linux-nvme.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: Max Gurtovoy <maxg@mellanox.com>
To: linux-nvme@lists.infradead.org, sagi@grimberg.me,
	linux-rdma@vger.kernel.org, kbusch@kernel.org, hch@lst.de,
	martin.petersen@oracle.com
Cc: axboe@kernel.dk, vladimirk@mellanox.com, shlomin@mellanox.com,
	israelr@mellanox.com, idanb@mellanox.com, maxg@mellanox.com
Subject: [PATCH 17/19] RDMA/rw: Expose maximal page list for a device per 1 MR
Date: Mon, 24 Feb 2020 18:45:42 +0200	[thread overview]
Message-ID: <20200224164544.219438-19-maxg@mellanox.com> (raw)
In-Reply-To: <20200224164544.219438-1-maxg@mellanox.com>

ULP's will use this information to determine the maximal data transfer
size per IO operation.

Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
---
 drivers/infiniband/core/rw.c | 14 ++++++++++++--
 include/rdma/rw.h            |  1 +
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c
index 4fad732..edc9bee 100644
--- a/drivers/infiniband/core/rw.c
+++ b/drivers/infiniband/core/rw.c
@@ -56,8 +56,17 @@ static inline bool rdma_rw_io_needs_mr(struct ib_device *dev, u8 port_num,
 	return false;
 }
 
-static inline u32 rdma_rw_fr_page_list_len(struct ib_device *dev,
-					   bool pi_support)
+/**
+ * rdma_rw_fr_page_list_len - return the max number of pages mapped by 1 MR
+ * @dev:	RDMA device that will eventually create a PD for needed MRs
+ * @pi_support:	Whether MRs will be created for protection information offload
+ *
+ * Returns the number of pages that one MR can map for RDMA operation by the
+ * given device. One can determine the maximal data size according to the
+ * result of this function, or chose using multiple MRs for the RDMA operation
+ * as well.
+ */
+u32 rdma_rw_fr_page_list_len(struct ib_device *dev, bool pi_support)
 {
 	u32 max_pages;
 
@@ -69,6 +78,7 @@ static inline u32 rdma_rw_fr_page_list_len(struct ib_device *dev,
 	/* arbitrary limit to avoid allocating gigantic resources */
 	return min_t(u32, max_pages, 256);
 }
+EXPORT_SYMBOL(rdma_rw_fr_page_list_len);
 
 static inline int rdma_rw_inv_key(struct rdma_rw_reg_ctx *reg)
 {
diff --git a/include/rdma/rw.h b/include/rdma/rw.h
index 6ad9dc8..a9bbda7 100644
--- a/include/rdma/rw.h
+++ b/include/rdma/rw.h
@@ -69,5 +69,6 @@ unsigned int rdma_rw_mr_factor(struct ib_device *device, u8 port_num,
 void rdma_rw_init_qp(struct ib_device *dev, struct ib_qp_init_attr *attr);
 int rdma_rw_init_mrs(struct ib_qp *qp, struct ib_qp_init_attr *attr);
 void rdma_rw_cleanup_mrs(struct ib_qp *qp);
+u32 rdma_rw_fr_page_list_len(struct ib_device *dev, bool pi_support);
 
 #endif /* _RDMA_RW_H */
-- 
1.8.3.1


_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

  parent reply	other threads:[~2020-02-24 16:46 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-24 16:45 [PATCH 00/19 V4] nvme-rdma/nvmet-rdma: Add metadata/T10-PI support Max Gurtovoy
2020-02-24 16:45 ` [PATCH] nvme-cli/fabrics: Add pi_enable param to connect cmd Max Gurtovoy
2020-02-24 16:45 ` [PATCH 01/19] nvme: Introduce namespace features flag Max Gurtovoy
2020-02-24 16:45 ` [PATCH 02/19] nvme: Add has_pi field to the nvme_req structure Max Gurtovoy
2020-02-24 16:45 ` [PATCH 03/19] nvme: Enforce extended LBA format for fabrics metadata Max Gurtovoy
2020-02-24 16:45 ` [PATCH 04/19] nvme: Introduce max_integrity_segments ctrl attribute Max Gurtovoy
2020-02-24 16:45 ` [PATCH 05/19] nvme-fabrics: Allow user enabling metadata/T10-PI support Max Gurtovoy
2020-02-24 16:45 ` [PATCH 06/19] nvme: Introduce NVME_INLINE_PROT_SG_CNT Max Gurtovoy
2020-02-24 16:45 ` [PATCH 07/19] nvme-rdma: Introduce nvme_rdma_sgl structure Max Gurtovoy
2020-02-24 16:45 ` [PATCH 08/19] nvme-rdma: Add metadata/T10-PI support Max Gurtovoy
2020-02-24 16:45 ` [PATCH 09/19] nvmet: Prepare metadata request Max Gurtovoy
2020-02-24 16:45 ` [PATCH 10/19] nvmet: Add metadata characteristics for a namespace Max Gurtovoy
2020-02-24 16:45 ` [PATCH 11/19] nvmet: Rename nvmet_rw_len to nvmet_rw_data_len Max Gurtovoy
2020-02-24 16:45 ` [PATCH 12/19] nvmet: Rename nvmet_check_data_len to nvmet_check_transfer_len Max Gurtovoy
2020-02-24 16:45 ` [PATCH 13/19] nvme: Add Metadata Capabilities enumerations Max Gurtovoy
2020-02-24 16:45 ` [PATCH 14/19] nvmet: Add mdts setting op for controllers Max Gurtovoy
2020-02-24 16:45 ` [PATCH 15/19] nvmet: Add metadata/T10-PI support Max Gurtovoy
2020-02-24 16:45 ` [PATCH 16/19] nvmet: Add metadata support for block devices Max Gurtovoy
2020-02-24 16:45 ` Max Gurtovoy [this message]
2020-02-24 16:45 ` [PATCH 18/19] nvmet-rdma: Implement set_mdts controller op Max Gurtovoy
2020-02-24 16:45 ` [PATCH 19/19] nvmet-rdma: Add metadata/T10-PI support Max Gurtovoy
2020-02-24 18:13 ` [PATCH 00/19 V4] nvme-rdma/nvmet-rdma: " James Smart

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=20200224164544.219438-19-maxg@mellanox.com \
    --to=maxg@mellanox.com \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=idanb@mellanox.com \
    --cc=israelr@mellanox.com \
    --cc=kbusch@kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=martin.petersen@oracle.com \
    --cc=sagi@grimberg.me \
    --cc=shlomin@mellanox.com \
    --cc=vladimirk@mellanox.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;
as well as URLs for NNTP newsgroup(s).