From f4b41f062c424209e3939a81e6da022e049a45f2 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 4 Apr 2022 18:30:22 +0200 Subject: net: remove noblock parameter from skb_recv_datagram() skb_recv_datagram() has two parameters 'flags' and 'noblock' that are merged inside skb_recv_datagram() by 'flags | (noblock ? MSG_DONTWAIT : 0)' As 'flags' may contain MSG_DONTWAIT as value most callers split the 'flags' into 'flags' and 'noblock' with finally obsolete bit operations like this: skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &rc); And this is not even done consistently with the 'flags' parameter. This patch removes the obsolete and costly splitting into two parameters and only performs bit operations when really needed on the caller side. One missing conversion thankfully reported by kernel test robot. I missed to enable kunit tests to build the mctp code. Reported-by: kernel test robot Signed-off-by: Oliver Hartkopp Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3a30cae8b0a5..2394441fa3dd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3836,8 +3836,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); -struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, - int *err); +struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, -- cgit v1.3-8-gc7d7 From 9f8ed577c28813410614b418bad42285840c1a00 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 7 Apr 2022 14:20:50 +0800 Subject: net: skb: rename SKB_DROP_REASON_PTYPE_ABSENT As David Ahern suggested, the reasons for skb drops should be more general and not be code based. Therefore, rename SKB_DROP_REASON_PTYPE_ABSENT to SKB_DROP_REASON_UNHANDLED_PROTO, which is used for the cases of no L3 protocol handler, no L4 protocol handler, version extensions, etc. From previous discussion, now we have the aim to make these reasons more abstract and users based, avoiding code based. Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 8 +++----- include/trace/events/skb.h | 2 +- net/core/dev.c | 8 +++----- 3 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2394441fa3dd..173bc35a10a3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -408,11 +408,9 @@ enum skb_drop_reason { */ SKB_DROP_REASON_XDP, /* dropped by XDP in input path */ SKB_DROP_REASON_TC_INGRESS, /* dropped in TC ingress HOOK */ - SKB_DROP_REASON_PTYPE_ABSENT, /* not packet_type found to handle - * the skb. For an etner packet, - * this means that L3 protocol is - * not supported - */ + SKB_DROP_REASON_UNHANDLED_PROTO, /* protocol not implemented + * or not supported + */ SKB_DROP_REASON_SKB_CSUM, /* sk_buff checksum computation * error */ diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index e1670e1e4934..85abd7cbd221 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -50,7 +50,7 @@ EM(SKB_DROP_REASON_CPU_BACKLOG, CPU_BACKLOG) \ EM(SKB_DROP_REASON_XDP, XDP) \ EM(SKB_DROP_REASON_TC_INGRESS, TC_INGRESS) \ - EM(SKB_DROP_REASON_PTYPE_ABSENT, PTYPE_ABSENT) \ + EM(SKB_DROP_REASON_UNHANDLED_PROTO, UNHANDLED_PROTO) \ EM(SKB_DROP_REASON_SKB_CSUM, SKB_CSUM) \ EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG) \ EM(SKB_DROP_REASON_SKB_UCOPY_FAULT, SKB_UCOPY_FAULT) \ diff --git a/net/core/dev.c b/net/core/dev.c index e027410e861b..ba853e878007 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5375,13 +5375,11 @@ check_vlan_id: *ppt_prev = pt_prev; } else { drop: - if (!deliver_exact) { + if (!deliver_exact) dev_core_stats_rx_dropped_inc(skb->dev); - kfree_skb_reason(skb, SKB_DROP_REASON_PTYPE_ABSENT); - } else { + else dev_core_stats_rx_nohandler_inc(skb->dev); - kfree_skb(skb); - } + kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) */ -- cgit v1.3-8-gc7d7 From b384c95a861eebf47e88695cf6a29f34e0b10b0f Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 7 Apr 2022 14:20:52 +0800 Subject: net: icmp: add skb drop reasons to icmp protocol Replace kfree_skb() used in icmp_rcv() and icmpv6_rcv() with kfree_skb_reason(). In order to get the reasons of the skb drops after icmp message handle, we change the return type of 'handler()' in 'struct icmp_control' from 'bool' to 'enum skb_drop_reason'. This may change its original intention, as 'false' means failure, but 'SKB_NOT_DROPPED_YET' means success now. Therefore, all 'handler' and the call of them need to be handled. Following 'handler' functions are involved: icmp_unreach() icmp_redirect() icmp_echo() icmp_timestamp() icmp_discard() And following new drop reasons are added: SKB_DROP_REASON_ICMP_CSUM SKB_DROP_REASON_INVALID_PROTO The reason 'INVALID_PROTO' is introduced for the case that the packet doesn't follow rfc 1122 and is dropped. This is not a common case, and I believe we can locate the problem from the data in the packet. For now, this 'INVALID_PROTO' is used for the icmp broadcasts with wrong types. Maybe there should be a document file for these reasons. For example, list all the case that causes the 'UNHANDLED_PROTO' and 'INVALID_PROTO' drop reason. Therefore, users can locate their problems according to the document. Reviewed-by: Hao Peng Reviewed-by: Jiang Biao Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 ++++ include/net/ping.h | 2 +- include/trace/events/skb.h | 2 ++ net/ipv4/icmp.c | 75 +++++++++++++++++++++++++++------------------- net/ipv4/ping.c | 14 +++++---- net/ipv6/icmp.c | 24 +++++++++------ 6 files changed, 75 insertions(+), 47 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 173bc35a10a3..9b81ba497665 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -442,6 +442,11 @@ enum skb_drop_reason { SKB_DROP_REASON_TAP_TXFILTER, /* dropped by tx filter implemented * at tun/tap, e.g., check_filter() */ + SKB_DROP_REASON_ICMP_CSUM, /* ICMP checksum error */ + SKB_DROP_REASON_INVALID_PROTO, /* the packet doesn't follow RFC + * 2211, such as a broadcasts + * ICMP_TIMESTAMP + */ SKB_DROP_REASON_MAX, }; diff --git a/include/net/ping.h b/include/net/ping.h index 2fe78874318c..b68fbfdb606f 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -76,7 +76,7 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, void *user_icmph, size_t icmph_len); int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); -bool ping_rcv(struct sk_buff *skb); +enum skb_drop_reason ping_rcv(struct sk_buff *skb); #ifdef CONFIG_PROC_FS void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family); diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 85abd7cbd221..42647114fffe 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -61,6 +61,8 @@ EM(SKB_DROP_REASON_HDR_TRUNC, HDR_TRUNC) \ EM(SKB_DROP_REASON_TAP_FILTER, TAP_FILTER) \ EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \ + EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM) \ + EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 72a375c7f417..236debd9fded 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -186,7 +186,7 @@ EXPORT_SYMBOL(icmp_err_convert); */ struct icmp_control { - bool (*handler)(struct sk_buff *skb); + enum skb_drop_reason (*handler)(struct sk_buff *skb); short error; /* This ICMP is classed as an error message */ }; @@ -839,8 +839,9 @@ static bool icmp_tag_validation(int proto) * ICMP_PARAMETERPROB. */ -static bool icmp_unreach(struct sk_buff *skb) +static enum skb_drop_reason icmp_unreach(struct sk_buff *skb) { + enum skb_drop_reason reason = SKB_NOT_DROPPED_YET; const struct iphdr *iph; struct icmphdr *icmph; struct net *net; @@ -860,8 +861,10 @@ static bool icmp_unreach(struct sk_buff *skb) icmph = icmp_hdr(skb); iph = (const struct iphdr *)skb->data; - if (iph->ihl < 5) /* Mangled header, drop. */ + if (iph->ihl < 5) { /* Mangled header, drop. */ + reason = SKB_DROP_REASON_IP_INHDR; goto out_err; + } switch (icmph->type) { case ICMP_DEST_UNREACH: @@ -941,10 +944,10 @@ static bool icmp_unreach(struct sk_buff *skb) icmp_socket_deliver(skb, info); out: - return true; + return reason; out_err: __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); - return false; + return reason ?: SKB_DROP_REASON_NOT_SPECIFIED; } @@ -952,20 +955,20 @@ out_err: * Handle ICMP_REDIRECT. */ -static bool icmp_redirect(struct sk_buff *skb) +static enum skb_drop_reason icmp_redirect(struct sk_buff *skb) { if (skb->len < sizeof(struct iphdr)) { __ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS); - return false; + return SKB_DROP_REASON_PKT_TOO_SMALL; } if (!pskb_may_pull(skb, sizeof(struct iphdr))) { /* there aught to be a stat */ - return false; + return SKB_DROP_REASON_NOMEM; } icmp_socket_deliver(skb, ntohl(icmp_hdr(skb)->un.gateway)); - return true; + return SKB_NOT_DROPPED_YET; } /* @@ -982,7 +985,7 @@ static bool icmp_redirect(struct sk_buff *skb) * See also WRT handling of options once they are done and working. */ -static bool icmp_echo(struct sk_buff *skb) +static enum skb_drop_reason icmp_echo(struct sk_buff *skb) { struct icmp_bxm icmp_param; struct net *net; @@ -990,7 +993,7 @@ static bool icmp_echo(struct sk_buff *skb) net = dev_net(skb_dst(skb)->dev); /* should there be an ICMP stat for ignored echos? */ if (net->ipv4.sysctl_icmp_echo_ignore_all) - return true; + return SKB_NOT_DROPPED_YET; icmp_param.data.icmph = *icmp_hdr(skb); icmp_param.skb = skb; @@ -1001,10 +1004,10 @@ static bool icmp_echo(struct sk_buff *skb) if (icmp_param.data.icmph.type == ICMP_ECHO) icmp_param.data.icmph.type = ICMP_ECHOREPLY; else if (!icmp_build_probe(skb, &icmp_param.data.icmph)) - return true; + return SKB_NOT_DROPPED_YET; icmp_reply(&icmp_param, skb); - return true; + return SKB_NOT_DROPPED_YET; } /* Helper for icmp_echo and icmpv6_echo_reply. @@ -1122,7 +1125,7 @@ EXPORT_SYMBOL_GPL(icmp_build_probe); * MUST be accurate to a few minutes. * MUST be updated at least at 15Hz. */ -static bool icmp_timestamp(struct sk_buff *skb) +static enum skb_drop_reason icmp_timestamp(struct sk_buff *skb) { struct icmp_bxm icmp_param; /* @@ -1147,17 +1150,17 @@ static bool icmp_timestamp(struct sk_buff *skb) icmp_param.data_len = 0; icmp_param.head_len = sizeof(struct icmphdr) + 12; icmp_reply(&icmp_param, skb); - return true; + return SKB_NOT_DROPPED_YET; out_err: __ICMP_INC_STATS(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS); - return false; + return SKB_DROP_REASON_PKT_TOO_SMALL; } -static bool icmp_discard(struct sk_buff *skb) +static enum skb_drop_reason icmp_discard(struct sk_buff *skb) { /* pretend it was a success */ - return true; + return SKB_NOT_DROPPED_YET; } /* @@ -1165,18 +1168,20 @@ static bool icmp_discard(struct sk_buff *skb) */ int icmp_rcv(struct sk_buff *skb) { - struct icmphdr *icmph; + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct rtable *rt = skb_rtable(skb); struct net *net = dev_net(rt->dst.dev); - bool success; + struct icmphdr *icmph; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { struct sec_path *sp = skb_sec_path(skb); int nh; if (!(sp && sp->xvec[sp->len - 1]->props.flags & - XFRM_STATE_ICMP)) + XFRM_STATE_ICMP)) { + reason = SKB_DROP_REASON_XFRM_POLICY; goto drop; + } if (!pskb_may_pull(skb, sizeof(*icmph) + sizeof(struct iphdr))) goto drop; @@ -1184,8 +1189,11 @@ int icmp_rcv(struct sk_buff *skb) nh = skb_network_offset(skb); skb_set_network_header(skb, sizeof(*icmph)); - if (!xfrm4_policy_check_reverse(NULL, XFRM_POLICY_IN, skb)) + if (!xfrm4_policy_check_reverse(NULL, XFRM_POLICY_IN, + skb)) { + reason = SKB_DROP_REASON_XFRM_POLICY; goto drop; + } skb_set_network_header(skb, nh); } @@ -1207,13 +1215,13 @@ int icmp_rcv(struct sk_buff *skb) /* We can't use icmp_pointers[].handler() because it is an array of * size NR_ICMP_TYPES + 1 (19 elements) and PROBE has code 42. */ - success = icmp_echo(skb); - goto success_check; + reason = icmp_echo(skb); + goto reason_check; } if (icmph->type == ICMP_EXT_ECHOREPLY) { - success = ping_rcv(skb); - goto success_check; + reason = ping_rcv(skb); + goto reason_check; } /* @@ -1222,8 +1230,10 @@ int icmp_rcv(struct sk_buff *skb) * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently * discarded. */ - if (icmph->type > NR_ICMP_TYPES) + if (icmph->type > NR_ICMP_TYPES) { + reason = SKB_DROP_REASON_UNHANDLED_PROTO; goto error; + } /* * Parse the ICMP message @@ -1239,27 +1249,30 @@ int icmp_rcv(struct sk_buff *skb) if ((icmph->type == ICMP_ECHO || icmph->type == ICMP_TIMESTAMP) && net->ipv4.sysctl_icmp_echo_ignore_broadcasts) { + reason = SKB_DROP_REASON_INVALID_PROTO; goto error; } if (icmph->type != ICMP_ECHO && icmph->type != ICMP_TIMESTAMP && icmph->type != ICMP_ADDRESS && icmph->type != ICMP_ADDRESSREPLY) { + reason = SKB_DROP_REASON_INVALID_PROTO; goto error; } } - success = icmp_pointers[icmph->type].handler(skb); -success_check: - if (success) { + reason = icmp_pointers[icmph->type].handler(skb); +reason_check: + if (!reason) { consume_skb(skb); return NET_RX_SUCCESS; } drop: - kfree_skb(skb); + kfree_skb_reason(skb, reason); return NET_RX_DROP; csum_error: + reason = SKB_DROP_REASON_ICMP_CSUM; __ICMP_INC_STATS(net, ICMP_MIB_CSUMERRORS); error: __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 9878c7696acf..2897fcf71211 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -961,12 +961,12 @@ EXPORT_SYMBOL_GPL(ping_queue_rcv_skb); * All we need to do is get the socket. */ -bool ping_rcv(struct sk_buff *skb) +enum skb_drop_reason ping_rcv(struct sk_buff *skb) { + enum skb_drop_reason reason = SKB_DROP_REASON_NO_SOCKET; struct sock *sk; struct net *net = dev_net(skb->dev); struct icmphdr *icmph = icmp_hdr(skb); - bool rc = false; /* We assume the packet has already been checked by icmp_rcv */ @@ -981,15 +981,17 @@ bool ping_rcv(struct sk_buff *skb) struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); pr_debug("rcv on socket %p\n", sk); - if (skb2 && !ping_queue_rcv_skb(sk, skb2)) - rc = true; + if (skb2) + reason = __ping_queue_rcv_skb(sk, skb2); + else + reason = SKB_DROP_REASON_NOMEM; sock_put(sk); } - if (!rc) + if (reason) pr_debug("no socket, dropping\n"); - return rc; + return reason; } EXPORT_SYMBOL_GPL(ping_rcv); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index e6b978ea0e87..01c8003c9fc9 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -864,21 +864,23 @@ out: static int icmpv6_rcv(struct sk_buff *skb) { + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct net *net = dev_net(skb->dev); struct net_device *dev = icmp6_dev(skb); struct inet6_dev *idev = __in6_dev_get(dev); const struct in6_addr *saddr, *daddr; struct icmp6hdr *hdr; u8 type; - bool success = false; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { struct sec_path *sp = skb_sec_path(skb); int nh; if (!(sp && sp->xvec[sp->len - 1]->props.flags & - XFRM_STATE_ICMP)) + XFRM_STATE_ICMP)) { + reason = SKB_DROP_REASON_XFRM_POLICY; goto drop_no_count; + } if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr))) goto drop_no_count; @@ -886,8 +888,11 @@ static int icmpv6_rcv(struct sk_buff *skb) nh = skb_network_offset(skb); skb_set_network_header(skb, sizeof(*hdr)); - if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN, skb)) + if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN, + skb)) { + reason = SKB_DROP_REASON_XFRM_POLICY; goto drop_no_count; + } skb_set_network_header(skb, nh); } @@ -924,11 +929,11 @@ static int icmpv6_rcv(struct sk_buff *skb) break; case ICMPV6_ECHO_REPLY: - success = ping_rcv(skb); + reason = ping_rcv(skb); break; case ICMPV6_EXT_ECHO_REPLY: - success = ping_rcv(skb); + reason = ping_rcv(skb); break; case ICMPV6_PKT_TOOBIG: @@ -994,19 +999,20 @@ static int icmpv6_rcv(struct sk_buff *skb) /* until the v6 path can be better sorted assume failure and * preserve the status quo behaviour for the rest of the paths to here */ - if (success) - consume_skb(skb); + if (reason) + kfree_skb_reason(skb, reason); else - kfree_skb(skb); + consume_skb(skb); return 0; csum_error: + reason = SKB_DROP_REASON_ICMP_CSUM; __ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_CSUMERRORS); discard_it: __ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INERRORS); drop_no_count: - kfree_skb(skb); + kfree_skb_reason(skb, reason); return 0; } -- cgit v1.3-8-gc7d7 From d6d3146ce532268ad0ffd8d92d2b7492898decf1 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 13 Apr 2022 16:15:52 +0800 Subject: skb: add some helpers for skb drop reasons In order to simply the definition and assignment for 'enum skb_drop_reason', introduce some helpers. SKB_DR() is used to define a variable of type 'enum skb_drop_reason' with the 'SKB_DROP_REASON_NOT_SPECIFIED' initial value. SKB_DR_SET() is used to set the value of the variable. Seems it is a little useless? But it makes the code shorter. SKB_DR_OR() is used to set the value of the variable if it is not set yet, which means its value is SKB_DROP_REASON_NOT_SPECIFIED. Signed-off-by: Menglong Dong Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: David S. Miller --- include/linux/skbuff.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9b81ba497665..0cbd6ada957c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -450,6 +450,18 @@ enum skb_drop_reason { SKB_DROP_REASON_MAX, }; +#define SKB_DR_INIT(name, reason) \ + enum skb_drop_reason name = SKB_DROP_REASON_##reason +#define SKB_DR(name) \ + SKB_DR_INIT(name, NOT_SPECIFIED) +#define SKB_DR_SET(name, reason) \ + (name = SKB_DROP_REASON_##reason) +#define SKB_DR_OR(name, reason) \ + do { \ + if (name == SKB_DROP_REASON_NOT_SPECIFIED) \ + SKB_DR_SET(name, reason); \ + } while (0) + /* To allow 64K frame to be packed as single skb without frag_list we * require 64K/PAGE_SIZE pages plus 1 additional page to allow for * buffers which do not start on a page boundary. -- cgit v1.3-8-gc7d7 From c4eb664191b4a5ff6856478f903924176697719e Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 13 Apr 2022 16:15:53 +0800 Subject: net: ipv4: add skb drop reasons to ip_error() Eventually, I find out the handler function for inputting route lookup fail: ip_error(). The drop reasons we used in ip_error() are almost corresponding to IPSTATS_MIB_*, and following new reasons are introduced: SKB_DROP_REASON_IP_INADDRERRORS SKB_DROP_REASON_IP_INNOROUTES Isn't the name SKB_DROP_REASON_IP_HOSTUNREACH and SKB_DROP_REASON_IP_NETUNREACH more accurate? To make them corresponding to IPSTATS_MIB_*, we keep their name still. Signed-off-by: Menglong Dong Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ include/trace/events/skb.h | 2 ++ net/ipv4/route.c | 6 +++++- 3 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0cbd6ada957c..886e83ac4b70 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -447,6 +447,12 @@ enum skb_drop_reason { * 2211, such as a broadcasts * ICMP_TIMESTAMP */ + SKB_DROP_REASON_IP_INADDRERRORS, /* host unreachable, corresponding + * to IPSTATS_MIB_INADDRERRORS + */ + SKB_DROP_REASON_IP_INNOROUTES, /* network unreachable, corresponding + * to IPSTATS_MIB_INADDRERRORS + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 42647114fffe..0acac7e5a019 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -63,6 +63,8 @@ EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \ EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM) \ EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ + EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS) \ + EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 80f96170876c..e839d424b861 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -945,6 +945,7 @@ static int ip_error(struct sk_buff *skb) struct inet_peer *peer; unsigned long now; struct net *net; + SKB_DR(reason); bool send; int code; @@ -964,10 +965,12 @@ static int ip_error(struct sk_buff *skb) if (!IN_DEV_FORWARD(in_dev)) { switch (rt->dst.error) { case EHOSTUNREACH: + SKB_DR_SET(reason, IP_INADDRERRORS); __IP_INC_STATS(net, IPSTATS_MIB_INADDRERRORS); break; case ENETUNREACH: + SKB_DR_SET(reason, IP_INNOROUTES); __IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES); break; } @@ -983,6 +986,7 @@ static int ip_error(struct sk_buff *skb) break; case ENETUNREACH: code = ICMP_NET_UNREACH; + SKB_DR_SET(reason, IP_INNOROUTES); __IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES); break; case EACCES: @@ -1009,7 +1013,7 @@ static int ip_error(struct sk_buff *skb) if (send) icmp_send(skb, ICMP_DEST_UNREACH, code, 0); -out: kfree_skb(skb); +out: kfree_skb_reason(skb, reason); return 0; } -- cgit v1.3-8-gc7d7 From 2edc1a383fda8d2f580216292dfd9daeae691e47 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 13 Apr 2022 16:15:55 +0800 Subject: net: ip: add skb drop reasons to ip forwarding Replace kfree_skb() which is used in ip6_forward() and ip_forward() with kfree_skb_reason(). The new drop reason 'SKB_DROP_REASON_PKT_TOO_BIG' is introduced for the case that the length of the packet exceeds MTU and can't fragment. Signed-off-by: Menglong Dong Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ include/trace/events/skb.h | 1 + net/ipv4/ip_forward.c | 13 ++++++++++--- net/ipv6/ip6_output.c | 9 ++++++--- 4 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 886e83ac4b70..0ef11df1bc67 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -453,6 +453,9 @@ enum skb_drop_reason { SKB_DROP_REASON_IP_INNOROUTES, /* network unreachable, corresponding * to IPSTATS_MIB_INADDRERRORS */ + SKB_DROP_REASON_PKT_TOO_BIG, /* packet size is too big (maybe exceed + * the MTU) + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 0acac7e5a019..2da72a9a5764 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -65,6 +65,7 @@ EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS) \ EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES) \ + EM(SKB_DROP_REASON_PKT_TOO_BIG, PKT_TOO_BIG) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 92ba3350274b..e3aa436a1bdf 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -90,6 +90,7 @@ int ip_forward(struct sk_buff *skb) struct rtable *rt; /* Route we use */ struct ip_options *opt = &(IPCB(skb)->opt); struct net *net; + SKB_DR(reason); /* that should never happen */ if (skb->pkt_type != PACKET_HOST) @@ -101,8 +102,10 @@ int ip_forward(struct sk_buff *skb) if (skb_warn_if_lro(skb)) goto drop; - if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb)) + if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb)) { + SKB_DR_SET(reason, XFRM_POLICY); goto drop; + } if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb)) return NET_RX_SUCCESS; @@ -118,8 +121,10 @@ int ip_forward(struct sk_buff *skb) if (ip_hdr(skb)->ttl <= 1) goto too_many_hops; - if (!xfrm4_route_forward(skb)) + if (!xfrm4_route_forward(skb)) { + SKB_DR_SET(reason, XFRM_POLICY); goto drop; + } rt = skb_rtable(skb); @@ -132,6 +137,7 @@ int ip_forward(struct sk_buff *skb) IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); + SKB_DR_SET(reason, PKT_TOO_BIG); goto drop; } @@ -169,7 +175,8 @@ too_many_hops: /* Tell the sender its packet died... */ __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0); + SKB_DR_SET(reason, IP_INHDR); drop: - kfree_skb(skb); + kfree_skb_reason(skb, reason); return NET_RX_DROP; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e23f058166af..3e729cee6486 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -469,6 +469,7 @@ int ip6_forward(struct sk_buff *skb) struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(dst->dev); struct inet6_dev *idev; + SKB_DR(reason); u32 mtu; idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); @@ -518,7 +519,7 @@ int ip6_forward(struct sk_buff *skb) icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return -ETIMEDOUT; } @@ -537,6 +538,7 @@ int ip6_forward(struct sk_buff *skb) if (!xfrm6_route_forward(skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); + SKB_DR_SET(reason, XFRM_POLICY); goto drop; } dst = skb_dst(skb); @@ -596,7 +598,7 @@ int ip6_forward(struct sk_buff *skb) __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTOOBIGERRORS); __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG); return -EMSGSIZE; } @@ -618,8 +620,9 @@ int ip6_forward(struct sk_buff *skb) error: __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); + SKB_DR_SET(reason, IP_INADDRERRORS); drop: - kfree_skb(skb); + kfree_skb_reason(skb, reason); return -EINVAL; } -- cgit v1.3-8-gc7d7 From da40b613f89c43c58986e6f30560ad6573a4d569 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:41 -0700 Subject: tcp: add drop reason support to tcp_validate_incoming() Creates four new drop reasons for the following cases: 1) packet being rejected by RFC 7323 PAWS check 2) packet being rejected by SEQUENCE check 3) Invalid RST packet 4) Invalid SYN packet Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ include/trace/events/skb.h | 5 +++++ net/ipv4/tcp_input.c | 7 ++++++- 3 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0ef11df1bc67..a903da1fa0ed 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -381,6 +381,12 @@ enum skb_drop_reason { * the ofo queue, corresponding to * LINUX_MIB_TCPOFOMERGE */ + SKB_DROP_REASON_TCP_RFC7323_PAWS, /* PAWS check, corresponding to + * LINUX_MIB_PAWSESTABREJECTED + */ + SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */ + SKB_DROP_REASON_TCP_RESET, /* Invalid RST packet */ + SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 2da72a9a5764..820dacd14bad 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -37,6 +37,11 @@ EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ + EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS) \ + EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE, \ + TCP_INVALID_SEQUENCE) \ + EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET) \ + EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b2d5fbef6ce3..9a1cb3f48c3f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5667,6 +5667,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, int syn_inerr) { struct tcp_sock *tp = tcp_sk(sk); + SKB_DR(reason); /* RFC1323: H1. Apply PAWS check first. */ if (tcp_fast_parse_options(sock_net(sk), skb, th, tp) && @@ -5678,6 +5679,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, LINUX_MIB_TCPACKSKIPPEDPAWS, &tp->last_oow_ack_time)) tcp_send_dupack(sk, skb); + SKB_DR_SET(reason, TCP_RFC7323_PAWS); goto discard; } /* Reset is accepted even if it did not pass PAWS. */ @@ -5701,6 +5703,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, } else if (tcp_reset_check(sk, skb)) { goto reset; } + SKB_DR_SET(reason, TCP_INVALID_SEQUENCE); goto discard; } @@ -5743,6 +5746,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, sk->sk_state == TCP_ESTABLISHED) tcp_fastopen_active_disable(sk); tcp_send_challenge_ack(sk); + SKB_DR_SET(reason, TCP_RESET); goto discard; } @@ -5757,6 +5761,7 @@ syn_challenge: TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE); tcp_send_challenge_ack(sk); + SKB_DR_SET(reason, TCP_INVALID_SYN); goto discard; } @@ -5765,7 +5770,7 @@ syn_challenge: return true; discard: - tcp_drop(sk, skb); + tcp_drop_reason(sk, skb, reason); return false; reset: -- cgit v1.3-8-gc7d7 From 669da7a71890b2b2a31a7e9571c0fdf1123e26ef Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:43 -0700 Subject: tcp: add drop reasons to tcp_rcv_state_process() Add basic support for drop reasons in tcp_rcv_state_process() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ include/trace/events/skb.h | 3 +++ net/ipv4/tcp_input.c | 24 +++++++++++++++++------- 3 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a903da1fa0ed..6f1410b5ff13 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -387,6 +387,9 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */ SKB_DROP_REASON_TCP_RESET, /* Invalid RST packet */ SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */ + SKB_DROP_REASON_TCP_CLOSE, /* TCP socket in CLOSE state */ + SKB_DROP_REASON_TCP_FASTOPEN, /* dropped by FASTOPEN request socket */ + SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 820dacd14bad..fbe21ad038bc 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -42,6 +42,9 @@ TCP_INVALID_SEQUENCE) \ EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET) \ EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN) \ + EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE) \ + EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN) \ + EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f95a8368981d..85fae79c894d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6413,21 +6413,26 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) struct request_sock *req; int queued = 0; bool acceptable; + SKB_DR(reason); switch (sk->sk_state) { case TCP_CLOSE: + SKB_DR_SET(reason, TCP_CLOSE); goto discard; case TCP_LISTEN: if (th->ack) return 1; - if (th->rst) + if (th->rst) { + SKB_DR_SET(reason, TCP_RESET); goto discard; - + } if (th->syn) { - if (th->fin) + if (th->fin) { + SKB_DR_SET(reason, TCP_FLAGS); goto discard; + } /* It is possible that we process SYN packets from backlog, * so we need to make sure to disable BH and RCU right there. */ @@ -6442,6 +6447,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) consume_skb(skb); return 0; } + SKB_DR_SET(reason, TCP_FLAGS); goto discard; case TCP_SYN_SENT: @@ -6468,13 +6474,16 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - if (!tcp_check_req(sk, skb, req, true, &req_stolen)) + if (!tcp_check_req(sk, skb, req, true, &req_stolen)) { + SKB_DR_SET(reason, TCP_FASTOPEN); goto discard; + } } - if (!th->ack && !th->rst && !th->syn) + if (!th->ack && !th->rst && !th->syn) { + SKB_DR_SET(reason, TCP_FLAGS); goto discard; - + } if (!tcp_validate_incoming(sk, skb, th, 0)) return 0; @@ -6487,6 +6496,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (sk->sk_state == TCP_SYN_RECV) return 1; /* send one RST */ tcp_send_challenge_ack(sk); + SKB_DR_SET(reason, TCP_OLD_ACK); goto discard; } switch (sk->sk_state) { @@ -6647,7 +6657,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (!queued) { discard: - tcp_drop(sk, skb); + tcp_drop_reason(sk, skb, reason); } return 0; -- cgit v1.3-8-gc7d7 From 4b506af9c5b8de0da34097d50d9448dfb33d70c3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:44 -0700 Subject: tcp: add two drop reasons for tcp_ack() Add TCP_TOO_OLD_ACK and TCP_ACK_UNSENT_DATA drop reasons so that tcp_rcv_established() can report them. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ include/trace/events/skb.h | 3 +++ net/ipv4/tcp_input.c | 7 ++++--- 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f1410b5ff13..9ff5557b1909 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -390,6 +390,8 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_CLOSE, /* TCP socket in CLOSE state */ SKB_DROP_REASON_TCP_FASTOPEN, /* dropped by FASTOPEN request socket */ SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ + SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ + SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index fbe21ad038bc..eab0b09223f3 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -45,6 +45,9 @@ EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE) \ EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN) \ EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK) \ + EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK) \ + EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, \ + TCP_ACK_UNSENT_DATA) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 85fae79c894d..8a68785b0405 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3766,7 +3766,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (before(ack, prior_snd_una - tp->max_window)) { if (!(flag & FLAG_NO_CHALLENGE_ACK)) tcp_send_challenge_ack(sk); - return -1; + return -SKB_DROP_REASON_TCP_TOO_OLD_ACK; } goto old_ack; } @@ -3775,7 +3775,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) * this segment (RFC793 Section 3.9). */ if (after(ack, tp->snd_nxt)) - return -1; + return -SKB_DROP_REASON_TCP_ACK_UNSENT_DATA; if (after(ack, prior_snd_una)) { flag |= FLAG_SND_UNA_ADVANCED; @@ -5962,7 +5962,8 @@ slow_path: return; step5: - if (tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT) < 0) + reason = tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT); + if (reason < 0) goto discard; tcp_rcv_rtt_measure_ts(sk, skb); -- cgit v1.3-8-gc7d7 From e7c89ae4078eab24af71ba26b91642e819a4bd7f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:45 -0700 Subject: tcp: add drop reason support to tcp_prune_ofo_queue() Add one reason for packets dropped from OFO queue because of memory pressure. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/trace/events/skb.h | 2 ++ net/ipv4/tcp_input.c | 3 ++- 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9ff5557b1909..ad15ad208b56 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -392,6 +392,7 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ + SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index eab0b09223f3..73d7a6e594cb 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -48,6 +48,8 @@ EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK) \ EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, \ TCP_ACK_UNSENT_DATA) \ + EM(SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, \ + TCP_OFO_QUEUE_PRUNE) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8a68785b0405..a1077adeb1b6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5334,7 +5334,8 @@ static bool tcp_prune_ofo_queue(struct sock *sk) prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); goal -= rb_to_skb(node)->truesize; - tcp_drop(sk, rb_to_skb(node)); + tcp_drop_reason(sk, rb_to_skb(node), + SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE); if (!prev || goal <= 0) { sk_mem_reclaim(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && -- cgit v1.3-8-gc7d7 From 8fbf195798b56e1e87f62d01be636a6425c304c2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:48 -0700 Subject: tcp: add drop reason support to tcp_ofo_queue() packets in OFO queue might be redundant, and dropped. tcp_drop() is no longer needed. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/trace/events/skb.h | 1 + net/ipv4/tcp_input.c | 9 ++------- 3 files changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ad15ad208b56..84d78df60453 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -393,6 +393,7 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */ + SKB_DROP_REASON_TCP_OFO_DROP, /* data already in receive queue */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 73d7a6e594cb..a477bf907498 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -37,6 +37,7 @@ EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ + EM(SKB_DROP_REASON_TCP_OFO_DROP, TCP_OFO_DROP) \ EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS) \ EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE, \ TCP_INVALID_SEQUENCE) \ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 339cc3d40745..cf2dc19bb8c7 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4674,7 +4674,7 @@ static bool tcp_ooo_try_coalesce(struct sock *sk, { bool res = tcp_try_coalesce(sk, to, from, fragstolen); - /* In case tcp_drop() is called later, update to->gso_segs */ + /* In case tcp_drop_reason() is called later, update to->gso_segs */ if (res) { u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) + max_t(u16, 1, skb_shinfo(from)->gso_segs); @@ -4691,11 +4691,6 @@ static void tcp_drop_reason(struct sock *sk, struct sk_buff *skb, kfree_skb_reason(skb, reason); } -static void tcp_drop(struct sock *sk, struct sk_buff *skb) -{ - tcp_drop_reason(sk, skb, SKB_DROP_REASON_NOT_SPECIFIED); -} - /* This one checks to see if we can put data from the * out_of_order queue into the receive_queue. */ @@ -4723,7 +4718,7 @@ static void tcp_ofo_queue(struct sock *sk) rb_erase(&skb->rbnode, &tp->out_of_order_queue); if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) { - tcp_drop(sk, skb); + tcp_drop_reason(sk, skb, SKB_DROP_REASON_TCP_OFO_DROP); continue; } -- cgit v1.3-8-gc7d7 From 92ece28072f18f30099770c5d4b8e300ea6820fa Mon Sep 17 00:00:00 2001 From: Liu Jian Date: Sat, 16 Apr 2022 18:58:00 +0800 Subject: net: Change skb_ensure_writable()'s write_len param to unsigned int type Both pskb_may_pull() and skb_clone_writable()'s length parameters are of type unsigned int already. Therefore, change this function's write_len param to unsigned int type. Signed-off-by: Liu Jian Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20220416105801.88708-3-liujian56@huawei.com --- include/linux/skbuff.h | 2 +- net/core/skbuff.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2394441fa3dd..b37c829d08e1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3885,7 +3885,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); -int skb_ensure_writable(struct sk_buff *skb, int write_len); +int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 30b523fa4ad2..a84e00e44ad2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5601,7 +5601,7 @@ err_free: } EXPORT_SYMBOL(skb_vlan_untag); -int skb_ensure_writable(struct sk_buff *skb, int write_len) +int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len) { if (!pskb_may_pull(skb, write_len)) return -ENOMEM; -- cgit v1.3-8-gc7d7 From 68822bdf76f10c3dc80609d4e2cdc1e847429086 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 22 Apr 2022 13:12:37 -0700 Subject: net: generalize skb freeing deferral to per-cpu lists Logic added in commit f35f821935d8 ("tcp: defer skb freeing after socket lock is released") helped bulk TCP flows to move the cost of skbs frees outside of critical section where socket lock was held. But for RPC traffic, or hosts with RFS enabled, the solution is far from being ideal. For RPC traffic, recvmsg() has to return to user space right after skb payload has been consumed, meaning that BH handler has no chance to pick the skb before recvmsg() thread. This issue is more visible with BIG TCP, as more RPC fit one skb. For RFS, even if BH handler picks the skbs, they are still picked from the cpu on which user thread is running. Ideally, it is better to free the skbs (and associated page frags) on the cpu that originally allocated them. This patch removes the per socket anchor (sk->defer_list) and instead uses a per-cpu list, which will hold more skbs per round. This new per-cpu list is drained at the end of net_action_rx(), after incoming packets have been processed, to lower latencies. In normal conditions, skbs are added to the per-cpu list with no further action. In the (unlikely) cases where the cpu does not run net_action_rx() handler fast enough, we use an IPI to raise NET_RX_SOFTIRQ on the remote cpu. Also, we do not bother draining the per-cpu list from dev_cpu_dead() This is because skbs in this list have no requirement on how fast they should be freed. Note that we can add in the future a small per-cpu cache if we see any contention on sd->defer_lock. Tested on a pair of hosts with 100Gbit NIC, RFS enabled, and /proc/sys/net/ipv4/tcp_rmem[2] tuned to 16MB to work around page recycling strategy used by NIC driver (its page pool capacity being too small compared to number of skbs/pages held in sockets receive queues) Note that this tuning was only done to demonstrate worse conditions for skb freeing for this particular test. These conditions can happen in more general production workload. 10 runs of one TCP_STREAM flow Before: Average throughput: 49685 Mbit. Kernel profiles on cpu running user thread recvmsg() show high cost for skb freeing related functions (*) 57.81% [kernel] [k] copy_user_enhanced_fast_string (*) 12.87% [kernel] [k] skb_release_data (*) 4.25% [kernel] [k] __free_one_page (*) 3.57% [kernel] [k] __list_del_entry_valid 1.85% [kernel] [k] __netif_receive_skb_core 1.60% [kernel] [k] __skb_datagram_iter (*) 1.59% [kernel] [k] free_unref_page_commit (*) 1.16% [kernel] [k] __slab_free 1.16% [kernel] [k] _copy_to_iter (*) 1.01% [kernel] [k] kfree (*) 0.88% [kernel] [k] free_unref_page 0.57% [kernel] [k] ip6_rcv_core 0.55% [kernel] [k] ip6t_do_table 0.54% [kernel] [k] flush_smp_call_function_queue (*) 0.54% [kernel] [k] free_pcppages_bulk 0.51% [kernel] [k] llist_reverse_order 0.38% [kernel] [k] process_backlog (*) 0.38% [kernel] [k] free_pcp_prepare 0.37% [kernel] [k] tcp_recvmsg_locked (*) 0.37% [kernel] [k] __list_add_valid 0.34% [kernel] [k] sock_rfree 0.34% [kernel] [k] _raw_spin_lock_irq (*) 0.33% [kernel] [k] __page_cache_release 0.33% [kernel] [k] tcp_v6_rcv (*) 0.33% [kernel] [k] __put_page (*) 0.29% [kernel] [k] __mod_zone_page_state 0.27% [kernel] [k] _raw_spin_lock After patch: Average throughput: 73076 Mbit. Kernel profiles on cpu running user thread recvmsg() looks better: 81.35% [kernel] [k] copy_user_enhanced_fast_string 1.95% [kernel] [k] _copy_to_iter 1.95% [kernel] [k] __skb_datagram_iter 1.27% [kernel] [k] __netif_receive_skb_core 1.03% [kernel] [k] ip6t_do_table 0.60% [kernel] [k] sock_rfree 0.50% [kernel] [k] tcp_v6_rcv 0.47% [kernel] [k] ip6_rcv_core 0.45% [kernel] [k] read_tsc 0.44% [kernel] [k] _raw_spin_lock_irqsave 0.37% [kernel] [k] _raw_spin_lock 0.37% [kernel] [k] native_irq_return_iret 0.33% [kernel] [k] __inet6_lookup_established 0.31% [kernel] [k] ip6_protocol_deliver_rcu 0.29% [kernel] [k] tcp_rcv_established 0.29% [kernel] [k] llist_reverse_order v2: kdoc issue (kernel bots) do not defer if (alloc_cpu == smp_processor_id()) (Paolo) replace the sk_buff_head with a single-linked list (Jakub) add a READ_ONCE()/WRITE_ONCE() for the lockless read of sd->defer_list Signed-off-by: Eric Dumazet Acked-by: Paolo Abeni Link: https://lore.kernel.org/r/20220422201237.416238-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 5 +++++ include/linux/skbuff.h | 3 +++ include/net/sock.h | 2 -- include/net/tcp.h | 12 ----------- net/core/dev.c | 31 ++++++++++++++++++++++++++++ net/core/skbuff.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++- net/core/sock.c | 3 --- net/ipv4/tcp.c | 25 +---------------------- net/ipv4/tcp_ipv4.c | 1 - net/ipv6/tcp_ipv6.c | 1 - net/tls/tls_sw.c | 2 -- 11 files changed, 90 insertions(+), 46 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7dccbfd1bf56..ac8a5f71220a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3081,6 +3081,11 @@ struct softnet_data { struct sk_buff_head input_pkt_queue; struct napi_struct backlog; + /* Another possibly contended cache line */ + spinlock_t defer_lock ____cacheline_aligned_in_smp; + int defer_count; + struct sk_buff *defer_list; + call_single_data_t defer_csd; }; static inline void input_queue_head_incr(struct softnet_data *sd) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 84d78df60453..5cbc184ca685 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -888,6 +888,7 @@ typedef unsigned char *sk_buff_data_t; * delivery_time at egress. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS + * @alloc_cpu: CPU which did the skb allocation. * @secmark: security marking * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available @@ -1080,6 +1081,7 @@ struct sk_buff { unsigned int sender_cpu; }; #endif + u16 alloc_cpu; #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif @@ -1321,6 +1323,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); +void skb_attempt_defer_free(struct sk_buff *skb); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); diff --git a/include/net/sock.h b/include/net/sock.h index a01d6c421aa2..f9f8ecae0f8d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -292,7 +292,6 @@ struct sk_filter; * @sk_pacing_shift: scaling factor for TCP Small Queues * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held - * @defer_list: head of llist storing skbs to be freed * @sk_callback_lock: used with the callbacks in the end of this struct * @sk_error_queue: rarely used * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, @@ -417,7 +416,6 @@ struct sock { struct sk_buff *head; struct sk_buff *tail; } sk_backlog; - struct llist_head defer_list; #define sk_rmem_alloc sk_backlog.rmem_alloc diff --git a/include/net/tcp.h b/include/net/tcp.h index 679b1964d494..94a52ad1101c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1375,18 +1375,6 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason); -#ifdef CONFIG_INET -void __sk_defer_free_flush(struct sock *sk); - -static inline void sk_defer_free_flush(struct sock *sk) -{ - if (llist_empty(&sk->defer_list)) - return; - __sk_defer_free_flush(sk); -} -#else -static inline void sk_defer_free_flush(struct sock *sk) {} -#endif int tcp_filter(struct sock *sk, struct sk_buff *skb); void tcp_set_state(struct sock *sk, int state); diff --git a/net/core/dev.c b/net/core/dev.c index 4a77ebda4fb1..611bd7197064 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4545,6 +4545,12 @@ static void rps_trigger_softirq(void *data) #endif /* CONFIG_RPS */ +/* Called from hardirq (IPI) context */ +static void trigger_rx_softirq(void *data __always_unused) +{ + __raise_softirq_irqoff(NET_RX_SOFTIRQ); +} + /* * Check if this softnet_data structure is another cpu one * If yes, queue it to our IPI list and return 1 @@ -6571,6 +6577,28 @@ static int napi_threaded_poll(void *data) return 0; } +static void skb_defer_free_flush(struct softnet_data *sd) +{ + struct sk_buff *skb, *next; + unsigned long flags; + + /* Paired with WRITE_ONCE() in skb_attempt_defer_free() */ + if (!READ_ONCE(sd->defer_list)) + return; + + spin_lock_irqsave(&sd->defer_lock, flags); + skb = sd->defer_list; + sd->defer_list = NULL; + sd->defer_count = 0; + spin_unlock_irqrestore(&sd->defer_lock, flags); + + while (skb != NULL) { + next = skb->next; + __kfree_skb(skb); + skb = next; + } +} + static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); @@ -6616,6 +6644,7 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) __raise_softirq_irqoff(NET_RX_SOFTIRQ); net_rps_action_and_irq_enable(sd); + skb_defer_free_flush(sd); } struct netdev_adjacent { @@ -11326,6 +11355,8 @@ static int __init net_dev_init(void) INIT_CSD(&sd->csd, rps_trigger_softirq, sd); sd->cpu = i; #endif + INIT_CSD(&sd->defer_csd, trigger_rx_softirq, NULL); + spin_lock_init(&sd->defer_lock); init_gro_hash(&sd->backlog); sd->backlog.poll = process_backlog; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 30b523fa4ad2..028a280fbabd 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -204,7 +204,7 @@ static void __build_skb_around(struct sk_buff *skb, void *data, skb_set_end_offset(skb, size); skb->mac_header = (typeof(skb->mac_header))~0U; skb->transport_header = (typeof(skb->transport_header))~0U; - + skb->alloc_cpu = raw_smp_processor_id(); /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); @@ -1037,6 +1037,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #ifdef CONFIG_NET_RX_BUSY_POLL CHECK_SKB_FIELD(napi_id); #endif + CHECK_SKB_FIELD(alloc_cpu); #ifdef CONFIG_XPS CHECK_SKB_FIELD(sender_cpu); #endif @@ -6486,3 +6487,51 @@ free_now: } EXPORT_SYMBOL(__skb_ext_put); #endif /* CONFIG_SKB_EXTENSIONS */ + +/** + * skb_attempt_defer_free - queue skb for remote freeing + * @skb: buffer + * + * Put @skb in a per-cpu list, using the cpu which + * allocated the skb/pages to reduce false sharing + * and memory zone spinlock contention. + */ +void skb_attempt_defer_free(struct sk_buff *skb) +{ + int cpu = skb->alloc_cpu; + struct softnet_data *sd; + unsigned long flags; + bool kick; + + if (WARN_ON_ONCE(cpu >= nr_cpu_ids) || + !cpu_online(cpu) || + cpu == raw_smp_processor_id()) { + __kfree_skb(skb); + return; + } + + sd = &per_cpu(softnet_data, cpu); + /* We do not send an IPI or any signal. + * Remote cpu will eventually call skb_defer_free_flush() + */ + spin_lock_irqsave(&sd->defer_lock, flags); + skb->next = sd->defer_list; + /* Paired with READ_ONCE() in skb_defer_free_flush() */ + WRITE_ONCE(sd->defer_list, skb); + sd->defer_count++; + + /* kick every time queue length reaches 128. + * This should avoid blocking in smp_call_function_single_async(). + * This condition should hardly be bit under normal conditions, + * unless cpu suddenly stopped to receive NIC interrupts. + */ + kick = sd->defer_count == 128; + + spin_unlock_irqrestore(&sd->defer_lock, flags); + + /* Make sure to trigger NET_RX_SOFTIRQ on the remote CPU + * if we are unlucky enough (this seems very unlikely). + */ + if (unlikely(kick)) + smp_call_function_single_async(cpu, &sd->defer_csd); +} diff --git a/net/core/sock.c b/net/core/sock.c index 29abec3eabd8..a0f3989de3d6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2082,9 +2082,6 @@ void sk_destruct(struct sock *sk) { bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE); - WARN_ON_ONCE(!llist_empty(&sk->defer_list)); - sk_defer_free_flush(sk); - if (rcu_access_pointer(sk->sk_reuseport_cb)) { reuseport_detach_sock(sk); use_call_rcu = true; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e20b87b3bf90..db55af9eb37b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -843,7 +843,6 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, } release_sock(sk); - sk_defer_free_flush(sk); if (spliced) return spliced; @@ -1589,20 +1588,6 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) tcp_send_ack(sk); } -void __sk_defer_free_flush(struct sock *sk) -{ - struct llist_node *head; - struct sk_buff *skb, *n; - - head = llist_del_all(&sk->defer_list); - llist_for_each_entry_safe(skb, n, head, ll_node) { - prefetch(n); - skb_mark_not_on_list(skb); - __kfree_skb(skb); - } -} -EXPORT_SYMBOL(__sk_defer_free_flush); - static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); @@ -1610,11 +1595,7 @@ static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb) sock_rfree(skb); skb->destructor = NULL; skb->sk = NULL; - if (!skb_queue_empty(&sk->sk_receive_queue) || - !llist_empty(&sk->defer_list)) { - llist_add(&skb->ll_node, &sk->defer_list); - return; - } + return skb_attempt_defer_free(skb); } __kfree_skb(skb); } @@ -2453,7 +2434,6 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, __sk_flush_backlog(sk); } else { tcp_cleanup_rbuf(sk, copied); - sk_defer_free_flush(sk); sk_wait_data(sk, &timeo, last); } @@ -2571,7 +2551,6 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, lock_sock(sk); ret = tcp_recvmsg_locked(sk, msg, len, flags, &tss, &cmsg_flags); release_sock(sk); - sk_defer_free_flush(sk); if (cmsg_flags && ret >= 0) { if (cmsg_flags & TCP_CMSG_TS) @@ -3096,7 +3075,6 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_frag.page = NULL; sk->sk_frag.offset = 0; } - sk_defer_free_flush(sk); sk_error_report(sk); return 0; } @@ -4225,7 +4203,6 @@ static int do_tcp_getsockopt(struct sock *sk, int level, err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname, &zc, &len, err); release_sock(sk); - sk_defer_free_flush(sk); if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags)) goto zerocopy_rcv_cmsg; switch (len) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2c2d42142555..918816ec5dd4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2065,7 +2065,6 @@ process: sk_incoming_cpu_update(sk); - sk_defer_free_flush(sk); bh_lock_sock_nested(sk); tcp_segs_in(tcp_sk(sk), skb); ret = 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 54277de7474b..60bdec257ba7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1728,7 +1728,6 @@ process: sk_incoming_cpu_update(sk); - sk_defer_free_flush(sk); bh_lock_sock_nested(sk); tcp_segs_in(tcp_sk(sk), skb); ret = 0; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index ddbe05ec5489..bc54f6c5b1a4 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1911,7 +1911,6 @@ recv_end: end: release_sock(sk); - sk_defer_free_flush(sk); if (psock) sk_psock_put(sk, psock); return copied ? : err; @@ -1983,7 +1982,6 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, splice_read_end: release_sock(sk); - sk_defer_free_flush(sk); return copied ? : err; } -- cgit v1.3-8-gc7d7 From 657dd5f97b2ed16cdaa6339f42f9130240af1c04 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 28 Apr 2022 11:58:45 +0100 Subject: net: inline skb_zerocopy_iter_dgram skb_zerocopy_iter_dgram() is a small proxy function, inline it. For that, move __zerocopy_sg_from_iter into linux/skbuff.h Signed-off-by: Pavel Begunkov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 36 ++++++++++++++++++++++-------------- net/core/datagram.c | 2 -- net/core/datagram.h | 15 --------------- net/core/skbuff.c | 7 ------- 4 files changed, 22 insertions(+), 38 deletions(-) delete mode 100644 net/core/datagram.h (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dc4b3e1cf21b..3270cb72e4d8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -684,20 +684,6 @@ struct ubuf_info { int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); -struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size); -struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, - struct ubuf_info *uarg); - -void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); - -void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, - bool success); - -int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len); -int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, - struct msghdr *msg, int len, - struct ubuf_info *uarg); - /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ @@ -1679,6 +1665,28 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif +struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size); +struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, + struct ubuf_info *uarg); + +void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); + +void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, + bool success); + +int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, + struct iov_iter *from, size_t length); + +static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, + struct msghdr *msg, int len) +{ + return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len); +} + +int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, + struct msghdr *msg, int len, + struct ubuf_info *uarg); + /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) diff --git a/net/core/datagram.c b/net/core/datagram.c index 70126d15ca6e..50f4faeea76c 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -62,8 +62,6 @@ #include #include -#include "datagram.h" - /* * Is a socket 'connection oriented' ? */ diff --git a/net/core/datagram.h b/net/core/datagram.h deleted file mode 100644 index bcfb75bfa3b2..000000000000 --- a/net/core/datagram.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#ifndef _NET_CORE_DATAGRAM_H_ -#define _NET_CORE_DATAGRAM_H_ - -#include - -struct sock; -struct sk_buff; -struct iov_iter; - -int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, - struct iov_iter *from, size_t length); - -#endif /* _NET_CORE_DATAGRAM_H_ */ diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 00980e62415b..b92e93dcaa91 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -80,7 +80,6 @@ #include #include -#include "datagram.h" #include "sock_destructor.h" struct kmem_cache *skbuff_head_cache __ro_after_init; @@ -1340,12 +1339,6 @@ void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) } EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort); -int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) -{ - return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len); -} -EXPORT_SYMBOL_GPL(skb_zerocopy_iter_dgram); - int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg) -- cgit v1.3-8-gc7d7 From c67b627e99affe4865b13557d68152ad4c35515c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 4 May 2022 10:09:47 -0700 Subject: net: Make msg_zerocopy_alloc static msg_zerocopy_alloc is only used by msg_zerocopy_realloc; remove the export and make static in skbuff.c Signed-off-by: David Ahern Acked-by: Jonathan Lemon Link: https://lore.kernel.org/r/20220504170947.18773-1-dsahern@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 1 - net/core/skbuff.c | 3 +-- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3270cb72e4d8..5c2599e3fe7d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1665,7 +1665,6 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif -struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size); struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 475183f37891..15f7b6f99a8f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1165,7 +1165,7 @@ void mm_unaccount_pinned_pages(struct mmpin *mmp) } EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages); -struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) +static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) { struct ubuf_info *uarg; struct sk_buff *skb; @@ -1196,7 +1196,6 @@ struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) return uarg; } -EXPORT_SYMBOL_GPL(msg_zerocopy_alloc); static inline struct sk_buff *skb_from_uarg(struct ubuf_info *uarg) { -- cgit v1.3-8-gc7d7 From a4ff365346c98081311c299955d91d657123e8aa Mon Sep 17 00:00:00 2001 From: Ricardo Martinez Date: Fri, 6 May 2022 11:12:58 -0700 Subject: net: skb: introduce skb_data_area_size() Helper to calculate the linear data space in the skb. Signed-off-by: Ricardo Martinez Reviewed-by: Sergey Ryazanov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5c2599e3fe7d..d58669d6cb91 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1665,6 +1665,11 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif +static inline unsigned int skb_data_area_size(struct sk_buff *skb) +{ + return skb_end_pointer(skb) - skb->data; +} + struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); -- cgit v1.3-8-gc7d7 From 51eb7492af276b5b4d27cfa4474d40bdac7b9cf8 Mon Sep 17 00:00:00 2001 From: Gerhard Engleder Date: Fri, 6 May 2022 22:01:38 +0200 Subject: ptp: Request cycles for TX timestamp The free running cycle counter of physical clocks called cycles shall be used for hardware timestamps to enable synchronisation. Introduce new flag SKBTX_HW_TSTAMP_USE_CYCLES, which signals driver to provide a TX timestamp based on cycles if cycles are supported. Signed-off-by: Gerhard Engleder Acked-by: Richard Cochran Signed-off-by: Paolo Abeni --- include/linux/skbuff.h | 7 ++++++- net/socket.c | 11 ++++++++++- 2 files changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d58669d6cb91..4a4f25975ca2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -615,6 +615,9 @@ enum { /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, + /* generate hardware time stamp based on cycles if supported */ + SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3, + /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, @@ -624,7 +627,9 @@ enum { #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) -#define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP) +#define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ + SKBTX_HW_TSTAMP_USE_CYCLES | \ + SKBTX_ANY_SW_TSTAMP) /* Definitions for flags in struct skb_shared_info */ enum { diff --git a/net/socket.c b/net/socket.c index f0c39c874665..5c1c5e6100e1 100644 --- a/net/socket.c +++ b/net/socket.c @@ -683,9 +683,18 @@ void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags) { u8 flags = *tx_flags; - if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) + if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) { flags |= SKBTX_HW_TSTAMP; + /* PTP hardware clocks can provide a free running cycle counter + * as a time base for virtual clocks. Tell driver to use the + * free running cycle counter for timestamp if socket is bound + * to virtual clock. + */ + if (tsflags & SOF_TIMESTAMPING_BIND_PHC) + flags |= SKBTX_HW_TSTAMP_USE_CYCLES; + } + if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE) flags |= SKBTX_SW_TSTAMP; -- cgit v1.3-8-gc7d7 From 97dc7cd92ac67f6e05df418df1772ba4a7fbf693 Mon Sep 17 00:00:00 2001 From: Gerhard Engleder Date: Fri, 6 May 2022 22:01:40 +0200 Subject: ptp: Support late timestamp determination If a physical clock supports a free running cycle counter, then timestamps shall be based on this time too. For TX it is known in advance before the transmission if a timestamp based on the free running cycle counter is needed. For RX it is impossible to know which timestamp is needed before the packet is received and assigned to a socket. Support late timestamp determination by a network device. Therefore, an address/cookie is stored within the new netdev_data field of struct skb_shared_hwtstamps. This address/cookie is provided to a new network device function called ndo_get_tstamp(), which returns a timestamp based on the normal/adjustable time or based on the free running cycle counter. If function is not supported, then timestamp handling is not changed. This mechanism is intended for RX, but TX use is also possible. Signed-off-by: Gerhard Engleder Acked-by: Jonathan Lemon Acked-by: Richard Cochran Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 21 ++++++++++++++++++++ include/linux/skbuff.h | 14 +++++++++++--- net/socket.c | 49 +++++++++++++++++++++++++++++++++++++---------- 3 files changed, 71 insertions(+), 13 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 74c97a34921d..51fe143091cf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1356,6 +1356,12 @@ struct netdev_net_notifier { * The caller must be under RCU read context. * int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); * Get the forwarding path to reach the real device from the HW destination address + * ktime_t (*ndo_get_tstamp)(struct net_device *dev, + * const struct skb_shared_hwtstamps *hwtstamps, + * bool cycles); + * Get hardware timestamp based on normal/adjustable time or free running + * cycle counter. This function is required if physical clock supports a + * free running cycle counter. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1578,6 +1584,9 @@ struct net_device_ops { struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); + ktime_t (*ndo_get_tstamp)(struct net_device *dev, + const struct skb_shared_hwtstamps *hwtstamps, + bool cycles); }; /** @@ -4761,6 +4770,18 @@ static inline void netdev_rx_csum_fault(struct net_device *dev, void net_enable_timestamp(void); void net_disable_timestamp(void); +static inline ktime_t netdev_get_tstamp(struct net_device *dev, + const struct skb_shared_hwtstamps *hwtstamps, + bool cycles) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_get_tstamp) + return ops->ndo_get_tstamp(dev, hwtstamps, cycles); + + return hwtstamps->hwtstamp; +} + static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, struct sk_buff *skb, struct net_device *dev, bool more) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4a4f25975ca2..97de40bcfef6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -588,8 +588,10 @@ static inline bool skb_frag_must_loop(struct page *p) /** * struct skb_shared_hwtstamps - hardware time stamps - * @hwtstamp: hardware time stamp transformed into duration - * since arbitrary point in time + * @hwtstamp: hardware time stamp transformed into duration + * since arbitrary point in time + * @netdev_data: address/cookie of network device driver used as + * reference to actual hardware time stamp * * Software time stamps generated by ktime_get_real() are stored in * skb->tstamp. @@ -601,7 +603,10 @@ static inline bool skb_frag_must_loop(struct page *p) * &skb_shared_info. Use skb_hwtstamps() to get a pointer. */ struct skb_shared_hwtstamps { - ktime_t hwtstamp; + union { + ktime_t hwtstamp; + void *netdev_data; + }; }; /* Definitions for tx_flags in struct skb_shared_info */ @@ -621,6 +626,9 @@ enum { /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, + /* determine hardware time stamp based on time or cycles */ + SKBTX_HW_TSTAMP_NETDEV = 1 << 5, + /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, }; diff --git a/net/socket.c b/net/socket.c index 0f680c7d968a..6ee634c01eca 100644 --- a/net/socket.c +++ b/net/socket.c @@ -805,7 +805,28 @@ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp) return skb->tstamp && !false_tstamp && skb_is_err_queue(skb); } -static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb) +static ktime_t get_timestamp(struct sock *sk, struct sk_buff *skb, int *if_index) +{ + bool cycles = sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC; + struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); + struct net_device *orig_dev; + ktime_t hwtstamp; + + rcu_read_lock(); + orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); + if (orig_dev) { + *if_index = orig_dev->ifindex; + hwtstamp = netdev_get_tstamp(orig_dev, shhwtstamps, cycles); + } else { + hwtstamp = shhwtstamps->hwtstamp; + } + rcu_read_unlock(); + + return hwtstamp; +} + +static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb, + int if_index) { struct scm_ts_pktinfo ts_pktinfo; struct net_device *orig_dev; @@ -815,11 +836,14 @@ static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb) memset(&ts_pktinfo, 0, sizeof(ts_pktinfo)); - rcu_read_lock(); - orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); - if (orig_dev) - ts_pktinfo.if_index = orig_dev->ifindex; - rcu_read_unlock(); + if (!if_index) { + rcu_read_lock(); + orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); + if (orig_dev) + if_index = orig_dev->ifindex; + rcu_read_unlock(); + } + ts_pktinfo.if_index = if_index; ts_pktinfo.pkt_length = skb->len - skb_mac_offset(skb); put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_PKTINFO, @@ -839,6 +863,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); + int if_index; ktime_t hwtstamp; /* Race occurred between timestamp enabling and packet @@ -887,18 +912,22 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, if (shhwtstamps && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && !skb_is_swtx_tstamp(skb, false_tstamp)) { - if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC) - hwtstamp = ptp_convert_timestamp(&shhwtstamps->hwtstamp, - sk->sk_bind_phc); + if_index = 0; + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV) + hwtstamp = get_timestamp(sk, skb, &if_index); else hwtstamp = shhwtstamps->hwtstamp; + if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC) + hwtstamp = ptp_convert_timestamp(&hwtstamp, + sk->sk_bind_phc); + if (ktime_to_timespec64_cond(hwtstamp, tss.ts + 2)) { empty = 0; if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && !skb_is_err_queue(skb)) - put_ts_pktinfo(msg, skb); + put_ts_pktinfo(msg, skb, if_index); } } if (!empty) { -- cgit v1.3-8-gc7d7 From ddccc9ef55992716ad477d38fbcd9f8f1d34fc67 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 May 2022 09:04:54 -0700 Subject: skbuff: add a basic intro doc Add basic skb documentation. It's mostly an intro to the subsequent patches - it would looks strange if we documented advanced topics without covering the basics in any way. Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- Documentation/networking/skbuff.rst | 25 +++++++++++++++++++++++ include/linux/skbuff.h | 40 +++++++++++++++++++++++++++++++++++++ 2 files changed, 65 insertions(+) create mode 100644 Documentation/networking/skbuff.rst (limited to 'include/linux/skbuff.h') diff --git a/Documentation/networking/skbuff.rst b/Documentation/networking/skbuff.rst new file mode 100644 index 000000000000..b4a008feceb4 --- /dev/null +++ b/Documentation/networking/skbuff.rst @@ -0,0 +1,25 @@ +.. SPDX-License-Identifier: GPL-2.0 + +struct sk_buff +============== + +:c:type:`sk_buff` is the main networking structure representing +a packet. + +Basic sk_buff geometry +---------------------- + +.. kernel-doc:: include/linux/skbuff.h + :doc: Basic sk_buff geometry + +Shared skbs and skb clones +-------------------------- + +:c:member:`sk_buff.users` is a simple refcount allowing multiple entities +to keep a struct sk_buff alive. skbs with a ``sk_buff.users != 1`` are referred +to as shared skbs (see skb_shared()). + +skb_clone() allows for fast duplication of skbs. None of the data buffers +get copied, but caller gets a new metadata struct (struct sk_buff). +&skb_shared_info.refcount indicates the number of skbs pointing at the same +packet data (i.e. clones). diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 97de40bcfef6..69802624276d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -800,6 +800,46 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif +/** + * DOC: Basic sk_buff geometry + * + * struct sk_buff itself is a metadata structure and does not hold any packet + * data. All the data is held in associated buffers. + * + * &sk_buff.head points to the main "head" buffer. The head buffer is divided + * into two parts: + * + * - data buffer, containing headers and sometimes payload; + * this is the part of the skb operated on by the common helpers + * such as skb_put() or skb_pull(); + * - shared info (struct skb_shared_info) which holds an array of pointers + * to read-only data in the (page, offset, length) format. + * + * Optionally &skb_shared_info.frag_list may point to another skb. + * + * Basic diagram may look like this:: + * + * --------------- + * | sk_buff | + * --------------- + * ,--------------------------- + head + * / ,----------------- + data + * / / ,----------- + tail + * | | | , + end + * | | | | + * v v v v + * ----------------------------------------------- + * | headroom | data | tailroom | skb_shared_info | + * ----------------------------------------------- + * + [page frag] + * + [page frag] + * + [page frag] + * + [page frag] --------- + * + frag_list --> | sk_buff | + * --------- + * + */ + /** * struct sk_buff - socket buffer * @next: Next buffer in list -- cgit v1.3-8-gc7d7 From 9ec7ea1462084df695f34c5ac2d2d2250d9d6897 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 May 2022 09:04:55 -0700 Subject: skbuff: rewrite the doc for data-only skbs The comment about shinfo->dataref split is really unhelpful, at least to me. Rewrite it and render it to skb documentation. Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- Documentation/networking/index.rst | 1 + Documentation/networking/skbuff.rst | 6 ++++++ include/linux/skbuff.h | 42 ++++++++++++++++++++++++++----------- 3 files changed, 37 insertions(+), 12 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 72cf33579b78..a1c271fe484e 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -97,6 +97,7 @@ Contents: sctp secid seg6-sysctl + skbuff smc-sysctl statistics strparser diff --git a/Documentation/networking/skbuff.rst b/Documentation/networking/skbuff.rst index b4a008feceb4..94681523e345 100644 --- a/Documentation/networking/skbuff.rst +++ b/Documentation/networking/skbuff.rst @@ -23,3 +23,9 @@ skb_clone() allows for fast duplication of skbs. None of the data buffers get copied, but caller gets a new metadata struct (struct sk_buff). &skb_shared_info.refcount indicates the number of skbs pointing at the same packet data (i.e. clones). + +dataref and headerless skbs +--------------------------- + +.. kernel-doc:: include/linux/skbuff.h + :doc: dataref and headerless skbs diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 69802624276d..0e492f9bf532 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -727,16 +727,32 @@ struct skb_shared_info { skb_frag_t frags[MAX_SKB_FRAGS]; }; -/* We divide dataref into two halves. The higher 16 bits hold references - * to the payload part of skb->data. The lower 16 bits hold references to - * the entire skb->data. A clone of a headerless skb holds the length of - * the header in skb->hdr_len. - * - * All users must obey the rule that the skb->data reference count must be - * greater than or equal to the payload reference count. - * - * Holding a reference to the payload part means that the user does not - * care about modifications to the header part of skb->data. +/** + * DOC: dataref and headerless skbs + * + * Transport layers send out clones of payload skbs they hold for + * retransmissions. To allow lower layers of the stack to prepend their headers + * we split &skb_shared_info.dataref into two halves. + * The lower 16 bits count the overall number of references. + * The higher 16 bits indicate how many of the references are payload-only. + * skb_header_cloned() checks if skb is allowed to add / write the headers. + * + * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr + * (via __skb_header_release()). Any clone created from marked skb will get + * &sk_buff.hdr_len populated with the available headroom. + * If there's the only clone in existence it's able to modify the headroom + * at will. The sequence of calls inside the transport layer is:: + * + * + * skb_reserve() + * __skb_header_release() + * skb_clone() + * // send the clone down the stack + * + * This is not a very generic construct and it depends on the transport layers + * doing the right thing. In practice there's usually only one payload-only skb. + * Having multiple payload-only skbs with different lengths of hdr_len is not + * possible. The payload-only skbs should never leave their owner. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) @@ -2027,8 +2043,10 @@ static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) } /** - * __skb_header_release - release reference to header - * @skb: buffer to operate on + * __skb_header_release() - allow clones to use the headroom + * @skb: buffer to operate on + * + * See "DOC: dataref and headerless skbs". */ static inline void __skb_header_release(struct sk_buff *skb) { -- cgit v1.3-8-gc7d7 From 9facd94114b59afebd405e74b3bc2bf184efe986 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 May 2022 09:04:56 -0700 Subject: skbuff: render the checksum comment to documentation Long time ago Tom added a giant comment to skbuff.h explaining checksums. Now that we have a place in Documentation for skbuff docs we should render it. Sprinkle some markup while at it. Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- Documentation/networking/skbuff.rst | 6 + include/linux/skbuff.h | 219 ++++++++++++++++++++---------------- 2 files changed, 130 insertions(+), 95 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/Documentation/networking/skbuff.rst b/Documentation/networking/skbuff.rst index 94681523e345..5b74275a73a3 100644 --- a/Documentation/networking/skbuff.rst +++ b/Documentation/networking/skbuff.rst @@ -29,3 +29,9 @@ dataref and headerless skbs .. kernel-doc:: include/linux/skbuff.h :doc: dataref and headerless skbs + +Checksum information +-------------------- + +.. kernel-doc:: include/linux/skbuff.h + :doc: skb checksums diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0e492f9bf532..5296b2c37f62 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -43,98 +43,112 @@ #include #endif -/* The interface for checksum offload between the stack and networking drivers +/** + * DOC: skb checksums + * + * The interface for checksum offload between the stack and networking drivers * is as follows... * - * A. IP checksum related features + * IP checksum related features + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Drivers advertise checksum offload capabilities in the features of a device. * From the stack's point of view these are capabilities offered by the driver. * A driver typically only advertises features that it is capable of offloading * to its device. * - * The checksum related features are: - * - * NETIF_F_HW_CSUM - The driver (or its device) is able to compute one - * IP (one's complement) checksum for any combination - * of protocols or protocol layering. The checksum is - * computed and set in a packet per the CHECKSUM_PARTIAL - * interface (see below). - * - * NETIF_F_IP_CSUM - Driver (device) is only able to checksum plain - * TCP or UDP packets over IPv4. These are specifically - * unencapsulated packets of the form IPv4|TCP or - * IPv4|UDP where the Protocol field in the IPv4 header - * is TCP or UDP. The IPv4 header may contain IP options. - * This feature cannot be set in features for a device - * with NETIF_F_HW_CSUM also set. This feature is being - * DEPRECATED (see below). - * - * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain - * TCP or UDP packets over IPv6. These are specifically - * unencapsulated packets of the form IPv6|TCP or - * IPv6|UDP where the Next Header field in the IPv6 - * header is either TCP or UDP. IPv6 extension headers - * are not supported with this feature. This feature - * cannot be set in features for a device with - * NETIF_F_HW_CSUM also set. This feature is being - * DEPRECATED (see below). - * - * NETIF_F_RXCSUM - Driver (device) performs receive checksum offload. - * This flag is only used to disable the RX checksum - * feature for a device. The stack will accept receive - * checksum indication in packets received on a device - * regardless of whether NETIF_F_RXCSUM is set. - * - * B. Checksumming of received packets by device. Indication of checksum - * verification is set in skb->ip_summed. Possible values are: - * - * CHECKSUM_NONE: + * .. flat-table:: Checksum related device features + * :widths: 1 10 + * + * * - %NETIF_F_HW_CSUM + * - The driver (or its device) is able to compute one + * IP (one's complement) checksum for any combination + * of protocols or protocol layering. The checksum is + * computed and set in a packet per the CHECKSUM_PARTIAL + * interface (see below). + * + * * - %NETIF_F_IP_CSUM + * - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv4. These are specifically + * unencapsulated packets of the form IPv4|TCP or + * IPv4|UDP where the Protocol field in the IPv4 header + * is TCP or UDP. The IPv4 header may contain IP options. + * This feature cannot be set in features for a device + * with NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * * - %NETIF_F_IPV6_CSUM + * - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv6. These are specifically + * unencapsulated packets of the form IPv6|TCP or + * IPv6|UDP where the Next Header field in the IPv6 + * header is either TCP or UDP. IPv6 extension headers + * are not supported with this feature. This feature + * cannot be set in features for a device with + * NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * * - %NETIF_F_RXCSUM + * - Driver (device) performs receive checksum offload. + * This flag is only used to disable the RX checksum + * feature for a device. The stack will accept receive + * checksum indication in packets received on a device + * regardless of whether NETIF_F_RXCSUM is set. + * + * Checksumming of received packets by device + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * Indication of checksum verification is set in &sk_buff.ip_summed. + * Possible values are: + * + * - %CHECKSUM_NONE * * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * - * CHECKSUM_UNNECESSARY: + * - %CHECKSUM_UNNECESSARY * * The hardware you're dealing with doesn't calculate the full checksum - * (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums - * for specific protocols. For such packets it will set CHECKSUM_UNNECESSARY - * if their checksums are okay. skb->csum is still undefined in this case + * (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums + * for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY + * if their checksums are okay. &sk_buff.csum is still undefined in this case * though. A driver or device must never modify the checksum field in the * packet even if checksum is verified. * - * CHECKSUM_UNNECESSARY is applicable to following protocols: - * TCP: IPv6 and IPv4. - * UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a + * %CHECKSUM_UNNECESSARY is applicable to following protocols: + * + * - TCP: IPv6 and IPv4. + * - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a * zero UDP checksum for either IPv4 or IPv6, the networking stack * may perform further validation in this case. - * GRE: only if the checksum is present in the header. - * SCTP: indicates the CRC in SCTP header has been validated. - * FCOE: indicates the CRC in FC frame has been validated. + * - GRE: only if the checksum is present in the header. + * - SCTP: indicates the CRC in SCTP header has been validated. + * - FCOE: indicates the CRC in FC frame has been validated. * - * skb->csum_level indicates the number of consecutive checksums found in - * the packet minus one that have been verified as CHECKSUM_UNNECESSARY. + * &sk_buff.csum_level indicates the number of consecutive checksums found in + * the packet minus one that have been verified as %CHECKSUM_UNNECESSARY. * For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet * and a device is able to verify the checksums for UDP (possibly zero), - * GRE (checksum flag is set) and TCP, skb->csum_level would be set to + * GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to * two. If the device were only able to verify the UDP checksum and not * GRE, either because it doesn't support GRE checksum or because GRE * checksum is bad, skb->csum_level would be set to zero (TCP checksum is * not considered in this case). * - * CHECKSUM_COMPLETE: + * - %CHECKSUM_COMPLETE * * This is the most generic way. The device supplied checksum of the _whole_ - * packet as seen by netif_rx() and fills in skb->csum. This means the + * packet as seen by netif_rx() and fills in &sk_buff.csum. This means the * hardware doesn't need to parse L3/L4 headers to implement this. * * Notes: + * * - Even if device supports only some protocols, but is able to produce * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * - * CHECKSUM_PARTIAL: + * - %CHECKSUM_PARTIAL * * A checksum is set up to be offloaded to a device as described in the * output description for CHECKSUM_PARTIAL. This may occur on a packet @@ -146,14 +160,18 @@ * packet that are after the checksum being offloaded are not considered to * be verified. * - * C. Checksumming on transmit for non-GSO. The stack requests checksum offload - * in the skb->ip_summed for a packet. Values are: + * Checksumming on transmit for non-GSO + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * The stack requests checksum offload in the &sk_buff.ip_summed for a packet. + * Values are: * - * CHECKSUM_PARTIAL: + * - %CHECKSUM_PARTIAL * * The driver is required to checksum the packet as seen by hard_start_xmit() - * from skb->csum_start up to the end, and to record/write the checksum at - * offset skb->csum_start + skb->csum_offset. A driver may verify that the + * from &sk_buff.csum_start up to the end, and to record/write the checksum at + * offset &sk_buff.csum_start + &sk_buff.csum_offset. + * A driver may verify that the * csum_start and csum_offset values are valid values given the length and * offset of the packet, but it should not attempt to validate that the * checksum refers to a legitimate transport layer checksum -- it is the @@ -165,55 +183,66 @@ * checksum calculation to the device, or call skb_checksum_help (in the case * that the device does not support offload for a particular checksum). * - * NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM are being deprecated in favor of - * NETIF_F_HW_CSUM. New devices should use NETIF_F_HW_CSUM to indicate + * %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of + * %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate * checksum offload capability. - * skb_csum_hwoffload_help() can be called to resolve CHECKSUM_PARTIAL based + * skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based * on network device checksumming capabilities: if a packet does not match - * them, skb_checksum_help or skb_crc32c_help (depending on the value of - * csum_not_inet, see item D.) is called to resolve the checksum. + * them, skb_checksum_help() or skb_crc32c_help() (depending on the value of + * &sk_buff.csum_not_inet, see :ref:`crc`) + * is called to resolve the checksum. * - * CHECKSUM_NONE: + * - %CHECKSUM_NONE * * The skb was already checksummed by the protocol, or a checksum is not * required. * - * CHECKSUM_UNNECESSARY: + * - %CHECKSUM_UNNECESSARY * * This has the same meaning as CHECKSUM_NONE for checksum offload on * output. * - * CHECKSUM_COMPLETE: + * - %CHECKSUM_COMPLETE + * * Not used in checksum output. If a driver observes a packet with this value - * set in skbuff, it should treat the packet as if CHECKSUM_NONE were set. - * - * D. Non-IP checksum (CRC) offloads - * - * NETIF_F_SCTP_CRC - This feature indicates that a device is capable of - * offloading the SCTP CRC in a packet. To perform this offload the stack - * will set csum_start and csum_offset accordingly, set ip_summed to - * CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication in - * the skbuff that the CHECKSUM_PARTIAL refers to CRC32c. - * A driver that supports both IP checksum offload and SCTP CRC32c offload - * must verify which offload is configured for a packet by testing the - * value of skb->csum_not_inet; skb_crc32c_csum_help is provided to resolve - * CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. - * - * NETIF_F_FCOE_CRC - This feature indicates that a device is capable of - * offloading the FCOE CRC in a packet. To perform this offload the stack - * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset - * accordingly. Note that there is no indication in the skbuff that the - * CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports - * both IP checksum offload and FCOE CRC offload must verify which offload - * is configured for a packet, presumably by inspecting packet headers. - * - * E. Checksumming on output with GSO. - * - * In the case of a GSO packet (skb_is_gso(skb) is true), checksum offload + * set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set. + * + * .. _crc: + * + * Non-IP checksum (CRC) offloads + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * .. flat-table:: + * :widths: 1 10 + * + * * - %NETIF_F_SCTP_CRC + * - This feature indicates that a device is capable of + * offloading the SCTP CRC in a packet. To perform this offload the stack + * will set csum_start and csum_offset accordingly, set ip_summed to + * %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication + * in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c. + * A driver that supports both IP checksum offload and SCTP CRC32c offload + * must verify which offload is configured for a packet by testing the + * value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to + * resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. + * + * * - %NETIF_F_FCOE_CRC + * - This feature indicates that a device is capable of offloading the FCOE + * CRC in a packet. To perform this offload the stack will set ip_summed + * to %CHECKSUM_PARTIAL and set csum_start and csum_offset + * accordingly. Note that there is no indication in the skbuff that the + * %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports + * both IP checksum offload and FCOE CRC offload must verify which offload + * is configured for a packet, presumably by inspecting packet headers. + * + * Checksumming on output with GSO + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * In the case of a GSO packet (skb_is_gso() is true), checksum offload * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the - * gso_type is SKB_GSO_TCPV4 or SKB_GSO_TCPV6, TCP checksum offload as + * gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as * part of the GSO operation is implied. If a checksum is being offloaded - * with GSO then ip_summed is CHECKSUM_PARTIAL, and both csum_start and + * with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and * csum_offset are set to refer to the outermost checksum being offloaded * (two offloaded checksums are possible with UDP encapsulation). */ -- cgit v1.3-8-gc7d7 From 66e4c8d950083df8e12981babca788e1635c92b6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 9 May 2022 20:57:39 -0700 Subject: net: warn if transport header was not set Make sure skb_transport_header() and skb_transport_offset() uses are not fooled if the transport header has not been set. This change will likely expose existing bugs in linux networking stacks. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5296b2c37f62..b91d225fdc13 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -42,6 +42,7 @@ #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include #endif +#include /** * DOC: skb checksums @@ -2904,6 +2905,7 @@ static inline bool skb_transport_header_was_set(const struct sk_buff *skb) static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { + DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->head + skb->transport_header; } -- cgit v1.3-8-gc7d7 From 0df65743537dd6e1c8b0924714f14dc367cba2be Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 11 May 2022 10:23:05 -0700 Subject: skbuff: replace a BUG_ON() with the new DEBUG_NET_WARN_ON_ONCE() Very few drivers actually have Kconfig knobs for adding -DDEBUG. 8 according to a quick grep, while there are 93 users of skb_checksum_none_assert(). Switch to the new DEBUG_NET_WARN_ON_ONCE() to catch bad skbs. Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220511172305.1382810-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b91d225fdc13..9d82a8b6c8f1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -5048,9 +5048,7 @@ static inline void skb_forward_csum(struct sk_buff *skb) */ static inline void skb_checksum_none_assert(const struct sk_buff *skb) { -#ifdef DEBUG - BUG_ON(skb->ip_summed != CHECKSUM_NONE); -#endif + DEBUG_NET_WARN_ON_ONCE(skb->ip_summed != CHECKSUM_NONE); } bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); -- cgit v1.3-8-gc7d7 From 7ebd3f3ee51a9e02994cd0a1be44fbd325d1e0dc Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 13 May 2022 11:03:38 +0800 Subject: net: skb: change the definition SKB_DR_SET() The SKB_DR_OR() is used to set the drop reason to a value when it is not set or specified yet. SKB_NOT_DROPPED_YET should also be considered as not set. Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9d82a8b6c8f1..5a2b29df6cab 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -510,7 +510,8 @@ enum skb_drop_reason { (name = SKB_DROP_REASON_##reason) #define SKB_DR_OR(name, reason) \ do { \ - if (name == SKB_DROP_REASON_NOT_SPECIFIED) \ + if (name == SKB_DROP_REASON_NOT_SPECIFIED || \ + name == SKB_NOT_DROPPED_YET) \ SKB_DR_SET(name, reason); \ } while (0) -- cgit v1.3-8-gc7d7 From 89af2ce2d95c80f6da9388d9da2e35c84c2573b1 Mon Sep 17 00:00:00 2001 From: Ricardo Martinez Date: Fri, 13 May 2022 10:34:00 -0700 Subject: net: skb: Remove skb_data_area_size() skb_data_area_size() is not needed. As Jakub pointed out [1]: For Rx, drivers can use the size passed during skb allocation or use skb_tailroom(). For Tx, drivers should use skb_headlen(). [1] https://lore.kernel.org/netdev/CAHNKnsTmH-rGgWi3jtyC=ktM1DW2W1VJkYoTMJV2Z_Bt498bsg@mail.gmail.com/ Signed-off-by: Ricardo Martinez Reviewed-by: Andy Shevchenko Reviewed-by: Sergey Ryazanov Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5a2b29df6cab..da96f0d3e753 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1765,11 +1765,6 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif -static inline unsigned int skb_data_area_size(struct sk_buff *skb) -{ - return skb_end_pointer(skb) - skb->data; -} - struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); -- cgit v1.3-8-gc7d7 From 22296a5c0cd35aaf62e1af3266f82cdf6b0b9b78 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 2 Jun 2022 09:18:58 -0700 Subject: net: add debug info to __skb_pull() While analyzing yet another syzbot report, I found the following patch very useful. It allows to better understand what went wrong. This debug info is only enabled if CONFIG_DEBUG_NET=y, which is the case for syzbot builds. Signed-off-by: Eric Dumazet Acked-by: Willem de Bruijn Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux/skbuff.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index da96f0d3e753..d3d10556f0fa 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2696,7 +2696,14 @@ void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { skb->len -= len; - BUG_ON(skb->len < skb->data_len); + if (unlikely(skb->len < skb->data_len)) { +#if defined(CONFIG_DEBUG_NET) + skb->len += len; + pr_err("__skb_pull(len=%u)\n", len); + skb_dump(KERN_ERR, skb, false); +#endif + BUG(); + } return skb->data += len; } -- cgit v1.3-8-gc7d7