[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20230212153250.1099136-3-vdonnefort@google.com>
Date: Sun, 12 Feb 2023 15:32:50 +0000
From: Vincent Donnefort <vdonnefort@...gle.com>
To: rostedt@...dmis.org, mhiramat@...nel.org,
linux-kernel@...r.kernel.org, linux-trace-kernel@...r.kernel.org
Cc: kernel-team@...roid.com, Vincent Donnefort <vdonnefort@...gle.com>
Subject: [RFC PATCH 2/2] tracing: Allow user-space mapping of the ring-buffer
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 not possible 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 exposed via the per-CPU file trace_pipe_raw. The first page
is the meta-page and is followed by each page of the ring-buffer,
ordered by their unique page ID. It is therefore easy to translate a
page-ID to an offset into the mapping.
* Meta-page -- include/uapi/linux/trace_mmap.h for a description
* Page ID 0
* Page ID 1
...
The mapper must then do what use to be the kernel jobs: swap the reader
with the head. This is done with a newly introduced ioctl:
TRACE_MMAP_IOCTL_GET_READER_PAGE.
To avoid putting to much work on the writer, the meta-page is not
automatically updated. User-space must query an update before reading
with another ioctl: TRACE_MMAP_IOCTL_UPDATE_META_PAGE.
Signed-off-by: Vincent Donnefort <vdonnefort@...gle.com>
diff --git a/include/uapi/linux/trace_mmap.h b/include/uapi/linux/trace_mmap.h
index 0f3282fa1a94..fe3bbe02e571 100644
--- a/include/uapi/linux/trace_mmap.h
+++ b/include/uapi/linux/trace_mmap.h
@@ -11,4 +11,7 @@ struct ring_buffer_meta_page {
__u32 data_pages[];
};
+#define TRACE_MMAP_IOCTL_GET_READER_PAGE _IO('T', 0x1)
+#define TRACE_MMAP_IOCTL_UPDATE_META_PAGE _IO('T', 0x2)
+
#endif /* _UAPI_TRACE_MMAP_H_ */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 78ed5f1baa8c..e7d999499dde 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6351,7 +6351,7 @@ 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)
@@ -8384,15 +8384,27 @@ 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;
+ switch (cmd) {
+ case TRACE_MMAP_IOCTL_GET_READER_PAGE:
+ return ring_buffer_get_reader_page(iter->array_buffer->buffer,
+ iter->cpu_file);
+ case TRACE_MMAP_IOCTL_UPDATE_META_PAGE:
+ return ring_buffer_update_meta_page(iter->array_buffer->buffer,
+ iter->cpu_file);
+ }
+
if (cmd)
- return -ENOIOCTLCMD;
+ 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++;
@@ -8405,6 +8417,61 @@ 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;
+
+ return 0;
+}
+
+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);
+}
+
+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;
+
+ if (vma->vm_flags & VM_WRITE)
+ return -EPERM;
+
+ vma->vm_flags |= VM_DONTCOPY | VM_DONTDUMP;
+ vma->vm_flags &= ~VM_MAYWRITE;
+ vma->vm_ops = &tracing_buffers_vmops;
+
+ return ring_buffer_map(iter->array_buffer->buffer, iter->cpu_file);
+}
+
static const struct file_operations tracing_buffers_fops = {
.open = tracing_buffers_open,
.read = tracing_buffers_read,
@@ -8413,6 +8480,7 @@ 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
--
2.39.1.581.gbfd45094c4-goog
Powered by blists - more mailing lists