linux/net/ipv4/inet_hashtables.c

1280 lines
34 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.
*
* Generic INET transport hashtables
*
* Authors: Lotsa people, from code originally in tcp
*/
#include <linux/module.h>
#include <linux/random.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/wait.h>
#include <linux/vmalloc.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 01:09:49 +03:00
#include <linux/memblock.h>
#include <net/addrconf.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
#if IS_ENABLED(CONFIG_IPV6)
#include <net/inet6_hashtables.h>
#endif
#include <net/secure_seq.h>
#include <net/ip.h>
net: Require exact match for TCP socket lookups if dif is l3mdev Currently, socket lookups for l3mdev (vrf) use cases can match a socket that is bound to a port but not a device (ie., a global socket). If the sysctl tcp_l3mdev_accept is not set this leads to ack packets going out based on the main table even though the packet came in from an L3 domain. The end result is that the connection does not establish creating confusion for users since the service is running and a socket shows in ss output. Fix by requiring an exact dif to sk_bound_dev_if match if the skb came through an interface enslaved to an l3mdev device and the tcp_l3mdev_accept is not set. skb's through an l3mdev interface are marked by setting a flag in inet{6}_skb_parm. The IPv6 variant is already set; this patch adds the flag for IPv4. Using an skb flag avoids a device lookup on the dif. The flag is set in the VRF driver using the IP{6}CB macros. For IPv4, the inet_skb_parm struct is moved in the cb per commit 971f10eca186, so the match function in the TCP stack needs to use TCP_SKB_CB. For IPv6, the move is done after the socket lookup, so IP6CB is used. The flags field in inet_skb_parm struct needs to be increased to add another flag. There is currently a 1-byte hole following the flags, so it can be expanded to u16 without increasing the size of the struct. Fixes: 193125dbd8eb ("net: Introduce VRF device driver") Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-17 06:02:52 +03:00
#include <net/tcp.h>
#include <net/sock_reuseport.h>
static u32 inet_ehashfn(const struct net *net, const __be32 laddr,
const __u16 lport, const __be32 faddr,
const __be16 fport)
{
static u32 inet_ehash_secret __read_mostly;
net_get_random_once(&inet_ehash_secret, sizeof(inet_ehash_secret));
return __inet_ehashfn(laddr, lport, faddr, fport,
inet_ehash_secret + net_hash_mix(net));
}
/* This function handles inet_sock, but also timewait and request sockets
* for IPv4/IPv6.
*/
static u32 sk_ehashfn(const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6 &&
!ipv6_addr_v4mapped(&sk->sk_v6_daddr))
return inet6_ehashfn(sock_net(sk),
&sk->sk_v6_rcv_saddr, sk->sk_num,
&sk->sk_v6_daddr, sk->sk_dport);
#endif
return inet_ehashfn(sock_net(sk),
sk->sk_rcv_saddr, sk->sk_num,
sk->sk_daddr, sk->sk_dport);
}
/*
* Allocate and initialize a new local port bind bucket.
* The bindhash mutex for snum's hash chain must be held here.
*/
struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
struct net *net,
struct inet_bind_hashbucket *head,
const unsigned short snum,
int l3mdev)
{
struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
if (tb) {
write_pnet(&tb->ib_net, net);
tb->l3mdev = l3mdev;
tb->port = snum;
tb->fastreuse = 0;
tb->fastreuseport = 0;
INIT_HLIST_HEAD(&tb->owners);
hlist_add_head(&tb->node, &head->chain);
}
return tb;
}
/*
* Caller must hold hashbucket lock for this tb with local BH disabled
*/
void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb)
{
if (hlist_empty(&tb->owners)) {
__hlist_del(&tb->node);
kmem_cache_free(cachep, tb);
}
}
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, const struct net *net,
unsigned short port, int l3mdev)
{
return net_eq(ib_net(tb), net) && tb->port == port &&
tb->l3mdev == l3mdev;
}
static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb,
struct net *net,
struct inet_bind_hashbucket *head,
unsigned short port, int l3mdev,
const struct sock *sk)
{
write_pnet(&tb->ib_net, net);
tb->l3mdev = l3mdev;
tb->port = port;
#if IS_ENABLED(CONFIG_IPV6)
tb->family = sk->sk_family;
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
if (sk->sk_family == AF_INET6)
tb->v6_rcv_saddr = sk->sk_v6_rcv_saddr;
else
#endif
tb->rcv_saddr = sk->sk_rcv_saddr;
INIT_HLIST_HEAD(&tb->owners);
INIT_HLIST_HEAD(&tb->deathrow);
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
hlist_add_head(&tb->node, &head->chain);
}
struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep,
struct net *net,
struct inet_bind_hashbucket *head,
unsigned short port,
int l3mdev,
const struct sock *sk)
{
struct inet_bind2_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
if (tb)
inet_bind2_bucket_init(tb, net, head, port, l3mdev, sk);
return tb;
}
/* Caller must hold hashbucket lock for this tb with local BH disabled */
void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb)
{
if (hlist_empty(&tb->owners) && hlist_empty(&tb->deathrow)) {
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
__hlist_del(&tb->node);
kmem_cache_free(cachep, tb);
}
}
static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2,
const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family != tb2->family)
return false;
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
if (sk->sk_family == AF_INET6)
return ipv6_addr_equal(&tb2->v6_rcv_saddr,
&sk->sk_v6_rcv_saddr);
#endif
return tb2->rcv_saddr == sk->sk_rcv_saddr;
}
void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
struct inet_bind2_bucket *tb2, unsigned short port)
{
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
inet_sk(sk)->inet_num = port;
sk_add_bind_node(sk, &tb->owners);
inet_csk(sk)->icsk_bind_hash = tb;
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
sk_add_bind2_node(sk, &tb2->owners);
inet_csk(sk)->icsk_bind2_hash = tb2;
}
/*
* Get rid of any references to a local port held by the given sock.
*/
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 15:06:04 +03:00
static void __inet_put_port(struct sock *sk)
{
struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
struct inet_bind_hashbucket *head, *head2;
struct net *net = sock_net(sk);
struct inet_bind_bucket *tb;
int bhash;
bhash = inet_bhashfn(net, inet_sk(sk)->inet_num, hashinfo->bhash_size);
head = &hashinfo->bhash[bhash];
head2 = inet_bhashfn_portaddr(hashinfo, sk, net, inet_sk(sk)->inet_num);
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
__sk_del_bind_node(sk);
inet_csk(sk)->icsk_bind_hash = NULL;
inet_sk(sk)->inet_num = 0;
inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
spin_lock(&head2->lock);
if (inet_csk(sk)->icsk_bind2_hash) {
struct inet_bind2_bucket *tb2 = inet_csk(sk)->icsk_bind2_hash;
__sk_del_bind2_node(sk);
inet_csk(sk)->icsk_bind2_hash = NULL;
inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
}
spin_unlock(&head2->lock);
spin_unlock(&head->lock);
}
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 15:06:04 +03:00
void inet_put_port(struct sock *sk)
{
local_bh_disable();
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 15:06:04 +03:00
__inet_put_port(sk);
local_bh_enable();
}
EXPORT_SYMBOL(inet_put_port);
int __inet_inherit_port(const struct sock *sk, struct sock *child)
{
struct inet_hashinfo *table = tcp_or_dccp_get_hashinfo(sk);
unsigned short port = inet_sk(child)->inet_num;
struct inet_bind_hashbucket *head, *head2;
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
bool created_inet_bind_bucket = false;
struct net *net = sock_net(sk);
bool update_fastreuse = false;
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
struct inet_bind2_bucket *tb2;
struct inet_bind_bucket *tb;
int bhash, l3mdev;
bhash = inet_bhashfn(net, port, table->bhash_size);
head = &table->bhash[bhash];
head2 = inet_bhashfn_portaddr(table, child, net, port);
spin_lock(&head->lock);
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
spin_lock(&head2->lock);
tb = inet_csk(sk)->icsk_bind_hash;
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
tb2 = inet_csk(sk)->icsk_bind2_hash;
if (unlikely(!tb || !tb2)) {
spin_unlock(&head2->lock);
spin_unlock(&head->lock);
return -ENOENT;
}
if (tb->port != port) {
l3mdev = inet_sk_bound_l3mdev(sk);
/* NOTE: using tproxy and redirecting skbs to a proxy
* on a different listener port breaks the assumption
* that the listener socket's icsk_bind_hash is the same
* as that of the child socket. We have to look up or
* create a new bind bucket for the child here. */
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 05:06:00 +04:00
inet_bind_bucket_for_each(tb, &head->chain) {
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
if (inet_bind_bucket_match(tb, net, port, l3mdev))
break;
}
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 05:06:00 +04:00
if (!tb) {
tb = inet_bind_bucket_create(table->bind_bucket_cachep,
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
net, head, port, l3mdev);
if (!tb) {
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
spin_unlock(&head2->lock);
spin_unlock(&head->lock);
return -ENOMEM;
}
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
created_inet_bind_bucket = true;
}
update_fastreuse = true;
goto bhash2_find;
} else if (!inet_bind2_bucket_addr_match(tb2, child)) {
l3mdev = inet_sk_bound_l3mdev(sk);
bhash2_find:
tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, child);
if (!tb2) {
tb2 = inet_bind2_bucket_create(table->bind2_bucket_cachep,
net, head2, port,
l3mdev, child);
if (!tb2)
goto error;
}
}
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
if (update_fastreuse)
inet_csk_update_fastreuse(tb, child);
inet_bind_hash(child, tb, tb2, port);
spin_unlock(&head2->lock);
spin_unlock(&head->lock);
return 0;
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
error:
if (created_inet_bind_bucket)
inet_bind_bucket_destroy(table->bind_bucket_cachep, tb);
spin_unlock(&head2->lock);
spin_unlock(&head->lock);
return -ENOMEM;
}
EXPORT_SYMBOL_GPL(__inet_inherit_port);
static struct inet_listen_hashbucket *
inet_lhash2_bucket_sk(struct inet_hashinfo *h, struct sock *sk)
{
u32 hash;
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6)
hash = ipv6_portaddr_hash(sock_net(sk),
&sk->sk_v6_rcv_saddr,
inet_sk(sk)->inet_num);
else
#endif
hash = ipv4_portaddr_hash(sock_net(sk),
inet_sk(sk)->inet_rcv_saddr,
inet_sk(sk)->inet_num);
return inet_lhash2_bucket(h, hash);
}
static inline int compute_score(struct sock *sk, struct net *net,
const unsigned short hnum, const __be32 daddr,
const int dif, const int sdif)
{
int score = -1;
if (net_eq(sock_net(sk), net) && sk->sk_num == hnum &&
!ipv6_only_sock(sk)) {
if (sk->sk_rcv_saddr != daddr)
return -1;
if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
return -1;
score = sk->sk_bound_dev_if ? 2 : 1;
if (sk->sk_family == PF_INET)
score++;
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>
2019-10-30 23:00:04 +03:00
if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
score++;
}
return score;
}
static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
struct sk_buff *skb, int doff,
__be32 saddr, __be16 sport,
__be32 daddr, unsigned short hnum)
{
struct sock *reuse_sk = NULL;
u32 phash;
if (sk->sk_reuseport) {
phash = inet_ehashfn(net, daddr, hnum, saddr, sport);
reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
}
return reuse_sk;
}
/*
* Here are some nice properties to exploit here. The BSD API
* does not allow a listening sock to specify the remote port nor the
* remote address for the connection. So always assume those are both
* wildcarded during the search since they can never be otherwise.
*/
/* called with rcu_read_lock() : No refcount taken on the socket */
static struct sock *inet_lhash2_lookup(struct net *net,
struct inet_listen_hashbucket *ilb2,
struct sk_buff *skb, int doff,
const __be32 saddr, __be16 sport,
const __be32 daddr, const unsigned short hnum,
const int dif, const int sdif)
{
struct sock *sk, *result = NULL;
net: inet: Retire port only listening_hash The listen sk is currently stored in two hash tables, listening_hash (hashed by port) and lhash2 (hashed by port and address). After commit 0ee58dad5b06 ("net: tcp6: prefer listeners bound to an address") and commit d9fbc7f6431f ("net: tcp: prefer listeners bound to an address"), the TCP-SYN lookup fast path does not use listening_hash. The commit 05c0b35709c5 ("tcp: seq_file: Replace listening_hash with lhash2") also moved the seq_file (/proc/net/tcp) iteration usage from listening_hash to lhash2. There are still a few listening_hash usages left. One of them is inet_reuseport_add_sock() which uses the listening_hash to search a listen sk during the listen() system call. This turns out to be very slow on use cases that listen on many different VIPs at a popular port (e.g. 443). [ On top of the slowness in adding to the tail in the IPv6 case ]. The latter patch has a selftest to demonstrate this case. This patch takes this chance to move all remaining listening_hash usages to lhash2 and then retire listening_hash. Since most changes need to be done together, it is hard to cut the listening_hash to lhash2 switch into small patches. The changes in this patch is highlighted here for the review purpose. 1. Because of the listening_hash removal, lhash2 can use the sk->sk_nulls_node instead of the icsk->icsk_listen_portaddr_node. This will also keep the sk_unhashed() check to work as is after stop adding sk to listening_hash. The union is removed from inet_listen_hashbucket because only nulls_head is needed. 2. icsk->icsk_listen_portaddr_node and its helpers are removed. 3. The current lhash2 users needs to iterate with sk_nulls_node instead of icsk_listen_portaddr_node. One case is in the inet[6]_lhash2_lookup(). Another case is the seq_file iterator in tcp_ipv4.c. One thing to note is sk_nulls_next() is needed because the old inet_lhash2_for_each_icsk_continue() does a "next" first before iterating. 4. Move the remaining listening_hash usage to lhash2 inet_reuseport_add_sock() which this series is trying to improve. inet_diag.c and mptcp_diag.c are the final two remaining use cases and is moved to lhash2 now also. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-05-12 03:06:05 +03:00
struct hlist_nulls_node *node;
int score, hiscore = 0;
net: inet: Retire port only listening_hash The listen sk is currently stored in two hash tables, listening_hash (hashed by port) and lhash2 (hashed by port and address). After commit 0ee58dad5b06 ("net: tcp6: prefer listeners bound to an address") and commit d9fbc7f6431f ("net: tcp: prefer listeners bound to an address"), the TCP-SYN lookup fast path does not use listening_hash. The commit 05c0b35709c5 ("tcp: seq_file: Replace listening_hash with lhash2") also moved the seq_file (/proc/net/tcp) iteration usage from listening_hash to lhash2. There are still a few listening_hash usages left. One of them is inet_reuseport_add_sock() which uses the listening_hash to search a listen sk during the listen() system call. This turns out to be very slow on use cases that listen on many different VIPs at a popular port (e.g. 443). [ On top of the slowness in adding to the tail in the IPv6 case ]. The latter patch has a selftest to demonstrate this case. This patch takes this chance to move all remaining listening_hash usages to lhash2 and then retire listening_hash. Since most changes need to be done together, it is hard to cut the listening_hash to lhash2 switch into small patches. The changes in this patch is highlighted here for the review purpose. 1. Because of the listening_hash removal, lhash2 can use the sk->sk_nulls_node instead of the icsk->icsk_listen_portaddr_node. This will also keep the sk_unhashed() check to work as is after stop adding sk to listening_hash. The union is removed from inet_listen_hashbucket because only nulls_head is needed. 2. icsk->icsk_listen_portaddr_node and its helpers are removed. 3. The current lhash2 users needs to iterate with sk_nulls_node instead of icsk_listen_portaddr_node. One case is in the inet[6]_lhash2_lookup(). Another case is the seq_file iterator in tcp_ipv4.c. One thing to note is sk_nulls_next() is needed because the old inet_lhash2_for_each_icsk_continue() does a "next" first before iterating. 4. Move the remaining listening_hash usage to lhash2 inet_reuseport_add_sock() which this series is trying to improve. inet_diag.c and mptcp_diag.c are the final two remaining use cases and is moved to lhash2 now also. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-05-12 03:06:05 +03:00
sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) {
score = compute_score(sk, net, hnum, daddr, dif, sdif);
if (score > hiscore) {
result = lookup_reuseport(net, sk, skb, doff,
saddr, sport, daddr, hnum);
if (result)
return result;
result = sk;
hiscore = score;
}
}
return result;
}
inet: Run SK_LOOKUP BPF program on socket lookup Run a BPF program before looking up a listening socket on the receive path. Program selects a listening socket to yield as result of socket lookup by calling bpf_sk_assign() helper and returning SK_PASS code. Program can revert its decision by assigning a NULL socket with bpf_sk_assign(). Alternatively, BPF program can also fail the lookup by returning with SK_DROP, or let the lookup continue as usual with SK_PASS on return, when no socket has been selected with bpf_sk_assign(). This lets the user match packets with listening sockets freely at the last possible point on the receive path, where we know that packets are destined for local delivery after undergoing policing, filtering, and routing. With BPF code selecting the socket, directing packets destined to an IP range or to a port range to a single socket becomes possible. In case multiple programs are attached, they are run in series in the order in which they were attached. The end result is determined from return codes of all the programs according to following rules: 1. If any program returned SK_PASS and selected a valid socket, the socket is used as result of socket lookup. 2. If more than one program returned SK_PASS and selected a socket, last selection takes effect. 3. If any program returned SK_DROP, and no program returned SK_PASS and selected a socket, socket lookup fails with -ECONNREFUSED. 4. If all programs returned SK_PASS and none of them selected a socket, socket lookup continues to htable-based lookup. Suggested-by: Marek Majkowski <marek@cloudflare.com> Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200717103536.397595-5-jakub@cloudflare.com
2020-07-17 13:35:25 +03:00
static inline struct sock *inet_lookup_run_bpf(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
__be32 saddr, __be16 sport,
__be32 daddr, u16 hnum, const int dif)
inet: Run SK_LOOKUP BPF program on socket lookup Run a BPF program before looking up a listening socket on the receive path. Program selects a listening socket to yield as result of socket lookup by calling bpf_sk_assign() helper and returning SK_PASS code. Program can revert its decision by assigning a NULL socket with bpf_sk_assign(). Alternatively, BPF program can also fail the lookup by returning with SK_DROP, or let the lookup continue as usual with SK_PASS on return, when no socket has been selected with bpf_sk_assign(). This lets the user match packets with listening sockets freely at the last possible point on the receive path, where we know that packets are destined for local delivery after undergoing policing, filtering, and routing. With BPF code selecting the socket, directing packets destined to an IP range or to a port range to a single socket becomes possible. In case multiple programs are attached, they are run in series in the order in which they were attached. The end result is determined from return codes of all the programs according to following rules: 1. If any program returned SK_PASS and selected a valid socket, the socket is used as result of socket lookup. 2. If more than one program returned SK_PASS and selected a socket, last selection takes effect. 3. If any program returned SK_DROP, and no program returned SK_PASS and selected a socket, socket lookup fails with -ECONNREFUSED. 4. If all programs returned SK_PASS and none of them selected a socket, socket lookup continues to htable-based lookup. Suggested-by: Marek Majkowski <marek@cloudflare.com> Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200717103536.397595-5-jakub@cloudflare.com
2020-07-17 13:35:25 +03:00
{
struct sock *sk, *reuse_sk;
bool no_reuseport;
if (hashinfo != net->ipv4.tcp_death_row.hashinfo)
inet: Run SK_LOOKUP BPF program on socket lookup Run a BPF program before looking up a listening socket on the receive path. Program selects a listening socket to yield as result of socket lookup by calling bpf_sk_assign() helper and returning SK_PASS code. Program can revert its decision by assigning a NULL socket with bpf_sk_assign(). Alternatively, BPF program can also fail the lookup by returning with SK_DROP, or let the lookup continue as usual with SK_PASS on return, when no socket has been selected with bpf_sk_assign(). This lets the user match packets with listening sockets freely at the last possible point on the receive path, where we know that packets are destined for local delivery after undergoing policing, filtering, and routing. With BPF code selecting the socket, directing packets destined to an IP range or to a port range to a single socket becomes possible. In case multiple programs are attached, they are run in series in the order in which they were attached. The end result is determined from return codes of all the programs according to following rules: 1. If any program returned SK_PASS and selected a valid socket, the socket is used as result of socket lookup. 2. If more than one program returned SK_PASS and selected a socket, last selection takes effect. 3. If any program returned SK_DROP, and no program returned SK_PASS and selected a socket, socket lookup fails with -ECONNREFUSED. 4. If all programs returned SK_PASS and none of them selected a socket, socket lookup continues to htable-based lookup. Suggested-by: Marek Majkowski <marek@cloudflare.com> Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200717103536.397595-5-jakub@cloudflare.com
2020-07-17 13:35:25 +03:00
return NULL; /* only TCP is supported */
no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, saddr, sport,
daddr, hnum, dif, &sk);
inet: Run SK_LOOKUP BPF program on socket lookup Run a BPF program before looking up a listening socket on the receive path. Program selects a listening socket to yield as result of socket lookup by calling bpf_sk_assign() helper and returning SK_PASS code. Program can revert its decision by assigning a NULL socket with bpf_sk_assign(). Alternatively, BPF program can also fail the lookup by returning with SK_DROP, or let the lookup continue as usual with SK_PASS on return, when no socket has been selected with bpf_sk_assign(). This lets the user match packets with listening sockets freely at the last possible point on the receive path, where we know that packets are destined for local delivery after undergoing policing, filtering, and routing. With BPF code selecting the socket, directing packets destined to an IP range or to a port range to a single socket becomes possible. In case multiple programs are attached, they are run in series in the order in which they were attached. The end result is determined from return codes of all the programs according to following rules: 1. If any program returned SK_PASS and selected a valid socket, the socket is used as result of socket lookup. 2. If more than one program returned SK_PASS and selected a socket, last selection takes effect. 3. If any program returned SK_DROP, and no program returned SK_PASS and selected a socket, socket lookup fails with -ECONNREFUSED. 4. If all programs returned SK_PASS and none of them selected a socket, socket lookup continues to htable-based lookup. Suggested-by: Marek Majkowski <marek@cloudflare.com> Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200717103536.397595-5-jakub@cloudflare.com
2020-07-17 13:35:25 +03:00
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
if (reuse_sk)
sk = reuse_sk;
return sk;
}
struct sock *__inet_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
const __be32 saddr, __be16 sport,
const __be32 daddr, const unsigned short hnum,
const int dif, const int sdif)
{
struct inet_listen_hashbucket *ilb2;
struct sock *result = NULL;
unsigned int hash2;
inet: Run SK_LOOKUP BPF program on socket lookup Run a BPF program before looking up a listening socket on the receive path. Program selects a listening socket to yield as result of socket lookup by calling bpf_sk_assign() helper and returning SK_PASS code. Program can revert its decision by assigning a NULL socket with bpf_sk_assign(). Alternatively, BPF program can also fail the lookup by returning with SK_DROP, or let the lookup continue as usual with SK_PASS on return, when no socket has been selected with bpf_sk_assign(). This lets the user match packets with listening sockets freely at the last possible point on the receive path, where we know that packets are destined for local delivery after undergoing policing, filtering, and routing. With BPF code selecting the socket, directing packets destined to an IP range or to a port range to a single socket becomes possible. In case multiple programs are attached, they are run in series in the order in which they were attached. The end result is determined from return codes of all the programs according to following rules: 1. If any program returned SK_PASS and selected a valid socket, the socket is used as result of socket lookup. 2. If more than one program returned SK_PASS and selected a socket, last selection takes effect. 3. If any program returned SK_DROP, and no program returned SK_PASS and selected a socket, socket lookup fails with -ECONNREFUSED. 4. If all programs returned SK_PASS and none of them selected a socket, socket lookup continues to htable-based lookup. Suggested-by: Marek Majkowski <marek@cloudflare.com> Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200717103536.397595-5-jakub@cloudflare.com
2020-07-17 13:35:25 +03:00
/* Lookup redirect from BPF */
if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
result = inet_lookup_run_bpf(net, hashinfo, skb, doff,
saddr, sport, daddr, hnum, dif);
inet: Run SK_LOOKUP BPF program on socket lookup Run a BPF program before looking up a listening socket on the receive path. Program selects a listening socket to yield as result of socket lookup by calling bpf_sk_assign() helper and returning SK_PASS code. Program can revert its decision by assigning a NULL socket with bpf_sk_assign(). Alternatively, BPF program can also fail the lookup by returning with SK_DROP, or let the lookup continue as usual with SK_PASS on return, when no socket has been selected with bpf_sk_assign(). This lets the user match packets with listening sockets freely at the last possible point on the receive path, where we know that packets are destined for local delivery after undergoing policing, filtering, and routing. With BPF code selecting the socket, directing packets destined to an IP range or to a port range to a single socket becomes possible. In case multiple programs are attached, they are run in series in the order in which they were attached. The end result is determined from return codes of all the programs according to following rules: 1. If any program returned SK_PASS and selected a valid socket, the socket is used as result of socket lookup. 2. If more than one program returned SK_PASS and selected a socket, last selection takes effect. 3. If any program returned SK_DROP, and no program returned SK_PASS and selected a socket, socket lookup fails with -ECONNREFUSED. 4. If all programs returned SK_PASS and none of them selected a socket, socket lookup continues to htable-based lookup. Suggested-by: Marek Majkowski <marek@cloudflare.com> Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200717103536.397595-5-jakub@cloudflare.com
2020-07-17 13:35:25 +03:00
if (result)
goto done;
}
hash2 = ipv4_portaddr_hash(net, daddr, hnum);
ilb2 = inet_lhash2_bucket(hashinfo, hash2);
result = inet_lhash2_lookup(net, ilb2, skb, doff,
saddr, sport, daddr, hnum,
dif, sdif);
if (result)
bpf: Enable BPF_PROG_TYPE_SK_REUSEPORT bpf prog in reuseport selection This patch allows a BPF_PROG_TYPE_SK_REUSEPORT bpf prog to select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY introduced in the earlier patch. "bpf_run_sk_reuseport()" will return -ECONNREFUSED when the BPF_PROG_TYPE_SK_REUSEPORT prog returns SK_DROP. The callers, in inet[6]_hashtable.c and ipv[46]/udp.c, are modified to handle this case and return NULL immediately instead of continuing the sk search from its hashtable. It re-uses the existing SO_ATTACH_REUSEPORT_EBPF setsockopt to attach BPF_PROG_TYPE_SK_REUSEPORT. The "sk_reuseport_attach_bpf()" will check if the attaching bpf prog is in the new SK_REUSEPORT or the existing SOCKET_FILTER type and then check different things accordingly. One level of "__reuseport_attach_prog()" call is removed. The "sk_unhashed() && ..." and "sk->sk_reuseport_cb" tests are pushed back to "reuseport_attach_prog()" in sock_reuseport.c. sock_reuseport.c seems to have more knowledge on those test requirements than filter.c. In "reuseport_attach_prog()", after new_prog is attached to reuse->prog, the old_prog (if any) is also directly freed instead of returning the old_prog to the caller and asking the caller to free. The sysctl_optmem_max check is moved back to the "sk_reuseport_attach_filter()" and "sk_reuseport_attach_bpf()". As of other bpf prog types, the new BPF_PROG_TYPE_SK_REUSEPORT is only bounded by the usual "bpf_prog_charge_memlock()" during load time instead of bounded by both bpf_prog_charge_memlock and sysctl_optmem_max. 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 11:01:26 +03:00
goto done;
/* Lookup lhash2 with INADDR_ANY */
hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
ilb2 = inet_lhash2_bucket(hashinfo, hash2);
bpf: Enable BPF_PROG_TYPE_SK_REUSEPORT bpf prog in reuseport selection This patch allows a BPF_PROG_TYPE_SK_REUSEPORT bpf prog to select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY introduced in the earlier patch. "bpf_run_sk_reuseport()" will return -ECONNREFUSED when the BPF_PROG_TYPE_SK_REUSEPORT prog returns SK_DROP. The callers, in inet[6]_hashtable.c and ipv[46]/udp.c, are modified to handle this case and return NULL immediately instead of continuing the sk search from its hashtable. It re-uses the existing SO_ATTACH_REUSEPORT_EBPF setsockopt to attach BPF_PROG_TYPE_SK_REUSEPORT. The "sk_reuseport_attach_bpf()" will check if the attaching bpf prog is in the new SK_REUSEPORT or the existing SOCKET_FILTER type and then check different things accordingly. One level of "__reuseport_attach_prog()" call is removed. The "sk_unhashed() && ..." and "sk->sk_reuseport_cb" tests are pushed back to "reuseport_attach_prog()" in sock_reuseport.c. sock_reuseport.c seems to have more knowledge on those test requirements than filter.c. In "reuseport_attach_prog()", after new_prog is attached to reuse->prog, the old_prog (if any) is also directly freed instead of returning the old_prog to the caller and asking the caller to free. The sysctl_optmem_max check is moved back to the "sk_reuseport_attach_filter()" and "sk_reuseport_attach_bpf()". As of other bpf prog types, the new BPF_PROG_TYPE_SK_REUSEPORT is only bounded by the usual "bpf_prog_charge_memlock()" during load time instead of bounded by both bpf_prog_charge_memlock and sysctl_optmem_max. 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 11:01:26 +03:00
result = inet_lhash2_lookup(net, ilb2, skb, doff,
saddr, sport, htonl(INADDR_ANY), hnum,
bpf: Enable BPF_PROG_TYPE_SK_REUSEPORT bpf prog in reuseport selection This patch allows a BPF_PROG_TYPE_SK_REUSEPORT bpf prog to select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY introduced in the earlier patch. "bpf_run_sk_reuseport()" will return -ECONNREFUSED when the BPF_PROG_TYPE_SK_REUSEPORT prog returns SK_DROP. The callers, in inet[6]_hashtable.c and ipv[46]/udp.c, are modified to handle this case and return NULL immediately instead of continuing the sk search from its hashtable. It re-uses the existing SO_ATTACH_REUSEPORT_EBPF setsockopt to attach BPF_PROG_TYPE_SK_REUSEPORT. The "sk_reuseport_attach_bpf()" will check if the attaching bpf prog is in the new SK_REUSEPORT or the existing SOCKET_FILTER type and then check different things accordingly. One level of "__reuseport_attach_prog()" call is removed. The "sk_unhashed() && ..." and "sk->sk_reuseport_cb" tests are pushed back to "reuseport_attach_prog()" in sock_reuseport.c. sock_reuseport.c seems to have more knowledge on those test requirements than filter.c. In "reuseport_attach_prog()", after new_prog is attached to reuse->prog, the old_prog (if any) is also directly freed instead of returning the old_prog to the caller and asking the caller to free. The sysctl_optmem_max check is moved back to the "sk_reuseport_attach_filter()" and "sk_reuseport_attach_bpf()". As of other bpf prog types, the new BPF_PROG_TYPE_SK_REUSEPORT is only bounded by the usual "bpf_prog_charge_memlock()" during load time instead of bounded by both bpf_prog_charge_memlock and sysctl_optmem_max. 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 11:01:26 +03:00
dif, sdif);
done:
if (IS_ERR(result))
bpf: Enable BPF_PROG_TYPE_SK_REUSEPORT bpf prog in reuseport selection This patch allows a BPF_PROG_TYPE_SK_REUSEPORT bpf prog to select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY introduced in the earlier patch. "bpf_run_sk_reuseport()" will return -ECONNREFUSED when the BPF_PROG_TYPE_SK_REUSEPORT prog returns SK_DROP. The callers, in inet[6]_hashtable.c and ipv[46]/udp.c, are modified to handle this case and return NULL immediately instead of continuing the sk search from its hashtable. It re-uses the existing SO_ATTACH_REUSEPORT_EBPF setsockopt to attach BPF_PROG_TYPE_SK_REUSEPORT. The "sk_reuseport_attach_bpf()" will check if the attaching bpf prog is in the new SK_REUSEPORT or the existing SOCKET_FILTER type and then check different things accordingly. One level of "__reuseport_attach_prog()" call is removed. The "sk_unhashed() && ..." and "sk->sk_reuseport_cb" tests are pushed back to "reuseport_attach_prog()" in sock_reuseport.c. sock_reuseport.c seems to have more knowledge on those test requirements than filter.c. In "reuseport_attach_prog()", after new_prog is attached to reuse->prog, the old_prog (if any) is also directly freed instead of returning the old_prog to the caller and asking the caller to free. The sysctl_optmem_max check is moved back to the "sk_reuseport_attach_filter()" and "sk_reuseport_attach_bpf()". As of other bpf prog types, the new BPF_PROG_TYPE_SK_REUSEPORT is only bounded by the usual "bpf_prog_charge_memlock()" during load time instead of bounded by both bpf_prog_charge_memlock and sysctl_optmem_max. 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 11:01:26 +03:00
return NULL;
return result;
}
EXPORT_SYMBOL_GPL(__inet_lookup_listener);
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 11:22:02 +04:00
/* All sockets share common refcount, but have different destructors */
void sock_gen_put(struct sock *sk)
{
if (!refcount_dec_and_test(&sk->sk_refcnt))
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 11:22:02 +04:00
return;
if (sk->sk_state == TCP_TIME_WAIT)
inet_twsk_free(inet_twsk(sk));
else if (sk->sk_state == TCP_NEW_SYN_RECV)
reqsk_free(inet_reqsk(sk));
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 11:22:02 +04:00
else
sk_free(sk);
}
EXPORT_SYMBOL_GPL(sock_gen_put);
void sock_edemux(struct sk_buff *skb)
{
sock_gen_put(skb->sk);
}
EXPORT_SYMBOL(sock_edemux);
struct sock *__inet_lookup_established(struct net *net,
struct inet_hashinfo *hashinfo,
const __be32 saddr, const __be16 sport,
const __be32 daddr, const u16 hnum,
const int dif, const int sdif)
{
INET_ADDR_COOKIE(acookie, saddr, daddr);
const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
struct sock *sk;
const struct hlist_nulls_node *node;
/* Optimize here for direct hit, only listening connections can
* have wildcards anyways.
*/
unsigned int hash = inet_ehashfn(net, daddr, hnum, saddr, sport);
unsigned int slot = hash & hashinfo->ehash_mask;
struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
begin:
sk_nulls_for_each_rcu(sk, node, &head->chain) {
net: move inet_dport/inet_num in sock_common commit 68835aba4d9b (net: optimize INET input path further) moved some fields used for tcp/udp sockets lookup in the first cache line of struct sock_common. This patch moves inet_dport/inet_num as well, filling a 32bit hole on 64 bit arches and reducing number of cache line misses in lookups. Also change INET_MATCH()/INET_TW_MATCH() to perform the ports match before addresses match, as this check is more discriminant. Remove the hash check from MATCH() macros because we dont need to re validate the hash value after taking a refcount on socket, and use likely/unlikely compiler hints, as the sk_hash/hash check makes the following conditional tests 100% predicted by cpu. Introduce skc_addrpair/skc_portpair pair values to better document the alignment requirements of the port/addr pairs used in the various MATCH() macros, and remove some casts. The namespace check can also be done at last. This slightly improves TCP/UDP lookup times. IP/TCP early demux needs inet->rx_dst_ifindex and TCP needs inet->min_ttl, lets group them together in same cache line. With help from Ben Hutchings & Joe Perches. Idea of this patch came after Ling Ma proposal to move skc_hash to the beginning of struct sock_common, and should allow him to submit a final version of his patch. My tests show an improvement doing so. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Joe Perches <joe@perches.com> Cc: Ling Ma <ling.ma.program@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-30 13:49:27 +04:00
if (sk->sk_hash != hash)
continue;
if (likely(inet_match(net, sk, acookie, ports, dif, sdif))) {
if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 11:22:02 +04:00
goto out;
if (unlikely(!inet_match(net, sk, acookie,
ports, dif, sdif))) {
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 11:22:02 +04:00
sock_gen_put(sk);
goto begin;
}
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 11:22:02 +04:00
goto found;
}
}
/*
* if the nulls value we got at the end of this lookup is
* not the expected one, we must restart lookup.
* We probably met an item that was moved to another chain.
*/
if (get_nulls_value(node) != slot)
goto begin;
out:
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 11:22:02 +04:00
sk = NULL;
found:
return sk;
}
EXPORT_SYMBOL_GPL(__inet_lookup_established);
/* called with local bh disabled */
static int __inet_check_established(struct inet_timewait_death_row *death_row,
struct sock *sk, __u16 lport,
struct inet_timewait_sock **twp)
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
struct inet_sock *inet = inet_sk(sk);
__be32 daddr = inet->inet_rcv_saddr;
__be32 saddr = inet->inet_daddr;
int dif = sk->sk_bound_dev_if;
struct net *net = sock_net(sk);
int sdif = l3mdev_master_ifindex_by_index(net, dif);
INET_ADDR_COOKIE(acookie, saddr, daddr);
const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
unsigned int hash = inet_ehashfn(net, daddr, lport,
saddr, inet->inet_dport);
struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
struct sock *sk2;
const struct hlist_nulls_node *node;
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 11:22:02 +04:00
struct inet_timewait_sock *tw = NULL;
spin_lock(lock);
sk_nulls_for_each(sk2, node, &head->chain) {
net: move inet_dport/inet_num in sock_common commit 68835aba4d9b (net: optimize INET input path further) moved some fields used for tcp/udp sockets lookup in the first cache line of struct sock_common. This patch moves inet_dport/inet_num as well, filling a 32bit hole on 64 bit arches and reducing number of cache line misses in lookups. Also change INET_MATCH()/INET_TW_MATCH() to perform the ports match before addresses match, as this check is more discriminant. Remove the hash check from MATCH() macros because we dont need to re validate the hash value after taking a refcount on socket, and use likely/unlikely compiler hints, as the sk_hash/hash check makes the following conditional tests 100% predicted by cpu. Introduce skc_addrpair/skc_portpair pair values to better document the alignment requirements of the port/addr pairs used in the various MATCH() macros, and remove some casts. The namespace check can also be done at last. This slightly improves TCP/UDP lookup times. IP/TCP early demux needs inet->rx_dst_ifindex and TCP needs inet->min_ttl, lets group them together in same cache line. With help from Ben Hutchings & Joe Perches. Idea of this patch came after Ling Ma proposal to move skc_hash to the beginning of struct sock_common, and should allow him to submit a final version of his patch. My tests show an improvement doing so. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Joe Perches <joe@perches.com> Cc: Ling Ma <ling.ma.program@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-30 13:49:27 +04:00
if (sk2->sk_hash != hash)
continue;
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 11:22:02 +04:00
if (likely(inet_match(net, sk2, acookie, ports, dif, sdif))) {
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 11:22:02 +04:00
if (sk2->sk_state == TCP_TIME_WAIT) {
tw = inet_twsk(sk2);
if (twsk_unique(sk, sk2, twp))
break;
}
goto not_unique;
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 11:22:02 +04:00
}
}
/* Must record num and sport now. Otherwise we will see
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 11:22:02 +04:00
* in hash table socket with a funny identity.
*/
inet->inet_num = lport;
inet->inet_sport = htons(lport);
sk->sk_hash = hash;
WARN_ON(!sk_unhashed(sk));
__sk_nulls_add_node_rcu(sk, &head->chain);
if (tw) {
sk_nulls_del_node_init_rcu((struct sock *)tw);
__NET_INC_STATS(net, LINUX_MIB_TIMEWAITRECYCLED);
}
spin_unlock(lock);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
if (twp) {
*twp = tw;
} else if (tw) {
/* Silly. Should hash-dance instead... */
inet_twsk_deschedule_put(tw);
}
return 0;
not_unique:
spin_unlock(lock);
return -EADDRNOTAVAIL;
}
static u64 inet_sk_port_offset(const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
return secure_ipv4_port_ephemeral(inet->inet_rcv_saddr,
inet->inet_daddr,
inet->inet_dport);
}
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
/* Searches for an exsiting socket in the ehash bucket list.
* Returns true if found, false otherwise.
*/
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
static bool inet_ehash_lookup_by_sk(struct sock *sk,
struct hlist_nulls_head *list)
{
const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport, sk->sk_num);
const int sdif = sk->sk_bound_dev_if;
const int dif = sk->sk_bound_dev_if;
const struct hlist_nulls_node *node;
struct net *net = sock_net(sk);
struct sock *esk;
INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr);
sk_nulls_for_each_rcu(esk, node, list) {
if (esk->sk_hash != sk->sk_hash)
continue;
if (sk->sk_family == AF_INET) {
if (unlikely(inet_match(net, esk, acookie,
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
ports, dif, sdif))) {
return true;
}
}
#if IS_ENABLED(CONFIG_IPV6)
else if (sk->sk_family == AF_INET6) {
if (unlikely(inet6_match(net, esk,
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
&sk->sk_v6_daddr,
&sk->sk_v6_rcv_saddr,
ports, dif, sdif))) {
return true;
}
}
#endif
}
return false;
}
/* Insert a socket into ehash, and eventually remove another one
* (The another one can be a SYN_RECV or TIMEWAIT)
* If an existing socket already exists, socket sk is not inserted,
* and sets found_dup_sk parameter to true.
*/
bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
{
struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
struct inet_ehash_bucket *head;
struct hlist_nulls_head *list;
spinlock_t *lock;
bool ret = true;
WARN_ON_ONCE(!sk_unhashed(sk));
sk->sk_hash = sk_ehashfn(sk);
head = inet_ehash_bucket(hashinfo, sk->sk_hash);
list = &head->chain;
lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
spin_lock(lock);
if (osk) {
WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
tcp: avoid the lookup process failing to get sk in ehash table While one cpu is working on looking up the right socket from ehash table, another cpu is done deleting the request socket and is about to add (or is adding) the big socket from the table. It means that we could miss both of them, even though it has little chance. Let me draw a call trace map of the server side. CPU 0 CPU 1 ----- ----- tcp_v4_rcv() syn_recv_sock() inet_ehash_insert() -> sk_nulls_del_node_init_rcu(osk) __inet_lookup_established() -> __sk_nulls_add_node_rcu(sk, list) Notice that the CPU 0 is receiving the data after the final ack during 3-way shakehands and CPU 1 is still handling the final ack. Why could this be a real problem? This case is happening only when the final ack and the first data receiving by different CPUs. Then the server receiving data with ACK flag tries to search one proper established socket from ehash table, but apparently it fails as my map shows above. After that, the server fetches a listener socket and then sends a RST because it finds a ACK flag in the skb (data), which obeys RST definition in RFC 793. Besides, Eric pointed out there's one more race condition where it handles tw socket hashdance. Only by adding to the tail of the list before deleting the old one can we avoid the race if the reader has already begun the bucket traversal and it would possibly miss the head. Many thanks to Eric for great help from beginning to end. Fixes: 5e0724d027f0 ("tcp/dccp: fix hashdance race for passive sessions") Suggested-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jason Xing <kernelxing@tencent.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com> Link: https://lore.kernel.org/lkml/20230112065336.41034-1-kerneljasonxing@gmail.com/ Link: https://lore.kernel.org/r/20230118015941.1313-1-kerneljasonxing@gmail.com Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2023-01-18 04:59:41 +03:00
ret = sk_hashed(osk);
if (ret) {
/* Before deleting the node, we insert a new one to make
* sure that the look-up-sk process would not miss either
* of them and that at least one node would exist in ehash
* table all the time. Otherwise there's a tiny chance
* that lookup process could find nothing in ehash table.
*/
__sk_nulls_add_node_tail_rcu(sk, list);
sk_nulls_del_node_init_rcu(osk);
}
goto unlock;
}
if (found_dup_sk) {
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
*found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
if (*found_dup_sk)
ret = false;
}
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
if (ret)
__sk_nulls_add_node_rcu(sk, list);
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
tcp: avoid the lookup process failing to get sk in ehash table While one cpu is working on looking up the right socket from ehash table, another cpu is done deleting the request socket and is about to add (or is adding) the big socket from the table. It means that we could miss both of them, even though it has little chance. Let me draw a call trace map of the server side. CPU 0 CPU 1 ----- ----- tcp_v4_rcv() syn_recv_sock() inet_ehash_insert() -> sk_nulls_del_node_init_rcu(osk) __inet_lookup_established() -> __sk_nulls_add_node_rcu(sk, list) Notice that the CPU 0 is receiving the data after the final ack during 3-way shakehands and CPU 1 is still handling the final ack. Why could this be a real problem? This case is happening only when the final ack and the first data receiving by different CPUs. Then the server receiving data with ACK flag tries to search one proper established socket from ehash table, but apparently it fails as my map shows above. After that, the server fetches a listener socket and then sends a RST because it finds a ACK flag in the skb (data), which obeys RST definition in RFC 793. Besides, Eric pointed out there's one more race condition where it handles tw socket hashdance. Only by adding to the tail of the list before deleting the old one can we avoid the race if the reader has already begun the bucket traversal and it would possibly miss the head. Many thanks to Eric for great help from beginning to end. Fixes: 5e0724d027f0 ("tcp/dccp: fix hashdance race for passive sessions") Suggested-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jason Xing <kernelxing@tencent.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com> Link: https://lore.kernel.org/lkml/20230112065336.41034-1-kerneljasonxing@gmail.com/ Link: https://lore.kernel.org/r/20230118015941.1313-1-kerneljasonxing@gmail.com Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2023-01-18 04:59:41 +03:00
unlock:
spin_unlock(lock);
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
return ret;
}
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk)
{
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
bool ok = inet_ehash_insert(sk, osk, found_dup_sk);
if (ok) {
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
} else {
tcp: switch orphan_count to bare per-cpu counters Use of percpu_counter structure to track count of orphaned sockets is causing problems on modern hosts with 256 cpus or more. Stefan Bach reported a serious spinlock contention in real workloads, that I was able to reproduce with a netfilter rule dropping incoming FIN packets. 53.56% server [kernel.kallsyms] [k] queued_spin_lock_slowpath | ---queued_spin_lock_slowpath | --53.51%--_raw_spin_lock_irqsave | --53.51%--__percpu_counter_sum tcp_check_oom | |--39.03%--__tcp_close | tcp_close | inet_release | inet6_release | sock_close | __fput | ____fput | task_work_run | exit_to_usermode_loop | do_syscall_64 | entry_SYSCALL_64_after_hwframe | __GI___libc_close | --14.48%--tcp_out_of_resources tcp_write_timeout tcp_retransmit_timer tcp_write_timer_handler tcp_write_timer call_timer_fn expire_timers __run_timers run_timer_softirq __softirqentry_text_start As explained in commit cf86a086a180 ("net/dst: use a smaller percpu_counter batch for dst entries accounting"), default batch size is too big for the default value of tcp_max_orphans (262144). But even if we reduce batch sizes, there would still be cases where the estimated count of orphans is beyond the limit, and where tcp_too_many_orphans() has to call the expensive percpu_counter_sum_positive(). One solution is to use plain per-cpu counters, and have a timer to periodically refresh this cache. Updating this cache every 100ms seems about right, tcp pressure state is not radically changing over shorter periods. percpu_counter was nice 15 years ago while hosts had less than 16 cpus, not anymore by current standards. v2: Fix the build issue for CONFIG_CRYPTO_DEV_CHELSIO_TLS=m, reported by kernel test robot <lkp@intel.com> Remove unused socket argument from tcp_too_many_orphans() Fixes: dd24c00191d5 ("net: Use a percpu_counter for orphan_count") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Stefan Bach <sfb@google.com> Cc: Neal Cardwell <ncardwell@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-10-14 16:41:26 +03:00
this_cpu_inc(*sk->sk_prot->orphan_count);
inet_sk_set_state(sk, TCP_CLOSE);
sock_set_flag(sk, SOCK_DEAD);
inet_csk_destroy_sock(sk);
}
return ok;
}
EXPORT_SYMBOL_GPL(inet_ehash_nolisten);
static int inet_reuseport_add_sock(struct sock *sk,
struct inet_listen_hashbucket *ilb)
{
struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash;
const struct hlist_nulls_node *node;
struct sock *sk2;
kuid_t uid = sock_i_uid(sk);
sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) {
if (sk2 != sk &&
sk2->sk_family == sk->sk_family &&
ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&
sk2->sk_bound_dev_if == sk->sk_bound_dev_if &&
inet_csk(sk2)->icsk_bind_hash == tb &&
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 11:01:25 +03:00
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 11:01:25 +03:00
return reuseport_alloc(sk, inet_rcv_saddr_any(sk));
}
int __inet_hash(struct sock *sk, struct sock *osk)
{
struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
struct inet_listen_hashbucket *ilb2;
int err = 0;
if (sk->sk_state != TCP_LISTEN) {
tcp: Don't acquire inet_listen_hashbucket::lock with disabled BH. Commit 9652dc2eb9e40 ("tcp: relax listening_hash operations") removed the need to disable bottom half while acquiring listening_hash.lock. There are still two callers left which disable bottom half before the lock is acquired. On PREEMPT_RT the softirqs are preemptible and local_bh_disable() acts as a lock to ensure that resources, that are protected by disabling bottom halves, remain protected. This leads to a circular locking dependency if the lock acquired with disabled bottom halves is also acquired with enabled bottom halves followed by disabling bottom halves. This is the reverse locking order. It has been observed with inet_listen_hashbucket::lock: local_bh_disable() + spin_lock(&ilb->lock): inet_listen() inet_csk_listen_start() sk->sk_prot->hash() := inet_hash() local_bh_disable() __inet_hash() spin_lock(&ilb->lock); acquire(&ilb->lock); Reverse order: spin_lock(&ilb2->lock) + local_bh_disable(): tcp_seq_next() listening_get_next() spin_lock(&ilb2->lock); acquire(&ilb2->lock); tcp4_seq_show() get_tcp4_sock() sock_i_ino() read_lock_bh(&sk->sk_callback_lock); acquire(softirq_ctrl) // <---- whoops acquire(&sk->sk_callback_lock) Drop local_bh_disable() around __inet_hash() which acquires listening_hash->lock. Split inet_unhash() and acquire the listen_hashbucket lock without disabling bottom halves; the inet_ehash lock with disabled bottom halves. Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Link: https://lkml.kernel.org/r/12d6f9879a97cd56c09fb53dee343cbb14f7f1f7.camel@gmx.de Link: https://lkml.kernel.org/r/X9CheYjuXWc75Spa@hirez.programming.kicks-ass.net Link: https://lore.kernel.org/r/YgQOebeZ10eNx1W6@linutronix.de Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-02-09 21:56:57 +03:00
local_bh_disable();
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
inet_ehash_nolisten(sk, osk, NULL);
tcp: Don't acquire inet_listen_hashbucket::lock with disabled BH. Commit 9652dc2eb9e40 ("tcp: relax listening_hash operations") removed the need to disable bottom half while acquiring listening_hash.lock. There are still two callers left which disable bottom half before the lock is acquired. On PREEMPT_RT the softirqs are preemptible and local_bh_disable() acts as a lock to ensure that resources, that are protected by disabling bottom halves, remain protected. This leads to a circular locking dependency if the lock acquired with disabled bottom halves is also acquired with enabled bottom halves followed by disabling bottom halves. This is the reverse locking order. It has been observed with inet_listen_hashbucket::lock: local_bh_disable() + spin_lock(&ilb->lock): inet_listen() inet_csk_listen_start() sk->sk_prot->hash() := inet_hash() local_bh_disable() __inet_hash() spin_lock(&ilb->lock); acquire(&ilb->lock); Reverse order: spin_lock(&ilb2->lock) + local_bh_disable(): tcp_seq_next() listening_get_next() spin_lock(&ilb2->lock); acquire(&ilb2->lock); tcp4_seq_show() get_tcp4_sock() sock_i_ino() read_lock_bh(&sk->sk_callback_lock); acquire(softirq_ctrl) // <---- whoops acquire(&sk->sk_callback_lock) Drop local_bh_disable() around __inet_hash() which acquires listening_hash->lock. Split inet_unhash() and acquire the listen_hashbucket lock without disabling bottom halves; the inet_ehash lock with disabled bottom halves. Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Link: https://lkml.kernel.org/r/12d6f9879a97cd56c09fb53dee343cbb14f7f1f7.camel@gmx.de Link: https://lkml.kernel.org/r/X9CheYjuXWc75Spa@hirez.programming.kicks-ass.net Link: https://lore.kernel.org/r/YgQOebeZ10eNx1W6@linutronix.de Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-02-09 21:56:57 +03:00
local_bh_enable();
return 0;
}
WARN_ON(!sk_unhashed(sk));
ilb2 = inet_lhash2_bucket_sk(hashinfo, sk);
spin_lock(&ilb2->lock);
if (sk->sk_reuseport) {
net: inet: Retire port only listening_hash The listen sk is currently stored in two hash tables, listening_hash (hashed by port) and lhash2 (hashed by port and address). After commit 0ee58dad5b06 ("net: tcp6: prefer listeners bound to an address") and commit d9fbc7f6431f ("net: tcp: prefer listeners bound to an address"), the TCP-SYN lookup fast path does not use listening_hash. The commit 05c0b35709c5 ("tcp: seq_file: Replace listening_hash with lhash2") also moved the seq_file (/proc/net/tcp) iteration usage from listening_hash to lhash2. There are still a few listening_hash usages left. One of them is inet_reuseport_add_sock() which uses the listening_hash to search a listen sk during the listen() system call. This turns out to be very slow on use cases that listen on many different VIPs at a popular port (e.g. 443). [ On top of the slowness in adding to the tail in the IPv6 case ]. The latter patch has a selftest to demonstrate this case. This patch takes this chance to move all remaining listening_hash usages to lhash2 and then retire listening_hash. Since most changes need to be done together, it is hard to cut the listening_hash to lhash2 switch into small patches. The changes in this patch is highlighted here for the review purpose. 1. Because of the listening_hash removal, lhash2 can use the sk->sk_nulls_node instead of the icsk->icsk_listen_portaddr_node. This will also keep the sk_unhashed() check to work as is after stop adding sk to listening_hash. The union is removed from inet_listen_hashbucket because only nulls_head is needed. 2. icsk->icsk_listen_portaddr_node and its helpers are removed. 3. The current lhash2 users needs to iterate with sk_nulls_node instead of icsk_listen_portaddr_node. One case is in the inet[6]_lhash2_lookup(). Another case is the seq_file iterator in tcp_ipv4.c. One thing to note is sk_nulls_next() is needed because the old inet_lhash2_for_each_icsk_continue() does a "next" first before iterating. 4. Move the remaining listening_hash usage to lhash2 inet_reuseport_add_sock() which this series is trying to improve. inet_diag.c and mptcp_diag.c are the final two remaining use cases and is moved to lhash2 now also. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-05-12 03:06:05 +03:00
err = inet_reuseport_add_sock(sk, ilb2);
if (err)
goto unlock;
}
if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
net: inet: Retire port only listening_hash The listen sk is currently stored in two hash tables, listening_hash (hashed by port) and lhash2 (hashed by port and address). After commit 0ee58dad5b06 ("net: tcp6: prefer listeners bound to an address") and commit d9fbc7f6431f ("net: tcp: prefer listeners bound to an address"), the TCP-SYN lookup fast path does not use listening_hash. The commit 05c0b35709c5 ("tcp: seq_file: Replace listening_hash with lhash2") also moved the seq_file (/proc/net/tcp) iteration usage from listening_hash to lhash2. There are still a few listening_hash usages left. One of them is inet_reuseport_add_sock() which uses the listening_hash to search a listen sk during the listen() system call. This turns out to be very slow on use cases that listen on many different VIPs at a popular port (e.g. 443). [ On top of the slowness in adding to the tail in the IPv6 case ]. The latter patch has a selftest to demonstrate this case. This patch takes this chance to move all remaining listening_hash usages to lhash2 and then retire listening_hash. Since most changes need to be done together, it is hard to cut the listening_hash to lhash2 switch into small patches. The changes in this patch is highlighted here for the review purpose. 1. Because of the listening_hash removal, lhash2 can use the sk->sk_nulls_node instead of the icsk->icsk_listen_portaddr_node. This will also keep the sk_unhashed() check to work as is after stop adding sk to listening_hash. The union is removed from inet_listen_hashbucket because only nulls_head is needed. 2. icsk->icsk_listen_portaddr_node and its helpers are removed. 3. The current lhash2 users needs to iterate with sk_nulls_node instead of icsk_listen_portaddr_node. One case is in the inet[6]_lhash2_lookup(). Another case is the seq_file iterator in tcp_ipv4.c. One thing to note is sk_nulls_next() is needed because the old inet_lhash2_for_each_icsk_continue() does a "next" first before iterating. 4. Move the remaining listening_hash usage to lhash2 inet_reuseport_add_sock() which this series is trying to improve. inet_diag.c and mptcp_diag.c are the final two remaining use cases and is moved to lhash2 now also. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-05-12 03:06:05 +03:00
sk->sk_family == AF_INET6)
__sk_nulls_add_node_tail_rcu(sk, &ilb2->nulls_head);
else
__sk_nulls_add_node_rcu(sk, &ilb2->nulls_head);
sock_set_flag(sk, SOCK_RCU_FREE);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
unlock:
spin_unlock(&ilb2->lock);
return err;
}
EXPORT_SYMBOL(__inet_hash);
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 15:06:04 +03:00
int inet_hash(struct sock *sk)
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 15:06:04 +03:00
{
int err = 0;
tcp: Don't acquire inet_listen_hashbucket::lock with disabled BH. Commit 9652dc2eb9e40 ("tcp: relax listening_hash operations") removed the need to disable bottom half while acquiring listening_hash.lock. There are still two callers left which disable bottom half before the lock is acquired. On PREEMPT_RT the softirqs are preemptible and local_bh_disable() acts as a lock to ensure that resources, that are protected by disabling bottom halves, remain protected. This leads to a circular locking dependency if the lock acquired with disabled bottom halves is also acquired with enabled bottom halves followed by disabling bottom halves. This is the reverse locking order. It has been observed with inet_listen_hashbucket::lock: local_bh_disable() + spin_lock(&ilb->lock): inet_listen() inet_csk_listen_start() sk->sk_prot->hash() := inet_hash() local_bh_disable() __inet_hash() spin_lock(&ilb->lock); acquire(&ilb->lock); Reverse order: spin_lock(&ilb2->lock) + local_bh_disable(): tcp_seq_next() listening_get_next() spin_lock(&ilb2->lock); acquire(&ilb2->lock); tcp4_seq_show() get_tcp4_sock() sock_i_ino() read_lock_bh(&sk->sk_callback_lock); acquire(softirq_ctrl) // <---- whoops acquire(&sk->sk_callback_lock) Drop local_bh_disable() around __inet_hash() which acquires listening_hash->lock. Split inet_unhash() and acquire the listen_hashbucket lock without disabling bottom halves; the inet_ehash lock with disabled bottom halves. Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Link: https://lkml.kernel.org/r/12d6f9879a97cd56c09fb53dee343cbb14f7f1f7.camel@gmx.de Link: https://lkml.kernel.org/r/X9CheYjuXWc75Spa@hirez.programming.kicks-ass.net Link: https://lore.kernel.org/r/YgQOebeZ10eNx1W6@linutronix.de Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-02-09 21:56:57 +03:00
if (sk->sk_state != TCP_CLOSE)
err = __inet_hash(sk, NULL);
return err;
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 15:06:04 +03:00
}
EXPORT_SYMBOL_GPL(inet_hash);
tcp: Don't acquire inet_listen_hashbucket::lock with disabled BH. Commit 9652dc2eb9e40 ("tcp: relax listening_hash operations") removed the need to disable bottom half while acquiring listening_hash.lock. There are still two callers left which disable bottom half before the lock is acquired. On PREEMPT_RT the softirqs are preemptible and local_bh_disable() acts as a lock to ensure that resources, that are protected by disabling bottom halves, remain protected. This leads to a circular locking dependency if the lock acquired with disabled bottom halves is also acquired with enabled bottom halves followed by disabling bottom halves. This is the reverse locking order. It has been observed with inet_listen_hashbucket::lock: local_bh_disable() + spin_lock(&ilb->lock): inet_listen() inet_csk_listen_start() sk->sk_prot->hash() := inet_hash() local_bh_disable() __inet_hash() spin_lock(&ilb->lock); acquire(&ilb->lock); Reverse order: spin_lock(&ilb2->lock) + local_bh_disable(): tcp_seq_next() listening_get_next() spin_lock(&ilb2->lock); acquire(&ilb2->lock); tcp4_seq_show() get_tcp4_sock() sock_i_ino() read_lock_bh(&sk->sk_callback_lock); acquire(softirq_ctrl) // <---- whoops acquire(&sk->sk_callback_lock) Drop local_bh_disable() around __inet_hash() which acquires listening_hash->lock. Split inet_unhash() and acquire the listen_hashbucket lock without disabling bottom halves; the inet_ehash lock with disabled bottom halves. Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Link: https://lkml.kernel.org/r/12d6f9879a97cd56c09fb53dee343cbb14f7f1f7.camel@gmx.de Link: https://lkml.kernel.org/r/X9CheYjuXWc75Spa@hirez.programming.kicks-ass.net Link: https://lore.kernel.org/r/YgQOebeZ10eNx1W6@linutronix.de Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-02-09 21:56:57 +03:00
void inet_unhash(struct sock *sk)
{
struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk);
tcp: Don't acquire inet_listen_hashbucket::lock with disabled BH. Commit 9652dc2eb9e40 ("tcp: relax listening_hash operations") removed the need to disable bottom half while acquiring listening_hash.lock. There are still two callers left which disable bottom half before the lock is acquired. On PREEMPT_RT the softirqs are preemptible and local_bh_disable() acts as a lock to ensure that resources, that are protected by disabling bottom halves, remain protected. This leads to a circular locking dependency if the lock acquired with disabled bottom halves is also acquired with enabled bottom halves followed by disabling bottom halves. This is the reverse locking order. It has been observed with inet_listen_hashbucket::lock: local_bh_disable() + spin_lock(&ilb->lock): inet_listen() inet_csk_listen_start() sk->sk_prot->hash() := inet_hash() local_bh_disable() __inet_hash() spin_lock(&ilb->lock); acquire(&ilb->lock); Reverse order: spin_lock(&ilb2->lock) + local_bh_disable(): tcp_seq_next() listening_get_next() spin_lock(&ilb2->lock); acquire(&ilb2->lock); tcp4_seq_show() get_tcp4_sock() sock_i_ino() read_lock_bh(&sk->sk_callback_lock); acquire(softirq_ctrl) // <---- whoops acquire(&sk->sk_callback_lock) Drop local_bh_disable() around __inet_hash() which acquires listening_hash->lock. Split inet_unhash() and acquire the listen_hashbucket lock without disabling bottom halves; the inet_ehash lock with disabled bottom halves. Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Link: https://lkml.kernel.org/r/12d6f9879a97cd56c09fb53dee343cbb14f7f1f7.camel@gmx.de Link: https://lkml.kernel.org/r/X9CheYjuXWc75Spa@hirez.programming.kicks-ass.net Link: https://lore.kernel.org/r/YgQOebeZ10eNx1W6@linutronix.de Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-02-09 21:56:57 +03:00
if (sk_unhashed(sk))
return;
if (sk->sk_state == TCP_LISTEN) {
struct inet_listen_hashbucket *ilb2;
tcp: Don't acquire inet_listen_hashbucket::lock with disabled BH. Commit 9652dc2eb9e40 ("tcp: relax listening_hash operations") removed the need to disable bottom half while acquiring listening_hash.lock. There are still two callers left which disable bottom half before the lock is acquired. On PREEMPT_RT the softirqs are preemptible and local_bh_disable() acts as a lock to ensure that resources, that are protected by disabling bottom halves, remain protected. This leads to a circular locking dependency if the lock acquired with disabled bottom halves is also acquired with enabled bottom halves followed by disabling bottom halves. This is the reverse locking order. It has been observed with inet_listen_hashbucket::lock: local_bh_disable() + spin_lock(&ilb->lock): inet_listen() inet_csk_listen_start() sk->sk_prot->hash() := inet_hash() local_bh_disable() __inet_hash() spin_lock(&ilb->lock); acquire(&ilb->lock); Reverse order: spin_lock(&ilb2->lock) + local_bh_disable(): tcp_seq_next() listening_get_next() spin_lock(&ilb2->lock); acquire(&ilb2->lock); tcp4_seq_show() get_tcp4_sock() sock_i_ino() read_lock_bh(&sk->sk_callback_lock); acquire(softirq_ctrl) // <---- whoops acquire(&sk->sk_callback_lock) Drop local_bh_disable() around __inet_hash() which acquires listening_hash->lock. Split inet_unhash() and acquire the listen_hashbucket lock without disabling bottom halves; the inet_ehash lock with disabled bottom halves. Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Link: https://lkml.kernel.org/r/12d6f9879a97cd56c09fb53dee343cbb14f7f1f7.camel@gmx.de Link: https://lkml.kernel.org/r/X9CheYjuXWc75Spa@hirez.programming.kicks-ass.net Link: https://lore.kernel.org/r/YgQOebeZ10eNx1W6@linutronix.de Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-02-09 21:56:57 +03:00
ilb2 = inet_lhash2_bucket_sk(hashinfo, sk);
tcp: Don't acquire inet_listen_hashbucket::lock with disabled BH. Commit 9652dc2eb9e40 ("tcp: relax listening_hash operations") removed the need to disable bottom half while acquiring listening_hash.lock. There are still two callers left which disable bottom half before the lock is acquired. On PREEMPT_RT the softirqs are preemptible and local_bh_disable() acts as a lock to ensure that resources, that are protected by disabling bottom halves, remain protected. This leads to a circular locking dependency if the lock acquired with disabled bottom halves is also acquired with enabled bottom halves followed by disabling bottom halves. This is the reverse locking order. It has been observed with inet_listen_hashbucket::lock: local_bh_disable() + spin_lock(&ilb->lock): inet_listen() inet_csk_listen_start() sk->sk_prot->hash() := inet_hash() local_bh_disable() __inet_hash() spin_lock(&ilb->lock); acquire(&ilb->lock); Reverse order: spin_lock(&ilb2->lock) + local_bh_disable(): tcp_seq_next() listening_get_next() spin_lock(&ilb2->lock); acquire(&ilb2->lock); tcp4_seq_show() get_tcp4_sock() sock_i_ino() read_lock_bh(&sk->sk_callback_lock); acquire(softirq_ctrl) // <---- whoops acquire(&sk->sk_callback_lock) Drop local_bh_disable() around __inet_hash() which acquires listening_hash->lock. Split inet_unhash() and acquire the listen_hashbucket lock without disabling bottom halves; the inet_ehash lock with disabled bottom halves. Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Link: https://lkml.kernel.org/r/12d6f9879a97cd56c09fb53dee343cbb14f7f1f7.camel@gmx.de Link: https://lkml.kernel.org/r/X9CheYjuXWc75Spa@hirez.programming.kicks-ass.net Link: https://lore.kernel.org/r/YgQOebeZ10eNx1W6@linutronix.de Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-02-09 21:56:57 +03:00
/* Don't disable bottom halves while acquiring the lock to
* avoid circular locking dependency on PREEMPT_RT.
*/
spin_lock(&ilb2->lock);
if (sk_unhashed(sk)) {
spin_unlock(&ilb2->lock);
return;
}
if (rcu_access_pointer(sk->sk_reuseport_cb))
reuseport_stop_listen_sock(sk);
__sk_nulls_del_node_init_rcu(sk);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
spin_unlock(&ilb2->lock);
tcp: Don't acquire inet_listen_hashbucket::lock with disabled BH. Commit 9652dc2eb9e40 ("tcp: relax listening_hash operations") removed the need to disable bottom half while acquiring listening_hash.lock. There are still two callers left which disable bottom half before the lock is acquired. On PREEMPT_RT the softirqs are preemptible and local_bh_disable() acts as a lock to ensure that resources, that are protected by disabling bottom halves, remain protected. This leads to a circular locking dependency if the lock acquired with disabled bottom halves is also acquired with enabled bottom halves followed by disabling bottom halves. This is the reverse locking order. It has been observed with inet_listen_hashbucket::lock: local_bh_disable() + spin_lock(&ilb->lock): inet_listen() inet_csk_listen_start() sk->sk_prot->hash() := inet_hash() local_bh_disable() __inet_hash() spin_lock(&ilb->lock); acquire(&ilb->lock); Reverse order: spin_lock(&ilb2->lock) + local_bh_disable(): tcp_seq_next() listening_get_next() spin_lock(&ilb2->lock); acquire(&ilb2->lock); tcp4_seq_show() get_tcp4_sock() sock_i_ino() read_lock_bh(&sk->sk_callback_lock); acquire(softirq_ctrl) // <---- whoops acquire(&sk->sk_callback_lock) Drop local_bh_disable() around __inet_hash() which acquires listening_hash->lock. Split inet_unhash() and acquire the listen_hashbucket lock without disabling bottom halves; the inet_ehash lock with disabled bottom halves. Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Link: https://lkml.kernel.org/r/12d6f9879a97cd56c09fb53dee343cbb14f7f1f7.camel@gmx.de Link: https://lkml.kernel.org/r/X9CheYjuXWc75Spa@hirez.programming.kicks-ass.net Link: https://lore.kernel.org/r/YgQOebeZ10eNx1W6@linutronix.de Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-02-09 21:56:57 +03:00
} else {
spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
spin_lock_bh(lock);
if (sk_unhashed(sk)) {
spin_unlock_bh(lock);
return;
}
__sk_nulls_del_node_init_rcu(sk);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
tcp: Don't acquire inet_listen_hashbucket::lock with disabled BH. Commit 9652dc2eb9e40 ("tcp: relax listening_hash operations") removed the need to disable bottom half while acquiring listening_hash.lock. There are still two callers left which disable bottom half before the lock is acquired. On PREEMPT_RT the softirqs are preemptible and local_bh_disable() acts as a lock to ensure that resources, that are protected by disabling bottom halves, remain protected. This leads to a circular locking dependency if the lock acquired with disabled bottom halves is also acquired with enabled bottom halves followed by disabling bottom halves. This is the reverse locking order. It has been observed with inet_listen_hashbucket::lock: local_bh_disable() + spin_lock(&ilb->lock): inet_listen() inet_csk_listen_start() sk->sk_prot->hash() := inet_hash() local_bh_disable() __inet_hash() spin_lock(&ilb->lock); acquire(&ilb->lock); Reverse order: spin_lock(&ilb2->lock) + local_bh_disable(): tcp_seq_next() listening_get_next() spin_lock(&ilb2->lock); acquire(&ilb2->lock); tcp4_seq_show() get_tcp4_sock() sock_i_ino() read_lock_bh(&sk->sk_callback_lock); acquire(softirq_ctrl) // <---- whoops acquire(&sk->sk_callback_lock) Drop local_bh_disable() around __inet_hash() which acquires listening_hash->lock. Split inet_unhash() and acquire the listen_hashbucket lock without disabling bottom halves; the inet_ehash lock with disabled bottom halves. Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Link: https://lkml.kernel.org/r/12d6f9879a97cd56c09fb53dee343cbb14f7f1f7.camel@gmx.de Link: https://lkml.kernel.org/r/X9CheYjuXWc75Spa@hirez.programming.kicks-ass.net Link: https://lore.kernel.org/r/YgQOebeZ10eNx1W6@linutronix.de Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-02-09 21:56:57 +03:00
spin_unlock_bh(lock);
}
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 15:06:04 +03:00
}
EXPORT_SYMBOL_GPL(inet_unhash);
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb,
const struct net *net, unsigned short port,
int l3mdev, const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family != tb->family)
return false;
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
if (sk->sk_family == AF_INET6)
return net_eq(ib2_net(tb), net) && tb->port == port &&
tb->l3mdev == l3mdev &&
ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr);
else
#endif
return net_eq(ib2_net(tb), net) && tb->port == port &&
tb->l3mdev == l3mdev && tb->rcv_saddr == sk->sk_rcv_saddr;
}
bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net,
unsigned short port, int l3mdev, const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
struct in6_addr addr_any = {};
if (sk->sk_family != tb->family)
return false;
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
if (sk->sk_family == AF_INET6)
return net_eq(ib2_net(tb), net) && tb->port == port &&
tb->l3mdev == l3mdev &&
ipv6_addr_equal(&tb->v6_rcv_saddr, &addr_any);
else
#endif
return net_eq(ib2_net(tb), net) && tb->port == port &&
tb->l3mdev == l3mdev && tb->rcv_saddr == 0;
}
/* The socket's bhash2 hashbucket spinlock must be held when this is called */
struct inet_bind2_bucket *
inet_bind2_bucket_find(const struct inet_bind_hashbucket *head, const struct net *net,
unsigned short port, int l3mdev, const struct sock *sk)
{
struct inet_bind2_bucket *bhash2 = NULL;
inet_bind_bucket_for_each(bhash2, &head->chain)
if (inet_bind2_bucket_match(bhash2, net, port, l3mdev, sk))
break;
return bhash2;
}
struct inet_bind_hashbucket *
inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port)
{
struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
u32 hash;
#if IS_ENABLED(CONFIG_IPV6)
struct in6_addr addr_any = {};
if (sk->sk_family == AF_INET6)
hash = ipv6_portaddr_hash(net, &addr_any, port);
else
#endif
hash = ipv4_portaddr_hash(net, 0, port);
return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)];
}
static void inet_update_saddr(struct sock *sk, void *saddr, int family)
{
if (family == AF_INET) {
inet_sk(sk)->inet_saddr = *(__be32 *)saddr;
sk_rcv_saddr_set(sk, inet_sk(sk)->inet_saddr);
}
#if IS_ENABLED(CONFIG_IPV6)
else {
sk->sk_v6_rcv_saddr = *(struct in6_addr *)saddr;
}
#endif
}
dccp/tcp: Fixup bhash2 bucket when connect() fails. If a socket bound to a wildcard address fails to connect(), we only reset saddr and keep the port. Then, we have to fix up the bhash2 bucket; otherwise, the bucket has an inconsistent address in the list. Also, listen() for such a socket will fire the WARN_ON() in inet_csk_get_port(). [0] Note that when a system runs out of memory, we give up fixing the bucket and unlink sk from bhash and bhash2 by inet_put_port(). [0]: WARNING: CPU: 0 PID: 207 at net/ipv4/inet_connection_sock.c:548 inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Modules linked in: CPU: 0 PID: 207 Comm: bhash2_prev_rep Not tainted 6.1.0-rc3-00799-gc8421681c845 #63 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014 RIP: 0010:inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Code: 74 a7 eb 93 48 8b 54 24 18 0f b7 cb 4c 89 e6 4c 89 ff e8 48 b2 ff ff 49 8b 87 18 04 00 00 e9 32 ff ff ff 0f 0b e9 34 ff ff ff <0f> 0b e9 42 ff ff ff 41 8b 7f 50 41 8b 4f 54 89 fe 81 f6 00 00 ff RSP: 0018:ffffc900003d7e50 EFLAGS: 00010202 RAX: ffff8881047fb500 RBX: 0000000000004e20 RCX: 0000000000000000 RDX: 000000000000000a RSI: 00000000fffffe00 RDI: 00000000ffffffff RBP: ffffffff8324dc00 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000001 R14: 0000000000004e20 R15: ffff8881054e1280 FS: 00007f8ac04dc740(0000) GS:ffff88842fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020001540 CR3: 00000001055fa003 CR4: 0000000000770ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> inet_csk_listen_start (net/ipv4/inet_connection_sock.c:1205) inet_listen (net/ipv4/af_inet.c:228) __sys_listen (net/socket.c:1810) __x64_sys_listen (net/socket.c:1819 net/socket.c:1817 net/socket.c:1817) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f8ac051de5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 93 af 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007ffc1c177248 EFLAGS: 00000206 ORIG_RAX: 0000000000000032 RAX: ffffffffffffffda RBX: 0000000020001550 RCX: 00007f8ac051de5d RDX: ffffffffffffff80 RSI: 0000000000000000 RDI: 0000000000000004 RBP: 00007ffc1c177270 R08: 0000000000000018 R09: 0000000000000007 R10: 0000000020001540 R11: 0000000000000206 R12: 00007ffc1c177388 R13: 0000000000401169 R14: 0000000000403e18 R15: 00007f8ac0723000 </TASK> Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Acked-by: Joanne Koong <joannelkoong@gmail.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-11-19 04:49:14 +03:00
static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset)
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
{
struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
struct inet_bind_hashbucket *head, *head2;
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
struct inet_bind2_bucket *tb2, *new_tb2;
int l3mdev = inet_sk_bound_l3mdev(sk);
int port = inet_sk(sk)->inet_num;
struct net *net = sock_net(sk);
int bhash;
if (!inet_csk(sk)->icsk_bind2_hash) {
/* Not bind()ed before. */
dccp/tcp: Fixup bhash2 bucket when connect() fails. If a socket bound to a wildcard address fails to connect(), we only reset saddr and keep the port. Then, we have to fix up the bhash2 bucket; otherwise, the bucket has an inconsistent address in the list. Also, listen() for such a socket will fire the WARN_ON() in inet_csk_get_port(). [0] Note that when a system runs out of memory, we give up fixing the bucket and unlink sk from bhash and bhash2 by inet_put_port(). [0]: WARNING: CPU: 0 PID: 207 at net/ipv4/inet_connection_sock.c:548 inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Modules linked in: CPU: 0 PID: 207 Comm: bhash2_prev_rep Not tainted 6.1.0-rc3-00799-gc8421681c845 #63 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014 RIP: 0010:inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Code: 74 a7 eb 93 48 8b 54 24 18 0f b7 cb 4c 89 e6 4c 89 ff e8 48 b2 ff ff 49 8b 87 18 04 00 00 e9 32 ff ff ff 0f 0b e9 34 ff ff ff <0f> 0b e9 42 ff ff ff 41 8b 7f 50 41 8b 4f 54 89 fe 81 f6 00 00 ff RSP: 0018:ffffc900003d7e50 EFLAGS: 00010202 RAX: ffff8881047fb500 RBX: 0000000000004e20 RCX: 0000000000000000 RDX: 000000000000000a RSI: 00000000fffffe00 RDI: 00000000ffffffff RBP: ffffffff8324dc00 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000001 R14: 0000000000004e20 R15: ffff8881054e1280 FS: 00007f8ac04dc740(0000) GS:ffff88842fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020001540 CR3: 00000001055fa003 CR4: 0000000000770ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> inet_csk_listen_start (net/ipv4/inet_connection_sock.c:1205) inet_listen (net/ipv4/af_inet.c:228) __sys_listen (net/socket.c:1810) __x64_sys_listen (net/socket.c:1819 net/socket.c:1817 net/socket.c:1817) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f8ac051de5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 93 af 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007ffc1c177248 EFLAGS: 00000206 ORIG_RAX: 0000000000000032 RAX: ffffffffffffffda RBX: 0000000020001550 RCX: 00007f8ac051de5d RDX: ffffffffffffff80 RSI: 0000000000000000 RDI: 0000000000000004 RBP: 00007ffc1c177270 R08: 0000000000000018 R09: 0000000000000007 R10: 0000000020001540 R11: 0000000000000206 R12: 00007ffc1c177388 R13: 0000000000401169 R14: 0000000000403e18 R15: 00007f8ac0723000 </TASK> Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Acked-by: Joanne Koong <joannelkoong@gmail.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-11-19 04:49:14 +03:00
if (reset)
inet_reset_saddr(sk);
else
inet_update_saddr(sk, saddr, family);
return 0;
}
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
/* Allocate a bind2 bucket ahead of time to avoid permanently putting
* the bhash2 table in an inconsistent state if a new tb2 bucket
* allocation fails.
*/
new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC);
dccp/tcp: Fixup bhash2 bucket when connect() fails. If a socket bound to a wildcard address fails to connect(), we only reset saddr and keep the port. Then, we have to fix up the bhash2 bucket; otherwise, the bucket has an inconsistent address in the list. Also, listen() for such a socket will fire the WARN_ON() in inet_csk_get_port(). [0] Note that when a system runs out of memory, we give up fixing the bucket and unlink sk from bhash and bhash2 by inet_put_port(). [0]: WARNING: CPU: 0 PID: 207 at net/ipv4/inet_connection_sock.c:548 inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Modules linked in: CPU: 0 PID: 207 Comm: bhash2_prev_rep Not tainted 6.1.0-rc3-00799-gc8421681c845 #63 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014 RIP: 0010:inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Code: 74 a7 eb 93 48 8b 54 24 18 0f b7 cb 4c 89 e6 4c 89 ff e8 48 b2 ff ff 49 8b 87 18 04 00 00 e9 32 ff ff ff 0f 0b e9 34 ff ff ff <0f> 0b e9 42 ff ff ff 41 8b 7f 50 41 8b 4f 54 89 fe 81 f6 00 00 ff RSP: 0018:ffffc900003d7e50 EFLAGS: 00010202 RAX: ffff8881047fb500 RBX: 0000000000004e20 RCX: 0000000000000000 RDX: 000000000000000a RSI: 00000000fffffe00 RDI: 00000000ffffffff RBP: ffffffff8324dc00 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000001 R14: 0000000000004e20 R15: ffff8881054e1280 FS: 00007f8ac04dc740(0000) GS:ffff88842fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020001540 CR3: 00000001055fa003 CR4: 0000000000770ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> inet_csk_listen_start (net/ipv4/inet_connection_sock.c:1205) inet_listen (net/ipv4/af_inet.c:228) __sys_listen (net/socket.c:1810) __x64_sys_listen (net/socket.c:1819 net/socket.c:1817 net/socket.c:1817) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f8ac051de5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 93 af 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007ffc1c177248 EFLAGS: 00000206 ORIG_RAX: 0000000000000032 RAX: ffffffffffffffda RBX: 0000000020001550 RCX: 00007f8ac051de5d RDX: ffffffffffffff80 RSI: 0000000000000000 RDI: 0000000000000004 RBP: 00007ffc1c177270 R08: 0000000000000018 R09: 0000000000000007 R10: 0000000020001540 R11: 0000000000000206 R12: 00007ffc1c177388 R13: 0000000000401169 R14: 0000000000403e18 R15: 00007f8ac0723000 </TASK> Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Acked-by: Joanne Koong <joannelkoong@gmail.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-11-19 04:49:14 +03:00
if (!new_tb2) {
if (reset) {
/* The (INADDR_ANY, port) bucket might have already
* been freed, then we cannot fixup icsk_bind2_hash,
* so we give up and unlink sk from bhash/bhash2 not
* to leave inconsistency in bhash2.
*/
inet_put_port(sk);
inet_reset_saddr(sk);
}
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
return -ENOMEM;
dccp/tcp: Fixup bhash2 bucket when connect() fails. If a socket bound to a wildcard address fails to connect(), we only reset saddr and keep the port. Then, we have to fix up the bhash2 bucket; otherwise, the bucket has an inconsistent address in the list. Also, listen() for such a socket will fire the WARN_ON() in inet_csk_get_port(). [0] Note that when a system runs out of memory, we give up fixing the bucket and unlink sk from bhash and bhash2 by inet_put_port(). [0]: WARNING: CPU: 0 PID: 207 at net/ipv4/inet_connection_sock.c:548 inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Modules linked in: CPU: 0 PID: 207 Comm: bhash2_prev_rep Not tainted 6.1.0-rc3-00799-gc8421681c845 #63 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014 RIP: 0010:inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Code: 74 a7 eb 93 48 8b 54 24 18 0f b7 cb 4c 89 e6 4c 89 ff e8 48 b2 ff ff 49 8b 87 18 04 00 00 e9 32 ff ff ff 0f 0b e9 34 ff ff ff <0f> 0b e9 42 ff ff ff 41 8b 7f 50 41 8b 4f 54 89 fe 81 f6 00 00 ff RSP: 0018:ffffc900003d7e50 EFLAGS: 00010202 RAX: ffff8881047fb500 RBX: 0000000000004e20 RCX: 0000000000000000 RDX: 000000000000000a RSI: 00000000fffffe00 RDI: 00000000ffffffff RBP: ffffffff8324dc00 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000001 R14: 0000000000004e20 R15: ffff8881054e1280 FS: 00007f8ac04dc740(0000) GS:ffff88842fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020001540 CR3: 00000001055fa003 CR4: 0000000000770ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> inet_csk_listen_start (net/ipv4/inet_connection_sock.c:1205) inet_listen (net/ipv4/af_inet.c:228) __sys_listen (net/socket.c:1810) __x64_sys_listen (net/socket.c:1819 net/socket.c:1817 net/socket.c:1817) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f8ac051de5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 93 af 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007ffc1c177248 EFLAGS: 00000206 ORIG_RAX: 0000000000000032 RAX: ffffffffffffffda RBX: 0000000020001550 RCX: 00007f8ac051de5d RDX: ffffffffffffff80 RSI: 0000000000000000 RDI: 0000000000000004 RBP: 00007ffc1c177270 R08: 0000000000000018 R09: 0000000000000007 R10: 0000000020001540 R11: 0000000000000206 R12: 00007ffc1c177388 R13: 0000000000401169 R14: 0000000000403e18 R15: 00007f8ac0723000 </TASK> Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Acked-by: Joanne Koong <joannelkoong@gmail.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-11-19 04:49:14 +03:00
}
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
bhash = inet_bhashfn(net, port, hinfo->bhash_size);
head = &hinfo->bhash[bhash];
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);
/* If we change saddr locklessly, another thread
* iterating over bhash might see corrupted address.
*/
spin_lock_bh(&head->lock);
spin_lock(&head2->lock);
__sk_del_bind2_node(sk);
inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash);
spin_unlock(&head2->lock);
dccp/tcp: Fixup bhash2 bucket when connect() fails. If a socket bound to a wildcard address fails to connect(), we only reset saddr and keep the port. Then, we have to fix up the bhash2 bucket; otherwise, the bucket has an inconsistent address in the list. Also, listen() for such a socket will fire the WARN_ON() in inet_csk_get_port(). [0] Note that when a system runs out of memory, we give up fixing the bucket and unlink sk from bhash and bhash2 by inet_put_port(). [0]: WARNING: CPU: 0 PID: 207 at net/ipv4/inet_connection_sock.c:548 inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Modules linked in: CPU: 0 PID: 207 Comm: bhash2_prev_rep Not tainted 6.1.0-rc3-00799-gc8421681c845 #63 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014 RIP: 0010:inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Code: 74 a7 eb 93 48 8b 54 24 18 0f b7 cb 4c 89 e6 4c 89 ff e8 48 b2 ff ff 49 8b 87 18 04 00 00 e9 32 ff ff ff 0f 0b e9 34 ff ff ff <0f> 0b e9 42 ff ff ff 41 8b 7f 50 41 8b 4f 54 89 fe 81 f6 00 00 ff RSP: 0018:ffffc900003d7e50 EFLAGS: 00010202 RAX: ffff8881047fb500 RBX: 0000000000004e20 RCX: 0000000000000000 RDX: 000000000000000a RSI: 00000000fffffe00 RDI: 00000000ffffffff RBP: ffffffff8324dc00 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000001 R14: 0000000000004e20 R15: ffff8881054e1280 FS: 00007f8ac04dc740(0000) GS:ffff88842fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020001540 CR3: 00000001055fa003 CR4: 0000000000770ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> inet_csk_listen_start (net/ipv4/inet_connection_sock.c:1205) inet_listen (net/ipv4/af_inet.c:228) __sys_listen (net/socket.c:1810) __x64_sys_listen (net/socket.c:1819 net/socket.c:1817 net/socket.c:1817) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f8ac051de5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 93 af 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007ffc1c177248 EFLAGS: 00000206 ORIG_RAX: 0000000000000032 RAX: ffffffffffffffda RBX: 0000000020001550 RCX: 00007f8ac051de5d RDX: ffffffffffffff80 RSI: 0000000000000000 RDI: 0000000000000004 RBP: 00007ffc1c177270 R08: 0000000000000018 R09: 0000000000000007 R10: 0000000020001540 R11: 0000000000000206 R12: 00007ffc1c177388 R13: 0000000000401169 R14: 0000000000403e18 R15: 00007f8ac0723000 </TASK> Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Acked-by: Joanne Koong <joannelkoong@gmail.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-11-19 04:49:14 +03:00
if (reset)
inet_reset_saddr(sk);
else
inet_update_saddr(sk, saddr, family);
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);
spin_lock(&head2->lock);
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
if (!tb2) {
tb2 = new_tb2;
inet_bind2_bucket_init(tb2, net, head2, port, l3mdev, sk);
}
sk_add_bind2_node(sk, &tb2->owners);
inet_csk(sk)->icsk_bind2_hash = tb2;
spin_unlock(&head2->lock);
spin_unlock_bh(&head->lock);
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
if (tb2 != new_tb2)
kmem_cache_free(hinfo->bind2_bucket_cachep, new_tb2);
return 0;
}
dccp/tcp: Fixup bhash2 bucket when connect() fails. If a socket bound to a wildcard address fails to connect(), we only reset saddr and keep the port. Then, we have to fix up the bhash2 bucket; otherwise, the bucket has an inconsistent address in the list. Also, listen() for such a socket will fire the WARN_ON() in inet_csk_get_port(). [0] Note that when a system runs out of memory, we give up fixing the bucket and unlink sk from bhash and bhash2 by inet_put_port(). [0]: WARNING: CPU: 0 PID: 207 at net/ipv4/inet_connection_sock.c:548 inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Modules linked in: CPU: 0 PID: 207 Comm: bhash2_prev_rep Not tainted 6.1.0-rc3-00799-gc8421681c845 #63 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014 RIP: 0010:inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Code: 74 a7 eb 93 48 8b 54 24 18 0f b7 cb 4c 89 e6 4c 89 ff e8 48 b2 ff ff 49 8b 87 18 04 00 00 e9 32 ff ff ff 0f 0b e9 34 ff ff ff <0f> 0b e9 42 ff ff ff 41 8b 7f 50 41 8b 4f 54 89 fe 81 f6 00 00 ff RSP: 0018:ffffc900003d7e50 EFLAGS: 00010202 RAX: ffff8881047fb500 RBX: 0000000000004e20 RCX: 0000000000000000 RDX: 000000000000000a RSI: 00000000fffffe00 RDI: 00000000ffffffff RBP: ffffffff8324dc00 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000001 R14: 0000000000004e20 R15: ffff8881054e1280 FS: 00007f8ac04dc740(0000) GS:ffff88842fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020001540 CR3: 00000001055fa003 CR4: 0000000000770ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> inet_csk_listen_start (net/ipv4/inet_connection_sock.c:1205) inet_listen (net/ipv4/af_inet.c:228) __sys_listen (net/socket.c:1810) __x64_sys_listen (net/socket.c:1819 net/socket.c:1817 net/socket.c:1817) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f8ac051de5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 93 af 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007ffc1c177248 EFLAGS: 00000206 ORIG_RAX: 0000000000000032 RAX: ffffffffffffffda RBX: 0000000020001550 RCX: 00007f8ac051de5d RDX: ffffffffffffff80 RSI: 0000000000000000 RDI: 0000000000000004 RBP: 00007ffc1c177270 R08: 0000000000000018 R09: 0000000000000007 R10: 0000000020001540 R11: 0000000000000206 R12: 00007ffc1c177388 R13: 0000000000401169 R14: 0000000000403e18 R15: 00007f8ac0723000 </TASK> Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Acked-by: Joanne Koong <joannelkoong@gmail.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-11-19 04:49:14 +03:00
int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family)
{
return __inet_bhash2_update_saddr(sk, saddr, family, false);
}
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr);
dccp/tcp: Fixup bhash2 bucket when connect() fails. If a socket bound to a wildcard address fails to connect(), we only reset saddr and keep the port. Then, we have to fix up the bhash2 bucket; otherwise, the bucket has an inconsistent address in the list. Also, listen() for such a socket will fire the WARN_ON() in inet_csk_get_port(). [0] Note that when a system runs out of memory, we give up fixing the bucket and unlink sk from bhash and bhash2 by inet_put_port(). [0]: WARNING: CPU: 0 PID: 207 at net/ipv4/inet_connection_sock.c:548 inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Modules linked in: CPU: 0 PID: 207 Comm: bhash2_prev_rep Not tainted 6.1.0-rc3-00799-gc8421681c845 #63 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014 RIP: 0010:inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Code: 74 a7 eb 93 48 8b 54 24 18 0f b7 cb 4c 89 e6 4c 89 ff e8 48 b2 ff ff 49 8b 87 18 04 00 00 e9 32 ff ff ff 0f 0b e9 34 ff ff ff <0f> 0b e9 42 ff ff ff 41 8b 7f 50 41 8b 4f 54 89 fe 81 f6 00 00 ff RSP: 0018:ffffc900003d7e50 EFLAGS: 00010202 RAX: ffff8881047fb500 RBX: 0000000000004e20 RCX: 0000000000000000 RDX: 000000000000000a RSI: 00000000fffffe00 RDI: 00000000ffffffff RBP: ffffffff8324dc00 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000001 R14: 0000000000004e20 R15: ffff8881054e1280 FS: 00007f8ac04dc740(0000) GS:ffff88842fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020001540 CR3: 00000001055fa003 CR4: 0000000000770ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <TASK> inet_csk_listen_start (net/ipv4/inet_connection_sock.c:1205) inet_listen (net/ipv4/af_inet.c:228) __sys_listen (net/socket.c:1810) __x64_sys_listen (net/socket.c:1819 net/socket.c:1817 net/socket.c:1817) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f8ac051de5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 93 af 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007ffc1c177248 EFLAGS: 00000206 ORIG_RAX: 0000000000000032 RAX: ffffffffffffffda RBX: 0000000020001550 RCX: 00007f8ac051de5d RDX: ffffffffffffff80 RSI: 0000000000000000 RDI: 0000000000000004 RBP: 00007ffc1c177270 R08: 0000000000000018 R09: 0000000000000007 R10: 0000000020001540 R11: 0000000000000206 R12: 00007ffc1c177388 R13: 0000000000401169 R14: 0000000000403e18 R15: 00007f8ac0723000 </TASK> Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address") Reported-by: syzbot <syzkaller@googlegroups.com> Reported-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Acked-by: Joanne Koong <joannelkoong@gmail.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-11-19 04:49:14 +03:00
void inet_bhash2_reset_saddr(struct sock *sk)
{
if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
__inet_bhash2_update_saddr(sk, NULL, 0, true);
}
EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr);
/* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm
* Note that we use 32bit integers (vs RFC 'short integers')
* because 2^16 is not a multiple of num_ephemeral and this
* property might be used by clever attacker.
*
* RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though
* attacks were since demonstrated, thus we use 65536 by default instead
* to really give more isolation and privacy, at the expense of 256kB
* of kernel memory.
*/
#define INET_TABLE_PERTURB_SIZE (1 << CONFIG_INET_TABLE_PERTURB_ORDER)
static u32 *table_perturb;
int __inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk, u64 port_offset,
int (*check_established)(struct inet_timewait_death_row *,
struct sock *, __u16, struct inet_timewait_sock **))
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
struct inet_bind_hashbucket *head, *head2;
struct inet_timewait_sock *tw = NULL;
int port = inet_sk(sk)->inet_num;
struct net *net = sock_net(sk);
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
struct inet_bind2_bucket *tb2;
struct inet_bind_bucket *tb;
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
bool tb_created = false;
u32 remaining, offset;
int ret, i, low, high;
int l3mdev;
u32 index;
if (port) {
head = &hinfo->bhash[inet_bhashfn(net, port,
hinfo->bhash_size)];
tb = inet_csk(sk)->icsk_bind_hash;
spin_lock_bh(&head->lock);
if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
inet_ehash_nolisten(sk, NULL, NULL);
spin_unlock_bh(&head->lock);
return 0;
}
spin_unlock(&head->lock);
/* No definite answer... Walk to established hash table */
ret = check_established(death_row, sk, port, NULL);
local_bh_enable();
return ret;
}
l3mdev = inet_sk_bound_l3mdev(sk);
inet_get_local_port_range(net, &low, &high);
high++; /* [32768, 60999] -> [32768, 61000[ */
remaining = high - low;
if (likely(remaining > 1))
remaining &= ~1U;
get_random_sleepable_once(table_perturb,
INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb));
index = port_offset & (INET_TABLE_PERTURB_SIZE - 1);
offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32);
offset %= remaining;
/* In first pass we try ports of @low parity.
* inet_csk_get_port() does the opposite choice.
*/
offset &= ~1U;
other_parity_scan:
port = low + offset;
for (i = 0; i < remaining; i += 2, port += 2) {
if (unlikely(port >= high))
port -= remaining;
if (inet_is_local_reserved_port(net, port))
continue;
head = &hinfo->bhash[inet_bhashfn(net, port,
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
/* Does not bother with rcv_saddr checks, because
* the established check is already unique enough.
*/
inet_bind_bucket_for_each(tb, &head->chain) {
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
if (inet_bind_bucket_match(tb, net, port, l3mdev)) {
if (tb->fastreuse >= 0 ||
tb->fastreuseport >= 0)
goto next_port;
WARN_ON(hlist_empty(&tb->owners));
if (!check_established(death_row, sk,
port, &tw))
goto ok;
goto next_port;
}
}
tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
net, head, port, l3mdev);
if (!tb) {
spin_unlock_bh(&head->lock);
return -ENOMEM;
}
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
tb_created = true;
tb->fastreuse = -1;
tb->fastreuseport = -1;
goto ok;
next_port:
spin_unlock_bh(&head->lock);
cond_resched();
}
offset++;
if ((offset & 1) && remaining > 1)
goto other_parity_scan;
return -EADDRNOTAVAIL;
ok:
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
/* Find the corresponding tb2 bucket since we need to
* add the socket to the bhash2 table as well
*/
head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);
spin_lock(&head2->lock);
tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
if (!tb2) {
tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, net,
head2, port, l3mdev, sk);
if (!tb2)
goto error;
}
/* Here we want to add a little bit of randomness to the next source
* port that will be chosen. We use a max() with a random here so that
* on low contention the randomness is maximal and on high contention
* it may be inexistent.
*/
i = max_t(int, i, get_random_u32_below(8) * 2);
WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2);
/* Head lock still held and bh's disabled */
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
inet_bind_hash(sk, tb, tb2, port);
if (sk_unhashed(sk)) {
inet_sk(sk)->inet_sport = htons(port);
tcp: fix race condition when creating child sockets from syncookies When the TCP stack is in SYN flood mode, the server child socket is created from the SYN cookie received in a TCP packet with the ACK flag set. The child socket is created when the server receives the first TCP packet with a valid SYN cookie from the client. Usually, this packet corresponds to the final step of the TCP 3-way handshake, the ACK packet. But is also possible to receive a valid SYN cookie from the first TCP data packet sent by the client, and thus create a child socket from that SYN cookie. Since a client socket is ready to send data as soon as it receives the SYN+ACK packet from the server, the client can send the ACK packet (sent by the TCP stack code), and the first data packet (sent by the userspace program) almost at the same time, and thus the server will equally receive the two TCP packets with valid SYN cookies almost at the same instant. When such event happens, the TCP stack code has a race condition that occurs between the momement a lookup is done to the established connections hashtable to check for the existence of a connection for the same client, and the moment that the child socket is added to the established connections hashtable. As a consequence, this race condition can lead to a situation where we add two child sockets to the established connections hashtable and deliver two sockets to the userspace program to the same client. This patch fixes the race condition by checking if an existing child socket exists for the same client when we are adding the second child socket to the established connections socket. If an existing child socket exists, we drop the packet and discard the second child socket to the same client. Signed-off-by: Ricardo Dias <rdias@singlestore.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/r/20201120111133.GA67501@rdias-suse-pc.lan Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-20 14:11:33 +03:00
inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
}
if (tw)
inet_twsk_bind_unhash(tw, hinfo);
spin_unlock(&head2->lock);
spin_unlock(&head->lock);
if (tw)
inet_twsk_deschedule_put(tw);
local_bh_enable();
return 0;
net: Add a bhash2 table hashed by port and address The current bind hashtable (bhash) is hashed by port only. In the socket bind path, we have to check for bind conflicts by traversing the specified port's inet_bind_bucket while holding the hashbucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, the bind conflict check is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch adds a second bind table, bhash2, that hashes by port and sk->sk_rcv_saddr (ipv4) and sk->sk_v6_rcv_saddr (ipv6). Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the hashbucket spinlock. Please note a few things: * There can be the case where the a socket's address changes after it has been bound. There are two cases where this happens: 1) The case where there is a bind() call on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6) and then a connect() call. The kernel will assign the socket an address when it handles the connect() 2) In inet_sk_reselect_saddr(), which is called when rebuilding the sk header and a few pre-conditions are met (eg rerouting fails). In these two cases, we need to update the bhash2 table by removing the entry for the old address, and add a new entry reflecting the updated address. * The bhash2 table must have its own lock, even though concurrent accesses on the same port are protected by the bhash lock. Bhash2 must have its own lock to protect against cases where sockets on different ports hash to different bhash hashbuckets but to the same bhash2 hashbucket. This brings up a few stipulations: 1) When acquiring both the bhash and the bhash2 lock, the bhash2 lock will always be acquired after the bhash lock and released before the bhash lock is released. 2) There are no nested bhash2 hashbucket locks. A bhash2 lock is always acquired+released before another bhash2 lock is acquired+released. * The bhash table cannot be superseded by the bhash2 table because for bind requests on INADDR_ANY (ipv4) or IPV6_ADDR_ANY (ipv6), every socket bound to that port must be checked for a potential conflict. The bhash table is the only source of port->socket associations. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-22 21:10:21 +03:00
error:
spin_unlock(&head2->lock);
if (tb_created)
inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb);
spin_unlock_bh(&head->lock);
return -ENOMEM;
}
/*
* Bind a port for a connect operation and hash it.
*/
int inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
u64 port_offset = 0;
if (!inet_sk(sk)->inet_num)
port_offset = inet_sk_port_offset(sk);
return __inet_hash_connect(death_row, sk, port_offset,
__inet_check_established);
}
EXPORT_SYMBOL_GPL(inet_hash_connect);
static void init_hashinfo_lhash2(struct inet_hashinfo *h)
{
int i;
for (i = 0; i <= h->lhash2_mask; i++) {
spin_lock_init(&h->lhash2[i].lock);
net: inet: Retire port only listening_hash The listen sk is currently stored in two hash tables, listening_hash (hashed by port) and lhash2 (hashed by port and address). After commit 0ee58dad5b06 ("net: tcp6: prefer listeners bound to an address") and commit d9fbc7f6431f ("net: tcp: prefer listeners bound to an address"), the TCP-SYN lookup fast path does not use listening_hash. The commit 05c0b35709c5 ("tcp: seq_file: Replace listening_hash with lhash2") also moved the seq_file (/proc/net/tcp) iteration usage from listening_hash to lhash2. There are still a few listening_hash usages left. One of them is inet_reuseport_add_sock() which uses the listening_hash to search a listen sk during the listen() system call. This turns out to be very slow on use cases that listen on many different VIPs at a popular port (e.g. 443). [ On top of the slowness in adding to the tail in the IPv6 case ]. The latter patch has a selftest to demonstrate this case. This patch takes this chance to move all remaining listening_hash usages to lhash2 and then retire listening_hash. Since most changes need to be done together, it is hard to cut the listening_hash to lhash2 switch into small patches. The changes in this patch is highlighted here for the review purpose. 1. Because of the listening_hash removal, lhash2 can use the sk->sk_nulls_node instead of the icsk->icsk_listen_portaddr_node. This will also keep the sk_unhashed() check to work as is after stop adding sk to listening_hash. The union is removed from inet_listen_hashbucket because only nulls_head is needed. 2. icsk->icsk_listen_portaddr_node and its helpers are removed. 3. The current lhash2 users needs to iterate with sk_nulls_node instead of icsk_listen_portaddr_node. One case is in the inet[6]_lhash2_lookup(). Another case is the seq_file iterator in tcp_ipv4.c. One thing to note is sk_nulls_next() is needed because the old inet_lhash2_for_each_icsk_continue() does a "next" first before iterating. 4. Move the remaining listening_hash usage to lhash2 inet_reuseport_add_sock() which this series is trying to improve. inet_diag.c and mptcp_diag.c are the final two remaining use cases and is moved to lhash2 now also. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-05-12 03:06:05 +03:00
INIT_HLIST_NULLS_HEAD(&h->lhash2[i].nulls_head,
i + LISTENING_NULLS_BASE);
}
}
void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
unsigned long numentries, int scale,
unsigned long low_limit,
unsigned long high_limit)
{
h->lhash2 = alloc_large_system_hash(name,
sizeof(*h->lhash2),
numentries,
scale,
0,
NULL,
&h->lhash2_mask,
low_limit,
high_limit);
init_hashinfo_lhash2(h);
/* this one is used for source ports of outgoing connections */
table_perturb = alloc_large_system_hash("Table-perturb",
sizeof(*table_perturb),
INET_TABLE_PERTURB_SIZE,
0, 0, NULL, NULL,
INET_TABLE_PERTURB_SIZE,
INET_TABLE_PERTURB_SIZE);
}
int inet_hashinfo2_init_mod(struct inet_hashinfo *h)
{
h->lhash2 = kmalloc_array(INET_LHTABLE_SIZE, sizeof(*h->lhash2), GFP_KERNEL);
if (!h->lhash2)
return -ENOMEM;
h->lhash2_mask = INET_LHTABLE_SIZE - 1;
/* INET_LHTABLE_SIZE must be a power of 2 */
BUG_ON(INET_LHTABLE_SIZE & h->lhash2_mask);
init_hashinfo_lhash2(h);
return 0;
}
EXPORT_SYMBOL_GPL(inet_hashinfo2_init_mod);
int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
{
unsigned int locksz = sizeof(spinlock_t);
unsigned int i, nblocks = 1;
if (locksz != 0) {
/* allocate 2 cache lines or at least one spinlock per cpu */
nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U);
nblocks = roundup_pow_of_two(nblocks * num_possible_cpus());
/* no more locks than number of hash buckets */
nblocks = min(nblocks, hashinfo->ehash_mask + 1);
treewide: use kv[mz]alloc* rather than opencoded variants There are many code paths opencoding kvmalloc. Let's use the helper instead. The main difference to kvmalloc is that those users are usually not considering all the aspects of the memory allocator. E.g. allocation requests <= 32kB (with 4kB pages) are basically never failing and invoke OOM killer to satisfy the allocation. This sounds too disruptive for something that has a reasonable fallback - the vmalloc. On the other hand those requests might fallback to vmalloc even when the memory allocator would succeed after several more reclaim/compaction attempts previously. There is no guarantee something like that happens though. This patch converts many of those places to kv[mz]alloc* helpers because they are more conservative. Link: http://lkml.kernel.org/r/20170306103327.2766-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> # Xen bits Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Andreas Dilger <andreas.dilger@intel.com> # Lustre Acked-by: Christian Borntraeger <borntraeger@de.ibm.com> # KVM/s390 Acked-by: Dan Williams <dan.j.williams@intel.com> # nvdim Acked-by: David Sterba <dsterba@suse.com> # btrfs Acked-by: Ilya Dryomov <idryomov@gmail.com> # Ceph Acked-by: Tariq Toukan <tariqt@mellanox.com> # mlx4 Acked-by: Leon Romanovsky <leonro@mellanox.com> # mlx5 Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Anton Vorontsov <anton@enomsg.org> Cc: Colin Cross <ccross@android.com> Cc: Tony Luck <tony.luck@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Santosh Raspatur <santosh@chelsio.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Yishai Hadas <yishaih@mellanox.com> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: "Yan, Zheng" <zyan@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-09 01:57:27 +03:00
hashinfo->ehash_locks = kvmalloc_array(nblocks, locksz, GFP_KERNEL);
if (!hashinfo->ehash_locks)
return -ENOMEM;
for (i = 0; i < nblocks; i++)
spin_lock_init(&hashinfo->ehash_locks[i]);
}
hashinfo->ehash_locks_mask = nblocks - 1;
return 0;
}
EXPORT_SYMBOL_GPL(inet_ehash_locks_alloc);
tcp: Introduce optional per-netns ehash. The more sockets we have in the hash table, the longer we spend looking up the socket. While running a number of small workloads on the same host, they penalise each other and cause performance degradation. The root cause might be a single workload that consumes much more resources than the others. It often happens on a cloud service where different workloads share the same computing resource. On EC2 c5.24xlarge instance (196 GiB memory and 524288 (1Mi / 2) ehash entries), after running iperf3 in different netns, creating 24Mi sockets without data transfer in the root netns causes about 10% performance regression for the iperf3's connection. thash_entries sockets length Gbps 524288 1 1 50.7 24Mi 48 45.1 It is basically related to the length of the list of each hash bucket. For testing purposes to see how performance drops along the length, I set 131072 (1Mi / 8) to thash_entries, and here's the result. thash_entries sockets length Gbps 131072 1 1 50.7 1Mi 8 49.9 2Mi 16 48.9 4Mi 32 47.3 8Mi 64 44.6 16Mi 128 40.6 24Mi 192 36.3 32Mi 256 32.5 40Mi 320 27.0 48Mi 384 25.0 To resolve the socket lookup degradation, we introduce an optional per-netns hash table for TCP, but it's just ehash, and we still share the global bhash, bhash2 and lhash2. With a smaller ehash, we can look up non-listener sockets faster and isolate such noisy neighbours. In addition, we can reduce lock contention. We can control the ehash size by a new sysctl knob. However, depending on workloads, it will require very sensitive tuning, so we disable the feature by default (net.ipv4.tcp_child_ehash_entries == 0). Moreover, we can fall back to using the global ehash in case we fail to allocate enough memory for a new ehash. The maximum size is 16Mi, which is large enough that even if we have 48Mi sockets, the average list length is 3, and regression would be less than 1%. We can check the current ehash size by another read-only sysctl knob, net.ipv4.tcp_ehash_entries. A negative value means the netns shares the global ehash (per-netns ehash is disabled or failed to allocate memory). # dmesg | cut -d ' ' -f 5- | grep "established hash" TCP established hash table entries: 524288 (order: 10, 4194304 bytes, vmalloc hugepage) # sysctl net.ipv4.tcp_ehash_entries net.ipv4.tcp_ehash_entries = 524288 # can be changed by thash_entries # sysctl net.ipv4.tcp_child_ehash_entries net.ipv4.tcp_child_ehash_entries = 0 # disabled by default # ip netns add test1 # ip netns exec test1 sysctl net.ipv4.tcp_ehash_entries net.ipv4.tcp_ehash_entries = -524288 # share the global ehash # sysctl -w net.ipv4.tcp_child_ehash_entries=100 net.ipv4.tcp_child_ehash_entries = 100 # ip netns add test2 # ip netns exec test2 sysctl net.ipv4.tcp_ehash_entries net.ipv4.tcp_ehash_entries = 128 # own a per-netns ehash with 2^n buckets When more than two processes in the same netns create per-netns ehash concurrently with different sizes, we need to guarantee the size in one of the following ways: 1) Share the global ehash and create per-netns ehash First, unshare() with tcp_child_ehash_entries==0. It creates dedicated netns sysctl knobs where we can safely change tcp_child_ehash_entries and clone()/unshare() to create a per-netns ehash. 2) Control write on sysctl by BPF We can use BPF_PROG_TYPE_CGROUP_SYSCTL to allow/deny read/write on sysctl knobs. Note that the global ehash allocated at the boot time is spread over available NUMA nodes, but inet_pernet_hashinfo_alloc() will allocate pages for each per-netns ehash depending on the current process's NUMA policy. By default, the allocation is done in the local node only, so the per-netns hash table could fully reside on a random node. Thus, depending on the NUMA policy the netns is created with and the CPU the current thread is running on, we could see some performance differences for highly optimised networking applications. Note also that the default values of two sysctl knobs depend on the ehash size and should be tuned carefully: tcp_max_tw_buckets : tcp_child_ehash_entries / 2 tcp_max_syn_backlog : max(128, tcp_child_ehash_entries / 128) As a bonus, we can dismantle netns faster. Currently, while destroying netns, we call inet_twsk_purge(), which walks through the global ehash. It can be potentially big because it can have many sockets other than TIME_WAIT in all netns. Splitting ehash changes that situation, where it's only necessary for inet_twsk_purge() to clean up TIME_WAIT sockets in each netns. With regard to this, we do not free the per-netns ehash in inet_twsk_kill() to avoid UAF while iterating the per-netns ehash in inet_twsk_purge(). Instead, we do it in tcp_sk_exit_batch() after calling tcp_twsk_purge() to keep it protocol-family-independent. In the future, we could optimise ehash lookup/iteration further by removing netns comparison for the per-netns ehash. Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-09-08 04:10:22 +03:00
struct inet_hashinfo *inet_pernet_hashinfo_alloc(struct inet_hashinfo *hashinfo,
unsigned int ehash_entries)
{
struct inet_hashinfo *new_hashinfo;
int i;
new_hashinfo = kmemdup(hashinfo, sizeof(*hashinfo), GFP_KERNEL);
if (!new_hashinfo)
goto err;
new_hashinfo->ehash = vmalloc_huge(ehash_entries * sizeof(struct inet_ehash_bucket),
GFP_KERNEL_ACCOUNT);
if (!new_hashinfo->ehash)
goto free_hashinfo;
new_hashinfo->ehash_mask = ehash_entries - 1;
if (inet_ehash_locks_alloc(new_hashinfo))
goto free_ehash;
for (i = 0; i < ehash_entries; i++)
INIT_HLIST_NULLS_HEAD(&new_hashinfo->ehash[i].chain, i);
new_hashinfo->pernet = true;
return new_hashinfo;
free_ehash:
vfree(new_hashinfo->ehash);
free_hashinfo:
kfree(new_hashinfo);
err:
return NULL;
}
EXPORT_SYMBOL_GPL(inet_pernet_hashinfo_alloc);
void inet_pernet_hashinfo_free(struct inet_hashinfo *hashinfo)
{
if (!hashinfo->pernet)
return;
inet_ehash_locks_free(hashinfo);
vfree(hashinfo->ehash);
kfree(hashinfo);
}
EXPORT_SYMBOL_GPL(inet_pernet_hashinfo_free);