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

Cross-merge networking fixes after downstream PR.

Conflicts:

drivers/net/ethernet/intel/iavf/iavf_ethtool.c
  3a0b5a2929fd ("iavf: Introduce new state machines for flow director")
  95260816b489 ("iavf: use iavf_schedule_aq_request() helper")
https://lore.kernel.org/all/84e12519-04dc-bd80-bc34-8cf50d7898ce@intel.com/

drivers/net/ethernet/broadcom/bnxt/bnxt.c
  c13e268c0768 ("bnxt_en: Fix HWTSTAMP_FILTER_ALL packet timestamp logic")
  c2f8063309da ("bnxt_en: Refactor RX VLAN acceleration logic.")
  a7445d69809f ("bnxt_en: Add support for new RX and TPA_START completion types for P7")
  1c7fd6ee2fe4 ("bnxt_en: Rename some macros for the P5 chips")
https://lore.kernel.org/all/20231211110022.27926ad9@canb.auug.org.au/

drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
  bd6781c18cb5 ("bnxt_en: Fix wrong return value check in bnxt_close_nic()")
  84793a499578 ("bnxt_en: Skip nic close/open when configuring tstamp filters")
https://lore.kernel.org/all/20231214113041.3a0c003c@canb.auug.org.au/

drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
  3d7a3f2612d7 ("net/mlx5: Nack sync reset request when HotPlug is enabled")
  cecf44ea1a1f ("net/mlx5: Allow sync reset flow when BF MGT interface device is present")
https://lore.kernel.org/all/20231211110328.76c925af@canb.auug.org.au/

No adjacent changes.

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

1 files changed, 38 insertions, 23 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index b704d83a28b2..c9d123e13b57 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1814,31 +1814,34 @@ static inline void perf_event__state_init(struct perf_event *event)
 					      PERF_EVENT_STATE_INACTIVE;
 }
 
-static void __perf_event_read_size(struct perf_event *event, int nr_siblings)
+static int __perf_event_read_size(u64 read_format, int nr_siblings)
 {
 	int entry = sizeof(u64); /* value */
 	int size = 0;
 	int nr = 1;
 
-	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
 		size += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
 		size += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_ID)
+	if (read_format & PERF_FORMAT_ID)
 		entry += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_LOST)
+	if (read_format & PERF_FORMAT_LOST)
 		entry += sizeof(u64);
 
-	if (event->attr.read_format & PERF_FORMAT_GROUP) {
+	if (read_format & PERF_FORMAT_GROUP) {
 		nr += nr_siblings;
 		size += sizeof(u64);
 	}
 
-	size += entry * nr;
-	event->read_size = size;
+	/*
+	 * Since perf_event_validate_size() limits this to 16k and inhibits
+	 * adding more siblings, this will never overflow.
+	 */
+	return size + nr * entry;
 }
 
 static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
@@ -1888,8 +1891,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
  */
 static void perf_event__header_size(struct perf_event *event)
 {
-	__perf_event_read_size(event,
-			       event->group_leader->nr_siblings);
+	event->read_size =
+		__perf_event_read_size(event->attr.read_format,
+				       event->group_leader->nr_siblings);
 	__perf_event_header_size(event, event->attr.sample_type);
 }
 
@@ -1920,24 +1924,35 @@ static void perf_event__id_header_size(struct perf_event *event)
 	event->id_header_size = size;
 }
 
+/*
+ * Check that adding an event to the group does not result in anybody
+ * overflowing the 64k event limit imposed by the output buffer.
+ *
+ * Specifically, check that the read_size for the event does not exceed 16k,
+ * read_size being the one term that grows with groups size. Since read_size
+ * depends on per-event read_format, also (re)check the existing events.
+ *
+ * This leaves 48k for the constant size fields and things like callchains,
+ * branch stacks and register sets.
+ */
 static bool perf_event_validate_size(struct perf_event *event)
 {
-	/*
-	 * The values computed here will be over-written when we actually
-	 * attach the event.
-	 */
-	__perf_event_read_size(event, event->group_leader->nr_siblings + 1);
-	__perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ);
-	perf_event__id_header_size(event);
+	struct perf_event *sibling, *group_leader = event->group_leader;
 
-	/*
-	 * Sum the lot; should not exceed the 64k limit we have on records.
-	 * Conservative limit to allow for callchains and other variable fields.
-	 */
-	if (event->read_size + event->header_size +
-	    event->id_header_size + sizeof(struct perf_event_header) >= 16*1024)
+	if (__perf_event_read_size(event->attr.read_format,
+				   group_leader->nr_siblings + 1) > 16*1024)
 		return false;
 
+	if (__perf_event_read_size(group_leader->attr.read_format,
+				   group_leader->nr_siblings + 1) > 16*1024)
+		return false;
+
+	for_each_sibling_event(sibling, group_leader) {
+		if (__perf_event_read_size(sibling->attr.read_format,
+					   group_leader->nr_siblings + 1) > 16*1024)
+			return false;
+	}
+
 	return true;
 }