linux/drivers/oprofile, branch v3.2.38

oprofile: perf: use NR_CPUS instead or nr_cpumask_bits for static array

2012-07-04T04:44:25Z

commit e734568b675c985db2026848fefaac01c22977a5 upstream. The OProfile perf backend uses a static array to keep track of the perf events on the system. When compiling with CONFIG_CPUMASK_OFFSTACK=y && SMP, nr_cpumask_bits is not a compile-time constant and the build will fail with: oprofile_perf.c:28: error: variably modified 'perf_events' at file scope This patch uses NR_CPUs instead of nr_cpumask_bits for the array initialisation. If this causes space problems in the future, we can always move to dynamic allocation for the events array. Cc: Matt Fleming Reported-by: Russell King - ARM Linux Signed-off-by: Will Deacon Signed-off-by: Robert Richter Signed-off-by: Ben Hutchings

oprofile: Fix uninitialized memory access when writing to writing to oprofilefs

2011-12-19T16:18:43Z

If oprofilefs_ulong_from_user() is called with count equals zero, *val remains unchanged. Depending on the implementation it might be uninitialized. Change oprofilefs_ulong_from_user()'s interface to return count on success. Thus, we are able to return early if count equals zero which avoids using *val uninitialized. Fixing all users of oprofilefs_ulong_ from_user(). This follows write syscall implementation when count is zero: "If count is zero ... [and if] no errors are detected, 0 will be returned without causing any other effect." (man 2 write) Reported-By: Mike Waychison Signed-off-by: Robert Richter Cc: Andrew Morton Cc: Cc: oprofile-list Link: http://lkml.kernel.org/r/20111219153830.GH16765@erda.amd.com Signed-off-by: Ingo Molnar

Merge branch 'urgent' of git://amd64.org/linux/rric into perf/urgent

2011-11-15T10:03:30Z

oprofile: Fix crash when unloading module (hr timer mode)

2011-11-04T14:04:33Z

Oprofile may crash in a KVM guest while unlaoding modules. This happens if oprofile_arch_init() fails and oprofile switches to the hr timer mode as a fallback. In this case oprofile_arch_exit() is called, but it never was initialized properly which causes the crash. This patch fixes this. oprofile: using timer interrupt. BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 IP: [] unregister_syscore_ops+0x41/0x58 PGD 41da3f067 PUD 41d80e067 PMD 0 Oops: 0002 [#1] PREEMPT SMP CPU 5 Modules linked in: oprofile(-) Pid: 2382, comm: modprobe Not tainted 3.1.0-rc7-00018-g709a39d #18 Advanced Micro Device Anaheim/Anaheim RIP: 0010:[] [] unregister_syscore_ops+0x41/0x58 RSP: 0018:ffff88041de1de98 EFLAGS: 00010296 RAX: 0000000000000000 RBX: ffffffffa00060e0 RCX: dead000000200200 RDX: 0000000000000000 RSI: dead000000100100 RDI: ffffffff8178c620 RBP: ffff88041de1dea8 R08: 0000000000000001 R09: 0000000000000082 R10: 0000000000000000 R11: ffff88041de1dde8 R12: 0000000000000080 R13: fffffffffffffff5 R14: 0000000000000001 R15: 0000000000610210 FS: 00007f9ae5bef700(0000) GS:ffff88042fd40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000008 CR3: 000000041ca44000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process modprobe (pid: 2382, threadinfo ffff88041de1c000, task ffff88042db6d040) Stack: ffff88041de1deb8 ffffffffa0006770 ffff88041de1deb8 ffffffffa000251e ffff88041de1dec8 ffffffffa00022c2 ffff88041de1ded8 ffffffffa0004993 ffff88041de1df78 ffffffff81073115 656c69666f72706f 0000000000610200 Call Trace: [] op_nmi_exit+0x15/0x17 [oprofile] [] oprofile_arch_exit+0xe/0x10 [oprofile] [] oprofile_exit+0x13/0x15 [oprofile] [] sys_delete_module+0x1c3/0x22f [] ? trace_hardirqs_on_thunk+0x3a/0x3f [] system_call_fastpath+0x16/0x1b Code: 20 c6 78 81 e8 c5 cc 23 00 48 8b 13 48 8b 43 08 48 be 00 01 10 00 00 00 ad de 48 b9 00 02 20 00 00 00 ad de 48 c7 c7 20 c6 78 81 89 42 08 48 89 10 48 89 33 48 89 4b 08 e8 a6 c0 23 00 5a 5b RIP [] unregister_syscore_ops+0x41/0x58 RSP CR2: 0000000000000008 ---[ end trace 06d4e95b6aa3b437 ]--- CC: stable@kernel.org # 2.6.37+ Signed-off-by: Robert Richter

locking, oprofile: Annotate oprofilefs lock as raw

2011-09-13T09:12:05Z

The oprofilefs_lock can be taken in atomic context (in profiling interrupts) and therefore cannot cannot be preempted on -rt - annotate it. In mainline this change documents the low level nature of the lock - otherwise there's no functional difference. Lockdep and Sparse checking will work as usual. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar

atomic: use

2011-07-26T23:49:47Z

This allows us to move duplicated code in (atomic_inc_not_zero() for now) to Signed-off-by: Arun Sharma Reviewed-by: Eric Dumazet Cc: Ingo Molnar Cc: David Miller Cc: Eric Dumazet Acked-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

perf: Remove the nmi parameter from the oprofile_perf backend

2011-07-21T18:41:58Z

In commit a8b0ca17b80e ("perf: Remove the nmi parameter from the swevent and overflow interface") one site was overlooked. Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110708173442.GB31972@e102144-lin.cambridge.arm.com Signed-off-by: Ingo Molnar

perf: Add context field to perf_event

2011-07-01T09:06:38Z

The perf_event overflow handler does not receive any caller-derived argument, so many callers need to resort to looking up the perf_event in their local data structure. This is ugly and doesn't scale if a single callback services many perf_events. Fix by adding a context parameter to perf_event_create_kernel_counter() (and derived hardware breakpoints APIs) and storing it in the perf_event. The field can be accessed from the callback as event->overflow_handler_context. All callers are updated. Signed-off-by: Avi Kivity Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1309362157-6596-2-git-send-email-avi@redhat.com Signed-off-by: Ingo Molnar

oprofile: Fix locking dependency in sync_start()

2011-05-31T14:33:34Z

This fixes the A->B/B->A locking dependency, see the warning below. The function task_exit_notify() is called with (task_exit_notifier) .rwsem set and then calls sync_buffer() which locks buffer_mutex. In sync_start() the buffer_mutex was set to prevent notifier functions to be started before sync_start() is finished. But when registering the notifier, (task_exit_notifier).rwsem is locked too, but now in different order than in sync_buffer(). In theory this causes a locking dependency, what does not occur in practice since task_exit_notify() is always called after the notifier is registered which means the lock is already released. However, after checking the notifier functions it turned out the buffer_mutex in sync_start() is unnecessary. This is because sync_buffer() may be called from the notifiers even if sync_start() did not finish yet, the buffers are already allocated but empty. No need to protect this with the mutex. So we fix this theoretical locking dependency by removing buffer_mutex in sync_start(). This is similar to the implementation before commit: 750d857 oprofile: fix crash when accessing freed task structs which introduced the locking dependency. Lockdep warning: oprofiled/4447 is trying to acquire lock: (buffer_mutex){+.+...}, at: [] sync_buffer+0x31/0x3ec [oprofile] but task is already holding lock: ((task_exit_notifier).rwsem){++++..}, at: [] __blocking_notifier_call_chain+0x39/0x67 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 ((task_exit_notifier).rwsem){++++..}: [] lock_acquire+0xf8/0x11e [] down_write+0x44/0x67 [] blocking_notifier_chain_register+0x52/0x8b [] profile_event_register+0x2d/0x2f [] sync_start+0x47/0xc6 [oprofile] [] oprofile_setup+0x60/0xa5 [oprofile] [] event_buffer_open+0x59/0x8c [oprofile] [] __dentry_open+0x1eb/0x308 [] nameidata_to_filp+0x60/0x67 [] do_last+0x5be/0x6b2 [] path_openat+0xc7/0x360 [] do_filp_open+0x3d/0x8c [] do_sys_open+0x110/0x1a9 [] sys_open+0x20/0x22 [] system_call_fastpath+0x16/0x1b -> #0 (buffer_mutex){+.+...}: [] __lock_acquire+0x1085/0x1711 [] lock_acquire+0xf8/0x11e [] mutex_lock_nested+0x63/0x309 [] sync_buffer+0x31/0x3ec [oprofile] [] task_exit_notify+0x16/0x1a [oprofile] [] notifier_call_chain+0x37/0x63 [] __blocking_notifier_call_chain+0x50/0x67 [] blocking_notifier_call_chain+0x14/0x16 [] profile_task_exit+0x1a/0x1c [] do_exit+0x2a/0x6fc [] do_group_exit+0x83/0xae [] sys_exit_group+0x17/0x1b [] system_call_fastpath+0x16/0x1b other info that might help us debug this: 1 lock held by oprofiled/4447: #0: ((task_exit_notifier).rwsem){++++..}, at: [] __blocking_notifier_call_chain+0x39/0x67 stack backtrace: Pid: 4447, comm: oprofiled Not tainted 2.6.39-00007-gcf4d8d4 #10 Call Trace: [] print_circular_bug+0xae/0xbc [] __lock_acquire+0x1085/0x1711 [] ? sync_buffer+0x31/0x3ec [oprofile] [] lock_acquire+0xf8/0x11e [] ? sync_buffer+0x31/0x3ec [oprofile] [] ? mark_lock+0x42f/0x552 [] ? sync_buffer+0x31/0x3ec [oprofile] [] mutex_lock_nested+0x63/0x309 [] ? sync_buffer+0x31/0x3ec [oprofile] [] sync_buffer+0x31/0x3ec [oprofile] [] ? __blocking_notifier_call_chain+0x39/0x67 [] ? __blocking_notifier_call_chain+0x39/0x67 [] task_exit_notify+0x16/0x1a [oprofile] [] notifier_call_chain+0x37/0x63 [] __blocking_notifier_call_chain+0x50/0x67 [] blocking_notifier_call_chain+0x14/0x16 [] profile_task_exit+0x1a/0x1c [] do_exit+0x2a/0x6fc [] ? retint_swapgs+0xe/0x13 [] do_group_exit+0x83/0xae [] sys_exit_group+0x17/0x1b [] system_call_fastpath+0x16/0x1b Reported-by: Marcin Slusarz Cc: Carl Love Cc: # .36+ Signed-off-by: Robert Richter

oprofile: Free potentially owned tasks in case of errors

2011-05-31T14:33:33Z

After registering the task free notifier we possibly have tasks in our dying_tasks list. Free them after unregistering the notifier in case of an error. Cc: # .36+ Signed-off-by: Robert Richter