Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "This contains:

   - a set of fixes found by directed-random perf fuzzing efforts by
     Vince Weaver, Alexander Shishkin and Peter Zijlstra

   - a cqm driver crash fix

   - an AMD uncore driver use after free fix"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel: Fix PEBSv3 record drain
  perf/x86/intel/bts: Kill a silly warning
  perf/x86/intel/bts: Fix BTS PMI detection
  perf/x86/intel/bts: Fix confused ordering of PMU callbacks
  perf/core: Fix aux_mmap_count vs aux_refcount order
  perf/core: Fix a race between mmap_close() and set_output() of AUX events
  perf/x86/amd/uncore: Prevent use after free
  perf/x86/intel/cqm: Check cqm/mbm enabled state in event init
  perf/core: Remove WARN from perf_event_read()
This commit is contained in:
Linus Torvalds 2016-09-13 12:47:29 -07:00
commit ee319d5834
6 changed files with 180 additions and 55 deletions

View File

@ -29,6 +29,8 @@
#define COUNTER_SHIFT 16
static HLIST_HEAD(uncore_unused_list);
struct amd_uncore {
int id;
int refcnt;
@ -39,7 +41,7 @@ struct amd_uncore {
cpumask_t *active_mask;
struct pmu *pmu;
struct perf_event *events[MAX_COUNTERS];
struct amd_uncore *free_when_cpu_online;
struct hlist_node node;
};
static struct amd_uncore * __percpu *amd_uncore_nb;
@ -306,6 +308,7 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
uncore_nb->active_mask = &amd_nb_active_mask;
uncore_nb->pmu = &amd_nb_pmu;
uncore_nb->id = -1;
*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
}
@ -319,6 +322,7 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
uncore_l2->active_mask = &amd_l2_active_mask;
uncore_l2->pmu = &amd_l2_pmu;
uncore_l2->id = -1;
*per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
}
@ -348,7 +352,7 @@ amd_uncore_find_online_sibling(struct amd_uncore *this,
continue;
if (this->id == that->id) {
that->free_when_cpu_online = this;
hlist_add_head(&this->node, &uncore_unused_list);
this = that;
break;
}
@ -388,13 +392,23 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
return 0;
}
static void uncore_clean_online(void)
{
struct amd_uncore *uncore;
struct hlist_node *n;
hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) {
hlist_del(&uncore->node);
kfree(uncore);
}
}
static void uncore_online(unsigned int cpu,
struct amd_uncore * __percpu *uncores)
{
struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
kfree(uncore->free_when_cpu_online);
uncore->free_when_cpu_online = NULL;
uncore_clean_online();
if (cpu == uncore->cpu)
cpumask_set_cpu(cpu, uncore->active_mask);

View File

@ -31,7 +31,17 @@
struct bts_ctx {
struct perf_output_handle handle;
struct debug_store ds_back;
int started;
int state;
};
/* BTS context states: */
enum {
/* no ongoing AUX transactions */
BTS_STATE_STOPPED = 0,
/* AUX transaction is on, BTS tracing is disabled */
BTS_STATE_INACTIVE,
/* AUX transaction is on, BTS tracing is running */
BTS_STATE_ACTIVE,
};
static DEFINE_PER_CPU(struct bts_ctx, bts_ctx);
@ -204,6 +214,15 @@ static void bts_update(struct bts_ctx *bts)
static int
bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
/*
* Ordering PMU callbacks wrt themselves and the PMI is done by means
* of bts::state, which:
* - is set when bts::handle::event is valid, that is, between
* perf_aux_output_begin() and perf_aux_output_end();
* - is zero otherwise;
* - is ordered against bts::handle::event with a compiler barrier.
*/
static void __bts_event_start(struct perf_event *event)
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
@ -221,10 +240,13 @@ static void __bts_event_start(struct perf_event *event)
/*
* local barrier to make sure that ds configuration made it
* before we enable BTS
* before we enable BTS and bts::state goes ACTIVE
*/
wmb();
/* INACTIVE/STOPPED -> ACTIVE */
WRITE_ONCE(bts->state, BTS_STATE_ACTIVE);
intel_pmu_enable_bts(config);
}
@ -251,9 +273,6 @@ static void bts_event_start(struct perf_event *event, int flags)
__bts_event_start(event);
/* PMI handler: this counter is running and likely generating PMIs */
ACCESS_ONCE(bts->started) = 1;
return;
fail_end_stop:
@ -263,30 +282,34 @@ fail_stop:
event->hw.state = PERF_HES_STOPPED;
}
static void __bts_event_stop(struct perf_event *event)
static void __bts_event_stop(struct perf_event *event, int state)
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
/* ACTIVE -> INACTIVE(PMI)/STOPPED(->stop()) */
WRITE_ONCE(bts->state, state);
/*
* No extra synchronization is mandated by the documentation to have
* BTS data stores globally visible.
*/
intel_pmu_disable_bts();
if (event->hw.state & PERF_HES_STOPPED)
return;
ACCESS_ONCE(event->hw.state) |= PERF_HES_STOPPED;
}
static void bts_event_stop(struct perf_event *event, int flags)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
struct bts_buffer *buf = perf_get_aux(&bts->handle);
struct bts_buffer *buf = NULL;
int state = READ_ONCE(bts->state);
/* PMI handler: don't restart this counter */
ACCESS_ONCE(bts->started) = 0;
if (state == BTS_STATE_ACTIVE)
__bts_event_stop(event, BTS_STATE_STOPPED);
__bts_event_stop(event);
if (state != BTS_STATE_STOPPED)
buf = perf_get_aux(&bts->handle);
event->hw.state |= PERF_HES_STOPPED;
if (flags & PERF_EF_UPDATE) {
bts_update(bts);
@ -296,6 +319,7 @@ static void bts_event_stop(struct perf_event *event, int flags)
bts->handle.head =
local_xchg(&buf->data_size,
buf->nr_pages << PAGE_SHIFT);
perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
!!local_xchg(&buf->lost, 0));
}
@ -310,8 +334,20 @@ static void bts_event_stop(struct perf_event *event, int flags)
void intel_bts_enable_local(void)
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
int state = READ_ONCE(bts->state);
if (bts->handle.event && bts->started)
/*
* Here we transition from INACTIVE to ACTIVE;
* if we instead are STOPPED from the interrupt handler,
* stay that way. Can't be ACTIVE here though.
*/
if (WARN_ON_ONCE(state == BTS_STATE_ACTIVE))
return;
if (state == BTS_STATE_STOPPED)
return;
if (bts->handle.event)
__bts_event_start(bts->handle.event);
}
@ -319,8 +355,15 @@ void intel_bts_disable_local(void)
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
/*
* Here we transition from ACTIVE to INACTIVE;
* do nothing for STOPPED or INACTIVE.
*/
if (READ_ONCE(bts->state) != BTS_STATE_ACTIVE)
return;
if (bts->handle.event)
__bts_event_stop(bts->handle.event);
__bts_event_stop(bts->handle.event, BTS_STATE_INACTIVE);
}
static int
@ -335,8 +378,6 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
return 0;
head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
if (WARN_ON_ONCE(head != local_read(&buf->head)))
return -EINVAL;
phys = &buf->buf[buf->cur_buf];
space = phys->offset + phys->displacement + phys->size - head;
@ -403,22 +444,37 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
int intel_bts_interrupt(void)
{
struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
struct perf_event *event = bts->handle.event;
struct bts_buffer *buf;
s64 old_head;
int err;
int err = -ENOSPC, handled = 0;
if (!event || !bts->started)
return 0;
/*
* The only surefire way of knowing if this NMI is ours is by checking
* the write ptr against the PMI threshold.
*/
if (ds->bts_index >= ds->bts_interrupt_threshold)
handled = 1;
/*
* this is wrapped in intel_bts_enable_local/intel_bts_disable_local,
* so we can only be INACTIVE or STOPPED
*/
if (READ_ONCE(bts->state) == BTS_STATE_STOPPED)
return handled;
buf = perf_get_aux(&bts->handle);
if (!buf)
return handled;
/*
* Skip snapshot counters: they don't use the interrupt, but
* there's no other way of telling, because the pointer will
* keep moving
*/
if (!buf || buf->snapshot)
if (buf->snapshot)
return 0;
old_head = local_read(&buf->head);
@ -426,18 +482,27 @@ int intel_bts_interrupt(void)
/* no new data */
if (old_head == local_read(&buf->head))
return 0;
return handled;
perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
!!local_xchg(&buf->lost, 0));
buf = perf_aux_output_begin(&bts->handle, event);
if (!buf)
return 1;
if (buf)
err = bts_buffer_reset(buf, &bts->handle);
err = bts_buffer_reset(buf, &bts->handle);
if (err)
perf_aux_output_end(&bts->handle, 0, false);
if (err) {
WRITE_ONCE(bts->state, BTS_STATE_STOPPED);
if (buf) {
/*
* BTS_STATE_STOPPED should be visible before
* cleared handle::event
*/
barrier();
perf_aux_output_end(&bts->handle, 0, false);
}
}
return 1;
}

View File

@ -458,6 +458,11 @@ static void __intel_cqm_event_count(void *info);
static void init_mbm_sample(u32 rmid, u32 evt_type);
static void __intel_mbm_event_count(void *info);
static bool is_cqm_event(int e)
{
return (e == QOS_L3_OCCUP_EVENT_ID);
}
static bool is_mbm_event(int e)
{
return (e >= QOS_MBM_TOTAL_EVENT_ID && e <= QOS_MBM_LOCAL_EVENT_ID);
@ -1366,6 +1371,10 @@ static int intel_cqm_event_init(struct perf_event *event)
(event->attr.config > QOS_MBM_LOCAL_EVENT_ID))
return -EINVAL;
if ((is_cqm_event(event->attr.config) && !cqm_enabled) ||
(is_mbm_event(event->attr.config) && !mbm_enabled))
return -EINVAL;
/* unsupported modes and filters */
if (event->attr.exclude_user ||
event->attr.exclude_kernel ||

View File

@ -1274,18 +1274,18 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
struct pebs_record_nhm *p = at;
u64 pebs_status;
/* PEBS v3 has accurate status bits */
pebs_status = p->status & cpuc->pebs_enabled;
pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
/* PEBS v3 has more accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3) {
for_each_set_bit(bit, (unsigned long *)&p->status,
MAX_PEBS_EVENTS)
for_each_set_bit(bit, (unsigned long *)&pebs_status,
x86_pmu.max_pebs_events)
counts[bit]++;
continue;
}
pebs_status = p->status & cpuc->pebs_enabled;
pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
/*
* On some CPUs the PEBS status can be zero when PEBS is
* racing with clearing of GLOBAL_STATUS.
@ -1333,8 +1333,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
continue;
event = cpuc->events[bit];
WARN_ON_ONCE(!event);
WARN_ON_ONCE(!event->attr.precise_ip);
if (WARN_ON_ONCE(!event))
continue;
if (WARN_ON_ONCE(!event->attr.precise_ip))
continue;
/* log dropped samples number */
if (error[bit])

View File

@ -2496,11 +2496,11 @@ static int __perf_event_stop(void *info)
return 0;
}
static int perf_event_restart(struct perf_event *event)
static int perf_event_stop(struct perf_event *event, int restart)
{
struct stop_event_data sd = {
.event = event,
.restart = 1,
.restart = restart,
};
int ret = 0;
@ -3549,10 +3549,18 @@ static int perf_event_read(struct perf_event *event, bool group)
.group = group,
.ret = 0,
};
ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
/* The event must have been read from an online CPU: */
WARN_ON_ONCE(ret);
ret = ret ? : data.ret;
/*
* Purposely ignore the smp_call_function_single() return
* value.
*
* If event->oncpu isn't a valid CPU it means the event got
* scheduled out and that will have updated the event count.
*
* Therefore, either way, we'll have an up-to-date event count
* after this.
*/
(void)smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
ret = data.ret;
} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
struct perf_event_context *ctx = event->ctx;
unsigned long flags;
@ -4837,6 +4845,19 @@ static void ring_buffer_attach(struct perf_event *event,
spin_unlock_irqrestore(&rb->event_lock, flags);
}
/*
* Avoid racing with perf_mmap_close(AUX): stop the event
* before swizzling the event::rb pointer; if it's getting
* unmapped, its aux_mmap_count will be 0 and it won't
* restart. See the comment in __perf_pmu_output_stop().
*
* Data will inevitably be lost when set_output is done in
* mid-air, but then again, whoever does it like this is
* not in for the data anyway.
*/
if (has_aux(event))
perf_event_stop(event, 0);
rcu_assign_pointer(event->rb, rb);
if (old_rb) {
@ -6112,7 +6133,7 @@ static void perf_event_addr_filters_exec(struct perf_event *event, void *data)
raw_spin_unlock_irqrestore(&ifh->lock, flags);
if (restart)
perf_event_restart(event);
perf_event_stop(event, 1);
}
void perf_event_exec(void)
@ -6156,7 +6177,13 @@ static void __perf_event_output_stop(struct perf_event *event, void *data)
/*
* In case of inheritance, it will be the parent that links to the
* ring-buffer, but it will be the child that's actually using it:
* ring-buffer, but it will be the child that's actually using it.
*
* We are using event::rb to determine if the event should be stopped,
* however this may race with ring_buffer_attach() (through set_output),
* which will make us skip the event that actually needs to be stopped.
* So ring_buffer_attach() has to stop an aux event before re-assigning
* its rb pointer.
*/
if (rcu_dereference(parent->rb) == rb)
ro->err = __perf_event_stop(&sd);
@ -6670,7 +6697,7 @@ static void __perf_addr_filters_adjust(struct perf_event *event, void *data)
raw_spin_unlock_irqrestore(&ifh->lock, flags);
if (restart)
perf_event_restart(event);
perf_event_stop(event, 1);
}
/*
@ -7859,7 +7886,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
mmput(mm);
restart:
perf_event_restart(event);
perf_event_stop(event, 1);
}
/*

View File

@ -330,15 +330,22 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
if (!rb)
return NULL;
if (!rb_has_aux(rb) || !atomic_inc_not_zero(&rb->aux_refcount))
if (!rb_has_aux(rb))
goto err;
/*
* If rb::aux_mmap_count is zero (and rb_has_aux() above went through),
* the aux buffer is in perf_mmap_close(), about to get freed.
* If aux_mmap_count is zero, the aux buffer is in perf_mmap_close(),
* about to get freed, so we leave immediately.
*
* Checking rb::aux_mmap_count and rb::refcount has to be done in
* the same order, see perf_mmap_close. Otherwise we end up freeing
* aux pages in this path, which is a bug, because in_atomic().
*/
if (!atomic_read(&rb->aux_mmap_count))
goto err_put;
goto err;
if (!atomic_inc_not_zero(&rb->aux_refcount))
goto err;
/*
* Nesting is not supported for AUX area, make sure nested