Currently, user-space extracts data from the ring-buffer via splice,
which is handy for storage or network sharing. However, due to splice
limitations, it is imposible to do real-time analysis without a copy.
A solution for that problem is to let the user-space map the ring-buffer
directly.
The mapping is exposed via the per-CPU file trace_pipe_raw. The first
element of the mapping is the meta-page. It is followed by each
subbuffer constituting the ring-buffer, ordered by their unique page ID:
* Meta-page -- include/uapi/linux/trace_mmap.h for a description
* Subbuf ID 0
* Subbuf ID 1
...
It is therefore easy to translate a subbuf ID into an offset in the
mapping:
reader_id = meta->reader->id;
reader_offset = meta->meta_page_size + reader_id * meta->subbuf_size;
When new data is available, the mapper must call a newly introduced ioctl:
TRACE_MMAP_IOCTL_GET_READER. This will update the Meta-page reader ID to
point to the next reader containing unread data.
Mapping will prevent snapshot and buffer size modifications.
Signed-off-by: Vincent Donnefort <vdonnef...@google.com>
diff --git a/include/uapi/linux/trace_mmap.h b/include/uapi/linux/trace_mmap.h
index ffcd8dfcaa4f..d25b9d504a7c 100644
--- a/include/uapi/linux/trace_mmap.h
+++ b/include/uapi/linux/trace_mmap.h
@@ -43,4 +43,6 @@ struct trace_buffer_meta {
__u64 Reserved2;
};
+#define TRACE_MMAP_IOCTL_GET_READER _IO('T', 0x1)
+
#endif /* _TRACE_MMAP_H_ */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8ae7c2cb63a0..67ce7b367edb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1176,6 +1176,12 @@ static void tracing_snapshot_instance_cond(struct
trace_array *tr,
return;
}
+ if (tr->mapped) {
+ trace_array_puts(tr, "*** BUFFER MEMORY MAPPED ***\n");
+ trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n");
+ return;
+ }
+
local_irq_save(flags);
update_max_tr(tr, current, smp_processor_id(), cond_data);
local_irq_restore(flags);
@@ -1308,7 +1314,7 @@ static int tracing_arm_snapshot_locked(struct trace_array
*tr)
lockdep_assert_held(&trace_types_lock);
spin_lock(&tr->snapshot_trigger_lock);
- if (tr->snapshot == UINT_MAX) {
+ if (tr->snapshot == UINT_MAX || tr->mapped) {
spin_unlock(&tr->snapshot_trigger_lock);
return -EBUSY;
}
@@ -6535,7 +6541,7 @@ static void tracing_set_nop(struct trace_array *tr)
{
if (tr->current_trace == &nop_trace)
return;
-
+
tr->current_trace->enabled--;
if (tr->current_trace->reset)
@@ -8654,15 +8660,31 @@ tracing_buffers_splice_read(struct file *file, loff_t
*ppos,
return ret;
}
-/* An ioctl call with cmd 0 to the ring buffer file will wake up all waiters */
static long tracing_buffers_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
struct ftrace_buffer_info *info = file->private_data;
struct trace_iterator *iter = &info->iter;
+ int err;
- if (cmd)
- return -ENOIOCTLCMD;
+ if (cmd == TRACE_MMAP_IOCTL_GET_READER) {
+ if (!(file->f_flags & O_NONBLOCK)) {
+ err = ring_buffer_wait(iter->array_buffer->buffer,
+ iter->cpu_file,
+ iter->tr->buffer_percent);
+ if (err)
+ return err;
+ }
+ return ring_buffer_map_get_reader(iter->array_buffer->buffer,
+ iter->cpu_file);
+ } else if (cmd) {
+ return -ENOTTY;
+ }
+
+ /*
+ * An ioctl call with cmd 0 to the ring buffer file will wake up all
+ * waiters
+ */
mutex_lock(&trace_types_lock);
iter->wait_index++;
@@ -8675,6 +8697,110 @@ static long tracing_buffers_ioctl(struct file *file,
unsigned int cmd, unsigned
return 0;
}
+static vm_fault_t tracing_buffers_mmap_fault(struct vm_fault *vmf)
+{
+ struct ftrace_buffer_info *info = vmf->vma->vm_file->private_data;
+ struct trace_iterator *iter = &info->iter;
+ vm_fault_t ret = VM_FAULT_SIGBUS;
+ struct page *page;
+
+ page = ring_buffer_map_fault(iter->array_buffer->buffer, iter->cpu_file,
+ vmf->pgoff);
+ if (!page)
+ return ret;
+
+ get_page(page);
+ vmf->page = page;
+ vmf->page->mapping = vmf->vma->vm_file->f_mapping;
+ vmf->page->index = vmf->pgoff;
+
+ return 0;
+}
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+static int get_snapshot_map(struct trace_array *tr)
+{
+ int err = 0;
+
+ /*
+ * Called with mmap_lock held. lockdep would be unhappy if we would now
+ * take trace_types_lock. Instead use the specific
+ * snapshot_trigger_lock.
+ */
+ spin_lock(&tr->snapshot_trigger_lock);
+
+ if (tr->snapshot || tr->mapped == UINT_MAX)
+ err = -EBUSY;
+ else
+ tr->mapped++;
+
+ spin_unlock(&tr->snapshot_trigger_lock);
+
+ /* Wait for update_max_tr() to observe iter->tr->mapped */
+ if (tr->mapped == 1)
+ synchronize_rcu();
+
+ return err;
+
+}
+static void put_snapshot_map(struct trace_array *tr)
+{
+ spin_lock(&tr->snapshot_trigger_lock);
+ if (!WARN_ON(!tr->mapped))
+ tr->mapped--;
+ spin_unlock(&tr->snapshot_trigger_lock);
+}
+#else
+static inline int get_snapshot_map(struct trace_array *tr) { return 0; }
+static inline void put_snapshot_map(struct trace_array *tr) { }
+#endif
+
+static void tracing_buffers_mmap_close(struct vm_area_struct *vma)
+{
+ struct ftrace_buffer_info *info = vma->vm_file->private_data;
+ struct trace_iterator *iter = &info->iter;
+
+ ring_buffer_unmap(iter->array_buffer->buffer, iter->cpu_file);
+ put_snapshot_map(iter->tr);
+}
+
+static void tracing_buffers_mmap_open(struct vm_area_struct *vma)
+{
+ struct ftrace_buffer_info *info = vma->vm_file->private_data;
+ struct trace_iterator *iter = &info->iter;
+
+ WARN_ON(ring_buffer_map(iter->array_buffer->buffer, iter->cpu_file));
+}
+
+static const struct vm_operations_struct tracing_buffers_vmops = {
+ .open = tracing_buffers_mmap_open,
+ .close = tracing_buffers_mmap_close,
+ .fault = tracing_buffers_mmap_fault,
+};
+
+static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+ struct ftrace_buffer_info *info = filp->private_data;
+ struct trace_iterator *iter = &info->iter;
+ int ret = 0;
+
+ if (vma->vm_flags & VM_WRITE || vma->vm_flags & VM_EXEC)
+ return -EPERM;
+
+ vm_flags_mod(vma, VM_DONTCOPY | VM_DONTDUMP, VM_MAYWRITE);
+ vma->vm_ops = &tracing_buffers_vmops;
+
+ ret = get_snapshot_map(iter->tr);
+ if (ret)
+ return ret;
+
+ ret = ring_buffer_map(iter->array_buffer->buffer, iter->cpu_file);
+ if (ret)
+ put_snapshot_map(iter->tr);
+
+ return ret;
+}
+
static const struct file_operations tracing_buffers_fops = {
.open = tracing_buffers_open,
.read = tracing_buffers_read,
@@ -8683,6 +8809,7 @@ static const struct file_operations tracing_buffers_fops
= {
.splice_read = tracing_buffers_splice_read,
.unlocked_ioctl = tracing_buffers_ioctl,
.llseek = no_llseek,
+ .mmap = tracing_buffers_mmap,
};
static ssize_t
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index bd312e9afe25..8a96e7a89e6b 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -336,6 +336,7 @@ struct trace_array {
bool allocated_snapshot;
spinlock_t snapshot_trigger_lock;
unsigned int snapshot;
+ unsigned int mapped;
unsigned long max_latency;
#ifdef CONFIG_FSNOTIFY
struct dentry *d_max_latency;
--
2.44.0.rc0.258.g7320e95886-goog
