From 296f7ea75b45913d5e2067baef0812087e0b6eb9 Mon Sep 17 00:00:00 2001 From: Satoru Moriya Date: Fri, 17 Jun 2011 11:58:39 +0000 Subject: udp: add tracepoints for queueing skb to rcvbuf This patch adds a tracepoint to __udp_queue_rcv_skb to get the return value of ip_queue_rcv_skb. It indicates why kernel drops a packet at this point. ip_queue_rcv_skb returns following values in the packet drop case: rcvbuf is full : -ENOMEM sk_filter returns error : -EINVAL, -EACCESS, -ENOMEM, etc. __sk_mem_schedule returns error: -ENOBUF Signed-off-by: Satoru Moriya Acked-by: Neil Horman Signed-off-by: David S. Miller --- net/ipv4/udp.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv4/udp.c') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index abca870d8ff..37aa9bf8d38 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -105,6 +105,7 @@ #include #include #include +#include #include "udp_impl.h" struct udp_table udp_table __read_mostly; @@ -1363,6 +1364,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) is_udplite); UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); + trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } -- cgit v1.2.3-70-g09d2 From 9cfaa8def1c795a512bc04f2aec333b03724ca2e Mon Sep 17 00:00:00 2001 From: Xufeng Zhang Date: Tue, 21 Jun 2011 10:43:40 +0000 Subject: udp/recvmsg: Clear MSG_TRUNC flag when starting over for a new packet Consider this scenario: When the size of the first received udp packet is bigger than the receive buffer, MSG_TRUNC bit is set in msg->msg_flags. However, if checksum error happens and this is a blocking socket, it will goto try_again loop to receive the next packet. But if the size of the next udp packet is smaller than receive buffer, MSG_TRUNC flag should not be set, but because MSG_TRUNC bit is not cleared in msg->msg_flags before receive the next packet, MSG_TRUNC is still set, which is wrong. Fix this problem by clearing MSG_TRUNC flag when starting over for a new packet. Signed-off-by: Xufeng Zhang Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- net/ipv4/udp.c | 3 +++ net/ipv6/udp.c | 3 +++ 2 files changed, 6 insertions(+) (limited to 'net/ipv4/udp.c') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index abca870d8ff..48cd88e6255 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1249,6 +1249,9 @@ csum_copy_err: if (noblock) return -EAGAIN; + + /* starting over for a new packet */ + msg->msg_flags &= ~MSG_TRUNC; goto try_again; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1e7a43f500a..328985c4088 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -455,6 +455,9 @@ csum_copy_err: if (noblock) return -EAGAIN; + + /* starting over for a new packet */ + msg->msg_flags &= ~MSG_TRUNC; goto try_again; } -- cgit v1.2.3-70-g09d2 From f03d78db65085609938fdb686238867e65003181 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Jul 2011 00:27:05 -0700 Subject: net: refine {udp|tcp|sctp}_mem limits Current tcp/udp/sctp global memory limits are not taking into account hugepages allocations, and allow 50% of ram to be used by buffers of a single protocol [ not counting space used by sockets / inodes ...] Lets use nr_free_buffer_pages() and allow a default of 1/8 of kernel ram per protocol, and a minimum of 128 pages. Heavy duty machines sysadmins probably need to tweak limits anyway. References: https://bugzilla.stlinux.com/show_bug.cgi?id=38032 Reported-by: starlight Suggested-by: Andrew Morton Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 10 ++-------- net/ipv4/udp.c | 10 ++-------- net/sctp/protocol.c | 11 +---------- 3 files changed, 5 insertions(+), 26 deletions(-) (limited to 'net/ipv4/udp.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 054a59d21eb..46febcacb72 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3220,7 +3220,7 @@ __setup("thash_entries=", set_thash_entries); void __init tcp_init(void) { struct sk_buff *skb = NULL; - unsigned long nr_pages, limit; + unsigned long limit; int i, max_share, cnt; unsigned long jiffy = jiffies; @@ -3277,13 +3277,7 @@ void __init tcp_init(void) sysctl_tcp_max_orphans = cnt / 2; sysctl_max_syn_backlog = max(128, cnt / 256); - /* Set the pressure threshold to be a fraction of global memory that - * is up to 1/2 at 256 MB, decreasing toward zero with the amount of - * memory, with a floor of 128 pages. - */ - nr_pages = totalram_pages - totalhigh_pages; - limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_tcp_mem[0] = limit / 4 * 3; sysctl_tcp_mem[1] = limit; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 48cd88e6255..198f75b7bdd 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2209,16 +2209,10 @@ void __init udp_table_init(struct udp_table *table, const char *name) void __init udp_init(void) { - unsigned long nr_pages, limit; + unsigned long limit; udp_table_init(&udp_table, "UDP"); - /* Set the pressure threshold up by the same strategy of TCP. It is a - * fraction of global memory that is up to 1/2 at 256 MB, decreasing - * toward zero with the amount of memory, with a floor of 128 pages. - */ - nr_pages = totalram_pages - totalhigh_pages; - limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_udp_mem[0] = limit / 4 * 3; sysctl_udp_mem[1] = limit; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 67380a29e2e..207175b2f40 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1058,7 +1058,6 @@ SCTP_STATIC __init int sctp_init(void) int status = -EINVAL; unsigned long goal; unsigned long limit; - unsigned long nr_pages; int max_share; int order; @@ -1148,15 +1147,7 @@ SCTP_STATIC __init int sctp_init(void) /* Initialize handle used for association ids. */ idr_init(&sctp_assocs_id); - /* Set the pressure threshold to be a fraction of global memory that - * is up to 1/2 at 256 MB, decreasing toward zero with the amount of - * memory, with a floor of 128 pages. - * Note this initializes the data in sctpv6_prot too - * Unabashedly stolen from tcp_init - */ - nr_pages = totalram_pages - totalhigh_pages; - limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_sctp_mem[0] = limit / 4 * 3; sysctl_sctp_mem[1] = limit; -- cgit v1.2.3-70-g09d2