Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

No conflicts.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 45 insertions, 13 deletions

diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config
index 07df6d93c4df..e8db8d938661 100644
--- a/kernel/configs/debug.config
+++ b/kernel/configs/debug.config
@@ -16,6 +16,7 @@ CONFIG_SYMBOLIC_ERRNAME=y
 #
 # Compile-time checks and compiler options
 #
+CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_FRAME_WARN=2048
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index a4b462b6f944..6105b7036482 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -7790,7 +7790,7 @@ int ftrace_is_dead(void)
 
 /**
  * register_ftrace_function - register a function for profiling
- * @ops - ops structure that holds the function for profiling.
+ * @ops:	ops structure that holds the function for profiling.
  *
  * Register a function to be called by all functions in the
  * kernel.
@@ -7817,7 +7817,7 @@ EXPORT_SYMBOL_GPL(register_ftrace_function);
 
 /**
  * unregister_ftrace_function - unregister a function for profiling.
- * @ops - ops structure that holds the function to unregister
+ * @ops:	ops structure that holds the function to unregister
  *
  * Unregister a function that was added to be called by ftrace profiling.
  */
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index cfddb30e65ab..5e3c62a08fc0 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1387,6 +1387,26 @@ static int run_osnoise(void)
 		}
 
 		/*
+		 * In some cases, notably when running on a nohz_full CPU with
+		 * a stopped tick PREEMPT_RCU has no way to account for QSs.
+		 * This will eventually cause unwarranted noise as PREEMPT_RCU
+		 * will force preemption as the means of ending the current
+		 * grace period. We avoid this problem by calling
+		 * rcu_momentary_dyntick_idle(), which performs a zero duration
+		 * EQS allowing PREEMPT_RCU to end the current grace period.
+		 * This call shouldn't be wrapped inside an RCU critical
+		 * section.
+		 *
+		 * Note that in non PREEMPT_RCU kernels QSs are handled through
+		 * cond_resched()
+		 */
+		if (IS_ENABLED(CONFIG_PREEMPT_RCU)) {
+			local_irq_disable();
+			rcu_momentary_dyntick_idle();
+			local_irq_enable();
+		}
+
+		/*
 		 * For the non-preemptive kernel config: let threads runs, if
 		 * they so wish.
 		 */
@@ -2200,6 +2220,17 @@ static void osnoise_workload_stop(void)
 	if (osnoise_has_registered_instances())
 		return;
 
+	/*
+	 * If callbacks were already disabled in a previous stop
+	 * call, there is no need to disable then again.
+	 *
+	 * For instance, this happens when tracing is stopped via:
+	 * echo 0 > tracing_on
+	 * echo nop > current_tracer.
+	 */
+	if (!trace_osnoise_callback_enabled)
+		return;
+
 	trace_osnoise_callback_enabled = false;
 	/*
 	 * Make sure that ftrace_nmi_enter/exit() see
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index 9c9eb20dd2c5..00703444a219 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -54,6 +54,7 @@ static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe,
 	bit += page->index;
 
 	set_bit(bit, wqueue->notes_bitmap);
+	generic_pipe_buf_release(pipe, buf);
 }
 
 // No try_steal function => no stealing
@@ -112,7 +113,7 @@ static bool post_one_notification(struct watch_queue *wqueue,
 	buf->offset = offset;
 	buf->len = len;
 	buf->flags = PIPE_BUF_FLAG_WHOLE;
-	pipe->head = head + 1;
+	smp_store_release(&pipe->head, head + 1); /* vs pipe_read() */
 
 	if (!test_and_clear_bit(note, wqueue->notes_bitmap)) {
 		spin_unlock_irq(&pipe->rd_wait.lock);
@@ -219,7 +220,6 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
 	struct page **pages;
 	unsigned long *bitmap;
 	unsigned long user_bufs;
-	unsigned int bmsize;
 	int ret, i, nr_pages;
 
 	if (!wqueue)
@@ -243,7 +243,8 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
 		goto error;
 	}
 
-	ret = pipe_resize_ring(pipe, nr_notes);
+	nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE;
+	ret = pipe_resize_ring(pipe, roundup_pow_of_two(nr_notes));
 	if (ret < 0)
 		goto error;
 
@@ -258,17 +259,15 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
 		pages[i]->index = i * WATCH_QUEUE_NOTES_PER_PAGE;
 	}
 
-	bmsize = (nr_notes + BITS_PER_LONG - 1) / BITS_PER_LONG;
-	bmsize *= sizeof(unsigned long);
-	bitmap = kmalloc(bmsize, GFP_KERNEL);
+	bitmap = bitmap_alloc(nr_notes, GFP_KERNEL);
 	if (!bitmap)
 		goto error_p;
 
-	memset(bitmap, 0xff, bmsize);
+	bitmap_fill(bitmap, nr_notes);
 	wqueue->notes = pages;
 	wqueue->notes_bitmap = bitmap;
 	wqueue->nr_pages = nr_pages;
-	wqueue->nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE;
+	wqueue->nr_notes = nr_notes;
 	return 0;
 
 error_p:
@@ -320,7 +319,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe,
 		    tf[i].info_mask & WATCH_INFO_LENGTH)
 			goto err_filter;
 		/* Ignore any unknown types */
-		if (tf[i].type >= sizeof(wfilter->type_filter) * 8)
+		if (tf[i].type >= WATCH_TYPE__NR)
 			continue;
 		nr_filter++;
 	}
@@ -336,7 +335,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe,
 
 	q = wfilter->filters;
 	for (i = 0; i < filter.nr_filters; i++) {
-		if (tf[i].type >= sizeof(wfilter->type_filter) * BITS_PER_LONG)
+		if (tf[i].type >= WATCH_TYPE__NR)
 			continue;
 
 		q->type			= tf[i].type;
@@ -371,6 +370,7 @@ static void __put_watch_queue(struct kref *kref)
 
 	for (i = 0; i < wqueue->nr_pages; i++)
 		__free_page(wqueue->notes[i]);
+	bitmap_free(wqueue->notes_bitmap);
 
 	wfilter = rcu_access_pointer(wqueue->filter);
 	if (wfilter)
@@ -566,7 +566,7 @@ void watch_queue_clear(struct watch_queue *wqueue)
 	rcu_read_lock();
 	spin_lock_bh(&wqueue->lock);
 
-	/* Prevent new additions and prevent notifications from happening */
+	/* Prevent new notifications from being stored. */
 	wqueue->defunct = true;
 
 	while (!hlist_empty(&wqueue->watches)) {