Patch "tracing: Introduce pipe_cpumask to avoid race on trace_pipes" has been added to the 5.15-stable tree

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



This is a note to let you know that I've just added the patch titled

    tracing: Introduce pipe_cpumask to avoid race on trace_pipes

to the 5.15-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     tracing-introduce-pipe_cpumask-to-avoid-race-on-trac.patch
and it can be found in the queue-5.15 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.



commit 5dd31bd739611356893ceac22f4e1652d4d09dab
Author: Zheng Yejian <zhengyejian1@xxxxxxxxxx>
Date:   Fri Aug 18 10:26:45 2023 +0800

    tracing: Introduce pipe_cpumask to avoid race on trace_pipes
    
    [ Upstream commit c2489bb7e6be2e8cdced12c16c42fa128403ac03 ]
    
    There is race issue when concurrently splice_read main trace_pipe and
    per_cpu trace_pipes which will result in data read out being different
    from what actually writen.
    
    As suggested by Steven:
      > I believe we should add a ref count to trace_pipe and the per_cpu
      > trace_pipes, where if they are opened, nothing else can read it.
      >
      > Opening trace_pipe locks all per_cpu ref counts, if any of them are
      > open, then the trace_pipe open will fail (and releases any ref counts
      > it had taken).
      >
      > Opening a per_cpu trace_pipe will up the ref count for just that
      > CPU buffer. This will allow multiple tasks to read different per_cpu
      > trace_pipe files, but will prevent the main trace_pipe file from
      > being opened.
    
    But because we only need to know whether per_cpu trace_pipe is open or
    not, using a cpumask instead of using ref count may be easier.
    
    After this patch, users will find that:
     - Main trace_pipe can be opened by only one user, and if it is
       opened, all per_cpu trace_pipes cannot be opened;
     - Per_cpu trace_pipes can be opened by multiple users, but each per_cpu
       trace_pipe can only be opened by one user. And if one of them is
       opened, main trace_pipe cannot be opened.
    
    Link: https://lore.kernel.org/linux-trace-kernel/20230818022645.1948314-1-zhengyejian1@xxxxxxxxxx
    
    Suggested-by: Steven Rostedt (Google) <rostedt@xxxxxxxxxxx>
    Signed-off-by: Zheng Yejian <zhengyejian1@xxxxxxxxxx>
    Reviewed-by: Masami Hiramatsu (Google) <mhiramat@xxxxxxxxxx>
    Signed-off-by: Steven Rostedt (Google) <rostedt@xxxxxxxxxxx>
    Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8769cd18f622f..92b381aab8f2b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6587,10 +6587,36 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
 
 #endif
 
+static int open_pipe_on_cpu(struct trace_array *tr, int cpu)
+{
+	if (cpu == RING_BUFFER_ALL_CPUS) {
+		if (cpumask_empty(tr->pipe_cpumask)) {
+			cpumask_setall(tr->pipe_cpumask);
+			return 0;
+		}
+	} else if (!cpumask_test_cpu(cpu, tr->pipe_cpumask)) {
+		cpumask_set_cpu(cpu, tr->pipe_cpumask);
+		return 0;
+	}
+	return -EBUSY;
+}
+
+static void close_pipe_on_cpu(struct trace_array *tr, int cpu)
+{
+	if (cpu == RING_BUFFER_ALL_CPUS) {
+		WARN_ON(!cpumask_full(tr->pipe_cpumask));
+		cpumask_clear(tr->pipe_cpumask);
+	} else {
+		WARN_ON(!cpumask_test_cpu(cpu, tr->pipe_cpumask));
+		cpumask_clear_cpu(cpu, tr->pipe_cpumask);
+	}
+}
+
 static int tracing_open_pipe(struct inode *inode, struct file *filp)
 {
 	struct trace_array *tr = inode->i_private;
 	struct trace_iterator *iter;
+	int cpu;
 	int ret;
 
 	ret = tracing_check_open_get_tr(tr);
@@ -6598,13 +6624,16 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 		return ret;
 
 	mutex_lock(&trace_types_lock);
+	cpu = tracing_get_cpu(inode);
+	ret = open_pipe_on_cpu(tr, cpu);
+	if (ret)
+		goto fail_pipe_on_cpu;
 
 	/* create a buffer to store the information to pass to userspace */
 	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
 	if (!iter) {
 		ret = -ENOMEM;
-		__trace_array_put(tr);
-		goto out;
+		goto fail_alloc_iter;
 	}
 
 	trace_seq_init(&iter->seq);
@@ -6627,7 +6656,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 
 	iter->tr = tr;
 	iter->array_buffer = &tr->array_buffer;
-	iter->cpu_file = tracing_get_cpu(inode);
+	iter->cpu_file = cpu;
 	mutex_init(&iter->mutex);
 	filp->private_data = iter;
 
@@ -6637,12 +6666,15 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	nonseekable_open(inode, filp);
 
 	tr->trace_ref++;
-out:
+
 	mutex_unlock(&trace_types_lock);
 	return ret;
 
 fail:
 	kfree(iter);
+fail_alloc_iter:
+	close_pipe_on_cpu(tr, cpu);
+fail_pipe_on_cpu:
 	__trace_array_put(tr);
 	mutex_unlock(&trace_types_lock);
 	return ret;
@@ -6659,7 +6691,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 
 	if (iter->trace->pipe_close)
 		iter->trace->pipe_close(iter);
-
+	close_pipe_on_cpu(tr, iter->cpu_file);
 	mutex_unlock(&trace_types_lock);
 
 	free_cpumask_var(iter->started);
@@ -9311,6 +9343,9 @@ static struct trace_array *trace_array_create(const char *name)
 	if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL))
 		goto out_free_tr;
 
+	if (!alloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL))
+		goto out_free_tr;
+
 	tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS;
 
 	cpumask_copy(tr->tracing_cpumask, cpu_all_mask);
@@ -9352,6 +9387,7 @@ static struct trace_array *trace_array_create(const char *name)
  out_free_tr:
 	ftrace_free_ftrace_ops(tr);
 	free_trace_buffers(tr);
+	free_cpumask_var(tr->pipe_cpumask);
 	free_cpumask_var(tr->tracing_cpumask);
 	kfree(tr->name);
 	kfree(tr);
@@ -9454,6 +9490,7 @@ static int __remove_instance(struct trace_array *tr)
 	}
 	kfree(tr->topts);
 
+	free_cpumask_var(tr->pipe_cpumask);
 	free_cpumask_var(tr->tracing_cpumask);
 	kfree(tr->name);
 	kfree(tr);
@@ -10164,12 +10201,14 @@ __init static int tracer_alloc_buffers(void)
 	if (trace_create_savedcmd() < 0)
 		goto out_free_temp_buffer;
 
+	if (!alloc_cpumask_var(&global_trace.pipe_cpumask, GFP_KERNEL))
+		goto out_free_savedcmd;
+
 	/* TODO: make the number of buffers hot pluggable with CPUS */
 	if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
 		MEM_FAIL(1, "tracer: failed to allocate ring buffer!\n");
-		goto out_free_savedcmd;
+		goto out_free_pipe_cpumask;
 	}
-
 	if (global_trace.buffer_disabled)
 		tracing_off();
 
@@ -10222,6 +10261,8 @@ __init static int tracer_alloc_buffers(void)
 
 	return 0;
 
+out_free_pipe_cpumask:
+	free_cpumask_var(global_trace.pipe_cpumask);
 out_free_savedcmd:
 	free_saved_cmdlines_buffer(savedcmd);
 out_free_temp_buffer:
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 43058077a4def..90ab921884b10 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -367,6 +367,8 @@ struct trace_array {
 	struct list_head	events;
 	struct trace_event_file *trace_marker_file;
 	cpumask_var_t		tracing_cpumask; /* only trace on set CPUs */
+	/* one per_cpu trace_pipe can be opened by only one user */
+	cpumask_var_t		pipe_cpumask;
 	int			ref;
 	int			trace_ref;
 #ifdef CONFIG_FUNCTION_TRACER



[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Index of Archives]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux