From: Chia-Yu Chang <[email protected]>
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]; /* 2521 0 */
/* XXX 3 bytes hole, try to pack */
[...]
struct tcp_options_received rx_opt; /* 2588 24 */
u8 nonagle:4; /* 2612: 0 1 */
u8 rate_app_limited:1; /* 2612: 4 1 */
/* XXX 3 bits hole, try to pack */
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2613 0 */
/* XXX 3 bytes hole, try to pack */
__cacheline_group_begin__tcp_sock_write_rx[0]
__attribute__((__aligned__(8))); /* 2616 0 */
[...]
__cacheline_group_end__tcp_sock_write_rx[0]; /* 2712 0 */
[...]
/* size: 3200, cachelines: 50, members: 161 */
}
[AFTER THIS PATCH]
struct tcp_sock {
[...]
__cacheline_group_begin__tcp_sock_write_txrx[0]; /* 2521 0 */
u8 nonagle:4; /* 2521: 0 1 */
u8 rate_app_limited:1; /* 2521: 4 1 */
/* XXX 3 bits hole, try to pack */
/* XXX 2 bytes hole, try to pack */
[...]
struct tcp_options_received rx_opt; /* 2588 24 */
__cacheline_group_end__tcp_sock_write_txrx[0]; /* 2612 0 */
/* XXX 4 bytes hole, try to pack */
__cacheline_group_begin__tcp_sock_write_rx[0]
__attribute__((__aligned__(8))); /* 2616 0 */
[...]
__cacheline_group_end__tcp_sock_write_rx[0]; /* 2712 0 */
[...]
/* size: 3200, cachelines: 50, members: 161 */
}
Signed-off-by: Chia-Yu Chang <[email protected]>
Reviewed-by: Eric Dumazet <[email protected]>
---
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 57e478bfaef2..d103cc0e7a35 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -285,6 +285,8 @@ 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 */
@@ -303,8 +305,6 @@ 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 588932c3cf1d..897cd28d2d8c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -5129,7 +5129,7 @@ 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);
@@ -5146,7 +5146,7 @@ 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
