netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Boris Pismenny <borisp@mellanox.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, Ben Ben-Ishay <benishay@mellanox.com>,
	Or Gerlitz <ogerlitz@mellanox.com>,
	Yoray Zack <yorayz@mellanox.com>
Subject: [PATCH v3 net-next  01/21] iov_iter: Introduce new procedures for copy to iter/pages
Date: Mon,  1 Feb 2021 12:04:49 +0200	[thread overview]
Message-ID: <20210201100509.27351-2-borisp@mellanox.com> (raw)
In-Reply-To: <20210201100509.27351-1-borisp@mellanox.com>

When using direct data placement the NIC writes some of the payload
directly to the destination buffer, and constructs the SKB such that it
points to this data. As a result, the skb_copy datagram_iter call will
attempt to copy data when it is not necessary.

Introduce new procedures for copy to iter/pages in case that the
source of the copy operation might be identical to the destination,
in such cases the copy is skipped only for bio_vec, later commits
uses those functions to introduce new skb copy(+hash) functions.

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 | 12 ++++++++++++
 lib/iov_iter.c      | 47 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+)

diff --git a/include/linux/uio.h b/include/linux/uio.h
index 72d88566694e..3c42125a7f24 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -123,6 +123,7 @@ 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);
+size_t _ddp_copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
 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);
@@ -137,6 +138,15 @@ size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 		return _copy_to_iter(addr, bytes, i);
 }
 
+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;
+	else
+		return _ddp_copy_to_iter(addr, bytes, i);
+}
+
 static __always_inline __must_check
 size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
 {
@@ -265,6 +275,8 @@ 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);
+size_t ddp_hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
+		struct iov_iter *i);
 
 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 a21e6a5792c5..b8af1d3bbec0 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -473,6 +473,16 @@ static void memcpy_from_page(char *to, struct page *page, size_t offset, size_t
 	kunmap_atomic(from);
 }
 
+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);
+}
+
 static void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len)
 {
 	char *to = kmap_atomic(page);
@@ -625,6 +635,24 @@ static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes,
 	return bytes;
 }
 
+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)
+		)
+
+	return bytes;
+}
+EXPORT_SYMBOL(_ddp_copy_to_iter);
+
 size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	const char *from = addr;
@@ -1566,6 +1594,25 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump,
 }
 EXPORT_SYMBOL(csum_and_copy_to_iter);
 
+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);
+
 size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
 		struct iov_iter *i)
 {
-- 
2.24.1


  reply	other threads:[~2021-02-01 10:10 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-01 10:04 [PATCH v3 net-next 00/21] nvme-tcp receive offloads Boris Pismenny
2021-02-01 10:04 ` Boris Pismenny [this message]
2021-02-01 17:35   ` [PATCH v3 net-next 01/21] iov_iter: Introduce new procedures for copy to iter/pages Christoph Hellwig
2021-02-02 18:00     ` Or Gerlitz
2021-02-03 16:56       ` Christoph Hellwig
2021-02-03 19:34         ` Ira Weiny
2021-02-07 14:13           ` Boris Pismenny
2021-02-07 14:24         ` Boris Pismenny
2021-02-01 10:04 ` [PATCH v3 net-next 02/21] net: Introduce direct data placement tcp offload Boris Pismenny
2021-02-02 10:06   ` Tom Parkin
2021-02-01 10:04 ` [PATCH v3 net-next 03/21] net: Introduce crc offload for tcp ddp ulp Boris Pismenny
2021-02-01 10:04 ` [PATCH v3 net-next 04/21] net: SKB copy(+hash) iterators for DDP offloads Boris Pismenny
2021-02-01 10:04 ` [PATCH v3 net-next 05/21] net/tls: expose get_netdev_for_sock Boris Pismenny
2021-02-01 10:04 ` [PATCH v3 net-next 06/21] nvme-tcp: Add DDP offload control path Boris Pismenny
2021-02-01 17:37   ` Christoph Hellwig
2021-02-02 18:09     ` Or Gerlitz
2021-02-03  9:17   ` Sagi Grimberg
2021-02-01 10:04 ` [PATCH v3 net-next 07/21] nvme-tcp: Add DDP data-path Boris Pismenny
2021-02-01 17:37   ` Christoph Hellwig
2021-02-02 18:14     ` Or Gerlitz
2021-02-03  8:56       ` Sagi Grimberg
2021-02-03 10:02         ` Christoph Hellwig
2021-02-03 10:21           ` Sagi Grimberg
2021-02-03  8:51   ` Sagi Grimberg
2021-02-04 19:20     ` Or Gerlitz
2021-02-01 10:04 ` [PATCH v3 net-next 08/21] nvme-tcp : Recalculate crc in the end of the capsule Boris Pismenny
2021-02-03  9:06   ` Sagi Grimberg
2021-02-04 18:36     ` Or Gerlitz
2021-02-07 16:40     ` Or Gerlitz
2021-02-01 10:04 ` [PATCH v3 net-next 09/21] nvme-tcp: Deal with netdevice DOWN events Boris Pismenny
2021-02-03  9:09   ` Sagi Grimberg
2021-02-04 18:29     ` Or Gerlitz
2021-02-01 10:04 ` [PATCH v3 net-next 10/21] net/mlx5: Header file changes for nvme-tcp offload Boris Pismenny
2021-02-01 10:04 ` [PATCH v3 net-next 11/21] net/mlx5: Add 128B CQE for NVMEoTCP offload Boris Pismenny
2021-02-01 10:05 ` [PATCH v3 net-next 12/21] net/mlx5e: TCP flow steering for nvme-tcp Boris Pismenny
2021-02-01 10:05 ` [PATCH v3 net-next 13/21] net/mlx5e: NVMEoTCP offload initialization Boris Pismenny
2021-02-01 10:05 ` [PATCH v3 net-next 14/21] net/mlx5e: KLM UMR helper macros Boris Pismenny
2021-02-01 10:05 ` [PATCH v3 net-next 15/21] net/mlx5e: NVMEoTCP use KLM UMRs Boris Pismenny
2021-02-01 10:05 ` [PATCH v3 net-next 16/21] net/mlx5e: NVMEoTCP queue init/teardown Boris Pismenny
2021-02-01 10:05 ` [PATCH v3 net-next 17/21] net/mlx5e: NVMEoTCP async ddp invalidation Boris Pismenny
2021-02-01 10:05 ` [PATCH v3 net-next 18/21] net/mlx5e: NVMEoTCP ddp setup and resync Boris Pismenny
2021-02-01 10:05 ` [PATCH v3 net-next 19/21] net/mlx5e: NVMEoTCP, data-path for DDP+CRC offload Boris Pismenny
2021-02-01 10:05 ` [PATCH v3 net-next 20/21] net/mlx5e: NVMEoTCP statistics Boris Pismenny
2021-02-01 10:05 ` [PATCH v3 net-next 21/21] Documentation: add TCP DDP offload documentation Boris Pismenny

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=20210201100509.27351-2-borisp@mellanox.com \
    --to=borisp@mellanox.com \
    --cc=axboe@fb.com \
    --cc=benishay@mellanox.com \
    --cc=benishay@nvidia.com \
    --cc=boris.pismenny@gmail.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 \
    /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).