Netdev Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Boris Pismenny <borisp@nvidia.com>
To: <dsahern@gmail.com>, <kuba@kernel.org>, <davem@davemloft.net>,
	<saeedm@nvidia.com>, <hch@lst.de>, <sagi@grimberg.me>,
	<axboe@fb.com>, <kbusch@kernel.org>, <viro@zeniv.linux.org.uk>,
	<edumazet@google.com>, <smalin@marvell.com>
Cc: <boris.pismenny@gmail.com>, <linux-nvme@lists.infradead.org>,
	<netdev@vger.kernel.org>, <benishay@nvidia.com>,
	<ogerlitz@nvidia.com>, <yorayz@nvidia.com>,
	Boris Pismenny <borisp@mellanox.com>,
	Ben Ben-Ishay <benishay@mellanox.com>,
	Or Gerlitz <ogerlitz@mellanox.com>,
	Yoray Zack <yorayz@mellanox.com>
Subject: [PATCH v5 net-next 02/36] iov_iter: DDP copy to iter/pages
Date: Thu, 22 Jul 2021 14:02:51 +0300	[thread overview]
Message-ID: <20210722110325.371-3-borisp@nvidia.com> (raw)
In-Reply-To: <20210722110325.371-1-borisp@nvidia.com>

From: Boris Pismenny <borisp@mellanox.com>

When using direct data placement (DDP) the NIC writes some of the payload
directly to the destination buffer, and constructs SKBs such that they
point to this data. To skip copies when SKB data already resides in the
destination we use the newly introduced routines in this commit, which
check if (src == dst), and skip the copy when that's true.

As the current user for these routines is in the block layer (nvme-tcp),
then we only apply the change for bio_vec. Other routines use the normal
methods for copying.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ben Ben-Ishay <benishay@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Yoray Zack <yorayz@mellanox.com>
---
 include/linux/uio.h | 17 ++++++++++++++
 lib/iov_iter.c      | 55 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 72 insertions(+)

diff --git a/include/linux/uio.h b/include/linux/uio.h
index d3ec87706d75..a61fdb369e0e 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -131,6 +131,9 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
 
 size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
+#ifdef CONFIG_ULP_DDP
+size_t _ddp_copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
+#endif
 size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
 bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i);
 size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i);
@@ -145,6 +148,16 @@ size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 		return _copy_to_iter(addr, bytes, i);
 }
 
+#ifdef CONFIG_ULP_DDP
+static __always_inline __must_check
+size_t ddp_copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
+{
+	if (unlikely(!check_copy_size(addr, bytes, true)))
+		return 0;
+	return _ddp_copy_to_iter(addr, bytes, i);
+}
+#endif
+
 static __always_inline __must_check
 size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
@@ -281,6 +294,10 @@ size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct io
 bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
 		struct iov_iter *i);
+#ifdef CONFIG_ULP_DDP
+size_t ddp_hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
+		struct iov_iter *i);
+#endif
 
 struct iovec *iovec_from_user(const struct iovec __user *uvector,
 		unsigned long nr_segs, unsigned long fast_segs,
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index c701b7a187f2..2e9be46a9b56 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -508,6 +508,18 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction,
 }
 EXPORT_SYMBOL(iov_iter_init);
 
+#ifdef CONFIG_ULP_DDP
+static void ddp_memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len)
+{
+	char *to = kmap_atomic(page);
+
+	if (to + offset != from)
+		memcpy(to + offset, from, len);
+
+	kunmap_atomic(to);
+}
+#endif
+
 static inline bool allocated(struct pipe_buffer *buf)
 {
 	return buf->ops == &default_pipe_buf_ops;
@@ -648,6 +660,28 @@ static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes,
 	return bytes;
 }
 
+#ifdef CONFIG_ULP_DDP
+size_t _ddp_copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
+{
+	const char *from = addr;
+	if (unlikely(iov_iter_is_pipe(i)))
+		return copy_pipe_to_iter(addr, bytes, i);
+	if (iter_is_iovec(i))
+		might_fault();
+	iterate_and_advance(i, bytes, v,
+		copyout(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len),
+		ddp_memcpy_to_page(v.bv_page, v.bv_offset,
+				   (from += v.bv_len) - v.bv_len, v.bv_len),
+		memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len),
+		ddp_memcpy_to_page(v.bv_page, v.bv_offset,
+				   (from += v.bv_len) - v.bv_len, v.bv_len)
+		)
+
+	return bytes;
+}
+EXPORT_SYMBOL(_ddp_copy_to_iter);
+#endif
+
 size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	const char *from = addr;
@@ -1818,6 +1852,27 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate,
 }
 EXPORT_SYMBOL(csum_and_copy_to_iter);
 
+#ifdef CONFIG_ULP_DDP
+size_t ddp_hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
+		struct iov_iter *i)
+{
+#ifdef CONFIG_CRYPTO_HASH
+	struct ahash_request *hash = hashp;
+	struct scatterlist sg;
+	size_t copied;
+
+	copied = ddp_copy_to_iter(addr, bytes, i);
+	sg_init_one(&sg, addr, copied);
+	ahash_request_set_crypt(hash, &sg, NULL, copied);
+	crypto_ahash_update(hash);
+	return copied;
+#else
+	return 0;
+#endif
+}
+EXPORT_SYMBOL(ddp_hash_and_copy_to_iter);
+#endif
+
 size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
 		struct iov_iter *i)
 {
-- 
2.24.1


  parent reply	other threads:[~2021-07-22 11:04 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-22 11:02 [PATCH v5 net-next 00/36] nvme-tcp receive and tarnsmit offloads Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 01/36] net: Introduce direct data placement tcp offload Boris Pismenny
2021-07-22 11:26   ` Eric Dumazet
2021-07-22 12:18     ` Boris Pismenny
2021-07-22 13:10       ` Eric Dumazet
2021-07-22 13:33         ` Boris Pismenny
2021-07-22 13:39           ` Eric Dumazet
2021-07-22 14:02             ` Boris Pismenny
2021-07-22 11:02 ` Boris Pismenny [this message]
2021-07-22 13:31   ` [PATCH v5 net-next 02/36] iov_iter: DDP copy to iter/pages Christoph Hellwig
2021-07-22 20:23     ` Boris Pismenny
2021-07-23  5:03       ` Christoph Hellwig
2021-07-23  5:21         ` Al Viro
2021-08-04 14:13           ` Or Gerlitz
2021-08-10 13:29             ` Or Gerlitz
2021-07-22 20:55   ` Al Viro
2021-07-22 11:02 ` [PATCH v5 net-next 03/36] net: skb copy(+hash) iterators for DDP offloads Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 04/36] net/tls: expose get_netdev_for_sock Boris Pismenny
2021-07-23  6:06   ` Christoph Hellwig
2021-08-04 13:26     ` Or Gerlitz
     [not found]       ` <20210804072918.17ba9cff@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com>
2021-08-04 15:07         ` Or Gerlitz
2021-08-10 13:25           ` Or Gerlitz
2021-07-22 11:02 ` [PATCH v5 net-next 05/36] nvme-tcp: Add DDP offload control path Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 06/36] nvme-tcp: Add DDP data-path Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 07/36] nvme-tcp: RX DDGST offload Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 08/36] nvme-tcp: Deal with netdevice DOWN events Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 09/36] net/mlx5: Header file changes for nvme-tcp offload Boris Pismenny
2021-07-22 11:02 ` [PATCH v5 net-next 10/36] net/mlx5: Add 128B CQE for NVMEoTCP offload Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 11/36] net/mlx5e: TCP flow steering for nvme-tcp Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 12/36] net/mlx5e: NVMEoTCP offload initialization Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 13/36] net/mlx5e: KLM UMR helper macros Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 14/36] net/mlx5e: NVMEoTCP use KLM UMRs Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 15/36] net/mlx5e: NVMEoTCP queue init/teardown Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 16/36] net/mlx5e: NVMEoTCP async ddp invalidation Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 17/36] net/mlx5e: NVMEoTCP ddp setup and resync Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 18/36] net/mlx5e: NVMEoTCP, data-path for DDP+DDGST offload Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 19/36] net/mlx5e: NVMEoTCP statistics Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 20/36] Documentation: add ULP DDP offload documentation Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 21/36] net: drop ULP DDP HW offload feature if no CSUM offload feature Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 22/36] net: Add ulp_ddp_pdu_info struct Boris Pismenny
2021-07-23 19:42   ` Sagi Grimberg
2021-07-22 11:03 ` [PATCH v5 net-next 23/36] net: Add to ulp_ddp support for fallback flow Boris Pismenny
2021-07-23  6:09   ` Christoph Hellwig
2021-07-22 11:03 ` [PATCH v5 net-next 24/36] net: Add MSG_DDP_CRC flag Boris Pismenny
2021-07-22 14:23   ` Eric Dumazet
2021-07-22 11:03 ` [PATCH v5 net-next 25/36] nvme-tcp: TX DDGST offload Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 26/36] nvme-tcp: Mapping between Tx NVMEoTCP pdu and TCP sequence Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 27/36] mlx5e: make preparation in TLS code for NVMEoTCP CRC Tx offload Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 28/36] mlx5: Add sq state test bit for nvmeotcp Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 29/36] mlx5: Add support to NETIF_F_HW_TCP_DDP_CRC_TX feature Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 30/36] net/mlx5e: NVMEoTCP DDGST TX offload TIS Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 31/36] net/mlx5e: NVMEoTCP DDGST Tx offload queue init/teardown Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 32/36] net/mlx5e: NVMEoTCP DDGST TX BSF and PSV Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 33/36] net/mlx5e: NVMEoTCP DDGST TX Data path Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 34/36] net/mlx5e: NVMEoTCP DDGST TX handle OOO packets Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 35/36] net/mlx5e: NVMEoTCP DDGST TX offload optimization Boris Pismenny
2021-07-22 11:03 ` [PATCH v5 net-next 36/36] net/mlx5e: NVMEoTCP DDGST TX statistics Boris Pismenny
2021-07-23  5:56 ` [PATCH v5 net-next 00/36] nvme-tcp receive and tarnsmit offloads Christoph Hellwig
2021-07-23 19:58   ` Sagi Grimberg
2021-08-04 13:51     ` Or Gerlitz
2021-08-06 19:46       ` Sagi Grimberg
2021-08-10 13:37         ` Or Gerlitz

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=20210722110325.371-3-borisp@nvidia.com \
    --to=borisp@nvidia.com \
    --cc=axboe@fb.com \
    --cc=benishay@mellanox.com \
    --cc=benishay@nvidia.com \
    --cc=boris.pismenny@gmail.com \
    --cc=borisp@mellanox.com \
    --cc=davem@davemloft.net \
    --cc=dsahern@gmail.com \
    --cc=edumazet@google.com \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=kuba@kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=netdev@vger.kernel.org \
    --cc=ogerlitz@mellanox.com \
    --cc=ogerlitz@nvidia.com \
    --cc=saeedm@nvidia.com \
    --cc=sagi@grimberg.me \
    --cc=smalin@marvell.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=yorayz@mellanox.com \
    --cc=yorayz@nvidia.com \
    --subject='Re: [PATCH v5 net-next 02/36] iov_iter: DDP copy to iter/pages' \
    /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

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).