diff mbox series

[v2,01/11] ring-buffer: Allow mapped field to be set without mapping

Message ID 20240411012904.237435058@goodmis.org (mailing list archive)
State Superseded
Headers show
Series tracing: Persistent traces across a reboot or crash | expand

Commit Message

Steven Rostedt April 11, 2024, 1:25 a.m. UTC
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>

In preparation for having the ring buffer mapped to a dedicated location,
which will have the same restrictions as user space memory mapped buffers,
allow it to use the "mapped" field of the ring_buffer_per_cpu structure
without having the user space meta page mapping.

When this starts using the mapped field, it will need to handle adding a
user space mapping (and removing it) from a ring buffer that is using a
dedicated memory range.

Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

Comments

Vincent Donnefort April 12, 2024, 2:47 p.m. UTC | #1
On Wed, Apr 10, 2024 at 09:25:42PM -0400, Steven Rostedt wrote:
> From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
> 
> In preparation for having the ring buffer mapped to a dedicated location,
> which will have the same restrictions as user space memory mapped buffers,
> allow it to use the "mapped" field of the ring_buffer_per_cpu structure
> without having the user space meta page mapping.
> 
> When this starts using the mapped field, it will need to handle adding a
> user space mapping (and removing it) from a ring buffer that is using a
> dedicated memory range.
> 
> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
> ---
>  kernel/trace/ring_buffer.c | 10 +++++++---
>  1 file changed, 7 insertions(+), 3 deletions(-)
> 
> diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
> index 793ecc454039..44b1d5f1a99a 100644
> --- a/kernel/trace/ring_buffer.c
> +++ b/kernel/trace/ring_buffer.c
> @@ -5223,6 +5223,9 @@ static void rb_update_meta_page(struct ring_buffer_per_cpu *cpu_buffer)
>  {
>  	struct trace_buffer_meta *meta = cpu_buffer->meta_page;
>  
> +	if (!meta)
> +		return;
> +
>  	meta->reader.read = cpu_buffer->reader_page->read;
>  	meta->reader.id = cpu_buffer->reader_page->id;
>  	meta->reader.lost_events = cpu_buffer->lost_events;
> @@ -6167,7 +6170,7 @@ rb_get_mapped_buffer(struct trace_buffer *buffer, int cpu)
>  
>  	mutex_lock(&cpu_buffer->mapping_lock);
>  
> -	if (!cpu_buffer->mapped) {
> +	if (!cpu_buffer->mapped || !cpu_buffer->meta_page) {
>  		mutex_unlock(&cpu_buffer->mapping_lock);
>  		return ERR_PTR(-ENODEV);
>  	}
> @@ -6345,12 +6348,13 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,

IIUC, we still allow to map from user-space this buffer. So we now can have
mapped && !meta_page.

Then the "if (cpu_buffer->mapped) {" that skips the meta_page creation in
ring_buffer_map() should be replaced by if (cpu_buffer->meta_page).

>  	 */
>  	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
>  	rb_setup_ids_meta_page(cpu_buffer, subbuf_ids);
> +
>  	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
>  
>  	err = __rb_map_vma(cpu_buffer, vma);
>  	if (!err) {
>  		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
> -		cpu_buffer->mapped = 1;
> +		cpu_buffer->mapped++;
>  		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
>  	} else {
>  		kfree(cpu_buffer->subbuf_ids);
> @@ -6388,7 +6392,7 @@ int ring_buffer_unmap(struct trace_buffer *buffer, int cpu)
>  	mutex_lock(&buffer->mutex);
>  	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);

In this function, there's also a check for cpu_buffer->mapped > 1. This avoids
killing the meta-page while someone is still in use.

It seems like a dedicated meta_page counter will be necessary. Otherwise, in the
event of a ring-buffer mapped at boot we, would setup the meta-page on the first
mmap() and never tear it down.

>  
> -	cpu_buffer->mapped = 0;
> +	cpu_buffer->mapped--;
>  
>  	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
>  
> -- 
> 2.43.0
> 
>
diff mbox series

Patch

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 793ecc454039..44b1d5f1a99a 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5223,6 +5223,9 @@  static void rb_update_meta_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct trace_buffer_meta *meta = cpu_buffer->meta_page;
 
+	if (!meta)
+		return;
+
 	meta->reader.read = cpu_buffer->reader_page->read;
 	meta->reader.id = cpu_buffer->reader_page->id;
 	meta->reader.lost_events = cpu_buffer->lost_events;
@@ -6167,7 +6170,7 @@  rb_get_mapped_buffer(struct trace_buffer *buffer, int cpu)
 
 	mutex_lock(&cpu_buffer->mapping_lock);
 
-	if (!cpu_buffer->mapped) {
+	if (!cpu_buffer->mapped || !cpu_buffer->meta_page) {
 		mutex_unlock(&cpu_buffer->mapping_lock);
 		return ERR_PTR(-ENODEV);
 	}
@@ -6345,12 +6348,13 @@  int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 	 */
 	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	rb_setup_ids_meta_page(cpu_buffer, subbuf_ids);
+
 	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	err = __rb_map_vma(cpu_buffer, vma);
 	if (!err) {
 		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
-		cpu_buffer->mapped = 1;
+		cpu_buffer->mapped++;
 		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 	} else {
 		kfree(cpu_buffer->subbuf_ids);
@@ -6388,7 +6392,7 @@  int ring_buffer_unmap(struct trace_buffer *buffer, int cpu)
 	mutex_lock(&buffer->mutex);
 	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
-	cpu_buffer->mapped = 0;
+	cpu_buffer->mapped--;
 
 	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);