perf: Add AUX area to ring buffer for raw data streams

This patch introduces "AUX space" in the perf mmap buffer, intended for
exporting high bandwidth data streams to userspace, such as instruction
flow traces.

AUX space is a ring buffer, defined by aux_{offset,size} fields in the
user_page structure, and read/write pointers aux_{head,tail}, which abide
by the same rules as data_* counterparts of the main perf buffer.

In order to allocate/mmap AUX, userspace needs to set up aux_offset to
such an offset that will be greater than data_offset+data_size and
aux_size to be the desired buffer size. Both need to be page aligned.
Then, same aux_offset and aux_size should be passed to mmap() call and
if everything adds up, you should have an AUX buffer as a result.

Pages that are mapped into this buffer also come out of user's mlock
rlimit plus perf_event_mlock_kb allowance.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kaixu Xia <kaixu.xia@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Robert Richter <rric@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@infradead.org
Cc: adrian.hunter@intel.com
Cc: kan.liang@intel.com
Cc: markus.t.metzger@intel.com
Cc: mathieu.poirier@linaro.org
Link: http://lkml.kernel.org/r/1421237903-181015-3-git-send-email-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 116 insertions, 25 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6efa516f1ab8..da51128c337a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4306,6 +4306,9 @@ static void perf_mmap_open(struct vm_area_struct *vma)
 	atomic_inc(&event->mmap_count);
 	atomic_inc(&event->rb->mmap_count);
 
+	if (vma->vm_pgoff)
+		atomic_inc(&event->rb->aux_mmap_count);
+
 	if (event->pmu->event_mapped)
 		event->pmu->event_mapped(event);
 }
@@ -4330,6 +4333,20 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 	if (event->pmu->event_unmapped)
 		event->pmu->event_unmapped(event);
 
+	/*
+	 * rb->aux_mmap_count will always drop before rb->mmap_count and
+	 * event->mmap_count, so it is ok to use event->mmap_mutex to
+	 * serialize with perf_mmap here.
+	 */
+	if (rb_has_aux(rb) && vma->vm_pgoff == rb->aux_pgoff &&
+	    atomic_dec_and_mutex_lock(&rb->aux_mmap_count, &event->mmap_mutex)) {
+		atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm);
+		vma->vm_mm->pinned_vm -= rb->aux_mmap_locked;
+
+		rb_free_aux(rb);
+		mutex_unlock(&event->mmap_mutex);
+	}
+
 	atomic_dec(&rb->mmap_count);
 
 	if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex))
@@ -4403,7 +4420,7 @@ out_put:
 
 static const struct vm_operations_struct perf_mmap_vmops = {
 	.open		= perf_mmap_open,
-	.close		= perf_mmap_close,
+	.close		= perf_mmap_close, /* non mergable */
 	.fault		= perf_mmap_fault,
 	.page_mkwrite	= perf_mmap_fault,
 };
@@ -4414,10 +4431,10 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	unsigned long user_locked, user_lock_limit;
 	struct user_struct *user = current_user();
 	unsigned long locked, lock_limit;
-	struct ring_buffer *rb;
+	struct ring_buffer *rb = NULL;
 	unsigned long vma_size;
 	unsigned long nr_pages;
-	long user_extra, extra;
+	long user_extra = 0, extra = 0;
 	int ret = 0, flags = 0;
 
 	/*
@@ -4432,7 +4449,66 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		return -EINVAL;
 
 	vma_size = vma->vm_end - vma->vm_start;
-	nr_pages = (vma_size / PAGE_SIZE) - 1;
+
+	if (vma->vm_pgoff == 0) {
+		nr_pages = (vma_size / PAGE_SIZE) - 1;
+	} else {
+		/*
+		 * AUX area mapping: if rb->aux_nr_pages != 0, it's already
+		 * mapped, all subsequent mappings should have the same size
+		 * and offset. Must be above the normal perf buffer.
+		 */
+		u64 aux_offset, aux_size;
+
+		if (!event->rb)
+			return -EINVAL;
+
+		nr_pages = vma_size / PAGE_SIZE;
+
+		mutex_lock(&event->mmap_mutex);
+		ret = -EINVAL;
+
+		rb = event->rb;
+		if (!rb)
+			goto aux_unlock;
+
+		aux_offset = ACCESS_ONCE(rb->user_page->aux_offset);
+		aux_size = ACCESS_ONCE(rb->user_page->aux_size);
+
+		if (aux_offset < perf_data_size(rb) + PAGE_SIZE)
+			goto aux_unlock;
+
+		if (aux_offset != vma->vm_pgoff << PAGE_SHIFT)
+			goto aux_unlock;
+
+		/* already mapped with a different offset */
+		if (rb_has_aux(rb) && rb->aux_pgoff != vma->vm_pgoff)
+			goto aux_unlock;
+
+		if (aux_size != vma_size || aux_size != nr_pages * PAGE_SIZE)
+			goto aux_unlock;
+
+		/* already mapped with a different size */
+		if (rb_has_aux(rb) && rb->aux_nr_pages != nr_pages)
+			goto aux_unlock;
+
+		if (!is_power_of_2(nr_pages))
+			goto aux_unlock;
+
+		if (!atomic_inc_not_zero(&rb->mmap_count))
+			goto aux_unlock;
+
+		if (rb_has_aux(rb)) {
+			atomic_inc(&rb->aux_mmap_count);
+			ret = 0;
+			goto unlock;
+		}
+
+		atomic_set(&rb->aux_mmap_count, 1);
+		user_extra = nr_pages;
+
+		goto accounting;
+	}
 
 	/*
 	 * If we have rb pages ensure they're a power-of-two number, so we
@@ -4444,9 +4520,6 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	if (vma_size != PAGE_SIZE * (1 + nr_pages))
 		return -EINVAL;
 
-	if (vma->vm_pgoff != 0)
-		return -EINVAL;
-
 	WARN_ON_ONCE(event->ctx->parent_ctx);
 again:
 	mutex_lock(&event->mmap_mutex);
@@ -4470,6 +4543,8 @@ again:
 	}
 
 	user_extra = nr_pages + 1;
+
+accounting:
 	user_lock_limit = sysctl_perf_event_mlock >> (PAGE_SHIFT - 10);
 
 	/*
@@ -4479,7 +4554,6 @@ again:
 
 	user_locked = atomic_long_read(&user->locked_vm) + user_extra;
 
-	extra = 0;
 	if (user_locked > user_lock_limit)
 		extra = user_locked - user_lock_limit;
 
@@ -4493,35 +4567,45 @@ again:
 		goto unlock;
 	}
 
-	WARN_ON(event->rb);
+	WARN_ON(!rb && event->rb);
 
 	if (vma->vm_flags & VM_WRITE)
 		flags |= RING_BUFFER_WRITABLE;
 
-	rb = rb_alloc(nr_pages, 
-		event->attr.watermark ? event->attr.wakeup_watermark : 0,
-		event->cpu, flags);
-
 	if (!rb) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+		rb = rb_alloc(nr_pages,
+			      event->attr.watermark ? event->attr.wakeup_watermark : 0,
+			      event->cpu, flags);
 
-	atomic_set(&rb->mmap_count, 1);
-	rb->mmap_locked = extra;
-	rb->mmap_user = get_current_user();
+		if (!rb) {
+			ret = -ENOMEM;
+			goto unlock;
+		}
 
-	atomic_long_add(user_extra, &user->locked_vm);
-	vma->vm_mm->pinned_vm += extra;
+		atomic_set(&rb->mmap_count, 1);
+		rb->mmap_user = get_current_user();
+		rb->mmap_locked = extra;
 
-	ring_buffer_attach(event, rb);
+		ring_buffer_attach(event, rb);
 
-	perf_event_init_userpage(event);
-	perf_event_update_userpage(event);
+		perf_event_init_userpage(event);
+		perf_event_update_userpage(event);
+	} else {
+		ret = rb_alloc_aux(rb, event, vma->vm_pgoff, nr_pages, flags);
+		if (!ret)
+			rb->aux_mmap_locked = extra;
+	}
 
 unlock:
-	if (!ret)
+	if (!ret) {
+		atomic_long_add(user_extra, &user->locked_vm);
+		vma->vm_mm->pinned_vm += extra;
+
 		atomic_inc(&event->mmap_count);
+	} else if (rb) {
+		atomic_dec(&rb->mmap_count);
+	}
+aux_unlock:
 	mutex_unlock(&event->mmap_mutex);
 
 	/*
@@ -7506,6 +7590,13 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
 	if (output_event->clock != event->clock)
 		goto out;
 
+	/*
+	 * If both events generate aux data, they must be on the same PMU
+	 */
+	if (has_aux(event) && has_aux(output_event) &&
+	    event->pmu != output_event->pmu)
+		goto out;
+
 set:
 	mutex_lock(&event->mmap_mutex);
 	/* Can't redirect output if we've got an active mmap() */