| 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: <20250430205305.22844-10-kanchana.p.sridhar@intel.com>
Date: Wed, 30 Apr 2025 13:52:55 -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,
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
Cc: wajdi.k.feghali@...el.com,
vinodh.gopal@...el.com,
kanchana.p.sridhar@...el.com
Subject: [PATCH v9 09/19] crypto: iaa - CRYPTO_ACOMP_REQ_POLL acomp_req flag for sequential vs. parallel.
The purpose of this commit is to allow kernel users of iaa_crypto, such
as zswap, to be able to invoke the crypto_acomp_compress() API in fully
synchronous mode for non-batching use cases (i.e. today's status-quo),
where zswap calls crypto_wait_req(crypto_acomp_compress(req), wait);
and to non-instrusively invoke the fully asynchronous batch
compress/decompress API that will be introduced in subsequent
patches. Both use cases need to reuse same code paths in the driver to
interface with hardware: the CRYPTO_ACOMP_REQ_POLL flag allows this
shared code to determine whether we need to process an acomp_req
synchronously/asynchronously. The idea is to simplify the crypto_acomp
sequential/batching interfaces for use by zswap.
Thus, regardless of the iaa_crypto driver's 'sync_mode' setting, it
can still be forced to use synchronous mode by turning
off the CRYPTO_ACOMP_REQ_POLL flag in req->base.flags (the default to
support sequential use cases in zswap today).
IAA batching functionality will be implemented in subsequent patches,
that will set the CRYPTO_ACOMP_REQ_POLL flag for the acomp_reqs in a
batch. This enables the iaa_crypto driver to implement true
async "submit-polling" for parallel compressions and decompressions in
the IAA hardware accelerator.
In other words, all three of the following need to be true for a request
to be processed in fully async submit-poll mode:
1) async_mode should be "true"
2) use_irq should be "false"
3) req->base.flags & CRYPTO_ACOMP_REQ_POLL should be "true"
Subsequent patches will:
- Set (1) and (2) as iaa_crypto defaults once async submit-poll is
implemented.
- Enable (3) for iaa_crypto batching, and clear the
CRYPTO_ACOMP_REQ_POLL flags before exiting from the batching
routines since the assumption is that the acomp_reqs are
created/managed by a higher level kernel user such as zswap, and are
reused for both, sequential and batching use cases from zswap's
perspective.
This patch also removes "disable_async" from iaa_decompress().
Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@...el.com>
---
drivers/crypto/intel/iaa/iaa_crypto_main.c | 15 +++++++--------
include/crypto/acompress.h | 6 ++++++
2 files changed, 13 insertions(+), 8 deletions(-)
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
index 7dab340c4a34..52fe68606f4d 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -1785,7 +1785,7 @@ static int iaa_compress(struct crypto_tfm *tfm, struct acomp_req *req,
" src_addr %llx, dst_addr %llx\n", __func__,
active_compression_mode->name,
src_addr, dst_addr);
- } else if (ctx->async_mode) {
+ } else if (ctx->async_mode && (req->base.flags & CRYPTO_ACOMP_REQ_POLL)) {
req->data = idxd_desc;
}
@@ -1807,7 +1807,7 @@ static int iaa_compress(struct crypto_tfm *tfm, struct acomp_req *req,
update_total_comp_calls();
update_wq_comp_calls(wq);
- if (ctx->async_mode) {
+ if (ctx->async_mode && (req->base.flags & CRYPTO_ACOMP_REQ_POLL)) {
ret = -EINPROGRESS;
dev_dbg(dev, "%s: returning -EINPROGRESS\n", __func__);
goto out;
@@ -1836,8 +1836,7 @@ static int iaa_compress(struct crypto_tfm *tfm, struct acomp_req *req,
static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
struct idxd_wq *wq,
dma_addr_t src_addr, unsigned int slen,
- dma_addr_t dst_addr, unsigned int *dlen,
- bool disable_async)
+ dma_addr_t dst_addr, unsigned int *dlen)
{
struct iaa_device_compression_mode *active_compression_mode;
struct iaa_compression_ctx *ctx = crypto_tfm_ctx(tfm);
@@ -1886,7 +1885,7 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
desc->src1_size = slen;
desc->completion_addr = idxd_desc->compl_dma;
- if (ctx->use_irq && !disable_async) {
+ if (ctx->use_irq) {
desc->flags |= IDXD_OP_FLAG_RCI;
idxd_desc->crypto.req = req;
@@ -1899,7 +1898,7 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
" src_addr %llx, dst_addr %llx\n", __func__,
active_compression_mode->name,
src_addr, dst_addr);
- } else if (ctx->async_mode && !disable_async) {
+ } else if (ctx->async_mode && (req->base.flags & CRYPTO_ACOMP_REQ_POLL)) {
req->data = idxd_desc;
}
@@ -1921,7 +1920,7 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
update_total_decomp_calls();
update_wq_decomp_calls(wq);
- if (ctx->async_mode && !disable_async) {
+ if (ctx->async_mode && (req->base.flags & CRYPTO_ACOMP_REQ_POLL)) {
ret = -EINPROGRESS;
dev_dbg(dev, "%s: returning -EINPROGRESS\n", __func__);
goto out;
@@ -2127,7 +2126,7 @@ static int iaa_comp_adecompress(struct acomp_req *req)
req->dst, req->dlen, sg_dma_len(req->dst));
ret = iaa_decompress(tfm, req, wq, src_addr, req->slen,
- dst_addr, &req->dlen, false);
+ dst_addr, &req->dlen);
if (ret == -EINPROGRESS)
return ret;
diff --git a/include/crypto/acompress.h b/include/crypto/acompress.h
index 01389fd7055f..939e51d122b0 100644
--- a/include/crypto/acompress.h
+++ b/include/crypto/acompress.h
@@ -20,6 +20,12 @@
#include <linux/spinlock_types.h>
#include <linux/types.h>
+/*
+ * If set, the driver must have a way to submit the req, then
+ * poll its completion status for success/error.
+ */
+#define CRYPTO_ACOMP_REQ_POLL 0x00000001
+
/* Set this bit if source is virtual address instead of SG list. */
#define CRYPTO_ACOMP_REQ_SRC_VIRT 0x00000002
--
2.27.0
Powered by blists - more mailing lists