Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 217 insertions, 0 deletions

diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c
new file mode 100644
index 000000000..f97a752e9
--- /dev/null
+++ b/lib/dynamic_queue_limits.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Dynamic byte queue limits.  See include/linux/dynamic_queue_limits.h
+ *
+ * Copyright (c) 2011, Tom Herbert <therbert@google.com>
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/jiffies.h>
+#include <linux/dynamic_queue_limits.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
+#include <trace/events/napi.h>
+
+#define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0)
+#define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0)
+
+static void dql_check_stall(struct dql *dql, unsigned short stall_thrs)
+{
+	unsigned long now;
+
+	if (!stall_thrs)
+		return;
+
+	now = jiffies;
+	/* Check for a potential stall */
+	if (time_after_eq(now, dql->last_reap + stall_thrs)) {
+		unsigned long hist_head, t, start, end;
+
+		/* We are trying to detect a period of at least @stall_thrs
+		 * jiffies without any Tx completions, but during first half
+		 * of which some Tx was posted.
+		 */
+dqs_again:
+		hist_head = READ_ONCE(dql->history_head);
+		/* pairs with smp_wmb() in dql_queued() */
+		smp_rmb();
+
+		/* Get the previous entry in the ring buffer, which is the
+		 * oldest sample.
+		 */
+		start = (hist_head - DQL_HIST_LEN + 1) * BITS_PER_LONG;
+
+		/* Advance start to continue from the last reap time */
+		if (time_before(start, dql->last_reap + 1))
+			start = dql->last_reap + 1;
+
+		/* Newest sample we should have already seen a completion for */
+		end = hist_head * BITS_PER_LONG + (BITS_PER_LONG - 1);
+
+		/* Shrink the search space to [start, (now - start_thrs/2)] if
+		 * `end` is beyond the stall zone
+		 */
+		if (time_before(now, end + stall_thrs / 2))
+			end = now - stall_thrs / 2;
+
+		/* Search for the queued time in [t, end] */
+		for (t = start; time_before_eq(t, end); t++)
+			if (test_bit(t % (DQL_HIST_LEN * BITS_PER_LONG),
+				     dql->history))
+				break;
+
+		/* Variable t contains the time of the queue */
+		if (!time_before_eq(t, end))
+			goto no_stall;
+
+		/* The ring buffer was modified in the meantime, retry */
+		if (hist_head != READ_ONCE(dql->history_head))
+			goto dqs_again;
+
+		dql->stall_cnt++;
+		dql->stall_max = max_t(unsigned short, dql->stall_max, now - t);
+
+		trace_dql_stall_detected(dql->stall_thrs, now - t,
+					 dql->last_reap, dql->history_head,
+					 now, dql->history);
+	}
+no_stall:
+	dql->last_reap = now;
+}
+
+/* Records completed count and recalculates the queue limit */
+void dql_completed(struct dql *dql, unsigned int count)
+{
+	unsigned int inprogress, prev_inprogress, limit;
+	unsigned int ovlimit, completed, num_queued;
+	unsigned short stall_thrs;
+	bool all_prev_completed;
+
+	num_queued = READ_ONCE(dql->num_queued);
+	/* Read stall_thrs in advance since it belongs to the same (first)
+	 * cache line as ->num_queued. This way, dql_check_stall() does not
+	 * need to touch the first cache line again later, reducing the window
+	 * of possible false sharing.
+	 */
+	stall_thrs = READ_ONCE(dql->stall_thrs);
+
+	/* Can't complete more than what's in queue */
+	BUG_ON(count > num_queued - dql->num_completed);
+
+	completed = dql->num_completed + count;
+	limit = dql->limit;
+	ovlimit = POSDIFF(num_queued - dql->num_completed, limit);
+	inprogress = num_queued - completed;
+	prev_inprogress = dql->prev_num_queued - dql->num_completed;
+	all_prev_completed = AFTER_EQ(completed, dql->prev_num_queued);
+
+	if ((ovlimit && !inprogress) ||
+	    (dql->prev_ovlimit && all_prev_completed)) {
+		/*
+		 * Queue considered starved if:
+		 *   - The queue was over-limit in the last interval,
+		 *     and there is no more data in the queue.
+		 *  OR
+		 *   - The queue was over-limit in the previous interval and
+		 *     when enqueuing it was possible that all queued data
+		 *     had been consumed.  This covers the case when queue
+		 *     may have becomes starved between completion processing
+		 *     running and next time enqueue was scheduled.
+		 *
+		 *     When queue is starved increase the limit by the amount
+		 *     of bytes both sent and completed in the last interval,
+		 *     plus any previous over-limit.
+		 */
+		limit += POSDIFF(completed, dql->prev_num_queued) +
+		     dql->prev_ovlimit;
+		dql->slack_start_time = jiffies;
+		dql->lowest_slack = UINT_MAX;
+	} else if (inprogress && prev_inprogress && !all_prev_completed) {
+		/*
+		 * Queue was not starved, check if the limit can be decreased.
+		 * A decrease is only considered if the queue has been busy in
+		 * the whole interval (the check above).
+		 *
+		 * If there is slack, the amount of excess data queued above
+		 * the amount needed to prevent starvation, the queue limit
+		 * can be decreased.  To avoid hysteresis we consider the
+		 * minimum amount of slack found over several iterations of the
+		 * completion routine.
+		 */
+		unsigned int slack, slack_last_objs;
+
+		/*
+		 * Slack is the maximum of
+		 *   - The queue limit plus previous over-limit minus twice
+		 *     the number of objects completed.  Note that two times
+		 *     number of completed bytes is a basis for an upper bound
+		 *     of the limit.
+		 *   - Portion of objects in the last queuing operation that
+		 *     was not part of non-zero previous over-limit.  That is
+		 *     "round down" by non-overlimit portion of the last
+		 *     queueing operation.
+		 */
+		slack = POSDIFF(limit + dql->prev_ovlimit,
+		    2 * (completed - dql->num_completed));
+		slack_last_objs = dql->prev_ovlimit ?
+		    POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0;
+
+		slack = max(slack, slack_last_objs);
+
+		if (slack < dql->lowest_slack)
+			dql->lowest_slack = slack;
+
+		if (time_after(jiffies,
+			       dql->slack_start_time + dql->slack_hold_time)) {
+			limit = POSDIFF(limit, dql->lowest_slack);
+			dql->slack_start_time = jiffies;
+			dql->lowest_slack = UINT_MAX;
+		}
+	}
+
+	/* Enforce bounds on limit */
+	limit = clamp(limit, dql->min_limit, dql->max_limit);
+
+	if (limit != dql->limit) {
+		dql->limit = limit;
+		ovlimit = 0;
+	}
+
+	dql->adj_limit = limit + completed;
+	dql->prev_ovlimit = ovlimit;
+	dql->prev_last_obj_cnt = READ_ONCE(dql->last_obj_cnt);
+	dql->num_completed = completed;
+	dql->prev_num_queued = num_queued;
+
+	dql_check_stall(dql, stall_thrs);
+}
+EXPORT_SYMBOL(dql_completed);
+
+void dql_reset(struct dql *dql)
+{
+	/* Reset all dynamic values */
+	dql->limit = dql->min_limit;
+	dql->num_queued = 0;
+	dql->num_completed = 0;
+	dql->last_obj_cnt = 0;
+	dql->prev_num_queued = 0;
+	dql->prev_last_obj_cnt = 0;
+	dql->prev_ovlimit = 0;
+	dql->lowest_slack = UINT_MAX;
+	dql->slack_start_time = jiffies;
+
+	dql->last_reap = jiffies;
+	dql->history_head = jiffies / BITS_PER_LONG;
+	memset(dql->history, 0, sizeof(dql->history));
+}
+EXPORT_SYMBOL(dql_reset);
+
+void dql_init(struct dql *dql, unsigned int hold_time)
+{
+	dql->max_limit = DQL_MAX_LIMIT;
+	dql->min_limit = 0;
+	dql->slack_hold_time = hold_time;
+	dql->stall_thrs = 0;
+	dql_reset(dql);
+}
+EXPORT_SYMBOL(dql_init);