net: avoid double accounting for pure zerocopy skbs

Track skbs containing only zerocopy data and avoid charging them to
kernel memory to correctly account the memory utilization for
msg_zerocopy. All of the data in such skbs is held in user pages which
are already accounted to user. Before this change, they are charged
again in kernel in __zerocopy_sg_from_iter. The charging in kernel is
excessive because data is not being copied into skb frags. This
excessive charging can lead to kernel going into memory pressure
state which impacts all sockets in the system adversely. Mark pure
zerocopy skbs with a SKBFL_PURE_ZEROCOPY flag and remove
charge/uncharge for data in such skbs.

Initially, an skb is marked pure zerocopy when it is empty and in
zerocopy path. skb can then change from a pure zerocopy skb to mixed
data skb (zerocopy and copy data) if it is at tail of write queue and
there is room available in it and non-zerocopy data is being sent in
the next sendmsg call. At this time sk_mem_charge is done for the pure
zerocopied data and the pure zerocopy flag is unmarked. We found that
this happens very rarely on workloads that pass MSG_ZEROCOPY.

A pure zerocopy skb can later be coalesced into normal skb if they are
next to each other in queue but this patch prevents coalescing from
happening. This avoids complexity of charging when skb downgrades from
pure zerocopy to mixed. This is also rare.

In sk_wmem_free_skb, if it is a pure zerocopy skb, an sk_mem_uncharge
for SKB_TRUESIZE(skb_end_offset(skb)) is done for sk_mem_charge in
tcp_skb_entail for an skb without data.

Testing with the msg_zerocopy.c benchmark between two hosts(100G nics)
with zerocopy showed that before this patch the 'sock' variable in
memory.stat for cgroup2 that tracks sum of sk_forward_alloc,
sk_rmem_alloc and sk_wmem_queued is around 1822720 and with this
change it is 0. This is due to no charge to sk_forward_alloc for
zerocopy data and shows memory utilization for kernel is lowered.

With this commit we don't see the warning we saw in previous commit
which resulted in commit 84882cf72cd774cf16fd338bdbf00f69ac9f9194.

Signed-off-by: Talal Ahmad <talalahmad@google.com>
Acked-by: Arjun Roy <arjunroy@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 29 insertions, 6 deletions

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 15ab9ffb27fe..ee290776c661 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -646,7 +646,8 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
 		skb->truesize += truesize;
 		if (sk && sk->sk_type == SOCK_STREAM) {
 			sk_wmem_queued_add(sk, truesize);
-			sk_mem_charge(sk, truesize);
+			if (!skb_zcopy_pure(skb))
+				sk_mem_charge(sk, truesize);
 		} else {
 			refcount_add(truesize, &skb->sk->sk_wmem_alloc);
 		}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3ec42cdee16a..ba2f38246f07 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3433,8 +3433,9 @@ static inline void skb_split_no_header(struct sk_buff *skb,
 void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len)
 {
 	int pos = skb_headlen(skb);
+	const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY;
 
-	skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG;
+	skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags;
 	skb_zerocopy_clone(skb1, skb, 0);
 	if (len < pos)	/* Split line is inside header. */
 		skb_split_inside_header(skb, skb1, len, pos);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bc7f419184aa..b461ae573afc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -863,6 +863,7 @@ struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
 	if (likely(skb)) {
 		bool mem_scheduled;
 
+		skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
 		if (force_schedule) {
 			mem_scheduled = true;
 			sk_forced_mem_schedule(sk, skb->truesize);
@@ -1319,6 +1320,15 @@ new_segment:
 
 			copy = min_t(int, copy, pfrag->size - pfrag->offset);
 
+			/* skb changing from pure zc to mixed, must charge zc */
+			if (unlikely(skb_zcopy_pure(skb))) {
+				if (!sk_wmem_schedule(sk, skb->data_len))
+					goto wait_for_space;
+
+				sk_mem_charge(sk, skb->data_len);
+				skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY;
+			}
+
 			if (!sk_wmem_schedule(sk, copy))
 				goto wait_for_space;
 
@@ -1339,8 +1349,16 @@ new_segment:
 			}
 			pfrag->offset += copy;
 		} else {
-			if (!sk_wmem_schedule(sk, copy))
-				goto wait_for_space;
+			/* First append to a fragless skb builds initial
+			 * pure zerocopy skb
+			 */
+			if (!skb->len)
+				skb_shinfo(skb)->flags |= SKBFL_PURE_ZEROCOPY;
+
+			if (!skb_zcopy_pure(skb)) {
+				if (!sk_wmem_schedule(sk, copy))
+					goto wait_for_space;
+			}
 
 			err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg);
 			if (err == -EMSGSIZE || err == -EEXIST) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 76cc1641beb4..6f7860e283c6 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1677,7 +1677,8 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 	if (delta_truesize) {
 		skb->truesize	   -= delta_truesize;
 		sk_wmem_queued_add(sk, -delta_truesize);
-		sk_mem_uncharge(sk, delta_truesize);
+		if (!skb_zcopy_pure(skb))
+			sk_mem_uncharge(sk, delta_truesize);
 	}
 
 	/* Any change of skb->len requires recalculation of tso factor. */
@@ -2295,7 +2296,9 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
 		if (len <= skb->len)
 			break;
 
-		if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb))
+		if (unlikely(TCP_SKB_CB(skb)->eor) ||
+		    tcp_has_tx_tstamp(skb) ||
+		    !skb_pure_zcopy_same(skb, next))
 			return false;
 
 		len -= skb->len;