OpenCloudOS-Kernel/net/ipv4/udp.c

3496 lines
88 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* The User Datagram Protocol (UDP).
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
* Alan Cox, <alan@lxorguk.ukuu.org.uk>
* Hirokazu Takahashi, <taka@valinux.co.jp>
*
* Fixes:
* Alan Cox : verify_area() calls
* Alan Cox : stopped close while in use off icmp
* messages. Not a fix but a botch that
* for udp at least is 'valid'.
* Alan Cox : Fixed icmp handling properly
* Alan Cox : Correct error for oversized datagrams
* Alan Cox : Tidied select() semantics.
* Alan Cox : udp_err() fixed properly, also now
* select and read wake correctly on errors
* Alan Cox : udp_send verify_area moved to avoid mem leak
* Alan Cox : UDP can count its memory
* Alan Cox : send to an unknown connection causes
* an ECONNREFUSED off the icmp, but
* does NOT close.
* Alan Cox : Switched to new sk_buff handlers. No more backlog!
* Alan Cox : Using generic datagram code. Even smaller and the PEEK
* bug no longer crashes it.
* Fred Van Kempen : Net2e support for sk->broadcast.
* Alan Cox : Uses skb_free_datagram
* Alan Cox : Added get/set sockopt support.
* Alan Cox : Broadcasting without option set returns EACCES.
* Alan Cox : No wakeup calls. Instead we now use the callbacks.
* Alan Cox : Use ip_tos and ip_ttl
* Alan Cox : SNMP Mibs
* Alan Cox : MSG_DONTROUTE, and 0.0.0.0 support.
* Matt Dillon : UDP length checks.
* Alan Cox : Smarter af_inet used properly.
* Alan Cox : Use new kernel side addressing.
* Alan Cox : Incorrect return on truncated datagram receive.
* Arnt Gulbrandsen : New udp_send and stuff
* Alan Cox : Cache last socket
* Alan Cox : Route cache
* Jon Peatfield : Minor efficiency fix to sendto().
* Mike Shaver : RFC1122 checks.
* Alan Cox : Nonblocking error fix.
* Willy Konynenberg : Transparent proxying support.
* Mike McLagan : Routing by source
* David S. Miller : New socket lookup architecture.
* Last socket cache retained as it
* does have a high hit rate.
* Olaf Kirch : Don't linearise iovec on sendmsg.
* Andi Kleen : Some cleanups, cache destination entry
* for connect.
* Vitaly E. Lavrov : Transparent proxy revived after year coma.
* Melvin Smith : Check msg_name not msg_namelen in sendto(),
* return ENOTCONN for unconnected sockets (POSIX)
* Janos Farkas : don't deliver multi/broadcasts to a different
* bound-to-device socket
* Hirokazu Takahashi : HW checksumming for outgoing UDP
* datagrams.
* Hirokazu Takahashi : sendfile() on UDP works now.
* Arnaldo C. Melo : convert /proc/net/udp to seq_file
* YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which
* Alexey Kuznetsov: allow both IPv4 and IPv6 sockets to bind
* a single port at the same time.
* Derek Atkins <derek@ihtfp.com>: Add Encapulation Support
* James Chapman : Add L2TP encapsulation type.
*/
#define pr_fmt(fmt) "UDP: " fmt
#include <linux/bpf-cgroup.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
mm: remove include/linux/bootmem.h Move remaining definitions and declarations from include/linux/bootmem.h into include/linux/memblock.h and remove the redundant header. The includes were replaced with the semantic patch below and then semi-automated removal of duplicated '#include <linux/memblock.h> @@ @@ - #include <linux/bootmem.h> + #include <linux/memblock.h> [sfr@canb.auug.org.au: dma-direct: fix up for the removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181002185342.133d1680@canb.auug.org.au [sfr@canb.auug.org.au: powerpc: fix up for removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181005161406.73ef8727@canb.auug.org.au [sfr@canb.auug.org.au: x86/kaslr, ACPI/NUMA: fix for linux/bootmem.h removal] Link: http://lkml.kernel.org/r/20181008190341.5e396491@canb.auug.org.au Link: http://lkml.kernel.org/r/1536927045-23536-30-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Ingo Molnar <mingo@redhat.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Jonas Bonn <jonas@southpole.se> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ley Foon Tan <lftan@altera.com> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Paul Burton <paul.burton@mips.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Serge Semin <fancer.lancer@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-31 06:09:49 +08:00
#include <linux/memblock.h>
#include <linux/highmem.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/module.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/igmp.h>
#include <linux/inetdevice.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <net/tcp_states.h>
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <net/net_namespace.h>
#include <net/icmp.h>
#include <net/inet_hashtables.h>
#include <net/ip_tunnels.h>
#include <net/route.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <trace/events/udp.h>
#include <linux/static_key.h>
#include <linux/btf_ids.h>
#include <trace/events/skb.h>
#include <net/busy_poll.h>
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-28 03:10:57 +08:00
#include "udp_impl.h"
#include <net/sock_reuseport.h>
#include <net/addrconf.h>
#include <net/udp_tunnel.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6_stubs.h>
#endif
struct udp_table udp_table __read_mostly;
EXPORT_SYMBOL(udp_table);
long sysctl_udp_mem[3] __read_mostly;
EXPORT_SYMBOL(sysctl_udp_mem);
atomic_long_t udp_memory_allocated ____cacheline_aligned_in_smp;
EXPORT_SYMBOL(udp_memory_allocated);
DEFINE_PER_CPU(int, udp_memory_per_cpu_fw_alloc);
EXPORT_PER_CPU_SYMBOL_GPL(udp_memory_per_cpu_fw_alloc);
#define MAX_UDP_PORTS 65536
udp: Introduce optional per-netns hash table. The maximum hash table size is 64K due to the nature of the protocol. [0] It's smaller than TCP, and fewer sockets can cause a performance drop. On an EC2 c5.24xlarge instance (192 GiB memory), after running iperf3 in different netns, creating 32Mi sockets without data transfer in the root netns causes regression for the iperf3's connection. uhash_entries sockets length Gbps 64K 1 1 5.69 1Mi 16 5.27 2Mi 32 4.90 4Mi 64 4.09 8Mi 128 2.96 16Mi 256 2.06 32Mi 512 1.12 The per-netns hash table breaks the lengthy lists into shorter ones. It is useful on a multi-tenant system with thousands of netns. With smaller hash tables, we can look up sockets faster, isolate noisy neighbours, and reduce lock contention. The max size of the per-netns table is 64K as well. This is because the possible hash range by udp_hashfn() always fits in 64K within the same netns and we cannot make full use of the whole buckets larger than 64K. /* 0 < num < 64K -> X < hash < X + 64K */ (num + net_hash_mix(net)) & mask; Also, the min size is 128. We use a bitmap to search for an available port in udp_lib_get_port(). To keep the bitmap on the stack and not fire the CONFIG_FRAME_WARN error at build time, we round up the table size to 128. The sysctl usage is the same with TCP: $ dmesg | cut -d ' ' -f 6- | grep "UDP hash" UDP hash table entries: 65536 (order: 9, 2097152 bytes, vmalloc) # sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 65536 # can be changed by uhash_entries # sysctl net.ipv4.udp_child_hash_entries net.ipv4.udp_child_hash_entries = 0 # disabled by default # ip netns add test1 # ip netns exec test1 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = -65536 # share the global table # sysctl -w net.ipv4.udp_child_hash_entries=100 net.ipv4.udp_child_hash_entries = 100 # ip netns add test2 # ip netns exec test2 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 128 # own a per-netns table with 2^n buckets We could optimise the hash table lookup/iteration further by removing the netns comparison for the per-netns one in the future. Also, we could optimise the sparse udp_hslot layout by putting it in udp_table. [0]: https://lore.kernel.org/netdev/4ACC2815.7010101@gmail.com/ Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-11-15 05:57:57 +08:00
#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN_PERNET)
static struct udp_table *udp_get_table_prot(struct sock *sk)
{
return sk->sk_prot->h.udp_table ? : sock_net(sk)->ipv4.udp_table;
}
static int udp_lib_lport_inuse(struct net *net, __u16 num,
const struct udp_hslot *hslot,
unsigned long *bitmap,
struct sock *sk, unsigned int log)
{
struct sock *sk2;
kuid_t uid = sock_i_uid(sk);
sk_for_each(sk2, &hslot->head) {
if (net_eq(sock_net(sk2), net) &&
sk2 != sk &&
(bitmap || udp_sk(sk2)->udp_port_hash == num) &&
(!sk2->sk_reuse || !sk->sk_reuse) &&
(!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
inet_rcv_saddr_equal(sk, sk2, true)) {
if (sk2->sk_reuseport && sk->sk_reuseport &&
!rcu_access_pointer(sk->sk_reuseport_cb) &&
uid_eq(uid, sock_i_uid(sk2))) {
if (!bitmap)
return 0;
} else {
if (!bitmap)
return 1;
__set_bit(udp_sk(sk2)->udp_port_hash >> log,
bitmap);
}
}
}
return 0;
}
/*
* Note: we still hold spinlock of primary hash chain, so no other writer
* can insert/delete a socket with local_port == num
*/
static int udp_lib_lport_inuse2(struct net *net, __u16 num,
struct udp_hslot *hslot2,
struct sock *sk)
{
struct sock *sk2;
kuid_t uid = sock_i_uid(sk);
int res = 0;
spin_lock(&hslot2->lock);
udp_portaddr_for_each_entry(sk2, &hslot2->head) {
if (net_eq(sock_net(sk2), net) &&
sk2 != sk &&
(udp_sk(sk2)->udp_port_hash == num) &&
(!sk2->sk_reuse || !sk->sk_reuse) &&
(!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
inet_rcv_saddr_equal(sk, sk2, true)) {
if (sk2->sk_reuseport && sk->sk_reuseport &&
!rcu_access_pointer(sk->sk_reuseport_cb) &&
uid_eq(uid, sock_i_uid(sk2))) {
res = 0;
} else {
res = 1;
}
break;
}
}
spin_unlock(&hslot2->lock);
return res;
}
static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot)
{
struct net *net = sock_net(sk);
kuid_t uid = sock_i_uid(sk);
struct sock *sk2;
sk_for_each(sk2, &hslot->head) {
if (net_eq(sock_net(sk2), net) &&
sk2 != sk &&
sk2->sk_family == sk->sk_family &&
ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&
(udp_sk(sk2)->udp_port_hash == udp_sk(sk)->udp_port_hash) &&
(sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) &&
inet_rcv_saddr_equal(sk, sk2, false)) {
bpf: Introduce BPF_PROG_TYPE_SK_REUSEPORT This patch adds a BPF_PROG_TYPE_SK_REUSEPORT which can select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY. Like other non SK_FILTER/CGROUP_SKB program, it requires CAP_SYS_ADMIN. BPF_PROG_TYPE_SK_REUSEPORT introduces "struct sk_reuseport_kern" to store the bpf context instead of using the skb->cb[48]. At the SO_REUSEPORT sk lookup time, it is in the middle of transiting from a lower layer (ipv4/ipv6) to a upper layer (udp/tcp). At this point, it is not always clear where the bpf context can be appended in the skb->cb[48] to avoid saving-and-restoring cb[]. Even putting aside the difference between ipv4-vs-ipv6 and udp-vs-tcp. It is not clear if the lower layer is only ipv4 and ipv6 in the future and will it not touch the cb[] again before transiting to the upper layer. For example, in udp_gro_receive(), it uses the 48 byte NAPI_GRO_CB instead of IP[6]CB and it may still modify the cb[] after calling the udp[46]_lib_lookup_skb(). Because of the above reason, if sk->cb is used for the bpf ctx, saving-and-restoring is needed and likely the whole 48 bytes cb[] has to be saved and restored. Instead of saving, setting and restoring the cb[], this patch opts to create a new "struct sk_reuseport_kern" and setting the needed values in there. The new BPF_PROG_TYPE_SK_REUSEPORT and "struct sk_reuseport_(kern|md)" will serve all ipv4/ipv6 + udp/tcp combinations. There is no protocol specific usage at this point and it is also inline with the current sock_reuseport.c implementation (i.e. no protocol specific requirement). In "struct sk_reuseport_md", this patch exposes data/data_end/len with semantic similar to other existing usages. Together with "bpf_skb_load_bytes()" and "bpf_skb_load_bytes_relative()", the bpf prog can peek anywhere in the skb. The "bind_inany" tells the bpf prog that the reuseport group is bind-ed to a local INANY address which cannot be learned from skb. The new "bind_inany" is added to "struct sock_reuseport" which will be used when running the new "BPF_PROG_TYPE_SK_REUSEPORT" bpf prog in order to avoid repeating the "bind INANY" test on "sk_v6_rcv_saddr/sk->sk_rcv_saddr" every time a bpf prog is run. It can only be properly initialized when a "sk->sk_reuseport" enabled sk is adding to a hashtable (i.e. during "reuseport_alloc()" and "reuseport_add_sock()"). The new "sk_select_reuseport()" is the main helper that the bpf prog will use to select a SO_REUSEPORT sk. It is the only function that can use the new BPF_MAP_TYPE_REUSEPORT_ARRAY. As mentioned in the earlier patch, the validity of a selected sk is checked in run time in "sk_select_reuseport()". Doing the check in verification time is difficult and inflexible (consider the map-in-map use case). The runtime check is to compare the selected sk's reuseport_id with the reuseport_id that we want. This helper will return -EXXX if the selected sk cannot serve the incoming request (e.g. reuseport_id not match). The bpf prog can decide if it wants to do SK_DROP as its discretion. When the bpf prog returns SK_PASS, the kernel will check if a valid sk has been selected (i.e. "reuse_kern->selected_sk != NULL"). If it does , it will use the selected sk. If not, the kernel will select one from "reuse->socks[]" (as before this patch). The SK_DROP and SK_PASS handling logic will be in the next patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-08-08 16:01:25 +08:00
return reuseport_add_sock(sk, sk2,
inet_rcv_saddr_any(sk));
}
}
bpf: Introduce BPF_PROG_TYPE_SK_REUSEPORT This patch adds a BPF_PROG_TYPE_SK_REUSEPORT which can select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY. Like other non SK_FILTER/CGROUP_SKB program, it requires CAP_SYS_ADMIN. BPF_PROG_TYPE_SK_REUSEPORT introduces "struct sk_reuseport_kern" to store the bpf context instead of using the skb->cb[48]. At the SO_REUSEPORT sk lookup time, it is in the middle of transiting from a lower layer (ipv4/ipv6) to a upper layer (udp/tcp). At this point, it is not always clear where the bpf context can be appended in the skb->cb[48] to avoid saving-and-restoring cb[]. Even putting aside the difference between ipv4-vs-ipv6 and udp-vs-tcp. It is not clear if the lower layer is only ipv4 and ipv6 in the future and will it not touch the cb[] again before transiting to the upper layer. For example, in udp_gro_receive(), it uses the 48 byte NAPI_GRO_CB instead of IP[6]CB and it may still modify the cb[] after calling the udp[46]_lib_lookup_skb(). Because of the above reason, if sk->cb is used for the bpf ctx, saving-and-restoring is needed and likely the whole 48 bytes cb[] has to be saved and restored. Instead of saving, setting and restoring the cb[], this patch opts to create a new "struct sk_reuseport_kern" and setting the needed values in there. The new BPF_PROG_TYPE_SK_REUSEPORT and "struct sk_reuseport_(kern|md)" will serve all ipv4/ipv6 + udp/tcp combinations. There is no protocol specific usage at this point and it is also inline with the current sock_reuseport.c implementation (i.e. no protocol specific requirement). In "struct sk_reuseport_md", this patch exposes data/data_end/len with semantic similar to other existing usages. Together with "bpf_skb_load_bytes()" and "bpf_skb_load_bytes_relative()", the bpf prog can peek anywhere in the skb. The "bind_inany" tells the bpf prog that the reuseport group is bind-ed to a local INANY address which cannot be learned from skb. The new "bind_inany" is added to "struct sock_reuseport" which will be used when running the new "BPF_PROG_TYPE_SK_REUSEPORT" bpf prog in order to avoid repeating the "bind INANY" test on "sk_v6_rcv_saddr/sk->sk_rcv_saddr" every time a bpf prog is run. It can only be properly initialized when a "sk->sk_reuseport" enabled sk is adding to a hashtable (i.e. during "reuseport_alloc()" and "reuseport_add_sock()"). The new "sk_select_reuseport()" is the main helper that the bpf prog will use to select a SO_REUSEPORT sk. It is the only function that can use the new BPF_MAP_TYPE_REUSEPORT_ARRAY. As mentioned in the earlier patch, the validity of a selected sk is checked in run time in "sk_select_reuseport()". Doing the check in verification time is difficult and inflexible (consider the map-in-map use case). The runtime check is to compare the selected sk's reuseport_id with the reuseport_id that we want. This helper will return -EXXX if the selected sk cannot serve the incoming request (e.g. reuseport_id not match). The bpf prog can decide if it wants to do SK_DROP as its discretion. When the bpf prog returns SK_PASS, the kernel will check if a valid sk has been selected (i.e. "reuse_kern->selected_sk != NULL"). If it does , it will use the selected sk. If not, the kernel will select one from "reuse->socks[]" (as before this patch). The SK_DROP and SK_PASS handling logic will be in the next patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-08-08 16:01:25 +08:00
return reuseport_alloc(sk, inet_rcv_saddr_any(sk));
}
/**
* udp_lib_get_port - UDP/-Lite port lookup for IPv4 and IPv6
*
* @sk: socket struct in question
* @snum: port number to look up
* @hash2_nulladdr: AF-dependent hash value in secondary hash chains,
* with NULL address
*/
int udp_lib_get_port(struct sock *sk, unsigned short snum,
unsigned int hash2_nulladdr)
{
struct udp_table *udptable = udp_get_table_prot(sk);
struct udp_hslot *hslot, *hslot2;
struct net *net = sock_net(sk);
int error = -EADDRINUSE;
if (!snum) {
DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);
unsigned short first, last;
int low, high, remaining;
unsigned int rand;
inet: Add IP_LOCAL_PORT_RANGE socket option Users who want to share a single public IP address for outgoing connections between several hosts traditionally reach for SNAT. However, SNAT requires state keeping on the node(s) performing the NAT. A stateless alternative exists, where a single IP address used for egress can be shared between several hosts by partitioning the available ephemeral port range. In such a setup: 1. Each host gets assigned a disjoint range of ephemeral ports. 2. Applications open connections from the host-assigned port range. 3. Return traffic gets routed to the host based on both, the destination IP and the destination port. An application which wants to open an outgoing connection (connect) from a given port range today can choose between two solutions: 1. Manually pick the source port by bind()'ing to it before connect()'ing the socket. This approach has a couple of downsides: a) Search for a free port has to be implemented in the user-space. If the chosen 4-tuple happens to be busy, the application needs to retry from a different local port number. Detecting if 4-tuple is busy can be either easy (TCP) or hard (UDP). In TCP case, the application simply has to check if connect() returned an error (EADDRNOTAVAIL). That is assuming that the local port sharing was enabled (REUSEADDR) by all the sockets. # Assume desired local port range is 60_000-60_511 s = socket(AF_INET, SOCK_STREAM) s.setsockopt(SOL_SOCKET, SO_REUSEADDR, 1) s.bind(("192.0.2.1", 60_000)) s.connect(("1.1.1.1", 53)) # Fails only if 192.0.2.1:60000 -> 1.1.1.1:53 is busy # Application must retry with another local port In case of UDP, the network stack allows binding more than one socket to the same 4-tuple, when local port sharing is enabled (REUSEADDR). Hence detecting the conflict is much harder and involves querying sock_diag and toggling the REUSEADDR flag [1]. b) For TCP, bind()-ing to a port within the ephemeral port range means that no connecting sockets, that is those which leave it to the network stack to find a free local port at connect() time, can use the this port. IOW, the bind hash bucket tb->fastreuse will be 0 or 1, and the port will be skipped during the free port search at connect() time. 2. Isolate the app in a dedicated netns and use the use the per-netns ip_local_port_range sysctl to adjust the ephemeral port range bounds. The per-netns setting affects all sockets, so this approach can be used only if: - there is just one egress IP address, or - the desired egress port range is the same for all egress IP addresses used by the application. For TCP, this approach avoids the downsides of (1). Free port search and 4-tuple conflict detection is done by the network stack: system("sysctl -w net.ipv4.ip_local_port_range='60000 60511'") s = socket(AF_INET, SOCK_STREAM) s.setsockopt(SOL_IP, IP_BIND_ADDRESS_NO_PORT, 1) s.bind(("192.0.2.1", 0)) s.connect(("1.1.1.1", 53)) # Fails if all 4-tuples 192.0.2.1:60000-60511 -> 1.1.1.1:53 are busy For UDP this approach has limited applicability. Setting the IP_BIND_ADDRESS_NO_PORT socket option does not result in local source port being shared with other connected UDP sockets. Hence relying on the network stack to find a free source port, limits the number of outgoing UDP flows from a single IP address down to the number of available ephemeral ports. To put it another way, partitioning the ephemeral port range between hosts using the existing Linux networking API is cumbersome. To address this use case, add a new socket option at the SOL_IP level, named IP_LOCAL_PORT_RANGE. The new option can be used to clamp down the ephemeral port range for each socket individually. The option can be used only to narrow down the per-netns local port range. If the per-socket range lies outside of the per-netns range, the latter takes precedence. UAPI-wise, the low and high range bounds are passed to the kernel as a pair of u16 values in host byte order packed into a u32. This avoids pointer passing. PORT_LO = 40_000 PORT_HI = 40_511 s = socket(AF_INET, SOCK_STREAM) v = struct.pack("I", PORT_HI << 16 | PORT_LO) s.setsockopt(SOL_IP, IP_LOCAL_PORT_RANGE, v) s.bind(("127.0.0.1", 0)) s.getsockname() # Local address between ("127.0.0.1", 40_000) and ("127.0.0.1", 40_511), # if there is a free port. EADDRINUSE otherwise. [1] https://github.com/cloudflare/cloudflare-blog/blob/232b432c1d57/2022-02-connectx/connectx.py#L116 Reviewed-by: Marek Majkowski <marek@cloudflare.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-01-24 21:36:43 +08:00
inet_sk_get_local_port_range(sk, &low, &high);
remaining = (high - low) + 1;
rand = get_random_u32();
first = reciprocal_scale(rand, remaining) + low;
/*
* force rand to be an odd multiple of UDP_HTABLE_SIZE
*/
rand = (rand | 1) * (udptable->mask + 1);
last = first + udptable->mask + 1;
do {
hslot = udp_hashslot(udptable, net, first);
bitmap_zero(bitmap, PORTS_PER_CHAIN);
spin_lock_bh(&hslot->lock);
udp_lib_lport_inuse(net, snum, hslot, bitmap, sk,
udptable->log);
snum = first;
/*
* Iterate on all possible values of snum for this hash.
* Using steps of an odd multiple of UDP_HTABLE_SIZE
* give us randomization and full range coverage.
*/
do {
if (low <= snum && snum <= high &&
!test_bit(snum >> udptable->log, bitmap) &&
!inet_is_local_reserved_port(net, snum))
goto found;
snum += rand;
} while (snum != first);
spin_unlock_bh(&hslot->lock);
cond_resched();
} while (++first != last);
goto fail;
} else {
hslot = udp_hashslot(udptable, net, snum);
spin_lock_bh(&hslot->lock);
if (hslot->count > 10) {
int exist;
unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum;
slot2 &= udptable->mask;
hash2_nulladdr &= udptable->mask;
hslot2 = udp_hashslot2(udptable, slot2);
if (hslot->count < hslot2->count)
goto scan_primary_hash;
exist = udp_lib_lport_inuse2(net, snum, hslot2, sk);
if (!exist && (hash2_nulladdr != slot2)) {
hslot2 = udp_hashslot2(udptable, hash2_nulladdr);
exist = udp_lib_lport_inuse2(net, snum, hslot2,
sk);
}
if (exist)
goto fail_unlock;
else
goto found;
}
scan_primary_hash:
if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, 0))
goto fail_unlock;
}
found:
inet_sk(sk)->inet_num = snum;
udp_sk(sk)->udp_port_hash = snum;
udp_sk(sk)->udp_portaddr_hash ^= snum;
if (sk_unhashed(sk)) {
if (sk->sk_reuseport &&
udp_reuseport_add_sock(sk, hslot)) {
inet_sk(sk)->inet_num = 0;
udp_sk(sk)->udp_port_hash = 0;
udp_sk(sk)->udp_portaddr_hash ^= snum;
goto fail_unlock;
}
sk_add_node_rcu(sk, &hslot->head);
hslot->count++;
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
spin_lock(&hslot2->lock);
soreuseport: fix ordering for mixed v4/v6 sockets With the SO_REUSEPORT socket option, it is possible to create sockets in the AF_INET and AF_INET6 domains which are bound to the same IPv4 address. This is only possible with SO_REUSEPORT and when not using IPV6_V6ONLY on the AF_INET6 sockets. Prior to the commits referenced below, an incoming IPv4 packet would always be routed to a socket of type AF_INET when this mixed-mode was used. After those changes, the same packet would be routed to the most recently bound socket (if this happened to be an AF_INET6 socket, it would have an IPv4 mapped IPv6 address). The change in behavior occurred because the recent SO_REUSEPORT optimizations short-circuit the socket scoring logic as soon as they find a match. They did not take into account the scoring logic that favors AF_INET sockets over AF_INET6 sockets in the event of a tie. To fix this problem, this patch changes the insertion order of AF_INET and AF_INET6 addresses in the TCP and UDP socket lists when the sockets have SO_REUSEPORT set. AF_INET sockets will be inserted at the head of the list and AF_INET6 sockets with SO_REUSEPORT set will always be inserted at the tail of the list. This will force AF_INET sockets to always be considered first. Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection") Fixes: 125e80b88687 ("soreuseport: fast reuseport TCP socket selection") Reported-by: Maciej Żenczykowski <maze@google.com> Signed-off-by: Craig Gallek <kraig@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-13 01:11:25 +08:00
if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
sk->sk_family == AF_INET6)
hlist_add_tail_rcu(&udp_sk(sk)->udp_portaddr_node,
&hslot2->head);
soreuseport: fix ordering for mixed v4/v6 sockets With the SO_REUSEPORT socket option, it is possible to create sockets in the AF_INET and AF_INET6 domains which are bound to the same IPv4 address. This is only possible with SO_REUSEPORT and when not using IPV6_V6ONLY on the AF_INET6 sockets. Prior to the commits referenced below, an incoming IPv4 packet would always be routed to a socket of type AF_INET when this mixed-mode was used. After those changes, the same packet would be routed to the most recently bound socket (if this happened to be an AF_INET6 socket, it would have an IPv4 mapped IPv6 address). The change in behavior occurred because the recent SO_REUSEPORT optimizations short-circuit the socket scoring logic as soon as they find a match. They did not take into account the scoring logic that favors AF_INET sockets over AF_INET6 sockets in the event of a tie. To fix this problem, this patch changes the insertion order of AF_INET and AF_INET6 addresses in the TCP and UDP socket lists when the sockets have SO_REUSEPORT set. AF_INET sockets will be inserted at the head of the list and AF_INET6 sockets with SO_REUSEPORT set will always be inserted at the tail of the list. This will force AF_INET sockets to always be considered first. Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection") Fixes: 125e80b88687 ("soreuseport: fast reuseport TCP socket selection") Reported-by: Maciej Żenczykowski <maze@google.com> Signed-off-by: Craig Gallek <kraig@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-13 01:11:25 +08:00
else
hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
&hslot2->head);
hslot2->count++;
spin_unlock(&hslot2->lock);
}
sock_set_flag(sk, SOCK_RCU_FREE);
error = 0;
fail_unlock:
spin_unlock_bh(&hslot->lock);
fail:
return error;
}
EXPORT_SYMBOL(udp_lib_get_port);
int udp_v4_get_port(struct sock *sk, unsigned short snum)
{
unsigned int hash2_nulladdr =
ipv4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum);
unsigned int hash2_partial =
ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0);
/* precompute partial secondary hash */
udp_sk(sk)->udp_portaddr_hash = hash2_partial;
return udp_lib_get_port(sk, snum, hash2_nulladdr);
}
udp reuseport: fix packet of same flow hashed to different socket There is a corner case in which udp packets belonging to a same flow are hashed to different socket when hslot->count changes from 10 to 11: 1) When hslot->count <= 10, __udp_lib_lookup() searches udp_table->hash, and always passes 'daddr' to udp_ehashfn(). 2) When hslot->count > 10, __udp_lib_lookup() searches udp_table->hash2, but may pass 'INADDR_ANY' to udp_ehashfn() if the sockets are bound to INADDR_ANY instead of some specific addr. That means when hslot->count changes from 10 to 11, the hash calculated by udp_ehashfn() is also changed, and the udp packets belonging to a same flow will be hashed to different socket. This is easily reproduced: 1) Create 10 udp sockets and bind all of them to 0.0.0.0:40000. 2) From the same host send udp packets to 127.0.0.1:40000, record the socket index which receives the packets. 3) Create 1 more udp socket and bind it to 0.0.0.0:44096. The number 44096 is 40000 + UDP_HASH_SIZE(4096), this makes the new socket put into the same hslot as the aformentioned 10 sockets, and makes the hslot->count change from 10 to 11. 4) From the same host send udp packets to 127.0.0.1:40000, and the socket index which receives the packets will be different from the one received in step 2. This should not happen as the socket bound to 0.0.0.0:44096 should not change the behavior of the sockets bound to 0.0.0.0:40000. It's the same case for IPv6, and this patch also fixes that. Signed-off-by: Su, Xuemin <suxm@chinanetcenter.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-13 11:02:50 +08:00
static int compute_score(struct sock *sk, struct net *net,
__be32 saddr, __be16 sport,
__be32 daddr, unsigned short hnum,
int dif, int sdif)
{
int score;
struct inet_sock *inet;
net: ensure unbound datagram socket to be chosen when not in a VRF Ensure an unbound datagram skt is chosen when not in a VRF. The check for a device match in compute_score() for UDP must be performed when there is no device match. For this, a failure is returned when there is no device match. This ensures that bound sockets are never selected, even if there is no unbound socket. Allow IPv6 packets to be sent over a datagram skt bound to a VRF. These packets are currently blocked, as flowi6_oif was set to that of the master vrf device, and the ipi6_ifindex is that of the slave device. Allow these packets to be sent by checking the device with ipi6_ifindex has the same L3 scope as that of the bound device of the skt, which is the master vrf device. Note that this check always succeeds if the skt is unbound. Even though the right datagram skt is now selected by compute_score(), a different skt is being returned that is bound to the wrong vrf. The difference between these and stream sockets is the handling of the skt option for SO_REUSEPORT. While the handling when adding a skt for reuse correctly checks that the bound device of the skt is a match, the skts in the hashslot are already incorrect. So for the same hash, a skt for the wrong vrf may be selected for the required port. The root cause is that the skt is immediately placed into a slot when it is created, but when the skt is then bound using SO_BINDTODEVICE, it remains in the same slot. The solution is to move the skt to the correct slot by forcing a rehash. Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-07 23:36:04 +08:00
bool dev_match;
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
ipv6_only_sock(sk))
return -1;
if (sk->sk_rcv_saddr != daddr)
return -1;
score = (sk->sk_family == PF_INET) ? 2 : 1;
inet = inet_sk(sk);
if (inet->inet_daddr) {
if (inet->inet_daddr != saddr)
return -1;
score += 4;
}
if (inet->inet_dport) {
if (inet->inet_dport != sport)
return -1;
score += 4;
}
net: ensure unbound datagram socket to be chosen when not in a VRF Ensure an unbound datagram skt is chosen when not in a VRF. The check for a device match in compute_score() for UDP must be performed when there is no device match. For this, a failure is returned when there is no device match. This ensures that bound sockets are never selected, even if there is no unbound socket. Allow IPv6 packets to be sent over a datagram skt bound to a VRF. These packets are currently blocked, as flowi6_oif was set to that of the master vrf device, and the ipi6_ifindex is that of the slave device. Allow these packets to be sent by checking the device with ipi6_ifindex has the same L3 scope as that of the bound device of the skt, which is the master vrf device. Note that this check always succeeds if the skt is unbound. Even though the right datagram skt is now selected by compute_score(), a different skt is being returned that is bound to the wrong vrf. The difference between these and stream sockets is the handling of the skt option for SO_REUSEPORT. While the handling when adding a skt for reuse correctly checks that the bound device of the skt is a match, the skts in the hashslot are already incorrect. So for the same hash, a skt for the wrong vrf may be selected for the required port. The root cause is that the skt is immediately placed into a slot when it is created, but when the skt is then bound using SO_BINDTODEVICE, it remains in the same slot. The solution is to move the skt to the correct slot by forcing a rehash. Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-07 23:36:04 +08:00
dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
dif, sdif);
if (!dev_match)
return -1;
if (sk->sk_bound_dev_if)
score += 4;
net: annotate accesses to sk->sk_incoming_cpu This socket field can be read and written by concurrent cpus. Use READ_ONCE() and WRITE_ONCE() annotations to document this, and avoid some compiler 'optimizations'. KCSAN reported : BUG: KCSAN: data-race in tcp_v4_rcv / tcp_v4_rcv write to 0xffff88812220763c of 4 bytes by interrupt on cpu 0: sk_incoming_cpu_update include/net/sock.h:953 [inline] tcp_v4_rcv+0x1b3c/0x1bb0 net/ipv4/tcp_ipv4.c:1934 ip_protocol_deliver_rcu+0x4d/0x420 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5010 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5124 process_backlog+0x1d3/0x420 net/core/dev.c:5955 napi_poll net/core/dev.c:6392 [inline] net_rx_action+0x3ae/0xa90 net/core/dev.c:6460 __do_softirq+0x115/0x33f kernel/softirq.c:292 do_softirq_own_stack+0x2a/0x40 arch/x86/entry/entry_64.S:1082 do_softirq.part.0+0x6b/0x80 kernel/softirq.c:337 do_softirq kernel/softirq.c:329 [inline] __local_bh_enable_ip+0x76/0x80 kernel/softirq.c:189 read to 0xffff88812220763c of 4 bytes by interrupt on cpu 1: sk_incoming_cpu_update include/net/sock.h:952 [inline] tcp_v4_rcv+0x181a/0x1bb0 net/ipv4/tcp_ipv4.c:1934 ip_protocol_deliver_rcu+0x4d/0x420 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5010 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5124 process_backlog+0x1d3/0x420 net/core/dev.c:5955 napi_poll net/core/dev.c:6392 [inline] net_rx_action+0x3ae/0xa90 net/core/dev.c:6460 __do_softirq+0x115/0x33f kernel/softirq.c:292 run_ksoftirqd+0x46/0x60 kernel/softirq.c:603 smpboot_thread_fn+0x37d/0x4a0 kernel/smpboot.c:165 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 16 Comm: ksoftirqd/1 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-10-31 04:00:04 +08:00
if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
score++;
return score;
}
static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
const __u16 lport, const __be32 faddr,
const __be16 fport)
{
static u32 udp_ehash_secret __read_mostly;
net_get_random_once(&udp_ehash_secret, sizeof(udp_ehash_secret));
return __inet_ehashfn(laddr, lport, faddr, fport,
udp_ehash_secret + net_hash_mix(net));
}
static struct sock *lookup_reuseport(struct net *net, struct sock *sk,
struct sk_buff *skb,
__be32 saddr, __be16 sport,
__be32 daddr, unsigned short hnum)
{
struct sock *reuse_sk = NULL;
u32 hash;
if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
hash = udp_ehashfn(net, daddr, hnum, saddr, sport);
reuse_sk = reuseport_select_sock(sk, hash, skb,
sizeof(struct udphdr));
}
return reuse_sk;
}
udp reuseport: fix packet of same flow hashed to different socket There is a corner case in which udp packets belonging to a same flow are hashed to different socket when hslot->count changes from 10 to 11: 1) When hslot->count <= 10, __udp_lib_lookup() searches udp_table->hash, and always passes 'daddr' to udp_ehashfn(). 2) When hslot->count > 10, __udp_lib_lookup() searches udp_table->hash2, but may pass 'INADDR_ANY' to udp_ehashfn() if the sockets are bound to INADDR_ANY instead of some specific addr. That means when hslot->count changes from 10 to 11, the hash calculated by udp_ehashfn() is also changed, and the udp packets belonging to a same flow will be hashed to different socket. This is easily reproduced: 1) Create 10 udp sockets and bind all of them to 0.0.0.0:40000. 2) From the same host send udp packets to 127.0.0.1:40000, record the socket index which receives the packets. 3) Create 1 more udp socket and bind it to 0.0.0.0:44096. The number 44096 is 40000 + UDP_HASH_SIZE(4096), this makes the new socket put into the same hslot as the aformentioned 10 sockets, and makes the hslot->count change from 10 to 11. 4) From the same host send udp packets to 127.0.0.1:40000, and the socket index which receives the packets will be different from the one received in step 2. This should not happen as the socket bound to 0.0.0.0:44096 should not change the behavior of the sockets bound to 0.0.0.0:40000. It's the same case for IPv6, and this patch also fixes that. Signed-off-by: Su, Xuemin <suxm@chinanetcenter.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-13 11:02:50 +08:00
/* called with rcu_read_lock() */
static struct sock *udp4_lib_lookup2(struct net *net,
__be32 saddr, __be16 sport,
__be32 daddr, unsigned int hnum,
int dif, int sdif,
struct udp_hslot *hslot2,
struct sk_buff *skb)
{
struct sock *sk, *result;
int score, badness;
result = NULL;
badness = 0;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
udp reuseport: fix packet of same flow hashed to different socket There is a corner case in which udp packets belonging to a same flow are hashed to different socket when hslot->count changes from 10 to 11: 1) When hslot->count <= 10, __udp_lib_lookup() searches udp_table->hash, and always passes 'daddr' to udp_ehashfn(). 2) When hslot->count > 10, __udp_lib_lookup() searches udp_table->hash2, but may pass 'INADDR_ANY' to udp_ehashfn() if the sockets are bound to INADDR_ANY instead of some specific addr. That means when hslot->count changes from 10 to 11, the hash calculated by udp_ehashfn() is also changed, and the udp packets belonging to a same flow will be hashed to different socket. This is easily reproduced: 1) Create 10 udp sockets and bind all of them to 0.0.0.0:40000. 2) From the same host send udp packets to 127.0.0.1:40000, record the socket index which receives the packets. 3) Create 1 more udp socket and bind it to 0.0.0.0:44096. The number 44096 is 40000 + UDP_HASH_SIZE(4096), this makes the new socket put into the same hslot as the aformentioned 10 sockets, and makes the hslot->count change from 10 to 11. 4) From the same host send udp packets to 127.0.0.1:40000, and the socket index which receives the packets will be different from the one received in step 2. This should not happen as the socket bound to 0.0.0.0:44096 should not change the behavior of the sockets bound to 0.0.0.0:40000. It's the same case for IPv6, and this patch also fixes that. Signed-off-by: Su, Xuemin <suxm@chinanetcenter.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-13 11:02:50 +08:00
score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif, sdif);
if (score > badness) {
result = lookup_reuseport(net, sk, skb,
saddr, sport, daddr, hnum);
/* Fall back to scoring if group has connections */
udp: Update reuse->has_conns under reuseport_lock. When we call connect() for a UDP socket in a reuseport group, we have to update sk->sk_reuseport_cb->has_conns to 1. Otherwise, the kernel could select a unconnected socket wrongly for packets sent to the connected socket. However, the current way to set has_conns is illegal and possible to trigger that problem. reuseport_has_conns() changes has_conns under rcu_read_lock(), which upgrades the RCU reader to the updater. Then, it must do the update under the updater's lock, reuseport_lock, but it doesn't for now. For this reason, there is a race below where we fail to set has_conns resulting in the wrong socket selection. To avoid the race, let's split the reader and updater with proper locking. cpu1 cpu2 +----+ +----+ __ip[46]_datagram_connect() reuseport_grow() . . |- reuseport_has_conns(sk, true) |- more_reuse = __reuseport_alloc(more_socks_size) | . | | |- rcu_read_lock() | |- reuse = rcu_dereference(sk->sk_reuseport_cb) | | | | | /* reuse->has_conns == 0 here */ | | |- more_reuse->has_conns = reuse->has_conns | |- reuse->has_conns = 1 | /* more_reuse->has_conns SHOULD BE 1 HERE */ | | | | | |- rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, | | | more_reuse) | `- rcu_read_unlock() `- kfree_rcu(reuse, rcu) | |- sk->sk_state = TCP_ESTABLISHED Note the likely(reuse) in reuseport_has_conns_set() is always true, but we put the test there for ease of review. [0] For the record, usually, sk_reuseport_cb is changed under lock_sock(). The only exception is reuseport_grow() & TCP reqsk migration case. 1) shutdown() TCP listener, which is moved into the latter part of reuse->socks[] to migrate reqsk. 2) New listen() overflows reuse->socks[] and call reuseport_grow(). 3) reuse->max_socks overflows u16 with the new listener. 4) reuseport_grow() pops the old shutdown()ed listener from the array and update its sk->sk_reuseport_cb as NULL without lock_sock(). shutdown()ed TCP sk->sk_reuseport_cb can be changed without lock_sock(), but, reuseport_has_conns_set() is called only for UDP under lock_sock(), so likely(reuse) never be false in reuseport_has_conns_set(). [0]: https://lore.kernel.org/netdev/CANn89iLja=eQHbsM_Ta2sQF0tOGU8vAGrh_izRuuHjuO1ouUag@mail.gmail.com/ Fixes: acdcecc61285 ("udp: correct reuseport selection with connected sockets") Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Link: https://lore.kernel.org/r/20221014182625.89913-1-kuniyu@amazon.com Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-10-15 02:26:25 +08:00
if (result && !reuseport_has_conns(sk))
return result;
result = result ? : sk;
badness = score;
}
}
return result;
}
static struct sock *udp4_lookup_run_bpf(struct net *net,
struct udp_table *udptable,
struct sk_buff *skb,
__be32 saddr, __be16 sport,
__be32 daddr, u16 hnum, const int dif)
{
struct sock *sk, *reuse_sk;
bool no_reuseport;
if (udptable != net->ipv4.udp_table)
return NULL; /* only UDP is supported */
no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport,
daddr, hnum, dif, &sk);
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
if (reuse_sk)
sk = reuse_sk;
return sk;
}
/* UDP is nearly always wildcards out the wazoo, it makes no sense to try
* harder than this. -DaveM
*/
struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
__be16 sport, __be32 daddr, __be16 dport, int dif,
int sdif, struct udp_table *udptable, struct sk_buff *skb)
{
unsigned short hnum = ntohs(dport);
unsigned int hash2, slot2;
struct udp_hslot *hslot2;
struct sock *result, *sk;
hash2 = ipv4_portaddr_hash(net, daddr, hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
/* Lookup connected or non-wildcard socket */
result = udp4_lib_lookup2(net, saddr, sport,
daddr, hnum, dif, sdif,
hslot2, skb);
if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED)
goto done;
/* Lookup redirect from BPF */
if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
sk = udp4_lookup_run_bpf(net, udptable, skb,
saddr, sport, daddr, hnum, dif);
if (sk) {
result = sk;
goto done;
}
}
/* Got non-wildcard socket or error on first lookup */
if (result)
goto done;
/* Lookup wildcard sockets */
hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
result = udp4_lib_lookup2(net, saddr, sport,
htonl(INADDR_ANY), hnum, dif, sdif,
hslot2, skb);
done:
if (IS_ERR(result))
return NULL;
return result;
}
EXPORT_SYMBOL_GPL(__udp4_lib_lookup);
static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport,
struct udp_table *udptable)
{
const struct iphdr *iph = ip_hdr(skb);
udp: Resolve NULL pointer dereference over flow-based vxlan device While testing an OpenStack configuration using VXLANs I saw the following call trace: RIP: 0010:[<ffffffff815fad49>] udp4_lib_lookup_skb+0x49/0x80 RSP: 0018:ffff88103867bc50 EFLAGS: 00010286 RAX: ffff88103269bf00 RBX: ffff88103269bf00 RCX: 00000000ffffffff RDX: 0000000000004300 RSI: 0000000000000000 RDI: ffff880f2932e780 RBP: ffff88103867bc60 R08: 0000000000000000 R09: 000000009001a8c0 R10: 0000000000004400 R11: ffffffff81333a58 R12: ffff880f2932e794 R13: 0000000000000014 R14: 0000000000000014 R15: ffffe8efbfd89ca0 FS: 0000000000000000(0000) GS:ffff88103fd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000488 CR3: 0000000001c06000 CR4: 00000000001426e0 Stack: ffffffff81576515 ffffffff815733c0 ffff88103867bc98 ffffffff815fcc17 ffff88103269bf00 ffffe8efbfd89ca0 0000000000000014 0000000000000080 ffffe8efbfd89ca0 ffff88103867bcc8 ffffffff815fcf8b ffff880f2932e794 Call Trace: [<ffffffff81576515>] ? skb_checksum+0x35/0x50 [<ffffffff815733c0>] ? skb_push+0x40/0x40 [<ffffffff815fcc17>] udp_gro_receive+0x57/0x130 [<ffffffff815fcf8b>] udp4_gro_receive+0x10b/0x2c0 [<ffffffff81605863>] inet_gro_receive+0x1d3/0x270 [<ffffffff81589e59>] dev_gro_receive+0x269/0x3b0 [<ffffffff8158a1b8>] napi_gro_receive+0x38/0x120 [<ffffffffa0871297>] gro_cell_poll+0x57/0x80 [vxlan] [<ffffffff815899d0>] net_rx_action+0x160/0x380 [<ffffffff816965c7>] __do_softirq+0xd7/0x2c5 [<ffffffff8107d969>] run_ksoftirqd+0x29/0x50 [<ffffffff8109a50f>] smpboot_thread_fn+0x10f/0x160 [<ffffffff8109a400>] ? sort_range+0x30/0x30 [<ffffffff81096da8>] kthread+0xd8/0xf0 [<ffffffff81693c82>] ret_from_fork+0x22/0x40 [<ffffffff81096cd0>] ? kthread_park+0x60/0x60 The following trace is seen when receiving a DHCP request over a flow-based VXLAN tunnel. I believe this is caused by the metadata dst having a NULL dev value and as a result dev_net(dev) is causing a NULL pointer dereference. To resolve this I am replacing the check for skb_dst(skb)->dev with just skb->dev. This makes sense as the callers of this function are usually in the receive path and as such skb->dev should always be populated. In addition other functions in the area where these are called are already using dev_net(skb->dev) to determine the namespace the UDP packet belongs in. Fixes: 63058308cd55 ("udp: Add udp6_lib_lookup_skb and udp4_lib_lookup_skb") Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-13 07:23:44 +08:00
return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
udp: ipv4: fix an use after free in __udp4_lib_rcv() Dave Jones reported a use after free in UDP stack : [ 5059.434216] ========================= [ 5059.434314] [ BUG: held lock freed! ] [ 5059.434420] 3.13.0-rc3+ #9 Not tainted [ 5059.434520] ------------------------- [ 5059.434620] named/863 is freeing memory ffff88005e960000-ffff88005e96061f, with a lock still held there! [ 5059.434815] (slock-AF_INET){+.-...}, at: [<ffffffff8149bd21>] udp_queue_rcv_skb+0xd1/0x4b0 [ 5059.435012] 3 locks held by named/863: [ 5059.435086] #0: (rcu_read_lock){.+.+..}, at: [<ffffffff8143054d>] __netif_receive_skb_core+0x11d/0x940 [ 5059.435295] #1: (rcu_read_lock){.+.+..}, at: [<ffffffff81467a5e>] ip_local_deliver_finish+0x3e/0x410 [ 5059.435500] #2: (slock-AF_INET){+.-...}, at: [<ffffffff8149bd21>] udp_queue_rcv_skb+0xd1/0x4b0 [ 5059.435734] stack backtrace: [ 5059.435858] CPU: 0 PID: 863 Comm: named Not tainted 3.13.0-rc3+ #9 [loadavg: 0.21 0.06 0.06 1/115 1365] [ 5059.436052] Hardware name: /D510MO, BIOS MOPNV10J.86A.0175.2010.0308.0620 03/08/2010 [ 5059.436223] 0000000000000002 ffff88007e203ad8 ffffffff8153a372 ffff8800677130e0 [ 5059.436390] ffff88007e203b10 ffffffff8108cafa ffff88005e960000 ffff88007b00cfc0 [ 5059.436554] ffffea00017a5800 ffffffff8141c490 0000000000000246 ffff88007e203b48 [ 5059.436718] Call Trace: [ 5059.436769] <IRQ> [<ffffffff8153a372>] dump_stack+0x4d/0x66 [ 5059.436904] [<ffffffff8108cafa>] debug_check_no_locks_freed+0x15a/0x160 [ 5059.437037] [<ffffffff8141c490>] ? __sk_free+0x110/0x230 [ 5059.437147] [<ffffffff8112da2a>] kmem_cache_free+0x6a/0x150 [ 5059.437260] [<ffffffff8141c490>] __sk_free+0x110/0x230 [ 5059.437364] [<ffffffff8141c5c9>] sk_free+0x19/0x20 [ 5059.437463] [<ffffffff8141cb25>] sock_edemux+0x25/0x40 [ 5059.437567] [<ffffffff8141c181>] sock_queue_rcv_skb+0x81/0x280 [ 5059.437685] [<ffffffff8149bd21>] ? udp_queue_rcv_skb+0xd1/0x4b0 [ 5059.437805] [<ffffffff81499c82>] __udp_queue_rcv_skb+0x42/0x240 [ 5059.437925] [<ffffffff81541d25>] ? _raw_spin_lock+0x65/0x70 [ 5059.438038] [<ffffffff8149bebb>] udp_queue_rcv_skb+0x26b/0x4b0 [ 5059.438155] [<ffffffff8149c712>] __udp4_lib_rcv+0x152/0xb00 [ 5059.438269] [<ffffffff8149d7f5>] udp_rcv+0x15/0x20 [ 5059.438367] [<ffffffff81467b2f>] ip_local_deliver_finish+0x10f/0x410 [ 5059.438492] [<ffffffff81467a5e>] ? ip_local_deliver_finish+0x3e/0x410 [ 5059.438621] [<ffffffff81468653>] ip_local_deliver+0x43/0x80 [ 5059.438733] [<ffffffff81467f70>] ip_rcv_finish+0x140/0x5a0 [ 5059.438843] [<ffffffff81468926>] ip_rcv+0x296/0x3f0 [ 5059.438945] [<ffffffff81430b72>] __netif_receive_skb_core+0x742/0x940 [ 5059.439074] [<ffffffff8143054d>] ? __netif_receive_skb_core+0x11d/0x940 [ 5059.442231] [<ffffffff8108c81d>] ? trace_hardirqs_on+0xd/0x10 [ 5059.442231] [<ffffffff81430d83>] __netif_receive_skb+0x13/0x60 [ 5059.442231] [<ffffffff81431c1e>] netif_receive_skb+0x1e/0x1f0 [ 5059.442231] [<ffffffff814334e0>] napi_gro_receive+0x70/0xa0 [ 5059.442231] [<ffffffffa01de426>] rtl8169_poll+0x166/0x700 [r8169] [ 5059.442231] [<ffffffff81432bc9>] net_rx_action+0x129/0x1e0 [ 5059.442231] [<ffffffff810478cd>] __do_softirq+0xed/0x240 [ 5059.442231] [<ffffffff81047e25>] irq_exit+0x125/0x140 [ 5059.442231] [<ffffffff81004241>] do_IRQ+0x51/0xc0 [ 5059.442231] [<ffffffff81542bef>] common_interrupt+0x6f/0x6f We need to keep a reference on the socket, by using skb_steal_sock() at the right place. Note that another patch is needed to fix a race in udp_sk_rx_dst_set(), as we hold no lock protecting the dst. Fixes: 421b3885bf6d ("udp: ipv4: Add udp early demux") Reported-by: Dave Jones <davej@redhat.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Shawn Bohrer <sbohrer@rgmadvisors.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-11 10:07:23 +08:00
iph->daddr, dport, inet_iif(skb),
inet_sdif(skb), udptable, skb);
}
struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport)
{
const struct iphdr *iph = ip_hdr(skb);
struct net *net = dev_net(skb->dev);
return __udp4_lib_lookup(net, iph->saddr, sport,
iph->daddr, dport, inet_iif(skb),
inet_sdif(skb), net->ipv4.udp_table, NULL);
}
/* Must be called under rcu_read_lock().
* Does increment socket refcount.
*/
#if IS_ENABLED(CONFIG_NF_TPROXY_IPV4) || IS_ENABLED(CONFIG_NF_SOCKET_IPV4)
struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
__be32 daddr, __be16 dport, int dif)
{
struct sock *sk;
sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport,
dif, 0, net->ipv4.udp_table, NULL);
if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
return sk;
}
EXPORT_SYMBOL_GPL(udp4_lib_lookup);
#endif
static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
__be16 loc_port, __be32 loc_addr,
__be16 rmt_port, __be32 rmt_addr,
int dif, int sdif, unsigned short hnum)
{
struct inet_sock *inet = inet_sk(sk);
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
(inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
(inet->inet_dport != rmt_port && inet->inet_dport) ||
(inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) ||
ipv6_only_sock(sk) ||
!udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
return false;
if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif, sdif))
return false;
return true;
}
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
void udp_encap_enable(void)
{
static_branch_inc(&udp_encap_needed_key);
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
}
EXPORT_SYMBOL(udp_encap_enable);
void udp_encap_disable(void)
{
static_branch_dec(&udp_encap_needed_key);
}
EXPORT_SYMBOL(udp_encap_disable);
/* Handler for tunnels with arbitrary destination ports: no socket lookup, go
* through error handlers in encapsulations looking for a match.
*/
static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info)
{
int i;
for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
int (*handler)(struct sk_buff *skb, u32 info);
const struct ip_tunnel_encap_ops *encap;
encap = rcu_dereference(iptun_encaps[i]);
if (!encap)
continue;
handler = encap->err_handler;
if (handler && !handler(skb, info))
return 0;
}
return -ENOENT;
}
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
/* Try to match ICMP errors to UDP tunnels by looking up a socket without
* reversing source and destination port: this will match tunnels that force the
* same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that
* lwtunnels might actually break this assumption by being configured with
* different destination ports on endpoints, in this case we won't be able to
* trace ICMP messages back to them.
*
* If this doesn't match any socket, probe tunnels with arbitrary destination
* ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port
* we've sent packets to won't necessarily match the local destination port.
*
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
* Then ask the tunnel implementation to match the error against a valid
* association.
*
* Return an error if we can't find a match, the socket if we need further
* processing, zero otherwise.
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
*/
static struct sock *__udp4_lib_err_encap(struct net *net,
const struct iphdr *iph,
struct udphdr *uh,
struct udp_table *udptable,
struct sock *sk,
struct sk_buff *skb, u32 info)
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
{
int (*lookup)(struct sock *sk, struct sk_buff *skb);
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
int network_offset, transport_offset;
struct udp_sock *up;
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
network_offset = skb_network_offset(skb);
transport_offset = skb_transport_offset(skb);
/* Network header needs to point to the outer IPv4 header inside ICMP */
skb_reset_network_header(skb);
/* Transport header needs to point to the UDP header */
skb_set_transport_header(skb, iph->ihl << 2);
if (sk) {
up = udp_sk(sk);
lookup = READ_ONCE(up->encap_err_lookup);
if (lookup && lookup(sk, skb))
sk = NULL;
goto out;
}
sk = __udp4_lib_lookup(net, iph->daddr, uh->source,
iph->saddr, uh->dest, skb->dev->ifindex, 0,
udptable, NULL);
if (sk) {
up = udp_sk(sk);
lookup = READ_ONCE(up->encap_err_lookup);
if (!lookup || lookup(sk, skb))
sk = NULL;
}
out:
if (!sk)
sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info));
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
skb_set_transport_header(skb, transport_offset);
skb_set_network_header(skb, network_offset);
return sk;
}
/*
* This routine is called by the ICMP module when it gets some
* sort of error condition. If err < 0 then the socket should
* be closed and the error returned to the user. If err > 0
* it's just the icmp type << 8 | icmp code.
* Header points to the ip header of the error packet. We move
* on past this. Then (as it used to claim before adjustment)
* header points to the first 8 bytes of the udp header. We need
* to find the appropriate port.
*/
int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
{
struct inet_sock *inet;
const struct iphdr *iph = (const struct iphdr *)skb->data;
struct udphdr *uh = (struct udphdr *)(skb->data+(iph->ihl<<2));
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
bool tunnel = false;
struct sock *sk;
int harderr;
int err;
struct net *net = dev_net(skb->dev);
sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
iph->saddr, uh->source, skb->dev->ifindex,
inet_sdif(skb), udptable, NULL);
if (!sk || udp_sk(sk)->encap_type) {
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
/* No socket for error: try tunnels before discarding */
if (static_branch_unlikely(&udp_encap_needed_key)) {
sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb,
info);
if (!sk)
return 0;
} else
sk = ERR_PTR(-ENOENT);
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
if (IS_ERR(sk)) {
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
return PTR_ERR(sk);
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
}
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
tunnel = true;
}
err = 0;
harderr = 0;
inet = inet_sk(sk);
switch (type) {
default:
case ICMP_TIME_EXCEEDED:
err = EHOSTUNREACH;
break;
case ICMP_SOURCE_QUENCH:
goto out;
case ICMP_PARAMETERPROB:
err = EPROTO;
harderr = 1;
break;
case ICMP_DEST_UNREACH:
if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
ipv4_sk_update_pmtu(skb, sk, info);
if (inet->pmtudisc != IP_PMTUDISC_DONT) {
err = EMSGSIZE;
harderr = 1;
break;
}
goto out;
}
err = EHOSTUNREACH;
if (code <= NR_ICMP_UNREACH) {
harderr = icmp_err_convert[code].fatal;
err = icmp_err_convert[code].errno;
}
break;
case ICMP_REDIRECT:
ipv4_sk_redirect(skb, sk);
goto out;
}
/*
* RFC1122: OK. Passes ICMP errors back to application, as per
* 4.1.3.3.
*/
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
if (tunnel) {
/* ...not for tunnels though: we don't have a sending socket */
if (udp_sk(sk)->encap_err_rcv)
udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest, info,
(u8 *)(uh+1));
udp: Handle ICMP errors for tunnels with same destination port on both endpoints For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-11-08 19:19:14 +08:00
goto out;
}
if (!inet->recverr) {
if (!harderr || sk->sk_state != TCP_ESTABLISHED)
goto out;
} else
ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1));
sk->sk_err = err;
sk_error_report(sk);
out:
return 0;
}
int udp_err(struct sk_buff *skb, u32 info)
{
return __udp4_lib_err(skb, info, dev_net(skb->dev)->ipv4.udp_table);
}
/*
* Throw away all pending data and cancel the corking. Socket is locked.
*/
void udp_flush_pending_frames(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
if (up->pending) {
up->len = 0;
up->pending = 0;
ip_flush_pending_frames(sk);
}
}
EXPORT_SYMBOL(udp_flush_pending_frames);
/**
* udp4_hwcsum - handle outgoing HW checksumming
* @skb: sk_buff containing the filled-in UDP header
* (checksum field must be zeroed out)
* @src: source IP address
* @dst: destination IP address
*/
void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
{
struct udphdr *uh = udp_hdr(skb);
int offset = skb_transport_offset(skb);
int len = skb->len - offset;
int hlen = len;
__wsum csum = 0;
if (!skb_has_frag_list(skb)) {
/*
* Only one fragment on the socket.
*/
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct udphdr, check);
uh->check = ~csum_tcpudp_magic(src, dst, len,
IPPROTO_UDP, 0);
} else {
struct sk_buff *frags;
/*
* HW-checksum won't work as there are two or more
* fragments on the socket so that all csums of sk_buffs
* should be together
*/
skb_walk_frags(skb, frags) {
csum = csum_add(csum, frags->csum);
hlen -= frags->len;
}
csum = skb_checksum(skb, offset, hlen, csum);
skb->ip_summed = CHECKSUM_NONE;
uh->check = csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, csum);
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
}
}
EXPORT_SYMBOL_GPL(udp4_hwcsum);
/* Function to set UDP checksum for an IPv4 UDP packet. This is intended
* for the simple case like when setting the checksum for a UDP tunnel.
*/
void udp_set_csum(bool nocheck, struct sk_buff *skb,
__be32 saddr, __be32 daddr, int len)
{
struct udphdr *uh = udp_hdr(skb);
if (nocheck) {
uh->check = 0;
} else if (skb_is_gso(skb)) {
uh->check = ~udp_v4_check(len, saddr, daddr, 0);
} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
uh->check = 0;
uh->check = udp_v4_check(len, saddr, daddr, lco_csum(skb));
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
} else {
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct udphdr, check);
uh->check = ~udp_v4_check(len, saddr, daddr, 0);
}
}
EXPORT_SYMBOL(udp_set_csum);
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-27 01:42:17 +08:00
static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
struct inet_cork *cork)
{
struct sock *sk = skb->sk;
struct inet_sock *inet = inet_sk(sk);
struct udphdr *uh;
int err;
int is_udplite = IS_UDPLITE(sk);
int offset = skb_transport_offset(skb);
int len = skb->len - offset;
int datalen = len - sizeof(*uh);
__wsum csum = 0;
/*
* Create a UDP header
*/
uh = udp_hdr(skb);
uh->source = inet->inet_sport;
uh->dest = fl4->fl4_dport;
uh->len = htons(len);
uh->check = 0;
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-27 01:42:17 +08:00
if (cork->gso_size) {
const int hlen = skb_network_header_len(skb) +
sizeof(struct udphdr);
if (hlen + cork->gso_size > cork->fragsize) {
kfree_skb(skb);
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-27 01:42:17 +08:00
return -EINVAL;
}
if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
kfree_skb(skb);
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-27 01:42:17 +08:00
return -EINVAL;
}
if (sk->sk_no_check_tx) {
kfree_skb(skb);
return -EINVAL;
}
if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite ||
dst_xfrm(skb_dst(skb))) {
kfree_skb(skb);
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-27 01:42:17 +08:00
return -EIO;
}
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-27 01:42:17 +08:00
if (datalen > cork->gso_size) {
skb_shinfo(skb)->gso_size = cork->gso_size;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
cork->gso_size);
}
goto csum_partial;
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-27 01:42:17 +08:00
}
if (is_udplite) /* UDP-Lite */
csum = udplite_csum(skb);
else if (sk->sk_no_check_tx) { /* UDP csum off */
skb->ip_summed = CHECKSUM_NONE;
goto send;
} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
csum_partial:
udp4_hwcsum(skb, fl4->saddr, fl4->daddr);
goto send;
} else
csum = udp_csum(skb);
/* add protocol-dependent pseudo-header */
uh->check = csum_tcpudp_magic(fl4->saddr, fl4->daddr, len,
sk->sk_protocol, csum);
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
send:
err = ip_send_skb(sock_net(sk), skb);
if (err) {
if (err == -ENOBUFS && !inet->recverr) {
UDP_INC_STATS(sock_net(sk),
UDP_MIB_SNDBUFERRORS, is_udplite);
err = 0;
}
} else
UDP_INC_STATS(sock_net(sk),
UDP_MIB_OUTDATAGRAMS, is_udplite);
return err;
}
/*
* Push out all pending data as one UDP datagram. Socket is locked.
*/
ipv6: call udp_push_pending_frames when uncorking a socket with AF_INET pending data We accidentally call down to ip6_push_pending_frames when uncorking pending AF_INET data on a ipv6 socket. This results in the following splat (from Dave Jones): skbuff: skb_under_panic: text:ffffffff816765f6 len:48 put:40 head:ffff88013deb6df0 data:ffff88013deb6dec tail:0x2c end:0xc0 dev:<NULL> ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:126! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: dccp_ipv4 dccp 8021q garp bridge stp dlci mpoa snd_seq_dummy sctp fuse hidp tun bnep nfnetlink scsi_transport_iscsi rfcomm can_raw can_bcm af_802154 appletalk caif_socket can caif ipt_ULOG x25 rose af_key pppoe pppox ipx phonet irda llc2 ppp_generic slhc p8023 psnap p8022 llc crc_ccitt atm bluetooth +netrom ax25 nfc rfkill rds af_rxrpc coretemp hwmon kvm_intel kvm crc32c_intel snd_hda_codec_realtek ghash_clmulni_intel microcode pcspkr snd_hda_codec_hdmi snd_hda_intel snd_hda_codec snd_hwdep usb_debug snd_seq snd_seq_device snd_pcm e1000e snd_page_alloc snd_timer ptp snd pps_core soundcore xfs libcrc32c CPU: 2 PID: 8095 Comm: trinity-child2 Not tainted 3.10.0-rc7+ #37 task: ffff8801f52c2520 ti: ffff8801e6430000 task.ti: ffff8801e6430000 RIP: 0010:[<ffffffff816e759c>] [<ffffffff816e759c>] skb_panic+0x63/0x65 RSP: 0018:ffff8801e6431de8 EFLAGS: 00010282 RAX: 0000000000000086 RBX: ffff8802353d3cc0 RCX: 0000000000000006 RDX: 0000000000003b90 RSI: ffff8801f52c2ca0 RDI: ffff8801f52c2520 RBP: ffff8801e6431e08 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff88022ea0c800 R13: ffff88022ea0cdf8 R14: ffff8802353ecb40 R15: ffffffff81cc7800 FS: 00007f5720a10740(0000) GS:ffff880244c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000005862000 CR3: 000000022843c000 CR4: 00000000001407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000600 Stack: ffff88013deb6dec 000000000000002c 00000000000000c0 ffffffff81a3f6e4 ffff8801e6431e18 ffffffff8159a9aa ffff8801e6431e90 ffffffff816765f6 ffffffff810b756b 0000000700000002 ffff8801e6431e40 0000fea9292aa8c0 Call Trace: [<ffffffff8159a9aa>] skb_push+0x3a/0x40 [<ffffffff816765f6>] ip6_push_pending_frames+0x1f6/0x4d0 [<ffffffff810b756b>] ? mark_held_locks+0xbb/0x140 [<ffffffff81694919>] udp_v6_push_pending_frames+0x2b9/0x3d0 [<ffffffff81694660>] ? udplite_getfrag+0x20/0x20 [<ffffffff8162092a>] udp_lib_setsockopt+0x1aa/0x1f0 [<ffffffff811cc5e7>] ? fget_light+0x387/0x4f0 [<ffffffff816958a4>] udpv6_setsockopt+0x34/0x40 [<ffffffff815949f4>] sock_common_setsockopt+0x14/0x20 [<ffffffff81593c31>] SyS_setsockopt+0x71/0xd0 [<ffffffff816f5d54>] tracesys+0xdd/0xe2 Code: 00 00 48 89 44 24 10 8b 87 d8 00 00 00 48 89 44 24 08 48 8b 87 e8 00 00 00 48 c7 c7 c0 04 aa 81 48 89 04 24 31 c0 e8 e1 7e ff ff <0f> 0b 55 48 89 e5 0f 0b 55 48 89 e5 0f 0b 55 48 89 e5 0f 0b 55 RIP [<ffffffff816e759c>] skb_panic+0x63/0x65 RSP <ffff8801e6431de8> This patch adds a check if the pending data is of address family AF_INET and directly calls udp_push_ending_frames from udp_v6_push_pending_frames if that is the case. This bug was found by Dave Jones with trinity. (Also move the initialization of fl6 below the AF_INET check, even if not strictly necessary.) Cc: Dave Jones <davej@redhat.com> Cc: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-07-02 02:21:30 +08:00
int udp_push_pending_frames(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
struct flowi4 *fl4 = &inet->cork.fl.u.ip4;
struct sk_buff *skb;
int err = 0;
skb = ip_finish_skb(sk, fl4);
if (!skb)
goto out;
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-27 01:42:17 +08:00
err = udp_send_skb(skb, fl4, &inet->cork.base);
out:
up->len = 0;
up->pending = 0;
return err;
}
ipv6: call udp_push_pending_frames when uncorking a socket with AF_INET pending data We accidentally call down to ip6_push_pending_frames when uncorking pending AF_INET data on a ipv6 socket. This results in the following splat (from Dave Jones): skbuff: skb_under_panic: text:ffffffff816765f6 len:48 put:40 head:ffff88013deb6df0 data:ffff88013deb6dec tail:0x2c end:0xc0 dev:<NULL> ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:126! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: dccp_ipv4 dccp 8021q garp bridge stp dlci mpoa snd_seq_dummy sctp fuse hidp tun bnep nfnetlink scsi_transport_iscsi rfcomm can_raw can_bcm af_802154 appletalk caif_socket can caif ipt_ULOG x25 rose af_key pppoe pppox ipx phonet irda llc2 ppp_generic slhc p8023 psnap p8022 llc crc_ccitt atm bluetooth +netrom ax25 nfc rfkill rds af_rxrpc coretemp hwmon kvm_intel kvm crc32c_intel snd_hda_codec_realtek ghash_clmulni_intel microcode pcspkr snd_hda_codec_hdmi snd_hda_intel snd_hda_codec snd_hwdep usb_debug snd_seq snd_seq_device snd_pcm e1000e snd_page_alloc snd_timer ptp snd pps_core soundcore xfs libcrc32c CPU: 2 PID: 8095 Comm: trinity-child2 Not tainted 3.10.0-rc7+ #37 task: ffff8801f52c2520 ti: ffff8801e6430000 task.ti: ffff8801e6430000 RIP: 0010:[<ffffffff816e759c>] [<ffffffff816e759c>] skb_panic+0x63/0x65 RSP: 0018:ffff8801e6431de8 EFLAGS: 00010282 RAX: 0000000000000086 RBX: ffff8802353d3cc0 RCX: 0000000000000006 RDX: 0000000000003b90 RSI: ffff8801f52c2ca0 RDI: ffff8801f52c2520 RBP: ffff8801e6431e08 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff88022ea0c800 R13: ffff88022ea0cdf8 R14: ffff8802353ecb40 R15: ffffffff81cc7800 FS: 00007f5720a10740(0000) GS:ffff880244c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000005862000 CR3: 000000022843c000 CR4: 00000000001407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000600 Stack: ffff88013deb6dec 000000000000002c 00000000000000c0 ffffffff81a3f6e4 ffff8801e6431e18 ffffffff8159a9aa ffff8801e6431e90 ffffffff816765f6 ffffffff810b756b 0000000700000002 ffff8801e6431e40 0000fea9292aa8c0 Call Trace: [<ffffffff8159a9aa>] skb_push+0x3a/0x40 [<ffffffff816765f6>] ip6_push_pending_frames+0x1f6/0x4d0 [<ffffffff810b756b>] ? mark_held_locks+0xbb/0x140 [<ffffffff81694919>] udp_v6_push_pending_frames+0x2b9/0x3d0 [<ffffffff81694660>] ? udplite_getfrag+0x20/0x20 [<ffffffff8162092a>] udp_lib_setsockopt+0x1aa/0x1f0 [<ffffffff811cc5e7>] ? fget_light+0x387/0x4f0 [<ffffffff816958a4>] udpv6_setsockopt+0x34/0x40 [<ffffffff815949f4>] sock_common_setsockopt+0x14/0x20 [<ffffffff81593c31>] SyS_setsockopt+0x71/0xd0 [<ffffffff816f5d54>] tracesys+0xdd/0xe2 Code: 00 00 48 89 44 24 10 8b 87 d8 00 00 00 48 89 44 24 08 48 8b 87 e8 00 00 00 48 c7 c7 c0 04 aa 81 48 89 04 24 31 c0 e8 e1 7e ff ff <0f> 0b 55 48 89 e5 0f 0b 55 48 89 e5 0f 0b 55 48 89 e5 0f 0b 55 RIP [<ffffffff816e759c>] skb_panic+0x63/0x65 RSP <ffff8801e6431de8> This patch adds a check if the pending data is of address family AF_INET and directly calls udp_push_ending_frames from udp_v6_push_pending_frames if that is the case. This bug was found by Dave Jones with trinity. (Also move the initialization of fl6 below the AF_INET check, even if not strictly necessary.) Cc: Dave Jones <davej@redhat.com> Cc: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-07-02 02:21:30 +08:00
EXPORT_SYMBOL(udp_push_pending_frames);
static int __udp_cmsg_send(struct cmsghdr *cmsg, u16 *gso_size)
{
switch (cmsg->cmsg_type) {
case UDP_SEGMENT:
if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u16)))
return -EINVAL;
*gso_size = *(__u16 *)CMSG_DATA(cmsg);
return 0;
default:
return -EINVAL;
}
}
int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size)
{
struct cmsghdr *cmsg;
bool need_ip = false;
int err;
for_each_cmsghdr(cmsg, msg) {
if (!CMSG_OK(msg, cmsg))
return -EINVAL;
if (cmsg->cmsg_level != SOL_UDP) {
need_ip = true;
continue;
}
err = __udp_cmsg_send(cmsg, gso_size);
if (err)
return err;
}
return need_ip;
}
EXPORT_SYMBOL_GPL(udp_cmsg_send);
int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct inet_sock *inet = inet_sk(sk);
struct udp_sock *up = udp_sk(sk);
bpf: Hooks for sys_sendmsg In addition to already existing BPF hooks for sys_bind and sys_connect, the patch provides new hooks for sys_sendmsg. It leverages existing BPF program type `BPF_PROG_TYPE_CGROUP_SOCK_ADDR` that provides access to socket itlself (properties like family, type, protocol) and user-passed `struct sockaddr *` so that BPF program can override destination IP and port for system calls such as sendto(2) or sendmsg(2) and/or assign source IP to the socket. The hooks are implemented as two new attach types: `BPF_CGROUP_UDP4_SENDMSG` and `BPF_CGROUP_UDP6_SENDMSG` for UDPv4 and UDPv6 correspondingly. UDPv4 and UDPv6 separate attach types for same reason as sys_bind and sys_connect hooks, i.e. to prevent reading from / writing to e.g. user_ip6 fields when user passes sockaddr_in since it'd be out-of-bound. The difference with already existing hooks is sys_sendmsg are implemented only for unconnected UDP. For TCP it doesn't make sense to change user-provided `struct sockaddr *` at sendto(2)/sendmsg(2) time since socket either was already connected and has source/destination set or wasn't connected and call to sendto(2)/sendmsg(2) would lead to ENOTCONN anyway. Connected UDP is already handled by sys_connect hooks that can override source/destination at connect time and use fast-path later, i.e. these hooks don't affect UDP fast-path. Rewriting source IP is implemented differently than that in sys_connect hooks. When sys_sendmsg is used with unconnected UDP it doesn't work to just bind socket to desired local IP address since source IP can be set on per-packet basis by using ancillary data (cmsg(3)). So no matter if socket is bound or not, source IP has to be rewritten on every call to sys_sendmsg. To do so two new fields are added to UAPI `struct bpf_sock_addr`; * `msg_src_ip4` to set source IPv4 for UDPv4; * `msg_src_ip6` to set source IPv6 for UDPv6. Signed-off-by: Andrey Ignatov <rdna@fb.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-25 23:55:23 +08:00
DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
struct flowi4 fl4_stack;
struct flowi4 *fl4;
int ulen = len;
struct ipcm_cookie ipc;
struct rtable *rt = NULL;
int free = 0;
int connected = 0;
__be32 daddr, faddr, saddr;
__be16 dport;
u8 tos;
int err, is_udplite = IS_UDPLITE(sk);
int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE;
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
struct sk_buff *skb;
struct ip_options_data opt_copy;
if (len > 0xFFFF)
return -EMSGSIZE;
/*
* Check the flags.
*/
if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message compatibility */
return -EOPNOTSUPP;
getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
fl4 = &inet->cork.fl.u.ip4;
if (up->pending) {
/*
* There are pending frames.
* The socket lock must be held while it's corked.
*/
lock_sock(sk);
if (likely(up->pending)) {
if (unlikely(up->pending != AF_INET)) {
release_sock(sk);
return -EINVAL;
}
goto do_append_data;
}
release_sock(sk);
}
ulen += sizeof(struct udphdr);
/*
* Get and verify the address.
*/
bpf: Hooks for sys_sendmsg In addition to already existing BPF hooks for sys_bind and sys_connect, the patch provides new hooks for sys_sendmsg. It leverages existing BPF program type `BPF_PROG_TYPE_CGROUP_SOCK_ADDR` that provides access to socket itlself (properties like family, type, protocol) and user-passed `struct sockaddr *` so that BPF program can override destination IP and port for system calls such as sendto(2) or sendmsg(2) and/or assign source IP to the socket. The hooks are implemented as two new attach types: `BPF_CGROUP_UDP4_SENDMSG` and `BPF_CGROUP_UDP6_SENDMSG` for UDPv4 and UDPv6 correspondingly. UDPv4 and UDPv6 separate attach types for same reason as sys_bind and sys_connect hooks, i.e. to prevent reading from / writing to e.g. user_ip6 fields when user passes sockaddr_in since it'd be out-of-bound. The difference with already existing hooks is sys_sendmsg are implemented only for unconnected UDP. For TCP it doesn't make sense to change user-provided `struct sockaddr *` at sendto(2)/sendmsg(2) time since socket either was already connected and has source/destination set or wasn't connected and call to sendto(2)/sendmsg(2) would lead to ENOTCONN anyway. Connected UDP is already handled by sys_connect hooks that can override source/destination at connect time and use fast-path later, i.e. these hooks don't affect UDP fast-path. Rewriting source IP is implemented differently than that in sys_connect hooks. When sys_sendmsg is used with unconnected UDP it doesn't work to just bind socket to desired local IP address since source IP can be set on per-packet basis by using ancillary data (cmsg(3)). So no matter if socket is bound or not, source IP has to be rewritten on every call to sys_sendmsg. To do so two new fields are added to UAPI `struct bpf_sock_addr`; * `msg_src_ip4` to set source IPv4 for UDPv4; * `msg_src_ip6` to set source IPv6 for UDPv6. Signed-off-by: Andrey Ignatov <rdna@fb.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-25 23:55:23 +08:00
if (usin) {
if (msg->msg_namelen < sizeof(*usin))
return -EINVAL;
if (usin->sin_family != AF_INET) {
if (usin->sin_family != AF_UNSPEC)
return -EAFNOSUPPORT;
}
daddr = usin->sin_addr.s_addr;
dport = usin->sin_port;
if (dport == 0)
return -EINVAL;
} else {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
daddr = inet->inet_daddr;
dport = inet->inet_dport;
/* Open fast path for connected socket.
Route will not be used, if at least one option is set.
*/
connected = 1;
}
ipcm_init_sk(&ipc, inet);
udp: annotate data races around unix_sk(sk)->gso_size Accesses to unix_sk(sk)->gso_size are lockless. Add READ_ONCE()/WRITE_ONCE() around them. BUG: KCSAN: data-race in udp_lib_setsockopt / udpv6_sendmsg write to 0xffff88812d78f47c of 2 bytes by task 10849 on cpu 1: udp_lib_setsockopt+0x3b3/0x710 net/ipv4/udp.c:2696 udpv6_setsockopt+0x63/0x90 net/ipv6/udp.c:1630 sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3265 __sys_setsockopt+0x18f/0x200 net/socket.c:2104 __do_sys_setsockopt net/socket.c:2115 [inline] __se_sys_setsockopt net/socket.c:2112 [inline] __x64_sys_setsockopt+0x62/0x70 net/socket.c:2112 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88812d78f47c of 2 bytes by task 10852 on cpu 0: udpv6_sendmsg+0x161/0x16b0 net/ipv6/udp.c:1299 inet6_sendmsg+0x5f/0x80 net/ipv6/af_inet6.c:642 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2337 ___sys_sendmsg net/socket.c:2391 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2477 __do_sys_sendmmsg net/socket.c:2506 [inline] __se_sys_sendmmsg net/socket.c:2503 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2503 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x0000 -> 0x0005 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 10852 Comm: syz-executor.0 Not tainted 5.13.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Willem de Bruijn <willemb@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-01 00:42:44 +08:00
ipc.gso_size = READ_ONCE(up->gso_size);
if (msg->msg_controllen) {
err = udp_cmsg_send(sk, msg, &ipc.gso_size);
if (err > 0)
err = ip_cmsg_send(sk, msg, &ipc,
sk->sk_family == AF_INET6);
if (unlikely(err < 0)) {
kfree(ipc.opt);
return err;
}
if (ipc.opt)
free = 1;
connected = 0;
}
if (!ipc.opt) {
struct ip_options_rcu *inet_opt;
rcu_read_lock();
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt) {
memcpy(&opt_copy, inet_opt,
sizeof(*inet_opt) + inet_opt->opt.optlen);
ipc.opt = &opt_copy.opt;
}
rcu_read_unlock();
}
if (cgroup_bpf_enabled(CGROUP_UDP4_SENDMSG) && !connected) {
bpf: Hooks for sys_sendmsg In addition to already existing BPF hooks for sys_bind and sys_connect, the patch provides new hooks for sys_sendmsg. It leverages existing BPF program type `BPF_PROG_TYPE_CGROUP_SOCK_ADDR` that provides access to socket itlself (properties like family, type, protocol) and user-passed `struct sockaddr *` so that BPF program can override destination IP and port for system calls such as sendto(2) or sendmsg(2) and/or assign source IP to the socket. The hooks are implemented as two new attach types: `BPF_CGROUP_UDP4_SENDMSG` and `BPF_CGROUP_UDP6_SENDMSG` for UDPv4 and UDPv6 correspondingly. UDPv4 and UDPv6 separate attach types for same reason as sys_bind and sys_connect hooks, i.e. to prevent reading from / writing to e.g. user_ip6 fields when user passes sockaddr_in since it'd be out-of-bound. The difference with already existing hooks is sys_sendmsg are implemented only for unconnected UDP. For TCP it doesn't make sense to change user-provided `struct sockaddr *` at sendto(2)/sendmsg(2) time since socket either was already connected and has source/destination set or wasn't connected and call to sendto(2)/sendmsg(2) would lead to ENOTCONN anyway. Connected UDP is already handled by sys_connect hooks that can override source/destination at connect time and use fast-path later, i.e. these hooks don't affect UDP fast-path. Rewriting source IP is implemented differently than that in sys_connect hooks. When sys_sendmsg is used with unconnected UDP it doesn't work to just bind socket to desired local IP address since source IP can be set on per-packet basis by using ancillary data (cmsg(3)). So no matter if socket is bound or not, source IP has to be rewritten on every call to sys_sendmsg. To do so two new fields are added to UAPI `struct bpf_sock_addr`; * `msg_src_ip4` to set source IPv4 for UDPv4; * `msg_src_ip6` to set source IPv6 for UDPv6. Signed-off-by: Andrey Ignatov <rdna@fb.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-05-25 23:55:23 +08:00
err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk,
(struct sockaddr *)usin, &ipc.addr);
if (err)
goto out_free;
if (usin) {
if (usin->sin_port == 0) {
/* BPF program set invalid port. Reject it. */
err = -EINVAL;
goto out_free;
}
daddr = usin->sin_addr.s_addr;
dport = usin->sin_port;
}
}
saddr = ipc.addr;
ipc.addr = faddr = daddr;
if (ipc.opt && ipc.opt->opt.srr) {
if (!daddr) {
err = -EINVAL;
goto out_free;
}
faddr = ipc.opt->opt.faddr;
connected = 0;
}
tos = get_rttos(&ipc, inet);
if (sock_flag(sk, SOCK_LOCALROUTE) ||
(msg->msg_flags & MSG_DONTROUTE) ||
(ipc.opt && ipc.opt->opt.is_strictroute)) {
tos |= RTO_ONLINK;
connected = 0;
}
if (ipv4_is_multicast(daddr)) {
if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
ipc.oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
connected = 0;
} else if (!ipc.oif) {
ipv4: Implement IP_UNICAST_IF socket option. The IP_UNICAST_IF feature is needed by the Wine project. This patch implements the feature by setting the outgoing interface in a similar fashion to that of IP_MULTICAST_IF. A separate option is needed to handle this feature since the existing options do not provide all of the characteristics required by IP_UNICAST_IF, a summary is provided below. SO_BINDTODEVICE: * SO_BINDTODEVICE requires administrative privileges, IP_UNICAST_IF does not. From reading some old mailing list articles my understanding is that SO_BINDTODEVICE requires administrative privileges because it can override the administrator's routing settings. * The SO_BINDTODEVICE option restricts both outbound and inbound traffic, IP_UNICAST_IF only impacts outbound traffic. IP_PKTINFO: * Since IP_PKTINFO and IP_UNICAST_IF are independent options, implementing IP_UNICAST_IF with IP_PKTINFO will likely break some applications. * Implementing IP_UNICAST_IF on top of IP_PKTINFO significantly complicates the Wine codebase and reduces the socket performance (doing this requires a lot of extra communication between the "server" and "user" layers). bind(): * bind() does not work on broadcast packets, IP_UNICAST_IF is specifically intended to work with broadcast packets. * Like SO_BINDTODEVICE, bind() restricts both outbound and inbound traffic. Signed-off-by: Erich E. Hoover <ehoover@mines.edu> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-08 17:11:07 +08:00
ipc.oif = inet->uc_index;
} else if (ipv4_is_lbcast(daddr) && inet->uc_index) {
/* oif is set, packet is to local broadcast and
* uc_index is set. oif is most likely set
* by sk_bound_dev_if. If uc_index != oif check if the
* oif is an L3 master and uc_index is an L3 slave.
* If so, we want to allow the send using the uc_index.
*/
if (ipc.oif != inet->uc_index &&
ipc.oif == l3mdev_master_ifindex_by_index(sock_net(sk),
inet->uc_index)) {
ipc.oif = inet->uc_index;
}
}
if (connected)
rt = (struct rtable *)sk_dst_check(sk, 0);
if (!rt) {
struct net *net = sock_net(sk);
__u8 flow_flags = inet_sk_flowi_flags(sk);
fl4 = &fl4_stack;
flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
flow_flags,
faddr, saddr, dport, inet->inet_sport,
sk->sk_uid);
security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
if (err == -ENETUNREACH)
IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
goto out;
}
err = -EACCES;
if ((rt->rt_flags & RTCF_BROADCAST) &&
!sock_flag(sk, SOCK_BROADCAST))
goto out;
if (connected)
sk_dst_set(sk, dst_clone(&rt->dst));
}
if (msg->msg_flags&MSG_CONFIRM)
goto do_confirm;
back_from_confirm:
saddr = fl4->saddr;
if (!ipc.addr)
daddr = ipc.addr = fl4->daddr;
/* Lockless fast path for the non-corking case. */
if (!corkreq) {
struct inet_cork cork;
skb = ip_make_skb(sk, fl4, getfrag, msg, ulen,
sizeof(struct udphdr), &ipc, &rt,
&cork, msg->msg_flags);
err = PTR_ERR(skb);
if (!IS_ERR_OR_NULL(skb))
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-27 01:42:17 +08:00
err = udp_send_skb(skb, fl4, &cork);
goto out;
}
lock_sock(sk);
if (unlikely(up->pending)) {
/* The socket is already corked while preparing it. */
/* ... which is an evident application bug. --ANK */
release_sock(sk);
net_dbg_ratelimited("socket already corked\n");
err = -EINVAL;
goto out;
}
/*
* Now cork the socket to pend data.
*/
fl4 = &inet->cork.fl.u.ip4;
fl4->daddr = daddr;
fl4->saddr = saddr;
fl4->fl4_dport = dport;
fl4->fl4_sport = inet->inet_sport;
up->pending = AF_INET;
do_append_data:
up->len += ulen;
err = ip_append_data(sk, fl4, getfrag, msg, ulen,
sizeof(struct udphdr), &ipc, &rt,
corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
if (err)
udp_flush_pending_frames(sk);
else if (!corkreq)
err = udp_push_pending_frames(sk);
else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
up->pending = 0;
release_sock(sk);
out:
ip_rt_put(rt);
out_free:
if (free)
kfree(ipc.opt);
if (!err)
return len;
/*
* ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting
* ENOBUFS might not be good (it's not tunable per se), but otherwise
* we don't have a good statistic (IpOutDiscards but it can be too many
* things). We could add another new stat but at least for now that
* seems like overkill.
*/
if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
UDP_INC_STATS(sock_net(sk),
UDP_MIB_SNDBUFERRORS, is_udplite);
}
return err;
do_confirm:
if (msg->msg_flags & MSG_PROBE)
dst_confirm_neigh(&rt->dst, &fl4->daddr);
if (!(msg->msg_flags&MSG_PROBE) || len)
goto back_from_confirm;
err = 0;
goto out;
}
EXPORT_SYMBOL(udp_sendmsg);
int udp_sendpage(struct sock *sk, struct page *page, int offset,
size_t size, int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct udp_sock *up = udp_sk(sk);
int ret;
if (flags & MSG_SENDPAGE_NOTLAST)
flags |= MSG_MORE;
if (!up->pending) {
struct msghdr msg = { .msg_flags = flags|MSG_MORE };
/* Call udp_sendmsg to specify destination address which
* sendpage interface can't pass.
* This will succeed only when the socket is connected.
*/
ret = udp_sendmsg(sk, &msg, 0);
if (ret < 0)
return ret;
}
lock_sock(sk);
if (unlikely(!up->pending)) {
release_sock(sk);
net_dbg_ratelimited("cork failed\n");
return -EINVAL;
}
ret = ip_append_page(sk, &inet->cork.fl.u.ip4,
page, offset, size, flags);
if (ret == -EOPNOTSUPP) {
release_sock(sk);
return sock_no_sendpage(sk->sk_socket, page, offset,
size, flags);
}
if (ret < 0) {
udp_flush_pending_frames(sk);
goto out;
}
up->len += size;
if (!(READ_ONCE(up->corkflag) || (flags&MSG_MORE)))
ret = udp_push_pending_frames(sk);
if (!ret)
ret = size;
out:
release_sock(sk);
return ret;
}
#define UDP_SKB_IS_STATELESS 0x80000000
/* all head states (dst, sk, nf conntrack) except skb extensions are
* cleared by udp_rcv().
*
* We need to preserve secpath, if present, to eventually process
* IP_CMSG_PASSSEC at recvmsg() time.
*
* Other extensions can be cleared.
*/
static bool udp_try_make_stateless(struct sk_buff *skb)
{
if (!skb_has_extensions(skb))
return true;
if (!secpath_exists(skb)) {
skb_ext_reset(skb);
return true;
}
return false;
}
static void udp_set_dev_scratch(struct sk_buff *skb)
{
struct udp_dev_scratch *scratch = udp_skb_scratch(skb);
BUILD_BUG_ON(sizeof(struct udp_dev_scratch) > sizeof(long));
scratch->_tsize_state = skb->truesize;
#if BITS_PER_LONG == 64
scratch->len = skb->len;
scratch->csum_unnecessary = !!skb_csum_unnecessary(skb);
scratch->is_linear = !skb_is_nonlinear(skb);
#endif
if (udp_try_make_stateless(skb))
scratch->_tsize_state |= UDP_SKB_IS_STATELESS;
}
udp: fix data-race in udp_set_dev_scratch() KCSAN reported a data-race in udp_set_dev_scratch() [1] The issue here is that we must not write over skb fields if skb is shared. A similar issue has been fixed in commit 89c22d8c3b27 ("net: Fix skb csum races when peeking") While we are at it, use a helper only dealing with udp_skb_scratch(skb)->csum_unnecessary, as this allows udp_set_dev_scratch() to be called once and thus inlined. [1] BUG: KCSAN: data-race in udp_set_dev_scratch / udpv6_recvmsg write to 0xffff888120278317 of 1 bytes by task 10411 on cpu 1: udp_set_dev_scratch+0xea/0x200 net/ipv4/udp.c:1308 __first_packet_length+0x147/0x420 net/ipv4/udp.c:1556 first_packet_length+0x68/0x2a0 net/ipv4/udp.c:1579 udp_poll+0xea/0x110 net/ipv4/udp.c:2720 sock_poll+0xed/0x250 net/socket.c:1256 vfs_poll include/linux/poll.h:90 [inline] do_select+0x7d0/0x1020 fs/select.c:534 core_sys_select+0x381/0x550 fs/select.c:677 do_pselect.constprop.0+0x11d/0x160 fs/select.c:759 __do_sys_pselect6 fs/select.c:784 [inline] __se_sys_pselect6 fs/select.c:769 [inline] __x64_sys_pselect6+0x12e/0x170 fs/select.c:769 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x44/0xa9 read to 0xffff888120278317 of 1 bytes by task 10413 on cpu 0: udp_skb_csum_unnecessary include/net/udp.h:358 [inline] udpv6_recvmsg+0x43e/0xe90 net/ipv6/udp.c:310 inet6_recvmsg+0xbb/0x240 net/ipv6/af_inet6.c:592 sock_recvmsg_nosec+0x5c/0x70 net/socket.c:871 ___sys_recvmsg+0x1a0/0x3e0 net/socket.c:2480 do_recvmmsg+0x19a/0x5c0 net/socket.c:2601 __sys_recvmmsg+0x1ef/0x200 net/socket.c:2680 __do_sys_recvmmsg net/socket.c:2703 [inline] __se_sys_recvmmsg net/socket.c:2696 [inline] __x64_sys_recvmmsg+0x89/0xb0 net/socket.c:2696 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 10413 Comm: syz-executor.0 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 2276f58ac589 ("udp: use a separate rx queue for packet reception") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-10-25 02:43:31 +08:00
static void udp_skb_csum_unnecessary_set(struct sk_buff *skb)
{
/* We come here after udp_lib_checksum_complete() returned 0.
* This means that __skb_checksum_complete() might have
* set skb->csum_valid to 1.
* On 64bit platforms, we can set csum_unnecessary
* to true, but only if the skb is not shared.
*/
#if BITS_PER_LONG == 64
if (!skb_shared(skb))
udp_skb_scratch(skb)->csum_unnecessary = true;
#endif
}
static int udp_skb_truesize(struct sk_buff *skb)
{
return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS;
}
static bool udp_skb_has_head_state(struct sk_buff *skb)
{
return !(udp_skb_scratch(skb)->_tsize_state & UDP_SKB_IS_STATELESS);
}
/* fully reclaim rmem/fwd memory allocated for skb */
static void udp_rmem_release(struct sock *sk, int size, int partial,
bool rx_queue_lock_held)
2016-10-21 19:55:46 +08:00
{
struct udp_sock *up = udp_sk(sk);
struct sk_buff_head *sk_queue;
2016-10-21 19:55:46 +08:00
int amt;
if (likely(partial)) {
up->forward_deficit += size;
size = up->forward_deficit;
if (size < READ_ONCE(up->forward_threshold) &&
!skb_queue_empty(&up->reader_queue))
return;
} else {
size += up->forward_deficit;
}
up->forward_deficit = 0;
/* acquire the sk_receive_queue for fwd allocated memory scheduling,
* if the called don't held it already
*/
sk_queue = &sk->sk_receive_queue;
if (!rx_queue_lock_held)
spin_lock(&sk_queue->lock);
2016-10-21 19:55:46 +08:00
sk->sk_forward_alloc += size;
amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1);
2016-10-21 19:55:46 +08:00
sk->sk_forward_alloc -= amt;
if (amt)
__sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT);
atomic_sub(size, &sk->sk_rmem_alloc);
/* this can save us from acquiring the rx queue lock on next receive */
skb_queue_splice_tail_init(sk_queue, &up->reader_queue);
if (!rx_queue_lock_held)
spin_unlock(&sk_queue->lock);
2016-10-21 19:55:46 +08:00
}
/* Note: called with reader_queue.lock held.
* Instead of using skb->truesize here, find a copy of it in skb->dev_scratch
* This avoids a cache line miss while receive_queue lock is held.
* Look at __udp_enqueue_schedule_skb() to find where this copy is done.
*/
void udp_skb_destructor(struct sock *sk, struct sk_buff *skb)
2016-10-21 19:55:46 +08:00
{
prefetch(&skb->data);
udp_rmem_release(sk, udp_skb_truesize(skb), 1, false);
2016-10-21 19:55:46 +08:00
}
EXPORT_SYMBOL(udp_skb_destructor);
2016-10-21 19:55:46 +08:00
/* as above, but the caller held the rx queue lock, too */
static void udp_skb_dtor_locked(struct sock *sk, struct sk_buff *skb)
{
prefetch(&skb->data);
udp_rmem_release(sk, udp_skb_truesize(skb), 1, true);
}
/* Idea of busylocks is to let producers grab an extra spinlock
* to relieve pressure on the receive_queue spinlock shared by consumer.
* Under flood, this means that only one producer can be in line
* trying to acquire the receive_queue spinlock.
* These busylock can be allocated on a per cpu manner, instead of a
* per socket one (that would consume a cache line per socket)
*/
static int udp_busylocks_log __read_mostly;
static spinlock_t *udp_busylocks __read_mostly;
static spinlock_t *busylock_acquire(void *ptr)
{
spinlock_t *busy;
busy = udp_busylocks + hash_ptr(ptr, udp_busylocks_log);
spin_lock(busy);
return busy;
}
static void busylock_release(spinlock_t *busy)
{
if (busy)
spin_unlock(busy);
}
2016-10-21 19:55:46 +08:00
int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
{
struct sk_buff_head *list = &sk->sk_receive_queue;
int rmem, delta, amt, err = -ENOMEM;
spinlock_t *busy = NULL;
int size;
2016-10-21 19:55:46 +08:00
/* try to avoid the costly atomic add/sub pair when the receive
* queue is full; always allow at least a packet
*/
rmem = atomic_read(&sk->sk_rmem_alloc);
if (rmem > sk->sk_rcvbuf)
2016-10-21 19:55:46 +08:00
goto drop;
/* Under mem pressure, it might be helpful to help udp_recvmsg()
* having linear skbs :
* - Reduce memory overhead and thus increase receive queue capacity
* - Less cache line misses at copyout() time
* - Less work at consume_skb() (less alien page frag freeing)
*/
if (rmem > (sk->sk_rcvbuf >> 1)) {
skb_condense(skb);
busy = busylock_acquire(sk);
}
size = skb->truesize;
udp_set_dev_scratch(skb);
2016-10-21 19:55:46 +08:00
/* we drop only if the receive buf is full and the receive
* queue contains some other skb
*/
rmem = atomic_add_return(size, &sk->sk_rmem_alloc);
if (rmem > (size + (unsigned int)sk->sk_rcvbuf))
2016-10-21 19:55:46 +08:00
goto uncharge_drop;
spin_lock(&list->lock);
if (size >= sk->sk_forward_alloc) {
amt = sk_mem_pages(size);
delta = amt << PAGE_SHIFT;
2016-10-21 19:55:46 +08:00
if (!__sk_mem_raise_allocated(sk, delta, amt, SK_MEM_RECV)) {
err = -ENOBUFS;
spin_unlock(&list->lock);
goto uncharge_drop;
}
sk->sk_forward_alloc += delta;
}
sk->sk_forward_alloc -= size;
/* no need to setup a destructor, we will explicitly release the
* forward allocated memory on dequeue
*/
2016-10-21 19:55:46 +08:00
sock_skb_set_dropcount(sk, skb);
__skb_queue_tail(list, skb);
spin_unlock(&list->lock);
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_data_ready(sk);
busylock_release(busy);
2016-10-21 19:55:46 +08:00
return 0;
uncharge_drop:
atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
drop:
atomic_inc(&sk->sk_drops);
busylock_release(busy);
2016-10-21 19:55:46 +08:00
return err;
}
EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb);
tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct(). Originally, inet6_sk(sk)->XXX were changed under lock_sock(), so we were able to clean them up by calling inet6_destroy_sock() during the IPv6 -> IPv4 conversion by IPV6_ADDRFORM. However, commit 03485f2adcde ("udpv6: Add lockless sendmsg() support") added a lockless memory allocation path, which could cause a memory leak: setsockopt(IPV6_ADDRFORM) sendmsg() +-----------------------+ +-------+ - do_ipv6_setsockopt(sk, ...) - udpv6_sendmsg(sk, ...) - sockopt_lock_sock(sk) ^._ called via udpv6_prot - lock_sock(sk) before WRITE_ONCE() - WRITE_ONCE(sk->sk_prot, &tcp_prot) - inet6_destroy_sock() - if (!corkreq) - sockopt_release_sock(sk) - ip6_make_skb(sk, ...) - release_sock(sk) ^._ lockless fast path for the non-corking case - __ip6_append_data(sk, ...) - ipv6_local_rxpmtu(sk, ...) - xchg(&np->rxpmtu, skb) ^._ rxpmtu is never freed. - goto out_no_dst; - lock_sock(sk) For now, rxpmtu is only the case, but not to miss the future change and a similar bug fixed in commit e27326009a3d ("net: ping6: Fix memleak in ipv6_renew_options()."), let's set a new function to IPv6 sk->sk_destruct() and call inet6_cleanup_sock() there. Since the conversion does not change sk->sk_destruct(), we can guarantee that we can clean up IPv6 resources finally. We can now remove all inet6_destroy_sock() calls from IPv6 protocol specific ->destroy() functions, but such changes are invasive to backport. So they can be posted as a follow-up later for net-next. Fixes: 03485f2adcde ("udpv6: Add lockless sendmsg() support") Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-10-07 02:53:47 +08:00
void udp_destruct_common(struct sock *sk)
2016-10-21 19:55:46 +08:00
{
/* reclaim completely the forward allocated memory */
struct udp_sock *up = udp_sk(sk);
unsigned int total = 0;
struct sk_buff *skb;
skb_queue_splice_tail_init(&sk->sk_receive_queue, &up->reader_queue);
while ((skb = __skb_dequeue(&up->reader_queue)) != NULL) {
total += skb->truesize;
kfree_skb(skb);
}
udp_rmem_release(sk, total, 0, true);
tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct(). Originally, inet6_sk(sk)->XXX were changed under lock_sock(), so we were able to clean them up by calling inet6_destroy_sock() during the IPv6 -> IPv4 conversion by IPV6_ADDRFORM. However, commit 03485f2adcde ("udpv6: Add lockless sendmsg() support") added a lockless memory allocation path, which could cause a memory leak: setsockopt(IPV6_ADDRFORM) sendmsg() +-----------------------+ +-------+ - do_ipv6_setsockopt(sk, ...) - udpv6_sendmsg(sk, ...) - sockopt_lock_sock(sk) ^._ called via udpv6_prot - lock_sock(sk) before WRITE_ONCE() - WRITE_ONCE(sk->sk_prot, &tcp_prot) - inet6_destroy_sock() - if (!corkreq) - sockopt_release_sock(sk) - ip6_make_skb(sk, ...) - release_sock(sk) ^._ lockless fast path for the non-corking case - __ip6_append_data(sk, ...) - ipv6_local_rxpmtu(sk, ...) - xchg(&np->rxpmtu, skb) ^._ rxpmtu is never freed. - goto out_no_dst; - lock_sock(sk) For now, rxpmtu is only the case, but not to miss the future change and a similar bug fixed in commit e27326009a3d ("net: ping6: Fix memleak in ipv6_renew_options()."), let's set a new function to IPv6 sk->sk_destruct() and call inet6_cleanup_sock() there. Since the conversion does not change sk->sk_destruct(), we can guarantee that we can clean up IPv6 resources finally. We can now remove all inet6_destroy_sock() calls from IPv6 protocol specific ->destroy() functions, but such changes are invasive to backport. So they can be posted as a follow-up later for net-next. Fixes: 03485f2adcde ("udpv6: Add lockless sendmsg() support") Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-10-07 02:53:47 +08:00
}
EXPORT_SYMBOL_GPL(udp_destruct_common);
tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct(). Originally, inet6_sk(sk)->XXX were changed under lock_sock(), so we were able to clean them up by calling inet6_destroy_sock() during the IPv6 -> IPv4 conversion by IPV6_ADDRFORM. However, commit 03485f2adcde ("udpv6: Add lockless sendmsg() support") added a lockless memory allocation path, which could cause a memory leak: setsockopt(IPV6_ADDRFORM) sendmsg() +-----------------------+ +-------+ - do_ipv6_setsockopt(sk, ...) - udpv6_sendmsg(sk, ...) - sockopt_lock_sock(sk) ^._ called via udpv6_prot - lock_sock(sk) before WRITE_ONCE() - WRITE_ONCE(sk->sk_prot, &tcp_prot) - inet6_destroy_sock() - if (!corkreq) - sockopt_release_sock(sk) - ip6_make_skb(sk, ...) - release_sock(sk) ^._ lockless fast path for the non-corking case - __ip6_append_data(sk, ...) - ipv6_local_rxpmtu(sk, ...) - xchg(&np->rxpmtu, skb) ^._ rxpmtu is never freed. - goto out_no_dst; - lock_sock(sk) For now, rxpmtu is only the case, but not to miss the future change and a similar bug fixed in commit e27326009a3d ("net: ping6: Fix memleak in ipv6_renew_options()."), let's set a new function to IPv6 sk->sk_destruct() and call inet6_cleanup_sock() there. Since the conversion does not change sk->sk_destruct(), we can guarantee that we can clean up IPv6 resources finally. We can now remove all inet6_destroy_sock() calls from IPv6 protocol specific ->destroy() functions, but such changes are invasive to backport. So they can be posted as a follow-up later for net-next. Fixes: 03485f2adcde ("udpv6: Add lockless sendmsg() support") Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-10-07 02:53:47 +08:00
static void udp_destruct_sock(struct sock *sk)
{
udp_destruct_common(sk);
2016-10-21 19:55:46 +08:00
inet_sock_destruct(sk);
}
int udp_init_sock(struct sock *sk)
{
udp_lib_init_sock(sk);
2016-10-21 19:55:46 +08:00
sk->sk_destruct = udp_destruct_sock;
set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
2016-10-21 19:55:46 +08:00
return 0;
}
void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
{
if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) {
bool slow = lock_sock_fast(sk);
sk_peek_offset_bwd(sk, len);
unlock_sock_fast(sk, slow);
}
if (!skb_unref(skb))
return;
/* In the more common cases we cleared the head states previously,
* see __udp_queue_rcv_skb().
*/
if (unlikely(udp_skb_has_head_state(skb)))
skb_release_head_state(skb);
__consume_stateless_skb(skb);
2016-10-21 19:55:46 +08:00
}
EXPORT_SYMBOL_GPL(skb_consume_udp);
static struct sk_buff *__first_packet_length(struct sock *sk,
struct sk_buff_head *rcvq,
int *total)
{
struct sk_buff *skb;
while ((skb = skb_peek(rcvq)) != NULL) {
if (udp_lib_checksum_complete(skb)) {
__UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS,
IS_UDPLITE(sk));
__UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
IS_UDPLITE(sk));
atomic_inc(&sk->sk_drops);
__skb_unlink(skb, rcvq);
*total += skb->truesize;
kfree_skb(skb);
} else {
udp: fix data-race in udp_set_dev_scratch() KCSAN reported a data-race in udp_set_dev_scratch() [1] The issue here is that we must not write over skb fields if skb is shared. A similar issue has been fixed in commit 89c22d8c3b27 ("net: Fix skb csum races when peeking") While we are at it, use a helper only dealing with udp_skb_scratch(skb)->csum_unnecessary, as this allows udp_set_dev_scratch() to be called once and thus inlined. [1] BUG: KCSAN: data-race in udp_set_dev_scratch / udpv6_recvmsg write to 0xffff888120278317 of 1 bytes by task 10411 on cpu 1: udp_set_dev_scratch+0xea/0x200 net/ipv4/udp.c:1308 __first_packet_length+0x147/0x420 net/ipv4/udp.c:1556 first_packet_length+0x68/0x2a0 net/ipv4/udp.c:1579 udp_poll+0xea/0x110 net/ipv4/udp.c:2720 sock_poll+0xed/0x250 net/socket.c:1256 vfs_poll include/linux/poll.h:90 [inline] do_select+0x7d0/0x1020 fs/select.c:534 core_sys_select+0x381/0x550 fs/select.c:677 do_pselect.constprop.0+0x11d/0x160 fs/select.c:759 __do_sys_pselect6 fs/select.c:784 [inline] __se_sys_pselect6 fs/select.c:769 [inline] __x64_sys_pselect6+0x12e/0x170 fs/select.c:769 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x44/0xa9 read to 0xffff888120278317 of 1 bytes by task 10413 on cpu 0: udp_skb_csum_unnecessary include/net/udp.h:358 [inline] udpv6_recvmsg+0x43e/0xe90 net/ipv6/udp.c:310 inet6_recvmsg+0xbb/0x240 net/ipv6/af_inet6.c:592 sock_recvmsg_nosec+0x5c/0x70 net/socket.c:871 ___sys_recvmsg+0x1a0/0x3e0 net/socket.c:2480 do_recvmmsg+0x19a/0x5c0 net/socket.c:2601 __sys_recvmmsg+0x1ef/0x200 net/socket.c:2680 __do_sys_recvmmsg net/socket.c:2703 [inline] __se_sys_recvmmsg net/socket.c:2696 [inline] __x64_sys_recvmmsg+0x89/0xb0 net/socket.c:2696 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 10413 Comm: syz-executor.0 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 2276f58ac589 ("udp: use a separate rx queue for packet reception") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-10-25 02:43:31 +08:00
udp_skb_csum_unnecessary_set(skb);
break;
}
}
return skb;
}
/**
* first_packet_length - return length of first packet in receive queue
* @sk: socket
*
* Drops all bad checksum frames, until a valid one is found.
* Returns the length of found skb, or -1 if none is found.
*/
static int first_packet_length(struct sock *sk)
{
struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue;
struct sk_buff_head *sk_queue = &sk->sk_receive_queue;
struct sk_buff *skb;
int total = 0;
int res;
spin_lock_bh(&rcvq->lock);
skb = __first_packet_length(sk, rcvq, &total);
udp: use skb_queue_empty_lockless() syzbot reported a data-race [1]. We should use skb_queue_empty_lockless() to document that we are not ensuring a mutual exclusion and silence KCSAN. [1] BUG: KCSAN: data-race in __skb_recv_udp / __udp_enqueue_schedule_skb write to 0xffff888122474b50 of 8 bytes by interrupt on cpu 0: __skb_insert include/linux/skbuff.h:1852 [inline] __skb_queue_before include/linux/skbuff.h:1958 [inline] __skb_queue_tail include/linux/skbuff.h:1991 [inline] __udp_enqueue_schedule_skb+0x2c1/0x410 net/ipv4/udp.c:1470 __udp_queue_rcv_skb net/ipv4/udp.c:1940 [inline] udp_queue_rcv_one_skb+0x7bd/0xc70 net/ipv4/udp.c:2057 udp_queue_rcv_skb+0xb5/0x400 net/ipv4/udp.c:2074 udp_unicast_rcv_skb.isra.0+0x7e/0x1c0 net/ipv4/udp.c:2233 __udp4_lib_rcv+0xa44/0x17c0 net/ipv4/udp.c:2300 udp_rcv+0x2b/0x40 net/ipv4/udp.c:2470 ip_protocol_deliver_rcu+0x4d/0x420 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5010 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5124 process_backlog+0x1d3/0x420 net/core/dev.c:5955 read to 0xffff888122474b50 of 8 bytes by task 8921 on cpu 1: skb_queue_empty include/linux/skbuff.h:1494 [inline] __skb_recv_udp+0x18d/0x500 net/ipv4/udp.c:1653 udp_recvmsg+0xe1/0xb10 net/ipv4/udp.c:1712 inet_recvmsg+0xbb/0x250 net/ipv4/af_inet.c:838 sock_recvmsg_nosec+0x5c/0x70 net/socket.c:871 ___sys_recvmsg+0x1a0/0x3e0 net/socket.c:2480 do_recvmmsg+0x19a/0x5c0 net/socket.c:2601 __sys_recvmmsg+0x1ef/0x200 net/socket.c:2680 __do_sys_recvmmsg net/socket.c:2703 [inline] __se_sys_recvmmsg net/socket.c:2696 [inline] __x64_sys_recvmmsg+0x89/0xb0 net/socket.c:2696 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 8921 Comm: syz-executor.4 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-10-24 13:44:49 +08:00
if (!skb && !skb_queue_empty_lockless(sk_queue)) {
spin_lock(&sk_queue->lock);
skb_queue_splice_tail_init(sk_queue, rcvq);
spin_unlock(&sk_queue->lock);
skb = __first_packet_length(sk, rcvq, &total);
}
res = skb ? skb->len : -1;
if (total)
udp_rmem_release(sk, total, 1, false);
spin_unlock_bh(&rcvq->lock);
return res;
}
/*
* IOCTL requests applicable to the UDP protocol
*/
int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
switch (cmd) {
case SIOCOUTQ:
{
int amount = sk_wmem_alloc_get(sk);
return put_user(amount, (int __user *)arg);
}
case SIOCINQ:
{
int amount = max_t(int, 0, first_packet_length(sk));
return put_user(amount, (int __user *)arg);
}
default:
return -ENOIOCTLCMD;
}
return 0;
}
EXPORT_SYMBOL(udp_ioctl);
struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
int *off, int *err)
{
struct sk_buff_head *sk_queue = &sk->sk_receive_queue;
struct sk_buff_head *queue;
struct sk_buff *last;
long timeo;
int error;
queue = &udp_sk(sk)->reader_queue;
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
do {
struct sk_buff *skb;
error = sock_error(sk);
if (error)
break;
error = -EAGAIN;
do {
spin_lock_bh(&queue->lock);
skb = __skb_try_recv_from_queue(sk, queue, flags, off,
err, &last);
if (skb) {
if (!(flags & MSG_PEEK))
udp_skb_destructor(sk, skb);
spin_unlock_bh(&queue->lock);
return skb;
}
udp: use skb_queue_empty_lockless() syzbot reported a data-race [1]. We should use skb_queue_empty_lockless() to document that we are not ensuring a mutual exclusion and silence KCSAN. [1] BUG: KCSAN: data-race in __skb_recv_udp / __udp_enqueue_schedule_skb write to 0xffff888122474b50 of 8 bytes by interrupt on cpu 0: __skb_insert include/linux/skbuff.h:1852 [inline] __skb_queue_before include/linux/skbuff.h:1958 [inline] __skb_queue_tail include/linux/skbuff.h:1991 [inline] __udp_enqueue_schedule_skb+0x2c1/0x410 net/ipv4/udp.c:1470 __udp_queue_rcv_skb net/ipv4/udp.c:1940 [inline] udp_queue_rcv_one_skb+0x7bd/0xc70 net/ipv4/udp.c:2057 udp_queue_rcv_skb+0xb5/0x400 net/ipv4/udp.c:2074 udp_unicast_rcv_skb.isra.0+0x7e/0x1c0 net/ipv4/udp.c:2233 __udp4_lib_rcv+0xa44/0x17c0 net/ipv4/udp.c:2300 udp_rcv+0x2b/0x40 net/ipv4/udp.c:2470 ip_protocol_deliver_rcu+0x4d/0x420 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5010 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5124 process_backlog+0x1d3/0x420 net/core/dev.c:5955 read to 0xffff888122474b50 of 8 bytes by task 8921 on cpu 1: skb_queue_empty include/linux/skbuff.h:1494 [inline] __skb_recv_udp+0x18d/0x500 net/ipv4/udp.c:1653 udp_recvmsg+0xe1/0xb10 net/ipv4/udp.c:1712 inet_recvmsg+0xbb/0x250 net/ipv4/af_inet.c:838 sock_recvmsg_nosec+0x5c/0x70 net/socket.c:871 ___sys_recvmsg+0x1a0/0x3e0 net/socket.c:2480 do_recvmmsg+0x19a/0x5c0 net/socket.c:2601 __sys_recvmmsg+0x1ef/0x200 net/socket.c:2680 __do_sys_recvmmsg net/socket.c:2703 [inline] __se_sys_recvmmsg net/socket.c:2696 [inline] __x64_sys_recvmmsg+0x89/0xb0 net/socket.c:2696 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 8921 Comm: syz-executor.4 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-10-24 13:44:49 +08:00
if (skb_queue_empty_lockless(sk_queue)) {
spin_unlock_bh(&queue->lock);
goto busy_check;
}
/* refill the reader queue and walk it again
* keep both queues locked to avoid re-acquiring
* the sk_receive_queue lock if fwd memory scheduling
* is needed.
*/
spin_lock(&sk_queue->lock);
skb_queue_splice_tail_init(sk_queue, queue);
skb = __skb_try_recv_from_queue(sk, queue, flags, off,
err, &last);
if (skb && !(flags & MSG_PEEK))
udp_skb_dtor_locked(sk, skb);
spin_unlock(&sk_queue->lock);
spin_unlock_bh(&queue->lock);
if (skb)
return skb;
busy_check:
if (!sk_can_busy_loop(sk))
break;
sk_busy_loop(sk, flags & MSG_DONTWAIT);
udp: use skb_queue_empty_lockless() syzbot reported a data-race [1]. We should use skb_queue_empty_lockless() to document that we are not ensuring a mutual exclusion and silence KCSAN. [1] BUG: KCSAN: data-race in __skb_recv_udp / __udp_enqueue_schedule_skb write to 0xffff888122474b50 of 8 bytes by interrupt on cpu 0: __skb_insert include/linux/skbuff.h:1852 [inline] __skb_queue_before include/linux/skbuff.h:1958 [inline] __skb_queue_tail include/linux/skbuff.h:1991 [inline] __udp_enqueue_schedule_skb+0x2c1/0x410 net/ipv4/udp.c:1470 __udp_queue_rcv_skb net/ipv4/udp.c:1940 [inline] udp_queue_rcv_one_skb+0x7bd/0xc70 net/ipv4/udp.c:2057 udp_queue_rcv_skb+0xb5/0x400 net/ipv4/udp.c:2074 udp_unicast_rcv_skb.isra.0+0x7e/0x1c0 net/ipv4/udp.c:2233 __udp4_lib_rcv+0xa44/0x17c0 net/ipv4/udp.c:2300 udp_rcv+0x2b/0x40 net/ipv4/udp.c:2470 ip_protocol_deliver_rcu+0x4d/0x420 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5010 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5124 process_backlog+0x1d3/0x420 net/core/dev.c:5955 read to 0xffff888122474b50 of 8 bytes by task 8921 on cpu 1: skb_queue_empty include/linux/skbuff.h:1494 [inline] __skb_recv_udp+0x18d/0x500 net/ipv4/udp.c:1653 udp_recvmsg+0xe1/0xb10 net/ipv4/udp.c:1712 inet_recvmsg+0xbb/0x250 net/ipv4/af_inet.c:838 sock_recvmsg_nosec+0x5c/0x70 net/socket.c:871 ___sys_recvmsg+0x1a0/0x3e0 net/socket.c:2480 do_recvmmsg+0x19a/0x5c0 net/socket.c:2601 __sys_recvmmsg+0x1ef/0x200 net/socket.c:2680 __do_sys_recvmmsg net/socket.c:2703 [inline] __se_sys_recvmmsg net/socket.c:2696 [inline] __x64_sys_recvmmsg+0x89/0xb0 net/socket.c:2696 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 8921 Comm: syz-executor.4 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-10-24 13:44:49 +08:00
} while (!skb_queue_empty_lockless(sk_queue));
/* sk_queue is empty, reader_queue may contain peeked packets */
} while (timeo &&
!__skb_wait_for_more_packets(sk, &sk->sk_receive_queue,
&error, &timeo,
(struct sk_buff *)sk_queue));
*err = error;
return NULL;
}
EXPORT_SYMBOL(__skb_recv_udp);
int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
{
struct sk_buff *skb;
int err, copied;
try_again:
skb = skb_recv_udp(sk, MSG_DONTWAIT, &err);
if (!skb)
return err;
if (udp_lib_checksum_complete(skb)) {
int is_udplite = IS_UDPLITE(sk);
struct net *net = sock_net(sk);
__UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, is_udplite);
__UDP_INC_STATS(net, UDP_MIB_INERRORS, is_udplite);
atomic_inc(&sk->sk_drops);
kfree_skb(skb);
goto try_again;
}
WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk));
copied = recv_actor(sk, skb);
kfree_skb(skb);
return copied;
}
EXPORT_SYMBOL(udp_read_skb);
/*
* This should be easy, if there is something there we
* return it, otherwise we block.
*/
int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
int *addr_len)
{
struct inet_sock *inet = inet_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
struct sk_buff *skb;
unsigned int ulen, copied;
int off, err, peeking = flags & MSG_PEEK;
int is_udplite = IS_UDPLITE(sk);
bool checksum_valid = false;
if (flags & MSG_ERRQUEUE)
return ip_recv_error(sk, msg, len, addr_len);
try_again:
datagram: When peeking datagrams with offset < 0 don't skip empty skbs Due to commit e6afc8ace6dd5cef5e812f26c72579da8806f5ac ("udp: remove headers from UDP packets before queueing"), when udp packets are being peeked the requested extra offset is always 0 as there is no need to skip the udp header. However, when the offset is 0 and the next skb is of length 0, it is only returned once. The behaviour can be seen with the following python script: from socket import *; f=socket(AF_INET6, SOCK_DGRAM | SOCK_NONBLOCK, 0); g=socket(AF_INET6, SOCK_DGRAM | SOCK_NONBLOCK, 0); f.bind(('::', 0)); addr=('::1', f.getsockname()[1]); g.sendto(b'', addr) g.sendto(b'b', addr) print(f.recvfrom(10, MSG_PEEK)); print(f.recvfrom(10, MSG_PEEK)); Where the expected output should be the empty string twice. Instead, make sk_peek_offset return negative values, and pass those values to __skb_try_recv_datagram/__skb_try_recv_from_queue. If the passed offset to __skb_try_recv_from_queue is negative, the checked skb is never skipped. __skb_try_recv_from_queue will then ensure the offset is reset back to 0 if a peek is requested without an offset, unless no packets are found. Also simplify the if condition in __skb_try_recv_from_queue. If _off is greater then 0, and off is greater then or equal to skb->len, then (_off || skb->len) must always be true assuming skb->len >= 0 is always true. Also remove a redundant check around a call to sk_peek_offset in af_unix.c, as it double checked if MSG_PEEK was set in the flags. V2: - Moved the negative fixup into __skb_try_recv_from_queue, and remove now redundant checks - Fix peeking in udp{,v6}_recvmsg to report the right value when the offset is 0 V3: - Marked new branch in __skb_try_recv_from_queue as unlikely. Signed-off-by: Matthew Dawson <matthew@mjdsystems.ca> Acked-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-19 03:04:54 +08:00
off = sk_peek_offset(sk, flags);
skb = __skb_recv_udp(sk, flags, &off, &err);
if (!skb)
return err;
ulen = udp_skb_len(skb);
copied = len;
if (copied > ulen - off)
copied = ulen - off;
else if (copied < ulen)
msg->msg_flags |= MSG_TRUNC;
/*
* If checksum is needed at all, try to do it while copying the
* data. If the data is truncated, or if we only want a partial
* coverage checksum (UDP-Lite), do it before the copy.
*/
if (copied < ulen || peeking ||
(is_udplite && UDP_SKB_CB(skb)->partial_cov)) {
checksum_valid = udp_skb_csum_unnecessary(skb) ||
!__udp_lib_checksum_complete(skb);
if (!checksum_valid)
goto csum_copy_err;
}
if (checksum_valid || udp_skb_csum_unnecessary(skb)) {
if (udp_skb_is_linear(skb))
err = copy_linear_skb(skb, copied, off, &msg->msg_iter);
else
err = skb_copy_datagram_msg(skb, off, msg, copied);
} else {
err = skb_copy_and_csum_datagram_msg(skb, off, msg);
if (err == -EINVAL)
goto csum_copy_err;
}
if (unlikely(err)) {
if (!peeking) {
atomic_inc(&sk->sk_drops);
UDP_INC_STATS(sock_net(sk),
UDP_MIB_INERRORS, is_udplite);
}
kfree_skb(skb);
return err;
}
if (!peeking)
UDP_INC_STATS(sock_net(sk),
UDP_MIB_INDATAGRAMS, is_udplite);
sock_recv_cmsgs(msg, sk, skb);
/* Copy the address. */
if (sin) {
sin->sin_family = AF_INET;
sin->sin_port = udp_hdr(skb)->source;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
*addr_len = sizeof(*sin);
bpf: fix unconnected udp hooks Intention of cgroup bind/connect/sendmsg BPF hooks is to act transparently to applications as also stated in original motivation in 7828f20e3779 ("Merge branch 'bpf-cgroup-bind-connect'"). When recently integrating the latter two hooks into Cilium to enable host based load-balancing with Kubernetes, I ran into the issue that pods couldn't start up as DNS got broken. Kubernetes typically sets up DNS as a service and is thus subject to load-balancing. Upon further debugging, it turns out that the cgroupv2 sendmsg BPF hooks API is currently insufficient and thus not usable as-is for standard applications shipped with most distros. To break down the issue we ran into with a simple example: # cat /etc/resolv.conf nameserver 147.75.207.207 nameserver 147.75.207.208 For the purpose of a simple test, we set up above IPs as service IPs and transparently redirect traffic to a different DNS backend server for that node: # cilium service list ID Frontend Backend 1 147.75.207.207:53 1 => 8.8.8.8:53 2 147.75.207.208:53 1 => 8.8.8.8:53 The attached BPF program is basically selecting one of the backends if the service IP/port matches on the cgroup hook. DNS breaks here, because the hooks are not transparent enough to applications which have built-in msg_name address checks: # nslookup 1.1.1.1 ;; reply from unexpected source: 8.8.8.8#53, expected 147.75.207.207#53 ;; reply from unexpected source: 8.8.8.8#53, expected 147.75.207.208#53 ;; reply from unexpected source: 8.8.8.8#53, expected 147.75.207.207#53 [...] ;; connection timed out; no servers could be reached # dig 1.1.1.1 ;; reply from unexpected source: 8.8.8.8#53, expected 147.75.207.207#53 ;; reply from unexpected source: 8.8.8.8#53, expected 147.75.207.208#53 ;; reply from unexpected source: 8.8.8.8#53, expected 147.75.207.207#53 [...] ; <<>> DiG 9.11.3-1ubuntu1.7-Ubuntu <<>> 1.1.1.1 ;; global options: +cmd ;; connection timed out; no servers could be reached For comparison, if none of the service IPs is used, and we tell nslookup to use 8.8.8.8 directly it works just fine, of course: # nslookup 1.1.1.1 8.8.8.8 1.1.1.1.in-addr.arpa name = one.one.one.one. In order to fix this and thus act more transparent to the application, this needs reverse translation on recvmsg() side. A minimal fix for this API is to add similar recvmsg() hooks behind the BPF cgroups static key such that the program can track state and replace the current sockaddr_in{,6} with the original service IP. From BPF side, this basically tracks the service tuple plus socket cookie in an LRU map where the reverse NAT can then be retrieved via map value as one example. Side-note: the BPF cgroups static key should be converted to a per-hook static key in future. Same example after this fix: # cilium service list ID Frontend Backend 1 147.75.207.207:53 1 => 8.8.8.8:53 2 147.75.207.208:53 1 => 8.8.8.8:53 Lookups work fine now: # nslookup 1.1.1.1 1.1.1.1.in-addr.arpa name = one.one.one.one. Authoritative answers can be found from: # dig 1.1.1.1 ; <<>> DiG 9.11.3-1ubuntu1.7-Ubuntu <<>> 1.1.1.1 ;; global options: +cmd ;; Got answer: ;; ->>HEADER<<- opcode: QUERY, status: NXDOMAIN, id: 51550 ;; flags: qr rd ra ad; QUERY: 1, ANSWER: 0, AUTHORITY: 1, ADDITIONAL: 1 ;; OPT PSEUDOSECTION: ; EDNS: version: 0, flags:; udp: 512 ;; QUESTION SECTION: ;1.1.1.1. IN A ;; AUTHORITY SECTION: . 23426 IN SOA a.root-servers.net. nstld.verisign-grs.com. 2019052001 1800 900 604800 86400 ;; Query time: 17 msec ;; SERVER: 147.75.207.207#53(147.75.207.207) ;; WHEN: Tue May 21 12:59:38 UTC 2019 ;; MSG SIZE rcvd: 111 And from an actual packet level it shows that we're using the back end server when talking via 147.75.207.20{7,8} front end: # tcpdump -i any udp [...] 12:59:52.698732 IP foo.42011 > google-public-dns-a.google.com.domain: 18803+ PTR? 1.1.1.1.in-addr.arpa. (38) 12:59:52.698735 IP foo.42011 > google-public-dns-a.google.com.domain: 18803+ PTR? 1.1.1.1.in-addr.arpa. (38) 12:59:52.701208 IP google-public-dns-a.google.com.domain > foo.42011: 18803 1/0/0 PTR one.one.one.one. (67) 12:59:52.701208 IP google-public-dns-a.google.com.domain > foo.42011: 18803 1/0/0 PTR one.one.one.one. (67) [...] In order to be flexible and to have same semantics as in sendmsg BPF programs, we only allow return codes in [1,1] range. In the sendmsg case the program is called if msg->msg_name is present which can be the case in both, connected and unconnected UDP. The former only relies on the sockaddr_in{,6} passed via connect(2) if passed msg->msg_name was NULL. Therefore, on recvmsg side, we act in similar way to call into the BPF program whenever a non-NULL msg->msg_name was passed independent of sk->sk_state being TCP_ESTABLISHED or not. Note that for TCP case, the msg->msg_name is ignored in the regular recvmsg path and therefore not relevant. For the case of ip{,v6}_recv_error() paths, picked up via MSG_ERRQUEUE, the hook is not called. This is intentional as it aligns with the same semantics as in case of TCP cgroup BPF hooks right now. This might be better addressed in future through a different bpf_attach_type such that this case can be distinguished from the regular recvmsg paths, for example. Fixes: 1cedee13d25a ("bpf: Hooks for sys_sendmsg") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrey Ignatov <rdna@fb.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Martynas Pumputis <m@lambda.lt> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-06-07 07:48:57 +08:00
BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk,
(struct sockaddr *)sin);
}
if (udp_sk(sk)->gro_enabled)
udp_cmsg_recv(msg, sk, skb);
if (inet->cmsg_flags)
ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off);
err = copied;
if (flags & MSG_TRUNC)
err = ulen;
skb_consume_udp(sk, skb, peeking ? -err : err);
return err;
csum_copy_err:
if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags,
udp_skb_destructor)) {
UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
}
kfree_skb(skb);
/* starting over for a new packet, but check if we need to yield */
cond_resched();
msg->msg_flags &= ~MSG_TRUNC;
goto try_again;
}
bpf: Hooks for sys_connect == The problem == See description of the problem in the initial patch of this patch set. == The solution == The patch provides much more reliable in-kernel solution for the 2nd part of the problem: making outgoing connecttion from desired IP. It adds new attach types `BPF_CGROUP_INET4_CONNECT` and `BPF_CGROUP_INET6_CONNECT` for program type `BPF_PROG_TYPE_CGROUP_SOCK_ADDR` that can be used to override both source and destination of a connection at connect(2) time. Local end of connection can be bound to desired IP using newly introduced BPF-helper `bpf_bind()`. It allows to bind to only IP though, and doesn't support binding to port, i.e. leverages `IP_BIND_ADDRESS_NO_PORT` socket option. There are two reasons for this: * looking for a free port is expensive and can affect performance significantly; * there is no use-case for port. As for remote end (`struct sockaddr *` passed by user), both parts of it can be overridden, remote IP and remote port. It's useful if an application inside cgroup wants to connect to another application inside same cgroup or to itself, but knows nothing about IP assigned to the cgroup. Support is added for IPv4 and IPv6, for TCP and UDP. IPv4 and IPv6 have separate attach types for same reason as sys_bind hooks, i.e. to prevent reading from / writing to e.g. user_ip6 fields when user passes sockaddr_in since it'd be out-of-bound. == Implementation notes == The patch introduces new field in `struct proto`: `pre_connect` that is a pointer to a function with same signature as `connect` but is called before it. The reason is in some cases BPF hooks should be called way before control is passed to `sk->sk_prot->connect`. Specifically `inet_dgram_connect` autobinds socket before calling `sk->sk_prot->connect` and there is no way to call `bpf_bind()` from hooks from e.g. `ip4_datagram_connect` or `ip6_datagram_connect` since it'd cause double-bind. On the other hand `proto.pre_connect` provides a flexible way to add BPF hooks for connect only for necessary `proto` and call them at desired time before `connect`. Since `bpf_bind()` is allowed to bind only to IP and autobind in `inet_dgram_connect` binds only port there is no chance of double-bind. bpf_bind() sets `force_bind_address_no_port` to bind to only IP despite of value of `bind_address_no_port` socket field. bpf_bind() sets `with_lock` to `false` when calling to __inet_bind() and __inet6_bind() since all call-sites, where bpf_bind() is called, already hold socket lock. Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-31 06:08:05 +08:00
int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
/* This check is replicated from __ip4_datagram_connect() and
* intended to prevent BPF program called below from accessing bytes
* that are out of the bound specified by user in addr_len.
*/
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr);
}
EXPORT_SYMBOL(udp_pre_connect);
int __udp_disconnect(struct sock *sk, int flags)
{
struct inet_sock *inet = inet_sk(sk);
/*
* 1003.1g - break association.
*/
sk->sk_state = TCP_CLOSE;
inet->inet_daddr = 0;
inet->inet_dport = 0;
sock_rps_reset_rxhash(sk);
sk->sk_bound_dev_if = 0;
if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) {
inet_reset_saddr(sk);
if (sk->sk_prot->rehash &&
(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
sk->sk_prot->rehash(sk);
}
if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) {
sk->sk_prot->unhash(sk);
inet->inet_sport = 0;
}
sk_dst_reset(sk);
return 0;
}
EXPORT_SYMBOL(__udp_disconnect);
int udp_disconnect(struct sock *sk, int flags)
{
lock_sock(sk);
__udp_disconnect(sk, flags);
release_sock(sk);
return 0;
}
EXPORT_SYMBOL(udp_disconnect);
void udp_lib_unhash(struct sock *sk)
{
if (sk_hashed(sk)) {
struct udp_table *udptable = udp_get_table_prot(sk);
struct udp_hslot *hslot, *hslot2;
hslot = udp_hashslot(udptable, sock_net(sk),
udp_sk(sk)->udp_port_hash);
hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
spin_lock_bh(&hslot->lock);
if (rcu_access_pointer(sk->sk_reuseport_cb))
reuseport_detach_sock(sk);
if (sk_del_node_init_rcu(sk)) {
hslot->count--;
inet_sk(sk)->inet_num = 0;
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
spin_lock(&hslot2->lock);
hlist_del_init_rcu(&udp_sk(sk)->udp_portaddr_node);
hslot2->count--;
spin_unlock(&hslot2->lock);
}
spin_unlock_bh(&hslot->lock);
}
}
EXPORT_SYMBOL(udp_lib_unhash);
/*
* inet_rcv_saddr was changed, we must rehash secondary hash
*/
void udp_lib_rehash(struct sock *sk, u16 newhash)
{
if (sk_hashed(sk)) {
struct udp_table *udptable = udp_get_table_prot(sk);
struct udp_hslot *hslot, *hslot2, *nhslot2;
hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
nhslot2 = udp_hashslot2(udptable, newhash);
udp_sk(sk)->udp_portaddr_hash = newhash;
if (hslot2 != nhslot2 ||
rcu_access_pointer(sk->sk_reuseport_cb)) {
hslot = udp_hashslot(udptable, sock_net(sk),
udp_sk(sk)->udp_port_hash);
/* we must lock primary chain too */
spin_lock_bh(&hslot->lock);
if (rcu_access_pointer(sk->sk_reuseport_cb))
reuseport_detach_sock(sk);
if (hslot2 != nhslot2) {
spin_lock(&hslot2->lock);
hlist_del_init_rcu(&udp_sk(sk)->udp_portaddr_node);
hslot2->count--;
spin_unlock(&hslot2->lock);
spin_lock(&nhslot2->lock);
hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
&nhslot2->head);
nhslot2->count++;
spin_unlock(&nhslot2->lock);
}
spin_unlock_bh(&hslot->lock);
}
}
}
EXPORT_SYMBOL(udp_lib_rehash);
void udp_v4_rehash(struct sock *sk)
{
u16 new_hash = ipv4_portaddr_hash(sock_net(sk),
inet_sk(sk)->inet_rcv_saddr,
inet_sk(sk)->inet_num);
udp_lib_rehash(sk, new_hash);
}
static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
rfs: Receive Flow Steering This patch implements receive flow steering (RFS). RFS steers received packets for layer 3 and 4 processing to the CPU where the application for the corresponding flow is running. RFS is an extension of Receive Packet Steering (RPS). The basic idea of RFS is that when an application calls recvmsg (or sendmsg) the application's running CPU is stored in a hash table that is indexed by the connection's rxhash which is stored in the socket structure. The rxhash is passed in skb's received on the connection from netif_receive_skb. For each received packet, the associated rxhash is used to look up the CPU in the hash table, if a valid CPU is set then the packet is steered to that CPU using the RPS mechanisms. The convolution of the simple approach is that it would potentially allow OOO packets. If threads are thrashing around CPUs or multiple threads are trying to read from the same sockets, a quickly changing CPU value in the hash table could cause rampant OOO packets-- we consider this a non-starter. To avoid OOO packets, this solution implements two types of hash tables: rps_sock_flow_table and rps_dev_flow_table. rps_sock_table is a global hash table. Each entry is just a CPU number and it is populated in recvmsg and sendmsg as described above. This table contains the "desired" CPUs for flows. rps_dev_flow_table is specific to each device queue. Each entry contains a CPU and a tail queue counter. The CPU is the "current" CPU for a matching flow. The tail queue counter holds the value of a tail queue counter for the associated CPU's backlog queue at the time of last enqueue for a flow matching the entry. Each backlog queue has a queue head counter which is incremented on dequeue, and so a queue tail counter is computed as queue head count + queue length. When a packet is enqueued on a backlog queue, the current value of the queue tail counter is saved in the hash entry of the rps_dev_flow_table. And now the trick: when selecting the CPU for RPS (get_rps_cpu) the rps_sock_flow table and the rps_dev_flow table for the RX queue are consulted. When the desired CPU for the flow (found in the rps_sock_flow table) does not match the current CPU (found in the rps_dev_flow table), the current CPU is changed to the desired CPU if one of the following is true: - The current CPU is unset (equal to RPS_NO_CPU) - Current CPU is offline - The current CPU's queue head counter >= queue tail counter in the rps_dev_flow table. This checks if the queue tail has advanced beyond the last packet that was enqueued using this table entry. This guarantees that all packets queued using this entry have been dequeued, thus preserving in order delivery. Making each queue have its own rps_dev_flow table has two advantages: 1) the tail queue counters will be written on each receive, so keeping the table local to interrupting CPU s good for locality. 2) this allows lockless access to the table-- the CPU number and queue tail counter need to be accessed together under mutual exclusion from netif_receive_skb, we assume that this is only called from device napi_poll which is non-reentrant. This patch implements RFS for TCP and connected UDP sockets. It should be usable for other flow oriented protocols. There are two configuration parameters for RFS. The "rps_flow_entries" kernel init parameter sets the number of entries in the rps_sock_flow_table, the per rxqueue sysfs entry "rps_flow_cnt" contains the number of entries in the rps_dev_flow table for the rxqueue. Both are rounded to power of two. The obvious benefit of RFS (over just RPS) is that it achieves CPU locality between the receive processing for a flow and the applications processing; this can result in increased performance (higher pps, lower latency). The benefits of RFS are dependent on cache hierarchy, application load, and other factors. On simple benchmarks, we don't necessarily see improvement and sometimes see degradation. However, for more complex benchmarks and for applications where cache pressure is much higher this technique seems to perform very well. Below are some benchmark results which show the potential benfit of this patch. The netperf test has 500 instances of netperf TCP_RR test with 1 byte req. and resp. The RPC test is an request/response test similar in structure to netperf RR test ith 100 threads on each host, but does more work in userspace that netperf. e1000e on 8 core Intel No RFS or RPS 104K tps at 30% CPU No RFS (best RPS config): 290K tps at 63% CPU RFS 303K tps at 61% CPU RPC test tps CPU% 50/90/99% usec latency Latency StdDev No RFS/RPS 103K 48% 757/900/3185 4472.35 RPS only: 174K 73% 415/993/2468 491.66 RFS 223K 73% 379/651/1382 315.61 Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-17 07:01:27 +08:00
int rc;
if (inet_sk(sk)->inet_daddr) {
sock_rps_save_rxhash(sk, skb);
sk_mark_napi_id(sk, skb);
sk_incoming_cpu_update(sk);
} else {
sk_mark_napi_id_once(sk, skb);
}
rfs: Receive Flow Steering This patch implements receive flow steering (RFS). RFS steers received packets for layer 3 and 4 processing to the CPU where the application for the corresponding flow is running. RFS is an extension of Receive Packet Steering (RPS). The basic idea of RFS is that when an application calls recvmsg (or sendmsg) the application's running CPU is stored in a hash table that is indexed by the connection's rxhash which is stored in the socket structure. The rxhash is passed in skb's received on the connection from netif_receive_skb. For each received packet, the associated rxhash is used to look up the CPU in the hash table, if a valid CPU is set then the packet is steered to that CPU using the RPS mechanisms. The convolution of the simple approach is that it would potentially allow OOO packets. If threads are thrashing around CPUs or multiple threads are trying to read from the same sockets, a quickly changing CPU value in the hash table could cause rampant OOO packets-- we consider this a non-starter. To avoid OOO packets, this solution implements two types of hash tables: rps_sock_flow_table and rps_dev_flow_table. rps_sock_table is a global hash table. Each entry is just a CPU number and it is populated in recvmsg and sendmsg as described above. This table contains the "desired" CPUs for flows. rps_dev_flow_table is specific to each device queue. Each entry contains a CPU and a tail queue counter. The CPU is the "current" CPU for a matching flow. The tail queue counter holds the value of a tail queue counter for the associated CPU's backlog queue at the time of last enqueue for a flow matching the entry. Each backlog queue has a queue head counter which is incremented on dequeue, and so a queue tail counter is computed as queue head count + queue length. When a packet is enqueued on a backlog queue, the current value of the queue tail counter is saved in the hash entry of the rps_dev_flow_table. And now the trick: when selecting the CPU for RPS (get_rps_cpu) the rps_sock_flow table and the rps_dev_flow table for the RX queue are consulted. When the desired CPU for the flow (found in the rps_sock_flow table) does not match the current CPU (found in the rps_dev_flow table), the current CPU is changed to the desired CPU if one of the following is true: - The current CPU is unset (equal to RPS_NO_CPU) - Current CPU is offline - The current CPU's queue head counter >= queue tail counter in the rps_dev_flow table. This checks if the queue tail has advanced beyond the last packet that was enqueued using this table entry. This guarantees that all packets queued using this entry have been dequeued, thus preserving in order delivery. Making each queue have its own rps_dev_flow table has two advantages: 1) the tail queue counters will be written on each receive, so keeping the table local to interrupting CPU s good for locality. 2) this allows lockless access to the table-- the CPU number and queue tail counter need to be accessed together under mutual exclusion from netif_receive_skb, we assume that this is only called from device napi_poll which is non-reentrant. This patch implements RFS for TCP and connected UDP sockets. It should be usable for other flow oriented protocols. There are two configuration parameters for RFS. The "rps_flow_entries" kernel init parameter sets the number of entries in the rps_sock_flow_table, the per rxqueue sysfs entry "rps_flow_cnt" contains the number of entries in the rps_dev_flow table for the rxqueue. Both are rounded to power of two. The obvious benefit of RFS (over just RPS) is that it achieves CPU locality between the receive processing for a flow and the applications processing; this can result in increased performance (higher pps, lower latency). The benefits of RFS are dependent on cache hierarchy, application load, and other factors. On simple benchmarks, we don't necessarily see improvement and sometimes see degradation. However, for more complex benchmarks and for applications where cache pressure is much higher this technique seems to perform very well. Below are some benchmark results which show the potential benfit of this patch. The netperf test has 500 instances of netperf TCP_RR test with 1 byte req. and resp. The RPC test is an request/response test similar in structure to netperf RR test ith 100 threads on each host, but does more work in userspace that netperf. e1000e on 8 core Intel No RFS or RPS 104K tps at 30% CPU No RFS (best RPS config): 290K tps at 63% CPU RFS 303K tps at 61% CPU RPC test tps CPU% 50/90/99% usec latency Latency StdDev No RFS/RPS 103K 48% 757/900/3185 4472.35 RPS only: 174K 73% 415/993/2468 491.66 RFS 223K 73% 379/651/1382 315.61 Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-17 07:01:27 +08:00
rc = __udp_enqueue_schedule_skb(sk, skb);
if (rc < 0) {
int is_udplite = IS_UDPLITE(sk);
int drop_reason;
/* Note that an ENOMEM error is charged twice */
if (rc == -ENOMEM) {
UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS,
is_udplite);
drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF;
} else {
UDP_INC_STATS(sock_net(sk), UDP_MIB_MEMERRORS,
is_udplite);
drop_reason = SKB_DROP_REASON_PROTO_MEM;
}
UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
kfree_skb_reason(skb, drop_reason);
trace_udp_fail_queue_rcv_skb(rc, sk);
return -1;
}
return 0;
}
/* returns:
* -1: error
* 0: success
* >0: "udp encap" protocol resubmission
*
* Note that in the success and error cases, the skb is assumed to
* have either been requeued or freed.
*/
static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
{
int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
struct udp_sock *up = udp_sk(sk);
int is_udplite = IS_UDPLITE(sk);
/*
* Charge it to the socket, dropping if the queue is full.
*/
if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) {
drop_reason = SKB_DROP_REASON_XFRM_POLICY;
goto drop;
}
nf_reset_ct(skb);
if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) {
int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
/*
* This is an encapsulation socket so pass the skb to
* the socket's udp_encap_rcv() hook. Otherwise, just
* fall through and pass this up the UDP socket.
* up->encap_rcv() returns the following value:
* =0 if skb was successfully passed to the encap
* handler or was discarded by it.
* >0 if skb should be passed on to UDP.
* <0 if skb should be resubmitted as proto -N
*/
/* if we're overly short, let UDP handle it */
locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE() Please do not apply this to mainline directly, instead please re-run the coccinelle script shown below and apply its output. For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't harmful, and changing them results in churn. However, for some features, the read/write distinction is critical to correct operation. To distinguish these cases, separate read/write accessors must be used. This patch migrates (most) remaining ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following coccinelle script: ---- // Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and // WRITE_ONCE() // $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-24 05:07:29 +08:00
encap_rcv = READ_ONCE(up->encap_rcv);
if (encap_rcv) {
int ret;
/* Verify checksum before giving to encap */
if (udp_lib_checksum_complete(skb))
goto csum_error;
ret = encap_rcv(sk, skb);
if (ret <= 0) {
__UDP_INC_STATS(sock_net(sk),
UDP_MIB_INDATAGRAMS,
is_udplite);
return -ret;
}
}
/* FALLTHROUGH -- it's a UDP Packet */
}
/*
* UDP-Lite specific tests, ignored on UDP sockets
*/
if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) {
/*
* MIB statistics other than incrementing the error count are
* disabled for the following two types of errors: these depend
* on the application settings, not on the functioning of the
* protocol stack as such.
*
* RFC 3828 here recommends (sec 3.3): "There should also be a
* way ... to ... at least let the receiving application block
* delivery of packets with coverage values less than a value
* provided by the application."
*/
if (up->pcrlen == 0) { /* full coverage was set */
net_dbg_ratelimited("UDPLite: partial coverage %d while full coverage %d requested\n",
UDP_SKB_CB(skb)->cscov, skb->len);
goto drop;
}
/* The next case involves violating the min. coverage requested
* by the receiver. This is subtle: if receiver wants x and x is
* greater than the buffersize/MTU then receiver will complain
* that it wants x while sender emits packets of smaller size y.
* Therefore the above ...()->partial_cov statement is essential.
*/
if (UDP_SKB_CB(skb)->cscov < up->pcrlen) {
net_dbg_ratelimited("UDPLite: coverage %d too small, need min %d\n",
UDP_SKB_CB(skb)->cscov, up->pcrlen);
goto drop;
}
}
prefetch(&sk->sk_rmem_alloc);
if (rcu_access_pointer(sk->sk_filter) &&
udp_lib_checksum_complete(skb))
goto csum_error;
if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) {
drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
goto drop;
}
udp_csum_pull_header(skb);
ipv4_pktinfo_prepare(sk, skb);
return __udp_queue_rcv_skb(sk, skb);
csum_error:
drop_reason = SKB_DROP_REASON_UDP_CSUM;
__UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
drop:
__UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
atomic_inc(&sk->sk_drops);
kfree_skb_reason(skb, drop_reason);
return -1;
}
static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
struct sk_buff *next, *segs;
int ret;
if (likely(!udp_unexpected_gso(sk, skb)))
return udp_queue_rcv_one_skb(sk, skb);
BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_GSO_CB_OFFSET);
__skb_push(skb, -skb_mac_offset(skb));
segs = udp_rcv_segment(sk, skb, true);
skb_list_walk_safe(segs, skb, next) {
__skb_pull(skb, skb_transport_offset(skb));
udp: fixup csum for GSO receive slow path When UDP packets generated locally by a socket with UDP_SEGMENT traverse the following path: UDP tunnel(xmit) -> veth (segmentation) -> veth (gro) -> UDP tunnel (rx) -> UDP socket (no UDP_GRO) ip_summed will be set to CHECKSUM_PARTIAL at creation time and such checksum mode will be preserved in the above path up to the UDP tunnel receive code where we have: __iptunnel_pull_header() -> skb_pull_rcsum() -> skb_postpull_rcsum() -> __skb_postpull_rcsum() The latter will convert the skb to CHECKSUM_NONE. The UDP GSO packet will be later segmented as part of the rx socket receive operation, and will present a CHECKSUM_NONE after segmentation. Additionally the segmented packets UDP CB still refers to the original GSO packet len. Overall that causes unexpected/wrong csum validation errors later in the UDP receive path. We could possibly address the issue with some additional checks and csum mangling in the UDP tunnel code. Since the issue affects only this UDP receive slow path, let's set a suitable csum status there. Note that SKB_GSO_UDP_L4 or SKB_GSO_FRAGLIST packets lacking an UDP encapsulation present a valid checksum when landing to udp_queue_rcv_skb(), as the UDP checksum has been validated by the GRO engine. v2 -> v3: - even more verbose commit message and comments v1 -> v2: - restrict the csum update to the packets strictly needing them - hopefully clarify the commit message and code comments Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-03-30 18:28:49 +08:00
udp_post_segment_fix_csum(skb);
ret = udp_queue_rcv_one_skb(sk, skb);
if (ret > 0)
ip_protocol_deliver_rcu(dev_net(skb->dev), skb, ret);
}
return 0;
}
/* For TCP sockets, sk_rx_dst is protected by socket lock
* For UDP, we use xchg() to guard against concurrent changes.
*/
bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
{
struct dst_entry *old;
if (dst_hold_safe(dst)) {
inet: fully convert sk->sk_rx_dst to RCU rules syzbot reported various issues around early demux, one being included in this changelog [1] sk->sk_rx_dst is using RCU protection without clearly documenting it. And following sequences in tcp_v4_do_rcv()/tcp_v6_do_rcv() are not following standard RCU rules. [a] dst_release(dst); [b] sk->sk_rx_dst = NULL; They look wrong because a delete operation of RCU protected pointer is supposed to clear the pointer before the call_rcu()/synchronize_rcu() guarding actual memory freeing. In some cases indeed, dst could be freed before [b] is done. We could cheat by clearing sk_rx_dst before calling dst_release(), but this seems the right time to stick to standard RCU annotations and debugging facilities. [1] BUG: KASAN: use-after-free in dst_check include/net/dst.h:470 [inline] BUG: KASAN: use-after-free in tcp_v4_early_demux+0x95b/0x960 net/ipv4/tcp_ipv4.c:1792 Read of size 2 at addr ffff88807f1cb73a by task syz-executor.5/9204 CPU: 0 PID: 9204 Comm: syz-executor.5 Not tainted 5.16.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description.constprop.0.cold+0x8d/0x320 mm/kasan/report.c:247 __kasan_report mm/kasan/report.c:433 [inline] kasan_report.cold+0x83/0xdf mm/kasan/report.c:450 dst_check include/net/dst.h:470 [inline] tcp_v4_early_demux+0x95b/0x960 net/ipv4/tcp_ipv4.c:1792 ip_rcv_finish_core.constprop.0+0x15de/0x1e80 net/ipv4/ip_input.c:340 ip_list_rcv_finish.constprop.0+0x1b2/0x6e0 net/ipv4/ip_input.c:583 ip_sublist_rcv net/ipv4/ip_input.c:609 [inline] ip_list_rcv+0x34e/0x490 net/ipv4/ip_input.c:644 __netif_receive_skb_list_ptype net/core/dev.c:5508 [inline] __netif_receive_skb_list_core+0x549/0x8e0 net/core/dev.c:5556 __netif_receive_skb_list net/core/dev.c:5608 [inline] netif_receive_skb_list_internal+0x75e/0xd80 net/core/dev.c:5699 gro_normal_list net/core/dev.c:5853 [inline] gro_normal_list net/core/dev.c:5849 [inline] napi_complete_done+0x1f1/0x880 net/core/dev.c:6590 virtqueue_napi_complete drivers/net/virtio_net.c:339 [inline] virtnet_poll+0xca2/0x11b0 drivers/net/virtio_net.c:1557 __napi_poll+0xaf/0x440 net/core/dev.c:7023 napi_poll net/core/dev.c:7090 [inline] net_rx_action+0x801/0xb40 net/core/dev.c:7177 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 invoke_softirq kernel/softirq.c:432 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:637 irq_exit_rcu+0x5/0x20 kernel/softirq.c:649 common_interrupt+0x52/0xc0 arch/x86/kernel/irq.c:240 asm_common_interrupt+0x1e/0x40 arch/x86/include/asm/idtentry.h:629 RIP: 0033:0x7f5e972bfd57 Code: 39 d1 73 14 0f 1f 80 00 00 00 00 48 8b 50 f8 48 83 e8 08 48 39 ca 77 f3 48 39 c3 73 3e 48 89 13 48 8b 50 f8 48 89 38 49 8b 0e <48> 8b 3e 48 83 c3 08 48 83 c6 08 eb bc 48 39 d1 72 9e 48 39 d0 73 RSP: 002b:00007fff8a413210 EFLAGS: 00000283 RAX: 00007f5e97108990 RBX: 00007f5e97108338 RCX: ffffffff81d3aa45 RDX: ffffffff81d3aa45 RSI: 00007f5e97108340 RDI: ffffffff81d3aa45 RBP: 00007f5e97107eb8 R08: 00007f5e97108d88 R09: 0000000093c2e8d9 R10: 0000000000000000 R11: 0000000000000000 R12: 00007f5e97107eb0 R13: 00007f5e97108338 R14: 00007f5e97107ea8 R15: 0000000000000019 </TASK> Allocated by task 13: kasan_save_stack+0x1e/0x50 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:434 [inline] __kasan_slab_alloc+0x90/0xc0 mm/kasan/common.c:467 kasan_slab_alloc include/linux/kasan.h:259 [inline] slab_post_alloc_hook mm/slab.h:519 [inline] slab_alloc_node mm/slub.c:3234 [inline] slab_alloc mm/slub.c:3242 [inline] kmem_cache_alloc+0x202/0x3a0 mm/slub.c:3247 dst_alloc+0x146/0x1f0 net/core/dst.c:92 rt_dst_alloc+0x73/0x430 net/ipv4/route.c:1613 ip_route_input_slow+0x1817/0x3a20 net/ipv4/route.c:2340 ip_route_input_rcu net/ipv4/route.c:2470 [inline] ip_route_input_noref+0x116/0x2a0 net/ipv4/route.c:2415 ip_rcv_finish_core.constprop.0+0x288/0x1e80 net/ipv4/ip_input.c:354 ip_list_rcv_finish.constprop.0+0x1b2/0x6e0 net/ipv4/ip_input.c:583 ip_sublist_rcv net/ipv4/ip_input.c:609 [inline] ip_list_rcv+0x34e/0x490 net/ipv4/ip_input.c:644 __netif_receive_skb_list_ptype net/core/dev.c:5508 [inline] __netif_receive_skb_list_core+0x549/0x8e0 net/core/dev.c:5556 __netif_receive_skb_list net/core/dev.c:5608 [inline] netif_receive_skb_list_internal+0x75e/0xd80 net/core/dev.c:5699 gro_normal_list net/core/dev.c:5853 [inline] gro_normal_list net/core/dev.c:5849 [inline] napi_complete_done+0x1f1/0x880 net/core/dev.c:6590 virtqueue_napi_complete drivers/net/virtio_net.c:339 [inline] virtnet_poll+0xca2/0x11b0 drivers/net/virtio_net.c:1557 __napi_poll+0xaf/0x440 net/core/dev.c:7023 napi_poll net/core/dev.c:7090 [inline] net_rx_action+0x801/0xb40 net/core/dev.c:7177 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 Freed by task 13: kasan_save_stack+0x1e/0x50 mm/kasan/common.c:38 kasan_set_track+0x21/0x30 mm/kasan/common.c:46 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:370 ____kasan_slab_free mm/kasan/common.c:366 [inline] ____kasan_slab_free mm/kasan/common.c:328 [inline] __kasan_slab_free+0xff/0x130 mm/kasan/common.c:374 kasan_slab_free include/linux/kasan.h:235 [inline] slab_free_hook mm/slub.c:1723 [inline] slab_free_freelist_hook+0x8b/0x1c0 mm/slub.c:1749 slab_free mm/slub.c:3513 [inline] kmem_cache_free+0xbd/0x5d0 mm/slub.c:3530 dst_destroy+0x2d6/0x3f0 net/core/dst.c:127 rcu_do_batch kernel/rcu/tree.c:2506 [inline] rcu_core+0x7ab/0x1470 kernel/rcu/tree.c:2741 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 Last potentially related work creation: kasan_save_stack+0x1e/0x50 mm/kasan/common.c:38 __kasan_record_aux_stack+0xf5/0x120 mm/kasan/generic.c:348 __call_rcu kernel/rcu/tree.c:2985 [inline] call_rcu+0xb1/0x740 kernel/rcu/tree.c:3065 dst_release net/core/dst.c:177 [inline] dst_release+0x79/0xe0 net/core/dst.c:167 tcp_v4_do_rcv+0x612/0x8d0 net/ipv4/tcp_ipv4.c:1712 sk_backlog_rcv include/net/sock.h:1030 [inline] __release_sock+0x134/0x3b0 net/core/sock.c:2768 release_sock+0x54/0x1b0 net/core/sock.c:3300 tcp_sendmsg+0x36/0x40 net/ipv4/tcp.c:1441 inet_sendmsg+0x99/0xe0 net/ipv4/af_inet.c:819 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 sock_write_iter+0x289/0x3c0 net/socket.c:1057 call_write_iter include/linux/fs.h:2162 [inline] new_sync_write+0x429/0x660 fs/read_write.c:503 vfs_write+0x7cd/0xae0 fs/read_write.c:590 ksys_write+0x1ee/0x250 fs/read_write.c:643 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae The buggy address belongs to the object at ffff88807f1cb700 which belongs to the cache ip_dst_cache of size 176 The buggy address is located 58 bytes inside of 176-byte region [ffff88807f1cb700, ffff88807f1cb7b0) The buggy address belongs to the page: page:ffffea0001fc72c0 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x7f1cb flags: 0xfff00000000200(slab|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000000200 dead000000000100 dead000000000122 ffff8881413bb780 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 0, migratetype Unmovable, gfp_mask 0x112a20(GFP_ATOMIC|__GFP_NOWARN|__GFP_NORETRY|__GFP_HARDWALL), pid 5, ts 108466983062, free_ts 108048976062 prep_new_page mm/page_alloc.c:2418 [inline] get_page_from_freelist+0xa72/0x2f50 mm/page_alloc.c:4149 __alloc_pages+0x1b2/0x500 mm/page_alloc.c:5369 alloc_pages+0x1a7/0x300 mm/mempolicy.c:2191 alloc_slab_page mm/slub.c:1793 [inline] allocate_slab mm/slub.c:1930 [inline] new_slab+0x32d/0x4a0 mm/slub.c:1993 ___slab_alloc+0x918/0xfe0 mm/slub.c:3022 __slab_alloc.constprop.0+0x4d/0xa0 mm/slub.c:3109 slab_alloc_node mm/slub.c:3200 [inline] slab_alloc mm/slub.c:3242 [inline] kmem_cache_alloc+0x35c/0x3a0 mm/slub.c:3247 dst_alloc+0x146/0x1f0 net/core/dst.c:92 rt_dst_alloc+0x73/0x430 net/ipv4/route.c:1613 __mkroute_output net/ipv4/route.c:2564 [inline] ip_route_output_key_hash_rcu+0x921/0x2d00 net/ipv4/route.c:2791 ip_route_output_key_hash+0x18b/0x300 net/ipv4/route.c:2619 __ip_route_output_key include/net/route.h:126 [inline] ip_route_output_flow+0x23/0x150 net/ipv4/route.c:2850 ip_route_output_key include/net/route.h:142 [inline] geneve_get_v4_rt+0x3a6/0x830 drivers/net/geneve.c:809 geneve_xmit_skb drivers/net/geneve.c:899 [inline] geneve_xmit+0xc4a/0x3540 drivers/net/geneve.c:1082 __netdev_start_xmit include/linux/netdevice.h:4994 [inline] netdev_start_xmit include/linux/netdevice.h:5008 [inline] xmit_one net/core/dev.c:3590 [inline] dev_hard_start_xmit+0x1eb/0x920 net/core/dev.c:3606 __dev_queue_xmit+0x299a/0x3650 net/core/dev.c:4229 page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1338 [inline] free_pcp_prepare+0x374/0x870 mm/page_alloc.c:1389 free_unref_page_prepare mm/page_alloc.c:3309 [inline] free_unref_page+0x19/0x690 mm/page_alloc.c:3388 qlink_free mm/kasan/quarantine.c:146 [inline] qlist_free_all+0x5a/0xc0 mm/kasan/quarantine.c:165 kasan_quarantine_reduce+0x180/0x200 mm/kasan/quarantine.c:272 __kasan_slab_alloc+0xa2/0xc0 mm/kasan/common.c:444 kasan_slab_alloc include/linux/kasan.h:259 [inline] slab_post_alloc_hook mm/slab.h:519 [inline] slab_alloc_node mm/slub.c:3234 [inline] kmem_cache_alloc_node+0x255/0x3f0 mm/slub.c:3270 __alloc_skb+0x215/0x340 net/core/skbuff.c:414 alloc_skb include/linux/skbuff.h:1126 [inline] alloc_skb_with_frags+0x93/0x620 net/core/skbuff.c:6078 sock_alloc_send_pskb+0x783/0x910 net/core/sock.c:2575 mld_newpack+0x1df/0x770 net/ipv6/mcast.c:1754 add_grhead+0x265/0x330 net/ipv6/mcast.c:1857 add_grec+0x1053/0x14e0 net/ipv6/mcast.c:1995 mld_send_initial_cr.part.0+0xf6/0x230 net/ipv6/mcast.c:2242 mld_send_initial_cr net/ipv6/mcast.c:1232 [inline] mld_dad_work+0x1d3/0x690 net/ipv6/mcast.c:2268 process_one_work+0x9b2/0x1690 kernel/workqueue.c:2298 worker_thread+0x658/0x11f0 kernel/workqueue.c:2445 Memory state around the buggy address: ffff88807f1cb600: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88807f1cb680: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc >ffff88807f1cb700: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88807f1cb780: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc ffff88807f1cb800: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 41063e9dd119 ("ipv4: Early TCP socket demux.") Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20211220143330.680945-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-12-20 22:33:30 +08:00
old = xchg((__force struct dst_entry **)&sk->sk_rx_dst, dst);
dst_release(old);
return old != dst;
}
return false;
}
EXPORT_SYMBOL(udp_sk_rx_dst_set);
/*
* Multicasts and broadcasts go to each listener.
*
* Note: called only from the BH handler context.
*/
static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
struct udphdr *uh,
__be32 saddr, __be32 daddr,
struct udp_table *udptable,
int proto)
{
struct sock *sk, *first = NULL;
unsigned short hnum = ntohs(uh->dest);
struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum);
unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
unsigned int offset = offsetof(typeof(*sk), sk_node);
int dif = skb->dev->ifindex;
int sdif = inet_sdif(skb);
struct hlist_node *node;
struct sk_buff *nskb;
if (use_hash2) {
hash2_any = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum) &
udptable->mask;
hash2 = ipv4_portaddr_hash(net, daddr, hnum) & udptable->mask;
start_lookup:
hslot = &udptable->hash2[hash2];
offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node);
}
sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
if (!__udp_is_mcast_sock(net, sk, uh->dest, daddr,
uh->source, saddr, dif, sdif, hnum))
continue;
if (!first) {
first = sk;
continue;
}
nskb = skb_clone(skb, GFP_ATOMIC);
if (unlikely(!nskb)) {
atomic_inc(&sk->sk_drops);
__UDP_INC_STATS(net, UDP_MIB_RCVBUFERRORS,
IS_UDPLITE(sk));
__UDP_INC_STATS(net, UDP_MIB_INERRORS,
IS_UDPLITE(sk));
continue;
}
if (udp_queue_rcv_skb(sk, nskb) > 0)
consume_skb(nskb);
}
/* Also lookup *:port if we are using hash2 and haven't done so yet. */
if (use_hash2 && hash2 != hash2_any) {
hash2 = hash2_any;
goto start_lookup;
}
if (first) {
if (udp_queue_rcv_skb(first, skb) > 0)
consume_skb(skb);
} else {
kfree_skb(skb);
__UDP_INC_STATS(net, UDP_MIB_IGNOREDMULTI,
proto == IPPROTO_UDPLITE);
}
return 0;
}
/* Initialize UDP checksum. If exited with zero value (success),
* CHECKSUM_UNNECESSARY means, that no more checks are required.
* Otherwise, csum completion requires checksumming packet body,
* including udp header and folding it to skb->csum.
*/
static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
int proto)
{
int err;
UDP_SKB_CB(skb)->partial_cov = 0;
UDP_SKB_CB(skb)->cscov = skb->len;
if (proto == IPPROTO_UDPLITE) {
err = udplite_checksum_init(skb, uh);
if (err)
return err;
if (UDP_SKB_CB(skb)->partial_cov) {
skb->csum = inet_compute_pseudo(skb, proto);
return 0;
}
}
/* Note, we are only interested in != 0 or == 0, thus the
* force to int.
*/
net: udp: fix handling of CHECKSUM_COMPLETE packets Current handling of CHECKSUM_COMPLETE packets by the UDP stack is incorrect for any packet that has an incorrect checksum value. udp4/6_csum_init() will both make a call to __skb_checksum_validate_complete() to initialize/validate the csum field when receiving a CHECKSUM_COMPLETE packet. When this packet fails validation, skb->csum will be overwritten with the pseudoheader checksum so the packet can be fully validated by software, but the skb->ip_summed value will be left as CHECKSUM_COMPLETE so that way the stack can later warn the user about their hardware spewing bad checksums. Unfortunately, leaving the SKB in this state can cause problems later on in the checksum calculation. Since the the packet is still marked as CHECKSUM_COMPLETE, udp_csum_pull_header() will SUBTRACT the checksum of the UDP header from skb->csum instead of adding it, leaving us with a garbage value in that field. Once we try to copy the packet to userspace in the udp4/6_recvmsg(), we'll make a call to skb_copy_and_csum_datagram_msg() to checksum the packet data and add it in the garbage skb->csum value to perform our final validation check. Since the value we're validating is not the proper checksum, it's possible that the folded value could come out to 0, causing us not to drop the packet. Instead, we believe that the packet was checksummed incorrectly by hardware since skb->ip_summed is still CHECKSUM_COMPLETE, and we attempt to warn the user with netdev_rx_csum_fault(skb->dev); Unfortunately, since this is the UDP path, skb->dev has been overwritten by skb->dev_scratch and is no longer a valid pointer, so we end up reading invalid memory. This patch addresses this problem in two ways: 1) Do not use the dev pointer when calling netdev_rx_csum_fault() from skb_copy_and_csum_datagram_msg(). Since this gets called from the UDP path where skb->dev has been overwritten, we have no way of knowing if the pointer is still valid. Also for the sake of consistency with the other uses of netdev_rx_csum_fault(), don't attempt to call it if the packet was checksummed by software. 2) Add better CHECKSUM_COMPLETE handling to udp4/6_csum_init(). If we receive a packet that's CHECKSUM_COMPLETE that fails verification (i.e. skb->csum_valid == 0), check who performed the calculation. It's possible that the checksum was done in software by the network stack earlier (such as Netfilter's CONNTRACK module), and if that says the checksum is bad, we can drop the packet immediately instead of waiting until we try and copy it to userspace. Otherwise, we need to mark the SKB as CHECKSUM_NONE, since the skb->csum field no longer contains the full packet checksum after the call to __skb_checksum_validate_complete(). Fixes: e6afc8ace6dd ("udp: remove headers from UDP packets before queueing") Fixes: c84d949057ca ("udp: copy skb->truesize in the first cache line") Cc: Sam Kumar <samanthakumar@google.com> Cc: Eric Dumazet <edumazet@google.com> Signed-off-by: Sean Tranchetti <stranche@codeaurora.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-24 06:04:31 +08:00
err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
inet_compute_pseudo);
if (err)
return err;
if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) {
/* If SW calculated the value, we know it's bad */
if (skb->csum_complete_sw)
return 1;
/* HW says the value is bad. Let's validate that.
* skb->csum is no longer the full packet checksum,
* so don't treat it as such.
*/
skb_checksum_complete_unset(skb);
}
return 0;
}
/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and
* return code conversion for ip layer consumption
*/
static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb,
struct udphdr *uh)
{
int ret;
if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
skb_checksum_try_convert(skb, IPPROTO_UDP, inet_compute_pseudo);
ret = udp_queue_rcv_skb(sk, skb);
/* a return value > 0 means to resubmit the input, but
* it wants the return to be -protocol, or 0
*/
if (ret > 0)
return -ret;
return 0;
}
/*
* All we need to do is get the socket, and then do a checksum.
*/
int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
int proto)
{
struct sock *sk;
struct udphdr *uh;
unsigned short ulen;
struct rtable *rt = skb_rtable(skb);
__be32 saddr, daddr;
struct net *net = dev_net(skb->dev);
bool refcounted;
int drop_reason;
drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
/*
* Validate the packet.
*/
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto drop; /* No space for header. */
uh = udp_hdr(skb);
ulen = ntohs(uh->len);
saddr = ip_hdr(skb)->saddr;
daddr = ip_hdr(skb)->daddr;
if (ulen > skb->len)
goto short_packet;
if (proto == IPPROTO_UDP) {
/* UDP validates ulen. */
if (ulen < sizeof(*uh) || pskb_trim_rcsum(skb, ulen))
goto short_packet;
uh = udp_hdr(skb);
}
if (udp4_csum_init(skb, uh, proto))
goto csum_error;
sk = skb_steal_sock(skb, &refcounted);
udp: ipv4: fix an use after free in __udp4_lib_rcv() Dave Jones reported a use after free in UDP stack : [ 5059.434216] ========================= [ 5059.434314] [ BUG: held lock freed! ] [ 5059.434420] 3.13.0-rc3+ #9 Not tainted [ 5059.434520] ------------------------- [ 5059.434620] named/863 is freeing memory ffff88005e960000-ffff88005e96061f, with a lock still held there! [ 5059.434815] (slock-AF_INET){+.-...}, at: [<ffffffff8149bd21>] udp_queue_rcv_skb+0xd1/0x4b0 [ 5059.435012] 3 locks held by named/863: [ 5059.435086] #0: (rcu_read_lock){.+.+..}, at: [<ffffffff8143054d>] __netif_receive_skb_core+0x11d/0x940 [ 5059.435295] #1: (rcu_read_lock){.+.+..}, at: [<ffffffff81467a5e>] ip_local_deliver_finish+0x3e/0x410 [ 5059.435500] #2: (slock-AF_INET){+.-...}, at: [<ffffffff8149bd21>] udp_queue_rcv_skb+0xd1/0x4b0 [ 5059.435734] stack backtrace: [ 5059.435858] CPU: 0 PID: 863 Comm: named Not tainted 3.13.0-rc3+ #9 [loadavg: 0.21 0.06 0.06 1/115 1365] [ 5059.436052] Hardware name: /D510MO, BIOS MOPNV10J.86A.0175.2010.0308.0620 03/08/2010 [ 5059.436223] 0000000000000002 ffff88007e203ad8 ffffffff8153a372 ffff8800677130e0 [ 5059.436390] ffff88007e203b10 ffffffff8108cafa ffff88005e960000 ffff88007b00cfc0 [ 5059.436554] ffffea00017a5800 ffffffff8141c490 0000000000000246 ffff88007e203b48 [ 5059.436718] Call Trace: [ 5059.436769] <IRQ> [<ffffffff8153a372>] dump_stack+0x4d/0x66 [ 5059.436904] [<ffffffff8108cafa>] debug_check_no_locks_freed+0x15a/0x160 [ 5059.437037] [<ffffffff8141c490>] ? __sk_free+0x110/0x230 [ 5059.437147] [<ffffffff8112da2a>] kmem_cache_free+0x6a/0x150 [ 5059.437260] [<ffffffff8141c490>] __sk_free+0x110/0x230 [ 5059.437364] [<ffffffff8141c5c9>] sk_free+0x19/0x20 [ 5059.437463] [<ffffffff8141cb25>] sock_edemux+0x25/0x40 [ 5059.437567] [<ffffffff8141c181>] sock_queue_rcv_skb+0x81/0x280 [ 5059.437685] [<ffffffff8149bd21>] ? udp_queue_rcv_skb+0xd1/0x4b0 [ 5059.437805] [<ffffffff81499c82>] __udp_queue_rcv_skb+0x42/0x240 [ 5059.437925] [<ffffffff81541d25>] ? _raw_spin_lock+0x65/0x70 [ 5059.438038] [<ffffffff8149bebb>] udp_queue_rcv_skb+0x26b/0x4b0 [ 5059.438155] [<ffffffff8149c712>] __udp4_lib_rcv+0x152/0xb00 [ 5059.438269] [<ffffffff8149d7f5>] udp_rcv+0x15/0x20 [ 5059.438367] [<ffffffff81467b2f>] ip_local_deliver_finish+0x10f/0x410 [ 5059.438492] [<ffffffff81467a5e>] ? ip_local_deliver_finish+0x3e/0x410 [ 5059.438621] [<ffffffff81468653>] ip_local_deliver+0x43/0x80 [ 5059.438733] [<ffffffff81467f70>] ip_rcv_finish+0x140/0x5a0 [ 5059.438843] [<ffffffff81468926>] ip_rcv+0x296/0x3f0 [ 5059.438945] [<ffffffff81430b72>] __netif_receive_skb_core+0x742/0x940 [ 5059.439074] [<ffffffff8143054d>] ? __netif_receive_skb_core+0x11d/0x940 [ 5059.442231] [<ffffffff8108c81d>] ? trace_hardirqs_on+0xd/0x10 [ 5059.442231] [<ffffffff81430d83>] __netif_receive_skb+0x13/0x60 [ 5059.442231] [<ffffffff81431c1e>] netif_receive_skb+0x1e/0x1f0 [ 5059.442231] [<ffffffff814334e0>] napi_gro_receive+0x70/0xa0 [ 5059.442231] [<ffffffffa01de426>] rtl8169_poll+0x166/0x700 [r8169] [ 5059.442231] [<ffffffff81432bc9>] net_rx_action+0x129/0x1e0 [ 5059.442231] [<ffffffff810478cd>] __do_softirq+0xed/0x240 [ 5059.442231] [<ffffffff81047e25>] irq_exit+0x125/0x140 [ 5059.442231] [<ffffffff81004241>] do_IRQ+0x51/0xc0 [ 5059.442231] [<ffffffff81542bef>] common_interrupt+0x6f/0x6f We need to keep a reference on the socket, by using skb_steal_sock() at the right place. Note that another patch is needed to fix a race in udp_sk_rx_dst_set(), as we hold no lock protecting the dst. Fixes: 421b3885bf6d ("udp: ipv4: Add udp early demux") Reported-by: Dave Jones <davej@redhat.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Shawn Bohrer <sbohrer@rgmadvisors.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-11 10:07:23 +08:00
if (sk) {
struct dst_entry *dst = skb_dst(skb);
int ret;
inet: fully convert sk->sk_rx_dst to RCU rules syzbot reported various issues around early demux, one being included in this changelog [1] sk->sk_rx_dst is using RCU protection without clearly documenting it. And following sequences in tcp_v4_do_rcv()/tcp_v6_do_rcv() are not following standard RCU rules. [a] dst_release(dst); [b] sk->sk_rx_dst = NULL; They look wrong because a delete operation of RCU protected pointer is supposed to clear the pointer before the call_rcu()/synchronize_rcu() guarding actual memory freeing. In some cases indeed, dst could be freed before [b] is done. We could cheat by clearing sk_rx_dst before calling dst_release(), but this seems the right time to stick to standard RCU annotations and debugging facilities. [1] BUG: KASAN: use-after-free in dst_check include/net/dst.h:470 [inline] BUG: KASAN: use-after-free in tcp_v4_early_demux+0x95b/0x960 net/ipv4/tcp_ipv4.c:1792 Read of size 2 at addr ffff88807f1cb73a by task syz-executor.5/9204 CPU: 0 PID: 9204 Comm: syz-executor.5 Not tainted 5.16.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description.constprop.0.cold+0x8d/0x320 mm/kasan/report.c:247 __kasan_report mm/kasan/report.c:433 [inline] kasan_report.cold+0x83/0xdf mm/kasan/report.c:450 dst_check include/net/dst.h:470 [inline] tcp_v4_early_demux+0x95b/0x960 net/ipv4/tcp_ipv4.c:1792 ip_rcv_finish_core.constprop.0+0x15de/0x1e80 net/ipv4/ip_input.c:340 ip_list_rcv_finish.constprop.0+0x1b2/0x6e0 net/ipv4/ip_input.c:583 ip_sublist_rcv net/ipv4/ip_input.c:609 [inline] ip_list_rcv+0x34e/0x490 net/ipv4/ip_input.c:644 __netif_receive_skb_list_ptype net/core/dev.c:5508 [inline] __netif_receive_skb_list_core+0x549/0x8e0 net/core/dev.c:5556 __netif_receive_skb_list net/core/dev.c:5608 [inline] netif_receive_skb_list_internal+0x75e/0xd80 net/core/dev.c:5699 gro_normal_list net/core/dev.c:5853 [inline] gro_normal_list net/core/dev.c:5849 [inline] napi_complete_done+0x1f1/0x880 net/core/dev.c:6590 virtqueue_napi_complete drivers/net/virtio_net.c:339 [inline] virtnet_poll+0xca2/0x11b0 drivers/net/virtio_net.c:1557 __napi_poll+0xaf/0x440 net/core/dev.c:7023 napi_poll net/core/dev.c:7090 [inline] net_rx_action+0x801/0xb40 net/core/dev.c:7177 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 invoke_softirq kernel/softirq.c:432 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:637 irq_exit_rcu+0x5/0x20 kernel/softirq.c:649 common_interrupt+0x52/0xc0 arch/x86/kernel/irq.c:240 asm_common_interrupt+0x1e/0x40 arch/x86/include/asm/idtentry.h:629 RIP: 0033:0x7f5e972bfd57 Code: 39 d1 73 14 0f 1f 80 00 00 00 00 48 8b 50 f8 48 83 e8 08 48 39 ca 77 f3 48 39 c3 73 3e 48 89 13 48 8b 50 f8 48 89 38 49 8b 0e <48> 8b 3e 48 83 c3 08 48 83 c6 08 eb bc 48 39 d1 72 9e 48 39 d0 73 RSP: 002b:00007fff8a413210 EFLAGS: 00000283 RAX: 00007f5e97108990 RBX: 00007f5e97108338 RCX: ffffffff81d3aa45 RDX: ffffffff81d3aa45 RSI: 00007f5e97108340 RDI: ffffffff81d3aa45 RBP: 00007f5e97107eb8 R08: 00007f5e97108d88 R09: 0000000093c2e8d9 R10: 0000000000000000 R11: 0000000000000000 R12: 00007f5e97107eb0 R13: 00007f5e97108338 R14: 00007f5e97107ea8 R15: 0000000000000019 </TASK> Allocated by task 13: kasan_save_stack+0x1e/0x50 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:434 [inline] __kasan_slab_alloc+0x90/0xc0 mm/kasan/common.c:467 kasan_slab_alloc include/linux/kasan.h:259 [inline] slab_post_alloc_hook mm/slab.h:519 [inline] slab_alloc_node mm/slub.c:3234 [inline] slab_alloc mm/slub.c:3242 [inline] kmem_cache_alloc+0x202/0x3a0 mm/slub.c:3247 dst_alloc+0x146/0x1f0 net/core/dst.c:92 rt_dst_alloc+0x73/0x430 net/ipv4/route.c:1613 ip_route_input_slow+0x1817/0x3a20 net/ipv4/route.c:2340 ip_route_input_rcu net/ipv4/route.c:2470 [inline] ip_route_input_noref+0x116/0x2a0 net/ipv4/route.c:2415 ip_rcv_finish_core.constprop.0+0x288/0x1e80 net/ipv4/ip_input.c:354 ip_list_rcv_finish.constprop.0+0x1b2/0x6e0 net/ipv4/ip_input.c:583 ip_sublist_rcv net/ipv4/ip_input.c:609 [inline] ip_list_rcv+0x34e/0x490 net/ipv4/ip_input.c:644 __netif_receive_skb_list_ptype net/core/dev.c:5508 [inline] __netif_receive_skb_list_core+0x549/0x8e0 net/core/dev.c:5556 __netif_receive_skb_list net/core/dev.c:5608 [inline] netif_receive_skb_list_internal+0x75e/0xd80 net/core/dev.c:5699 gro_normal_list net/core/dev.c:5853 [inline] gro_normal_list net/core/dev.c:5849 [inline] napi_complete_done+0x1f1/0x880 net/core/dev.c:6590 virtqueue_napi_complete drivers/net/virtio_net.c:339 [inline] virtnet_poll+0xca2/0x11b0 drivers/net/virtio_net.c:1557 __napi_poll+0xaf/0x440 net/core/dev.c:7023 napi_poll net/core/dev.c:7090 [inline] net_rx_action+0x801/0xb40 net/core/dev.c:7177 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 Freed by task 13: kasan_save_stack+0x1e/0x50 mm/kasan/common.c:38 kasan_set_track+0x21/0x30 mm/kasan/common.c:46 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:370 ____kasan_slab_free mm/kasan/common.c:366 [inline] ____kasan_slab_free mm/kasan/common.c:328 [inline] __kasan_slab_free+0xff/0x130 mm/kasan/common.c:374 kasan_slab_free include/linux/kasan.h:235 [inline] slab_free_hook mm/slub.c:1723 [inline] slab_free_freelist_hook+0x8b/0x1c0 mm/slub.c:1749 slab_free mm/slub.c:3513 [inline] kmem_cache_free+0xbd/0x5d0 mm/slub.c:3530 dst_destroy+0x2d6/0x3f0 net/core/dst.c:127 rcu_do_batch kernel/rcu/tree.c:2506 [inline] rcu_core+0x7ab/0x1470 kernel/rcu/tree.c:2741 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 Last potentially related work creation: kasan_save_stack+0x1e/0x50 mm/kasan/common.c:38 __kasan_record_aux_stack+0xf5/0x120 mm/kasan/generic.c:348 __call_rcu kernel/rcu/tree.c:2985 [inline] call_rcu+0xb1/0x740 kernel/rcu/tree.c:3065 dst_release net/core/dst.c:177 [inline] dst_release+0x79/0xe0 net/core/dst.c:167 tcp_v4_do_rcv+0x612/0x8d0 net/ipv4/tcp_ipv4.c:1712 sk_backlog_rcv include/net/sock.h:1030 [inline] __release_sock+0x134/0x3b0 net/core/sock.c:2768 release_sock+0x54/0x1b0 net/core/sock.c:3300 tcp_sendmsg+0x36/0x40 net/ipv4/tcp.c:1441 inet_sendmsg+0x99/0xe0 net/ipv4/af_inet.c:819 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 sock_write_iter+0x289/0x3c0 net/socket.c:1057 call_write_iter include/linux/fs.h:2162 [inline] new_sync_write+0x429/0x660 fs/read_write.c:503 vfs_write+0x7cd/0xae0 fs/read_write.c:590 ksys_write+0x1ee/0x250 fs/read_write.c:643 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae The buggy address belongs to the object at ffff88807f1cb700 which belongs to the cache ip_dst_cache of size 176 The buggy address is located 58 bytes inside of 176-byte region [ffff88807f1cb700, ffff88807f1cb7b0) The buggy address belongs to the page: page:ffffea0001fc72c0 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x7f1cb flags: 0xfff00000000200(slab|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000000200 dead000000000100 dead000000000122 ffff8881413bb780 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 0, migratetype Unmovable, gfp_mask 0x112a20(GFP_ATOMIC|__GFP_NOWARN|__GFP_NORETRY|__GFP_HARDWALL), pid 5, ts 108466983062, free_ts 108048976062 prep_new_page mm/page_alloc.c:2418 [inline] get_page_from_freelist+0xa72/0x2f50 mm/page_alloc.c:4149 __alloc_pages+0x1b2/0x500 mm/page_alloc.c:5369 alloc_pages+0x1a7/0x300 mm/mempolicy.c:2191 alloc_slab_page mm/slub.c:1793 [inline] allocate_slab mm/slub.c:1930 [inline] new_slab+0x32d/0x4a0 mm/slub.c:1993 ___slab_alloc+0x918/0xfe0 mm/slub.c:3022 __slab_alloc.constprop.0+0x4d/0xa0 mm/slub.c:3109 slab_alloc_node mm/slub.c:3200 [inline] slab_alloc mm/slub.c:3242 [inline] kmem_cache_alloc+0x35c/0x3a0 mm/slub.c:3247 dst_alloc+0x146/0x1f0 net/core/dst.c:92 rt_dst_alloc+0x73/0x430 net/ipv4/route.c:1613 __mkroute_output net/ipv4/route.c:2564 [inline] ip_route_output_key_hash_rcu+0x921/0x2d00 net/ipv4/route.c:2791 ip_route_output_key_hash+0x18b/0x300 net/ipv4/route.c:2619 __ip_route_output_key include/net/route.h:126 [inline] ip_route_output_flow+0x23/0x150 net/ipv4/route.c:2850 ip_route_output_key include/net/route.h:142 [inline] geneve_get_v4_rt+0x3a6/0x830 drivers/net/geneve.c:809 geneve_xmit_skb drivers/net/geneve.c:899 [inline] geneve_xmit+0xc4a/0x3540 drivers/net/geneve.c:1082 __netdev_start_xmit include/linux/netdevice.h:4994 [inline] netdev_start_xmit include/linux/netdevice.h:5008 [inline] xmit_one net/core/dev.c:3590 [inline] dev_hard_start_xmit+0x1eb/0x920 net/core/dev.c:3606 __dev_queue_xmit+0x299a/0x3650 net/core/dev.c:4229 page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1338 [inline] free_pcp_prepare+0x374/0x870 mm/page_alloc.c:1389 free_unref_page_prepare mm/page_alloc.c:3309 [inline] free_unref_page+0x19/0x690 mm/page_alloc.c:3388 qlink_free mm/kasan/quarantine.c:146 [inline] qlist_free_all+0x5a/0xc0 mm/kasan/quarantine.c:165 kasan_quarantine_reduce+0x180/0x200 mm/kasan/quarantine.c:272 __kasan_slab_alloc+0xa2/0xc0 mm/kasan/common.c:444 kasan_slab_alloc include/linux/kasan.h:259 [inline] slab_post_alloc_hook mm/slab.h:519 [inline] slab_alloc_node mm/slub.c:3234 [inline] kmem_cache_alloc_node+0x255/0x3f0 mm/slub.c:3270 __alloc_skb+0x215/0x340 net/core/skbuff.c:414 alloc_skb include/linux/skbuff.h:1126 [inline] alloc_skb_with_frags+0x93/0x620 net/core/skbuff.c:6078 sock_alloc_send_pskb+0x783/0x910 net/core/sock.c:2575 mld_newpack+0x1df/0x770 net/ipv6/mcast.c:1754 add_grhead+0x265/0x330 net/ipv6/mcast.c:1857 add_grec+0x1053/0x14e0 net/ipv6/mcast.c:1995 mld_send_initial_cr.part.0+0xf6/0x230 net/ipv6/mcast.c:2242 mld_send_initial_cr net/ipv6/mcast.c:1232 [inline] mld_dad_work+0x1d3/0x690 net/ipv6/mcast.c:2268 process_one_work+0x9b2/0x1690 kernel/workqueue.c:2298 worker_thread+0x658/0x11f0 kernel/workqueue.c:2445 Memory state around the buggy address: ffff88807f1cb600: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88807f1cb680: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc >ffff88807f1cb700: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88807f1cb780: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc ffff88807f1cb800: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 41063e9dd119 ("ipv4: Early TCP socket demux.") Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20211220143330.680945-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-12-20 22:33:30 +08:00
if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst))
udp_sk_rx_dst_set(sk, dst);
ret = udp_unicast_rcv_skb(sk, skb, uh);
if (refcounted)
sock_put(sk);
return ret;
}
if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
return __udp4_lib_mcast_deliver(net, skb, uh,
saddr, daddr, udptable, proto);
sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
if (sk)
return udp_unicast_rcv_skb(sk, skb, uh);
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
nf_reset_ct(skb);
/* No socket. Drop packet silently, if checksum is wrong */
if (udp_lib_checksum_complete(skb))
goto csum_error;
drop_reason = SKB_DROP_REASON_NO_SOCKET;
__UDP_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
/*
* Hmm. We got an UDP packet to a port to which we
* don't wanna listen. Ignore it.
*/
kfree_skb_reason(skb, drop_reason);
return 0;
short_packet:
drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL;
net_dbg_ratelimited("UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n",
proto == IPPROTO_UDPLITE ? "Lite" : "",
&saddr, ntohs(uh->source),
ulen, skb->len,
&daddr, ntohs(uh->dest));
goto drop;
csum_error:
/*
* RFC1122: OK. Discards the bad packet silently (as far as
* the network is concerned, anyway) as per 4.1.3.4 (MUST).
*/
drop_reason = SKB_DROP_REASON_UDP_CSUM;
net_dbg_ratelimited("UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n",
proto == IPPROTO_UDPLITE ? "Lite" : "",
&saddr, ntohs(uh->source), &daddr, ntohs(uh->dest),
ulen);
__UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
drop:
__UDP_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
kfree_skb_reason(skb, drop_reason);
return 0;
}
/* We can only early demux multicast if there is a single matching socket.
* If more than one socket found returns NULL
*/
static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
__be16 loc_port, __be32 loc_addr,
__be16 rmt_port, __be32 rmt_addr,
int dif, int sdif)
{
struct udp_table *udptable = net->ipv4.udp_table;
unsigned short hnum = ntohs(loc_port);
struct sock *sk, *result;
struct udp_hslot *hslot;
unsigned int slot;
slot = udp_hashfn(net, hnum, udptable->mask);
hslot = &udptable->hash[slot];
/* Do not bother scanning a too big list */
if (hslot->count > 10)
return NULL;
result = NULL;
sk_for_each_rcu(sk, &hslot->head) {
if (__udp_is_mcast_sock(net, sk, loc_port, loc_addr,
rmt_port, rmt_addr, dif, sdif, hnum)) {
if (result)
return NULL;
result = sk;
}
}
return result;
}
/* For unicast we should only early demux connected sockets or we can
* break forwarding setups. The chains here can be long so only check
* if the first socket is an exact match and if not move on.
*/
static struct sock *__udp4_lib_demux_lookup(struct net *net,
__be16 loc_port, __be32 loc_addr,
__be16 rmt_port, __be32 rmt_addr,
int dif, int sdif)
{
struct udp_table *udptable = net->ipv4.udp_table;
INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr);
unsigned short hnum = ntohs(loc_port);
unsigned int hash2, slot2;
struct udp_hslot *hslot2;
__portpair ports;
struct sock *sk;
hash2 = ipv4_portaddr_hash(net, loc_addr, hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
ports = INET_COMBINED_PORTS(rmt_port, hnum);
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
if (inet_match(net, sk, acookie, ports, dif, sdif))
return sk;
/* Only check first socket in chain */
break;
}
return NULL;
}
int udp_v4_early_demux(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
struct in_device *in_dev = NULL;
const struct iphdr *iph;
const struct udphdr *uh;
struct sock *sk = NULL;
struct dst_entry *dst;
int dif = skb->dev->ifindex;
int sdif = inet_sdif(skb);
int ours;
/* validate the packet */
if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
return 0;
iph = ip_hdr(skb);
uh = udp_hdr(skb);
if (skb->pkt_type == PACKET_MULTICAST) {
in_dev = __in_dev_get_rcu(skb->dev);
if (!in_dev)
return 0;
ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
iph->protocol);
if (!ours)
return 0;
sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
uh->source, iph->saddr,
dif, sdif);
} else if (skb->pkt_type == PACKET_HOST) {
sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
uh->source, iph->saddr, dif, sdif);
}
if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))
return 0;
skb->sk = sk;
skb->destructor = sock_efree;
inet: fully convert sk->sk_rx_dst to RCU rules syzbot reported various issues around early demux, one being included in this changelog [1] sk->sk_rx_dst is using RCU protection without clearly documenting it. And following sequences in tcp_v4_do_rcv()/tcp_v6_do_rcv() are not following standard RCU rules. [a] dst_release(dst); [b] sk->sk_rx_dst = NULL; They look wrong because a delete operation of RCU protected pointer is supposed to clear the pointer before the call_rcu()/synchronize_rcu() guarding actual memory freeing. In some cases indeed, dst could be freed before [b] is done. We could cheat by clearing sk_rx_dst before calling dst_release(), but this seems the right time to stick to standard RCU annotations and debugging facilities. [1] BUG: KASAN: use-after-free in dst_check include/net/dst.h:470 [inline] BUG: KASAN: use-after-free in tcp_v4_early_demux+0x95b/0x960 net/ipv4/tcp_ipv4.c:1792 Read of size 2 at addr ffff88807f1cb73a by task syz-executor.5/9204 CPU: 0 PID: 9204 Comm: syz-executor.5 Not tainted 5.16.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description.constprop.0.cold+0x8d/0x320 mm/kasan/report.c:247 __kasan_report mm/kasan/report.c:433 [inline] kasan_report.cold+0x83/0xdf mm/kasan/report.c:450 dst_check include/net/dst.h:470 [inline] tcp_v4_early_demux+0x95b/0x960 net/ipv4/tcp_ipv4.c:1792 ip_rcv_finish_core.constprop.0+0x15de/0x1e80 net/ipv4/ip_input.c:340 ip_list_rcv_finish.constprop.0+0x1b2/0x6e0 net/ipv4/ip_input.c:583 ip_sublist_rcv net/ipv4/ip_input.c:609 [inline] ip_list_rcv+0x34e/0x490 net/ipv4/ip_input.c:644 __netif_receive_skb_list_ptype net/core/dev.c:5508 [inline] __netif_receive_skb_list_core+0x549/0x8e0 net/core/dev.c:5556 __netif_receive_skb_list net/core/dev.c:5608 [inline] netif_receive_skb_list_internal+0x75e/0xd80 net/core/dev.c:5699 gro_normal_list net/core/dev.c:5853 [inline] gro_normal_list net/core/dev.c:5849 [inline] napi_complete_done+0x1f1/0x880 net/core/dev.c:6590 virtqueue_napi_complete drivers/net/virtio_net.c:339 [inline] virtnet_poll+0xca2/0x11b0 drivers/net/virtio_net.c:1557 __napi_poll+0xaf/0x440 net/core/dev.c:7023 napi_poll net/core/dev.c:7090 [inline] net_rx_action+0x801/0xb40 net/core/dev.c:7177 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 invoke_softirq kernel/softirq.c:432 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:637 irq_exit_rcu+0x5/0x20 kernel/softirq.c:649 common_interrupt+0x52/0xc0 arch/x86/kernel/irq.c:240 asm_common_interrupt+0x1e/0x40 arch/x86/include/asm/idtentry.h:629 RIP: 0033:0x7f5e972bfd57 Code: 39 d1 73 14 0f 1f 80 00 00 00 00 48 8b 50 f8 48 83 e8 08 48 39 ca 77 f3 48 39 c3 73 3e 48 89 13 48 8b 50 f8 48 89 38 49 8b 0e <48> 8b 3e 48 83 c3 08 48 83 c6 08 eb bc 48 39 d1 72 9e 48 39 d0 73 RSP: 002b:00007fff8a413210 EFLAGS: 00000283 RAX: 00007f5e97108990 RBX: 00007f5e97108338 RCX: ffffffff81d3aa45 RDX: ffffffff81d3aa45 RSI: 00007f5e97108340 RDI: ffffffff81d3aa45 RBP: 00007f5e97107eb8 R08: 00007f5e97108d88 R09: 0000000093c2e8d9 R10: 0000000000000000 R11: 0000000000000000 R12: 00007f5e97107eb0 R13: 00007f5e97108338 R14: 00007f5e97107ea8 R15: 0000000000000019 </TASK> Allocated by task 13: kasan_save_stack+0x1e/0x50 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:434 [inline] __kasan_slab_alloc+0x90/0xc0 mm/kasan/common.c:467 kasan_slab_alloc include/linux/kasan.h:259 [inline] slab_post_alloc_hook mm/slab.h:519 [inline] slab_alloc_node mm/slub.c:3234 [inline] slab_alloc mm/slub.c:3242 [inline] kmem_cache_alloc+0x202/0x3a0 mm/slub.c:3247 dst_alloc+0x146/0x1f0 net/core/dst.c:92 rt_dst_alloc+0x73/0x430 net/ipv4/route.c:1613 ip_route_input_slow+0x1817/0x3a20 net/ipv4/route.c:2340 ip_route_input_rcu net/ipv4/route.c:2470 [inline] ip_route_input_noref+0x116/0x2a0 net/ipv4/route.c:2415 ip_rcv_finish_core.constprop.0+0x288/0x1e80 net/ipv4/ip_input.c:354 ip_list_rcv_finish.constprop.0+0x1b2/0x6e0 net/ipv4/ip_input.c:583 ip_sublist_rcv net/ipv4/ip_input.c:609 [inline] ip_list_rcv+0x34e/0x490 net/ipv4/ip_input.c:644 __netif_receive_skb_list_ptype net/core/dev.c:5508 [inline] __netif_receive_skb_list_core+0x549/0x8e0 net/core/dev.c:5556 __netif_receive_skb_list net/core/dev.c:5608 [inline] netif_receive_skb_list_internal+0x75e/0xd80 net/core/dev.c:5699 gro_normal_list net/core/dev.c:5853 [inline] gro_normal_list net/core/dev.c:5849 [inline] napi_complete_done+0x1f1/0x880 net/core/dev.c:6590 virtqueue_napi_complete drivers/net/virtio_net.c:339 [inline] virtnet_poll+0xca2/0x11b0 drivers/net/virtio_net.c:1557 __napi_poll+0xaf/0x440 net/core/dev.c:7023 napi_poll net/core/dev.c:7090 [inline] net_rx_action+0x801/0xb40 net/core/dev.c:7177 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 Freed by task 13: kasan_save_stack+0x1e/0x50 mm/kasan/common.c:38 kasan_set_track+0x21/0x30 mm/kasan/common.c:46 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:370 ____kasan_slab_free mm/kasan/common.c:366 [inline] ____kasan_slab_free mm/kasan/common.c:328 [inline] __kasan_slab_free+0xff/0x130 mm/kasan/common.c:374 kasan_slab_free include/linux/kasan.h:235 [inline] slab_free_hook mm/slub.c:1723 [inline] slab_free_freelist_hook+0x8b/0x1c0 mm/slub.c:1749 slab_free mm/slub.c:3513 [inline] kmem_cache_free+0xbd/0x5d0 mm/slub.c:3530 dst_destroy+0x2d6/0x3f0 net/core/dst.c:127 rcu_do_batch kernel/rcu/tree.c:2506 [inline] rcu_core+0x7ab/0x1470 kernel/rcu/tree.c:2741 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 Last potentially related work creation: kasan_save_stack+0x1e/0x50 mm/kasan/common.c:38 __kasan_record_aux_stack+0xf5/0x120 mm/kasan/generic.c:348 __call_rcu kernel/rcu/tree.c:2985 [inline] call_rcu+0xb1/0x740 kernel/rcu/tree.c:3065 dst_release net/core/dst.c:177 [inline] dst_release+0x79/0xe0 net/core/dst.c:167 tcp_v4_do_rcv+0x612/0x8d0 net/ipv4/tcp_ipv4.c:1712 sk_backlog_rcv include/net/sock.h:1030 [inline] __release_sock+0x134/0x3b0 net/core/sock.c:2768 release_sock+0x54/0x1b0 net/core/sock.c:3300 tcp_sendmsg+0x36/0x40 net/ipv4/tcp.c:1441 inet_sendmsg+0x99/0xe0 net/ipv4/af_inet.c:819 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 sock_write_iter+0x289/0x3c0 net/socket.c:1057 call_write_iter include/linux/fs.h:2162 [inline] new_sync_write+0x429/0x660 fs/read_write.c:503 vfs_write+0x7cd/0xae0 fs/read_write.c:590 ksys_write+0x1ee/0x250 fs/read_write.c:643 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae The buggy address belongs to the object at ffff88807f1cb700 which belongs to the cache ip_dst_cache of size 176 The buggy address is located 58 bytes inside of 176-byte region [ffff88807f1cb700, ffff88807f1cb7b0) The buggy address belongs to the page: page:ffffea0001fc72c0 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x7f1cb flags: 0xfff00000000200(slab|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000000200 dead000000000100 dead000000000122 ffff8881413bb780 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 0, migratetype Unmovable, gfp_mask 0x112a20(GFP_ATOMIC|__GFP_NOWARN|__GFP_NORETRY|__GFP_HARDWALL), pid 5, ts 108466983062, free_ts 108048976062 prep_new_page mm/page_alloc.c:2418 [inline] get_page_from_freelist+0xa72/0x2f50 mm/page_alloc.c:4149 __alloc_pages+0x1b2/0x500 mm/page_alloc.c:5369 alloc_pages+0x1a7/0x300 mm/mempolicy.c:2191 alloc_slab_page mm/slub.c:1793 [inline] allocate_slab mm/slub.c:1930 [inline] new_slab+0x32d/0x4a0 mm/slub.c:1993 ___slab_alloc+0x918/0xfe0 mm/slub.c:3022 __slab_alloc.constprop.0+0x4d/0xa0 mm/slub.c:3109 slab_alloc_node mm/slub.c:3200 [inline] slab_alloc mm/slub.c:3242 [inline] kmem_cache_alloc+0x35c/0x3a0 mm/slub.c:3247 dst_alloc+0x146/0x1f0 net/core/dst.c:92 rt_dst_alloc+0x73/0x430 net/ipv4/route.c:1613 __mkroute_output net/ipv4/route.c:2564 [inline] ip_route_output_key_hash_rcu+0x921/0x2d00 net/ipv4/route.c:2791 ip_route_output_key_hash+0x18b/0x300 net/ipv4/route.c:2619 __ip_route_output_key include/net/route.h:126 [inline] ip_route_output_flow+0x23/0x150 net/ipv4/route.c:2850 ip_route_output_key include/net/route.h:142 [inline] geneve_get_v4_rt+0x3a6/0x830 drivers/net/geneve.c:809 geneve_xmit_skb drivers/net/geneve.c:899 [inline] geneve_xmit+0xc4a/0x3540 drivers/net/geneve.c:1082 __netdev_start_xmit include/linux/netdevice.h:4994 [inline] netdev_start_xmit include/linux/netdevice.h:5008 [inline] xmit_one net/core/dev.c:3590 [inline] dev_hard_start_xmit+0x1eb/0x920 net/core/dev.c:3606 __dev_queue_xmit+0x299a/0x3650 net/core/dev.c:4229 page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1338 [inline] free_pcp_prepare+0x374/0x870 mm/page_alloc.c:1389 free_unref_page_prepare mm/page_alloc.c:3309 [inline] free_unref_page+0x19/0x690 mm/page_alloc.c:3388 qlink_free mm/kasan/quarantine.c:146 [inline] qlist_free_all+0x5a/0xc0 mm/kasan/quarantine.c:165 kasan_quarantine_reduce+0x180/0x200 mm/kasan/quarantine.c:272 __kasan_slab_alloc+0xa2/0xc0 mm/kasan/common.c:444 kasan_slab_alloc include/linux/kasan.h:259 [inline] slab_post_alloc_hook mm/slab.h:519 [inline] slab_alloc_node mm/slub.c:3234 [inline] kmem_cache_alloc_node+0x255/0x3f0 mm/slub.c:3270 __alloc_skb+0x215/0x340 net/core/skbuff.c:414 alloc_skb include/linux/skbuff.h:1126 [inline] alloc_skb_with_frags+0x93/0x620 net/core/skbuff.c:6078 sock_alloc_send_pskb+0x783/0x910 net/core/sock.c:2575 mld_newpack+0x1df/0x770 net/ipv6/mcast.c:1754 add_grhead+0x265/0x330 net/ipv6/mcast.c:1857 add_grec+0x1053/0x14e0 net/ipv6/mcast.c:1995 mld_send_initial_cr.part.0+0xf6/0x230 net/ipv6/mcast.c:2242 mld_send_initial_cr net/ipv6/mcast.c:1232 [inline] mld_dad_work+0x1d3/0x690 net/ipv6/mcast.c:2268 process_one_work+0x9b2/0x1690 kernel/workqueue.c:2298 worker_thread+0x658/0x11f0 kernel/workqueue.c:2445 Memory state around the buggy address: ffff88807f1cb600: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88807f1cb680: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc >ffff88807f1cb700: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88807f1cb780: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc ffff88807f1cb800: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 41063e9dd119 ("ipv4: Early TCP socket demux.") Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20211220143330.680945-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-12-20 22:33:30 +08:00
dst = rcu_dereference(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, 0);
if (dst) {
u32 itag = 0;
/* set noref for now.
* any place which wants to hold dst has to call
* dst_hold_safe()
*/
skb_dst_set_noref(skb, dst);
/* for unconnected multicast sockets we need to validate
* the source on each packet
*/
if (!inet_sk(sk)->inet_daddr && in_dev)
return ip_mc_validate_source(skb, iph->daddr,
udp: mask TOS bits in udp_v4_early_demux() udp_v4_early_demux() is the only function that calls ip_mc_validate_source() with a TOS that hasn't been masked with IPTOS_RT_MASK. This results in different behaviours for incoming multicast UDPv4 packets, depending on if ip_mc_validate_source() is called from the early-demux path (udp_v4_early_demux) or from the regular input path (ip_route_input_noref). ECN would normally not be used with UDP multicast packets, so the practical consequences should be limited on that side. However, IPTOS_RT_MASK is used to also masks the TOS' high order bits, to align with the non-early-demux path behaviour. Reproducer: Setup two netns, connected with veth: $ ip netns add ns0 $ ip netns add ns1 $ ip -netns ns0 link set dev lo up $ ip -netns ns1 link set dev lo up $ ip link add name veth01 netns ns0 type veth peer name veth10 netns ns1 $ ip -netns ns0 link set dev veth01 up $ ip -netns ns1 link set dev veth10 up $ ip -netns ns0 address add 192.0.2.10 peer 192.0.2.11/32 dev veth01 $ ip -netns ns1 address add 192.0.2.11 peer 192.0.2.10/32 dev veth10 In ns0, add route to multicast address 224.0.2.0/24 using source address 198.51.100.10: $ ip -netns ns0 address add 198.51.100.10/32 dev lo $ ip -netns ns0 route add 224.0.2.0/24 dev veth01 src 198.51.100.10 In ns1, define route to 198.51.100.10, only for packets with TOS 4: $ ip -netns ns1 route add 198.51.100.10/32 tos 4 dev veth10 Also activate rp_filter in ns1, so that incoming packets not matching the above route get dropped: $ ip netns exec ns1 sysctl -wq net.ipv4.conf.veth10.rp_filter=1 Now try to receive packets on 224.0.2.11: $ ip netns exec ns1 socat UDP-RECVFROM:1111,ip-add-membership=224.0.2.11:veth10,ignoreeof - In ns0, send packet to 224.0.2.11 with TOS 4 and ECT(0) (that is, tos 6 for socat): $ echo test0 | ip netns exec ns0 socat - UDP-DATAGRAM:224.0.2.11:1111,bind=:1111,tos=6 The "test0" message is properly received by socat in ns1, because early-demux has no cached dst to use, so source address validation is done by ip_route_input_mc(), which receives a TOS that has the ECN bits masked. Now send another packet to 224.0.2.11, still with TOS 4 and ECT(0): $ echo test1 | ip netns exec ns0 socat - UDP-DATAGRAM:224.0.2.11:1111,bind=:1111,tos=6 The "test1" message isn't received by socat in ns1, because, now, early-demux has a cached dst to use and calls ip_mc_validate_source() immediately, without masking the ECN bits. Fixes: bc044e8db796 ("udp: perform source validation for mcast early demux") Signed-off-by: Guillaume Nault <gnault@redhat.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-16 18:44:22 +08:00
iph->saddr,
iph->tos & IPTOS_RT_MASK,
skb->dev, in_dev, &itag);
}
return 0;
}
int udp_rcv(struct sk_buff *skb)
{
return __udp4_lib_rcv(skb, dev_net(skb->dev)->ipv4.udp_table, IPPROTO_UDP);
}
void udp_destroy_sock(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
bool slow = lock_sock_fast(sk);
/* protects from races with udp_abort() */
sock_set_flag(sk, SOCK_DEAD);
udp_flush_pending_frames(sk);
unlock_sock_fast(sk, slow);
if (static_branch_unlikely(&udp_encap_needed_key)) {
if (up->encap_type) {
void (*encap_destroy)(struct sock *sk);
encap_destroy = READ_ONCE(up->encap_destroy);
if (encap_destroy)
encap_destroy(sk);
}
if (up->encap_enabled)
static_branch_dec(&udp_encap_needed_key);
}
}
/*
* Socket option code for UDP
*/
int udp_lib_setsockopt(struct sock *sk, int level, int optname,
sockptr_t optval, unsigned int optlen,
int (*push_pending_frames)(struct sock *))
{
struct udp_sock *up = udp_sk(sk);
int val, valbool;
int err = 0;
int is_udplite = IS_UDPLITE(sk);
if (level == SOL_SOCKET) {
err = sk_setsockopt(sk, level, optname, optval, optlen);
if (optname == SO_RCVBUF || optname == SO_RCVBUFFORCE) {
sockopt_lock_sock(sk);
/* paired with READ_ONCE in udp_rmem_release() */
WRITE_ONCE(up->forward_threshold, sk->sk_rcvbuf >> 2);
sockopt_release_sock(sk);
}
return err;
}
if (optlen < sizeof(int))
return -EINVAL;
if (copy_from_sockptr(&val, optval, sizeof(val)))
return -EFAULT;
valbool = val ? 1 : 0;
switch (optname) {
case UDP_CORK:
if (val != 0) {
WRITE_ONCE(up->corkflag, 1);
} else {
WRITE_ONCE(up->corkflag, 0);
lock_sock(sk);
push_pending_frames(sk);
release_sock(sk);
}
break;
case UDP_ENCAP:
switch (val) {
case 0:
#ifdef CONFIG_XFRM
case UDP_ENCAP_ESPINUDP:
case UDP_ENCAP_ESPINUDP_NON_IKE:
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6)
up->encap_rcv = ipv6_stub->xfrm6_udp_encap_rcv;
else
#endif
up->encap_rcv = xfrm4_udp_encap_rcv;
#endif
fallthrough;
case UDP_ENCAP_L2TPINUDP:
up->encap_type = val;
lock_sock(sk);
udp_tunnel_encap_enable(sk->sk_socket);
release_sock(sk);
break;
default:
err = -ENOPROTOOPT;
break;
}
break;
case UDP_NO_CHECK6_TX:
up->no_check6_tx = valbool;
break;
case UDP_NO_CHECK6_RX:
up->no_check6_rx = valbool;
break;
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-27 01:42:17 +08:00
case UDP_SEGMENT:
if (val < 0 || val > USHRT_MAX)
return -EINVAL;
udp: annotate data races around unix_sk(sk)->gso_size Accesses to unix_sk(sk)->gso_size are lockless. Add READ_ONCE()/WRITE_ONCE() around them. BUG: KCSAN: data-race in udp_lib_setsockopt / udpv6_sendmsg write to 0xffff88812d78f47c of 2 bytes by task 10849 on cpu 1: udp_lib_setsockopt+0x3b3/0x710 net/ipv4/udp.c:2696 udpv6_setsockopt+0x63/0x90 net/ipv6/udp.c:1630 sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3265 __sys_setsockopt+0x18f/0x200 net/socket.c:2104 __do_sys_setsockopt net/socket.c:2115 [inline] __se_sys_setsockopt net/socket.c:2112 [inline] __x64_sys_setsockopt+0x62/0x70 net/socket.c:2112 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88812d78f47c of 2 bytes by task 10852 on cpu 0: udpv6_sendmsg+0x161/0x16b0 net/ipv6/udp.c:1299 inet6_sendmsg+0x5f/0x80 net/ipv6/af_inet6.c:642 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2337 ___sys_sendmsg net/socket.c:2391 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2477 __do_sys_sendmmsg net/socket.c:2506 [inline] __se_sys_sendmmsg net/socket.c:2503 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2503 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x0000 -> 0x0005 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 10852 Comm: syz-executor.0 Not tainted 5.13.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Willem de Bruijn <willemb@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-01 00:42:44 +08:00
WRITE_ONCE(up->gso_size, val);
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-27 01:42:17 +08:00
break;
case UDP_GRO:
lock_sock(sk);
/* when enabling GRO, accept the related GSO packet type */
if (valbool)
udp_tunnel_encap_enable(sk->sk_socket);
up->gro_enabled = valbool;
up->accept_udp_l4 = valbool;
release_sock(sk);
break;
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-28 03:10:57 +08:00
/*
* UDP-Lite's partial checksum coverage (RFC 3828).
*/
/* The sender sets actual checksum coverage length via this option.
* The case coverage > packet length is handled by send module. */
case UDPLITE_SEND_CSCOV:
if (!is_udplite) /* Disable the option on UDP sockets */
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-28 03:10:57 +08:00
return -ENOPROTOOPT;
if (val != 0 && val < 8) /* Illegal coverage: use default (8) */
val = 8;
else if (val > USHRT_MAX)
val = USHRT_MAX;
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-28 03:10:57 +08:00
up->pcslen = val;
up->pcflag |= UDPLITE_SEND_CC;
break;
/* The receiver specifies a minimum checksum coverage value. To make
* sense, this should be set to at least 8 (as done below). If zero is
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-28 03:10:57 +08:00
* used, this again means full checksum coverage. */
case UDPLITE_RECV_CSCOV:
if (!is_udplite) /* Disable the option on UDP sockets */
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-28 03:10:57 +08:00
return -ENOPROTOOPT;
if (val != 0 && val < 8) /* Avoid silly minimal values. */
val = 8;
else if (val > USHRT_MAX)
val = USHRT_MAX;
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-28 03:10:57 +08:00
up->pcrlen = val;
up->pcflag |= UDPLITE_RECV_CC;
break;
default:
err = -ENOPROTOOPT;
break;
}
return err;
}
EXPORT_SYMBOL(udp_lib_setsockopt);
int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
unsigned int optlen)
{
if (level == SOL_UDP || level == SOL_UDPLITE || level == SOL_SOCKET)
return udp_lib_setsockopt(sk, level, optname,
optval, optlen,
udp_push_pending_frames);
return ip_setsockopt(sk, level, optname, optval, optlen);
}
int udp_lib_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
struct udp_sock *up = udp_sk(sk);
int val, len;
if (get_user(len, optlen))
return -EFAULT;
len = min_t(unsigned int, len, sizeof(int));
if (len < 0)
return -EINVAL;
switch (optname) {
case UDP_CORK:
val = READ_ONCE(up->corkflag);
break;
case UDP_ENCAP:
val = up->encap_type;
break;
case UDP_NO_CHECK6_TX:
val = up->no_check6_tx;
break;
case UDP_NO_CHECK6_RX:
val = up->no_check6_rx;
break;
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-27 01:42:17 +08:00
case UDP_SEGMENT:
udp: annotate data races around unix_sk(sk)->gso_size Accesses to unix_sk(sk)->gso_size are lockless. Add READ_ONCE()/WRITE_ONCE() around them. BUG: KCSAN: data-race in udp_lib_setsockopt / udpv6_sendmsg write to 0xffff88812d78f47c of 2 bytes by task 10849 on cpu 1: udp_lib_setsockopt+0x3b3/0x710 net/ipv4/udp.c:2696 udpv6_setsockopt+0x63/0x90 net/ipv6/udp.c:1630 sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3265 __sys_setsockopt+0x18f/0x200 net/socket.c:2104 __do_sys_setsockopt net/socket.c:2115 [inline] __se_sys_setsockopt net/socket.c:2112 [inline] __x64_sys_setsockopt+0x62/0x70 net/socket.c:2112 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88812d78f47c of 2 bytes by task 10852 on cpu 0: udpv6_sendmsg+0x161/0x16b0 net/ipv6/udp.c:1299 inet6_sendmsg+0x5f/0x80 net/ipv6/af_inet6.c:642 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2337 ___sys_sendmsg net/socket.c:2391 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2477 __do_sys_sendmmsg net/socket.c:2506 [inline] __se_sys_sendmmsg net/socket.c:2503 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2503 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x0000 -> 0x0005 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 10852 Comm: syz-executor.0 Not tainted 5.13.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Willem de Bruijn <willemb@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-01 00:42:44 +08:00
val = READ_ONCE(up->gso_size);
udp: generate gso with UDP_SEGMENT Support generic segmentation offload for udp datagrams. Callers can concatenate and send at once the payload of multiple datagrams with the same destination. To set segment size, the caller sets socket option UDP_SEGMENT to the length of each discrete payload. This value must be smaller than or equal to the relevant MTU. A follow-up patch adds cmsg UDP_SEGMENT to specify segment size on a per send call basis. Total byte length may then exceed MTU. If not an exact multiple of segment size, the last segment will be shorter. The implementation adds a gso_size field to the udp socket, ip(v6) cmsg cookie and inet_cork structure to be able to set the value at setsockopt or cmsg time and to work with both lockless and corked paths. Initial benchmark numbers show UDP GSO about as expensive as TCP GSO. tcp tso 3197 MB/s 54232 msg/s 54232 calls/s 6,457,754,262 cycles tcp gso 1765 MB/s 29939 msg/s 29939 calls/s 11,203,021,806 cycles tcp without tso/gso * 739 MB/s 12548 msg/s 12548 calls/s 11,205,483,630 cycles udp 876 MB/s 14873 msg/s 624666 calls/s 11,205,777,429 cycles udp gso 2139 MB/s 36282 msg/s 36282 calls/s 11,204,374,561 cycles [*] after reverting commit 0a6b2a1dc2a2 ("tcp: switch to GSO being always on") Measured total system cycles ('-a') for one core while pinning both the network receive path and benchmark process to that core: perf stat -a -C 12 -e cycles \ ./udpgso_bench_tx -C 12 -4 -D "$DST" -l 4 Note the reduction in calls/s with GSO. Bytes per syscall drops increases from 1470 to 61818. Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-27 01:42:17 +08:00
break;
case UDP_GRO:
val = up->gro_enabled;
break;
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-28 03:10:57 +08:00
/* The following two cannot be changed on UDP sockets, the return is
* always 0 (which corresponds to the full checksum coverage of UDP). */
case UDPLITE_SEND_CSCOV:
val = up->pcslen;
break;
case UDPLITE_RECV_CSCOV:
val = up->pcrlen;
break;
default:
return -ENOPROTOOPT;
}
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &val, len))
return -EFAULT;
return 0;
}
EXPORT_SYMBOL(udp_lib_getsockopt);
int udp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
if (level == SOL_UDP || level == SOL_UDPLITE)
return udp_lib_getsockopt(sk, level, optname, optval, optlen);
return ip_getsockopt(sk, level, optname, optval, optlen);
}
/**
* udp_poll - wait for a UDP event.
* @file: - file struct
* @sock: - socket
* @wait: - poll table
*
* This is same as datagram poll, except for the special case of
* blocking sockets. If application is using a blocking fd
* and a packet with checksum error is in the queue;
* then it could get return from select indicating data available
* but then block when reading it. Add special case code
* to work around these arguably broken applications.
*/
__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
__poll_t mask = datagram_poll(file, sock, wait);
struct sock *sk = sock->sk;
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-28 03:10:57 +08:00
if (!skb_queue_empty_lockless(&udp_sk(sk)->reader_queue))
mask |= EPOLLIN | EPOLLRDNORM;
/* Check for false positives due to checksum errors */
if ((mask & EPOLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
!(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
mask &= ~(EPOLLIN | EPOLLRDNORM);
/* psock ingress_msg queue should not contain any bad checksum frames */
if (sk_is_readable(sk))
mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
EXPORT_SYMBOL(udp_poll);
int udp_abort(struct sock *sk, int err)
{
lock_sock(sk);
/* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing
* with close()
*/
if (sock_flag(sk, SOCK_DEAD))
goto out;
sk->sk_err = err;
sk_error_report(sk);
__udp_disconnect(sk, 0);
out:
release_sock(sk);
return 0;
}
EXPORT_SYMBOL_GPL(udp_abort);
struct proto udp_prot = {
.name = "UDP",
.owner = THIS_MODULE,
.close = udp_lib_close,
bpf: Hooks for sys_connect == The problem == See description of the problem in the initial patch of this patch set. == The solution == The patch provides much more reliable in-kernel solution for the 2nd part of the problem: making outgoing connecttion from desired IP. It adds new attach types `BPF_CGROUP_INET4_CONNECT` and `BPF_CGROUP_INET6_CONNECT` for program type `BPF_PROG_TYPE_CGROUP_SOCK_ADDR` that can be used to override both source and destination of a connection at connect(2) time. Local end of connection can be bound to desired IP using newly introduced BPF-helper `bpf_bind()`. It allows to bind to only IP though, and doesn't support binding to port, i.e. leverages `IP_BIND_ADDRESS_NO_PORT` socket option. There are two reasons for this: * looking for a free port is expensive and can affect performance significantly; * there is no use-case for port. As for remote end (`struct sockaddr *` passed by user), both parts of it can be overridden, remote IP and remote port. It's useful if an application inside cgroup wants to connect to another application inside same cgroup or to itself, but knows nothing about IP assigned to the cgroup. Support is added for IPv4 and IPv6, for TCP and UDP. IPv4 and IPv6 have separate attach types for same reason as sys_bind hooks, i.e. to prevent reading from / writing to e.g. user_ip6 fields when user passes sockaddr_in since it'd be out-of-bound. == Implementation notes == The patch introduces new field in `struct proto`: `pre_connect` that is a pointer to a function with same signature as `connect` but is called before it. The reason is in some cases BPF hooks should be called way before control is passed to `sk->sk_prot->connect`. Specifically `inet_dgram_connect` autobinds socket before calling `sk->sk_prot->connect` and there is no way to call `bpf_bind()` from hooks from e.g. `ip4_datagram_connect` or `ip6_datagram_connect` since it'd cause double-bind. On the other hand `proto.pre_connect` provides a flexible way to add BPF hooks for connect only for necessary `proto` and call them at desired time before `connect`. Since `bpf_bind()` is allowed to bind only to IP and autobind in `inet_dgram_connect` binds only port there is no chance of double-bind. bpf_bind() sets `force_bind_address_no_port` to bind to only IP despite of value of `bind_address_no_port` socket field. bpf_bind() sets `with_lock` to `false` when calling to __inet_bind() and __inet6_bind() since all call-sites, where bpf_bind() is called, already hold socket lock. Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-31 06:08:05 +08:00
.pre_connect = udp_pre_connect,
.connect = ip4_datagram_connect,
.disconnect = udp_disconnect,
.ioctl = udp_ioctl,
.init = udp_init_sock,
.destroy = udp_destroy_sock,
.setsockopt = udp_setsockopt,
.getsockopt = udp_getsockopt,
.sendmsg = udp_sendmsg,
.recvmsg = udp_recvmsg,
.sendpage = udp_sendpage,
.release_cb = ip4_datagram_release_cb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
.rehash = udp_v4_rehash,
.get_port = udp_v4_get_port,
net: bpf: Handle return value of BPF_CGROUP_RUN_PROG_INET{4,6}_POST_BIND() The return value of BPF_CGROUP_RUN_PROG_INET{4,6}_POST_BIND() in __inet_bind() is not handled properly. While the return value is non-zero, it will set inet_saddr and inet_rcv_saddr to 0 and exit: err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; goto out_release_sock; } Let's take UDP for example and see what will happen. For UDP socket, it will be added to 'udp_prot.h.udp_table->hash' and 'udp_prot.h.udp_table->hash2' after the sk->sk_prot->get_port() called success. If 'inet->inet_rcv_saddr' is specified here, then 'sk' will be in the 'hslot2' of 'hash2' that it don't belong to (because inet_saddr is changed to 0), and UDP packet received will not be passed to this sock. If 'inet->inet_rcv_saddr' is not specified here, the sock will work fine, as it can receive packet properly, which is wired, as the 'bind()' is already failed. To undo the get_port() operation, introduce the 'put_port' field for 'struct proto'. For TCP proto, it is inet_put_port(); For UDP proto, it is udp_lib_unhash(); For icmp proto, it is ping_unhash(). Therefore, after sys_bind() fail caused by BPF_CGROUP_RUN_PROG_INET4_POST_BIND(), it will be unbinded, which means that it can try to be binded to another port. Signed-off-by: Menglong Dong <imagedong@tencent.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20220106132022.3470772-2-imagedong@tencent.com
2022-01-06 21:20:20 +08:00
.put_port = udp_lib_unhash,
#ifdef CONFIG_BPF_SYSCALL
.psock_update_sk_prot = udp_bpf_update_proto,
#endif
.memory_allocated = &udp_memory_allocated,
.per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc,
.sysctl_mem = sysctl_udp_mem,
.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
.sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
.obj_size = sizeof(struct udp_sock),
.h.udp_table = NULL,
.diag_destroy = udp_abort,
};
EXPORT_SYMBOL(udp_prot);
/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS
static struct udp_table *udp_get_table_afinfo(struct udp_seq_afinfo *afinfo,
struct net *net)
{
return afinfo->udp_table ? : net->ipv4.udp_table;
}
static struct sock *udp_get_first(struct seq_file *seq, int start)
{
struct udp_iter_state *state = seq->private;
struct net *net = seq_file_net(seq);
struct udp_seq_afinfo *afinfo;
struct udp_table *udptable;
struct sock *sk;
if (state->bpf_seq_afinfo)
afinfo = state->bpf_seq_afinfo;
else
afinfo = pde_data(file_inode(seq->file));
udptable = udp_get_table_afinfo(afinfo, net);
for (state->bucket = start; state->bucket <= udptable->mask;
++state->bucket) {
struct udp_hslot *hslot = &udptable->hash[state->bucket];
if (hlist_empty(&hslot->head))
continue;
spin_lock_bh(&hslot->lock);
sk_for_each(sk, &hslot->head) {
if (!net_eq(sock_net(sk), net))
continue;
if (afinfo->family == AF_UNSPEC ||
sk->sk_family == afinfo->family)
goto found;
}
spin_unlock_bh(&hslot->lock);
}
sk = NULL;
found:
return sk;
}
static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
{
struct udp_iter_state *state = seq->private;
struct net *net = seq_file_net(seq);
struct udp_seq_afinfo *afinfo;
struct udp_table *udptable;
if (state->bpf_seq_afinfo)
afinfo = state->bpf_seq_afinfo;
else
afinfo = pde_data(file_inode(seq->file));
do {
sk = sk_next(sk);
} while (sk && (!net_eq(sock_net(sk), net) ||
(afinfo->family != AF_UNSPEC &&
sk->sk_family != afinfo->family)));
if (!sk) {
udptable = udp_get_table_afinfo(afinfo, net);
if (state->bucket <= udptable->mask)
spin_unlock_bh(&udptable->hash[state->bucket].lock);
return udp_get_first(seq, state->bucket + 1);
}
return sk;
}
static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos)
{
struct sock *sk = udp_get_first(seq, 0);
if (sk)
while (pos && (sk = udp_get_next(seq, sk)) != NULL)
--pos;
return pos ? NULL : sk;
}
void *udp_seq_start(struct seq_file *seq, loff_t *pos)
{
udp: Wrong locking code in udp seq_file infrastructure Reading zero bytes from /proc/net/udp or other similar files which use the same seq_file udp infrastructure panics kernel in that way: ===================================== [ BUG: bad unlock balance detected! ] ------------------------------------- read/1985 is trying to release lock (&table->hash[i].lock) at: [<ffffffff81321d83>] udp_seq_stop+0x27/0x29 but there are no more locks to release! other info that might help us debug this: 1 lock held by read/1985: #0: (&p->lock){--..}, at: [<ffffffff810eefb6>] seq_read+0x38/0x348 stack backtrace: Pid: 1985, comm: read Not tainted 2.6.29-rc8 #9 Call Trace: [<ffffffff81321d83>] ? udp_seq_stop+0x27/0x29 [<ffffffff8106dab9>] print_unlock_inbalance_bug+0xd6/0xe1 [<ffffffff8106db62>] lock_release_non_nested+0x9e/0x1c6 [<ffffffff810ef030>] ? seq_read+0xb2/0x348 [<ffffffff8106bdba>] ? mark_held_locks+0x68/0x86 [<ffffffff81321d83>] ? udp_seq_stop+0x27/0x29 [<ffffffff8106dde7>] lock_release+0x15d/0x189 [<ffffffff8137163c>] _spin_unlock_bh+0x1e/0x34 [<ffffffff81321d83>] udp_seq_stop+0x27/0x29 [<ffffffff810ef239>] seq_read+0x2bb/0x348 [<ffffffff810eef7e>] ? seq_read+0x0/0x348 [<ffffffff8111aedd>] proc_reg_read+0x90/0xaf [<ffffffff810d878f>] vfs_read+0xa6/0x103 [<ffffffff8106bfac>] ? trace_hardirqs_on_caller+0x12f/0x153 [<ffffffff810d88a2>] sys_read+0x45/0x69 [<ffffffff8101123a>] system_call_fastpath+0x16/0x1b BUG: scheduling while atomic: read/1985/0xffffff00 INFO: lockdep is turned off. Modules linked in: cpufreq_ondemand acpi_cpufreq freq_table dm_multipath kvm ppdev snd_hda_codec_analog snd_hda_intel snd_hda_codec snd_hwdep snd_seq_dummy snd_seq_oss snd_seq_midi_event arc4 snd_s eq ecb thinkpad_acpi snd_seq_device iwl3945 hwmon sdhci_pci snd_pcm_oss sdhci rfkill mmc_core snd_mixer_oss i2c_i801 mac80211 yenta_socket ricoh_mmc i2c_core iTCO_wdt snd_pcm iTCO_vendor_support rs rc_nonstatic snd_timer snd lib80211 cfg80211 soundcore snd_page_alloc video parport_pc output parport e1000e [last unloaded: scsi_wait_scan] Pid: 1985, comm: read Not tainted 2.6.29-rc8 #9 Call Trace: [<ffffffff8106b456>] ? __debug_show_held_locks+0x1b/0x24 [<ffffffff81043660>] __schedule_bug+0x7e/0x83 [<ffffffff8136ede9>] schedule+0xce/0x838 [<ffffffff810d7972>] ? fsnotify_access+0x5f/0x67 [<ffffffff810112d0>] ? sysret_careful+0xb/0x37 [<ffffffff8106be9c>] ? trace_hardirqs_on_caller+0x1f/0x153 [<ffffffff8137127b>] ? trace_hardirqs_on_thunk+0x3a/0x3f [<ffffffff810112f6>] sysret_careful+0x31/0x37 read[1985]: segfault at 7fffc479bfe8 ip 0000003e7420a180 sp 00007fffc479bfa0 error 6 Kernel panic - not syncing: Aiee, killing interrupt handler! udp_seq_stop() tries to unlock not yet locked spinlock. The lock was lost during splitting global udp_hash_lock to subsequent spinlocks. Signed-off by: Vitaly Mayatskikh <v.mayatskih@gmail.com> Acked-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-24 06:22:33 +08:00
struct udp_iter_state *state = seq->private;
state->bucket = MAX_UDP_PORTS;
udp: Wrong locking code in udp seq_file infrastructure Reading zero bytes from /proc/net/udp or other similar files which use the same seq_file udp infrastructure panics kernel in that way: ===================================== [ BUG: bad unlock balance detected! ] ------------------------------------- read/1985 is trying to release lock (&table->hash[i].lock) at: [<ffffffff81321d83>] udp_seq_stop+0x27/0x29 but there are no more locks to release! other info that might help us debug this: 1 lock held by read/1985: #0: (&p->lock){--..}, at: [<ffffffff810eefb6>] seq_read+0x38/0x348 stack backtrace: Pid: 1985, comm: read Not tainted 2.6.29-rc8 #9 Call Trace: [<ffffffff81321d83>] ? udp_seq_stop+0x27/0x29 [<ffffffff8106dab9>] print_unlock_inbalance_bug+0xd6/0xe1 [<ffffffff8106db62>] lock_release_non_nested+0x9e/0x1c6 [<ffffffff810ef030>] ? seq_read+0xb2/0x348 [<ffffffff8106bdba>] ? mark_held_locks+0x68/0x86 [<ffffffff81321d83>] ? udp_seq_stop+0x27/0x29 [<ffffffff8106dde7>] lock_release+0x15d/0x189 [<ffffffff8137163c>] _spin_unlock_bh+0x1e/0x34 [<ffffffff81321d83>] udp_seq_stop+0x27/0x29 [<ffffffff810ef239>] seq_read+0x2bb/0x348 [<ffffffff810eef7e>] ? seq_read+0x0/0x348 [<ffffffff8111aedd>] proc_reg_read+0x90/0xaf [<ffffffff810d878f>] vfs_read+0xa6/0x103 [<ffffffff8106bfac>] ? trace_hardirqs_on_caller+0x12f/0x153 [<ffffffff810d88a2>] sys_read+0x45/0x69 [<ffffffff8101123a>] system_call_fastpath+0x16/0x1b BUG: scheduling while atomic: read/1985/0xffffff00 INFO: lockdep is turned off. Modules linked in: cpufreq_ondemand acpi_cpufreq freq_table dm_multipath kvm ppdev snd_hda_codec_analog snd_hda_intel snd_hda_codec snd_hwdep snd_seq_dummy snd_seq_oss snd_seq_midi_event arc4 snd_s eq ecb thinkpad_acpi snd_seq_device iwl3945 hwmon sdhci_pci snd_pcm_oss sdhci rfkill mmc_core snd_mixer_oss i2c_i801 mac80211 yenta_socket ricoh_mmc i2c_core iTCO_wdt snd_pcm iTCO_vendor_support rs rc_nonstatic snd_timer snd lib80211 cfg80211 soundcore snd_page_alloc video parport_pc output parport e1000e [last unloaded: scsi_wait_scan] Pid: 1985, comm: read Not tainted 2.6.29-rc8 #9 Call Trace: [<ffffffff8106b456>] ? __debug_show_held_locks+0x1b/0x24 [<ffffffff81043660>] __schedule_bug+0x7e/0x83 [<ffffffff8136ede9>] schedule+0xce/0x838 [<ffffffff810d7972>] ? fsnotify_access+0x5f/0x67 [<ffffffff810112d0>] ? sysret_careful+0xb/0x37 [<ffffffff8106be9c>] ? trace_hardirqs_on_caller+0x1f/0x153 [<ffffffff8137127b>] ? trace_hardirqs_on_thunk+0x3a/0x3f [<ffffffff810112f6>] sysret_careful+0x31/0x37 read[1985]: segfault at 7fffc479bfe8 ip 0000003e7420a180 sp 00007fffc479bfa0 error 6 Kernel panic - not syncing: Aiee, killing interrupt handler! udp_seq_stop() tries to unlock not yet locked spinlock. The lock was lost during splitting global udp_hash_lock to subsequent spinlocks. Signed-off by: Vitaly Mayatskikh <v.mayatskih@gmail.com> Acked-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-03-24 06:22:33 +08:00
return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
}
EXPORT_SYMBOL(udp_seq_start);
void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct sock *sk;
if (v == SEQ_START_TOKEN)
sk = udp_get_idx(seq, 0);
else
sk = udp_get_next(seq, v);
++*pos;
return sk;
}
EXPORT_SYMBOL(udp_seq_next);
void udp_seq_stop(struct seq_file *seq, void *v)
{
struct udp_iter_state *state = seq->private;
struct udp_seq_afinfo *afinfo;
struct udp_table *udptable;
if (state->bpf_seq_afinfo)
afinfo = state->bpf_seq_afinfo;
else
afinfo = pde_data(file_inode(seq->file));
udptable = udp_get_table_afinfo(afinfo, seq_file_net(seq));
if (state->bucket <= udptable->mask)
spin_unlock_bh(&udptable->hash[state->bucket].lock);
}
EXPORT_SYMBOL(udp_seq_stop);
/* ------------------------------------------------------------------------ */
static void udp4_format_sock(struct sock *sp, struct seq_file *f,
int bucket)
{
struct inet_sock *inet = inet_sk(sp);
__be32 dest = inet->inet_daddr;
__be32 src = inet->inet_rcv_saddr;
__u16 destp = ntohs(inet->inet_dport);
__u16 srcp = ntohs(inet->inet_sport);
seq_printf(f, "%5d: %08X:%04X %08X:%04X"
" %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u",
bucket, src, srcp, dest, destp, sp->sk_state,
sk_wmem_alloc_get(sp),
udp_rqueue_get(sp),
0, 0L, 0,
from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
0, sock_i_ino(sp),
refcount_read(&sp->sk_refcnt), sp,
atomic_read(&sp->sk_drops));
}
int udp4_seq_show(struct seq_file *seq, void *v)
{
seq_setwidth(seq, 127);
if (v == SEQ_START_TOKEN)
seq_puts(seq, " sl local_address rem_address st tx_queue "
"rx_queue tr tm->when retrnsmt uid timeout "
"inode ref pointer drops");
else {
struct udp_iter_state *state = seq->private;
udp4_format_sock(v, seq, state->bucket);
}
seq_pad(seq, '\n');
return 0;
}
#ifdef CONFIG_BPF_SYSCALL
struct bpf_iter__udp {
__bpf_md_ptr(struct bpf_iter_meta *, meta);
__bpf_md_ptr(struct udp_sock *, udp_sk);
uid_t uid __aligned(8);
int bucket __aligned(8);
};
static int udp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta,
struct udp_sock *udp_sk, uid_t uid, int bucket)
{
struct bpf_iter__udp ctx;
meta->seq_num--; /* skip SEQ_START_TOKEN */
ctx.meta = meta;
ctx.udp_sk = udp_sk;
ctx.uid = uid;
ctx.bucket = bucket;
return bpf_iter_run_prog(prog, &ctx);
}
static int bpf_iter_udp_seq_show(struct seq_file *seq, void *v)
{
struct udp_iter_state *state = seq->private;
struct bpf_iter_meta meta;
struct bpf_prog *prog;
struct sock *sk = v;
uid_t uid;
if (v == SEQ_START_TOKEN)
return 0;
uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk));
meta.seq = seq;
prog = bpf_iter_get_info(&meta, false);
return udp_prog_seq_show(prog, &meta, v, uid, state->bucket);
}
static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v)
{
struct bpf_iter_meta meta;
struct bpf_prog *prog;
if (!v) {
meta.seq = seq;
prog = bpf_iter_get_info(&meta, true);
if (prog)
(void)udp_prog_seq_show(prog, &meta, v, 0, 0);
}
udp_seq_stop(seq, v);
}
static const struct seq_operations bpf_iter_udp_seq_ops = {
.start = udp_seq_start,
.next = udp_seq_next,
.stop = bpf_iter_udp_seq_stop,
.show = bpf_iter_udp_seq_show,
};
#endif
const struct seq_operations udp_seq_ops = {
.start = udp_seq_start,
.next = udp_seq_next,
.stop = udp_seq_stop,
.show = udp4_seq_show,
};
EXPORT_SYMBOL(udp_seq_ops);
static struct udp_seq_afinfo udp4_seq_afinfo = {
.family = AF_INET,
.udp_table = NULL,
};
static int __net_init udp4_proc_init_net(struct net *net)
{
if (!proc_create_net_data("udp", 0444, net->proc_net, &udp_seq_ops,
sizeof(struct udp_iter_state), &udp4_seq_afinfo))
return -ENOMEM;
return 0;
}
static void __net_exit udp4_proc_exit_net(struct net *net)
{
remove_proc_entry("udp", net->proc_net);
}
static struct pernet_operations udp4_net_ops = {
.init = udp4_proc_init_net,
.exit = udp4_proc_exit_net,
};
int __init udp4_proc_init(void)
{
return register_pernet_subsys(&udp4_net_ops);
}
void udp4_proc_exit(void)
{
unregister_pernet_subsys(&udp4_net_ops);
}
#endif /* CONFIG_PROC_FS */
static __initdata unsigned long uhash_entries;
static int __init set_uhash_entries(char *str)
{
ssize_t ret;
if (!str)
return 0;
ret = kstrtoul(str, 0, &uhash_entries);
if (ret)
return 0;
if (uhash_entries && uhash_entries < UDP_HTABLE_SIZE_MIN)
uhash_entries = UDP_HTABLE_SIZE_MIN;
return 1;
}
__setup("uhash_entries=", set_uhash_entries);
void __init udp_table_init(struct udp_table *table, const char *name)
{
unsigned int i;
table->hash = alloc_large_system_hash(name,
2 * sizeof(struct udp_hslot),
uhash_entries,
21, /* one slot per 2 MB */
0,
&table->log,
&table->mask,
UDP_HTABLE_SIZE_MIN,
udp: Introduce optional per-netns hash table. The maximum hash table size is 64K due to the nature of the protocol. [0] It's smaller than TCP, and fewer sockets can cause a performance drop. On an EC2 c5.24xlarge instance (192 GiB memory), after running iperf3 in different netns, creating 32Mi sockets without data transfer in the root netns causes regression for the iperf3's connection. uhash_entries sockets length Gbps 64K 1 1 5.69 1Mi 16 5.27 2Mi 32 4.90 4Mi 64 4.09 8Mi 128 2.96 16Mi 256 2.06 32Mi 512 1.12 The per-netns hash table breaks the lengthy lists into shorter ones. It is useful on a multi-tenant system with thousands of netns. With smaller hash tables, we can look up sockets faster, isolate noisy neighbours, and reduce lock contention. The max size of the per-netns table is 64K as well. This is because the possible hash range by udp_hashfn() always fits in 64K within the same netns and we cannot make full use of the whole buckets larger than 64K. /* 0 < num < 64K -> X < hash < X + 64K */ (num + net_hash_mix(net)) & mask; Also, the min size is 128. We use a bitmap to search for an available port in udp_lib_get_port(). To keep the bitmap on the stack and not fire the CONFIG_FRAME_WARN error at build time, we round up the table size to 128. The sysctl usage is the same with TCP: $ dmesg | cut -d ' ' -f 6- | grep "UDP hash" UDP hash table entries: 65536 (order: 9, 2097152 bytes, vmalloc) # sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 65536 # can be changed by uhash_entries # sysctl net.ipv4.udp_child_hash_entries net.ipv4.udp_child_hash_entries = 0 # disabled by default # ip netns add test1 # ip netns exec test1 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = -65536 # share the global table # sysctl -w net.ipv4.udp_child_hash_entries=100 net.ipv4.udp_child_hash_entries = 100 # ip netns add test2 # ip netns exec test2 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 128 # own a per-netns table with 2^n buckets We could optimise the hash table lookup/iteration further by removing the netns comparison for the per-netns one in the future. Also, we could optimise the sparse udp_hslot layout by putting it in udp_table. [0]: https://lore.kernel.org/netdev/4ACC2815.7010101@gmail.com/ Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-11-15 05:57:57 +08:00
UDP_HTABLE_SIZE_MAX);
table->hash2 = table->hash + (table->mask + 1);
for (i = 0; i <= table->mask; i++) {
INIT_HLIST_HEAD(&table->hash[i].head);
table->hash[i].count = 0;
spin_lock_init(&table->hash[i].lock);
}
for (i = 0; i <= table->mask; i++) {
INIT_HLIST_HEAD(&table->hash2[i].head);
table->hash2[i].count = 0;
spin_lock_init(&table->hash2[i].lock);
}
}
u32 udp_flow_hashrnd(void)
{
static u32 hashrnd __read_mostly;
net_get_random_once(&hashrnd, sizeof(hashrnd));
return hashrnd;
}
EXPORT_SYMBOL(udp_flow_hashrnd);
udp: Introduce optional per-netns hash table. The maximum hash table size is 64K due to the nature of the protocol. [0] It's smaller than TCP, and fewer sockets can cause a performance drop. On an EC2 c5.24xlarge instance (192 GiB memory), after running iperf3 in different netns, creating 32Mi sockets without data transfer in the root netns causes regression for the iperf3's connection. uhash_entries sockets length Gbps 64K 1 1 5.69 1Mi 16 5.27 2Mi 32 4.90 4Mi 64 4.09 8Mi 128 2.96 16Mi 256 2.06 32Mi 512 1.12 The per-netns hash table breaks the lengthy lists into shorter ones. It is useful on a multi-tenant system with thousands of netns. With smaller hash tables, we can look up sockets faster, isolate noisy neighbours, and reduce lock contention. The max size of the per-netns table is 64K as well. This is because the possible hash range by udp_hashfn() always fits in 64K within the same netns and we cannot make full use of the whole buckets larger than 64K. /* 0 < num < 64K -> X < hash < X + 64K */ (num + net_hash_mix(net)) & mask; Also, the min size is 128. We use a bitmap to search for an available port in udp_lib_get_port(). To keep the bitmap on the stack and not fire the CONFIG_FRAME_WARN error at build time, we round up the table size to 128. The sysctl usage is the same with TCP: $ dmesg | cut -d ' ' -f 6- | grep "UDP hash" UDP hash table entries: 65536 (order: 9, 2097152 bytes, vmalloc) # sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 65536 # can be changed by uhash_entries # sysctl net.ipv4.udp_child_hash_entries net.ipv4.udp_child_hash_entries = 0 # disabled by default # ip netns add test1 # ip netns exec test1 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = -65536 # share the global table # sysctl -w net.ipv4.udp_child_hash_entries=100 net.ipv4.udp_child_hash_entries = 100 # ip netns add test2 # ip netns exec test2 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 128 # own a per-netns table with 2^n buckets We could optimise the hash table lookup/iteration further by removing the netns comparison for the per-netns one in the future. Also, we could optimise the sparse udp_hslot layout by putting it in udp_table. [0]: https://lore.kernel.org/netdev/4ACC2815.7010101@gmail.com/ Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-11-15 05:57:57 +08:00
static void __net_init udp_sysctl_init(struct net *net)
{
net->ipv4.sysctl_udp_rmem_min = PAGE_SIZE;
net->ipv4.sysctl_udp_wmem_min = PAGE_SIZE;
#ifdef CONFIG_NET_L3_MASTER_DEV
net->ipv4.sysctl_udp_l3mdev_accept = 0;
#endif
udp: Introduce optional per-netns hash table. The maximum hash table size is 64K due to the nature of the protocol. [0] It's smaller than TCP, and fewer sockets can cause a performance drop. On an EC2 c5.24xlarge instance (192 GiB memory), after running iperf3 in different netns, creating 32Mi sockets without data transfer in the root netns causes regression for the iperf3's connection. uhash_entries sockets length Gbps 64K 1 1 5.69 1Mi 16 5.27 2Mi 32 4.90 4Mi 64 4.09 8Mi 128 2.96 16Mi 256 2.06 32Mi 512 1.12 The per-netns hash table breaks the lengthy lists into shorter ones. It is useful on a multi-tenant system with thousands of netns. With smaller hash tables, we can look up sockets faster, isolate noisy neighbours, and reduce lock contention. The max size of the per-netns table is 64K as well. This is because the possible hash range by udp_hashfn() always fits in 64K within the same netns and we cannot make full use of the whole buckets larger than 64K. /* 0 < num < 64K -> X < hash < X + 64K */ (num + net_hash_mix(net)) & mask; Also, the min size is 128. We use a bitmap to search for an available port in udp_lib_get_port(). To keep the bitmap on the stack and not fire the CONFIG_FRAME_WARN error at build time, we round up the table size to 128. The sysctl usage is the same with TCP: $ dmesg | cut -d ' ' -f 6- | grep "UDP hash" UDP hash table entries: 65536 (order: 9, 2097152 bytes, vmalloc) # sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 65536 # can be changed by uhash_entries # sysctl net.ipv4.udp_child_hash_entries net.ipv4.udp_child_hash_entries = 0 # disabled by default # ip netns add test1 # ip netns exec test1 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = -65536 # share the global table # sysctl -w net.ipv4.udp_child_hash_entries=100 net.ipv4.udp_child_hash_entries = 100 # ip netns add test2 # ip netns exec test2 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 128 # own a per-netns table with 2^n buckets We could optimise the hash table lookup/iteration further by removing the netns comparison for the per-netns one in the future. Also, we could optimise the sparse udp_hslot layout by putting it in udp_table. [0]: https://lore.kernel.org/netdev/4ACC2815.7010101@gmail.com/ Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-11-15 05:57:57 +08:00
}
static struct udp_table __net_init *udp_pernet_table_alloc(unsigned int hash_entries)
{
struct udp_table *udptable;
int i;
udptable = kmalloc(sizeof(*udptable), GFP_KERNEL);
if (!udptable)
goto out;
udptable->hash = vmalloc_huge(hash_entries * 2 * sizeof(struct udp_hslot),
GFP_KERNEL_ACCOUNT);
if (!udptable->hash)
goto free_table;
udptable->hash2 = udptable->hash + hash_entries;
udptable->mask = hash_entries - 1;
udptable->log = ilog2(hash_entries);
for (i = 0; i < hash_entries; i++) {
INIT_HLIST_HEAD(&udptable->hash[i].head);
udptable->hash[i].count = 0;
spin_lock_init(&udptable->hash[i].lock);
INIT_HLIST_HEAD(&udptable->hash2[i].head);
udptable->hash2[i].count = 0;
spin_lock_init(&udptable->hash2[i].lock);
}
return udptable;
free_table:
kfree(udptable);
out:
return NULL;
}
static void __net_exit udp_pernet_table_free(struct net *net)
{
struct udp_table *udptable = net->ipv4.udp_table;
if (udptable == &udp_table)
return;
kvfree(udptable->hash);
kfree(udptable);
}
static void __net_init udp_set_table(struct net *net)
{
struct udp_table *udptable;
unsigned int hash_entries;
struct net *old_net;
if (net_eq(net, &init_net))
goto fallback;
old_net = current->nsproxy->net_ns;
hash_entries = READ_ONCE(old_net->ipv4.sysctl_udp_child_hash_entries);
if (!hash_entries)
goto fallback;
/* Set min to keep the bitmap on stack in udp_lib_get_port() */
if (hash_entries < UDP_HTABLE_SIZE_MIN_PERNET)
hash_entries = UDP_HTABLE_SIZE_MIN_PERNET;
else
hash_entries = roundup_pow_of_two(hash_entries);
udptable = udp_pernet_table_alloc(hash_entries);
if (udptable) {
net->ipv4.udp_table = udptable;
} else {
pr_warn("Failed to allocate UDP hash table (entries: %u) "
"for a netns, fallback to the global one\n",
hash_entries);
fallback:
net->ipv4.udp_table = &udp_table;
}
}
static int __net_init udp_pernet_init(struct net *net)
{
udp_sysctl_init(net);
udp_set_table(net);
return 0;
}
udp: Introduce optional per-netns hash table. The maximum hash table size is 64K due to the nature of the protocol. [0] It's smaller than TCP, and fewer sockets can cause a performance drop. On an EC2 c5.24xlarge instance (192 GiB memory), after running iperf3 in different netns, creating 32Mi sockets without data transfer in the root netns causes regression for the iperf3's connection. uhash_entries sockets length Gbps 64K 1 1 5.69 1Mi 16 5.27 2Mi 32 4.90 4Mi 64 4.09 8Mi 128 2.96 16Mi 256 2.06 32Mi 512 1.12 The per-netns hash table breaks the lengthy lists into shorter ones. It is useful on a multi-tenant system with thousands of netns. With smaller hash tables, we can look up sockets faster, isolate noisy neighbours, and reduce lock contention. The max size of the per-netns table is 64K as well. This is because the possible hash range by udp_hashfn() always fits in 64K within the same netns and we cannot make full use of the whole buckets larger than 64K. /* 0 < num < 64K -> X < hash < X + 64K */ (num + net_hash_mix(net)) & mask; Also, the min size is 128. We use a bitmap to search for an available port in udp_lib_get_port(). To keep the bitmap on the stack and not fire the CONFIG_FRAME_WARN error at build time, we round up the table size to 128. The sysctl usage is the same with TCP: $ dmesg | cut -d ' ' -f 6- | grep "UDP hash" UDP hash table entries: 65536 (order: 9, 2097152 bytes, vmalloc) # sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 65536 # can be changed by uhash_entries # sysctl net.ipv4.udp_child_hash_entries net.ipv4.udp_child_hash_entries = 0 # disabled by default # ip netns add test1 # ip netns exec test1 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = -65536 # share the global table # sysctl -w net.ipv4.udp_child_hash_entries=100 net.ipv4.udp_child_hash_entries = 100 # ip netns add test2 # ip netns exec test2 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 128 # own a per-netns table with 2^n buckets We could optimise the hash table lookup/iteration further by removing the netns comparison for the per-netns one in the future. Also, we could optimise the sparse udp_hslot layout by putting it in udp_table. [0]: https://lore.kernel.org/netdev/4ACC2815.7010101@gmail.com/ Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-11-15 05:57:57 +08:00
static void __net_exit udp_pernet_exit(struct net *net)
{
udp_pernet_table_free(net);
}
static struct pernet_operations __net_initdata udp_sysctl_ops = {
udp: Introduce optional per-netns hash table. The maximum hash table size is 64K due to the nature of the protocol. [0] It's smaller than TCP, and fewer sockets can cause a performance drop. On an EC2 c5.24xlarge instance (192 GiB memory), after running iperf3 in different netns, creating 32Mi sockets without data transfer in the root netns causes regression for the iperf3's connection. uhash_entries sockets length Gbps 64K 1 1 5.69 1Mi 16 5.27 2Mi 32 4.90 4Mi 64 4.09 8Mi 128 2.96 16Mi 256 2.06 32Mi 512 1.12 The per-netns hash table breaks the lengthy lists into shorter ones. It is useful on a multi-tenant system with thousands of netns. With smaller hash tables, we can look up sockets faster, isolate noisy neighbours, and reduce lock contention. The max size of the per-netns table is 64K as well. This is because the possible hash range by udp_hashfn() always fits in 64K within the same netns and we cannot make full use of the whole buckets larger than 64K. /* 0 < num < 64K -> X < hash < X + 64K */ (num + net_hash_mix(net)) & mask; Also, the min size is 128. We use a bitmap to search for an available port in udp_lib_get_port(). To keep the bitmap on the stack and not fire the CONFIG_FRAME_WARN error at build time, we round up the table size to 128. The sysctl usage is the same with TCP: $ dmesg | cut -d ' ' -f 6- | grep "UDP hash" UDP hash table entries: 65536 (order: 9, 2097152 bytes, vmalloc) # sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 65536 # can be changed by uhash_entries # sysctl net.ipv4.udp_child_hash_entries net.ipv4.udp_child_hash_entries = 0 # disabled by default # ip netns add test1 # ip netns exec test1 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = -65536 # share the global table # sysctl -w net.ipv4.udp_child_hash_entries=100 net.ipv4.udp_child_hash_entries = 100 # ip netns add test2 # ip netns exec test2 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 128 # own a per-netns table with 2^n buckets We could optimise the hash table lookup/iteration further by removing the netns comparison for the per-netns one in the future. Also, we could optimise the sparse udp_hslot layout by putting it in udp_table. [0]: https://lore.kernel.org/netdev/4ACC2815.7010101@gmail.com/ Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-11-15 05:57:57 +08:00
.init = udp_pernet_init,
.exit = udp_pernet_exit,
};
#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
DEFINE_BPF_ITER_FUNC(udp, struct bpf_iter_meta *meta,
struct udp_sock *udp_sk, uid_t uid, int bucket)
static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux)
{
struct udp_iter_state *st = priv_data;
struct udp_seq_afinfo *afinfo;
int ret;
afinfo = kmalloc(sizeof(*afinfo), GFP_USER | __GFP_NOWARN);
if (!afinfo)
return -ENOMEM;
afinfo->family = AF_UNSPEC;
afinfo->udp_table = NULL;
st->bpf_seq_afinfo = afinfo;
ret = bpf_iter_init_seq_net(priv_data, aux);
if (ret)
kfree(afinfo);
return ret;
}
static void bpf_iter_fini_udp(void *priv_data)
{
struct udp_iter_state *st = priv_data;
kfree(st->bpf_seq_afinfo);
bpf_iter_fini_seq_net(priv_data);
}
static const struct bpf_iter_seq_info udp_seq_info = {
.seq_ops = &bpf_iter_udp_seq_ops,
.init_seq_private = bpf_iter_init_udp,
.fini_seq_private = bpf_iter_fini_udp,
.seq_priv_size = sizeof(struct udp_iter_state),
};
static struct bpf_iter_reg udp_reg_info = {
.target = "udp",
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__udp, udp_sk),
PTR_TO_BTF_ID_OR_NULL },
},
.seq_info = &udp_seq_info,
};
static void __init bpf_iter_register(void)
{
udp_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_UDP];
if (bpf_iter_reg_target(&udp_reg_info))
pr_warn("Warning: could not register bpf iterator udp\n");
}
#endif
void __init udp_init(void)
{
unsigned long limit;
unsigned int i;
udp_table_init(&udp_table, "UDP");
limit = nr_free_buffer_pages() / 8;
limit = max(limit, 128UL);
sysctl_udp_mem[0] = limit / 4 * 3;
sysctl_udp_mem[1] = limit;
sysctl_udp_mem[2] = sysctl_udp_mem[0] * 2;
/* 16 spinlocks per cpu */
udp_busylocks_log = ilog2(nr_cpu_ids) + 4;
udp_busylocks = kmalloc(sizeof(spinlock_t) << udp_busylocks_log,
GFP_KERNEL);
if (!udp_busylocks)
panic("UDP: failed to alloc udp_busylocks\n");
for (i = 0; i < (1U << udp_busylocks_log); i++)
spin_lock_init(udp_busylocks + i);
if (register_pernet_subsys(&udp_sysctl_ops))
panic("UDP: failed to init sysctl parameters.\n");
#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
bpf_iter_register();
#endif
}