#include <linux/fs.h>
#include <linux/cpu.h>
#include <linux/smp.h>
+#include <linux/file.h>
#include <linux/poll.h>
#include <linux/sysfs.h>
#include <linux/ptrace.h>
/*
* Architecture provided APIs - weak aliases:
*/
-
-int __weak hw_perf_counter_init(struct perf_counter *counter, u32 hw_event_type)
+extern __weak const struct hw_perf_counter_ops *
+hw_perf_counter_init(struct perf_counter *counter)
{
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
}
-void __weak hw_perf_counter_enable(struct perf_counter *counter) { }
-void __weak hw_perf_counter_disable(struct perf_counter *counter) { }
-void __weak hw_perf_counter_read(struct perf_counter *counter) { }
-void __weak hw_perf_disable_all(void) { }
-void __weak hw_perf_enable_all(void) { }
-void __weak hw_perf_counter_setup(void) { }
+u64 __weak hw_perf_save_disable(void) { return 0; }
+void __weak hw_perf_restore(u64 ctrl) { }
+void __weak hw_perf_counter_setup(void) { }
#if BITS_PER_LONG == 64
* Read the cached counter in counter safe against cross CPU / NMI
* modifications. 64 bit version - no complications.
*/
-static inline u64 perf_read_counter_safe(struct perf_counter *counter)
+static inline u64 perf_counter_read_safe(struct perf_counter *counter)
{
return (u64) atomic64_read(&counter->count);
}
+void atomic64_counter_set(struct perf_counter *counter, u64 val)
+{
+ atomic64_set(&counter->count, val);
+}
+
+u64 atomic64_counter_read(struct perf_counter *counter)
+{
+ return atomic64_read(&counter->count);
+}
+
#else
/*
* Read the cached counter in counter safe against cross CPU / NMI
* modifications. 32 bit version.
*/
-static u64 perf_read_counter_safe(struct perf_counter *counter)
+static u64 perf_counter_read_safe(struct perf_counter *counter)
{
u32 cntl, cnth;
return cntl | ((u64) cnth) << 32;
}
+void atomic64_counter_set(struct perf_counter *counter, u64 val64)
+{
+ u32 *val32 = (void *)&val64;
+
+ atomic_set(counter->count32 + 0, *(val32 + 0));
+ atomic_set(counter->count32 + 1, *(val32 + 1));
+}
+
+u64 atomic64_counter_read(struct perf_counter *counter)
+{
+ return atomic_read(counter->count32 + 0) |
+ (u64) atomic_read(counter->count32 + 1) << 32;
+}
+
#endif
+static void
+list_add_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
+{
+ struct perf_counter *group_leader = counter->group_leader;
+
+ /*
+ * Depending on whether it is a standalone or sibling counter,
+ * add it straight to the context's counter list, or to the group
+ * leader's sibling list:
+ */
+ if (counter->group_leader == counter)
+ list_add_tail(&counter->list_entry, &ctx->counter_list);
+ else
+ list_add_tail(&counter->list_entry, &group_leader->sibling_list);
+}
+
+static void
+list_del_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
+{
+ struct perf_counter *sibling, *tmp;
+
+ list_del_init(&counter->list_entry);
+
+ /*
+ * If this was a group counter with sibling counters then
+ * upgrade the siblings to singleton counters by adding them
+ * to the context list directly:
+ */
+ list_for_each_entry_safe(sibling, tmp,
+ &counter->sibling_list, list_entry) {
+
+ list_del_init(&sibling->list_entry);
+ list_add_tail(&sibling->list_entry, &ctx->counter_list);
+ WARN_ON_ONCE(!sibling->group_leader);
+ WARN_ON_ONCE(sibling->group_leader == sibling);
+ sibling->group_leader = sibling;
+ }
+}
+
/*
* Cross CPU call to remove a performance counter
*
* We disable the counter on the hardware level first. After that we
* remove it from the context list.
*/
-static void __perf_remove_from_context(void *info)
+static void __perf_counter_remove_from_context(void *info)
{
struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
struct perf_counter *counter = info;
struct perf_counter_context *ctx = counter->ctx;
+ u64 perf_flags;
/*
* If this is a task context, we need to check whether it is
spin_lock(&ctx->lock);
if (counter->active) {
- hw_perf_counter_disable(counter);
+ counter->hw_ops->hw_perf_counter_disable(counter);
counter->active = 0;
ctx->nr_active--;
cpuctx->active_oncpu--;
* Protect the list operation against NMI by disabling the
* counters on a global level. NOP for non NMI based counters.
*/
- hw_perf_disable_all();
- list_del_init(&counter->list);
- hw_perf_enable_all();
+ perf_flags = hw_perf_save_disable();
+ list_del_counter(counter, ctx);
+ hw_perf_restore(perf_flags);
if (!ctx->task) {
/*
* CPU counters are removed with a smp call. For task counters we only
* call when the task is on a CPU.
*/
-static void perf_remove_from_context(struct perf_counter *counter)
+static void perf_counter_remove_from_context(struct perf_counter *counter)
{
struct perf_counter_context *ctx = counter->ctx;
struct task_struct *task = ctx->task;
* the removal is always sucessful.
*/
smp_call_function_single(counter->cpu,
- __perf_remove_from_context,
+ __perf_counter_remove_from_context,
counter, 1);
return;
}
retry:
- task_oncpu_function_call(task, __perf_remove_from_context,
+ task_oncpu_function_call(task, __perf_counter_remove_from_context,
counter);
spin_lock_irq(&ctx->lock);
/*
* If the context is active we need to retry the smp call.
*/
- if (ctx->nr_active && !list_empty(&counter->list)) {
+ if (ctx->nr_active && !list_empty(&counter->list_entry)) {
spin_unlock_irq(&ctx->lock);
goto retry;
}
/*
* The lock prevents that this context is scheduled in so we
- * can remove the counter safely, if it the call above did not
+ * can remove the counter safely, if the call above did not
* succeed.
*/
- if (!list_empty(&counter->list)) {
+ if (!list_empty(&counter->list_entry)) {
ctx->nr_counters--;
- list_del_init(&counter->list);
+ list_del_counter(counter, ctx);
counter->task = NULL;
}
spin_unlock_irq(&ctx->lock);
struct perf_counter *counter = info;
struct perf_counter_context *ctx = counter->ctx;
int cpu = smp_processor_id();
+ u64 perf_flags;
/*
* If this is a task context, we need to check whether it is
* Protect the list operation against NMI by disabling the
* counters on a global level. NOP for non NMI based counters.
*/
- hw_perf_disable_all();
- list_add_tail(&counter->list, &ctx->counters);
- hw_perf_enable_all();
+ perf_flags = hw_perf_save_disable();
+ list_add_counter(counter, ctx);
+ hw_perf_restore(perf_flags);
ctx->nr_counters++;
if (cpuctx->active_oncpu < perf_max_counters) {
- hw_perf_counter_enable(counter);
+ counter->hw_ops->hw_perf_counter_enable(counter);
counter->active = 1;
counter->oncpu = cpu;
ctx->nr_active++;
* If the context is active and the counter has not been added
* we need to retry the smp call.
*/
- if (ctx->nr_active && list_empty(&counter->list)) {
+ if (ctx->nr_active && list_empty(&counter->list_entry)) {
spin_unlock_irq(&ctx->lock);
goto retry;
}
* can add the counter safely, if it the call above did not
* succeed.
*/
- if (list_empty(&counter->list)) {
- list_add_tail(&counter->list, &ctx->counters);
+ if (list_empty(&counter->list_entry)) {
+ list_add_counter(counter, ctx);
ctx->nr_counters++;
}
spin_unlock_irq(&ctx->lock);
}
+static void
+counter_sched_out(struct perf_counter *counter,
+ struct perf_cpu_context *cpuctx,
+ struct perf_counter_context *ctx)
+{
+ if (!counter->active)
+ return;
+
+ counter->hw_ops->hw_perf_counter_disable(counter);
+ counter->active = 0;
+ counter->oncpu = -1;
+
+ cpuctx->active_oncpu--;
+ ctx->nr_active--;
+}
+
+static void
+group_sched_out(struct perf_counter *group_counter,
+ struct perf_cpu_context *cpuctx,
+ struct perf_counter_context *ctx)
+{
+ struct perf_counter *counter;
+
+ counter_sched_out(group_counter, cpuctx, ctx);
+
+ /*
+ * Schedule out siblings (if any):
+ */
+ list_for_each_entry(counter, &group_counter->sibling_list, list_entry)
+ counter_sched_out(counter, cpuctx, ctx);
+}
+
/*
* Called from scheduler to remove the counters of the current task,
* with interrupts disabled.
return;
spin_lock(&ctx->lock);
- list_for_each_entry(counter, &ctx->counters, list) {
- if (!ctx->nr_active)
- break;
- if (counter->active) {
- hw_perf_counter_disable(counter);
- counter->active = 0;
- counter->oncpu = -1;
- ctx->nr_active--;
- cpuctx->active_oncpu--;
- }
+ if (ctx->nr_active) {
+ list_for_each_entry(counter, &ctx->counter_list, list_entry)
+ group_sched_out(counter, cpuctx, ctx);
}
spin_unlock(&ctx->lock);
cpuctx->task_ctx = NULL;
}
+static void
+counter_sched_in(struct perf_counter *counter,
+ struct perf_cpu_context *cpuctx,
+ struct perf_counter_context *ctx,
+ int cpu)
+{
+ counter->hw_ops->hw_perf_counter_enable(counter);
+ counter->active = 1;
+ counter->oncpu = cpu; /* TODO: put 'cpu' into cpuctx->cpu */
+
+ cpuctx->active_oncpu++;
+ ctx->nr_active++;
+}
+
+static void
+group_sched_in(struct perf_counter *group_counter,
+ struct perf_cpu_context *cpuctx,
+ struct perf_counter_context *ctx,
+ int cpu)
+{
+ struct perf_counter *counter;
+
+ counter_sched_in(group_counter, cpuctx, ctx, cpu);
+
+ /*
+ * Schedule in siblings as one group (if any):
+ */
+ list_for_each_entry(counter, &group_counter->sibling_list, list_entry)
+ counter_sched_in(counter, cpuctx, ctx, cpu);
+}
+
/*
* Called from scheduler to add the counters of the current task
* with interrupts disabled.
return;
spin_lock(&ctx->lock);
- list_for_each_entry(counter, &ctx->counters, list) {
+ list_for_each_entry(counter, &ctx->counter_list, list_entry) {
if (ctx->nr_active == cpuctx->max_pertask)
break;
+
+ /*
+ * Listen to the 'cpu' scheduling filter constraint
+ * of counters:
+ */
if (counter->cpu != -1 && counter->cpu != cpu)
continue;
- hw_perf_counter_enable(counter);
- counter->active = 1;
- counter->oncpu = cpu;
- ctx->nr_active++;
- cpuctx->active_oncpu++;
+ group_sched_in(counter, cpuctx, ctx, cpu);
}
spin_unlock(&ctx->lock);
+
cpuctx->task_ctx = ctx;
}
{
struct perf_counter_context *ctx = &curr->perf_counter_ctx;
struct perf_counter *counter;
+ u64 perf_flags;
if (likely(!ctx->nr_counters))
return;
spin_lock(&ctx->lock);
/*
- * Rotate the first entry last:
+ * Rotate the first entry last (works just fine for group counters too):
*/
- hw_perf_disable_all();
- list_for_each_entry(counter, &ctx->counters, list) {
- list_del(&counter->list);
- list_add_tail(&counter->list, &ctx->counters);
+ perf_flags = hw_perf_save_disable();
+ list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+ list_del(&counter->list_entry);
+ list_add_tail(&counter->list_entry, &ctx->counter_list);
break;
}
- hw_perf_enable_all();
+ hw_perf_restore(perf_flags);
spin_unlock(&ctx->lock);
perf_counter_task_sched_in(curr, cpu);
}
+/*
+ * Initialize the perf_counter context in a task_struct:
+ */
+static void
+__perf_counter_init_context(struct perf_counter_context *ctx,
+ struct task_struct *task)
+{
+ spin_lock_init(&ctx->lock);
+ INIT_LIST_HEAD(&ctx->counter_list);
+ ctx->nr_counters = 0;
+ ctx->task = task;
+}
/*
* Initialize the perf_counter context in task_struct
*/
void perf_counter_init_task(struct task_struct *task)
{
- struct perf_counter_context *ctx = &task->perf_counter_ctx;
-
- spin_lock_init(&ctx->lock);
- INIT_LIST_HEAD(&ctx->counters);
- ctx->nr_counters = 0;
- ctx->task = task;
+ __perf_counter_init_context(&task->perf_counter_ctx, task);
}
/*
*/
static void __hw_perf_counter_read(void *info)
{
- hw_perf_counter_read(info);
+ struct perf_counter *counter = info;
+
+ counter->hw_ops->hw_perf_counter_read(counter);
}
-static u64 perf_read_counter(struct perf_counter *counter)
+static u64 perf_counter_read(struct perf_counter *counter)
{
/*
* If counter is enabled and currently active on a CPU, update the
__hw_perf_counter_read, counter, 1);
}
- return perf_read_counter_safe(counter);
+ return perf_counter_read_safe(counter);
}
/*
mutex_lock(&counter->mutex);
- perf_remove_from_context(counter);
+ perf_counter_remove_from_context(counter);
put_context(ctx);
mutex_unlock(&counter->mutex);
return -EINVAL;
mutex_lock(&counter->mutex);
- cntval = perf_read_counter(counter);
+ cntval = perf_counter_read(counter);
mutex_unlock(&counter->mutex);
return put_user(cntval, (u64 __user *) buf) ? -EFAULT : sizeof(cntval);
{
struct perf_counter *counter = file->private_data;
- switch (counter->record_type) {
+ switch (counter->hw_event.record_type) {
case PERF_RECORD_SIMPLE:
return perf_read_hw(counter, buf, count);
.poll = perf_poll,
};
+static void cpu_clock_perf_counter_enable(struct perf_counter *counter)
+{
+}
+
+static void cpu_clock_perf_counter_disable(struct perf_counter *counter)
+{
+}
+
+static void cpu_clock_perf_counter_read(struct perf_counter *counter)
+{
+ int cpu = raw_smp_processor_id();
+
+ atomic64_counter_set(counter, cpu_clock(cpu));
+}
+
+static const struct hw_perf_counter_ops perf_ops_cpu_clock = {
+ .hw_perf_counter_enable = cpu_clock_perf_counter_enable,
+ .hw_perf_counter_disable = cpu_clock_perf_counter_disable,
+ .hw_perf_counter_read = cpu_clock_perf_counter_read,
+};
+
+static const struct hw_perf_counter_ops *
+sw_perf_counter_init(struct perf_counter *counter)
+{
+ const struct hw_perf_counter_ops *hw_ops = NULL;
+
+ switch (counter->hw_event.type) {
+ case PERF_COUNT_CPU_CLOCK:
+ hw_ops = &perf_ops_cpu_clock;
+ break;
+ default:
+ break;
+ }
+ return hw_ops;
+}
+
/*
* Allocate and initialize a counter structure
*/
static struct perf_counter *
-perf_counter_alloc(u32 hw_event_period, int cpu, u32 record_type)
+perf_counter_alloc(struct perf_counter_hw_event *hw_event,
+ int cpu,
+ struct perf_counter *group_leader)
{
- struct perf_counter *counter = kzalloc(sizeof(*counter), GFP_KERNEL);
+ const struct hw_perf_counter_ops *hw_ops;
+ struct perf_counter *counter;
+ counter = kzalloc(sizeof(*counter), GFP_KERNEL);
if (!counter)
return NULL;
+ /*
+ * Single counters are their own group leaders, with an
+ * empty sibling list:
+ */
+ if (!group_leader)
+ group_leader = counter;
+
mutex_init(&counter->mutex);
- INIT_LIST_HEAD(&counter->list);
+ INIT_LIST_HEAD(&counter->list_entry);
+ INIT_LIST_HEAD(&counter->sibling_list);
init_waitqueue_head(&counter->waitq);
- counter->irqdata = &counter->data[0];
- counter->usrdata = &counter->data[1];
- counter->cpu = cpu;
- counter->record_type = record_type;
- counter->__irq_period = hw_event_period;
- counter->wakeup_pending = 0;
+ counter->irqdata = &counter->data[0];
+ counter->usrdata = &counter->data[1];
+ counter->cpu = cpu;
+ counter->hw_event = *hw_event;
+ counter->wakeup_pending = 0;
+ counter->group_leader = group_leader;
+ counter->hw_ops = NULL;
+
+ hw_ops = NULL;
+ if (!hw_event->raw && hw_event->type < 0)
+ hw_ops = sw_perf_counter_init(counter);
+ if (!hw_ops) {
+ hw_ops = hw_perf_counter_init(counter);
+ }
+
+ if (!hw_ops) {
+ kfree(counter);
+ return NULL;
+ }
+ counter->hw_ops = hw_ops;
return counter;
}
/**
- * sys_perf_task_open - open a performance counter associate it to a task
- * @hw_event_type: event type for monitoring/sampling...
+ * sys_perf_task_open - open a performance counter, associate it to a task/cpu
+ *
+ * @hw_event_uptr: event type attributes for monitoring/sampling
* @pid: target pid
+ * @cpu: target cpu
+ * @group_fd: group leader counter fd
*/
-asmlinkage int
-sys_perf_counter_open(u32 hw_event_type,
- u32 hw_event_period,
- u32 record_type,
- pid_t pid,
- int cpu)
+asmlinkage int sys_perf_counter_open(
+
+ struct perf_counter_hw_event *hw_event_uptr __user,
+ pid_t pid,
+ int cpu,
+ int group_fd)
+
{
+ struct perf_counter *counter, *group_leader;
+ struct perf_counter_hw_event hw_event;
struct perf_counter_context *ctx;
- struct perf_counter *counter;
+ struct file *group_file = NULL;
+ int fput_needed = 0;
int ret;
+ if (copy_from_user(&hw_event, hw_event_uptr, sizeof(hw_event)) != 0)
+ return -EFAULT;
+
+ /*
+ * Get the target context (task or percpu):
+ */
ctx = find_get_context(pid, cpu);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
- ret = -ENOMEM;
- counter = perf_counter_alloc(hw_event_period, cpu, record_type);
+ /*
+ * Look up the group leader (we will attach this counter to it):
+ */
+ group_leader = NULL;
+ if (group_fd != -1) {
+ ret = -EINVAL;
+ group_file = fget_light(group_fd, &fput_needed);
+ if (!group_file)
+ goto err_put_context;
+ if (group_file->f_op != &perf_fops)
+ goto err_put_context;
+
+ group_leader = group_file->private_data;
+ /*
+ * Do not allow a recursive hierarchy (this new sibling
+ * becoming part of another group-sibling):
+ */
+ if (group_leader->group_leader != group_leader)
+ goto err_put_context;
+ /*
+ * Do not allow to attach to a group in a different
+ * task or CPU context:
+ */
+ if (group_leader->ctx != ctx)
+ goto err_put_context;
+ }
+
+ ret = -EINVAL;
+ counter = perf_counter_alloc(&hw_event, cpu, group_leader);
if (!counter)
goto err_put_context;
- ret = hw_perf_counter_init(counter, hw_event_type);
- if (ret)
- goto err_free_put_context;
-
perf_install_in_context(ctx, counter, cpu);
ret = anon_inode_getfd("[perf_counter]", &perf_fops, counter, 0);
if (ret < 0)
goto err_remove_free_put_context;
+out_fput:
+ fput_light(group_file, fput_needed);
+
return ret;
err_remove_free_put_context:
mutex_lock(&counter->mutex);
- perf_remove_from_context(counter);
+ perf_counter_remove_from_context(counter);
mutex_unlock(&counter->mutex);
-
-err_free_put_context:
kfree(counter);
err_put_context:
put_context(ctx);
- return ret;
+ goto out_fput;
}
-static void __cpuinit perf_init_cpu(int cpu)
+static void __cpuinit perf_counter_init_cpu(int cpu)
{
- struct perf_cpu_context *ctx;
+ struct perf_cpu_context *cpuctx;
- ctx = &per_cpu(perf_cpu_context, cpu);
- spin_lock_init(&ctx->ctx.lock);
- INIT_LIST_HEAD(&ctx->ctx.counters);
+ cpuctx = &per_cpu(perf_cpu_context, cpu);
+ __perf_counter_init_context(&cpuctx->ctx, NULL);
mutex_lock(&perf_resource_mutex);
- ctx->max_pertask = perf_max_counters - perf_reserved_percpu;
+ cpuctx->max_pertask = perf_max_counters - perf_reserved_percpu;
mutex_unlock(&perf_resource_mutex);
+
hw_perf_counter_setup();
}
#ifdef CONFIG_HOTPLUG_CPU
-static void __perf_exit_cpu(void *info)
+static void __perf_counter_exit_cpu(void *info)
{
struct perf_cpu_context *cpuctx = &__get_cpu_var(perf_cpu_context);
struct perf_counter_context *ctx = &cpuctx->ctx;
struct perf_counter *counter, *tmp;
- list_for_each_entry_safe(counter, tmp, &ctx->counters, list)
- __perf_remove_from_context(counter);
+ list_for_each_entry_safe(counter, tmp, &ctx->counter_list, list_entry)
+ __perf_counter_remove_from_context(counter);
}
-static void perf_exit_cpu(int cpu)
+static void perf_counter_exit_cpu(int cpu)
{
- smp_call_function_single(cpu, __perf_exit_cpu, NULL, 1);
+ smp_call_function_single(cpu, __perf_counter_exit_cpu, NULL, 1);
}
#else
-static inline void perf_exit_cpu(int cpu) { }
+static inline void perf_counter_exit_cpu(int cpu) { }
#endif
static int __cpuinit
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
- perf_init_cpu(cpu);
+ perf_counter_init_cpu(cpu);
break;
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
- perf_exit_cpu(cpu);
+ perf_counter_exit_cpu(cpu);
break;
default:
projects / deliverable / linux.git / blobdiff