netdev - [PATCH v7 net-next 03/15] tcp: reorganize tcp_sock_write

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20250514135642.11203-4-chia-yu.chang@nokia-bell-labs.com>
Date: Wed, 14 May 2025 15:56:30 +0200
From: chia-yu.chang@...ia-bell-labs.com
To: linux-doc@...r.kernel.org,
	corbet@....net,
	horms@...nel.org,
	dsahern@...nel.org,
	kuniyu@...zon.com,
	bpf@...r.kernel.org,
	netdev@...r.kernel.org,
	dave.taht@...il.com,
	pabeni@...hat.com,
	jhs@...atatu.com,
	kuba@...nel.org,
	stephen@...workplumber.org,
	xiyou.wangcong@...il.com,
	jiri@...nulli.us,
	davem@...emloft.net,
	edumazet@...gle.com,
	andrew+netdev@...n.ch,
	donald.hunter@...il.com,
	ast@...erby.net,
	liuhangbin@...il.com,
	shuah@...nel.org,
	linux-kselftest@...r.kernel.org,
	ij@...nel.org,
	ncardwell@...gle.com,
	koen.de_schepper@...ia-bell-labs.com,
	g.white@...lelabs.com,
	ingemar.s.johansson@...csson.com,
	mirja.kuehlewind@...csson.com,
	cheshire@...le.com,
	rs.ietf@....at,
	Jason_Livingood@...cast.com,
	vidhi_goel@...le.com
Cc: Chia-Yu Chang <chia-yu.chang@...ia-bell-labs.com>
Subject: [PATCH v7 net-next 03/15] tcp: reorganize tcp_sock_write_txrx group for variables later

From: Chia-Yu Chang <chia-yu.chang@...ia-bell-labs.com>

Use the first 3-byte hole at the beginning of the tcp_sock_write_txrx
group for 'noneagle'/'rate_app_limited' to fill in the existing hole
in later patches. Therefore, the group size of tcp_sock_write_txrx is
reduced from 92 + 4 to 91 + 4. In addition, the group size of
tcp_sock_write_rx is changed to 96 to fit in the pahole outcome.
Below are the trimmed pahole outcomes before and after this patch:

[BEFORE THIS PATCH]
struct tcp_sock {
    [...]
    __cacheline_group_begin__tcp_sock_write_txrx[0]; /*  2585     0 */
    /* XXX 3 bytes hole, try to pack */

    [...]
    struct tcp_options_received rx_opt;              /*  2652    24 */
    u8                         nonagle:4;            /*  2676: 0  1 */
    u8                         rate_app_limited:1;   /*  2676: 4  1 */
    /* XXX 3 bits hole, try to pack */

    __cacheline_group_end__tcp_sock_write_txrx[0];   /*  2677     0 */
    /* XXX 3 bytes hole, try to pack */

    __cacheline_group_begin__tcp_sock_write_rx[0] __attribute__((__aligned__(8))); /*  2680     0 */

    [...]
    __cacheline_group_end__tcp_sock_write_rx[0];     /*  2776     0 */

    [...]
    /* size: 3264, cachelines: 51, members: 163 */
}

[AFTER THIS PATCH]
struct tcp_sock {
    [...]
    __cacheline_group_begin__tcp_sock_write_txrx[0]; /*  2585     0 */
    u8                         nonagle:4;            /*  2585: 0  1 */
    u8                         rate_app_limited:1;   /*  2585: 4  1 */
    /* XXX 3 bits hole, try to pack */
    /* XXX 2 bytes hole, try to pack */

    [...]
    struct tcp_options_received rx_opt;              /*  2652    24 */

    __cacheline_group_end__tcp_sock_write_txrx[0];   /*  2676     0 */
    /* XXX 4 bytes hole, try to pack */

    __cacheline_group_begin__tcp_sock_write_rx[0] __attribute__((__aligned__(8))); /*  2680     0 */

    [...]
    __cacheline_group_end__tcp_sock_write_rx[0];     /*  2776     0 */

    [...]
    /* size: 3264, cachelines: 51, members: 163 */
}

Signed-off-by: Chia-Yu Chang <chia-yu.chang@...ia-bell-labs.com>
---
 include/linux/tcp.h | 4 ++--
 net/ipv4/tcp.c      | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index a8af71623ba7..0c82a8c942dc 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -286,6 +286,8 @@ struct tcp_sock {
  *	Header prediction flags
  *	0x5?10 << 16 + snd_wnd in net byte order
  */
+	u8	nonagle     : 4,/* Disable Nagle algorithm?             */
+		rate_app_limited:1;  /* rate_{delivered,interval_us} limited? */
 	__be32	pred_flags;
 	u64	tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
 	u64	tcp_mstamp;	/* most recent packet received/sent */
@@ -304,8 +306,6 @@ struct tcp_sock {
  *      Options received (usually on last packet, some only on SYN packets).
  */
 	struct tcp_options_received rx_opt;
-	u8	nonagle     : 4,/* Disable Nagle algorithm?             */
-		rate_app_limited:1;  /* rate_{delivered,interval_us} limited? */
 	__cacheline_group_end(tcp_sock_write_txrx);
 
 	/* RX read-write hotpath cache lines */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0ae265d39184..bc9ab715fc2b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -5130,7 +5130,7 @@ static void __init tcp_struct_check(void)
 	/* 32bit arches with 8byte alignment on u64 fields might need padding
 	 * before tcp_clock_cache.
 	 */
-	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 92 + 4);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 91 + 4);
 
 	/* RX read-write hotpath cache lines */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received);
@@ -5147,7 +5147,7 @@ static void __init tcp_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_est);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcvq_space);
-	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 99);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 96);
 }
 
 void __init tcp_init(void)
-- 
2.34.1