[PATCH 3/6] ring-buffer: Have ring_buffer_alloc_read_page() return error on offline CPU

[Steven Rostedt]

From: "Steven Rostedt (VMware)" <rostedt@xxxxxxxxxxx>

Chunyu Hu reported:
  "per_cpu trace directories and files are created for all possible cpus,
   but only the cpus which have ever been on-lined have their own per cpu
   ring buffer (allocated by cpuhp threads). While trace_buffers_open, the
   open handler for trace file 'trace_pipe_raw' is always trying to access
   field of ring_buffer_per_cpu, and would panic with the NULL pointer.

   Align the behavior of trace_pipe_raw with trace_pipe, that returns -NODEV
   when openning it if that cpu does not have trace ring buffer.

   Reproduce:
   cat /sys/kernel/debug/tracing/per_cpu/cpu31/trace_pipe_raw
   (cpu31 is never on-lined, this is a 16 cores x86_64 box)

   Tested with:
   1) boot with maxcpus=14, read trace_pipe_raw of cpu15.
      Got -NODEV.
   2) oneline cpu15, read trace_pipe_raw of cpu15.
      Get the raw trace data.

   Call trace:
   [ 5760.950995] RIP: 0010:ring_buffer_alloc_read_page+0x32/0xe0
   [ 5760.961678]  tracing_buffers_read+0x1f6/0x230
   [ 5760.962695]  __vfs_read+0x37/0x160
   [ 5760.963498]  ? __vfs_read+0x5/0x160
   [ 5760.964339]  ? security_file_permission+0x9d/0xc0
   [ 5760.965451]  ? __vfs_read+0x5/0x160
   [ 5760.966280]  vfs_read+0x8c/0x130
   [ 5760.967070]  SyS_read+0x55/0xc0
   [ 5760.967779]  do_syscall_64+0x67/0x150
   [ 5760.968687]  entry_SYSCALL64_slow_path+0x25/0x25"

This was introduced by the addition of the feature to reuse reader pages
instead of re-allocating them. The problem is that the allocation of a
reader page (which is per cpu) does not check if the cpu is online and set
up for the ring buffer.

Link: http://lkml.kernel.org/r/1500880866-1177-1-git-send-email-chuhu@xxxxxxxxxx

Cc: stable@xxxxxxxxxxxxxxx
Fixes: 73a757e63114 ("ring-buffer: Return reader page back into existing ring buffer")
Reported-by: Chunyu Hu <chuhu@xxxxxxxxxx>
Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
---
 kernel/trace/ring_buffer.c           | 14 +++++++++-----
 kernel/trace/ring_buffer_benchmark.c |  2 +-
 kernel/trace/trace.c                 | 16 +++++++++++-----
 3 files changed, 21 insertions(+), 11 deletions(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 529cc50d7243..81279c6602ff 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -4386,15 +4386,19 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
  * the page that was allocated, with the read page of the buffer.
  *
  * Returns:
- *  The page allocated, or NULL on error.
+ *  The page allocated, or ERR_PTR
  */
 void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
 {
-	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+	struct ring_buffer_per_cpu *cpu_buffer;
 	struct buffer_data_page *bpage = NULL;
 	unsigned long flags;
 	struct page *page;
 
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return ERR_PTR(-ENODEV);
+
+	cpu_buffer = buffer->buffers[cpu];
 	local_irq_save(flags);
 	arch_spin_lock(&cpu_buffer->lock);
 
@@ -4412,7 +4416,7 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
 	page = alloc_pages_node(cpu_to_node(cpu),
 				GFP_KERNEL | __GFP_NORETRY, 0);
 	if (!page)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	bpage = page_address(page);
 
@@ -4467,8 +4471,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
  *
  * for example:
  *	rpage = ring_buffer_alloc_read_page(buffer, cpu);
- *	if (!rpage)
- *		return error;
+ *	if (IS_ERR(rpage))
+ *		return PTR_ERR(rpage);
  *	ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0);
  *	if (ret >= 0)
  *		process_page(rpage, ret);
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 9fbcaf567886..68ee79afe31c 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -113,7 +113,7 @@ static enum event_status read_page(int cpu)
 	int i;
 
 	bpage = ring_buffer_alloc_read_page(buffer, cpu);
-	if (!bpage)
+	if (IS_ERR(bpage))
 		return EVENT_DROPPED;
 
 	ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d815fc317e9d..44004d8aa3b3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6598,7 +6598,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 {
 	struct ftrace_buffer_info *info = filp->private_data;
 	struct trace_iterator *iter = &info->iter;
-	ssize_t ret;
+	ssize_t ret = 0;
 	ssize_t size;
 
 	if (!count)
@@ -6612,10 +6612,15 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	if (!info->spare) {
 		info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer,
 							  iter->cpu_file);
-		info->spare_cpu = iter->cpu_file;
+		if (IS_ERR(info->spare)) {
+			ret = PTR_ERR(info->spare);
+			info->spare = NULL;
+		} else {
+			info->spare_cpu = iter->cpu_file;
+		}
 	}
 	if (!info->spare)
-		return -ENOMEM;
+		return ret;
 
 	/* Do we have previous read data to read? */
 	if (info->read < PAGE_SIZE)
@@ -6790,8 +6795,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		ref->ref = 1;
 		ref->buffer = iter->trace_buffer->buffer;
 		ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
-		if (!ref->page) {
-			ret = -ENOMEM;
+		if (IS_ERR(ref->page)) {
+			ret = PTR_ERR(ref->page);
+			ref->page = NULL;
 			kfree(ref);
 			break;
 		}
-- 
2.13.2