From 2fc391112fb6f3424435a3aa2fda887497b5f807 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 10 Aug 2009 12:33:05 +0100 Subject: locking, sched: Give waitqueue spinlocks their own lockdep classes Give waitqueue spinlocks their own lockdep classes when they are initialised from init_waitqueue_head(). This means that struct wait_queue::func functions can operate other waitqueues. This is used by CacheFiles to catch the page from a backing fs being unlocked and to wake up another thread to take a copy of it. Signed-off-by: Peter Zijlstra Signed-off-by: David Howells Tested-by: Takashi Iwai Cc: linux-cachefs@redhat.com Cc: torvalds@osdl.org Cc: akpm@linux-foundation.org LKML-Reference: <20090810113305.17284.81508.stgit@warthog.procyon.org.uk> Signed-off-by: Ingo Molnar --- include/linux/wait.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 6788e1a4d4ca..cf3c2f5dba51 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -77,7 +77,14 @@ struct task_struct; #define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ { .flags = word, .bit_nr = bit, } -extern void init_waitqueue_head(wait_queue_head_t *q); +extern void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *); + +#define init_waitqueue_head(q) \ + do { \ + static struct lock_class_key __key; \ + \ + __init_waitqueue_head((q), &__key); \ + } while (0) #ifdef CONFIG_LOCKDEP # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ -- cgit v1.2.3 From 1ae88b2e446261c038f2c0c3150ffae142b227a2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 12 Aug 2009 09:12:30 -0400 Subject: NFS: Fix an O_DIRECT Oops... We can't call nfs_readdata_release()/nfs_writedata_release() without first initialising and referencing args.context. Doing so inside nfs_direct_read_schedule_segment()/nfs_direct_write_schedule_segment() causes an Oops. We should rather be calling nfs_readdata_free()/nfs_writedata_free() in those cases. Looking at the O_DIRECT code, the "struct nfs_direct_req" is already referencing the nfs_open_context for us. Since the readdata and writedata structures carry a reference to that, we can simplify things by getting rid of the extra nfs_open_context references, so that we can replace all instances of nfs_readdata_release()/nfs_writedata_release(). Reported-by: Catalin Marinas Signed-off-by: Trond Myklebust Tested-by: Catalin Marinas Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/nfs_fs.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index fdffb413b192..f6b90240dd41 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -473,7 +473,6 @@ extern int nfs_writepages(struct address_space *, struct writeback_control *); extern int nfs_flush_incompatible(struct file *file, struct page *page); extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int); extern int nfs_writeback_done(struct rpc_task *, struct nfs_write_data *); -extern void nfs_writedata_release(void *); /* * Try to write back everything synchronously (but check the @@ -488,7 +487,6 @@ extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_write_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_write_data *wdata); -extern void nfs_commitdata_release(void *wdata); #else static inline int nfs_commit_inode(struct inode *inode, int how) @@ -507,6 +505,7 @@ nfs_have_writebacks(struct inode *inode) * Allocate nfs_write_data structures */ extern struct nfs_write_data *nfs_writedata_alloc(unsigned int npages); +extern void nfs_writedata_free(struct nfs_write_data *); /* * linux/fs/nfs/read.c @@ -515,7 +514,6 @@ extern int nfs_readpage(struct file *, struct page *); extern int nfs_readpages(struct file *, struct address_space *, struct list_head *, unsigned); extern int nfs_readpage_result(struct rpc_task *, struct nfs_read_data *); -extern void nfs_readdata_release(void *data); extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, struct page *); @@ -523,6 +521,7 @@ extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, * Allocate nfs_read_data structures */ extern struct nfs_read_data *nfs_readdata_alloc(unsigned int npages); +extern void nfs_readdata_free(struct nfs_read_data *); /* * linux/fs/nfs3proc.c -- cgit v1.2.3 From 28402971d869e26271b25301011f667d3a5640c3 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 13 Aug 2009 10:13:22 +0200 Subject: perf_counter: Provide hw_perf_counter_setup_online() APIs Provide weak aliases for hw_perf_counter_setup_online(). This is used by the BTS patches (for v2.6.32), but it interacts with fixes so propagate this upstream. (it has no effect as of yet) Also export perf_counter_output() to architecture code. Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Frederic Weisbecker LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_counter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index a9d823a93fe8..2b36afe6ae0f 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -694,6 +694,8 @@ struct perf_sample_data { extern int perf_counter_overflow(struct perf_counter *counter, int nmi, struct perf_sample_data *data); +extern void perf_counter_output(struct perf_counter *counter, int nmi, + struct perf_sample_data *data); /* * Return 1 for a software counter, 0 for a hardware counter -- cgit v1.2.3 From 3dab77fb1bf89664bb1c9544607159dcab6f7d57 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 13 Aug 2009 11:47:53 +0200 Subject: perf: Rework/fix the whole read vs group stuff Replace PERF_SAMPLE_GROUP with PERF_SAMPLE_READ and introduce PERF_FORMAT_GROUP to deal with group reads in a more generic way. This allows you to get group reads out of read() as well. Signed-off-by: Peter Zijlstra Cc: Corey J Ashford Cc: Paul Mackerras Cc: stephane eranian LKML-Reference: <20090813103655.117411814@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/perf_counter.h | 47 +++++++++++++++++++++++++++++++++----------- 1 file changed, 36 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index 2b36afe6ae0f..b53f7006cc4e 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -115,7 +115,7 @@ enum perf_counter_sample_format { PERF_SAMPLE_TID = 1U << 1, PERF_SAMPLE_TIME = 1U << 2, PERF_SAMPLE_ADDR = 1U << 3, - PERF_SAMPLE_GROUP = 1U << 4, + PERF_SAMPLE_READ = 1U << 4, PERF_SAMPLE_CALLCHAIN = 1U << 5, PERF_SAMPLE_ID = 1U << 6, PERF_SAMPLE_CPU = 1U << 7, @@ -127,16 +127,32 @@ enum perf_counter_sample_format { }; /* - * Bits that can be set in attr.read_format to request that - * reads on the counter should return the indicated quantities, - * in increasing order of bit value, after the counter value. + * The format of the data returned by read() on a perf counter fd, + * as specified by attr.read_format: + * + * struct read_format { + * { u64 value; + * { u64 time_enabled; } && PERF_FORMAT_ENABLED + * { u64 time_running; } && PERF_FORMAT_RUNNING + * { u64 id; } && PERF_FORMAT_ID + * } && !PERF_FORMAT_GROUP + * + * { u64 nr; + * { u64 time_enabled; } && PERF_FORMAT_ENABLED + * { u64 time_running; } && PERF_FORMAT_RUNNING + * { u64 value; + * { u64 id; } && PERF_FORMAT_ID + * } cntr[nr]; + * } && PERF_FORMAT_GROUP + * }; */ enum perf_counter_read_format { PERF_FORMAT_TOTAL_TIME_ENABLED = 1U << 0, PERF_FORMAT_TOTAL_TIME_RUNNING = 1U << 1, PERF_FORMAT_ID = 1U << 2, + PERF_FORMAT_GROUP = 1U << 3, - PERF_FORMAT_MAX = 1U << 3, /* non-ABI */ + PERF_FORMAT_MAX = 1U << 4, /* non-ABI */ }; #define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ @@ -343,10 +359,8 @@ enum perf_event_type { * struct { * struct perf_event_header header; * u32 pid, tid; - * u64 value; - * { u64 time_enabled; } && PERF_FORMAT_ENABLED - * { u64 time_running; } && PERF_FORMAT_RUNNING - * { u64 parent_id; } && PERF_FORMAT_ID + * + * struct read_format values; * }; */ PERF_EVENT_READ = 8, @@ -364,11 +378,22 @@ enum perf_event_type { * { u32 cpu, res; } && PERF_SAMPLE_CPU * { u64 period; } && PERF_SAMPLE_PERIOD * - * { u64 nr; - * { u64 id, val; } cnt[nr]; } && PERF_SAMPLE_GROUP + * { struct read_format values; } && PERF_SAMPLE_READ * * { u64 nr, * u64 ips[nr]; } && PERF_SAMPLE_CALLCHAIN + * + * # + * # The RAW record below is opaque data wrt the ABI + * # + * # That is, the ABI doesn't make any promises wrt to + * # the stability of its content, it may vary depending + * # on event, hardware, kernel version and phase of + * # the moon. + * # + * # In other words, PERF_SAMPLE_RAW contents are not an ABI. + * # + * * { u32 size; * char data[size];}&& PERF_SAMPLE_RAW * }; -- cgit v1.2.3 From 9c0d90103c7e0eb6e638e5b649e9f6d8d9c1b4b3 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 31 Jul 2009 12:53:58 -0400 Subject: Capabilities: move cap_file_mmap to commoncap.c Currently we duplicate the mmap_min_addr test in cap_file_mmap and in security_file_mmap if !CONFIG_SECURITY. This patch moves cap_file_mmap into commoncap.c and then calls that function directly from security_file_mmap ifndef CONFIG_SECURITY like all of the other capability checks are done. Signed-off-by: Eric Paris Acked-by: Serge Hallyn Signed-off-by: James Morris --- include/linux/security.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 5eff459b3833..ac4bc3760b46 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -66,6 +66,9 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name, extern int cap_inode_removexattr(struct dentry *dentry, const char *name); extern int cap_inode_need_killpriv(struct dentry *dentry); extern int cap_inode_killpriv(struct dentry *dentry); +extern int cap_file_mmap(struct file *file, unsigned long reqprot, + unsigned long prot, unsigned long flags, + unsigned long addr, unsigned long addr_only); extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags); extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); @@ -2197,9 +2200,7 @@ static inline int security_file_mmap(struct file *file, unsigned long reqprot, unsigned long addr, unsigned long addr_only) { - if ((addr < mmap_min_addr) && !capable(CAP_SYS_RAWIO)) - return -EACCES; - return 0; + return cap_file_mmap(file, reqprot, prot, flags, addr, addr_only); } static inline int security_file_mprotect(struct vm_area_struct *vma, -- cgit v1.2.3 From 788084aba2ab7348257597496befcbccabdc98a3 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 31 Jul 2009 12:54:11 -0400 Subject: Security/SELinux: seperate lsm specific mmap_min_addr Currently SELinux enforcement of controls on the ability to map low memory is determined by the mmap_min_addr tunable. This patch causes SELinux to ignore the tunable and instead use a seperate Kconfig option specific to how much space the LSM should protect. The tunable will now only control the need for CAP_SYS_RAWIO and SELinux permissions will always protect the amount of low memory designated by CONFIG_LSM_MMAP_MIN_ADDR. This allows users who need to disable the mmap_min_addr controls (usual reason being they run WINE as a non-root user) to do so and still have SELinux controls preventing confined domains (like a web server) from being able to map some area of low memory. Signed-off-by: Eric Paris Signed-off-by: James Morris --- include/linux/mm.h | 15 --------------- include/linux/security.h | 17 +++++++++++++++++ 2 files changed, 17 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ba3a7cb1eaa0..9a72cc78e6b8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -34,8 +34,6 @@ extern int sysctl_legacy_va_layout; #define sysctl_legacy_va_layout 0 #endif -extern unsigned long mmap_min_addr; - #include #include #include @@ -574,19 +572,6 @@ static inline void set_page_links(struct page *page, enum zone_type zone, set_page_section(page, pfn_to_section_nr(pfn)); } -/* - * If a hint addr is less than mmap_min_addr change hint to be as - * low as possible but still greater than mmap_min_addr - */ -static inline unsigned long round_hint_to_min(unsigned long hint) -{ - hint &= PAGE_MASK; - if (((void *)hint != NULL) && - (hint < mmap_min_addr)) - return PAGE_ALIGN(mmap_min_addr); - return hint; -} - /* * Some inline functions in vmstat.h depend on page_zone() */ diff --git a/include/linux/security.h b/include/linux/security.h index ac4bc3760b46..dc3472c1f781 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -28,6 +28,7 @@ #include #include #include +#include /* PAGE_ALIGN */ #include #include #include @@ -95,6 +96,7 @@ extern int cap_netlink_send(struct sock *sk, struct sk_buff *skb); extern int cap_netlink_recv(struct sk_buff *skb, int cap); extern unsigned long mmap_min_addr; +extern unsigned long dac_mmap_min_addr; /* * Values used in the task_security_ops calls */ @@ -147,6 +149,21 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) opts->num_mnt_opts = 0; } +/* + * If a hint addr is less than mmap_min_addr change hint to be as + * low as possible but still greater than mmap_min_addr + */ +static inline unsigned long round_hint_to_min(unsigned long hint) +{ + hint &= PAGE_MASK; + if (((void *)hint != NULL) && + (hint < mmap_min_addr)) + return PAGE_ALIGN(mmap_min_addr); + return hint; +} + +extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos); /** * struct security_operations - main security structure * -- cgit v1.2.3 From 1d9959734a1949ea4f2427bd2d8b21ede6b2441c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Fri, 7 Aug 2009 14:53:57 -0400 Subject: security: define round_hint_to_min in !CONFIG_SECURITY Fix the header files to define round_hint_to_min() and to define mmap_min_addr_handler() in the !CONFIG_SECURITY case. Built and tested with !CONFIG_SECURITY Signed-off-by: Eric Paris Signed-off-by: James Morris --- include/linux/security.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index dc3472c1f781..1f16eea2017b 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -121,6 +121,21 @@ struct request_sock; #define LSM_UNSAFE_PTRACE 2 #define LSM_UNSAFE_PTRACE_CAP 4 +/* + * If a hint addr is less than mmap_min_addr change hint to be as + * low as possible but still greater than mmap_min_addr + */ +static inline unsigned long round_hint_to_min(unsigned long hint) +{ + hint &= PAGE_MASK; + if (((void *)hint != NULL) && + (hint < mmap_min_addr)) + return PAGE_ALIGN(mmap_min_addr); + return hint; +} +extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos); + #ifdef CONFIG_SECURITY struct security_mnt_opts { @@ -149,21 +164,6 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) opts->num_mnt_opts = 0; } -/* - * If a hint addr is less than mmap_min_addr change hint to be as - * low as possible but still greater than mmap_min_addr - */ -static inline unsigned long round_hint_to_min(unsigned long hint) -{ - hint &= PAGE_MASK; - if (((void *)hint != NULL) && - (hint < mmap_min_addr)) - return PAGE_ALIGN(mmap_min_addr); - return hint; -} - -extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, - void __user *buffer, size_t *lenp, loff_t *ppos); /** * struct security_operations - main security structure * -- cgit v1.2.3 From c1a8f1f1c8e01eab5862c8db39b49ace814e6c66 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 16 Aug 2009 09:36:49 +0000 Subject: net: restore gnet_stats_basic to previous definition In 5e140dfc1fe87eae27846f193086724806b33c7d "net: reorder struct Qdisc for better SMP performance" the definition of struct gnet_stats_basic changed incompatibly, as copies of this struct are shipped to userland via netlink. Restoring old behavior is not welcome, for performance reason. Fix is to use a private structure for kernel, and teach gnet_stats_copy_basic() to convert from kernel to user land, using legacy structure (struct gnet_stats_basic) Based on a report and initial patch from Michael Spang. Reported-by: Michael Spang Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/gen_stats.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gen_stats.h b/include/linux/gen_stats.h index 0ffa41df0ee8..710e901085d0 100644 --- a/include/linux/gen_stats.h +++ b/include/linux/gen_stats.h @@ -19,6 +19,11 @@ enum { * @packets: number of seen packets */ struct gnet_stats_basic +{ + __u64 bytes; + __u32 packets; +}; +struct gnet_stats_basic_packed { __u64 bytes; __u32 packets; -- cgit v1.2.3 From 0753ba01e126020bf0f8150934903b48935b697d Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 18 Aug 2009 14:11:10 -0700 Subject: mm: revert "oom: move oom_adj value" The commit 2ff05b2b (oom: move oom_adj value) moveed the oom_adj value to the mm_struct. It was a very good first step for sanitize OOM. However Paul Menage reported the commit makes regression to his job scheduler. Current OOM logic can kill OOM_DISABLED process. Why? His program has the code of similar to the following. ... set_oom_adj(OOM_DISABLE); /* The job scheduler never killed by oom */ ... if (vfork() == 0) { set_oom_adj(0); /* Invoked child can be killed */ execve("foo-bar-cmd"); } .... vfork() parent and child are shared the same mm_struct. then above set_oom_adj(0) doesn't only change oom_adj for vfork() child, it's also change oom_adj for vfork() parent. Then, vfork() parent (job scheduler) lost OOM immune and it was killed. Actually, fork-setting-exec idiom is very frequently used in userland program. We must not break this assumption. Then, this patch revert commit 2ff05b2b and related commit. Reverted commit list --------------------- - commit 2ff05b2b4e (oom: move oom_adj value from task_struct to mm_struct) - commit 4d8b9135c3 (oom: avoid unnecessary mm locking and scanning for OOM_DISABLE) - commit 8123681022 (oom: only oom kill exiting tasks with attached memory) - commit 933b787b57 (mm: copy over oom_adj value at fork time) Signed-off-by: KOSAKI Motohiro Cc: Paul Menage Cc: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: Rik van Riel Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Nick Piggin Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 -- include/linux/sched.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7acc8439d9b3..0042090a4d70 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -240,8 +240,6 @@ struct mm_struct { unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ - s8 oom_adj; /* OOM kill score adjustment (bit shift) */ - cpumask_t cpu_vm_mask; /* Architecture-specific MM context */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 3ab08e4bb6b8..0f1ea4a66957 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1198,6 +1198,7 @@ struct task_struct { * a short time */ unsigned char fpu_counter; + s8 oomkilladj; /* OOM kill score adjustment (bit shift). */ #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif -- cgit v1.2.3