DMA Engine development
 help / color / mirror / Atom feed
From: Yi Sun <yi.sun@intel.com>
To: dave.jiang@intel.com, vinicius.gomes@intel.com,
	dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: yi.sun@intel.com, gordon.jin@intel.com, fenghuay@nvidia.com,
	anil.s.keshavamurthy@intel.com, philip.lantz@intel.com
Subject: [PATCH 2/2] dmaengine: idxd: Add Max SGL Size Support for DSA3.0
Date: Sat, 14 Jun 2025 00:18:34 +0800	[thread overview]
Message-ID: <20250613161834.2912353-3-yi.sun@intel.com> (raw)
In-Reply-To: <20250613161834.2912353-1-yi.sun@intel.com>

Certain DSA 3.0 opcodes, such as Gather copy and Gather reduce requires max
SGL configured for workqueues prior to support these opcodes.

Configure the maximum scatter-gather list (SGL) size for workqueues during
setup on the supported HW. Application can then properly handle the SGL
size without explicitly setting it.

Signed-off-by: Yi Sun <yi.sun@intel.com>
Co-developed-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Signed-off-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>

diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 5cf419fe6b46..1c10b030bea7 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -375,6 +375,7 @@ static void idxd_wq_disable_cleanup(struct idxd_wq *wq)
 	memset(wq->name, 0, WQ_NAME_SIZE);
 	wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER;
 	idxd_wq_set_max_batch_size(idxd->data->type, wq, WQ_DEFAULT_MAX_BATCH);
+	idxd_wq_set_init_max_sgl_size(idxd, wq);
 	if (wq->opcap_bmap)
 		bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS);
 }
@@ -974,6 +975,8 @@ static int idxd_wq_config_write(struct idxd_wq *wq)
 	/* bytes 12-15 */
 	wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes);
 	idxd_wqcfg_set_max_batch_shift(idxd->data->type, wq->wqcfg, ilog2(wq->max_batch_size));
+	if (idxd_sgl_supported(idxd))
+		wq->wqcfg->max_sgl_shift = ilog2(wq->max_sgl_size);
 
 	/* bytes 32-63 */
 	if (idxd->hw.wq_cap.op_config && wq->opcap_bmap) {
@@ -1152,6 +1155,8 @@ static int idxd_wq_load_config(struct idxd_wq *wq)
 
 	wq->max_xfer_bytes = 1ULL << wq->wqcfg->max_xfer_shift;
 	idxd_wq_set_max_batch_size(idxd->data->type, wq, 1U << wq->wqcfg->max_batch_shift);
+	if (idxd_sgl_supported(idxd))
+		wq->max_sgl_size = 1U << wq->wqcfg->max_sgl_shift;
 
 	for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
 		wqcfg_offset = WQCFG_OFFSET(idxd, wq->id, i);
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index cc0a3fe1c957..fe5af50b58a4 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -227,6 +227,7 @@ struct idxd_wq {
 	char name[WQ_NAME_SIZE + 1];
 	u64 max_xfer_bytes;
 	u32 max_batch_size;
+	u32 max_sgl_size;
 
 	/* Lock to protect upasid_xa access. */
 	struct mutex uc_lock;
@@ -348,6 +349,7 @@ struct idxd_device {
 
 	u64 max_xfer_bytes;
 	u32 max_batch_size;
+	u32 max_sgl_size;
 	int max_groups;
 	int max_engines;
 	int max_rdbufs;
@@ -692,6 +694,20 @@ static inline void idxd_wq_set_max_batch_size(int idxd_type, struct idxd_wq *wq,
 		wq->max_batch_size = max_batch_size;
 }
 
+static bool idxd_sgl_supported(struct idxd_device *idxd)
+{
+	return idxd->hw.dsacap0.sgl_formats &&
+	       idxd->data->type == IDXD_TYPE_DSA &&
+	       idxd->hw.version >= DEVICE_VERSION_3;
+}
+
+static inline void idxd_wq_set_init_max_sgl_size(struct idxd_device *idxd,
+						 struct idxd_wq *wq)
+{
+	if (idxd_sgl_supported(idxd))
+		wq->max_sgl_size = 1U << idxd->hw.dsacap0.max_sgl_shift;
+}
+
 static inline void idxd_wqcfg_set_max_batch_shift(int idxd_type, union wqcfg *wqcfg,
 						  u32 max_batch_shift)
 {
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index cc8203320d40..f37a7d7b537a 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -217,6 +217,7 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 		init_completion(&wq->wq_resurrect);
 		wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER;
 		idxd_wq_set_max_batch_size(idxd->data->type, wq, WQ_DEFAULT_MAX_BATCH);
+		idxd_wq_set_init_max_sgl_size(idxd, wq);
 		wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES;
 		wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev));
 		if (!wq->wqcfg) {
@@ -585,6 +586,10 @@ static void idxd_read_caps(struct idxd_device *idxd)
 	idxd->hw.dsacap0.bits = ioread64(idxd->reg_base + IDXD_DSACAP0_OFFSET);
 	idxd->hw.dsacap1.bits = ioread64(idxd->reg_base + IDXD_DSACAP1_OFFSET);
 	idxd->hw.dsacap2.bits = ioread64(idxd->reg_base + IDXD_DSACAP2_OFFSET);
+	if (idxd_sgl_supported(idxd)) {
+		idxd->max_sgl_size = 1U << idxd->hw.dsacap0.max_sgl_shift;
+		dev_dbg(dev, "max sgl size: %u\n", idxd->max_sgl_size);
+	}
 
 	/* read iaa cap */
 	if (idxd->data->type == IDXD_TYPE_IAX && idxd->hw.version >= DEVICE_VERSION_2)
diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h
index 45485ecd7bb6..0401cfc95f27 100644
--- a/drivers/dma/idxd/registers.h
+++ b/drivers/dma/idxd/registers.h
@@ -385,7 +385,8 @@ union wqcfg {
 		/* bytes 12-15 */
 		u32 max_xfer_shift:5;
 		u32 max_batch_shift:4;
-		u32 rsvd4:23;
+		u32 max_sgl_shift:4;
+		u32 rsvd4:19;
 
 		/* bytes 16-19 */
 		u16 occupancy_inth;
@@ -585,6 +586,15 @@ union evl_status_reg {
 
 #define IDXD_DSACAP0_OFFSET		0x180
 union dsacap0_reg {
+	struct {
+		u64 max_sgl_shift:4;
+		u64 max_gr_block_shift:4;
+		u64 ops_inter_domain:7;
+		u64 rsvd1:17;
+		u64 sgl_formats:16;
+		u64 max_sg_process:8;
+		u64 rsvd2:8;
+	};
 	u64 bits;
 };
 
-- 
2.43.0


  parent reply	other threads:[~2025-06-13 16:19 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-13 16:18 [PATCH 0/2] dmaengine: idxd: Add basic DSA 3.0 capability and SGL support Yi Sun
2025-06-13 16:18 ` [PATCH 1/2] dmaengine: idxd: Expose DSA3.0 capabilities through sysfs Yi Sun
2025-06-13 20:59   ` Dave Jiang
2025-06-14 10:01     ` Yi Sun
2025-06-13 21:43   ` Fenghua Yu
2025-06-13 22:07   ` Fenghua Yu
2025-06-13 22:26     ` Lantz, Philip
2025-06-16 18:08       ` Fenghua Yu
2025-06-19  2:51         ` Sun, Yi
2025-06-13 16:18 ` Yi Sun [this message]
2025-06-13 21:00   ` [PATCH 2/2] dmaengine: idxd: Add Max SGL Size Support for DSA3.0 Dave Jiang
2025-06-13 22:03   ` Fenghua Yu
2025-06-14  7:56     ` Yi Sun

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=20250613161834.2912353-3-yi.sun@intel.com \
    --to=yi.sun@intel.com \
    --cc=anil.s.keshavamurthy@intel.com \
    --cc=dave.jiang@intel.com \
    --cc=dmaengine@vger.kernel.org \
    --cc=fenghuay@nvidia.com \
    --cc=gordon.jin@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=philip.lantz@intel.com \
    --cc=vinicius.gomes@intel.com \
    /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