myron Stowe Signed-off-by: Bjorn Helgaas --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index f11c1c2609d5..a80f9e6ce9e5 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1604,6 +1604,7 @@ #define PCI_SUBDEVICE_ID_KEYSPAN_SX2 0x5334 #define PCI_VENDOR_ID_MARVELL 0x11ab +#define PCI_VENDOR_ID_MARVELL_EXT 0x1b4b #define PCI_DEVICE_ID_MARVELL_GT64111 0x4146 #define PCI_DEVICE_ID_MARVELL_GT64260 0x6430 #define PCI_DEVICE_ID_MARVELL_MV64360 0x6460 -- cgit v1.2.3 From f00baae7ad6c5f1503528efa852f0be8e9513f0e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 15 Apr 2013 13:41:15 -0700 Subject: memcg: force use_hierarchy if sane_behavior Turn on use_hierarchy by default if sane_behavior is specified and don't create .use_hierarchy file. It is debatable whether to remove .use_hierarchy file or make it ro as the former could make transition easier in certain cases; however, the behavior changes which will be gated by sane_behavior are intensive including changing basic meaning of certain control knobs in a few controllers and I don't really think keeping this piece would make things easier in any noticeable way, so let's remove it. v2: Explain that mem_cgroup_bind() doesn't have to worry about children as suggested by Michal Hocko. Signed-off-by: Tejun Heo Acked-by: Serge E. Hallyn Acked-by: Li Zefan Acked-by: Michal Hocko Acked-by: KAMEZAWA Hiroyuki --- include/linux/cgroup.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 64047ae7fde1..cda7eb2239e1 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -268,6 +268,9 @@ enum { * * - Remount is disallowed. * + * - memcg: use_hierarchy is on by default and the cgroup file for + * the flag is not created. + * * The followings are planned changes. * * - release_agent will be disallowed once replacement notification -- cgit v1.2.3 From aa2fbe6d44892070d78995f0df875ce930904e29 Mon Sep 17 00:00:00 2001 From: Yang Zhang Date: Thu, 11 Apr 2013 19:21:40 +0800 Subject: KVM: Let ioapic know the irq line status Userspace may deliver RTC interrupt without query the status. So we want to track RTC EOI for this case. Signed-off-by: Yang Zhang Reviewed-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 20d77d24d764..4a76aca31478 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -292,7 +292,8 @@ struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; int (*set)(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level); + struct kvm *kvm, int irq_source_id, int level, + bool line_status); union { struct { unsigned irqchip; @@ -591,7 +592,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem); -int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level); +int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, + bool line_status); long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); @@ -722,10 +724,11 @@ void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, union kvm_ioapic_redirect_entry *entry, unsigned long *deliver_bitmask); #endif -int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level); +int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, + bool line_status); int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level); int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm, - int irq_source_id, int level); + int irq_source_id, int level, bool line_status); bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, -- cgit v1.2.3 From 76ec9d18b8972f1b228f819f6126c9f022b3e642 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Thu, 28 Mar 2013 04:34:56 -0700 Subject: Convert selectors of GENERIC_GPIO to GPIOLIB GENERIC_GPIO is now equivalent to GPIOLIB and features that depended on GENERIC_GPIO can now depend on GPIOLIB to allow removal of this option. Signed-off-by: Alexandre Courbot Acked-by: Linus Walleij Acked-by: Grant Likely --- include/linux/gpio.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index f6c7ae3e223b..552e3f46e4a3 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -39,7 +39,7 @@ struct gpio { const char *label; }; -#ifdef CONFIG_GENERIC_GPIO +#ifdef CONFIG_GPIOLIB #ifdef CONFIG_ARCH_HAVE_CUSTOM_GPIO_H #include @@ -74,7 +74,7 @@ static inline int irq_to_gpio(unsigned int irq) #endif /* ! CONFIG_ARCH_HAVE_CUSTOM_GPIO_H */ -#else /* ! CONFIG_GENERIC_GPIO */ +#else /* ! CONFIG_GPIOLIB */ #include #include @@ -226,7 +226,7 @@ gpiochip_remove_pin_ranges(struct gpio_chip *chip) WARN_ON(1); } -#endif /* ! CONFIG_GENERIC_GPIO */ +#endif /* ! CONFIG_GPIOLIB */ struct device; -- cgit v1.2.3 From 37799e52a29af2268d1fbe18908a0d6b9f68af88 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 26 Mar 2013 14:02:26 +0100 Subject: mac80211: unify CSA action frame/beacon processing CSA action frame content should be processed as variable IEs rather than fixed to make it extensible. Unify the code and process them just like CSA in beacons to make it easier to extend for HT/VHT. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index e46fea8b972e..8f80b3a93501 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -840,9 +840,7 @@ struct ieee80211_mgmt { } __packed wme_action; struct{ u8 action_code; - u8 element_id; - u8 length; - struct ieee80211_channel_sw_ie sw_elem; + u8 variable[0]; } __packed chan_switch; struct{ u8 action_code; -- cgit v1.2.3 From b4f286a1c0ad0b84c2d502b354d4d98d5a86c64b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 26 Mar 2013 14:13:58 +0100 Subject: mac80211: support extended channel switch Support extended channel switch when the operating class is one of the global operating classes as defined in Annex E of 802.11-2012. If it isn't, disconnect from the AP instead. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 8f80b3a93501..2a10acc65a54 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -672,6 +672,18 @@ struct ieee80211_channel_sw_ie { u8 count; } __packed; +/** + * struct ieee80211_ext_chansw_ie + * + * This structure represents the "Extended Channel Switch Announcement element" + */ +struct ieee80211_ext_chansw_ie { + u8 mode; + u8 new_operating_class; + u8 new_ch_num; + u8 count; +} __packed; + /** * struct ieee80211_tim * -- cgit v1.2.3 From 85220d71bf3ca1ba9129e0744247ae5f61bec559 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 25 Mar 2013 18:29:27 +0100 Subject: mac80211: support secondary channel offset in CSA Add support for the secondary channel offset IE in channel switch announcements. This is necessary for proper handling of CSA on HT access points. For this to work it is also necessary to convert everything here to use chandef structs instead of just channels. The driver updates aren't really correct though. In particular, the TI wl18xx driver update can't possibly be right since it just ignores the new channel width for lack of firmware API. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2a10acc65a54..95621528436c 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -684,6 +684,16 @@ struct ieee80211_ext_chansw_ie { u8 count; } __packed; +/** + * struct ieee80211_sec_chan_offs_ie - secondary channel offset IE + * @sec_chan_offs: secondary channel offset, uses IEEE80211_HT_PARAM_CHA_SEC_* + * values here + * This structure represents the "Secondary Channel Offset element" + */ +struct ieee80211_sec_chan_offs_ie { + u8 sec_chan_offs; +} __packed; + /** * struct ieee80211_tim * @@ -1648,6 +1658,7 @@ enum ieee80211_eid { WLAN_EID_HT_CAPABILITY = 45, WLAN_EID_HT_OPERATION = 61, + WLAN_EID_SECONDARY_CHANNEL_OFFSET = 62, WLAN_EID_RSN = 48, WLAN_EID_MMIE = 76, -- cgit v1.2.3 From 1b3a2e494bc793445f576c5476e9767cf7621684 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 26 Mar 2013 15:17:18 +0100 Subject: mac80211: handle extended channel switch announcement Handle the (public) extended channel switch announcement action frames. Parts of the data in these frames isn't really in IEs, but put it into the elems struct anyway to simplify the handling. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 95621528436c..ce07161c8735 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -864,6 +864,11 @@ struct ieee80211_mgmt { u8 action_code; u8 variable[0]; } __packed chan_switch; + struct{ + u8 action_code; + struct ieee80211_ext_chansw_ie data; + u8 variable[0]; + } __packed ext_chan_switch; struct{ u8 action_code; u8 dialog_token; @@ -1816,6 +1821,7 @@ enum ieee80211_key_len { /* Public action codes */ enum ieee80211_pub_actioncode { + WLAN_PUB_ACTION_EXT_CHANSW_ANN = 4, WLAN_PUB_ACTION_TDLS_DISCOVER_RES = 14, }; -- cgit v1.2.3 From b2e506bfc4d752b68a0ccaae1e977898263eba4c Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 26 Mar 2013 14:54:16 +0100 Subject: mac80211: parse VHT channel switch IEs VHT introduces multiple IEs that need to be parsed for a wide bandwidth channel switch. Two are (currently) needed in mac80211: * wide bandwidth channel switch element * channel switch wrapper element The former is contained in the latter for beacons and probe responses, but not for the spectrum management action frames so the IE parser needs a new argument to differentiate them. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index ce07161c8735..06b0ed0154a4 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -694,6 +694,14 @@ struct ieee80211_sec_chan_offs_ie { u8 sec_chan_offs; } __packed; +/** + * struct ieee80211_wide_bw_chansw_ie - wide bandwidth channel switch IE + */ +struct ieee80211_wide_bw_chansw_ie { + u8 new_channel_width; + u8 new_center_freq_seg0, new_center_freq_seg1; +} __packed; + /** * struct ieee80211_tim * @@ -1698,6 +1706,8 @@ enum ieee80211_eid { WLAN_EID_VHT_CAPABILITY = 191, WLAN_EID_VHT_OPERATION = 192, WLAN_EID_OPMODE_NOTIF = 199, + WLAN_EID_WIDE_BW_CHANNEL_SWITCH = 194, + WLAN_EID_CHANNEL_SWITCH_WRAPPER = 196, /* 802.11ad */ WLAN_EID_NON_TX_BSSID_CAP = 83, -- cgit v1.2.3 From c309dbb4debb714566e4cf0d5d4e4023c3c4ff2f Mon Sep 17 00:00:00 2001 From: Myron Stowe Date: Fri, 12 Apr 2013 05:44:30 +0000 Subject: PCI/ACPI: Remove support of ACPI PCI subdrivers Both sub-drivers of the "PCI Root Bridge ("pci_bridge")" driver, "acpiphp" and "pci_slot", have been converted to hook directly into the PCI core. With the conversions there are no remaining usages of the 'struct acpi_pci_driver' list based infrastructure. This patch removes it. Signed-off-by: Myron Stowe Signed-off-by: Jiang Liu Signed-off-by: Bjorn Helgaas Reviewed-by: Yinghai Lu Cc: "Rafael J. Wysocki" Cc: Toshi Kani --- include/linux/acpi.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index bcbdd7484e58..03053aca5b32 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -152,15 +152,6 @@ void acpi_penalize_isa_irq(int irq, int active); void acpi_pci_irq_disable (struct pci_dev *dev); -struct acpi_pci_driver { - struct list_head node; - int (*add)(struct acpi_pci_root *root); - void (*remove)(struct acpi_pci_root *root); -}; - -int acpi_pci_register_driver(struct acpi_pci_driver *driver); -void acpi_pci_unregister_driver(struct acpi_pci_driver *driver); - extern int ec_read(u8 addr, u8 *val); extern int ec_write(u8 addr, u8 val); extern int ec_transaction(u8 command, -- cgit v1.2.3 From 063cc6d5591ea9c0631b81ac5c7b829d99738b2f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 27 Mar 2013 21:28:22 -0400 Subject: NVMe: Abstract out sector to block number conversion Introduce nvme_block_nr() to help convert sectors to block numbers. This fixes an integer overflow in the SCSI conversion layer, and it's slightly less typing than opencoding it. Signed-off-by: Matthew Wilcox Acked-by: Keith Busch --- include/linux/nvme.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index aa575033dbe7..09f419d4da4e 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -566,6 +566,11 @@ struct nvme_iod { struct scatterlist sg[0]; }; +static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector) +{ + return (sector >> (ns->lba_shift - 9)); +} + /** * nvme_free_iod - frees an nvme_iod * @dev: The device that the I/O was submitted to -- cgit v1.2.3 From 1c9b52651dad0ff1fa71fc6205c86d972f25bcc0 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 16 Apr 2013 15:21:06 -0400 Subject: NVMe: Fix endian-related problems in user I/O submission path When constructing the command, dsmgmt needs to be treated as a 32-bit value, not a 16-bit value. reftag, apptag and appmask all need to be converted from native-endian to little-endian. Again, sparse's bitwise warnings caught this problem. Thanks to Keith for pointing out the correct way to fix the reftag. Signed-off-by: Matthew Wilcox Acked-by: Keith Busch --- include/linux/nvme.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 09f419d4da4e..7ae7ecfc0947 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -207,11 +207,11 @@ struct nvme_common_command { __u8 flags; __u16 command_id; __le32 nsid; - __u32 cdw2[2]; + __le32 cdw2[2]; __le64 metadata; __le64 prp1; __le64 prp2; - __u32 cdw10[6]; + __le32 cdw10[6]; }; struct nvme_rw_command { -- cgit v1.2.3 From 3d81bc7e96d6bca0b8f8b7d1bf6ea72caa3aac57 Mon Sep 17 00:00:00 2001 From: Yang Zhang Date: Thu, 11 Apr 2013 19:25:13 +0800 Subject: KVM: Call common update function when ioapic entry changed. Both TMR and EOI exit bitmap need to be updated when ioapic changed or vcpu's id/ldr/dfr changed. So use common function instead eoi exit bitmap specific function. Signed-off-by: Yang Zhang Reviewed-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4a76aca31478..93a50054d46c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -126,7 +126,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_MASTERCLOCK_UPDATE 19 #define KVM_REQ_MCLOCK_INPROGRESS 20 #define KVM_REQ_EPR_EXIT 21 -#define KVM_REQ_EOIBITMAP 22 +#define KVM_REQ_SCAN_IOAPIC 22 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -575,7 +575,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); void kvm_make_mclock_inprogress_request(struct kvm *kvm); -void kvm_make_update_eoibitmap_request(struct kvm *kvm); +void kvm_make_scan_ioapic_request(struct kvm *kvm); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); -- cgit v1.2.3 From 5e82e952f04681c10f35e02ee0a4a43ec027137a Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 19 Feb 2013 10:17:58 -0700 Subject: NVMe: Add a character device for each nvme device Registers a miscellaneous device for each nvme controller probed. This creates character device files as /dev/nvmeN, where N is the device instance, and supports nvme admin ioctl commands so devices without namespaces can be managed. Signed-off-by: Keith Busch Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 7ae7ecfc0947..9b6fba872f47 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -507,6 +507,8 @@ struct nvme_admin_cmd { #ifdef __KERNEL__ #include +#include +#include #define NVME_IO_TIMEOUT (5 * HZ) @@ -527,6 +529,9 @@ struct nvme_dev { struct msix_entry *entry; struct nvme_bar __iomem *bar; struct list_head namespaces; + struct kref kref; + struct miscdevice miscdev; + char name[12]; char serial[20]; char model[40]; char firmware_rev[8]; -- cgit v1.2.3 From 43b5abe0640100a9e9424c91298c7993d443ffb7 Mon Sep 17 00:00:00 2001 From: Sascha Herrmann Date: Sun, 14 Apr 2013 22:33:28 +0000 Subject: at86rf230: add irq type configuration option Add option to at86rf230 platform data to configure the type of the interrupt used by the driver. The irq polarity of the device will be configured accordingly. Signed-off-by: Sascha Herrmann Signed-off-by: David S. Miller --- include/linux/spi/at86rf230.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/at86rf230.h b/include/linux/spi/at86rf230.h index b2b1afbb3202..aa327a8105ad 100644 --- a/include/linux/spi/at86rf230.h +++ b/include/linux/spi/at86rf230.h @@ -26,6 +26,20 @@ struct at86rf230_platform_data { int rstn; int slp_tr; int dig2; + + /* Setting the irq_type will configure the driver to request + * the platform irq trigger type according to the given value + * and configure the interrupt polarity of the device to the + * corresponding polarity. + * + * Allowed values are: IRQF_TRIGGER_RISING, IRQF_TRIGGER_FALLING, + * IRQF_TRIGGER_HIGH and IRQF_TRIGGER_LOW + * + * Setting it to 0, the driver does not touch the trigger type + * configuration of the interrupt and sets the interrupt polarity + * of the device to high active (the default value). + */ + int irq_type; }; #endif -- cgit v1.2.3 From 62062cf8a3a99a933efdac549da380f230dbe982 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Tue, 16 Apr 2013 13:08:43 -0400 Subject: audit: allow checking the type of audit message in the user filter When userspace sends messages to the audit system it includes a type. We want to be able to filter messages based on that type without have to do the all or nothing option currently available on the AUDIT_FILTER_TYPE filter list. Instead we should be able to use the AUDIT_FILTER_USER filter list and just use the message type as one part of the matching decision. Signed-off-by: Eric Paris --- include/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 8f92e1dea966..b26d7f121ac5 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -438,7 +438,7 @@ static inline void audit_log_secctx(struct audit_buffer *ab, u32 secid) extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ -extern int audit_filter_user(void); +extern int audit_filter_user(int type); extern int audit_filter_type(int type); extern int audit_receive_filter(int type, int pid, int seq, void *data, size_t datasz, kuid_t loginuid, -- cgit v1.2.3 From 549b19cc9f31e8fdda317625d564bac0052a3328 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 16 Apr 2013 18:42:34 -0400 Subject: NFSv4: Record the OPEN create mode used in the nfs4_opendata structure If we're doing NFSv4.1 against a server that has persistent sessions, then we should not need to call SETATTR in order to reset the file attributes immediately after doing an exclusive create. Note that since the create mode depends on the type of session that has been negotiated with the server, we should not choose the mode until after we've got a session slot. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 90a4aa190b43..bdc100f66dfb 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -349,6 +349,7 @@ struct nfs_openargs { const u32 * bitmask; const u32 * open_bitmap; __u32 claim; + enum createmode4 createmode; }; struct nfs_openres { -- cgit v1.2.3 From b4cbb197c7e7a68dbad0d491242e3ca67420c13e Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 16 Apr 2013 13:45:37 -0700 Subject: vm: add vm_iomap_memory() helper function Various drivers end up replicating the code to mmap() their memory buffers into user space, and our core memory remapping function may be very flexible but it is unnecessarily complicated for the common cases to use. Our internal VM uses pfn's ("page frame numbers") which simplifies things for the VM, and allows us to pass physical addresses around in a denser and more efficient format than passing a "phys_addr_t" around, and having to shift it up and down by the page size. But it just means that drivers end up doing that shifting instead at the interface level. It also means that drivers end up mucking around with internal VM things like the vma details (vm_pgoff, vm_start/end) way more than they really need to. So this just exports a function to map a certain physical memory range into user space (using a phys_addr_t based interface that is much more natural for a driver) and hides all the complexity from the driver. Some drivers will still end up tweaking the vm_page_prot details for things like prefetching or cacheability etc, but that's actually relevant to the driver, rather than caring about what the page offset of the mapping is into the particular IO memory region. Acked-by: Greg Kroah-Hartman Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e19ff30ad0a2..e2091b88d24c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1611,6 +1611,8 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); +int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); + struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags, -- cgit v1.2.3 From 6f780965aaf3354a3a6165d9018393a4a381b81d Mon Sep 17 00:00:00 2001 From: Hongbo Zhang Date: Wed, 3 Apr 2013 20:18:08 +0800 Subject: ab8500_btemp: Make ab8500_btemp_get* interfaces public Make ab8500_btemp_get_temp interface public, export it and also export the ab8500_btemp_get, ab8500_btemp_get_batctrl_temp interfaces, so that the ab8500 hwmon driver can use them. Signed-off-by: Hongbo Zhang Signed-off-by: Anton Vorontsov --- include/linux/mfd/abx500/ab8500-bm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h index f5214dc651f9..cc892a8d8d6e 100644 --- a/include/linux/mfd/abx500/ab8500-bm.h +++ b/include/linux/mfd/abx500/ab8500-bm.h @@ -465,6 +465,7 @@ void ab8500_fg_reinit(void); void ab8500_charger_usb_state_changed(u8 bm_usb_state, u16 mA); struct ab8500_btemp *ab8500_btemp_get(void); int ab8500_btemp_get_batctrl_temp(struct ab8500_btemp *btemp); +int ab8500_btemp_get_temp(struct ab8500_btemp *btemp); struct ab8500_fg *ab8500_fg_get(void); int ab8500_fg_inst_curr_blocking(struct ab8500_fg *dev); int ab8500_fg_inst_curr_start(struct ab8500_fg *di); -- cgit v1.2.3 From 2c89940786ef8c6e4dbcd2960142ce513e289f1e Mon Sep 17 00:00:00 2001 From: Hongbo Zhang Date: Wed, 3 Apr 2013 20:18:10 +0800 Subject: ab8500_{bmdata,fg}: Add const attributes to some data arrays This patch adds const attributes to AB8500 power and temperature related read-only data arrays. Signed-off-by: Hongbo Zhang Signed-off-by: Anton Vorontsov --- include/linux/mfd/abx500.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500.h b/include/linux/mfd/abx500.h index 33b0253569a3..3301b2031c8d 100644 --- a/include/linux/mfd/abx500.h +++ b/include/linux/mfd/abx500.h @@ -183,11 +183,11 @@ struct abx500_battery_type { int low_high_vol_lvl; int battery_resistance; int n_temp_tbl_elements; - struct abx500_res_to_temp *r_to_t_tbl; + const struct abx500_res_to_temp *r_to_t_tbl; int n_v_cap_tbl_elements; - struct abx500_v_to_cap *v_to_cap_tbl; + const struct abx500_v_to_cap *v_to_cap_tbl; int n_batres_tbl_elements; - struct batres_vs_temp *batres_tbl; + const struct batres_vs_temp *batres_tbl; }; /** -- cgit v1.2.3 From ea2be6f21071b4af3b765a0f228be2bef08515e9 Mon Sep 17 00:00:00 2001 From: Hongbo Zhang Date: Wed, 3 Apr 2013 20:18:11 +0800 Subject: ab8500_bmdata: Export abx500_res_to_temp tables for hwmon This patch exports the thermistor resistance-to-temperature tables, so that the hwmon driver can access them, and also adds the corresponding table size variables. Signed-off-by: Hongbo Zhang Acked-by: Guenter Roeck Signed-off-by: Anton Vorontsov --- include/linux/power/ab8500.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/linux/power/ab8500.h (limited to 'include/linux') diff --git a/include/linux/power/ab8500.h b/include/linux/power/ab8500.h new file mode 100644 index 000000000000..cdbb6c2a8c51 --- /dev/null +++ b/include/linux/power/ab8500.h @@ -0,0 +1,16 @@ +/* + * Copyright (C) ST-Ericsson 2013 + * Author: Hongbo Zhang + * License terms: GNU General Public License v2 + */ + +#ifndef PWR_AB8500_H +#define PWR_AB8500_H + +extern const struct abx500_res_to_temp ab8500_temp_tbl_a_thermistor[]; +extern const int ab8500_temp_tbl_a_size; + +extern const struct abx500_res_to_temp ab8500_temp_tbl_b_thermistor[]; +extern const int ab8500_temp_tbl_b_size; + +#endif /* PWR_AB8500_H */ -- cgit v1.2.3 From 5e0848c6026ab98f47e0e179f5c76875cd509d58 Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Mon, 1 Apr 2013 17:45:54 -0400 Subject: power_supply: Add core support for supplied_from This patch adds support for supplies to register a list of char *'s which represent the list of supplies which supply them. This is the opposite as the supplied_to list. This change maintains support for supplied_to until all drivers which make use of it already are converted. Signed-off-by: Rhyland Klein Reviewed-by: Stephen Warren Signed-off-by: Anton Vorontsov --- include/linux/power_supply.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 002a99f96331..c1cbd5e4e484 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -171,6 +171,9 @@ struct power_supply { char **supplied_to; size_t num_supplicants; + char **supplied_from; + size_t num_supplies; + int (*get_property)(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val); -- cgit v1.2.3 From f6e0b081fb300a4601b064346963cf6bb163f437 Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Mon, 1 Apr 2013 17:45:55 -0400 Subject: power_supply: Populate supplied_from hierarchy from the device tree With this patch the power_supply_core will try to populate supplied_from hierarchy from the device tree. Signed-off-by: Rhyland Klein Signed-off-by: Anton Vorontsov --- include/linux/power_supply.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index c1cbd5e4e484..3828cefb4f65 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -173,6 +173,9 @@ struct power_supply { char **supplied_from; size_t num_supplies; +#ifdef CONFIG_OF + struct device_node *of_node; +#endif int (*get_property)(struct power_supply *psy, enum power_supply_property psp, -- cgit v1.2.3 From 9f550553a470d3b05fc8bdced3a738d8ed5b8d8a Mon Sep 17 00:00:00 2001 From: Shlomo Pongratz Date: Wed, 10 Apr 2013 14:26:47 +0000 Subject: mlx4_core: Implement SRQ object lookup from srqn Expose a new API mlx4_srq_lookup() to retrive a SRQ based on its number. This API is needed in the mlx4_ib driver CQ polling logic, when a work completion is associated with a XRC TGT QP. Since a target QP may redirect to more than one XRC SRQ, the srq field in the QP has no usage and the real XRC SRQ need to be retrived using the information from the XRCETH IB header which is placed in the HW CQE. Signed-off-by: Shlomo Pongratz Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/srq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/srq.h b/include/linux/mlx4/srq.h index 799a0697a383..192e0f7784f2 100644 --- a/include/linux/mlx4/srq.h +++ b/include/linux/mlx4/srq.h @@ -39,4 +39,6 @@ struct mlx4_wqe_srq_next_seg { u32 reserved2[3]; }; +struct mlx4_srq *mlx4_srq_lookup(struct mlx4_dev *dev, u32 srqn); + #endif /* MLX4_SRQ_H */ -- cgit v1.2.3 From d5abc7c1050ab2b9556a4bf21626cd74e83cd086 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Sun, 3 Feb 2013 19:53:46 +0000 Subject: efi: move utf16 string functions to efi.h There are currently two implementations of the utf16 string functions. Somewhat confusingly, they've got different names. Centralise the functions in efi.h. Reviewed-by: Tom Gundersen Tested-by: Tom Gundersen Reviewed-by: Mike Waychison Signed-off-by: Matt Fleming --- include/linux/efi.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 9bf2f1fcae27..d1d782a6d34c 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -719,6 +719,23 @@ static inline void memrange_efi_to_native(u64 *addr, u64 *npages) *addr &= PAGE_MASK; } +/* Return the number of unicode characters in data */ +static inline unsigned long +utf16_strnlen(efi_char16_t *s, size_t maxlength) +{ + unsigned long length = 0; + + while (*s++ != 0 && length < maxlength) + length++; + return length; +} + +static inline unsigned long +utf16_strlen(efi_char16_t *s) +{ + return utf16_strnlen(s, ~0UL); +} + #if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE) /* * EFI Variable support. -- cgit v1.2.3 From e14ab23dde12b80db4c94b684a2e485b72b16af3 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Sun, 3 Feb 2013 20:16:40 +0000 Subject: efivars: efivar_entry API There isn't really a formal interface for dealing with EFI variables or struct efivar_entry. Historically, this has led to various bits of code directly accessing the generic EFI variable ops, which inherently ties it to specific EFI variable operations instead of indirectly using whatever ops were registered with register_efivars(). This lead to the efivarfs code only working with the generic EFI variable ops and not CONFIG_GOOGLE_SMI. Encapsulate everything that needs to access '__efivars' inside an efivar_entry_* API and use the new API in the pstore, sysfs and efivarfs code. Much of the efivars code had to be rewritten to use this new API. For instance, it is now up to the users of the API to build the initial list of EFI variables in their efivar_init() callback function. The variable list needs to be passed to efivar_init() which allows us to keep work arounds for things like implementation bugs in GetNextVariable() in a central location. Allowing users of the API to use a callback function to build the list greatly benefits the efivarfs code which needs to allocate inodes and dentries for every variable. It previously did this in a racy way because the code ran without holding the variable spinlock. Both the sysfs and efivarfs code maintain their own lists which means the two interfaces can be running simultaneously without interference, though it should be noted that because no synchronisation is performed it is very easy to create inconsistencies. efibootmgr doesn't currently use efivarfs and users are likely to also require the old sysfs interface, so it makes sense to allow both to be built. Reviewed-by: Tom Gundersen Tested-by: Tom Gundersen Cc: Seiji Aguchi Cc: Matthew Garrett Cc: Jeremy Kerr Cc: Tony Luck Cc: Mike Waychison Signed-off-by: Matt Fleming --- include/linux/efi.h | 76 ++++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 69 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index d1d782a6d34c..cd561b301e6a 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -662,6 +662,12 @@ static inline int efi_enabled(int facility) EFI_VARIABLE_AUTHENTICATED_WRITE_ACCESS | \ EFI_VARIABLE_TIME_BASED_AUTHENTICATED_WRITE_ACCESS | \ EFI_VARIABLE_APPEND_WRITE) +/* + * Length of a GUID string (strlen("aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee")) + * not including trailing NUL + */ +#define EFI_VARIABLE_GUID_LEN 36 + /* * The type of search to perform when calling boottime->locate_handle */ @@ -762,19 +768,75 @@ struct efivars { * which is protected by the BKL, so that path is safe. */ spinlock_t lock; - struct list_head list; struct kset *kset; struct kobject *kobject; - struct bin_attribute *new_var, *del_var; const struct efivar_operations *ops; - struct efivar_entry *walk_entry; - struct pstore_info efi_pstore_info; }; -int register_efivars(struct efivars *efivars, +/* + * The maximum size of VariableName + Data = 1024 + * Therefore, it's reasonable to save that much + * space in each part of the structure, + * and we use a page for reading/writing. + */ + +struct efi_variable { + efi_char16_t VariableName[1024/sizeof(efi_char16_t)]; + efi_guid_t VendorGuid; + unsigned long DataSize; + __u8 Data[1024]; + efi_status_t Status; + __u32 Attributes; +} __attribute__((packed)); + +struct efivar_entry { + struct efi_variable var; + struct list_head list; + struct kobject kobj; +}; + +int efivars_register(struct efivars *efivars, const struct efivar_operations *ops, - struct kobject *parent_kobj); -void unregister_efivars(struct efivars *efivars); + struct kobject *kobject); +int efivars_unregister(struct efivars *efivars); +struct kobject *efivars_kobject(void); + +int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), + void *data, bool atomic, bool duplicates, + struct list_head *head); + +void efivar_entry_add(struct efivar_entry *entry, struct list_head *head); +void efivar_entry_remove(struct efivar_entry *entry); + +int __efivar_entry_delete(struct efivar_entry *entry); +int efivar_entry_delete(struct efivar_entry *entry); + +int __efivar_entry_size(struct efivar_entry *entry, unsigned long *size); +int efivar_entry_size(struct efivar_entry *entry, unsigned long *size); +int efivar_entry_get(struct efivar_entry *entry, u32 *attributes, + unsigned long *size, void *data); +int efivar_entry_set(struct efivar_entry *entry, u32 attributes, + unsigned long size, void *data, struct list_head *head); +int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes, + unsigned long *size, void *data, bool *set); +int efivar_entry_set_safe(efi_char16_t *name, efi_guid_t vendor, u32 attributes, + bool block, unsigned long size, void *data); + +void efivar_entry_iter_begin(void); +void efivar_entry_iter_end(void); + +int __efivar_entry_iter(int (*func)(struct efivar_entry *, void *), + struct list_head *head, void *data, + struct efivar_entry **prev); +int efivar_entry_iter(int (*func)(struct efivar_entry *, void *), + struct list_head *head, void *data); + +struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, + struct list_head *head, bool remove); + +bool efivar_validate(struct efi_variable *var, u8 *data, unsigned long len); + +int efivars_sysfs_init(void); #endif /* CONFIG_EFI_VARS */ -- cgit v1.2.3 From 048517722cde2595a7366d0c3c72b8b1ec142a9c Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Fri, 8 Feb 2013 15:48:51 +0000 Subject: efivars: Move pstore code into the new EFI directory efivars.c has grown far too large and needs to be divided up. Create a new directory and move the persistence storage code to efi-pstore.c now that it uses the new efivar API. This helps us to greatly reduce the size of efivars.c and paves the way for moving other code out of efivars.c. Note that because CONFIG_EFI_VARS can be built as a module efi-pstore must also include support for building as a module. Reviewed-by: Tom Gundersen Tested-by: Tom Gundersen Cc: Seiji Aguchi Cc: Anton Vorontsov Cc: Colin Cross Cc: Kees Cook Cc: Matthew Garrett Cc: Tony Luck Signed-off-by: Matt Fleming --- include/linux/efi.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index cd561b301e6a..8ff6ec1ac046 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -743,6 +743,34 @@ utf16_strlen(efi_char16_t *s) } #if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE) +/* + * Return the number of bytes is the length of this string + * Note: this is NOT the same as the number of unicode characters + */ +static inline unsigned long +utf16_strsize(efi_char16_t *data, unsigned long maxlength) +{ + return utf16_strnlen(data, maxlength/sizeof(efi_char16_t)) * sizeof(efi_char16_t); +} + +static inline int +utf16_strncmp(const efi_char16_t *a, const efi_char16_t *b, size_t len) +{ + while (1) { + if (len == 0) + return 0; + if (*a < *b) + return -1; + if (*a > *b) + return 1; + if (*a == 0) /* implies *b == 0 */ + return 0; + a++; + b++; + len--; + } +} + /* * EFI Variable support. * @@ -795,6 +823,14 @@ struct efivar_entry { struct kobject kobj; }; +extern struct list_head efivar_sysfs_list; + +static inline void +efivar_unregister(struct efivar_entry *var) +{ + kobject_put(&var->kobj); +} + int efivars_register(struct efivars *efivars, const struct efivar_operations *ops, struct kobject *kobject); @@ -836,6 +872,8 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, bool efivar_validate(struct efi_variable *var, u8 *data, unsigned long len); +void efivar_run_worker(void); + int efivars_sysfs_init(void); #endif /* CONFIG_EFI_VARS */ -- cgit v1.2.3 From a9499fa7cd3fd4824a7202d00c766b269fa3bda6 Mon Sep 17 00:00:00 2001 From: Tom Gundersen Date: Fri, 8 Feb 2013 15:37:06 +0000 Subject: efi: split efisubsystem from efivars This registers /sys/firmware/efi/{,systab,efivars/} whenever EFI is enabled and the system is booted with EFI. This allows *) userspace to check for the existence of /sys/firmware/efi as a way to determine whether or it is running on an EFI system. *) 'mount -t efivarfs none /sys/firmware/efi/efivars' without manually loading any modules. [ Also, move the efivar API into vars.c and unconditionally compile it. This allows us to move efivars.c, which now only contains the sysfs variable code, into the firmware/efi directory. Note that the efivars.c filename is kept to maintain backwards compatability with the old efivars.ko module. With this patch it is now possible for efivarfs to be built without CONFIG_EFI_VARS - Matt ] Cc: Seiji Aguchi Cc: Tony Luck Cc: Mike Waychison Cc: Kay Sievers Cc: Jeremy Kerr Cc: Matthew Garrett Cc: Chun-Yi Lee Cc: Andy Whitcroft Cc: Tobias Powalowski Signed-off-by: Tom Gundersen Signed-off-by: Matt Fleming --- include/linux/efi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 8ff6ec1ac046..2fc816682714 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -742,7 +742,6 @@ utf16_strlen(efi_char16_t *s) return utf16_strnlen(s, ~0UL); } -#if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE) /* * Return the number of bytes is the length of this string * Note: this is NOT the same as the number of unicode characters @@ -872,8 +871,10 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, bool efivar_validate(struct efi_variable *var, u8 *data, unsigned long len); +extern struct work_struct efivar_work; void efivar_run_worker(void); +#if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE) int efivars_sysfs_init(void); #endif /* CONFIG_EFI_VARS */ -- cgit v1.2.3 From aa07f02793ec149d560142f25af0243fff84208b Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Wed, 17 Apr 2013 15:13:12 +0530 Subject: regulator: palmas: support for external regulator through control outputs Palmas device have control outputs like REGEN1, REGEN2, REGEN3, SYSEN1 and SYSEN2. These control outputs can be used for controlling external voltage switches to enabled/disable voltage outputs. Add support of these control outputs through regulator framework. Signed-off-by: Laxman Dewangan Signed-off-by: Mark Brown --- include/linux/mfd/palmas.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index a4d13d7cd001..44256aa7b46a 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -154,6 +154,12 @@ enum palmas_regulators { PALMAS_REG_LDO9, PALMAS_REG_LDOLN, PALMAS_REG_LDOUSB, + /* External regulators */ + PALMAS_REG_REGEN1, + PALMAS_REG_REGEN2, + PALMAS_REG_REGEN3, + PALMAS_REG_SYSEN1, + PALMAS_REG_SYSEN2, /* Total number of regulators */ PALMAS_NUM_REGS, }; -- cgit v1.2.3 From 17c11a7603496949989ed286ed218a9e645b6259 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Wed, 17 Apr 2013 15:13:13 +0530 Subject: regulator: palmas: add support for LDO8 tracking mode LDO8 of Palma device like tps65913 support the tracking mode on which LDO8 track the SMPS45 voltage when SMPS45 is ON and use the LDO8.VOLTAGE_SEL register when SMPS45 is OFF. On track mode, the steps of voltage change for LDO8 is 25mV where in non-tracking mode it is 50mV. Set the steps accordingly. Number of voltage count is still same for both the cases. Signed-off-by: Laxman Dewangan Acked-by: Graeme Gregory Signed-off-by: Mark Brown --- include/linux/mfd/palmas.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 44256aa7b46a..10daa8c1e73c 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -177,6 +177,9 @@ struct palmas_pmic_platform_data { /* use LDO6 for vibrator control */ int ldo6_vibrator; + + /* Enable tracking mode of LDO8 */ + bool enable_ldo8_tracking; }; struct palmas_usb_platform_data { -- cgit v1.2.3 From f39d5b72913e2a9ff00ba5ab145ee05a888b1286 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 12 Apr 2013 12:02:59 -0600 Subject: PCI: Remove "extern" from function declarations We had an inconsistent mix of using and omitting the "extern" keyword on function declarations in header files. This removes them all. Signed-off-by: Bjorn Helgaas --- include/linux/pci-aspm.h | 20 +++++----- include/linux/pci-ats.h | 26 ++++++------- include/linux/pci.h | 95 ++++++++++++++++++++++----------------------- include/linux/pci_hotplug.h | 12 +++--- include/linux/pcieport_if.h | 4 +- 5 files changed, 78 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-aspm.h b/include/linux/pci-aspm.h index c8320144fe79..8af4610c2e41 100644 --- a/include/linux/pci-aspm.h +++ b/include/linux/pci-aspm.h @@ -23,14 +23,14 @@ #define PCIE_LINK_STATE_CLKPM 4 #ifdef CONFIG_PCIEASPM -extern void pcie_aspm_init_link_state(struct pci_dev *pdev); -extern void pcie_aspm_exit_link_state(struct pci_dev *pdev); -extern void pcie_aspm_pm_state_change(struct pci_dev *pdev); -extern void pcie_aspm_powersave_config_link(struct pci_dev *pdev); -extern void pci_disable_link_state(struct pci_dev *pdev, int state); -extern void pci_disable_link_state_locked(struct pci_dev *pdev, int state); -extern void pcie_clear_aspm(struct pci_bus *bus); -extern void pcie_no_aspm(void); +void pcie_aspm_init_link_state(struct pci_dev *pdev); +void pcie_aspm_exit_link_state(struct pci_dev *pdev); +void pcie_aspm_pm_state_change(struct pci_dev *pdev); +void pcie_aspm_powersave_config_link(struct pci_dev *pdev); +void pci_disable_link_state(struct pci_dev *pdev, int state); +void pci_disable_link_state_locked(struct pci_dev *pdev, int state); +void pcie_clear_aspm(struct pci_bus *bus); +void pcie_no_aspm(void); #else static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { @@ -56,8 +56,8 @@ static inline void pcie_no_aspm(void) #endif #ifdef CONFIG_PCIEASPM_DEBUG /* this depends on CONFIG_PCIEASPM */ -extern void pcie_aspm_create_sysfs_dev_files(struct pci_dev *pdev); -extern void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev); +void pcie_aspm_create_sysfs_dev_files(struct pci_dev *pdev); +void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev); #else static inline void pcie_aspm_create_sysfs_dev_files(struct pci_dev *pdev) { diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 7ef68724f0f0..68bcefd7fca0 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -14,9 +14,9 @@ struct pci_ats { #ifdef CONFIG_PCI_ATS -extern int pci_enable_ats(struct pci_dev *dev, int ps); -extern void pci_disable_ats(struct pci_dev *dev); -extern int pci_ats_queue_depth(struct pci_dev *dev); +int pci_enable_ats(struct pci_dev *dev, int ps); +void pci_disable_ats(struct pci_dev *dev); +int pci_ats_queue_depth(struct pci_dev *dev); /** * pci_ats_enabled - query the ATS status @@ -54,12 +54,12 @@ static inline int pci_ats_enabled(struct pci_dev *dev) #ifdef CONFIG_PCI_PRI -extern int pci_enable_pri(struct pci_dev *pdev, u32 reqs); -extern void pci_disable_pri(struct pci_dev *pdev); -extern bool pci_pri_enabled(struct pci_dev *pdev); -extern int pci_reset_pri(struct pci_dev *pdev); -extern bool pci_pri_stopped(struct pci_dev *pdev); -extern int pci_pri_status(struct pci_dev *pdev); +int pci_enable_pri(struct pci_dev *pdev, u32 reqs); +void pci_disable_pri(struct pci_dev *pdev); +bool pci_pri_enabled(struct pci_dev *pdev); +int pci_reset_pri(struct pci_dev *pdev); +bool pci_pri_stopped(struct pci_dev *pdev); +int pci_pri_status(struct pci_dev *pdev); #else /* CONFIG_PCI_PRI */ @@ -95,10 +95,10 @@ static inline int pci_pri_status(struct pci_dev *pdev) #ifdef CONFIG_PCI_PASID -extern int pci_enable_pasid(struct pci_dev *pdev, int features); -extern void pci_disable_pasid(struct pci_dev *pdev); -extern int pci_pasid_features(struct pci_dev *pdev); -extern int pci_max_pasids(struct pci_dev *pdev); +int pci_enable_pasid(struct pci_dev *pdev, int features); +void pci_disable_pasid(struct pci_dev *pdev); +int pci_pasid_features(struct pci_dev *pdev); +int pci_max_pasids(struct pci_dev *pdev); #else /* CONFIG_PCI_PASID */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 2461033a7987..614512bed7b0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -348,7 +348,7 @@ static inline struct pci_dev *pci_physfn(struct pci_dev *dev) return dev; } -extern struct pci_dev *alloc_pci_dev(void); +struct pci_dev *alloc_pci_dev(void); #define to_pci_dev(n) container_of(n, struct pci_dev, dev) #define for_each_pci_dev(d) while ((d = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, d)) != NULL) @@ -504,10 +504,10 @@ struct pci_ops { * ACPI needs to be able to access PCI config space before we've done a * PCI bus scan and created pci_bus structures. */ -extern int raw_pci_read(unsigned int domain, unsigned int bus, - unsigned int devfn, int reg, int len, u32 *val); -extern int raw_pci_write(unsigned int domain, unsigned int bus, - unsigned int devfn, int reg, int len, u32 val); +int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn, + int reg, int len, u32 *val); +int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn, + int reg, int len, u32 val); struct pci_bus_region { resource_size_t start; @@ -658,7 +658,7 @@ struct pci_driver { /* these external functions are only available when PCI support is enabled */ #ifdef CONFIG_PCI -extern void pcie_bus_configure_settings(struct pci_bus *bus, u8 smpss); +void pcie_bus_configure_settings(struct pci_bus *bus, u8 smpss); enum pcie_bus_config_types { PCIE_BUS_TUNE_OFF, @@ -675,7 +675,7 @@ extern struct bus_type pci_bus_type; * code, or pci core code. */ extern struct list_head pci_root_buses; /* list of all known PCI buses */ /* Some device drivers need know if pci is initiated */ -extern int no_pci_devices(void); +int no_pci_devices(void); void pcibios_resource_survey_bus(struct pci_bus *bus); void pcibios_fixup_bus(struct pci_bus *); @@ -699,7 +699,7 @@ void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region, void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res, struct pci_bus_region *region); void pcibios_scan_specific_bus(int busn); -extern struct pci_bus *pci_find_bus(int domain, int busnr); +struct pci_bus *pci_find_bus(int domain, int busnr); void pci_bus_add_devices(const struct pci_bus *bus); struct pci_bus *pci_scan_bus_parented(struct device *parent, int bus, struct pci_ops *ops, void *sysdata); @@ -732,14 +732,14 @@ struct resource *pci_find_parent_resource(const struct pci_dev *dev, u8 pci_swizzle_interrupt_pin(const struct pci_dev *dev, u8 pin); int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge); u8 pci_common_swizzle(struct pci_dev *dev, u8 *pinp); -extern struct pci_dev *pci_dev_get(struct pci_dev *dev); -extern void pci_dev_put(struct pci_dev *dev); -extern void pci_remove_bus(struct pci_bus *b); -extern void pci_stop_and_remove_bus_device(struct pci_dev *dev); +struct pci_dev *pci_dev_get(struct pci_dev *dev); +void pci_dev_put(struct pci_dev *dev); +void pci_remove_bus(struct pci_bus *b); +void pci_stop_and_remove_bus_device(struct pci_dev *dev); void pci_stop_root_bus(struct pci_bus *bus); void pci_remove_root_bus(struct pci_bus *bus); void pci_setup_cardbus(struct pci_bus *bus); -extern void pci_sort_breadthfirst(void); +void pci_sort_breadthfirst(void); #define dev_is_pci(d) ((d)->bus == &pci_bus_type) #define dev_is_pf(d) ((dev_is_pci(d) ? to_pci_dev(d)->is_physfn : false)) #define dev_num_vf(d) ((dev_is_pci(d) ? pci_num_vf(to_pci_dev(d)) : 0)) @@ -1141,18 +1141,17 @@ static inline int pci_msi_enabled(void) return 0; } #else -extern int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec); -extern int pci_enable_msi_block_auto(struct pci_dev *dev, unsigned int *maxvec); -extern void pci_msi_shutdown(struct pci_dev *dev); -extern void pci_disable_msi(struct pci_dev *dev); -extern int pci_msix_table_size(struct pci_dev *dev); -extern int pci_enable_msix(struct pci_dev *dev, - struct msix_entry *entries, int nvec); -extern void pci_msix_shutdown(struct pci_dev *dev); -extern void pci_disable_msix(struct pci_dev *dev); -extern void msi_remove_pci_irq_vectors(struct pci_dev *dev); -extern void pci_restore_msi_state(struct pci_dev *dev); -extern int pci_msi_enabled(void); +int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec); +int pci_enable_msi_block_auto(struct pci_dev *dev, unsigned int *maxvec); +void pci_msi_shutdown(struct pci_dev *dev); +void pci_disable_msi(struct pci_dev *dev); +int pci_msix_table_size(struct pci_dev *dev); +int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec); +void pci_msix_shutdown(struct pci_dev *dev); +void pci_disable_msix(struct pci_dev *dev); +void msi_remove_pci_irq_vectors(struct pci_dev *dev); +void pci_restore_msi_state(struct pci_dev *dev); +int pci_msi_enabled(void); #endif #ifdef CONFIG_PCIEPORTBUS @@ -1167,8 +1166,8 @@ extern bool pcie_ports_auto; static inline int pcie_aspm_enabled(void) { return 0; } static inline bool pcie_aspm_support_enabled(void) { return false; } #else -extern int pcie_aspm_enabled(void); -extern bool pcie_aspm_support_enabled(void); +int pcie_aspm_enabled(void); +bool pcie_aspm_support_enabled(void); #endif #ifdef CONFIG_PCIEAER @@ -1186,8 +1185,8 @@ static inline void pcie_set_ecrc_checking(struct pci_dev *dev) } static inline void pcie_ecrc_get_policy(char *str) {}; #else -extern void pcie_set_ecrc_checking(struct pci_dev *dev); -extern void pcie_ecrc_get_policy(char *str); +void pcie_set_ecrc_checking(struct pci_dev *dev); +void pcie_ecrc_get_policy(char *str); #endif #define pci_enable_msi(pdev) pci_enable_msi_block(pdev, 1) @@ -1198,9 +1197,9 @@ int ht_create_irq(struct pci_dev *dev, int idx); void ht_destroy_irq(unsigned int irq); #endif /* CONFIG_HT_IRQ */ -extern void pci_cfg_access_lock(struct pci_dev *dev); -extern bool pci_cfg_access_trylock(struct pci_dev *dev); -extern void pci_cfg_access_unlock(struct pci_dev *dev); +void pci_cfg_access_lock(struct pci_dev *dev); +bool pci_cfg_access_trylock(struct pci_dev *dev); +void pci_cfg_access_unlock(struct pci_dev *dev); /* * PCI domain support. Sometimes called PCI segment (eg by ACPI), @@ -1225,7 +1224,7 @@ static inline int pci_proc_domain(struct pci_bus *bus) /* some architectures require additional setup to direct VGA traffic */ typedef int (*arch_set_vga_state_t)(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags); -extern void pci_register_set_vga_state(arch_set_vga_state_t func); +void pci_register_set_vga_state(arch_set_vga_state_t func); #else /* CONFIG_PCI is not enabled */ @@ -1627,8 +1626,8 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, int pcibios_add_device(struct pci_dev *dev); #ifdef CONFIG_PCI_MMCONFIG -extern void __init pci_mmcfg_early_init(void); -extern void __init pci_mmcfg_late_init(void); +void __init pci_mmcfg_early_init(void); +void __init pci_mmcfg_late_init(void); #else static inline void pci_mmcfg_early_init(void) { } static inline void pci_mmcfg_late_init(void) { } @@ -1639,12 +1638,12 @@ int pci_ext_cfg_avail(void); void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar); #ifdef CONFIG_PCI_IOV -extern int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); -extern void pci_disable_sriov(struct pci_dev *dev); -extern irqreturn_t pci_sriov_migration(struct pci_dev *dev); -extern int pci_num_vf(struct pci_dev *dev); -extern int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs); -extern int pci_sriov_get_totalvfs(struct pci_dev *dev); +int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); +void pci_disable_sriov(struct pci_dev *dev); +irqreturn_t pci_sriov_migration(struct pci_dev *dev); +int pci_num_vf(struct pci_dev *dev); +int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs); +int pci_sriov_get_totalvfs(struct pci_dev *dev); #else static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) { @@ -1672,8 +1671,8 @@ static inline int pci_sriov_get_totalvfs(struct pci_dev *dev) #endif #if defined(CONFIG_HOTPLUG_PCI) || defined(CONFIG_HOTPLUG_PCI_MODULE) -extern void pci_hp_create_module_link(struct pci_slot *pci_slot); -extern void pci_hp_remove_module_link(struct pci_slot *pci_slot); +void pci_hp_create_module_link(struct pci_slot *pci_slot); +void pci_hp_remove_module_link(struct pci_slot *pci_slot); #endif /** @@ -1817,13 +1816,13 @@ int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, /* PCI <-> OF binding helpers */ #ifdef CONFIG_OF struct device_node; -extern void pci_set_of_node(struct pci_dev *dev); -extern void pci_release_of_node(struct pci_dev *dev); -extern void pci_set_bus_of_node(struct pci_bus *bus); -extern void pci_release_bus_of_node(struct pci_bus *bus); +void pci_set_of_node(struct pci_dev *dev); +void pci_release_of_node(struct pci_dev *dev); +void pci_set_bus_of_node(struct pci_bus *bus); +void pci_release_bus_of_node(struct pci_bus *bus); /* Arch may override this (weak) */ -extern struct device_node * __weak pcibios_get_phb_of_node(struct pci_bus *bus); +struct device_node * __weak pcibios_get_phb_of_node(struct pci_bus *bus); static inline struct device_node * pci_device_to_OF_node(const struct pci_dev *pdev) diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 45fc162cbdc0..8db71dcd6337 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -125,12 +125,12 @@ static inline const char *hotplug_slot_name(const struct hotplug_slot *slot) return pci_slot_name(slot->pci_slot); } -extern int __pci_hp_register(struct hotplug_slot *slot, struct pci_bus *pbus, - int nr, const char *name, - struct module *owner, const char *mod_name); -extern int pci_hp_deregister(struct hotplug_slot *slot); -extern int __must_check pci_hp_change_slot_info (struct hotplug_slot *slot, - struct hotplug_slot_info *info); +int __pci_hp_register(struct hotplug_slot *slot, struct pci_bus *pbus, int nr, + const char *name, struct module *owner, + const char *mod_name); +int pci_hp_deregister(struct hotplug_slot *slot); +int __must_check pci_hp_change_slot_info(struct hotplug_slot *slot, + struct hotplug_slot_info *info); /* use a define to avoid include chaining to get THIS_MODULE & friends */ #define pci_hp_register(slot, pbus, devnr, name) \ diff --git a/include/linux/pcieport_if.h b/include/linux/pcieport_if.h index e6f91b1406d8..9572669eea97 100644 --- a/include/linux/pcieport_if.h +++ b/include/linux/pcieport_if.h @@ -62,7 +62,7 @@ struct pcie_port_service_driver { #define to_service_driver(d) \ container_of(d, struct pcie_port_service_driver, driver) -extern int pcie_port_service_register(struct pcie_port_service_driver *new); -extern void pcie_port_service_unregister(struct pcie_port_service_driver *new); +int pcie_port_service_register(struct pcie_port_service_driver *new); +void pcie_port_service_unregister(struct pcie_port_service_driver *new); #endif /* _PCIEPORT_IF_H_ */ -- cgit v1.2.3 From 5ed67f05f66c41e39880a6d61358438a25f9fee5 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Mon, 11 Mar 2013 13:12:21 +0400 Subject: posix timers: Allocate timer id per process (v2) Currently kernel generates IDs for posix timers in a global manner -- there's a kernel-wide IDR tree from which IDs are created. This makes it impossible to recreate a timer with a desired ID (in particular this is done by the CRIU checkpoint-restore project) -- since these IDs are global it may happen, that at the time we recreate a timer, the ID we want for it is already busy by some other timer. In order to address this, replace the IDR tree with a global hash table for timers and makes timer IDs unique per signal_struct (to which timers are linked anyway). With this, two timers belonging to different processes may have equal IDs and we can recreate either of them with the ID we want. Signed-off-by: Pavel Emelyanov Cc: Peter Zijlstra Cc: Michael Kerrisk Cc: Matthew Helsley Link: http://lkml.kernel.org/r/513D9FF5.9010004@parallels.com Signed-off-by: Thomas Gleixner --- include/linux/posix-timers.h | 1 + include/linux/sched.h | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 042058fdb0af..60bac697a91b 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -55,6 +55,7 @@ struct cpu_timer_list { /* POSIX.1b interval timer structure. */ struct k_itimer { struct list_head list; /* free/ allocate list */ + struct hlist_node t_hash; spinlock_t it_lock; clockid_t it_clock; /* which timer type */ timer_t it_id; /* timer id */ diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6ddbfb..d13341b55096 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -526,7 +526,8 @@ struct signal_struct { unsigned int has_child_subreaper:1; /* POSIX.1b Interval Timers */ - struct list_head posix_timers; + int posix_timer_id; + struct list_head posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; -- cgit v1.2.3 From c729de8fcea37a1c444e81857eace12494c804a9 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 15 Apr 2013 22:23:45 -0700 Subject: x86, kdump: Set crashkernel_low automatically Chao said that kdump does does work well on his system on 3.8 without extra parameter, even iommu does not work with kdump. And now have to append crashkernel_low=Y in first kernel to make kdump work. We have now modified crashkernel=X to allocate memory beyong 4G (if available) and do not allocate low range for crashkernel if the user does not specify that with crashkernel_low=Y. This causes regression if iommu is not enabled. Without iommu, swiotlb needs to be setup in first 4G and there is no low memory available to second kernel. Set crashkernel_low automatically if the user does not specify that. For system that does support IOMMU with kdump properly, user could specify crashkernel_low=0 to save that 72M low ram. -v3: add swiotlb_size() according to Konrad. -v4: add comments what 8M is for according to hpa. also update more crashkernel_low= in kernel-parameters.txt -v5: update changelog according to Vivek. -v6: Change description about swiotlb referring according to HATAYAMA. Reported-by: WANG Chao Tested-by: WANG Chao Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1366089828-19692-2-git-send-email-yinghai@kernel.org Acked-by: Vivek Goyal Signed-off-by: H. Peter Anvin --- include/linux/swiotlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 2de42f9401d2..a5ffd32642fd 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -25,6 +25,7 @@ extern int swiotlb_force; extern void swiotlb_init(int verbose); int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); extern unsigned long swiotlb_nr_tbl(void); +unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); /* -- cgit v1.2.3 From 55a20ee7804ab64ac90bcdd4e2868a42829e2784 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 15 Apr 2013 22:23:47 -0700 Subject: x86, kdump: Retore crashkernel= to allocate under 896M Vivek found old kexec-tools does not work new kernel anymore. So change back crashkernel= back to old behavoir, and add crashkernel_high= to let user decide if buffer could be above 4G, and also new kexec-tools will be needed. -v2: let crashkernel=X override crashkernel_high= update description about _high will be ignored by crashkernel=X -v3: update description about kernel-parameters.txt according to Vivek. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1366089828-19692-4-git-send-email-yinghai@kernel.org Acked-by: Vivek Goyal Signed-off-by: H. Peter Anvin --- include/linux/kexec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d2e6927bbaae..d78d28a733b1 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -200,6 +200,8 @@ extern size_t vmcoreinfo_max_size; int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base); +int parse_crashkernel_high(char *cmdline, unsigned long long system_ram, + unsigned long long *crash_size, unsigned long long *crash_base); int parse_crashkernel_low(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base); int crash_shrink_memory(unsigned long new_size); -- cgit v1.2.3 From 86239ceb33b0d8480b0f0ca0eec08e7f7a807374 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 27 Feb 2013 13:18:50 -0500 Subject: intel_idle: initial C8, C9, C10 support Allow intel_idle and cpuidle to utilize C8, C9, C10 when they are present on... "Fourth Generation Intel(R) Core(TM) Processors", which are based on Intel(R) microarchitecture code name Haswell. Signed-off-by: Len Brown --- include/linux/cpuidle.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 480c14dc1ddd..309f7f596b4c 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -17,7 +17,7 @@ #include #include -#define CPUIDLE_STATE_MAX 8 +#define CPUIDLE_STATE_MAX 10 #define CPUIDLE_NAME_LEN 16 #define CPUIDLE_DESC_LEN 32 -- cgit v1.2.3 From fcf371ee5624cc87abac205cd0dad2432d7f0346 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Thu, 18 Apr 2013 10:34:49 +0800 Subject: regulator: core: Add regulator_map_voltage_ascend() API A lot of regulator hardware has ascendant voltage list. This patch adds regulator_map_voltage_ascend() and export it. Drivers that have ascendant voltage list can use this as their map_voltage() operation, this is more efficient than default regulator_map_voltage_iterate() function. Signed-off-by: Axel Lin Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 7df93f52db08..2acdc66f8342 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -329,6 +329,8 @@ int regulator_map_voltage_linear(struct regulator_dev *rdev, int min_uV, int max_uV); int regulator_map_voltage_iterate(struct regulator_dev *rdev, int min_uV, int max_uV); +int regulator_map_voltage_ascend(struct regulator_dev *rdev, + int min_uV, int max_uV); int regulator_get_voltage_sel_regmap(struct regulator_dev *rdev); int regulator_set_voltage_sel_regmap(struct regulator_dev *rdev, unsigned sel); int regulator_is_enabled_regmap(struct regulator_dev *rdev); -- cgit v1.2.3 From 0a82a8d132b26d438eb90b3ab35a7016e7227a1d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 18 Apr 2013 09:00:26 -0700 Subject: Revert "block: add missing block_bio_complete() tracepoint" This reverts commit 3a366e614d0837d9fc23f78cdb1a1186ebc3387f. Wanlong Gao reports that it causes a kernel panic on his machine several minutes after boot. Reverting it removes the panic. Jens says: "It's not quite clear why that is yet, so I think we should just revert the commit for 3.9 final (which I'm assuming is pretty close). The wifi is crap at the LSF hotel, so sending this email instead of queueing up a revert and pull request." Reported-by: Wanlong Gao Requested-by: Jens Axboe Cc: Tejun Heo Cc: Steven Rostedt Signed-off-by: Linus Torvalds --- include/linux/blktrace_api.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 0ea61e07a91c..7c2e030e72f1 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -12,7 +12,6 @@ struct blk_trace { int trace_state; - bool rq_based; struct rchan *rchan; unsigned long __percpu *sequence; unsigned char __percpu *msg_data; -- cgit v1.2.3 From 76c24fb054b52b34af4dcde589cbb9e2b98fc74c Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 18 Apr 2013 00:15:40 +0200 Subject: nohz: New APIs to re-evaluate the tick on full dynticks CPUs Provide two new helpers in order to notify the full dynticks CPUs about some internal system changes against which they may reconsider the state of their tick. Some practical examples include: posix cpu timers, perf tick and sched clock tick. For now the notifying handler, implemented through IPIs, is a stub that will be implemented when we get the tick stop/restart infrastructure in. Signed-off-by: Frederic Weisbecker Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Oleg Nesterov Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- include/linux/tick.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index b4e3b0c9639e..c2dcfb18f65b 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -159,8 +159,12 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } #ifdef CONFIG_NO_HZ_FULL extern int tick_nohz_full_cpu(int cpu); +extern void tick_nohz_full_kick(void); +extern void tick_nohz_full_kick_all(void); #else static inline int tick_nohz_full_cpu(int cpu) { return 0; } +static inline void tick_nohz_full_kick(void) { } +static inline void tick_nohz_full_kick_all(void) { } #endif -- cgit v1.2.3 From 28d1e8cd671a53d6b4f967abbbc2a55f7bd333f6 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Thu, 18 Apr 2013 18:32:47 +0530 Subject: regulator: palma: add ramp delay support through regulator constraints Currently Palma regulator driver support the ramp delay through rail specific platform data. As regulator framework support the configuration of ramp delay through regulator constraint, using the framework method and removing the platform specific data approach. Signed-off-by: Laxman Dewangan Acked-by: Graeme Gregory Signed-off-by: Mark Brown --- include/linux/mfd/palmas.h | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 10daa8c1e73c..a58c579e8cf4 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -109,19 +109,6 @@ struct palmas_reg_init { */ int mode_sleep; - /* tstep is the timestep loaded to the TSTEP register - * - * For SMPS - * - * 0: Jump (no slope control) - * 1: 10mV/us - * 2: 5mV/us - * 3: 2.5mV/us - * - * For LDO unused - */ - int tstep; - /* voltage_sel is the bitfield loaded onto the SMPSX_VOLTAGE * register. Set this is the default voltage set in OTP needs * to be overridden. @@ -339,6 +326,7 @@ struct palmas_pmic { int smps457; int range[PALMAS_REG_SMPS10]; + unsigned int ramp_delay[PALMAS_REG_SMPS10]; }; struct palmas_resource { -- cgit v1.2.3 From 51d3a0c999e18a802a654171b5e05952b4630148 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Thu, 18 Apr 2013 18:32:48 +0530 Subject: regulator: palmas: preserve modes of rails during enable/disable The Palma device like TPS65913 have the mode mask which is also used for enable/disable the rails. The mode bits are defined as 00: OFF 01: AUTO 10: ECO 11: Forced PWM and modes are set accordingly as REGULATOR_MODE_NORMAL: AUTO REGULATOR_MODE_IDLE: ECO REGULATOR_MODE_FAST: PWM Two issue observed: 1. If client calls following sequence: regulator_enable(), regulator_set_mode(FAST), regulator_disable() and again the regulator_enable() then the mode is reset to NORMAL inplace of keeping the mode as FAST. Fixing this by storing the current mode configured by client and restoring modes when enable() is called after disable(). 2. In following sequence, the regulator get enabled: regulator_disable() regulator_set_mode(FAST), Fixing this by updating new mode in register only if it is enabled. Signed-off-by: Laxman Dewangan Acked-by: Graeme Gregory Signed-off-by: Mark Brown --- include/linux/mfd/palmas.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index a58c579e8cf4..e971a7c81b79 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -327,6 +327,7 @@ struct palmas_pmic { int range[PALMAS_REG_SMPS10]; unsigned int ramp_delay[PALMAS_REG_SMPS10]; + unsigned int current_reg_mode[PALMAS_REG_SMPS10]; }; struct palmas_resource { -- cgit v1.2.3 From 360e64d8bbe7c78784d769a60d152804f5079577 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 14 Apr 2013 20:35:48 +0200 Subject: mfd: ucb1400: Pass ucb1400-gpio data through ac97 bus Cc: Jean Delvare Cc: Guenter Roeck Cc: Grant Likely Acked-by: Linus Walleij Reviewed-by: Mark Brown Signed-off-by: Marek Vasut Signed-off-by: Samuel Ortiz --- include/linux/ucb1400.h | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ucb1400.h b/include/linux/ucb1400.h index d21b33c4c6ca..2e9ee4d1c676 100644 --- a/include/linux/ucb1400.h +++ b/include/linux/ucb1400.h @@ -83,15 +83,12 @@ #define UCB_ID 0x7e #define UCB_ID_1400 0x4304 -struct ucb1400_gpio_data { - int gpio_offset; - int (*gpio_setup)(struct device *dev, int ngpio); - int (*gpio_teardown)(struct device *dev, int ngpio); -}; - struct ucb1400_gpio { struct gpio_chip gc; struct snd_ac97 *ac97; + int gpio_offset; + int (*gpio_setup)(struct device *dev, int ngpio); + int (*gpio_teardown)(struct device *dev, int ngpio); }; struct ucb1400_ts { @@ -110,6 +107,9 @@ struct ucb1400 { struct ucb1400_pdata { int irq; + int gpio_offset; + int (*gpio_setup)(struct device *dev, int ngpio); + int (*gpio_teardown)(struct device *dev, int ngpio); }; static inline u16 ucb1400_reg_read(struct snd_ac97 *ac97, u16 reg) @@ -162,10 +162,4 @@ static inline void ucb1400_adc_disable(struct snd_ac97 *ac97) unsigned int ucb1400_adc_read(struct snd_ac97 *ac97, u16 adc_channel, int adcsync); -#ifdef CONFIG_GPIO_UCB1400 -void __init ucb1400_gpio_set_data(struct ucb1400_gpio_data *data); -#else -static inline void ucb1400_gpio_set_data(struct ucb1400_gpio_data *data) {} -#endif - #endif -- cgit v1.2.3 From 95e50f6a2fe9ece6503e355400c171e0f5de61be Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Tue, 9 Apr 2013 22:51:25 +0300 Subject: mfd: retu: Add Tahvo support Tahvo is a multi-function device on Nokia 770, implementing USB transceiver and charge/battery control. It's so close to Retu that a single driver can support both. Signed-off-by: Aaro Koskinen Signed-off-by: Samuel Ortiz --- include/linux/mfd/retu.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/retu.h b/include/linux/mfd/retu.h index 1e2715d5b836..65471c4a3926 100644 --- a/include/linux/mfd/retu.h +++ b/include/linux/mfd/retu.h @@ -1,5 +1,5 @@ /* - * Retu MFD driver interface + * Retu/Tahvo MFD driver interface * * This file is subject to the terms and conditions of the GNU General * Public License. See the file "COPYING" in the main directory of this @@ -19,4 +19,10 @@ int retu_write(struct retu_dev *, u8, u16); #define RETU_REG_CC1 0x0d /* Common control register 1 */ #define RETU_REG_STATUS 0x16 /* Status register */ +/* Interrupt sources */ +#define TAHVO_INT_VBUS 0 /* VBUS state */ + +/* Interrupt status */ +#define TAHVO_STAT_VBUS (1 << TAHVO_INT_VBUS) + #endif /* __LINUX_MFD_RETU_H */ -- cgit v1.2.3 From 712317ad97f41e738e1a19aa0a6392a78a84094e Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Thu, 18 Apr 2013 23:09:52 -0700 Subject: cgroup: fix broken file xattrs We should store file xattrs in struct cfent instead of struct cftype, because cftype is a type while cfent is object instance of cftype. For example each cgroup has a tasks file, and each tasks file is associated with a uniq cfent, but all those files share the same struct cftype. Alexey Kodanev reported a crash, which can be reproduced: # mount -t cgroup -o xattr /sys/fs/cgroup # mkdir /sys/fs/cgroup/test # setfattr -n trusted.value -v test_value /sys/fs/cgroup/tasks # rmdir /sys/fs/cgroup/test # umount /sys/fs/cgroup oops! In this case, simple_xattrs_free() will free the same struct simple_xattrs twice. tj: Dropped unused local variable @cft from cgroup_diput(). Cc: # 3.8.x Reported-by: Alexey Kodanev Signed-off-by: Li Zefan Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index cda7eb2239e1..c371888298d5 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -422,9 +422,6 @@ struct cftype { /* CFTYPE_* flags */ unsigned int flags; - /* file xattrs */ - struct simple_xattrs xattrs; - int (*open)(struct inode *inode, struct file *file); ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, struct file *file, -- cgit v1.2.3 From 41fcb9f230bf773656d1768b73000ef720bf00c3 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 17 Apr 2013 15:23:11 -0400 Subject: mutex: Move mutex spinning code from sched/core.c back to mutex.c As mentioned by Ingo, the SCHED_FEAT_OWNER_SPIN scheduler feature bit was really just an early hack to make with/without mutex-spinning testable. So it is no longer necessary. This patch removes the SCHED_FEAT_OWNER_SPIN feature bit and move the mutex spinning code from kernel/sched/core.c back to kernel/mutex.c which is where they should belong. Signed-off-by: Waiman Long Cc: Linus Torvalds Cc: Andrew Morton Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Chandramouleeswaran Aswin Cc: Davidlohr Bueso Cc: Norton Scott J Cc: Rik van Riel Cc: Paul E. McKenney Cc: David Howells Cc: Dave Jones Cc: Clark Williams Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1366226594-5506-2-git-send-email-Waiman.Long@hp.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d35d2b6ddbfb..aefe45d79f53 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -320,7 +320,6 @@ extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); -extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner); struct nsproxy; struct user_namespace; -- cgit v1.2.3 From 2bd2c92cf07cc4a373bf316c75b78ac465fefd35 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 17 Apr 2013 15:23:13 -0400 Subject: mutex: Queue mutex spinners with MCS lock to reduce cacheline contention The current mutex spinning code (with MUTEX_SPIN_ON_OWNER option turned on) allow multiple tasks to spin on a single mutex concurrently. A potential problem with the current approach is that when the mutex becomes available, all the spinning tasks will try to acquire the mutex more or less simultaneously. As a result, there will be a lot of cacheline bouncing especially on systems with a large number of CPUs. This patch tries to reduce this kind of contention by putting the mutex spinners into a queue so that only the first one in the queue will try to acquire the mutex. This will reduce contention and allow all the tasks to move forward faster. The queuing of mutex spinners is done using an MCS lock based implementation which will further reduce contention on the mutex cacheline than a similar ticket spinlock based implementation. This patch will add a new field into the mutex data structure for holding the MCS lock. This expands the mutex size by 8 bytes for 64-bit system and 4 bytes for 32-bit system. This overhead will be avoid if the MUTEX_SPIN_ON_OWNER option is turned off. The following table shows the jobs per minute (JPM) scalability data on an 8-node 80-core Westmere box with a 3.7.10 kernel. The numactl command is used to restrict the running of the fserver workloads to 1/2/4/8 nodes with hyperthreading off. +-----------------+-----------+-----------+-------------+----------+ | Configuration | Mean JPM | Mean JPM | Mean JPM | % Change | | | w/o patch | patch 1 | patches 1&2 | 1->1&2 | +-----------------+------------------------------------------------+ | | User Range 1100 - 2000 | +-----------------+------------------------------------------------+ | 8 nodes, HT off | 227972 | 227237 | 305043 | +34.2% | | 4 nodes, HT off | 393503 | 381558 | 394650 | +3.4% | | 2 nodes, HT off | 334957 | 325240 | 338853 | +4.2% | | 1 node , HT off | 198141 | 197972 | 198075 | +0.1% | +-----------------+------------------------------------------------+ | | User Range 200 - 1000 | +-----------------+------------------------------------------------+ | 8 nodes, HT off | 282325 | 312870 | 332185 | +6.2% | | 4 nodes, HT off | 390698 | 378279 | 393419 | +4.0% | | 2 nodes, HT off | 336986 | 326543 | 340260 | +4.2% | | 1 node , HT off | 197588 | 197622 | 197582 | 0.0% | +-----------------+-----------+-----------+-------------+----------+ At low user range 10-100, the JPM differences were within +/-1%. So they are not that interesting. The fserver workload uses mutex spinning extensively. With just the mutex change in the first patch, there is no noticeable change in performance. Rather, there is a slight drop in performance. This mutex spinning patch more than recovers the lost performance and show a significant increase of +30% at high user load with the full 8 nodes. Similar improvements were also seen in a 3.8 kernel. The table below shows the %time spent by different kernel functions as reported by perf when running the fserver workload at 1500 users with all 8 nodes. +-----------------------+-----------+---------+-------------+ | Function | % time | % time | % time | | | w/o patch | patch 1 | patches 1&2 | +-----------------------+-----------+---------+-------------+ | __read_lock_failed | 34.96% | 34.91% | 29.14% | | __write_lock_failed | 10.14% | 10.68% | 7.51% | | mutex_spin_on_owner | 3.62% | 3.42% | 2.33% | | mspin_lock | N/A | N/A | 9.90% | | __mutex_lock_slowpath | 1.46% | 0.81% | 0.14% | | _raw_spin_lock | 2.25% | 2.50% | 1.10% | +-----------------------+-----------+---------+-------------+ The fserver workload for an 8-node system is dominated by the contention in the read/write lock. Mutex contention also plays a role. With the first patch only, mutex contention is down (as shown by the __mutex_lock_slowpath figure) which help a little bit. We saw only a few percents improvement with that. By applying patch 2 as well, the single mutex_spin_on_owner figure is now split out into an additional mspin_lock figure. The time increases from 3.42% to 11.23%. It shows a great reduction in contention among the spinners leading to a 30% improvement. The time ratio 9.9/2.33=4.3 indicates that there are on average 4+ spinners waiting in the spin_lock loop for each spinner in the mutex_spin_on_owner loop. Contention in other locking functions also go down by quite a lot. The table below shows the performance change of both patches 1 & 2 over patch 1 alone in other AIM7 workloads (at 8 nodes, hyperthreading off). +--------------+---------------+----------------+-----------------+ | Workload | mean % change | mean % change | mean % change | | | 10-100 users | 200-1000 users | 1100-2000 users | +--------------+---------------+----------------+-----------------+ | alltests | 0.0% | -0.8% | +0.6% | | five_sec | -0.3% | +0.8% | +0.8% | | high_systime | +0.4% | +2.4% | +2.1% | | new_fserver | +0.1% | +14.1% | +34.2% | | shared | -0.5% | -0.3% | -0.4% | | short | -1.7% | -9.8% | -8.3% | +--------------+---------------+----------------+-----------------+ The short workload is the only one that shows a decline in performance probably due to the spinner locking and queuing overhead. Signed-off-by: Waiman Long Reviewed-by: Davidlohr Bueso Acked-by: Rik van Riel Cc: Linus Torvalds Cc: Andrew Morton Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Chandramouleeswaran Aswin Cc: Norton Scott J Cc: Paul E. McKenney Cc: David Howells Cc: Dave Jones Cc: Clark Williams Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1366226594-5506-4-git-send-email-Waiman.Long@hp.com Signed-off-by: Ingo Molnar --- include/linux/mutex.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 9121595a8ebf..433da8a1a426 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -53,6 +53,9 @@ struct mutex { #if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP) struct task_struct *owner; #endif +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER + void *spin_mlock; /* Spinner MCS lock */ +#endif #ifdef CONFIG_DEBUG_MUTEXES const char *name; void *magic; -- cgit v1.2.3 From 94c1acf2c85b03a59a42d931a94a13a76c123a62 Mon Sep 17 00:00:00 2001 From: Aravind Gopalakrishnan Date: Wed, 17 Apr 2013 14:57:13 -0500 Subject: amd64_edac: Add Family 16h support Add code to handle DRAM ECC errors decoding for Fam16h. Tested on Fam16h with ECC turned on using the mce_amd_inj facility and works fine. Signed-off-by: Aravind Gopalakrishnan [ Boris: cleanups and clarifications ] Signed-off-by: Borislav Petkov --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index f11c1c2609d5..9b3b85822302 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -524,6 +524,8 @@ #define PCI_DEVICE_ID_AMD_15H_NB_F3 0x1603 #define PCI_DEVICE_ID_AMD_15H_NB_F4 0x1604 #define PCI_DEVICE_ID_AMD_15H_NB_F5 0x1605 +#define PCI_DEVICE_ID_AMD_16H_NB_F3 0x1533 +#define PCI_DEVICE_ID_AMD_16H_NB_F4 0x1534 #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 -- cgit v1.2.3 From cc014f3e29e15140e35e14fa194034baee92df2a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 4 Mar 2013 18:28:21 +0100 Subject: mmc: sdhci-s3c: remove platform dependencies plat/regs-sdhci.h is not used anywhere but in the sdhci-s3c driver, so it can become a local file there and all other inclusions removed. plat/sdhci.h is used only to define the platform devices, and with the exception of the platform_data structure not needed by the driver, so we can split out the platform_data definition instead and leave the rest to platform code. Signed-off-by: Arnd Bergmann Acked-by: Chris Ball --- include/linux/platform_data/mmc-sdhci-s3c.h | 56 +++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 include/linux/platform_data/mmc-sdhci-s3c.h (limited to 'include/linux') diff --git a/include/linux/platform_data/mmc-sdhci-s3c.h b/include/linux/platform_data/mmc-sdhci-s3c.h new file mode 100644 index 000000000000..249f02387a35 --- /dev/null +++ b/include/linux/platform_data/mmc-sdhci-s3c.h @@ -0,0 +1,56 @@ +#ifndef __PLATFORM_DATA_SDHCI_S3C_H +#define __PLATFORM_DATA_SDHCI_S3C_H + +struct platform_device; + +enum cd_types { + S3C_SDHCI_CD_INTERNAL, /* use mmc internal CD line */ + S3C_SDHCI_CD_EXTERNAL, /* use external callback */ + S3C_SDHCI_CD_GPIO, /* use external gpio pin for CD line */ + S3C_SDHCI_CD_NONE, /* no CD line, use polling to detect card */ + S3C_SDHCI_CD_PERMANENT, /* no CD line, card permanently wired to host */ +}; + +/** + * struct s3c_sdhci_platdata() - Platform device data for Samsung SDHCI + * @max_width: The maximum number of data bits supported. + * @host_caps: Standard MMC host capabilities bit field. + * @host_caps2: The second standard MMC host capabilities bit field. + * @cd_type: Type of Card Detection method (see cd_types enum above) + * @ext_cd_init: Initialize external card detect subsystem. Called on + * sdhci-s3c driver probe when cd_type == S3C_SDHCI_CD_EXTERNAL. + * notify_func argument is a callback to the sdhci-s3c driver + * that triggers the card detection event. Callback arguments: + * dev is pointer to platform device of the host controller, + * state is new state of the card (0 - removed, 1 - inserted). + * @ext_cd_cleanup: Cleanup external card detect subsystem. Called on + * sdhci-s3c driver remove when cd_type == S3C_SDHCI_CD_EXTERNAL. + * notify_func argument is the same callback as for ext_cd_init. + * @ext_cd_gpio: gpio pin used for external CD line, valid only if + * cd_type == S3C_SDHCI_CD_GPIO + * @ext_cd_gpio_invert: invert values for external CD gpio line + * @cfg_gpio: Configure the GPIO for a specific card bit-width + * + * Initialisation data specific to either the machine or the platform + * for the device driver to use or call-back when configuring gpio or + * card speed information. +*/ +struct s3c_sdhci_platdata { + unsigned int max_width; + unsigned int host_caps; + unsigned int host_caps2; + unsigned int pm_caps; + enum cd_types cd_type; + + int ext_cd_gpio; + bool ext_cd_gpio_invert; + int (*ext_cd_init)(void (*notify_func)(struct platform_device *, + int state)); + int (*ext_cd_cleanup)(void (*notify_func)(struct platform_device *, + int state)); + + void (*cfg_gpio)(struct platform_device *dev, int width); +}; + + +#endif /* __PLATFORM_DATA_SDHCI_S3C_H */ -- cgit v1.2.3 From d1e43fa5f8bb25f83a86a29f11fcfb57ed4d7566 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 26 Mar 2013 23:47:24 +0100 Subject: nohz: Ensure full dynticks CPUs are RCU nocbs We need full dynticks CPU to also be RCU nocb so that we don't have to keep the tick to handle RCU callbacks. Make sure the range passed to nohz_full= boot parameter is a subset of rcu_nocbs= The CPUs that fail to meet this requirement will be excluded from the nohz_full range. This is checked early in boot time, before any CPU has the opportunity to stop its tick. Suggested-by: Steven Rostedt Reviewed-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- include/linux/rcupdate.h | 7 +++++++ include/linux/tick.h | 2 ++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index b758ce17b309..8e0948c872fc 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -999,4 +999,11 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define kfree_rcu(ptr, rcu_head) \ __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head)) +#ifdef CONFIG_RCU_NOCB_CPU +extern bool rcu_is_nocb_cpu(int cpu); +#else +static inline bool rcu_is_nocb_cpu(int cpu) { return false; } +#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ + + #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/tick.h b/include/linux/tick.h index b4e3b0c9639e..0b6873cbf512 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -158,8 +158,10 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } # endif /* !CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL +extern void tick_nohz_init(void); extern int tick_nohz_full_cpu(int cpu); #else +static inline void tick_nohz_init(void) { } static inline int tick_nohz_full_cpu(int cpu) { return 0; } #endif -- cgit v1.2.3 From f07512e615dd8ebd0866efc38b39ccd41f1495d8 Mon Sep 17 00:00:00 2001 From: Laurent Meunier Date: Thu, 18 Apr 2013 10:48:07 +0200 Subject: pinctrl/pinconfig: add debug interface This update adds a debugfs interface to modify a pin configuration for a given state in the pinctrl map. This allows to modify the configuration for a non-active state, typically sleep state. This configuration is not applied right away, but only when the state will be entered. This solution is mandated for us by HW validation: in order to test and verify several pin configurations during sleep without recompiling the software. Change log in this patch set; Take into account latest feedback from Stephen Warren: - stale comments update - improved code efficiency and readibility - limit size of global variable pinconf_dbg_conf - remove req_type as it can easily be added later when add/delete requests support is implemented Signed-off-by: Laurent Meunier Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h index e7a720104a47..1ad4f31ef6b8 100644 --- a/include/linux/pinctrl/pinconf.h +++ b/include/linux/pinctrl/pinconf.h @@ -14,6 +14,8 @@ #ifdef CONFIG_PINCONF +#include + struct pinctrl_dev; struct seq_file; @@ -28,6 +30,7 @@ struct seq_file; * @pin_config_set: configure an individual pin * @pin_config_group_get: get configurations for an entire pin group * @pin_config_group_set: configure all pins in a group + * @pin_config_group_dbg_set: optional debugfs to modify a pin configuration * @pin_config_dbg_show: optional debugfs display hook that will provide * per-device info for a certain pin in debugfs * @pin_config_group_dbg_show: optional debugfs display hook that will provide @@ -51,6 +54,9 @@ struct pinconf_ops { int (*pin_config_group_set) (struct pinctrl_dev *pctldev, unsigned selector, unsigned long config); + int (*pin_config_dbg_parse_modify) (struct pinctrl_dev *pctldev, + const char *arg, + unsigned long *config); void (*pin_config_dbg_show) (struct pinctrl_dev *pctldev, struct seq_file *s, unsigned offset); -- cgit v1.2.3 From 555347f6c080d2f25265f981c963605b4dd3610d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 19 Apr 2013 16:17:38 +0200 Subject: posix_timers: New API to prevent from stopping the tick when timers are running Bring a new helper that the full dynticks infrastructure can call in order to know if it can safely stop the tick from the posix cpu timers subsystem point of view. Signed-off-by: Frederic Weisbecker Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Oleg Nesterov Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- include/linux/posix-timers.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 042058fdb0af..3698d9d08978 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -122,6 +122,8 @@ void run_posix_cpu_timers(struct task_struct *task); void posix_cpu_timers_exit(struct task_struct *task); void posix_cpu_timers_exit_group(struct task_struct *task); +bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk); + void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, cputime_t *newval, cputime_t *oldval); -- cgit v1.2.3 From 4c4b8c105a7bbd4a8d41ab4458f01174fdf3fcbb Mon Sep 17 00:00:00 2001 From: Wei WANG Date: Thu, 11 Apr 2013 10:43:40 +0800 Subject: mfd: rtsx: Support RTS5249 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit RTS5249 supports SD UHS-II interface. In order to support SD UHS-II，the definitions of some internal registers of RTS5249 have to be modified and are different from its predecessors. So we need this patch to ensure RTS5249 can work, even SD/MMC stack doesn't support UHS-II interface. Signed-off-by: Wei WANG Signed-off-by: Samuel Ortiz --- include/linux/mfd/rtsx_pci.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index 26ea7f1b7caf..86bc635f8385 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -500,6 +500,8 @@ #define BPP_POWER_15_PERCENT_ON 0x08 #define BPP_POWER_ON 0x00 #define BPP_POWER_MASK 0x0F +#define SD_VCC_PARTIAL_POWER_ON 0x02 +#define SD_VCC_POWER_ON 0x00 /* PWR_GATE_CTRL */ #define PWR_GATE_EN 0x01 @@ -689,6 +691,40 @@ #define IMAGE_FLAG_ADDR0 0xCE80 #define IMAGE_FLAG_ADDR1 0xCE81 +/* Phy register */ +#define PHY_PCR 0x00 +#define PHY_RCR0 0x01 +#define PHY_RCR1 0x02 +#define PHY_RCR2 0x03 +#define PHY_RTCR 0x04 +#define PHY_RDR 0x05 +#define PHY_TCR0 0x06 +#define PHY_TCR1 0x07 +#define PHY_TUNE 0x08 +#define PHY_IMR 0x09 +#define PHY_BPCR 0x0A +#define PHY_BIST 0x0B +#define PHY_RAW_L 0x0C +#define PHY_RAW_H 0x0D +#define PHY_RAW_DATA 0x0E +#define PHY_HOST_CLK_CTRL 0x0F +#define PHY_DMR 0x10 +#define PHY_BACR 0x11 +#define PHY_IER 0x12 +#define PHY_BCSR 0x13 +#define PHY_BPR 0x14 +#define PHY_BPNR2 0x15 +#define PHY_BPNR 0x16 +#define PHY_BRNR2 0x17 +#define PHY_BENR 0x18 +#define PHY_REG_REV 0x19 +#define PHY_FLD0 0x1A +#define PHY_FLD1 0x1B +#define PHY_FLD2 0x1C +#define PHY_FLD3 0x1D +#define PHY_FLD4 0x1E +#define PHY_DUM_REG 0x1F + #define rtsx_pci_init_cmd(pcr) ((pcr)->ci = 0) struct rtsx_pcr; -- cgit v1.2.3 From 9b8e1a5e4670b3b24c0e35c0884b4185f17fceab Mon Sep 17 00:00:00 2001 From: Andrey Smirnov Date: Thu, 18 Apr 2013 09:58:30 -0700 Subject: mfd: si476x: Add header files and Kbuild plumbing This patch adds all necessary header files and Kbuild plumbing for the core driver for Silicon Laboratories Si476x series of AM/FM tuner chips. The driver as a whole is implemented as an MFD device and this patch adds a core portion of it that provides all the necessary functionality to the two other drivers that represent radio and audio codec subsystems of the chip. Acked-by: Hans Verkuil Acked-by: Sam Ravnborg Signed-off-by: Andrey Smirnov Signed-off-by: Samuel Ortiz --- include/linux/mfd/si476x-core.h | 533 ++++++++++++++++++++++++++++++++++++ include/linux/mfd/si476x-platform.h | 267 ++++++++++++++++++ include/linux/mfd/si476x-reports.h | 163 +++++++++++ 3 files changed, 963 insertions(+) create mode 100644 include/linux/mfd/si476x-core.h create mode 100644 include/linux/mfd/si476x-platform.h create mode 100644 include/linux/mfd/si476x-reports.h (limited to 'include/linux') diff --git a/include/linux/mfd/si476x-core.h b/include/linux/mfd/si476x-core.h new file mode 100644 index 000000000000..ede3022c03c4 --- /dev/null +++ b/include/linux/mfd/si476x-core.h @@ -0,0 +1,533 @@ +/* + * include/media/si476x-core.h -- Common definitions for si476x core + * device + * + * Copyright (C) 2012 Innovative Converged Devices(ICD) + * Copyright (C) 2013 Andrey Smirnov + * + * Author: Andrey Smirnov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + */ + +#ifndef SI476X_CORE_H +#define SI476X_CORE_H + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +/* Command Timeouts */ +#define SI476X_DEFAULT_TIMEOUT 100000 +#define SI476X_TIMEOUT_TUNE 700000 +#define SI476X_TIMEOUT_POWER_UP 330000 +#define SI476X_STATUS_POLL_US 0 + +/* -------------------- si476x-i2c.c ----------------------- */ + +enum si476x_freq_supported_chips { + SI476X_CHIP_SI4761 = 1, + SI476X_CHIP_SI4764, + SI476X_CHIP_SI4768, +}; + +enum si476x_part_revisions { + SI476X_REVISION_A10 = 0, + SI476X_REVISION_A20 = 1, + SI476X_REVISION_A30 = 2, +}; + +enum si476x_mfd_cells { + SI476X_RADIO_CELL = 0, + SI476X_CODEC_CELL, + SI476X_MFD_CELLS, +}; + +/** + * enum si476x_power_state - possible power state of the si476x + * device. + * + * @SI476X_POWER_DOWN: In this state all regulators are turned off + * and the reset line is pulled low. The device is completely + * inactive. + * @SI476X_POWER_UP_FULL: In this state all the power regualtors are + * turned on, reset line pulled high, IRQ line is enabled(polling is + * active for polling use scenario) and device is turned on with + * POWER_UP command. The device is ready to be used. + * @SI476X_POWER_INCONSISTENT: This state indicates that previous + * power down was inconsistent, meaning some of the regulators were + * not turned down and thus use of the device, without power-cycling + * is impossible. + */ +enum si476x_power_state { + SI476X_POWER_DOWN = 0, + SI476X_POWER_UP_FULL = 1, + SI476X_POWER_INCONSISTENT = 2, +}; + +/** + * struct si476x_core - internal data structure representing the + * underlying "core" device which all the MFD cell-devices use. + * + * @client: Actual I2C client used to transfer commands to the chip. + * @chip_id: Last digit of the chip model(E.g. "1" for SI4761) + * @cells: MFD cell devices created by this driver. + * @cmd_lock: Mutex used to serialize all the requests to the core + * device. This filed should not be used directly. Instead + * si476x_core_lock()/si476x_core_unlock() should be used to get + * exclusive access to the "core" device. + * @users: Active users counter(Used by the radio cell) + * @rds_read_queue: Wait queue used to wait for RDS data. + * @rds_fifo: FIFO in which all the RDS data received from the chip is + * placed. + * @rds_fifo_drainer: Worker that drains on-chip RDS FIFO. + * @rds_drainer_is_working: Flag used for launching only one instance + * of the @rds_fifo_drainer. + * @rds_drainer_status_lock: Lock used to guard access to the + * @rds_drainer_is_working variable. + * @command: Wait queue for wainting on the command comapletion. + * @cts: Clear To Send flag set upon receiving first status with CTS + * set. + * @tuning: Wait queue used for wainting for tune/seek comand + * completion. + * @stc: Similar to @cts, but for the STC bit of the status value. + * @power_up_parameters: Parameters used as argument for POWER_UP + * command when the device is started. + * @state: Current power state of the device. + * @supplues: Structure containing handles to all power supplies used + * by the device (NULL ones are ignored). + * @gpio_reset: GPIO pin connectet to the RSTB pin of the chip. + * @pinmux: Chip's configurable pins configuration. + * @diversity_mode: Chips role when functioning in diversity mode. + * @status_monitor: Polling worker used in polling use case scenarion + * (when IRQ is not avalible). + * @revision: Chip's running firmware revision number(Used for correct + * command set support). + */ + +struct si476x_core { + struct i2c_client *client; + struct regmap *regmap; + int chip_id; + struct mfd_cell cells[SI476X_MFD_CELLS]; + + struct mutex cmd_lock; /* for serializing fm radio operations */ + atomic_t users; + + wait_queue_head_t rds_read_queue; + struct kfifo rds_fifo; + struct work_struct rds_fifo_drainer; + bool rds_drainer_is_working; + struct mutex rds_drainer_status_lock; + + wait_queue_head_t command; + atomic_t cts; + + wait_queue_head_t tuning; + atomic_t stc; + + struct si476x_power_up_args power_up_parameters; + + enum si476x_power_state power_state; + + struct regulator_bulk_data supplies[4]; + + int gpio_reset; + + struct si476x_pinmux pinmux; + enum si476x_phase_diversity_mode diversity_mode; + + atomic_t is_alive; + + struct delayed_work status_monitor; +#define SI476X_WORK_TO_CORE(w) container_of(to_delayed_work(w), \ + struct si476x_core, \ + status_monitor) + + int revision; + + int rds_fifo_depth; +}; + +static inline struct si476x_core *i2c_mfd_cell_to_core(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev->parent); + return i2c_get_clientdata(client); +} + + +/** + * si476x_core_lock() - lock the core device to get an exclusive access + * to it. + */ +static inline void si476x_core_lock(struct si476x_core *core) +{ + mutex_lock(&core->cmd_lock); +} + +/** + * si476x_core_unlock() - unlock the core device to relinquish an + * exclusive access to it. + */ +static inline void si476x_core_unlock(struct si476x_core *core) +{ + mutex_unlock(&core->cmd_lock); +} + +/* *_TUNE_FREQ family of commands accept frequency in multiples of + 10kHz */ +static inline u16 hz_to_si476x(struct si476x_core *core, int freq) +{ + u16 result; + + switch (core->power_up_parameters.func) { + default: + case SI476X_FUNC_FM_RECEIVER: + result = freq / 10000; + break; + case SI476X_FUNC_AM_RECEIVER: + result = freq / 1000; + break; + } + + return result; +} + +static inline int si476x_to_hz(struct si476x_core *core, u16 freq) +{ + int result; + + switch (core->power_up_parameters.func) { + default: + case SI476X_FUNC_FM_RECEIVER: + result = freq * 10000; + break; + case SI476X_FUNC_AM_RECEIVER: + result = freq * 1000; + break; + } + + return result; +} + +/* Since the V4L2_TUNER_CAP_LOW flag is supplied, V4L2 subsystem + * mesures frequency in 62.5 Hz units */ + +static inline int hz_to_v4l2(int freq) +{ + return (freq * 10) / 625; +} + +static inline int v4l2_to_hz(int freq) +{ + return (freq * 625) / 10; +} + +static inline u16 v4l2_to_si476x(struct si476x_core *core, int freq) +{ + return hz_to_si476x(core, v4l2_to_hz(freq)); +} + +static inline int si476x_to_v4l2(struct si476x_core *core, u16 freq) +{ + return hz_to_v4l2(si476x_to_hz(core, freq)); +} + + + +/** + * struct si476x_func_info - structure containing result of the + * FUNC_INFO command. + * + * @firmware.major: Firmware major number. + * @firmware.minor[...]: Firmware minor numbers. + * @patch_id: + * @func: Mode tuner is working in. + */ +struct si476x_func_info { + struct { + u8 major, minor[2]; + } firmware; + u16 patch_id; + enum si476x_func func; +}; + +/** + * struct si476x_power_down_args - structure used to pass parameters + * to POWER_DOWN command + * + * @xosc: true - Power down, but leav oscillator running. + * false - Full power down. + */ +struct si476x_power_down_args { + bool xosc; +}; + +/** + * enum si476x_tunemode - enum representing possible tune modes for + * the chip. + * @SI476X_TM_VALIDATED_NORMAL_TUNE: Unconditionally stay on the new + * channel after tune, tune status is valid. + * @SI476X_TM_INVALIDATED_FAST_TUNE: Unconditionally stay in the new + * channel after tune, tune status invalid. + * @SI476X_TM_VALIDATED_AF_TUNE: Jump back to previous channel if + * metric thresholds are not met. + * @SI476X_TM_VALIDATED_AF_CHECK: Unconditionally jump back to the + * previous channel. + */ +enum si476x_tunemode { + SI476X_TM_VALIDATED_NORMAL_TUNE = 0, + SI476X_TM_INVALIDATED_FAST_TUNE = 1, + SI476X_TM_VALIDATED_AF_TUNE = 2, + SI476X_TM_VALIDATED_AF_CHECK = 3, +}; + +/** + * enum si476x_smoothmetrics - enum containing the possible setting fo + * audio transitioning of the chip + * @SI476X_SM_INITIALIZE_AUDIO: Initialize audio state to match this + * new channel + * @SI476X_SM_TRANSITION_AUDIO: Transition audio state from previous + * channel values to the new values + */ +enum si476x_smoothmetrics { + SI476X_SM_INITIALIZE_AUDIO = 0, + SI476X_SM_TRANSITION_AUDIO = 1, +}; + +/** + * struct si476x_rds_status_report - the structure representing the + * response to 'FM_RD_STATUS' command + * @rdstpptyint: Traffic program flag(TP) and/or program type(PTY) + * code has changed. + * @rdspiint: Program indentifiaction(PI) code has changed. + * @rdssyncint: RDS synchronization has changed. + * @rdsfifoint: RDS was received and the RDS FIFO has at least + * 'FM_RDS_INTERRUPT_FIFO_COUNT' elements in it. + * @tpptyvalid: TP flag and PTY code are valid falg. + * @pivalid: PI code is valid flag. + * @rdssync: RDS is currently synchronized. + * @rdsfifolost: On or more RDS groups have been lost/discarded flag. + * @tp: Current channel's TP flag. + * @pty: Current channel's PTY code. + * @pi: Current channel's PI code. + * @rdsfifoused: Number of blocks remaining in the RDS FIFO (0 if + * empty). + */ +struct si476x_rds_status_report { + bool rdstpptyint, rdspiint, rdssyncint, rdsfifoint; + bool tpptyvalid, pivalid, rdssync, rdsfifolost; + bool tp; + + u8 pty; + u16 pi; + + u8 rdsfifoused; + u8 ble[4]; + + struct v4l2_rds_data rds[4]; +}; + +struct si476x_rsq_status_args { + bool primary; + bool rsqack; + bool attune; + bool cancel; + bool stcack; +}; + +enum si476x_injside { + SI476X_INJSIDE_AUTO = 0, + SI476X_INJSIDE_LOW = 1, + SI476X_INJSIDE_HIGH = 2, +}; + +struct si476x_tune_freq_args { + bool zifsr; + bool hd; + enum si476x_injside injside; + int freq; + enum si476x_tunemode tunemode; + enum si476x_smoothmetrics smoothmetrics; + int antcap; +}; + +int si476x_core_stop(struct si476x_core *, bool); +int si476x_core_start(struct si476x_core *, bool); +int si476x_core_set_power_state(struct si476x_core *, enum si476x_power_state); +bool si476x_core_has_am(struct si476x_core *); +bool si476x_core_has_diversity(struct si476x_core *); +bool si476x_core_is_a_secondary_tuner(struct si476x_core *); +bool si476x_core_is_a_primary_tuner(struct si476x_core *); +bool si476x_core_is_in_am_receiver_mode(struct si476x_core *core); +bool si476x_core_is_powered_up(struct si476x_core *core); + +enum si476x_i2c_type { + SI476X_I2C_SEND, + SI476X_I2C_RECV +}; + +int si476x_core_i2c_xfer(struct si476x_core *, + enum si476x_i2c_type, + char *, int); + + +/* -------------------- si476x-cmd.c ----------------------- */ + +int si476x_core_cmd_func_info(struct si476x_core *, struct si476x_func_info *); +int si476x_core_cmd_set_property(struct si476x_core *, u16, u16); +int si476x_core_cmd_get_property(struct si476x_core *, u16); +int si476x_core_cmd_dig_audio_pin_cfg(struct si476x_core *, + enum si476x_dclk_config, + enum si476x_dfs_config, + enum si476x_dout_config, + enum si476x_xout_config); +int si476x_core_cmd_zif_pin_cfg(struct si476x_core *, + enum si476x_iqclk_config, + enum si476x_iqfs_config, + enum si476x_iout_config, + enum si476x_qout_config); +int si476x_core_cmd_ic_link_gpo_ctl_pin_cfg(struct si476x_core *, + enum si476x_icin_config, + enum si476x_icip_config, + enum si476x_icon_config, + enum si476x_icop_config); +int si476x_core_cmd_ana_audio_pin_cfg(struct si476x_core *, + enum si476x_lrout_config); +int si476x_core_cmd_intb_pin_cfg(struct si476x_core *, enum si476x_intb_config, + enum si476x_a1_config); +int si476x_core_cmd_fm_seek_start(struct si476x_core *, bool, bool); +int si476x_core_cmd_am_seek_start(struct si476x_core *, bool, bool); +int si476x_core_cmd_fm_rds_status(struct si476x_core *, bool, bool, bool, + struct si476x_rds_status_report *); +int si476x_core_cmd_fm_rds_blockcount(struct si476x_core *, bool, + struct si476x_rds_blockcount_report *); +int si476x_core_cmd_fm_tune_freq(struct si476x_core *, + struct si476x_tune_freq_args *); +int si476x_core_cmd_am_tune_freq(struct si476x_core *, + struct si476x_tune_freq_args *); +int si476x_core_cmd_am_rsq_status(struct si476x_core *, + struct si476x_rsq_status_args *, + struct si476x_rsq_status_report *); +int si476x_core_cmd_fm_rsq_status(struct si476x_core *, + struct si476x_rsq_status_args *, + struct si476x_rsq_status_report *); +int si476x_core_cmd_power_up(struct si476x_core *, + struct si476x_power_up_args *); +int si476x_core_cmd_power_down(struct si476x_core *, + struct si476x_power_down_args *); +int si476x_core_cmd_fm_phase_div_status(struct si476x_core *); +int si476x_core_cmd_fm_phase_diversity(struct si476x_core *, + enum si476x_phase_diversity_mode); + +int si476x_core_cmd_fm_acf_status(struct si476x_core *, + struct si476x_acf_status_report *); +int si476x_core_cmd_am_acf_status(struct si476x_core *, + struct si476x_acf_status_report *); +int si476x_core_cmd_agc_status(struct si476x_core *, + struct si476x_agc_status_report *); + +enum si476x_power_grid_type { + SI476X_POWER_GRID_50HZ = 0, + SI476X_POWER_GRID_60HZ, +}; + +/* Properties */ + +enum si476x_interrupt_flags { + SI476X_STCIEN = (1 << 0), + SI476X_ACFIEN = (1 << 1), + SI476X_RDSIEN = (1 << 2), + SI476X_RSQIEN = (1 << 3), + + SI476X_ERRIEN = (1 << 6), + SI476X_CTSIEN = (1 << 7), + + SI476X_STCREP = (1 << 8), + SI476X_ACFREP = (1 << 9), + SI476X_RDSREP = (1 << 10), + SI476X_RSQREP = (1 << 11), +}; + +enum si476x_rdsint_sources { + SI476X_RDSTPPTY = (1 << 4), + SI476X_RDSPI = (1 << 3), + SI476X_RDSSYNC = (1 << 1), + SI476X_RDSRECV = (1 << 0), +}; + +enum si476x_status_response_bits { + SI476X_CTS = (1 << 7), + SI476X_ERR = (1 << 6), + /* Status response for WB receiver */ + SI476X_WB_ASQ_INT = (1 << 4), + SI476X_RSQ_INT = (1 << 3), + /* Status response for FM receiver */ + SI476X_FM_RDS_INT = (1 << 2), + SI476X_ACF_INT = (1 << 1), + SI476X_STC_INT = (1 << 0), +}; + +/* -------------------- si476x-prop.c ----------------------- */ + +enum si476x_common_receiver_properties { + SI476X_PROP_INT_CTL_ENABLE = 0x0000, + SI476X_PROP_DIGITAL_IO_INPUT_SAMPLE_RATE = 0x0200, + SI476X_PROP_DIGITAL_IO_INPUT_FORMAT = 0x0201, + SI476X_PROP_DIGITAL_IO_OUTPUT_SAMPLE_RATE = 0x0202, + SI476X_PROP_DIGITAL_IO_OUTPUT_FORMAT = 0x0203, + + SI476X_PROP_SEEK_BAND_BOTTOM = 0x1100, + SI476X_PROP_SEEK_BAND_TOP = 0x1101, + SI476X_PROP_SEEK_FREQUENCY_SPACING = 0x1102, + + SI476X_PROP_VALID_MAX_TUNE_ERROR = 0x2000, + SI476X_PROP_VALID_SNR_THRESHOLD = 0x2003, + SI476X_PROP_VALID_RSSI_THRESHOLD = 0x2004, +}; + +enum si476x_am_receiver_properties { + SI476X_PROP_AUDIO_PWR_LINE_FILTER = 0x0303, +}; + +enum si476x_fm_receiver_properties { + SI476X_PROP_AUDIO_DEEMPHASIS = 0x0302, + + SI476X_PROP_FM_RDS_INTERRUPT_SOURCE = 0x4000, + SI476X_PROP_FM_RDS_INTERRUPT_FIFO_COUNT = 0x4001, + SI476X_PROP_FM_RDS_CONFIG = 0x4002, +}; + +enum si476x_prop_audio_pwr_line_filter_bits { + SI476X_PROP_PWR_HARMONICS_MASK = 0b0000000000011111, + SI476X_PROP_PWR_GRID_MASK = 0b0000000100000000, + SI476X_PROP_PWR_ENABLE_MASK = 0b0000001000000000, + SI476X_PROP_PWR_GRID_50HZ = 0b0000000000000000, + SI476X_PROP_PWR_GRID_60HZ = 0b0000000100000000, +}; + +enum si476x_prop_fm_rds_config_bits { + SI476X_PROP_RDSEN_MASK = 0x1, + SI476X_PROP_RDSEN = 0x1, +}; + + +struct regmap *devm_regmap_init_si476x(struct si476x_core *); + +#endif /* SI476X_CORE_H */ diff --git a/include/linux/mfd/si476x-platform.h b/include/linux/mfd/si476x-platform.h new file mode 100644 index 000000000000..88bb93b7a9d5 --- /dev/null +++ b/include/linux/mfd/si476x-platform.h @@ -0,0 +1,267 @@ +/* + * include/media/si476x-platform.h -- Platform data specific definitions + * + * Copyright (C) 2013 Andrey Smirnov + * + * Author: Andrey Smirnov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + */ + +#ifndef __SI476X_PLATFORM_H__ +#define __SI476X_PLATFORM_H__ + +/* It is possible to select one of the four adresses using pins A0 + * and A1 on SI476x */ +#define SI476X_I2C_ADDR_1 0x60 +#define SI476X_I2C_ADDR_2 0x61 +#define SI476X_I2C_ADDR_3 0x62 +#define SI476X_I2C_ADDR_4 0x63 + +enum si476x_iqclk_config { + SI476X_IQCLK_NOOP = 0, + SI476X_IQCLK_TRISTATE = 1, + SI476X_IQCLK_IQ = 21, +}; +enum si476x_iqfs_config { + SI476X_IQFS_NOOP = 0, + SI476X_IQFS_TRISTATE = 1, + SI476X_IQFS_IQ = 21, +}; +enum si476x_iout_config { + SI476X_IOUT_NOOP = 0, + SI476X_IOUT_TRISTATE = 1, + SI476X_IOUT_OUTPUT = 22, +}; +enum si476x_qout_config { + SI476X_QOUT_NOOP = 0, + SI476X_QOUT_TRISTATE = 1, + SI476X_QOUT_OUTPUT = 22, +}; + +enum si476x_dclk_config { + SI476X_DCLK_NOOP = 0, + SI476X_DCLK_TRISTATE = 1, + SI476X_DCLK_DAUDIO = 10, +}; + +enum si476x_dfs_config { + SI476X_DFS_NOOP = 0, + SI476X_DFS_TRISTATE = 1, + SI476X_DFS_DAUDIO = 10, +}; + +enum si476x_dout_config { + SI476X_DOUT_NOOP = 0, + SI476X_DOUT_TRISTATE = 1, + SI476X_DOUT_I2S_OUTPUT = 12, + SI476X_DOUT_I2S_INPUT = 13, +}; + +enum si476x_xout_config { + SI476X_XOUT_NOOP = 0, + SI476X_XOUT_TRISTATE = 1, + SI476X_XOUT_I2S_INPUT = 13, + SI476X_XOUT_MODE_SELECT = 23, +}; + +enum si476x_icin_config { + SI476X_ICIN_NOOP = 0, + SI476X_ICIN_TRISTATE = 1, + SI476X_ICIN_GPO1_HIGH = 2, + SI476X_ICIN_GPO1_LOW = 3, + SI476X_ICIN_IC_LINK = 30, +}; + +enum si476x_icip_config { + SI476X_ICIP_NOOP = 0, + SI476X_ICIP_TRISTATE = 1, + SI476X_ICIP_GPO2_HIGH = 2, + SI476X_ICIP_GPO2_LOW = 3, + SI476X_ICIP_IC_LINK = 30, +}; + +enum si476x_icon_config { + SI476X_ICON_NOOP = 0, + SI476X_ICON_TRISTATE = 1, + SI476X_ICON_I2S = 10, + SI476X_ICON_IC_LINK = 30, +}; + +enum si476x_icop_config { + SI476X_ICOP_NOOP = 0, + SI476X_ICOP_TRISTATE = 1, + SI476X_ICOP_I2S = 10, + SI476X_ICOP_IC_LINK = 30, +}; + + +enum si476x_lrout_config { + SI476X_LROUT_NOOP = 0, + SI476X_LROUT_TRISTATE = 1, + SI476X_LROUT_AUDIO = 2, + SI476X_LROUT_MPX = 3, +}; + + +enum si476x_intb_config { + SI476X_INTB_NOOP = 0, + SI476X_INTB_TRISTATE = 1, + SI476X_INTB_DAUDIO = 10, + SI476X_INTB_IRQ = 40, +}; + +enum si476x_a1_config { + SI476X_A1_NOOP = 0, + SI476X_A1_TRISTATE = 1, + SI476X_A1_IRQ = 40, +}; + + +struct si476x_pinmux { + enum si476x_dclk_config dclk; + enum si476x_dfs_config dfs; + enum si476x_dout_config dout; + enum si476x_xout_config xout; + + enum si476x_iqclk_config iqclk; + enum si476x_iqfs_config iqfs; + enum si476x_iout_config iout; + enum si476x_qout_config qout; + + enum si476x_icin_config icin; + enum si476x_icip_config icip; + enum si476x_icon_config icon; + enum si476x_icop_config icop; + + enum si476x_lrout_config lrout; + + enum si476x_intb_config intb; + enum si476x_a1_config a1; +}; + +enum si476x_ibias6x { + SI476X_IBIAS6X_OTHER = 0, + SI476X_IBIAS6X_RCVR1_NON_4MHZ_CLK = 1, +}; + +enum si476x_xstart { + SI476X_XSTART_MULTIPLE_TUNER = 0x11, + SI476X_XSTART_NORMAL = 0x77, +}; + +enum si476x_freq { + SI476X_FREQ_4_MHZ = 0, + SI476X_FREQ_37P209375_MHZ = 1, + SI476X_FREQ_36P4_MHZ = 2, + SI476X_FREQ_37P8_MHZ = 3, +}; + +enum si476x_xmode { + SI476X_XMODE_CRYSTAL_RCVR1 = 1, + SI476X_XMODE_EXT_CLOCK = 2, + SI476X_XMODE_CRYSTAL_RCVR2_3 = 3, +}; + +enum si476x_xbiashc { + SI476X_XBIASHC_SINGLE_RECEIVER = 0, + SI476X_XBIASHC_MULTIPLE_RECEIVER = 1, +}; + +enum si476x_xbias { + SI476X_XBIAS_RCVR2_3 = 0, + SI476X_XBIAS_4MHZ_RCVR1 = 3, + SI476X_XBIAS_RCVR1 = 7, +}; + +enum si476x_func { + SI476X_FUNC_BOOTLOADER = 0, + SI476X_FUNC_FM_RECEIVER = 1, + SI476X_FUNC_AM_RECEIVER = 2, + SI476X_FUNC_WB_RECEIVER = 3, +}; + + +/** + * @xcload: Selects the amount of additional on-chip capacitance to + * be connected between XTAL1 and gnd and between XTAL2 and + * GND. One half of the capacitance value shown here is the + * additional load capacitance presented to the xtal. The + * minimum step size is 0.277 pF. Recommended value is 0x28 + * but it will be layout dependent. Range is 0–0x3F i.e. + * (0–16.33 pF) + * @ctsien: enable CTSINT(interrupt request when CTS condition + * arises) when set + * @intsel: when set A1 pin becomes the interrupt pin; otherwise, + * INTB is the interrupt pin + * @func: selects the boot function of the device. I.e. + * SI476X_BOOTLOADER - Boot loader + * SI476X_FM_RECEIVER - FM receiver + * SI476X_AM_RECEIVER - AM receiver + * SI476X_WB_RECEIVER - Weatherband receiver + * @freq: oscillator's crystal frequency: + * SI476X_XTAL_37P209375_MHZ - 37.209375 Mhz + * SI476X_XTAL_36P4_MHZ - 36.4 Mhz + * SI476X_XTAL_37P8_MHZ - 37.8 Mhz + */ +struct si476x_power_up_args { + enum si476x_ibias6x ibias6x; + enum si476x_xstart xstart; + u8 xcload; + bool fastboot; + enum si476x_xbiashc xbiashc; + enum si476x_xbias xbias; + enum si476x_func func; + enum si476x_freq freq; + enum si476x_xmode xmode; +}; + + +/** + * enum si476x_phase_diversity_mode - possbile phase diversity modes + * for SI4764/5/6/7 chips. + * + * @SI476X_PHDIV_DISABLED: Phase diversity feature is + * disabled. + * @SI476X_PHDIV_PRIMARY_COMBINING: Tuner works as a primary tuner + * in combination with a + * secondary one. + * @SI476X_PHDIV_PRIMARY_ANTENNA: Tuner works as a primary tuner + * using only its own antenna. + * @SI476X_PHDIV_SECONDARY_ANTENNA: Tuner works as a primary tuner + * usning seconary tuner's antenna. + * @SI476X_PHDIV_SECONDARY_COMBINING: Tuner works as a secondary + * tuner in combination with the + * primary one. + */ +enum si476x_phase_diversity_mode { + SI476X_PHDIV_DISABLED = 0, + SI476X_PHDIV_PRIMARY_COMBINING = 1, + SI476X_PHDIV_PRIMARY_ANTENNA = 2, + SI476X_PHDIV_SECONDARY_ANTENNA = 3, + SI476X_PHDIV_SECONDARY_COMBINING = 5, +}; + + +/* + * Platform dependent definition + */ +struct si476x_platform_data { + int gpio_reset; /* < 0 if not used */ + + struct si476x_power_up_args power_up_parameters; + enum si476x_phase_diversity_mode diversity_mode; + + struct si476x_pinmux pinmux; +}; + + +#endif /* __SI476X_PLATFORM_H__ */ diff --git a/include/linux/mfd/si476x-reports.h b/include/linux/mfd/si476x-reports.h new file mode 100644 index 000000000000..e0b9455a79c0 --- /dev/null +++ b/include/linux/mfd/si476x-reports.h @@ -0,0 +1,163 @@ +/* + * include/media/si476x-platform.h -- Definitions of the data formats + * returned by debugfs hooks + * + * Copyright (C) 2013 Andrey Smirnov + * + * Author: Andrey Smirnov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + */ + +#ifndef __SI476X_REPORTS_H__ +#define __SI476X_REPORTS_H__ + +/** + * struct si476x_rsq_status - structure containing received signal + * quality + * @multhint: Multipath Detect High. + * true - Indicatedes that the value is below + * FM_RSQ_MULTIPATH_HIGH_THRESHOLD + * false - Indicatedes that the value is above + * FM_RSQ_MULTIPATH_HIGH_THRESHOLD + * @multlint: Multipath Detect Low. + * true - Indicatedes that the value is below + * FM_RSQ_MULTIPATH_LOW_THRESHOLD + * false - Indicatedes that the value is above + * FM_RSQ_MULTIPATH_LOW_THRESHOLD + * @snrhint: SNR Detect High. + * true - Indicatedes that the value is below + * FM_RSQ_SNR_HIGH_THRESHOLD + * false - Indicatedes that the value is above + * FM_RSQ_SNR_HIGH_THRESHOLD + * @snrlint: SNR Detect Low. + * true - Indicatedes that the value is below + * FM_RSQ_SNR_LOW_THRESHOLD + * false - Indicatedes that the value is above + * FM_RSQ_SNR_LOW_THRESHOLD + * @rssihint: RSSI Detect High. + * true - Indicatedes that the value is below + * FM_RSQ_RSSI_HIGH_THRESHOLD + * false - Indicatedes that the value is above + * FM_RSQ_RSSI_HIGH_THRESHOLD + * @rssilint: RSSI Detect Low. + * true - Indicatedes that the value is below + * FM_RSQ_RSSI_LOW_THRESHOLD + * false - Indicatedes that the value is above + * FM_RSQ_RSSI_LOW_THRESHOLD + * @bltf: Band Limit. + * Set if seek command hits the band limit or wrapped to + * the original frequency. + * @snr_ready: SNR measurement in progress. + * @rssiready: RSSI measurement in progress. + * @afcrl: Set if FREQOFF >= MAX_TUNE_ERROR + * @valid: Set if the channel is valid + * rssi < FM_VALID_RSSI_THRESHOLD + * snr < FM_VALID_SNR_THRESHOLD + * tune_error < FM_VALID_MAX_TUNE_ERROR + * @readfreq: Current tuned frequency. + * @freqoff: Signed frequency offset. + * @rssi: Received Signal Strength Indicator(dBuV). + * @snr: RF SNR Indicator(dB). + * @lassi: + * @hassi: Low/High side Adjacent(100 kHz) Channel Strength Indicator + * @mult: Multipath indicator + * @dev: Who knows? But values may vary. + * @readantcap: Antenna tuning capacity value. + * @assi: Adjacent Channel(+/- 200kHz) Strength Indicator + * @usn: Ultrasonic Noise Inticator in -DBFS + */ +struct si476x_rsq_status_report { + __u8 multhint, multlint; + __u8 snrhint, snrlint; + __u8 rssihint, rssilint; + __u8 bltf; + __u8 snr_ready; + __u8 rssiready; + __u8 injside; + __u8 afcrl; + __u8 valid; + + __u16 readfreq; + __s8 freqoff; + __s8 rssi; + __s8 snr; + __s8 issi; + __s8 lassi, hassi; + __s8 mult; + __u8 dev; + __u16 readantcap; + __s8 assi; + __s8 usn; + + __u8 pilotdev; + __u8 rdsdev; + __u8 assidev; + __u8 strongdev; + __u16 rdspi; +} __packed; + +/** + * si476x_acf_status_report - ACF report results + * + * @blend_int: If set, indicates that stereo separation has crossed + * below the blend threshold as set by FM_ACF_BLEND_THRESHOLD + * @hblend_int: If set, indicates that HiBlend cutoff frequency is + * lower than threshold as set by FM_ACF_HBLEND_THRESHOLD + * @hicut_int: If set, indicates that HiCut cutoff frequency is lower + * than the threshold set by ACF_ + + */ +struct si476x_acf_status_report { + __u8 blend_int; + __u8 hblend_int; + __u8 hicut_int; + __u8 chbw_int; + __u8 softmute_int; + __u8 smute; + __u8 smattn; + __u8 chbw; + __u8 hicut; + __u8 hiblend; + __u8 pilot; + __u8 stblend; +} __packed; + +enum si476x_fmagc { + SI476X_FMAGC_10K_OHM = 0, + SI476X_FMAGC_800_OHM = 1, + SI476X_FMAGC_400_OHM = 2, + SI476X_FMAGC_200_OHM = 4, + SI476X_FMAGC_100_OHM = 8, + SI476X_FMAGC_50_OHM = 16, + SI476X_FMAGC_25_OHM = 32, + SI476X_FMAGC_12P5_OHM = 64, + SI476X_FMAGC_6P25_OHM = 128, +}; + +struct si476x_agc_status_report { + __u8 mxhi; + __u8 mxlo; + __u8 lnahi; + __u8 lnalo; + __u8 fmagc1; + __u8 fmagc2; + __u8 pgagain; + __u8 fmwblang; +} __packed; + +struct si476x_rds_blockcount_report { + __u16 expected; + __u16 received; + __u16 uncorrectable; +} __packed; + +#endif /* __SI476X_REPORTS_H__ */ -- cgit v1.2.3 From f646968f8f7c624587de729115d802372b9063dd Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Apr 2013 02:04:27 +0000 Subject: net: vlan: rename NETIF_F_HW_VLAN_* feature flags to NETIF_F_HW_VLAN_CTAG_* Rename the hardware VLAN acceleration features to include "CTAG" to indicate that they only support CTAGs. Follow up patches will introduce 802.1ad server provider tagging (STAGs) and require the distinction for hardware not supporting acclerating both. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 4 ++-- include/linux/netdev_features.h | 12 ++++++------ include/linux/netdevice.h | 6 ++++-- 3 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 70962f3fdb79..fee28291a824 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -238,7 +238,7 @@ static inline struct sk_buff *__vlan_hwaccel_put_tag(struct sk_buff *skb, */ static inline struct sk_buff *vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) { - if (skb->dev->features & NETIF_F_HW_VLAN_TX) { + if (skb->dev->features & NETIF_F_HW_VLAN_CTAG_TX) { return __vlan_hwaccel_put_tag(skb, vlan_tci); } else { return __vlan_put_tag(skb, vlan_tci); @@ -294,7 +294,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, */ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { - if (skb->dev->features & NETIF_F_HW_VLAN_TX) { + if (skb->dev->features & NETIF_F_HW_VLAN_CTAG_TX) { return __vlan_hwaccel_get_tag(skb, vlan_tci); } else { return __vlan_get_tag(skb, vlan_tci); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index d6ee2d008ee4..785913b8983d 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -22,9 +22,9 @@ enum { NETIF_F_IPV6_CSUM_BIT, /* Can checksum TCP/UDP over IPV6 */ NETIF_F_HIGHDMA_BIT, /* Can DMA to high memory. */ NETIF_F_FRAGLIST_BIT, /* Scatter/gather IO. */ - NETIF_F_HW_VLAN_TX_BIT, /* Transmit VLAN hw acceleration */ - NETIF_F_HW_VLAN_RX_BIT, /* Receive VLAN hw acceleration */ - NETIF_F_HW_VLAN_FILTER_BIT, /* Receive filtering on VLAN */ + NETIF_F_HW_VLAN_CTAG_TX_BIT, /* Transmit VLAN CTAG HW acceleration */ + NETIF_F_HW_VLAN_CTAG_RX_BIT, /* Receive VLAN CTAG HW acceleration */ + NETIF_F_HW_VLAN_CTAG_FILTER_BIT,/* Receive filtering on VLAN CTAGs */ NETIF_F_VLAN_CHALLENGED_BIT, /* Device cannot handle VLAN packets */ NETIF_F_GSO_BIT, /* Enable software GSO. */ NETIF_F_LLTX_BIT, /* LockLess TX - deprecated. Please */ @@ -80,9 +80,9 @@ enum { #define NETIF_F_GSO_ROBUST __NETIF_F(GSO_ROBUST) #define NETIF_F_HIGHDMA __NETIF_F(HIGHDMA) #define NETIF_F_HW_CSUM __NETIF_F(HW_CSUM) -#define NETIF_F_HW_VLAN_FILTER __NETIF_F(HW_VLAN_FILTER) -#define NETIF_F_HW_VLAN_RX __NETIF_F(HW_VLAN_RX) -#define NETIF_F_HW_VLAN_TX __NETIF_F(HW_VLAN_TX) +#define NETIF_F_HW_VLAN_CTAG_FILTER __NETIF_F(HW_VLAN_CTAG_FILTER) +#define NETIF_F_HW_VLAN_CTAG_RX __NETIF_F(HW_VLAN_CTAG_RX) +#define NETIF_F_HW_VLAN_CTAG_TX __NETIF_F(HW_VLAN_CTAG_TX) #define NETIF_F_IP_CSUM __NETIF_F(IP_CSUM) #define NETIF_F_IPV6_CSUM __NETIF_F(IPV6_CSUM) #define NETIF_F_LLTX __NETIF_F(LLTX) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 623b57b52195..7eb7e03ee417 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -785,11 +785,13 @@ struct netdev_fcoe_hbainfo { * neither operation. * * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, unsigned short vid); - * If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER) + * If device support VLAN filtering (dev->features & + * NETIF_F_HW_VLAN_CTAG_FILTER) * this function is called when a VLAN id is registered. * * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid); - * If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER) + * If device support VLAN filtering (dev->features & + * NETIF_F_HW_VLAN_CTAG_FILTER) * this function is called when a VLAN id is unregistered. * * void (*ndo_poll_controller)(struct net_device *dev); -- cgit v1.2.3 From 80d5c3689b886308247da295a228a54df49a44f6 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Apr 2013 02:04:28 +0000 Subject: net: vlan: prepare for 802.1ad VLAN filtering offload Change the rx_{add,kill}_vid callbacks to take a protocol argument in preparation of 802.1ad support. The protocol argument used so far is always htons(ETH_P_8021Q). Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 4 ++-- include/linux/netdevice.h | 16 +++++++--------- 2 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index fee28291a824..fcb9ef82aae1 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -93,8 +93,8 @@ extern u16 vlan_dev_vlan_id(const struct net_device *dev); extern bool vlan_do_receive(struct sk_buff **skb); extern struct sk_buff *vlan_untag(struct sk_buff *skb); -extern int vlan_vid_add(struct net_device *dev, unsigned short vid); -extern void vlan_vid_del(struct net_device *dev, unsigned short vid); +extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid); +extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid); extern int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7eb7e03ee417..f8898a435dc5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -784,15 +784,13 @@ struct netdev_fcoe_hbainfo { * 3. Update dev->stats asynchronously and atomically, and define * neither operation. * - * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, unsigned short vid); - * If device support VLAN filtering (dev->features & - * NETIF_F_HW_VLAN_CTAG_FILTER) - * this function is called when a VLAN id is registered. + * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16t vid); + * If device support VLAN filtering this function is called when a + * VLAN id is registered. * * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid); - * If device support VLAN filtering (dev->features & - * NETIF_F_HW_VLAN_CTAG_FILTER) - * this function is called when a VLAN id is unregistered. + * If device support VLAN filtering this function is called when a + * VLAN id is unregistered. * * void (*ndo_poll_controller)(struct net_device *dev); * @@ -936,9 +934,9 @@ struct net_device_ops { struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); int (*ndo_vlan_rx_add_vid)(struct net_device *dev, - unsigned short vid); + __be16 proto, u16 vid); int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, - unsigned short vid); + __be16 proto, u16 vid); #ifdef CONFIG_NET_POLL_CONTROLLER void (*ndo_poll_controller)(struct net_device *dev); int (*ndo_netpoll_setup)(struct net_device *dev, -- cgit v1.2.3 From 1fd9b1fc310314911f66d2f14a8e4f0ef37bf47b Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Apr 2013 02:04:29 +0000 Subject: net: vlan: prepare for 802.1ad support Make the encapsulation protocol value a property of VLAN devices and change the device lookup functions to take the protocol value into account. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index fcb9ef82aae1..2c9fb65f8267 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -86,7 +86,7 @@ static inline int is_vlan_dev(struct net_device *dev) #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev, - u16 vlan_id); + __be16 vlan_proto, u16 vlan_id); extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); -- cgit v1.2.3 From 86a9bad3ab6b6f858fd4443b48738cabbb6d094c Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Apr 2013 02:04:30 +0000 Subject: net: vlan: add protocol argument to packet tagging functions Add a protocol argument to the VLAN packet tagging functions. In case of HW tagging, we need that protocol available in the ndo_start_xmit functions, so it is stored in a new field in the skb. The new field fits into a hole (on 64 bit) and doesn't increase the sks's size. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 33 ++++++++++++++++++++++++--------- include/linux/skbuff.h | 2 ++ 2 files changed, 26 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 2c9fb65f8267..8086ff9988b1 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -157,9 +157,18 @@ static inline bool vlan_uses_dev(const struct net_device *dev) } #endif +static inline bool vlan_hw_offload_capable(netdev_features_t features, + __be16 proto) +{ + if (proto == htons(ETH_P_8021Q) && features & NETIF_F_HW_VLAN_CTAG_TX) + return true; + return false; +} + /** * vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag + * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload @@ -170,7 +179,8 @@ static inline bool vlan_uses_dev(const struct net_device *dev) * * Does not change skb->protocol so this function can be used during receive. */ -static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, u16 vlan_tci) +static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci) { struct vlan_ethhdr *veth; @@ -185,7 +195,7 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, u16 vlan_tci) skb->mac_header -= VLAN_HLEN; /* first, the ethernet type */ - veth->h_vlan_proto = htons(ETH_P_8021Q); + veth->h_vlan_proto = vlan_proto; /* now, the TCI */ veth->h_vlan_TCI = htons(vlan_tci); @@ -204,24 +214,28 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, u16 vlan_tci) * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. */ -static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) +static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci) { - skb = vlan_insert_tag(skb, vlan_tci); + skb = vlan_insert_tag(skb, vlan_proto, vlan_tci); if (skb) - skb->protocol = htons(ETH_P_8021Q); + skb->protocol = vlan_proto; return skb; } /** * __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting * @skb: skbuff to tag + * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Puts the VLAN TCI in @skb->vlan_tci and lets the device do the rest */ static inline struct sk_buff *__vlan_hwaccel_put_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci) { + skb->vlan_proto = vlan_proto; skb->vlan_tci = VLAN_TAG_PRESENT | vlan_tci; return skb; } @@ -236,12 +250,13 @@ static inline struct sk_buff *__vlan_hwaccel_put_tag(struct sk_buff *skb, * Assumes skb->dev is the target that will xmit this frame. * Returns a VLAN tagged skb. */ -static inline struct sk_buff *vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) +static inline struct sk_buff *vlan_put_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci) { - if (skb->dev->features & NETIF_F_HW_VLAN_CTAG_TX) { - return __vlan_hwaccel_put_tag(skb, vlan_tci); + if (vlan_hw_offload_capable(skb->dev->features, vlan_proto)) { + return __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); } else { - return __vlan_put_tag(skb, vlan_tci); + return __vlan_put_tag(skb, vlan_proto, vlan_tci); } } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e27d1c782f32..f5bed7b31954 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -387,6 +387,7 @@ typedef unsigned char *sk_buff_data_t; * @secmark: security marking * @mark: Generic packet mark * @dropcount: total number of sk_receive_queue overflows + * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) @@ -465,6 +466,7 @@ struct sk_buff { __u32 rxhash; + __be16 vlan_proto; __u16 vlan_tci; #ifdef CONFIG_NET_SCHED -- cgit v1.2.3 From 8ad227ff89a7e6f05d07cd0acfd95ed3a24450ca Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Apr 2013 02:04:31 +0000 Subject: net: vlan: add 802.1ad support Add support for 802.1ad VLAN devices. This mainly consists of checking for ETH_P_8021AD in addition to ETH_P_8021Q in a couple of places and check offloading capabilities based on the used protocol. Configuration is done using "ip link": # ip link add link eth0 eth0.1000 \ type vlan proto 802.1ad id 1000 # ip link add link eth0.1000 eth0.1000.1000 \ type vlan proto 802.1q id 1000 52:54:00:12:34:56 > 92:b1:54:28:e4:8c, ethertype 802.1Q (0x8100), length 106: vlan 1000, p 0, ethertype 802.1Q, vlan 1000, p 0, ethertype IPv4, (tos 0x0, ttl 64, id 0, offset 0, flags [DF], proto ICMP (1), length 84) 20.1.0.2 > 20.1.0.1: ICMP echo request, id 3003, seq 8, length 64 92:b1:54:28:e4:8c > 52:54:00:12:34:56, ethertype 802.1Q-QinQ (0x88a8), length 106: vlan 1000, p 0, ethertype 802.1Q, vlan 1000, p 0, ethertype IPv4, (tos 0x0, ttl 64, id 47944, offset 0, flags [none], proto ICMP (1), length 84) 20.1.0.1 > 20.1.0.2: ICMP echo reply, id 3003, seq 8, length 64 Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 6 ++++-- include/linux/netdev_features.h | 6 ++++++ 2 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 8086ff9988b1..a78f9390da87 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -162,6 +162,8 @@ static inline bool vlan_hw_offload_capable(netdev_features_t features, { if (proto == htons(ETH_P_8021Q) && features & NETIF_F_HW_VLAN_CTAG_TX) return true; + if (proto == htons(ETH_P_8021AD) && features & NETIF_F_HW_VLAN_STAG_TX) + return true; return false; } @@ -271,9 +273,9 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { struct vlan_ethhdr *veth = (struct vlan_ethhdr *)skb->data; - if (veth->h_vlan_proto != htons(ETH_P_8021Q)) { + if (veth->h_vlan_proto != htons(ETH_P_8021Q) && + veth->h_vlan_proto != htons(ETH_P_8021AD)) return -EINVAL; - } *vlan_tci = ntohs(veth->h_vlan_TCI); return 0; diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 785913b8983d..cbaa027ef5a7 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -25,6 +25,9 @@ enum { NETIF_F_HW_VLAN_CTAG_TX_BIT, /* Transmit VLAN CTAG HW acceleration */ NETIF_F_HW_VLAN_CTAG_RX_BIT, /* Receive VLAN CTAG HW acceleration */ NETIF_F_HW_VLAN_CTAG_FILTER_BIT,/* Receive filtering on VLAN CTAGs */ + NETIF_F_HW_VLAN_STAG_TX_BIT, /* Transmit VLAN STAG HW acceleration */ + NETIF_F_HW_VLAN_STAG_RX_BIT, /* Receive VLAN STAG HW acceleration */ + NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */ NETIF_F_VLAN_CHALLENGED_BIT, /* Device cannot handle VLAN packets */ NETIF_F_GSO_BIT, /* Enable software GSO. */ NETIF_F_LLTX_BIT, /* LockLess TX - deprecated. Please */ @@ -83,6 +86,9 @@ enum { #define NETIF_F_HW_VLAN_CTAG_FILTER __NETIF_F(HW_VLAN_CTAG_FILTER) #define NETIF_F_HW_VLAN_CTAG_RX __NETIF_F(HW_VLAN_CTAG_RX) #define NETIF_F_HW_VLAN_CTAG_TX __NETIF_F(HW_VLAN_CTAG_TX) +#define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER) +#define NETIF_F_HW_VLAN_STAG_RX __NETIF_F(HW_VLAN_STAG_RX) +#define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) #define NETIF_F_IP_CSUM __NETIF_F(IP_CSUM) #define NETIF_F_IPV6_CSUM __NETIF_F(IPV6_CSUM) #define NETIF_F_LLTX __NETIF_F(LLTX) -- cgit v1.2.3 From e32123e59871b9389d5b3fe9318611c7f1d1307a Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:46:57 +0000 Subject: netlink: rename ssk to sk in struct netlink_skb_params Memory mapped netlink needs to store the receiving userspace socket when sending from the kernel to userspace. Rename 'ssk' to 'sk' to avoid confusion. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index e0f746b7b95c..d8e9264ae04a 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -19,7 +19,7 @@ struct netlink_skb_parms { struct scm_creds creds; /* Skb credentials */ __u32 portid; __u32 dst_group; - struct sock *ssk; + struct sock *sk; }; #define NETLINK_CB(skb) (*(struct netlink_skb_parms*)&((skb)->cb)) -- cgit v1.2.3 From 0ebd0ac5ff01ebf412e1bd3c33620ef7ffc5d866 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:46:58 +0000 Subject: net: add function to allocate sk_buff head without data area Add a function to allocate a sk_buff head without any data. This will be used by memory mapped netlink to attach data from the mmaped area to the skb. Additionally change skb_release_all() to check whether the skb has a data area to allow the skb destructor to clear the data pointer in case only a head has been allocated. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f5bed7b31954..2e0ced1af3b1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -651,6 +651,12 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } +extern struct sk_buff *__alloc_skb_head(gfp_t priority, int node); +static inline struct sk_buff *alloc_skb_head(gfp_t priority) +{ + return __alloc_skb_head(priority, -1); +} + extern struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); extern int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); extern struct sk_buff *skb_clone(struct sk_buff *skb, -- cgit v1.2.3 From 9652e931e73be7e54a9c40e9bcd4bbdafe92a406 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:47:02 +0000 Subject: netlink: add mmap'ed netlink helper functions Add helper functions for looking up mmap'ed frame headers, reading and writing their status, allocating skbs with mmap'ed data areas and a poll function. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netlink.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index d8e9264ae04a..07c473848dbd 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -15,10 +15,17 @@ static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) return (struct nlmsghdr *)skb->data; } +enum netlink_skb_flags { + NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */ + NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */ + NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */ +}; + struct netlink_skb_parms { struct scm_creds creds; /* Skb credentials */ __u32 portid; __u32 dst_group; + __u32 flags; struct sock *sk; }; -- cgit v1.2.3 From f9c2288837ba072b21dba955f04a4c97eaa77b1e Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:47:04 +0000 Subject: netlink: implement memory mapped recvmsg() Add support for mmap'ed recvmsg(). To allow the kernel to construct messages into the mapped area, a dataless skb is allocated and the data pointer is set to point into the ring frame. This means frames will be delivered to userspace in order of allocation instead of order of transmission. This usually doesn't matter since the order is either not determinable by userspace or message creation/transmission is serialized. The only case where this can have a visible difference is nfnetlink_queue. Userspace can't assume mmap'ed messages have ordered IDs anymore and needs to check this if using batched verdicts. For non-mapped sockets, nothing changes. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 07c473848dbd..6358da5eeee8 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -64,6 +64,8 @@ extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group) extern void netlink_clear_multicast_users(struct sock *sk, unsigned int group); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_has_listeners(struct sock *sk, unsigned int group); +extern struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, + u32 dst_portid, gfp_t gfp_mask); extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); -- cgit v1.2.3 From ec464e5dc504a164c5dbff4a06812d495e44e34d Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:47:08 +0000 Subject: netfilter: rename netlink related "pid" variables to "portid" Get rid of the confusing mix of pid and portid and use portid consistently for all netlink related socket identities. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index ecbb8e495912..60b164171daf 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -29,10 +29,11 @@ extern int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n); extern int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n); extern int nfnetlink_has_listeners(struct net *net, unsigned int group); -extern int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, - int echo, gfp_t flags); -extern int nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error); -extern int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u_int32_t pid, int flags); +extern int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, + unsigned int group, int echo, gfp_t flags); +extern int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error); +extern int nfnetlink_unicast(struct sk_buff *skb, struct net *net, + u32 portid, int flags); extern void nfnl_lock(__u8 subsys_id); extern void nfnl_unlock(__u8 subsys_id); -- cgit v1.2.3 From 3ab1f683bf8be7aa7869cc3ffb8d1db2ec8c8307 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 17 Apr 2013 06:47:09 +0000 Subject: nfnetlink: add support for memory mapped netlink Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter/nfnetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 60b164171daf..cadb7402d7a7 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -29,6 +29,8 @@ extern int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n); extern int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n); extern int nfnetlink_has_listeners(struct net *net, unsigned int group); +extern struct sk_buff *nfnetlink_alloc_skb(struct net *net, unsigned int size, + u32 dst_portid, gfp_t gfp_mask); extern int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags); extern int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error); -- cgit v1.2.3 From 9a08d3766874835f4eba1b3d66938326c069d817 Mon Sep 17 00:00:00 2001 From: Wang YanQing Date: Fri, 19 Apr 2013 09:38:04 +0800 Subject: iommu: Include linux/err.h The linux/iommu.h header uses ERR_PTR defined in linux/err.h but doesn't include it. Cc:joro@8bytes.org Reviewed-by: Alex Williamson Signed-off-by: Wang YanQing Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index ba3b8a98a049..6a027dc8dbfe 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -20,6 +20,7 @@ #define __LINUX_IOMMU_H #include +#include #include #define IOMMU_READ (1) -- cgit v1.2.3 From e34d3865ee4a71195f91b23fd09e2619a5f727d3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 28 Jan 2013 17:42:24 +0000 Subject: ata: arasan: remove the need for platform_data This adds a complete DT binding for the arasan device driver. There is currently only one user, which is the spear13xx platform, so we don't actually have to parse all the properties until another user comes in, but this does use the generic DMA binding to find the DMA channel. The patch is untested so far and is part of a series to convert the spear platform over to use the generic DMA binding, so it should stay with the rest of the series. Signed-off-by: Arnd Bergmann Acked-by: Viresh Kumar Cc: Vinod Koul Cc: Jeff Garzik Cc: devicetree-discuss@lists.ozlabs.org --- include/linux/pata_arasan_cf_data.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pata_arasan_cf_data.h b/include/linux/pata_arasan_cf_data.h index a7b4fc386e63..3cc21c9cc1e8 100644 --- a/include/linux/pata_arasan_cf_data.h +++ b/include/linux/pata_arasan_cf_data.h @@ -37,8 +37,6 @@ struct arasan_cf_pdata { #define CF_BROKEN_PIO (1) #define CF_BROKEN_MWDMA (1 << 1) #define CF_BROKEN_UDMA (1 << 2) - /* This is platform specific data for the DMA controller */ - void *dma_priv; }; static inline void -- cgit v1.2.3 From 6e94d1ef37e439bf45659cc071553574ccb98080 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 16 Apr 2013 01:29:10 +0000 Subject: net: socket: move ktime2ts to ktime header api Currently, ktime2ts is a small helper function that is only used in net/socket.c. Move this helper into the ktime API as a small inline function, so that i) it's maintained together with ktime routines, and ii) also other files can make use of it. The function is named ktime_to_timespec_cond() and placed into the generic part of ktime, since we internally make use of ktime_to_timespec(). ktime_to_timespec() itself does not check the ktime variable for zero, hence, we name this function ktime_to_timespec_cond() for only a conditional conversion, and adapt its users to it. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/ktime.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index e83512f63df5..bbca12804d12 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -330,6 +330,24 @@ static inline ktime_t ktime_sub_us(const ktime_t kt, const u64 usec) extern ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs); +/** + * ktime_to_timespec_cond - convert a ktime_t variable to timespec + * format only if the variable contains data + * @kt: the ktime_t variable to convert + * @ts: the timespec variable to store the result in + * + * Returns true if there was a successful conversion, false if kt was 0. + */ +static inline bool ktime_to_timespec_cond(const ktime_t kt, struct timespec *ts) +{ + if (kt.tv64) { + *ts = ktime_to_timespec(kt); + return true; + } else { + return false; + } +} + /* * The resolution of the clocks. The resolution value is returned in * the clock_getres() system call to give application programmers an -- cgit v1.2.3 From d2802d0739dcc61af5e5ea00773ce7ddead4e9c2 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 19 Apr 2013 17:10:27 -0400 Subject: tracing: Compare to 1 instead of zero for is_signed_type() The formats of the trace events show if the type of a event field is signed or not via a macro called is_signed_type(). This does a trick with the type and compares a -1 to zero after typecasting to the tested type. If it returns true, it's signed, otherwise its not. But this unfortunately triggers a warning by gcc: warning: comparison of unsigned expression < 0 is always false As we know it is always false (that's why we do it), this is a false warning. Luckily for us, the comparison works with a 1 as well, without giving the warning. Convert the check to compare (type)-1 < (type)0 to (type)-1 < (type)1 to determine if the type is signed or not. Link: http://lkml.kernel.org/r/CAErSpo4YXcY9fuOKWYGDkddJwk68kmZTohsmVB6QvrhjboOh1Q@mail.gmail.com Reported-by: Bjorn Helgaas Reported-by: Gary Hade Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 4e28b011e63b..34e00fb49bec 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -333,7 +333,7 @@ extern int trace_define_field(struct ftrace_event_call *call, const char *type, extern int trace_add_event_call(struct ftrace_event_call *call); extern void trace_remove_event_call(struct ftrace_event_call *call); -#define is_signed_type(type) (((type)(-1)) < (type)0) +#define is_signed_type(type) (((type)(-1)) < (type)1) int trace_set_clr_event(const char *system, const char *event, int set); -- cgit v1.2.3 From 28daf4fae8693d4a285123494899fe01950cba50 Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Fri, 19 Apr 2013 17:49:23 -0400 Subject: jbd2: use kmem_cache_zalloc instead of kmem_cache_alloc/memset The jbd2_alloc_handle() function is only called by new_handle(). So this commit uses kmem_cache_zalloc() instead of kmem_cache_alloc()/memset(). Signed-off-by: Zheng Liu Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index f9fe88957b7a..6e051f472edb 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1145,7 +1145,7 @@ extern struct kmem_cache *jbd2_handle_cache; static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags) { - return kmem_cache_alloc(jbd2_handle_cache, gfp_flags); + return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags); } static inline void jbd2_free_handle(handle_t *handle) -- cgit v1.2.3 From 877f962c5edacfef60ab21cfed6d8d54ce25b8a6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 20 Apr 2013 19:58:37 -0400 Subject: buffer: add BH_Prio and BH_Meta flags Add buffer_head flags so that buffer cache writebacks can be marked with the the appropriate request flags, so that metadata blocks can be marked appropriately in blktrace. Signed-off-by: "Theodore Ts'o" --- include/linux/buffer_head.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 5afc4f94d110..33c0f8103fe4 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -34,6 +34,8 @@ enum bh_state_bits { BH_Write_EIO, /* I/O error on write */ BH_Unwritten, /* Buffer is allocated on disk but not written */ BH_Quiet, /* Buffer Error Prinks to be quiet */ + BH_Meta, /* Buffer contains metadata */ + BH_Prio, /* Buffer should be submitted with REQ_PRIO */ BH_PrivateStart,/* not a state bit, but the first bit available * for private allocation by other entities @@ -124,6 +126,8 @@ BUFFER_FNS(Delay, delay) BUFFER_FNS(Boundary, boundary) BUFFER_FNS(Write_EIO, write_io_error) BUFFER_FNS(Unwritten, unwritten) +BUFFER_FNS(Meta, meta) +BUFFER_FNS(Prio, prio) #define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) -- cgit v1.2.3 From 9fae27b33785cb6350f21449073d9f7d1a2bbfd6 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sat, 20 Apr 2013 23:51:41 +0000 Subject: net: vlan: fix dummy function signatures for CONFIG_VLAN=n Fix up some function signatures for CONFIG_VLAN=n that were missed during the 802.1ad support patches. Found by the kbuild robot. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index a78f9390da87..52bd03b38962 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -104,7 +104,8 @@ extern void vlan_vids_del_by_dev(struct net_device *dev, extern bool vlan_uses_dev(const struct net_device *dev); #else static inline struct net_device * -__vlan_find_dev_deep(struct net_device *real_dev, u16 vlan_id) +__vlan_find_dev_deep(struct net_device *real_dev, + __be16 vlan_proto, u16 vlan_id) { return NULL; } @@ -131,12 +132,12 @@ static inline struct sk_buff *vlan_untag(struct sk_buff *skb) return skb; } -static inline int vlan_vid_add(struct net_device *dev, unsigned short vid) +static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid) { return 0; } -static inline void vlan_vid_del(struct net_device *dev, unsigned short vid) +static inline void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid) { } -- cgit v1.2.3 From 026249ef100b5384b6c74c360db46728e98354da Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 20 Apr 2013 15:58:34 +0200 Subject: perf: New helper to prevent full dynticks CPUs from stopping tick Provide a new helper that help full dynticks CPUs to prevent from stopping their tick in case there are events in the local rotation list. This way we make sure that perf_event_task_tick() is serviced on demand. Signed-off-by: Frederic Weisbecker Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Oleg Nesterov Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Stephane Eranian Cc: Jiri Olsa --- include/linux/perf_event.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e47ee462c2f2..0140830225e2 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -799,6 +799,12 @@ static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } #endif +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_NO_HZ_FULL) +extern bool perf_event_can_stop_tick(void); +#else +static inline bool perf_event_can_stop_tick(void) { return true; } +#endif + #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) /* -- cgit v1.2.3 From ce831b38ca4920739a7a5b0c73b921da41f03718 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 20 Apr 2013 15:15:35 +0200 Subject: sched: New helper to prevent from stopping the tick in full dynticks Provide a new helper to be called from the full dynticks engine before stopping the tick in order to make sure we don't stop it when there is more than one task running on the CPU. This way we make sure that the tick stays alive to maintain fairness. Signed-off-by: Frederic Weisbecker Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Oleg Nesterov Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- include/linux/sched.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 1ff9e0a5de27..a74adedcdd10 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1856,6 +1856,12 @@ extern void wake_up_nohz_cpu(int cpu); static inline void wake_up_nohz_cpu(int cpu) { } #endif +#ifdef CONFIG_NO_HZ_FULL +extern bool sched_can_stop_tick(void); +#else +static inline bool sched_can_stop_tick(void) { return false; } +#endif + #ifdef CONFIG_SCHED_AUTOGROUP extern void sched_autogroup_create_attach(struct task_struct *p); extern void sched_autogroup_detach(struct task_struct *p); -- cgit v1.2.3 From ff442c51f6543378cf23107c75b7949dc64a9119 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 20 Apr 2013 15:27:08 +0200 Subject: nohz: Re-evaluate the tick from the scheduler IPI The scheduler IPI is used by the scheduler to kick full dynticks CPUs asynchronously when more than one task are running or when a new timer list timer is enqueued. This way the destination CPU can decide to restart the tick to handle this new situation. Now let's call that kick in the scheduler IPI. (Reusing the scheduler IPI rather than implementing a new IPI was suggested by Peter Zijlstra a while ago) Signed-off-by: Frederic Weisbecker Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Oleg Nesterov Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- include/linux/tick.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index d290168335bc..e31e67623ea1 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -160,11 +160,13 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } #ifdef CONFIG_NO_HZ_FULL extern void tick_nohz_init(void); extern int tick_nohz_full_cpu(int cpu); +extern void tick_nohz_full_check(void); extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_all(void); #else static inline void tick_nohz_init(void) { } static inline int tick_nohz_full_cpu(int cpu) { return 0; } +static inline void tick_nohz_full_check(void) { } static inline void tick_nohz_full_kick(void) { } static inline void tick_nohz_full_kick_all(void) { } #endif -- cgit v1.2.3 From 99e5ada9407cc19d7c4c05ce2165f20dc46fc093 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 20 Apr 2013 17:11:50 +0200 Subject: nohz: Re-evaluate the tick for the new task after a context switch When a task is scheduled in, it may have some properties of its own that could make the CPU reconsider the need for the tick: posix cpu timers, perf events, ... So notify the full dynticks subsystem when a task gets scheduled in and re-check the tick dependency at this stage. This is done through a self IPI to avoid messing up with any current lock scenario. Signed-off-by: Frederic Weisbecker Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Oleg Nesterov Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- include/linux/tick.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index e31e67623ea1..9180f4b85e6d 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -163,12 +163,14 @@ extern int tick_nohz_full_cpu(int cpu); extern void tick_nohz_full_check(void); extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_all(void); +extern void tick_nohz_task_switch(struct task_struct *tsk); #else static inline void tick_nohz_init(void) { } static inline int tick_nohz_full_cpu(int cpu) { return 0; } static inline void tick_nohz_full_check(void) { } static inline void tick_nohz_full_kick(void) { } static inline void tick_nohz_full_kick_all(void) { } +static inline void tick_nohz_task_switch(struct task_struct *tsk) { } #endif -- cgit v1.2.3 From 554c06ba3ee29cf453fca17e9e61120b75aa476d Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 23 Apr 2013 08:54:31 +0000 Subject: cpuidle: remove en_core_tk_irqen flag The en_core_tk_irqen flag is set in all the cpuidle driver which means it is not necessary to specify this flag. Remove the flag and the code related to it. Signed-off-by: Daniel Lezcano Acked-by: Kevin Hilman # for mach-omap2/* Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index fc3e5808b7ff..79e38114e5f4 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -105,8 +105,6 @@ struct cpuidle_driver { struct module *owner; int refcnt; - /* set to 1 to use the core cpuidle time keeping (for all states). */ - unsigned int en_core_tk_irqen:1; /* used by the cpuidle framework to setup the broadcast timer */ unsigned int bctimer:1; /* states array must be ordered in decreasing power consumption */ @@ -132,10 +130,6 @@ extern void cpuidle_pause(void); extern void cpuidle_resume(void); extern int cpuidle_enable_device(struct cpuidle_device *dev); extern void cpuidle_disable_device(struct cpuidle_device *dev); -extern int cpuidle_wrap_enter(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index, - int (*enter)(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index)); extern int cpuidle_play_dead(void); extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev); @@ -162,11 +156,6 @@ static inline void cpuidle_resume(void) { } static inline int cpuidle_enable_device(struct cpuidle_device *dev) {return -ENODEV; } static inline void cpuidle_disable_device(struct cpuidle_device *dev) { } -static inline int cpuidle_wrap_enter(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index, - int (*enter)(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index)) -{ return -ENODEV; } static inline int cpuidle_play_dead(void) {return -ENODEV; } #endif -- cgit v1.2.3 From 4c637b2175a0dc65d533494225525c6c82d73293 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 23 Apr 2013 08:54:33 +0000 Subject: cpuidle: make a single register function for all The usual scheme to initialize a cpuidle driver on a SMP is: cpuidle_register_driver(drv); for_each_possible_cpu(cpu) { device = &per_cpu(cpuidle_dev, cpu); cpuidle_register_device(device); } This code is duplicated in each cpuidle driver. On UP systems, it is done this way: cpuidle_register_driver(drv); device = &per_cpu(cpuidle_dev, cpu); cpuidle_register_device(device); On UP, the macro 'for_each_cpu' does one iteration: #define for_each_cpu(cpu, mask) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) Hence, the initialization loop is the same for UP than SMP. Beside, we saw different bugs / mis-initialization / return code unchecked in the different drivers, the code is duplicated including bugs. After fixing all these ones, it appears the initialization pattern is the same for everyone. Please note, some drivers are doing dev->state_count = drv->state_count. This is not necessary because it is done by the cpuidle_enable_device function in the cpuidle framework. This is true, until you have the same states for all your devices. Otherwise, the 'low level' API should be used instead with the specific initialization for the driver. Let's add a wrapper function doing this initialization with a cpumask parameter for the coupled idle states and use it for all the drivers. That will save a lot of LOC, consolidate the code, and the modifications in the future could be done in a single place. Another benefit is the consolidation of the cpuidle_device variable which is now in the cpuidle framework and no longer spread accross the different arch specific drivers. Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 79e38114e5f4..3c86faa59798 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -123,7 +123,9 @@ extern void cpuidle_driver_unref(void); extern void cpuidle_unregister_driver(struct cpuidle_driver *drv); extern int cpuidle_register_device(struct cpuidle_device *dev); extern void cpuidle_unregister_device(struct cpuidle_device *dev); - +extern int cpuidle_register(struct cpuidle_driver *drv, + const struct cpumask *const coupled_cpus); +extern void cpuidle_unregister(struct cpuidle_driver *drv); extern void cpuidle_pause_and_lock(void); extern void cpuidle_resume_and_unlock(void); extern void cpuidle_pause(void); @@ -148,7 +150,10 @@ static inline void cpuidle_unregister_driver(struct cpuidle_driver *drv) { } static inline int cpuidle_register_device(struct cpuidle_device *dev) {return -ENODEV; } static inline void cpuidle_unregister_device(struct cpuidle_device *dev) { } - +static inline int cpuidle_register(struct cpuidle_driver *drv, + const struct cpumask *const coupled_cpus) +{return -ENODEV; } +static inline void cpuidle_unregister(struct cpuidle_driver *drv) { } static inline void cpuidle_pause_and_lock(void) { } static inline void cpuidle_resume_and_unlock(void) { } static inline void cpuidle_pause(void) { } -- cgit v1.2.3 From 703860ed4e36ded696bd44af6107243fdedfb746 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 17 Apr 2013 16:57:56 -0600 Subject: PCI: Use u8, not int, for PM capability offset The Power Management Capability (PCI_CAP_ID_PM == 0x01) is defined by PCI and must appear in the 256-byte PCI Configuration Space from 0-0xff. It cannot be in the PCIe Extended Configuration space from 0x100-0xfff, so we only need a u8 to hold its offset. Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki --- include/linux/pci.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 2461033a7987..9587d4d19279 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -249,8 +249,7 @@ struct pci_dev { pci_power_t current_state; /* Current operating state. In ACPI-speak, this is D0-D3, D0 being fully functional, and D3 being off. */ - int pm_cap; /* PM capability offset in the - configuration space */ + u8 pm_cap; /* PM capability offset */ unsigned int pme_support:5; /* Bitmask of states from which PME# can be generated */ unsigned int pme_interrupt:1; -- cgit v1.2.3 From e375b561817d9ae098cc4296a729fc88924a0159 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 4 Apr 2013 16:54:30 +0000 Subject: PCI: Cache MSI/MSI-X capability offsets in struct pci_dev The patch caches the MSI and MSI-X capability offset in PCI device (struct pci_dev) so that we needn't read it from the config space upon enabling or disabling MSI or MSI-X interrupts. [bhelgaas: moved pm_cap size change to separate patch] Signed-off-by: Gavin Shan Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 9587d4d19279..b73c2460ad57 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -232,6 +232,8 @@ struct pci_dev { u8 revision; /* PCI revision, low byte of class word */ u8 hdr_type; /* PCI header type (`multi' flag masked out) */ u8 pcie_cap; /* PCI-E capability offset */ + u8 msi_cap; /* MSI capability offset */ + u8 msix_cap; /* MSI-X capability offset */ u8 pcie_mpss:3; /* PCI-E Max Payload Size Supported */ u8 rom_base_reg; /* which config register controls the ROM */ u8 pin; /* which interrupt pin this device uses */ -- cgit v1.2.3 From 2366d06eb15d3cf21d3b243ff586bcb80896c9f2 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 18 Apr 2013 10:55:46 -0600 Subject: PCI: Remove "extern" from function declarations We had an inconsistent mix of using and omitting the "extern" keyword on function declarations in header files. This removes them all. Signed-off-by: Bjorn Helgaas --- include/linux/msi.h | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index ce93a341337d..20c2d6dd5d25 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -13,14 +13,14 @@ struct msi_msg { /* Helper functions */ struct irq_data; struct msi_desc; -extern void mask_msi_irq(struct irq_data *data); -extern void unmask_msi_irq(struct irq_data *data); -extern void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); -extern void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg); -extern void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); -extern void read_msi_msg(unsigned int irq, struct msi_msg *msg); -extern void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); -extern void write_msi_msg(unsigned int irq, struct msi_msg *msg); +void mask_msi_irq(struct irq_data *data); +void unmask_msi_irq(struct irq_data *data); +void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); +void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg); +void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); +void read_msi_msg(unsigned int irq, struct msi_msg *msg); +void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); +void write_msi_msg(unsigned int irq, struct msi_msg *msg); struct msi_desc { struct { @@ -54,9 +54,8 @@ struct msi_desc { */ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); -extern int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); -extern void arch_teardown_msi_irqs(struct pci_dev *dev); -extern int arch_msi_check_device(struct pci_dev* dev, int nvec, int type); - +int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); +void arch_teardown_msi_irqs(struct pci_dev *dev); +int arch_msi_check_device(struct pci_dev* dev, int nvec, int type); #endif /* LINUX_MSI_H */ -- cgit v1.2.3 From ee5d5499edb94cd03738a52a7e234b139da8fd72 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 23 Apr 2013 21:05:40 +0200 Subject: usb: phy: tegra: don't call into tegra-ehci directly Both phy-tegra-usb.c and ehci-tegra.c export symbols used by the other one, which does not work if one of them or both are loadable modules, resulting in an error like: drivers/built-in.o: In function `utmi_phy_clk_disable': drivers/usb/phy/phy-tegra-usb.c:302: undefined reference to `tegra_ehci_set_phcd' drivers/built-in.o: In function `utmi_phy_clk_enable': drivers/usb/phy/phy-tegra-usb.c:324: undefined reference to `tegra_ehci_set_phcd' drivers/built-in.o: In function `utmi_phy_power_on': drivers/usb/phy/phy-tegra-usb.c:447: undefined reference to `tegra_ehci_set_pts' This turns the interface into a one-way dependency by letting the tegra ehci driver pass two function pointers for callbacks that need to be called by the phy driver. Signed-off-by: Arnd Bergmann Cc: Venu Byravarasu Cc: Alan Stern Cc: Felipe Balbi Cc: Stephen Warren Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tegra_usb_phy.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 9ebebe906925..1b7519a8c0bf 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -61,10 +61,14 @@ struct tegra_usb_phy { struct device *dev; bool is_legacy_phy; bool is_ulpi_phy; + void (*set_pts)(struct usb_phy *x, u8 pts_val); + void (*set_phcd)(struct usb_phy *x, bool enable); }; struct tegra_usb_phy *tegra_usb_phy_open(struct device *dev, int instance, - void __iomem *regs, void *config, enum tegra_usb_phy_mode phy_mode); + void __iomem *regs, void *config, enum tegra_usb_phy_mode phy_mode, + void (*set_pts)(struct usb_phy *x, u8 pts_val), + void (*set_phcd)(struct usb_phy *x, bool enable)); void tegra_usb_phy_preresume(struct usb_phy *phy); @@ -75,8 +79,4 @@ void tegra_ehci_phy_restore_start(struct usb_phy *phy, void tegra_ehci_phy_restore_end(struct usb_phy *phy); -void tegra_ehci_set_pts(struct usb_phy *x, u8 pts_val); - -void tegra_ehci_set_phcd(struct usb_phy *x, bool enable); - #endif /* __TEGRA_USB_PHY_H */ -- cgit v1.2.3 From 871dd9286e25330c8a581e5dacfa8b1dfe1dd641 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Wed, 24 Apr 2013 08:52:50 -0600 Subject: block: fix max discard sectors limit linux-v3.8-rc1 and later support for plug for blkdev_issue_discard with commit 0cfbcafcae8b7364b5fa96c2b26ccde7a3a296a9 (block: add plug for blkdev_issue_discard ) For example, 1) DISCARD rq-1 with size size 4GB 2) DISCARD rq-2 with size size 1GB If these 2 discard requests get merged, final request size will be 5GB. In this case, request's __data_len field may overflow as it can store max 4GB(unsigned int). This issue was observed while doing mkfs.f2fs on 5GB SD card: https://lkml.org/lkml/2013/4/1/292 Info: sector size = 512 Info: total sectors = 11370496 (in 512bytes) Info: zone aligned segment0 blkaddr: 512 [ 257.789764] blk_update_request: bio idx 0 >= vcnt 0 mkfs process gets stuck in D state and I see the following in the dmesg: [ 257.789733] __end_that: dev mmcblk0: type=1, flags=122c8081 [ 257.789764] sector 4194304, nr/cnr 2981888/4294959104 [ 257.789764] bio df3840c0, biotail df3848c0, buffer (null), len 1526726656 [ 257.789764] blk_update_request: bio idx 0 >= vcnt 0 [ 257.794921] request botched: dev mmcblk0: type=1, flags=122c8081 [ 257.794921] sector 4194304, nr/cnr 2981888/4294959104 [ 257.794921] bio df3840c0, biotail df3848c0, buffer (null), len 1526726656 This patch fixes this issue. Reported-by: Max Filippov Signed-off-by: James Bottomley Signed-off-by: Namjae Jeon Tested-by: Max Filippov Cc: Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 89d89c7162aa..6189bf26b53d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -844,7 +844,7 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, unsigned int cmd_flags) { if (unlikely(cmd_flags & REQ_DISCARD)) - return q->limits.max_discard_sectors; + return min(q->limits.max_discard_sectors, UINT_MAX >> 9); if (unlikely(cmd_flags & REQ_WRITE_SAME)) return q->limits.max_write_same_sectors; -- cgit v1.2.3 From 198f38f7fb2d0956cc3394655d03cdb7054b0dcd Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Wed, 24 Apr 2013 23:10:28 +0800 Subject: thermal: cpu_cooling: add needed header for cpu_cooling.h Update header list for cpu_cooling.h. Missing definition of cpumask. Signed-off-by: Eduardo Valentin Acked-by: Amit Daniel Kachhap Signed-off-by: Zhang Rui --- include/linux/cpu_cooling.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index 77c87c9d0193..75ef931fc4fc 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -25,6 +25,7 @@ #define __CPU_COOLING_H__ #include +#include #define CPUFREQ_COOLING_START 0 #define CPUFREQ_COOLING_STOP 1 -- cgit v1.2.3 From e44dec77be9e032ff9c2f95f17f7df3a55b58f60 Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Wed, 17 Apr 2013 17:12:22 +0000 Subject: thermal: cpu_cooling: remove unused symbols on cpu_cooling.h Remove defines that are not in used. Signed-off-by: Eduardo Valentin Acked-by: Amit Daniel Kachhap Signed-off-by: Zhang Rui --- include/linux/cpu_cooling.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index 75ef931fc4fc..f48f6fbcd3be 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -27,9 +27,6 @@ #include #include -#define CPUFREQ_COOLING_START 0 -#define CPUFREQ_COOLING_STOP 1 - #ifdef CONFIG_CPU_THERMAL /** * cpufreq_cooling_register - function to create cpufreq cooling device. -- cgit v1.2.3 From 7b73c993776b9f7d833dde7d09fd861508c54777 Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Tue, 23 Apr 2013 21:48:14 +0000 Subject: thermal: rename notify_thermal_framework to thermal_notify_framework To follow the prefix names used by the thermal functions, this patch renames notify_thermal_framework to thermal_notify_framework. Signed-off-by: Eduardo Valentin Signed-off-by: Zhang Rui --- include/linux/thermal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index ec2b886f9d96..d7272ab20ebc 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -246,7 +246,7 @@ int get_tz_trend(struct thermal_zone_device *, int); struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, struct thermal_cooling_device *, int); void thermal_cdev_update(struct thermal_cooling_device *); -void notify_thermal_framework(struct thermal_zone_device *, int); +void thermal_notify_framework(struct thermal_zone_device *, int); #ifdef CONFIG_NET extern int thermal_generate_netlink_event(struct thermal_zone_device *tz, -- cgit v1.2.3 From aa16bea929aed6ea854b55d2be8306a9fb40e694 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Mon, 25 Mar 2013 10:23:49 +1100 Subject: iommu: Add a function to find an iommu group by id As IOMMU groups are exposed to the user space by their numbers, the user space can use them in various kernel APIs so the kernel might need an API to find a group by its ID. As an example, QEMU VFIO on PPC64 platform needs it to associate a logical bus number (LIOBN) with a specific IOMMU group in order to support in-kernel handling of DMA map/unmap requests. The patch adds the iommu_group_get_by_id(id) function which performs such search. v2: fixed reference counting. Signed-off-by: Alexey Kardashevskiy Acked-by: Alex Williamson Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 6a027dc8dbfe..8e1b5be72b02 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -126,6 +126,7 @@ struct iommu_ops { extern int bus_set_iommu(struct bus_type *bus, struct iommu_ops *ops); extern bool iommu_present(struct bus_type *bus); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); +extern struct iommu_group *iommu_group_get_by_id(int id); extern void iommu_domain_free(struct iommu_domain *domain); extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); -- cgit v1.2.3 From d998735f443427c1530cac5eeda0a45c8cb60a57 Mon Sep 17 00:00:00 2001 From: Eugenia Emantayev Date: Tue, 23 Apr 2013 06:06:47 +0000 Subject: net/mlx4_core: Add timestamping device capability Add new device capability for timestamping support and query FW to retrieve it. Signed-off-by: Eugenia Emantayev Signed-off-by: Or Gerlitz Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 1bc5a750b330..86ae260c2e53 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -152,7 +152,8 @@ enum { MLX4_DEV_CAP_FLAG2_RSS_TOP = 1LL << 1, MLX4_DEV_CAP_FLAG2_RSS_XOR = 1LL << 2, MLX4_DEV_CAP_FLAG2_FS_EN = 1LL << 3, - MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN = 1LL << 4 + MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN = 1LL << 4, + MLX4_DEV_CAP_FLAG2_TS = 1LL << 5 }; enum { -- cgit v1.2.3 From ddd8a6c12d7e494902a9435a9a7a543ef730b2d8 Mon Sep 17 00:00:00 2001 From: Eugenia Emantayev Date: Tue, 23 Apr 2013 06:06:48 +0000 Subject: net/mlx4_core: Read HCA frequency and map internal clock Read HCA frequency, read PCI clock bar and offset, map internal clock to PCI bar. Signed-off-by: Eugenia Emantayev Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 86ae260c2e53..e088290d9792 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -445,6 +445,7 @@ struct mlx4_caps { u8 eqe_factor; u32 userspace_caps; /* userspace must be aware of these */ u32 function_caps; /* VFs must be aware of these */ + u16 hca_core_clock; }; struct mlx4_buf_list { -- cgit v1.2.3 From ec693d47010e8302e61e0bdf3f47496c5610641a Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Tue, 23 Apr 2013 06:06:49 +0000 Subject: net/mlx4_en: Add HW timestamping (TS) support The patch allows to enable/disable HW timestamping for incoming and/or outgoing packets. It adds and initializes all structs and callbacks needed by kernel TS API. To enable/disable HW timestamping appropriate ioctl should be used. Currently HWTSTAMP_FILTER_ALL/NONE and HWTSAMP_TX_ON/OFF only are supported. When enabling TS on receive flow - VLAN stripping will be disabled. Also were made all relevant changes in RX/TX flows to consider TS request and plant HW timestamps into relevant structures. mlx4_ib was fixed to compile with new mlx4_cq_alloc() signature. Signed-off-by: Eugenia Emantayev Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/cq.h | 16 ++++++++++++++++ include/linux/mlx4/device.h | 6 +++++- 2 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/cq.h b/include/linux/mlx4/cq.h index 6f65b2c8bb89..98fa492cf406 100644 --- a/include/linux/mlx4/cq.h +++ b/include/linux/mlx4/cq.h @@ -64,6 +64,22 @@ struct mlx4_err_cqe { u8 owner_sr_opcode; }; +struct mlx4_ts_cqe { + __be32 vlan_my_qpn; + __be32 immed_rss_invalid; + __be32 g_mlpath_rqpn; + __be32 timestamp_hi; + __be16 status; + u8 ipv6_ext_mask; + u8 badfcs_enc; + __be32 byte_cnt; + __be16 wqe_index; + __be16 checksum; + u8 reserved; + __be16 timestamp_lo; + u8 owner_sr_opcode; +} __packed; + enum { MLX4_CQE_VLAN_PRESENT_MASK = 1 << 29, MLX4_CQE_QPN_MASK = 0xffffff, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index e088290d9792..2fbc1464b53b 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -40,6 +40,8 @@ #include +#include + #define MAX_MSIX_P_PORT 17 #define MAX_MSIX 64 #define MSIX_LEGACY_SZ 4 @@ -840,7 +842,7 @@ void mlx4_free_hwq_res(struct mlx4_dev *mdev, struct mlx4_hwq_resources *wqres, int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt, struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq, - unsigned vector, int collapsed); + unsigned vector, int collapsed, int timestamp_en); void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq); int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base); @@ -1031,4 +1033,6 @@ int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave, u8 port, int void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid); __be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave); +cycle_t mlx4_read_clock(struct mlx4_dev *dev); + #endif /* MLX4_DEVICE_H */ -- cgit v1.2.3 From 3cd0e1789ad39c3b7ed006ce53a83328bdadbee8 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Wed, 24 Apr 2013 13:58:44 +0000 Subject: mlx4_core: Move DMFS HW structs to common header file Move flow steering HW structures to be on the public mlx4 include directory, as a pre-step for the mlx4 IB driver to use them too. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 79 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 79 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 811f91cf5e8c..9fbf416fa694 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -962,6 +962,85 @@ struct mlx4_net_trans_rule { u32 qpn; }; +struct mlx4_net_trans_rule_hw_ctrl { + __be32 ctrl; + u8 rsvd1; + u8 funcid; + u8 vep; + u8 port; + __be32 qpn; + __be32 rsvd2; +}; + +struct mlx4_net_trans_rule_hw_ib { + u8 size; + u8 rsvd1; + __be16 id; + u32 rsvd2; + __be32 qpn; + __be32 qpn_mask; + u8 dst_gid[16]; + u8 dst_gid_msk[16]; +} __packed; + +struct mlx4_net_trans_rule_hw_eth { + u8 size; + u8 rsvd; + __be16 id; + u8 rsvd1[6]; + u8 dst_mac[6]; + u16 rsvd2; + u8 dst_mac_msk[6]; + u16 rsvd3; + u8 src_mac[6]; + u16 rsvd4; + u8 src_mac_msk[6]; + u8 rsvd5; + u8 ether_type_enable; + __be16 ether_type; + __be16 vlan_id_msk; + __be16 vlan_id; +} __packed; + +struct mlx4_net_trans_rule_hw_tcp_udp { + u8 size; + u8 rsvd; + __be16 id; + __be16 rsvd1[3]; + __be16 dst_port; + __be16 rsvd2; + __be16 dst_port_msk; + __be16 rsvd3; + __be16 src_port; + __be16 rsvd4; + __be16 src_port_msk; +} __packed; + +struct mlx4_net_trans_rule_hw_ipv4 { + u8 size; + u8 rsvd; + __be16 id; + __be32 rsvd1; + __be32 dst_ip; + __be32 dst_ip_msk; + __be32 src_ip; + __be32 src_ip_msk; +} __packed; + +struct _rule_hw { + union { + struct { + u8 size; + u8 rsvd; + __be16 id; + }; + struct mlx4_net_trans_rule_hw_eth eth; + struct mlx4_net_trans_rule_hw_ib ib; + struct mlx4_net_trans_rule_hw_ipv4 ipv4; + struct mlx4_net_trans_rule_hw_tcp_udp tcp_udp; + }; +}; + int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, enum mlx4_net_trans_promisc_mode mode); int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port, -- cgit v1.2.3 From f91625398a2e6e03f0155861b630021ceddb42e7 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Wed, 24 Apr 2013 13:58:45 +0000 Subject: mlx4: Match DMFS promiscuous field names to firmware spec Align the names used by enum mlx4_net_trans_promisc_mode with the actual firmware specification. The patch doesn't introduce any functional change or API change towards the firmware. Remove MLX4_FS_PROMISC_FUNCTION_PORT which isn't of use. Add new enums MLX4_FS_{UC/MC}_SNIFFER as a preparation step for sniffer support. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 9fbf416fa694..b2fe59d199f8 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -896,11 +896,12 @@ static inline int map_hw_to_sw_id(u16 header_id) } enum mlx4_net_trans_promisc_mode { - MLX4_FS_PROMISC_NONE = 0, - MLX4_FS_PROMISC_UPLINK, - /* For future use. Not implemented yet */ - MLX4_FS_PROMISC_FUNCTION_PORT, - MLX4_FS_PROMISC_ALL_MULTI, + MLX4_FS_REGULAR = 1, + MLX4_FS_ALL_DEFAULT, + MLX4_FS_MC_DEFAULT, + MLX4_FS_UC_SNIFFER, + MLX4_FS_MC_SNIFFER, + }; struct mlx4_spec_eth { -- cgit v1.2.3 From ba60a3560ccf8e4253da9c0e8d1292375fd51796 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Wed, 24 Apr 2013 13:58:46 +0000 Subject: mlx4_core: Change a few DMFS fields names to match firmare spec Change struct mlx4_net_trans_rule_hw_eth :: vlan_id name to vlan_tag Change struct mlx4_net_trans_rule_hw_ib :: r_u_qpn name to l3_qpn The patch doesn't introduce any functional change or API change towards the firmware. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b2fe59d199f8..a69bda77c1d1 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -930,7 +930,7 @@ struct mlx4_spec_ipv4 { }; struct mlx4_spec_ib { - __be32 r_qpn; + __be32 l3_qpn; __be32 qpn_msk; u8 dst_gid[16]; u8 dst_gid_msk[16]; @@ -978,7 +978,7 @@ struct mlx4_net_trans_rule_hw_ib { u8 rsvd1; __be16 id; u32 rsvd2; - __be32 qpn; + __be32 l3_qpn; __be32 qpn_mask; u8 dst_gid[16]; u8 dst_gid_msk[16]; @@ -999,8 +999,8 @@ struct mlx4_net_trans_rule_hw_eth { u8 rsvd5; u8 ether_type_enable; __be16 ether_type; - __be16 vlan_id_msk; - __be16 vlan_id; + __be16 vlan_tag_msk; + __be16 vlan_tag; } __packed; struct mlx4_net_trans_rule_hw_tcp_udp { -- cgit v1.2.3 From bcf372971d471f6cb4070adb7bfc987d8b3d21f2 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Wed, 24 Apr 2013 13:58:47 +0000 Subject: mlx4_core: Directly expose fields of DMFS HW rule control segment Some of struct mlx4_net_trans_rule_hw_ctrl fields were packed into u32 and accessed through bit field operations. Expose and access them directly as u8 or u16. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index a69bda77c1d1..08e5bc1387e1 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -964,7 +964,9 @@ struct mlx4_net_trans_rule { }; struct mlx4_net_trans_rule_hw_ctrl { - __be32 ctrl; + __be16 prio; + u8 type; + u8 flags; u8 rsvd1; u8 funcid; u8 vep; -- cgit v1.2.3 From c2c19dc3c9a1585e58804041e5a328cde425403a Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Wed, 24 Apr 2013 13:58:48 +0000 Subject: mlx4_core: Expose a few helpers to fill DMFS HW strucutures Re-arrange some of code which fills DMFS HW structures so we can use it from within the core driver and from the IB driver too, e.g when verbs DMFS structures are transformed into mlx4 hardware structs. Also, add struct mlx4_flow_handle struct which will be of use by the DMFS verbs flow in the IB driver. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 08e5bc1387e1..ad4a53fbdddf 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -901,7 +901,7 @@ enum mlx4_net_trans_promisc_mode { MLX4_FS_MC_DEFAULT, MLX4_FS_UC_SNIFFER, MLX4_FS_MC_SNIFFER, - + MLX4_FS_MODE_NUM, /* should be last */ }; struct mlx4_spec_eth { @@ -1044,6 +1044,11 @@ struct _rule_hw { }; }; +/* translating DMFS verbs sniffer rule to the FW API would need two reg IDs */ +struct mlx4_flow_handle { + u64 reg_id[2]; +}; + int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, enum mlx4_net_trans_promisc_mode mode); int mlx4_flow_steer_promisc_remove(struct mlx4_dev *dev, u8 port, @@ -1093,6 +1098,11 @@ void mlx4_counter_free(struct mlx4_dev *dev, u32 idx); int mlx4_flow_attach(struct mlx4_dev *dev, struct mlx4_net_trans_rule *rule, u64 *reg_id); int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id); +int mlx4_map_sw_to_hw_steering_mode(struct mlx4_dev *dev, + enum mlx4_net_trans_promisc_mode flow_type); +int mlx4_map_sw_to_hw_steering_id(struct mlx4_dev *dev, + enum mlx4_net_trans_rule_id id); +int mlx4_hw_rule_sz(struct mlx4_dev *dev, enum mlx4_net_trans_rule_id id); void mlx4_sync_pkey_table(struct mlx4_dev *dev, int slave, int port, int i, int val); -- cgit v1.2.3 From 5a8eb24292ffd68604cedeb24ad2b4bc02cfc037 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 25 Apr 2013 04:42:29 +0000 Subject: pci: Add SRIOV helper function to determine if VFs are assigned to guest This function is meant to add a helper function that will determine if a PF has any VFs that are currently assigned to a guest. We currently have been implementing this function per driver, and going forward I would like to avoid that by making this function generic and using this helper. v2: Removed extern from declaration of pci_vfs_assigned in pci.h and return 0 if SR-IOV is disabled with is inline with other PCI SRIOV functions. Signed-off-by: Alexander Duyck Acked-by: Bjorn Helgaas Signed-off-by: Jeff Kirsher --- include/linux/pci.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 710067f3618c..43e45ac36458 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1644,6 +1644,7 @@ extern int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); extern void pci_disable_sriov(struct pci_dev *dev); extern irqreturn_t pci_sriov_migration(struct pci_dev *dev); extern int pci_num_vf(struct pci_dev *dev); +int pci_vfs_assigned(struct pci_dev *dev); extern int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs); extern int pci_sriov_get_totalvfs(struct pci_dev *dev); #else @@ -1662,6 +1663,10 @@ static inline int pci_num_vf(struct pci_dev *dev) { return 0; } +static inline int pci_vfs_assigned(struct pci_dev *dev) +{ + return 0; +} static inline int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs) { return 0; -- cgit v1.2.3 From 1907da78bf6a3f74e5d030a4a4f6700ba0d0a234 Mon Sep 17 00:00:00 2001 From: Alexander Clouter Date: Sun, 31 Mar 2013 17:34:50 +0100 Subject: hwrng: timeriomem - update to support more than one device timeriomem_rng only supports a single device instance. This patch enables multiple timeriomem_rng devices to coexist as well as adds some additional error checking. Signed-off-by: Alexander Clouter Signed-off-by: Herbert Xu --- include/linux/timeriomem-rng.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timeriomem-rng.h b/include/linux/timeriomem-rng.h index 3e08a1c86830..46eb27ddbfab 100644 --- a/include/linux/timeriomem-rng.h +++ b/include/linux/timeriomem-rng.h @@ -8,12 +8,7 @@ * published by the Free Software Foundation. */ -#include - struct timeriomem_rng_data { - struct completion completion; - unsigned int present:1; - void __iomem *address; /* measures in usecs */ -- cgit v1.2.3 From e162b2f835eeda0d255bd463753b5eb823735205 Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Fri, 12 Apr 2013 02:24:06 +0000 Subject: jbd: use kmem_cache_zalloc instead of kmem_cache_alloc/memset Now jbd_alloc_handle is only called by new_handle. So this commit uses kmem_cache_zalloc instead of kmem_cache_alloc/memset. Signed-off-by: Zheng Liu Signed-off-by: Jan Kara --- include/linux/jbd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index c8f32975f0e4..7e0b622503c4 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -887,7 +887,7 @@ extern struct kmem_cache *jbd_handle_cache; static inline handle_t *jbd_alloc_handle(gfp_t gfp_flags) { - return kmem_cache_alloc(jbd_handle_cache, gfp_flags); + return kmem_cache_zalloc(jbd_handle_cache, gfp_flags); } static inline void jbd_free_handle(handle_t *handle) -- cgit v1.2.3 From 25f55d9d01ad7a7ad248fd5af1d22675ffd202c5 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Tue, 23 Apr 2013 16:59:02 +0200 Subject: sched: Fix init NOHZ_IDLE flag On my SMP platform which is made of 5 cores in 2 clusters, I have the nr_busy_cpu field of sched_group_power struct that is not null when the platform is fully idle - which makes the scheduler unhappy. The root cause is: During the boot sequence, some CPUs reach the idle loop and set their NOHZ_IDLE flag while waiting for others CPUs to boot. But the nr_busy_cpus field is initialized later with the assumption that all CPUs are in the busy state whereas some CPUs have already set their NOHZ_IDLE flag. More generally, the NOHZ_IDLE flag must be initialized when new sched_domains are created in order to ensure that NOHZ_IDLE and nr_busy_cpus are aligned. This condition can be ensured by adding a synchronize_rcu() between the destruction of old sched_domains and the creation of new ones so the NOHZ_IDLE flag will not be updated with old sched_domain once it has been initialized. But this solution introduces a additionnal latency in the rebuild sequence that is called during cpu hotplug. As suggested by Frederic Weisbecker, another solution is to have the same rcu lifecycle for both NOHZ_IDLE and sched_domain struct. A new nohz_idle field is added to sched_domain so both status and sched_domain will share the same RCU lifecycle and will be always synchronized. In addition, there is no more need to protect nohz_idle against concurrent access as it is only modified by 2 exclusive functions called by local cpu. This solution has been prefered to the creation of a new struct with an extra pointer indirection for sched_domain. The synchronization is done at the cost of : - An additional indirection and a rcu_dereference for accessing nohz_idle. - We use only the nohz_idle field of the top sched_domain. Signed-off-by: Vincent Guittot Acked-by: Peter Zijlstra Cc: linaro-kernel@lists.linaro.org Cc: peterz@infradead.org Cc: fweisbec@gmail.com Cc: pjt@google.com Cc: rostedt@goodmis.org Cc: efault@gmx.de Link: http://lkml.kernel.org/r/1366729142-14662-1-git-send-email-vincent.guittot@linaro.org [ Fixed !NO_HZ build bug. ] Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6bdaa73ede13..a25168f4ab86 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -808,6 +808,8 @@ struct sched_domain { unsigned int wake_idx; unsigned int forkexec_idx; unsigned int smt_gain; + + int nohz_idle; /* NOHZ IDLE status */ int flags; /* See SD_* */ int level; -- cgit v1.2.3 From 99f4c6b66a9ae362d21e6df95d04bc74e04d285e Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 26 Apr 2013 17:23:26 +0200 Subject: mfd: si476x: Don't use 0bNNN This doesn't compile with sparc64 gcc-3.4.5. Cc: Hans Verkuil Cc: Sam Ravnborg Cc: Andrey Smirnov Signed-off-by: Andrew Morton Signed-off-by: Samuel Ortiz --- include/linux/mfd/si476x-core.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/si476x-core.h b/include/linux/mfd/si476x-core.h index ede3022c03c4..ba89b94e4a56 100644 --- a/include/linux/mfd/si476x-core.h +++ b/include/linux/mfd/si476x-core.h @@ -515,11 +515,11 @@ enum si476x_fm_receiver_properties { }; enum si476x_prop_audio_pwr_line_filter_bits { - SI476X_PROP_PWR_HARMONICS_MASK = 0b0000000000011111, - SI476X_PROP_PWR_GRID_MASK = 0b0000000100000000, - SI476X_PROP_PWR_ENABLE_MASK = 0b0000001000000000, - SI476X_PROP_PWR_GRID_50HZ = 0b0000000000000000, - SI476X_PROP_PWR_GRID_60HZ = 0b0000000100000000, + SI476X_PROP_PWR_HARMONICS_MASK = 0x001f, + SI476X_PROP_PWR_GRID_MASK = 0x0100, + SI476X_PROP_PWR_ENABLE_MASK = 0x0200, + SI476X_PROP_PWR_GRID_50HZ = 0x0000, + SI476X_PROP_PWR_GRID_60HZ = 0x0100, }; enum si476x_prop_fm_rds_config_bits { -- cgit v1.2.3 From 33d90ac0581ce81d1ebfc51918a2757e41a6011c Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 11 Apr 2013 15:06:36 -0400 Subject: SUNRPC: allow disabling idle timeout In the gss-proxy case we don't want to have to reconnect at random--we want to connect only on gss-proxy startup when we can steal gss-proxy's context to do the connect in the right namespace. So, provide a flag that allows the rpc_create caller to turn off the idle timeout. Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/clnt.h | 1 + include/linux/sunrpc/xprt.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index e7d492ce7c18..bfe11be81f6f 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -125,6 +125,7 @@ struct rpc_create_args { #define RPC_CLNT_CREATE_DISCRTRY (1UL << 5) #define RPC_CLNT_CREATE_QUIET (1UL << 6) #define RPC_CLNT_CREATE_INFINITE_SLOTS (1UL << 7) +#define RPC_CLNT_CREATE_NO_IDLE_TIMEOUT (1UL << 8) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index ff5392421cb2..cec7b9b5e1bf 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -256,6 +256,7 @@ static inline int bc_prealloc(struct rpc_rqst *req) #endif /* CONFIG_SUNRPC_BACKCHANNEL */ #define XPRT_CREATE_INFINITE_SLOTS (1U) +#define XPRT_CREATE_NO_IDLE_TIMEOUT (1U << 1) struct xprt_create { int ident; /* XPRT_TRANSPORT identifier */ -- cgit v1.2.3 From 400f26b542e86995662a0cc5483656b7b1f42af6 Mon Sep 17 00:00:00 2001 From: Simo Sorce Date: Fri, 25 May 2012 18:09:53 -0400 Subject: SUNRPC: conditionally return endtime from import_sec_context We expose this parameter for a future caller. It will be used to extract the endtime from the gss-proxy upcall mechanism, in order to set the rsc cache expiration time. Signed-off-by: Simo Sorce Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/gss_api.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index a19e2547ae6a..04d03bb2de5d 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -37,6 +37,7 @@ int gss_import_sec_context( size_t bufsize, struct gss_api_mech *mech, struct gss_ctx **ctx_id, + time_t *endtime, gfp_t gfp_mask); u32 gss_get_mic( struct gss_ctx *ctx_id, @@ -92,6 +93,7 @@ struct gss_api_ops { const void *input_token, size_t bufsize, struct gss_ctx *ctx_id, + time_t *endtime, gfp_t gfp_mask); u32 (*gss_get_mic)( struct gss_ctx *ctx_id, -- cgit v1.2.3 From 8175e5b79c38a1d85225da516fa1a0ecbf2fdbca Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 15 Apr 2013 10:42:33 +0200 Subject: KVM: Add KVM_IRQCHIP_NUM_PINS in addition to KVM_IOAPIC_NUM_PINS The concept of routing interrupt lines to an irqchip is nothing that is IOAPIC specific. Every irqchip has a maximum number of pins that can be linked to irq lines. So let's add a new define that allows us to reuse generic code for non-IOAPIC platforms. Signed-off-by: Alexander Graf Acked-by: Michael S. Tsirkin --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 93a50054d46c..bf3b1dcb8b3d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -307,7 +307,7 @@ struct kvm_kernel_irq_routing_entry { #ifdef __KVM_HAVE_IOAPIC struct kvm_irq_routing_table { - int chip[KVM_NR_IRQCHIPS][KVM_IOAPIC_NUM_PINS]; + int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS]; struct kvm_kernel_irq_routing_entry *rt_entries; u32 nr_rt_entries; /* -- cgit v1.2.3 From a725d56a02ec3582bb5b9756f261fdc6962c79ee Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Wed, 17 Apr 2013 13:29:30 +0200 Subject: KVM: Introduce CONFIG_HAVE_KVM_IRQ_ROUTING Quite a bit of code in KVM has been conditionalized on availability of IOAPIC emulation. However, most of it is generically applicable to platforms that don't have an IOPIC, but a different type of irq chip. Make code that only relies on IRQ routing, not an APIC itself, on CONFIG_HAVE_KVM_IRQ_ROUTING, so that we can reuse it later. Signed-off-by: Alexander Graf Acked-by: Michael S. Tsirkin --- include/linux/kvm_host.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bf3b1dcb8b3d..4215d4f3d86f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -304,7 +304,7 @@ struct kvm_kernel_irq_routing_entry { struct hlist_node link; }; -#ifdef __KVM_HAVE_IOAPIC +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING struct kvm_irq_routing_table { int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS]; @@ -432,7 +432,7 @@ void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); int __must_check vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); -#ifdef __KVM_HAVE_IOAPIC +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING int kvm_irqfd_init(void); void kvm_irqfd_exit(void); #else @@ -957,7 +957,7 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) } #endif -#ifdef KVM_CAP_IRQ_ROUTING +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING #define KVM_MAX_IRQ_ROUTES 1024 -- cgit v1.2.3 From 7eee2efdc6978aa70ab4046394128c1a10bc2d80 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 15 Apr 2013 10:50:54 +0200 Subject: KVM: Remove kvm_get_intr_delivery_bitmask The prototype has been stale for a while, I can't spot any real function define behind it. Let's just remove it. Signed-off-by: Alexander Graf Acked-by: Michael S. Tsirkin --- include/linux/kvm_host.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4215d4f3d86f..a7bfe9d3aa5e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -719,11 +719,6 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, bool mask); -#ifdef __KVM_HAVE_IOAPIC -void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, - union kvm_ioapic_redirect_entry *entry, - unsigned long *deliver_bitmask); -#endif int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status); int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level); -- cgit v1.2.3 From e8cde0939d8ebe9c8ebe5a4bdf71af51a0d56053 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Mon, 15 Apr 2013 23:23:21 +0200 Subject: KVM: Move irq routing setup to irqchip.c Setting up IRQ routes is nothing IOAPIC specific. Extract everything that really is generic code into irqchip.c and only leave the ioapic specific bits to irq_comm.c. Signed-off-by: Alexander Graf Acked-by: Michael S. Tsirkin --- include/linux/kvm_host.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a7bfe9d3aa5e..dcef724f4ba6 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -961,6 +961,9 @@ int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, unsigned flags); +int kvm_set_routing_entry(struct kvm_irq_routing_table *rt, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue); void kvm_free_irq_routing(struct kvm *kvm); int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); -- cgit v1.2.3 From 852b6d57dc7fa378019786fa84727036e56839ea Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Fri, 12 Apr 2013 14:08:42 +0000 Subject: kvm: add device control API Currently, devices that are emulated inside KVM are configured in a hardcoded manner based on an assumption that any given architecture only has one way to do it. If there's any need to access device state, it is done through inflexible one-purpose-only IOCTLs (e.g. KVM_GET/SET_LAPIC). Defining new IOCTLs for every little thing is cumbersome and depletes a limited numberspace. This API provides a mechanism to instantiate a device of a certain type, returning an ID that can be used to set/get attributes of the device. Attributes may include configuration parameters (e.g. register base address), device state, operational commands, etc. It is similar to the ONE_REG API, except that it acts on devices rather than vcpus. Both device types and individual attributes can be tested without having to create the device or get/set the attribute, without the need for separately managing enumerated capabilities. Signed-off-by: Scott Wood Signed-off-by: Alexander Graf --- include/linux/kvm_host.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index dcef724f4ba6..6dab6b5b3e3b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1064,6 +1064,41 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) extern bool kvm_rebooting; +struct kvm_device_ops; + +struct kvm_device { + struct kvm_device_ops *ops; + struct kvm *kvm; + atomic_t users; + void *private; +}; + +/* create, destroy, and name are mandatory */ +struct kvm_device_ops { + const char *name; + int (*create)(struct kvm_device *dev, u32 type); + + /* + * Destroy is responsible for freeing dev. + * + * Destroy may be called before or after destructors are called + * on emulated I/O regions, depending on whether a reference is + * held by a vcpu or other kvm component that gets destroyed + * after the emulated I/O. + */ + void (*destroy)(struct kvm_device *dev); + + int (*set_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); + int (*get_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); + int (*has_attr)(struct kvm_device *dev, struct kvm_device_attr *attr); + long (*ioctl)(struct kvm_device *dev, unsigned int ioctl, + unsigned long arg); +}; + +void kvm_device_get(struct kvm_device *dev); +void kvm_device_put(struct kvm_device *dev); +struct kvm_device *kvm_device_from_filp(struct file *filp); + #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) -- cgit v1.2.3 From 5df554ad5b7522ea62b0ff9d5be35183494efc21 Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Fri, 12 Apr 2013 14:08:46 +0000 Subject: kvm/ppc/mpic: in-kernel MPIC emulation Hook the MPIC code up to the KVM interfaces, add locking, etc. Signed-off-by: Scott Wood [agraf: add stub function for kvmppc_mpic_set_epr, non-booke, 64bit] Signed-off-by: Alexander Graf --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 6dab6b5b3e3b..feffbdaf8986 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1099,6 +1099,8 @@ void kvm_device_get(struct kvm_device *dev); void kvm_device_put(struct kvm_device *dev); struct kvm_device *kvm_device_from_filp(struct file *filp); +extern struct kvm_device_ops kvm_mpic_ops; + #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val) -- cgit v1.2.3 From 07f0a7bdec5c4039cfb9b836482c45004d4c21cc Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Thu, 25 Apr 2013 14:11:23 +0000 Subject: kvm: destroy emulated devices on VM exit The hassle of getting refcounting right was greater than the hassle of keeping a list of devices to destroy on VM exit. Signed-off-by: Scott Wood Signed-off-by: Alexander Graf --- include/linux/kvm_host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index feffbdaf8986..36c977694741 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -393,6 +393,7 @@ struct kvm { long mmu_notifier_count; #endif long tlbs_dirty; + struct list_head devices; }; #define kvm_err(fmt, ...) \ @@ -1069,8 +1070,8 @@ struct kvm_device_ops; struct kvm_device { struct kvm_device_ops *ops; struct kvm *kvm; - atomic_t users; void *private; + struct list_head vm_node; }; /* create, destroy, and name are mandatory */ -- cgit v1.2.3 From d44ada516277f5d58b9bda2ea0a2c9503b316bbf Mon Sep 17 00:00:00 2001 From: Eduardo Valentin Date: Wed, 17 Apr 2013 17:12:23 +0000 Subject: thermal: cpu_cooling: improve line breaking To improve code readiness, change the way the lines are broken in this file. Signed-off-by: Eduardo Valentin Signed-off-by: Zhang Rui --- include/linux/cpu_cooling.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index f48f6fbcd3be..282e27028418 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -32,8 +32,8 @@ * cpufreq_cooling_register - function to create cpufreq cooling device. * @clip_cpus: cpumask of cpus where the frequency constraints will happen */ -struct thermal_cooling_device *cpufreq_cooling_register( - const struct cpumask *clip_cpus); +struct thermal_cooling_device * +cpufreq_cooling_register(const struct cpumask *clip_cpus); /** * cpufreq_cooling_unregister - function to remove cpufreq cooling device. @@ -43,18 +43,18 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); unsigned long cpufreq_cooling_get_level(unsigned int, unsigned int); #else /* !CONFIG_CPU_THERMAL */ -static inline struct thermal_cooling_device *cpufreq_cooling_register( - const struct cpumask *clip_cpus) +static inline struct thermal_cooling_device * +cpufreq_cooling_register(const struct cpumask *clip_cpus) { return NULL; } -static inline void cpufreq_cooling_unregister( - struct thermal_cooling_device *cdev) +static inline +void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { return; } -static inline unsigned long cpufreq_cooling_get_level(unsigned int, - unsigned int) +static inline +unsigned long cpufreq_cooling_get_level(unsigned int, unsigned int) { return THERMAL_CSTATE_INVALID; } -- cgit v1.2.3 From 8f7ba3ca12f6f16526fa4a8aaf2cae91563eee69 Mon Sep 17 00:00:00 2001 From: Rony Efraim Date: Thu, 25 Apr 2013 05:22:27 +0000 Subject: net/mlx4: Add set VF mac address support Add ndo_set_vf_mac support which allows to set the MAC address for mlx4 VF Ethernet NICs from the host. Signed-off-by: Rony Efraim Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 260695186256..f21ddc6203bd 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -232,6 +232,7 @@ struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev); void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox); u32 mlx4_comm_get_version(void); +int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8) -- cgit v1.2.3 From 3f7fb021d081c8aaac1d0cf69a288d21625e872e Mon Sep 17 00:00:00 2001 From: Rony Efraim Date: Thu, 25 Apr 2013 05:22:28 +0000 Subject: net/mlx4: Add set VF default vlan ID and priority support Add support to ndo_set_vf_vlan in the driver. Once this call is used the vport is considered to be in VST mode. In this mode, the PPF driver configures Ethernet QPs created by this VF to use this vlan id and priority. Currently RoCE isn't supported on that mode. The special values of VID=4095 or VID=0,UP=0 are considered as VGT. Signed-off-by: Rony Efraim Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 2 ++ include/linux/mlx4/device.h | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index f21ddc6203bd..7daead75a6f5 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -233,6 +233,8 @@ void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbo u32 mlx4_comm_get_version(void); int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); +int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos); + #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8) diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 2fbc1464b53b..6606d8f5862a 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -155,7 +155,8 @@ enum { MLX4_DEV_CAP_FLAG2_RSS_XOR = 1LL << 2, MLX4_DEV_CAP_FLAG2_FS_EN = 1LL << 3, MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN = 1LL << 4, - MLX4_DEV_CAP_FLAG2_TS = 1LL << 5 + MLX4_DEV_CAP_FLAG2_TS = 1LL << 5, + MLX4_DEV_CAP_FLAG2_VLAN_CONTROL = 1LL << 6 }; enum { -- cgit v1.2.3 From e6b6a2316379feebebacec0979b3ebc5743e7502 Mon Sep 17 00:00:00 2001 From: Rony Efraim Date: Thu, 25 Apr 2013 05:22:29 +0000 Subject: net/mlx4: Add VF MAC spoof checking support Add ndo_set_vf_spoofchk support Signed-off-by: Rony Efraim Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 1 + include/linux/mlx4/device.h | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 7daead75a6f5..95c3223719fa 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -234,6 +234,7 @@ void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbo u32 mlx4_comm_get_version(void); int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos); +int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting); #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8) diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 6606d8f5862a..53acaf64189f 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -156,7 +156,8 @@ enum { MLX4_DEV_CAP_FLAG2_FS_EN = 1LL << 3, MLX4_DEV_CAP_FLAGS2_REASSIGN_MAC_EN = 1LL << 4, MLX4_DEV_CAP_FLAG2_TS = 1LL << 5, - MLX4_DEV_CAP_FLAG2_VLAN_CONTROL = 1LL << 6 + MLX4_DEV_CAP_FLAG2_VLAN_CONTROL = 1LL << 6, + MLX4_DEV_CAP_FLAG2_FSM = 1LL << 7 }; enum { -- cgit v1.2.3 From 2cccb9e4f3476da916146c2ec571c4f3eff738b1 Mon Sep 17 00:00:00 2001 From: Rony Efraim Date: Thu, 25 Apr 2013 05:22:30 +0000 Subject: net/mlx4: Add support to get VF config Support getting VF config. Signed-off-by: Rony Efraim Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 95c3223719fa..adf6e0648f20 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -34,6 +34,7 @@ #define MLX4_CMD_H #include +#include enum { /* initialization and general commands */ @@ -235,6 +236,7 @@ u32 mlx4_comm_get_version(void); int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac); int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos); int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting); +int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_info *ivf); #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8) -- cgit v1.2.3 From 730dca42c1d363c939da18c1499c7327c66e2b37 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Sun, 28 Apr 2013 10:50:52 +0200 Subject: KVM: x86: Rework request for immediate exit The VMX implementation of enable_irq_window raised KVM_REQ_IMMEDIATE_EXIT after we checked it in vcpu_enter_guest. This caused infinite loops on vmentry. Fix it by letting enable_irq_window signal the need for an immediate exit via its return value and drop KVM_REQ_IMMEDIATE_EXIT. This issue only affects nested VMX scenarios. Signed-off-by: Jan Kiszka Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 93a50054d46c..7bde42470e37 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -119,14 +119,13 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_APF_HALT 12 #define KVM_REQ_STEAL_UPDATE 13 #define KVM_REQ_NMI 14 -#define KVM_REQ_IMMEDIATE_EXIT 15 -#define KVM_REQ_PMU 16 -#define KVM_REQ_PMI 17 -#define KVM_REQ_WATCHDOG 18 -#define KVM_REQ_MASTERCLOCK_UPDATE 19 -#define KVM_REQ_MCLOCK_INPROGRESS 20 -#define KVM_REQ_EPR_EXIT 21 -#define KVM_REQ_SCAN_IOAPIC 22 +#define KVM_REQ_PMU 15 +#define KVM_REQ_PMI 16 +#define KVM_REQ_WATCHDOG 17 +#define KVM_REQ_MASTERCLOCK_UPDATE 18 +#define KVM_REQ_MCLOCK_INPROGRESS 19 +#define KVM_REQ_EPR_EXIT 20 +#define KVM_REQ_SCAN_IOAPIC 21 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 -- cgit v1.2.3 From 2a5bab1004729f3302c776e53ee7c895b98bb1ce Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Tue, 16 Apr 2013 13:49:18 -0600 Subject: kvm: Allow build-time configuration of KVM device assignment We hope to at some point deprecate KVM legacy device assignment in favor of VFIO-based assignment. Towards that end, allow legacy device assignment to be deconfigured. Signed-off-by: Alex Williamson Reviewed-by: Alexander Graf Acked-by: Michael S. Tsirkin Signed-off-by: Gleb Natapov --- include/linux/kvm_host.h | 30 ++++++++---------------------- 1 file changed, 8 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 309774715897..996661eb8e99 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -667,7 +667,6 @@ static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); -void kvm_free_all_assigned_devices(struct kvm *kvm); void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); @@ -736,7 +735,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); /* For vcpu->arch.iommu_flags */ #define KVM_IOMMU_CACHE_COHERENCY 0x1 -#ifdef CONFIG_IOMMU_API +#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot); int kvm_iommu_map_guest(struct kvm *kvm); @@ -745,7 +744,7 @@ int kvm_assign_device(struct kvm *kvm, struct kvm_assigned_dev_kernel *assigned_dev); int kvm_deassign_device(struct kvm *kvm, struct kvm_assigned_dev_kernel *assigned_dev); -#else /* CONFIG_IOMMU_API */ +#else static inline int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) { @@ -757,28 +756,11 @@ static inline void kvm_iommu_unmap_pages(struct kvm *kvm, { } -static inline int kvm_iommu_map_guest(struct kvm *kvm) -{ - return -ENODEV; -} - static inline int kvm_iommu_unmap_guest(struct kvm *kvm) { return 0; } - -static inline int kvm_assign_device(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - return 0; -} - -static inline int kvm_deassign_device(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - return 0; -} -#endif /* CONFIG_IOMMU_API */ +#endif static inline void __guest_enter(void) { @@ -1032,11 +1014,13 @@ static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; } #endif -#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT +#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, unsigned long arg); +void kvm_free_all_assigned_devices(struct kvm *kvm); + #else static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, @@ -1045,6 +1029,8 @@ static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, return -ENOTTY; } +static inline void kvm_free_all_assigned_devices(struct kvm *kvm) {} + #endif static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) -- cgit v1.2.3 From e8d9612c181b1a68ba5f71384629343466f1bd13 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 25 Apr 2013 06:53:54 +0000 Subject: sock_diag: allow to dump bpf filters This patch allows to dump BPF filters attached to a socket with SO_ATTACH_FILTER. Note that we check CAP_SYS_ADMIN before allowing to dump this info. For now, only AF_PACKET sockets use this feature. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/sock_diag.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index e8d702e0fd89..54f91d35e5fd 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -1,6 +1,7 @@ #ifndef __SOCK_DIAG_H__ #define __SOCK_DIAG_H__ +#include #include struct sk_buff; @@ -22,5 +23,7 @@ int sock_diag_check_cookie(void *sk, __u32 *cookie); void sock_diag_save_cookie(void *sk, __u32 *cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); +int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, + struct sk_buff *skb, int attrtype); #endif -- cgit v1.2.3 From 5f5624cf156283687e11ea329c7a0523c677ea0e Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 25 Apr 2013 11:08:30 +0000 Subject: ipv6: Kill ipv6 dependency of icmpv6_send(). Following patch adds icmp-registration module for ipv6. It allows ipv6 protocol to register icmp_sender which is used for sending ipv6 icmp msgs. This extra layer allows us to kill ipv6 dependency for sending icmp packets. This patch also fixes ip_tunnel compilation problem when ip_tunnel is statically compiled in kernel but ipv6 is module Signed-off-by: Pravin B Shelar Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index b4f6c29caced..630f45335c73 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -11,9 +11,21 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) #include -extern void icmpv6_send(struct sk_buff *skb, - u8 type, u8 code, - __u32 info); +#if IS_ENABLED(CONFIG_IPV6) +extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info); + +typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info); +extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); +extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); + +#else + +static inline void icmpv6_send(struct sk_buff *skb, + u8 type, u8 code, __u32 info) +{ + +} +#endif extern int icmpv6_init(void); extern int icmpv6_err_convert(u8 type, u8 code, -- cgit v1.2.3 From 43c56e595bb81319230affd545392536c933317e Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 8 Apr 2013 21:51:25 +0200 Subject: netfilter: ipset: Make possible to test elements marked with nomatch Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 7958e84a65af..970187187f5b 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -200,6 +200,14 @@ ip_set_eexist(int ret, u32 flags) return ret == -IPSET_ERR_EXIST && (flags & IPSET_FLAG_EXIST); } +/* Match elements marked with nomatch */ +static inline bool +ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt) +{ + return adt == IPSET_TEST && + ret == -ENOTEMPTY && ((flags >> 16) & IPSET_FLAG_NOMATCH); +} + /* Check the NLA_F_NET_BYTEORDER flag */ static inline bool ip_set_attr_netorder(struct nlattr *tb[], int type) -- cgit v1.2.3 From 8672d4d1a00b59057bb1f9659259967d2a19e086 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 8 Apr 2013 20:54:37 +0200 Subject: netfilter: ipset: Move often used IPv6 address masking function to header file Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/pfxlen.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/pfxlen.h b/include/linux/netfilter/ipset/pfxlen.h index 199fd11fedc0..1afbb94b4b65 100644 --- a/include/linux/netfilter/ipset/pfxlen.h +++ b/include/linux/netfilter/ipset/pfxlen.h @@ -41,4 +41,13 @@ do { \ to = from | ~ip_set_hostmask(cidr); \ } while (0) +static inline void +ip6_netmask(union nf_inet_addr *ip, u8 prefix) +{ + ip->ip6[0] &= ip_set_netmask6(prefix)[0]; + ip->ip6[1] &= ip_set_netmask6(prefix)[1]; + ip->ip6[2] &= ip_set_netmask6(prefix)[2]; + ip->ip6[3] &= ip_set_netmask6(prefix)[3]; +} + #endif /*_PFXLEN_H */ -- cgit v1.2.3 From 075e64c041b5d3c29651965608e1e76505e01d54 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Sat, 27 Apr 2013 14:28:55 +0200 Subject: netfilter: ipset: Introduce extensions to elements in the core Introduce extensions to elements in the core and prepare timeout as the first one. This patch also modifies the em_ipset classifier to use the new extension struct layout. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 46 +++++++++-- include/linux/netfilter/ipset/ip_set_timeout.h | 102 ++++++------------------- 2 files changed, 61 insertions(+), 87 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 970187187f5b..bf0220cbf46a 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -1,7 +1,7 @@ /* Copyright (C) 2000-2002 Joakim Axelsson * Patrick Schaaf * Martin Josefsson - * Copyright (C) 2003-2011 Jozsef Kadlecsik + * Copyright (C) 2003-2013 Jozsef Kadlecsik * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -47,10 +47,30 @@ enum ip_set_feature { IPSET_DUMP_LAST = (1 << IPSET_DUMP_LAST_FLAG), }; +/* Set extensions */ +enum ip_set_extension { + IPSET_EXT_NONE = 0, + IPSET_EXT_BIT_TIMEOUT = 1, + IPSET_EXT_TIMEOUT = (1 << IPSET_EXT_BIT_TIMEOUT), +}; + +/* Extension offsets */ +enum ip_set_offset { + IPSET_OFFSET_TIMEOUT = 0, + IPSET_OFFSET_MAX, +}; + +#define SET_WITH_TIMEOUT(s) ((s)->extensions & IPSET_EXT_TIMEOUT) + +struct ip_set_ext { + unsigned long timeout; +}; + struct ip_set; typedef int (*ipset_adtfn)(struct ip_set *set, void *value, - u32 timeout, u32 flags); + const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); /* Kernel API function options */ struct ip_set_adt_opt { @@ -58,7 +78,7 @@ struct ip_set_adt_opt { u8 dim; /* Dimension of match/target */ u8 flags; /* Direction and negation flags */ u32 cmdflags; /* Command-like flags */ - u32 timeout; /* Timeout value */ + struct ip_set_ext ext; /* Extensions */ }; /* Set type, variant-specific part */ @@ -69,7 +89,7 @@ struct ip_set_type_variant { * positive for matching element */ int (*kadt)(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, - enum ipset_adt adt, const struct ip_set_adt_opt *opt); + enum ipset_adt adt, struct ip_set_adt_opt *opt); /* Userspace: test/add/del entries * returns negative error code, @@ -151,6 +171,8 @@ struct ip_set { u8 family; /* The type revision */ u8 revision; + /* Extensions */ + u8 extensions; /* The type specific data */ void *data; }; @@ -167,19 +189,21 @@ extern void ip_set_nfnl_put(ip_set_id_t index); extern int ip_set_add(ip_set_id_t id, const struct sk_buff *skb, const struct xt_action_param *par, - const struct ip_set_adt_opt *opt); + struct ip_set_adt_opt *opt); extern int ip_set_del(ip_set_id_t id, const struct sk_buff *skb, const struct xt_action_param *par, - const struct ip_set_adt_opt *opt); + struct ip_set_adt_opt *opt); extern int ip_set_test(ip_set_id_t id, const struct sk_buff *skb, const struct xt_action_param *par, - const struct ip_set_adt_opt *opt); + struct ip_set_adt_opt *opt); /* Utility functions */ extern void *ip_set_alloc(size_t size); extern void ip_set_free(void *members); extern int ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr); extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr); +extern int ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[], + struct ip_set_ext *ext); static inline int ip_set_get_hostipaddr4(struct nlattr *nla, u32 *ipaddr) @@ -292,4 +316,12 @@ bitmap_bytes(u32 a, u32 b) return 4 * ((((b - a + 8) / 8) + 3) / 4); } +#include + +#define IP_SET_INIT_KEXT(skb, opt, map) \ + { .timeout = ip_set_adt_opt_timeout(opt, map) } + +#define IP_SET_INIT_UEXT(map) \ + { .timeout = (map)->timeout } + #endif /*_IP_SET_H */ diff --git a/include/linux/netfilter/ipset/ip_set_timeout.h b/include/linux/netfilter/ipset/ip_set_timeout.h index 41d9cfa08167..3aac04167ca7 100644 --- a/include/linux/netfilter/ipset/ip_set_timeout.h +++ b/include/linux/netfilter/ipset/ip_set_timeout.h @@ -1,7 +1,7 @@ #ifndef _IP_SET_TIMEOUT_H #define _IP_SET_TIMEOUT_H -/* Copyright (C) 2003-2011 Jozsef Kadlecsik +/* Copyright (C) 2003-2013 Jozsef Kadlecsik * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -17,13 +17,14 @@ #define IPSET_GC_PERIOD(timeout) \ ((timeout/3) ? min_t(u32, (timeout)/3, IPSET_GC_TIME) : 1) -/* Set is defined without timeout support: timeout value may be 0 */ -#define IPSET_NO_TIMEOUT UINT_MAX +/* Entry is set with no timeout value */ +#define IPSET_ELEM_PERMANENT 0 -#define with_timeout(timeout) ((timeout) != IPSET_NO_TIMEOUT) +/* Set is defined with timeout support: timeout value may be 0 */ +#define IPSET_NO_TIMEOUT UINT_MAX -#define opt_timeout(opt, map) \ - (with_timeout((opt)->timeout) ? (opt)->timeout : (map)->timeout) +#define ip_set_adt_opt_timeout(opt, map) \ +((opt)->ext.timeout != IPSET_NO_TIMEOUT ? (opt)->ext.timeout : (map)->timeout) static inline unsigned int ip_set_timeout_uget(struct nlattr *tb) @@ -38,61 +39,6 @@ ip_set_timeout_uget(struct nlattr *tb) return timeout == IPSET_NO_TIMEOUT ? IPSET_NO_TIMEOUT - 1 : timeout; } -#ifdef IP_SET_BITMAP_TIMEOUT - -/* Bitmap specific timeout constants and macros for the entries */ - -/* Bitmap entry is unset */ -#define IPSET_ELEM_UNSET 0 -/* Bitmap entry is set with no timeout value */ -#define IPSET_ELEM_PERMANENT (UINT_MAX/2) - -static inline bool -ip_set_timeout_test(unsigned long timeout) -{ - return timeout != IPSET_ELEM_UNSET && - (timeout == IPSET_ELEM_PERMANENT || - time_is_after_jiffies(timeout)); -} - -static inline bool -ip_set_timeout_expired(unsigned long timeout) -{ - return timeout != IPSET_ELEM_UNSET && - timeout != IPSET_ELEM_PERMANENT && - time_is_before_jiffies(timeout); -} - -static inline unsigned long -ip_set_timeout_set(u32 timeout) -{ - unsigned long t; - - if (!timeout) - return IPSET_ELEM_PERMANENT; - - t = msecs_to_jiffies(timeout * 1000) + jiffies; - if (t == IPSET_ELEM_UNSET || t == IPSET_ELEM_PERMANENT) - /* Bingo! */ - t++; - - return t; -} - -static inline u32 -ip_set_timeout_get(unsigned long timeout) -{ - return timeout == IPSET_ELEM_PERMANENT ? 0 : - jiffies_to_msecs(timeout - jiffies)/1000; -} - -#else - -/* Hash specific timeout constants and macros for the entries */ - -/* Hash entry is set with no timeout value */ -#define IPSET_ELEM_PERMANENT 0 - static inline bool ip_set_timeout_test(unsigned long timeout) { @@ -101,36 +47,32 @@ ip_set_timeout_test(unsigned long timeout) } static inline bool -ip_set_timeout_expired(unsigned long timeout) +ip_set_timeout_expired(unsigned long *timeout) { - return timeout != IPSET_ELEM_PERMANENT && - time_is_before_jiffies(timeout); + return *timeout != IPSET_ELEM_PERMANENT && + time_is_before_jiffies(*timeout); } -static inline unsigned long -ip_set_timeout_set(u32 timeout) +static inline void +ip_set_timeout_set(unsigned long *timeout, u32 t) { - unsigned long t; - - if (!timeout) - return IPSET_ELEM_PERMANENT; + if (!t) { + *timeout = IPSET_ELEM_PERMANENT; + return; + } - t = msecs_to_jiffies(timeout * 1000) + jiffies; - if (t == IPSET_ELEM_PERMANENT) + *timeout = msecs_to_jiffies(t * 1000) + jiffies; + if (*timeout == IPSET_ELEM_PERMANENT) /* Bingo! :-) */ - t++; - - return t; + (*timeout)--; } static inline u32 -ip_set_timeout_get(unsigned long timeout) +ip_set_timeout_get(unsigned long *timeout) { - return timeout == IPSET_ELEM_PERMANENT ? 0 : - jiffies_to_msecs(timeout - jiffies)/1000; + return *timeout == IPSET_ELEM_PERMANENT ? 0 : + jiffies_to_msecs(*timeout - jiffies)/1000; } -#endif /* ! IP_SET_BITMAP_TIMEOUT */ #endif /* __KERNEL__ */ - #endif /* _IP_SET_TIMEOUT_H */ -- cgit v1.2.3 From 4d73de38c256623b324474098f7d2bb4e97f7cf0 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 8 Apr 2013 21:00:52 +0200 Subject: netfilter: ipset: Unified bitmap type generation Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_bitmap.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_bitmap.h b/include/linux/netfilter/ipset/ip_set_bitmap.h index 1a30646d5be8..5e4662a71e01 100644 --- a/include/linux/netfilter/ipset/ip_set_bitmap.h +++ b/include/linux/netfilter/ipset/ip_set_bitmap.h @@ -5,6 +5,12 @@ #define IPSET_BITMAP_MAX_RANGE 0x0000FFFF +enum { + IPSET_ADD_FAILED = 1, + IPSET_ADD_STORE_PLAIN_TIMEOUT, + IPSET_ADD_START_STORED_TIMEOUT, +}; + /* Common functions */ static inline u32 -- cgit v1.2.3 From 1feab10d7e6ddb5e13d6a4bd93a1b877390262ec Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 8 Apr 2013 21:05:44 +0200 Subject: netfilter: ipset: Unified hash type generation Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_ahash.h | 1241 -------------------------- 1 file changed, 1241 deletions(-) delete mode 100644 include/linux/netfilter/ipset/ip_set_ahash.h (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h deleted file mode 100644 index 0214c4c146fa..000000000000 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ /dev/null @@ -1,1241 +0,0 @@ -#ifndef _IP_SET_AHASH_H -#define _IP_SET_AHASH_H - -#include -#include -#include - -#define CONCAT(a, b, c) a##b##c -#define TOKEN(a, b, c) CONCAT(a, b, c) - -#define type_pf_next TOKEN(TYPE, PF, _elem) - -/* Hashing which uses arrays to resolve clashing. The hash table is resized - * (doubled) when searching becomes too long. - * Internally jhash is used with the assumption that the size of the - * stored data is a multiple of sizeof(u32). If storage supports timeout, - * the timeout field must be the last one in the data structure - that field - * is ignored when computing the hash key. - * - * Readers and resizing - * - * Resizing can be triggered by userspace command only, and those - * are serialized by the nfnl mutex. During resizing the set is - * read-locked, so the only possible concurrent operations are - * the kernel side readers. Those must be protected by proper RCU locking. - */ - -/* Number of elements to store in an initial array block */ -#define AHASH_INIT_SIZE 4 -/* Max number of elements to store in an array block */ -#define AHASH_MAX_SIZE (3*AHASH_INIT_SIZE) - -/* Max number of elements can be tuned */ -#ifdef IP_SET_HASH_WITH_MULTI -#define AHASH_MAX(h) ((h)->ahash_max) - -static inline u8 -tune_ahash_max(u8 curr, u32 multi) -{ - u32 n; - - if (multi < curr) - return curr; - - n = curr + AHASH_INIT_SIZE; - /* Currently, at listing one hash bucket must fit into a message. - * Therefore we have a hard limit here. - */ - return n > curr && n <= 64 ? n : curr; -} -#define TUNE_AHASH_MAX(h, multi) \ - ((h)->ahash_max = tune_ahash_max((h)->ahash_max, multi)) -#else -#define AHASH_MAX(h) AHASH_MAX_SIZE -#define TUNE_AHASH_MAX(h, multi) -#endif - -/* A hash bucket */ -struct hbucket { - void *value; /* the array of the values */ - u8 size; /* size of the array */ - u8 pos; /* position of the first free entry */ -}; - -/* The hash table: the table size stored here in order to make resizing easy */ -struct htable { - u8 htable_bits; /* size of hash table == 2^htable_bits */ - struct hbucket bucket[0]; /* hashtable buckets */ -}; - -#define hbucket(h, i) (&((h)->bucket[i])) - -/* Book-keeping of the prefixes added to the set */ -struct ip_set_hash_nets { - u8 cidr; /* the different cidr values in the set */ - u32 nets; /* number of elements per cidr */ -}; - -/* The generic ip_set hash structure */ -struct ip_set_hash { - struct htable *table; /* the hash table */ - u32 maxelem; /* max elements in the hash */ - u32 elements; /* current element (vs timeout) */ - u32 initval; /* random jhash init value */ - u32 timeout; /* timeout value, if enabled */ - struct timer_list gc; /* garbage collection when timeout enabled */ - struct type_pf_next next; /* temporary storage for uadd */ -#ifdef IP_SET_HASH_WITH_MULTI - u8 ahash_max; /* max elements in an array block */ -#endif -#ifdef IP_SET_HASH_WITH_NETMASK - u8 netmask; /* netmask value for subnets to store */ -#endif -#ifdef IP_SET_HASH_WITH_RBTREE - struct rb_root rbtree; -#endif -#ifdef IP_SET_HASH_WITH_NETS - struct ip_set_hash_nets nets[0]; /* book-keeping of prefixes */ -#endif -}; - -static size_t -htable_size(u8 hbits) -{ - size_t hsize; - - /* We must fit both into u32 in jhash and size_t */ - if (hbits > 31) - return 0; - hsize = jhash_size(hbits); - if ((((size_t)-1) - sizeof(struct htable))/sizeof(struct hbucket) - < hsize) - return 0; - - return hsize * sizeof(struct hbucket) + sizeof(struct htable); -} - -/* Compute htable_bits from the user input parameter hashsize */ -static u8 -htable_bits(u32 hashsize) -{ - /* Assume that hashsize == 2^htable_bits */ - u8 bits = fls(hashsize - 1); - if (jhash_size(bits) != hashsize) - /* Round up to the first 2^n value */ - bits = fls(hashsize); - - return bits; -} - -#ifdef IP_SET_HASH_WITH_NETS -#ifdef IP_SET_HASH_WITH_NETS_PACKED -/* When cidr is packed with nomatch, cidr - 1 is stored in the entry */ -#define CIDR(cidr) (cidr + 1) -#else -#define CIDR(cidr) (cidr) -#endif - -#define SET_HOST_MASK(family) (family == AF_INET ? 32 : 128) -#ifdef IP_SET_HASH_WITH_MULTI -#define NETS_LENGTH(family) (SET_HOST_MASK(family) + 1) -#else -#define NETS_LENGTH(family) SET_HOST_MASK(family) -#endif - -/* Network cidr size book keeping when the hash stores different - * sized networks */ -static void -add_cidr(struct ip_set_hash *h, u8 cidr, u8 nets_length) -{ - int i, j; - - /* Add in increasing prefix order, so larger cidr first */ - for (i = 0, j = -1; i < nets_length && h->nets[i].nets; i++) { - if (j != -1) - continue; - else if (h->nets[i].cidr < cidr) - j = i; - else if (h->nets[i].cidr == cidr) { - h->nets[i].nets++; - return; - } - } - if (j != -1) { - for (; i > j; i--) { - h->nets[i].cidr = h->nets[i - 1].cidr; - h->nets[i].nets = h->nets[i - 1].nets; - } - } - h->nets[i].cidr = cidr; - h->nets[i].nets = 1; -} - -static void -del_cidr(struct ip_set_hash *h, u8 cidr, u8 nets_length) -{ - u8 i, j; - - for (i = 0; i < nets_length - 1 && h->nets[i].cidr != cidr; i++) - ; - h->nets[i].nets--; - - if (h->nets[i].nets != 0) - return; - - for (j = i; j < nets_length - 1 && h->nets[j].nets; j++) { - h->nets[j].cidr = h->nets[j + 1].cidr; - h->nets[j].nets = h->nets[j + 1].nets; - } -} -#else -#define NETS_LENGTH(family) 0 -#endif - -/* Destroy the hashtable part of the set */ -static void -ahash_destroy(struct htable *t) -{ - struct hbucket *n; - u32 i; - - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = hbucket(t, i); - if (n->size) - /* FIXME: use slab cache */ - kfree(n->value); - } - - ip_set_free(t); -} - -/* Calculate the actual memory size of the set data */ -static size_t -ahash_memsize(const struct ip_set_hash *h, size_t dsize, u8 nets_length) -{ - u32 i; - struct htable *t = h->table; - size_t memsize = sizeof(*h) - + sizeof(*t) -#ifdef IP_SET_HASH_WITH_NETS - + sizeof(struct ip_set_hash_nets) * nets_length -#endif - + jhash_size(t->htable_bits) * sizeof(struct hbucket); - - for (i = 0; i < jhash_size(t->htable_bits); i++) - memsize += t->bucket[i].size * dsize; - - return memsize; -} - -/* Flush a hash type of set: destroy all elements */ -static void -ip_set_hash_flush(struct ip_set *set) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - struct hbucket *n; - u32 i; - - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = hbucket(t, i); - if (n->size) { - n->size = n->pos = 0; - /* FIXME: use slab cache */ - kfree(n->value); - } - } -#ifdef IP_SET_HASH_WITH_NETS - memset(h->nets, 0, sizeof(struct ip_set_hash_nets) - * NETS_LENGTH(set->family)); -#endif - h->elements = 0; -} - -/* Destroy a hash type of set */ -static void -ip_set_hash_destroy(struct ip_set *set) -{ - struct ip_set_hash *h = set->data; - - if (with_timeout(h->timeout)) - del_timer_sync(&h->gc); - - ahash_destroy(h->table); -#ifdef IP_SET_HASH_WITH_RBTREE - rbtree_destroy(&h->rbtree); -#endif - kfree(h); - - set->data = NULL; -} - -#endif /* _IP_SET_AHASH_H */ - -#ifndef HKEY_DATALEN -#define HKEY_DATALEN sizeof(struct type_pf_elem) -#endif - -#define HKEY(data, initval, htable_bits) \ -(jhash2((u32 *)(data), HKEY_DATALEN/sizeof(u32), initval) \ - & jhash_mask(htable_bits)) - -/* Type/family dependent function prototypes */ - -#define type_pf_data_equal TOKEN(TYPE, PF, _data_equal) -#define type_pf_data_isnull TOKEN(TYPE, PF, _data_isnull) -#define type_pf_data_copy TOKEN(TYPE, PF, _data_copy) -#define type_pf_data_zero_out TOKEN(TYPE, PF, _data_zero_out) -#define type_pf_data_netmask TOKEN(TYPE, PF, _data_netmask) -#define type_pf_data_list TOKEN(TYPE, PF, _data_list) -#define type_pf_data_tlist TOKEN(TYPE, PF, _data_tlist) -#define type_pf_data_next TOKEN(TYPE, PF, _data_next) -#define type_pf_data_flags TOKEN(TYPE, PF, _data_flags) -#define type_pf_data_reset_flags TOKEN(TYPE, PF, _data_reset_flags) -#ifdef IP_SET_HASH_WITH_NETS -#define type_pf_data_match TOKEN(TYPE, PF, _data_match) -#else -#define type_pf_data_match(d) 1 -#endif - -#define type_pf_elem TOKEN(TYPE, PF, _elem) -#define type_pf_telem TOKEN(TYPE, PF, _telem) -#define type_pf_data_timeout TOKEN(TYPE, PF, _data_timeout) -#define type_pf_data_expired TOKEN(TYPE, PF, _data_expired) -#define type_pf_data_timeout_set TOKEN(TYPE, PF, _data_timeout_set) - -#define type_pf_elem_add TOKEN(TYPE, PF, _elem_add) -#define type_pf_add TOKEN(TYPE, PF, _add) -#define type_pf_del TOKEN(TYPE, PF, _del) -#define type_pf_test_cidrs TOKEN(TYPE, PF, _test_cidrs) -#define type_pf_test TOKEN(TYPE, PF, _test) - -#define type_pf_elem_tadd TOKEN(TYPE, PF, _elem_tadd) -#define type_pf_del_telem TOKEN(TYPE, PF, _ahash_del_telem) -#define type_pf_expire TOKEN(TYPE, PF, _expire) -#define type_pf_tadd TOKEN(TYPE, PF, _tadd) -#define type_pf_tdel TOKEN(TYPE, PF, _tdel) -#define type_pf_ttest_cidrs TOKEN(TYPE, PF, _ahash_ttest_cidrs) -#define type_pf_ttest TOKEN(TYPE, PF, _ahash_ttest) - -#define type_pf_resize TOKEN(TYPE, PF, _resize) -#define type_pf_tresize TOKEN(TYPE, PF, _tresize) -#define type_pf_flush ip_set_hash_flush -#define type_pf_destroy ip_set_hash_destroy -#define type_pf_head TOKEN(TYPE, PF, _head) -#define type_pf_list TOKEN(TYPE, PF, _list) -#define type_pf_tlist TOKEN(TYPE, PF, _tlist) -#define type_pf_same_set TOKEN(TYPE, PF, _same_set) -#define type_pf_kadt TOKEN(TYPE, PF, _kadt) -#define type_pf_uadt TOKEN(TYPE, PF, _uadt) -#define type_pf_gc TOKEN(TYPE, PF, _gc) -#define type_pf_gc_init TOKEN(TYPE, PF, _gc_init) -#define type_pf_variant TOKEN(TYPE, PF, _variant) -#define type_pf_tvariant TOKEN(TYPE, PF, _tvariant) - -/* Flavour without timeout */ - -/* Get the ith element from the array block n */ -#define ahash_data(n, i) \ - ((struct type_pf_elem *)((n)->value) + (i)) - -/* Add an element to the hash table when resizing the set: - * we spare the maintenance of the internal counters. */ -static int -type_pf_elem_add(struct hbucket *n, const struct type_pf_elem *value, - u8 ahash_max, u32 cadt_flags) -{ - struct type_pf_elem *data; - - if (n->pos >= n->size) { - void *tmp; - - if (n->size >= ahash_max) - /* Trigger rehashing */ - return -EAGAIN; - - tmp = kzalloc((n->size + AHASH_INIT_SIZE) - * sizeof(struct type_pf_elem), - GFP_ATOMIC); - if (!tmp) - return -ENOMEM; - if (n->size) { - memcpy(tmp, n->value, - sizeof(struct type_pf_elem) * n->size); - kfree(n->value); - } - n->value = tmp; - n->size += AHASH_INIT_SIZE; - } - data = ahash_data(n, n->pos++); - type_pf_data_copy(data, value); -#ifdef IP_SET_HASH_WITH_NETS - /* Resizing won't overwrite stored flags */ - if (cadt_flags) - type_pf_data_flags(data, cadt_flags); -#endif - return 0; -} - -/* Resize a hash: create a new hash table with doubling the hashsize - * and inserting the elements to it. Repeat until we succeed or - * fail due to memory pressures. */ -static int -type_pf_resize(struct ip_set *set, bool retried) -{ - struct ip_set_hash *h = set->data; - struct htable *t, *orig = h->table; - u8 htable_bits = orig->htable_bits; - struct type_pf_elem *data; - struct hbucket *n, *m; - u32 i, j, flags = 0; - int ret; - -retry: - ret = 0; - htable_bits++; - pr_debug("attempt to resize set %s from %u to %u, t %p\n", - set->name, orig->htable_bits, htable_bits, orig); - if (!htable_bits) { - /* In case we have plenty of memory :-) */ - pr_warning("Cannot increase the hashsize of set %s further\n", - set->name); - return -IPSET_ERR_HASH_FULL; - } - t = ip_set_alloc(sizeof(*t) - + jhash_size(htable_bits) * sizeof(struct hbucket)); - if (!t) - return -ENOMEM; - t->htable_bits = htable_bits; - - read_lock_bh(&set->lock); - for (i = 0; i < jhash_size(orig->htable_bits); i++) { - n = hbucket(orig, i); - for (j = 0; j < n->pos; j++) { - data = ahash_data(n, j); -#ifdef IP_SET_HASH_WITH_NETS - flags = 0; - type_pf_data_reset_flags(data, &flags); -#endif - m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_add(m, data, AHASH_MAX(h), flags); - if (ret < 0) { -#ifdef IP_SET_HASH_WITH_NETS - type_pf_data_flags(data, flags); -#endif - read_unlock_bh(&set->lock); - ahash_destroy(t); - if (ret == -EAGAIN) - goto retry; - return ret; - } - } - } - - rcu_assign_pointer(h->table, t); - read_unlock_bh(&set->lock); - - /* Give time to other readers of the set */ - synchronize_rcu_bh(); - - pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name, - orig->htable_bits, orig, t->htable_bits, t); - ahash_destroy(orig); - - return 0; -} - -static inline void -type_pf_data_next(struct ip_set_hash *h, const struct type_pf_elem *d); - -/* Add an element to a hash and update the internal counters when succeeded, - * otherwise report the proper error code. */ -static int -type_pf_add(struct ip_set *set, void *value, u32 timeout, u32 flags) -{ - struct ip_set_hash *h = set->data; - struct htable *t; - const struct type_pf_elem *d = value; - struct hbucket *n; - int i, ret = 0; - u32 key, multi = 0; - u32 cadt_flags = flags >> 16; - - if (h->elements >= h->maxelem) { - if (net_ratelimit()) - pr_warning("Set %s is full, maxelem %u reached\n", - set->name, h->maxelem); - return -IPSET_ERR_HASH_FULL; - } - - rcu_read_lock_bh(); - t = rcu_dereference_bh(h->table); - key = HKEY(value, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) - if (type_pf_data_equal(ahash_data(n, i), d, &multi)) { -#ifdef IP_SET_HASH_WITH_NETS - if (flags & IPSET_FLAG_EXIST) - /* Support overwriting just the flags */ - type_pf_data_flags(ahash_data(n, i), - cadt_flags); -#endif - ret = -IPSET_ERR_EXIST; - goto out; - } - TUNE_AHASH_MAX(h, multi); - ret = type_pf_elem_add(n, value, AHASH_MAX(h), cadt_flags); - if (ret != 0) { - if (ret == -EAGAIN) - type_pf_data_next(h, d); - goto out; - } - -#ifdef IP_SET_HASH_WITH_NETS - add_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); -#endif - h->elements++; -out: - rcu_read_unlock_bh(); - return ret; -} - -/* Delete an element from the hash: swap it with the last element - * and free up space if possible. - */ -static int -type_pf_del(struct ip_set *set, void *value, u32 timeout, u32 flags) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - const struct type_pf_elem *d = value; - struct hbucket *n; - int i; - struct type_pf_elem *data; - u32 key, multi = 0; - - key = HKEY(value, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_data(n, i); - if (!type_pf_data_equal(data, d, &multi)) - continue; - if (i != n->pos - 1) - /* Not last one */ - type_pf_data_copy(data, ahash_data(n, n->pos - 1)); - - n->pos--; - h->elements--; -#ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); -#endif - if (n->pos + AHASH_INIT_SIZE < n->size) { - void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) - * sizeof(struct type_pf_elem), - GFP_ATOMIC); - if (!tmp) - return 0; - n->size -= AHASH_INIT_SIZE; - memcpy(tmp, n->value, - n->size * sizeof(struct type_pf_elem)); - kfree(n->value); - n->value = tmp; - } - return 0; - } - - return -IPSET_ERR_EXIST; -} - -#ifdef IP_SET_HASH_WITH_NETS - -/* Special test function which takes into account the different network - * sizes added to the set */ -static int -type_pf_test_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - struct hbucket *n; - const struct type_pf_elem *data; - int i, j = 0; - u32 key, multi = 0; - u8 nets_length = NETS_LENGTH(set->family); - - pr_debug("test by nets\n"); - for (; j < nets_length && h->nets[j].nets && !multi; j++) { - type_pf_data_netmask(d, h->nets[j].cidr); - key = HKEY(d, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_data(n, i); - if (type_pf_data_equal(data, d, &multi)) - return type_pf_data_match(data); - } - } - return 0; -} -#endif - -/* Test whether the element is added to the set */ -static int -type_pf_test(struct ip_set *set, void *value, u32 timeout, u32 flags) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - struct type_pf_elem *d = value; - struct hbucket *n; - const struct type_pf_elem *data; - int i; - u32 key, multi = 0; - -#ifdef IP_SET_HASH_WITH_NETS - /* If we test an IP address and not a network address, - * try all possible network sizes */ - if (CIDR(d->cidr) == SET_HOST_MASK(set->family)) - return type_pf_test_cidrs(set, d, timeout); -#endif - - key = HKEY(d, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_data(n, i); - if (type_pf_data_equal(data, d, &multi)) - return type_pf_data_match(data); - } - return 0; -} - -/* Reply a HEADER request: fill out the header part of the set */ -static int -type_pf_head(struct ip_set *set, struct sk_buff *skb) -{ - const struct ip_set_hash *h = set->data; - struct nlattr *nested; - size_t memsize; - - read_lock_bh(&set->lock); - memsize = ahash_memsize(h, with_timeout(h->timeout) - ? sizeof(struct type_pf_telem) - : sizeof(struct type_pf_elem), - NETS_LENGTH(set->family)); - read_unlock_bh(&set->lock); - - nested = ipset_nest_start(skb, IPSET_ATTR_DATA); - if (!nested) - goto nla_put_failure; - if (nla_put_net32(skb, IPSET_ATTR_HASHSIZE, - htonl(jhash_size(h->table->htable_bits))) || - nla_put_net32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem))) - goto nla_put_failure; -#ifdef IP_SET_HASH_WITH_NETMASK - if (h->netmask != HOST_MASK && - nla_put_u8(skb, IPSET_ATTR_NETMASK, h->netmask)) - goto nla_put_failure; -#endif - if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || - nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || - (with_timeout(h->timeout) && - nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(h->timeout)))) - goto nla_put_failure; - ipset_nest_end(skb, nested); - - return 0; -nla_put_failure: - return -EMSGSIZE; -} - -/* Reply a LIST/SAVE request: dump the elements of the specified set */ -static int -type_pf_list(const struct ip_set *set, - struct sk_buff *skb, struct netlink_callback *cb) -{ - const struct ip_set_hash *h = set->data; - const struct htable *t = h->table; - struct nlattr *atd, *nested; - const struct hbucket *n; - const struct type_pf_elem *data; - u32 first = cb->args[2]; - /* We assume that one hash bucket fills into one page */ - void *incomplete; - int i; - - atd = ipset_nest_start(skb, IPSET_ATTR_ADT); - if (!atd) - return -EMSGSIZE; - pr_debug("list hash set %s\n", set->name); - for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) { - incomplete = skb_tail_pointer(skb); - n = hbucket(t, cb->args[2]); - pr_debug("cb->args[2]: %lu, t %p n %p\n", cb->args[2], t, n); - for (i = 0; i < n->pos; i++) { - data = ahash_data(n, i); - pr_debug("list hash %lu hbucket %p i %u, data %p\n", - cb->args[2], n, i, data); - nested = ipset_nest_start(skb, IPSET_ATTR_DATA); - if (!nested) { - if (cb->args[2] == first) { - nla_nest_cancel(skb, atd); - return -EMSGSIZE; - } else - goto nla_put_failure; - } - if (type_pf_data_list(skb, data)) - goto nla_put_failure; - ipset_nest_end(skb, nested); - } - } - ipset_nest_end(skb, atd); - /* Set listing finished */ - cb->args[2] = 0; - - return 0; - -nla_put_failure: - nlmsg_trim(skb, incomplete); - ipset_nest_end(skb, atd); - if (unlikely(first == cb->args[2])) { - pr_warning("Can't list set %s: one bucket does not fit into " - "a message. Please report it!\n", set->name); - cb->args[2] = 0; - return -EMSGSIZE; - } - return 0; -} - -static int -type_pf_kadt(struct ip_set *set, const struct sk_buff *skb, - const struct xt_action_param *par, - enum ipset_adt adt, const struct ip_set_adt_opt *opt); -static int -type_pf_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags, bool retried); - -static const struct ip_set_type_variant type_pf_variant = { - .kadt = type_pf_kadt, - .uadt = type_pf_uadt, - .adt = { - [IPSET_ADD] = type_pf_add, - [IPSET_DEL] = type_pf_del, - [IPSET_TEST] = type_pf_test, - }, - .destroy = type_pf_destroy, - .flush = type_pf_flush, - .head = type_pf_head, - .list = type_pf_list, - .resize = type_pf_resize, - .same_set = type_pf_same_set, -}; - -/* Flavour with timeout support */ - -#define ahash_tdata(n, i) \ - (struct type_pf_elem *)((struct type_pf_telem *)((n)->value) + (i)) - -static inline u32 -type_pf_data_timeout(const struct type_pf_elem *data) -{ - const struct type_pf_telem *tdata = - (const struct type_pf_telem *) data; - - return tdata->timeout; -} - -static inline bool -type_pf_data_expired(const struct type_pf_elem *data) -{ - const struct type_pf_telem *tdata = - (const struct type_pf_telem *) data; - - return ip_set_timeout_expired(tdata->timeout); -} - -static inline void -type_pf_data_timeout_set(struct type_pf_elem *data, u32 timeout) -{ - struct type_pf_telem *tdata = (struct type_pf_telem *) data; - - tdata->timeout = ip_set_timeout_set(timeout); -} - -static int -type_pf_elem_tadd(struct hbucket *n, const struct type_pf_elem *value, - u8 ahash_max, u32 cadt_flags, u32 timeout) -{ - struct type_pf_elem *data; - - if (n->pos >= n->size) { - void *tmp; - - if (n->size >= ahash_max) - /* Trigger rehashing */ - return -EAGAIN; - - tmp = kzalloc((n->size + AHASH_INIT_SIZE) - * sizeof(struct type_pf_telem), - GFP_ATOMIC); - if (!tmp) - return -ENOMEM; - if (n->size) { - memcpy(tmp, n->value, - sizeof(struct type_pf_telem) * n->size); - kfree(n->value); - } - n->value = tmp; - n->size += AHASH_INIT_SIZE; - } - data = ahash_tdata(n, n->pos++); - type_pf_data_copy(data, value); - type_pf_data_timeout_set(data, timeout); -#ifdef IP_SET_HASH_WITH_NETS - /* Resizing won't overwrite stored flags */ - if (cadt_flags) - type_pf_data_flags(data, cadt_flags); -#endif - return 0; -} - -/* Delete expired elements from the hashtable */ -static void -type_pf_expire(struct ip_set_hash *h, u8 nets_length) -{ - struct htable *t = h->table; - struct hbucket *n; - struct type_pf_elem *data; - u32 i; - int j; - - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = hbucket(t, i); - for (j = 0; j < n->pos; j++) { - data = ahash_tdata(n, j); - if (type_pf_data_expired(data)) { - pr_debug("expired %u/%u\n", i, j); -#ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, CIDR(data->cidr), nets_length); -#endif - if (j != n->pos - 1) - /* Not last one */ - type_pf_data_copy(data, - ahash_tdata(n, n->pos - 1)); - n->pos--; - h->elements--; - } - } - if (n->pos + AHASH_INIT_SIZE < n->size) { - void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) - * sizeof(struct type_pf_telem), - GFP_ATOMIC); - if (!tmp) - /* Still try to delete expired elements */ - continue; - n->size -= AHASH_INIT_SIZE; - memcpy(tmp, n->value, - n->size * sizeof(struct type_pf_telem)); - kfree(n->value); - n->value = tmp; - } - } -} - -static int -type_pf_tresize(struct ip_set *set, bool retried) -{ - struct ip_set_hash *h = set->data; - struct htable *t, *orig = h->table; - u8 htable_bits = orig->htable_bits; - struct type_pf_elem *data; - struct hbucket *n, *m; - u32 i, j, flags = 0; - int ret; - - /* Try to cleanup once */ - if (!retried) { - i = h->elements; - write_lock_bh(&set->lock); - type_pf_expire(set->data, NETS_LENGTH(set->family)); - write_unlock_bh(&set->lock); - if (h->elements < i) - return 0; - } - -retry: - ret = 0; - htable_bits++; - pr_debug("attempt to resize set %s from %u to %u, t %p\n", - set->name, orig->htable_bits, htable_bits, orig); - if (!htable_bits) { - /* In case we have plenty of memory :-) */ - pr_warning("Cannot increase the hashsize of set %s further\n", - set->name); - return -IPSET_ERR_HASH_FULL; - } - t = ip_set_alloc(sizeof(*t) - + jhash_size(htable_bits) * sizeof(struct hbucket)); - if (!t) - return -ENOMEM; - t->htable_bits = htable_bits; - - read_lock_bh(&set->lock); - for (i = 0; i < jhash_size(orig->htable_bits); i++) { - n = hbucket(orig, i); - for (j = 0; j < n->pos; j++) { - data = ahash_tdata(n, j); -#ifdef IP_SET_HASH_WITH_NETS - flags = 0; - type_pf_data_reset_flags(data, &flags); -#endif - m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), flags, - ip_set_timeout_get(type_pf_data_timeout(data))); - if (ret < 0) { -#ifdef IP_SET_HASH_WITH_NETS - type_pf_data_flags(data, flags); -#endif - read_unlock_bh(&set->lock); - ahash_destroy(t); - if (ret == -EAGAIN) - goto retry; - return ret; - } - } - } - - rcu_assign_pointer(h->table, t); - read_unlock_bh(&set->lock); - - /* Give time to other readers of the set */ - synchronize_rcu_bh(); - - ahash_destroy(orig); - - return 0; -} - -static int -type_pf_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - const struct type_pf_elem *d = value; - struct hbucket *n; - struct type_pf_elem *data; - int ret = 0, i, j = AHASH_MAX(h) + 1; - bool flag_exist = flags & IPSET_FLAG_EXIST; - u32 key, multi = 0; - u32 cadt_flags = flags >> 16; - - if (h->elements >= h->maxelem) - /* FIXME: when set is full, we slow down here */ - type_pf_expire(h, NETS_LENGTH(set->family)); - if (h->elements >= h->maxelem) { - if (net_ratelimit()) - pr_warning("Set %s is full, maxelem %u reached\n", - set->name, h->maxelem); - return -IPSET_ERR_HASH_FULL; - } - - rcu_read_lock_bh(); - t = rcu_dereference_bh(h->table); - key = HKEY(d, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_tdata(n, i); - if (type_pf_data_equal(data, d, &multi)) { - if (type_pf_data_expired(data) || flag_exist) - /* Just timeout value may be updated */ - j = i; - else { - ret = -IPSET_ERR_EXIST; - goto out; - } - } else if (j == AHASH_MAX(h) + 1 && - type_pf_data_expired(data)) - j = i; - } - if (j != AHASH_MAX(h) + 1) { - data = ahash_tdata(n, j); -#ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, CIDR(data->cidr), NETS_LENGTH(set->family)); - add_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); -#endif - type_pf_data_copy(data, d); - type_pf_data_timeout_set(data, timeout); -#ifdef IP_SET_HASH_WITH_NETS - type_pf_data_flags(data, cadt_flags); -#endif - goto out; - } - TUNE_AHASH_MAX(h, multi); - ret = type_pf_elem_tadd(n, d, AHASH_MAX(h), cadt_flags, timeout); - if (ret != 0) { - if (ret == -EAGAIN) - type_pf_data_next(h, d); - goto out; - } - -#ifdef IP_SET_HASH_WITH_NETS - add_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); -#endif - h->elements++; -out: - rcu_read_unlock_bh(); - return ret; -} - -static int -type_pf_tdel(struct ip_set *set, void *value, u32 timeout, u32 flags) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - const struct type_pf_elem *d = value; - struct hbucket *n; - int i; - struct type_pf_elem *data; - u32 key, multi = 0; - - key = HKEY(value, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_tdata(n, i); - if (!type_pf_data_equal(data, d, &multi)) - continue; - if (type_pf_data_expired(data)) - return -IPSET_ERR_EXIST; - if (i != n->pos - 1) - /* Not last one */ - type_pf_data_copy(data, ahash_tdata(n, n->pos - 1)); - - n->pos--; - h->elements--; -#ifdef IP_SET_HASH_WITH_NETS - del_cidr(h, CIDR(d->cidr), NETS_LENGTH(set->family)); -#endif - if (n->pos + AHASH_INIT_SIZE < n->size) { - void *tmp = kzalloc((n->size - AHASH_INIT_SIZE) - * sizeof(struct type_pf_telem), - GFP_ATOMIC); - if (!tmp) - return 0; - n->size -= AHASH_INIT_SIZE; - memcpy(tmp, n->value, - n->size * sizeof(struct type_pf_telem)); - kfree(n->value); - n->value = tmp; - } - return 0; - } - - return -IPSET_ERR_EXIST; -} - -#ifdef IP_SET_HASH_WITH_NETS -static int -type_pf_ttest_cidrs(struct ip_set *set, struct type_pf_elem *d, u32 timeout) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - struct type_pf_elem *data; - struct hbucket *n; - int i, j = 0; - u32 key, multi = 0; - u8 nets_length = NETS_LENGTH(set->family); - - for (; j < nets_length && h->nets[j].nets && !multi; j++) { - type_pf_data_netmask(d, h->nets[j].cidr); - key = HKEY(d, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_tdata(n, i); -#ifdef IP_SET_HASH_WITH_MULTI - if (type_pf_data_equal(data, d, &multi)) { - if (!type_pf_data_expired(data)) - return type_pf_data_match(data); - multi = 0; - } -#else - if (type_pf_data_equal(data, d, &multi) && - !type_pf_data_expired(data)) - return type_pf_data_match(data); -#endif - } - } - return 0; -} -#endif - -static int -type_pf_ttest(struct ip_set *set, void *value, u32 timeout, u32 flags) -{ - struct ip_set_hash *h = set->data; - struct htable *t = h->table; - struct type_pf_elem *data, *d = value; - struct hbucket *n; - int i; - u32 key, multi = 0; - -#ifdef IP_SET_HASH_WITH_NETS - if (CIDR(d->cidr) == SET_HOST_MASK(set->family)) - return type_pf_ttest_cidrs(set, d, timeout); -#endif - key = HKEY(d, h->initval, t->htable_bits); - n = hbucket(t, key); - for (i = 0; i < n->pos; i++) { - data = ahash_tdata(n, i); - if (type_pf_data_equal(data, d, &multi) && - !type_pf_data_expired(data)) - return type_pf_data_match(data); - } - return 0; -} - -static int -type_pf_tlist(const struct ip_set *set, - struct sk_buff *skb, struct netlink_callback *cb) -{ - const struct ip_set_hash *h = set->data; - const struct htable *t = h->table; - struct nlattr *atd, *nested; - const struct hbucket *n; - const struct type_pf_elem *data; - u32 first = cb->args[2]; - /* We assume that one hash bucket fills into one page */ - void *incomplete; - int i; - - atd = ipset_nest_start(skb, IPSET_ATTR_ADT); - if (!atd) - return -EMSGSIZE; - for (; cb->args[2] < jhash_size(t->htable_bits); cb->args[2]++) { - incomplete = skb_tail_pointer(skb); - n = hbucket(t, cb->args[2]); - for (i = 0; i < n->pos; i++) { - data = ahash_tdata(n, i); - pr_debug("list %p %u\n", n, i); - if (type_pf_data_expired(data)) - continue; - pr_debug("do list %p %u\n", n, i); - nested = ipset_nest_start(skb, IPSET_ATTR_DATA); - if (!nested) { - if (cb->args[2] == first) { - nla_nest_cancel(skb, atd); - return -EMSGSIZE; - } else - goto nla_put_failure; - } - if (type_pf_data_tlist(skb, data)) - goto nla_put_failure; - ipset_nest_end(skb, nested); - } - } - ipset_nest_end(skb, atd); - /* Set listing finished */ - cb->args[2] = 0; - - return 0; - -nla_put_failure: - nlmsg_trim(skb, incomplete); - ipset_nest_end(skb, atd); - if (unlikely(first == cb->args[2])) { - pr_warning("Can't list set %s: one bucket does not fit into " - "a message. Please report it!\n", set->name); - cb->args[2] = 0; - return -EMSGSIZE; - } - return 0; -} - -static const struct ip_set_type_variant type_pf_tvariant = { - .kadt = type_pf_kadt, - .uadt = type_pf_uadt, - .adt = { - [IPSET_ADD] = type_pf_tadd, - [IPSET_DEL] = type_pf_tdel, - [IPSET_TEST] = type_pf_ttest, - }, - .destroy = type_pf_destroy, - .flush = type_pf_flush, - .head = type_pf_head, - .list = type_pf_tlist, - .resize = type_pf_tresize, - .same_set = type_pf_same_set, -}; - -static void -type_pf_gc(unsigned long ul_set) -{ - struct ip_set *set = (struct ip_set *) ul_set; - struct ip_set_hash *h = set->data; - - pr_debug("called\n"); - write_lock_bh(&set->lock); - type_pf_expire(h, NETS_LENGTH(set->family)); - write_unlock_bh(&set->lock); - - h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ; - add_timer(&h->gc); -} - -static void -type_pf_gc_init(struct ip_set *set) -{ - struct ip_set_hash *h = set->data; - - init_timer(&h->gc); - h->gc.data = (unsigned long) set; - h->gc.function = type_pf_gc; - h->gc.expires = jiffies + IPSET_GC_PERIOD(h->timeout) * HZ; - add_timer(&h->gc); - pr_debug("gc initialized, run in every %u\n", - IPSET_GC_PERIOD(h->timeout)); -} - -#undef HKEY_DATALEN -#undef HKEY -#undef type_pf_data_equal -#undef type_pf_data_isnull -#undef type_pf_data_copy -#undef type_pf_data_zero_out -#undef type_pf_data_netmask -#undef type_pf_data_list -#undef type_pf_data_tlist -#undef type_pf_data_next -#undef type_pf_data_flags -#undef type_pf_data_reset_flags -#undef type_pf_data_match - -#undef type_pf_elem -#undef type_pf_telem -#undef type_pf_data_timeout -#undef type_pf_data_expired -#undef type_pf_data_timeout_set - -#undef type_pf_elem_add -#undef type_pf_add -#undef type_pf_del -#undef type_pf_test_cidrs -#undef type_pf_test - -#undef type_pf_elem_tadd -#undef type_pf_del_telem -#undef type_pf_expire -#undef type_pf_tadd -#undef type_pf_tdel -#undef type_pf_ttest_cidrs -#undef type_pf_ttest - -#undef type_pf_resize -#undef type_pf_tresize -#undef type_pf_flush -#undef type_pf_destroy -#undef type_pf_head -#undef type_pf_list -#undef type_pf_tlist -#undef type_pf_same_set -#undef type_pf_kadt -#undef type_pf_uadt -#undef type_pf_gc -#undef type_pf_gc_init -#undef type_pf_variant -#undef type_pf_tvariant -- cgit v1.2.3 From 34d666d489cf70c246ca99b2387741915c34b88c Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Sat, 27 Apr 2013 14:38:56 +0200 Subject: netfilter: ipset: Introduce the counter extension in the core Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 75 ++++++++++++++++++++++++++++++++-- 1 file changed, 71 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index bf0220cbf46a..0f978ebfaefb 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -52,18 +52,24 @@ enum ip_set_extension { IPSET_EXT_NONE = 0, IPSET_EXT_BIT_TIMEOUT = 1, IPSET_EXT_TIMEOUT = (1 << IPSET_EXT_BIT_TIMEOUT), + IPSET_EXT_BIT_COUNTER = 2, + IPSET_EXT_COUNTER = (1 << IPSET_EXT_BIT_COUNTER), }; /* Extension offsets */ enum ip_set_offset { IPSET_OFFSET_TIMEOUT = 0, + IPSET_OFFSET_COUNTER, IPSET_OFFSET_MAX, }; #define SET_WITH_TIMEOUT(s) ((s)->extensions & IPSET_EXT_TIMEOUT) +#define SET_WITH_COUNTER(s) ((s)->extensions & IPSET_EXT_COUNTER) struct ip_set_ext { unsigned long timeout; + u64 packets; + u64 bytes; }; struct ip_set; @@ -177,6 +183,65 @@ struct ip_set { void *data; }; +struct ip_set_counter { + atomic64_t bytes; + atomic64_t packets; +}; + +static inline void +ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter) +{ + atomic64_add((long long)bytes, &(counter)->bytes); +} + +static inline void +ip_set_add_packets(u64 packets, struct ip_set_counter *counter) +{ + atomic64_add((long long)packets, &(counter)->packets); +} + +static inline u64 +ip_set_get_bytes(const struct ip_set_counter *counter) +{ + return (u64)atomic64_read(&(counter)->bytes); +} + +static inline u64 +ip_set_get_packets(const struct ip_set_counter *counter) +{ + return (u64)atomic64_read(&(counter)->packets); +} + +static inline void +ip_set_update_counter(struct ip_set_counter *counter, + const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags) +{ + if (ext->packets != ULLONG_MAX) { + ip_set_add_bytes(ext->bytes, counter); + ip_set_add_packets(ext->packets, counter); + } +} + +static inline bool +ip_set_put_counter(struct sk_buff *skb, struct ip_set_counter *counter) +{ + return nla_put_net64(skb, IPSET_ATTR_BYTES, + cpu_to_be64(ip_set_get_bytes(counter))) || + nla_put_net64(skb, IPSET_ATTR_PACKETS, + cpu_to_be64(ip_set_get_packets(counter))); +} + +static inline void +ip_set_init_counter(struct ip_set_counter *counter, + const struct ip_set_ext *ext) +{ + if (ext->bytes != ULLONG_MAX) + atomic64_set(&(counter)->bytes, (long long)(ext->bytes)); + if (ext->packets != ULLONG_MAX) + atomic64_set(&(counter)->packets, (long long)(ext->packets)); +} + /* register and unregister set references */ extern ip_set_id_t ip_set_get_byname(const char *name, struct ip_set **set); extern void ip_set_put_byindex(ip_set_id_t index); @@ -318,10 +383,12 @@ bitmap_bytes(u32 a, u32 b) #include -#define IP_SET_INIT_KEXT(skb, opt, map) \ - { .timeout = ip_set_adt_opt_timeout(opt, map) } +#define IP_SET_INIT_KEXT(skb, opt, map) \ + { .bytes = (skb)->len, .packets = 1, \ + .timeout = ip_set_adt_opt_timeout(opt, map) } -#define IP_SET_INIT_UEXT(map) \ - { .timeout = (map)->timeout } +#define IP_SET_INIT_UEXT(map) \ + { .bytes = ULLONG_MAX, .packets = ULLONG_MAX, \ + .timeout = (map)->timeout } #endif /*_IP_SET_H */ -- cgit v1.2.3 From 6e01781d1c80e2e8263471252a631e86165b15c5 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Sat, 27 Apr 2013 14:40:50 +0200 Subject: netfilter: ipset: set match: add support to match the counters The new revision of the set match supports to match the counters and to suppress updating the counters at matching too. At the set:list types, the updating of the subcounters can be suppressed as well. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 0f978ebfaefb..d80e2753847c 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -76,7 +76,7 @@ struct ip_set; typedef int (*ipset_adtfn)(struct ip_set *set, void *value, const struct ip_set_ext *ext, - struct ip_set_ext *mext, u32 flags); + struct ip_set_ext *mext, u32 cmdflags); /* Kernel API function options */ struct ip_set_adt_opt { @@ -217,10 +217,15 @@ ip_set_update_counter(struct ip_set_counter *counter, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { - if (ext->packets != ULLONG_MAX) { + if (ext->packets != ULLONG_MAX && + !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) { ip_set_add_bytes(ext->bytes, counter); ip_set_add_packets(ext->packets, counter); } + if (flags & IPSET_FLAG_MATCH_COUNTERS) { + mext->packets = ip_set_get_packets(counter); + mext->bytes = ip_set_get_bytes(counter); + } } static inline bool -- cgit v1.2.3 From 3dc20cb282ec03cc4c997130d680c800011ed479 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 13 Apr 2013 20:31:37 -0400 Subject: new helper: read_code() switch binfmts that use ->read() to that (and to kernel_read() in several cases in binfmt_flat - sure, it's nommu, but still, doing ->read() into kmalloc'ed buffer...) Signed-off-by: Al Viro --- include/linux/binfmts.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index c3a09149f793..70cf138690e9 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -118,5 +118,6 @@ extern int prepare_bprm_creds(struct linux_binprm *bprm); extern void install_exec_creds(struct linux_binprm *bprm); extern void set_binfmt(struct linux_binfmt *new); extern void free_bprm(struct linux_binprm *); +extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t); #endif /* _LINUX_BINFMTS_H */ -- cgit v1.2.3 From d0206fb55540cfdc3a2634ffdafc6f1d86cf1f15 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 9 Apr 2013 21:11:47 +0100 Subject: procfs: Mark create_proc_read_entry deprecated Mark create_proc_read_entry deprecated. proc_create[_data]() should be used instead. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/proc_fs.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 2781e498f709..8175b49396a6 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -155,7 +155,8 @@ static inline struct proc_dir_entry *proc_create(const char *name, umode_t mode, return proc_create_data(name, mode, parent, proc_fops, NULL); } -extern struct proc_dir_entry *create_proc_read_entry(const char *name, +extern __deprecated +struct proc_dir_entry *create_proc_read_entry(const char *name, umode_t mode, struct proc_dir_entry *base, read_proc_t *read_proc, void *data); @@ -191,7 +192,8 @@ static inline struct proc_dir_entry *proc_mkdir(const char *name, static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent) { return NULL; } -static inline struct proc_dir_entry *create_proc_read_entry(const char *name, +static inline __deprecated +struct proc_dir_entry *create_proc_read_entry(const char *name, umode_t mode, struct proc_dir_entry *base, read_proc_t *read_proc, void * data) { return NULL; } -- cgit v1.2.3 From 11db656ad462c9aa7aff7e3817214578cfc307b3 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 10 Apr 2013 15:05:38 +0100 Subject: nubus: Don't use create_proc_read_entry() Don't use create_proc_read_entry() as that is deprecated, but rather use proc_create_data() and seq_file instead. Signed-off-by: David Howells cc: linux-m68k@lists.linux-m68k.org Signed-off-by: Al Viro --- include/linux/nubus.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nubus.h b/include/linux/nubus.h index a8696bbdfbc4..b3740527571a 100644 --- a/include/linux/nubus.h +++ b/include/linux/nubus.h @@ -80,7 +80,11 @@ extern struct nubus_board* nubus_boards; /* Generic NuBus interface functions, modelled after the PCI interface */ void nubus_scan_bus(void); +#ifdef CONFIG_PROC_FS extern void nubus_proc_init(void); +#else +static inline void nubus_proc_init(void) {} +#endif int get_nubus_list(char *buf); int nubus_proc_attach_device(struct nubus_dev *dev); int nubus_proc_detach_device(struct nubus_dev *dev); -- cgit v1.2.3 From 3cb5bf1bf947d325fcf6e9458952b51cfd7e6677 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 11 Apr 2013 03:20:50 +0100 Subject: proc: Delete create_proc_read_entry() Delete create_proc_read_entry() as it no longer has any users. Also delete read_proc_t, write_proc_t, the read_proc member of the proc_dir_entry struct and the support functions that use them. This saves a pointer for every PDE allocated. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/proc_fs.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 8175b49396a6..f5105f4e54f4 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -47,11 +47,6 @@ enum { * non-directory entries). */ -typedef int (read_proc_t)(char *page, char **start, off_t off, - int count, int *eof, void *data); -typedef int (write_proc_t)(struct file *file, const char __user *buffer, - unsigned long count, void *data); - struct proc_dir_entry { unsigned int low_ino; umode_t mode; @@ -63,7 +58,6 @@ struct proc_dir_entry { const struct file_operations *proc_fops; struct proc_dir_entry *next, *parent, *subdir; void *data; - read_proc_t *read_proc; atomic_t count; /* use count */ atomic_t in_use; /* number of callers into module in progress; */ /* negative -> it's going away RSN */ @@ -154,11 +148,6 @@ static inline struct proc_dir_entry *proc_create(const char *name, umode_t mode, { return proc_create_data(name, mode, parent, proc_fops, NULL); } - -extern __deprecated -struct proc_dir_entry *create_proc_read_entry(const char *name, - umode_t mode, struct proc_dir_entry *base, - read_proc_t *read_proc, void *data); extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name, struct proc_dir_entry *parent); @@ -192,11 +181,6 @@ static inline struct proc_dir_entry *proc_mkdir(const char *name, static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent) { return NULL; } -static inline __deprecated -struct proc_dir_entry *create_proc_read_entry(const char *name, - umode_t mode, struct proc_dir_entry *base, - read_proc_t *read_proc, void * data) { return NULL; } - struct tty_driver; static inline void proc_tty_register_driver(struct tty_driver *driver) {}; static inline void proc_tty_unregister_driver(struct tty_driver *driver) {}; -- cgit v1.2.3 From 2f96b8c1d5d492c1d0457b253015330f844136f6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 12 Apr 2013 00:10:25 +0100 Subject: proc: Split kcore bits from linux/procfs.h into linux/kcore.h Split kcore bits from linux/procfs.h into linux/kcore.h. Signed-off-by: David Howells Acked-by: KOSAKI Motohiro Acked-by: Ralf Baechle cc: linux-mips@linux-mips.org cc: sparclinux@vger.kernel.org cc: x86@kernel.org cc: linux-mm@kvack.org Signed-off-by: Al Viro --- include/linux/kcore.h | 38 ++++++++++++++++++++++++++++++++++++++ include/linux/proc_fs.h | 31 ------------------------------- 2 files changed, 38 insertions(+), 31 deletions(-) create mode 100644 include/linux/kcore.h (limited to 'include/linux') diff --git a/include/linux/kcore.h b/include/linux/kcore.h new file mode 100644 index 000000000000..d92762286645 --- /dev/null +++ b/include/linux/kcore.h @@ -0,0 +1,38 @@ +/* + * /proc/kcore definitions + */ +#ifndef _LINUX_KCORE_H +#define _LINUX_KCORE_H + +enum kcore_type { + KCORE_TEXT, + KCORE_VMALLOC, + KCORE_RAM, + KCORE_VMEMMAP, + KCORE_OTHER, +}; + +struct kcore_list { + struct list_head list; + unsigned long addr; + size_t size; + int type; +}; + +struct vmcore { + struct list_head list; + unsigned long long paddr; + unsigned long long size; + loff_t offset; +}; + +#ifdef CONFIG_PROC_KCORE +extern void kclist_add(struct kcore_list *, void *, size_t, int type); +#else +static inline +void kclist_add(struct kcore_list *new, void *addr, size_t size, int type) +{ +} +#endif + +#endif /* _LINUX_KCORE_H */ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index f5105f4e54f4..805edacfc2fc 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -68,28 +68,6 @@ struct proc_dir_entry { char name[]; }; -enum kcore_type { - KCORE_TEXT, - KCORE_VMALLOC, - KCORE_RAM, - KCORE_VMEMMAP, - KCORE_OTHER, -}; - -struct kcore_list { - struct list_head list; - unsigned long addr; - size_t size; - int type; -}; - -struct vmcore { - struct list_head list; - unsigned long long paddr; - unsigned long long size; - loff_t offset; -}; - #ifdef CONFIG_PROC_FS extern void proc_root_init(void); @@ -214,15 +192,6 @@ static inline void proc_free_inum(unsigned int inum) } #endif /* CONFIG_PROC_FS */ -#if !defined(CONFIG_PROC_KCORE) -static inline void -kclist_add(struct kcore_list *new, void *addr, size_t size, int type) -{ -} -#else -extern void kclist_add(struct kcore_list *, void *, size_t, int type); -#endif - struct nsproxy; struct proc_ns_operations { const char *name; -- cgit v1.2.3 From 68a2d20b79b105f02dcbc52c211d7e62f98996b7 Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Mon, 29 Apr 2013 15:05:42 -0700 Subject: drivers/video: add Hyper-V Synthetic Video Frame Buffer Driver This is the driver for the Hyper-V Synthetic Video, which supports screen resolution up to Full HD 1920x1080 on Windows Server 2012 host, and 1600x1200 on Windows Server 2008 R2 or earlier. It also solves the double mouse cursor issue of the emulated video mode. Signed-off-by: Haiyang Zhang Reviewed-by: K. Y. Srinivasan Cc: Greg Kroah-Hartman , Cc: Olaf Hering Cc: Geert Uytterhoeven Cc: Florian Tobias Schandinat Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hyperv.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 95d0850584da..c2559847d7ee 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1317,6 +1317,17 @@ void vmbus_driver_unregister(struct hv_driver *hv_driver); 0x29, 0x2e, 0xfa, 0x35, 0x23, 0xea, 0x36, 0x42, \ 0x96, 0xae, 0x3a, 0x6e, 0xba, 0xcb, 0xa4, 0x40 \ } +/* + * Synthetic Video GUID + * {DA0A7802-E377-4aac-8E77-0558EB1073F8} + */ +#define HV_SYNTHVID_GUID \ + .guid = { \ + 0x02, 0x78, 0x0a, 0xda, 0x77, 0xe3, 0xac, 0x4a, \ + 0x8e, 0x77, 0x05, 0x58, 0xeb, 0x10, 0x73, 0xf8 \ + } + + /* * Common header for Hyper-V ICs */ -- cgit v1.2.3 From 2c2fea11957c8c45bf873d9bcd7cd9a342654e79 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Mon, 29 Apr 2013 15:06:06 -0700 Subject: debug_locks.h: make warning more verbose The WARN_ON(1) in DEBUG_LOCKS_WARN_ON is surprisingly awkward to track down when it's hit, as it's usually buried in macros, causing multiple instances to land on the same line number. This patch makes it more useful by switching to: WARN(1, "DEBUG_LOCKS_WARN_ON(%s)", #c); so that the particular DEBUG_LOCKS_WARN_ON is more easily identified and grep'd for. For example: WARNING: at kernel/mutex.c:198 _mutex_lock_nested+0x31c/0x380() DEBUG_LOCKS_WARN_ON(l->magic != l) Signed-off-by: James Hogan Cc: Paul Gortmaker Cc: David Howells Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/debug_locks.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 3bd46f766751..21ca773f77bf 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -27,7 +27,7 @@ extern int debug_locks_off(void); \ if (!oops_in_progress && unlikely(c)) { \ if (debug_locks_off() && !debug_locks_silent) \ - WARN_ON(1); \ + WARN(1, "DEBUG_LOCKS_WARN_ON(%s)", #c); \ __ret = 1; \ } \ __ret; \ -- cgit v1.2.3 From 4b59e6c4730978679b414a8da61514a2518da512 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 29 Apr 2013 15:06:11 -0700 Subject: mm, show_mem: suppress page counts in non-blockable contexts On large systems with a lot of memory, walking all RAM to determine page types may take a half second or even more. In non-blockable contexts, the page allocator will emit a page allocation failure warning unless __GFP_NOWARN is specified. In such contexts, irqs are typically disabled and such a lengthy delay may even result in NMI watchdog timeouts. To fix this, suppress the page walk in such contexts when printing the page allocation failure warning. Signed-off-by: David Rientjes Cc: Mel Gorman Acked-by: Michal Hocko Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e2091b88d24c..f3c7b1f9d1d8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -899,7 +899,8 @@ extern void pagefault_out_of_memory(void); * Flags passed to show_mem() and show_free_areas() to suppress output in * various contexts. */ -#define SHOW_MEM_FILTER_NODES (0x0001u) /* filter disallowed nodes */ +#define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ +#define SHOW_MEM_FILTER_PAGE_COUNT (0x0002u) /* page type count */ extern void show_free_areas(unsigned int flags); extern bool skip_free_areas_node(unsigned int flags, int nid); -- cgit v1.2.3 From 250297edf83292c831fbf4504df54953c2aacfe4 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 29 Apr 2013 15:06:12 -0700 Subject: mm/shmem.c: remove an ifdef Create a CONFIG_MMU=y stub for ramfs_nommu_expand_for_mapping() in the usual fashion. Cc: Al Viro Cc: Wolfram Sang Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ramfs.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ramfs.h b/include/linux/ramfs.h index 5bf5500db83d..69e37c2d1ea5 100644 --- a/include/linux/ramfs.h +++ b/include/linux/ramfs.h @@ -6,7 +6,13 @@ struct inode *ramfs_get_inode(struct super_block *sb, const struct inode *dir, extern struct dentry *ramfs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data); -#ifndef CONFIG_MMU +#ifdef CONFIG_MMU +static inline int +ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) +{ + return 0; +} +#else extern int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize); extern unsigned long ramfs_nommu_get_unmapped_area(struct file *file, unsigned long addr, -- cgit v1.2.3 From 8375ad98cc1defc36adf4a77d9ea1e71db51a371 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 29 Apr 2013 15:06:13 -0700 Subject: vm: adjust ifdef for TINY_RCU There is an ifdef in page_cache_get_speculative() that checks for !SMP and TREE_RCU, which has been an impossible combination since the advent of TINY_RCU. The ifdef enables a fastpath that is valid when preemption is disabled by rcu_read_lock() in UP systems, which is the case when TINY_RCU is enabled. This commit therefore adjusts the ifdef to generate the fastpath when TINY_RCU is enabled. Signed-off-by: Paul E. McKenney Reported-by: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0e38e13eb249..e3dea75a078b 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -149,7 +149,7 @@ static inline int page_cache_get_speculative(struct page *page) { VM_BUG_ON(in_interrupt()); -#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU) +#ifdef CONFIG_TINY_RCU # ifdef CONFIG_PREEMPT_COUNT VM_BUG_ON(!in_atomic()); # endif -- cgit v1.2.3 From 69afade72a3e13e96a065f757891d384d466123f Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 29 Apr 2013 15:06:21 -0700 Subject: mm: introduce common help functions to deal with reserved/managed pages The original goal of this patchset is to fix the bug reported by https://bugzilla.kernel.org/show_bug.cgi?id=53501 Now it has also been expanded to reduce common code used by memory initializion. This is the first part, which applies to v3.9-rc1. It introduces following common helper functions to simplify free_initmem() and free_initrd_mem() on different architectures: adjust_managed_page_count(): will be used to adjust totalram_pages, totalhigh_pages, zone->managed_pages when reserving/unresering a page. __free_reserved_page(): free a reserved page into the buddy system without adjusting page statistics info free_reserved_page(): free a reserved page into the buddy system and adjust page statistics info mark_page_reserved(): mark a page as reserved and adjust page statistics info free_reserved_area(): free a continous ranges of pages by calling free_reserved_page() free_initmem_default(): default method to free __init pages. We have only tested these patchset on x86 platforms, and have done basic compliation tests using cross-compilers from ftp.kernel.org. That means some code may not pass compilation on some architectures. So any help to test this patchset are welcomed! There are several other parts still under development: Part2: introduce free_highmem_page() to simplify freeing highmem pages Part3: refine code to manage totalram_pages, totalhigh_pages and zone->managed_pages Part4: introduce helper functions to simplify mem_init() and remove the global variable num_physpages. This patch: Code to deal with reserved/managed pages are duplicated by many architectures, so introduce common help functions to reduce duplicated code. These common help functions will also be used to concentrate code to modify totalram_pages and zone->managed_pages, which makes the code much more clear. Signed-off-by: Jiang Liu Acked-by: Geert Uytterhoeven Cc: "H. Peter Anvin" Cc: "James E.J. Bottomley" Cc: Anatolij Gustschin Cc: Aurelien Jacquiot Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Chen Liqin Cc: Chris Zankel Cc: David Howells Cc: David S. Miller Cc: Eric Biederman Cc: Fenghua Yu Cc: Guan Xuetao Cc: Haavard Skinnemoen Cc: Hans-Christian Egtvedt Cc: Heiko Carstens Cc: Helge Deller Cc: Hirokazu Takata Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: James Hogan Cc: Jeff Dike Cc: Jiang Liu Cc: Jiang Liu Cc: Jonas Bonn Cc: Koichi Yasutake Cc: Lennox Wu Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Max Filippov Cc: Michal Simek Cc: Mikael Starvik Cc: Mike Frysinger Cc: Paul Mackerras Cc: Paul Mundt Cc: Ralf Baechle Cc: Richard Henderson Cc: Russell King Cc: Sam Ravnborg Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Cc: Zhang Yanfei Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f3c7b1f9d1d8..d064c73c925e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1295,6 +1295,54 @@ extern void free_area_init_node(int nid, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); extern void free_initmem(void); +/* + * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK) + * into the buddy system. The freed pages will be poisoned with pattern + * "poison" if it's non-zero. + * Return pages freed into the buddy system. + */ +extern unsigned long free_reserved_area(unsigned long start, unsigned long end, + int poison, char *s); + +static inline void adjust_managed_page_count(struct page *page, long count) +{ + totalram_pages += count; +} + +/* Free the reserved page into the buddy system, so it gets managed. */ +static inline void __free_reserved_page(struct page *page) +{ + ClearPageReserved(page); + init_page_count(page); + __free_page(page); +} + +static inline void free_reserved_page(struct page *page) +{ + __free_reserved_page(page); + adjust_managed_page_count(page, 1); +} + +static inline void mark_page_reserved(struct page *page) +{ + SetPageReserved(page); + adjust_managed_page_count(page, -1); +} + +/* + * Default method to free all the __init memory into the buddy system. + * The freed pages will be poisoned with pattern "poison" if it is + * non-zero. Return pages freed into the buddy system. + */ +static inline unsigned long free_initmem_default(int poison) +{ + extern char __init_begin[], __init_end[]; + + return free_reserved_area(PAGE_ALIGN((unsigned long)&__init_begin) , + ((unsigned long)&__init_end) & PAGE_MASK, + poison, "unused kernel"); +} + #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* * With CONFIG_HAVE_MEMBLOCK_NODE_MAP set, an architecture may initialise its -- cgit v1.2.3 From cfa11e08ed39eb28a9eff9a907b20913020c69b5 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 29 Apr 2013 15:07:00 -0700 Subject: mm: introduce free_highmem_page() helper to free highmem pages into buddy system The original goal of this patchset is to fix the bug reported by https://bugzilla.kernel.org/show_bug.cgi?id=53501 Now it has also been expanded to reduce common code used by memory initializion. This is the second part, which applies to the previous part at: http://marc.info/?l=linux-mm&m=136289696323825&w=2 It introduces a helper function free_highmem_page() to free highmem pages into the buddy system when initializing mm subsystem. Introduction of free_highmem_page() is one step forward to clean up accesses and modificaitons of totalhigh_pages, totalram_pages and zone->managed_pages etc. I hope we could remove all references to totalhigh_pages from the arch/ subdirectory. We have only tested these patchset on x86 platforms, and have done basic compliation tests using cross-compilers from ftp.kernel.org. That means some code may not pass compilation on some architectures. So any help to test this patchset are welcomed! There are several other parts still under development: Part3: refine code to manage totalram_pages, totalhigh_pages and zone->managed_pages Part4: introduce helper functions to simplify mem_init() and remove the global variable num_physpages. This patch: Introduce helper function free_highmem_page(), which will be used by architectures with HIGHMEM enabled to free highmem pages into the buddy system. Signed-off-by: Jiang Liu Cc: "David S. Miller" Cc: "H. Peter Anvin" Cc: "Suzuki K. Poulose" Cc: Alexander Graf Cc: Arnd Bergmann Cc: Attilio Rao Cc: Benjamin Herrenschmidt Cc: Cong Wang Cc: David Daney Cc: David Howells Cc: Geert Uytterhoeven Cc: Ingo Molnar Cc: James Hogan Cc: Jeff Dike Cc: Jiang Liu Cc: Jiang Liu Cc: Konrad Rzeszutek Wilk Cc: Konstantin Khlebnikov Cc: Linus Walleij Cc: Marek Szyprowski Cc: Mel Gorman Cc: Michal Nazarewicz Cc: Michal Simek Cc: Michel Lespinasse Cc: Minchan Kim Cc: Paul Mackerras Cc: Ralf Baechle Cc: Richard Weinberger Cc: Rik van Riel Cc: Russell King Cc: Sam Ravnborg Cc: Stephen Boyd Cc: Thomas Gleixner Cc: Yinghai Lu Reviewed-by: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d064c73c925e..43b70d5f8201 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1303,6 +1303,13 @@ extern void free_initmem(void); */ extern unsigned long free_reserved_area(unsigned long start, unsigned long end, int poison, char *s); +#ifdef CONFIG_HIGHMEM +/* + * Free a highmem page into the buddy system, adjusting totalhigh_pages + * and totalram_pages. + */ +extern void free_highmem_page(struct page *page); +#endif static inline void adjust_managed_page_count(struct page *page, long count) { -- cgit v1.2.3 From 6d2488f64a240191f0733c1f32d73607916b01b7 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Mon, 29 Apr 2013 15:07:21 -0700 Subject: cgroup: remove css_get_next Now that we have generic and well ordered cgroup tree walkers there is no need to keep css_get_next in the place. Signed-off-by: Michal Hocko Acked-by: KAMEZAWA Hiroyuki Acked-by: Li Zefan Cc: Johannes Weiner Cc: Ying Han Cc: Tejun Heo Cc: Glauber Costa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 900af5964f55..470073bf93d0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -687,13 +687,6 @@ void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id); -/* - * Get a cgroup whose id is greater than or equal to id under tree of root. - * Returning a cgroup_subsys_state or NULL. - */ -struct cgroup_subsys_state *css_get_next(struct cgroup_subsys *ss, int id, - struct cgroup_subsys_state *root, int *foundid); - /* Returns true if root is ancestor of cg */ bool css_is_ancestor(struct cgroup_subsys_state *cg, const struct cgroup_subsys_state *root); -- cgit v1.2.3 From 146732ce104ddfed3d4d82722c0b336074016b92 Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Mon, 29 Apr 2013 15:07:22 -0700 Subject: fs: don't compile in drop_caches.c when CONFIG_SYSCTL=n drop_caches.c provides code only invokable via sysctl, so don't compile it in when CONFIG_SYSCTL=n. Signed-off-by: Josh Triplett Acked-by: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 43b70d5f8201..98a44376e4f3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1731,8 +1731,12 @@ int in_gate_area_no_mm(unsigned long addr); #define in_gate_area(mm, addr) ({(void)mm; in_gate_area_no_mm(addr);}) #endif /* __HAVE_ARCH_GATE_AREA */ +#ifdef CONFIG_SYSCTL +extern int sysctl_drop_caches; int drop_caches_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +#endif + unsigned long shrink_slab(struct shrink_control *shrink, unsigned long nr_pages_scanned, unsigned long lru_pages); -- cgit v1.2.3 From 7136851117744f1d291bed6d307432699d405109 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 29 Apr 2013 15:07:25 -0700 Subject: mm: make snapshotting pages for stable writes a per-bio operation Walking a bio's page mappings has proved problematic, so create a new bio flag to indicate that a bio's data needs to be snapshotted in order to guarantee stable pages during writeback. Next, for the one user (ext3/jbd) of snapshotting, hook all the places where writes can be initiated without PG_writeback set, and set BIO_SNAP_STABLE there. We must also flag journal "metadata" bios for stable writeout, since file data can be written through the journal. Finally, the MS_SNAP_STABLE mount flag (only used by ext3) is now superfluous, so get rid of it. [akpm@linux-foundation.org: rename _submit_bh()'s `flags' to `bio_flags', delobotomize the _submit_bh declaration] [akpm@linux-foundation.org: teeny cleanup] Signed-off-by: Darrick J. Wong Cc: Andy Lutomirski Cc: Adrian Hunter Cc: Artem Bityutskiy Reviewed-by: Jan Kara Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/blk_types.h | 3 ++- include/linux/buffer_head.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index cdf11191e645..22990cf4439d 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -111,12 +111,13 @@ struct bio { #define BIO_FS_INTEGRITY 9 /* fs owns integrity data, not block layer */ #define BIO_QUIET 10 /* Make BIO Quiet */ #define BIO_MAPPED_INTEGRITY 11/* integrity metadata has been remapped */ +#define BIO_SNAP_STABLE 12 /* bio data must be snapshotted during write */ /* * Flags starting here get preserved by bio_reset() - this includes * BIO_POOL_IDX() */ -#define BIO_RESET_BITS 12 +#define BIO_RESET_BITS 13 #define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag))) diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 5afc4f94d110..4c16c4a88d47 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -181,6 +181,7 @@ void ll_rw_block(int, int, struct buffer_head * bh[]); int sync_dirty_buffer(struct buffer_head *bh); int __sync_dirty_buffer(struct buffer_head *bh, int rw); void write_dirty_buffer(struct buffer_head *bh, int rw); +int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags); int submit_bh(int, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); -- cgit v1.2.3 From db3808c1bac64740b9d830fda92801ae65f1c851 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Mon, 29 Apr 2013 15:07:28 -0700 Subject: mm, vmalloc: move get_vmalloc_info() to vmalloc.c Now get_vmalloc_info() is in fs/proc/mmu.c. There is no reason that this code must be here and it's implementation needs vmlist_lock and it iterate a vmlist which may be internal data structure for vmalloc. It is preferable that vmlist_lock and vmlist is only used in vmalloc.c for maintainability. So move the code to vmalloc.c Signed-off-by: Joonsoo Kim Signed-off-by: Joonsoo Kim Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Atsushi Kumagai Cc: Chris Metcalf Cc: Dave Anderson Cc: Eric Biederman Cc: Guan Xuetao Cc: Ingo Molnar Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 6071e911c7f4..698b1e50d3a4 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -158,4 +158,22 @@ pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) # endif #endif +struct vmalloc_info { + unsigned long used; + unsigned long largest_chunk; +}; + +#ifdef CONFIG_MMU +#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) +extern void get_vmalloc_info(struct vmalloc_info *vmi); +#else + +#define VMALLOC_TOTAL 0UL +#define get_vmalloc_info(vmi) \ +do { \ + (vmi)->used = 0; \ + (vmi)->largest_chunk = 0; \ +} while (0) +#endif + #endif /* _LINUX_VMALLOC_H */ -- cgit v1.2.3 From f1c4069e1dc128dc8a851174cba2e273652e9216 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Mon, 29 Apr 2013 15:07:37 -0700 Subject: mm, vmalloc: export vmap_area_list, instead of vmlist Although our intention is to unexport internal structure entirely, but there is one exception for kexec. kexec dumps address of vmlist and makedumpfile uses this information. We are about to remove vmlist, then another way to retrieve information of vmalloc layer is needed for makedumpfile. For this purpose, we export vmap_area_list, instead of vmlist. Signed-off-by: Joonsoo Kim Signed-off-by: Joonsoo Kim Cc: Eric Biederman Cc: Dave Anderson Cc: Vivek Goyal Cc: Atsushi Kumagai Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Chris Metcalf Cc: Guan Xuetao Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 698b1e50d3a4..8a25f9081ed0 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -130,8 +130,7 @@ extern long vwrite(char *buf, char *addr, unsigned long count); /* * Internals. Dont't use.. */ -extern rwlock_t vmlist_lock; -extern struct vm_struct *vmlist; +extern struct list_head vmap_area_list; extern __init void vm_area_add_early(struct vm_struct *vm); extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); -- cgit v1.2.3 From 13ba3fcbbe31068b1ee7c39a0b58ecbed03c4d72 Mon Sep 17 00:00:00 2001 From: Atsushi Kumagai Date: Mon, 29 Apr 2013 15:07:40 -0700 Subject: kexec, vmalloc: export additional vmalloc layer information Now, vmap_area_list is exported as VMCOREINFO for makedumpfile to get the start address of vmalloc region (vmalloc_start). The address which contains vmalloc_start value is represented as below: vmap_area_list.next - OFFSET(vmap_area.list) + OFFSET(vmap_area.va_start) However, both OFFSET(vmap_area.va_start) and OFFSET(vmap_area.list) aren't exported as VMCOREINFO. So this patch exports them externally with small cleanup. [akpm@linux-foundation.org: vmalloc.h should include list.h for list_head] Signed-off-by: Atsushi Kumagai Cc: Joonsoo Kim Cc: Joonsoo Kim Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Atsushi Kumagai Cc: Chris Metcalf Cc: Dave Anderson Cc: Eric Biederman Cc: Guan Xuetao Cc: Ingo Molnar Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 8a25f9081ed0..7d5773a99f20 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -3,7 +3,9 @@ #include #include +#include #include /* pgprot_t */ +#include struct vm_area_struct; /* vma defining user mapping in mm_types.h */ @@ -35,6 +37,17 @@ struct vm_struct { const void *caller; }; +struct vmap_area { + unsigned long va_start; + unsigned long va_end; + unsigned long flags; + struct rb_node rb_node; /* address sorted rbtree */ + struct list_head list; /* address sorted list */ + struct list_head purge_list; /* "lazy purge" list */ + struct vm_struct *vm; + struct rcu_head rcu_head; +}; + /* * Highlevel APIs for driver use */ -- cgit v1.2.3 From 949f7ec5760b021da3cccc1eaeb0671270e4238f Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 29 Apr 2013 15:07:48 -0700 Subject: mm, hugetlb: include hugepages in meminfo Particularly in oom conditions, it's troublesome that hugetlb memory is not displayed. All other meminfo that is emitted will not add up to what is expected, and there is no artifact left in the kernel log to show that a potentially significant amount of memory is actually allocated as hugepages which are not available to be reclaimed. Booting with hugepages=8192 on the command line, this memory is now shown in oom conditions. For example, with echo m > /proc/sysrq-trigger: Node 0 hugepages_total=2048 hugepages_free=2048 hugepages_surp=0 hugepages_size=2048kB Node 1 hugepages_total=2048 hugepages_free=2048 hugepages_surp=0 hugepages_size=2048kB Node 2 hugepages_total=2048 hugepages_free=2048 hugepages_surp=0 hugepages_size=2048kB Node 3 hugepages_total=2048 hugepages_free=2048 hugepages_surp=0 hugepages_size=2048kB [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: David Rientjes Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 16e4e9a643fb..3a62df310f2e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -58,6 +58,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, int hugetlb_prefault(struct address_space *, struct vm_area_struct *); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(int, char *); +void hugetlb_show_meminfo(void); unsigned long hugetlb_total_pages(void); int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); @@ -114,6 +115,9 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) { } #define hugetlb_report_node_meminfo(n, buf) 0 +static inline void hugetlb_show_meminfo(void) +{ +} #define follow_huge_pmd(mm, addr, pmd, write) NULL #define follow_huge_pud(mm, addr, pud, write) NULL #define prepare_hugepage_range(file, addr, len) (-EINVAL) -- cgit v1.2.3 From 0aad818b2de455f1bfd7ef87c28cdbbaaed9a699 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 29 Apr 2013 15:07:50 -0700 Subject: sparse-vmemmap: specify vmemmap population range in bytes The sparse code, when asking the architecture to populate the vmemmap, specifies the section range as a starting page and a number of pages. This is an awkward interface, because none of the arch-specific code actually thinks of the range in terms of 'struct page' units and always translates it to bytes first. In addition, later patches mix huge page and regular page backing for the vmemmap. For this, they need to call vmemmap_populate_basepages() on sub-section ranges with PAGE_SIZE and PMD_SIZE in mind. But these are not necessarily multiples of the 'struct page' size and so this unit is too coarse. Just translate the section range into bytes once in the generic sparse code, then pass byte ranges down the stack. Signed-off-by: Johannes Weiner Cc: Ben Hutchings Cc: Bernhard Schmidt Cc: Johannes Weiner Cc: Russell King Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Benjamin Herrenschmidt Cc: "Luck, Tony" Cc: Heiko Carstens Acked-by: David S. Miller Tested-by: David S. Miller Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 98a44376e4f3..6d7266842abd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1764,12 +1764,12 @@ pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node); void *vmemmap_alloc_block(unsigned long size, int node); void *vmemmap_alloc_block_buf(unsigned long size, int node); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); -int vmemmap_populate_basepages(struct page *start_page, - unsigned long pages, int node); -int vmemmap_populate(struct page *start_page, unsigned long pages, int node); +int vmemmap_populate_basepages(unsigned long start, unsigned long end, + int node); +int vmemmap_populate(unsigned long start, unsigned long end, int node); void vmemmap_populate_print_last(void); #ifdef CONFIG_MEMORY_HOTPLUG -void vmemmap_free(struct page *memmap, unsigned long nr_pages); +void vmemmap_free(unsigned long start, unsigned long end); #endif void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long size); -- cgit v1.2.3 From f9872caf07c1c774034b8bddde7d4a3a7f4a6484 Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Mon, 29 Apr 2013 15:08:01 -0700 Subject: page_alloc: make setup_nr_node_ids() usable for arch init code powerpc and x86 were opencoding copies of setup_nr_node_ids(), which page_alloc provides but makes static. Make it avaliable to the archs in linux/mm.h. Signed-off-by: Cody P Schafer Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6d7266842abd..7aa11a6736eb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1816,5 +1816,11 @@ static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool page_is_guard(struct page *page) { return false; } #endif /* CONFIG_DEBUG_PAGEALLOC */ +#if MAX_NUMNODES > 1 +void __init setup_nr_node_ids(void); +#else +static inline void setup_nr_node_ids(void) {} +#endif + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ -- cgit v1.2.3 From f02c696800886382198df897b30bb796b46a8dae Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 29 Apr 2013 15:08:04 -0700 Subject: include/linux/memory.h: implement register_hotmemory_notifier() When CONFIG_MEMORY_HOTPLUG=n, we don't want the memory-hotplug notifier handlers to be included in the .o files, for space reasons. The existing hotplug_memory_notifier() tries to handle this but testing with gcc-4.4.4 shows that it doesn't work - the hotplug functions are still present in the .o files. So implement a new register_hotmemory_notifier() which is a copy of register_hotcpu_notifier(), and which actually works as desired. hotplug_memory_notifier() and register_memory_notifier() callsites should be converted to use this new register_hotmemory_notifier(). While we're there, let's repair the existing hotplug_memory_notifier(): it simply stomps on the register_memory_notifier() return value, so well-behaved code cannot check for errors. Apparently non of the existing callers were well-behaved :( Cc: Andrew Shewmaker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 14 ++++++++++---- include/linux/notifier.h | 5 ++++- 2 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 45e93b468878..0ff6598ee62f 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -18,6 +18,7 @@ #include #include #include +#include #define MIN_MEMORY_BLOCK_SIZE (1UL << SECTION_SIZE_BITS) @@ -127,13 +128,18 @@ enum mem_add_context { BOOT, HOTPLUG }; #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ #ifdef CONFIG_MEMORY_HOTPLUG -#define hotplug_memory_notifier(fn, pri) { \ +#define hotplug_memory_notifier(fn, pri) ({ \ static __meminitdata struct notifier_block fn##_mem_nb =\ - { .notifier_call = fn, .priority = pri }; \ + { .notifier_call = fn, .priority = pri };\ register_memory_notifier(&fn##_mem_nb); \ -} +}) +#define register_hotmemory_notifier(nb) register_memory_notifier(nb) +#define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) #else -#define hotplug_memory_notifier(fn, pri) do { } while (0) +#define hotplug_memory_notifier(fn, pri) (0) +/* These aren't inline functions due to a GCC bug. */ +#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) +#define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) #endif /* diff --git a/include/linux/notifier.h b/include/linux/notifier.h index d65746efc954..d14a4c362465 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -47,8 +47,11 @@ * runtime initialization. */ +typedef int (*notifier_fn_t)(struct notifier_block *nb, + unsigned long action, void *data); + struct notifier_block { - int (*notifier_call)(struct notifier_block *, unsigned long, void *); + notifier_fn_t notifier_call; struct notifier_block __rcu *next; int priority; }; -- cgit v1.2.3 From c9b1d0981fcce3d9976d7b7a56e4e0503bc610dd Mon Sep 17 00:00:00 2001 From: Andrew Shewmaker Date: Mon, 29 Apr 2013 15:08:10 -0700 Subject: mm: limit growth of 3% hardcoded other user reserve Add user_reserve_kbytes knob. Limit the growth of the memory reserved for other user processes to min(3% current process size, user_reserve_pages). Only about 8MB is necessary to enable recovery in the default mode, and only a few hundred MB are required even when overcommit is disabled. user_reserve_pages defaults to min(3% free pages, 128MB) I arrived at 128MB by taking the max VSZ of sshd, login, bash, and top ... then adding the RSS of each. This only affects OVERCOMMIT_NEVER mode. Background 1. user reserve __vm_enough_memory reserves a hardcoded 3% of the current process size for other applications when overcommit is disabled. This was done so that a user could recover if they launched a memory hogging process. Without the reserve, a user would easily run into a message such as: bash: fork: Cannot allocate memory 2. admin reserve Additionally, a hardcoded 3% of free memory is reserved for root in both overcommit 'guess' and 'never' modes. This was intended to prevent a scenario where root-cant-log-in and perform recovery operations. Note that this reserve shrinks, and doesn't guarantee a useful reserve. Motivation The two hardcoded memory reserves should be updated to account for current memory sizes. Also, the admin reserve would be more useful if it didn't shrink too much. When the current code was originally written, 1GB was considered "enterprise". Now the 3% reserve can grow to multiple GB on large memory systems, and it only needs to be a few hundred MB at most to enable a user or admin to recover a system with an unwanted memory hogging process. I've found that reducing these reserves is especially beneficial for a specific type of application load: * single application system * one or few processes (e.g. one per core) * allocating all available memory * not initializing every page immediately * long running I've run scientific clusters with this sort of load. A long running job sometimes failed many hours (weeks of CPU time) into a calculation. They weren't initializing all of their memory immediately, and they weren't using calloc, so I put systems into overcommit 'never' mode. These clusters run diskless and have no swap. However, with the current reserves, a user wishing to allocate as much memory as possible to one process may be prevented from using, for example, almost 2GB out of 32GB. The effect is less, but still significant when a user starts a job with one process per core. I have repeatedly seen a set of processes requesting the same amount of memory fail because one of them could not allocate the amount of memory a user would expect to be able to allocate. For example, Message Passing Interfce (MPI) processes, one per core. And it is similar for other parallel programming frameworks. Changing this reserve code will make the overcommit never mode more useful by allowing applications to allocate nearly all of the available memory. Also, the new admin_reserve_kbytes will be safer than the current behavior since the hardcoded 3% of available memory reserve can shrink to something useless in the case where applications have grabbed all available memory. Risks * "bash: fork: Cannot allocate memory" The downside of the first patch-- which creates a tunable user reserve that is only used in overcommit 'never' mode--is that an admin can set it so low that a user may not be able to kill their process, even if they already have a shell prompt. Of course, a user can get in the same predicament with the current 3% reserve--they just have to launch processes until 3% becomes negligible. * root-cant-log-in problem The second patch, adding the tunable rootuser_reserve_pages, allows the admin to shoot themselves in the foot by setting it too small. They can easily get the system into a state where root-can't-log-in. However, the new admin_reserve_kbytes will be safer than the current behavior since the hardcoded 3% of available memory reserve can shrink to something useless in the case where applications have grabbed all available memory. Alternatives * Memory cgroups provide a more flexible way to limit application memory. Not everyone wants to set up cgroups or deal with their overhead. * We could create a fourth overcommit mode which provides smaller reserves. The size of useful reserves may be drastically different depending on the whether the system is embedded or enterprise. * Force users to initialize all of their memory or use calloc. Some users don't want/expect the system to overcommit when they malloc. Overcommit 'never' mode is for this scenario, and it should work well. The new user and admin reserve tunables are simple to use, with low overhead compared to cgroups. The patches preserve current behavior where 3% of memory is less than 128MB, except that the admin reserve doesn't shrink to an unusable size under pressure. The code allows admins to tune for embedded and enterprise usage. FAQ * How is the root-cant-login problem addressed? What happens if admin_reserve_pages is set to 0? Root is free to shoot themselves in the foot by setting admin_reserve_kbytes too low. On x86_64, the minimum useful reserve is: 8MB for overcommit 'guess' 128MB for overcommit 'never' admin_reserve_pages defaults to min(3% free memory, 8MB) So, anyone switching to 'never' mode needs to adjust admin_reserve_pages. * How do you calculate a minimum useful reserve? A user or the admin needs enough memory to login and perform recovery operations, which includes, at a minimum: sshd or login + bash (or some other shell) + top (or ps, kill, etc.) For overcommit 'guess', we can sum resident set sizes (RSS) because we only need enough memory to handle what the recovery programs will typically use. On x86_64 this is about 8MB. For overcommit 'never', we can take the max of their virtual sizes (VSZ) and add the sum of their RSS. We use VSZ instead of RSS because mode forces us to ensure we can fulfill all of the requested memory allocations-- even if the programs only use a fraction of what they ask for. On x86_64 this is about 128MB. When swap is enabled, reserves are useful even when they are as small as 10MB, regardless of overcommit mode. When both swap and overcommit are disabled, then the admin should tune the reserves higher to be absolutley safe. Over 230MB each was safest in my testing. * What happens if user_reserve_pages is set to 0? Note, this only affects overcomitt 'never' mode. Then a user will be able to allocate all available memory minus admin_reserve_kbytes. However, they will easily see a message such as: "bash: fork: Cannot allocate memory" And they won't be able to recover/kill their application. The admin should be able to recover the system if admin_reserve_kbytes is set appropriately. * What's the difference between overcommit 'guess' and 'never'? "Guess" allows an allocation if there are enough free + reclaimable pages. It has a hardcoded 3% of free pages reserved for root. "Never" allows an allocation if there is enough swap + a configurable percentage (default is 50) of physical RAM. It has a hardcoded 3% of free pages reserved for root, like "Guess" mode. It also has a hardcoded 3% of the current process size reserved for additional applications. * Why is overcommit 'guess' not suitable even when an app eventually writes to every page? It takes free pages, file pages, available swap pages, reclaimable slab pages into consideration. In other words, these are all pages available, then why isn't overcommit suitable? Because it only looks at the present state of the system. It does not take into account the memory that other applications have malloced, but haven't initialized yet. It overcommits the system. Test Summary There was little change in behavior in the default overcommit 'guess' mode with swap enabled before and after the patch. This was expected. Systems run most predictably (i.e. no oom kills) in overcommit 'never' mode with swap enabled. This also allowed the most memory to be allocated to a user application. Overcommit 'guess' mode without swap is a bad idea. It is easy to crash the system. None of the other tested combinations crashed. This matches my experience on the Roadrunner supercomputer. Without the tunable user reserve, a system in overcommit 'never' mode and without swap does not allow the admin to recover, although the admin can. With the new tunable reserves, a system in overcommit 'never' mode and without swap can be configured to: 1. maximize user-allocatable memory, running close to the edge of recoverability 2. maximize recoverability, sacrificing allocatable memory to ensure that a user cannot take down a system Test Description Fedora 18 VM - 4 x86_64 cores, 5725MB RAM, 4GB Swap System is booted into multiuser console mode, with unnecessary services turned off. Caches were dropped before each test. Hogs are user memtester processes that attempt to allocate all free memory as reported by /proc/meminfo In overcommit 'never' mode, memory_ratio=100 Test Results 3.9.0-rc1-mm1 Overcommit | Swap | Hogs | MB Got/Wanted | OOMs | User Recovery | Admin Recovery ---------- ---- ---- ------------- ---- ------------- -------------- guess yes 1 5432/5432 no yes yes guess yes 4 5444/5444 1 yes yes guess no 1 5302/5449 no yes yes guess no 4 - crash no no never yes 1 5460/5460 1 yes yes never yes 4 5460/5460 1 yes yes never no 1 5218/5432 no no yes never no 4 5203/5448 no no yes 3.9.0-rc1-mm1-tunablereserves User and Admin Recovery show their respective reserves, if applicable. Overcommit | Swap | Hogs | MB Got/Wanted | OOMs | User Recovery | Admin Recovery ---------- ---- ---- ------------- ---- ------------- -------------- guess yes 1 5419/5419 no - yes 8MB yes guess yes 4 5436/5436 1 - yes 8MB yes guess no 1 5440/5440 * - yes 8MB yes guess no 4 - crash - no 8MB no * process would successfully mlock, then the oom killer would pick it never yes 1 5446/5446 no 10MB yes 20MB yes never yes 4 5456/5456 no 10MB yes 20MB yes never no 1 5387/5429 no 128MB no 8MB barely never no 1 5323/5428 no 226MB barely 8MB barely never no 1 5323/5428 no 226MB barely 8MB barely never no 1 5359/5448 no 10MB no 10MB barely never no 1 5323/5428 no 0MB no 10MB barely never no 1 5332/5428 no 0MB no 50MB yes never no 1 5293/5429 no 0MB no 90MB yes never no 1 5001/5427 no 230MB yes 338MB yes never no 4* 4998/5424 no 230MB yes 338MB yes * more memtesters were launched, able to allocate approximately another 100MB Future Work - Test larger memory systems. - Test an embedded image. - Test other architectures. - Time malloc microbenchmarks. - Would it be useful to be able to set overcommit policy for each memory cgroup? - Some lines are slightly above 80 chars. Perhaps define a macro to convert between pages and kb? Other places in the kernel do this. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: make init_user_reserve() static] Signed-off-by: Andrew Shewmaker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7aa11a6736eb..43cfaabbde40 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -44,6 +44,8 @@ extern int sysctl_legacy_va_layout; #include #include +extern unsigned long sysctl_user_reserve_kbytes; + #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) /* to align the pointer to the (next) page boundary */ -- cgit v1.2.3 From 4eeab4f5580d11bffedc697684b91b0bca0d5009 Mon Sep 17 00:00:00 2001 From: Andrew Shewmaker Date: Mon, 29 Apr 2013 15:08:11 -0700 Subject: mm: replace hardcoded 3% with admin_reserve_pages knob Add an admin_reserve_kbytes knob to allow admins to change the hardcoded memory reserve to something other than 3%, which may be multiple gigabytes on large memory systems. Only about 8MB is necessary to enable recovery in the default mode, and only a few hundred MB are required even when overcommit is disabled. This affects OVERCOMMIT_GUESS and OVERCOMMIT_NEVER. admin_reserve_kbytes is initialized to min(3% free pages, 8MB) I arrived at 8MB by summing the RSS of sshd or login, bash, and top. Please see first patch in this series for full background, motivation, testing, and full changelog. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: make init_admin_reserve() static] Signed-off-by: Andrew Shewmaker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 43cfaabbde40..c05d7cfbb6b9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -45,6 +45,7 @@ extern int sysctl_legacy_va_layout; #include extern unsigned long sysctl_user_reserve_kbytes; +extern unsigned long sysctl_admin_reserve_kbytes; #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) -- cgit v1.2.3 From f1cb08798e2497238b28f377bd131426f0b9835d Mon Sep 17 00:00:00 2001 From: Yijing Wang Date: Mon, 29 Apr 2013 15:08:14 -0700 Subject: mm: remove CONFIG_HOTPLUG ifdefs CONFIG_HOTPLUG is going away as an option, cleanup CONFIG_HOTPLUG ifdefs in mm files. Signed-off-by: Yijing Wang Acked-by: Greg Kroah-Hartman Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 5fd71a7d0dfd..c586679b6fef 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -48,13 +48,8 @@ static inline void count_vm_events(enum vm_event_item item, long delta) } extern void all_vm_events(unsigned long *); -#ifdef CONFIG_HOTPLUG + extern void vm_events_fold_cpu(int cpu); -#else -static inline void vm_events_fold_cpu(int cpu) -{ -} -#endif #else -- cgit v1.2.3 From 825f787bb49676083b97c1de1f8f2f8f26b5c908 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Mon, 29 Apr 2013 15:08:19 -0700 Subject: resource: add release_mem_region_adjustable() Add release_mem_region_adjustable(), which releases a requested region from a currently busy memory resource. This interface adjusts the matched memory resource accordingly even if the requested region does not match exactly but still fits into. This new interface is intended for memory hot-delete. During bootup, memory resources are inserted from the boot descriptor table, such as EFI Memory Table and e820. Each memory resource entry usually covers the whole contigous memory range. Memory hot-delete request, on the other hand, may target to a particular range of memory resource, and its size can be much smaller than the whole contiguous memory. Since the existing release interfaces like __release_region() require a requested region to be exactly matched to a resource entry, they do not allow a partial resource to be released. This new interface is restrictive (i.e. release under certain conditions), which is consistent with other release interfaces, __release_region() and __release_resource(). Additional release conditions, such as an overlapping region to a resource entry, can be supported after they are confirmed as valid cases. There is no change to the existing interfaces since their restriction is valid for I/O resources. [akpm@linux-foundation.org: use GFP_ATOMIC under write_lock()] [akpm@linux-foundation.org: switch back to GFP_KERNEL, less buggily] [akpm@linux-foundation.org: remove unneeded and wrong kfree(), per Toshi] Signed-off-by: Toshi Kani Reviewed-by : Yasuaki Ishimatsu Cc: David Rientjes Reviewed-by: Ram Pai Cc: T Makphaibulchoke Cc: Wen Congyang Cc: Tang Chen Cc: Jiang Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ioport.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 85ac9b9b72a2..89b7c24a36e9 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -192,6 +192,10 @@ extern struct resource * __request_region(struct resource *, extern int __check_region(struct resource *, resource_size_t, resource_size_t); extern void __release_region(struct resource *, resource_size_t, resource_size_t); +#ifdef CONFIG_MEMORY_HOTREMOVE +extern int release_mem_region_adjustable(struct resource *, resource_size_t, + resource_size_t); +#endif static inline int __deprecated check_region(resource_size_t s, resource_size_t n) -- cgit v1.2.3 From 4edd7ceff0662afde195da6f6c43e7cbe1ed2dc4 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 29 Apr 2013 15:08:22 -0700 Subject: mm, hotplug: avoid compiling memory hotremove functions when disabled __remove_pages() is only necessary for CONFIG_MEMORY_HOTREMOVE. PowerPC pseries will return -EOPNOTSUPP if unsupported. Adding an #ifdef causes several other functions it depends on to also become unnecessary, which saves in .text when disabled (it's disabled in most defconfigs besides powerpc, including x86). remove_memory_block() becomes static since it is not referenced outside of drivers/base/memory.c. Build tested on x86 and powerpc with CONFIG_MEMORY_HOTREMOVE both enabled and disabled. Signed-off-by: David Rientjes Acked-by: Toshi Kani Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Greg Kroah-Hartman Cc: Wen Congyang Cc: Tang Chen Cc: Yasuaki Ishimatsu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 3 ++- include/linux/memory_hotplug.h | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 0ff6598ee62f..73817af8b480 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -115,9 +115,10 @@ extern void unregister_memory_notifier(struct notifier_block *nb); extern int register_memory_isolate_notifier(struct notifier_block *nb); extern void unregister_memory_isolate_notifier(struct notifier_block *nb); extern int register_new_memory(int, struct mem_section *); +#ifdef CONFIG_MEMORY_HOTREMOVE extern int unregister_memory_section(struct mem_section *); +#endif extern int memory_dev_init(void); -extern int remove_memory_block(unsigned long, struct mem_section *, int); extern int memory_notify(unsigned long val, void *v); extern int memory_isolate_notify(unsigned long val, void *v); extern struct memory_block *find_memory_block_hinted(struct mem_section *, diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index b6a3be7d47bf..3e622c610925 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -97,13 +97,13 @@ extern void __online_page_free(struct page *page); #ifdef CONFIG_MEMORY_HOTREMOVE extern bool is_pageblock_removable_nolock(struct page *page); extern int arch_remove_memory(u64 start, u64 size); +extern int __remove_pages(struct zone *zone, unsigned long start_pfn, + unsigned long nr_pages); #endif /* CONFIG_MEMORY_HOTREMOVE */ /* reasonably generic interface to expand the physical pages in a zone */ extern int __add_pages(int nid, struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); -extern int __remove_pages(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages); #ifdef CONFIG_NUMA extern int memory_add_physaddr_to_nid(u64 start); -- cgit v1.2.3 From 70ddf637eebe47e61fb2be08a59315581b6d2f38 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Mon, 29 Apr 2013 15:08:31 -0700 Subject: memcg: add memory.pressure_level events With this patch userland applications that want to maintain the interactivity/memory allocation cost can use the pressure level notifications. The levels are defined like this: The "low" level means that the system is reclaiming memory for new allocations. Monitoring this reclaiming activity might be useful for maintaining cache level. Upon notification, the program (typically "Activity Manager") might analyze vmstat and act in advance (i.e. prematurely shutdown unimportant services). The "medium" level means that the system is experiencing medium memory pressure, the system might be making swap, paging out active file caches, etc. Upon this event applications may decide to further analyze vmstat/zoneinfo/memcg or internal memory usage statistics and free any resources that can be easily reconstructed or re-read from a disk. The "critical" level means that the system is actively thrashing, it is about to out of memory (OOM) or even the in-kernel OOM killer is on its way to trigger. Applications should do whatever they can to help the system. It might be too late to consult with vmstat or any other statistics, so it's advisable to take an immediate action. The events are propagated upward until the event is handled, i.e. the events are not pass-through. Here is what this means: for example you have three cgroups: A->B->C. Now you set up an event listener on cgroups A, B and C, and suppose group C experiences some pressure. In this situation, only group C will receive the notification, i.e. groups A and B will not receive it. This is done to avoid excessive "broadcasting" of messages, which disturbs the system and which is especially bad if we are low on memory or thrashing. So, organize the cgroups wisely, or propagate the events manually (or, ask us to implement the pass-through events, explaining why would you need them.) Performance wise, the memory pressure notifications feature itself is lightweight and does not require much of bookkeeping, in contrast to the rest of memcg features. Unfortunately, as of current memcg implementation, pages accounting is an inseparable part and cannot be turned off. The good news is that there are some efforts[1] to improve the situation; plus, implementing the same, fully API-compatible[2] interface for CONFIG_MEMCG=n case (e.g. embedded) is also a viable option, so it will not require any changes on the userland side. [1] http://permalink.gmane.org/gmane.linux.kernel.cgroups/6291 [2] http://lkml.org/lkml/2013/2/21/454 [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix CONFIG_CGROPUPS=n warnings] Signed-off-by: Anton Vorontsov Acked-by: Kirill A. Shutemov Acked-by: KAMEZAWA Hiroyuki Cc: Tejun Heo Cc: David Rientjes Cc: Pekka Enberg Cc: Mel Gorman Cc: Glauber Costa Cc: Michal Hocko Cc: Luiz Capitulino Cc: Greg Thelen Cc: Leonid Moiseichuk Cc: KOSAKI Motohiro Cc: Minchan Kim Cc: Bartlomiej Zolnierkiewicz Cc: John Stultz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmpressure.h | 47 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 include/linux/vmpressure.h (limited to 'include/linux') diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h new file mode 100644 index 000000000000..76be077340ea --- /dev/null +++ b/include/linux/vmpressure.h @@ -0,0 +1,47 @@ +#ifndef __LINUX_VMPRESSURE_H +#define __LINUX_VMPRESSURE_H + +#include +#include +#include +#include +#include +#include + +struct vmpressure { + unsigned long scanned; + unsigned long reclaimed; + /* The lock is used to keep the scanned/reclaimed above in sync. */ + struct mutex sr_lock; + + /* The list of vmpressure_event structs. */ + struct list_head events; + /* Have to grab the lock on events traversal or modifications. */ + struct mutex events_lock; + + struct work_struct work; +}; + +struct mem_cgroup; + +#ifdef CONFIG_MEMCG +extern void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, + unsigned long scanned, unsigned long reclaimed); +extern void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio); + +extern void vmpressure_init(struct vmpressure *vmpr); +extern struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg); +extern struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr); +extern struct vmpressure *css_to_vmpressure(struct cgroup_subsys_state *css); +extern int vmpressure_register_event(struct cgroup *cg, struct cftype *cft, + struct eventfd_ctx *eventfd, + const char *args); +extern void vmpressure_unregister_event(struct cgroup *cg, struct cftype *cft, + struct eventfd_ctx *eventfd); +#else +static inline void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, + unsigned long scanned, unsigned long reclaimed) {} +static inline void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, + int prio) {} +#endif /* CONFIG_MEMCG */ +#endif /* __LINUX_VMPRESSURE_H */ -- cgit v1.2.3 From 2f772e6cadf8ad8fca38927b17e6be028be669f5 Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Mon, 29 Apr 2013 15:08:34 -0700 Subject: mm: break up swap_writepage() for frontswap backends swap_writepage() is currently where frontswap hooks into the swap write path to capture pages with the frontswap_store() function. However, if a frontswap backend wants to "resume" the writeback of a page to the swap device, it can't call swap_writepage() as the page will simply reenter the backend. This patch separates swap_writepage() into a top and bottom half, the bottom half named __swap_writepage() to allow a frontswap backend, like zswap, to resume writeback beyond the frontswap_store() hook. __add_to_swap_cache() is also made non-static so that the page for which writeback is to be resumed can be added to the swap cache. Signed-off-by: Seth Jennings Signed-off-by: Bob Liu Acked-by: Minchan Kim Reviewed-by: Dan Magenheimer Cc: Konrad Rzeszutek Wilk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 2818a123f3ea..76f6c3b31235 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -330,6 +330,7 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t ent) /* linux/mm/page_io.c */ extern int swap_readpage(struct page *); extern int swap_writepage(struct page *page, struct writeback_control *wbc); +extern int __swap_writepage(struct page *page, struct writeback_control *wbc); extern int swap_set_page_dirty(struct page *page); extern void end_swap_bio_read(struct bio *bio, int err); @@ -345,6 +346,7 @@ extern unsigned long total_swapcache_pages(void); extern void show_swap_cache_info(void); extern int add_to_swap(struct page *); extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); +extern int __add_to_swap_cache(struct page *page, swp_entry_t entry); extern void __delete_from_swap_cache(struct page *); extern void delete_from_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); -- cgit v1.2.3 From 1eec6702a80e04416d528846a5ff2122484d95ec Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Mon, 29 Apr 2013 15:08:35 -0700 Subject: mm: allow for outstanding swap writeback accounting To prevent flooding the swap device with writebacks, frontswap backends need to count and limit the number of outstanding writebacks. The incrementing of the counter can be done before the call to __swap_writepage(). However, the caller must receive a notification when the writeback completes in order to decrement the counter. To achieve this functionality, this patch modifies __swap_writepage() to take the bio completion callback function as an argument. end_swap_bio_write(), the normal bio completion function, is also made non-static so that code doing the accounting can call it after the accounting is done. There should be no behavioural change to existing code. Signed-off-by: Seth Jennings Signed-off-by: Bob Liu Acked-by: Minchan Kim Reviewed-by: Dan Magenheimer Cc: Konrad Rzeszutek Wilk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 76f6c3b31235..b5b12c71a2af 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -330,7 +330,9 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t ent) /* linux/mm/page_io.c */ extern int swap_readpage(struct page *); extern int swap_writepage(struct page *page, struct writeback_control *wbc); -extern int __swap_writepage(struct page *page, struct writeback_control *wbc); +extern void end_swap_bio_write(struct bio *bio, int err); +extern int __swap_writepage(struct page *page, struct writeback_control *wbc, + void (*end_write_func)(struct bio *, int)); extern int swap_set_page_dirty(struct page *page); extern void end_swap_bio_read(struct bio *bio, int err); -- cgit v1.2.3 From 5bc7b8aca942d03bf2716ddcfcb4e0b57e43a1b8 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Mon, 29 Apr 2013 15:08:36 -0700 Subject: mm: thp: add split tail pages to shrink page list in page reclaim In page reclaim, huge page is split. split_huge_page() adds tail pages to LRU list. Since we are reclaiming a huge page, it's better we reclaim all subpages of the huge page instead of just the head page. This patch adds split tail pages to shrink page list so the tail pages can be reclaimed soon. Before this patch, run a swap workload: thp_fault_alloc 3492 thp_fault_fallback 608 thp_collapse_alloc 6 thp_collapse_alloc_failed 0 thp_split 916 With this patch: thp_fault_alloc 4085 thp_fault_fallback 16 thp_collapse_alloc 90 thp_collapse_alloc_failed 0 thp_split 1272 fallback allocation is reduced a lot. [akpm@linux-foundation.org: fix CONFIG_SWAP=n build] Signed-off-by: Shaohua Li Acked-by: Rik van Riel Acked-by: Minchan Kim Acked-by: Johannes Weiner Reviewed-by: Wanpeng Li Cc: Andrea Arcangeli Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 11 ++++++++++- include/linux/swap.h | 6 +++--- 2 files changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ee1c244a62a1..528454c2caa9 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -99,7 +99,11 @@ extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, extern int handle_pte_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *pte, pmd_t *pmd, unsigned int flags); -extern int split_huge_page(struct page *page); +extern int split_huge_page_to_list(struct page *page, struct list_head *list); +static inline int split_huge_page(struct page *page) +{ + return split_huge_page_to_list(page, NULL); +} extern void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd); #define split_huge_page_pmd(__vma, __address, __pmd) \ @@ -186,6 +190,11 @@ extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vm #define transparent_hugepage_enabled(__vma) 0 #define transparent_hugepage_flags 0UL +static inline int +split_huge_page_to_list(struct page *page, struct list_head *list) +{ + return 0; +} static inline int split_huge_page(struct page *page) { return 0; diff --git a/include/linux/swap.h b/include/linux/swap.h index b5b12c71a2af..1701ce4be746 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -236,7 +236,7 @@ extern unsigned long nr_free_pagecache_pages(void); extern void __lru_cache_add(struct page *, enum lru_list lru); extern void lru_cache_add_lru(struct page *, enum lru_list lru); extern void lru_add_page_tail(struct page *page, struct page *page_tail, - struct lruvec *lruvec); + struct lruvec *lruvec, struct list_head *head); extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); @@ -346,7 +346,7 @@ extern struct address_space swapper_spaces[]; #define swap_address_space(entry) (&swapper_spaces[swp_type(entry)]) extern unsigned long total_swapcache_pages(void); extern void show_swap_cache_info(void); -extern int add_to_swap(struct page *); +extern int add_to_swap(struct page *, struct list_head *list); extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); extern int __add_to_swap_cache(struct page *page, swp_entry_t entry); extern void __delete_from_swap_cache(struct page *); @@ -465,7 +465,7 @@ static inline struct page *lookup_swap_cache(swp_entry_t swp) return NULL; } -static inline int add_to_swap(struct page *page) +static inline int add_to_swap(struct page *page, struct list_head *list) { return 0; } -- cgit v1.2.3 From b4def3509d18c1db9198f92d4c35065e029a09a1 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Mon, 29 Apr 2013 15:08:52 -0700 Subject: mm, nobootmem: clean-up of free_low_memory_core_early() Remove unused argument and make function static, because there is no user outside of nobootmem.c Signed-off-by: Joonsoo Kim Cc: Yinghai Lu Acked-by: Johannes Weiner Cc: Jiang Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index cdc3bab01832..5f0b0e1f7c08 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -44,7 +44,6 @@ extern unsigned long init_bootmem_node(pg_data_t *pgdat, unsigned long endpfn); extern unsigned long init_bootmem(unsigned long addr, unsigned long memend); -extern unsigned long free_low_memory_core_early(int nodeid); extern unsigned long free_all_bootmem_node(pg_data_t *pgdat); extern unsigned long free_all_bootmem(void); -- cgit v1.2.3 From 9375db07adeaeea5f5ea7ca0463a8b371d71ddbb Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 29 Apr 2013 16:17:10 -0700 Subject: genalloc: add devres support, allow to find a managed pool by device This patch adds three exported functions to lib/genalloc.c: devm_gen_pool_create, dev_get_gen_pool, and of_get_named_gen_pool. devm_gen_pool_create is a managed version of gen_pool_create that keeps track of the pool via devres and allows the management code to automatically destroy it after device removal. dev_get_gen_pool retrieves the gen_pool for a given device, if it was created with devm_gen_pool_create, using devres_find. of_get_named_gen_pool retrieves the gen_pool for a given device node and property name, where the property must contain a phandle pointing to a platform device node. The corresponding platform device is then fed into dev_get_gen_pool and the resulting gen_pool is returned. [akpm@linux-foundation.org: make the of_get_named_gen_pool() stub static, fixing a zillion link errors] [akpm@linux-foundation.org: squish "struct device declared inside parameter list" warning] Signed-off-by: Philipp Zabel Acked-by: Grant Likely Tested-by: Michal Simek Cc: Fabio Estevam Cc: Matt Porter Cc: Dong Aisheng Cc: Greg Kroah-Hartman Cc: Rob Herring Cc: Paul Gortmaker Cc: Javier Martin Cc: Huang Shijie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/genalloc.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index dd7c569aacad..661d374aeb2d 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -29,6 +29,10 @@ #ifndef __GENALLOC_H__ #define __GENALLOC_H__ + +struct device; +struct device_node; + /** * Allocation callback function type definition * @map: Pointer to bitmap @@ -105,4 +109,18 @@ extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size, extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, void *data); +extern struct gen_pool *devm_gen_pool_create(struct device *dev, + int min_alloc_order, int nid); +extern struct gen_pool *dev_get_gen_pool(struct device *dev); + +#ifdef CONFIG_OF +extern struct gen_pool *of_get_named_gen_pool(struct device_node *np, + const char *propname, int index); +#else +static inline struct gen_pool *of_get_named_gen_pool(struct device_node *np, + const char *propname, int index) +{ + return NULL; +} +#endif #endif /* __GENALLOC_H__ */ -- cgit v1.2.3 From 657eee7d25fb1422422ca32d5619185ae56a245d Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 29 Apr 2013 16:17:14 -0700 Subject: media: coda: use genalloc API This patch depends on "genalloc: add devres support, allow to find a managed pool by device", which provides the of_get_named_gen_pool and dev_get_gen_pool functions. Signed-off-by: Philipp Zabel Acked-by: Javier Martin Acked-by: Grant Likely Cc: Michal Simek Cc: Dong Aisheng Cc: Fabio Estevam Cc: Greg Kroah-Hartman Cc: Huang Shijie Cc: Matt Porter Cc: Paul Gortmaker Cc: Rob Herring Cc: Shawn Guo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/platform_data/coda.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/platform_data/coda.h (limited to 'include/linux') diff --git a/include/linux/platform_data/coda.h b/include/linux/platform_data/coda.h new file mode 100644 index 000000000000..6ad4410d9e20 --- /dev/null +++ b/include/linux/platform_data/coda.h @@ -0,0 +1,18 @@ +/* + * Copyright (C) 2013 Philipp Zabel, Pengutronix + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#ifndef PLATFORM_CODA_H +#define PLATFORM_CODA_H + +struct device; + +struct coda_platform_data { + struct device *iram_dev; +}; + +#endif -- cgit v1.2.3 From 2fb0815c9ee6b9ac50e15dd8360ec76d9fa46a22 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Mon, 29 Apr 2013 16:17:15 -0700 Subject: gcc4: disable __compiletime_object_size for GCC 4.6+ __builtin_object_size is known to be broken on gcc 4.6+. See http://gcc.gnu.org/bugzilla/show_bug.cgi?id=48880 for details. This causes unnecssary build warnings and errors such as In function 'copy_from_user', inlined from 'sb16_copy_from_user' at sound/oss/sb_audio.c:878:22: arch/x86/include/asm/uaccess_32.h:211:26: error: call to 'copy_from_user_overflow' declared with attribute error: copy_from_user() buffer size is not provably correct make[3]: [sound/oss/sb_audio.o] Error 1 (ignored) Disable it where broken. Signed-off-by: Guenter Roeck Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index 68b162d92254..842de225055f 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -13,7 +13,7 @@ #define __must_check __attribute__((warn_unused_result)) #define __compiler_offsetof(a,b) __builtin_offsetof(a,b) -#if GCC_VERSION >= 40100 +#if GCC_VERSION >= 40100 && GCC_VERSION < 40600 # define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #endif -- cgit v1.2.3 From d0380e6c3c0f6edb986d8798a23acfaf33d5df23 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 29 Apr 2013 16:17:18 -0700 Subject: early_printk: consolidate random copies of identical code The early console implementations are the same all over the place. Move the print function to kernel/printk and get rid of the copies. [akpm@linux-foundation.org: arch/mips/kernel/early_printk.c needs kernel.h for va_list] [paul.gortmaker@windriver.com: sh4: make the bios early console support depend on EARLY_PRINTK] Signed-off-by: Thomas Gleixner Signed-off-by: Paul Gortmaker Cc: Russell King Acked-by: Mike Frysinger Cc: Michal Simek Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mundt Cc: "David S. Miller" Cc: Chris Metcalf Cc: Richard Weinberger Reviewed-by: Ingo Molnar Tested-by: Paul Gortmaker Cc: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/console.h | 1 + include/linux/printk.h | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 29680a8cda99..73bab0f58af5 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -141,6 +141,7 @@ struct console { for (con = console_drivers; con != NULL; con = con->next) extern int console_set_on_cmdline; +extern struct console *early_console; extern int add_preferred_console(char *name, int idx, char *options); extern int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, char *options); diff --git a/include/linux/printk.h b/include/linux/printk.h index 822171fcb1c8..1c35c23bccd7 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -95,8 +95,14 @@ int no_printk(const char *fmt, ...) return 0; } +#ifdef CONFIG_EARLY_PRINTK extern asmlinkage __printf(1, 2) void early_printk(const char *fmt, ...); +void early_vprintk(const char *fmt, va_list ap); +#else +static inline __printf(1, 2) __cold +void early_printk(const char *s, ...) { } +#endif #ifdef CONFIG_PRINTK asmlinkage __printf(5, 0) -- cgit v1.2.3 From 1b2c289b4f9018f4bd54d22ab54aaeda9181cd2a Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 29 Apr 2013 16:17:19 -0700 Subject: include/linux/printk.h: include stdarg.h printk.h uses va_list but doesn't include stdarg.h. Hence printk.h is unusable unless its includer has already included kernel.h (which includes stdarg.h). Remove the dependency by including stdarg.h in printk.h Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 1c35c23bccd7..4890fe62c011 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -1,6 +1,7 @@ #ifndef __KERNEL_PRINTK__ #define __KERNEL_PRINTK__ +#include #include #include -- cgit v1.2.3 From 600ffd33d09e3803d81607d3404a8cad709160e4 Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Mon, 29 Apr 2013 16:18:02 -0700 Subject: backlight: lp855x: convert a type of device name Configurable data, backlight device name is set to constant character type. Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/platform_data/lp855x.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/lp855x.h b/include/linux/platform_data/lp855x.h index 20ee8b221dbd..d135939d392a 100644 --- a/include/linux/platform_data/lp855x.h +++ b/include/linux/platform_data/lp855x.h @@ -128,7 +128,7 @@ struct lp855x_rom_data { * @rom_data : list of new eeprom/eprom registers */ struct lp855x_platform_data { - char *name; + const char *name; enum lp855x_brightness_ctrl_mode mode; u8 device_control; int initial_brightness; -- cgit v1.2.3 From 0b8185733966c1863b6b90ca2697327118ce5032 Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Mon, 29 Apr 2013 16:18:03 -0700 Subject: backlight: lp855x: move backlight mode platform data The brightness of LP855x devices is controlled by I2C register or PWM input . This mode was selected through the platform data, but it can be chosen by the driver internally without platform data configuration. How to decide the control mode: If the PWM period has specific value, the mode is PWM input. On the other hand, the mode is register-based. This mode selection is done on the _probe(). Move 'mode' from a header file to the driver private data structure, 'lp855 x'. And correlated code was replaced. Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/platform_data/lp855x.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/lp855x.h b/include/linux/platform_data/lp855x.h index d135939d392a..e0954dfea7ee 100644 --- a/include/linux/platform_data/lp855x.h +++ b/include/linux/platform_data/lp855x.h @@ -69,11 +69,6 @@ enum lp855x_chip_id { LP8557, }; -enum lp855x_brightness_ctrl_mode { - PWM_BASED = 1, - REGISTER_BASED, -}; - enum lp8550_brighntess_source { LP8550_PWM_ONLY, LP8550_I2C_ONLY = 2, @@ -116,7 +111,6 @@ struct lp855x_rom_data { /** * struct lp855x_platform_data * @name : Backlight driver name. If it is not defined, default name is set. - * @mode : brightness control by pwm or lp855x register * @device_control : value of DEVICE CONTROL register * @initial_brightness : initial value of backlight brightness * @period_ns : platform specific pwm period value. unit is nano. @@ -129,7 +123,6 @@ struct lp855x_rom_data { */ struct lp855x_platform_data { const char *name; - enum lp855x_brightness_ctrl_mode mode; u8 device_control; int initial_brightness; unsigned int period_ns; -- cgit v1.2.3 From 98e35be2badd7a499a001a0681d1904f8c56f3e6 Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Mon, 29 Apr 2013 16:18:04 -0700 Subject: backlight: lp855x: fix initial brightness type Valid range of the brightness is from 0 to 255, so initial brightness is changed from integer to u8. Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/platform_data/lp855x.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/lp855x.h b/include/linux/platform_data/lp855x.h index e0954dfea7ee..a4ed0bd65fda 100644 --- a/include/linux/platform_data/lp855x.h +++ b/include/linux/platform_data/lp855x.h @@ -124,7 +124,7 @@ struct lp855x_rom_data { struct lp855x_platform_data { const char *name; u8 device_control; - int initial_brightness; + u8 initial_brightness; unsigned int period_ns; u8 load_new_rom_data; int size_program; -- cgit v1.2.3 From c365e59d47b75c5f288f7e63d95dc0c9abcfe516 Mon Sep 17 00:00:00 2001 From: "Kim, Milo" Date: Mon, 29 Apr 2013 16:18:05 -0700 Subject: backlight: lp855x: remove duplicate platform data The 'load_new_rom_data' was used for checking whether new ROM data should be updated or not. However, we can decide it with 'size_program' data. If the size is greater than 0, it means updating ROM area is required. Otherwise, the default ROM data will be used. Therefore, this duplicate platform data can be removed. Signed-off-by: Milo(Woogyom) Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/platform_data/lp855x.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/lp855x.h b/include/linux/platform_data/lp855x.h index a4ed0bd65fda..ea3200527dd3 100644 --- a/include/linux/platform_data/lp855x.h +++ b/include/linux/platform_data/lp855x.h @@ -115,9 +115,6 @@ struct lp855x_rom_data { * @initial_brightness : initial value of backlight brightness * @period_ns : platform specific pwm period value. unit is nano. Only valid when mode is PWM_BASED. - * @load_new_rom_data : - 0 : use default configuration data - 1 : update values of eeprom or eprom registers on loading driver * @size_program : total size of lp855x_rom_data * @rom_data : list of new eeprom/eprom registers */ @@ -126,7 +123,6 @@ struct lp855x_platform_data { u8 device_control; u8 initial_brightness; unsigned int period_ns; - u8 load_new_rom_data; int size_program; struct lp855x_rom_data *rom_data; }; -- cgit v1.2.3 From 4d22f8c306233433bdf9298b2e7806e9c71674bc Mon Sep 17 00:00:00 2001 From: Matus Ujhelyi Date: Mon, 29 Apr 2013 16:18:08 -0700 Subject: drivers/video/backlight/tps65217_bl.c add default brightness value option Signed-off-by: Matus Ujhelyi Cc: Grant Likely Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mfd/tps65217.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h index 290762f93930..29eab2bd3dfa 100644 --- a/include/linux/mfd/tps65217.h +++ b/include/linux/mfd/tps65217.h @@ -228,6 +228,7 @@ enum tps65217_bl_fdim { struct tps65217_bl_pdata { enum tps65217_bl_isel isel; enum tps65217_bl_fdim fdim; + int dft_brightness; }; /** -- cgit v1.2.3 From 2e0fb404c86d6c86dc33e284310eb5d28d192dcf Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 29 Apr 2013 16:18:11 -0700 Subject: lib, net: make isodigit() public and use it There are at least two users of isodigit(). Let's make it a public function of ctype.h. Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ctype.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ctype.h b/include/linux/ctype.h index 8acfe312f947..653589e3e30e 100644 --- a/include/linux/ctype.h +++ b/include/linux/ctype.h @@ -61,4 +61,10 @@ static inline char _tolower(const char c) return c | 0x20; } +/* Fast check for octal digit */ +static inline int isodigit(const char c) +{ + return c >= '0' && c <= '7'; +} + #endif -- cgit v1.2.3 From 3e217b660281bbdf2db7e58725a4934b5635cb46 Mon Sep 17 00:00:00 2001 From: Jingoo Han Date: Mon, 29 Apr 2013 16:18:27 -0700 Subject: rtc: add devm_rtc_device_{register,unregister}() These functions allow the driver core to automatically clean up any allocation made by rtc drivers. Thus it simplifies the error paths. Signed-off-by: Jingoo Han Acked-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rtc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 580b24c8b8ca..d9557689bb8d 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -133,7 +133,13 @@ extern struct rtc_device *rtc_device_register(const char *name, struct device *dev, const struct rtc_class_ops *ops, struct module *owner); +extern struct rtc_device *devm_rtc_device_register(const char *name, + struct device *dev, + const struct rtc_class_ops *ops, + struct module *owner); extern void rtc_device_unregister(struct rtc_device *rtc); +extern void devm_rtc_device_unregister(struct device *dev, + struct rtc_device *rtc); extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm); -- cgit v1.2.3 From 6636a9944b9d3b6c4a0a27d5be5abc49ceca3381 Mon Sep 17 00:00:00 2001 From: Jingoo Han Date: Mon, 29 Apr 2013 16:18:33 -0700 Subject: drivers/rtc/class.c: use struct device as the first argument for devm_rtc_device_register() Other devm_* APIs use 'struct device *dev' as the first argument. Thus, in order to sync with other devm_* functions, struct device is used as the first argument for devm_rtc_device_register(). Signed-off-by: Jingoo Han Cc: Tejun Heo Cc: Alessandro Zummo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rtc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index d9557689bb8d..c2c28975293c 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -133,8 +133,8 @@ extern struct rtc_device *rtc_device_register(const char *name, struct device *dev, const struct rtc_class_ops *ops, struct module *owner); -extern struct rtc_device *devm_rtc_device_register(const char *name, - struct device *dev, +extern struct rtc_device *devm_rtc_device_register(struct device *dev, + const char *name, const struct rtc_class_ops *ops, struct module *owner); extern void rtc_device_unregister(struct rtc_device *rtc); -- cgit v1.2.3 From ea3983ace6b79c96e6ab3d3837e2eaf81ab881e2 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Mon, 29 Apr 2013 16:21:11 -0700 Subject: fat: restructure export_operations Define two nfs export_operation structures,one for 'stale_rw' mounts and the other for 'nostale_ro'. The latter uses i_pos as a basis for encoding and decoding file handles. Also, assign i_pos to kstat->ino. The logic for rebuilding the inode is added in the subsequent patches. Signed-off-by: Namjae Jeon Signed-off-by: Ravishankar N Signed-off-by: Amit Sahrawat Acked-by: OGAWA Hirofumi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/exportfs.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 5b9b5b317180..41b223a59a63 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -84,6 +84,17 @@ enum fid_type { */ FILEID_NILFS_WITH_PARENT = 0x62, + /* + * 32 bit generation number, 40 bit i_pos. + */ + FILEID_FAT_WITHOUT_PARENT = 0x71, + + /* + * 32 bit generation number, 40 bit i_pos, + * 32 bit parent generation number, 40 bit parent i_pos + */ + FILEID_FAT_WITH_PARENT = 0x72, + /* * Filesystems must not use 0xff file ID. */ -- cgit v1.2.3 From 3e6628c4b347a558965041290c5a92791dd4c741 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 29 Apr 2013 16:21:16 -0700 Subject: idr: introduce idr_alloc_cyclic() As Tejun points out, there are several users of the IDR facility that attempt to use it in a cyclic fashion. These users are likely to see -ENOSPC errors after the counter wraps one or more times however. This patchset adds a new idr_alloc_cyclic routine and converts several of these users to it. Many of these users are in obscure parts of the kernel, and I don't have a good way to test some of them. The change is pretty straightforward though, so hopefully it won't be an issue. There is one other cyclic user of idr_alloc that I didn't touch in ipc/util.c. That one is doing some strange stuff that I didn't quite understand, but it looks like it should probably be converted later somehow. This patch: Thus spake Tejun Heo: Ooh, BTW, the cyclic allocation is broken. It's prone to -ENOSPC after the first wraparound. There are several cyclic users in the kernel and I think it probably would be best to implement cyclic support in idr. This patch does that by adding new idr_alloc_cyclic function that such users in the kernel can use. With this, there's no need for a caller to keep track of the last value used as that's now tracked internally. This should prevent the ENOSPC problems that can hit when the "last allocated" counter exceeds INT_MAX. Later patches will convert existing cyclic users to the new interface. Signed-off-by: Jeff Layton Reviewed-by: Tejun Heo Cc: "David S. Miller" Cc: "J. Bruce Fields" Cc: Eric Paris Cc: Jack Morgenstein Cc: John McCutchan Cc: Neil Horman Cc: Or Gerlitz Cc: Robert Love Cc: Roland Dreier Cc: Sridhar Samudrala Cc: Steve Wise Cc: Tom Tucker Cc: Vlad Yasevich Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/idr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 2640c7e99e51..a470ac3ef49d 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -42,6 +42,7 @@ struct idr { struct idr_layer *id_free; int layers; /* only valid w/o concurrent changes */ int id_free_cnt; + int cur; /* current pos for cyclic allocation */ spinlock_t lock; }; @@ -75,6 +76,7 @@ struct idr { void *idr_find_slowpath(struct idr *idp, int id); void idr_preload(gfp_t gfp_mask); int idr_alloc(struct idr *idp, void *ptr, int start, int end, gfp_t gfp_mask); +int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask); int idr_for_each(struct idr *idp, int (*fn)(int id, void *p, void *data), void *data); void *idr_get_next(struct idr *idp, int *nextid); -- cgit v1.2.3 From a66c04b4534f9b25e1241dff9a9d94dff9fd66f8 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 29 Apr 2013 16:21:21 -0700 Subject: inotify: convert inotify_add_to_idr() to use idr_alloc_cyclic() Signed-off-by: Jeff Layton Cc: John McCutchan Cc: Robert Love Cc: Eric Paris Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fsnotify_backend.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index d5b0910d4961..4b2ee8d12f5e 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -157,7 +157,6 @@ struct fsnotify_group { struct inotify_group_private_data { spinlock_t idr_lock; struct idr idr; - u32 last_wd; struct user_struct *user; } inotify_data; #endif -- cgit v1.2.3 From 8d564368a9a3197f43e56dadf4a18c5738849f94 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Mon, 29 Apr 2013 16:21:42 -0700 Subject: net: rename random32 to prandom Commit 496f2f93b1cc ("random32: rename random32 to prandom") renamed random32() and srandom32() to prandom_u32() and prandom_seed() respectively. net_random() and net_srandom() need to be redefined with prandom_* in order to finish the naming transition. While I'm at it, enclose macro argument of net_srandom() with parenthesis. Signed-off-by: Akinobu Mita Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/net.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index aa1673160a45..99c9f0c103c2 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -240,8 +240,8 @@ do { \ #define net_dbg_ratelimited(fmt, ...) \ net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__) -#define net_random() random32() -#define net_srandom(seed) srandom32((__force u32)seed) +#define net_random() prandom_u32() +#define net_srandom(seed) prandom_seed((__force u32)(seed)) extern int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); -- cgit v1.2.3 From a5f04b9df1113e0c16271afe5e43028f0d763f13 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Wed, 17 Apr 2013 19:38:13 +0200 Subject: HID: debug: break out hid_dump_report() into hid-debug No semantic changes, but hid_dump_report should be in hid-debug.c, not in hid-core.c Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid-debug.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid-debug.h b/include/linux/hid-debug.h index 53744fa1c8b7..8663f216c563 100644 --- a/include/linux/hid-debug.h +++ b/include/linux/hid-debug.h @@ -22,11 +22,12 @@ * */ -#define HID_DEBUG_BUFSIZE 512 - #ifdef CONFIG_DEBUG_FS +#define HID_DEBUG_BUFSIZE 512 + void hid_dump_input(struct hid_device *, struct hid_usage *, __s32); +void hid_dump_report(struct hid_device *, int , u8 *, int); void hid_dump_device(struct hid_device *, struct seq_file *); void hid_dump_field(struct hid_field *, int, struct seq_file *); char *hid_resolv_usage(unsigned, struct seq_file *); @@ -50,6 +51,7 @@ struct hid_debug_list { #else #define hid_dump_input(a,b,c) do { } while (0) +#define hid_dump_report(a,b,c,d) do { } while (0) #define hid_dump_device(a,b) do { } while (0) #define hid_dump_field(a,b,c) do { } while (0) #define hid_resolv_usage(a,b) do { } while (0) -- cgit v1.2.3 From 2353f2bea307390e015493118e425152b8a5a431 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Tue, 16 Apr 2013 15:40:09 -0700 Subject: HID: protect hid_debug_list Accesses to hid_device->hid_debug_list are not serialized properly, which could result in SMP concurrency issues when HID debugfs events are accessesed by multiple userspace processess. Serialize all the list operations by a mutex. Spotted by Al Viro. Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index e14b465b1146..06579c72d195 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -512,6 +512,7 @@ struct hid_device { /* device report descriptor */ struct dentry *debug_rdesc; struct dentry *debug_events; struct list_head debug_list; + struct mutex debug_list_lock; wait_queue_head_t debug_wait; }; -- cgit v1.2.3 From 18a1053f7b85acdda2428c9f694101070cb8e62a Mon Sep 17 00:00:00 2001 From: "Shimoda, Yoshihiro" Date: Tue, 23 Apr 2013 20:00:12 +0900 Subject: sudmac: add support for SUDMAC Some Renesas USB modules have SUDMAC. This patch supports it using the shdma-base driver. Signed-off-by: Yoshihiro Shimoda Reviewed-by: Guennadi Liakhovetski Acked-by: Kuninori Morimoto Signed-off-by: Vinod Koul --- include/linux/sudmac.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) create mode 100644 include/linux/sudmac.h (limited to 'include/linux') diff --git a/include/linux/sudmac.h b/include/linux/sudmac.h new file mode 100644 index 000000000000..377b8a5788fa --- /dev/null +++ b/include/linux/sudmac.h @@ -0,0 +1,52 @@ +/* + * Header for the SUDMAC driver + * + * Copyright (C) 2013 Renesas Solutions Corp. + * + * This is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + */ +#ifndef SUDMAC_H +#define SUDMAC_H + +#include +#include +#include + +/* Used by slave DMA clients to request DMA to/from a specific peripheral */ +struct sudmac_slave { + struct shdma_slave shdma_slave; /* Set by the platform */ +}; + +/* + * Supplied by platforms to specify, how a DMA channel has to be configured for + * a certain peripheral + */ +struct sudmac_slave_config { + int slave_id; +}; + +struct sudmac_channel { + unsigned long offset; + unsigned long config; + unsigned long wait; /* The configuable range is 0 to 3 */ + unsigned long dint_end_bit; +}; + +struct sudmac_pdata { + const struct sudmac_slave_config *slave; + int slave_num; + const struct sudmac_channel *channel; + int channel_num; +}; + +/* Definitions for the sudmac_channel.config */ +#define SUDMAC_TX_BUFFER_MODE BIT(0) +#define SUDMAC_RX_END_MODE BIT(1) + +/* Definitions for the sudmac_channel.dint_end_bit */ +#define SUDMAC_DMA_BIT_CH0 BIT(0) +#define SUDMAC_DMA_BIT_CH1 BIT(1) + +#endif -- cgit v1.2.3 From 8a415b8c05f261a52f45f2271b6c4731376fd5b5 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Mon, 29 Apr 2013 20:08:02 +0100 Subject: efi, pstore: Read data from variable store before memcpy() Seiji reported getting empty dmesg-* files, because the data was never actually read in efi_pstore_read_func(), and so the memcpy() was copying garbage data. This patch necessitated adding __efivar_entry_get() which is callable between efivar_entry_iter_{begin,end}(). We can also delete __efivar_entry_size() because efi_pstore_read_func() was the only caller. Reported-by: Seiji Aguchi Tested-by: Seiji Aguchi Cc: Tony Luck Cc: Matthew Garrett Signed-off-by: Matt Fleming --- include/linux/efi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 3f7257f1f5e8..2bc0ad78d058 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -808,8 +808,9 @@ void efivar_entry_remove(struct efivar_entry *entry); int __efivar_entry_delete(struct efivar_entry *entry); int efivar_entry_delete(struct efivar_entry *entry); -int __efivar_entry_size(struct efivar_entry *entry, unsigned long *size); int efivar_entry_size(struct efivar_entry *entry, unsigned long *size); +int __efivar_entry_get(struct efivar_entry *entry, u32 *attributes, + unsigned long *size, void *data); int efivar_entry_get(struct efivar_entry *entry, u32 *attributes, unsigned long *size, void *data); int efivar_entry_set(struct efivar_entry *entry, u32 attributes, -- cgit v1.2.3 From f3002134158092178be81339ec5a22ff80e6c308 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Tue, 30 Apr 2013 11:35:07 +0200 Subject: Revert "math64: New div64_u64_rem helper" This reverts commit f792685006274a850e6cc0ea9ade275ccdfc90bc. The cputime scaling code was changed/fixed and does not need the div64_u64_rem() primitive anymore. It has no other users, so let's remove them. Signed-off-by: Stanislaw Gruszka Cc: Frederic Weisbecker Cc: rostedt@goodmis.org Cc: Linus Torvalds Cc: Dave Hansen Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1367314507-9728-4-git-send-email-sgruszka@redhat.com Signed-off-by: Ingo Molnar --- include/linux/math64.h | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index 931a619407bf..b8ba85544721 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -29,15 +29,6 @@ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder) return dividend / divisor; } -/** - * div64_u64_rem - unsigned 64bit divide with 64bit divisor - */ -static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder) -{ - *remainder = dividend % divisor; - return dividend / divisor; -} - /** * div64_u64 - unsigned 64bit divide with 64bit divisor */ @@ -70,16 +61,8 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) extern s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder); #endif -#ifndef div64_u64_rem -extern u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder); -#endif - #ifndef div64_u64 -static inline u64 div64_u64(u64 dividend, u64 divisor) -{ - u64 remainder; - return div64_u64_rem(dividend, divisor, &remainder); -} +extern u64 div64_u64(u64 dividend, u64 divisor); #endif #ifndef div64_s64 -- cgit v1.2.3 From dc9eb698f441889f2d7926b1cc6f1e14f0787f00 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 19 Apr 2013 13:23:09 -0400 Subject: audit: stop pushing loginid, uid, sessionid as arguments We always use current. Stop pulling this when the skb comes in and pushing it around as arguments. Just get it at the end when you need it. Signed-off-by: Eric Paris --- include/linux/audit.h | 3 +-- include/linux/tty.h | 6 ++---- 2 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index b26d7f121ac5..a3a50cca1efb 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -441,8 +441,7 @@ extern int audit_update_lsm_rules(void); extern int audit_filter_user(int type); extern int audit_filter_type(int type); extern int audit_receive_filter(int type, int pid, int seq, - void *data, size_t datasz, kuid_t loginuid, - u32 sessionid, u32 sid); + void *data, size_t datasz); extern int audit_enabled; #else /* CONFIG_AUDIT */ static inline __printf(4, 5) diff --git a/include/linux/tty.h b/include/linux/tty.h index 8db1b569c37a..78e378b3971c 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -517,8 +517,7 @@ extern void tty_audit_exit(void); extern void tty_audit_fork(struct signal_struct *sig); extern void tty_audit_tiocsti(struct tty_struct *tty, char ch); extern void tty_audit_push(struct tty_struct *tty); -extern int tty_audit_push_task(struct task_struct *tsk, - kuid_t loginuid, u32 sessionid); +extern int tty_audit_push_task(struct task_struct *tsk); #else static inline void tty_audit_add_data(struct tty_struct *tty, unsigned char *data, size_t size, unsigned icanon) @@ -536,8 +535,7 @@ static inline void tty_audit_fork(struct signal_struct *sig) static inline void tty_audit_push(struct tty_struct *tty) { } -static inline int tty_audit_push_task(struct task_struct *tsk, - kuid_t loginuid, u32 sessionid) +static inline int tty_audit_push_task(struct task_struct *tsk) { return 0; } -- cgit v1.2.3 From 152f497b9b5940f81de3205465840a5eb316458e Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 19 Apr 2013 13:56:11 -0400 Subject: audit: push loginuid and sessionid processing down Since we are always current, we can push a lot of this stuff to the bottom and get rid of useless interfaces and arguments. Signed-off-by: Eric Paris --- include/linux/tty.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 78e378b3971c..96d640b32cd8 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -517,7 +517,7 @@ extern void tty_audit_exit(void); extern void tty_audit_fork(struct signal_struct *sig); extern void tty_audit_tiocsti(struct tty_struct *tty, char ch); extern void tty_audit_push(struct tty_struct *tty); -extern int tty_audit_push_task(struct task_struct *tsk); +extern int tty_audit_push_current(void); #else static inline void tty_audit_add_data(struct tty_struct *tty, unsigned char *data, size_t size, unsigned icanon) @@ -535,7 +535,7 @@ static inline void tty_audit_fork(struct signal_struct *sig) static inline void tty_audit_push(struct tty_struct *tty) { } -static inline int tty_audit_push_task(struct task_struct *tsk) +static inline int tty_audit_push_current(void) { return 0; } -- cgit v1.2.3 From b122c3767c1d89763b4babca062c3171a71ed97c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 19 Apr 2013 15:00:33 -0400 Subject: audit: use a consistent audit helper to log lsm information We have a number of places we were reimplementing the same code to write out lsm labels. Just do it one darn place. Signed-off-by: Eric Paris --- include/linux/audit.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index a3a50cca1efb..e2dd9c124140 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -188,7 +188,7 @@ static inline int audit_get_sessionid(struct task_struct *tsk) return tsk->sessionid; } -extern void audit_log_task_context(struct audit_buffer *ab); +extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk); extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); @@ -344,8 +344,10 @@ static inline int audit_get_sessionid(struct task_struct *tsk) { return -1; } -static inline void audit_log_task_context(struct audit_buffer *ab) -{ } +static int void audit_log_task_context(struct audit_buffer *ab) +{ + return 0; +} static inline void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk) { } -- cgit v1.2.3 From 4d3fb709b285ac885c40950a837edbfc90029c5f Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Tue, 30 Apr 2013 09:53:34 -0400 Subject: helper for some session id stuff --- include/linux/audit.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index e2dd9c124140..b76bfc8efc25 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -89,6 +89,8 @@ extern int audit_classify_arch(int arch); struct filename; +extern void audit_log_session_info(struct audit_buffer *ab); + #ifdef CONFIG_AUDITSYSCALL /* These are defined in auditsc.c */ /* Public API */ -- cgit v1.2.3 From 46e959ea2969cc1668d09b0dc55226946cf781f1 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Fri, 3 May 2013 14:03:50 -0400 Subject: audit: add an option to control logging of passwords with pam_tty_audit Most commands are entered one line at a time and processed as complete lines in non-canonical mode. Commands that interactively require a password, enter canonical mode to do this while shutting off echo. This pair of features (icanon and !echo) can be used to avoid logging passwords by audit while still logging the rest of the command. Adding a member (log_passwd) to the struct audit_tty_status passed in by pam_tty_audit allows control of canonical mode without echo per task. Signed-off-by: Richard Guy Briggs Signed-off-by: Eric Paris --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d2112477ff5e..c4689fe92864 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -641,6 +641,7 @@ struct signal_struct { #endif #ifdef CONFIG_AUDIT unsigned audit_tty; + unsigned audit_tty_log_passwd; struct tty_audit_buf *tty_audit_buf; #endif #ifdef CONFIG_CGROUPS -- cgit v1.2.3 From b24a30a7305418ff138ff51776fc555ec57c011a Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Tue, 30 Apr 2013 15:30:32 -0400 Subject: audit: fix event coverage of AUDIT_ANOM_LINK The userspace audit tools didn't like the existing formatting of the AUDIT_ANOM_LINK event. It needed to be expanded to emit an AUDIT_PATH event as well, so this implements the change. The bulk of the patch is moving code out of auditsc.c into audit.c and audit.h for general use. It expands audit_log_name to include an optional "struct path" argument for the simple case of just needing to report a pathname. This also makes audit_log_task_info available when syscall auditing is not enabled, since it is needed in either case for process details. Signed-off-by: Kees Cook Reported-by: Steve Grubb --- include/linux/audit.h | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index b76bfc8efc25..469d11755e46 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -190,8 +190,6 @@ static inline int audit_get_sessionid(struct task_struct *tsk) return tsk->sessionid; } -extern int audit_log_task_context(struct audit_buffer *ab); -extern void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk); extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern int __audit_bprm(struct linux_binprm *bprm); @@ -346,13 +344,6 @@ static inline int audit_get_sessionid(struct task_struct *tsk) { return -1; } -static int void audit_log_task_context(struct audit_buffer *ab) -{ - return 0; -} -static inline void audit_log_task_info(struct audit_buffer *ab, - struct task_struct *tsk) -{ } static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, @@ -439,6 +430,10 @@ static inline void audit_log_secctx(struct audit_buffer *ab, u32 secid) { } #endif +extern int audit_log_task_context(struct audit_buffer *ab); +extern void audit_log_task_info(struct audit_buffer *ab, + struct task_struct *tsk); + extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ @@ -485,6 +480,13 @@ static inline void audit_log_link_denied(const char *string, { } static inline void audit_log_secctx(struct audit_buffer *ab, u32 secid) { } +static inline int audit_log_task_context(struct audit_buffer *ab) +{ + return 0; +} +static inline void audit_log_task_info(struct audit_buffer *ab, + struct task_struct *tsk) +{ } #define audit_enabled 0 #endif /* CONFIG_AUDIT */ static inline void audit_log_string(struct audit_buffer *ab, const char *buf) -- cgit v1.2.3 From ace6128d603d3f15238baba104d0b37ccf0b6c07 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Vincent=20Stehl=C3=A9?= Date: Tue, 30 Apr 2013 15:26:45 -0700 Subject: memory hotplug: fix warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following compilation warnings: mm/slab.c: In function `kmem_cache_init_late': mm/slab.c:1778:2: warning: statement with no effect [-Wunused-value] mm/page_cgroup.c: In function `page_cgroup_init': mm/page_cgroup.c:305:2: warning: statement with no effect [-Wunused-value] Signed-off-by: Vincent Stehlé Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 73817af8b480..85c31a8e2904 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -137,7 +137,7 @@ enum mem_add_context { BOOT, HOTPLUG }; #define register_hotmemory_notifier(nb) register_memory_notifier(nb) #define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) #else -#define hotplug_memory_notifier(fn, pri) (0) +#define hotplug_memory_notifier(fn, pri) ({ 0; }) /* These aren't inline functions due to a GCC bug. */ #define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) #define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) -- cgit v1.2.3 From 1e01c968db3d0aebd48e31db15f24516b03128df Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Tue, 30 Apr 2013 15:26:51 -0700 Subject: frontswap: make frontswap_init use a pointer for the ops This simplifies the code in the frontswap - we can get rid of the 'backend_registered' test and instead check against frontswap_ops. [v1: Rebase on top of 703ba7fe5e0 (ramster->zcache move] Signed-off-by: Konrad Rzeszutek Wilk Signed-off-by: Bob Liu Cc: Wanpeng Li Cc: Andor Daam Cc: Dan Magenheimer Cc: Florian Schmaus Cc: Minchan Kim Cc: Stefan Hengelein Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/frontswap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index 30442547b9e6..d4f29875c7cc 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -14,7 +14,7 @@ struct frontswap_ops { }; extern bool frontswap_enabled; -extern struct frontswap_ops +extern struct frontswap_ops * frontswap_register_ops(struct frontswap_ops *ops); extern void frontswap_shrink(unsigned long); extern unsigned long frontswap_curr_pages(void); -- cgit v1.2.3 From f066ea230a65f939afc354beae62716ab5f0e645 Mon Sep 17 00:00:00 2001 From: Bob Liu Date: Tue, 30 Apr 2013 15:26:53 -0700 Subject: mm: frontswap: cleanup code After allowing tmem backends to build/run as modules, frontswap_enabled always true if defined CONFIG_FRONTSWAP. But frontswap_test() depends on whether backend is registered, mv it into frontswap.c using fronstswap_ops to make the decision. frontswap_set/clear are not used outside frontswap, so don't export them. Signed-off-by: Bob Liu Cc: Wanpeng Li Cc: Andor Daam Cc: Dan Magenheimer Cc: Florian Schmaus Cc: Konrad Rzeszutek Wilk Cc: Minchan Kim Cc: Stefan Hengelein Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/frontswap.h | 28 +++------------------------- 1 file changed, 3 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index d4f29875c7cc..6c49e1eba552 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -22,6 +22,7 @@ extern void frontswap_writethrough(bool); #define FRONTSWAP_HAS_EXCLUSIVE_GETS extern void frontswap_tmem_exclusive_gets(bool); +extern bool __frontswap_test(struct swap_info_struct *, pgoff_t); extern void __frontswap_init(unsigned type); extern int __frontswap_store(struct page *page); extern int __frontswap_load(struct page *page); @@ -29,26 +30,11 @@ extern void __frontswap_invalidate_page(unsigned, pgoff_t); extern void __frontswap_invalidate_area(unsigned); #ifdef CONFIG_FRONTSWAP +#define frontswap_enabled (1) static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) { - bool ret = false; - - if (frontswap_enabled && sis->frontswap_map) - ret = test_bit(offset, sis->frontswap_map); - return ret; -} - -static inline void frontswap_set(struct swap_info_struct *sis, pgoff_t offset) -{ - if (frontswap_enabled && sis->frontswap_map) - set_bit(offset, sis->frontswap_map); -} - -static inline void frontswap_clear(struct swap_info_struct *sis, pgoff_t offset) -{ - if (frontswap_enabled && sis->frontswap_map) - clear_bit(offset, sis->frontswap_map); + return __frontswap_test(sis, offset); } static inline void frontswap_map_set(struct swap_info_struct *p, @@ -71,14 +57,6 @@ static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) return false; } -static inline void frontswap_set(struct swap_info_struct *sis, pgoff_t offset) -{ -} - -static inline void frontswap_clear(struct swap_info_struct *sis, pgoff_t offset) -{ -} - static inline void frontswap_map_set(struct swap_info_struct *p, unsigned long *map) { -- cgit v1.2.3 From 4f89849da22db9d0edb378acea65e23fcd546173 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 30 Apr 2013 15:26:54 -0700 Subject: frontswap: get rid of swap_lock dependency Frontswap initialization routine depends on swap_lock, which want to be atomic about frontswap's first appearance. IOW, frontswap is not present and will fail all calls OR frontswap is fully functional but if new swap_info_struct isn't registered by enable_swap_info, swap subsystem doesn't start I/O so there is no race between init procedure and page I/O working on frontswap. So let's remove unnecessary swap_lock dependency. Cc: Dan Magenheimer Signed-off-by: Minchan Kim [v1: Rebased on my branch, reworked to work with backends loading late] [v2: Added a check for !map] [v3: Made the invalidate path follow the init path] [v4: Address comments by Wanpeng Li ] Signed-off-by: Konrad Rzeszutek Wilk Signed-off-by: Bob Liu Cc: Wanpeng Li Cc: Andor Daam Cc: Florian Schmaus Cc: Stefan Hengelein Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/frontswap.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index 6c49e1eba552..8293262401de 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -23,7 +23,7 @@ extern void frontswap_writethrough(bool); extern void frontswap_tmem_exclusive_gets(bool); extern bool __frontswap_test(struct swap_info_struct *, pgoff_t); -extern void __frontswap_init(unsigned type); +extern void __frontswap_init(unsigned type, unsigned long *map); extern int __frontswap_store(struct page *page); extern int __frontswap_load(struct page *page); extern void __frontswap_invalidate_page(unsigned, pgoff_t); @@ -98,10 +98,10 @@ static inline void frontswap_invalidate_area(unsigned type) __frontswap_invalidate_area(type); } -static inline void frontswap_init(unsigned type) +static inline void frontswap_init(unsigned type, unsigned long *map) { if (frontswap_enabled) - __frontswap_init(type); + __frontswap_init(type, map); } #endif /* _LINUX_FRONTSWAP_H */ -- cgit v1.2.3 From 833f8662af9659508afc3cb80f09138eade378e2 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Tue, 30 Apr 2013 15:26:57 -0700 Subject: cleancache: Make cleancache_init use a pointer for the ops Instead of using a backend_registered to determine whether a backend is enabled. This allows us to remove the backend_register check and just do 'if (cleancache_ops)' [v1: Rebase on top of b97c4b430b0a (ramster->zcache move] Signed-off-by: Konrad Rzeszutek Wilk Signed-off-by: Bob Liu Cc: Wanpeng Li Cc: Andor Daam Cc: Dan Magenheimer Cc: Florian Schmaus Cc: Minchan Kim Cc: Stefan Hengelein Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cleancache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h index 42e55deee757..3af5ea839558 100644 --- a/include/linux/cleancache.h +++ b/include/linux/cleancache.h @@ -33,7 +33,7 @@ struct cleancache_ops { void (*invalidate_fs)(int); }; -extern struct cleancache_ops +extern struct cleancache_ops * cleancache_register_ops(struct cleancache_ops *ops); extern void __cleancache_init_fs(struct super_block *); extern void __cleancache_init_shared_fs(char *, struct super_block *); -- cgit v1.2.3 From ff610a1d55da22bf95bbc6a8b193e052169b34b7 Mon Sep 17 00:00:00 2001 From: Bob Liu Date: Tue, 30 Apr 2013 15:26:58 -0700 Subject: mm: cleancache: clean up cleancache_enabled cleancache_ops is used to decide whether backend is registered. So now cleancache_enabled is always true if defined CONFIG_CLEANCACHE. Signed-off-by: Bob Liu Cc: Wanpeng Li Cc: Andor Daam Cc: Dan Magenheimer Cc: Florian Schmaus Cc: Konrad Rzeszutek Wilk Cc: Minchan Kim Cc: Stefan Hengelein Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cleancache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h index 3af5ea839558..4ce9056b31a8 100644 --- a/include/linux/cleancache.h +++ b/include/linux/cleancache.h @@ -42,9 +42,9 @@ extern void __cleancache_put_page(struct page *); extern void __cleancache_invalidate_page(struct address_space *, struct page *); extern void __cleancache_invalidate_inode(struct address_space *); extern void __cleancache_invalidate_fs(struct super_block *); -extern int cleancache_enabled; #ifdef CONFIG_CLEANCACHE +#define cleancache_enabled (1) static inline bool cleancache_fs_enabled(struct page *page) { return page->mapping->host->i_sb->cleancache_poolid >= 0; -- cgit v1.2.3 From 196779b9b4ce1922afabdc20d0270720603bd46c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 30 Apr 2013 15:27:12 -0700 Subject: dump_stack: consolidate dump_stack() implementations and unify their behaviors Both dump_stack() and show_stack() are currently implemented by each architecture. show_stack(NULL, NULL) dumps the backtrace for the current task as does dump_stack(). On some archs, dump_stack() prints extra information - pid, utsname and so on - in addition to the backtrace while the two are identical on other archs. The usages in arch-independent code of the two functions indicate show_stack(NULL, NULL) should print out bare backtrace while dump_stack() is used for debugging purposes when something went wrong, so it does make sense to print additional information on the task which triggered dump_stack(). There's no reason to require archs to implement two separate but mostly identical functions. It leads to unnecessary subtle information. This patch expands the dummy fallback dump_stack() implementation in lib/dump_stack.c such that it prints out debug information (taken from x86) and invokes show_stack(NULL, NULL) and drops arch-specific dump_stack() implementations in all archs except blackfin. Blackfin's dump_stack() does something wonky that I don't understand. Debug information can be printed separately by calling dump_stack_print_info() so that arch-specific dump_stack() implementation can still emit the same debug information. This is used in blackfin. This patch brings the following behavior changes. * On some archs, an extra level in backtrace for show_stack() could be printed. This is because the top frame was determined in dump_stack() on those archs while generic dump_stack() can't do that reliably. It can be compensated by inlining dump_stack() but not sure whether that'd be necessary. * Most archs didn't use to print debug info on dump_stack(). They do now. An example WARN dump follows. WARNING: at kernel/workqueue.c:4841 init_workqueues+0x35/0x505() Hardware name: empty Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #9 0000000000000009 ffff88007c861e08 ffffffff81c614dc ffff88007c861e48 ffffffff8108f50f ffffffff82228240 0000000000000040 ffffffff8234a03c 0000000000000000 0000000000000000 0000000000000000 ffff88007c861e58 Call Trace: [] dump_stack+0x19/0x1b [] warn_slowpath_common+0x7f/0xc0 [] warn_slowpath_null+0x1a/0x20 [] init_workqueues+0x35/0x505 ... v2: CPU number added to the generic debug info as requested by s390 folks and dropped the s390 specific dump_stack(). This loses %ksp from the debug message which the maintainers think isn't important enough to keep the s390-specific dump_stack() implementation. dump_stack_print_info() is moved to kernel/printk.c from lib/dump_stack.c. Because linkage is per objecct file, dump_stack_print_info() living in the same lib file as generic dump_stack() means that archs which implement custom dump_stack() - at this point, only blackfin - can't use dump_stack_print_info() as that will bring in the generic version of dump_stack() too. v1 The v1 patch broke build on blackfin due to this issue. The build breakage was reported by Fengguang Wu. Signed-off-by: Tejun Heo Acked-by: David S. Miller Acked-by: Vineet Gupta Acked-by: Jesper Nilsson Acked-by: Vineet Gupta Acked-by: Martin Schwidefsky [s390 bits] Cc: Heiko Carstens Cc: Mike Frysinger Cc: Fengguang Wu Cc: Bjorn Helgaas Cc: Sam Ravnborg Acked-by: Richard Kuo [hexagon bits] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 4890fe62c011..7ce1f878cf6a 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -145,6 +145,7 @@ extern void wake_up_klogd(void); void log_buf_kexec_setup(void); void __init setup_log_buf(int early); +void dump_stack_print_info(const char *log_lvl); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -182,6 +183,10 @@ static inline void log_buf_kexec_setup(void) static inline void setup_log_buf(int early) { } + +static inline void dump_stack_print_info(const char *log_lvl) +{ +} #endif extern void dump_stack(void) __cold; -- cgit v1.2.3 From 98e5e1bf722c4f976a860aed06dd365a56a34ee0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 30 Apr 2013 15:27:15 -0700 Subject: dump_stack: implement arch-specific hardware description in task dumps x86 and ia64 can acquire extra hardware identification information from DMI and print it along with task dumps; however, the usage isn't consistent. * x86 show_regs() collects vendor, product and board strings and print them out with PID, comm and utsname. Some of the information is printed again later in the same dump. * warn_slowpath_common() explicitly accesses the DMI board and prints it out with "Hardware name:" label. This applies to both x86 and ia64 but is irrelevant on all other archs. * ia64 doesn't show DMI information on other non-WARN dumps. This patch introduces arch-specific hardware description used by dump_stack(). It can be set by calling dump_stack_set_arch_desc() during boot and, if exists, printed out in a separate line with "Hardware name:" label. dmi_set_dump_stack_arch_desc() is added which sets arch-specific description from DMI data. It uses dmi_ids_string[] which is set from dmi_present() used for DMI debug message. It is superset of the information x86 show_regs() is using. The function is called from x86 and ia64 boot code right after dmi_scan_machine(). This makes the explicit DMI handling in warn_slowpath_common() unnecessary. Removed. show_regs() isn't yet converted to use generic debug information printing and this patch doesn't remove the duplicate DMI handling in x86 show_regs(). The next patch will unify show_regs() handling and remove the duplication. An example WARN dump follows. WARNING: at kernel/workqueue.c:4841 init_workqueues+0x35/0x505() Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #3 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 0000000000000009 ffff88007c861e08 ffffffff81c614dc ffff88007c861e48 ffffffff8108f500 ffffffff82228240 0000000000000040 ffffffff8234a08e 0000000000000000 0000000000000000 0000000000000000 ffff88007c861e58 Call Trace: [] dump_stack+0x19/0x1b [] warn_slowpath_common+0x70/0xa0 [] warn_slowpath_null+0x1a/0x20 [] init_workqueues+0x35/0x505 ... v2: Use the same string as the debug message from dmi_present() which also contains BIOS information. Move hardware name into its own line as warn_slowpath_common() did. This change was suggested by Bjorn Helgaas. Signed-off-by: Tejun Heo Cc: Bjorn Helgaas Cc: David S. Miller Cc: Fengguang Wu Cc: Heiko Carstens Cc: Jesper Nilsson Cc: Martin Schwidefsky Cc: Mike Frysinger Cc: Vineet Gupta Cc: Sam Ravnborg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dmi.h | 2 ++ include/linux/printk.h | 5 +++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmi.h b/include/linux/dmi.h index f156cca25ad0..b6eb7a05d58e 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -99,6 +99,7 @@ extern const char * dmi_get_system_info(int field); extern const struct dmi_device * dmi_find_device(int type, const char *name, const struct dmi_device *from); extern void dmi_scan_machine(void); +extern void dmi_set_dump_stack_arch_desc(void); extern bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp); extern int dmi_name_in_vendors(const char *str); extern int dmi_name_in_serial(const char *str); @@ -114,6 +115,7 @@ static inline const char * dmi_get_system_info(int field) { return NULL; } static inline const struct dmi_device * dmi_find_device(int type, const char *name, const struct dmi_device *from) { return NULL; } static inline void dmi_scan_machine(void) { return; } +static inline void dmi_set_dump_stack_arch_desc(void) { } static inline bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp) { if (yearp) diff --git a/include/linux/printk.h b/include/linux/printk.h index 7ce1f878cf6a..47827c0a034d 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -145,6 +145,7 @@ extern void wake_up_klogd(void); void log_buf_kexec_setup(void); void __init setup_log_buf(int early); +void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); #else static inline __printf(1, 0) @@ -184,6 +185,10 @@ static inline void setup_log_buf(int early) { } +static inline void dump_stack_set_arch_desc(const char *fmt, ...) +{ +} + static inline void dump_stack_print_info(const char *log_lvl) { } -- cgit v1.2.3 From a43cb95d547a061ed5bf1acb28e0f5fd575e26c1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 30 Apr 2013 15:27:17 -0700 Subject: dump_stack: unify debug information printed by show_regs() show_regs() is inherently arch-dependent but it does make sense to print generic debug information and some archs already do albeit in slightly different forms. This patch introduces a generic function to print debug information from show_regs() so that different archs print out the same information and it's much easier to modify what's printed. show_regs_print_info() prints out the same debug info as dump_stack() does plus task and thread_info pointers. * Archs which didn't print debug info now do. alpha, arc, blackfin, c6x, cris, frv, h8300, hexagon, ia64, m32r, metag, microblaze, mn10300, openrisc, parisc, score, sh64, sparc, um, xtensa * Already prints debug info. Replaced with show_regs_print_info(). The printed information is superset of what used to be there. arm, arm64, avr32, mips, powerpc, sh32, tile, unicore32, x86 * s390 is special in that it used to print arch-specific information along with generic debug info. Heiko and Martin think that the arch-specific extra isn't worth keeping s390 specfic implementation. Converted to use the generic version. Note that now all archs print the debug info before actual register dumps. An example BUG() dump follows. kernel BUG at /work/os/work/kernel/workqueue.c:4841! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.9.0-rc1-work+ #7 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 task: ffff88007c85e040 ti: ffff88007c860000 task.ti: ffff88007c860000 RIP: 0010:[] [] init_workqueues+0x4/0x6 RSP: 0000:ffff88007c861ec8 EFLAGS: 00010246 RAX: ffff88007c861fd8 RBX: ffffffff824466a8 RCX: 0000000000000001 RDX: 0000000000000046 RSI: 0000000000000001 RDI: ffffffff8234a07a RBP: ffff88007c861ec8 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000000 R12: ffffffff8234a07a R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88007dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: ffff88015f7ff000 CR3: 00000000021f1000 CR4: 00000000000007f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Stack: ffff88007c861ef8 ffffffff81000312 ffffffff824466a8 ffff88007c85e650 0000000000000003 0000000000000000 ffff88007c861f38 ffffffff82335e5d ffff88007c862080 ffffffff8223d8c0 ffff88007c862080 ffffffff81c47760 Call Trace: [] do_one_initcall+0x122/0x170 [] kernel_init_freeable+0x9b/0x1c8 [] ? rest_init+0x140/0x140 [] kernel_init+0xe/0xf0 [] ret_from_fork+0x7c/0xb0 [] ? rest_init+0x140/0x140 ... v2: Typo fix in x86-32. v3: CPU number dropped from show_regs_print_info() as dump_stack_print_info() has been updated to print it. s390 specific implementation dropped as requested by s390 maintainers. Signed-off-by: Tejun Heo Acked-by: David S. Miller Acked-by: Jesper Nilsson Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Bjorn Helgaas Cc: Fengguang Wu Cc: Mike Frysinger Cc: Vineet Gupta Cc: Sam Ravnborg Acked-by: Chris Metcalf [tile bits] Acked-by: Richard Kuo [hexagon bits] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 47827c0a034d..6af944ab38f0 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -147,6 +147,7 @@ void log_buf_kexec_setup(void); void __init setup_log_buf(int early); void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); +void show_regs_print_info(const char *log_lvl); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -192,6 +193,10 @@ static inline void dump_stack_set_arch_desc(const char *fmt, ...) static inline void dump_stack_print_info(const char *log_lvl) { } + +static inline void show_regs_print_info(const char *log_lvl) +{ +} #endif extern void dump_stack(void) __cold; -- cgit v1.2.3 From cd42d559e45e3563c74403e453f8954b593db69d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 30 Apr 2013 15:27:21 -0700 Subject: kthread: implement probe_kthread_data() One of the problems that arise when converting dedicated custom threadpool to workqueue is that the shared worker pool used by workqueue anonimizes each worker making it more difficult to identify what the worker was doing on which target from the output of sysrq-t or debug dump from oops, BUG() and friends. For example, after writeback is converted to use workqueue instead of priviate thread pool, there's no easy to tell which backing device a writeback work item was working on at the time of task dump, which, according to our writeback brethren, is important in tracking down issues with a lot of mounted file systems on a lot of different devices. This patchset implements a way for a work function to mark its execution instance so that task dump of the worker task includes information to indicate what the work item was doing. An example WARN dump would look like the following. WARNING: at fs/fs-writeback.c:1015 bdi_writeback_workfn+0x2b4/0x3c0() Modules linked in: CPU: 0 Pid: 28 Comm: kworker/u18:0 Not tainted 3.9.0-rc1-work+ #24 Hardware name: empty empty/S3992, BIOS 080011 10/26/2007 Workqueue: writeback bdi_writeback_workfn (flush-8:16) ffffffff820a3a98 ffff88015b927cb8 ffffffff81c61855 ffff88015b927cf8 ffffffff8108f500 0000000000000000 ffff88007a171948 ffff88007a1716b0 ffff88015b49df00 ffff88015b8d3940 0000000000000000 ffff88015b927d08 Call Trace: [] dump_stack+0x19/0x1b [] warn_slowpath_common+0x70/0xa0 ... This patch: Implement probe_kthread_data() which returns kthread_data if accessible. The function is equivalent to kthread_data() except that the specified @task may not be a kthread or its vfork_done is already cleared rendering struct kthread inaccessible. In the former case, probe_kthread_data() may return any value. In the latter, NULL. This will be used to safely print debug information without affecting synchronization in the normal paths. Workqueue debug info printing on dump_stack() and friends will make use of it. Signed-off-by: Tejun Heo Cc: Oleg Nesterov Acked-by: Jan Kara Cc: Dave Chinner Cc: Ingo Molnar Cc: Jens Axboe Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kthread.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 8d816646f766..7dcef3317689 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -43,6 +43,7 @@ bool kthread_should_stop(void); bool kthread_should_park(void); bool kthread_freezable_should_stop(bool *was_frozen); void *kthread_data(struct task_struct *k); +void *probe_kthread_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); -- cgit v1.2.3 From 3d1cb2059d9374e58da481b783332cf191cb6620 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 30 Apr 2013 15:27:22 -0700 Subject: workqueue: include workqueue info when printing debug dump of a worker task One of the problems that arise when converting dedicated custom threadpool to workqueue is that the shared worker pool used by workqueue anonimizes each worker making it more difficult to identify what the worker was doing on which target from the output of sysrq-t or debug dump from oops, BUG() and friends. This patch implements set_worker_desc() which can be called from any workqueue work function to set its description. When the worker task is dumped for whatever reason - sysrq-t, WARN, BUG, oops, lockdep assertion and so on - the description will be printed out together with the workqueue name and the worker function pointer. The printing side is implemented by print_worker_info() which is called from functions in task dump paths - sched_show_task() and dump_stack_print_info(). print_worker_info() can be safely called on any task in any state as long as the task struct itself is accessible. It uses probe_*() functions to access worker fields. It may print garbage if something went very wrong, but it wouldn't cause (another) oops. The description is currently limited to 24bytes including the terminating \0. worker->desc_valid and workder->desc[] are added and the 64 bytes marker which was already incorrect before adding the new fields is moved to the correct position. Here's an example dump with writeback updated to set the bdi name as worker desc. Hardware name: Bochs Modules linked in: Pid: 7, comm: kworker/u9:0 Not tainted 3.9.0-rc1-work+ #1 Workqueue: writeback bdi_writeback_workfn (flush-8:0) ffffffff820a3ab0 ffff88000f6e9cb8 ffffffff81c61845 ffff88000f6e9cf8 ffffffff8108f50f 0000000000000000 0000000000000000 ffff88000cde16b0 ffff88000cde1aa8 ffff88001ee19240 ffff88000f6e9fd8 ffff88000f6e9d08 Call Trace: [] dump_stack+0x19/0x1b [] warn_slowpath_common+0x7f/0xc0 [] warn_slowpath_null+0x1a/0x20 [] bdi_writeback_workfn+0x2a0/0x3b0 ... Signed-off-by: Tejun Heo Cc: Peter Zijlstra Cc: Ingo Molnar Acked-by: Jan Kara Cc: Oleg Nesterov Cc: Jens Axboe Cc: Dave Chinner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/workqueue.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 717975639378..623488fdc1f5 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -92,6 +92,9 @@ enum { /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, WORK_BUSY_RUNNING = 1 << 1, + + /* maximum string length for set_worker_desc() */ + WORKER_DESC_LEN = 24, }; struct work_struct { @@ -447,6 +450,8 @@ extern void workqueue_set_max_active(struct workqueue_struct *wq, extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); +extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); +extern void print_worker_info(const char *log_lvl, struct task_struct *task); /** * queue_work - queue work on a workqueue -- cgit v1.2.3 From 3440a1ca99707f093e9568ba9762764d3162dd8f Mon Sep 17 00:00:00 2001 From: liguang Date: Tue, 30 Apr 2013 15:27:26 -0700 Subject: kernel/smp.c: remove 'priv' of call_single_data The 'priv' field is redundant; we can pass data via 'info'. Signed-off-by: liguang Cc: Peter Zijlstra Cc: Oleg Nesterov Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/smp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 3e07a7df6478..e6564c1dc552 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -20,7 +20,6 @@ struct call_single_data { smp_call_func_t func; void *info; u16 flags; - u16 priv; }; /* total number of cpus in this system (may exceed NR_CPUS) */ -- cgit v1.2.3 From 74e3d1e17b2e11d175970b85acd44f5927000ba2 Mon Sep 17 00:00:00 2001 From: Fan Du Date: Tue, 30 Apr 2013 15:27:27 -0700 Subject: include/linux/fs.h: disable preempt when acquire i_size_seqcount write lock Two rt tasks bind to one CPU core. The higher priority rt task A preempts a lower priority rt task B which has already taken the write seq lock, and then the higher priority rt task A try to acquire read seq lock, it's doomed to lockup. rt task A with lower priority: call write i_size_write rt task B with higher priority: call sync, and preempt task A write_seqcount_begin(&inode->i_size_seqcount); i_size_read inode->i_size = i_size; read_seqcount_begin <-- lockup here... So disable preempt when acquiring every i_size_seqcount *write* lock will cure the problem. Signed-off-by: Fan Du Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2c28271ab9d4..17d8b1596215 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -675,9 +675,11 @@ static inline loff_t i_size_read(const struct inode *inode) static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) + preempt_disable(); write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); + preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) preempt_disable(); inode->i_size = i_size; -- cgit v1.2.3 From 16c7fa05829e8b91db48e3539c5d6ff3c2b18a23 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 30 Apr 2013 15:27:30 -0700 Subject: lib/string_helpers: introduce generic string_unescape There are several places in kernel where modules unescapes input to convert C-Style Escape Sequences into byte codes. The patch provides generic implementation of such approach. Test cases are also included into the patch. [akpm@linux-foundation.org: clarify comment] [akpm@linux-foundation.org: export get_random_int() to modules] Signed-off-by: Andy Shevchenko Cc: Samuel Thibault Cc: Greg Kroah-Hartman Cc: Jason Baron Cc: Alexander Viro Cc: William Hubbs Cc: Chris Brannon Cc: Kirk Reiser Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string_helpers.h | 58 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index a3eb2f65b656..3eeee9672a4a 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -13,4 +13,62 @@ enum string_size_units { int string_get_size(u64 size, enum string_size_units units, char *buf, int len); +#define UNESCAPE_SPACE 0x01 +#define UNESCAPE_OCTAL 0x02 +#define UNESCAPE_HEX 0x04 +#define UNESCAPE_SPECIAL 0x08 +#define UNESCAPE_ANY \ + (UNESCAPE_SPACE | UNESCAPE_OCTAL | UNESCAPE_HEX | UNESCAPE_SPECIAL) + +/** + * string_unescape - unquote characters in the given string + * @src: source buffer (escaped) + * @dst: destination buffer (unescaped) + * @size: size of the destination buffer (0 to unlimit) + * @flags: combination of the flags (bitwise OR): + * %UNESCAPE_SPACE: + * '\f' - form feed + * '\n' - new line + * '\r' - carriage return + * '\t' - horizontal tab + * '\v' - vertical tab + * %UNESCAPE_OCTAL: + * '\NNN' - byte with octal value NNN (1 to 3 digits) + * %UNESCAPE_HEX: + * '\xHH' - byte with hexadecimal value HH (1 to 2 digits) + * %UNESCAPE_SPECIAL: + * '\"' - double quote + * '\\' - backslash + * '\a' - alert (BEL) + * '\e' - escape + * %UNESCAPE_ANY: + * all previous together + * + * Returns amount of characters processed to the destination buffer excluding + * trailing '\0'. + * + * Because the size of the output will be the same as or less than the size of + * the input, the transformation may be performed in place. + * + * Caller must provide valid source and destination pointers. Be aware that + * destination buffer will always be NULL-terminated. Source string must be + * NULL-terminated as well. + */ +int string_unescape(char *src, char *dst, size_t size, unsigned int flags); + +static inline int string_unescape_inplace(char *buf, unsigned int flags) +{ + return string_unescape(buf, buf, 0, flags); +} + +static inline int string_unescape_any(char *src, char *dst, size_t size) +{ + return string_unescape(src, dst, size, UNESCAPE_ANY); +} + +static inline int string_unescape_any_inplace(char *buf) +{ + return string_unescape_any(buf, buf, 0); +} + #endif -- cgit v1.2.3 From 1a0df59444972105f0d4c2b0c16ce414d70c420a Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Tue, 30 Apr 2013 15:27:34 -0700 Subject: kernel/compat.c: make do_sysinfo() static The only use outside of kernel/timer.c was in kernel/compat.c, so move compat_sys_sysinfo() next to sys_sysinfo() in kernel/timer.c. Signed-off-by: Stephen Rothwell Cc: Thomas Gleixner Cc: Guenter Roeck Cc: Al Viro Acked-by: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2dac79c39199..6d1844f393c0 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -798,6 +798,4 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD #endif -extern int do_sysinfo(struct sysinfo *info); - #endif -- cgit v1.2.3 From 938e4b22e2a7d0f6f3962e601339347b2d8e09f5 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Tue, 30 Apr 2013 15:28:02 -0700 Subject: usermodehelper: export call_usermodehelper_exec() and call_usermodehelper_setup() call_usermodehelper_setup() + call_usermodehelper_exec() need to be called instead of call_usermodehelper_fns() when the cleanup function needs to be called even when an ENOMEM error occurs. In this case using call_usermodehelper_fns() the user can't distinguish if the cleanup function was called or not. [akpm@linux-foundation.org: export call_usermodehelper_setup() to modules] Signed-off-by: Lucas De Marchi Reviewed-by: Oleg Nesterov Cc: David Howells Cc: James Morris Cc: Al Viro Cc: Tejun Heo Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmod.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 5398d5807075..7eebcf5d75f1 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -71,6 +71,14 @@ call_usermodehelper_fns(char *path, char **argv, char **envp, int wait, int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *), void *data); +extern struct subprocess_info * +call_usermodehelper_setup(char *path, char **argv, char **envp, gfp_t gfp_mask, + int (*init)(struct subprocess_info *info, struct cred *new), + void (*cleanup)(struct subprocess_info *), void *data); + +extern int +call_usermodehelper_exec(struct subprocess_info *info, int wait); + static inline int call_usermodehelper(char *path, char **argv, char **envp, int wait) { -- cgit v1.2.3 From 66e5b7e1948cdbdca2b0cc6ddc6d69ee84583fb4 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Tue, 30 Apr 2013 15:28:09 -0700 Subject: kmod: remove call_usermodehelper_fns() This function suffers from not being able to determine if the cleanup is called in case it returns -ENOMEM. Nobody is using it anymore, so let's remove it. Signed-off-by: Lucas De Marchi Cc: Oleg Nesterov Cc: David Howells Cc: James Morris Cc: Al Viro Cc: Tejun Heo Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmod.h | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 7eebcf5d75f1..0555cc66a15b 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -67,9 +67,7 @@ struct subprocess_info { }; extern int -call_usermodehelper_fns(char *path, char **argv, char **envp, int wait, - int (*init)(struct subprocess_info *info, struct cred *new), - void (*cleanup)(struct subprocess_info *), void *data); +call_usermodehelper(char *path, char **argv, char **envp, int wait); extern struct subprocess_info * call_usermodehelper_setup(char *path, char **argv, char **envp, gfp_t gfp_mask, @@ -79,13 +77,6 @@ call_usermodehelper_setup(char *path, char **argv, char **envp, gfp_t gfp_mask, extern int call_usermodehelper_exec(struct subprocess_info *info, int wait); -static inline int -call_usermodehelper(char *path, char **argv, char **envp, int wait) -{ - return call_usermodehelper_fns(path, argv, envp, wait, - NULL, NULL, NULL); -} - extern struct ctl_table usermodehelper_table[]; enum umh_disable_depth { -- cgit v1.2.3 From 403bad72b67d8b3f5a0240af5023adfa48132a65 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 30 Apr 2013 15:28:10 -0700 Subject: coredump: only SIGKILL should interrupt the coredumping task There are 2 well known and ancient problems with coredump/signals, and a lot of related bug reports: - do_coredump() clears TIF_SIGPENDING but of course this can't help if, say, SIGCHLD comes after that. In this case the coredump can fail unexpectedly. See for example wait_for_dump_helper()->signal_pending() check but there are other reasons. - At the same time, dumping a huge core on the slow media can take a lot of time/resources and there is no way to kill the coredumping task reliably. In particular this is not oom_kill-friendly. This patch tries to fix the 1st problem, and makes the preparation for the next changes. We add the new SIGNAL_GROUP_COREDUMP flag set by zap_threads() to indicate that this process dumps the core. prepare_signal() checks this flag and nacks any signal except SIGKILL. Note that this check tries to be conservative, in the long term we should probably treat the SIGNAL_GROUP_EXIT case equally but this needs more discussion. See marc.info/?l=linux-kernel&m=120508897917439 Notes: - recalc_sigpending() doesn't check SIGNAL_GROUP_COREDUMP. The patch assumes that dump_write/etc paths should never call it, but we can change it as well. - There is another source of TIF_SIGPENDING, freezer. This will be addressed separately. Signed-off-by: Oleg Nesterov Tested-by: Mandeep Singh Baines Cc: Ingo Molnar Cc: Neil Horman Cc: "Rafael J. Wysocki" Cc: Roland McGrath Cc: Tejun Heo Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 54ddcb82cddf..a22baf83c20c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -626,6 +626,7 @@ struct signal_struct { #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ +#define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */ /* * Pending notifications to parent. */ -- cgit v1.2.3 From e56fb2874015370e3b7f8d85051f6dce26051df9 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 30 Apr 2013 15:28:20 -0700 Subject: exec: do not abuse ->cred_guard_mutex in threadgroup_lock() threadgroup_lock() takes signal->cred_guard_mutex to ensure that thread_group_leader() is stable. This doesn't look nice, the scope of this lock in do_execve() is huge. And as Dave pointed out this can lead to deadlock, we have the following dependencies: do_execve: cred_guard_mutex -> i_mutex cgroup_mount: i_mutex -> cgroup_mutex attach_task_by_pid: cgroup_mutex -> cred_guard_mutex Change de_thread() to take threadgroup_change_begin() around the switch-the-leader code and change threadgroup_lock() to avoid ->cred_guard_mutex. Note that de_thread() can't sleep with ->group_rwsem held, this can obviously deadlock with the exiting leader if the writer is active, so it does threadgroup_change_end() before schedule(). Reported-by: Dave Jones Acked-by: Tejun Heo Acked-by: Li Zefan Signed-off-by: Oleg Nesterov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a22baf83c20c..6f950048b6e9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2249,27 +2249,18 @@ static inline void threadgroup_change_end(struct task_struct *tsk) * * Lock the threadgroup @tsk belongs to. No new task is allowed to enter * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or - * perform exec. This is useful for cases where the threadgroup needs to - * stay stable across blockable operations. + * change ->group_leader/pid. This is useful for cases where the threadgroup + * needs to stay stable across blockable operations. * * fork and exit paths explicitly call threadgroup_change_{begin|end}() for * synchronization. While held, no new task will be added to threadgroup * and no existing live task will have its PF_EXITING set. * - * During exec, a task goes and puts its thread group through unusual - * changes. After de-threading, exclusive access is assumed to resources - * which are usually shared by tasks in the same group - e.g. sighand may - * be replaced with a new one. Also, the exec'ing task takes over group - * leader role including its pid. Exclude these changes while locked by - * grabbing cred_guard_mutex which is used to synchronize exec path. + * de_thread() does threadgroup_change_{begin|end}() when a non-leader + * sub-thread becomes a new leader. */ static inline void threadgroup_lock(struct task_struct *tsk) { - /* - * exec uses exit for de-threading nesting group_rwsem inside - * cred_guard_mutex. Grab cred_guard_mutex first. - */ - mutex_lock(&tsk->signal->cred_guard_mutex); down_write(&tsk->signal->group_rwsem); } @@ -2282,7 +2273,6 @@ static inline void threadgroup_lock(struct task_struct *tsk) static inline void threadgroup_unlock(struct task_struct *tsk) { up_write(&tsk->signal->group_rwsem); - mutex_unlock(&tsk->signal->cred_guard_mutex); } #else static inline void threadgroup_change_begin(struct task_struct *tsk) {} -- cgit v1.2.3 From 5cc5445164c16d32bab2912fac28356ab07aa8b4 Mon Sep 17 00:00:00 2001 From: "Raphael S.Carvalho" Date: Tue, 30 Apr 2013 15:28:27 -0700 Subject: pid_namespace.c/.h: simplify defines Move BITS_PER_PAGE from pid_namespace.c to pid_namespace.h, since we can simplify the define PID_MAP_ENTRIES by using the BITS_PER_PAGE. [akpm@linux-foundation.org: kernel/pid.c:54:1: warning: "BITS_PER_PAGE" redefined] Signed-off-by: Raphael S.Carvalho Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pid_namespace.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 215e5e3dda10..8ac32836690e 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -13,7 +13,9 @@ struct pidmap { void *page; }; -#define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8) +#define BITS_PER_PAGE (PAGE_SIZE * 8) +#define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1) +#define PIDMAP_ENTRIES ((PID_MAX_LIMIT+BITS_PER_PAGE-1)/BITS_PER_PAGE) struct bsd_acct_struct; -- cgit v1.2.3 From 536b39ecf1b52ab71c2c126db0137611b9e1a4d4 Mon Sep 17 00:00:00 2001 From: "zhangwei(Jovi)" Date: Tue, 30 Apr 2013 15:28:40 -0700 Subject: kernel/relay.c: move FIX_SIZE macro into relay.c It's better to place FIX_SIZE macro in relay.c, instead of relay.h Signed-off-by: zhangwei(Jovi) Cc: Jens Axboe Cc: Al Viro Cc: Eric Dumazet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/relay.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/relay.h b/include/linux/relay.h index 91cacc34c159..d7c8359693c6 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -20,9 +20,6 @@ #include #include -/* Needs a _much_ better name... */ -#define FIX_SIZE(x) ((((x) - 1) & PAGE_MASK) + PAGE_SIZE) - /* * Tracks changes to rchan/rchan_buf structs */ -- cgit v1.2.3 From 78df969550e7187f4dcd70b737217dcbc8e9a06a Mon Sep 17 00:00:00 2001 From: Sumit Semwal Date: Fri, 22 Mar 2013 18:22:16 +0530 Subject: dma-buf: replace dma_buf_export() with dma_buf_export_named() For debugging purposes, it is useful to have a name-string added while exporting buffers. Hence, dma_buf_export() is replaced with dma_buf_export_named(), which additionally takes 'exp_name' as a parameter. For backward compatibility, and for lazy exporters who don't wish to name themselves, a #define dma_buf_export() is also made available, which adds a __FILE__ instead of 'exp_name'. Cc: Daniel Vetter [Thanks for the idea!] Reviewed-by: Daniel Vetter Signed-off-by: Sumit Semwal --- include/linux/dma-buf.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 9978b614a1aa..6f55c0424f12 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -112,6 +112,7 @@ struct dma_buf_ops { * @file: file pointer used for sharing buffers across, and for refcounting. * @attachments: list of dma_buf_attachment that denotes all devices attached. * @ops: dma_buf_ops associated with this buffer object. + * @exp_name: name of the exporter; useful for debugging. * @priv: exporter specific private data for this buffer object. */ struct dma_buf { @@ -123,6 +124,7 @@ struct dma_buf { struct mutex lock; unsigned vmapping_counter; void *vmap_ptr; + const char *exp_name; void *priv; }; @@ -162,8 +164,13 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, struct device *dev); void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *dmabuf_attach); -struct dma_buf *dma_buf_export(void *priv, const struct dma_buf_ops *ops, - size_t size, int flags); + +struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, + size_t size, int flags, const char *); + +#define dma_buf_export(priv, ops, size, flags) \ + dma_buf_export_named(priv, ops, size, flags, __FILE__) + int dma_buf_fd(struct dma_buf *dmabuf, int flags); struct dma_buf *dma_buf_get(int fd); void dma_buf_put(struct dma_buf *dmabuf); -- cgit v1.2.3 From b89e35636bc75b72d15a1af6d49798802aff77d5 Mon Sep 17 00:00:00 2001 From: Sumit Semwal Date: Thu, 4 Apr 2013 11:44:37 +0530 Subject: dma-buf: Add debugfs support Add debugfs support to make it easier to print debug information about the dma-buf buffers. Cc: Dave Airlie [minor fixes on init and warning fix] Cc: Dan Carpenter [remove double unlock in fail case] Signed-off-by: Sumit Semwal --- include/linux/dma-buf.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 6f55c0424f12..dfac5ed31120 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -113,6 +113,7 @@ struct dma_buf_ops { * @attachments: list of dma_buf_attachment that denotes all devices attached. * @ops: dma_buf_ops associated with this buffer object. * @exp_name: name of the exporter; useful for debugging. + * @list_node: node for dma_buf accounting and debugging. * @priv: exporter specific private data for this buffer object. */ struct dma_buf { @@ -125,6 +126,7 @@ struct dma_buf { unsigned vmapping_counter; void *vmap_ptr; const char *exp_name; + struct list_head list_node; void *priv; }; @@ -192,5 +194,6 @@ int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, unsigned long); void *dma_buf_vmap(struct dma_buf *); void dma_buf_vunmap(struct dma_buf *, void *vaddr); - +int dma_buf_debugfs_create_file(const char *name, + int (*write)(struct seq_file *)); #endif /* __DMA_BUF_H__ */ -- cgit v1.2.3 From d69f3bad4675ac519d41ca2b11e1c00ca115cecd Mon Sep 17 00:00:00 2001 From: Robin Holt Date: Tue, 30 Apr 2013 19:15:54 -0700 Subject: ipc: sysv shared memory limited to 8TiB Trying to run an application which was trying to put data into half of memory using shmget(), we found that having a shmall value below 8EiB-8TiB would prevent us from using anything more than 8TiB. By setting kernel.shmall greater than 8EiB-8TiB would make the job work. In the newseg() function, ns->shm_tot which, at 8TiB is INT_MAX. ipc/shm.c: 458 static int newseg(struct ipc_namespace *ns, struct ipc_params *params) 459 { ... 465 int numpages = (size + PAGE_SIZE -1) >> PAGE_SHIFT; ... 474 if (ns->shm_tot + numpages > ns->shm_ctlall) 475 return -ENOSPC; [akpm@linux-foundation.org: make ipc/shm.c:newseg()'s numpages size_t, not int] Signed-off-by: Robin Holt Reported-by: Alex Thorlton Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index ae221a7b5092..c4d870b0d5e6 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -43,8 +43,8 @@ struct ipc_namespace { size_t shm_ctlmax; size_t shm_ctlall; + unsigned long shm_tot; int shm_ctlmni; - int shm_tot; /* * Defines whether IPC_RMID is forced for _all_ shm segments regardless * of shmctl() -- cgit v1.2.3 From bd7c4b604a6cd707803c7c6ba142bfa131f9a9f3 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Tue, 30 Apr 2013 05:35:05 +0000 Subject: netpoll: convert mutex into a semaphore Bart Van Assche recently reported a warning to me: [] warn_slowpath_common+0x7f/0xc0 [] warn_slowpath_null+0x1a/0x20 [] mutex_trylock+0x16d/0x180 [] netpoll_poll_dev+0x49/0xc30 [] ? __alloc_skb+0x82/0x2a0 [] netpoll_send_skb_on_dev+0x265/0x410 [] netpoll_send_udp+0x28a/0x3a0 [] ? write_msg+0x53/0x110 [netconsole] [] write_msg+0xcf/0x110 [netconsole] [] call_console_drivers.constprop.17+0xa1/0x1c0 [] console_unlock+0x2d6/0x450 [] vprintk_emit+0x1ee/0x510 [] printk+0x4d/0x4f [] scsi_print_command+0x7d/0xe0 [scsi_mod] This resulted from my commit ca99ca14c which introduced a mutex_trylock operation in a path that could execute in interrupt context. When mutex debugging is enabled, the above warns the user when we are in fact exectuting in interrupt context interrupt context. After some discussion, It seems that a semaphore is the proper mechanism to use here. While mutexes are defined to be unusable in interrupt context, no such condition exists for semaphores (save for the fact that the non blocking api calls, like up and down_trylock must be used when in irq context). Signed-off-by: Neil Horman Reported-by: Bart Van Assche CC: Bart Van Assche CC: David Miller CC: netdev@vger.kernel.org Signed-off-by: David S. Miller --- include/linux/netpoll.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 9d7d8c64f7c8..fa2cb76a7029 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -40,7 +40,7 @@ struct netpoll_info { unsigned long rx_flags; spinlock_t rx_lock; - struct mutex dev_lock; + struct semaphore dev_lock; struct list_head rx_np; /* netpolls that registered an rx_hook */ struct sk_buff_head neigh_tx; /* list of neigh requests to reply to */ -- cgit v1.2.3 From 20074f357da4a637430aec2879c9d864c5d2c23c Mon Sep 17 00:00:00 2001 From: Xi Wang Date: Wed, 1 May 2013 16:24:08 -0400 Subject: filter: fix va_list build error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch fixes the following build error. In file included from include/linux/filter.h:52:0, from arch/arm/net/bpf_jit_32.c:14: include/linux/printk.h:54:2: error: unknown type name ‘va_list’ include/linux/printk.h:105:21: error: unknown type name ‘va_list’ include/linux/printk.h:108:30: error: unknown type name ‘va_list’ Signed-off-by: Xi Wang Signed-off-by: David S. Miller --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index d1248f401a56..c050dcc322a4 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -48,6 +48,7 @@ extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen); extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len); #ifdef CONFIG_BPF_JIT +#include #include #include -- cgit v1.2.3 From 271a15eabe094538d958dc68ccfc9c36b699247a Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 12 Apr 2013 00:38:51 +0100 Subject: proc: Supply PDE attribute setting accessor functions Supply accessor functions to set attributes in proc_dir_entry structs. The following are supplied: proc_set_size() and proc_set_user(). Signed-off-by: David Howells Acked-by: Mauro Carvalho Chehab cc: linuxppc-dev@lists.ozlabs.org cc: linux-media@vger.kernel.org cc: netdev@vger.kernel.org cc: linux-wireless@vger.kernel.org cc: linux-pci@vger.kernel.org cc: netfilter-devel@vger.kernel.org cc: alsa-devel@alsa-project.org Signed-off-by: Al Viro --- include/linux/proc_fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 805edacfc2fc..28a4d7e78803 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -130,6 +130,9 @@ static inline struct proc_dir_entry *proc_create(const char *name, umode_t mode, extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name, struct proc_dir_entry *parent); +extern void proc_set_size(struct proc_dir_entry *, loff_t); +extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); + extern struct file *proc_ns_fget(int fd); extern bool proc_ns_inode(struct inode *inode); @@ -158,6 +161,8 @@ static inline struct proc_dir_entry *proc_mkdir(const char *name, struct proc_dir_entry *parent) {return NULL;} static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent) { return NULL; } +static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} +static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {} struct tty_driver; static inline void proc_tty_register_driver(struct tty_driver *driver) {}; -- cgit v1.2.3 From 0bb80f240520c4148b623161e7856858c021696d Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 12 Apr 2013 01:50:06 +0100 Subject: proc: Split the namespace stuff out into linux/proc_ns.h Split the proc namespace stuff out into linux/proc_ns.h. Signed-off-by: David Howells cc: netdev@vger.kernel.org cc: Serge E. Hallyn cc: Eric W. Biederman Signed-off-by: Al Viro --- include/linux/proc_fs.h | 68 ++------------------------------------------- include/linux/proc_ns.h | 74 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 76 insertions(+), 66 deletions(-) create mode 100644 include/linux/proc_ns.h (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 28a4d7e78803..8f7d8f24141a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -6,6 +6,7 @@ #include #include #include +#include struct net; struct completion; @@ -23,18 +24,6 @@ struct mm_struct; /* Worst case buffer size needed for holding an integer. */ #define PROC_NUMBUF 13 -/* - * We always define these enumerators - */ - -enum { - PROC_ROOT_INO = 1, - PROC_IPC_INIT_INO = 0xEFFFFFFFU, - PROC_UTS_INIT_INO = 0xEFFFFFFEU, - PROC_USER_INIT_INO = 0xEFFFFFFDU, - PROC_PID_INIT_INO = 0xEFFFFFFCU, -}; - /* * This is not completely implemented yet. The idea is to * create an in-memory tree (like the actual /proc filesystem @@ -81,10 +70,6 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent); extern int remove_proc_subtree(const char *name, struct proc_dir_entry *parent); -struct pid_namespace; - -extern int pid_ns_prepare_proc(struct pid_namespace *ns); -extern void pid_ns_release_proc(struct pid_namespace *ns); /* * proc_tty.c @@ -132,12 +117,6 @@ extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name, extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); - -extern struct file *proc_ns_fget(int fd); -extern bool proc_ns_inode(struct inode *inode); - -extern int proc_alloc_inum(unsigned int *pino); -extern void proc_free_inum(unsigned int inum); #else static inline void proc_flush_task(struct task_struct *task) @@ -168,50 +147,8 @@ struct tty_driver; static inline void proc_tty_register_driver(struct tty_driver *driver) {}; static inline void proc_tty_unregister_driver(struct tty_driver *driver) {}; -static inline int pid_ns_prepare_proc(struct pid_namespace *ns) -{ - return 0; -} - -static inline void pid_ns_release_proc(struct pid_namespace *ns) -{ -} - -static inline struct file *proc_ns_fget(int fd) -{ - return ERR_PTR(-EINVAL); -} - -static inline bool proc_ns_inode(struct inode *inode) -{ - return false; -} - -static inline int proc_alloc_inum(unsigned int *inum) -{ - *inum = 1; - return 0; -} -static inline void proc_free_inum(unsigned int inum) -{ -} #endif /* CONFIG_PROC_FS */ -struct nsproxy; -struct proc_ns_operations { - const char *name; - int type; - void *(*get)(struct task_struct *task); - void (*put)(void *ns); - int (*install)(struct nsproxy *nsproxy, void *ns); - unsigned int (*inum)(void *ns); -}; -extern const struct proc_ns_operations netns_operations; -extern const struct proc_ns_operations utsns_operations; -extern const struct proc_ns_operations ipcns_operations; -extern const struct proc_ns_operations pidns_operations; -extern const struct proc_ns_operations userns_operations; -extern const struct proc_ns_operations mntns_operations; union proc_op { int (*proc_get_link)(struct dentry *, struct path *); @@ -231,8 +168,7 @@ struct proc_inode { struct proc_dir_entry *pde; struct ctl_table_header *sysctl; struct ctl_table *sysctl_entry; - void *ns; - const struct proc_ns_operations *ns_ops; + struct proc_ns ns; struct inode vfs_inode; }; diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h new file mode 100644 index 000000000000..34a1e105bef4 --- /dev/null +++ b/include/linux/proc_ns.h @@ -0,0 +1,74 @@ +/* + * procfs namespace bits + */ +#ifndef _LINUX_PROC_NS_H +#define _LINUX_PROC_NS_H + +struct pid_namespace; +struct nsproxy; + +struct proc_ns_operations { + const char *name; + int type; + void *(*get)(struct task_struct *task); + void (*put)(void *ns); + int (*install)(struct nsproxy *nsproxy, void *ns); + unsigned int (*inum)(void *ns); +}; + +struct proc_ns { + void *ns; + const struct proc_ns_operations *ns_ops; +}; + +extern const struct proc_ns_operations netns_operations; +extern const struct proc_ns_operations utsns_operations; +extern const struct proc_ns_operations ipcns_operations; +extern const struct proc_ns_operations pidns_operations; +extern const struct proc_ns_operations userns_operations; +extern const struct proc_ns_operations mntns_operations; + +/* + * We always define these enumerators + */ +enum { + PROC_ROOT_INO = 1, + PROC_IPC_INIT_INO = 0xEFFFFFFFU, + PROC_UTS_INIT_INO = 0xEFFFFFFEU, + PROC_USER_INIT_INO = 0xEFFFFFFDU, + PROC_PID_INIT_INO = 0xEFFFFFFCU, +}; + +#ifdef CONFIG_PROC_FS + +extern int pid_ns_prepare_proc(struct pid_namespace *ns); +extern void pid_ns_release_proc(struct pid_namespace *ns); +extern struct file *proc_ns_fget(int fd); +extern struct proc_ns *get_proc_ns(struct inode *); +extern int proc_alloc_inum(unsigned int *pino); +extern void proc_free_inum(unsigned int inum); +extern bool proc_ns_inode(struct inode *inode); + +#else /* CONFIG_PROC_FS */ + +static inline int pid_ns_prepare_proc(struct pid_namespace *ns) { return 0; } +static inline void pid_ns_release_proc(struct pid_namespace *ns) {} + +static inline struct file *proc_ns_fget(int fd) +{ + return ERR_PTR(-EINVAL); +} + +static inline struct proc_ns *get_proc_ns(struct inode *inode) { return NULL; } + +static inline int proc_alloc_inum(unsigned int *inum) +{ + *inum = 1; + return 0; +} +static inline void proc_free_inum(unsigned int inum) {} +static inline bool proc_ns_inode(struct inode *inode) { return false; } + +#endif /* CONFIG_PROC_FS */ + +#endif /* _LINUX_PROC_NS_H */ -- cgit v1.2.3 From 4abfd0298900851930310e5d736a7f3a105089ec Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 12 Apr 2013 02:09:03 +0100 Subject: proc: Move PDE_NET() to fs/proc/proc_net.c Move PDE_NET() to fs/proc/proc_net.c as that's where the only user is. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/proc_fs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 8f7d8f24141a..33772248a3b1 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -187,11 +187,6 @@ static inline void *PDE_DATA(const struct inode *inode) return PROC_I(inode)->pde->data; } -static inline struct net *PDE_NET(struct proc_dir_entry *pde) -{ - return pde->parent->data; -} - #include void render_sigset_t(struct seq_file *m, const char *header, sigset_t *set); -- cgit v1.2.3 From 34db8aaf0f95ffac407d39da22972b38da631db4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 12 Apr 2013 02:29:19 +0100 Subject: proc: Move some bits from linux/proc_fs.h to linux/{of.h,signal.h,tty.h} Move some bits from linux/proc_fs.h to linux/of.h, signal.h and tty.h. Also move proc_tty_init() and proc_device_tree_init() to fs/proc/internal.h as they're internal to procfs. Signed-off-by: David Howells Acked-by: Greg Kroah-Hartman Acked-by: Grant Likely cc: devicetree-discuss@lists.ozlabs.org cc: linux-arch@vger.kernel.org cc: Greg Kroah-Hartman cc: Jri Slaby Signed-off-by: Al Viro --- include/linux/of.h | 10 ++++++++++ include/linux/proc_fs.h | 37 ------------------------------------- include/linux/signal.h | 5 +++++ include/linux/tty.h | 7 +++++++ 4 files changed, 22 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index a0f129284948..2d25ff8fe39a 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -540,4 +540,14 @@ static inline int of_property_read_u32(const struct device_node *np, return of_property_read_u32_array(np, propname, out_value, 1); } +#if defined(CONFIG_PROC_FS) && defined(CONFIG_PROC_DEVICETREE) +extern void proc_device_tree_add_node(struct device_node *, struct proc_dir_entry *); +extern void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop); +extern void proc_device_tree_remove_prop(struct proc_dir_entry *pde, + struct property *prop); +extern void proc_device_tree_update_prop(struct proc_dir_entry *pde, + struct property *newprop, + struct property *oldprop); +#endif + #endif /* _LINUX_OF_H */ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 33772248a3b1..80d9e24a79ac 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -70,36 +70,6 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent); extern int remove_proc_subtree(const char *name, struct proc_dir_entry *parent); - -/* - * proc_tty.c - */ -struct tty_driver; -#ifdef CONFIG_TTY -extern void proc_tty_init(void); -#else -static inline void proc_tty_init(void) -{ } -#endif -extern void proc_tty_register_driver(struct tty_driver *driver); -extern void proc_tty_unregister_driver(struct tty_driver *driver); - -/* - * proc_devtree.c - */ -#ifdef CONFIG_PROC_DEVICETREE -struct device_node; -struct property; -extern void proc_device_tree_init(void); -extern void proc_device_tree_add_node(struct device_node *, struct proc_dir_entry *); -extern void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop); -extern void proc_device_tree_remove_prop(struct proc_dir_entry *pde, - struct property *prop); -extern void proc_device_tree_update_prop(struct proc_dir_entry *pde, - struct property *newprop, - struct property *oldprop); -#endif /* CONFIG_PROC_DEVICETREE */ - extern struct proc_dir_entry *proc_symlink(const char *, struct proc_dir_entry *, const char *); extern struct proc_dir_entry *proc_mkdir(const char *,struct proc_dir_entry *); @@ -143,10 +113,6 @@ static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {} -struct tty_driver; -static inline void proc_tty_register_driver(struct tty_driver *driver) {}; -static inline void proc_tty_unregister_driver(struct tty_driver *driver) {}; - #endif /* CONFIG_PROC_FS */ @@ -187,7 +153,4 @@ static inline void *PDE_DATA(const struct inode *inode) return PROC_I(inode)->pde->data; } -#include - -void render_sigset_t(struct seq_file *m, const char *header, sigset_t *set); #endif /* _LINUX_PROC_FS_H */ diff --git a/include/linux/signal.h b/include/linux/signal.h index a2dcb94ea49d..1135e3696e81 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -434,4 +434,9 @@ void signals_init(void); int restore_altstack(const stack_t __user *); int __save_altstack(stack_t __user *, unsigned long); +#ifdef CONFIG_PROC_FS +struct seq_file; +extern void render_sigset_t(struct seq_file *, const char *, sigset_t *); +#endif + #endif /* _LINUX_SIGNAL_H */ diff --git a/include/linux/tty.h b/include/linux/tty.h index c75d886b0307..e014fb1a84bd 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -658,5 +658,12 @@ do { \ finish_wait(&wq, &__wait); \ } while (0) +#ifdef CONFIG_PROC_FS +extern void proc_tty_register_driver(struct tty_driver *); +extern void proc_tty_unregister_driver(struct tty_driver *); +#else +static inline void proc_tty_register_driver(struct tty_driver *d) {} +static inline void proc_tty_unregister_driver(struct tty_driver *d) {} +#endif #endif -- cgit v1.2.3 From 270b5ac2151707c25d3327722c5badfbd95945bc Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 12 Apr 2013 02:48:30 +0100 Subject: proc: Add proc_mkdir_data() Add proc_mkdir_data() to allow procfs directories to be created that are annotated at the time of creation with private data rather than doing this post-creation. This means no access is then required to the proc_dir_entry struct to set this. Signed-off-by: David Howells Acked-by: Mauro Carvalho Chehab Acked-by: Greg Kroah-Hartman cc: Neela Syam Kolli cc: Jerry Chuang cc: linux-scsi@vger.kernel.org cc: devel@driverdev.osuosl.org cc: linux-wireless@vger.kernel.org Signed-off-by: Al Viro --- include/linux/proc_fs.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 80d9e24a79ac..a0fb1c2f1d8e 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -73,6 +73,8 @@ extern int remove_proc_subtree(const char *name, struct proc_dir_entry *parent); extern struct proc_dir_entry *proc_symlink(const char *, struct proc_dir_entry *, const char *); extern struct proc_dir_entry *proc_mkdir(const char *,struct proc_dir_entry *); +extern struct proc_dir_entry *proc_mkdir_data(const char *, umode_t, + struct proc_dir_entry *, void *); extern struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent); @@ -82,9 +84,6 @@ static inline struct proc_dir_entry *proc_create(const char *name, umode_t mode, return proc_create_data(name, mode, parent, proc_fops, NULL); } -extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name, - struct proc_dir_entry *parent); - extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); #else @@ -108,6 +107,8 @@ static inline struct proc_dir_entry *proc_symlink(const char *name, struct proc_dir_entry *parent,const char *dest) {return NULL;} static inline struct proc_dir_entry *proc_mkdir(const char *name, struct proc_dir_entry *parent) {return NULL;} +static inline struct proc_dir_entry *proc_mkdir_data(const char *name, + umode_t mode, struct proc_dir_entry *parent, void *data) { return NULL; } static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent) { return NULL; } static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} @@ -153,4 +154,10 @@ static inline void *PDE_DATA(const struct inode *inode) return PROC_I(inode)->pde->data; } +static inline struct proc_dir_entry *proc_net_mkdir( + struct net *net, const char *name, struct proc_dir_entry *parent) +{ + return proc_mkdir_data(name, 0, parent, net); +} + #endif /* _LINUX_PROC_FS_H */ -- cgit v1.2.3 From 4a520d2769beb736ba2bd084b8293ce148a1a7ae Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 12 Apr 2013 14:06:01 +0100 Subject: proc: Supply an accessor for getting the data from a PDE's parent Supply an accessor function for getting the private data from the parent proc_dir_entry struct of the proc_dir_entry struct associated with an inode. ReiserFS, for instance, stores the super_block pointer in the proc directory it makes for that super_block, and a pointer to the respective seq_file show function in each of the proc files in that directory. This allows a reduction in the number of file_operations structs, open functions and seq_operations structs required. The problem otherwise is that each show function requires two pieces of data but only has storage for one per PDE (and this has no release function). Signed-off-by: David Howells Acked-by: Mauro Carvalho Chehab Acked-by: Greg Kroah-Hartman cc: Jerry Chuang cc: Maxim Mikityanskiy cc: YAMANE Toshiaki cc: linux-wireless@vger.kernel.org cc: linux-scsi@vger.kernel.org cc: devel@driverdev.osuosl.org Signed-off-by: Al Viro --- include/linux/proc_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index a0fb1c2f1d8e..bae820742341 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -86,6 +86,7 @@ static inline struct proc_dir_entry *proc_create(const char *name, umode_t mode, extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); +extern void *proc_get_parent_data(const struct inode *); #else static inline void proc_flush_task(struct task_struct *task) -- cgit v1.2.3 From 8d8b97ba499cb69fccb5fd9f2b439e3265fc3f27 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 19 Apr 2013 23:11:24 -0400 Subject: take cgroup_open() and cpuset_open() to fs/proc/base.c Signed-off-by: Al Viro --- include/linux/cgroup.h | 2 +- include/linux/cpuset.h | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 900af5964f55..68f2157b71d4 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -42,7 +42,7 @@ extern int cgroupstats_build(struct cgroupstats *stats, extern int cgroup_load_subsys(struct cgroup_subsys *ss); extern void cgroup_unload_subsys(struct cgroup_subsys *ss); -extern const struct file_operations proc_cgroup_operations; +extern int proc_cgroup_show(struct seq_file *, void *); /* Define the enumeration of all builtin cgroup subsystems */ #define SUBSYS(_x) _x ## _subsys_id, diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 8c8a60d29407..22b637c5ecae 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -64,10 +64,9 @@ extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, extern int cpuset_memory_pressure_enabled; extern void __cpuset_memory_pressure_bump(void); -extern const struct file_operations proc_cpuset_operations; -struct seq_file; extern void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task); +extern int proc_cpuset_show(struct seq_file *, void *); extern int cpuset_mem_spread_node(void); extern int cpuset_slab_spread_node(void); -- cgit v1.2.3 From a8ca16ea7b0abb0a7e49492d1123b715f0ec62e8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 12 Apr 2013 17:27:28 +0100 Subject: proc: Supply a function to remove a proc entry by PDE Supply a function (proc_remove()) to remove a proc entry (and any subtree rooted there) by proc_dir_entry pointer rather than by name and (optionally) root dir entry pointer. This allows us to eliminate all remaining pde->name accesses outside of procfs. Signed-off-by: David Howells Acked-by: Grant Likely cc: linux-acpi@vger.kernel.org cc: openipmi-developer@lists.sourceforge.net cc: devicetree-discuss@lists.ozlabs.org cc: linux-pci@vger.kernel.org cc: netdev@vger.kernel.org cc: netfilter-devel@vger.kernel.org cc: alsa-devel@alsa-project.org Signed-off-by: Al Viro --- include/linux/proc_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index bae820742341..cb78d5be6859 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -67,6 +67,7 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct file_operations *proc_fops, void *data); +extern void proc_remove(struct proc_dir_entry *); extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent); extern int remove_proc_subtree(const char *name, struct proc_dir_entry *parent); @@ -101,6 +102,7 @@ static inline struct proc_dir_entry *proc_create_data(const char *name, { return NULL; } +static inline void proc_remove(struct proc_dir_entry *de) {} #define remove_proc_entry(name, parent) do {} while (0) #define remove_proc_subtree(name, parent) do {} while (0) -- cgit v1.2.3 From c30480b92cf497aa3b463367a82f1c2fdc5c46e9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 12 Apr 2013 18:03:36 +0100 Subject: proc: Make the PROC_I() and PDE() macros internal to procfs Make the PROC_I() and PDE() macros internal to procfs. This means making PDE_DATA() out of line. This could be made more optimal by storing PDE()->data into inode->i_private. Also provide a __PDE_DATA() that is inline and internal to procfs. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/proc_fs.h | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index cb78d5be6859..2112926de854 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -87,6 +87,7 @@ static inline struct proc_dir_entry *proc_create(const char *name, umode_t mode, extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); +extern void *PDE_DATA(const struct inode *); extern void *proc_get_parent_data(const struct inode *); #else @@ -116,6 +117,7 @@ static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent) { return NULL; } static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {} +static inline void *PDE_DATA(const struct inode *inode) {BUG(); return NULL;} #endif /* CONFIG_PROC_FS */ @@ -142,21 +144,6 @@ struct proc_inode { struct inode vfs_inode; }; -static inline struct proc_inode *PROC_I(const struct inode *inode) -{ - return container_of(inode, struct proc_inode, vfs_inode); -} - -static inline struct proc_dir_entry *PDE(const struct inode *inode) -{ - return PROC_I(inode)->pde; -} - -static inline void *PDE_DATA(const struct inode *inode) -{ - return PROC_I(inode)->pde->data; -} - static inline struct proc_dir_entry *proc_net_mkdir( struct net *net, const char *name, struct proc_dir_entry *parent) { -- cgit v1.2.3 From 59d8053f1e16904d54ed7469d4b36801ea6b8f2c Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 11 Apr 2013 13:34:43 +0100 Subject: proc: Move non-public stuff from linux/proc_fs.h to fs/proc/internal.h Move non-public declarations and definitions from linux/proc_fs.h to fs/proc/internal.h. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/proc_fs.h | 140 ++++++++++++------------------------------------ 1 file changed, 33 insertions(+), 107 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 2112926de854..608e60a74c3c 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -1,148 +1,74 @@ -#ifndef _LINUX_PROC_FS_H -#define _LINUX_PROC_FS_H - -#include -#include -#include -#include -#include -#include - -struct net; -struct completion; -struct mm_struct; - /* * The proc filesystem constants/structures */ +#ifndef _LINUX_PROC_FS_H +#define _LINUX_PROC_FS_H -/* - * Offset of the first process in the /proc root directory.. - */ -#define FIRST_PROCESS_ENTRY 256 - -/* Worst case buffer size needed for holding an integer. */ -#define PROC_NUMBUF 13 - -/* - * This is not completely implemented yet. The idea is to - * create an in-memory tree (like the actual /proc filesystem - * tree) of these proc_dir_entries, so that we can dynamically - * add new files to /proc. - * - * The "next" pointer creates a linked list of one /proc directory, - * while parent/subdir create the directory structure (every - * /proc file has a parent, but "subdir" is NULL for all - * non-directory entries). - */ +#include +#include -struct proc_dir_entry { - unsigned int low_ino; - umode_t mode; - nlink_t nlink; - kuid_t uid; - kgid_t gid; - loff_t size; - const struct inode_operations *proc_iops; - const struct file_operations *proc_fops; - struct proc_dir_entry *next, *parent, *subdir; - void *data; - atomic_t count; /* use count */ - atomic_t in_use; /* number of callers into module in progress; */ - /* negative -> it's going away RSN */ - struct completion *pde_unload_completion; - struct list_head pde_openers; /* who did ->open, but not ->release */ - spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */ - u8 namelen; - char name[]; -}; +struct proc_dir_entry; #ifdef CONFIG_PROC_FS extern void proc_root_init(void); - -void proc_flush_task(struct task_struct *task); - -struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, - struct proc_dir_entry *parent, - const struct file_operations *proc_fops, - void *data); -extern void proc_remove(struct proc_dir_entry *); -extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent); -extern int remove_proc_subtree(const char *name, struct proc_dir_entry *parent); +extern void proc_flush_task(struct task_struct *); extern struct proc_dir_entry *proc_symlink(const char *, struct proc_dir_entry *, const char *); -extern struct proc_dir_entry *proc_mkdir(const char *,struct proc_dir_entry *); +extern struct proc_dir_entry *proc_mkdir(const char *, struct proc_dir_entry *); extern struct proc_dir_entry *proc_mkdir_data(const char *, umode_t, struct proc_dir_entry *, void *); -extern struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, - struct proc_dir_entry *parent); - -static inline struct proc_dir_entry *proc_create(const char *name, umode_t mode, - struct proc_dir_entry *parent, const struct file_operations *proc_fops) +extern struct proc_dir_entry *proc_mkdir_mode(const char *, umode_t, + struct proc_dir_entry *); + +extern struct proc_dir_entry *proc_create_data(const char *, umode_t, + struct proc_dir_entry *, + const struct file_operations *, + void *); + +static inline struct proc_dir_entry *proc_create( + const char *name, umode_t mode, struct proc_dir_entry *parent, + const struct file_operations *proc_fops) { return proc_create_data(name, mode, parent, proc_fops, NULL); } - + extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); extern void *PDE_DATA(const struct inode *); extern void *proc_get_parent_data(const struct inode *); -#else +extern void proc_remove(struct proc_dir_entry *); +extern void remove_proc_entry(const char *, struct proc_dir_entry *); +extern int remove_proc_subtree(const char *, struct proc_dir_entry *); + +#else /* CONFIG_PROC_FS */ static inline void proc_flush_task(struct task_struct *task) { } -#define proc_create(name, mode, parent, fops) ({ (void)(mode), NULL; }) - -static inline struct proc_dir_entry *proc_create_data(const char *name, - umode_t mode, struct proc_dir_entry *parent, - const struct file_operations *proc_fops, void *data) -{ - return NULL; -} -static inline void proc_remove(struct proc_dir_entry *de) {} -#define remove_proc_entry(name, parent) do {} while (0) -#define remove_proc_subtree(name, parent) do {} while (0) - static inline struct proc_dir_entry *proc_symlink(const char *name, - struct proc_dir_entry *parent,const char *dest) {return NULL;} + struct proc_dir_entry *parent,const char *dest) { return NULL;} static inline struct proc_dir_entry *proc_mkdir(const char *name, struct proc_dir_entry *parent) {return NULL;} static inline struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, struct proc_dir_entry *parent, void *data) { return NULL; } static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, umode_t mode, struct proc_dir_entry *parent) { return NULL; } +#define proc_create(name, mode, parent, proc_fops) ({NULL;}) +#define proc_create_data(name, mode, parent, proc_fops, data) ({NULL;}) + static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {} static inline void *PDE_DATA(const struct inode *inode) {BUG(); return NULL;} +static inline void *proc_get_parent_data(const struct inode *inode) { BUG(); return NULL; } -#endif /* CONFIG_PROC_FS */ - - -union proc_op { - int (*proc_get_link)(struct dentry *, struct path *); - int (*proc_read)(struct task_struct *task, char *page); - int (*proc_show)(struct seq_file *m, - struct pid_namespace *ns, struct pid *pid, - struct task_struct *task); -}; - -struct ctl_table_header; -struct ctl_table; +static inline void proc_remove(struct proc_dir_entry *de) {} +#define remove_proc_entry(name, parent) do {} while (0) +static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) { return 0; } -struct proc_inode { - struct pid *pid; - int fd; - union proc_op op; - struct proc_dir_entry *pde; - struct ctl_table_header *sysctl; - struct ctl_table *sysctl_entry; - struct proc_ns ns; - struct inode vfs_inode; -}; +#endif /* CONFIG_PROC_FS */ static inline struct proc_dir_entry *proc_net_mkdir( struct net *net, const char *name, struct proc_dir_entry *parent) -- cgit v1.2.3 From ac3e3c5b1164397656df81b9e9ab4991184d3236 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 28 Apr 2013 21:42:33 -0400 Subject: don't bother with deferred freeing of fdtables Signed-off-by: Al Viro --- include/linux/fdtable.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index fb7dacae0522..085197bd8812 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -27,7 +27,6 @@ struct fdtable { unsigned long *close_on_exec; unsigned long *open_fds; struct rcu_head rcu; - struct fdtable *next; }; static inline bool close_on_exec(int fd, const struct fdtable *fdt) -- cgit v1.2.3 From 126de6b20bfb82cc19012d5048f11f339ae5a021 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Wed, 1 May 2013 22:04:17 +0100 Subject: linkage.h: fix build breakage due to symbol prefix handling Al's commit e1b5bb6d1236 ("consolidate cond_syscall and SYSCALL_ALIAS declarations") broke the build on blackfin and metag due to the following code: #ifndef SYMBOL_NAME #ifdef CONFIG_SYMBOL_PREFIX #define SYMBOL_NAME(x) CONFIG_SYMBOL_PREFIX ## x #else #define SYMBOL_NAME(x) x #endif #endif #define __SYMBOL_NAME(x) __stringify(SYMBOL_NAME(x)) __stringify literally stringifies CONFIG_SYMBOL_PREFIX ##x, so you get lines like this in kernel/sys_ni.s: .weak CONFIG_SYMBOL_PREFIXsys_quotactl .set CONFIG_SYMBOL_PREFIXsys_quotactl,CONFIG_SYMBOL_PREFIXsys_ni_syscall The patches in Rusty's modules-next tree such as "CONFIG_SYMBOL_PREFIX: cleanup." cleans up the whole mess around symbol prefixes, so this patch just attempts to fix the build in the meantime. The intermediate definition of SYMBOL_NAME above isn't used and is incorrect when CONFIG_SYMBOL_PREFIX is defined as CONFIG_SYMBOL_PREFIX is a quoted string literal, so define __SYMBOL_NAME directly depending on CONFIG_SYMBOL_PREFIX. Signed-off-by: James Hogan Mea-culpa-by: Al Viro Cc: Rusty Russell Cc: Mike Frysinger Cc: uclinux-dist-devel@blackfin.uclinux.org Signed-off-by: Linus Torvalds --- include/linux/linkage.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 829d66c67fc2..de09dec25ec3 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -15,14 +15,11 @@ #define asmlinkage CPP_ASMLINKAGE #endif -#ifndef SYMBOL_NAME #ifdef CONFIG_SYMBOL_PREFIX -#define SYMBOL_NAME(x) CONFIG_SYMBOL_PREFIX ## x +#define __SYMBOL_NAME(x) CONFIG_SYMBOL_PREFIX __stringify(x) #else -#define SYMBOL_NAME(x) x +#define __SYMBOL_NAME(x) __stringify(x) #endif -#endif -#define __SYMBOL_NAME(x) __stringify(SYMBOL_NAME(x)) #ifndef cond_syscall #define cond_syscall(x) asm(".weak\t" __SYMBOL_NAME(x) \ -- cgit v1.2.3 From 07c09b725543ff2958c11522d583f90f7fdba735 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 15 Feb 2013 22:10:17 -0600 Subject: libceph: make ceph_msg->bio_seg be unsigned The bio_seg field is used by the ceph messenger in iterating through a bio. It should never have a negative value, so make it an unsigned. (I contemplated making it unsigned short to match the struct bio definition, but it offered no benefit.) Change variables used to hold bio_seg values to all be unsigned as well. Change two variable names in init_bio_iter() to match the convention used everywhere else. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 60903e0f665c..8297288a66e0 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -86,7 +86,7 @@ struct ceph_msg { #ifdef CONFIG_BLOCK struct bio *bio; /* instead of pages/pagelist */ struct bio *bio_iter; /* bio iterator */ - int bio_seg; /* current bio segment */ + unsigned int bio_seg; /* current bio segment */ #endif /* CONFIG_BLOCK */ struct ceph_pagelist *trail; /* the trailing part of the data */ bool front_is_vmalloc; -- cgit v1.2.3 From d4b515fa10dd52a2aef88df7299e9f3a8ab0957a Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 25 Feb 2013 17:35:46 -0600 Subject: libceph: distinguish page array and pagelist count Use distinct fields for tracking the number of pages in a message's page array and in a message's page list. Currently only one or the other is used at a time, but that will be changing soon. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 8297288a66e0..1b08349a413c 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -75,9 +75,10 @@ struct ceph_msg { struct kvec front; /* unaligned blobs of message */ struct ceph_buffer *middle; struct page **pages; /* data payload. NOT OWNER. */ - unsigned nr_pages; /* size of page array */ + unsigned page_count; /* size of page array */ unsigned page_alignment; /* io offset in first page */ struct ceph_pagelist *pagelist; /* instead of pages */ + unsigned int pagelist_count; /* number of pages in pagelist */ struct ceph_connection *con; struct list_head list_head; -- cgit v1.2.3 From 0d5af1643535508f82d6bcc2b9b93b180e8c3f4b Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 27 Feb 2013 10:26:25 -0600 Subject: libceph: complete lingering requests only once An osd request marked to linger will be re-submitted in the event a connection to the target osd gets dropped. Currently, if there is a callback function associated with a request it will be called each time a request is submitted--which for lingering requests can be more than once. Change it so a request--including lingering ones--will get completed (from the perspective of the user of the osd client) exactly once. This resolves: http://tracker.ceph.com/issues/3967 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 1dd5d466b6f9..a79f833bba4a 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -85,6 +85,7 @@ struct ceph_osd_request { s32 r_reply_op_result[CEPH_OSD_MAX_OP]; int r_got_reply; int r_linger; + int r_completed; struct ceph_osd_client *r_osdc; struct kref r_kref; -- cgit v1.2.3 From 2a24d1f4bd7995de133c857bfdc77ac82c842300 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:15 -0600 Subject: libceph: use (void *) for untyped data in osd ops Two of the fields defining osd operations are defined using (char *) while the data they represent are really untyped, not character strings. Change them to have type (void *). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index a79f833bba4a..ec33588194ef 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -184,7 +184,7 @@ struct ceph_osd_req_op { } extent; struct { const char *name; - const char *val; + const void *val; u32 name_len; u32 value_len; __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */ @@ -193,7 +193,7 @@ struct ceph_osd_req_op { struct { const char *class_name; const char *method_name; - const char *indata; + const void *indata; u32 indata_len; __u8 class_len; __u8 method_len; -- cgit v1.2.3 From ec02a2f2ffae13e038453ae89592a8c6210f7f4d Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:15 -0600 Subject: libceph: kill ceph_msg->pagelist_count The pagelist_count field is never actually used, so get rid of it. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 1b08349a413c..6c118748a7f8 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -78,7 +78,6 @@ struct ceph_msg { unsigned page_count; /* size of page array */ unsigned page_alignment; /* io offset in first page */ struct ceph_pagelist *pagelist; /* instead of pages */ - unsigned int pagelist_count; /* number of pages in pagelist */ struct ceph_connection *con; struct list_head list_head; -- cgit v1.2.3 From 41766f87f54cc8bef023b4b0550f48753959345a Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:15 -0600 Subject: libceph: rename ceph_calc_object_layout() The purpose of ceph_calc_object_layout() is to fill in the pool number and seed for a ceph_pg structure provided, based on a given osd map and target object id. Currently that function takes a file layout parameter, but the only thing used out of that is its pool number. Change the function so it takes a pool number rather than the full file layout structure. Only update the ceph_pg if the pool is found in the osd map. Get rid of few useless lines of code from the function while there. Since the function now very clearly just fills in the ceph_pg structure it's provided, rename it ceph_calc_ceph_pg(). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osdmap.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index c819190d1642..167daf60c4e8 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -131,10 +131,8 @@ extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, u64 *bno, u64 *oxoff, u64 *oxlen); /* calculate mapping of object to a placement group */ -extern int ceph_calc_object_layout(struct ceph_pg *pg, - const char *oid, - struct ceph_file_layout *fl, - struct ceph_osdmap *osdmap); +extern int ceph_calc_ceph_pg(struct ceph_pg *pg, const char *oid, + struct ceph_osdmap *osdmap, uint64_t pool); extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, int *acting); -- cgit v1.2.3 From 153e5167e0e237faaefb7adf82db5748c1452d73 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:15 -0600 Subject: libceph: don't assign page info in ceph_osdc_new_request() Currently ceph_osdc_new_request() assigns an osd request's r_num_pages and r_alignment fields. The only thing it does after that is call ceph_osdc_build_request(), and that doesn't need those fields to be assigned. Move the assignment of those fields out of ceph_osdc_new_request() and into its caller. As a result, the page_align parameter is no longer used, so get rid of it. Note that in ceph_sync_write(), the value for req->r_num_pages had already been calculated earlier (as num_pages, and fortunately it was computed the same way). So don't bother recomputing it, but because it's not needed earlier, move that calculation after the call to ceph_osdc_new_request(). Hold off making the assignment to r_alignment, doing it instead r_pages and r_num_pages are getting set. Similarly, in start_read(), nr_pages already holds the number of pages in the array (and is calculated the same way), so there's no need to recompute it. Move the assignment of the page alignment down with the others there as well. This and the next few patches are preparation work for: http://tracker.ceph.com/issues/4127 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index ec33588194ef..803a9db0b475 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -247,7 +247,7 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, int do_sync, u32 truncate_seq, u64 truncate_size, struct timespec *mtime, - bool use_mempool, int page_align); + bool use_mempool); extern void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc, struct ceph_osd_request *req); -- cgit v1.2.3 From 2794a82a11cfeae0890741b18b0049ddb55ce646 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Feb 2013 12:16:43 -0600 Subject: libceph: separate osd request data info Pull the fields in an osd request structure that define the data for the request out into a separate structure. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 803a9db0b475..600b8278d11e 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -50,6 +50,21 @@ struct ceph_osd { #define CEPH_OSD_MAX_OP 10 +struct ceph_osd_data { + struct { + struct { + struct page **pages; + u32 num_pages; + u32 alignment; + bool pages_from_pool; + bool own_pages; + }; +#ifdef CONFIG_BLOCK + struct bio *bio; +#endif /* CONFIG_BLOCK */ + }; +}; + /* an in-flight request */ struct ceph_osd_request { u64 r_tid; /* unique for this client */ @@ -105,15 +120,8 @@ struct ceph_osd_request { struct ceph_file_layout r_file_layout; struct ceph_snap_context *r_snapc; /* snap context for writes */ - unsigned r_num_pages; /* size of page array (follows) */ - unsigned r_page_alignment; /* io offset in first page */ - struct page **r_pages; /* pages for data payload */ - int r_pages_from_pool; - int r_own_pages; /* if true, i own page list */ -#ifdef CONFIG_BLOCK - struct bio *r_bio; /* instead of pages */ -#endif + struct ceph_osd_data r_data; struct ceph_pagelist r_trail; /* trailing part of the data */ }; -- cgit v1.2.3 From 2ac2b7a6d4976bd6b5dc0751aa77d12d48d3ac4c Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Feb 2013 12:16:43 -0600 Subject: libceph: distinguish page and bio requests An osd request uses either pages or a bio list for its data. Use a union to record information about the two, and add a data type tag to select between them. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 600b8278d11e..56604b33dc3c 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -50,8 +50,17 @@ struct ceph_osd { #define CEPH_OSD_MAX_OP 10 +enum ceph_osd_data_type { + CEPH_OSD_DATA_TYPE_NONE, + CEPH_OSD_DATA_TYPE_PAGES, +#ifdef CONFIG_BLOCK + CEPH_OSD_DATA_TYPE_BIO, +#endif /* CONFIG_BLOCK */ +}; + struct ceph_osd_data { - struct { + enum ceph_osd_data_type type; + union { struct { struct page **pages; u32 num_pages; -- cgit v1.2.3 From 0fff87ec798abdb4a99f01cbb0197266bb68c5dc Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Feb 2013 12:16:43 -0600 Subject: libceph: separate read and write data An osd request defines information about where data to be read should be placed as well as where data to write comes from. Currently these are represented by common fields. Keep information about data for writing separate from data to be read by splitting these into data_in and data_out fields. This is the key patch in this whole series, in that it actually identifies which osd requests generate outgoing data and which generate incoming data. It's less obvious (currently) that an osd CALL op generates both outgoing and incoming data; that's the focus of some upcoming work. This resolves: http://tracker.ceph.com/issues/4127 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 56604b33dc3c..40e02603723d 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -130,8 +130,9 @@ struct ceph_osd_request { struct ceph_file_layout r_file_layout; struct ceph_snap_context *r_snapc; /* snap context for writes */ - struct ceph_osd_data r_data; - struct ceph_pagelist r_trail; /* trailing part of the data */ + struct ceph_osd_data r_data_in; + struct ceph_osd_data r_data_out; + struct ceph_pagelist r_trail; /* trailing part of data out */ }; struct ceph_osd_event { -- cgit v1.2.3 From 7b11ba37585595034a91df8869414f732466b800 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 8 Mar 2013 18:51:03 -0600 Subject: libceph: define CEPH_MSG_MAX_MIDDLE_LEN This is probably unnecessary but the code read as if it were wrong in read_partial_message(). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/libceph.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 29818fc3fa49..5493d7b86423 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -66,6 +66,7 @@ struct ceph_options { #define CEPH_OSD_IDLE_TTL_DEFAULT 60 #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) +#define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) #define CEPH_MSG_MAX_DATA_LEN (16*1024*1024) #define CEPH_AUTH_NAME_DEFAULT "guest" -- cgit v1.2.3 From e0c594878e3211b09208c779df5f996f0b831d9e Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 7 Mar 2013 15:38:25 -0600 Subject: libceph: record byte count not page count Record the byte count for an osd request rather than the page count. The number of pages can always be derived from the byte count (and alignment/offset) but the reverse is not true. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 40e02603723d..a8016dfbfdba 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -63,7 +63,7 @@ struct ceph_osd_data { union { struct { struct page **pages; - u32 num_pages; + u64 length; u32 alignment; bool pages_from_pool; bool own_pages; -- cgit v1.2.3 From 02afca6ca00b7972887c5cc77068356f33bdfc18 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Feb 2013 12:16:43 -0600 Subject: libceph: isolate message page field manipulation Define a function ceph_msg_data_set_pages(), which more clearly abstracts the assignment page-related fields for data in a ceph message structure. Use this new function in the osd client and mds client. Ideally, these fields would never be set more than once (with BUG_ON() calls to guarantee that). At the moment though the osd client sets these every time it receives a message, and in the event of a communication problem this can happen more than once. (This will be resolved shortly, but setting up these helpers first makes it all a bit easier to work with.) Rearrange the field order in a ceph_msg structure to group those that are used to define the possible data payloads. This partially resolves: http://tracker.ceph.com/issues/4263 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 6c118748a7f8..aa463b9b30af 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -74,21 +74,22 @@ struct ceph_msg { struct ceph_msg_footer footer; /* footer */ struct kvec front; /* unaligned blobs of message */ struct ceph_buffer *middle; - struct page **pages; /* data payload. NOT OWNER. */ - unsigned page_count; /* size of page array */ - unsigned page_alignment; /* io offset in first page */ - struct ceph_pagelist *pagelist; /* instead of pages */ - - struct ceph_connection *con; - struct list_head list_head; - struct kref kref; + struct page **pages; /* data payload. NOT OWNER. */ + unsigned int page_alignment; /* io offset in first page */ + unsigned int page_count; /* # pages in array or list */ + struct ceph_pagelist *pagelist; /* instead of pages */ #ifdef CONFIG_BLOCK + unsigned int bio_seg; /* current bio segment */ struct bio *bio; /* instead of pages/pagelist */ struct bio *bio_iter; /* bio iterator */ - unsigned int bio_seg; /* current bio segment */ #endif /* CONFIG_BLOCK */ struct ceph_pagelist *trail; /* the trailing part of the data */ + + struct ceph_connection *con; + struct list_head list_head; /* links for connection lists */ + + struct kref kref; bool front_is_vmalloc; bool more_to_follow; bool needs_out_seq; @@ -218,6 +219,9 @@ extern void ceph_msg_revoke_incoming(struct ceph_msg *msg); extern void ceph_con_keepalive(struct ceph_connection *con); +extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, + unsigned int page_count, size_t alignment); + extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); extern void ceph_msg_kfree(struct ceph_msg *m); -- cgit v1.2.3 From f1baeb2b9fc1c2c87ec02f1bf8cb88e108d4fbce Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 7 Mar 2013 15:38:26 -0600 Subject: libceph: set page info with byte length When setting page array information for message data, provide the byte length rather than the page count ceph_msg_data_set_pages(). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index aa463b9b30af..e6d20e892a88 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -220,7 +220,7 @@ extern void ceph_msg_revoke_incoming(struct ceph_msg *msg); extern void ceph_con_keepalive(struct ceph_connection *con); extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, - unsigned int page_count, size_t alignment); + size_t length, size_t alignment); extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); -- cgit v1.2.3 From 27fa83852ba275361eaa1a1283cf6704fa8191a6 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Feb 2013 12:16:43 -0600 Subject: libceph: isolate other message data fields Define ceph_msg_data_set_pagelist(), ceph_msg_data_set_bio(), and ceph_msg_data_set_trail() to clearly abstract the assignment of the remaining data-related fields in a ceph message structure. Use the new functions in the osd client and mds client. This partially resolves: http://tracker.ceph.com/issues/4263 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index e6d20e892a88..9d9be4682ac3 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -221,6 +221,11 @@ extern void ceph_con_keepalive(struct ceph_connection *con); extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, size_t length, size_t alignment); +extern void ceph_msg_data_set_pagelist(struct ceph_msg *msg, + struct ceph_pagelist *pagelist); +extern void ceph_msg_data_set_bio(struct ceph_msg *msg, struct bio *bio); +extern void ceph_msg_data_set_trail(struct ceph_msg *msg, + struct ceph_pagelist *trail); extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); -- cgit v1.2.3 From 4a73ef27ad04f1b8ea23eb55e50b20fcc0530a6f Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 7 Mar 2013 15:38:26 -0600 Subject: libceph: record message data byte length Record the number of bytes of data in a page array rather than the number of pages in the array. It can be assumed that the page array is of sufficient size to hold the number of bytes indicated (and offset by the indicated alignment). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 9d9be4682ac3..1991a6f9dc90 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -77,7 +77,7 @@ struct ceph_msg { struct page **pages; /* data payload. NOT OWNER. */ unsigned int page_alignment; /* io offset in first page */ - unsigned int page_count; /* # pages in array or list */ + size_t length; /* # data bytes in array or list */ struct ceph_pagelist *pagelist; /* instead of pages */ #ifdef CONFIG_BLOCK unsigned int bio_seg; /* current bio segment */ -- cgit v1.2.3 From 97fb1c7f6637ee61c90b8bc186d464cfd426b063 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:16 -0600 Subject: libceph: define ceph_msg_has_*() data macros Define and use macros ceph_msg_has_*() to determine whether to operate on the pages, pagelist, bio, and trail fields of a message. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 1991a6f9dc90..889fe4720133 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -64,6 +64,13 @@ struct ceph_messenger { u32 required_features; }; +#define ceph_msg_has_pages(m) ((m)->pages != NULL) +#define ceph_msg_has_pagelist(m) ((m)->pagelist != NULL) +#ifdef CONFIG_BLOCK +#define ceph_msg_has_bio(m) ((m)->bio != NULL) +#endif /* CONFIG_BLOCK */ +#define ceph_msg_has_trail(m) ((m)->trail != NULL) + /* * a single message. it contains a header (src, dest, message type, etc.), * footer (crc values, mainly), a "front" message body, and possibly a -- cgit v1.2.3 From f9e15777afd87585f2222dfd446c2e52deb65eba Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:16 -0600 Subject: libceph: be explicit about message data representation A ceph message has a data payload portion. The memory for that data (either the source of data to send or the location to place data that is received) is specified in several ways. The ceph_msg structure includes fields for all of those ways, but this mispresents the fact that not all of them are used at a time. Specifically, the data in a message can be in: - an array of pages - a list of pages - a list of Linux bios - a second list of pages (the "trail") (The two page lists are currently only ever used for outgoing data.) Impose more structure on the ceph message, making the grouping of some of these fields explicit. Shorten the name of the "page_alignment" field. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 33 +++++++++++++++++++++------------ 1 file changed, 21 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 889fe4720133..fb2b18a20c13 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -64,12 +64,12 @@ struct ceph_messenger { u32 required_features; }; -#define ceph_msg_has_pages(m) ((m)->pages != NULL) -#define ceph_msg_has_pagelist(m) ((m)->pagelist != NULL) +#define ceph_msg_has_pages(m) ((m)->p.pages != NULL) +#define ceph_msg_has_pagelist(m) ((m)->l.pagelist != NULL) #ifdef CONFIG_BLOCK -#define ceph_msg_has_bio(m) ((m)->bio != NULL) +#define ceph_msg_has_bio(m) ((m)->b.bio != NULL) #endif /* CONFIG_BLOCK */ -#define ceph_msg_has_trail(m) ((m)->trail != NULL) +#define ceph_msg_has_trail(m) ((m)->t.trail != NULL) /* * a single message. it contains a header (src, dest, message type, etc.), @@ -82,16 +82,25 @@ struct ceph_msg { struct kvec front; /* unaligned blobs of message */ struct ceph_buffer *middle; - struct page **pages; /* data payload. NOT OWNER. */ - unsigned int page_alignment; /* io offset in first page */ - size_t length; /* # data bytes in array or list */ - struct ceph_pagelist *pagelist; /* instead of pages */ + /* data payload */ + struct { + struct page **pages; /* NOT OWNER. */ + size_t length; /* # data bytes in array */ + unsigned int alignment; /* first page */ + } p; + struct { + struct ceph_pagelist *pagelist; + } l; #ifdef CONFIG_BLOCK - unsigned int bio_seg; /* current bio segment */ - struct bio *bio; /* instead of pages/pagelist */ - struct bio *bio_iter; /* bio iterator */ + struct { + struct bio *bio_iter; /* iterator */ + struct bio *bio; + unsigned int bio_seg; /* current seg in bio */ + } b; #endif /* CONFIG_BLOCK */ - struct ceph_pagelist *trail; /* the trailing part of the data */ + struct { + struct ceph_pagelist *trail; /* trailing part of data */ + } t; struct ceph_connection *con; struct list_head list_head; /* links for connection lists */ -- cgit v1.2.3 From 437945094fed0deb1810e8da95465c8f26bc6f80 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 1 Mar 2013 18:00:16 -0600 Subject: libceph: abstract message data Group the types of message data into an abstract structure with a type indicator and a union containing fields appropriate to the type of data it represents. Use this to represent the pages, pagelist, bio, and trail in a ceph message. Verify message data is of type NONE in ceph_msg_data_set_*() routines. Since information about message data of type NONE really should not be interpreted, get rid of the other assertions in those functions. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 71 ++++++++++++++++++++++++++++++------------ 1 file changed, 51 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index fb2b18a20c13..5860dd0c2caf 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -64,12 +64,55 @@ struct ceph_messenger { u32 required_features; }; -#define ceph_msg_has_pages(m) ((m)->p.pages != NULL) -#define ceph_msg_has_pagelist(m) ((m)->l.pagelist != NULL) +#define ceph_msg_has_pages(m) ((m)->p.type == CEPH_MSG_DATA_PAGES) +#define ceph_msg_has_pagelist(m) ((m)->l.type == CEPH_MSG_DATA_PAGELIST) #ifdef CONFIG_BLOCK -#define ceph_msg_has_bio(m) ((m)->b.bio != NULL) +#define ceph_msg_has_bio(m) ((m)->b.type == CEPH_MSG_DATA_BIO) #endif /* CONFIG_BLOCK */ -#define ceph_msg_has_trail(m) ((m)->t.trail != NULL) +#define ceph_msg_has_trail(m) ((m)->t.type == CEPH_MSG_DATA_PAGELIST) + +enum ceph_msg_data_type { + CEPH_MSG_DATA_NONE, /* message contains no data payload */ + CEPH_MSG_DATA_PAGES, /* data source/destination is a page array */ + CEPH_MSG_DATA_PAGELIST, /* data source/destination is a pagelist */ +#ifdef CONFIG_BLOCK + CEPH_MSG_DATA_BIO, /* data source/destination is a bio list */ +#endif /* CONFIG_BLOCK */ +}; + +static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) +{ + switch (type) { + case CEPH_MSG_DATA_NONE: + case CEPH_MSG_DATA_PAGES: + case CEPH_MSG_DATA_PAGELIST: +#ifdef CONFIG_BLOCK + case CEPH_MSG_DATA_BIO: +#endif /* CONFIG_BLOCK */ + return true; + default: + return false; + } +} + +struct ceph_msg_data { + enum ceph_msg_data_type type; + union { +#ifdef CONFIG_BLOCK + struct { + struct bio *bio_iter; /* iterator */ + struct bio *bio; + unsigned int bio_seg; /* current seg in bio */ + }; +#endif /* CONFIG_BLOCK */ + struct { + struct page **pages; /* NOT OWNER. */ + size_t length; /* total # bytes */ + unsigned int alignment; /* first page */ + }; + struct ceph_pagelist *pagelist; + }; +}; /* * a single message. it contains a header (src, dest, message type, etc.), @@ -83,24 +126,12 @@ struct ceph_msg { struct ceph_buffer *middle; /* data payload */ - struct { - struct page **pages; /* NOT OWNER. */ - size_t length; /* # data bytes in array */ - unsigned int alignment; /* first page */ - } p; - struct { - struct ceph_pagelist *pagelist; - } l; + struct ceph_msg_data p; /* pages */ + struct ceph_msg_data l; /* pagelist */ #ifdef CONFIG_BLOCK - struct { - struct bio *bio_iter; /* iterator */ - struct bio *bio; - unsigned int bio_seg; /* current seg in bio */ - } b; + struct ceph_msg_data b; /* bio */ #endif /* CONFIG_BLOCK */ - struct { - struct ceph_pagelist *trail; /* trailing part of data */ - } t; + struct ceph_msg_data t; /* trail */ struct ceph_connection *con; struct list_head list_head; /* links for connection lists */ -- cgit v1.2.3 From fe38a2b67bc6b3a60da82a23e9082256a30e39d9 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 6 Mar 2013 23:39:39 -0600 Subject: libceph: start defining message data cursor This patch lays out the foundation for using generic routines to manage processing items of message data. For simplicity, we'll start with just the trail portion of a message, because it stands alone and is only present for outgoing data. First some basic concepts. We'll use the term "data item" to represent one of the ceph_msg_data structures associated with a message. There are currently four of those, with single-letter field names p, l, b, and t. A data item is further broken into "pieces" which always lie in a single page. A data item will include a "cursor" that will track state as the memory defined by the item is consumed by sending data from or receiving data into it. We define three routines to manipulate a data item's cursor: the "init" routine; the "next" routine; and the "advance" routine. The "init" routine initializes the cursor so it points at the beginning of the first piece in the item. The "next" routine returns the page, page offset, and length (limited by both the page and item size) of the next unconsumed piece in the item. It also indicates to the caller whether the piece being returned is the last one in the data item. The "advance" routine consumes the requested number of bytes in the item (advancing the cursor). This is used to record the number of bytes from the current piece that were actually sent or received by the network code. It returns an indication of whether the result means the current piece has been fully consumed. This is used by the message send code to determine whether it should calculate the CRC for the next piece processed. The trail of a message is implemented as a ceph pagelist. The routines defined for it will be usable for non-trail pagelist data as well. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 5860dd0c2caf..14862438faff 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -95,6 +95,12 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) } } +struct ceph_msg_data_cursor { + bool last_piece; /* now at last piece of data item */ + struct page *page; /* current page in pagelist */ + size_t offset; /* pagelist bytes consumed */ +}; + struct ceph_msg_data { enum ceph_msg_data_type type; union { @@ -112,6 +118,7 @@ struct ceph_msg_data { }; struct ceph_pagelist *pagelist; }; + struct ceph_msg_data_cursor cursor; /* pagelist only */ }; /* -- cgit v1.2.3 From dd236fcb65d7b6b80c408cb5f66aab55f4594284 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 6 Mar 2013 23:39:39 -0600 Subject: libceph: prepare for other message data item types This just inserts some infrastructure in preparation for handling other types of ceph message data items. No functional changes, just trying to simplify review by separating out some noise. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 14862438faff..716c3fdeb257 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -97,8 +97,12 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) struct ceph_msg_data_cursor { bool last_piece; /* now at last piece of data item */ - struct page *page; /* current page in pagelist */ - size_t offset; /* pagelist bytes consumed */ + union { + struct { /* pagelist */ + struct page *page; /* page from list */ + size_t offset; /* bytes from list */ + }; + }; }; struct ceph_msg_data { -- cgit v1.2.3 From 6aaa4511deb4b0fd776d1153dc63a89cdc024fb8 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 6 Mar 2013 23:39:39 -0600 Subject: libceph: implement bio message data item cursor Implement and use cursor routines for bio message data items for outbound message data. (See the previous commit for reasoning in support of the changes in out_msg_pos_next().) Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 716c3fdeb257..76b4645e2dff 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -98,6 +98,13 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) struct ceph_msg_data_cursor { bool last_piece; /* now at last piece of data item */ union { +#ifdef CONFIG_BLOCK + struct { /* bio */ + struct bio *bio; /* bio from list */ + unsigned int vector_index; /* vector from bio */ + unsigned int vector_offset; /* bytes from vector */ + }; +#endif /* CONFIG_BLOCK */ struct { /* pagelist */ struct page *page; /* page from list */ size_t offset; /* bytes from list */ -- cgit v1.2.3 From e766d7b55e10f93c7bab298135a4e90dcc46620d Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 7 Mar 2013 15:38:28 -0600 Subject: libceph: implement pages array cursor Implement and use cursor routines for page array message data items for outbound message data. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 76b4645e2dff..b53b9ef65009 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -105,6 +105,12 @@ struct ceph_msg_data_cursor { unsigned int vector_offset; /* bytes from vector */ }; #endif /* CONFIG_BLOCK */ + struct { /* pages */ + size_t resid; /* bytes from array */ + unsigned int page_offset; /* offset in page */ + unsigned short page_index; /* index in array */ + unsigned short page_count; /* pages in array */ + }; struct { /* pagelist */ struct page *page; /* page from list */ size_t offset; /* bytes from list */ -- cgit v1.2.3 From 175face2ba31025b0dcd6da4e711fca7764287fa Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 8 Mar 2013 13:35:36 -0600 Subject: libceph: let osd ops determine request data length The length of outgoing data in an osd request is dependent on the osd ops that are embedded in that request. Each op is encoded into a request message using osd_req_encode_op(), so that should be used to determine the amount of outgoing data implied by the op as it is encoded. Have osd_req_encode_op() return the number of bytes of outgoing data implied by the op being encoded, and accumulate and use that in ceph_osdc_build_request(). As a result, ceph_osdc_build_request() no longer requires its "len" parameter, so get rid of it. Using the sum of the op lengths rather than the length provided is a valid change because: - The only callers of osd ceph_osdc_build_request() are rbd and the osd client (in ceph_osdc_new_request() on behalf of the file system). - When rbd calls it, the length provided is only non-zero for write requests, and in that case the single op has the same length value as what was passed here. - When called from ceph_osdc_new_request(), (it's not all that easy to see, but) the length passed is also always the same as the extent length encoded in its (single) write op if present. This resolves: http://tracker.ceph.com/issues/4406 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index a8016dfbfdba..bcf3f72ec3f8 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -249,8 +249,7 @@ extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client * bool use_mempool, gfp_t gfp_flags); -extern void ceph_osdc_build_request(struct ceph_osd_request *req, - u64 off, u64 len, +extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off, unsigned int num_op, struct ceph_osd_req_op *src_ops, struct ceph_snap_context *snapc, -- cgit v1.2.3 From 9a5e6d09ddd0cd68ce64c3aa54095e4a0e85b089 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 8 Mar 2013 13:35:36 -0600 Subject: libceph: have osd requests support pagelist data Add support for recording a ceph pagelist as data associated with an osd request. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index bcf3f72ec3f8..cf0ba93426da 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -53,6 +53,7 @@ struct ceph_osd { enum ceph_osd_data_type { CEPH_OSD_DATA_TYPE_NONE, CEPH_OSD_DATA_TYPE_PAGES, + CEPH_OSD_DATA_TYPE_PAGELIST, #ifdef CONFIG_BLOCK CEPH_OSD_DATA_TYPE_BIO, #endif /* CONFIG_BLOCK */ @@ -68,8 +69,9 @@ struct ceph_osd_data { bool pages_from_pool; bool own_pages; }; + struct ceph_pagelist *pagelist; #ifdef CONFIG_BLOCK - struct bio *bio; + struct bio *bio; #endif /* CONFIG_BLOCK */ }; }; -- cgit v1.2.3 From 95e072eb38f99c724739d91a1f12bb8bfe1619b5 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 8 Mar 2013 13:35:36 -0600 Subject: libceph: kill osd request r_trail The osd trail is a pagelist, used only for a CALL osd operation to hold the class and method names, along with any input data for the call. It is only currently used by the rbd client, and when it's used it is the only bit of outbound data in the osd request. Since we already support (non-trail) pagelist data in a message, we can just save this outbound CALL data in the "normal" pagelist rather than the trail, and get rid of the trail entirely. The existing pagelist support depends on the pagelist being dynamically allocated, and ownership of it is passed to the messenger once it's been attached to a message. (That is to say, the messenger releases and frees the pagelist when it's done with it). That means we need to dynamically allocate the pagelist also. Note that we simply assert that the allocation of a pagelist structure succeeds. Appending to a pagelist might require a dynamic allocation, so we're already assuming we won't run into trouble doing so (we're just ignore any failures--and that should be fixed at some point). This resolves: http://tracker.ceph.com/issues/4407 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index cf0ba93426da..1dab291b2dc6 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -134,7 +134,6 @@ struct ceph_osd_request { struct ceph_osd_data r_data_in; struct ceph_osd_data r_data_out; - struct ceph_pagelist r_trail; /* trailing part of data out */ }; struct ceph_osd_event { -- cgit v1.2.3 From 9d2a06c2750177dca5f8d0e89884c1d409d64bbc Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 8 Mar 2013 13:35:36 -0600 Subject: libceph: kill message trail The wart that is the ceph message trail can now be removed, because its only user was the osd client, and the previous patch made that no longer the case. The result allows write_partial_msg_pages() to be simplified considerably. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index b53b9ef65009..0e4536cc46f0 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -69,7 +69,6 @@ struct ceph_messenger { #ifdef CONFIG_BLOCK #define ceph_msg_has_bio(m) ((m)->b.type == CEPH_MSG_DATA_BIO) #endif /* CONFIG_BLOCK */ -#define ceph_msg_has_trail(m) ((m)->t.type == CEPH_MSG_DATA_PAGELIST) enum ceph_msg_data_type { CEPH_MSG_DATA_NONE, /* message contains no data payload */ @@ -155,7 +154,6 @@ struct ceph_msg { #ifdef CONFIG_BLOCK struct ceph_msg_data b; /* bio */ #endif /* CONFIG_BLOCK */ - struct ceph_msg_data t; /* trail */ struct ceph_connection *con; struct list_head list_head; /* links for connection lists */ @@ -295,8 +293,6 @@ extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, extern void ceph_msg_data_set_pagelist(struct ceph_msg *msg, struct ceph_pagelist *pagelist); extern void ceph_msg_data_set_bio(struct ceph_msg *msg, struct bio *bio); -extern void ceph_msg_data_set_trail(struct ceph_msg *msg, - struct ceph_pagelist *trail); extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); -- cgit v1.2.3 From 3a23083bda56850a1dc0e1c6d270b1f5dc789f07 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Mon, 25 Mar 2013 08:47:40 -0700 Subject: libceph: implement RECONNECT_SEQ feature This is an old protocol extension that allows the client and server to avoid resending old messages after a reconnect (following a socket error). Instead, the exchange their sequence numbers during the handshake. This avoids sending a bunch of useless data over the socket. It has been supported in the server code since v0.22 (Sep 2010). Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/ceph_features.h | 2 ++ include/linux/ceph/msgr.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 76554cecaab2..4c42080347af 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -41,6 +41,7 @@ */ #define CEPH_FEATURES_SUPPORTED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ + CEPH_FEATURE_RECONNECT_SEQ | \ CEPH_FEATURE_PGID64 | \ CEPH_FEATURE_PGPOOL3 | \ CEPH_FEATURE_OSDENC | \ @@ -51,6 +52,7 @@ #define CEPH_FEATURES_REQUIRED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ + CEPH_FEATURE_RECONNECT_SEQ | \ CEPH_FEATURE_PGID64 | \ CEPH_FEATURE_PGPOOL3 | \ CEPH_FEATURE_OSDENC) diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h index 680d3d648cac..3d94a73b5f30 100644 --- a/include/linux/ceph/msgr.h +++ b/include/linux/ceph/msgr.h @@ -87,6 +87,7 @@ struct ceph_entity_inst { #define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */ #define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */ #define CEPH_MSGR_TAG_FEATURES 12 /* insufficient features */ +#define CEPH_MSGR_TAG_SEQ 13 /* 64-bit int follows with seen seq number */ /* -- cgit v1.2.3 From 0bed9b5c523d577378b6f83eab5835fe30c27208 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Mon, 25 Mar 2013 10:26:01 -0700 Subject: libceph: add update_authorizer auth method Currently the messenger calls out to a get_authorizer con op, which will create a new authorizer if it doesn't yet have one. In the meantime, when we rotate our service keys, the authorizer doesn't get updated. Eventually it will be rejected by the server on a new connection attempt and get invalidated, and we will then rebuild a new authorizer, but this is not ideal. Instead, if we do have an authorizer, call a new update_authorizer op that will verify that the current authorizer is using the latest secret. If it is not, we will build a new one that does. This avoids the transient failure. This fixes one of the sorry sequence of events for bug http://tracker.ceph.com/issues/4282 Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/auth.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h index d4080f309b56..73e973e70026 100644 --- a/include/linux/ceph/auth.h +++ b/include/linux/ceph/auth.h @@ -52,6 +52,9 @@ struct ceph_auth_client_ops { */ int (*create_authorizer)(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *auth); + /* ensure that an existing authorizer is up to date */ + int (*update_authorizer)(struct ceph_auth_client *ac, int peer_type, + struct ceph_auth_handshake *auth); int (*verify_authorizer_reply)(struct ceph_auth_client *ac, struct ceph_authorizer *a, size_t len); void (*destroy_authorizer)(struct ceph_auth_client *ac, -- cgit v1.2.3 From 27859f9773e4a0b2042435b13400ee2c891a61f4 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Mon, 25 Mar 2013 10:26:14 -0700 Subject: libceph: wrap auth ops in wrapper functions Use wrapper functions that check whether the auth op exists so that callers do not need a bunch of conditional checks. Simplifies the external interface. Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/auth.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h index 73e973e70026..c9c3b3abe4a3 100644 --- a/include/linux/ceph/auth.h +++ b/include/linux/ceph/auth.h @@ -97,5 +97,18 @@ extern int ceph_build_auth(struct ceph_auth_client *ac, void *msg_buf, size_t msg_len); extern int ceph_auth_is_authenticated(struct ceph_auth_client *ac); +extern int ceph_auth_create_authorizer(struct ceph_auth_client *ac, + int peer_type, + struct ceph_auth_handshake *auth); +extern void ceph_auth_destroy_authorizer(struct ceph_auth_client *ac, + struct ceph_authorizer *a); +extern int ceph_auth_update_authorizer(struct ceph_auth_client *ac, + int peer_type, + struct ceph_auth_handshake *a); +extern int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac, + struct ceph_authorizer *a, + size_t len); +extern void ceph_auth_invalidate_authorizer(struct ceph_auth_client *ac, + int peer_type); #endif -- cgit v1.2.3 From e9966076cdd952e19f2dd4854cd719be0d7cbebc Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Mon, 25 Mar 2013 10:26:30 -0700 Subject: libceph: wrap auth methods in a mutex The auth code is called from a variety of contexts, include the mon_client (protected by the monc's mutex) and the messenger callbacks (currently protected by nothing). Avoid chaos by protecting all auth state with a mutex. Nothing is blocking, so this should be simple and lightweight. Signed-off-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/auth.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h index c9c3b3abe4a3..5f3386844134 100644 --- a/include/linux/ceph/auth.h +++ b/include/linux/ceph/auth.h @@ -78,6 +78,8 @@ struct ceph_auth_client { u64 global_id; /* our unique id in system */ const struct ceph_crypto_key *key; /* our secret key */ unsigned want_keys; /* which services we want */ + + struct mutex mutex; }; extern struct ceph_auth_client *ceph_auth_init(const char *name, -- cgit v1.2.3 From 25aff7c559c8b54a810bc094d59fe037cfed6b18 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Mar 2013 23:34:22 -0500 Subject: libceph: record residual bytes for all message data types All of the data types can use this, not just the page array. Until now, only the bio type doesn't have it available, and only the initiator of the request (the rbd client) is able to supply the length of the full request without re-scanning the bio list. Change the cursor init routines so the length is supplied based on the message header "data_len" field, and use that length to intiialize the "resid" field of the cursor. In addition, change the way "last_piece" is defined so it is based on the residual number of bytes in the original request. This is necessary (at least for bio messages) because it is possible for a read request to succeed without consuming all of the space available in the data buffer. This resolves: http://tracker.ceph.com/issues/4427 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 0e4536cc46f0..459e55280bf8 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -95,6 +95,7 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) } struct ceph_msg_data_cursor { + size_t resid; /* bytes not yet consumed */ bool last_piece; /* now at last piece of data item */ union { #ifdef CONFIG_BLOCK @@ -105,7 +106,6 @@ struct ceph_msg_data_cursor { }; #endif /* CONFIG_BLOCK */ struct { /* pages */ - size_t resid; /* bytes from array */ unsigned int page_offset; /* offset in page */ unsigned short page_index; /* index in array */ unsigned short page_count; /* pages in array */ -- cgit v1.2.3 From 6518be47f910f62a98cb6044dbb457af55241f95 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Mar 2013 23:34:23 -0500 Subject: libceph: kill ceph message bio_iter, bio_seg The bio_iter and bio_seg fields in a message are no longer used, we use the cursor instead. So get rid of them and the functions that operate on them them. This is related to: http://tracker.ceph.com/issues/4428 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 459e55280bf8..252e01b7f7de 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -121,11 +121,7 @@ struct ceph_msg_data { enum ceph_msg_data_type type; union { #ifdef CONFIG_BLOCK - struct { - struct bio *bio_iter; /* iterator */ - struct bio *bio; - unsigned int bio_seg; /* current seg in bio */ - }; + struct bio *bio; #endif /* CONFIG_BLOCK */ struct { struct page **pages; /* NOT OWNER. */ -- cgit v1.2.3 From 4c59b4a278f9b7a418ad8af933fd7b341df64393 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Mar 2013 23:34:23 -0500 Subject: libceph: collapse all data items into one It turns out that only one of the data item types is ever used at any one time in a single message (currently). - A page array is used by the osd client (on behalf of the file system) and by rbd. Only one osd op (and therefore at most one data item) is ever used at a time by rbd. And the only time the file system sends two, the second op contains no data. - A bio is only used by the rbd client (and again, only one data item per message) - A page list is used by the file system and by rbd for outgoing data, but only one op (and one data item) at a time. We can therefore collapse all three of our data item fields into a single field "data", and depend on the messenger code to properly handle it based on its type. This allows us to eliminate quite a bit of duplicated code. This is related to: http://tracker.ceph.com/issues/4429 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 252e01b7f7de..af786b29f7a4 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -64,11 +64,7 @@ struct ceph_messenger { u32 required_features; }; -#define ceph_msg_has_pages(m) ((m)->p.type == CEPH_MSG_DATA_PAGES) -#define ceph_msg_has_pagelist(m) ((m)->l.type == CEPH_MSG_DATA_PAGELIST) -#ifdef CONFIG_BLOCK -#define ceph_msg_has_bio(m) ((m)->b.type == CEPH_MSG_DATA_BIO) -#endif /* CONFIG_BLOCK */ +#define ceph_msg_has_data(m) ((m)->data.type != CEPH_MSG_DATA_NONE) enum ceph_msg_data_type { CEPH_MSG_DATA_NONE, /* message contains no data payload */ @@ -145,11 +141,7 @@ struct ceph_msg { struct ceph_buffer *middle; /* data payload */ - struct ceph_msg_data p; /* pages */ - struct ceph_msg_data l; /* pagelist */ -#ifdef CONFIG_BLOCK - struct ceph_msg_data b; /* bio */ -#endif /* CONFIG_BLOCK */ + struct ceph_msg_data data; struct ceph_connection *con; struct list_head list_head; /* links for connection lists */ -- cgit v1.2.3 From 859a35d5523e8e6a5c3568c12febe2e1270bc3a1 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Mar 2013 23:34:23 -0500 Subject: libceph: kill most of ceph_msg_pos All but one of the fields in the ceph_msg_pos structure are now never used (only assigned), so get rid of them. This allows several small blocks of code to go away. This is cleanup of old code related to: http://tracker.ceph.com/issues/4428 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index af786b29f7a4..c76b228cb524 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -157,8 +157,6 @@ struct ceph_msg { }; struct ceph_msg_pos { - int page, page_pos; /* which page; offset in page */ - int data_pos; /* offset in data payload */ bool did_page_crc; /* true if we've calculated crc for current page */ }; -- cgit v1.2.3 From f5db90bcf2c69d099f9d828a8104796f41de6bc5 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Mar 2013 23:34:23 -0500 Subject: libceph: kill last of ceph_msg_pos The only remaining field in the ceph_msg_pos structure is did_page_crc. In the new cursor model of things that flag (or something like it) belongs in the cursor. Define a new field "need_crc" in the cursor (which applies to all types of data) and initialize it to true whenever a cursor is initialized. In write_partial_message_data(), the data CRC still will be computed as before, but it will check the cursor->need_crc field to determine whether it's needed. Any time the cursor is advanced to a new piece of a data item, need_crc will be set, and this will cause the crc for that entire piece to be accumulated into the data crc. In write_partial_message_data() the intermediate crc value is now held in a local variable so it doesn't have to be byte-swapped so many times. In read_partial_msg_data() we do something similar (but mainly for consistency there). With that, the ceph_msg_pos structure can go away, and it no longer needs to be passed as an argument to prepare_message_data(). This cleanup is related to: http://tracker.ceph.com/issues/4428 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index c76b228cb524..686df5bfa717 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -93,6 +93,7 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) struct ceph_msg_data_cursor { size_t resid; /* bytes not yet consumed */ bool last_piece; /* now at last piece of data item */ + bool need_crc; /* new piece; crc update needed */ union { #ifdef CONFIG_BLOCK struct { /* bio */ @@ -156,10 +157,6 @@ struct ceph_msg { struct ceph_msgpool *pool; }; -struct ceph_msg_pos { - bool did_page_crc; /* true if we've calculated crc for current page */ -}; - /* ceph connection fault delay defaults, for exponential backoff */ #define BASE_DELAY_INTERVAL (HZ/2) #define MAX_DELAY_INTERVAL (5 * 60 * HZ) @@ -217,7 +214,6 @@ struct ceph_connection { struct ceph_msg *out_msg; /* sending message (== tail of out_sent) */ bool out_msg_done; - struct ceph_msg_pos out_msg_pos; struct kvec out_kvec[8], /* sending header/footer data */ *out_kvec_cur; @@ -231,7 +227,6 @@ struct ceph_connection { /* message in temps */ struct ceph_msg_header in_hdr; struct ceph_msg *in_msg; - struct ceph_msg_pos in_msg_pos; u32 in_front_crc, in_middle_crc, in_data_crc; /* calculated crc */ char in_tag; /* protocol control byte */ -- cgit v1.2.3 From 6644ed7b7e04f8e588aebdaa58cededb9416ab95 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Mar 2013 23:34:24 -0500 Subject: libceph: make message data be a pointer Begin the transition from a single message data item to a list of them by replacing the "data" structure in a message with a pointer to a ceph_msg_data structure. A null pointer will indicate the message has no data; replace the use of ceph_msg_has_data() with a simple check for a null pointer. Create functions ceph_msg_data_create() and ceph_msg_data_destroy() to dynamically allocate and free a data item structure of a given type. When a message has its data item "set," allocate one of these to hold the data description, and free it when the last reference to the message is dropped. This partially resolves: http://tracker.ceph.com/issues/4429 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 686df5bfa717..3181321bed6d 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -64,8 +64,6 @@ struct ceph_messenger { u32 required_features; }; -#define ceph_msg_has_data(m) ((m)->data.type != CEPH_MSG_DATA_NONE) - enum ceph_msg_data_type { CEPH_MSG_DATA_NONE, /* message contains no data payload */ CEPH_MSG_DATA_PAGES, /* data source/destination is a page array */ @@ -141,8 +139,7 @@ struct ceph_msg { struct kvec front; /* unaligned blobs of message */ struct ceph_buffer *middle; - /* data payload */ - struct ceph_msg_data data; + struct ceph_msg_data *data; /* data payload */ struct ceph_connection *con; struct list_head list_head; /* links for connection lists */ -- cgit v1.2.3 From adfe695a25e92e3a4597807fbc7f9a8105218776 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 13 Mar 2013 20:50:00 -0500 Subject: ceph: move max constant definitions Move some definitions for max integer values out of the rbd code and into the more central "decode.h" header file. These really belong in a Linux (or libc) header somewhere, but I haven't gotten around to proposing that yet. This is in preparation for moving some code out of rbd.c and into the osd client. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/decode.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 360d9d08ca9e..689f1df37bff 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -8,6 +8,13 @@ #include +/* This seemed to be the easiest place to define these */ + +#define U8_MAX ((u8) (~0U)) +#define U16_MAX ((u16) (~0U)) +#define U32_MAX ((u32) (~0U)) +#define U64_MAX ((u64) (~0ULL)) + /* * in all cases, * void **p pointer to position pointer -- cgit v1.2.3 From 33803f3300265661b5c5d20a9811c6a2a157d545 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 13 Mar 2013 20:50:00 -0500 Subject: libceph: define source request op functions The rbd code has a function that allocates and populates a ceph_osd_req_op structure (the in-core version of an osd request operation). When reviewed, Josh suggested two things: that the big varargs function might be better split into type-specific functions; and that this functionality really belongs in the osd client rather than rbd. This patch implements both of Josh's suggestions. It breaks up the rbd function into separate functions and defines them in the osd client module as exported interfaces. Unlike the rbd version, however, the functions don't allocate an osd_req_op structure; they are provided the address of one and that is initialized instead. The rbd function has been eliminated and calls to it have been replaced by calls to the new routines. The rbd code now now use a stack (struct) variable to hold the op rather than allocating and freeing it each time. For now only the capabilities used by rbd are implemented. Implementing all the other osd op types, and making the rest of the code use it will be done separately, in the next few patches. Note that only the extent, cls, and watch portions of the ceph_osd_req_op structure are currently used. Delete the others (xattr, pgls, and snap) from its definition so nobody thinks it's actually implemented or needed. We can add it back again later if needed, when we know it's been tested. This (and a few follow-on patches) resolves: http://tracker.ceph.com/issues/3861 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 1dab291b2dc6..5fd2cbfcfd91 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -201,14 +201,6 @@ struct ceph_osd_req_op { u64 truncate_size; u32 truncate_seq; } extent; - struct { - const char *name; - const void *val; - u32 name_len; - u32 value_len; - __u8 cmp_op; /* CEPH_OSD_CMPXATTR_OP_* */ - __u8 cmp_mode; /* CEPH_OSD_CMPXATTR_MODE_* */ - } xattr; struct { const char *class_name; const char *method_name; @@ -218,13 +210,6 @@ struct ceph_osd_req_op { __u8 method_len; __u8 argc; } cls; - struct { - u64 cookie; - u64 count; - } pgls; - struct { - u64 snapid; - } snap; struct { u64 cookie; u64 ver; @@ -244,6 +229,17 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); +extern void osd_req_op_init(struct ceph_osd_req_op *op, u16 opcode); +extern void osd_req_op_extent_init(struct ceph_osd_req_op *op, u16 opcode, + u64 offset, u64 length, + u64 truncate_size, u32 truncate_seq); +extern void osd_req_op_cls_init(struct ceph_osd_req_op *op, u16 opcode, + const char *class, const char *method, + const void *request_data, + size_t request_data_size); +extern void osd_req_op_watch_init(struct ceph_osd_req_op *op, u16 opcode, + u64 cookie, u64 version, int flag); + extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, unsigned int num_op, -- cgit v1.2.3 From ef4859d6479d19bcc65c3156cf3b7dd747355c29 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 1 Apr 2013 18:58:26 -0500 Subject: libceph: define ceph_decode_pgid() only once There are two basically identical definitions of __decode_pgid() in libceph, one in "net/ceph/osdmap.c" and the other in "net/ceph/osd_client.c". Get rid of both, and instead define a single inline version in "include/linux/ceph/osdmap.h". Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osdmap.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 167daf60c4e8..d05cc4451af6 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -3,6 +3,7 @@ #include #include +#include #include #include @@ -119,6 +120,29 @@ static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map, return &map->osd_addr[osd]; } +static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid) +{ + __u8 version; + + if (!ceph_has_room(p, end, 1 + 8 + 4 + 4)) { + pr_warning("incomplete pg encoding"); + + return -EINVAL; + } + version = ceph_decode_8(p); + if (version > 1) { + pr_warning("do not understand pg encoding %d > 1", + (int)version); + return -EINVAL; + } + + pgid->pool = ceph_decode_64(p); + pgid->seed = ceph_decode_32(p); + *p += 4; /* skip deprecated preferred value */ + + return 0; +} + extern struct ceph_osdmap *osdmap_decode(void **p, void *end); extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, struct ceph_osdmap *map, -- cgit v1.2.3 From ace6d3a96f00c271b3f337adcde8e8cbe39c3820 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 1 Apr 2013 16:12:14 -0500 Subject: libceph: drop ceph_osd_request->r_con_filling_msg A field in an osd request keeps track of whether a connection is currently filling the request's reply message. This patch gets rid of that field. An osd request includes two messages--a request and a reply--and they're both associated with the connection that existed to its the target osd at the time the request was created. An osd request can be dropped early, even when it's in flight. And at that time both messages are released. It's possible the reply message has been supplied to its connection to receive an incoming response message at the time the osd request gets dropped. So ceph_osdc_release_request() revokes that message from the connection before releasing it so things get cleaned up properly. Previously this may have caused a problem, because the connection that a message was associated with might have gone away before the revoke request. And to avoid any problems using that connection, the osd client held a reference to it when it supplies its response message. However since this commit: 38941f80 libceph: have messages point to their connection all messages hold a reference to the connection they are associated with whenever the connection is actively operating on the message (i.e. while the message is queued to send or sending, and when it data is being received into it). And if a message has no connection associated with it, ceph_msg_revoke_incoming() won't do anything when asked to revoke it. As a result, there is no need to keep an additional reference to the connection associated with a message when we hand the message to the messenger when it calls our alloc_msg() method to receive something. If the connection *were* operating on it, it would have its own reference, and if not, there's no work to be done when we need to revoke it. So get rid of the osd request's r_con_filling_msg field. This resolves: http://tracker.ceph.com/issues/4647 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 5fd2cbfcfd91..3b5ba31c2cbd 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -89,8 +89,6 @@ struct ceph_osd_request { int r_pg_osds[CEPH_PG_MAX_SIZE]; int r_num_pg_osds; - struct ceph_connection *r_con_filling_msg; - struct ceph_msg *r_request, *r_reply; int r_flags; /* any additional flags for the osd */ u32 r_sent; /* >0 if r_request is sending/sent */ -- cgit v1.2.3 From fdce58ccb5df621695b079378c619046acabc778 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:06 -0500 Subject: libceph: record length of bio list with bio When assigning a bio pointer to an osd request, we don't have an efficient way of knowing the total length bytes in the bio list. That information is available at the point it's set up by the rbd code, so record it with the osd data when it's set. This and the next patch are related to maintaining the length of a message's data independent of the message header, as described here: http://tracker.ceph.com/issues/4589 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 3b5ba31c2cbd..fdda93ebbb4c 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -71,7 +71,10 @@ struct ceph_osd_data { }; struct ceph_pagelist *pagelist; #ifdef CONFIG_BLOCK - struct bio *bio; + struct { + struct bio *bio; /* list of bios */ + size_t bio_length; /* total in list */ + }; #endif /* CONFIG_BLOCK */ }; }; -- cgit v1.2.3 From a19308048182d5f9e16b03b1d1c038d9346c7589 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:06 -0500 Subject: libceph: record message data length Keep track of the length of the data portion for a message in a separate field in the ceph_msg structure. This information has been maintained in wire byte order in the message header, but that's going to change soon. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 3181321bed6d..b832c0ce899a 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -139,6 +139,7 @@ struct ceph_msg { struct kvec front; /* unaligned blobs of message */ struct ceph_buffer *middle; + size_t data_length; struct ceph_msg_data *data; /* data payload */ struct ceph_connection *con; @@ -270,7 +271,8 @@ extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, size_t length, size_t alignment); extern void ceph_msg_data_set_pagelist(struct ceph_msg *msg, struct ceph_pagelist *pagelist); -extern void ceph_msg_data_set_bio(struct ceph_msg *msg, struct bio *bio); +extern void ceph_msg_data_set_bio(struct ceph_msg *msg, struct bio *bio, + size_t length); extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); -- cgit v1.2.3 From acead002b200569273bed331c93c4a91d25e10b8 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:05 -0500 Subject: libceph: don't build request in ceph_osdc_new_request() This patch moves the call to ceph_osdc_build_request() out of ceph_osdc_new_request() and into its caller. This is in order to defer formatting osd operation information into the request message until just before request is started. The only unusual (ab)user of ceph_osdc_build_request() is ceph_writepages_start(), where the final length of write request may change (downward) based on the current inode size or the oldest snapshot context with dirty data for the inode. The remaining callers don't change anything in the request after has been built. This means the ops array is now supplied by the caller. It also means there is no need to pass the mtime to ceph_osdc_new_request() (it gets provided to ceph_osdc_build_request()). And rather than passing a do_sync flag, have the number of ops in the ops array supplied imply adding a second STARTSYNC operation after the READ or WRITE requested. This and some of the patches that follow are related to having the messenger (only) be responsible for filling the content of the message header, as described here: http://tracker.ceph.com/issues/4589 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index fdda93ebbb4c..ffaf9076fdc4 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -243,12 +243,12 @@ extern void osd_req_op_watch_init(struct ceph_osd_req_op *op, u16 opcode, extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, - unsigned int num_op, + unsigned int num_ops, bool use_mempool, gfp_t gfp_flags); extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off, - unsigned int num_op, + unsigned int num_ops, struct ceph_osd_req_op *src_ops, struct ceph_snap_context *snapc, u64 snap_id, @@ -257,11 +257,11 @@ extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off, extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, struct ceph_file_layout *layout, struct ceph_vino vino, - u64 offset, u64 *len, int op, int flags, + u64 offset, u64 *len, + int num_ops, struct ceph_osd_req_op *ops, + int opcode, int flags, struct ceph_snap_context *snapc, - int do_sync, u32 truncate_seq, - u64 truncate_size, - struct timespec *mtime, + u32 truncate_seq, u64 truncate_size, bool use_mempool); extern void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc, -- cgit v1.2.3 From e5975c7c8eb6aeab8d2f76a98c368081082795e0 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:05 -0500 Subject: ceph: build osd request message later for writepages Hold off building the osd request message in ceph_writepages_start() until just before it will be submitted to the osd client for execution. We'll still create the request and allocate the page pointer array after we learn we have at least one page to write. A local variable will be used to keep track of the allocated array of pages. Wait until just before submitting the request for assigning that page array pointer to the request message. Create ands use a new function osd_req_op_extent_update() whose purpose is to serve this one spot where the length value supplied when an osd request's op was initially formatted might need to get changed (reduced, never increased) before submitting the request. Previously, ceph_writepages_start() assigned the message header's data length because of this update. That's no longer necessary, because ceph_osdc_build_request() will recalculate the right value to use based on the content of the ops in the request. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index ffaf9076fdc4..5ee1a3776b4b 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -234,6 +234,7 @@ extern void osd_req_op_init(struct ceph_osd_req_op *op, u16 opcode); extern void osd_req_op_extent_init(struct ceph_osd_req_op *op, u16 opcode, u64 offset, u64 length, u64 truncate_size, u32 truncate_seq); +extern void osd_req_op_extent_update(struct ceph_osd_req_op *op, u64 length); extern void osd_req_op_cls_init(struct ceph_osd_req_op *op, u16 opcode, const char *class, const char *method, const void *request_data, -- cgit v1.2.3 From 43bfe5de9fa78e07248b70992ce50321efec622c Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 3 Apr 2013 01:28:57 -0500 Subject: libceph: define osd data initialization helpers Define and use functions that encapsulate the initializion of a ceph_osd_data structure. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 5ee1a3776b4b..af60dac1f9c0 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -280,6 +280,17 @@ static inline void ceph_osdc_put_request(struct ceph_osd_request *req) kref_put(&req->r_kref, ceph_osdc_release_request); } +extern void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data, + struct page **pages, u64 length, + u32 alignment, bool pages_from_pool, + bool own_pages); +extern void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data, + struct ceph_pagelist *pagelist); +#ifdef CONFIG_BLOCK +extern void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data, + struct bio *bio, size_t bio_length); +#endif /* CONFIG_BLOCK */ + extern int ceph_osdc_start_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req, bool nofail); -- cgit v1.2.3 From 79528734f3ae4699a2886f62f55e18fb34fb3651 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 3 Apr 2013 21:32:51 -0500 Subject: libceph: keep source rather than message osd op array An osd request keeps a pointer to the osd operations (ops) array that it builds in its request message. In order to allow each op in the array to have its own distinct data, we will need to keep track of each op's data, and that information does not go over the wire. As long as we're tracking the data we might as well just track the entire (source) op definition for each of the ops. And if we're doing that, we'll have no more need to keep a pointer to the wire-encoded version. This patch makes the array of source ops be kept with the osd request structure, and uses that instead of the version encoded in the message in places where that was previously used. The array will be embedded in the request structure, and the maximum number of ops we ever actually use is currently 2. So reduce CEPH_OSD_MAX_OP to 2 to reduce the size of the structure. The result of doing this sort of ripples back up, and as a result various function parameters and local variables become unnecessary. Make r_num_ops be unsigned, and move the definition of struct ceph_osd_req_op earlier to ensure it's defined where needed. It does not yet add per-op data, that's coming soon. This resolves: http://tracker.ceph.com/issues/4656 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 70 ++++++++++++++++++++--------------------- 1 file changed, 34 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index af60dac1f9c0..f4c1a2a22a14 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -48,7 +48,7 @@ struct ceph_osd { }; -#define CEPH_OSD_MAX_OP 10 +#define CEPH_OSD_MAX_OP 2 enum ceph_osd_data_type { CEPH_OSD_DATA_TYPE_NONE, @@ -79,6 +79,34 @@ struct ceph_osd_data { }; }; +struct ceph_osd_req_op { + u16 op; /* CEPH_OSD_OP_* */ + u32 payload_len; + union { + struct { + u64 offset, length; + u64 truncate_size; + u32 truncate_seq; + } extent; + struct { + const char *class_name; + const char *method_name; + const void *indata; + u32 indata_len; + __u8 class_len; + __u8 method_len; + __u8 argc; + } cls; + struct { + u64 cookie; + u64 ver; + u32 prot_ver; + u32 timeout; + __u8 flag; + } watch; + }; +}; + /* an in-flight request */ struct ceph_osd_request { u64 r_tid; /* unique for this client */ @@ -95,10 +123,11 @@ struct ceph_osd_request { struct ceph_msg *r_request, *r_reply; int r_flags; /* any additional flags for the osd */ u32 r_sent; /* >0 if r_request is sending/sent */ - int r_num_ops; - /* encoded message content */ - struct ceph_osd_op *r_request_ops; + /* request osd ops array */ + unsigned int r_num_ops; + struct ceph_osd_req_op r_ops[CEPH_OSD_MAX_OP]; + /* these are updated on each send */ __le32 *r_request_osdmap_epoch; __le32 *r_request_flags; @@ -193,34 +222,6 @@ struct ceph_osd_client { struct workqueue_struct *notify_wq; }; -struct ceph_osd_req_op { - u16 op; /* CEPH_OSD_OP_* */ - u32 payload_len; - union { - struct { - u64 offset, length; - u64 truncate_size; - u32 truncate_seq; - } extent; - struct { - const char *class_name; - const char *method_name; - const void *indata; - u32 indata_len; - __u8 class_len; - __u8 method_len; - __u8 argc; - } cls; - struct { - u64 cookie; - u64 ver; - u32 prot_ver; - u32 timeout; - __u8 flag; - } watch; - }; -}; - extern int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client); extern void ceph_osdc_stop(struct ceph_osd_client *osdc); @@ -249,8 +250,6 @@ extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client * gfp_t gfp_flags); extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off, - unsigned int num_ops, - struct ceph_osd_req_op *src_ops, struct ceph_snap_context *snapc, u64 snap_id, struct timespec *mtime); @@ -259,8 +258,7 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *, struct ceph_file_layout *layout, struct ceph_vino vino, u64 offset, u64 *len, - int num_ops, struct ceph_osd_req_op *ops, - int opcode, int flags, + int num_ops, int opcode, int flags, struct ceph_snap_context *snapc, u32 truncate_seq, u64 truncate_size, bool use_mempool); -- cgit v1.2.3 From 54d5064912649e296552f298e6472ffd37cd8f90 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 3 Apr 2013 01:28:58 -0500 Subject: libceph: rename data out field in osd request op There are fields "indata" and "indata_len" defined the ceph osd request op structure. The "in" part is with from the point of view of the osd server, but is a little confusing here on the client side. Change their names to use "request" instead of "in" to indicate that it defines data provided with the request (as opposed the data returned in the response). Rename the local variable in osd_req_encode_op() to match. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index f4c1a2a22a14..a9c4089894c8 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -91,8 +91,8 @@ struct ceph_osd_req_op { struct { const char *class_name; const char *method_name; - const void *indata; - u32 indata_len; + const void *request_data; + u32 request_data_len; __u8 class_len; __u8 method_len; __u8 argc; -- cgit v1.2.3 From 8c042b0df99cd06ef8473ef6e204b87b3dc80158 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 3 Apr 2013 01:28:58 -0500 Subject: libceph: add data pointers in osd op structures An extent type osd operation currently implies that there will be corresponding data supplied in the data portion of the request (for write) or response (for read) message. Similarly, an osd class method operation implies a data item will be supplied to receive the response data from the operation. Add a ceph_osd_data pointer to each of those structures, and assign it to point to eithre the incoming or the outgoing data structure in the osd message. The data is not always available when an op is initially set up, so add two new functions to allow setting them after the op has been initialized. Begin to make use of the data item pointer available in the osd operation rather than the request data in or out structure in places where it's convenient. Add some assertions to verify pointers are always set the way they're expected to be. This is a sort of stepping stone toward really moving the data into the osd request ops, to allow for some validation before making that jump. This is the first in a series of patches that resolve: http://tracker.ceph.com/issues/4657 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index a9c4089894c8..ae5193550fbf 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -87,12 +87,14 @@ struct ceph_osd_req_op { u64 offset, length; u64 truncate_size; u32 truncate_seq; + struct ceph_osd_data *osd_data; } extent; struct { const char *class_name; const char *method_name; const void *request_data; u32 request_data_len; + struct ceph_osd_data *response_data; __u8 class_len; __u8 method_len; __u8 argc; @@ -236,10 +238,14 @@ extern void osd_req_op_extent_init(struct ceph_osd_req_op *op, u16 opcode, u64 offset, u64 length, u64 truncate_size, u32 truncate_seq); extern void osd_req_op_extent_update(struct ceph_osd_req_op *op, u64 length); +extern void osd_req_op_extent_osd_data(struct ceph_osd_req_op *op, + struct ceph_osd_data *osd_data); extern void osd_req_op_cls_init(struct ceph_osd_req_op *op, u16 opcode, const char *class, const char *method, const void *request_data, size_t request_data_size); +extern void osd_req_op_cls_response_data(struct ceph_osd_req_op *op, + struct ceph_osd_data *response_data); extern void osd_req_op_watch_init(struct ceph_osd_req_op *op, u16 opcode, u64 cookie, u64 version, int flag); -- cgit v1.2.3 From c99d2d4abb6c405ef52e9bc1da87b382b8f41739 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 01:27:11 -0500 Subject: libceph: specify osd op by index in request An osd request now holds all of its source op structures, and every place that initializes one of these is in fact initializing one of the entries in the the osd request's array. So rather than supplying the address of the op to initialize, have caller specify the osd request and an indication of which op it would like to initialize. This better hides the details the op structure (and faciltates moving the data pointers they use). Since osd_req_op_init() is a common routine, and it's not used outside the osd client code, give it static scope. Also make it return the address of the specified op (so all the other init routines don't have to repeat that code). Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index ae5193550fbf..144d57cbef9e 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -233,20 +233,25 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); -extern void osd_req_op_init(struct ceph_osd_req_op *op, u16 opcode); -extern void osd_req_op_extent_init(struct ceph_osd_req_op *op, u16 opcode, +extern void osd_req_op_extent_init(struct ceph_osd_request *osd_req, + unsigned int which, u16 opcode, u64 offset, u64 length, u64 truncate_size, u32 truncate_seq); -extern void osd_req_op_extent_update(struct ceph_osd_req_op *op, u64 length); -extern void osd_req_op_extent_osd_data(struct ceph_osd_req_op *op, +extern void osd_req_op_extent_update(struct ceph_osd_request *osd_req, + unsigned int which, u64 length); +extern void osd_req_op_extent_osd_data(struct ceph_osd_request *osd_req, + unsigned int which, struct ceph_osd_data *osd_data); -extern void osd_req_op_cls_init(struct ceph_osd_req_op *op, u16 opcode, +extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req, + unsigned int which, u16 opcode, const char *class, const char *method, const void *request_data, size_t request_data_size); -extern void osd_req_op_cls_response_data(struct ceph_osd_req_op *op, +extern void osd_req_op_cls_response_data(struct ceph_osd_request *osd_req, + unsigned int which, struct ceph_osd_data *response_data); -extern void osd_req_op_watch_init(struct ceph_osd_req_op *op, u16 opcode, +extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req, + unsigned int which, u16 opcode, u64 cookie, u64 version, int flag); extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, -- cgit v1.2.3 From 5f562df5f59340eae4272501b974903f48d2ad92 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 01:27:12 -0500 Subject: libceph: format class info at init time An object class method is formatted using a pagelist which contains the class name, the method name, and the data concatenated into an osd request's outbound data. Currently when a class op is initialized in osd_req_op_cls_init(), the lengths of and pointers to these three items are recorded. Later, when the op is getting formatted into the request message, a new pagelist is created and that is when these items get copied into the pagelist. This patch makes it so the pagelist to hold these items is created when the op is initialized instead. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 144d57cbef9e..71c41575646d 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -93,8 +93,9 @@ struct ceph_osd_req_op { const char *class_name; const char *method_name; const void *request_data; - u32 request_data_len; + struct ceph_osd_data *request_info; struct ceph_osd_data *response_data; + u32 request_data_len; __u8 class_len; __u8 method_len; __u8 argc; -- cgit v1.2.3 From a4ce40a9a7c1053ac2a41cf64255e44e356e5522 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 01:27:12 -0500 Subject: libceph: combine initializing and setting osd data This ends up being a rather large patch but what it's doing is somewhat straightforward. Basically, this is replacing two calls with one. The first of the two calls is initializing a struct ceph_osd_data with data (either a page array, a page list, or a bio list); the second is setting an osd request op so it associates that data with one of the op's parameters. In place of those two will be a single function that initializes the op directly. That means we sort of fan out a set of the needed functions: - extent ops with pages data - extent ops with pagelist data - extent ops with bio list data and - class ops with page data for receiving a response We also have define another one, but it's only used internally: - class ops with pagelist data for request parameters Note that we *still* haven't gotten rid of the osd request's r_data_in and r_data_out fields. All the osd ops refer to them for their data. For now, these data fields are pointers assigned to the appropriate r_data_* field when these new functions are called. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 43 ++++++++++++++++++++++++++--------------- 1 file changed, 27 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 71c41575646d..f8a00b48e550 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -240,17 +240,39 @@ extern void osd_req_op_extent_init(struct ceph_osd_request *osd_req, u64 truncate_size, u32 truncate_seq); extern void osd_req_op_extent_update(struct ceph_osd_request *osd_req, unsigned int which, u64 length); -extern void osd_req_op_extent_osd_data(struct ceph_osd_request *osd_req, + +extern struct ceph_osd_data *osd_req_op_extent_osd_data( + struct ceph_osd_request *osd_req, + unsigned int which, bool write_request); +extern struct ceph_osd_data *osd_req_op_cls_response_data( + struct ceph_osd_request *osd_req, + unsigned int which); + +extern void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *, + unsigned int which, bool write_request, + struct page **pages, u64 length, + u32 alignment, bool pages_from_pool, + bool own_pages); +extern void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *, + unsigned int which, bool write_request, + struct ceph_pagelist *pagelist); +#ifdef CONFIG_BLOCK +extern void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *, + unsigned int which, bool write_request, + struct bio *bio, size_t bio_length); +#endif /* CONFIG_BLOCK */ + +extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, unsigned int which, - struct ceph_osd_data *osd_data); + struct page **pages, u64 length, + u32 alignment, bool pages_from_pool, + bool own_pages); + extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, const char *class, const char *method, const void *request_data, size_t request_data_size); -extern void osd_req_op_cls_response_data(struct ceph_osd_request *osd_req, - unsigned int which, - struct ceph_osd_data *response_data); extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u64 cookie, u64 version, int flag); @@ -290,17 +312,6 @@ static inline void ceph_osdc_put_request(struct ceph_osd_request *req) kref_put(&req->r_kref, ceph_osdc_release_request); } -extern void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data, - struct page **pages, u64 length, - u32 alignment, bool pages_from_pool, - bool own_pages); -extern void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data, - struct ceph_pagelist *pagelist); -#ifdef CONFIG_BLOCK -extern void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data, - struct bio *bio, size_t bio_length); -#endif /* CONFIG_BLOCK */ - extern int ceph_osdc_start_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req, bool nofail); -- cgit v1.2.3 From ec9123c56787fa7fb2608f05b19d21c5e1912d87 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 01:27:12 -0500 Subject: libceph: set the data pointers when encoding ops Still using the osd request r_data_in and r_data_out pointer, but we're basically only referring to it via the data pointers in the osd ops. And we're transferring that information to the request or reply message only when the op indicates it's needed, in osd_req_encode_op(). To avoid a forward reference, ceph_osdc_msg_data_set() was moved up in the file. Don't bother calling ceph_osd_data_init(), in ceph_osd_alloc(), because the ops array will already be zeroed anyway. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index f8a00b48e550..dd4ca4ba8cab 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -51,7 +51,7 @@ struct ceph_osd { #define CEPH_OSD_MAX_OP 2 enum ceph_osd_data_type { - CEPH_OSD_DATA_TYPE_NONE, + CEPH_OSD_DATA_TYPE_NONE = 0, CEPH_OSD_DATA_TYPE_PAGES, CEPH_OSD_DATA_TYPE_PAGELIST, #ifdef CONFIG_BLOCK -- cgit v1.2.3 From 5476492fba9fd0b4118aacf5b924dd29b8cca56c Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 01:27:12 -0500 Subject: libceph: kill off osd request r_data_in and r_data_out Finally! Convert the osd op data pointers into real structures, and make the switch over to using them instead of having all ops share the in and/or out data structures in the osd request. Set up a new function to traverse the set of ops and release any data associated with them (pages). This and the patches leading up to it resolve: http://tracker.ceph.com/issues/4657 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index dd4ca4ba8cab..4ec46c0ceaf7 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -87,14 +87,14 @@ struct ceph_osd_req_op { u64 offset, length; u64 truncate_size; u32 truncate_seq; - struct ceph_osd_data *osd_data; + struct ceph_osd_data osd_data; } extent; struct { const char *class_name; const char *method_name; const void *request_data; - struct ceph_osd_data *request_info; - struct ceph_osd_data *response_data; + struct ceph_osd_data request_info; + struct ceph_osd_data response_data; u32 request_data_len; __u8 class_len; __u8 method_len; @@ -164,9 +164,6 @@ struct ceph_osd_request { struct ceph_file_layout r_file_layout; struct ceph_snap_context *r_snapc; /* snap context for writes */ - - struct ceph_osd_data r_data_in; - struct ceph_osd_data r_data_out; }; struct ceph_osd_event { -- cgit v1.2.3 From ea96571f7b865edaf1acd472e6f2cddc9fb67892 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 14:46:01 -0500 Subject: libceph: fix possible CONFIG_BLOCK build problem This patch: 15a0d7b libceph: record message data length did not enclose some bio-specific code inside CONFIG_BLOCK as it should have. Fix that. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index b832c0ce899a..cdeebae03e0d 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -271,8 +271,10 @@ extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, size_t length, size_t alignment); extern void ceph_msg_data_set_pagelist(struct ceph_msg *msg, struct ceph_pagelist *pagelist); +#ifdef CONFIG_BLOCK extern void ceph_msg_data_set_bio(struct ceph_msg *msg, struct bio *bio, size_t length); +#endif /* CONFIG_BLOCK */ extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); -- cgit v1.2.3 From c851c49591ebf000c610711e39eea7da5ff05b21 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 14:46:01 -0500 Subject: libceph: record bio length The bio is the only data item type that doesn't record its full length. Fix that. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index cdeebae03e0d..4fb870a5b5fc 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -116,7 +116,10 @@ struct ceph_msg_data { enum ceph_msg_data_type type; union { #ifdef CONFIG_BLOCK - struct bio *bio; + struct { + struct bio *bio; + size_t bio_length; + }; #endif /* CONFIG_BLOCK */ struct { struct page **pages; /* NOT OWNER. */ -- cgit v1.2.3 From 36153ec9dd6287d7cedf6afb51453c445d946cee Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:06 -0500 Subject: libceph: move cursor into message A message will only be processing a single data item at a time, so there's no need for each data item to have its own cursor. Move the cursor embedded in the message data structure into the message itself. To minimize the impact, keep the data->cursor field, but make it be a pointer to the cursor in the message. Move the definition of ceph_msg_data above ceph_msg_data_cursor so the cursor can point to the data without a forward definition rather than vice-versa. This and the upcoming patches are part of: http://tracker.ceph.com/issues/3761 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 43 +++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 4fb870a5b5fc..e7557242817c 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -88,6 +88,25 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) } } +struct ceph_msg_data { + enum ceph_msg_data_type type; + union { +#ifdef CONFIG_BLOCK + struct { + struct bio *bio; + size_t bio_length; + }; +#endif /* CONFIG_BLOCK */ + struct { + struct page **pages; /* NOT OWNER. */ + size_t length; /* total # bytes */ + unsigned int alignment; /* first page */ + }; + struct ceph_pagelist *pagelist; + }; + struct ceph_msg_data_cursor *cursor; +}; + struct ceph_msg_data_cursor { size_t resid; /* bytes not yet consumed */ bool last_piece; /* now at last piece of data item */ @@ -112,25 +131,6 @@ struct ceph_msg_data_cursor { }; }; -struct ceph_msg_data { - enum ceph_msg_data_type type; - union { -#ifdef CONFIG_BLOCK - struct { - struct bio *bio; - size_t bio_length; - }; -#endif /* CONFIG_BLOCK */ - struct { - struct page **pages; /* NOT OWNER. */ - size_t length; /* total # bytes */ - unsigned int alignment; /* first page */ - }; - struct ceph_pagelist *pagelist; - }; - struct ceph_msg_data_cursor cursor; /* pagelist only */ -}; - /* * a single message. it contains a header (src, dest, message type, etc.), * footer (crc values, mainly), a "front" message body, and possibly a @@ -142,8 +142,9 @@ struct ceph_msg { struct kvec front; /* unaligned blobs of message */ struct ceph_buffer *middle; - size_t data_length; - struct ceph_msg_data *data; /* data payload */ + size_t data_length; + struct ceph_msg_data *data; + struct ceph_msg_data_cursor cursor; struct ceph_connection *con; struct list_head list_head; /* links for connection lists */ -- cgit v1.2.3 From 8ae4f4f5c056150d5480710ab356801e84d01a3d Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:06 -0500 Subject: libceph: have cursor point to data Rather than having a ceph message data item point to the cursor it's associated with, have the cursor point to a data item. This will allow a message cursor to be used for more than one data item. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index e7557242817c..8846ff610502 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -104,13 +104,13 @@ struct ceph_msg_data { }; struct ceph_pagelist *pagelist; }; - struct ceph_msg_data_cursor *cursor; }; struct ceph_msg_data_cursor { - size_t resid; /* bytes not yet consumed */ - bool last_piece; /* now at last piece of data item */ - bool need_crc; /* new piece; crc update needed */ + struct ceph_msg_data *data; /* data item this describes */ + size_t resid; /* bytes not yet consumed */ + bool last_piece; /* current is last piece */ + bool need_crc; /* crc update needed */ union { #ifdef CONFIG_BLOCK struct { /* bio */ -- cgit v1.2.3 From 5240d9f95dfe0f0701b35fbff1cb5b70825ad23f Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 14 Mar 2013 14:09:06 -0500 Subject: libceph: replace message data pointer with list In place of the message data pointer, use a list head which links through message data items. For now we only support a single entry on that list. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 8846ff610502..318da0170a1e 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -89,6 +89,7 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) } struct ceph_msg_data { + struct list_head links; /* ceph_msg->data */ enum ceph_msg_data_type type; union { #ifdef CONFIG_BLOCK @@ -143,7 +144,7 @@ struct ceph_msg { struct ceph_buffer *middle; size_t data_length; - struct ceph_msg_data *data; + struct list_head data; struct ceph_msg_data_cursor cursor; struct ceph_connection *con; -- cgit v1.2.3 From ca8b3a69174b04376722672d7dd6b666a7f17c50 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 14:46:01 -0500 Subject: libceph: implement multiple data items in a message This patch adds support to the messenger for more than one data item in its data list. A message data cursor has two more fields to support this: - a count of the number of bytes left to be consumed across all data items in the list, "total_resid" - a pointer to the head of the list (for validation only) The cursor initialization routine has been split into two parts: the outer one, which initializes the cursor for traversing the entire list of data items; and the inner one, which initializes the cursor to start processing a single data item. When a message cursor is first initialized, the outer initialization routine sets total_resid to the length provided. The data pointer is initialized to the first data item on the list. From there, the inner initialization routine finishes by setting up to process the data item the cursor points to. Advancing the cursor consumes bytes in total_resid. If the resid field reaches zero, it means the current data item is fully consumed. If total_resid indicates there is more data, the cursor is advanced to point to the next data item, and then the inner initialization routine prepares for using that. (A check is made at this point to make sure we don't wrap around the front of the list.) The type-specific init routines are modified so they can be given a length that's larger than what the data item can support. The resid field is initialized to the smaller of the provided length and the length of the entire data item. When total_resid reaches zero, we're done. This resolves: http://tracker.ceph.com/issues/3761 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 318da0170a1e..de1d2e1ecce2 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -108,7 +108,10 @@ struct ceph_msg_data { }; struct ceph_msg_data_cursor { - struct ceph_msg_data *data; /* data item this describes */ + size_t total_resid; /* across all data items */ + struct list_head *data_head; /* = &ceph_msg->data */ + + struct ceph_msg_data *data; /* current data item */ size_t resid; /* bytes not yet consumed */ bool last_piece; /* current is last piece */ bool need_crc; /* crc update needed */ -- cgit v1.2.3 From 90af36022aecdeeb1b9c0755461187de717c86dd Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 14:46:01 -0500 Subject: libceph: add, don't set data for a message Change the names of the functions that put data on a pagelist to reflect that we're adding to whatever's already there rather than just setting it to the one thing. Currently only one data item is ever added to a message, but that's about to change. This resolves: http://tracker.ceph.com/issues/2770 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/messenger.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index de1d2e1ecce2..7c1420bb1dce 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -275,12 +275,12 @@ extern void ceph_msg_revoke_incoming(struct ceph_msg *msg); extern void ceph_con_keepalive(struct ceph_connection *con); -extern void ceph_msg_data_set_pages(struct ceph_msg *msg, struct page **pages, +extern void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, size_t length, size_t alignment); -extern void ceph_msg_data_set_pagelist(struct ceph_msg *msg, +extern void ceph_msg_data_add_pagelist(struct ceph_msg *msg, struct ceph_pagelist *pagelist); #ifdef CONFIG_BLOCK -extern void ceph_msg_data_set_bio(struct ceph_msg *msg, struct bio *bio, +extern void ceph_msg_data_add_bio(struct ceph_msg *msg, struct bio *bio, size_t length); #endif /* CONFIG_BLOCK */ -- cgit v1.2.3 From 04017e29bbcf0673d8a6af616c56e395d05f5971 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 5 Apr 2013 14:46:02 -0500 Subject: libceph: make method call data be a separate data item Right now the data for a method call is specified via a pointer and length, and it's copied--along with the class and method name--into a pagelist data item to be sent to the osd. Instead, encode the data in a data item separate from the class and method names. This will allow large amounts of data to be supplied to methods without copying. Only rbd uses the class functionality right now, and when it really needs this it will probably need to use a page array rather than a page list. But this simple implementation demonstrates the functionality on the osd client, and that's enough for now. This resolves: http://tracker.ceph.com/issues/4104 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 4ec46c0ceaf7..2a68a7465c18 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -92,10 +92,9 @@ struct ceph_osd_req_op { struct { const char *class_name; const char *method_name; - const void *request_data; struct ceph_osd_data request_info; + struct ceph_osd_data request_data; struct ceph_osd_data response_data; - u32 request_data_len; __u8 class_len; __u8 method_len; __u8 argc; @@ -259,6 +258,9 @@ extern void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *, struct bio *bio, size_t bio_length); #endif /* CONFIG_BLOCK */ +extern void osd_req_op_cls_request_data_pagelist(struct ceph_osd_request *, + unsigned int which, + struct ceph_pagelist *pagelist); extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, unsigned int which, struct page **pages, u64 length, @@ -267,9 +269,7 @@ extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, - const char *class, const char *method, - const void *request_data, - size_t request_data_size); + const char *class, const char *method); extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u64 cookie, u64 version, int flag); -- cgit v1.2.3 From 26be88087ae8a04a5b576aa2f490597b649fc132 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 15 Apr 2013 11:20:42 -0500 Subject: libceph: change how "safe" callback is used An osd request currently has two callbacks. They inform the initiator of the request when we've received confirmation for the target osd that a request was received, and when the osd indicates all changes described by the request are durable. The only time the second callback is used is in the ceph file system for a synchronous write. There's a race that makes some handling of this case unsafe. This patch addresses this problem. The error handling for this callback is also kind of gross, and this patch changes that as well. In ceph_sync_write(), if a safe callback is requested we want to add the request on the ceph inode's unsafe items list. Because items on this list must have their tid set (by ceph_osd_start_request()), the request added *after* the call to that function returns. The problem with this is that there's a race between starting the request and adding it to the unsafe items list; the request may already be complete before ceph_sync_write() even begins to put it on the list. To address this, we change the way the "safe" callback is used. Rather than just calling it when the request is "safe", we use it to notify the initiator the bounds (start and end) of the period during which the request is *unsafe*. So the initiator gets notified just before the request gets sent to the osd (when it is "unsafe"), and again when it's known the results are durable (it's no longer unsafe). The first call will get made in __send_request(), just before the request message gets sent to the messenger for the first time. That function is only called by __send_queued(), which is always called with the osd client's request mutex held. We then have this callback function insert the request on the ceph inode's unsafe list when we're told the request is unsafe. This will avoid the race because this call will be made under protection of the osd client's request mutex. It also nicely groups the setup and cleanup of the state associated with managing unsafe requests. The name of the "safe" callback field is changed to "unsafe" to better reflect its new purpose. It has a Boolean "unsafe" parameter to indicate whether the request is becoming unsafe or is now safe. Because the "msg" parameter wasn't used, we drop that. This resolves the original problem reportedin: http://tracker.ceph.com/issues/4706 Reported-by: Yan, Zheng Signed-off-by: Alex Elder Reviewed-by: Yan, Zheng Reviewed-by: Sage Weil --- include/linux/ceph/osd_client.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 2a68a7465c18..0d3358ef5285 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -29,6 +29,7 @@ struct ceph_authorizer; */ typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *, struct ceph_msg *); +typedef void (*ceph_osdc_unsafe_callback_t)(struct ceph_osd_request *, bool); /* a given osd we're communicating with */ struct ceph_osd { @@ -149,7 +150,8 @@ struct ceph_osd_request { struct kref r_kref; bool r_mempool; struct completion r_completion, r_safe_completion; - ceph_osdc_callback_t r_callback, r_safe_callback; + ceph_osdc_callback_t r_callback; + ceph_osdc_unsafe_callback_t r_unsafe_callback; struct ceph_eversion r_reassert_version; struct list_head r_unsafe_item; -- cgit v1.2.3 From 406e2c9f9286fc93ae2191a7abf477dea05aadc9 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 15 Apr 2013 14:50:36 -0500 Subject: libceph: kill off osd data write_request parameters In the incremental move toward supporting distinct data items in an osd request some of the functions had "write_request" parameters to indicate, basically, whether the data belonged to in_data or the out_data. Now that we maintain the data fields in the op structure there is no need to indicate the direction, so get rid of the "write_request" parameters. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 0d3358ef5285..0e406934a551 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -241,22 +241,22 @@ extern void osd_req_op_extent_update(struct ceph_osd_request *osd_req, extern struct ceph_osd_data *osd_req_op_extent_osd_data( struct ceph_osd_request *osd_req, - unsigned int which, bool write_request); + unsigned int which); extern struct ceph_osd_data *osd_req_op_cls_response_data( struct ceph_osd_request *osd_req, unsigned int which); extern void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *, - unsigned int which, bool write_request, + unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages); extern void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *, - unsigned int which, bool write_request, + unsigned int which, struct ceph_pagelist *pagelist); #ifdef CONFIG_BLOCK extern void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *, - unsigned int which, bool write_request, + unsigned int which, struct bio *bio, size_t bio_length); #endif /* CONFIG_BLOCK */ -- cgit v1.2.3 From 49719778bfa5371ec9b5a7d989bb29000e3ac5df Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 11 Feb 2013 12:33:24 -0600 Subject: libceph: support raw data requests Allow osd request ops that aren't otherwise structured (not class, extent, or watch ops) to specify "raw" data to be used to hold incoming data for the op. Make use of this capability for the osd STAT op. Prefix the name of the private function osd_req_op_init() with "_", and expose a new function by that (earlier) name whose purpose is to initialize osd ops with (only) implied data. For now we'll just support the use of a page array for an osd op with incoming raw data. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 0e406934a551..4d84a2b44f18 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -84,6 +84,7 @@ struct ceph_osd_req_op { u16 op; /* CEPH_OSD_OP_* */ u32 payload_len; union { + struct ceph_osd_data raw_data_in; struct { u64 offset, length; u64 truncate_size; @@ -232,6 +233,15 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); +extern void osd_req_op_init(struct ceph_osd_request *osd_req, + unsigned int which, u16 opcode); + +extern void osd_req_op_raw_data_in_pages(struct ceph_osd_request *, + unsigned int which, + struct page **pages, u64 length, + u32 alignment, bool pages_from_pool, + bool own_pages); + extern void osd_req_op_extent_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u64 offset, u64 length, -- cgit v1.2.3 From 6c57b5545d46e276381a15a59283c984cf3f94e3 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 19 Apr 2013 15:34:49 -0500 Subject: libceph: support pages for class request data Add the ability to provide an array of pages as outbound request data for object class method calls. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 4d84a2b44f18..4191cd2c55e5 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -273,6 +273,11 @@ extern void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *, extern void osd_req_op_cls_request_data_pagelist(struct ceph_osd_request *, unsigned int which, struct ceph_pagelist *pagelist); +extern void osd_req_op_cls_request_data_pages(struct ceph_osd_request *, + unsigned int which, + struct page **pages, u64 length, + u32 alignment, bool pages_from_pool, + bool own_pages); extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, unsigned int which, struct page **pages, u64 length, -- cgit v1.2.3 From b587398a4ff6520753f9a58da294c80ee22443a5 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 19 Apr 2013 15:34:50 -0500 Subject: libceph: add signed type limits Flesh out the limits defined in to include the maximum and minimum values for signed type S8, S16, S32, and S64. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/decode.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 689f1df37bff..9575a52e011f 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -10,10 +10,20 @@ /* This seemed to be the easiest place to define these */ -#define U8_MAX ((u8) (~0U)) -#define U16_MAX ((u16) (~0U)) -#define U32_MAX ((u32) (~0U)) -#define U64_MAX ((u64) (~0ULL)) +#define U8_MAX ((u8)(~0U)) +#define U16_MAX ((u16)(~0U)) +#define U32_MAX ((u32)(~0U)) +#define U64_MAX ((u64)(~0ULL)) + +#define S8_MAX ((s8)(U8_MAX >> 1)) +#define S16_MAX ((s16)(U16_MAX >> 1)) +#define S32_MAX ((s32)(U32_MAX >> 1)) +#define S64_MAX ((s64)(U64_MAX >> 1LL)) + +#define S8_MIN ((s8)(-S8_MAX - 1)) +#define S16_MIN ((s16)(-S16_MAX - 1)) +#define S32_MIN ((s32)(-S32_MAX - 1)) +#define S64_MIN ((s64)(-S64_MAX - 1LL)) /* * in all cases, -- cgit v1.2.3 From c3f56102f28d90946171ae51753bd417b003fd42 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Fri, 19 Apr 2013 15:34:50 -0500 Subject: libceph: validate timespec conversions A ceph timespec contains 32-bit unsigned values for its seconds and nanoseconds components. For a standard timespec, both fields are signed, and the seconds field is almost surely 64 bits. Add some explicit casts so the fact that this conversion is taking place is obvious. Also trip a bug if we ever try to put out of range (negative or too big) values into a ceph timespec. Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/decode.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 9575a52e011f..379f71508995 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -154,14 +154,19 @@ bad: static inline void ceph_decode_timespec(struct timespec *ts, const struct ceph_timespec *tv) { - ts->tv_sec = le32_to_cpu(tv->tv_sec); - ts->tv_nsec = le32_to_cpu(tv->tv_nsec); + ts->tv_sec = (__kernel_time_t)le32_to_cpu(tv->tv_sec); + ts->tv_nsec = (long)le32_to_cpu(tv->tv_nsec); } static inline void ceph_encode_timespec(struct ceph_timespec *tv, const struct timespec *ts) { - tv->tv_sec = cpu_to_le32(ts->tv_sec); - tv->tv_nsec = cpu_to_le32(ts->tv_nsec); + BUG_ON(ts->tv_sec < 0); + BUG_ON(ts->tv_sec > (__kernel_time_t)U32_MAX); + BUG_ON(ts->tv_nsec < 0); + BUG_ON(ts->tv_nsec > (long)U32_MAX); + + tv->tv_sec = cpu_to_le32((u32)ts->tv_sec); + tv->tv_nsec = cpu_to_le32((u32)ts->tv_nsec); } /* -- cgit v1.2.3 From 4f0dcb10cf1454a1c38aeaa04cb2757535e4905e Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Tue, 30 Apr 2013 00:44:32 -0500 Subject: libceph: create source file "net/ceph/snapshot.c" This creates a new source file "net/ceph/snapshot.c" to contain utility routines related to ceph snapshot contexts. The main motivation was to define ceph_create_snap_context() as a common way to create these structures, but I've moved the definitions of ceph_get_snap_context() and ceph_put_snap_context() there too. (The benefit of inlining those is very small, and I'd rather keep this collection of functions together.) Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/libceph.h | 30 +++++------------------------- 1 file changed, 5 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 5493d7b86423..2e3024881a5e 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -157,31 +157,11 @@ struct ceph_snap_context { u64 snaps[]; }; -static inline struct ceph_snap_context * -ceph_get_snap_context(struct ceph_snap_context *sc) -{ - /* - printk("get_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref), - atomic_read(&sc->nref)+1); - */ - if (sc) - atomic_inc(&sc->nref); - return sc; -} - -static inline void ceph_put_snap_context(struct ceph_snap_context *sc) -{ - if (!sc) - return; - /* - printk("put_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref), - atomic_read(&sc->nref)-1); - */ - if (atomic_dec_and_test(&sc->nref)) { - /*printk(" deleting snap_context %p\n", sc);*/ - kfree(sc); - } -} +extern struct ceph_snap_context *ceph_create_snap_context(u32 snap_count, + gfp_t gfp_flags); +extern struct ceph_snap_context *ceph_get_snap_context( + struct ceph_snap_context *sc); +extern void ceph_put_snap_context(struct ceph_snap_context *sc); /* * calculate the number of pages a given length and offset map onto, -- cgit v1.2.3 From 5975a2e0950291a6bfe9fd5880e7952ff87764be Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Sat, 27 Apr 2013 00:28:37 +0000 Subject: KVM: PPC: Book3S: Add API for in-kernel XICS emulation This adds the API for userspace to instantiate an XICS device in a VM and connect VCPUs to it. The API consists of a new device type for the KVM_CREATE_DEVICE ioctl, a new capability KVM_CAP_IRQ_XICS, which functions similarly to KVM_CAP_IRQ_MPIC, and the KVM_IRQ_LINE ioctl, which is used to assert and deassert interrupt inputs of the XICS. The XICS device has one attribute group, KVM_DEV_XICS_GRP_SOURCES. Each attribute within this group corresponds to the state of one interrupt source. The attribute number is the same as the interrupt source number. This does not support irq routing or irqfd yet. Signed-off-by: Paul Mackerras Acked-by: David Gibson Signed-off-by: Alexander Graf --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 996661eb8e99..7823b6369c5e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1086,6 +1086,7 @@ void kvm_device_put(struct kvm_device *dev); struct kvm_device *kvm_device_from_filp(struct file *filp); extern struct kvm_device_ops kvm_mpic_ops; +extern struct kvm_device_ops kvm_xics_ops; #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT -- cgit v1.2.3 From c13d2b6d3640d1ef180e40191178b4f1271982c1 Mon Sep 17 00:00:00 2001 From: Bhanu Prakash Gollapudi Date: Fri, 8 Mar 2013 13:28:51 -0800 Subject: [SCSI] bnx2fc: Include chip number in the symbolic name [jejb: move PCI_DEVICE_ID definitions to include/pci_ids.h] Signed-off-by: Bhanu Prakash Gollapudi Signed-off-by: James Bottomley --- include/linux/pci_ids.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 2b85c521f737..c12916248469 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2147,11 +2147,13 @@ #define PCI_DEVICE_ID_TIGON3_5705M_2 0x165e #define PCI_DEVICE_ID_NX2_57712 0x1662 #define PCI_DEVICE_ID_NX2_57712E 0x1663 +#define PCI_DEVICE_ID_NX2_57712_MF 0x1663 #define PCI_DEVICE_ID_TIGON3_5714 0x1668 #define PCI_DEVICE_ID_TIGON3_5714S 0x1669 #define PCI_DEVICE_ID_TIGON3_5780 0x166a #define PCI_DEVICE_ID_TIGON3_5780S 0x166b #define PCI_DEVICE_ID_TIGON3_5705F 0x166e +#define PCI_DEVICE_ID_NX2_57712_VF 0x166f #define PCI_DEVICE_ID_TIGON3_5754M 0x1672 #define PCI_DEVICE_ID_TIGON3_5755M 0x1673 #define PCI_DEVICE_ID_TIGON3_5756 0x1674 @@ -2177,13 +2179,15 @@ #define PCI_DEVICE_ID_TIGON3_5787 0x169b #define PCI_DEVICE_ID_TIGON3_5788 0x169c #define PCI_DEVICE_ID_TIGON3_5789 0x169d +#define PCI_DEVICE_ID_NX2_57840_4_10 0x16a1 +#define PCI_DEVICE_ID_NX2_57840_2_20 0x16a2 +#define PCI_DEVICE_ID_NX2_57840_MF 0x16a4 #define PCI_DEVICE_ID_NX2_57800_MF 0x16a5 #define PCI_DEVICE_ID_TIGON3_5702X 0x16a6 #define PCI_DEVICE_ID_TIGON3_5703X 0x16a7 #define PCI_DEVICE_ID_TIGON3_5704S 0x16a8 #define PCI_DEVICE_ID_NX2_57800_VF 0x16a9 #define PCI_DEVICE_ID_NX2_5706S 0x16aa -#define PCI_DEVICE_ID_NX2_57840_MF 0x16a4 #define PCI_DEVICE_ID_NX2_5708S 0x16ac #define PCI_DEVICE_ID_NX2_57840_VF 0x16ad #define PCI_DEVICE_ID_NX2_57810_MF 0x16ae -- cgit v1.2.3 From 4ada8db38a44654446fe35ceb20a1972220e0f69 Mon Sep 17 00:00:00 2001 From: David Miller Date: Thu, 2 May 2013 04:31:32 -0400 Subject: net: Restore NETIF_F_* bit ordering. Commit 8ad227ff89a7 ("net: vlan: add 802.1ad support") added some new NETIF_F_* features bits, but it added them in the middle of existing values. Userland depends upon the flag bits via the per-netdevice 'flags' sysfs file. So restore the previous ordering by adding the new flags at the end. Reported-by: Linus Torvalds Signed-off-by: David S. Miller Signed-off-by: Linus Torvalds --- include/linux/netdev_features.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index cbaa027ef5a7..09906b7ca47d 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -25,9 +25,6 @@ enum { NETIF_F_HW_VLAN_CTAG_TX_BIT, /* Transmit VLAN CTAG HW acceleration */ NETIF_F_HW_VLAN_CTAG_RX_BIT, /* Receive VLAN CTAG HW acceleration */ NETIF_F_HW_VLAN_CTAG_FILTER_BIT,/* Receive filtering on VLAN CTAGs */ - NETIF_F_HW_VLAN_STAG_TX_BIT, /* Transmit VLAN STAG HW acceleration */ - NETIF_F_HW_VLAN_STAG_RX_BIT, /* Receive VLAN STAG HW acceleration */ - NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */ NETIF_F_VLAN_CHALLENGED_BIT, /* Device cannot handle VLAN packets */ NETIF_F_GSO_BIT, /* Enable software GSO. */ NETIF_F_LLTX_BIT, /* LockLess TX - deprecated. Please */ @@ -59,6 +56,9 @@ enum { NETIF_F_LOOPBACK_BIT, /* Enable loopback */ NETIF_F_RXFCS_BIT, /* Append FCS to skb pkt data */ NETIF_F_RXALL_BIT, /* Receive errored frames too */ + NETIF_F_HW_VLAN_STAG_TX_BIT, /* Transmit VLAN STAG HW acceleration */ + NETIF_F_HW_VLAN_STAG_RX_BIT, /* Receive VLAN STAG HW acceleration */ + NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */ /* * Add your fresh new feature above and remember to update @@ -86,9 +86,6 @@ enum { #define NETIF_F_HW_VLAN_CTAG_FILTER __NETIF_F(HW_VLAN_CTAG_FILTER) #define NETIF_F_HW_VLAN_CTAG_RX __NETIF_F(HW_VLAN_CTAG_RX) #define NETIF_F_HW_VLAN_CTAG_TX __NETIF_F(HW_VLAN_CTAG_TX) -#define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER) -#define NETIF_F_HW_VLAN_STAG_RX __NETIF_F(HW_VLAN_STAG_RX) -#define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) #define NETIF_F_IP_CSUM __NETIF_F(IP_CSUM) #define NETIF_F_IPV6_CSUM __NETIF_F(IPV6_CSUM) #define NETIF_F_LLTX __NETIF_F(LLTX) @@ -110,6 +107,9 @@ enum { #define NETIF_F_RXALL __NETIF_F(RXALL) #define NETIF_F_GSO_GRE __NETIF_F(GSO_GRE) #define NETIF_F_GSO_UDP_TUNNEL __NETIF_F(GSO_UDP_TUNNEL) +#define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER) +#define NETIF_F_HW_VLAN_STAG_RX __NETIF_F(HW_VLAN_STAG_RX) +#define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ -- cgit v1.2.3 From de61608acf89779c8831aaa1428b6975d49d98c0 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Fri, 19 Apr 2013 11:42:14 +0200 Subject: dma:of: Use a mutex to protect the of_dma_list Currently the OF DMA code uses a spin lock to protect the of_dma_list from concurrent access and a per controller reference count to protect the controller from being freed while a request operation is in progress. If of_dma_controller_free() is called for a controller who's reference count is not zero it will return -EBUSY and not remove the controller. This is fine up until here, but leaves the question what the caller of of_dma_controller_free() is supposed to do if the controller couldn't be freed. The only viable solution for the caller is to spin on of_dma_controller_free() until it returns success. E.g. do { ret = of_dma_controller_free(dev->of_node) } while (ret != -EBUSY); This is rather ugly and unnecessary and none of the current users of of_dma_controller_free() check it's return value anyway. Instead protect the list by a mutex. The mutex will be held as long as a request operation is in progress. So if of_dma_controller_free() is called while a request operation is in progress it will be put to sleep and only wake up once the request operation has finished. This means that it is no longer possible to register or unregister OF DMA controllers from a context where it's not possible to sleep. But I doubt that we'll ever need this. Also rename of_dma_get_controller back to of_dma_find_controller. Signed-off-by: Lars-Peter Clausen Acked-by: Arnd Bergmann Signed-off-by: Vinod Koul --- include/linux/of_dma.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_dma.h b/include/linux/of_dma.h index ce6a8ab3d2bb..364dda734877 100644 --- a/include/linux/of_dma.h +++ b/include/linux/of_dma.h @@ -25,7 +25,6 @@ struct of_dma { struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *); void *of_dma_data; - int use_count; }; struct of_dma_filter_info { @@ -38,7 +37,7 @@ extern int of_dma_controller_register(struct device_node *np, struct dma_chan *(*of_dma_xlate) (struct of_phandle_args *, struct of_dma *), void *data); -extern int of_dma_controller_free(struct device_node *np); +extern void of_dma_controller_free(struct device_node *np); extern struct dma_chan *of_dma_request_slave_channel(struct device_node *np, const char *name); extern struct dma_chan *of_dma_simple_xlate(struct of_phandle_args *dma_spec, @@ -52,9 +51,8 @@ static inline int of_dma_controller_register(struct device_node *np, return -ENODEV; } -static inline int of_dma_controller_free(struct device_node *np) +static inline void of_dma_controller_free(struct device_node *np) { - return -ENODEV; } static inline struct dma_chan *of_dma_request_slave_channel(struct device_node *np, -- cgit v1.2.3 From 5522ae0b68421e2645303ff010e27afc5292e0ab Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Wed, 1 May 2013 12:43:04 -0500 Subject: libceph: use slab cache for osd client requests Create a slab cache to manage allocation of ceph_osdc_request structures. This resolves: http://tracker.ceph.com/issues/3926 Signed-off-by: Alex Elder Reviewed-by: Josh Durgin --- include/linux/ceph/osd_client.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 4191cd2c55e5..186db0bf4951 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -224,6 +224,9 @@ struct ceph_osd_client { struct workqueue_struct *notify_wq; }; +extern int ceph_osdc_setup(void); +extern void ceph_osdc_cleanup(void); + extern int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client); extern void ceph_osdc_stop(struct ceph_osd_client *osdc); -- cgit v1.2.3 From 159b67d7aefe3902df91075be5d80943c1570aa8 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 9 Apr 2013 17:13:20 -0600 Subject: NVMe: Device specific stripe size handling We have an nvme device that has a concept of a stripe size. IO requests that do not transfer data crossing a stripe boundary has greater performance compared to IO that does cross it. This patch sets the stripe size for the device if the device and vendor ids match one with this feature and splits IO requests that cross the stripe boundary. Signed-off-by: Keith Busch Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 9b6fba872f47..af29b0e0b092 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -536,6 +536,7 @@ struct nvme_dev { char model[40]; char firmware_rev[8]; u32 max_hw_sectors; + u32 stripe_size; u16 oncs; }; -- cgit v1.2.3 From f410c680b5344f1cb63ff011c6ae3d4963f45c30 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 23 Apr 2013 17:23:59 -0600 Subject: NVMe: Meta-data support in NVME_IOCTL_SUBMIT_IO This adds support for namespaces with separate meta-data formats in the submit io ioctl. The meta-data buffer has to be a contiguous, so such a buffer is allocated and the mapped user pages are copied to/from this buffer for write/read commands. Signed-off-by: Keith Busch Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index af29b0e0b092..971ef086ed63 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -552,6 +552,7 @@ struct nvme_ns { int ns_id; int lba_shift; + int ms; u64 mode_select_num_blocks; u32 mode_select_block_len; }; -- cgit v1.2.3 From 265f22a975c1e4cc3a4d1f94a3ec53ffbb6f5b9f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 3 May 2013 03:39:05 +0200 Subject: sched: Keep at least 1 tick per second for active dynticks tasks The scheduler doesn't yet fully support environments with a single task running without a periodic tick. In order to ensure we still maintain the duties of scheduler_tick(), keep at least 1 tick per second. This makes sure that we keep the progression of various scheduler accounting and background maintainance even with a very low granularity. Examples include cpu load, sched average, CFS entity vruntime, avenrun and events such as load balancing, amongst other details handled in sched_class::task_tick(). This limitation will be removed in the future once we get these individual items to work in full dynticks CPUs. Suggested-by: Ingo Molnar Signed-off-by: Frederic Weisbecker Cc: Christoph Lameter Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ebf7095158a9..af008d7bad57 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1862,6 +1862,7 @@ static inline void wake_up_nohz_cpu(int cpu) { } #ifdef CONFIG_NO_HZ_FULL extern bool sched_can_stop_tick(void); +extern u64 scheduler_tick_max_deferment(void); #else static inline bool sched_can_stop_tick(void) { return false; } #endif -- cgit v1.2.3 From e765acb4673f377c53505c01279c040906bd706e Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 3 May 2013 22:20:38 +0200 Subject: nubus: Kill nubus_proc_detach_device() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 59d8053f1e16904d54ed7469d4b36801ea6b8f2c ("proc: Move non-public stuff from linux/proc_fs.h to fs/proc/internal.h") broke Apple NuBus support: drivers/nubus/proc.c: In function ‘nubus_proc_detach_device’: drivers/nubus/proc.c:156: error: dereferencing pointer to incomplete type drivers/nubus/proc.c:158: error: dereferencing pointer to incomplete type Fortunately nubus_proc_detach_device() is unused, and appears to have never been used, so just remove it. Signed-off-by: Geert Uytterhoeven Signed-off-by: Al Viro --- include/linux/nubus.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nubus.h b/include/linux/nubus.h index b3740527571a..6165b2c62040 100644 --- a/include/linux/nubus.h +++ b/include/linux/nubus.h @@ -87,7 +87,6 @@ static inline void nubus_proc_init(void) {} #endif int get_nubus_list(char *buf); int nubus_proc_attach_device(struct nubus_dev *dev); -int nubus_proc_detach_device(struct nubus_dev *dev); /* If we need more precision we can add some more of these */ struct nubus_dev* nubus_find_device(unsigned short category, unsigned short type, -- cgit v1.2.3 From 5ae98f1589e076e4b314fc54ae2beac58842ddc2 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Sat, 4 May 2013 00:11:23 +0200 Subject: fs: Fix hang with BSD accounting on frozen filesystem When BSD process accounting is enabled and logs information to a filesystem which gets frozen, system easily becomes unusable because each attempt to account process information blocks. Thus e.g. every task gets blocked in exit. It seems better to drop accounting information (which can already happen when filesystem is running out of space) instead of locking system up. So we just skip the write if the filesystem is frozen. Reported-by: Nikola Ciprich Signed-off-by: Jan Kara Signed-off-by: Al Viro --- include/linux/fs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e8cd6b839675..b5a24ba83b6f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2227,6 +2227,13 @@ static inline void file_start_write(struct file *file) __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); } +static inline bool file_start_write_trylock(struct file *file) +{ + if (!S_ISREG(file_inode(file)->i_mode)) + return true; + return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false); +} + static inline void file_end_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) -- cgit v1.2.3 From a8ca889ed9585894d53fd8919d80cbe8baff09e7 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 5 May 2013 21:31:22 -0400 Subject: mtd_blktrans_ops->release() should return void Both existing instances always return 0 and even if they didn't, the value would be lost on the way out. Just don't bother... Signed-off-by: Al Viro --- include/linux/mtd/blktrans.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index 4eb0a50d0c55..e93837f647de 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -74,7 +74,7 @@ struct mtd_blktrans_ops { /* Called with mtd_table_mutex held; no race with add/remove */ int (*open)(struct mtd_blktrans_dev *dev); - int (*release)(struct mtd_blktrans_dev *dev); + void (*release)(struct mtd_blktrans_dev *dev); /* Called on {de,}registration and on subsequent addition/removal of devices, with mtd_table_mutex held. */ -- cgit v1.2.3 From 6286ae97d10ea2b5cd90532163797ab217bfdbdf Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 3 May 2013 15:43:18 +0000 Subject: slab: Return NULL for oversized allocations The inline path seems to have changed the SLAB behavior for very large kmalloc allocations with commit e3366016 ("slab: Use common kmalloc_index/kmalloc_size functions"). This patch restores the old behavior but also adds diagnostics so that we can figure where in the code these large allocations occur. Reported-and-tested-by: Tetsuo Handa Signed-off-by: Christoph Lameter Link: http://lkml.kernel.org/r/201305040348.CIF81716.OStQOHFJMFLOVF@I-love.SAKURA.ne.jp [ penberg@kernel.org: use WARN_ON_ONCE ] Signed-off-by: Pekka Enberg --- include/linux/slab_def.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 113ec080313f..cd401580bdd3 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -126,6 +126,9 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) if (!size) return ZERO_SIZE_PTR; + if (WARN_ON_ONCE(size > KMALLOC_MAX_SIZE)) + return NULL; + i = kmalloc_index(size); #ifdef CONFIG_ZONE_DMA @@ -172,6 +175,9 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) if (!size) return ZERO_SIZE_PTR; + if (WARN_ON_ONCE(size > KMALLOC_MAX_SIZE)) + return NULL; + i = kmalloc_index(size); #ifdef CONFIG_ZONE_DMA -- cgit v1.2.3 From 1deb9d341d475ff84262e927d6c0e36fecb9942e Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Mon, 6 May 2013 13:05:50 +0200 Subject: HID: debug: fix RCU preemption issue Commit 2353f2bea ("HID: protect hid_debug_list") introduced mutex locking around debug_list access to prevent SMP races when debugfs nodes are being operated upon by multiple userspace processess. mutex is not a proper synchronization primitive though, as the hid-debug callbacks are being called from atomic contexts. We also have to be careful about disabling IRQs when taking the lock to prevent deadlock against IRQ handlers. Benjamin reports this has also been reported in RH bugzilla as bug #958935. =============================== [ INFO: suspicious RCU usage. ] 3.9.0+ #94 Not tainted ------------------------------- include/linux/rcupdate.h:476 Illegal context switch in RCU read-side critical section! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 0 4 locks held by Xorg/5502: #0: (&evdev->mutex){+.+...}, at: [] evdev_write+0x6d/0x160 #1: (&(&dev->event_lock)->rlock#2){-.-...}, at: [] input_inject_event+0x5b/0x230 #2: (rcu_read_lock){.+.+..}, at: [] input_inject_event+0x42/0x230 #3: (&(&usbhid->lock)->rlock){-.....}, at: [] usb_hidinput_input_event+0x89/0x120 stack backtrace: CPU: 0 PID: 5502 Comm: Xorg Not tainted 3.9.0+ #94 Hardware name: Dell Inc. OptiPlex 390/0M5DCD, BIOS A09 07/24/2012 0000000000000001 ffff8800689c7c38 ffffffff816f249f ffff8800689c7c68 ffffffff810acb1d 0000000000000000 ffffffff81a03ac7 000000000000019d 0000000000000000 ffff8800689c7c90 ffffffff8107cda7 0000000000000000 Call Trace: [] dump_stack+0x19/0x1b [] lockdep_rcu_suspicious+0xfd/0x130 [] __might_sleep+0xc7/0x230 [] mutex_lock_nested+0x40/0x3a0 [] ? vsnprintf+0x354/0x640 [] hid_debug_event+0x34/0x100 [] hid_dump_input+0x67/0xa0 [] hid_set_field+0x50/0x120 [] usb_hidinput_input_event+0x9a/0x120 [] input_handle_event+0x8e/0x530 [] input_inject_event+0x1d0/0x230 [] ? input_inject_event+0x42/0x230 [] evdev_write+0xde/0x160 [] vfs_write+0xc8/0x1f0 [] SyS_write+0x55/0xa0 [] system_call_fastpath+0x16/0x1b BUG: sleeping function called from invalid context at kernel/mutex.c:413 in_atomic(): 1, irqs_disabled(): 1, pid: 5502, name: Xorg INFO: lockdep is turned off. irq event stamp: 1098574 hardirqs last enabled at (1098573): [] _raw_spin_unlock_irqrestore+0x3f/0x70 hardirqs last disabled at (1098574): [] _raw_spin_lock_irqsave+0x25/0xa0 softirqs last enabled at (1098306): [] __do_softirq+0x18f/0x3c0 softirqs last disabled at (1097867): [] irq_exit+0xa5/0xb0 CPU: 0 PID: 5502 Comm: Xorg Not tainted 3.9.0+ #94 Hardware name: Dell Inc. OptiPlex 390/0M5DCD, BIOS A09 07/24/2012 ffffffff81a03ac7 ffff8800689c7c68 ffffffff816f249f ffff8800689c7c90 ffffffff8107ce60 0000000000000000 ffff8800689c7fd8 ffff88006a62c800 ffff8800689c7d10 ffffffff816f7770 ffff8800689c7d00 ffffffff81312ac4 Call Trace: [] dump_stack+0x19/0x1b [] __might_sleep+0x180/0x230 [] mutex_lock_nested+0x40/0x3a0 [] ? vsnprintf+0x354/0x640 [] hid_debug_event+0x34/0x100 [] hid_dump_input+0x67/0xa0 [] hid_set_field+0x50/0x120 [] usb_hidinput_input_event+0x9a/0x120 [] input_handle_event+0x8e/0x530 [] input_inject_event+0x1d0/0x230 [] ? input_inject_event+0x42/0x230 [] evdev_write+0xde/0x160 [] vfs_write+0xc8/0x1f0 [] SyS_write+0x55/0xa0 [] system_call_fastpath+0x16/0x1b Reported-by: majianpeng Reported-by: Benjamin Tissoires Reviewed-by: Dmitry Torokhov Signed-off-by: Jiri Kosina --- include/linux/hid.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index af1b86d46f6e..0c48991b0402 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -515,7 +515,7 @@ struct hid_device { /* device report descriptor */ struct dentry *debug_rdesc; struct dentry *debug_events; struct list_head debug_list; - struct mutex debug_list_lock; + spinlock_t debug_list_lock; wait_queue_head_t debug_wait; }; -- cgit v1.2.3 From 243198d09f535f5cd74114f1b779c3da25bc70c8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 5 May 2013 16:05:55 +0000 Subject: rps_dev_flow_table_release(): no need to delay vfree() The same story as with fib_trie patch - vfree() from RCU callbacks is legitimate now. Signed-off-by: Al Viro Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f8898a435dc5..a94a5a0ab122 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -593,7 +593,6 @@ struct rps_dev_flow { struct rps_dev_flow_table { unsigned int mask; struct rcu_head rcu; - struct work_struct free_work; struct rps_dev_flow flows[0]; }; #define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ -- cgit v1.2.3 From 7c1d5fae4a87d3cf3e9ffd68bcdbaf6529013009 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 3 May 2013 14:40:01 -0400 Subject: NFSv4: Convert nfs41_free_stateid to use an asynchronous RPC call The main reason for doing this is will be to allow for an asynchronous RPC mode that we can use for freeing lock stateids as per section 8.2.4 of RFC5661. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 766c5bc9d441..104b62f23ee0 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1176,7 +1176,7 @@ struct nfs41_test_stateid_res { struct nfs41_free_stateid_args { struct nfs4_sequence_args seq_args; - nfs4_stateid *stateid; + nfs4_stateid stateid; }; struct nfs41_free_stateid_res { -- cgit v1.2.3 From db2a144bedd58b3dcf19950c2f476c58c9f39d18 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 5 May 2013 21:52:57 -0400 Subject: block_device_operations->release() should return void The value passed is 0 in all but "it can never happen" cases (and those only in a couple of drivers) *and* it would've been lost on the way out anyway, even if something tried to pass something meaningful. Just don't bother. Signed-off-by: Al Viro --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 78feda9bbae2..e38cfe77f7f0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1484,7 +1484,7 @@ static inline bool blk_integrity_is_initialized(struct gendisk *g) struct block_device_operations { int (*open) (struct block_device *, fmode_t); - int (*release) (struct gendisk *, fmode_t); + void (*release) (struct gendisk *, fmode_t); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*direct_access) (struct block_device *, sector_t, -- cgit v1.2.3 From 4385bab128911df14ab25f0b5ae1a48d7b53dd94 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 5 May 2013 22:11:03 -0400 Subject: make blkdev_put() return void same story as with the previous patches - note that return value of blkdev_close() is lost, since there's nowhere the caller (__fput()) could return it to. Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b5a24ba83b6f..43db02e9c9fa 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2091,7 +2091,7 @@ extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); -extern int blkdev_put(struct block_device *bdev, fmode_t mode); +extern void blkdev_put(struct block_device *bdev, fmode_t mode); #ifdef CONFIG_SYSFS extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); extern void bd_unlink_disk_holder(struct block_device *bdev, -- cgit v1.2.3 From 2d864e41710f1d2ba406fb62018ab0487152e6f2 Mon Sep 17 00:00:00 2001 From: Anatol Pomozov Date: Tue, 7 May 2013 15:37:48 -0700 Subject: kref: minor cleanup - make warning smp-safe - result of atomic _unless_zero functions should be checked by caller to avoid use-after-free error - trivial whitespace fix. Link: https://lkml.org/lkml/2013/4/12/391 Tested: compile x86, boot machine and run xfstests Signed-off-by: Anatol Pomozov [ Removed line-break, changed to use WARN_ON_ONCE() - Linus ] Signed-off-by: Linus Torvalds --- include/linux/kref.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kref.h b/include/linux/kref.h index 4972e6e9ca93..e15828fd71f1 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -39,8 +39,11 @@ static inline void kref_init(struct kref *kref) */ static inline void kref_get(struct kref *kref) { - WARN_ON(!atomic_read(&kref->refcount)); - atomic_inc(&kref->refcount); + /* If refcount was 0 before incrementing then we have a race + * condition when this kref is freeing by some other thread right now. + * In this case one should use kref_get_unless_zero() + */ + WARN_ON_ONCE(atomic_inc_return(&kref->refcount) < 2); } /** @@ -100,7 +103,7 @@ static inline int kref_put_mutex(struct kref *kref, struct mutex *lock) { WARN_ON(release == NULL); - if (unlikely(!atomic_add_unless(&kref->refcount, -1, 1))) { + if (unlikely(!atomic_add_unless(&kref->refcount, -1, 1))) { mutex_lock(lock); if (unlikely(!atomic_dec_and_test(&kref->refcount))) { mutex_unlock(lock); -- cgit v1.2.3 From 0f157a5b58d0d2890f0ae20da9fe66aa19a91a4d Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Tue, 7 May 2013 16:18:10 -0700 Subject: include/linux/mm.h: complete the mm_walk definition That nameless-function-arguments thing drives me batty. Fix. Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1a7f19e7f1a0..e0c8528a41a4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -951,13 +951,19 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * (see walk_page_range for more details) */ struct mm_walk { - int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, struct mm_walk *); - int (*pud_entry)(pud_t *, unsigned long, unsigned long, struct mm_walk *); - int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *); - int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *); - int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *); - int (*hugetlb_entry)(pte_t *, unsigned long, - unsigned long, unsigned long, struct mm_walk *); + int (*pgd_entry)(pgd_t *pgd, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*pud_entry)(pud_t *pud, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*pmd_entry)(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*pte_entry)(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*pte_hole)(unsigned long addr, unsigned long next, + struct mm_walk *walk); + int (*hugetlb_entry)(pte_t *pte, unsigned long hmask, + unsigned long addr, unsigned long next, + struct mm_walk *walk); struct mm_struct *mm; void *private; }; -- cgit v1.2.3 From af73e4d9506d3b797509f3c030e7dcd554f7d9c4 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Tue, 7 May 2013 16:18:13 -0700 Subject: hugetlbfs: fix mmap failure in unaligned size request The current kernel returns -EINVAL unless a given mmap length is "almost" hugepage aligned. This is because in sys_mmap_pgoff() the given length is passed to vm_mmap_pgoff() as it is without being aligned with hugepage boundary. This is a regression introduced in commit 40716e29243d ("hugetlbfs: fix alignment of huge page requests"), where alignment code is pushed into hugetlb_file_setup() and the variable len in caller side is not changed. To fix this, this patch partially reverts that commit, and adds alignment code in caller side. And it also introduces hstate_sizelog() in order to get proper hstate to specified hugepage size. Addresses https://bugzilla.kernel.org/show_bug.cgi?id=56881 [akpm@linux-foundation.org: fix warning when CONFIG_HUGETLB_PAGE=n] Signed-off-by: Naoya Horiguchi Signed-off-by: Johannes Weiner Reported-by: Cc: Steven Truelove Cc: Jianguo Wu Cc: Hugh Dickins Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3a62df310f2e..6b4890fa57e7 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -189,8 +189,7 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; -struct file *hugetlb_file_setup(const char *name, unsigned long addr, - size_t size, vm_flags_t acct, +struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, struct user_struct **user, int creat_flags, int page_size_log); @@ -209,8 +208,8 @@ static inline int is_file_hugepages(struct file *file) #define is_file_hugepages(file) 0 static inline struct file * -hugetlb_file_setup(const char *name, unsigned long addr, size_t size, - vm_flags_t acctflag, struct user_struct **user, int creat_flags, +hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, + struct user_struct **user, int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); @@ -288,6 +287,13 @@ static inline struct hstate *hstate_file(struct file *f) return hstate_inode(file_inode(f)); } +static inline struct hstate *hstate_sizelog(int page_size_log) +{ + if (!page_size_log) + return &default_hstate; + return size_to_hstate(1 << page_size_log); +} + static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return hstate_file(vma->vm_file); @@ -352,11 +358,12 @@ static inline int hstate_index(struct hstate *h) return h - hstates; } -#else +#else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; #define alloc_huge_page_node(h, nid) NULL #define alloc_bootmem_huge_page(h) NULL #define hstate_file(f) NULL +#define hstate_sizelog(s) NULL #define hstate_vma(v) NULL #define hstate_inode(i) NULL #define huge_page_size(h) PAGE_SIZE @@ -371,6 +378,6 @@ static inline unsigned int pages_per_huge_page(struct hstate *h) } #define hstate_index_to_shift(index) 0 #define hstate_index(h) 0 -#endif +#endif /* CONFIG_HUGETLB_PAGE */ #endif /* _LINUX_HUGETLB_H */ -- cgit v1.2.3 From 22ea9c070350b824d6c3b65bce06ee7c6cc87b99 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Tue, 7 May 2013 16:18:17 -0700 Subject: remove unused random32() and srandom32() After finishing a naming transition, remove unused backward compatibility wrapper macros Signed-off-by: Akinobu Mita Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/random.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/random.h b/include/linux/random.h index 347ce553a306..3b9377d6b7a5 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -29,13 +29,6 @@ u32 prandom_u32(void); void prandom_bytes(void *buf, int nbytes); void prandom_seed(u32 seed); -/* - * These macros are preserved for backward compatibility and should be - * removed as soon as a transition is finished. - */ -#define random32() prandom_u32() -#define srandom32(seed) prandom_seed(seed) - u32 prandom_u32_state(struct rnd_state *); void prandom_bytes_state(struct rnd_state *state, void *buf, int nbytes); -- cgit v1.2.3 From 4b49bb8ad6d6e6e564017e2fad2357c3024683eb Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Tue, 7 May 2013 16:18:21 -0700 Subject: aio: remove dead code from aio.h Signed-off-by: Zach Brown Signed-off-by: Kent Overstreet Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Acked-by: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 31ff6dba4872..b46a09f73f1d 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -9,44 +9,22 @@ #include -#define AIO_MAXSEGS 4 -#define AIO_KIOGRP_NR_ATOMIC 8 - struct kioctx; -/* Notes on cancelling a kiocb: - * If a kiocb is cancelled, aio_complete may return 0 to indicate - * that cancel has not yet disposed of the kiocb. All cancel - * operations *must* call aio_put_req to dispose of the kiocb - * to guard against races with the completion code. - */ -#define KIOCB_C_CANCELLED 0x01 -#define KIOCB_C_COMPLETE 0x02 - #define KIOCB_SYNC_KEY (~0U) /* ki_flags bits */ -/* - * This may be used for cancel/retry serialization in the future, but - * for now it's unused and we probably don't want modules to even - * think they can use it. - */ -/* #define KIF_LOCKED 0 */ #define KIF_KICKED 1 #define KIF_CANCELLED 2 -#define kiocbTryLock(iocb) test_and_set_bit(KIF_LOCKED, &(iocb)->ki_flags) #define kiocbTryKick(iocb) test_and_set_bit(KIF_KICKED, &(iocb)->ki_flags) -#define kiocbSetLocked(iocb) set_bit(KIF_LOCKED, &(iocb)->ki_flags) #define kiocbSetKicked(iocb) set_bit(KIF_KICKED, &(iocb)->ki_flags) #define kiocbSetCancelled(iocb) set_bit(KIF_CANCELLED, &(iocb)->ki_flags) -#define kiocbClearLocked(iocb) clear_bit(KIF_LOCKED, &(iocb)->ki_flags) #define kiocbClearKicked(iocb) clear_bit(KIF_KICKED, &(iocb)->ki_flags) #define kiocbClearCancelled(iocb) clear_bit(KIF_CANCELLED, &(iocb)->ki_flags) -#define kiocbIsLocked(iocb) test_bit(KIF_LOCKED, &(iocb)->ki_flags) #define kiocbIsKicked(iocb) test_bit(KIF_KICKED, &(iocb)->ki_flags) #define kiocbIsCancelled(iocb) test_bit(KIF_CANCELLED, &(iocb)->ki_flags) @@ -207,8 +185,6 @@ struct kioctx { }; /* prototypes */ -extern unsigned aio_max_size; - #ifdef CONFIG_AIO extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb); extern int aio_put_req(struct kiocb *iocb); -- cgit v1.2.3 From 41003a7bcfed1255032e1e7c7b487e505b22e298 Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Tue, 7 May 2013 16:18:25 -0700 Subject: aio: remove retry-based AIO This removes the retry-based AIO infrastructure now that nothing in tree is using it. We want to remove retry-based AIO because it is fundemantally unsafe. It retries IO submission from a kernel thread that has only assumed the mm of the submitting task. All other task_struct references in the IO submission path will see the kernel thread, not the submitting task. This design flaw means that nothing of any meaningful complexity can use retry-based AIO. This removes all the code and data associated with the retry machinery. The most significant benefit of this is the removal of the locking around the unused run list in the submission path. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Kent Overstreet Signed-off-by: Zach Brown Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Acked-by: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 22 ---------------------- include/linux/errno.h | 1 - 2 files changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index b46a09f73f1d..019204e46c11 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -14,18 +14,12 @@ struct kioctx; #define KIOCB_SYNC_KEY (~0U) /* ki_flags bits */ -#define KIF_KICKED 1 #define KIF_CANCELLED 2 -#define kiocbTryKick(iocb) test_and_set_bit(KIF_KICKED, &(iocb)->ki_flags) - -#define kiocbSetKicked(iocb) set_bit(KIF_KICKED, &(iocb)->ki_flags) #define kiocbSetCancelled(iocb) set_bit(KIF_CANCELLED, &(iocb)->ki_flags) -#define kiocbClearKicked(iocb) clear_bit(KIF_KICKED, &(iocb)->ki_flags) #define kiocbClearCancelled(iocb) clear_bit(KIF_CANCELLED, &(iocb)->ki_flags) -#define kiocbIsKicked(iocb) test_bit(KIF_KICKED, &(iocb)->ki_flags) #define kiocbIsCancelled(iocb) test_bit(KIF_CANCELLED, &(iocb)->ki_flags) /* is there a better place to document function pointer methods? */ @@ -52,18 +46,8 @@ struct kioctx; * not ask the method again -- ki_retry must ensure forward progress. * aio_complete() must be called once and only once in the future, multiple * calls may result in undefined behaviour. - * - * If ki_retry returns -EIOCBRETRY it has made a promise that kick_iocb() - * will be called on the kiocb pointer in the future. This may happen - * through generic helpers that associate kiocb->ki_wait with a wait - * queue head that ki_retry uses via current->io_wait. It can also happen - * with custom tracking and manual calls to kick_iocb(), though that is - * discouraged. In either case, kick_iocb() must be called once and only - * once. ki_retry must ensure forward progress, the AIO core will wait - * indefinitely for kick_iocb() to be called. */ struct kiocb { - struct list_head ki_run_list; unsigned long ki_flags; int ki_users; unsigned ki_key; /* id of this request */ @@ -160,7 +144,6 @@ static inline unsigned aio_ring_avail(struct aio_ring_info *info, struct kioctx { atomic_t users; int dead; - struct mm_struct *mm; /* This needs improving */ unsigned long user_id; @@ -172,15 +155,12 @@ struct kioctx { int reqs_active; struct list_head active_reqs; /* used for cancellation */ - struct list_head run_list; /* used for kicked reqs */ /* sys_io_setup currently limits this to an unsigned int */ unsigned max_reqs; struct aio_ring_info ring_info; - struct delayed_work wq; - struct rcu_head rcu_head; }; @@ -188,7 +168,6 @@ struct kioctx { #ifdef CONFIG_AIO extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb); extern int aio_put_req(struct kiocb *iocb); -extern void kick_iocb(struct kiocb *iocb); extern int aio_complete(struct kiocb *iocb, long res, long res2); struct mm_struct; extern void exit_aio(struct mm_struct *mm); @@ -197,7 +176,6 @@ extern long do_io_submit(aio_context_t ctx_id, long nr, #else static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; } static inline int aio_put_req(struct kiocb *iocb) { return 0; } -static inline void kick_iocb(struct kiocb *iocb) { } static inline int aio_complete(struct kiocb *iocb, long res, long res2) { return 0; } struct mm_struct; static inline void exit_aio(struct mm_struct *mm) { } diff --git a/include/linux/errno.h b/include/linux/errno.h index f6bf082d4d4f..89627b9187f9 100644 --- a/include/linux/errno.h +++ b/include/linux/errno.h @@ -28,6 +28,5 @@ #define EBADTYPE 527 /* Type not supported by server */ #define EJUKEBOX 528 /* Request initiated, but will not complete before timeout */ #define EIOCBQUEUED 529 /* iocb queued, will get completion event */ -#define EIOCBRETRY 530 /* iocb queued, will trigger a retry */ #endif -- cgit v1.2.3 From 2d68449e86168744513ca4f13477f081ce167130 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:18:29 -0700 Subject: aio: kill return value of aio_complete() Nothing used the return value, and it probably wasn't possible to use it safely for the locked versions (aio_complete(), aio_put_req()). Just kill it. Signed-off-by: Kent Overstreet Acked-by: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Acked-by: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 019204e46c11..615d55a5d0be 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -167,16 +167,16 @@ struct kioctx { /* prototypes */ #ifdef CONFIG_AIO extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb); -extern int aio_put_req(struct kiocb *iocb); -extern int aio_complete(struct kiocb *iocb, long res, long res2); +extern void aio_put_req(struct kiocb *iocb); +extern void aio_complete(struct kiocb *iocb, long res, long res2); struct mm_struct; extern void exit_aio(struct mm_struct *mm); extern long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user *__user *iocbpp, bool compat); #else static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; } -static inline int aio_put_req(struct kiocb *iocb) { return 0; } -static inline int aio_complete(struct kiocb *iocb, long res, long res2) { return 0; } +static inline void aio_put_req(struct kiocb *iocb) { } +static inline void aio_complete(struct kiocb *iocb, long res, long res2) { } struct mm_struct; static inline void exit_aio(struct mm_struct *mm) { } static inline long do_io_submit(aio_context_t ctx_id, long nr, -- cgit v1.2.3 From 4e179bca6718693148c7445c236bc3e0e0013ffd Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:18:33 -0700 Subject: aio: move private stuff out of aio.h Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Acked-by: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 61 ----------------------------------------------------- 1 file changed, 61 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 615d55a5d0be..7b1eb234e0ab 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -103,67 +103,6 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) }; } -#define AIO_RING_MAGIC 0xa10a10a1 -#define AIO_RING_COMPAT_FEATURES 1 -#define AIO_RING_INCOMPAT_FEATURES 0 -struct aio_ring { - unsigned id; /* kernel internal index number */ - unsigned nr; /* number of io_events */ - unsigned head; - unsigned tail; - - unsigned magic; - unsigned compat_features; - unsigned incompat_features; - unsigned header_length; /* size of aio_ring */ - - - struct io_event io_events[0]; -}; /* 128 bytes + ring size */ - -#define AIO_RING_PAGES 8 -struct aio_ring_info { - unsigned long mmap_base; - unsigned long mmap_size; - - struct page **ring_pages; - spinlock_t ring_lock; - long nr_pages; - - unsigned nr, tail; - - struct page *internal_pages[AIO_RING_PAGES]; -}; - -static inline unsigned aio_ring_avail(struct aio_ring_info *info, - struct aio_ring *ring) -{ - return (ring->head + info->nr - 1 - ring->tail) % info->nr; -} - -struct kioctx { - atomic_t users; - int dead; - - /* This needs improving */ - unsigned long user_id; - struct hlist_node list; - - wait_queue_head_t wait; - - spinlock_t ctx_lock; - - int reqs_active; - struct list_head active_reqs; /* used for cancellation */ - - /* sys_io_setup currently limits this to an unsigned int */ - unsigned max_reqs; - - struct aio_ring_info ring_info; - - struct rcu_head rcu_head; -}; - /* prototypes */ #ifdef CONFIG_AIO extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb); -- cgit v1.2.3 From 11599ebac4a249ab3c8b9a535c21db7a51458c0a Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:18:39 -0700 Subject: aio: make aio_put_req() lockless Freeing a kiocb needed to touch the kioctx for three things: * Pull it off the reqs_active list * Decrementing reqs_active * Issuing a wakeup, if the kioctx was in the process of being freed. This patch moves these to aio_complete(), for a couple reasons: * aio_complete() already has to issue the wakeup, so if we drop the kioctx refcount before aio_complete does its wakeup we don't have to do it twice. * aio_complete currently has to take the kioctx lock, so it makes sense for it to pull the kiocb off the reqs_active list too. * A later patch is going to change reqs_active to include unreaped completions - this will mean allocating a kiocb doesn't have to look at the ringbuffer. So taking the decrement of reqs_active out of kiocb_free() is useful prep work for that patch. This doesn't really affect cancellation, since existing (usb) code that implements a cancel function still calls aio_complete() - we just have to make sure that aio_complete does the necessary teardown for cancelled kiocbs. It does affect code paths where we free kiocbs that were never submitted; they need to decrement reqs_active and pull the kiocb off the reqs_active list. This occurs in two places: kiocb_batch_free(), which is going away in a later patch, and the error path in io_submit_one. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Acked-by: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 7b1eb234e0ab..1e728f0086f8 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -49,7 +49,7 @@ struct kioctx; */ struct kiocb { unsigned long ki_flags; - int ki_users; + atomic_t ki_users; unsigned ki_key; /* id of this request */ struct file *ki_filp; @@ -96,7 +96,7 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { - .ki_users = 1, + .ki_users = ATOMIC_INIT(1), .ki_key = KIOCB_SYNC_KEY, .ki_filp = filp, .ki_obj.tsk = current, -- cgit v1.2.3 From 774a08b3548f3f4f36c1a4f2a29a1b3710a2c939 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:18:43 -0700 Subject: wait: add wait_event_hrtimeout() Analagous to wait_event_timeout() and friends, this adds wait_event_hrtimeout() and wait_event_interruptible_hrtimeout(). Note that unlike the versions that use regular timers, these don't return the amount of time remaining when they return - instead, they return 0 or -ETIME if they timed out. because I was uncomfortable with the semantics of doing it the other way (that I could get it right, anyways). If the timer expires, there's no real guarantee that expire_time - current_time would be <= 0 - due to timer slack certainly, and I'm not sure I want to know the implications of the different clock bases in hrtimers. If the timer does expire and the code calculates that the time remaining is nonnegative, that could be even worse if the calling code then reuses that timeout. Probably safer to just return 0 then, but I could imagine weird bugs or at least unintended behaviour arising from that too. I came to the conclusion that if other users end up actually needing the amount of time remaining, the sanest thing to do would be to create a version that uses absolute timeouts instead of relative. [akpm@linux-foundation.org: fix description of `timeout' arg] Signed-off-by: Kent Overstreet Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/wait.h | 86 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 7cb64d4b499d..ac38be2692d8 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -330,6 +330,92 @@ do { \ __ret; \ }) +#define __wait_event_hrtimeout(wq, condition, timeout, state) \ +({ \ + int __ret = 0; \ + DEFINE_WAIT(__wait); \ + struct hrtimer_sleeper __t; \ + \ + hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, \ + HRTIMER_MODE_REL); \ + hrtimer_init_sleeper(&__t, current); \ + if ((timeout).tv64 != KTIME_MAX) \ + hrtimer_start_range_ns(&__t.timer, timeout, \ + current->timer_slack_ns, \ + HRTIMER_MODE_REL); \ + \ + for (;;) { \ + prepare_to_wait(&wq, &__wait, state); \ + if (condition) \ + break; \ + if (state == TASK_INTERRUPTIBLE && \ + signal_pending(current)) { \ + __ret = -ERESTARTSYS; \ + break; \ + } \ + if (!__t.task) { \ + __ret = -ETIME; \ + break; \ + } \ + schedule(); \ + } \ + \ + hrtimer_cancel(&__t.timer); \ + destroy_hrtimer_on_stack(&__t.timer); \ + finish_wait(&wq, &__wait); \ + __ret; \ +}) + +/** + * wait_event_hrtimeout - sleep until a condition gets true or a timeout elapses + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, as a ktime_t + * + * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the + * @condition evaluates to true or a signal is received. + * The @condition is checked each time the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function returns 0 if @condition became true, or -ETIME if the timeout + * elapsed. + */ +#define wait_event_hrtimeout(wq, condition, timeout) \ +({ \ + int __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq, condition, timeout, \ + TASK_UNINTERRUPTIBLE); \ + __ret; \ +}) + +/** + * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, as a ktime_t + * + * The process is put to sleep (TASK_INTERRUPTIBLE) until the + * @condition evaluates to true or a signal is received. + * The @condition is checked each time the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * The function returns 0 if @condition became true, -ERESTARTSYS if it was + * interrupted by a signal, or -ETIME if the timeout elapsed. + */ +#define wait_event_interruptible_hrtimeout(wq, condition, timeout) \ +({ \ + long __ret = 0; \ + if (!(condition)) \ + __ret = __wait_event_hrtimeout(wq, condition, timeout, \ + TASK_INTERRUPTIBLE); \ + __ret; \ +}) + #define __wait_event_interruptible_exclusive(wq, condition, ret) \ do { \ DEFINE_WAIT(__wait); \ -- cgit v1.2.3 From 0460fef2a9215680f7f85415b57731b7e0fdf673 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:18:49 -0700 Subject: aio: use cancellation list lazily Cancelling kiocbs requires adding them to a per kioctx linked list, which is one of the few things we need to take the kioctx lock for in the fast path. But most kiocbs can't be cancelled - so if we just do this lazily, we can avoid quite a bit of locking overhead. While we're at it, instead of using a flag bit switch to using ki_cancel itself to indicate that a kiocb has been cancelled/completed. This lets us get rid of ki_flags entirely. [akpm@linux-foundation.org: remove buggy BUG()] Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 1e728f0086f8..d2a00038ec77 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -10,17 +10,24 @@ #include struct kioctx; +struct kiocb; #define KIOCB_SYNC_KEY (~0U) -/* ki_flags bits */ -#define KIF_CANCELLED 2 - -#define kiocbSetCancelled(iocb) set_bit(KIF_CANCELLED, &(iocb)->ki_flags) - -#define kiocbClearCancelled(iocb) clear_bit(KIF_CANCELLED, &(iocb)->ki_flags) +/* + * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either + * cancelled or completed (this makes a certain amount of sense because + * successful cancellation - io_cancel() - does deliver the completion to + * userspace). + * + * And since most things don't implement kiocb cancellation and we'd really like + * kiocb completion to be lockless when possible, we use ki_cancel to + * synchronize cancellation and completion - we only set it to KIOCB_CANCELLED + * with xchg() or cmpxchg(), see batch_complete_aio() and kiocb_cancel(). + */ +#define KIOCB_CANCELLED ((void *) (~0ULL)) -#define kiocbIsCancelled(iocb) test_bit(KIF_CANCELLED, &(iocb)->ki_flags) +typedef int (kiocb_cancel_fn)(struct kiocb *, struct io_event *); /* is there a better place to document function pointer methods? */ /** @@ -48,13 +55,12 @@ struct kioctx; * calls may result in undefined behaviour. */ struct kiocb { - unsigned long ki_flags; atomic_t ki_users; unsigned ki_key; /* id of this request */ struct file *ki_filp; struct kioctx *ki_ctx; /* may be NULL for sync ops */ - int (*ki_cancel)(struct kiocb *, struct io_event *); + kiocb_cancel_fn *ki_cancel; ssize_t (*ki_retry)(struct kiocb *); void (*ki_dtor)(struct kiocb *); @@ -112,6 +118,7 @@ struct mm_struct; extern void exit_aio(struct mm_struct *mm); extern long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user *__user *iocbpp, bool compat); +void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel); #else static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; } static inline void aio_put_req(struct kiocb *iocb) { } @@ -121,6 +128,8 @@ static inline void exit_aio(struct mm_struct *mm) { } static inline long do_io_submit(aio_context_t ctx_id, long nr, struct iocb __user * __user *iocbpp, bool compat) { return 0; } +static inline void kiocb_set_cancel_fn(struct kiocb *req, + kiocb_cancel_fn *cancel) { } #endif /* CONFIG_AIO */ static inline struct kiocb *list_kiocb(struct list_head *h) -- cgit v1.2.3 From a1c8eae75ea3b0168fca93788db1b5aef2424921 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:18:53 -0700 Subject: aio: kill batch allocation Previously, allocating a kiocb required touching quite a few global (well, per kioctx) cachelines... so batching up allocation to amortize those was worthwhile. But we've gotten rid of some of those, and in another couple of patches kiocb allocation won't require writing to any shared cachelines, so that means we can just rip this code out. Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index d2a00038ec77..f0a8481af99b 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -85,7 +85,6 @@ struct kiocb { struct list_head ki_list; /* the aio core uses this * for cancellation */ - struct list_head ki_batch; /* batch allocation */ /* * If the aio_resfd field of the userspace iocb is not zero, -- cgit v1.2.3 From 780a7654cee8d61819512385e778e4827db4bfbc Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 9 Apr 2013 02:22:10 -0700 Subject: audit: Make testing for a valid loginuid explicit. audit rule additions containing "-F auid!=4294967295" were failing with EINVAL because of a regression caused by e1760bd. Apparently some userland audit rule sets want to know if loginuid uid has been set and are using a test for auid != 4294967295 to determine that. In practice that is a horrible way to ask if a value has been set, because it relies on subtle implementation details and will break every time the uid implementation in the kernel changes. So add a clean way to test if the audit loginuid has been set, and silently convert the old idiom to the cleaner and more comprehensible new idiom. Cc: # 3.7 Reported-By: Richard Guy Briggs Signed-off-by: "Eric W. Biederman" Tested-by: Richard Guy Briggs Signed-off-by: Eric Paris --- include/linux/audit.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 469d11755e46..b20b03852f21 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -391,6 +391,11 @@ static inline void audit_ptrace(struct task_struct *t) #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ +static inline bool audit_loginuid_set(struct task_struct *tsk) +{ + return uid_valid(audit_get_loginuid(tsk)); +} + #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ -- cgit v1.2.3 From 8a6608907cf165b3ae658c9de2efe6af4be68bff Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:19:10 -0700 Subject: aio: kill ki_key ki_key wasn't actually used for anything previously - it was always 0. Drop it to trim struct kiocb a bit. Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index f0a8481af99b..7308836dd045 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -12,7 +12,7 @@ struct kioctx; struct kiocb; -#define KIOCB_SYNC_KEY (~0U) +#define KIOCB_KEY 0 /* * We use ki_cancel == KIOCB_CANCELLED to indicate that a kiocb has been either @@ -56,10 +56,9 @@ typedef int (kiocb_cancel_fn)(struct kiocb *, struct io_event *); */ struct kiocb { atomic_t ki_users; - unsigned ki_key; /* id of this request */ struct file *ki_filp; - struct kioctx *ki_ctx; /* may be NULL for sync ops */ + struct kioctx *ki_ctx; /* NULL for sync ops */ kiocb_cancel_fn *ki_cancel; ssize_t (*ki_retry)(struct kiocb *); void (*ki_dtor)(struct kiocb *); @@ -95,14 +94,14 @@ struct kiocb { static inline bool is_sync_kiocb(struct kiocb *kiocb) { - return kiocb->ki_key == KIOCB_SYNC_KEY; + return kiocb->ki_ctx == NULL; } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_users = ATOMIC_INIT(1), - .ki_key = KIOCB_SYNC_KEY, + .ki_ctx = NULL, .ki_filp = filp, .ki_obj.tsk = current, }; -- cgit v1.2.3 From 41ef4eb8eef8d06bc1399e7b00c940d771554711 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:19:11 -0700 Subject: aio: kill ki_retry Thanks to Zach Brown's work to rip out the retry infrastructure, we don't need this anymore - ki_retry was only called right after the kiocb was initialized. This also refactors and trims some duplicated code, as well as cleaning up the refcounting/error handling a bit. [akpm@linux-foundation.org: use fmode_t in aio_run_iocb()] [akpm@linux-foundation.org: fix file_start_write/file_end_write tests] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/aio.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aio.h b/include/linux/aio.h index 7308836dd045..1bdf965339f9 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -29,38 +29,12 @@ struct kiocb; typedef int (kiocb_cancel_fn)(struct kiocb *, struct io_event *); -/* is there a better place to document function pointer methods? */ -/** - * ki_retry - iocb forward progress callback - * @kiocb: The kiocb struct to advance by performing an operation. - * - * This callback is called when the AIO core wants a given AIO operation - * to make forward progress. The kiocb argument describes the operation - * that is to be performed. As the operation proceeds, perhaps partially, - * ki_retry is expected to update the kiocb with progress made. Typically - * ki_retry is set in the AIO core and it itself calls file_operations - * helpers. - * - * ki_retry's return value determines when the AIO operation is completed - * and an event is generated in the AIO event ring. Except the special - * return values described below, the value that is returned from ki_retry - * is transferred directly into the completion ring as the operation's - * resulting status. Once this has happened ki_retry *MUST NOT* reference - * the kiocb pointer again. - * - * If ki_retry returns -EIOCBQUEUED it has made a promise that aio_complete() - * will be called on the kiocb pointer in the future. The AIO core will - * not ask the method again -- ki_retry must ensure forward progress. - * aio_complete() must be called once and only once in the future, multiple - * calls may result in undefined behaviour. - */ struct kiocb { atomic_t ki_users; struct file *ki_filp; struct kioctx *ki_ctx; /* NULL for sync ops */ kiocb_cancel_fn *ki_cancel; - ssize_t (*ki_retry)(struct kiocb *); void (*ki_dtor)(struct kiocb *); union { -- cgit v1.2.3 From a27bb332c04cec8c4afd7912df0dc7890db27560 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 7 May 2013 16:19:08 -0700 Subject: aio: don't include aio.h in sched.h Faster kernel compiles by way of fewer unnecessary includes. [akpm@linux-foundation.org: fix fallout] [akpm@linux-foundation.org: fix build] Signed-off-by: Kent Overstreet Cc: Zach Brown Cc: Felipe Balbi Cc: Greg Kroah-Hartman Cc: Mark Fasheh Cc: Joel Becker Cc: Rusty Russell Cc: Jens Axboe Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Jeff Moyer Cc: Al Viro Cc: Benjamin LaHaise Reviewed-by: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 1 + include/linux/pid_namespace.h | 1 + include/linux/sched.h | 2 -- include/linux/writeback.h | 1 + 4 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3bff9ce09cf7..5047355b9a0f 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -28,6 +28,7 @@ struct cgroup_subsys; struct inode; struct cgroup; struct css_id; +struct eventfd_ctx; extern int cgroup_init_early(void); extern int cgroup_init(void); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 731e4ecee3bd..e2772666f004 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/sched.h b/include/linux/sched.h index 4800e9d1864c..022c085ac3c5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -313,8 +313,6 @@ extern void schedule_preempt_disabled(void); struct nsproxy; struct user_namespace; -#include - #ifdef CONFIG_MMU extern void arch_pick_mmap_layout(struct mm_struct *mm); extern unsigned long diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 9a9367c0c076..579a5007c696 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -5,6 +5,7 @@ #define WRITEBACK_H #include +#include #include DECLARE_PER_CPU(int, dirty_throttle_leaks); -- cgit v1.2.3 From ab3ea5bf37e7189e843e19e500e7af50e802b5f6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 6 May 2013 08:22:18 -0400 Subject: NVMe: Simplify Firmware Activate code slightly Add definitions for the three Firmware Activate actions, and change the SCSI translation code to construct the command into a temporary variable instead of translating the endianness back-and-forth. Signed-off-by: Matthew Wilcox Reviewed-by: Vishal Verma --- include/linux/nvme.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 971ef086ed63..f451c8d6e231 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -316,6 +316,9 @@ enum { NVME_FEAT_WRITE_ATOMIC = 0x0a, NVME_FEAT_ASYNC_EVENT = 0x0b, NVME_FEAT_SW_PROGRESS = 0x0c, + NVME_FWACT_REPL = (0 << 3), + NVME_FWACT_REPL_ACTV = (1 << 3), + NVME_FWACT_ACTV = (2 << 3), }; struct nvme_identify { -- cgit v1.2.3 From 6eecdc5f95a393cb558503123eae9a9a6642e835 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 6 May 2013 11:29:23 +0000 Subject: usbnet: allow status interrupt URB to always be active Some drivers (sierra_net) need the status interrupt URB active even when the device is closed, because they receive custom indications from firmware. Add functions to refcount the status interrupt URB submit/kill operation so that sub-drivers and the generic driver don't fight over whether the status interrupt URB is active or not. A sub-driver can call usbnet_status_start() at any time, but the URB is only submitted the first time the function is called. Likewise, when the sub-driver is done with the URB, it calls usbnet_status_stop() but the URB is only killed when all users have stopped it. The URB is still killed and re-submitted for suspend/resume, as before, with the same refcount it had at suspend. Signed-off-by: Dan Williams Acked-by: Oliver Neukum Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index da46327fca17..f18d64129f99 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -56,6 +56,8 @@ struct usbnet { struct sk_buff_head done; struct sk_buff_head rxq_pause; struct urb *interrupt; + unsigned interrupt_count; + struct mutex interrupt_mutex; struct usb_anchor deferred; struct tasklet_struct bh; @@ -248,4 +250,7 @@ extern int usbnet_nway_reset(struct net_device *net); extern int usbnet_manage_power(struct usbnet *, int); extern void usbnet_link_change(struct usbnet *, bool, bool); +extern int usbnet_status_start(struct usbnet *dev, gfp_t mem_flags); +extern void usbnet_status_stop(struct usbnet *dev); + #endif /* __LINUX_USB_USBNET_H */ -- cgit v1.2.3 From 91c2e0bcae72a3086c698b5de2b950b885abb0e6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 5 Mar 2013 20:10:59 -0500 Subject: unify compat fanotify_mark(2), switch to COMPAT_SYSCALL_DEFINE Signed-off-by: Al Viro --- include/linux/compat.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index d53c35352ea9..7f0c1dd09079 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -673,6 +673,8 @@ int __compat_save_altstack(compat_stack_t __user *, unsigned long); asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, struct compat_timespec __user *interval); +asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32, + int, const char __user *); #else #define is_compat_task() (0) -- cgit v1.2.3 From 60371952e1dd0d507039b2654c22083b32c38398 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Wed, 8 May 2013 21:05:54 +0800 Subject: ARM: imx: Select GENERIC_ALLOCATOR Since commit 657eee7 (media: coda: use genalloc API) the following build error happens with imx_v4_v5_defconfig: drivers/built-in.o: In function 'coda_remove': clk-composite.c:(.text+0x112180): undefined reference to 'gen_pool_free' drivers/built-in.o: In function 'coda_probe': clk-composite.c:(.text+0x112310): undefined reference to 'of_get_named_gen_pool' clk-composite.c:(.text+0x1123f4): undefined reference to 'gen_pool_alloc' clk-composite.c:(.text+0x11240c): undefined reference to 'gen_pool_virt_to_phys' clk-composite.c:(.text+0x112458): undefined reference to 'dev_get_gen_pool' Select GENERIC_ALLOCATOR and get rid of the custom IRAM_ALLOC. Signed-off-by: Fabio Estevam Signed-off-by: Shawn Guo Signed-off-by: Olof Johansson --- include/linux/platform_data/imx-iram.h | 41 ---------------------------------- 1 file changed, 41 deletions(-) delete mode 100644 include/linux/platform_data/imx-iram.h (limited to 'include/linux') diff --git a/include/linux/platform_data/imx-iram.h b/include/linux/platform_data/imx-iram.h deleted file mode 100644 index 022690c33702..000000000000 --- a/include/linux/platform_data/imx-iram.h +++ /dev/null @@ -1,41 +0,0 @@ -/* - * Copyright (C) 2010 Freescale Semiconductor, Inc. All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, - * MA 02110-1301, USA. - */ -#include - -#ifdef CONFIG_IRAM_ALLOC - -int __init iram_init(unsigned long base, unsigned long size); -void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr); -void iram_free(unsigned long dma_addr, unsigned int size); - -#else - -static inline int __init iram_init(unsigned long base, unsigned long size) -{ - return -ENOMEM; -} - -static inline void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr) -{ - return NULL; -} - -static inline void iram_free(unsigned long base, unsigned long size) {} - -#endif -- cgit v1.2.3 From f04f24fb7e48d446bd89a01c6056571f25972511 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 9 May 2013 14:44:17 +0900 Subject: ftrace, kprobes: Fix a deadlock on ftrace_regex_lock Fix a deadlock on ftrace_regex_lock which happens when setting an enable_event trigger on dynamic kprobe event as below. ---- sh-2.05b# echo p vfs_symlink > kprobe_events sh-2.05b# echo vfs_symlink:enable_event:kprobes:p_vfs_symlink_0 > set_ftrace_filter ============================================= [ INFO: possible recursive locking detected ] 3.9.0+ #35 Not tainted --------------------------------------------- sh/72 is trying to acquire lock: (ftrace_regex_lock){+.+.+.}, at: [] ftrace_set_hash+0x81/0x1f0 but task is already holding lock: (ftrace_regex_lock){+.+.+.}, at: [] ftrace_regex_write.isra.29.part.30+0x3d/0x220 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(ftrace_regex_lock); lock(ftrace_regex_lock); *** DEADLOCK *** ---- To fix that, this introduces a finer regex_lock for each ftrace_ops. ftrace_regex_lock is too big of a lock which protects all filter/notrace_hash operations, but it doesn't need to be a global lock after supporting multiple ftrace_ops because each ftrace_ops has its own filter/notrace_hash. Link: http://lkml.kernel.org/r/20130509054417.30398.84254.stgit@mhiramat-M0-7522 Cc: Srikar Dronamraju Cc: Oleg Nesterov Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Tom Zanussi Signed-off-by: Masami Hiramatsu [ Added initialization flag and automate mutex initialization for non ftrace.c ftrace_probes. ] Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index f83e17a40e8b..99d0fbcbaf79 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -90,6 +90,8 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, * not set this, then the ftrace infrastructure will add recursion * protection for the caller. * STUB - The ftrace_ops is just a place holder. + * INITIALIZED - The ftrace_ops has already been initialized (first use time + * register_ftrace_function() is called, it will initialized the ops) */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, @@ -100,6 +102,7 @@ enum { FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 5, FTRACE_OPS_FL_RECURSION_SAFE = 1 << 6, FTRACE_OPS_FL_STUB = 1 << 7, + FTRACE_OPS_FL_INITIALIZED = 1 << 8, }; struct ftrace_ops { @@ -110,6 +113,7 @@ struct ftrace_ops { #ifdef CONFIG_DYNAMIC_FTRACE struct ftrace_hash *notrace_hash; struct ftrace_hash *filter_hash; + struct mutex regex_lock; #endif }; -- cgit v1.2.3 From 1cf4c0732db3cd3c49cadbc60ff6bda08604e6fa Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 9 May 2013 14:44:29 +0900 Subject: tracing: Modify soft-mode only if there's no other referrer Modify soft-mode flag only if no other soft-mode referrer (currently only the ftrace triggers) by using a reference counter in each ftrace_event_file. Without this fix, adding and removing several different enable/disable_event triggers on the same event clear soft-mode bit from the ftrace_event_file. This also happens with a typo of glob on setting triggers. e.g. # echo vfs_symlink:enable_event:net:netif_rx > set_ftrace_filter # cat events/net/netif_rx/enable 0* # echo typo_func:enable_event:net:netif_rx > set_ftrace_filter # cat events/net/netif_rx/enable 0 # cat set_ftrace_filter #### all functions enabled #### vfs_symlink:enable_event:net:netif_rx:unlimited As above, we still have a trigger, but soft-mode is gone. Link: http://lkml.kernel.org/r/20130509054429.30398.7464.stgit@mhiramat-M0-7522 Cc: Srikar Dronamraju Cc: Oleg Nesterov Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: David Sharp Cc: Hiraku Toyooka Cc: Tom Zanussi Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 34e00fb49bec..4372658c73ae 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -293,6 +293,7 @@ struct ftrace_event_file { * caching and such. Which is mostly OK ;-) */ unsigned long flags; + atomic_t sm_ref; /* soft-mode reference counter */ }; #define __TRACE_EVENT_FLAGS(name, value) \ -- cgit v1.2.3 From 058ce5ca8155a4c8eeac9b9e8a70e6664996337b Mon Sep 17 00:00:00 2001 From: Alasdair G Kergon Date: Fri, 10 May 2013 14:37:17 +0100 Subject: dm: document iterate_devices Document iterate_devices in device-mapper.h. Signed-off-by: Alasdair G Kergon --- include/linux/device-mapper.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 1e483fa7afb4..3cd32478f2fd 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -79,11 +79,26 @@ typedef int (*dm_ioctl_fn) (struct dm_target *ti, unsigned int cmd, typedef int (*dm_merge_fn) (struct dm_target *ti, struct bvec_merge_data *bvm, struct bio_vec *biovec, int max_size); +/* + * These iteration functions are typically used to check (and combine) + * properties of underlying devices. + * E.g. Does at least one underlying device support flush? + * Does any underlying device not support WRITE_SAME? + * + * The callout function is called once for each contiguous section of + * an underlying device. State can be maintained in *data. + * Return non-zero to stop iterating through any further devices. + */ typedef int (*iterate_devices_callout_fn) (struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data); +/* + * This function must iterate through each section of device used by the + * target until it encounters a non-zero return code, which it then returns. + * Returns zero if no callout returned non-zero. + */ typedef int (*dm_iterate_devices_fn) (struct dm_target *ti, iterate_devices_callout_fn fn, void *data); -- cgit v1.2.3