public inbox for linux-rdma@vger.kernel.org
 help / color / mirror / Atom feed
From: Bob Pearson <rpearsonhpe@gmail.com>
To: jgg@nvidia.com, leon@kernel.org, zyjzyj2000@gmail.com,
	jhack@hpe.com, linux-rdma@vger.kernel.org
Cc: Bob Pearson <rpearsonhpe@gmail.com>
Subject: [PATCH for-next 08/17] RDMA/rxe: Add routine to compute number of frags for dma
Date: Thu, 27 Oct 2022 13:55:02 -0500	[thread overview]
Message-ID: <20221027185510.33808-9-rpearsonhpe@gmail.com> (raw)
In-Reply-To: <20221027185510.33808-1-rpearsonhpe@gmail.com>

Add routine named rxe_num_dma_frags() to compute the number of skb
frags needed to copy length bytes from a dma info struct.

Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
---
 drivers/infiniband/sw/rxe/rxe_loc.h |  4 +-
 drivers/infiniband/sw/rxe/rxe_mr.c  | 67 ++++++++++++++++++++++++++++-
 2 files changed, 69 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index c62fc2613a01..4c30ffaccc92 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -76,10 +76,12 @@ int rxe_copy_mr_data(struct sk_buff *skb, struct rxe_mr *mr, u64 iova,
 		     enum rxe_mr_copy_op op);
 int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, int length,
 		enum rxe_mr_copy_op op);
+int rxe_num_dma_frags(const struct rxe_pd *pd, const struct rxe_dma_info *dma,
+		      int length);
 int copy_data(struct rxe_pd *pd, int access, struct rxe_dma_info *dma,
 	      void *addr, int length, enum rxe_mr_copy_op op);
 void *iova_to_vaddr(struct rxe_mr *mr, u64 iova, int length);
-struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
+struct rxe_mr *lookup_mr(const struct rxe_pd *pd, int access, u32 key,
 			 enum rxe_mr_lookup_type type);
 int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length);
 int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index fd39b3e17f41..77437a0dd7ec 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -522,6 +522,71 @@ int rxe_copy_mr_data(struct sk_buff *skb, struct rxe_mr *mr, u64 iova,
 	return 0;
 }
 
+/**
+ * rxe_num_dma_frags() - Count the number of skb frags needed to copy
+ *			 length bytes from a dma info struct to an skb
+ * @pd: protection domain used by dma entries
+ * @dma: dma info
+ * @length: number of bytes to copy
+ *
+ * Returns: number of frags needed or negative error
+ */
+int rxe_num_dma_frags(const struct rxe_pd *pd, const struct rxe_dma_info *dma,
+		      int length)
+{
+	int cur_sge = dma->cur_sge;
+	const struct rxe_sge *sge = &dma->sge[cur_sge];
+	int buf_offset = dma->sge_offset;
+	int resid = dma->resid;
+	struct rxe_mr *mr = NULL;
+	int bytes;
+	u64 iova;
+	int ret;
+	int num_frags = 0;
+
+	if (length == 0)
+		return 0;
+
+	if (length > resid)
+		return -EINVAL;
+
+	while (length > 0) {
+		if (buf_offset >= sge->length) {
+			if (mr)
+				rxe_put(mr);
+
+			sge++;
+			cur_sge++;
+			buf_offset = 0;
+
+			if (cur_sge >= dma->num_sge)
+				return -ENOSPC;
+			if (!sge->length)
+				continue;
+		}
+
+		mr = lookup_mr(pd, 0, sge->lkey, RXE_LOOKUP_LOCAL);
+		if (!mr)
+			return -EINVAL;
+
+		bytes = min_t(int, length, sge->length - buf_offset);
+		if (bytes > 0) {
+			iova = sge->addr + buf_offset;
+			ret = rxe_num_mr_frags(mr, iova, length);
+			if (ret < 0) {
+				rxe_put(mr);
+				return ret;
+			}
+
+			buf_offset += bytes;
+			resid -= bytes;
+			length -= bytes;
+		}
+	}
+
+	return num_frags;
+}
+
 /* copy data in or out of a wqe, i.e. sg list
  * under the control of a dma descriptor
  */
@@ -658,7 +723,7 @@ int advance_dma_data(struct rxe_dma_info *dma, unsigned int length)
  * (3) verify that the mr can support the requested access
  * (4) verify that mr state is valid
  */
-struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
+struct rxe_mr *lookup_mr(const struct rxe_pd *pd, int access, u32 key,
 			 enum rxe_mr_lookup_type type)
 {
 	struct rxe_mr *mr;
-- 
2.34.1


  parent reply	other threads:[~2022-10-27 18:56 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-10-27 18:54 [PATCH for-next 00/17] RDMA/rxe: Enable scatter/gather support for skbs Bob Pearson
2022-10-27 18:54 ` [PATCH for-next 01/17] RDMA/rxe: Isolate code to fill request roce headers Bob Pearson
2022-10-27 18:54 ` [PATCH for-next 02/17] RDMA/rxe: Isolate request payload code in a subroutine Bob Pearson
2022-10-27 18:54 ` [PATCH for-next 03/17] RDMA/rxe: Isolate code to build request packet Bob Pearson
2022-10-30 18:52   ` kernel test robot
2022-10-27 18:54 ` [PATCH for-next 04/17] RDMA/rxe: Add sg fragment ops Bob Pearson
2022-10-27 18:54 ` [PATCH for-next 05/17] RDMA/rxe: Add rxe_add_frag() to rxe_mr.c Bob Pearson
2022-10-27 18:55 ` [PATCH for-next 06/17] RDMA/rxe: Add routine to compute the number of frags Bob Pearson
2022-10-27 18:55 ` [PATCH for-next 07/17] RDMA/rxe: Extend rxe_mr_copy to support skb frags Bob Pearson
2022-10-27 18:55 ` Bob Pearson [this message]
2022-10-27 18:55 ` [PATCH for-next 09/17] RDMA/rxe: Extend copy_data " Bob Pearson
2022-10-27 18:55 ` [PATCH for-next 10/17] RDMA/rxe: Replace rxe by qp as a parameter Bob Pearson
2022-10-27 18:55 ` [PATCH for-next 11/17] RDMA/rxe: Extend rxe_init_packet() to support frags Bob Pearson
2022-10-27 18:55 ` [PATCH for-next 12/17] RDMA/rxe: Extend rxe_icrc.c " Bob Pearson
2022-10-27 20:29   ` kernel test robot
2022-10-30 19:33   ` kernel test robot
2022-10-27 18:55 ` [PATCH for-next 13/17] RDMA/rxe: Extend rxe_init_req_packet() for frags Bob Pearson
2022-10-27 18:55 ` [PATCH for-next 14/17] RDMA/rxe: Extend response packets " Bob Pearson
2022-10-30 20:13   ` kernel test robot
2022-10-27 18:55 ` [PATCH for-next 15/17] RDMA/rxe: Extend send/write_data_in() " Bob Pearson
2022-10-27 18:55 ` [PATCH for-next 16/17] RDMA/rxe: Extend do_read() in rxe_comp,c " Bob Pearson
2022-10-27 18:55 ` [PATCH for-next 17/17] RDMA/rxe: Enable sg code in rxe Bob Pearson

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=20221027185510.33808-9-rpearsonhpe@gmail.com \
    --to=rpearsonhpe@gmail.com \
    --cc=jgg@nvidia.com \
    --cc=jhack@hpe.com \
    --cc=leon@kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=zyjzyj2000@gmail.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