Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Merge commit. Changes below are compared with the first parent: bbfb239a.
Changes
19 files changed · +746 −667
Only the first 600 diff lines are shown. Download the complete patch.
arch/x86/kernel/cpu/perf_event_intel.c
View filediff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index a667078..fed2ab1 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1960,7 +1960,8 @@ intel_bts_constraints(struct perf_event *event)
static int intel_alt_er(int idx, u64 config)
{
- int alt_idx;
+ int alt_idx = idx;
+
if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1))
return idx;
@@ -2897,14 +2898,12 @@ static void intel_pmu_cpu_starting(int cpu)
return;
if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) {
- void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED];
-
for_each_cpu(i, topology_sibling_cpumask(cpu)) {
struct intel_shared_regs *pc;
pc = per_cpu(cpu_hw_events, i).shared_regs;
if (pc && pc->core_id == core_id) {
- *onln = cpuc->shared_regs;
+ cpuc->kfree_on_online[0] = cpuc->shared_regs;
cpuc->shared_regs = pc;
break;
}
arch/x86/kernel/cpu/perf_event_intel_uncore.c
View filediff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index f97f807..3bf41d4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -995,6 +995,9 @@ static int __init uncore_pci_init(void)
case 87: /* Knights Landing */
ret = knl_uncore_pci_init();
break;
+ case 94: /* SkyLake */
+ ret = skl_uncore_pci_init();
+ break;
default:
return 0;
}
arch/x86/kernel/cpu/perf_event_intel_uncore.h
View filediff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 07aa2d6..a7086b8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -336,6 +336,7 @@ int snb_uncore_pci_init(void);
int ivb_uncore_pci_init(void);
int hsw_uncore_pci_init(void);
int bdw_uncore_pci_init(void);
+int skl_uncore_pci_init(void);
void snb_uncore_cpu_init(void);
void nhm_uncore_cpu_init(void);
int snb_pci2phy_map_init(int devid);
arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
View filediff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index 0b93482..2bd030d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -8,6 +8,7 @@
#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00
#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04
#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604
+#define PCI_DEVICE_ID_INTEL_SKL_IMC 0x191f
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
@@ -524,6 +525,14 @@ static const struct pci_device_id bdw_uncore_pci_ids[] = {
{ /* end: all zeroes */ },
};
+static const struct pci_device_id skl_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
static struct pci_driver snb_uncore_pci_driver = {
.name = "snb_uncore",
.id_table = snb_uncore_pci_ids,
@@ -544,6 +553,11 @@ static struct pci_driver bdw_uncore_pci_driver = {
.id_table = bdw_uncore_pci_ids,
};
+static struct pci_driver skl_uncore_pci_driver = {
+ .name = "skl_uncore",
+ .id_table = skl_uncore_pci_ids,
+};
+
struct imc_uncore_pci_dev {
__u32 pci_id;
struct pci_driver *driver;
@@ -558,6 +572,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */
IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */
IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */
+ IMC_DEV(SKL_IMC, &skl_uncore_pci_driver), /* 6th Gen Core */
{ /* end marker */ }
};
@@ -610,6 +625,11 @@ int bdw_uncore_pci_init(void)
return imc_uncore_pci_init();
}
+int skl_uncore_pci_init(void)
+{
+ return imc_uncore_pci_init();
+}
+
/* end of Sandy Bridge uncore support */
/* Nehalem uncore support */
include/linux/perf_event.h
View filediff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f9828a4..b35a61a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -634,9 +634,6 @@ struct perf_event_context {
int nr_cgroups; /* cgroup evts */
void *task_ctx_data; /* pmu specific data */
struct rcu_head rcu_head;
-
- struct delayed_work orphans_remove;
- bool orphans_remove_sched;
};
/*
@@ -729,7 +726,7 @@ extern int perf_event_init_task(struct task_struct *child);
extern void perf_event_exit_task(struct task_struct *child);
extern void perf_event_free_task(struct task_struct *task);
extern void perf_event_delayed_put(struct task_struct *task);
-extern struct perf_event *perf_event_get(unsigned int fd);
+extern struct file *perf_event_get(unsigned int fd);
extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event);
extern void perf_event_print_debug(void);
extern void perf_pmu_disable(struct pmu *pmu);
@@ -1044,7 +1041,7 @@ extern void perf_swevent_put_recursion_context(int rctx);
extern u64 perf_swevent_set_period(struct perf_event *event);
extern void perf_event_enable(struct perf_event *event);
extern void perf_event_disable(struct perf_event *event);
-extern int __perf_event_disable(void *info);
+extern void perf_event_disable_local(struct perf_event *event);
extern void perf_event_task_tick(void);
#else /* !CONFIG_PERF_EVENTS: */
static inline void *
@@ -1070,7 +1067,7 @@ static inline int perf_event_init_task(struct task_struct *child) { return 0; }
static inline void perf_event_exit_task(struct task_struct *child) { }
static inline void perf_event_free_task(struct task_struct *task) { }
static inline void perf_event_delayed_put(struct task_struct *task) { }
-static inline struct perf_event *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); }
+static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); }
static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
{
return ERR_PTR(-EINVAL);
kernel/bpf/arraymap.c
View filediff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index b0799bc..89ebbc4 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -291,10 +291,13 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
{
struct perf_event *event;
const struct perf_event_attr *attr;
+ struct file *file;
- event = perf_event_get(fd);
- if (IS_ERR(event))
- return event;
+ file = perf_event_get(fd);
+ if (IS_ERR(file))
+ return file;
+
+ event = file->private_data;
attr = perf_event_attrs(event);
if (IS_ERR(attr))
@@ -304,24 +307,22 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
goto err;
if (attr->type == PERF_TYPE_RAW)
- return event;
+ return file;
if (attr->type == PERF_TYPE_HARDWARE)
- return event;
+ return file;
if (attr->type == PERF_TYPE_SOFTWARE &&
attr->config == PERF_COUNT_SW_BPF_OUTPUT)
- return event;
+ return file;
err:
- perf_event_release_kernel(event);
+ fput(file);
return ERR_PTR(-EINVAL);
}
static void perf_event_fd_array_put_ptr(void *ptr)
{
- struct perf_event *event = ptr;
-
- perf_event_release_kernel(event);
+ fput((struct file *)ptr);
}
static const struct bpf_map_ops perf_event_array_ops = {
kernel/events/core.c
View filediff --git a/kernel/events/core.c b/kernel/events/core.c
index 06ae52e..5946460 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -49,8 +49,6 @@
#include <asm/irq_regs.h>
-static struct workqueue_struct *perf_wq;
-
typedef int (*remote_function_f)(void *);
struct remote_function_call {
@@ -126,44 +124,181 @@ static int cpu_function_call(int cpu, remote_function_f func, void *info)
return data.ret;
}
-static void event_function_call(struct perf_event *event,
- int (*active)(void *),
- void (*inactive)(void *),
- void *data)
+static inline struct perf_cpu_context *
+__get_cpu_context(struct perf_event_context *ctx)
+{
+ return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
+}
+
+static void perf_ctx_lock(struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx)
{
+ raw_spin_lock(&cpuctx->ctx.lock);
+ if (ctx)
+ raw_spin_lock(&ctx->lock);
+}
+
+static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx)
+{
+ if (ctx)
+ raw_spin_unlock(&ctx->lock);
+ raw_spin_unlock(&cpuctx->ctx.lock);
+}
+
+#define TASK_TOMBSTONE ((void *)-1L)
+
+static bool is_kernel_event(struct perf_event *event)
+{
+ return READ_ONCE(event->owner) == TASK_TOMBSTONE;
+}
+
+/*
+ * On task ctx scheduling...
+ *
+ * When !ctx->nr_events a task context will not be scheduled. This means
+ * we can disable the scheduler hooks (for performance) without leaving
+ * pending task ctx state.
+ *
+ * This however results in two special cases:
+ *
+ * - removing the last event from a task ctx; this is relatively straight
+ * forward and is done in __perf_remove_from_context.
+ *
+ * - adding the first event to a task ctx; this is tricky because we cannot
+ * rely on ctx->is_active and therefore cannot use event_function_call().
+ * See perf_install_in_context().
+ *
+ * This is because we need a ctx->lock serialized variable (ctx->is_active)
+ * to reliably determine if a particular task/context is scheduled in. The
+ * task_curr() use in task_function_call() is racy in that a remote context
+ * switch is not a single atomic operation.
+ *
+ * As is, the situation is 'safe' because we set rq->curr before we do the
+ * actual context switch. This means that task_curr() will fail early, but
+ * we'll continue spinning on ctx->is_active until we've passed
+ * perf_event_task_sched_out().
+ *
+ * Without this ctx->lock serialized variable we could have race where we find
+ * the task (and hence the context) would not be active while in fact they are.
+ *
+ * If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set.
+ */
+
+typedef void (*event_f)(struct perf_event *, struct perf_cpu_context *,
+ struct perf_event_context *, void *);
+
+struct event_function_struct {
+ struct perf_event *event;
+ event_f func;
+ void *data;
+};
+
+static int event_function(void *info)
+{
+ struct event_function_struct *efs = info;
+ struct perf_event *event = efs->event;
struct perf_event_context *ctx = event->ctx;
- struct task_struct *task = ctx->task;
+ struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+ struct perf_event_context *task_ctx = cpuctx->task_ctx;
+ int ret = 0;
+
+ WARN_ON_ONCE(!irqs_disabled());
+
+ perf_ctx_lock(cpuctx, task_ctx);
+ /*
+ * Since we do the IPI call without holding ctx->lock things can have
+ * changed, double check we hit the task we set out to hit.
+ */
+ if (ctx->task) {
+ if (ctx->task != current) {
+ ret = -EAGAIN;
+ goto unlock;
+ }
+
+ /*
+ * We only use event_function_call() on established contexts,
+ * and event_function() is only ever called when active (or
+ * rather, we'll have bailed in task_function_call() or the
+ * above ctx->task != current test), therefore we must have
+ * ctx->is_active here.
+ */
+ WARN_ON_ONCE(!ctx->is_active);
+ /*
+ * And since we have ctx->is_active, cpuctx->task_ctx must
+ * match.
+ */
+ WARN_ON_ONCE(task_ctx != ctx);
+ } else {
+ WARN_ON_ONCE(&cpuctx->ctx != ctx);
+ }
+
+ efs->func(event, cpuctx, ctx, efs->data);
+unlock:
+ perf_ctx_unlock(cpuctx, task_ctx);
+
+ return ret;
+}
+
+static void event_function_local(struct perf_event *event, event_f func, void *data)
+{
+ struct event_function_struct efs = {
+ .event = event,
+ .func = func,
+ .data = data,
+ };
+
+ int ret = event_function(&efs);
+ WARN_ON_ONCE(ret);
+}
+
+static void event_function_call(struct perf_event *event, event_f func, void *data)
+{
+ struct perf_event_context *ctx = event->ctx;
+ struct task_struct *task = READ_ONCE(ctx->task); /* verified in event_function */
+ struct event_function_struct efs = {
+ .event = event,
+ .func = func,
+ .data = data,
+ };
+
+ if (!event->parent) {
+ /*
+ * If this is a !child event, we must hold ctx::mutex to
+ * stabilize the the event->ctx relation. See
+ * perf_event_ctx_lock().
+ */
+ lockdep_assert_held(&ctx->mutex);
+ }
if (!task) {
- cpu_function_call(event->cpu, active, data);
+ cpu_function_call(event->cpu, event_function, &efs);
return;
}
again:
- if (!task_function_call(task, active, data))
+ if (task == TASK_TOMBSTONE)
+ return;
+
+ if (!task_function_call(task, event_function, &efs))
return;
raw_spin_lock_irq(&ctx->lock);
- if (ctx->is_active) {
- /*
- * Reload the task pointer, it might have been changed by
- * a concurrent perf_event_context_sched_out().
- */
- task = ctx->task;
- raw_spin_unlock_irq(&ctx->lock);
- goto again;
+ /*
+ * Reload the task pointer, it might have been changed by
+ * a concurrent perf_event_context_sched_out().
+ */
+ task = ctx->task;
+ if (task != TASK_TOMBSTONE) {
+ if (ctx->is_active) {
+ raw_spin_unlock_irq(&ctx->lock);
+ goto again;
+ }
+ func(event, NULL, ctx, data);
}
- inactive(data);
raw_spin_unlock_irq(&ctx->lock);
}
-#define EVENT_OWNER_KERNEL ((void *) -1)
-
-static bool is_kernel_event(struct perf_event *event)
-{
- return event->owner == EVENT_OWNER_KERNEL;
-}
-
#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
PERF_FLAG_FD_OUTPUT |\
PERF_FLAG_PID_CGROUP |\
@@ -368,28 +503,6 @@ static inline u64 perf_event_clock(struct perf_event *event)
return event->clock();
}
-static inline struct perf_cpu_context *
-__get_cpu_context(struct perf_event_context *ctx)
-{
- return this_cpu_ptr(ctx->pmu->pmu_cpu_context);
-}
-
-static void perf_ctx_lock(struct perf_cpu_context *cpuctx,
- struct perf_event_context *ctx)
-{
- raw_spin_lock(&cpuctx->ctx.lock);
- if (ctx)
- raw_spin_lock(&ctx->lock);
-}
-
-static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
- struct perf_event_context *ctx)
-{
- if (ctx)
- raw_spin_unlock(&ctx->lock);
- raw_spin_unlock(&cpuctx->ctx.lock);
-}
-
#ifdef CONFIG_CGROUP_PERF
static inline bool
@@ -579,13 +692,7 @@ static inline void perf_cgroup_sched_out(struct task_struct *task,
* we are holding the rcu lock
*/
cgrp1 = perf_cgroup_from_task(task, NULL);
-
- /*
- * next is NULL when called from perf_event_enable_on_exec()
- * that will systematically cause a cgroup_switch()
- */
- if (next)
- cgrp2 = perf_cgroup_from_task(next, NULL);
+ cgrp2 = perf_cgroup_from_task(next, NULL);
/*
* only schedule out current cgroup events if we know
@@ -611,8 +718,6 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev,
* we are holding the rcu lock
*/
cgrp1 = perf_cgroup_from_task(task, NULL);
-
- /* prev can never be NULL */
cgrp2 = perf_cgroup_from_task(prev, NULL);
/*
@@ -917,7 +1022,7 @@ static void put_ctx(struct perf_event_context *ctx)
if (atomic_dec_and_test(&ctx->refcount)) {
if (ctx->parent_ctx)
put_ctx(ctx->parent_ctx);
- if (ctx->task)
+ if (ctx->task && ctx->task != TASK_TOMBSTONE)
put_task_struct(ctx->task);
call_rcu(&ctx->rcu_head, free_ctx);
}
@@ -934,9 +1039,8 @@ static void put_ctx(struct perf_event_context *ctx)
* perf_event_context::mutex nests and those are:
*
* - perf_event_exit_task_context() [ child , 0 ]
- * __perf_event_exit_task()
- * sync_child_event()
- * put_event() [ parent, 1 ]
+ * perf_event_exit_event()
+ * put_event() [ parent, 1 ]
*
* - perf_event_init_context() [ parent, 0 ]
* inherit_task_group()
@@ -979,8 +1083,8 @@ static void put_ctx(struct perf_event_context *ctx)
* Lock order:
* task_struct::perf_event_mutex
* perf_event_context::mutex
- * perf_event_context::lock
* perf_event::child_mutex;
+ * perf_event_context::lock
* perf_event::mmap_mutex
* mmap_sem
*/
@@ -1078,6 +1182,7 @@ static u64 primary_event_id(struct perf_event *event)
/*
* Get the perf_event_context for a task and lock it.
+ *
* This has to cope with with the fact that until it is locked,
* the context could get moved to another task.
*/
@@ -1118,9 +1223,12 @@ retry:
goto retry;
}
- if (!atomic_inc_not_zero(&ctx->refcount)) {
+ if (ctx->task == TASK_TOMBSTONE ||
+ !atomic_inc_not_zero(&ctx->refcount)) {
raw_spin_unlock(&ctx->lock);
ctx = NULL;
+ } else {
+ WARN_ON_ONCE(ctx->task != task);
}
}
rcu_read_unlock();
@@ -1246,6 +1354,8 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
static void
list_add_event(struct perf_event *event, struct perf_event_context *ctx)
{
+ lockdep_assert_held(&ctx->lock);
+
WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
event->attach_state |= PERF_ATTACH_CONTEXT;
@@ -1448,11 +1558,14 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
if (is_cgroup_event(event)) {
ctx->nr_cgroups--;
+ /*
+ * Because cgroup events are always per-cpu events, this will
+ * always be called from the right CPU.
+ */
cpuctx = __get_cpu_context(ctx);
/*
- * if there are no more cgroup events
- * then cler cgrp to avoid stale pointer
- * in update_cgrp_time_from_cpuctx()
+ * If there are no more cgroup events then clear cgrp to avoid
+ * stale pointer in update_cgrp_time_from_cpuctx().
*/
if (!ctx->nr_cgroups)
cpuctx->cgrp = NULL;
@@ -1530,45 +1643,11 @@ out:
perf_event__header_size(tmp);
}
-/*
- * User event without the task.
- */
static bool is_orphaned_event(struct perf_event *event)
{
- return event && !is_kernel_event(event) && !event->owner;
+ return event->state == PERF_EVENT_STATE_EXIT;
}
-/*
- * Event has a parent but parent's task finished and it's
- * alive only because of children holding refference.
- */
-static bool is_orphaned_child(struct perf_event *event)
-{
- return is_orphaned_event(event->parent);
-}
-
-static void orphans_remove_work(struct work_struct *work);
-
-static void schedule_orphans_remove(struct perf_event_context *ctx)
-{
- if (!ctx->task || ctx->orphans_remove_sched || !perf_wq)
- return;
-
- if (queue_delayed_work(perf_wq, &ctx->orphans_remove, 1)) {
- get_ctx(ctx);
- ctx->orphans_remove_sched = true;
- }
-}
-
-static int __init perf_workqueue_init(void)
-{
- perf_wq = create_singlethread_workqueue("perf");
- WARN(!perf_wq, "failed to create perf workqueue\n");
- return perf_wq ? 0 : -1;
-}
-
This diff is incomplete. Download the complete patch.
kernel/events/hw_breakpoint.c
View fileThis diff is incomplete. Download the complete patch.
kernel/events/ring_buffer.c
View fileThis diff is incomplete. Download the complete patch.
kernel/trace/bpf_trace.c
View fileThis diff is incomplete. Download the complete patch.
tools/perf/Makefile.perf
View fileThis diff is incomplete. Download the complete patch.
tools/perf/arch/x86/tests/intel-cqm.c
View fileThis diff is incomplete. Download the complete patch.
tools/perf/config/Makefile
View fileThis diff is incomplete. Download the complete patch.
tools/perf/tests/make
View fileThis diff is incomplete. Download the complete patch.
tools/perf/ui/browsers/annotate.c
View fileThis diff is incomplete. Download the complete patch.
tools/perf/util/hist.c
View fileThis diff is incomplete. Download the complete patch.
tools/perf/util/session.c
View fileThis diff is incomplete. Download the complete patch.
tools/perf/util/stat.c
View fileThis diff is incomplete. Download the complete patch.
tools/perf/util/symbol.c
View fileThis diff is incomplete. Download the complete patch.