From: Raja Zidane <rzidane@nvidia.com>
To: <dev@dpdk.org>
Cc: <matan@nvidia.com>, <stable@dpdk.org>
Subject: [PATCH] compress/mlx5: support out-of-space status
Date: Wed, 23 Feb 2022 15:31:42 +0200 [thread overview]
Message-ID: <20220223133142.13407-1-rzidane@nvidia.com> (raw)
When trying to dequeue, an OP may fail due to insufficient space for the
OP output, the compressdev API defines out-of-space for OP status.
The driver can detect out-of-space errors and report them to the user.
Check if hw_error_syndrome specifies out-of-space and set the OP
status accordingly.
Also added an error message for a case of missing B-final flag.
Fixes: f8c97babc9f4 ("compress/mlx5: add data-path functions")
Cc: stable@dpdk.org
Signed-off-by: Raja Zidane <rzidane@nvidia.com>
---
Acked-by: Matan Azrad matan@nvidia.com
drivers/common/mlx5/mlx5_prm.h | 5 +++++
drivers/compress/mlx5/mlx5_compress.c | 12 +++++++++++-
2 files changed, 16 insertions(+), 1 deletion(-)
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_prm.h
index 495b63191a..fc05734ecd 100644
--- a/drivers/common/mlx5/mlx5_prm.h
+++ b/drivers/common/mlx5/mlx5_prm.h
@@ -249,6 +249,9 @@
/* Maximum number of DS in WQE. Limited by 6-bit field. */
#define MLX5_DSEG_MAX 63
+/* The 32 bit syndrome offset in struct mlx5_err_cqe. */
+#define MLX5_ERROR_CQE_SYNDROME_OFFSET 52
+
/* The completion mode offset in the WQE control segment line 2. */
#define MLX5_COMP_MODE_OFFSET 2
@@ -559,6 +562,8 @@ struct mlx5_rdma_write_wqe {
#define MLX5_GGA_COMP_LOG_BLOCK_SIZE_MAX 15u
#define MLX5_GGA_COMP_LOG_DYNAMIC_SIZE_MAX 15u
#define MLX5_GGA_COMP_LOG_DYNAMIC_SIZE_MIN 0u
+#define MLX5_GGA_COMP_OUT_OF_SPACE_SYNDROME_BE 0x29D0084
+#define MLX5_GGA_COMP_MISSING_BFINAL_SYNDROME_BE 0x29D0011
struct mlx5_wqe_metadata_seg {
uint32_t mmo_control_31_0; /* mmo_control_63_32 is in ctrl_seg.imm */
diff --git a/drivers/compress/mlx5/mlx5_compress.c b/drivers/compress/mlx5/mlx5_compress.c
index 7a482c3fbb..fc50b5bde9 100644
--- a/drivers/compress/mlx5/mlx5_compress.c
+++ b/drivers/compress/mlx5/mlx5_compress.c
@@ -562,7 +562,17 @@ mlx5_compress_cqe_err_handle(struct mlx5_compress_qp *qp,
qp->qp.wqes;
volatile struct mlx5_gga_compress_opaque *opaq = qp->opaque_mr.addr;
- op->status = RTE_COMP_OP_STATUS_ERROR;
+ volatile uint32_t *synd_word = RTE_PTR_ADD(cqe, MLX5_ERROR_CQE_SYNDROME_OFFSET);
+ switch (*synd_word) {
+ case MLX5_GGA_COMP_OUT_OF_SPACE_SYNDROME_BE:
+ op->status = RTE_COMP_OP_STATUS_OUT_OF_SPACE_TERMINATED;
+ DRV_LOG(DEBUG, "OUT OF SPACE error, output is bigger than dst buffer.");
+ break;
+ case MLX5_GGA_COMP_MISSING_BFINAL_SYNDROME_BE:
+ DRV_LOG(DEBUG, "The last compressed block missed the B-final flag; maybe the compressed data is not complete or garbaged?");
+ default:
+ op->status = RTE_COMP_OP_STATUS_ERROR;
+ }
op->consumed = 0;
op->produced = 0;
op->output_chksum = 0;
--
2.21.0
next reply other threads:[~2022-02-23 13:31 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-23 13:31 Raja Zidane [this message]
2022-02-27 14:00 ` [PATCH V2] " Raja Zidane
2022-03-04 9:47 ` [EXT] " Akhil Goyal
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220223133142.13407-1-rzidane@nvidia.com \
--to=rzidane@nvidia.com \
--cc=dev@dpdk.org \
--cc=matan@nvidia.com \
--cc=stable@dpdk.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).