[PATCH v3 07/23] perf: Add api for pmus to write to AUX space
From: Alexander Shishkin
Date: Mon Aug 11 2014 - 01:29:25 EST
For pmus that wish to write data to AUX space, provide
perf_aux_output_{begin,end}() calls to initiate/commit data writes,
similarly to perf_output_{begin,end}. These also use the same output
handle structure.
After the perf_aux_output_begin() returns successfully, handle->size
is set to the maximum amount of data that can be written wrt aux_tail
pointer, so that no data that the user hasn't seen will be overwritten.
PMU driver should pass the actual amount of data written as a parameter
to perf_aux_output_end().
Nested writers are forbidden and guards are in place to catch such
attempts.
Signed-off-by: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
---
include/linux/perf_event.h | 23 ++++++++++++-
kernel/events/core.c | 5 ++-
kernel/events/internal.h | 4 +++
kernel/events/ring_buffer.c | 81 +++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 109 insertions(+), 4 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b8902ebcb7..94961c73e0 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -550,12 +550,22 @@ struct perf_output_handle {
struct ring_buffer *rb;
unsigned long wakeup;
unsigned long size;
- void *addr;
+ union {
+ void *addr;
+ unsigned long head;
+ };
int page;
};
#ifdef CONFIG_PERF_EVENTS
+extern void *perf_aux_output_begin(struct perf_output_handle *handle,
+ struct perf_event *event);
+extern void perf_aux_output_end(struct perf_output_handle *handle,
+ unsigned long size, bool truncated);
+extern int perf_aux_output_skip(struct perf_output_handle *handle,
+ unsigned long size);
+extern void *perf_get_aux(struct perf_output_handle *handle);
extern int perf_pmu_register(struct pmu *pmu, const char *name, int type);
extern void perf_pmu_unregister(struct pmu *pmu);
@@ -805,6 +815,17 @@ extern void perf_event_disable(struct perf_event *event);
extern int __perf_event_disable(void *info);
extern void perf_event_task_tick(void);
#else /* !CONFIG_PERF_EVENTS: */
+static inline void *
+perf_aux_output_begin(struct perf_output_handle *handle,
+ struct perf_event *event) { return NULL; }
+static inline void
+perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
+ bool truncated) { }
+static inline int
+perf_aux_output_skip(struct perf_output_handle *handle,
+ unsigned long size) { return -EINVAL; }
+static inline void *
+perf_get_aux(struct perf_output_handle *handle) { return NULL; }
static inline void
perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task) { }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 55cd524564..848f2af576 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3212,7 +3212,6 @@ static void free_event_rcu(struct rcu_head *head)
kfree(event);
}
-static void ring_buffer_put(struct ring_buffer *rb);
static void ring_buffer_attach(struct perf_event *event,
struct ring_buffer *rb);
@@ -3948,7 +3947,7 @@ static void rb_free_rcu(struct rcu_head *rcu_head)
rb_free(rb);
}
-static struct ring_buffer *ring_buffer_get(struct perf_event *event)
+struct ring_buffer *ring_buffer_get(struct perf_event *event)
{
struct ring_buffer *rb;
@@ -3963,7 +3962,7 @@ static struct ring_buffer *ring_buffer_get(struct perf_event *event)
return rb;
}
-static void ring_buffer_put(struct ring_buffer *rb)
+void ring_buffer_put(struct ring_buffer *rb)
{
if (!atomic_dec_and_test(&rb->refcount))
return;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index e5374030b1..b8f6c193ea 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -36,6 +36,8 @@ struct ring_buffer {
struct user_struct *mmap_user;
/* AUX area */
+ local_t aux_head;
+ local_t aux_nest;
unsigned long aux_pgoff;
int aux_nr_pages;
atomic_t aux_mmap_count;
@@ -54,6 +56,8 @@ extern void perf_event_wakeup(struct perf_event *event);
extern int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
pgoff_t pgoff, int nr_pages, int flags);
extern void rb_free_aux(struct ring_buffer *rb, struct perf_event *event);
+extern struct ring_buffer *ring_buffer_get(struct perf_event *event);
+extern void ring_buffer_put(struct ring_buffer *rb);
static inline bool rb_has_aux(struct ring_buffer *rb)
{
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index f5ee3669f8..feee52077f 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -242,6 +242,87 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
spin_lock_init(&rb->event_lock);
}
+void *perf_aux_output_begin(struct perf_output_handle *handle,
+ struct perf_event *event)
+{
+ unsigned long aux_head, aux_tail;
+ struct ring_buffer *rb;
+
+ rb = ring_buffer_get(event);
+ if (!rb)
+ return NULL;
+
+ if (!rb_has_aux(rb))
+ goto err;
+
+ /*
+ * Nesting is not supported for AUX area, make sure nested
+ * writers are caught early
+ */
+ if (WARN_ON_ONCE(local_xchg(&rb->aux_nest, 1)))
+ goto err;
+
+ aux_head = local_read(&rb->aux_head);
+ aux_tail = ACCESS_ONCE(rb->user_page->aux_tail);
+
+ handle->rb = rb;
+ handle->event = event;
+ handle->head = aux_head;
+ handle->size = CIRC_SPACE(aux_head, aux_tail, perf_aux_size(rb));
+
+ if (!handle->size) {
+ event->pending_disable = 1;
+ event->hw.state = PERF_HES_STOPPED;
+ perf_output_wakeup(handle);
+ local_set(&rb->aux_nest, 0);
+ goto err;
+ }
+
+ return handle->rb->aux_priv;
+
+err:
+ ring_buffer_put(rb);
+ handle->event = NULL;
+
+ return NULL;
+}
+
+void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
+ bool truncated)
+{
+ struct ring_buffer *rb = handle->rb;
+
+ local_add(size, &rb->aux_head);
+
+ smp_wmb();
+ rb->user_page->aux_head = local_read(&rb->aux_head);
+
+ perf_output_wakeup(handle);
+ handle->event = NULL;
+
+ local_set(&rb->aux_nest, 0);
+ ring_buffer_put(rb);
+}
+
+int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size)
+{
+ struct ring_buffer *rb = handle->rb;
+
+ if (size > handle->size)
+ return -ENOSPC;
+
+ local_add(size, &rb->aux_head);
+ handle->head = local_read(&rb->aux_head);
+ handle->size -= size;
+
+ return 0;
+}
+
+void *perf_get_aux(struct perf_output_handle *handle)
+{
+ return handle->rb->aux_priv;
+}
+
#define PERF_AUX_GFP (GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY)
static struct page *rb_alloc_aux_page(int node, int order)
--
2.1.0.rc1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/