All of lore.kernel.org
 help / color / mirror / Atom feed
From: Michael Baum <michaelba@nvidia.com>
To: <dev@dpdk.org>
Cc: Matan Azrad <matan@nvidia.com>, Akhil Goyal <gakhil@marvell.com>,
	"Thomas Monjalon" <thomas@monjalon.net>
Subject: [PATCH v2 4/8] compress/mlx5: support new metadata layout added in BF3
Date: Thu, 2 Feb 2023 18:25:33 +0200	[thread overview]
Message-ID: <20230202162537.1067595-5-michaelba@nvidia.com> (raw)
In-Reply-To: <20230202162537.1067595-1-michaelba@nvidia.com>

Commit [1] add support in Bluefield-3, but Bluefield-3 has different
GGA opaque structure than Bluefield-2.

This patch updates the PRM structure to include both versions, and
culculate the relevant offset for each version in control path.

Commit [1] 559014f232b4 ("compress/mlx5: add Bluefield-3 device ID")

Signed-off-by: Michael Baum <michaelba@nvidia.com>
---
 drivers/common/mlx5/mlx5_devx_cmds.c  |  6 ++--
 drivers/common/mlx5/mlx5_devx_cmds.h  |  3 +-
 drivers/common/mlx5/mlx5_prm.h        | 40 +++++++++++++++---------
 drivers/compress/mlx5/mlx5_compress.c | 45 +++++++++++++++++----------
 4 files changed, 61 insertions(+), 33 deletions(-)

diff --git a/drivers/common/mlx5/mlx5_devx_cmds.c b/drivers/common/mlx5/mlx5_devx_cmds.c
index 59cebb530f..dfec4dcf1b 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.c
+++ b/drivers/common/mlx5/mlx5_devx_cmds.c
@@ -978,8 +978,10 @@ mlx5_devx_cmd_query_hca_attr(void *ctx,
 	attr->mmo_dma_qp_en = MLX5_GET(cmd_hca_cap, hcattr, dma_mmo_qp);
 	attr->mmo_compress_qp_en = MLX5_GET(cmd_hca_cap, hcattr,
 			compress_mmo_qp);
-	attr->mmo_decompress_qp_en = MLX5_GET(cmd_hca_cap, hcattr,
-			decompress_mmo_qp);
+	attr->decomp_deflate_v1_en = MLX5_GET(cmd_hca_cap, hcattr,
+					      decompress_deflate_v1);
+	attr->decomp_deflate_v2_en = MLX5_GET(cmd_hca_cap, hcattr,
+					      decompress_deflate_v2);
 	attr->compress_min_block_size = MLX5_GET(cmd_hca_cap, hcattr,
 						 compress_min_block_size);
 	attr->log_max_mmo_dma = MLX5_GET(cmd_hca_cap, hcattr, log_dma_mmo_size);
diff --git a/drivers/common/mlx5/mlx5_devx_cmds.h b/drivers/common/mlx5/mlx5_devx_cmds.h
index c94b9eac06..edb387e272 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.h
+++ b/drivers/common/mlx5/mlx5_devx_cmds.h
@@ -259,7 +259,8 @@ struct mlx5_hca_attr {
 	uint32_t mmo_decompress_sq_en:1;
 	uint32_t mmo_dma_qp_en:1;
 	uint32_t mmo_compress_qp_en:1;
-	uint32_t mmo_decompress_qp_en:1;
+	uint32_t decomp_deflate_v1_en:1;
+	uint32_t decomp_deflate_v2_en:1;
 	uint32_t mmo_regex_qp_en:1;
 	uint32_t mmo_regex_sq_en:1;
 	uint32_t compress_min_block_size:4;
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_prm.h
index 2b5c43ee6e..377cbfab87 100644
--- a/drivers/common/mlx5/mlx5_prm.h
+++ b/drivers/common/mlx5/mlx5_prm.h
@@ -607,17 +607,27 @@ struct mlx5_gga_wqe {
 	struct mlx5_wqe_dseg scatter;
 } __rte_packed;
 
-struct mlx5_gga_compress_opaque {
-	uint32_t syndrom;
-	uint32_t reserved0;
-	uint32_t scattered_length;
-	uint32_t gathered_length;
-	uint64_t scatter_crc;
-	uint64_t gather_crc;
-	uint32_t crc32;
-	uint32_t adler32;
-	uint8_t reserved1[216];
-} __rte_packed;
+union mlx5_gga_compress_opaque {
+	struct {
+		uint32_t syndrome;
+		uint32_t reserved0;
+		uint32_t scattered_length;
+		union {
+			struct {
+				uint32_t reserved1[5];
+				uint32_t crc32;
+				uint32_t adler32;
+			} v1 __rte_packed;
+			struct {
+				uint32_t crc32;
+				uint32_t adler32;
+				uint32_t crc32c;
+				uint32_t xxh32;
+			} v2 __rte_packed;
+		};
+	} __rte_packed;
+	uint32_t data[64];
+};
 
 struct mlx5_ifc_regexp_mmo_control_bits {
 	uint8_t reserved_at_31[0x2];
@@ -1463,7 +1473,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8 log_max_bsf_list_size[0x6];
 	u8 umr_extended_translation_offset[0x1];
 	u8 null_mkey[0x1];
-	u8 log_max_klm_list_size[0x6];
+	u8 log_maxklm_list_size[0x6];
 	u8 non_wire_sq[0x1];
 	u8 reserved_at_121[0x9];
 	u8 log_max_ra_req_dc[0x6];
@@ -1749,8 +1759,10 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8 dma_mmo_qp[0x1];
 	u8 regexp_mmo_qp[0x1];
 	u8 compress_mmo_qp[0x1];
-	u8 decompress_mmo_qp[0x1];
-	u8 reserved_at_74c[0x14];
+	u8 decompress_deflate_v1[0x1];
+	u8 reserved_at_74c[0x4];
+	u8 decompress_deflate_v2[0x1];
+	u8 reserved_at_751[0xf];
 	u8 reserved_at_760[0x3];
 	u8 log_max_num_header_modify_argument[0x5];
 	u8 log_header_modify_argument_granularity_offset[0x4];
diff --git a/drivers/compress/mlx5/mlx5_compress.c b/drivers/compress/mlx5/mlx5_compress.c
index c4bf62ed41..11fad72a4f 100644
--- a/drivers/compress/mlx5/mlx5_compress.c
+++ b/drivers/compress/mlx5/mlx5_compress.c
@@ -55,6 +55,7 @@ struct mlx5_compress_priv {
 	uint32_t mmo_dma_sq:1;
 	uint32_t mmo_dma_qp:1;
 	uint32_t log_block_sz;
+	uint32_t crc32_opaq_offs;
 };
 
 struct mlx5_compress_qp {
@@ -157,7 +158,7 @@ mlx5_compress_init_qp(struct mlx5_compress_qp *qp)
 {
 	volatile struct mlx5_gga_wqe *restrict wqe =
 				    (volatile struct mlx5_gga_wqe *)qp->qp.wqes;
-	volatile struct mlx5_gga_compress_opaque *opaq = qp->opaque_mr.addr;
+	volatile union mlx5_gga_compress_opaque *opaq = qp->opaque_mr.addr;
 	const uint32_t sq_ds = rte_cpu_to_be_32((qp->qp.qp->id << 8) | 4u);
 	const uint32_t flags = RTE_BE32(MLX5_COMP_ALWAYS <<
 					MLX5_COMP_MODE_OFFSET);
@@ -211,8 +212,8 @@ mlx5_compress_qp_setup(struct rte_compressdev *dev, uint16_t qp_id,
 		goto err;
 	}
 	opaq_buf = rte_calloc(__func__, (size_t)1 << log_ops_n,
-			      sizeof(struct mlx5_gga_compress_opaque),
-			      sizeof(struct mlx5_gga_compress_opaque));
+			      sizeof(union mlx5_gga_compress_opaque),
+			      sizeof(union mlx5_gga_compress_opaque));
 	if (opaq_buf == NULL) {
 		DRV_LOG(ERR, "Failed to allocate opaque memory.");
 		rte_errno = ENOMEM;
@@ -225,7 +226,7 @@ mlx5_compress_qp_setup(struct rte_compressdev *dev, uint16_t qp_id,
 	qp->ops = (struct rte_comp_op **)RTE_ALIGN((uintptr_t)(qp + 1),
 						   RTE_CACHE_LINE_SIZE);
 	if (mlx5_common_verbs_reg_mr(priv->cdev->pd, opaq_buf, qp->entries_n *
-					sizeof(struct mlx5_gga_compress_opaque),
+					sizeof(union mlx5_gga_compress_opaque),
 							 &qp->opaque_mr) != 0) {
 		rte_free(opaq_buf);
 		DRV_LOG(ERR, "Failed to register opaque MR.");
@@ -544,7 +545,7 @@ mlx5_compress_dump_err_objs(volatile uint32_t *cqe, volatile uint32_t *wqe,
 		DRV_LOG(ERR, "%08X %08X %08X %08X", wqe[i], wqe[i + 1],
 			wqe[i + 2], wqe[i + 3]);
 	DRV_LOG(ERR, "\nError opaq:");
-	for (i = 0; i < sizeof(struct mlx5_gga_compress_opaque) >> 2; i += 4)
+	for (i = 0; i < sizeof(union mlx5_gga_compress_opaque) >> 2; i += 4)
 		DRV_LOG(ERR, "%08X %08X %08X %08X", opaq[i], opaq[i + 1],
 			opaq[i + 2], opaq[i + 3]);
 }
@@ -558,7 +559,7 @@ mlx5_compress_cqe_err_handle(struct mlx5_compress_qp *qp,
 							      &qp->cq.cqes[idx];
 	volatile struct mlx5_gga_wqe *wqes = (volatile struct mlx5_gga_wqe *)
 								    qp->qp.wqes;
-	volatile struct mlx5_gga_compress_opaque *opaq = qp->opaque_mr.addr;
+	volatile union mlx5_gga_compress_opaque *opaq = qp->opaque_mr.addr;
 
 	volatile uint32_t *synd_word = RTE_PTR_ADD(cqe, MLX5_ERROR_CQE_SYNDROME_OFFSET);
 	switch (*synd_word) {
@@ -575,7 +576,7 @@ mlx5_compress_cqe_err_handle(struct mlx5_compress_qp *qp,
 	op->consumed = 0;
 	op->produced = 0;
 	op->output_chksum = 0;
-	op->debug_status = rte_be_to_cpu_32(opaq[idx].syndrom) |
+	op->debug_status = rte_be_to_cpu_32(opaq[idx].syndrome) |
 			      ((uint64_t)rte_be_to_cpu_32(cqe->syndrome) << 32);
 	mlx5_compress_dump_err_objs((volatile uint32_t *)cqe,
 				 (volatile uint32_t *)&wqes[idx],
@@ -590,13 +591,14 @@ mlx5_compress_dequeue_burst(void *queue_pair, struct rte_comp_op **ops,
 	struct mlx5_compress_qp *qp = queue_pair;
 	volatile struct mlx5_compress_xform *restrict xform;
 	volatile struct mlx5_cqe *restrict cqe;
-	volatile struct mlx5_gga_compress_opaque *opaq = qp->opaque_mr.addr;
+	volatile union mlx5_gga_compress_opaque *opaq = qp->opaque_mr.addr;
 	struct rte_comp_op *restrict op;
 	const unsigned int cq_size = qp->entries_n;
 	const unsigned int mask = cq_size - 1;
 	uint32_t idx;
 	uint32_t next_idx = qp->ci & mask;
 	const uint16_t max = RTE_MIN((uint16_t)(qp->pi - qp->ci), nb_ops);
+	uint32_t crc32_idx = qp->priv->crc32_opaq_offs;
 	uint16_t i = 0;
 	int ret;
 
@@ -629,17 +631,17 @@ mlx5_compress_dequeue_burst(void *queue_pair, struct rte_comp_op **ops,
 			switch (xform->csum_type) {
 			case RTE_COMP_CHECKSUM_CRC32:
 				op->output_chksum = (uint64_t)rte_be_to_cpu_32
-						    (opaq[idx].crc32);
+						    (opaq[idx].data[crc32_idx]);
 				break;
 			case RTE_COMP_CHECKSUM_ADLER32:
 				op->output_chksum = (uint64_t)rte_be_to_cpu_32
-						    (opaq[idx].adler32);
+						(opaq[idx].data[crc32_idx + 1]);
 				break;
 			case RTE_COMP_CHECKSUM_CRC32_ADLER32:
 				op->output_chksum = (uint64_t)rte_be_to_cpu_32
-							     (opaq[idx].crc32) |
+						   (opaq[idx].data[crc32_idx]) |
 						     ((uint64_t)rte_be_to_cpu_32
-						     (opaq[idx].adler32) << 32);
+					 (opaq[idx].data[crc32_idx + 1]) << 32);
 				break;
 			default:
 				break;
@@ -717,15 +719,17 @@ mlx5_compress_dev_probe(struct mlx5_common_device *cdev,
 		.socket_id = cdev->dev->numa_node,
 	};
 	const char *ibdev_name = mlx5_os_get_ctx_device_name(cdev->ctx);
+	uint32_t crc32_opaq_offset;
 
 	if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
 		DRV_LOG(ERR, "Non-primary process type is not supported.");
 		rte_errno = ENOTSUP;
 		return -rte_errno;
 	}
-	if (!attr->mmo_decompress_qp_en && !attr->mmo_decompress_sq_en
-		&& !attr->mmo_compress_qp_en && !attr->mmo_compress_sq_en
-		&& !attr->mmo_dma_qp_en && !attr->mmo_dma_sq_en) {
+	if (!attr->decomp_deflate_v1_en && !attr->decomp_deflate_v2_en &&
+	    !attr->mmo_decompress_sq_en && !attr->mmo_compress_qp_en &&
+	    !attr->mmo_compress_sq_en && !attr->mmo_dma_qp_en &&
+	    !attr->mmo_dma_sq_en) {
 		DRV_LOG(ERR, "Not enough capabilities to support compress operations, maybe old FW/OFED version?");
 		rte_errno = ENOTSUP;
 		return -ENOTSUP;
@@ -746,11 +750,20 @@ mlx5_compress_dev_probe(struct mlx5_common_device *cdev,
 	priv = compressdev->data->dev_private;
 	priv->log_block_sz = devarg_prms.log_block_sz;
 	priv->mmo_decomp_sq = attr->mmo_decompress_sq_en;
-	priv->mmo_decomp_qp = attr->mmo_decompress_qp_en;
+	priv->mmo_decomp_qp =
+			attr->decomp_deflate_v1_en | attr->decomp_deflate_v2_en;
 	priv->mmo_comp_sq = attr->mmo_compress_sq_en;
 	priv->mmo_comp_qp = attr->mmo_compress_qp_en;
 	priv->mmo_dma_sq = attr->mmo_dma_sq_en;
 	priv->mmo_dma_qp = attr->mmo_dma_qp_en;
+	if (attr->decomp_deflate_v2_en)
+		crc32_opaq_offset = offsetof(union mlx5_gga_compress_opaque,
+					     v2.crc32);
+	else
+		crc32_opaq_offset = offsetof(union mlx5_gga_compress_opaque,
+					     v1.crc32);
+	MLX5_ASSERT((crc32_opaq_offset % 4) == 0);
+	priv->crc32_opaq_offs = crc32_opaq_offset / 4;
 	priv->cdev = cdev;
 	priv->compressdev = compressdev;
 	priv->min_block_size = attr->compress_min_block_size;
-- 
2.25.1


  parent reply	other threads:[~2023-02-02 16:26 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-01-09  7:58 [PATCH 0/7] compress/mlx5: add LZ4 support Michael Baum
2023-01-09  7:58 ` [PATCH 1/7] compress/mlx5: fix wrong output Adler-32 checksum offset Michael Baum
2023-01-09  7:58 ` [PATCH 2/7] compress/mlx5: fix QP setup for partial transformations Michael Baum
2023-01-09  7:58 ` [PATCH 3/7] compress/mlx5: support new metadata layout added in BF3 Michael Baum
2023-01-09  7:58 ` [PATCH 4/7] compress/mlx5: remove unused variable from priv structure Michael Baum
2023-01-09  7:58 ` [PATCH 5/7] compress/mlx5: add xform validate function Michael Baum
2023-01-09  7:58 ` [PATCH 6/7] common/mlx5: add LZ4 capabilities check Michael Baum
2023-01-09  7:58 ` [PATCH 7/7] compress/mlx5: add support for LZ4 algorithm Michael Baum
2023-02-02 16:25 ` [PATCH v2 0/8] compress/mlx5: add LZ4 support Michael Baum
2023-02-02 16:25   ` [PATCH v2 1/8] compress/mlx5: fix decompress xform validation Michael Baum
2023-02-02 16:25   ` [PATCH v2 2/8] compress/mlx5: fix wrong output Adler-32 checksum offset Michael Baum
2023-02-02 16:25   ` [PATCH v2 3/8] compress/mlx5: fix QP setup for partial transformations Michael Baum
2023-02-02 16:25   ` Michael Baum [this message]
2023-02-02 16:25   ` [PATCH v2 5/8] compress/mlx5: remove unused variable from priv structure Michael Baum
2023-02-02 16:25   ` [PATCH v2 6/8] compress/mlx5: add xform validate function Michael Baum
2023-02-02 16:25   ` [PATCH v2 7/8] common/mlx5: add LZ4 capabilities check Michael Baum
2023-02-02 16:25   ` [PATCH v2 8/8] compress/mlx5: add support for LZ4 algorithm Michael Baum
2023-02-21  7:07   ` [PATCH v3 0/8] compress/mlx5: add LZ4 support Michael Baum
2023-02-21  7:07     ` [PATCH v3 1/8] compress/mlx5: fix decompress xform validation Michael Baum
2023-02-21  7:07     ` [PATCH v3 2/8] compress/mlx5: fix wrong output Adler-32 checksum offset Michael Baum
2023-02-21  7:07     ` [PATCH v3 3/8] compress/mlx5: fix QP setup for partial transformations Michael Baum
2023-02-21  7:07     ` [PATCH v3 4/8] compress/mlx5: support new metadata layout added in BF3 Michael Baum
2023-02-21  7:07     ` [PATCH v3 5/8] compress/mlx5: remove unused variable from priv structure Michael Baum
2023-02-21  7:07     ` [PATCH v3 6/8] compress/mlx5: add xform validate function Michael Baum
2023-02-21  7:07     ` [PATCH v3 7/8] common/mlx5: add LZ4 capabilities check Michael Baum
2023-02-21  7:07     ` [PATCH v3 8/8] compress/mlx5: add support for LZ4 algorithm Michael Baum
2023-02-27 18:17     ` [EXT] [PATCH v3 0/8] compress/mlx5: add LZ4 support 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=20230202162537.1067595-5-michaelba@nvidia.com \
    --to=michaelba@nvidia.com \
    --cc=dev@dpdk.org \
    --cc=gakhil@marvell.com \
    --cc=matan@nvidia.com \
    --cc=thomas@monjalon.net \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.