From febdbfe8a91ce0d11939d4940b592eb0dba8d663 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 6 Feb 2014 18:16:07 +0100 Subject: arch: Prepare for smp_mb__{before,after}_atomic() Since the smp_mb__{before,after}*() ops are fundamentally dependent on how an arch can implement atomics it doesn't make sense to have 3 variants of them. They must all be the same. Furthermore, the 3 variants suggest they're only valid for those 3 atomic ops, while we have many more where they could be applied. So move away from smp_mb__{before,after}_{atomic,clear}_{dec,inc,bit}() and reduce the interface to just the two: smp_mb__{before,after}_atomic(). This patch prepares the way by introducing default implementations in asm-generic/barrier.h that default to a full barrier and providing __deprecated inlines for the previous 6 barriers if they're not provided by the arch. This should allow for a mostly painless transition (lots of deprecated warns in the interim). Signed-off-by: Peter Zijlstra Acked-by: Paul E. McKenney Link: http://lkml.kernel.org/n/tip-wr59327qdyi9mbzn6x937s4e@git.kernel.org Cc: Arnd Bergmann Cc: "Chen, Gong" Cc: John Sullivan Cc: Linus Torvalds Cc: Mauro Carvalho Chehab Cc: Srinivas Pandruvada Cc: "Theodore Ts'o" Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/asm-generic/atomic.h | 7 +------ include/asm-generic/barrier.h | 8 ++++++++ include/asm-generic/bitops.h | 9 +-------- 3 files changed, 10 insertions(+), 14 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h index 33bd2de3bc1e..9c79e7603459 100644 --- a/include/asm-generic/atomic.h +++ b/include/asm-generic/atomic.h @@ -16,6 +16,7 @@ #define __ASM_GENERIC_ATOMIC_H #include +#include #ifdef CONFIG_SMP /* Force people to define core atomics */ @@ -182,11 +183,5 @@ static inline void atomic_set_mask(unsigned int mask, atomic_t *v) } #endif -/* Assume that atomic operations are already serializing */ -#define smp_mb__before_atomic_dec() barrier() -#define smp_mb__after_atomic_dec() barrier() -#define smp_mb__before_atomic_inc() barrier() -#define smp_mb__after_atomic_inc() barrier() - #endif /* __KERNEL__ */ #endif /* __ASM_GENERIC_ATOMIC_H */ diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index 6f692f8ac664..1402fa855388 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -62,6 +62,14 @@ #define set_mb(var, value) do { (var) = (value); mb(); } while (0) #endif +#ifndef smp_mb__before_atomic +#define smp_mb__before_atomic() smp_mb() +#endif + +#ifndef smp_mb__after_atomic +#define smp_mb__after_atomic() smp_mb() +#endif + #define smp_store_release(p, v) \ do { \ compiletime_assert_atomic_type(*p); \ diff --git a/include/asm-generic/bitops.h b/include/asm-generic/bitops.h index 280ca7a96f75..dcdcacf2fd2b 100644 --- a/include/asm-generic/bitops.h +++ b/include/asm-generic/bitops.h @@ -11,14 +11,7 @@ #include #include - -/* - * clear_bit may not imply a memory barrier - */ -#ifndef smp_mb__before_clear_bit -#define smp_mb__before_clear_bit() smp_mb() -#define smp_mb__after_clear_bit() smp_mb() -#endif +#include #include #include -- cgit v1.2.3 From 4e857c58efeb99393cba5a5d0d8ec7117183137c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 17 Mar 2014 18:06:10 +0100 Subject: arch: Mass conversion of smp_mb__*() Mostly scripted conversion of the smp_mb__* barriers. Signed-off-by: Peter Zijlstra Acked-by: Paul E. McKenney Link: http://lkml.kernel.org/n/tip-55dhyhocezdw1dg7u19hmh1u@git.kernel.org Cc: Linus Torvalds Cc: linux-arch@vger.kernel.org Signed-off-by: Ingo Molnar --- include/asm-generic/bitops/atomic.h | 2 +- include/asm-generic/bitops/lock.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h index 9ae6c34dc191..49673510b484 100644 --- a/include/asm-generic/bitops/atomic.h +++ b/include/asm-generic/bitops/atomic.h @@ -80,7 +80,7 @@ static inline void set_bit(int nr, volatile unsigned long *addr) * * clear_bit() is atomic and may not be reordered. However, it does * not contain a memory barrier, so if it is used for locking purposes, - * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit() + * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic() * in order to ensure changes are visible on other processors. */ static inline void clear_bit(int nr, volatile unsigned long *addr) diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h index 308a9e22c802..c30266e94806 100644 --- a/include/asm-generic/bitops/lock.h +++ b/include/asm-generic/bitops/lock.h @@ -20,7 +20,7 @@ */ #define clear_bit_unlock(nr, addr) \ do { \ - smp_mb__before_clear_bit(); \ + smp_mb__before_atomic(); \ clear_bit(nr, addr); \ } while (0) -- cgit v1.2.3 From 376e242429bf8539ef39a080ac113c8799840b13 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 17 Apr 2014 17:17:05 +0900 Subject: kprobes: Introduce NOKPROBE_SYMBOL() macro to maintain kprobes blacklist MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce NOKPROBE_SYMBOL() macro which builds a kprobes blacklist at kernel build time. The usage of this macro is similar to EXPORT_SYMBOL(), placed after the function definition: NOKPROBE_SYMBOL(function); Since this macro will inhibit inlining of static/inline functions, this patch also introduces a nokprobe_inline macro for static/inline functions. In this case, we must use NOKPROBE_SYMBOL() for the inline function caller. When CONFIG_KPROBES=y, the macro stores the given function address in the "_kprobe_blacklist" section. Since the data structures are not fully initialized by the macro (because there is no "size" information), those are re-initialized at boot time by using kallsyms. Signed-off-by: Masami Hiramatsu Link: http://lkml.kernel.org/r/20140417081705.26341.96719.stgit@ltc230.yrl.intra.hitachi.co.jp Cc: Alok Kataria Cc: Ananth N Mavinakayanahalli Cc: Andrew Morton Cc: Anil S Keshavamurthy Cc: Arnd Bergmann Cc: Christopher Li Cc: Chris Wright Cc: David S. Miller Cc: Jan-Simon Möller Cc: Jeremy Fitzhardinge Cc: Linus Torvalds Cc: Randy Dunlap Cc: Rusty Russell Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-sparse@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Signed-off-by: Ingo Molnar --- include/asm-generic/vmlinux.lds.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/asm-generic') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 146e4fffd710..40ceb3ceba79 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -109,6 +109,14 @@ #define BRANCH_PROFILE() #endif +#ifdef CONFIG_KPROBES +#define KPROBE_BLACKLIST() VMLINUX_SYMBOL(__start_kprobe_blacklist) = .; \ + *(_kprobe_blacklist) \ + VMLINUX_SYMBOL(__stop_kprobe_blacklist) = .; +#else +#define KPROBE_BLACKLIST() +#endif + #ifdef CONFIG_EVENT_TRACING #define FTRACE_EVENTS() . = ALIGN(8); \ VMLINUX_SYMBOL(__start_ftrace_events) = .; \ @@ -507,6 +515,7 @@ *(.init.rodata) \ FTRACE_EVENTS() \ TRACE_SYSCALLS() \ + KPROBE_BLACKLIST() \ MEM_DISCARD(init.rodata) \ CLK_OF_TABLES() \ RESERVEDMEM_OF_TABLES() \ -- cgit v1.2.3 From 69902c718c0b476e94ed7fccd3cf29ca39fe433a Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 1 May 2014 10:56:44 +0530 Subject: kprobes: Ensure blacklist data is aligned ARC Linux (not supporting native unaligned access) was failing to boot because __start_kprobe_blacklist was not aligned. This was because per generated vmlinux.lds it was emitted right next to .rodata with strings etc hence could be randomly unaligned. Fix that by ensuring a word alignment. While 4 would suffice for 32bit arches and problem at hand, it is probably better to put 8. | Path: (null) CPU: 0 PID: 1 Comm: swapper Not tainted | 3.15.0-rc3-next-20140430 #2 | task: 8f044000 ti: 8f01e000 task.ti: 8f01e000 | | [ECR ]: 0x00230400 => Misaligned r/w from 0x800fb0d3 | [EFA ]: 0x800fb0d3 | [BLINK ]: do_one_initcall+0x86/0x1bc | [ERET ]: init_kprobes+0x52/0x120 Signed-off-by: Vineet Gupta Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: anton Kolesov Link: http://lkml.kernel.org/r/5361DB14.7010406@synopsys.com Signed-off-by: Ingo Molnar --- include/asm-generic/vmlinux.lds.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 40ceb3ceba79..8e0204a68c74 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -110,7 +110,8 @@ #endif #ifdef CONFIG_KPROBES -#define KPROBE_BLACKLIST() VMLINUX_SYMBOL(__start_kprobe_blacklist) = .; \ +#define KPROBE_BLACKLIST() . = ALIGN(8); \ + VMLINUX_SYMBOL(__start_kprobe_blacklist) = .; \ *(_kprobe_blacklist) \ VMLINUX_SYMBOL(__stop_kprobe_blacklist) = .; #else -- cgit v1.2.3 From 0567f5facbdf04806a37ef521dd0893159fde715 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 1 May 2014 17:49:33 +0200 Subject: asm-generic: allow generic unaligned access if the arch supports it Switch the default unaligned access method to 'hardware implemented' if HAVE_EFFICIENT_UNALIGNED_ACCESS is set. Signed-off-by: Ard Biesheuvel Acked-by: Arnd Bergmann --- include/asm-generic/unaligned.h | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index 03cf5936bad6..1ac097279db1 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -4,22 +4,27 @@ /* * This is the most generic implementation of unaligned accesses * and should work almost anywhere. - * - * If an architecture can handle unaligned accesses in hardware, - * it may want to use the linux/unaligned/access_ok.h implementation - * instead. */ #include +/* Set by the arch if it can handle unaligned accesses in hardware. */ +#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS +# include +#endif + #if defined(__LITTLE_ENDIAN) -# include -# include +# ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS +# include +# include +# endif # include # define get_unaligned __get_unaligned_le # define put_unaligned __put_unaligned_le #elif defined(__BIG_ENDIAN) -# include -# include +# ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS +# include +# include +# endif # include # define get_unaligned __get_unaligned_be # define put_unaligned __put_unaligned_be -- cgit v1.2.3 From 735e0da7fc55a0456476f6b40f85024f68f87092 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 24 Mar 2014 16:06:42 -0500 Subject: irqchip: align irqchip OF match table section naming Make the irqchip OF match table section naming aligned with other OF match table sections in preparation to have a common definition. Acked-by: Arnd Bergmann Signed-off-by: Rob Herring --- include/asm-generic/vmlinux.lds.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 146e4fffd710..b1c6f9d0c4ff 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -151,9 +151,9 @@ #ifdef CONFIG_IRQCHIP #define IRQCHIP_OF_MATCH_TABLE() \ . = ALIGN(8); \ - VMLINUX_SYMBOL(__irqchip_begin) = .; \ + VMLINUX_SYMBOL(__irqchip_of_table) = .; \ *(__irqchip_of_table) \ - *(__irqchip_of_end) + *(__irqchip_of_table_end) #else #define IRQCHIP_OF_MATCH_TABLE() #endif -- cgit v1.2.3 From 9a721c41113a50ccbe184d67a5e551feb99e36a9 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 24 Mar 2014 16:11:54 -0500 Subject: ARM: align cpu_method_of_table naming The cpu_method_of_table is the oddball of the various OF linker sections. In preparation to have common linker section definitions, align the cpu_method_of_table with the other definitions for the naming and ending with a blank struct. Acked-by: Arnd Bergmann Signed-off-by: Rob Herring Cc: Russell King --- include/asm-generic/vmlinux.lds.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index b1c6f9d0c4ff..fe57c5f1bd1a 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -179,9 +179,9 @@ #ifdef CONFIG_SMP #define CPU_METHOD_OF_TABLES() . = ALIGN(8); \ - VMLINUX_SYMBOL(__cpu_method_of_table_begin) = .; \ + VMLINUX_SYMBOL(__cpu_method_of_table) = .; \ *(__cpu_method_of_table) \ - VMLINUX_SYMBOL(__cpu_method_of_table_end) = .; + *(__cpu_method_of_table_end) #else #define CPU_METHOD_OF_TABLES() #endif -- cgit v1.2.3 From 063092883039e49e5edc1f63133dc5ad437361a2 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 24 Mar 2014 16:59:20 -0500 Subject: vmlinuz.lds: define OF table sections with macros OF table sections all have the same pattern, so create a macro to define them and insure consistency. Acked-by: Arnd Bergmann Signed-off-by: Rob Herring --- include/asm-generic/vmlinux.lds.h | 58 ++++++++++----------------------------- 1 file changed, 14 insertions(+), 44 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index fe57c5f1bd1a..b9404f6590f1 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -139,52 +139,22 @@ #define TRACE_SYSCALLS() #endif -#ifdef CONFIG_CLKSRC_OF -#define CLKSRC_OF_TABLES() . = ALIGN(8); \ - VMLINUX_SYMBOL(__clksrc_of_table) = .; \ - *(__clksrc_of_table) \ - *(__clksrc_of_table_end) -#else -#define CLKSRC_OF_TABLES() -#endif -#ifdef CONFIG_IRQCHIP -#define IRQCHIP_OF_MATCH_TABLE() \ +#define ___OF_TABLE(cfg, name) _OF_TABLE_##cfg(name) +#define __OF_TABLE(cfg, name) ___OF_TABLE(cfg, name) +#define OF_TABLE(cfg, name) __OF_TABLE(config_enabled(cfg), name) +#define _OF_TABLE_0(name) +#define _OF_TABLE_1(name) \ . = ALIGN(8); \ - VMLINUX_SYMBOL(__irqchip_of_table) = .; \ - *(__irqchip_of_table) \ - *(__irqchip_of_table_end) -#else -#define IRQCHIP_OF_MATCH_TABLE() -#endif - -#ifdef CONFIG_COMMON_CLK -#define CLK_OF_TABLES() . = ALIGN(8); \ - VMLINUX_SYMBOL(__clk_of_table) = .; \ - *(__clk_of_table) \ - *(__clk_of_table_end) -#else -#define CLK_OF_TABLES() -#endif - -#ifdef CONFIG_OF_RESERVED_MEM -#define RESERVEDMEM_OF_TABLES() \ - . = ALIGN(8); \ - VMLINUX_SYMBOL(__reservedmem_of_table) = .; \ - *(__reservedmem_of_table) \ - *(__reservedmem_of_table_end) -#else -#define RESERVEDMEM_OF_TABLES() -#endif - -#ifdef CONFIG_SMP -#define CPU_METHOD_OF_TABLES() . = ALIGN(8); \ - VMLINUX_SYMBOL(__cpu_method_of_table) = .; \ - *(__cpu_method_of_table) \ - *(__cpu_method_of_table_end) -#else -#define CPU_METHOD_OF_TABLES() -#endif + VMLINUX_SYMBOL(__##name##_of_table) = .; \ + *(__##name##_of_table) \ + *(__##name##_of_table_end) + +#define CLKSRC_OF_TABLES() OF_TABLE(CONFIG_CLKSRC_OF, clksrc) +#define IRQCHIP_OF_MATCH_TABLE() OF_TABLE(CONFIG_IRQCHIP, irqchip) +#define CLK_OF_TABLES() OF_TABLE(CONFIG_COMMON_CLK, clk) +#define RESERVEDMEM_OF_TABLES() OF_TABLE(CONFIG_OF_RESERVED_MEM, reservedmem) +#define CPU_METHOD_OF_TABLES() OF_TABLE(CONFIG_SMP, cpu_method) #define KERNEL_DTB() \ STRUCT_ALIGN(); \ -- cgit v1.2.3 From b0b6abd34c1b508d4ac95dbc614f36c49d29e65a Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 27 Mar 2014 08:06:16 -0500 Subject: serial: earlycon: add DT support This adds the infrastructure to generic earlycon for earlycon setup using DT. The actual setup is not enabled until a following commit to add the FDT parsing. Signed-off-by: Rob Herring Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: Arnd Bergmann Acked-by: Grant Likely --- include/asm-generic/vmlinux.lds.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index b9404f6590f1..d647637cd699 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -155,6 +155,7 @@ #define CLK_OF_TABLES() OF_TABLE(CONFIG_COMMON_CLK, clk) #define RESERVEDMEM_OF_TABLES() OF_TABLE(CONFIG_OF_RESERVED_MEM, reservedmem) #define CPU_METHOD_OF_TABLES() OF_TABLE(CONFIG_SMP, cpu_method) +#define EARLYCON_OF_TABLES() OF_TABLE(CONFIG_SERIAL_EARLYCON, earlycon) #define KERNEL_DTB() \ STRUCT_ALIGN(); \ @@ -483,7 +484,8 @@ CLKSRC_OF_TABLES() \ CPU_METHOD_OF_TABLES() \ KERNEL_DTB() \ - IRQCHIP_OF_MATCH_TABLE() + IRQCHIP_OF_MATCH_TABLE() \ + EARLYCON_OF_TABLES() #define INIT_TEXT \ *(.init.text) \ -- cgit v1.2.3 From 88a984ba0795f14a3847edbd7fabe652289ea89b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 20 May 2014 16:54:22 -0600 Subject: DMA-API: Change dma_declare_coherent_memory() CPU address to phys_addr_t dma_declare_coherent_memory() takes two addresses for a region of memory: a "bus_addr" and a "device_addr". I think the intent is that "bus_addr" is the physical address a *CPU* would use to access the region, and "device_addr" is the bus address the *device* would use to address the region. Rename "bus_addr" to "phys_addr" and change its type to phys_addr_t. Most callers already supply a phys_addr_t for this argument. The others supply a 32-bit integer (a constant, unsigned int, or __u32) and need no change. Use "unsigned long", not phys_addr_t, to hold PFNs. No functional change (this could theoretically fix a truncation in a config with 32-bit dma_addr_t and 64-bit phys_addr_t, but I don't think there are any such cases involving this code). Signed-off-by: Bjorn Helgaas Acked-by: Arnd Bergmann Acked-by: Greg Kroah-Hartman Acked-by: James Bottomley Acked-by: Randy Dunlap --- include/asm-generic/dma-coherent.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/dma-coherent.h b/include/asm-generic/dma-coherent.h index 2be8a2dbc868..0297e5875798 100644 --- a/include/asm-generic/dma-coherent.h +++ b/include/asm-generic/dma-coherent.h @@ -16,16 +16,13 @@ int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma, * Standard interface */ #define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY -extern int -dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, - dma_addr_t device_addr, size_t size, int flags); +int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, + dma_addr_t device_addr, size_t size, int flags); -extern void -dma_release_declared_memory(struct device *dev); +void dma_release_declared_memory(struct device *dev); -extern void * -dma_mark_declared_memory_occupied(struct device *dev, - dma_addr_t device_addr, size_t size); +void *dma_mark_declared_memory_occupied(struct device *dev, + dma_addr_t device_addr, size_t size); #else #define dma_alloc_from_coherent(dev, size, handle, ret) (0) #define dma_release_from_coherent(dev, order, vaddr) (0) -- cgit v1.2.3 From c46a7c817e662a820373bb76b88d0ad67d6abe5d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:06:30 -0700 Subject: x86: define _PAGE_NUMA by reusing software bits on the PMD and PTE levels _PAGE_NUMA is currently an alias of _PROT_PROTNONE to trap NUMA hinting faults on x86. Care is taken such that _PAGE_NUMA is used only in situations where the VMA flags distinguish between NUMA hinting faults and prot_none faults. This decision was x86-specific and conceptually it is difficult requiring special casing to distinguish between PROTNONE and NUMA ptes based on context. Fundamentally, we only need the _PAGE_NUMA bit to tell the difference between an entry that is really unmapped and a page that is protected for NUMA hinting faults as if the PTE is not present then a fault will be trapped. Swap PTEs on x86-64 use the bits after _PAGE_GLOBAL for the offset. This patch shrinks the maximum possible swap size and uses the bit to uniquely distinguish between NUMA hinting ptes and swap ptes. Signed-off-by: Mel Gorman Cc: David Vrabel Cc: Ingo Molnar Cc: Peter Anvin Cc: Fengguang Wu Cc: Linus Torvalds Cc: Steven Noonan Cc: Rik van Riel Cc: Peter Zijlstra Cc: Andrea Arcangeli Cc: Dave Hansen Cc: Srikar Dronamraju Cc: Cyrill Gorcunov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/pgtable.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index a8015a7a55bb..53b2acc38213 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -233,6 +233,10 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) # define pte_accessible(mm, pte) ((void)(pte), 1) #endif +#ifndef pte_present_nonuma +#define pte_present_nonuma(pte) pte_present(pte) +#endif + #ifndef flush_tlb_fix_spurious_fault #define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) #endif @@ -670,7 +674,7 @@ static inline int pmd_trans_unstable(pmd_t *pmd) static inline int pte_numa(pte_t pte) { return (pte_flags(pte) & - (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA; + (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)) == _PAGE_NUMA; } #endif @@ -678,7 +682,7 @@ static inline int pte_numa(pte_t pte) static inline int pmd_numa(pmd_t pmd) { return (pmd_flags(pmd) & - (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA; + (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)) == _PAGE_NUMA; } #endif -- cgit v1.2.3 From 70af2f8a4f48d6cebdf92d533d3aef37853ce6de Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 3 Feb 2014 13:18:49 +0100 Subject: locking/rwlocks: Introduce 'qrwlocks' - fair, queued rwlocks This rwlock uses the arch_spin_lock_t as a waitqueue, and assuming the arch_spin_lock_t is a fair lock (ticket,mcs etc..) the resulting rwlock is a fair lock. It fits in the same 8 bytes as the regular rwlock_t by folding the reader and writer count into a single integer, using the remaining 4 bytes for the arch_spinlock_t. Architectures that can single-copy adress bytes can optimize queue_write_unlock() with a 0 write to the LSB (the write count). Performance as measured by Davidlohr Bueso (rwlock_t -> qrwlock_t): +--------------+-------------+---------------+ | Workload | #users | delta | +--------------+-------------+---------------+ | alltests | > 1400 | -4.83% | | custom | 0-100,> 100 | +1.43%,-1.57% | | high_systime | > 1000 | -2.61 | | shared | all | +0.32 | +--------------+-------------+---------------+ http://www.stgolabs.net/qrwlock-stuff/aim7-results-vs-rwsem_optsin/ Signed-off-by: Waiman Long [peterz: near complete rewrite] Signed-off-by: Peter Zijlstra Cc: Arnd Bergmann Cc: Linus Torvalds Cc: "Paul E.McKenney" Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/n/tip-gac1nnl3wvs2ij87zv2xkdzq@git.kernel.org Signed-off-by: Ingo Molnar --- include/asm-generic/qrwlock.h | 166 ++++++++++++++++++++++++++++++++++++ include/asm-generic/qrwlock_types.h | 21 +++++ 2 files changed, 187 insertions(+) create mode 100644 include/asm-generic/qrwlock.h create mode 100644 include/asm-generic/qrwlock_types.h (limited to 'include/asm-generic') diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h new file mode 100644 index 000000000000..6383d54bf983 --- /dev/null +++ b/include/asm-generic/qrwlock.h @@ -0,0 +1,166 @@ +/* + * Queue read/write lock + * + * 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. + * + * (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P. + * + * Authors: Waiman Long + */ +#ifndef __ASM_GENERIC_QRWLOCK_H +#define __ASM_GENERIC_QRWLOCK_H + +#include +#include +#include + +#include + +/* + * Writer states & reader shift and bias + */ +#define _QW_WAITING 1 /* A writer is waiting */ +#define _QW_LOCKED 0xff /* A writer holds the lock */ +#define _QW_WMASK 0xff /* Writer mask */ +#define _QR_SHIFT 8 /* Reader count shift */ +#define _QR_BIAS (1U << _QR_SHIFT) + +/* + * External function declarations + */ +extern void queue_read_lock_slowpath(struct qrwlock *lock); +extern void queue_write_lock_slowpath(struct qrwlock *lock); + +/** + * queue_read_can_lock- would read_trylock() succeed? + * @lock: Pointer to queue rwlock structure + */ +static inline int queue_read_can_lock(struct qrwlock *lock) +{ + return !(atomic_read(&lock->cnts) & _QW_WMASK); +} + +/** + * queue_write_can_lock- would write_trylock() succeed? + * @lock: Pointer to queue rwlock structure + */ +static inline int queue_write_can_lock(struct qrwlock *lock) +{ + return !atomic_read(&lock->cnts); +} + +/** + * queue_read_trylock - try to acquire read lock of a queue rwlock + * @lock : Pointer to queue rwlock structure + * Return: 1 if lock acquired, 0 if failed + */ +static inline int queue_read_trylock(struct qrwlock *lock) +{ + u32 cnts; + + cnts = atomic_read(&lock->cnts); + if (likely(!(cnts & _QW_WMASK))) { + cnts = (u32)atomic_add_return(_QR_BIAS, &lock->cnts); + if (likely(!(cnts & _QW_WMASK))) + return 1; + atomic_sub(_QR_BIAS, &lock->cnts); + } + return 0; +} + +/** + * queue_write_trylock - try to acquire write lock of a queue rwlock + * @lock : Pointer to queue rwlock structure + * Return: 1 if lock acquired, 0 if failed + */ +static inline int queue_write_trylock(struct qrwlock *lock) +{ + u32 cnts; + + cnts = atomic_read(&lock->cnts); + if (unlikely(cnts)) + return 0; + + return likely(atomic_cmpxchg(&lock->cnts, + cnts, cnts | _QW_LOCKED) == cnts); +} +/** + * queue_read_lock - acquire read lock of a queue rwlock + * @lock: Pointer to queue rwlock structure + */ +static inline void queue_read_lock(struct qrwlock *lock) +{ + u32 cnts; + + cnts = atomic_add_return(_QR_BIAS, &lock->cnts); + if (likely(!(cnts & _QW_WMASK))) + return; + + /* The slowpath will decrement the reader count, if necessary. */ + queue_read_lock_slowpath(lock); +} + +/** + * queue_write_lock - acquire write lock of a queue rwlock + * @lock : Pointer to queue rwlock structure + */ +static inline void queue_write_lock(struct qrwlock *lock) +{ + /* Optimize for the unfair lock case where the fair flag is 0. */ + if (atomic_cmpxchg(&lock->cnts, 0, _QW_LOCKED) == 0) + return; + + queue_write_lock_slowpath(lock); +} + +/** + * queue_read_unlock - release read lock of a queue rwlock + * @lock : Pointer to queue rwlock structure + */ +static inline void queue_read_unlock(struct qrwlock *lock) +{ + /* + * Atomically decrement the reader count + */ + smp_mb__before_atomic(); + atomic_sub(_QR_BIAS, &lock->cnts); +} + +#ifndef queue_write_unlock +/** + * queue_write_unlock - release write lock of a queue rwlock + * @lock : Pointer to queue rwlock structure + */ +static inline void queue_write_unlock(struct qrwlock *lock) +{ + /* + * If the writer field is atomic, it can be cleared directly. + * Otherwise, an atomic subtraction will be used to clear it. + */ + smp_mb__before_atomic(); + atomic_sub(_QW_LOCKED, &lock->cnts); +} +#endif + +/* + * Remapping rwlock architecture specific functions to the corresponding + * queue rwlock functions. + */ +#define arch_read_can_lock(l) queue_read_can_lock(l) +#define arch_write_can_lock(l) queue_write_can_lock(l) +#define arch_read_lock(l) queue_read_lock(l) +#define arch_write_lock(l) queue_write_lock(l) +#define arch_read_trylock(l) queue_read_trylock(l) +#define arch_write_trylock(l) queue_write_trylock(l) +#define arch_read_unlock(l) queue_read_unlock(l) +#define arch_write_unlock(l) queue_write_unlock(l) + +#endif /* __ASM_GENERIC_QRWLOCK_H */ diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h new file mode 100644 index 000000000000..4d76f24df518 --- /dev/null +++ b/include/asm-generic/qrwlock_types.h @@ -0,0 +1,21 @@ +#ifndef __ASM_GENERIC_QRWLOCK_TYPES_H +#define __ASM_GENERIC_QRWLOCK_TYPES_H + +#include +#include + +/* + * The queue read/write lock data structure + */ + +typedef struct qrwlock { + atomic_t cnts; + arch_spinlock_t lock; +} arch_rwlock_t; + +#define __ARCH_RW_LOCK_UNLOCKED { \ + .cnts = ATOMIC_INIT(0), \ + .lock = __ARCH_SPIN_LOCK_UNLOCKED, \ +} + +#endif /* __ASM_GENERIC_QRWLOCK_TYPES_H */ -- cgit v1.2.3 From d55875f5d52c067e2eff7536368596b4a96b3ade Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 6 Jun 2014 14:37:22 -0700 Subject: include/asm-generic/ioctl.h: fix _IOC_TYPECHECK sparse error When running sparse over drivers/media/v4l2-core/v4l2-ioctl.c I get these errors: drivers/media/v4l2-core/v4l2-ioctl.c:2043:9: error: bad integer constant expression drivers/media/v4l2-core/v4l2-ioctl.c:2044:9: error: bad integer constant expression drivers/media/v4l2-core/v4l2-ioctl.c:2045:9: error: bad integer constant expression drivers/media/v4l2-core/v4l2-ioctl.c:2046:9: error: bad integer constant expression etc. The root cause of that turns out to be in include/asm-generic/ioctl.h: #include /* provoke compile error for invalid uses of size argument */ extern unsigned int __invalid_size_argument_for_IOC; #define _IOC_TYPECHECK(t) \ ((sizeof(t) == sizeof(t[1]) && \ sizeof(t) < (1 << _IOC_SIZEBITS)) ? \ sizeof(t) : __invalid_size_argument_for_IOC) If it is defined as this (as is already done if __KERNEL__ is not defined): #define _IOC_TYPECHECK(t) (sizeof(t)) then all is well with the world. This patch allows sparse to work correctly. Signed-off-by: Hans Verkuil Reviewed-by: Josh Triplett Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/ioctl.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/asm-generic') diff --git a/include/asm-generic/ioctl.h b/include/asm-generic/ioctl.h index d17295b290fa..297fb0d7cd6c 100644 --- a/include/asm-generic/ioctl.h +++ b/include/asm-generic/ioctl.h @@ -3,10 +3,15 @@ #include +#ifdef __CHECKER__ +#define _IOC_TYPECHECK(t) (sizeof(t)) +#else /* provoke compile error for invalid uses of size argument */ extern unsigned int __invalid_size_argument_for_IOC; #define _IOC_TYPECHECK(t) \ ((sizeof(t) == sizeof(t[1]) && \ sizeof(t) < (1 << _IOC_SIZEBITS)) ? \ sizeof(t) : __invalid_size_argument_for_IOC) +#endif + #endif /* _ASM_GENERIC_IOCTL_H */ -- cgit v1.2.3 From 330d282216d6e4d845a21b72572dc4df4122e8fa Mon Sep 17 00:00:00 2001 From: Zhengyu He Date: Tue, 1 Jul 2014 12:11:47 -0700 Subject: core: fix typo in percpu read_mostly section This fixes a typo that named the read_mostly section of percpu as readmostly. It works fine with SMP because the linker script specifies .data..percpu..readmostly. However, UP kernel builds don't have percpu sections defined and the non-percpu version of the section is called data..read_mostly, so .data..readmostly will float around and may break things unexpectedly. Looking at the original change that introduced data..percpu..readmostly (commit c957ef2c59e952803766ddc22e89981ab534606f), it looks like this was the original intention. Tested: Built UP kernel and confirmed the sections got merged. - Before the patch: $ objdump -h vmlinux.o | grep '\.data\.\.read.*mostly' 38 .data..read_mostly 00004418 0000000000000000 0000000000000000 00431ac0 2**6 50 .data..readmostly 00000014 0000000000000000 0000000000000000 00444000 2**3 - After the patch: $ objdump -h vmlinux.o | grep '\.data\.\.read.*mostly' 38 .data..read_mostly 00004438 0000000000000000 0000000000000000 00431ac0 2**6 Signed-off-by: Zhengyu He Signed-off-by: Filipe Brandenburger Signed-off-by: Tejun Heo --- include/asm-generic/vmlinux.lds.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 471ba48c7ae4..c1c0b0cf39b4 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -693,7 +693,7 @@ . = ALIGN(PAGE_SIZE); \ *(.data..percpu..page_aligned) \ . = ALIGN(cacheline); \ - *(.data..percpu..readmostly) \ + *(.data..percpu..read_mostly) \ . = ALIGN(cacheline); \ *(.data..percpu) \ *(.data..percpu..shared_aligned) \ -- cgit v1.2.3