From 950eaaca681c44aab87a46225c9e44f902c080aa Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 31 Aug 2010 17:00:18 -0700 Subject: pid: make setpgid() system call use RCU read-side critical section [ 23.584719] [ 23.584720] =================================================== [ 23.585059] [ INFO: suspicious rcu_dereference_check() usage. ] [ 23.585176] --------------------------------------------------- [ 23.585176] kernel/pid.c:419 invoked rcu_dereference_check() without protection! [ 23.585176] [ 23.585176] other info that might help us debug this: [ 23.585176] [ 23.585176] [ 23.585176] rcu_scheduler_active = 1, debug_locks = 1 [ 23.585176] 1 lock held by rc.sysinit/728: [ 23.585176] #0: (tasklist_lock){.+.+..}, at: [] sys_setpgid+0x5f/0x193 [ 23.585176] [ 23.585176] stack backtrace: [ 23.585176] Pid: 728, comm: rc.sysinit Not tainted 2.6.36-rc2 #2 [ 23.585176] Call Trace: [ 23.585176] [] lockdep_rcu_dereference+0x99/0xa2 [ 23.585176] [] find_task_by_pid_ns+0x50/0x6a [ 23.585176] [] find_task_by_vpid+0x1d/0x1f [ 23.585176] [] sys_setpgid+0x67/0x193 [ 23.585176] [] system_call_fastpath+0x16/0x1b [ 24.959669] type=1400 audit(1282938522.956:4): avc: denied { module_request } for pid=766 comm="hwclock" kmod="char-major-10-135" scontext=system_u:system_r:hwclock_t:s0 tcontext=system_u:system_r:kernel_t:s0 tclas It turns out that the setpgid() system call fails to enter an RCU read-side critical section before doing a PID-to-task_struct translation. This commit therefore does rcu_read_lock() before the translation, and also does rcu_read_unlock() after the last use of the returned pointer. Reported-by: Andrew Morton Signed-off-by: Paul E. McKenney Acked-by: David Howells --- kernel/sys.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index e9ad44489828..7f5a0cd296a9 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -931,6 +931,7 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) pgid = pid; if (pgid < 0) return -EINVAL; + rcu_read_lock(); /* From this point forward we keep holding onto the tasklist lock * so that our parent does not change from under us. -DaveM @@ -984,6 +985,7 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) out: /* All paths lead to here, thus we are safe. -DaveM */ write_unlock_irq(&tasklist_lock); + rcu_read_unlock(); return err; } -- cgit v1.2.3 From ef5dc121d5a0bb1fa477c5395277259f07d318a3 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 2 Sep 2010 15:48:16 -0700 Subject: mutex: Fix annotations to include it in kernel-locking docbook Fix kernel-doc notation in linux/mutex.h and kernel/mutex.c, then add these 2 files to the kernel-locking docbook as the Mutex API reference chapter. Add one API function to mutex-design.txt and correct a typo in that file. Signed-off-by: Randy Dunlap Cc: Rusty Russell LKML-Reference: <20100902154816.6cc2f9ad.randy.dunlap@oracle.com> Signed-off-by: Ingo Molnar --- Documentation/DocBook/kernel-locking.tmpl | 6 ++++++ Documentation/mutex-design.txt | 3 ++- include/linux/mutex.h | 8 ++++++++ kernel/mutex.c | 23 +++++++---------------- 4 files changed, 23 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl index 0b1a3f97f285..a0d479d1e1dd 100644 --- a/Documentation/DocBook/kernel-locking.tmpl +++ b/Documentation/DocBook/kernel-locking.tmpl @@ -1961,6 +1961,12 @@ machines due to caching. + + Mutex API reference +!Iinclude/linux/mutex.h +!Ekernel/mutex.c + + Further reading diff --git a/Documentation/mutex-design.txt b/Documentation/mutex-design.txt index c91ccc0720fa..38c10fd7f411 100644 --- a/Documentation/mutex-design.txt +++ b/Documentation/mutex-design.txt @@ -9,7 +9,7 @@ firstly, there's nothing wrong with semaphores. But if the simpler mutex semantics are sufficient for your code, then there are a couple of advantages of mutexes: - - 'struct mutex' is smaller on most architectures: .e.g on x86, + - 'struct mutex' is smaller on most architectures: E.g. on x86, 'struct semaphore' is 20 bytes, 'struct mutex' is 16 bytes. A smaller structure size means less RAM footprint, and better CPU-cache utilization. @@ -136,3 +136,4 @@ the APIs of 'struct mutex' have been streamlined: void mutex_lock_nested(struct mutex *lock, unsigned int subclass); int mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass); + int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 878cab4f5fcc..f363bc8fdc74 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -78,6 +78,14 @@ struct mutex_waiter { # include #else # define __DEBUG_MUTEX_INITIALIZER(lockname) +/** + * mutex_init - initialize the mutex + * @mutex: the mutex to be initialized + * + * Initialize the mutex to unlocked state. + * + * It is not allowed to initialize an already locked mutex. + */ # define mutex_init(mutex) \ do { \ static struct lock_class_key __key; \ diff --git a/kernel/mutex.c b/kernel/mutex.c index 4c0b7b3e6d2e..200407c1502f 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -36,15 +36,6 @@ # include #endif -/*** - * mutex_init - initialize the mutex - * @lock: the mutex to be initialized - * @key: the lock_class_key for the class; used by mutex lock debugging - * - * Initialize the mutex to unlocked state. - * - * It is not allowed to initialize an already locked mutex. - */ void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) { @@ -68,7 +59,7 @@ EXPORT_SYMBOL(__mutex_init); static __used noinline void __sched __mutex_lock_slowpath(atomic_t *lock_count); -/*** +/** * mutex_lock - acquire the mutex * @lock: the mutex to be acquired * @@ -105,7 +96,7 @@ EXPORT_SYMBOL(mutex_lock); static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count); -/*** +/** * mutex_unlock - release the mutex * @lock: the mutex to be released * @@ -364,8 +355,8 @@ __mutex_lock_killable_slowpath(atomic_t *lock_count); static noinline int __sched __mutex_lock_interruptible_slowpath(atomic_t *lock_count); -/*** - * mutex_lock_interruptible - acquire the mutex, interruptable +/** + * mutex_lock_interruptible - acquire the mutex, interruptible * @lock: the mutex to be acquired * * Lock the mutex like mutex_lock(), and return 0 if the mutex has @@ -456,15 +447,15 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) return prev == 1; } -/*** - * mutex_trylock - try acquire the mutex, without waiting +/** + * mutex_trylock - try to acquire the mutex, without waiting * @lock: the mutex to be acquired * * Try to acquire the mutex atomically. Returns 1 if the mutex * has been acquired successfully, and 0 on contention. * * NOTE: this function follows the spin_trylock() convention, so - * it is negated to the down_trylock() return values! Be careful + * it is negated from the down_trylock() return values! Be careful * about this when converting semaphore users to mutexes. * * This function must not be used in interrupt context. The -- cgit v1.2.3 From b3bd3de66f60df4c9a2076e2886a622458929056 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 10 Aug 2010 14:17:51 -0700 Subject: gcc-4.6: kernel/*: Fix unused but set warnings No real bugs I believe, just some dead code. Signed-off-by: Andi Kleen Cc: Peter Zijlstra Cc: andi@firstfloor.org Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- kernel/debug/kdb/kdb_bp.c | 2 -- kernel/hrtimer.c | 3 +-- kernel/sched_fair.c | 3 +-- kernel/sysctl.c | 5 +---- kernel/trace/ring_buffer.c | 2 -- 5 files changed, 3 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index 75bd9b3ebbb7..20059ef4459a 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -274,7 +274,6 @@ static int kdb_bp(int argc, const char **argv) int i, bpno; kdb_bp_t *bp, *bp_check; int diag; - int free; char *symname = NULL; long offset = 0ul; int nextarg; @@ -305,7 +304,6 @@ static int kdb_bp(int argc, const char **argv) /* * Find an empty bp structure to allocate */ - free = KDB_MAXBPT; for (bpno = 0, bp = kdb_breakpoints; bpno < KDB_MAXBPT; bpno++, bp++) { if (bp->bp_free) break; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index ce669174f355..1decafbb6b1a 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1091,11 +1091,10 @@ EXPORT_SYMBOL_GPL(hrtimer_cancel); */ ktime_t hrtimer_get_remaining(const struct hrtimer *timer) { - struct hrtimer_clock_base *base; unsigned long flags; ktime_t rem; - base = lock_hrtimer_base(timer, &flags); + lock_hrtimer_base(timer, &flags); rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index ab661ebc4895..134f7edb30c6 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1313,7 +1313,7 @@ static struct sched_group * find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu, int load_idx) { - struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups; + struct sched_group *idlest = NULL, *group = sd->groups; unsigned long min_load = ULONG_MAX, this_load = 0; int imbalance = 100 + (sd->imbalance_pct-100)/2; @@ -1348,7 +1348,6 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, if (local_group) { this_load = avg_load; - this = group; } else if (avg_load < min_load) { min_load = avg_load; idlest = group; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ca38e8e3e907..f88552c6d227 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1713,10 +1713,7 @@ static __init int sysctl_init(void) { sysctl_set_parent(NULL, root_table); #ifdef CONFIG_SYSCTL_SYSCALL_CHECK - { - int err; - err = sysctl_check_table(current->nsproxy, root_table); - } + sysctl_check_table(current->nsproxy, root_table); #endif return 0; } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 19cccc3c3028..492197e2f86c 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2985,13 +2985,11 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) static void rb_advance_iter(struct ring_buffer_iter *iter) { - struct ring_buffer *buffer; struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; unsigned length; cpu_buffer = iter->cpu_buffer; - buffer = cpu_buffer->buffer; /* * Check if we are at the end of the buffer. -- cgit v1.2.3