[PATCH net-next 01/17] net: Copy slab data for sendmsg(MSG_SPLICE_PAGES)

[PATCH net-next 01/17] net: Copy slab data for sendmsg(MSG_SPLICE_PAGES)

[David Howells]

If sendmsg() is passed MSG_SPLICE_PAGES and is given a buffer that contains
some data that's resident in the slab, copy it rather than returning EIO.
This can be made use of by a number of drivers in the kernel, including:
iwarp, ceph/rds, dlm, nvme, ocfs2, drdb.  It could also be used by iscsi,
rxrpc, sunrpc, cifs and probably others.

skb_splice_from_iter() is given it's own fragment allocator as
page_frag_alloc_align() can't be used because it does no locking to prevent
parallel callers from racing.  alloc_skb_frag() uses a separate folio for
each cpu and locks to the cpu whilst allocating, reenabling cpu migration
around folio allocation.

This could allocate a whole page instead for each fragment to be copied, as
alloc_skb_with_frags() would do instead, but that would waste a lot of
space (most of the fragments look like they're going to be small).

This allows an entire message that consists of, say, a protocol header or
two, a number of pages of data and a protocol footer to be sent using a
single call to sock_sendmsg().

The callers could be made to copy the data into fragments before calling
sendmsg(), but that then penalises them if MSG_SPLICE_PAGES gets ignored.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Alexander Duyck <alexander.duyck@gmail.com>
cc: Eric Dumazet <edumazet@google.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: David Ahern <dsahern@kernel.org>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: Menglong Dong <imagedong@tencent.com>
cc: netdev@vger.kernel.org
---
 include/linux/skbuff.h |   5 ++
 net/core/skbuff.c      | 172 ++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 174 insertions(+), 3 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 91ed66952580..0ba776cd9be8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -5037,6 +5037,11 @@ static inline void skb_mark_for_recycle(struct sk_buff *skb)
 #endif
 }
 
+void *alloc_skb_frag(size_t fragsz, gfp_t gfp);
+void *copy_skb_frag(const void *s, size_t len, gfp_t gfp);
+ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
+			     ssize_t maxsize, gfp_t gfp);
+
 ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
 			     ssize_t maxsize, gfp_t gfp);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index fee2b1c105fe..9bd8d6bf6c21 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -6755,6 +6755,146 @@ nodefer:	__kfree_skb(skb);
 		smp_call_function_single_async(cpu, &sd->defer_csd);
 }
 
+struct skb_splice_frag_cache {
+	struct folio	*folio;
+	void		*virt;
+	unsigned int	offset;
+	/* we maintain a pagecount bias, so that we dont dirty cache line
+	 * containing page->_refcount every time we allocate a fragment.
+	 */
+	unsigned int	pagecnt_bias;
+	bool		pfmemalloc;
+};
+
+static DEFINE_PER_CPU(struct skb_splice_frag_cache, skb_splice_frag_cache);
+
+/**
+ * alloc_skb_frag - Allocate a page fragment for using in a socket
+ * @fragsz: The size of fragment required
+ * @gfp: Allocation flags
+ */
+void *alloc_skb_frag(size_t fragsz, gfp_t gfp)
+{
+	struct skb_splice_frag_cache *cache;
+	struct folio *folio, *spare = NULL;
+	size_t offset, fsize;
+	void *p;
+
+	if (WARN_ON_ONCE(fragsz == 0))
+		fragsz = 1;
+
+	cache = get_cpu_ptr(&skb_splice_frag_cache);
+reload:
+	folio = cache->folio;
+	offset = cache->offset;
+try_again:
+	if (fragsz > offset)
+		goto insufficient_space;
+
+	/* Make the allocation. */
+	cache->pagecnt_bias--;
+	offset = ALIGN_DOWN(offset - fragsz, SMP_CACHE_BYTES);
+	cache->offset = offset;
+	p = cache->virt + offset;
+	put_cpu_ptr(skb_splice_frag_cache);
+	if (spare)
+		folio_put(spare);
+	return p;
+
+insufficient_space:
+	/* See if we can refurbish the current folio. */
+	if (!folio || !folio_ref_sub_and_test(folio, cache->pagecnt_bias))
+		goto get_new_folio;
+	if (unlikely(cache->pfmemalloc)) {
+		__folio_put(folio);
+		goto get_new_folio;
+	}
+
+	fsize = folio_size(folio);
+	if (unlikely(fragsz > fsize))
+		goto frag_too_big;
+
+	/* OK, page count is 0, we can safely set it */
+	folio_set_count(folio, PAGE_FRAG_CACHE_MAX_SIZE + 1);
+
+	/* Reset page count bias and offset to start of new frag */
+	cache->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
+	offset = fsize;
+	goto try_again;
+
+get_new_folio:
+	if (!spare) {
+		cache->folio = NULL;
+		put_cpu_ptr(&skb_splice_frag_cache);
+
+#if PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE
+		spare = folio_alloc(gfp | __GFP_NOWARN | __GFP_NORETRY |
+				    __GFP_NOMEMALLOC,
+				    PAGE_FRAG_CACHE_MAX_ORDER);
+		if (!spare)
+#endif
+			spare = folio_alloc(gfp, 0);
+		if (!spare)
+			return NULL;
+
+		cache = get_cpu_ptr(&skb_splice_frag_cache);
+		/* We may now be on a different cpu and/or someone else may
+		 * have refilled it
+		 */
+		cache->pfmemalloc = folio_is_pfmemalloc(spare);
+		if (cache->folio)
+			goto reload;
+	}
+
+	cache->folio = spare;
+	cache->virt  = folio_address(spare);
+	folio = spare;
+	spare = NULL;
+
+	/* Even if we own the page, we do not use atomic_set().  This would
+	 * break get_page_unless_zero() users.
+	 */
+	folio_ref_add(folio, PAGE_FRAG_CACHE_MAX_SIZE);
+
+	/* Reset page count bias and offset to start of new frag */
+	cache->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
+	offset = folio_size(folio);
+	goto try_again;
+
+frag_too_big:
+	/*
+	 * The caller is trying to allocate a fragment with fragsz > PAGE_SIZE
+	 * but the cache isn't big enough to satisfy the request, this may
+	 * happen in low memory conditions.  We don't release the cache page
+	 * because it could make memory pressure worse so we simply return NULL
+	 * here.
+	 */
+	cache->offset = offset;
+	put_cpu_ptr(&skb_splice_frag_cache);
+	if (spare)
+		folio_put(spare);
+	return NULL;
+}
+EXPORT_SYMBOL(alloc_skb_frag);
+
+/**
+ * copy_skb_frag - Copy data into a page fragment.
+ * @s: The data to copy
+ * @len: The size of the data
+ * @gfp: Allocation flags
+ */
+void *copy_skb_frag(const void *s, size_t len, gfp_t gfp)
+{
+	void *p;
+
+	p = alloc_skb_frag(len, gfp);
+	if (!p)
+		return NULL;
+
+	return memcpy(p, s, len);
+}
+EXPORT_SYMBOL(copy_skb_frag);
+
 static void skb_splice_csum_page(struct sk_buff *skb, struct page *page,
 				 size_t offset, size_t len)
 {
@@ -6808,17 +6948,43 @@ ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
 			break;
 		}
 
+		if (space == 0 &&
+		    !skb_can_coalesce(skb, skb_shinfo(skb)->nr_frags,
+				      pages[0], off)) {
+			iov_iter_revert(iter, len);
+			break;
+		}
+
 		i = 0;
 		do {
 			struct page *page = pages[i++];
 			size_t part = min_t(size_t, PAGE_SIZE - off, len);
-
-			ret = -EIO;
-			if (WARN_ON_ONCE(!sendpage_ok(page)))
+			bool put = false;
+
+			if (PageSlab(page)) {
+				const void *p;
+				void *q;
+
+				p = kmap_local_page(page);
+				q = copy_skb_frag(p + off, part, gfp);
+				kunmap_local(p);
+				if (!q) {
+					iov_iter_revert(iter, len);
+					ret = -ENOMEM;
+					goto out;
+				}
+				page = virt_to_page(q);
+				off = offset_in_page(q);
+				put = true;
+			} else if (WARN_ON_ONCE(!sendpage_ok(page))) {
+				ret = -EIO;
 				goto out;
+			}
 
 			ret = skb_append_pagefrags(skb, page, off, part,
 						   frag_limit);
+			if (put)
+				put_page(page);
 			if (ret < 0) {
 				iov_iter_revert(iter, len);
 				goto out;

Re: [PATCH net-next 01/17] net: Copy slab data for sendmsg(MSG_SPLICE_PAGES)

[Simon Horman]

On Fri, Jun 16, 2023 at 05:12:44PM +0100, David Howells wrote:

...

> +/**
> + * alloc_skb_frag - Allocate a page fragment for using in a socket
> + * @fragsz: The size of fragment required
> + * @gfp: Allocation flags
> + */
> +void *alloc_skb_frag(size_t fragsz, gfp_t gfp)
> +{
> +	struct skb_splice_frag_cache *cache;
> +	struct folio *folio, *spare = NULL;
> +	size_t offset, fsize;
> +	void *p;
> +
> +	if (WARN_ON_ONCE(fragsz == 0))
> +		fragsz = 1;
> +
> +	cache = get_cpu_ptr(&skb_splice_frag_cache);
> +reload:
> +	folio = cache->folio;
> +	offset = cache->offset;
> +try_again:
> +	if (fragsz > offset)
> +		goto insufficient_space;
> +
> +	/* Make the allocation. */
> +	cache->pagecnt_bias--;
> +	offset = ALIGN_DOWN(offset - fragsz, SMP_CACHE_BYTES);
> +	cache->offset = offset;
> +	p = cache->virt + offset;
> +	put_cpu_ptr(skb_splice_frag_cache);

Hi David,

I don't think it makes any difference at run-time.
But to keep Sparse happy, perhaps this ought to be put_cpu_var()

...

Re: [PATCH net-next 01/17] net: Copy slab data for sendmsg(MSG_SPLICE_PAGES)

[David Howells]

Simon Horman <simon.horman@corigine.com> wrote:

> > +	cache = get_cpu_ptr(&skb_splice_frag_cache);
...
> > +	put_cpu_ptr(skb_splice_frag_cache);
> 
> Hi David,
> 
> I don't think it makes any difference at run-time.
> But to keep Sparse happy, perhaps this ought to be put_cpu_var()

Actually, the problem is a missing "&".  I think I should use put_cpu_ptr() to
match get_cpu_ptr().  It doesn't crash because the argument is ignored.

David

Re: [PATCH net-next 01/17] net: Copy slab data for sendmsg(MSG_SPLICE_PAGES)

[Simon Horman]

On Sat, Jun 17, 2023 at 07:43:15AM +0100, David Howells wrote:
> Simon Horman <simon.horman@corigine.com> wrote:
> 
> > > +	cache = get_cpu_ptr(&skb_splice_frag_cache);
> ...
> > > +	put_cpu_ptr(skb_splice_frag_cache);
> > 
> > Hi David,
> > 
> > I don't think it makes any difference at run-time.
> > But to keep Sparse happy, perhaps this ought to be put_cpu_var()
> 
> Actually, the problem is a missing "&".  I think I should use put_cpu_ptr() to
> match get_cpu_ptr().  It doesn't crash because the argument is ignored.

Thanks David, I agree that is a better idea.

[PATCH net-next 02/17] net: Display info about MSG_SPLICE_PAGES memory handling in proc

[David Howells]

Display information about the memory handling MSG_SPLICE_PAGES does to copy
slabbed data into page fragments.

For each CPU that has a cached folio, it displays the folio pfn, the offset
pointer within the folio and the size of the folio.

It also displays the number of pages refurbished and the number of pages
replaced.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Alexander Duyck <alexander.duyck@gmail.com>
cc: Eric Dumazet <edumazet@google.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: David Ahern <dsahern@kernel.org>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: Menglong Dong <imagedong@tencent.com>
cc: netdev@vger.kernel.org
---
 net/core/skbuff.c | 42 +++++++++++++++++++++++++++++++++++++++---
 1 file changed, 39 insertions(+), 3 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9bd8d6bf6c21..c388a73e5d4e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -83,6 +83,7 @@
 #include <linux/user_namespace.h>
 #include <linux/indirect_call_wrapper.h>
 #include <linux/textsearch.h>
+#include <linux/proc_fs.h>
 
 #include "dev.h"
 #include "sock_destructor.h"
@@ -6758,6 +6759,7 @@ nodefer:	__kfree_skb(skb);
 struct skb_splice_frag_cache {
 	struct folio	*folio;
 	void		*virt;
+	unsigned int	fsize;
 	unsigned int	offset;
 	/* we maintain a pagecount bias, so that we dont dirty cache line
 	 * containing page->_refcount every time we allocate a fragment.
@@ -6767,6 +6769,26 @@ struct skb_splice_frag_cache {
 };
 
 static DEFINE_PER_CPU(struct skb_splice_frag_cache, skb_splice_frag_cache);
+static atomic_t skb_splice_frag_replaced, skb_splice_frag_refurbished;
+
+static int skb_splice_show(struct seq_file *m, void *data)
+{
+	int cpu;
+
+	seq_printf(m, "refurb=%u repl=%u\n",
+		   atomic_read(&skb_splice_frag_refurbished),
+		   atomic_read(&skb_splice_frag_replaced));
+
+	for_each_possible_cpu(cpu) {
+		const struct skb_splice_frag_cache *cache =
+			per_cpu_ptr(&skb_splice_frag_cache, cpu);
+
+		seq_printf(m, "[%u] %lx %u/%u\n",
+			   cpu, folio_pfn(cache->folio),
+			   cache->offset, cache->fsize);
+	}
+	return 0;
+}
 
 /**
  * alloc_skb_frag - Allocate a page fragment for using in a socket
@@ -6803,17 +6825,21 @@ void *alloc_skb_frag(size_t fragsz, gfp_t gfp)
 
 insufficient_space:
 	/* See if we can refurbish the current folio. */
-	if (!folio || !folio_ref_sub_and_test(folio, cache->pagecnt_bias))
+	if (!folio)
 		goto get_new_folio;
+	if (!folio_ref_sub_and_test(folio, cache->pagecnt_bias))
+		goto replace_folio;
 	if (unlikely(cache->pfmemalloc)) {
 		__folio_put(folio);
-		goto get_new_folio;
+		goto replace_folio;
 	}
 
 	fsize = folio_size(folio);
 	if (unlikely(fragsz > fsize))
 		goto frag_too_big;
 
+	atomic_inc(&skb_splice_frag_refurbished);
+
 	/* OK, page count is 0, we can safely set it */
 	folio_set_count(folio, PAGE_FRAG_CACHE_MAX_SIZE + 1);
 
@@ -6822,6 +6848,8 @@ void *alloc_skb_frag(size_t fragsz, gfp_t gfp)
 	offset = fsize;
 	goto try_again;
 
+replace_folio:
+	atomic_inc(&skb_splice_frag_replaced);
 get_new_folio:
 	if (!spare) {
 		cache->folio = NULL;
@@ -6848,6 +6876,7 @@ void *alloc_skb_frag(size_t fragsz, gfp_t gfp)
 
 	cache->folio = spare;
 	cache->virt  = folio_address(spare);
+	cache->fsize = folio_size(spare);
 	folio = spare;
 	spare = NULL;
 
@@ -6858,7 +6887,7 @@ void *alloc_skb_frag(size_t fragsz, gfp_t gfp)
 
 	/* Reset page count bias and offset to start of new frag */
 	cache->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
-	offset = folio_size(folio);
+	offset = cache->fsize;
 	goto try_again;
 
 frag_too_big:
@@ -7008,3 +7037,10 @@ ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
 	return spliced ?: ret;
 }
 EXPORT_SYMBOL(skb_splice_from_iter);
+
+static int skb_splice_init(void)
+{
+	proc_create_single("pagefrags", S_IFREG | 0444, NULL, &skb_splice_show);
+	return 0;
+}
+late_initcall(skb_splice_init);

[PATCH net-next 03/17] tcp_bpf, smc, tls, espintcp: Reduce MSG_SENDPAGE_NOTLAST usage

[David Howells]

As MSG_SENDPAGE_NOTLAST is being phased out along with sendpage(), don't
use it further in than the sendpage methods, but rather translate it to
MSG_MORE and use that instead.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: John Fastabend <john.fastabend@gmail.com>
cc: Jakub Sitnicki <jakub@cloudflare.com>
cc: Eric Dumazet <edumazet@google.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: David Ahern <dsahern@kernel.org>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Karsten Graul <kgraul@linux.ibm.com>
cc: Wenjia Zhang <wenjia@linux.ibm.com>
cc: Jan Karcher <jaka@linux.ibm.com>
cc: "D. Wythe" <alibuda@linux.alibaba.com>
cc: Tony Lu <tonylu@linux.alibaba.com>
cc: Wen Gu <guwen@linux.alibaba.com>
cc: Boris Pismenny <borisp@nvidia.com>
cc: Steffen Klassert <steffen.klassert@secunet.com>
cc: Herbert Xu <herbert@gondor.apana.org.au>
cc: netdev@vger.kernel.org
cc: bpf@vger.kernel.org
cc: linux-s390@vger.kernel.org
---
 net/ipv4/tcp_bpf.c   |  3 ---
 net/smc/smc_tx.c     |  6 ++++--
 net/tls/tls_device.c |  4 ++--
 net/xfrm/espintcp.c  | 10 ++++++----
 4 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 5a84053ac62b..adcba77b0c50 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -111,9 +111,6 @@ static int tcp_bpf_push(struct sock *sk, struct sk_msg *msg, u32 apply_bytes,
 		if (has_tx_ulp)
 			msghdr.msg_flags |= MSG_SENDPAGE_NOPOLICY;
 
-		if (flags & MSG_SENDPAGE_NOTLAST)
-			msghdr.msg_flags |= MSG_MORE;
-
 		bvec_set_page(&bvec, page, size, off);
 		iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, size);
 		ret = tcp_sendmsg_locked(sk, &msghdr, size);
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 45128443f1f1..9b9e0a190734 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -168,8 +168,7 @@ static bool smc_tx_should_cork(struct smc_sock *smc, struct msghdr *msg)
 	 * should known how/when to uncork it.
 	 */
 	if ((msg->msg_flags & MSG_MORE ||
-	     smc_tx_is_corked(smc) ||
-	     msg->msg_flags & MSG_SENDPAGE_NOTLAST) &&
+	     smc_tx_is_corked(smc)) &&
 	    atomic_read(&conn->sndbuf_space))
 		return true;
 
@@ -306,6 +305,9 @@ int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset,
 	struct kvec iov;
 	int rc;
 
+	if (flags & MSG_SENDPAGE_NOTLAST)
+		msg.msg_flags |= MSG_MORE;
+
 	iov.iov_base = kaddr + offset;
 	iov.iov_len = size;
 	iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iov, 1, size);
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index b82770f68807..975299d7213b 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -449,7 +449,7 @@ static int tls_push_data(struct sock *sk,
 		return -sk->sk_err;
 
 	flags |= MSG_SENDPAGE_DECRYPTED;
-	tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
+	tls_push_record_flags = flags | MSG_MORE;
 
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 	if (tls_is_partially_sent_record(tls_ctx)) {
@@ -532,7 +532,7 @@ static int tls_push_data(struct sock *sk,
 		if (!size) {
 last_record:
 			tls_push_record_flags = flags;
-			if (flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE)) {
+			if (flags & MSG_MORE) {
 				more = true;
 				break;
 			}
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index 3504925babdb..d3b3f9e720b3 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -205,13 +205,15 @@ static int espintcp_sendskb_locked(struct sock *sk, struct espintcp_msg *emsg,
 static int espintcp_sendskmsg_locked(struct sock *sk,
 				     struct espintcp_msg *emsg, int flags)
 {
-	struct msghdr msghdr = { .msg_flags = flags | MSG_SPLICE_PAGES, };
+	struct msghdr msghdr = {
+		.msg_flags = flags | MSG_SPLICE_PAGES | MSG_MORE,
+	};
 	struct sk_msg *skmsg = &emsg->skmsg;
+	bool more = flags & MSG_MORE;
 	struct scatterlist *sg;
 	int done = 0;
 	int ret;
 
-	msghdr.msg_flags |= MSG_SENDPAGE_NOTLAST;
 	sg = &skmsg->sg.data[skmsg->sg.start];
 	do {
 		struct bio_vec bvec;
@@ -221,8 +223,8 @@ static int espintcp_sendskmsg_locked(struct sock *sk,
 
 		emsg->offset = 0;
 
-		if (sg_is_last(sg))
-			msghdr.msg_flags &= ~MSG_SENDPAGE_NOTLAST;
+		if (sg_is_last(sg) && !more)
+			msghdr.msg_flags &= ~MSG_MORE;
 
 		p = sg_page(sg);
 retry:

[PATCH net-next 04/17] siw: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage to transmit

[David Howells]

When transmitting data, call down into TCP using a single sendmsg with
MSG_SPLICE_PAGES to indicate that content should be spliced rather than
performing several sendmsg and sendpage calls to transmit header, data
pages and trailer.

To make this work, the data is assembled in a bio_vec array and attached to
a BVEC-type iterator.  The header and trailer (if present) are copied into
page fragments that can be freed with put_page().

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Bernard Metzler <bmt@zurich.ibm.com>
cc: Tom Talpey <tom@talpey.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: linux-rdma@vger.kernel.org
cc: netdev@vger.kernel.org
---
 drivers/infiniband/sw/siw/siw_qp_tx.c | 230 ++++----------------------
 1 file changed, 35 insertions(+), 195 deletions(-)

diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c
index ffb16beb6c30..a15b3fedf484 100644
--- a/drivers/infiniband/sw/siw/siw_qp_tx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_tx.c
@@ -311,114 +311,8 @@ static int siw_tx_ctrl(struct siw_iwarp_tx *c_tx, struct socket *s,
 	return rv;
 }
 
-/*
- * 0copy TCP transmit interface: Use MSG_SPLICE_PAGES.
- *
- * Using sendpage to push page by page appears to be less efficient
- * than using sendmsg, even if data are copied.
- *
- * A general performance limitation might be the extra four bytes
- * trailer checksum segment to be pushed after user data.
- */
-static int siw_tcp_sendpages(struct socket *s, struct page **page, int offset,
-			     size_t size)
-{
-	struct bio_vec bvec;
-	struct msghdr msg = {
-		.msg_flags = (MSG_MORE | MSG_DONTWAIT | MSG_SENDPAGE_NOTLAST |
-			      MSG_SPLICE_PAGES),
-	};
-	struct sock *sk = s->sk;
-	int i = 0, rv = 0, sent = 0;
-
-	while (size) {
-		size_t bytes = min_t(size_t, PAGE_SIZE - offset, size);
-
-		if (size + offset <= PAGE_SIZE)
-			msg.msg_flags &= ~MSG_SENDPAGE_NOTLAST;
-
-		tcp_rate_check_app_limited(sk);
-		bvec_set_page(&bvec, page[i], bytes, offset);
-		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
-
-try_page_again:
-		lock_sock(sk);
-		rv = tcp_sendmsg_locked(sk, &msg, size);
-		release_sock(sk);
-
-		if (rv > 0) {
-			size -= rv;
-			sent += rv;
-			if (rv != bytes) {
-				offset += rv;
-				bytes -= rv;
-				goto try_page_again;
-			}
-			offset = 0;
-		} else {
-			if (rv == -EAGAIN || rv == 0)
-				break;
-			return rv;
-		}
-		i++;
-	}
-	return sent;
-}
-
-/*
- * siw_0copy_tx()
- *
- * Pushes list of pages to TCP socket. If pages from multiple
- * SGE's, all referenced pages of each SGE are pushed in one
- * shot.
- */
-static int siw_0copy_tx(struct socket *s, struct page **page,
-			struct siw_sge *sge, unsigned int offset,
-			unsigned int size)
-{
-	int i = 0, sent = 0, rv;
-	int sge_bytes = min(sge->length - offset, size);
-
-	offset = (sge->laddr + offset) & ~PAGE_MASK;
-
-	while (sent != size) {
-		rv = siw_tcp_sendpages(s, &page[i], offset, sge_bytes);
-		if (rv >= 0) {
-			sent += rv;
-			if (size == sent || sge_bytes > rv)
-				break;
-
-			i += PAGE_ALIGN(sge_bytes + offset) >> PAGE_SHIFT;
-			sge++;
-			sge_bytes = min(sge->length, size - sent);
-			offset = sge->laddr & ~PAGE_MASK;
-		} else {
-			sent = rv;
-			break;
-		}
-	}
-	return sent;
-}
-
 #define MAX_TRAILER (MPA_CRC_SIZE + 4)
 
-static void siw_unmap_pages(struct kvec *iov, unsigned long kmap_mask, int len)
-{
-	int i;
-
-	/*
-	 * Work backwards through the array to honor the kmap_local_page()
-	 * ordering requirements.
-	 */
-	for (i = (len-1); i >= 0; i--) {
-		if (kmap_mask & BIT(i)) {
-			unsigned long addr = (unsigned long)iov[i].iov_base;
-
-			kunmap_local((void *)(addr & PAGE_MASK));
-		}
-	}
-}
-
 /*
  * siw_tx_hdt() tries to push a complete packet to TCP where all
  * packet fragments are referenced by the elements of one iovec.
@@ -438,30 +332,21 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 {
 	struct siw_wqe *wqe = &c_tx->wqe_active;
 	struct siw_sge *sge = &wqe->sqe.sge[c_tx->sge_idx];
-	struct kvec iov[MAX_ARRAY];
-	struct page *page_array[MAX_ARRAY];
+	struct bio_vec bvec[MAX_ARRAY];
 	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_EOR };
+	void *trl;
 
 	int seg = 0, do_crc = c_tx->do_crc, is_kva = 0, rv;
 	unsigned int data_len = c_tx->bytes_unsent, hdr_len = 0, trl_len = 0,
 		     sge_off = c_tx->sge_off, sge_idx = c_tx->sge_idx,
 		     pbl_idx = c_tx->pbl_idx;
-	unsigned long kmap_mask = 0L;
 
 	if (c_tx->state == SIW_SEND_HDR) {
-		if (c_tx->use_sendpage) {
-			rv = siw_tx_ctrl(c_tx, s, MSG_DONTWAIT | MSG_MORE);
-			if (rv)
-				goto done;
+		void *hdr = &c_tx->pkt.ctrl + c_tx->ctrl_sent;
 
-			c_tx->state = SIW_SEND_DATA;
-		} else {
-			iov[0].iov_base =
-				(char *)&c_tx->pkt.ctrl + c_tx->ctrl_sent;
-			iov[0].iov_len = hdr_len =
-				c_tx->ctrl_len - c_tx->ctrl_sent;
-			seg = 1;
-		}
+		hdr_len = c_tx->ctrl_len - c_tx->ctrl_sent;
+		bvec_set_virt(&bvec[0], hdr, hdr_len);
+		seg = 1;
 	}
 
 	wqe->processed += data_len;
@@ -477,28 +362,9 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 		} else {
 			is_kva = 1;
 		}
-		if (is_kva && !c_tx->use_sendpage) {
-			/*
-			 * tx from kernel virtual address: either inline data
-			 * or memory region with assigned kernel buffer
-			 */
-			iov[seg].iov_base =
-				ib_virt_dma_to_ptr(sge->laddr + sge_off);
-			iov[seg].iov_len = sge_len;
-
-			if (do_crc)
-				crypto_shash_update(c_tx->mpa_crc_hd,
-						    iov[seg].iov_base,
-						    sge_len);
-			sge_off += sge_len;
-			data_len -= sge_len;
-			seg++;
-			goto sge_done;
-		}
 
 		while (sge_len) {
 			size_t plen = min((int)PAGE_SIZE - fp_off, sge_len);
-			void *kaddr;
 
 			if (!is_kva) {
 				struct page *p;
@@ -511,33 +377,12 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 					p = siw_get_upage(mem->umem,
 							  sge->laddr + sge_off);
 				if (unlikely(!p)) {
-					siw_unmap_pages(iov, kmap_mask, seg);
 					wqe->processed -= c_tx->bytes_unsent;
 					rv = -EFAULT;
 					goto done_crc;
 				}
-				page_array[seg] = p;
-
-				if (!c_tx->use_sendpage) {
-					void *kaddr = kmap_local_page(p);
-
-					/* Remember for later kunmap() */
-					kmap_mask |= BIT(seg);
-					iov[seg].iov_base = kaddr + fp_off;
-					iov[seg].iov_len = plen;
-
-					if (do_crc)
-						crypto_shash_update(
-							c_tx->mpa_crc_hd,
-							iov[seg].iov_base,
-							plen);
-				} else if (do_crc) {
-					kaddr = kmap_local_page(p);
-					crypto_shash_update(c_tx->mpa_crc_hd,
-							    kaddr + fp_off,
-							    plen);
-					kunmap_local(kaddr);
-				}
+
+				bvec_set_page(&bvec[seg], p, plen, fp_off);
 			} else {
 				/*
 				 * Cast to an uintptr_t to preserve all 64 bits
@@ -545,12 +390,16 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 				 */
 				u64 va = sge->laddr + sge_off;
 
-				page_array[seg] = ib_virt_dma_to_page(va);
-				if (do_crc)
-					crypto_shash_update(
-						c_tx->mpa_crc_hd,
-						ib_virt_dma_to_ptr(va),
-						plen);
+				bvec_set_virt(&bvec[seg], ib_virt_dma_to_ptr(va), plen);
+			}
+
+			if (do_crc) {
+				void *kaddr =
+					kmap_local_page(bvec[seg].bv_page);
+				crypto_shash_update(c_tx->mpa_crc_hd,
+						    kaddr + bvec[seg].bv_offset,
+						    bvec[seg].bv_len);
+				kunmap_local(kaddr);
 			}
 
 			sge_len -= plen;
@@ -560,13 +409,12 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 
 			if (++seg >= (int)MAX_ARRAY) {
 				siw_dbg_qp(tx_qp(c_tx), "to many fragments\n");
-				siw_unmap_pages(iov, kmap_mask, seg-1);
 				wqe->processed -= c_tx->bytes_unsent;
 				rv = -EMSGSIZE;
 				goto done_crc;
 			}
 		}
-sge_done:
+
 		/* Update SGE variables at end of SGE */
 		if (sge_off == sge->length &&
 		    (data_len != 0 || wqe->processed < wqe->bytes)) {
@@ -575,15 +423,8 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 			sge_off = 0;
 		}
 	}
-	/* trailer */
-	if (likely(c_tx->state != SIW_SEND_TRAILER)) {
-		iov[seg].iov_base = &c_tx->trailer.pad[4 - c_tx->pad];
-		iov[seg].iov_len = trl_len = MAX_TRAILER - (4 - c_tx->pad);
-	} else {
-		iov[seg].iov_base = &c_tx->trailer.pad[c_tx->ctrl_sent];
-		iov[seg].iov_len = trl_len = MAX_TRAILER - c_tx->ctrl_sent;
-	}
 
+	/* Set the CRC in the trailer */
 	if (c_tx->pad) {
 		*(u32 *)c_tx->trailer.pad = 0;
 		if (do_crc)
@@ -596,23 +437,23 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 	else if (do_crc)
 		crypto_shash_final(c_tx->mpa_crc_hd, (u8 *)&c_tx->trailer.crc);
 
-	data_len = c_tx->bytes_unsent;
-
-	if (c_tx->use_sendpage) {
-		rv = siw_0copy_tx(s, page_array, &wqe->sqe.sge[c_tx->sge_idx],
-				  c_tx->sge_off, data_len);
-		if (rv == data_len) {
-			rv = kernel_sendmsg(s, &msg, &iov[seg], 1, trl_len);
-			if (rv > 0)
-				rv += data_len;
-			else
-				rv = data_len;
-		}
+	/* Copy the trailer and add it to the output list */
+	if (likely(c_tx->state != SIW_SEND_TRAILER)) {
+		trl = &c_tx->trailer.pad[4 - c_tx->pad];
+		trl_len = MAX_TRAILER - (4 - c_tx->pad);
 	} else {
-		rv = kernel_sendmsg(s, &msg, iov, seg + 1,
-				    hdr_len + data_len + trl_len);
-		siw_unmap_pages(iov, kmap_mask, seg);
+		trl = &c_tx->trailer.pad[c_tx->ctrl_sent];
+		trl_len = MAX_TRAILER - c_tx->ctrl_sent;
 	}
+	bvec_set_virt(&bvec[seg], trl, trl_len);
+
+	data_len = c_tx->bytes_unsent;
+
+	if (c_tx->use_sendpage)
+		msg.msg_flags |= MSG_SPLICE_PAGES;
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, bvec, seg + 1,
+		      hdr_len + data_len + trl_len);
+	rv = sock_sendmsg(s, &msg);
 	if (rv < (int)hdr_len) {
 		/* Not even complete hdr pushed or negative rv */
 		wqe->processed -= data_len;
@@ -673,7 +514,6 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
 	}
 done_crc:
 	c_tx->do_crc = 0;
-done:
 	return rv;
 }
 

[PATCH net-next 05/17] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage

[David Howells]

Use sendmsg() and MSG_SPLICE_PAGES rather than sendpage in ceph when
transmitting data.  For the moment, this can only transmit one page at a
time because of the architecture of net/ceph/, but if
write_partial_message_data() can be given a bvec[] at a time by the
iteration code, this would allow pages to be sent in a batch.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Ilya Dryomov <idryomov@gmail.com>
cc: Xiubo Li <xiubli@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: ceph-devel@vger.kernel.org
cc: netdev@vger.kernel.org
---
 net/ceph/messenger_v1.c | 58 ++++++++++++++---------------------------
 1 file changed, 19 insertions(+), 39 deletions(-)

diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
index d664cb1593a7..f082e5c780a3 100644
--- a/net/ceph/messenger_v1.c
+++ b/net/ceph/messenger_v1.c
@@ -74,37 +74,6 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
 	return r;
 }
 
-/*
- * @more: either or both of MSG_MORE and MSG_SENDPAGE_NOTLAST
- */
-static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
-			     int offset, size_t size, int more)
-{
-	ssize_t (*sendpage)(struct socket *sock, struct page *page,
-			    int offset, size_t size, int flags);
-	int flags = MSG_DONTWAIT | MSG_NOSIGNAL | more;
-	int ret;
-
-	/*
-	 * sendpage cannot properly handle pages with page_count == 0,
-	 * we need to fall back to sendmsg if that's the case.
-	 *
-	 * Same goes for slab pages: skb_can_coalesce() allows
-	 * coalescing neighboring slab objects into a single frag which
-	 * triggers one of hardened usercopy checks.
-	 */
-	if (sendpage_ok(page))
-		sendpage = sock->ops->sendpage;
-	else
-		sendpage = sock_no_sendpage;
-
-	ret = sendpage(sock, page, offset, size, flags);
-	if (ret == -EAGAIN)
-		ret = 0;
-
-	return ret;
-}
-
 static void con_out_kvec_reset(struct ceph_connection *con)
 {
 	BUG_ON(con->v1.out_skip);
@@ -464,7 +433,6 @@ static int write_partial_message_data(struct ceph_connection *con)
 	struct ceph_msg *msg = con->out_msg;
 	struct ceph_msg_data_cursor *cursor = &msg->cursor;
 	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
-	int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
 	u32 crc;
 
 	dout("%s %p msg %p\n", __func__, con, msg);
@@ -482,6 +450,10 @@ static int write_partial_message_data(struct ceph_connection *con)
 	 */
 	crc = do_datacrc ? le32_to_cpu(msg->footer.data_crc) : 0;
 	while (cursor->total_resid) {
+		struct bio_vec bvec;
+		struct msghdr msghdr = {
+			.msg_flags = MSG_SPLICE_PAGES,
+		};
 		struct page *page;
 		size_t page_offset;
 		size_t length;
@@ -494,9 +466,12 @@ static int write_partial_message_data(struct ceph_connection *con)
 
 		page = ceph_msg_data_next(cursor, &page_offset, &length);
 		if (length == cursor->total_resid)
-			more = MSG_MORE;
-		ret = ceph_tcp_sendpage(con->sock, page, page_offset, length,
-					more);
+			msghdr.msg_flags |= MSG_MORE;
+
+		bvec_set_page(&bvec, page, length, page_offset);
+		iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, length);
+
+		ret = sock_sendmsg(con->sock, &msghdr);
 		if (ret <= 0) {
 			if (do_datacrc)
 				msg->footer.data_crc = cpu_to_le32(crc);
@@ -526,7 +501,10 @@ static int write_partial_message_data(struct ceph_connection *con)
  */
 static int write_partial_skip(struct ceph_connection *con)
 {
-	int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
+	struct bio_vec bvec;
+	struct msghdr msghdr = {
+		.msg_flags = MSG_SPLICE_PAGES | MSG_MORE,
+	};
 	int ret;
 
 	dout("%s %p %d left\n", __func__, con, con->v1.out_skip);
@@ -534,9 +512,11 @@ static int write_partial_skip(struct ceph_connection *con)
 		size_t size = min(con->v1.out_skip, (int)PAGE_SIZE);
 
 		if (size == con->v1.out_skip)
-			more = MSG_MORE;
-		ret = ceph_tcp_sendpage(con->sock, ceph_zero_page, 0, size,
-					more);
+			msghdr.msg_flags &= ~MSG_MORE;
+		bvec_set_page(&bvec, ZERO_PAGE(0), size, 0);
+		iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, size);
+
+		ret = sock_sendmsg(con->sock, &msghdr);
 		if (ret <= 0)
 			goto out;
 		con->v1.out_skip -= ret;

[PATCH net-next 06/17] net: Use sendmsg(MSG_SPLICE_PAGES) not sendpage in skb_send_sock()

[David Howells]

Use sendmsg() with MSG_SPLICE_PAGES rather than sendpage in
skb_send_sock().  This causes pages to be spliced from the source iterator
if possible.

This allows ->sendpage() to be replaced by something that can handle
multiple multipage folios in a single transaction.

Note that this could perhaps be improved to fill out a bvec array with all
the frags and then make a single sendmsg call, possibly sticking the header
on the front also.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: netdev@vger.kernel.org
---
 net/core/skbuff.c | 49 ++++++++++++++++++++++++++---------------------
 1 file changed, 27 insertions(+), 22 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c388a73e5d4e..e518bb57183a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2990,32 +2990,32 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
 }
 EXPORT_SYMBOL_GPL(skb_splice_bits);
 
-static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg,
-			    struct kvec *vec, size_t num, size_t size)
+static int sendmsg_locked(struct sock *sk, struct msghdr *msg)
 {
 	struct socket *sock = sk->sk_socket;
+	size_t size = msg_data_left(msg);
 
 	if (!sock)
 		return -EINVAL;
-	return kernel_sendmsg(sock, msg, vec, num, size);
+
+	if (!sock->ops->sendmsg_locked)
+		return sock_no_sendmsg_locked(sk, msg, size);
+
+	return sock->ops->sendmsg_locked(sk, msg, size);
 }
 
-static int sendpage_unlocked(struct sock *sk, struct page *page, int offset,
-			     size_t size, int flags)
+static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg)
 {
 	struct socket *sock = sk->sk_socket;
 
 	if (!sock)
 		return -EINVAL;
-	return kernel_sendpage(sock, page, offset, size, flags);
+	return sock_sendmsg(sock, msg);
 }
 
-typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg,
-			    struct kvec *vec, size_t num, size_t size);
-typedef int (*sendpage_func)(struct sock *sk, struct page *page, int offset,
-			     size_t size, int flags);
+typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg);
 static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
-			   int len, sendmsg_func sendmsg, sendpage_func sendpage)
+			   int len, sendmsg_func sendmsg)
 {
 	unsigned int orig_len = len;
 	struct sk_buff *head = skb;
@@ -3035,8 +3035,9 @@ static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
 		memset(&msg, 0, sizeof(msg));
 		msg.msg_flags = MSG_DONTWAIT;
 
-		ret = INDIRECT_CALL_2(sendmsg, kernel_sendmsg_locked,
-				      sendmsg_unlocked, sk, &msg, &kv, 1, slen);
+		iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &kv, 1, slen);
+		ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
+				      sendmsg_unlocked, sk, &msg);
 		if (ret <= 0)
 			goto error;
 
@@ -3067,11 +3068,17 @@ static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
 		slen = min_t(size_t, len, skb_frag_size(frag) - offset);
 
 		while (slen) {
-			ret = INDIRECT_CALL_2(sendpage, kernel_sendpage_locked,
-					      sendpage_unlocked, sk,
-					      skb_frag_page(frag),
-					      skb_frag_off(frag) + offset,
-					      slen, MSG_DONTWAIT);
+			struct bio_vec bvec;
+			struct msghdr msg = {
+				.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT,
+			};
+
+			bvec_set_page(&bvec, skb_frag_page(frag), slen,
+				      skb_frag_off(frag) + offset);
+			iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, slen);
+
+			ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
+					      sendmsg_unlocked, sk, &msg);
 			if (ret <= 0)
 				goto error;
 
@@ -3108,16 +3115,14 @@ static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
 int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset,
 			 int len)
 {
-	return __skb_send_sock(sk, skb, offset, len, kernel_sendmsg_locked,
-			       kernel_sendpage_locked);
+	return __skb_send_sock(sk, skb, offset, len, sendmsg_locked);
 }
 EXPORT_SYMBOL_GPL(skb_send_sock_locked);
 
 /* Send skb data on a socket. Socket must be unlocked. */
 int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len)
 {
-	return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked,
-			       sendpage_unlocked);
+	return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked);
 }
 
 /**

[PATCH net-next 07/17] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage()

[David Howells]

Use sendmsg() and MSG_SPLICE_PAGES rather than sendpage in ceph when
transmitting data.  For the moment, this can only transmit one page at a
time because of the architecture of net/ceph/, but if
write_partial_message_data() can be given a bvec[] at a time by the
iteration code, this would allow pages to be sent in a batch.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Ilya Dryomov <idryomov@gmail.com>
cc: Xiubo Li <xiubli@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: ceph-devel@vger.kernel.org
cc: netdev@vger.kernel.org
---
 net/ceph/messenger_v2.c | 91 +++++++++--------------------------------
 1 file changed, 19 insertions(+), 72 deletions(-)

diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index 301a991dc6a6..87ac97073e75 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -117,91 +117,38 @@ static int ceph_tcp_recv(struct ceph_connection *con)
 	return ret;
 }
 
-static int do_sendmsg(struct socket *sock, struct iov_iter *it)
-{
-	struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS };
-	int ret;
-
-	msg.msg_iter = *it;
-	while (iov_iter_count(it)) {
-		ret = sock_sendmsg(sock, &msg);
-		if (ret <= 0) {
-			if (ret == -EAGAIN)
-				ret = 0;
-			return ret;
-		}
-
-		iov_iter_advance(it, ret);
-	}
-
-	WARN_ON(msg_data_left(&msg));
-	return 1;
-}
-
-static int do_try_sendpage(struct socket *sock, struct iov_iter *it)
-{
-	struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS };
-	struct bio_vec bv;
-	int ret;
-
-	if (WARN_ON(!iov_iter_is_bvec(it)))
-		return -EINVAL;
-
-	while (iov_iter_count(it)) {
-		/* iov_iter_iovec() for ITER_BVEC */
-		bvec_set_page(&bv, it->bvec->bv_page,
-			      min(iov_iter_count(it),
-				  it->bvec->bv_len - it->iov_offset),
-			      it->bvec->bv_offset + it->iov_offset);
-
-		/*
-		 * sendpage cannot properly handle pages with
-		 * page_count == 0, we need to fall back to sendmsg if
-		 * that's the case.
-		 *
-		 * Same goes for slab pages: skb_can_coalesce() allows
-		 * coalescing neighboring slab objects into a single frag
-		 * which triggers one of hardened usercopy checks.
-		 */
-		if (sendpage_ok(bv.bv_page)) {
-			ret = sock->ops->sendpage(sock, bv.bv_page,
-						  bv.bv_offset, bv.bv_len,
-						  CEPH_MSG_FLAGS);
-		} else {
-			iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, bv.bv_len);
-			ret = sock_sendmsg(sock, &msg);
-		}
-		if (ret <= 0) {
-			if (ret == -EAGAIN)
-				ret = 0;
-			return ret;
-		}
-
-		iov_iter_advance(it, ret);
-	}
-
-	return 1;
-}
-
 /*
  * Write as much as possible.  The socket is expected to be corked,
- * so we don't bother with MSG_MORE/MSG_SENDPAGE_NOTLAST here.
+ * so we don't bother with MSG_MORE here.
  *
  * Return:
- *   1 - done, nothing (else) to write
+ *  >0 - done, nothing (else) to write
  *   0 - socket is full, need to wait
  *  <0 - error
  */
 static int ceph_tcp_send(struct ceph_connection *con)
 {
+	struct msghdr msg = {
+		.msg_iter	= con->v2.out_iter,
+		.msg_flags	= CEPH_MSG_FLAGS,
+	};
 	int ret;
 
+	if (WARN_ON(!iov_iter_is_bvec(&con->v2.out_iter)))
+		return -EINVAL;
+
+	if (con->v2.out_iter_sendpage)
+		msg.msg_flags |= MSG_SPLICE_PAGES;
+
 	dout("%s con %p have %zu try_sendpage %d\n", __func__, con,
 	     iov_iter_count(&con->v2.out_iter), con->v2.out_iter_sendpage);
-	if (con->v2.out_iter_sendpage)
-		ret = do_try_sendpage(con->sock, &con->v2.out_iter);
-	else
-		ret = do_sendmsg(con->sock, &con->v2.out_iter);
+
+	ret = sock_sendmsg(con->sock, &msg);
+	if (ret > 0)
+		iov_iter_advance(&con->v2.out_iter, ret);
+	else if (ret == -EAGAIN)
+		ret = 0;
+
 	dout("%s con %p ret %d left %zu\n", __func__, con, ret,
 	     iov_iter_count(&con->v2.out_iter));
 	return ret;

[PATCH net-next 08/17] rds: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage

[David Howells]

When transmitting data, call down into TCP using a single sendmsg with
MSG_SPLICE_PAGES to indicate that content should be spliced rather than
performing several sendmsg and sendpage calls to transmit header and data
pages.

To make this work, the data is assembled in a bio_vec array and attached to
a BVEC-type iterator.  The header are copied into memory acquired from
zcopy_alloc() which just breaks a page up into small pieces that can be
freed with put_page().

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Santosh Shilimkar <santosh.shilimkar@oracle.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: linux-rdma@vger.kernel.org
cc: rds-devel@oss.oracle.com
cc: netdev@vger.kernel.org
---
 net/rds/tcp_send.c | 74 +++++++++++++++++-----------------------------
 1 file changed, 27 insertions(+), 47 deletions(-)

diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 8c4d1d6e9249..550390d5ff2b 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -52,29 +52,23 @@ void rds_tcp_xmit_path_complete(struct rds_conn_path *cp)
 	tcp_sock_set_cork(tc->t_sock->sk, false);
 }
 
-/* the core send_sem serializes this with other xmit and shutdown */
-static int rds_tcp_sendmsg(struct socket *sock, void *data, unsigned int len)
-{
-	struct kvec vec = {
-		.iov_base = data,
-		.iov_len = len,
-	};
-	struct msghdr msg = {
-		.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL,
-	};
-
-	return kernel_sendmsg(sock, &msg, &vec, 1, vec.iov_len);
-}
-
 /* the core send_sem serializes this with other xmit and shutdown */
 int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
 		 unsigned int hdr_off, unsigned int sg, unsigned int off)
 {
 	struct rds_conn_path *cp = rm->m_inc.i_conn_path;
 	struct rds_tcp_connection *tc = cp->cp_transport_data;
+	struct msghdr msg = {
+		.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT | MSG_NOSIGNAL,
+	};
+	struct bio_vec *bvec;
+	unsigned int i, size = 0, ix = 0;
 	int done = 0;
-	int ret = 0;
-	int more;
+	int ret = -ENOMEM;
+
+	bvec = kmalloc_array(1 + sg, sizeof(struct bio_vec), GFP_KERNEL);
+	if (!bvec)
+		goto out;
 
 	if (hdr_off == 0) {
 		/*
@@ -101,41 +95,26 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
 		/* see rds_tcp_write_space() */
 		set_bit(SOCK_NOSPACE, &tc->t_sock->sk->sk_socket->flags);
 
-		ret = rds_tcp_sendmsg(tc->t_sock,
-				      (void *)&rm->m_inc.i_hdr + hdr_off,
-				      sizeof(rm->m_inc.i_hdr) - hdr_off);
-		if (ret < 0)
-			goto out;
-		done += ret;
-		if (hdr_off + done != sizeof(struct rds_header))
-			goto out;
+		bvec_set_virt(&bvec[ix], (void *)&rm->m_inc.i_hdr + hdr_off,
+			      sizeof(rm->m_inc.i_hdr) - hdr_off);
+		size += bvec[ix].bv_len;
+		ix++;
 	}
 
-	more = rm->data.op_nents > 1 ? (MSG_MORE | MSG_SENDPAGE_NOTLAST) : 0;
-	while (sg < rm->data.op_nents) {
-		int flags = MSG_DONTWAIT | MSG_NOSIGNAL | more;
-
-		ret = tc->t_sock->ops->sendpage(tc->t_sock,
-						sg_page(&rm->data.op_sg[sg]),
-						rm->data.op_sg[sg].offset + off,
-						rm->data.op_sg[sg].length - off,
-						flags);
-		rdsdebug("tcp sendpage %p:%u:%u ret %d\n", (void *)sg_page(&rm->data.op_sg[sg]),
-			 rm->data.op_sg[sg].offset + off, rm->data.op_sg[sg].length - off,
-			 ret);
-		if (ret <= 0)
-			break;
-
-		off += ret;
-		done += ret;
-		if (off == rm->data.op_sg[sg].length) {
-			off = 0;
-			sg++;
-		}
-		if (sg == rm->data.op_nents - 1)
-			more = 0;
+	for (i = sg; i < rm->data.op_nents; i++) {
+		bvec_set_page(&bvec[ix],
+			      sg_page(&rm->data.op_sg[i]),
+			      rm->data.op_sg[i].length - off,
+			      rm->data.op_sg[i].offset + off);
+		off = 0;
+		size += bvec[ix].bv_len;
+		ix++;
 	}
 
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, bvec, ix, size);
+	ret = sock_sendmsg(tc->t_sock, &msg);
+	rdsdebug("tcp sendmsg-splice %u,%u ret %d\n", ix, size, ret);
+
 out:
 	if (ret <= 0) {
 		/* write_space will hit after EAGAIN, all else fatal */
@@ -158,6 +137,7 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
 	}
 	if (done == 0)
 		done = ret;
+	kfree(bvec);
 	return done;
 }
 

[PATCH net-next 09/17] dlm: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage

[David Howells]

When transmitting data, call down a layer using a single sendmsg with
MSG_SPLICE_PAGES to indicate that content should be spliced rather using
sendpage.  This allows ->sendpage() to be replaced by something that can
handle multiple multipage folios in a single transaction.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Christine Caulfield <ccaulfie@redhat.com>
cc: David Teigland <teigland@redhat.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: cluster-devel@redhat.com
cc: netdev@vger.kernel.org
---
 fs/dlm/lowcomms.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 3d3802c47b8b..5c12d8cdfc16 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1395,8 +1395,11 @@ int dlm_lowcomms_resend_msg(struct dlm_msg *msg)
 /* Send a message */
 static int send_to_sock(struct connection *con)
 {
-	const int msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
 	struct writequeue_entry *e;
+	struct bio_vec bvec;
+	struct msghdr msg = {
+		.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT | MSG_NOSIGNAL,
+	};
 	int len, offset, ret;
 
 	spin_lock_bh(&con->writequeue_lock);
@@ -1412,8 +1415,9 @@ static int send_to_sock(struct connection *con)
 	WARN_ON_ONCE(len == 0 && e->users == 0);
 	spin_unlock_bh(&con->writequeue_lock);
 
-	ret = kernel_sendpage(con->sock, e->page, offset, len,
-			      msg_flags);
+	bvec_set_page(&bvec, e->page, len, offset);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, len);
+	ret = sock_sendmsg(con->sock, &msg);
 	trace_dlm_send(con->nodeid, ret);
 	if (ret == -EAGAIN || ret == 0) {
 		lock_sock(con->sock->sk);

[PATCH net-next 10/17] nvme: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage

[David Howells]

When transmitting data, call down into TCP using a single sendmsg with
MSG_SPLICE_PAGES to indicate that content should be spliced rather than
performing several sendmsg and sendpage calls to transmit header, data
pages and trailer.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Keith Busch <kbusch@kernel.org>
cc: Jens Axboe <axboe@fb.com>
cc: Christoph Hellwig <hch@lst.de>
cc: Sagi Grimberg <sagi@grimberg.me>
cc: Chaitanya Kulkarni <kch@nvidia.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: linux-nvme@lists.infradead.org
cc: netdev@vger.kernel.org
---
 drivers/nvme/host/tcp.c   | 44 ++++++++++++++++++-------------------
 drivers/nvme/target/tcp.c | 46 ++++++++++++++++++++++++---------------
 2 files changed, 51 insertions(+), 39 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index bf0230442d57..947868c66ef4 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -997,25 +997,23 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 	u32 h2cdata_left = req->h2cdata_left;
 
 	while (true) {
+		struct bio_vec bvec;
+		struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES, };
 		struct page *page = nvme_tcp_req_cur_page(req);
 		size_t offset = nvme_tcp_req_cur_offset(req);
 		size_t len = nvme_tcp_req_cur_length(req);
 		bool last = nvme_tcp_pdu_last_send(req, len);
 		int req_data_sent = req->data_sent;
-		int ret, flags = MSG_DONTWAIT;
+		int ret;
 
 		if (last && !queue->data_digest && !nvme_tcp_queue_more(queue))
-			flags |= MSG_EOR;
+			msg.msg_flags |= MSG_EOR;
 		else
-			flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
+			msg.msg_flags |= MSG_MORE;
 
-		if (sendpage_ok(page)) {
-			ret = kernel_sendpage(queue->sock, page, offset, len,
-					flags);
-		} else {
-			ret = sock_no_sendpage(queue->sock, page, offset, len,
-					flags);
-		}
+		bvec_set_page(&bvec, page, len, offset);
+		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, len);
+		ret = sock_sendmsg(queue->sock, &msg);
 		if (ret <= 0)
 			return ret;
 
@@ -1054,22 +1052,24 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req)
 {
 	struct nvme_tcp_queue *queue = req->queue;
 	struct nvme_tcp_cmd_pdu *pdu = nvme_tcp_req_cmd_pdu(req);
+	struct bio_vec bvec;
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES, };
 	bool inline_data = nvme_tcp_has_inline_data(req);
 	u8 hdgst = nvme_tcp_hdgst_len(queue);
 	int len = sizeof(*pdu) + hdgst - req->offset;
-	int flags = MSG_DONTWAIT;
 	int ret;
 
 	if (inline_data || nvme_tcp_queue_more(queue))
-		flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
+		msg.msg_flags |= MSG_MORE;
 	else
-		flags |= MSG_EOR;
+		msg.msg_flags |= MSG_EOR;
 
 	if (queue->hdr_digest && !req->offset)
 		nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
 
-	ret = kernel_sendpage(queue->sock, virt_to_page(pdu),
-			offset_in_page(pdu) + req->offset, len,  flags);
+	bvec_set_virt(&bvec, (void *)pdu + req->offset, len);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, len);
+	ret = sock_sendmsg(queue->sock, &msg);
 	if (unlikely(ret <= 0))
 		return ret;
 
@@ -1093,6 +1093,8 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)
 {
 	struct nvme_tcp_queue *queue = req->queue;
 	struct nvme_tcp_data_pdu *pdu = nvme_tcp_req_data_pdu(req);
+	struct bio_vec bvec;
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_MORE, };
 	u8 hdgst = nvme_tcp_hdgst_len(queue);
 	int len = sizeof(*pdu) - req->offset + hdgst;
 	int ret;
@@ -1101,13 +1103,11 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)
 		nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu));
 
 	if (!req->h2cdata_left)
-		ret = kernel_sendpage(queue->sock, virt_to_page(pdu),
-				offset_in_page(pdu) + req->offset, len,
-				MSG_DONTWAIT | MSG_MORE | MSG_SENDPAGE_NOTLAST);
-	else
-		ret = sock_no_sendpage(queue->sock, virt_to_page(pdu),
-				offset_in_page(pdu) + req->offset, len,
-				MSG_DONTWAIT | MSG_MORE);
+		msg.msg_flags |= MSG_SPLICE_PAGES;
+
+	bvec_set_virt(&bvec, (void *)pdu + req->offset, len);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, len);
+	ret = sock_sendmsg(queue->sock, &msg);
 	if (unlikely(ret <= 0))
 		return ret;
 
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index ed98df72c76b..868aa4de2e4c 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -576,13 +576,17 @@ static void nvmet_tcp_execute_request(struct nvmet_tcp_cmd *cmd)
 
 static int nvmet_try_send_data_pdu(struct nvmet_tcp_cmd *cmd)
 {
+	struct msghdr msg = {
+		.msg_flags = MSG_DONTWAIT | MSG_MORE | MSG_SPLICE_PAGES,
+	};
+	struct bio_vec bvec;
 	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
 	int left = sizeof(*cmd->data_pdu) - cmd->offset + hdgst;
 	int ret;
 
-	ret = kernel_sendpage(cmd->queue->sock, virt_to_page(cmd->data_pdu),
-			offset_in_page(cmd->data_pdu) + cmd->offset,
-			left, MSG_DONTWAIT | MSG_MORE | MSG_SENDPAGE_NOTLAST);
+	bvec_set_virt(&bvec, (void *)cmd->data_pdu + cmd->offset, left);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, left);
+	ret = sock_sendmsg(cmd->queue->sock, &msg);
 	if (ret <= 0)
 		return ret;
 
@@ -603,17 +607,21 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 	int ret;
 
 	while (cmd->cur_sg) {
+		struct msghdr msg = {
+			.msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES,
+		};
 		struct page *page = sg_page(cmd->cur_sg);
+		struct bio_vec bvec;
 		u32 left = cmd->cur_sg->length - cmd->offset;
-		int flags = MSG_DONTWAIT;
 
 		if ((!last_in_batch && cmd->queue->send_list_len) ||
 		    cmd->wbytes_done + left < cmd->req.transfer_len ||
 		    queue->data_digest || !queue->nvme_sq.sqhd_disabled)
-			flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
+			msg.msg_flags |= MSG_MORE;
 
-		ret = kernel_sendpage(cmd->queue->sock, page, cmd->offset,
-					left, flags);
+		bvec_set_page(&bvec, page, left, cmd->offset);
+		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, left);
+		ret = sock_sendmsg(cmd->queue->sock, &msg);
 		if (ret <= 0)
 			return ret;
 
@@ -649,18 +657,20 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
 		bool last_in_batch)
 {
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES, };
+	struct bio_vec bvec;
 	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
 	int left = sizeof(*cmd->rsp_pdu) - cmd->offset + hdgst;
-	int flags = MSG_DONTWAIT;
 	int ret;
 
 	if (!last_in_batch && cmd->queue->send_list_len)
-		flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
+		msg.msg_flags |= MSG_MORE;
 	else
-		flags |= MSG_EOR;
+		msg.msg_flags |= MSG_EOR;
 
-	ret = kernel_sendpage(cmd->queue->sock, virt_to_page(cmd->rsp_pdu),
-		offset_in_page(cmd->rsp_pdu) + cmd->offset, left, flags);
+	bvec_set_virt(&bvec, (void *)cmd->rsp_pdu + cmd->offset, left);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, left);
+	ret = sock_sendmsg(cmd->queue->sock, &msg);
 	if (ret <= 0)
 		return ret;
 	cmd->offset += ret;
@@ -677,18 +687,20 @@ static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
 
 static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 {
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES, };
+	struct bio_vec bvec;
 	u8 hdgst = nvmet_tcp_hdgst_len(cmd->queue);
 	int left = sizeof(*cmd->r2t_pdu) - cmd->offset + hdgst;
-	int flags = MSG_DONTWAIT;
 	int ret;
 
 	if (!last_in_batch && cmd->queue->send_list_len)
-		flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
+		msg.msg_flags |= MSG_MORE;
 	else
-		flags |= MSG_EOR;
+		msg.msg_flags |= MSG_EOR;
 
-	ret = kernel_sendpage(cmd->queue->sock, virt_to_page(cmd->r2t_pdu),
-		offset_in_page(cmd->r2t_pdu) + cmd->offset, left, flags);
+	bvec_set_virt(&bvec, (void *)cmd->r2t_pdu + cmd->offset, left);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, left);
+	ret = sock_sendmsg(cmd->queue->sock, &msg);
 	if (ret <= 0)
 		return ret;
 	cmd->offset += ret;

[PATCH net-next 11/17] smc: Drop smc_sendpage() in favour of smc_sendmsg() + MSG_SPLICE_PAGES

[David Howells]

Drop the smc_sendpage() code as smc_sendmsg() just passes the call down to
the underlying TCP socket and smc_tx_sendpage() is just a wrapper around
its sendmsg implementation.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Karsten Graul <kgraul@linux.ibm.com>
cc: Wenjia Zhang <wenjia@linux.ibm.com>
cc: Jan Karcher <jaka@linux.ibm.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: linux-s390@vger.kernel.org
cc: netdev@vger.kernel.org
---
 net/smc/af_smc.c    | 29 -----------------------------
 net/smc/smc_stats.c |  2 +-
 net/smc/smc_stats.h |  1 -
 net/smc/smc_tx.c    | 22 +---------------------
 net/smc/smc_tx.h    |  2 --
 5 files changed, 2 insertions(+), 54 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 538e9c6ec8c9..a7f887d91d89 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -3133,34 +3133,6 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 	return put_user(answ, (int __user *)arg);
 }
 
-static ssize_t smc_sendpage(struct socket *sock, struct page *page,
-			    int offset, size_t size, int flags)
-{
-	struct sock *sk = sock->sk;
-	struct smc_sock *smc;
-	int rc = -EPIPE;
-
-	smc = smc_sk(sk);
-	lock_sock(sk);
-	if (sk->sk_state != SMC_ACTIVE) {
-		release_sock(sk);
-		goto out;
-	}
-	release_sock(sk);
-	if (smc->use_fallback) {
-		rc = kernel_sendpage(smc->clcsock, page, offset,
-				     size, flags);
-	} else {
-		lock_sock(sk);
-		rc = smc_tx_sendpage(smc, page, offset, size, flags);
-		release_sock(sk);
-		SMC_STAT_INC(smc, sendpage_cnt);
-	}
-
-out:
-	return rc;
-}
-
 /* Map the affected portions of the rmbe into an spd, note the number of bytes
  * to splice in conn->splice_pending, and press 'go'. Delays consumer cursor
  * updates till whenever a respective page has been fully processed.
@@ -3232,7 +3204,6 @@ static const struct proto_ops smc_sock_ops = {
 	.sendmsg	= smc_sendmsg,
 	.recvmsg	= smc_recvmsg,
 	.mmap		= sock_no_mmap,
-	.sendpage	= smc_sendpage,
 	.splice_read	= smc_splice_read,
 };
 
diff --git a/net/smc/smc_stats.c b/net/smc/smc_stats.c
index e80e34f7ac15..ca14c0f3a07d 100644
--- a/net/smc/smc_stats.c
+++ b/net/smc/smc_stats.c
@@ -227,7 +227,7 @@ static int smc_nl_fill_stats_tech_data(struct sk_buff *skb,
 			      SMC_NLA_STATS_PAD))
 		goto errattr;
 	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SENDPAGE_CNT,
-			      smc_tech->sendpage_cnt,
+			      0,
 			      SMC_NLA_STATS_PAD))
 		goto errattr;
 	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CORK_CNT,
diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h
index 84b7ecd8c05c..b60fe1eb37ab 100644
--- a/net/smc/smc_stats.h
+++ b/net/smc/smc_stats.h
@@ -71,7 +71,6 @@ struct smc_stats_tech {
 	u64			clnt_v2_succ_cnt;
 	u64			srv_v1_succ_cnt;
 	u64			srv_v2_succ_cnt;
-	u64			sendpage_cnt;
 	u64			urg_data_cnt;
 	u64			splice_cnt;
 	u64			cork_cnt;
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 9b9e0a190734..5147207808e5 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -167,8 +167,7 @@ static bool smc_tx_should_cork(struct smc_sock *smc, struct msghdr *msg)
 	 * sndbuf_space is still available. The applications
 	 * should known how/when to uncork it.
 	 */
-	if ((msg->msg_flags & MSG_MORE ||
-	     smc_tx_is_corked(smc)) &&
+	if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) &&
 	    atomic_read(&conn->sndbuf_space))
 		return true;
 
@@ -297,25 +296,6 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
 	return rc;
 }
 
-int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset,
-		    size_t size, int flags)
-{
-	struct msghdr msg = {.msg_flags = flags};
-	char *kaddr = kmap(page);
-	struct kvec iov;
-	int rc;
-
-	if (flags & MSG_SENDPAGE_NOTLAST)
-		msg.msg_flags |= MSG_MORE;
-
-	iov.iov_base = kaddr + offset;
-	iov.iov_len = size;
-	iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iov, 1, size);
-	rc = smc_tx_sendmsg(smc, &msg, size);
-	kunmap(page);
-	return rc;
-}
-
 /***************************** sndbuf consumer *******************************/
 
 /* sndbuf consumer: actual data transfer of one target chunk with ISM write */
diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h
index 34b578498b1f..a59f370b8b43 100644
--- a/net/smc/smc_tx.h
+++ b/net/smc/smc_tx.h
@@ -31,8 +31,6 @@ void smc_tx_pending(struct smc_connection *conn);
 void smc_tx_work(struct work_struct *work);
 void smc_tx_init(struct smc_sock *smc);
 int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len);
-int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset,
-		    size_t size, int flags);
 int smc_tx_sndbuf_nonempty(struct smc_connection *conn);
 void smc_tx_sndbuf_nonfull(struct smc_sock *smc);
 void smc_tx_consumer_update(struct smc_connection *conn, bool force);

[PATCH net-next 12/17] ocfs2: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage()

[David Howells]

Fix ocfs2 to use the page fragment allocator rather than kzalloc in order
to allocate the buffers for the handshake message and keepalive request and
reply messages.

Switch from using sendpage() to using sendmsg() + MSG_SPLICE_PAGES so that
sendpage can be phased out.

Signed-off-by: David Howells <dhowells@redhat.com>

cc: Mark Fasheh <mark@fasheh.com>
cc: Joel Becker <jlbec@evilplan.org>
cc: Joseph Qi <joseph.qi@linux.alibaba.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: ocfs2-devel@oss.oracle.com
cc: netdev@vger.kernel.org
---
 fs/ocfs2/cluster/tcp.c | 107 ++++++++++++++++++++++-------------------
 1 file changed, 58 insertions(+), 49 deletions(-)

diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index aecbd712a00c..b543f72d85f2 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -110,9 +110,6 @@ static struct work_struct o2net_listen_work;
 static struct o2hb_callback_func o2net_hb_up, o2net_hb_down;
 #define O2NET_HB_PRI 0x1
 
-static struct o2net_handshake *o2net_hand;
-static struct o2net_msg *o2net_keep_req, *o2net_keep_resp;
-
 static int o2net_sys_err_translations[O2NET_ERR_MAX] =
 		{[O2NET_ERR_NONE]	= 0,
 		 [O2NET_ERR_NO_HNDLR]	= -ENOPROTOOPT,
@@ -930,19 +927,22 @@ static int o2net_send_tcp_msg(struct socket *sock, struct kvec *vec,
 }
 
 static void o2net_sendpage(struct o2net_sock_container *sc,
-			   void *kmalloced_virt,
-			   size_t size)
+			   void *virt, size_t size)
 {
 	struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num);
+	struct msghdr msg = {};
+	struct bio_vec bv;
 	ssize_t ret;
 
+	bvec_set_virt(&bv, virt, size);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, size);
+
 	while (1) {
+		msg.msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES;
 		mutex_lock(&sc->sc_send_lock);
-		ret = sc->sc_sock->ops->sendpage(sc->sc_sock,
-						 virt_to_page(kmalloced_virt),
-						 offset_in_page(kmalloced_virt),
-						 size, MSG_DONTWAIT);
+		ret = sock_sendmsg(sc->sc_sock, &msg);
 		mutex_unlock(&sc->sc_send_lock);
+
 		if (ret == size)
 			break;
 		if (ret == (ssize_t)-EAGAIN) {
@@ -1168,6 +1168,7 @@ static int o2net_process_message(struct o2net_sock_container *sc,
 				 struct o2net_msg *hdr)
 {
 	struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num);
+	struct o2net_msg *keep_resp;
 	int ret = 0, handler_status;
 	enum  o2net_system_error syserr;
 	struct o2net_msg_handler *nmh = NULL;
@@ -1186,8 +1187,16 @@ static int o2net_process_message(struct o2net_sock_container *sc,
 					   be32_to_cpu(hdr->status));
 			goto out;
 		case O2NET_MSG_KEEP_REQ_MAGIC:
-			o2net_sendpage(sc, o2net_keep_resp,
-				       sizeof(*o2net_keep_resp));
+			keep_resp = alloc_skb_frag(sizeof(*keep_resp),
+						   GFP_KERNEL);
+			if (!keep_resp) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			memset(keep_resp, 0, sizeof(*keep_resp));
+			keep_resp->magic = cpu_to_be16(O2NET_MSG_KEEP_RESP_MAGIC);
+			o2net_sendpage(sc, keep_resp, sizeof(*keep_resp));
+			folio_put(virt_to_folio(keep_resp));
 			goto out;
 		case O2NET_MSG_KEEP_RESP_MAGIC:
 			goto out;
@@ -1439,15 +1448,22 @@ static void o2net_rx_until_empty(struct work_struct *work)
 	sc_put(sc);
 }
 
-static void o2net_initialize_handshake(void)
+static struct o2net_handshake *o2net_initialize_handshake(void)
 {
-	o2net_hand->o2hb_heartbeat_timeout_ms = cpu_to_be32(
-		O2HB_MAX_WRITE_TIMEOUT_MS);
-	o2net_hand->o2net_idle_timeout_ms = cpu_to_be32(o2net_idle_timeout());
-	o2net_hand->o2net_keepalive_delay_ms = cpu_to_be32(
-		o2net_keepalive_delay());
-	o2net_hand->o2net_reconnect_delay_ms = cpu_to_be32(
-		o2net_reconnect_delay());
+	struct o2net_handshake *hand;
+
+	hand = alloc_skb_frag(sizeof(*hand), GFP_KERNEL);
+	if (!hand)
+		return NULL;
+
+	memset(hand, 0, sizeof(*hand));
+	hand->protocol_version		= cpu_to_be64(O2NET_PROTOCOL_VERSION);
+	hand->connector_id		= cpu_to_be64(1);
+	hand->o2hb_heartbeat_timeout_ms	= cpu_to_be32(O2HB_MAX_WRITE_TIMEOUT_MS);
+	hand->o2net_idle_timeout_ms	= cpu_to_be32(o2net_idle_timeout());
+	hand->o2net_keepalive_delay_ms	= cpu_to_be32(o2net_keepalive_delay());
+	hand->o2net_reconnect_delay_ms	= cpu_to_be32(o2net_reconnect_delay());
+	return hand;
 }
 
 /* ------------------------------------------------------------ */
@@ -1456,16 +1472,22 @@ static void o2net_initialize_handshake(void)
  * rx path will see the response and mark the sc valid */
 static void o2net_sc_connect_completed(struct work_struct *work)
 {
+	struct o2net_handshake *hand;
 	struct o2net_sock_container *sc =
 		container_of(work, struct o2net_sock_container,
 			     sc_connect_work);
 
+	hand = o2net_initialize_handshake();
+	if (!hand)
+		goto out;
+
 	mlog(ML_MSG, "sc sending handshake with ver %llu id %llx\n",
               (unsigned long long)O2NET_PROTOCOL_VERSION,
-	      (unsigned long long)be64_to_cpu(o2net_hand->connector_id));
+	      (unsigned long long)be64_to_cpu(hand->connector_id));
 
-	o2net_initialize_handshake();
-	o2net_sendpage(sc, o2net_hand, sizeof(*o2net_hand));
+	o2net_sendpage(sc, hand, sizeof(*hand));
+	folio_put(virt_to_folio(hand));
+out:
 	sc_put(sc);
 }
 
@@ -1475,8 +1497,15 @@ static void o2net_sc_send_keep_req(struct work_struct *work)
 	struct o2net_sock_container *sc =
 		container_of(work, struct o2net_sock_container,
 			     sc_keepalive_work.work);
+	struct o2net_msg *keep_req;
 
-	o2net_sendpage(sc, o2net_keep_req, sizeof(*o2net_keep_req));
+	keep_req = alloc_skb_frag(sizeof(*keep_req), GFP_KERNEL);
+	if (keep_req) {
+		memset(keep_req, 0, sizeof(*keep_req));
+		keep_req->magic = cpu_to_be16(O2NET_MSG_KEEP_REQ_MAGIC);
+		o2net_sendpage(sc, keep_req, sizeof(*keep_req));
+		folio_put(virt_to_folio(keep_req));
+	}
 	sc_put(sc);
 }
 
@@ -1780,6 +1809,7 @@ static int o2net_accept_one(struct socket *sock, int *more)
 	struct socket *new_sock = NULL;
 	struct o2nm_node *node = NULL;
 	struct o2nm_node *local_node = NULL;
+	struct o2net_handshake *hand;
 	struct o2net_sock_container *sc = NULL;
 	struct o2net_node *nn;
 	unsigned int nofs_flag;
@@ -1882,8 +1912,11 @@ static int o2net_accept_one(struct socket *sock, int *more)
 	o2net_register_callbacks(sc->sc_sock->sk, sc);
 	o2net_sc_queue_work(sc, &sc->sc_rx_work);
 
-	o2net_initialize_handshake();
-	o2net_sendpage(sc, o2net_hand, sizeof(*o2net_hand));
+	hand = o2net_initialize_handshake();
+	if (hand) {
+		o2net_sendpage(sc, hand, sizeof(*hand));
+		folio_put(virt_to_folio(hand));
+	}
 
 out:
 	if (new_sock)
@@ -2090,21 +2123,8 @@ int o2net_init(void)
 	unsigned long i;
 
 	o2quo_init();
-
 	o2net_debugfs_init();
 
-	o2net_hand = kzalloc(sizeof(struct o2net_handshake), GFP_KERNEL);
-	o2net_keep_req = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL);
-	o2net_keep_resp = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL);
-	if (!o2net_hand || !o2net_keep_req || !o2net_keep_resp)
-		goto out;
-
-	o2net_hand->protocol_version = cpu_to_be64(O2NET_PROTOCOL_VERSION);
-	o2net_hand->connector_id = cpu_to_be64(1);
-
-	o2net_keep_req->magic = cpu_to_be16(O2NET_MSG_KEEP_REQ_MAGIC);
-	o2net_keep_resp->magic = cpu_to_be16(O2NET_MSG_KEEP_RESP_MAGIC);
-
 	for (i = 0; i < ARRAY_SIZE(o2net_nodes); i++) {
 		struct o2net_node *nn = o2net_nn_from_num(i);
 
@@ -2122,21 +2142,10 @@ int o2net_init(void)
 	}
 
 	return 0;
-
-out:
-	kfree(o2net_hand);
-	kfree(o2net_keep_req);
-	kfree(o2net_keep_resp);
-	o2net_debugfs_exit();
-	o2quo_exit();
-	return -ENOMEM;
 }
 
 void o2net_exit(void)
 {
 	o2quo_exit();
-	kfree(o2net_hand);
-	kfree(o2net_keep_req);
-	kfree(o2net_keep_resp);
 	o2net_debugfs_exit();
 }

[PATCH net-next 13/17] drbd: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage()

[David Howells]

Use sendmsg() conditionally with MSG_SPLICE_PAGES in _drbd_send_page()
rather than calling sendpage() or _drbd_no_send_page().

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Philipp Reisner <philipp.reisner@linbit.com>
cc: Lars Ellenberg <lars.ellenberg@linbit.com>
cc: "Christoph Böhmwalder" <christoph.boehmwalder@linbit.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: drbd-dev@lists.linbit.com
cc: linux-block@vger.kernel.org
cc: netdev@vger.kernel.org
---
 drivers/block/drbd/drbd_main.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 83987e7a5ef2..c9d84183844c 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1540,7 +1540,8 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa
 		    int offset, size_t size, unsigned msg_flags)
 {
 	struct socket *socket = peer_device->connection->data.socket;
-	int len = size;
+	struct bio_vec bvec;
+	struct msghdr msg = { .msg_flags = msg_flags, };
 	int err = -EIO;
 
 	/* e.g. XFS meta- & log-data is in slab pages, which have a
@@ -1549,33 +1550,33 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa
 	 * put_page(); and would cause either a VM_BUG directly, or
 	 * __page_cache_release a page that would actually still be referenced
 	 * by someone, leading to some obscure delayed Oops somewhere else. */
-	if (drbd_disable_sendpage || !sendpage_ok(page))
-		return _drbd_no_send_page(peer_device, page, offset, size, msg_flags);
+	if (!drbd_disable_sendpage && sendpage_ok(page))
+		msg.msg_flags |= MSG_NOSIGNAL | MSG_SPLICE_PAGES;
+
+	bvec_set_page(&bvec, page, offset, size);
+	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
 
-	msg_flags |= MSG_NOSIGNAL;
 	drbd_update_congested(peer_device->connection);
 	do {
 		int sent;
 
-		sent = socket->ops->sendpage(socket, page, offset, len, msg_flags);
+		sent = sock_sendmsg(socket, &msg);
 		if (sent <= 0) {
 			if (sent == -EAGAIN) {
 				if (we_should_drop_the_connection(peer_device->connection, socket))
 					break;
 				continue;
 			}
-			drbd_warn(peer_device->device, "%s: size=%d len=%d sent=%d\n",
-			     __func__, (int)size, len, sent);
+			drbd_warn(peer_device->device, "%s: size=%d len=%zu sent=%d\n",
+				  __func__, (int)size, msg_data_left(&msg), sent);
 			if (sent < 0)
 				err = sent;
 			break;
 		}
-		len    -= sent;
-		offset += sent;
-	} while (len > 0 /* THINK && device->cstate >= C_CONNECTED*/);
+	} while (msg_data_left(&msg) /* THINK && device->cstate >= C_CONNECTED*/);
 	clear_bit(NET_CONGESTED, &peer_device->connection->flags);
 
-	if (len == 0) {
+	if (!msg_data_left(&msg)) {
 		err = 0;
 		peer_device->device->send_cnt += size >> 9;
 	}

[PATCH net-next 14/17] drdb: Send an entire bio in a single sendmsg

[David Howells]

Since _drdb_sendpage() is now using sendmsg to send the pages rather
sendpage, pass the entire bio in one go using a bvec iterator instead of
doing it piecemeal.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Philipp Reisner <philipp.reisner@linbit.com>
cc: Lars Ellenberg <lars.ellenberg@linbit.com>
cc: "Christoph Böhmwalder" <christoph.boehmwalder@linbit.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: drbd-dev@lists.linbit.com
cc: linux-block@vger.kernel.org
cc: netdev@vger.kernel.org
---
 drivers/block/drbd/drbd_main.c | 77 +++++++++++-----------------------
 1 file changed, 25 insertions(+), 52 deletions(-)

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index c9d84183844c..f7ebdb5ab45e 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1520,28 +1520,15 @@ static void drbd_update_congested(struct drbd_connection *connection)
  * As a workaround, we disable sendpage on pages
  * with page_count == 0 or PageSlab.
  */
-static int _drbd_no_send_page(struct drbd_peer_device *peer_device, struct page *page,
-			      int offset, size_t size, unsigned msg_flags)
-{
-	struct socket *socket;
-	void *addr;
-	int err;
-
-	socket = peer_device->connection->data.socket;
-	addr = kmap(page) + offset;
-	err = drbd_send_all(peer_device->connection, socket, addr, size, msg_flags);
-	kunmap(page);
-	if (!err)
-		peer_device->device->send_cnt += size >> 9;
-	return err;
-}
-
-static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *page,
-		    int offset, size_t size, unsigned msg_flags)
+static int _drbd_send_pages(struct drbd_peer_device *peer_device,
+			    struct iov_iter *iter, unsigned msg_flags)
 {
 	struct socket *socket = peer_device->connection->data.socket;
-	struct bio_vec bvec;
-	struct msghdr msg = { .msg_flags = msg_flags, };
+	struct msghdr msg = {
+		.msg_flags	= msg_flags | MSG_NOSIGNAL,
+		.msg_iter	= *iter,
+	};
+	size_t size = iov_iter_count(iter);
 	int err = -EIO;
 
 	/* e.g. XFS meta- & log-data is in slab pages, which have a
@@ -1550,11 +1537,8 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa
 	 * put_page(); and would cause either a VM_BUG directly, or
 	 * __page_cache_release a page that would actually still be referenced
 	 * by someone, leading to some obscure delayed Oops somewhere else. */
-	if (!drbd_disable_sendpage && sendpage_ok(page))
-		msg.msg_flags |= MSG_NOSIGNAL | MSG_SPLICE_PAGES;
-
-	bvec_set_page(&bvec, page, offset, size);
-	iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
+	if (drbd_disable_sendpage)
+		msg.msg_flags &= ~(MSG_NOSIGNAL | MSG_SPLICE_PAGES);
 
 	drbd_update_congested(peer_device->connection);
 	do {
@@ -1585,39 +1569,22 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa
 
 static int _drbd_send_bio(struct drbd_peer_device *peer_device, struct bio *bio)
 {
-	struct bio_vec bvec;
-	struct bvec_iter iter;
+	struct iov_iter iter;
 
-	/* hint all but last page with MSG_MORE */
-	bio_for_each_segment(bvec, bio, iter) {
-		int err;
+	iov_iter_bvec(&iter, ITER_SOURCE, bio->bi_io_vec, bio->bi_vcnt,
+		      bio->bi_iter.bi_size);
 
-		err = _drbd_no_send_page(peer_device, bvec.bv_page,
-					 bvec.bv_offset, bvec.bv_len,
-					 bio_iter_last(bvec, iter)
-					 ? 0 : MSG_MORE);
-		if (err)
-			return err;
-	}
-	return 0;
+	return _drbd_send_pages(peer_device, &iter, 0);
 }
 
 static int _drbd_send_zc_bio(struct drbd_peer_device *peer_device, struct bio *bio)
 {
-	struct bio_vec bvec;
-	struct bvec_iter iter;
+	struct iov_iter iter;
 
-	/* hint all but last page with MSG_MORE */
-	bio_for_each_segment(bvec, bio, iter) {
-		int err;
+	iov_iter_bvec(&iter, ITER_SOURCE, bio->bi_io_vec, bio->bi_vcnt,
+		      bio->bi_iter.bi_size);
 
-		err = _drbd_send_page(peer_device, bvec.bv_page,
-				      bvec.bv_offset, bvec.bv_len,
-				      bio_iter_last(bvec, iter) ? 0 : MSG_MORE);
-		if (err)
-			return err;
-	}
-	return 0;
+	return _drbd_send_pages(peer_device, &iter, MSG_SPLICE_PAGES);
 }
 
 static int _drbd_send_zc_ee(struct drbd_peer_device *peer_device,
@@ -1629,10 +1596,16 @@ static int _drbd_send_zc_ee(struct drbd_peer_device *peer_device,
 
 	/* hint all but last page with MSG_MORE */
 	page_chain_for_each(page) {
+		struct iov_iter iter;
+		struct bio_vec bvec;
 		unsigned l = min_t(unsigned, len, PAGE_SIZE);
 
-		err = _drbd_send_page(peer_device, page, 0, l,
-				      page_chain_next(page) ? MSG_MORE : 0);
+		bvec_set_page(&bvec, page, 0, l);
+		iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, l);
+
+		err = _drbd_send_pages(peer_device, &iter,
+				       MSG_SPLICE_PAGES |
+				       (page_chain_next(page) ? MSG_MORE : 0));
 		if (err)
 			return err;
 		len -= l;

[PATCH net-next 15/17] iscsi: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage

[David Howells]

Use sendmsg() with MSG_SPLICE_PAGES rather than sendpage.  This allows
multiple pages and multipage folios to be passed through.

TODO: iscsit_fe_sendpage_sg() should perhaps set up a bio_vec array for the
entire set of pages it's going to transfer plus two for the header and
trailer and page fragments to hold the header and trailer - and then call
sendmsg once for the entire message.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: "Martin K. Petersen" <martin.petersen@oracle.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: linux-scsi@vger.kernel.org
cc: target-devel@vger.kernel.org
cc: netdev@vger.kernel.org
---
 drivers/scsi/iscsi_tcp.c                 | 26 +++++++++---------------
 drivers/scsi/iscsi_tcp.h                 |  2 +-
 drivers/target/iscsi/iscsi_target_util.c | 14 +++++++------
 3 files changed, 19 insertions(+), 23 deletions(-)

diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 9637d4bc2bc9..9ab8555180a3 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -301,35 +301,32 @@ static int iscsi_sw_tcp_xmit_segment(struct iscsi_tcp_conn *tcp_conn,
 
 	while (!iscsi_tcp_segment_done(tcp_conn, segment, 0, r)) {
 		struct scatterlist *sg;
+		struct msghdr msg = {};
+		struct bio_vec bv;
 		unsigned int offset, copy;
-		int flags = 0;
 
 		r = 0;
 		offset = segment->copied;
 		copy = segment->size - offset;
 
 		if (segment->total_copied + segment->size < segment->total_size)
-			flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
+			msg.msg_flags |= MSG_MORE;
 
 		if (tcp_sw_conn->queue_recv)
-			flags |= MSG_DONTWAIT;
+			msg.msg_flags |= MSG_DONTWAIT;
 
-		/* Use sendpage if we can; else fall back to sendmsg */
 		if (!segment->data) {
+			if (!tcp_conn->iscsi_conn->datadgst_en)
+				msg.msg_flags |= MSG_SPLICE_PAGES;
 			sg = segment->sg;
 			offset += segment->sg_offset + sg->offset;
-			r = tcp_sw_conn->sendpage(sk, sg_page(sg), offset,
-						  copy, flags);
+			bvec_set_page(&bv, sg_page(sg), copy, offset);
 		} else {
-			struct msghdr msg = { .msg_flags = flags };
-			struct kvec iov = {
-				.iov_base = segment->data + offset,
-				.iov_len = copy
-			};
-
-			r = kernel_sendmsg(sk, &msg, &iov, 1, copy);
+			bvec_set_virt(&bv, segment->data + offset, copy);
 		}
+		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, copy);
 
+		r = sock_sendmsg(sk, &msg);
 		if (r < 0) {
 			iscsi_tcp_segment_unmap(segment);
 			return r;
@@ -746,7 +743,6 @@ iscsi_sw_tcp_conn_bind(struct iscsi_cls_session *cls_session,
 	sock_no_linger(sk);
 
 	iscsi_sw_tcp_conn_set_callbacks(conn);
-	tcp_sw_conn->sendpage = tcp_sw_conn->sock->ops->sendpage;
 	/*
 	 * set receive state machine into initial state
 	 */
@@ -777,8 +773,6 @@ static int iscsi_sw_tcp_conn_set_param(struct iscsi_cls_conn *cls_conn,
 			return -ENOTCONN;
 		}
 		iscsi_set_param(cls_conn, param, buf, buflen);
-		tcp_sw_conn->sendpage = conn->datadgst_en ?
-			sock_no_sendpage : tcp_sw_conn->sock->ops->sendpage;
 		mutex_unlock(&tcp_sw_conn->sock_lock);
 		break;
 	case ISCSI_PARAM_MAX_R2T:
diff --git a/drivers/scsi/iscsi_tcp.h b/drivers/scsi/iscsi_tcp.h
index 68e14a344904..d6ec08d7eb63 100644
--- a/drivers/scsi/iscsi_tcp.h
+++ b/drivers/scsi/iscsi_tcp.h
@@ -48,7 +48,7 @@ struct iscsi_sw_tcp_conn {
 	uint32_t		sendpage_failures_cnt;
 	uint32_t		discontiguous_hdr_cnt;
 
-	ssize_t (*sendpage)(struct socket *, struct page *, int, size_t, int);
+	bool			can_splice_to_tcp;
 };
 
 struct iscsi_sw_tcp_host {
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index b14835fcb033..8bab1898f1d0 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -1129,6 +1129,8 @@ int iscsit_fe_sendpage_sg(
 	struct iscsit_conn *conn)
 {
 	struct scatterlist *sg = cmd->first_data_sg;
+	struct bio_vec bvec;
+	struct msghdr msghdr = { .msg_flags = MSG_SPLICE_PAGES,	};
 	struct kvec iov;
 	u32 tx_hdr_size, data_len;
 	u32 offset = cmd->first_data_sg_off;
@@ -1172,17 +1174,17 @@ int iscsit_fe_sendpage_sg(
 		u32 space = (sg->length - offset);
 		u32 sub_len = min_t(u32, data_len, space);
 send_pg:
-		tx_sent = conn->sock->ops->sendpage(conn->sock,
-					sg_page(sg), sg->offset + offset, sub_len, 0);
+		bvec_set_page(&bvec, sg_page(sg), sub_len, sg->offset + offset);
+		iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, sub_len);
+
+		tx_sent = conn->sock->ops->sendmsg(conn->sock, &msghdr, sub_len);
 		if (tx_sent != sub_len) {
 			if (tx_sent == -EAGAIN) {
-				pr_err("tcp_sendpage() returned"
-						" -EAGAIN\n");
+				pr_err("sendmsg/splice returned -EAGAIN\n");
 				goto send_pg;
 			}
 
-			pr_err("tcp_sendpage() failure: %d\n",
-					tx_sent);
+			pr_err("sendmsg/splice failure: %d\n", tx_sent);
 			return -1;
 		}
 

[PATCH net-next 17/17] net: Kill MSG_SENDPAGE_NOTLAST

[David Howells]

---
 include/linux/socket.h                         | 4 +---
 net/ipv4/tcp_bpf.c                             | 4 +++-
 net/tls/tls_device.c                           | 3 +--
 net/tls/tls_main.c                             | 2 +-
 net/tls/tls_sw.c                               | 2 +-
 tools/perf/trace/beauty/include/linux/socket.h | 1 -
 tools/perf/trace/beauty/msg_flags.c            | 3 ---
 7 files changed, 7 insertions(+), 12 deletions(-)

diff --git a/include/linux/socket.h b/include/linux/socket.h
index 58204700018a..39b74d83c7c4 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -319,7 +319,6 @@ struct ucred {
 #define MSG_MORE	0x8000	/* Sender will send more */
 #define MSG_WAITFORONE	0x10000	/* recvmmsg(): block until 1+ packets avail */
 #define MSG_SENDPAGE_NOPOLICY 0x10000 /* sendpage() internal : do no apply policy */
-#define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */
 #define MSG_BATCH	0x40000 /* sendmmsg(): more messages coming */
 #define MSG_EOF         MSG_FIN
 #define MSG_NO_SHARED_FRAGS 0x80000 /* sendpage() internal : page frags are not shared */
@@ -341,8 +340,7 @@ struct ucred {
 
 /* Flags to be cleared on entry by sendmsg and sendmmsg syscalls */
 #define MSG_INTERNAL_SENDMSG_FLAGS \
-	(MSG_SPLICE_PAGES | MSG_SENDPAGE_NOPOLICY | MSG_SENDPAGE_NOTLAST | \
-	 MSG_SENDPAGE_DECRYPTED)
+	(MSG_SPLICE_PAGES | MSG_SENDPAGE_NOPOLICY | MSG_SENDPAGE_DECRYPTED)
 
 /* Setsockoptions(2) level. Thanks to BSD these must match IPPROTO_xxx */
 #define SOL_IP		0
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 870c1cde4010..8f535e436ea3 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -90,7 +90,9 @@ static int tcp_bpf_push(struct sock *sk, struct sk_msg *msg, u32 apply_bytes,
 {
 	bool apply = apply_bytes;
 	struct scatterlist *sge;
-	struct msghdr msghdr = { .msg_flags = flags | MSG_SPLICE_PAGES, };
+	struct msghdr msghdr = {
+		.msg_flags = flags | MSG_SPLICE_PAGES | MSG_MORE,
+	};
 	struct page *page;
 	int size, ret = 0;
 	u32 off;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 840ee06f1708..2021fe557e50 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -441,8 +441,7 @@ static int tls_push_data(struct sock *sk,
 	long timeo;
 
 	if (flags &
-	    ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST |
-	      MSG_SPLICE_PAGES))
+	    ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SPLICE_PAGES))
 		return -EOPNOTSUPP;
 
 	if (unlikely(sk->sk_err))
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index d5ed4d47b16e..b6896126bb92 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -127,7 +127,7 @@ int tls_push_sg(struct sock *sk,
 {
 	struct bio_vec bvec;
 	struct msghdr msg = {
-		.msg_flags = MSG_SENDPAGE_NOTLAST | MSG_SPLICE_PAGES | flags,
+		.msg_flags = MSG_SPLICE_PAGES | flags,
 	};
 	int ret = 0;
 	struct page *p;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 9b3aa89a4292..53f944e6d8ef 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1194,7 +1194,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
 			       MSG_CMSG_COMPAT | MSG_SPLICE_PAGES |
-			       MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
+			       MSG_SENDPAGE_NOPOLICY))
 		return -EOPNOTSUPP;
 
 	ret = mutex_lock_interruptible(&tls_ctx->tx_lock);
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index 13c3a237b9c9..3bef212a24d7 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -318,7 +318,6 @@ struct ucred {
 #define MSG_MORE	0x8000	/* Sender will send more */
 #define MSG_WAITFORONE	0x10000	/* recvmmsg(): block until 1+ packets avail */
 #define MSG_SENDPAGE_NOPOLICY 0x10000 /* sendpage() internal : do no apply policy */
-#define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */
 #define MSG_BATCH	0x40000 /* sendmmsg(): more messages coming */
 #define MSG_EOF         MSG_FIN
 #define MSG_NO_SHARED_FRAGS 0x80000 /* sendpage() internal : page frags are not shared */
diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c
index ea68db08b8e7..b5b580e5a77e 100644
--- a/tools/perf/trace/beauty/msg_flags.c
+++ b/tools/perf/trace/beauty/msg_flags.c
@@ -8,9 +8,6 @@
 #ifndef MSG_WAITFORONE
 #define MSG_WAITFORONE		   0x10000
 #endif
-#ifndef MSG_SENDPAGE_NOTLAST
-#define MSG_SENDPAGE_NOTLAST	   0x20000
-#endif
 #ifndef MSG_FASTOPEN
 #define MSG_FASTOPEN		0x20000000
 #endif