All of lore.kernel.org
 help / color / mirror / Atom feed
From: Kuniyuki Iwashima <kuniyu@google.com>
To: Eric Dumazet <edumazet@kernel.org>,
	Neal Cardwell <ncardwell@google.com>,
	 "David S . Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	 Matthieu Baerts <matttbe@kernel.org>,
	Mat Martineau <martineau@kernel.org>
Cc: Simon Horman <horms@kernel.org>,
	Kuniyuki Iwashima <kuniyu@google.com>,
	 Kuniyuki Iwashima <kuni1840@gmail.com>,
	netdev@vger.kernel.org, mptcp@lists.linux.dev
Subject: [PATCH v3 net-next 4/7] tcp: Skip collapsing if collapsed skb is less-dense.
Date: Thu, 19 Nov 2026 07:15:56 +0000	[thread overview]
Message-ID: <20261119071649.374106-5-kuniyu@google.com> (raw)
In-Reply-To: <20261119071649.374106-1-kuniyu@google.com>

Once tcp_collapse() finds a collapsible skb, it collapses
consecutive bloated skbs.

However, the end result could be the same or larger than
as is in some cases:

  1. skb is already minimum

     If SKB_HEAD_ALIGN(len) <= SKB_SMALL_HEAD_CACHE_SIZE,
     skb is allocated from skbuff_small_head, and skb->truesize
     never changes.

  2. SKB_HEAD_ALIGN() and kmalloc_size_roundup() in alloc_skb()

     Assume two bloated skbs with len = 1448 B (truesize =
     2304 B, scaling_ratio = 160) and len = 300 B (truesize =
     896 B, scaling_ratio = 85), whose total truesize is
     3200 B.

     Collapsing them calls alloc_skb(1748), which rounds up
     SKB_HEAD_ALIGN(1748) = 2112 B to 4096 B and allocates a
     new skb with truesize = 4352 B (+1152 B!).

Even worse, in case 1, such a skb is reallocated repeatedly
by every tcp_collapse() in vain.

Let's calculate the final collapsed truesize before collapsing
skbs and skip the range if it does not shrink.

We could allocate skbs first and calculate the new truesize,
but given tcp_collapse() is called under memory pressure,
we want to avoid unnecessary allocation.

Note that kmalloc_reserve_size() uses __always_inline so that
this change does not affect non-FDO builds, and returns 0 when
skb_small_head_cache is used, similar to kmalloc_pfmemalloc().

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
v3:
  * Remove redundant kmalloc_size_roundup()
  * Rename helper with skb_ prefix
  * Declare {old,new}_truesize as unsigned int

v2: Add compute_skb_truesize() instead of macro
---
 include/linux/skbuff.h |  2 ++
 net/core/skbuff.c      | 27 +++++++++++++++++++++++----
 net/ipv4/tcp_input.c   | 15 +++++++++++++++
 3 files changed, 40 insertions(+), 4 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 1d6832878930..3fa8f140c58e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -274,6 +274,8 @@
 			 SKB_DATA_ALIGN(sizeof(struct sk_buff)) +	\
 			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 
+unsigned int skb_head_truesize(unsigned int size, gfp_t flags);
+
 struct net_device;
 struct scatterlist;
 struct pipe_inode_info;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2e81aacc998b..8616ce0785d0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -589,6 +589,17 @@ struct sk_buff *napi_build_skb(void *data, unsigned int frag_size)
 }
 EXPORT_SYMBOL(napi_build_skb);
 
+static __always_inline size_t kmalloc_reserve_size(unsigned int size, gfp_t flags)
+{
+	size_t obj_size = SKB_HEAD_ALIGN(size);
+
+	if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE &&
+	    !(flags & KMALLOC_NOT_NORMAL_BITS))
+		return 0;
+
+	return kmalloc_size_roundup(obj_size);
+}
+
 static void *kmalloc_pfmemalloc(size_t obj_size, gfp_t flags, int node)
 {
 	if (!gfp_pfmemalloc_allowed(flags))
@@ -612,9 +623,8 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
 	size_t obj_size;
 	void *obj;
 
-	obj_size = SKB_HEAD_ALIGN(*size);
-	if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE &&
-	    !(flags & KMALLOC_NOT_NORMAL_BITS)) {
+	obj_size = kmalloc_reserve_size(*size, flags);
+	if (!obj_size) {
 		obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache,
 				flags | __GFP_NOMEMALLOC | __GFP_NOWARN,
 				node);
@@ -627,7 +637,6 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
 		return kmalloc_pfmemalloc(0, flags, node);
 	}
 
-	obj_size = kmalloc_size_roundup(obj_size);
 	/* The following cast might truncate high-order bits of obj_size, this
 	 * is harmless because kmalloc(obj_size >= 2^32) will fail anyway.
 	 */
@@ -651,6 +660,16 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
 	return obj;
 }
 
+unsigned int skb_head_truesize(unsigned int size, gfp_t flags)
+{
+	size_t obj_size = kmalloc_reserve_size(size, flags);
+
+	if (!obj_size)
+		obj_size = SKB_SMALL_HEAD_CACHE_SIZE;
+
+	return obj_size + SKB_DATA_ALIGN(sizeof(struct sk_buff));
+}
+
 /* 	Allocate a new skbuff. We do this ourselves so we can fill in a few
  *	'private' fields and also do memory statistics to find all the
  *	[BEEP] leaks.
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5df60dd35afe..27ed9ba11ec9 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5860,8 +5860,10 @@ static void
 tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
 	     struct sk_buff *head, struct sk_buff *tail, u32 start)
 {
+	unsigned int old_truesize, new_truesize;
 	struct sk_buff *skb = head, *n;
 	struct sk_buff_head tmp;
+	int remainder, nskbs;
 	u8 scaling_ratio;
 	u32 sub_end;
 
@@ -5901,6 +5903,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
 
 	/* Second, find consecutive collapsible skb. */
 	sub_end = TCP_SKB_CB(skb)->end_seq;
+	old_truesize = skb->truesize;
 	n = tcp_skb_next(skb, list);
 
 	while (n && n != tail) {
@@ -5928,9 +5931,21 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
 			break;
 
 		sub_end = TCP_SKB_CB(n)->end_seq;
+		old_truesize += n->truesize;
 		n = tcp_skb_next(n, list);
 	}
 
+	/* Third, check if the new skbs have high density. */
+	nskbs = (sub_end - start) / TCP_COLLAPSE_MAX_SIZE;
+	new_truesize = nskbs * SKB_TRUESIZE(TCP_COLLAPSE_MAX_SIZE);
+
+	remainder = (sub_end - start) % TCP_COLLAPSE_MAX_SIZE;
+	if (remainder)
+		new_truesize += skb_head_truesize(remainder, GFP_ATOMIC);
+
+	if (old_truesize <= new_truesize)
+		goto skip;
+
 	while (before(start, sub_end)) {
 		int copy = min_t(int, TCP_COLLAPSE_MAX_SIZE, sub_end - start);
 		struct sk_buff *nskb;
-- 
2.56.1.708.g77570a6a1d-goog


  parent reply	other threads:[~2026-11-19  7:16 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-19  7:15 [PATCH v3 net-next 0/7] tcp: Prevent tcp_collapse() from bloating queue Kuniyuki Iwashima
2026-11-19  7:15 ` [PATCH v3 net-next 1/7] tcp: Refactor the first loop in tcp_collapse() Kuniyuki Iwashima
2026-11-19  7:15 ` [PATCH v3 net-next 2/7] tcp: Don't collapse high density skb Kuniyuki Iwashima
2026-11-19  7:15 ` [PATCH v3 net-next 3/7] tcp: Stop collapsing if not bloated Kuniyuki Iwashima
2026-11-19  7:39   ` Eric Dumazet
2026-11-20 14:58   ` Matthieu Baerts
2026-11-19  7:15 ` Kuniyuki Iwashima [this message]
2026-11-19  7:41   ` [PATCH v3 net-next 4/7] tcp: Skip collapsing if collapsed skb is less-dense Eric Dumazet
2026-11-19  7:15 ` [PATCH v3 net-next 5/7] tcp: Allocate all new skb before collapsing Kuniyuki Iwashima
2026-11-19  7:44   ` Eric Dumazet
2026-11-19 20:02     ` Kuniyuki Iwashima
2026-11-19  7:15 ` [PATCH v3 net-next 6/7] tcp: Batch memory accounting in tcp_collapse() Kuniyuki Iwashima
2026-11-19  7:15 ` [PATCH v3 net-next 7/7] selftest: packetdrill: Add test for tcp_collapse() Kuniyuki Iwashima
2026-11-19  7:45   ` Eric Dumazet

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261119071649.374106-5-kuniyu@google.com \
    --to=kuniyu@google.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@kernel.org \
    --cc=horms@kernel.org \
    --cc=kuba@kernel.org \
    --cc=kuni1840@gmail.com \
    --cc=martineau@kernel.org \
    --cc=matttbe@kernel.org \
    --cc=mptcp@lists.linux.dev \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.