From 0f624e7e5625f4c30c836b7a5decfe2553582391 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Tue, 15 Dec 2009 19:40:32 +1100 Subject: perf_event: Fix incorrect range check on cpu number It is quite legitimate for CPUs to be numbered sparsely, meaning that it possible for an online CPU to have a number which is greater than the total count of possible CPUs. Currently find_get_context() has a sanity check on the cpu number where it checks it against num_possible_cpus(). This test can fail for a legitimate cpu number if the cpu_possible_mask is sparsely populated. This fixes the problem by checking the CPU number against nr_cpumask_bits instead, since that is the appropriate check to ensure that the cpu number is same to pass to cpu_isset() subsequently. Reported-by: Michael Neuling Signed-off-by: Paul Mackerras Tested-by: Michael Neuling Acked-by: Peter Zijlstra Cc: LKML-Reference: <20091215084032.GA18661@brick.ozlabs.ibm.com> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index d891ec4a8100..8823b0885183 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -1603,7 +1603,7 @@ static struct perf_event_context *find_get_context(pid_t pid, int cpu) if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) return ERR_PTR(-EACCES); - if (cpu < 0 || cpu > num_possible_cpus()) + if (cpu < 0 || cpu >= nr_cpumask_bits) return ERR_PTR(-EINVAL); /* -- cgit v1.2.3 From f13c12c634e124d5d31f912b969d542a016d6105 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 Dec 2009 19:43:11 +0100 Subject: perf_events: Fix perf_event_attr layout The miss-alignment of bp_addr created a 32bit hole, causing different structure packings on 32 and 64 bit machines. Fix that by moving __reserve_2 into that hole. Further, remove the useless struct and redundant __bp_reserve muck. Signed-off-by: Peter Zijlstra Cc: Frederic Weisbecker Cc: Arnaldo Carvalho de Melo LKML-Reference: <1260902591.8023.781.camel@laptop> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 12 +++--------- kernel/perf_event.c | 2 +- 2 files changed, 4 insertions(+), 10 deletions(-) (limited to 'kernel') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 64a53f74c9a9..5fcbf7d2712a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -211,17 +211,11 @@ struct perf_event_attr { __u32 wakeup_watermark; /* bytes before wakeup */ }; - struct { /* Hardware breakpoint info */ - __u64 bp_addr; - __u32 bp_type; - __u32 bp_len; - __u64 __bp_reserved_1; - __u64 __bp_reserved_2; - }; - __u32 __reserved_2; - __u64 __reserved_3; + __u64 bp_addr; + __u32 bp_type; + __u32 bp_len; }; /* diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 8823b0885183..0dd8e5d02c66 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4564,7 +4564,7 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, if (attr->type >= PERF_TYPE_MAX) return -EINVAL; - if (attr->__reserved_1 || attr->__reserved_2 || attr->__reserved_3) + if (attr->__reserved_1 || attr->__reserved_2) return -EINVAL; if (attr->sample_type & ~(PERF_SAMPLE_MAX-1)) -- cgit v1.2.3 From f4c4176f21533e22bcc292030da72bcfa105f5b8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Dec 2009 17:55:54 +0100 Subject: perf events: Allow per-task-per-cpu counters In order to allow for per-task-per-cpu counters, useful for scalability when profiling task hierarchies, we allow installing events with event->cpu != -1 in task contexts. __perf_event_sched_in() already skips events where ->cpu mis-matches the current cpu, fix up __perf_install_in_context() and __perf_event_enable() to also respect this filter. This does lead to vary hard to interpret enabled/running times for such counters, but I don't see a simple solution for that. Signed-off-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: fweisbec@gmail.com Cc: Paul Mackerras LKML-Reference: <20091216165904.831451147@chello.nl> Signed-off-by: Ingo Molnar --- kernel/perf_event.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 0dd8e5d02c66..2e0aaa34fc7e 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -782,6 +782,9 @@ static void __perf_install_in_context(void *info) add_event_to_ctx(event, ctx); + if (event->cpu != -1 && event->cpu != smp_processor_id()) + goto unlock; + /* * Don't put the event on if it is disabled or if * it is in a group and the group isn't on. @@ -925,6 +928,9 @@ static void __perf_event_enable(void *info) goto unlock; __perf_event_mark_enabled(event, ctx); + if (event->cpu != -1 && event->cpu != smp_processor_id()) + goto unlock; + /* * If the event is in a group and isn't the group leader, * then don't put it on unless the group is on. @@ -1595,10 +1601,7 @@ static struct perf_event_context *find_get_context(pid_t pid, int cpu) unsigned long flags; int err; - /* - * If cpu is not a wildcard then this is a percpu event: - */ - if (cpu != -1) { + if (pid == -1 && cpu != -1) { /* Must be root to operate on a CPU event: */ if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) return ERR_PTR(-EACCES); -- cgit v1.2.3