rolling_buffer_load_from_ra() looms large in the perf report because it loops around doing an atomic clear for each of the three mark bits per folio. However, this is both inefficient (it would be better to build a mask and atomically AND them out) and unnecessary as they shouldn't be set. Fix this by removing the loop. Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Signed-off-by: David Howells <dhowells@xxxxxxxxxx> cc: Jeff Layton <jlayton@xxxxxxxxxx> cc: Steve French <sfrench@xxxxxxxxx> cc: Paulo Alcantara <pc@xxxxxxxxxxxxx> cc: netfs@xxxxxxxxxxxxxxx cc: linux-cifs@xxxxxxxxxxxxxxx cc: linux-fsdevel@xxxxxxxxxxxxxxx --- fs/netfs/rolling_buffer.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/fs/netfs/rolling_buffer.c b/fs/netfs/rolling_buffer.c index 75d97af14b4a..207b6a326651 100644 --- a/fs/netfs/rolling_buffer.c +++ b/fs/netfs/rolling_buffer.c @@ -146,10 +146,6 @@ ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, /* Store the counter after setting the slot. */ smp_store_release(&roll->next_head_slot, to); - - for (; ix < folioq_nr_slots(fq); ix++) - folioq_clear(fq, ix); - return size; }