net: dqs: make struct dql more cache efficient

With the previous change, struct dqs->stall_thrs will be in the hot path
(at queue side), even if DQS is disabled.

The other fields accessed in this function (last_obj_cnt and num_queued)
are in the first cache line, let's move this field  (stall_thrs) to the
very first cache line, since there is a hole there.

This does not change the structure size, since it moves an short (2
bytes) to 4-bytes whole in the first cache line.

This is the new structure format now:

struct dql {
	unsigned int    num_queued;
	unsigned int    last_obj_cnt;
...
	short unsigned int    stall_thrs;
	/* XXX 2 bytes hole, try to pack */
...
	/* --- cacheline 1 boundary (64 bytes) --- */
...
 	/* Longest stall detected, reported to user */
	short unsigned int         stall_max;
	/* XXX 2 bytes hole, try to pack */
};

Also, read the stall_thrs (now in the very first cache line) earlier,
together with dql->num_queued (also in the first cache line).

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240411192241.2498631-5-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 9 insertions, 4 deletions

diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c
index a1389db1c30a..e49deddd3de9 100644
--- a/lib/dynamic_queue_limits.c
+++ b/lib/dynamic_queue_limits.c
@@ -15,12 +15,10 @@
 #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)
+static void dql_check_stall(struct dql *dql, unsigned short stall_thrs)
 {
-	unsigned short stall_thrs;
 	unsigned long now;
 
-	stall_thrs = READ_ONCE(dql->stall_thrs);
 	if (!stall_thrs)
 		return;
 
@@ -86,9 +84,16 @@ 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);
@@ -178,7 +183,7 @@ void dql_completed(struct dql *dql, unsigned int count)
 	dql->num_completed = completed;
 	dql->prev_num_queued = num_queued;
 
-	dql_check_stall(dql);
+	dql_check_stall(dql, stall_thrs);
 }
 EXPORT_SYMBOL(dql_completed);