@@ -21,6 +21,9 @@
#define IAA_COMPLETION_TIMEOUT 1000000
+#define IAA_ALLOC_DESC_COMP_TIMEOUT 1000
+#define IAA_ALLOC_DESC_DECOMP_TIMEOUT 500
+
#define IAA_ANALYTICS_ERROR 0x0a
#define IAA_ERROR_DECOMP_BUF_OVERFLOW 0x0b
#define IAA_ERROR_COMP_BUF_OVERFLOW 0x19
@@ -1416,6 +1416,7 @@ static int deflate_generic_decompress(struct acomp_req *req)
ACOMP_REQUEST_ON_STACK(fbreq, crypto_acomp_reqtfm(req));
int ret;
+ req->dlen = PAGE_SIZE;
acomp_request_set_callback(fbreq, 0, NULL, NULL);
acomp_request_set_params(fbreq, req->src, req->dst, req->slen,
req->dlen);
@@ -1536,7 +1537,8 @@ static int iaa_compress_verify(struct crypto_tfm *tfm, struct acomp_req *req,
struct iaa_device_compression_mode *active_compression_mode;
struct iaa_compression_ctx *ctx = crypto_tfm_ctx(tfm);
struct iaa_device *iaa_device;
- struct idxd_desc *idxd_desc;
+ struct idxd_desc *idxd_desc = ERR_PTR(-EAGAIN);
+ u16 alloc_desc_retries = 0;
struct iax_hw_desc *desc;
struct idxd_device *idxd;
struct iaa_wq *iaa_wq;
@@ -1552,7 +1554,11 @@ static int iaa_compress_verify(struct crypto_tfm *tfm, struct acomp_req *req,
active_compression_mode = get_iaa_device_compression_mode(iaa_device, ctx->mode);
- idxd_desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
+ while ((idxd_desc == ERR_PTR(-EAGAIN)) && (alloc_desc_retries++ < IAA_ALLOC_DESC_DECOMP_TIMEOUT)) {
+ idxd_desc = idxd_alloc_desc(wq, IDXD_OP_NONBLOCK);
+ cpu_relax();
+ }
+
if (IS_ERR(idxd_desc)) {
dev_dbg(dev, "idxd descriptor allocation failed\n");
dev_dbg(dev, "iaa compress failed: ret=%ld\n",
@@ -1604,14 +1610,10 @@ static int iaa_compress_verify(struct crypto_tfm *tfm, struct acomp_req *req,
goto err;
}
- idxd_free_desc(wq, idxd_desc);
-out:
- return ret;
err:
idxd_free_desc(wq, idxd_desc);
- dev_dbg(dev, "iaa compress failed: ret=%d\n", ret);
- goto out;
+ return ret;
}
static void iaa_desc_complete(struct idxd_desc *idxd_desc,
@@ -1727,7 +1729,8 @@ static int iaa_compress(struct crypto_tfm *tfm, struct acomp_req *req,
struct iaa_device_compression_mode *active_compression_mode;
struct iaa_compression_ctx *ctx = crypto_tfm_ctx(tfm);
struct iaa_device *iaa_device;
- struct idxd_desc *idxd_desc;
+ struct idxd_desc *idxd_desc = ERR_PTR(-EAGAIN);
+ u16 alloc_desc_retries = 0;
struct iax_hw_desc *desc;
struct idxd_device *idxd;
struct iaa_wq *iaa_wq;
@@ -1743,7 +1746,11 @@ static int iaa_compress(struct crypto_tfm *tfm, struct acomp_req *req,
active_compression_mode = get_iaa_device_compression_mode(iaa_device, ctx->mode);
- idxd_desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
+ while ((idxd_desc == ERR_PTR(-EAGAIN)) && (alloc_desc_retries++ < IAA_ALLOC_DESC_COMP_TIMEOUT)) {
+ idxd_desc = idxd_alloc_desc(wq, IDXD_OP_NONBLOCK);
+ cpu_relax();
+ }
+
if (IS_ERR(idxd_desc)) {
dev_dbg(dev, "idxd descriptor allocation failed\n");
dev_dbg(dev, "iaa compress failed: ret=%ld\n", PTR_ERR(idxd_desc));
@@ -1820,15 +1827,10 @@ static int iaa_compress(struct crypto_tfm *tfm, struct acomp_req *req,
*compression_crc = idxd_desc->iax_completion->crc;
- if (!ctx->async_mode)
- idxd_free_desc(wq, idxd_desc);
-out:
- return ret;
err:
idxd_free_desc(wq, idxd_desc);
- dev_dbg(dev, "iaa compress failed: ret=%d\n", ret);
-
- goto out;
+out:
+ return ret;
}
static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
@@ -1840,7 +1842,8 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
struct iaa_device_compression_mode *active_compression_mode;
struct iaa_compression_ctx *ctx = crypto_tfm_ctx(tfm);
struct iaa_device *iaa_device;
- struct idxd_desc *idxd_desc;
+ struct idxd_desc *idxd_desc = ERR_PTR(-EAGAIN);
+ u16 alloc_desc_retries = 0;
struct iax_hw_desc *desc;
struct idxd_device *idxd;
struct iaa_wq *iaa_wq;
@@ -1856,12 +1859,18 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
active_compression_mode = get_iaa_device_compression_mode(iaa_device, ctx->mode);
- idxd_desc = idxd_alloc_desc(wq, IDXD_OP_BLOCK);
+ while ((idxd_desc == ERR_PTR(-EAGAIN)) && (alloc_desc_retries++ < IAA_ALLOC_DESC_DECOMP_TIMEOUT)) {
+ idxd_desc = idxd_alloc_desc(wq, IDXD_OP_NONBLOCK);
+ cpu_relax();
+ }
+
if (IS_ERR(idxd_desc)) {
dev_dbg(dev, "idxd descriptor allocation failed\n");
dev_dbg(dev, "iaa decompress failed: ret=%ld\n",
PTR_ERR(idxd_desc));
- return PTR_ERR(idxd_desc);
+ ret = PTR_ERR(idxd_desc);
+ idxd_desc = NULL;
+ goto fallback_software_decomp;
}
desc = idxd_desc->iax_hw;
@@ -1905,7 +1914,7 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
ret = idxd_submit_desc(wq, idxd_desc);
if (ret) {
dev_dbg(dev, "submit_desc failed ret=%d\n", ret);
- goto err;
+ goto fallback_software_decomp;
}
/* Update stats */
@@ -1919,40 +1928,37 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
}
ret = check_completion(dev, idxd_desc->iax_completion, false, false);
+
+fallback_software_decomp:
if (ret) {
- dev_dbg(dev, "%s: check_completion failed ret=%d\n", __func__, ret);
- if (idxd_desc->iax_completion->status == IAA_ANALYTICS_ERROR) {
+ dev_dbg(dev, "%s: desc allocation/submission/check_completion failed ret=%d\n", __func__, ret);
+ if (idxd_desc && idxd_desc->iax_completion->status == IAA_ANALYTICS_ERROR) {
pr_warn("%s: falling back to deflate-generic decompress, "
"analytics error code %x\n", __func__,
idxd_desc->iax_completion->error_code);
- ret = deflate_generic_decompress(req);
- if (ret) {
- dev_dbg(dev, "%s: deflate-generic failed ret=%d\n",
- __func__, ret);
- goto err;
- }
- } else {
+ }
+
+ ret = deflate_generic_decompress(req);
+
+ if (ret) {
+ pr_err("%s: iaa decompress failed: deflate-generic fallback to software decompress error ret=%d\n", __func__, ret);
goto err;
}
} else {
req->dlen = idxd_desc->iax_completion->output_size;
+
+ /* Update stats */
+ update_total_decomp_bytes_in(slen);
+ update_wq_decomp_bytes(wq, slen);
}
*dlen = req->dlen;
- if (!ctx->async_mode || disable_async)
+err:
+ if (idxd_desc)
idxd_free_desc(wq, idxd_desc);
-
- /* Update stats */
- update_total_decomp_bytes_in(slen);
- update_wq_decomp_bytes(wq, slen);
out:
return ret;
-err:
- idxd_free_desc(wq, idxd_desc);
- dev_dbg(dev, "iaa decompress failed: ret=%d\n", ret);
-
- goto out;
}
static int iaa_comp_acompress(struct acomp_req *req)
This patch modifies the descriptor allocation from blocking to non-blocking with bounded retries or "timeouts". This is necessary to prevent task blocked errors in high contention scenarios, for instance, when the platform has only 1 IAA device enabled. With 1 IAA device enabled per package on a dual-package Sapphire Rapids with 56 cores/package, there are 112 logical cores mapped to this single IAA device. In this scenario, the task blocked errors can occur because idxd_alloc_desc() is called with IDXD_OP_BLOCK. With batching, multiple descriptors will need to be allocated per batch. Any process that is able to do so, can cause contention for allocating descriptors for all other processes that share the use of the same sbitmap_queue. Under IDXD_OP_BLOCK, this can cause compress/decompress jobs to stall in stress test scenarios (e.g. zswap_store() of 2M folios). In order to make the iaa_crypto driver be more fail-safe, this commit implements the following: 1) Change compress/decompress descriptor allocations to be non-blocking with retries ("timeouts"). 2) Return compress error to zswap if descriptor allocation with timeouts fails during compress ops. zswap_store() will return an error and the folio gets stored in the backing swap device. 3) Fallback to software decompress if descriptor allocation with timeouts fails during decompress ops. With these fixes, there are no task blocked errors seen under stress testing conditions, and no performance degradation observed. This patch also simplifies the success/error return paths in iaa_[de]compress() and iaa_compress_verify(). Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com> --- drivers/crypto/intel/iaa/iaa_crypto.h | 3 + drivers/crypto/intel/iaa/iaa_crypto_main.c | 84 ++++++++++++---------- 2 files changed, 48 insertions(+), 39 deletions(-)