diff options
| author | Vakul Garg <vakul.garg@nxp.com> | 2019-03-05 21:03:14 +0300 |
|---|---|---|
| committer | Herbert Xu <herbert@gondor.apana.org.au> | 2019-03-22 15:57:26 +0300 |
| commit | 16c4dd83a1b2a23004e2728b7c6222592e64e354 (patch) | |
| tree | cf68af53279ebe79019009eb65ee2e3bdcda087c /drivers/crypto/caam/jr.c | |
| parent | 9e98c678c2d6ae3a17cb2de55d17f69dddaa231b (diff) | |
| download | linux-16c4dd83a1b2a23004e2728b7c6222592e64e354.tar.xz | |
crypto: caam/jr - optimize job ring enqueue and dequeue operations
Instead of reading job ring's occupancy registers for every req/rsp
enqueued/dequeued respectively, we read these registers once and store
them in memory. After completing a job enqueue/dequeue, we decrement
these values. When these values become zero, we refresh the snapshot of
job ring's occupancy registers. This eliminates need of expensive device
register read operations for every job enqueued and dequeued and hence
makes caam_jr_enqueue() and caam_jr_dequeue() faster. The performance of
kernel ipsec improved by about 6% on ls1028 (for frame size 408 bytes).
Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Reviewed-by: Horia Geantă <horia.geanta@nxp.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'drivers/crypto/caam/jr.c')
| -rw-r--r-- | drivers/crypto/caam/jr.c | 12 |
1 files changed, 10 insertions, 2 deletions
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c index d50085a03597..b9caa95755d1 100644 --- a/drivers/crypto/caam/jr.c +++ b/drivers/crypto/caam/jr.c @@ -170,8 +170,10 @@ static void caam_jr_dequeue(unsigned long devarg) void (*usercall)(struct device *dev, u32 *desc, u32 status, void *arg); u32 *userdesc, userstatus; void *userarg; + u32 outring_used = 0; - while (rd_reg32(&jrp->rregs->outring_used)) { + while (outring_used || + (outring_used = rd_reg32(&jrp->rregs->outring_used))) { head = READ_ONCE(jrp->head); @@ -236,6 +238,7 @@ static void caam_jr_dequeue(unsigned long devarg) /* Finally, execute user's callback */ usercall(dev, userdesc, userstatus, userarg); + outring_used--; } /* reenable / unmask IRQs */ @@ -345,7 +348,7 @@ int caam_jr_enqueue(struct device *dev, u32 *desc, head = jrp->head; tail = READ_ONCE(jrp->tail); - if (!rd_reg32(&jrp->rregs->inpring_avail) || + if (!jrp->inpring_avail || CIRC_SPACE(head, tail, JOBR_DEPTH) <= 0) { spin_unlock_bh(&jrp->inplock); dma_unmap_single(dev, desc_dma, desc_size, DMA_TO_DEVICE); @@ -380,6 +383,10 @@ int caam_jr_enqueue(struct device *dev, u32 *desc, wr_reg32(&jrp->rregs->inpring_jobadd, 1); + jrp->inpring_avail--; + if (!jrp->inpring_avail) + jrp->inpring_avail = rd_reg32(&jrp->rregs->inpring_avail); + spin_unlock_bh(&jrp->inplock); return 0; @@ -442,6 +449,7 @@ static int caam_jr_init(struct device *dev) wr_reg32(&jrp->rregs->outring_size, JOBR_DEPTH); jrp->ringsize = JOBR_DEPTH; + jrp->inpring_avail = JOBR_DEPTH; spin_lock_init(&jrp->inplock); spin_lock_init(&jrp->outlock); |