From a8de6639169b90e3dc4f27e752a3c5abac5e90da Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 7 May 2020 23:07:04 +0300 Subject: nvme-pci: fix "slimmer CQ head update" Pre-incrementing ->cq_head can't be done in memory because OOB value can be observed by another context. This devalues space savings compared to original code :-\ $ ./scripts/bloat-o-meter ../vmlinux-000 ../obj/vmlinux add/remove: 0/0 grow/shrink: 0/4 up/down: 0/-32 (-32) Function old new delta nvme_poll_irqdisable 464 456 -8 nvme_poll 455 447 -8 nvme_irq 388 380 -8 nvme_dev_disable 955 947 -8 But the code is minimal now: one read for head, one read for q_depth, one increment, one comparison, single instruction phase bit update and one write for new head. Signed-off-by: Alexey Dobriyan Reported-by: John Garry Tested-by: John Garry Fixes: e2a366a4b0feaeb ("nvme-pci: slimmer CQ head update") Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 4e79e412b276..e13c370de830 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -973,9 +973,13 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) static inline void nvme_update_cq_head(struct nvme_queue *nvmeq) { - if (++nvmeq->cq_head == nvmeq->q_depth) { + u16 tmp = nvmeq->cq_head + 1; + + if (tmp == nvmeq->q_depth) { nvmeq->cq_head = 0; nvmeq->cq_phase ^= 1; + } else { + nvmeq->cq_head = tmp; } } -- cgit v1.2.3