| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20250926033502.7486-11-kanchana.p.sridhar@intel.com>
Date: Thu, 25 Sep 2025 20:34:49 -0700
From: Kanchana P Sridhar <kanchana.p.sridhar@...el.com>
To: linux-kernel@...r.kernel.org,
linux-mm@...ck.org,
hannes@...xchg.org,
yosry.ahmed@...ux.dev,
nphamcs@...il.com,
chengming.zhou@...ux.dev,
usamaarif642@...il.com,
ryan.roberts@....com,
21cnbao@...il.com,
ying.huang@...ux.alibaba.com,
akpm@...ux-foundation.org,
senozhatsky@...omium.org,
sj@...nel.org,
kasong@...cent.com,
linux-crypto@...r.kernel.org,
herbert@...dor.apana.org.au,
davem@...emloft.net,
clabbe@...libre.com,
ardb@...nel.org,
ebiggers@...gle.com,
surenb@...gle.com,
kristen.c.accardi@...el.com,
vinicius.gomes@...el.com
Cc: wajdi.k.feghali@...el.com,
vinodh.gopal@...el.com,
kanchana.p.sridhar@...el.com
Subject: [PATCH v12 10/23] crypto: iaa - Expect a single scatterlist for a [de]compress request's src/dst.
The calls to dma_map_sg() were passing sg_nents() for the @nents
parameter, then error-ing out if more than one @nr_sgs were
returned. Furthermore, there are no use-cases for iaa_crypto that allow
multiple SG lists to be mapped for dma at once.
Moreover, as per Herbert's direction in [1] for the batching API from
higher mm layers to interface with crypto using SG lists, batching
within iaa_crypto will rely on there being exactly one SG list per
"unit" of [de]compression in a batch, where the component SG lists are
obtained by breaking down the @req->src and @req->dst.
Given all of the above, this patch simplifies the design by expecting
only 1 @nents in req->src and req->dst, which aligns with current and
batching use cases that will be developed in subsequent patches.
This alleviates the latency penalty of calling sg_nents() per
[de]compress op submitted to the hardware.
Some unlikely() annotations are added to conditionals in the core
[de]compress routines to further improve latency per op.
[1]: https://lore.kernel.org/all/aJ7Fk6RpNc815Ivd@gondor.apana.org.au/T/#m99aea2ce3d284e6c5a3253061d97b08c4752a798
Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@...el.com>
---
drivers/crypto/intel/iaa/iaa_crypto_main.c | 54 +++++++++++-----------
1 file changed, 27 insertions(+), 27 deletions(-)
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
index dd7c4831e092..16b071058f2b 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -1514,11 +1514,11 @@ static int iaa_remap_for_verify(struct device *dev, struct iaa_wq *iaa_wq,
int ret = 0;
int nr_sgs;
- dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
- dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+ dma_unmap_sg(dev, req->dst, 1, DMA_FROM_DEVICE);
+ dma_unmap_sg(dev, req->src, 1, DMA_TO_DEVICE);
- nr_sgs = dma_map_sg(dev, req->src, sg_nents(req->src), DMA_FROM_DEVICE);
- if (nr_sgs <= 0 || nr_sgs > 1) {
+ nr_sgs = dma_map_sg(dev, req->src, 1, DMA_FROM_DEVICE);
+ if (unlikely(nr_sgs <= 0 || nr_sgs > 1)) {
dev_dbg(dev, "verify: couldn't map src sg for iaa device %d,"
" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
iaa_wq->wq->id, ret);
@@ -1530,13 +1530,13 @@ static int iaa_remap_for_verify(struct device *dev, struct iaa_wq *iaa_wq,
" req->slen %d, sg_dma_len(sg) %d\n", *src_addr, nr_sgs,
req->src, req->slen, sg_dma_len(req->src));
- nr_sgs = dma_map_sg(dev, req->dst, sg_nents(req->dst), DMA_TO_DEVICE);
- if (nr_sgs <= 0 || nr_sgs > 1) {
+ nr_sgs = dma_map_sg(dev, req->dst, 1, DMA_TO_DEVICE);
+ if (unlikely(nr_sgs <= 0 || nr_sgs > 1)) {
dev_dbg(dev, "verify: couldn't map dst sg for iaa device %d,"
" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
iaa_wq->wq->id, ret);
ret = -EIO;
- dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_FROM_DEVICE);
+ dma_unmap_sg(dev, req->src, 1, DMA_FROM_DEVICE);
goto out;
}
*dst_addr = sg_dma_address(req->dst);
@@ -1704,14 +1704,14 @@ static void iaa_desc_complete(struct idxd_desc *idxd_desc,
err = -EIO;
}
- dma_unmap_sg(dev, ctx->req->dst, sg_nents(ctx->req->dst), DMA_TO_DEVICE);
- dma_unmap_sg(dev, ctx->req->src, sg_nents(ctx->req->src), DMA_FROM_DEVICE);
+ dma_unmap_sg(dev, ctx->req->dst, 1, DMA_TO_DEVICE);
+ dma_unmap_sg(dev, ctx->req->src, 1, DMA_FROM_DEVICE);
goto out;
}
err:
- dma_unmap_sg(dev, ctx->req->dst, sg_nents(ctx->req->dst), DMA_FROM_DEVICE);
- dma_unmap_sg(dev, ctx->req->src, sg_nents(ctx->req->src), DMA_TO_DEVICE);
+ dma_unmap_sg(dev, ctx->req->dst, 1, DMA_FROM_DEVICE);
+ dma_unmap_sg(dev, ctx->req->src, 1, DMA_TO_DEVICE);
out:
if (ret != 0)
dev_dbg(dev, "asynchronous compress failed ret=%d\n", ret);
@@ -2014,8 +2014,8 @@ static int iaa_comp_acompress(struct acomp_req *req)
dev = &wq->idxd->pdev->dev;
- nr_sgs = dma_map_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
- if (nr_sgs <= 0 || nr_sgs > 1) {
+ nr_sgs = dma_map_sg(dev, req->src, 1, DMA_TO_DEVICE);
+ if (unlikely(nr_sgs <= 0 || nr_sgs > 1)) {
dev_dbg(dev, "couldn't map src sg for iaa device %d,"
" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
iaa_wq->wq->id, ret);
@@ -2024,8 +2024,8 @@ static int iaa_comp_acompress(struct acomp_req *req)
}
src_addr = sg_dma_address(req->src);
- nr_sgs = dma_map_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
- if (nr_sgs <= 0 || nr_sgs > 1) {
+ nr_sgs = dma_map_sg(dev, req->dst, 1, DMA_FROM_DEVICE);
+ if (unlikely(nr_sgs <= 0 || nr_sgs > 1)) {
dev_dbg(dev, "couldn't map dst sg for iaa device %d,"
" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
iaa_wq->wq->id, ret);
@@ -2051,18 +2051,18 @@ static int iaa_comp_acompress(struct acomp_req *req)
if (ret)
dev_dbg(dev, "asynchronous compress verification failed ret=%d\n", ret);
- dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_TO_DEVICE);
- dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_FROM_DEVICE);
+ dma_unmap_sg(dev, req->dst, 1, DMA_TO_DEVICE);
+ dma_unmap_sg(dev, req->src, 1, DMA_FROM_DEVICE);
goto out;
}
- if (ret)
+ if (unlikely(ret))
dev_dbg(dev, "asynchronous compress failed ret=%d\n", ret);
- dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+ dma_unmap_sg(dev, req->dst, 1, DMA_FROM_DEVICE);
err_map_dst:
- dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+ dma_unmap_sg(dev, req->src, 1, DMA_TO_DEVICE);
out:
percpu_ref_put(&iaa_wq->ref);
@@ -2095,8 +2095,8 @@ static int iaa_comp_adecompress(struct acomp_req *req)
dev = &wq->idxd->pdev->dev;
- nr_sgs = dma_map_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
- if (nr_sgs <= 0 || nr_sgs > 1) {
+ nr_sgs = dma_map_sg(dev, req->src, 1, DMA_TO_DEVICE);
+ if (unlikely(nr_sgs <= 0 || nr_sgs > 1)) {
dev_dbg(dev, "couldn't map src sg for iaa device %d,"
" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
iaa_wq->wq->id, ret);
@@ -2105,8 +2105,8 @@ static int iaa_comp_adecompress(struct acomp_req *req)
}
src_addr = sg_dma_address(req->src);
- nr_sgs = dma_map_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
- if (nr_sgs <= 0 || nr_sgs > 1) {
+ nr_sgs = dma_map_sg(dev, req->dst, 1, DMA_FROM_DEVICE);
+ if (unlikely(nr_sgs <= 0 || nr_sgs > 1)) {
dev_dbg(dev, "couldn't map dst sg for iaa device %d,"
" wq %d: ret=%d\n", iaa_wq->iaa_device->idxd->id,
iaa_wq->wq->id, ret);
@@ -2120,12 +2120,12 @@ static int iaa_comp_adecompress(struct acomp_req *req)
if (ret == -EINPROGRESS)
return ret;
- if (ret != 0)
+ if (unlikely(ret != 0))
dev_dbg(dev, "asynchronous decompress failed ret=%d\n", ret);
- dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_FROM_DEVICE);
+ dma_unmap_sg(dev, req->dst, 1, DMA_FROM_DEVICE);
err_map_dst:
- dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_TO_DEVICE);
+ dma_unmap_sg(dev, req->src, 1, DMA_TO_DEVICE);
out:
percpu_ref_put(&iaa_wq->ref);
--
2.27.0
Powered by blists - more mailing lists