OpenCloudOS-Kernel/net/ipv4/inet_diag.c

1485 lines
35 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* inet_diag.c Module for monitoring INET transport protocols sockets.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/random.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/time.h>
#include <net/icmp.h>
#include <net/tcp.h>
#include <net/ipv6.h>
#include <net/inet_common.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
#include <net/inet_timewait_sock.h>
#include <net/inet6_hashtables.h>
bpf: inet_diag: Dump bpf_sk_storages in inet_diag_dump() This patch will dump out the bpf_sk_storages of a sk if the request has the INET_DIAG_REQ_SK_BPF_STORAGES nlattr. An array of SK_DIAG_BPF_STORAGE_REQ_MAP_FD can be specified in INET_DIAG_REQ_SK_BPF_STORAGES to select which bpf_sk_storage to dump. If no map_fd is specified, all bpf_sk_storages of a sk will be dumped. bpf_sk_storages can be added to the system at runtime. It is difficult to find a proper static value for cb->min_dump_alloc. This patch learns the nlattr size required to dump the bpf_sk_storages of a sk. If it happens to be the very first nlmsg of a dump and it cannot fit the needed bpf_sk_storages, it will try to expand the skb by "pskb_expand_head()". Instead of expanding it in inet_sk_diag_fill(), it is expanded at a sleepable context in __inet_diag_dump() so __GFP_DIRECT_RECLAIM can be used. In __inet_diag_dump(), it will retry as long as the skb is empty and the cb->min_dump_alloc becomes larger than before. cb->min_dump_alloc is bounded by KMALLOC_MAX_SIZE. The min_dump_alloc is also changed from 'u16' to 'u32' to accommodate a sk that may have a few large bpf_sk_storages. The updated cb->min_dump_alloc will also be used to allocate the skb in the next dump. This logic already exists in netlink_dump(). Here is the sample output of a locally modified 'ss' and it could be made more readable by using BTF later: [root@arch-fb-vm1 ~]# ss --bpf-map-id 14 --bpf-map-id 13 -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] [root@arch-fb-vm1 ~]# ~/devshare/github/iproute2/misc/ss --bpf-maps -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:Port Process ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200225230427.1976129-1-kafai@fb.com
2020-02-26 07:04:27 +08:00
#include <net/bpf_sk_storage.h>
#include <net/netlink.h>
#include <linux/inet.h>
#include <linux/stddef.h>
#include <linux/inet_diag.h>
#include <linux/sock_diag.h>
static const struct inet_diag_handler **inet_diag_table;
struct inet_diag_entry {
const __be32 *saddr;
const __be32 *daddr;
u16 sport;
u16 dport;
u16 family;
u16 userlocks;
u32 ifindex;
u32 mark;
#ifdef CONFIG_SOCK_CGROUP_DATA
u64 cgroup_id;
#endif
};
static DEFINE_MUTEX(inet_diag_table_mutex);
static const struct inet_diag_handler *inet_diag_lock_handler(int proto)
{
if (proto < 0 || proto >= IPPROTO_MAX) {
mutex_lock(&inet_diag_table_mutex);
return ERR_PTR(-ENOENT);
}
if (!inet_diag_table[proto])
sock_diag: request _diag module only when the family or proto has been registered Now when using 'ss' in iproute, kernel would try to load all _diag modules, which also causes corresponding family and proto modules to be loaded as well due to module dependencies. Like after running 'ss', sctp, dccp, af_packet (if it works as a module) would be loaded. For example: $ lsmod|grep sctp $ ss $ lsmod|grep sctp sctp_diag 16384 0 sctp 323584 5 sctp_diag inet_diag 24576 4 raw_diag,tcp_diag,sctp_diag,udp_diag libcrc32c 16384 3 nf_conntrack,nf_nat,sctp As these family and proto modules are loaded unintentionally, it could cause some problems, like: - Some debug tools use 'ss' to collect the socket info, which loads all those diag and family and protocol modules. It's noisy for identifying issues. - Users usually expect to drop sctp init packet silently when they have no sense of sctp protocol instead of sending abort back. - It wastes resources (especially with multiple netns), and SCTP module can't be unloaded once it's loaded. ... In short, it's really inappropriate to have these family and proto modules loaded unexpectedly when just doing debugging with inet_diag. This patch is to introduce sock_load_diag_module() where it loads the _diag module only when it's corresponding family or proto has been already registered. Note that we can't just load _diag module without the family or proto loaded, as some symbols used in _diag module are from the family or proto module. v1->v2: - move inet proto check to inet_diag to avoid a compiling err. v2->v3: - define sock_load_diag_module in sock.c and export one symbol only. - improve the changelog. Reported-by: Sabrina Dubroca <sd@queasysnail.net> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Acked-by: Phil Sutter <phil@nwl.cc> Acked-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-10 18:57:50 +08:00
sock_load_diag_module(AF_INET, proto);
mutex_lock(&inet_diag_table_mutex);
if (!inet_diag_table[proto])
return ERR_PTR(-ENOENT);
return inet_diag_table[proto];
}
static void inet_diag_unlock_handler(const struct inet_diag_handler *handler)
{
mutex_unlock(&inet_diag_table_mutex);
}
void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk)
{
r->idiag_family = sk->sk_family;
r->id.idiag_sport = htons(sk->sk_num);
r->id.idiag_dport = sk->sk_dport;
r->id.idiag_if = sk->sk_bound_dev_if;
sock_diag_save_cookie(sk, r->id.idiag_cookie);
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6) {
*(struct in6_addr *)r->id.idiag_src = sk->sk_v6_rcv_saddr;
*(struct in6_addr *)r->id.idiag_dst = sk->sk_v6_daddr;
} else
#endif
{
memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
r->id.idiag_src[0] = sk->sk_rcv_saddr;
r->id.idiag_dst[0] = sk->sk_daddr;
}
}
EXPORT_SYMBOL_GPL(inet_diag_msg_common_fill);
static size_t inet_sk_attr_size(struct sock *sk,
const struct inet_diag_req_v2 *req,
bool net_admin)
{
const struct inet_diag_handler *handler;
size_t aux = 0;
handler = inet_diag_table[req->sdiag_protocol];
if (handler && handler->idiag_get_aux_size)
aux = handler->idiag_get_aux_size(sk, net_admin);
return nla_total_size(sizeof(struct tcp_info))
+ nla_total_size(sizeof(struct inet_diag_msg))
+ inet_diag_msg_attrs_size()
+ nla_total_size(sizeof(struct inet_diag_meminfo))
+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
+ nla_total_size(TCP_CA_NAME_MAX)
+ nla_total_size(sizeof(struct tcpvegas_info))
+ aux
+ 64;
}
int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
struct inet_diag_msg *r, int ext,
struct user_namespace *user_ns,
bool net_admin)
{
const struct inet_sock *inet = inet_sk(sk);
struct inet_diag_sockopt inet_sockopt;
if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown))
goto errout;
/* IPv6 dual-stack sockets use inet->tos for IPv4 connections,
* hence this needs to be included regardless of socket family.
*/
if (ext & (1 << (INET_DIAG_TOS - 1)))
if (nla_put_u8(skb, INET_DIAG_TOS, inet->tos) < 0)
goto errout;
#if IS_ENABLED(CONFIG_IPV6)
if (r->idiag_family == AF_INET6) {
if (ext & (1 << (INET_DIAG_TCLASS - 1)))
if (nla_put_u8(skb, INET_DIAG_TCLASS,
inet6_sk(sk)->tclass) < 0)
goto errout;
if (((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) &&
nla_put_u8(skb, INET_DIAG_SKV6ONLY, ipv6_only_sock(sk)))
goto errout;
}
#endif
if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark))
goto errout;
if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
ext & (1 << (INET_DIAG_TCLASS - 1))) {
u32 classid = 0;
#ifdef CONFIG_SOCK_CGROUP_DATA
classid = sock_cgroup_classid(&sk->sk_cgrp_data);
#endif
/* Fallback to socket priority if class id isn't set.
* Classful qdiscs use it as direct reference to class.
* For cgroup2 classid is always zero.
*/
if (!classid)
classid = sk->sk_priority;
if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
goto errout;
}
#ifdef CONFIG_SOCK_CGROUP_DATA
if (nla_put_u64_64bit(skb, INET_DIAG_CGROUP_ID,
cgroup_id(sock_cgroup_ptr(&sk->sk_cgrp_data)),
INET_DIAG_PAD))
goto errout;
#endif
r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
r->idiag_inode = sock_i_ino(sk);
memset(&inet_sockopt, 0, sizeof(inet_sockopt));
inet_sockopt.recverr = inet->recverr;
inet_sockopt.is_icsk = inet->is_icsk;
inet_sockopt.freebind = inet->freebind;
inet_sockopt.hdrincl = inet->hdrincl;
inet_sockopt.mc_loop = inet->mc_loop;
inet_sockopt.transparent = inet->transparent;
inet_sockopt.mc_all = inet->mc_all;
inet_sockopt.nodefrag = inet->nodefrag;
inet_sockopt.bind_address_no_port = inet->bind_address_no_port;
inet_sockopt.recverr_rfc4884 = inet->recverr_rfc4884;
inet_sockopt.defer_connect = inet->defer_connect;
if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt),
&inet_sockopt))
goto errout;
return 0;
errout:
return 1;
}
EXPORT_SYMBOL_GPL(inet_diag_msg_attrs_fill);
inet_diag: validate INET_DIAG_REQ_PROTOCOL attribute User space could send an invalid INET_DIAG_REQ_PROTOCOL attribute as caught by syzbot. BUG: KMSAN: uninit-value in inet_diag_lock_handler net/ipv4/inet_diag.c:55 [inline] BUG: KMSAN: uninit-value in __inet_diag_dump+0x58c/0x720 net/ipv4/inet_diag.c:1147 CPU: 0 PID: 8505 Comm: syz-executor174 Not tainted 5.9.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x21c/0x280 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:122 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:219 inet_diag_lock_handler net/ipv4/inet_diag.c:55 [inline] __inet_diag_dump+0x58c/0x720 net/ipv4/inet_diag.c:1147 inet_diag_dump_compat+0x2a5/0x380 net/ipv4/inet_diag.c:1254 netlink_dump+0xb73/0x1cb0 net/netlink/af_netlink.c:2246 __netlink_dump_start+0xcf2/0xea0 net/netlink/af_netlink.c:2354 netlink_dump_start include/linux/netlink.h:246 [inline] inet_diag_rcv_msg_compat+0x5da/0x6c0 net/ipv4/inet_diag.c:1288 sock_diag_rcv_msg+0x24f/0x620 net/core/sock_diag.c:256 netlink_rcv_skb+0x6d7/0x7e0 net/netlink/af_netlink.c:2470 sock_diag_rcv+0x63/0x80 net/core/sock_diag.c:275 netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline] netlink_unicast+0x11c8/0x1490 net/netlink/af_netlink.c:1330 netlink_sendmsg+0x173a/0x1840 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc82/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d1/0x820 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x441389 Code: e8 fc ab 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 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 0f 83 1b 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fff3b02ce98 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441389 RDX: 0000000000000000 RSI: 0000000020001500 RDI: 0000000000000003 RBP: 00000000006cb018 R08: 00000000004002c8 R09: 00000000004002c8 R10: 0000000000000004 R11: 0000000000000246 R12: 0000000000402130 R13: 00000000004021c0 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:143 [inline] kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:126 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:80 slab_alloc_node mm/slub.c:2907 [inline] __kmalloc_node_track_caller+0x9aa/0x12f0 mm/slub.c:4511 __kmalloc_reserve net/core/skbuff.c:142 [inline] __alloc_skb+0x35f/0xb30 net/core/skbuff.c:210 alloc_skb include/linux/skbuff.h:1094 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1176 [inline] netlink_sendmsg+0xdb9/0x1840 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc82/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d1/0x820 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 3f935c75eb52 ("inet_diag: support for wider protocol numbers") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Christoph Paasch <cpaasch@apple.com> Cc: Mat Martineau <mathew.j.martineau@linux.intel.com> Acked-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-09-21 22:27:20 +08:00
static int inet_diag_parse_attrs(const struct nlmsghdr *nlh, int hdrlen,
struct nlattr **req_nlas)
{
struct nlattr *nla;
int remaining;
nlmsg_for_each_attr(nla, nlh, hdrlen, remaining) {
int type = nla_type(nla);
inet_diag: validate INET_DIAG_REQ_PROTOCOL attribute User space could send an invalid INET_DIAG_REQ_PROTOCOL attribute as caught by syzbot. BUG: KMSAN: uninit-value in inet_diag_lock_handler net/ipv4/inet_diag.c:55 [inline] BUG: KMSAN: uninit-value in __inet_diag_dump+0x58c/0x720 net/ipv4/inet_diag.c:1147 CPU: 0 PID: 8505 Comm: syz-executor174 Not tainted 5.9.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x21c/0x280 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:122 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:219 inet_diag_lock_handler net/ipv4/inet_diag.c:55 [inline] __inet_diag_dump+0x58c/0x720 net/ipv4/inet_diag.c:1147 inet_diag_dump_compat+0x2a5/0x380 net/ipv4/inet_diag.c:1254 netlink_dump+0xb73/0x1cb0 net/netlink/af_netlink.c:2246 __netlink_dump_start+0xcf2/0xea0 net/netlink/af_netlink.c:2354 netlink_dump_start include/linux/netlink.h:246 [inline] inet_diag_rcv_msg_compat+0x5da/0x6c0 net/ipv4/inet_diag.c:1288 sock_diag_rcv_msg+0x24f/0x620 net/core/sock_diag.c:256 netlink_rcv_skb+0x6d7/0x7e0 net/netlink/af_netlink.c:2470 sock_diag_rcv+0x63/0x80 net/core/sock_diag.c:275 netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline] netlink_unicast+0x11c8/0x1490 net/netlink/af_netlink.c:1330 netlink_sendmsg+0x173a/0x1840 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc82/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d1/0x820 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x441389 Code: e8 fc ab 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 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 0f 83 1b 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fff3b02ce98 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441389 RDX: 0000000000000000 RSI: 0000000020001500 RDI: 0000000000000003 RBP: 00000000006cb018 R08: 00000000004002c8 R09: 00000000004002c8 R10: 0000000000000004 R11: 0000000000000246 R12: 0000000000402130 R13: 00000000004021c0 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:143 [inline] kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:126 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:80 slab_alloc_node mm/slub.c:2907 [inline] __kmalloc_node_track_caller+0x9aa/0x12f0 mm/slub.c:4511 __kmalloc_reserve net/core/skbuff.c:142 [inline] __alloc_skb+0x35f/0xb30 net/core/skbuff.c:210 alloc_skb include/linux/skbuff.h:1094 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1176 [inline] netlink_sendmsg+0xdb9/0x1840 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc82/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d1/0x820 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 3f935c75eb52 ("inet_diag: support for wider protocol numbers") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Christoph Paasch <cpaasch@apple.com> Cc: Mat Martineau <mathew.j.martineau@linux.intel.com> Acked-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-09-21 22:27:20 +08:00
if (type == INET_DIAG_REQ_PROTOCOL && nla_len(nla) != sizeof(u32))
return -EINVAL;
if (type < __INET_DIAG_REQ_MAX)
req_nlas[type] = nla;
}
inet_diag: validate INET_DIAG_REQ_PROTOCOL attribute User space could send an invalid INET_DIAG_REQ_PROTOCOL attribute as caught by syzbot. BUG: KMSAN: uninit-value in inet_diag_lock_handler net/ipv4/inet_diag.c:55 [inline] BUG: KMSAN: uninit-value in __inet_diag_dump+0x58c/0x720 net/ipv4/inet_diag.c:1147 CPU: 0 PID: 8505 Comm: syz-executor174 Not tainted 5.9.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x21c/0x280 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:122 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:219 inet_diag_lock_handler net/ipv4/inet_diag.c:55 [inline] __inet_diag_dump+0x58c/0x720 net/ipv4/inet_diag.c:1147 inet_diag_dump_compat+0x2a5/0x380 net/ipv4/inet_diag.c:1254 netlink_dump+0xb73/0x1cb0 net/netlink/af_netlink.c:2246 __netlink_dump_start+0xcf2/0xea0 net/netlink/af_netlink.c:2354 netlink_dump_start include/linux/netlink.h:246 [inline] inet_diag_rcv_msg_compat+0x5da/0x6c0 net/ipv4/inet_diag.c:1288 sock_diag_rcv_msg+0x24f/0x620 net/core/sock_diag.c:256 netlink_rcv_skb+0x6d7/0x7e0 net/netlink/af_netlink.c:2470 sock_diag_rcv+0x63/0x80 net/core/sock_diag.c:275 netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline] netlink_unicast+0x11c8/0x1490 net/netlink/af_netlink.c:1330 netlink_sendmsg+0x173a/0x1840 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc82/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d1/0x820 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x441389 Code: e8 fc ab 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 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 0f 83 1b 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fff3b02ce98 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441389 RDX: 0000000000000000 RSI: 0000000020001500 RDI: 0000000000000003 RBP: 00000000006cb018 R08: 00000000004002c8 R09: 00000000004002c8 R10: 0000000000000004 R11: 0000000000000246 R12: 0000000000402130 R13: 00000000004021c0 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:143 [inline] kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:126 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:80 slab_alloc_node mm/slub.c:2907 [inline] __kmalloc_node_track_caller+0x9aa/0x12f0 mm/slub.c:4511 __kmalloc_reserve net/core/skbuff.c:142 [inline] __alloc_skb+0x35f/0xb30 net/core/skbuff.c:210 alloc_skb include/linux/skbuff.h:1094 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1176 [inline] netlink_sendmsg+0xdb9/0x1840 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc82/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d1/0x820 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 3f935c75eb52 ("inet_diag: support for wider protocol numbers") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Christoph Paasch <cpaasch@apple.com> Cc: Mat Martineau <mathew.j.martineau@linux.intel.com> Acked-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-09-21 22:27:20 +08:00
return 0;
}
static int inet_diag_get_protocol(const struct inet_diag_req_v2 *req,
const struct inet_diag_dump_data *data)
{
if (data->req_nlas[INET_DIAG_REQ_PROTOCOL])
return nla_get_u32(data->req_nlas[INET_DIAG_REQ_PROTOCOL]);
return req->sdiag_protocol;
}
bpf: inet_diag: Dump bpf_sk_storages in inet_diag_dump() This patch will dump out the bpf_sk_storages of a sk if the request has the INET_DIAG_REQ_SK_BPF_STORAGES nlattr. An array of SK_DIAG_BPF_STORAGE_REQ_MAP_FD can be specified in INET_DIAG_REQ_SK_BPF_STORAGES to select which bpf_sk_storage to dump. If no map_fd is specified, all bpf_sk_storages of a sk will be dumped. bpf_sk_storages can be added to the system at runtime. It is difficult to find a proper static value for cb->min_dump_alloc. This patch learns the nlattr size required to dump the bpf_sk_storages of a sk. If it happens to be the very first nlmsg of a dump and it cannot fit the needed bpf_sk_storages, it will try to expand the skb by "pskb_expand_head()". Instead of expanding it in inet_sk_diag_fill(), it is expanded at a sleepable context in __inet_diag_dump() so __GFP_DIRECT_RECLAIM can be used. In __inet_diag_dump(), it will retry as long as the skb is empty and the cb->min_dump_alloc becomes larger than before. cb->min_dump_alloc is bounded by KMALLOC_MAX_SIZE. The min_dump_alloc is also changed from 'u16' to 'u32' to accommodate a sk that may have a few large bpf_sk_storages. The updated cb->min_dump_alloc will also be used to allocate the skb in the next dump. This logic already exists in netlink_dump(). Here is the sample output of a locally modified 'ss' and it could be made more readable by using BTF later: [root@arch-fb-vm1 ~]# ss --bpf-map-id 14 --bpf-map-id 13 -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] [root@arch-fb-vm1 ~]# ~/devshare/github/iproute2/misc/ss --bpf-maps -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:Port Process ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200225230427.1976129-1-kafai@fb.com
2020-02-26 07:04:27 +08:00
#define MAX_DUMP_ALLOC_SIZE (KMALLOC_MAX_SIZE - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
struct sk_buff *skb, struct netlink_callback *cb,
const struct inet_diag_req_v2 *req,
u16 nlmsg_flags, bool net_admin)
{
const struct tcp_congestion_ops *ca_ops;
const struct inet_diag_handler *handler;
bpf: inet_diag: Dump bpf_sk_storages in inet_diag_dump() This patch will dump out the bpf_sk_storages of a sk if the request has the INET_DIAG_REQ_SK_BPF_STORAGES nlattr. An array of SK_DIAG_BPF_STORAGE_REQ_MAP_FD can be specified in INET_DIAG_REQ_SK_BPF_STORAGES to select which bpf_sk_storage to dump. If no map_fd is specified, all bpf_sk_storages of a sk will be dumped. bpf_sk_storages can be added to the system at runtime. It is difficult to find a proper static value for cb->min_dump_alloc. This patch learns the nlattr size required to dump the bpf_sk_storages of a sk. If it happens to be the very first nlmsg of a dump and it cannot fit the needed bpf_sk_storages, it will try to expand the skb by "pskb_expand_head()". Instead of expanding it in inet_sk_diag_fill(), it is expanded at a sleepable context in __inet_diag_dump() so __GFP_DIRECT_RECLAIM can be used. In __inet_diag_dump(), it will retry as long as the skb is empty and the cb->min_dump_alloc becomes larger than before. cb->min_dump_alloc is bounded by KMALLOC_MAX_SIZE. The min_dump_alloc is also changed from 'u16' to 'u32' to accommodate a sk that may have a few large bpf_sk_storages. The updated cb->min_dump_alloc will also be used to allocate the skb in the next dump. This logic already exists in netlink_dump(). Here is the sample output of a locally modified 'ss' and it could be made more readable by using BTF later: [root@arch-fb-vm1 ~]# ss --bpf-map-id 14 --bpf-map-id 13 -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] [root@arch-fb-vm1 ~]# ~/devshare/github/iproute2/misc/ss --bpf-maps -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:Port Process ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200225230427.1976129-1-kafai@fb.com
2020-02-26 07:04:27 +08:00
struct inet_diag_dump_data *cb_data;
int ext = req->idiag_ext;
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
struct nlattr *attr;
void *info = NULL;
bpf: inet_diag: Dump bpf_sk_storages in inet_diag_dump() This patch will dump out the bpf_sk_storages of a sk if the request has the INET_DIAG_REQ_SK_BPF_STORAGES nlattr. An array of SK_DIAG_BPF_STORAGE_REQ_MAP_FD can be specified in INET_DIAG_REQ_SK_BPF_STORAGES to select which bpf_sk_storage to dump. If no map_fd is specified, all bpf_sk_storages of a sk will be dumped. bpf_sk_storages can be added to the system at runtime. It is difficult to find a proper static value for cb->min_dump_alloc. This patch learns the nlattr size required to dump the bpf_sk_storages of a sk. If it happens to be the very first nlmsg of a dump and it cannot fit the needed bpf_sk_storages, it will try to expand the skb by "pskb_expand_head()". Instead of expanding it in inet_sk_diag_fill(), it is expanded at a sleepable context in __inet_diag_dump() so __GFP_DIRECT_RECLAIM can be used. In __inet_diag_dump(), it will retry as long as the skb is empty and the cb->min_dump_alloc becomes larger than before. cb->min_dump_alloc is bounded by KMALLOC_MAX_SIZE. The min_dump_alloc is also changed from 'u16' to 'u32' to accommodate a sk that may have a few large bpf_sk_storages. The updated cb->min_dump_alloc will also be used to allocate the skb in the next dump. This logic already exists in netlink_dump(). Here is the sample output of a locally modified 'ss' and it could be made more readable by using BTF later: [root@arch-fb-vm1 ~]# ss --bpf-map-id 14 --bpf-map-id 13 -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] [root@arch-fb-vm1 ~]# ~/devshare/github/iproute2/misc/ss --bpf-maps -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:Port Process ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200225230427.1976129-1-kafai@fb.com
2020-02-26 07:04:27 +08:00
cb_data = cb->data;
handler = inet_diag_table[inet_diag_get_protocol(req, cb_data)];
BUG_ON(!handler);
nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(!sk_fullsock(sk));
inet_diag_msg_common_fill(r, sk);
r->idiag_state = sk->sk_state;
r->idiag_timer = 0;
r->idiag_retrans = 0;
inet_diag: fix kernel-infoleak for UDP sockets KMSAN reported a kernel-infoleak [1], that can exploited by unpriv users. After analysis it turned out UDP was not initializing r->idiag_expires. Other users of inet_sk_diag_fill() might make the same mistake in the future, so fix this in inet_sk_diag_fill(). [1] BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:121 [inline] BUG: KMSAN: kernel-infoleak in copyout lib/iov_iter.c:156 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x69d/0x25c0 lib/iov_iter.c:670 instrument_copy_to_user include/linux/instrumented.h:121 [inline] copyout lib/iov_iter.c:156 [inline] _copy_to_iter+0x69d/0x25c0 lib/iov_iter.c:670 copy_to_iter include/linux/uio.h:155 [inline] simple_copy_to_iter+0xf3/0x140 net/core/datagram.c:519 __skb_datagram_iter+0x2cb/0x1280 net/core/datagram.c:425 skb_copy_datagram_iter+0xdc/0x270 net/core/datagram.c:533 skb_copy_datagram_msg include/linux/skbuff.h:3657 [inline] netlink_recvmsg+0x660/0x1c60 net/netlink/af_netlink.c:1974 sock_recvmsg_nosec net/socket.c:944 [inline] sock_recvmsg net/socket.c:962 [inline] sock_read_iter+0x5a9/0x630 net/socket.c:1035 call_read_iter include/linux/fs.h:2156 [inline] new_sync_read fs/read_write.c:400 [inline] vfs_read+0x1631/0x1980 fs/read_write.c:481 ksys_read+0x28c/0x520 fs/read_write.c:619 __do_sys_read fs/read_write.c:629 [inline] __se_sys_read fs/read_write.c:627 [inline] __x64_sys_read+0xdb/0x120 fs/read_write.c:627 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x44/0xae Uninit was created at: slab_post_alloc_hook mm/slab.h:524 [inline] slab_alloc_node mm/slub.c:3251 [inline] __kmalloc_node_track_caller+0xe0c/0x1510 mm/slub.c:4974 kmalloc_reserve net/core/skbuff.c:354 [inline] __alloc_skb+0x545/0xf90 net/core/skbuff.c:426 alloc_skb include/linux/skbuff.h:1126 [inline] netlink_dump+0x3d5/0x16a0 net/netlink/af_netlink.c:2245 __netlink_dump_start+0xd1c/0xee0 net/netlink/af_netlink.c:2370 netlink_dump_start include/linux/netlink.h:254 [inline] inet_diag_handler_cmd+0x2e7/0x400 net/ipv4/inet_diag.c:1343 sock_diag_rcv_msg+0x24a/0x620 netlink_rcv_skb+0x447/0x800 net/netlink/af_netlink.c:2491 sock_diag_rcv+0x63/0x80 net/core/sock_diag.c:276 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x1095/0x1360 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x16f3/0x1870 net/netlink/af_netlink.c:1916 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg net/socket.c:724 [inline] sock_write_iter+0x594/0x690 net/socket.c:1057 do_iter_readv_writev+0xa7f/0xc70 do_iter_write+0x52c/0x1500 fs/read_write.c:851 vfs_writev fs/read_write.c:924 [inline] do_writev+0x63f/0xe30 fs/read_write.c:967 __do_sys_writev fs/read_write.c:1040 [inline] __se_sys_writev fs/read_write.c:1037 [inline] __x64_sys_writev+0xe5/0x120 fs/read_write.c:1037 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x44/0xae Bytes 68-71 of 312 are uninitialized Memory access of size 312 starts at ffff88812ab54000 Data copied to user address 0000000020001440 CPU: 1 PID: 6365 Comm: syz-executor801 Not tainted 5.16.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 3c4d05c80567 ("inet_diag: Introduce the inet socket dumping routine") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Link: https://lore.kernel.org/r/20211209185058.53917-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-12-10 02:50:58 +08:00
r->idiag_expires = 0;
if (inet_diag_msg_attrs_fill(sk, skb, r, ext,
sk_user_ns(NETLINK_CB(cb->skb).sk),
net_admin))
goto errout;
if (ext & (1 << (INET_DIAG_MEMINFO - 1))) {
struct inet_diag_meminfo minfo = {
.idiag_rmem = sk_rmem_alloc_get(sk),
.idiag_wmem = READ_ONCE(sk->sk_wmem_queued),
.idiag_fmem = sk_forward_alloc_get(sk),
.idiag_tmem = sk_wmem_alloc_get(sk),
};
if (nla_put(skb, INET_DIAG_MEMINFO, sizeof(minfo), &minfo) < 0)
goto errout;
}
if (ext & (1 << (INET_DIAG_SKMEMINFO - 1)))
if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO))
goto errout;
net: ip, diag -- Add diag interface for raw sockets In criu we are actively using diag interface to collect sockets present in the system when dumping applications. And while for unix, tcp, udp[lite], packet, netlink it works as expected, the raw sockets do not have. Thus add it. v2: - add missing sock_put calls in raw_diag_dump_one (by eric.dumazet@) - implement @destroy for diag requests (by dsa@) v3: - add export of raw_abort for IPv6 (by dsa@) - pass net-admin flag into inet_sk_diag_fill due to changes in net-next branch (by dsa@) v4: - use @pad in struct inet_diag_req_v2 for raw socket protocol specification: raw module carries sockets which may have custom protocol passed from socket() syscall and sole @sdiag_protocol is not enough to match underlied ones - start reporting protocol specifed in socket() call when sockets are raw ones for the same reason: user space tools like ss may parse this attribute and use it for socket matching v5 (by eric.dumazet@): - use sock_hold in raw_sock_get instead of atomic_inc, we're holding (raw_v4_hashinfo|raw_v6_hashinfo)->lock when looking up so counter won't be zero here. v6: - use sdiag_raw_protocol() helper which will access @pad structure used for raw sockets protocol specification: we can't simply rename this member without breaking uapi v7: - sine sdiag_raw_protocol() helper is not suitable for uapi lets rather make an alias structure with proper names. __check_inet_diag_req_raw helper will catch if any of structure unintentionally changed. CC: David S. Miller <davem@davemloft.net> CC: Eric Dumazet <eric.dumazet@gmail.com> CC: David Ahern <dsa@cumulusnetworks.com> CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> CC: James Morris <jmorris@namei.org> CC: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> CC: Patrick McHardy <kaber@trash.net> CC: Andrey Vagin <avagin@openvz.org> CC: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 18:03:44 +08:00
/*
* RAW sockets might have user-defined protocols assigned,
* so report the one supplied on socket creation.
*/
if (sk->sk_type == SOCK_RAW) {
if (nla_put_u8(skb, INET_DIAG_PROTOCOL, sk->sk_protocol))
goto errout;
}
if (!icsk) {
handler->idiag_get_info(sk, r, NULL);
goto out;
}
tcp: Tail loss probe (TLP) This patch series implement the Tail loss probe (TLP) algorithm described in http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01. The first patch implements the basic algorithm. TLP's goal is to reduce tail latency of short transactions. It achieves this by converting retransmission timeouts (RTOs) occuring due to tail losses (losses at end of transactions) into fast recovery. TLP transmits one packet in two round-trips when a connection is in Open state and isn't receiving any ACKs. The transmitted packet, aka loss probe, can be either new or a retransmission. When there is tail loss, the ACK from a loss probe triggers FACK/early-retransmit based fast recovery, thus avoiding a costly RTO. In the absence of loss, there is no change in the connection state. PTO stands for probe timeout. It is a timer event indicating that an ACK is overdue and triggers a loss probe packet. The PTO value is set to max(2*SRTT, 10ms) and is adjusted to account for delayed ACK timer when there is only one oustanding packet. TLP Algorithm On transmission of new data in Open state: -> packets_out > 1: schedule PTO in max(2*SRTT, 10ms). -> packets_out == 1: schedule PTO in max(2*RTT, 1.5*RTT + 200ms) -> PTO = min(PTO, RTO) Conditions for scheduling PTO: -> Connection is in Open state. -> Connection is either cwnd limited or no new data to send. -> Number of probes per tail loss episode is limited to one. -> Connection is SACK enabled. When PTO fires: new_segment_exists: -> transmit new segment. -> packets_out++. cwnd remains same. no_new_packet: -> retransmit the last segment. Its ACK triggers FACK or early retransmit based recovery. ACK path: -> rearm RTO at start of ACK processing. -> reschedule PTO if need be. In addition, the patch includes a small variation to the Early Retransmit (ER) algorithm, such that ER and TLP together can in principle recover any N-degree of tail loss through fast recovery. TLP is controlled by the same sysctl as ER, tcp_early_retrans sysctl. tcp_early_retrans==0; disables TLP and ER. ==1; enables RFC5827 ER. ==2; delayed ER. ==3; TLP and delayed ER. [DEFAULT] ==4; TLP only. The TLP patch series have been extensively tested on Google Web servers. It is most effective for short Web trasactions, where it reduced RTOs by 15% and improved HTTP response time (average by 6%, 99th percentile by 10%). The transmitted probes account for <0.5% of the overall transmissions. Signed-off-by: Nandita Dukkipati <nanditad@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-11 18:00:43 +08:00
if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
tcp: add reordering timer in RACK loss detection This patch makes RACK install a reordering timer when it suspects some packets might be lost, but wants to delay the decision a little bit to accomodate reordering. It does not create a new timer but instead repurposes the existing RTO timer, because both are meant to retransmit packets. Specifically it arms a timer ICSK_TIME_REO_TIMEOUT when the RACK timing check fails. The wait time is set to RACK.RTT + RACK.reo_wnd - (NOW - Packet.xmit_time) + fudge This translates to expecting a packet (Packet) should take (RACK.RTT + RACK.reo_wnd + fudge) to deliver after it was sent. When there are multiple packets that need a timer, we use one timer with the maximum timeout. Therefore the timer conservatively uses the maximum window to expire N packets by one timeout, instead of N timeouts to expire N packets sent at different times. The fudge factor is 2 jiffies to ensure when the timer fires, all the suspected packets would exceed the deadline and be marked lost by tcp_rack_detect_loss(). It has to be at least 1 jiffy because the clock may tick between calling icsk_reset_xmit_timer(timeout) and actually hang the timer. The next jiffy is to lower-bound the timeout to 2 jiffies when reo_wnd is < 1ms. When the reordering timer fires (tcp_rack_reo_timeout): If we aren't in Recovery we'll enter fast recovery and force fast retransmit. This is very similar to the early retransmit (RFC5827) except RACK is not constrained to only enter recovery for small outstanding flights. Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-13 14:11:33 +08:00
icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
tcp: Tail loss probe (TLP) This patch series implement the Tail loss probe (TLP) algorithm described in http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01. The first patch implements the basic algorithm. TLP's goal is to reduce tail latency of short transactions. It achieves this by converting retransmission timeouts (RTOs) occuring due to tail losses (losses at end of transactions) into fast recovery. TLP transmits one packet in two round-trips when a connection is in Open state and isn't receiving any ACKs. The transmitted packet, aka loss probe, can be either new or a retransmission. When there is tail loss, the ACK from a loss probe triggers FACK/early-retransmit based fast recovery, thus avoiding a costly RTO. In the absence of loss, there is no change in the connection state. PTO stands for probe timeout. It is a timer event indicating that an ACK is overdue and triggers a loss probe packet. The PTO value is set to max(2*SRTT, 10ms) and is adjusted to account for delayed ACK timer when there is only one oustanding packet. TLP Algorithm On transmission of new data in Open state: -> packets_out > 1: schedule PTO in max(2*SRTT, 10ms). -> packets_out == 1: schedule PTO in max(2*RTT, 1.5*RTT + 200ms) -> PTO = min(PTO, RTO) Conditions for scheduling PTO: -> Connection is in Open state. -> Connection is either cwnd limited or no new data to send. -> Number of probes per tail loss episode is limited to one. -> Connection is SACK enabled. When PTO fires: new_segment_exists: -> transmit new segment. -> packets_out++. cwnd remains same. no_new_packet: -> retransmit the last segment. Its ACK triggers FACK or early retransmit based recovery. ACK path: -> rearm RTO at start of ACK processing. -> reschedule PTO if need be. In addition, the patch includes a small variation to the Early Retransmit (ER) algorithm, such that ER and TLP together can in principle recover any N-degree of tail loss through fast recovery. TLP is controlled by the same sysctl as ER, tcp_early_retrans sysctl. tcp_early_retrans==0; disables TLP and ER. ==1; enables RFC5827 ER. ==2; delayed ER. ==3; TLP and delayed ER. [DEFAULT] ==4; TLP only. The TLP patch series have been extensively tested on Google Web servers. It is most effective for short Web trasactions, where it reduced RTOs by 15% and improved HTTP response time (average by 6%, 99th percentile by 10%). The transmitted probes account for <0.5% of the overall transmissions. Signed-off-by: Nandita Dukkipati <nanditad@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-11 18:00:43 +08:00
icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
r->idiag_timer = 1;
r->idiag_retrans = icsk->icsk_retransmits;
r->idiag_expires =
jiffies_delta_to_msecs(icsk->icsk_timeout - jiffies);
} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
r->idiag_timer = 4;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires =
jiffies_delta_to_msecs(icsk->icsk_timeout - jiffies);
} else if (timer_pending(&sk->sk_timer)) {
r->idiag_timer = 2;
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires =
jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies);
}
if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) {
attr = nla_reserve_64bit(skb, INET_DIAG_INFO,
handler->idiag_info_size,
INET_DIAG_PAD);
if (!attr)
goto errout;
info = nla_data(attr);
}
if (ext & (1 << (INET_DIAG_CONG - 1))) {
int err = 0;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops)
err = nla_put_string(skb, INET_DIAG_CONG, ca_ops->name);
rcu_read_unlock();
if (err < 0)
goto errout;
}
handler->idiag_get_info(sk, r, info);
if (ext & (1 << (INET_DIAG_INFO - 1)) && handler->idiag_get_aux)
if (handler->idiag_get_aux(sk, net_admin, skb) < 0)
goto errout;
if (sk->sk_state < TCP_TIME_WAIT) {
union tcp_cc_info info;
size_t sz = 0;
int attr;
rcu_read_lock();
ca_ops = READ_ONCE(icsk->icsk_ca_ops);
if (ca_ops && ca_ops->get_info)
sz = ca_ops->get_info(sk, ext, &attr, &info);
rcu_read_unlock();
if (sz && nla_put(skb, attr, sz, &info) < 0)
goto errout;
}
bpf: inet_diag: Dump bpf_sk_storages in inet_diag_dump() This patch will dump out the bpf_sk_storages of a sk if the request has the INET_DIAG_REQ_SK_BPF_STORAGES nlattr. An array of SK_DIAG_BPF_STORAGE_REQ_MAP_FD can be specified in INET_DIAG_REQ_SK_BPF_STORAGES to select which bpf_sk_storage to dump. If no map_fd is specified, all bpf_sk_storages of a sk will be dumped. bpf_sk_storages can be added to the system at runtime. It is difficult to find a proper static value for cb->min_dump_alloc. This patch learns the nlattr size required to dump the bpf_sk_storages of a sk. If it happens to be the very first nlmsg of a dump and it cannot fit the needed bpf_sk_storages, it will try to expand the skb by "pskb_expand_head()". Instead of expanding it in inet_sk_diag_fill(), it is expanded at a sleepable context in __inet_diag_dump() so __GFP_DIRECT_RECLAIM can be used. In __inet_diag_dump(), it will retry as long as the skb is empty and the cb->min_dump_alloc becomes larger than before. cb->min_dump_alloc is bounded by KMALLOC_MAX_SIZE. The min_dump_alloc is also changed from 'u16' to 'u32' to accommodate a sk that may have a few large bpf_sk_storages. The updated cb->min_dump_alloc will also be used to allocate the skb in the next dump. This logic already exists in netlink_dump(). Here is the sample output of a locally modified 'ss' and it could be made more readable by using BTF later: [root@arch-fb-vm1 ~]# ss --bpf-map-id 14 --bpf-map-id 13 -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] [root@arch-fb-vm1 ~]# ~/devshare/github/iproute2/misc/ss --bpf-maps -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:Port Process ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200225230427.1976129-1-kafai@fb.com
2020-02-26 07:04:27 +08:00
/* Keep it at the end for potential retry with a larger skb,
* or else do best-effort fitting, which is only done for the
* first_nlmsg.
*/
if (cb_data->bpf_stg_diag) {
bool first_nlmsg = ((unsigned char *)nlh == skb->data);
unsigned int prev_min_dump_alloc;
unsigned int total_nla_size = 0;
unsigned int msg_len;
int err;
msg_len = skb_tail_pointer(skb) - (unsigned char *)nlh;
err = bpf_sk_storage_diag_put(cb_data->bpf_stg_diag, sk, skb,
INET_DIAG_SK_BPF_STORAGES,
&total_nla_size);
if (!err)
goto out;
total_nla_size += msg_len;
prev_min_dump_alloc = cb->min_dump_alloc;
if (total_nla_size > prev_min_dump_alloc)
cb->min_dump_alloc = min_t(u32, total_nla_size,
MAX_DUMP_ALLOC_SIZE);
if (!first_nlmsg)
goto errout;
if (cb->min_dump_alloc > prev_min_dump_alloc)
/* Retry with pskb_expand_head() with
* __GFP_DIRECT_RECLAIM
*/
goto errout;
WARN_ON_ONCE(total_nla_size <= prev_min_dump_alloc);
/* Send what we have for this sk
* and move on to the next sk in the following
* dump()
*/
}
out:
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-17 05:09:00 +08:00
nlmsg_end(skb, nlh);
return 0;
errout:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
EXPORT_SYMBOL_GPL(inet_sk_diag_fill);
static int inet_twsk_diag_fill(struct sock *sk,
struct sk_buff *skb,
struct netlink_callback *cb,
u16 nlmsg_flags, bool net_admin)
{
struct inet_timewait_sock *tw = inet_twsk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
tcp/dccp: get rid of central timewait timer Using a timer wheel for timewait sockets was nice ~15 years ago when memory was expensive and machines had a single processor. This does not scale, code is ugly and source of huge latencies (Typically 30 ms have been seen, cpus spinning on death_lock spinlock.) We can afford to use an extra 64 bytes per timewait sock and spread timewait load to all cpus to have better behavior. Tested: On following test, /proc/sys/net/ipv4/tcp_tw_recycle is set to 1 on the target (lpaa24) Before patch : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 419594 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 437171 While test is running, we can observe 25 or even 33 ms latencies. lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20601ms rtt min/avg/max/mdev = 0.020/0.217/25.771/1.535 ms, pipe 2 lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20702ms rtt min/avg/max/mdev = 0.019/0.183/33.761/1.441 ms, pipe 2 After patch : About 90% increase of throughput : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 810442 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 800992 And latencies are kept to minimal values during this load, even if network utilization is 90% higher : lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 19991ms rtt min/avg/max/mdev = 0.023/0.064/0.360/0.042 ms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-13 09:51:09 +08:00
long tmo;
nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type,
sizeof(*r), nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(tw->tw_state != TCP_TIME_WAIT);
inet_diag_msg_common_fill(r, sk);
r->idiag_retrans = 0;
r->idiag_state = tw->tw_substate;
r->idiag_timer = 3;
tmo = tw->tw_timer.expires - jiffies;
r->idiag_expires = jiffies_delta_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
if (net_admin && nla_put_u32(skb, INET_DIAG_MARK,
tw->tw_mark)) {
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-17 05:09:00 +08:00
nlmsg_end(skb, nlh);
return 0;
}
static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
struct netlink_callback *cb,
u16 nlmsg_flags, bool net_admin)
{
struct request_sock *reqsk = inet_reqsk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
inet_diag_msg_common_fill(r, sk);
r->idiag_state = TCP_SYN_RECV;
r->idiag_timer = 1;
r->idiag_retrans = reqsk->num_retrans;
BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) !=
offsetof(struct sock, sk_cookie));
tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies;
r->idiag_expires = jiffies_delta_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
r->idiag_uid = 0;
r->idiag_inode = 0;
if (net_admin && nla_put_u32(skb, INET_DIAG_MARK,
inet_rsk(reqsk)->ir_mark)) {
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
nlmsg_end(skb, nlh);
return 0;
}
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
struct netlink_callback *cb,
const struct inet_diag_req_v2 *r,
u16 nlmsg_flags, bool net_admin)
{
if (sk->sk_state == TCP_TIME_WAIT)
return inet_twsk_diag_fill(sk, skb, cb, nlmsg_flags, net_admin);
if (sk->sk_state == TCP_NEW_SYN_RECV)
return inet_req_diag_fill(sk, skb, cb, nlmsg_flags, net_admin);
return inet_sk_diag_fill(sk, inet_csk(sk), skb, cb, r, nlmsg_flags,
net_admin);
}
struct sock *inet_diag_find_one_icsk(struct net *net,
struct inet_hashinfo *hashinfo,
const struct inet_diag_req_v2 *req)
{
struct sock *sk;
rcu_read_lock();
if (req->sdiag_family == AF_INET)
sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[0],
req->id.idiag_dport, req->id.idiag_src[0],
req->id.idiag_sport, req->id.idiag_if);
#if IS_ENABLED(CONFIG_IPV6)
else if (req->sdiag_family == AF_INET6) {
if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[3],
req->id.idiag_dport, req->id.idiag_src[3],
req->id.idiag_sport, req->id.idiag_if);
else
sk = inet6_lookup(net, hashinfo, NULL, 0,
(struct in6_addr *)req->id.idiag_dst,
req->id.idiag_dport,
(struct in6_addr *)req->id.idiag_src,
req->id.idiag_sport,
req->id.idiag_if);
}
#endif
else {
rcu_read_unlock();
return ERR_PTR(-EINVAL);
}
rcu_read_unlock();
if (!sk)
return ERR_PTR(-ENOENT);
if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) {
sock_gen_put(sk);
return ERR_PTR(-ENOENT);
}
return sk;
}
EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk);
int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
struct netlink_callback *cb,
const struct inet_diag_req_v2 *req)
{
struct sk_buff *in_skb = cb->skb;
bool net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN);
struct net *net = sock_net(in_skb->sk);
struct sk_buff *rep;
struct sock *sk;
int err;
sk = inet_diag_find_one_icsk(net, hashinfo, req);
if (IS_ERR(sk))
return PTR_ERR(sk);
rep = nlmsg_new(inet_sk_attr_size(sk, req, net_admin), GFP_KERNEL);
if (!rep) {
err = -ENOMEM;
goto out;
}
err = sk_diag_fill(sk, rep, cb, req, 0, net_admin);
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
nlmsg_free(rep);
goto out;
}
err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
out:
if (sk)
sock_gen_put(sk);
return err;
}
EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk);
static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
int hdrlen,
const struct inet_diag_req_v2 *req)
{
const struct inet_diag_handler *handler;
struct inet_diag_dump_data dump_data;
int err, protocol;
memset(&dump_data, 0, sizeof(dump_data));
inet_diag: validate INET_DIAG_REQ_PROTOCOL attribute User space could send an invalid INET_DIAG_REQ_PROTOCOL attribute as caught by syzbot. BUG: KMSAN: uninit-value in inet_diag_lock_handler net/ipv4/inet_diag.c:55 [inline] BUG: KMSAN: uninit-value in __inet_diag_dump+0x58c/0x720 net/ipv4/inet_diag.c:1147 CPU: 0 PID: 8505 Comm: syz-executor174 Not tainted 5.9.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x21c/0x280 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:122 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:219 inet_diag_lock_handler net/ipv4/inet_diag.c:55 [inline] __inet_diag_dump+0x58c/0x720 net/ipv4/inet_diag.c:1147 inet_diag_dump_compat+0x2a5/0x380 net/ipv4/inet_diag.c:1254 netlink_dump+0xb73/0x1cb0 net/netlink/af_netlink.c:2246 __netlink_dump_start+0xcf2/0xea0 net/netlink/af_netlink.c:2354 netlink_dump_start include/linux/netlink.h:246 [inline] inet_diag_rcv_msg_compat+0x5da/0x6c0 net/ipv4/inet_diag.c:1288 sock_diag_rcv_msg+0x24f/0x620 net/core/sock_diag.c:256 netlink_rcv_skb+0x6d7/0x7e0 net/netlink/af_netlink.c:2470 sock_diag_rcv+0x63/0x80 net/core/sock_diag.c:275 netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline] netlink_unicast+0x11c8/0x1490 net/netlink/af_netlink.c:1330 netlink_sendmsg+0x173a/0x1840 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc82/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d1/0x820 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x441389 Code: e8 fc ab 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 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 0f 83 1b 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fff3b02ce98 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441389 RDX: 0000000000000000 RSI: 0000000020001500 RDI: 0000000000000003 RBP: 00000000006cb018 R08: 00000000004002c8 R09: 00000000004002c8 R10: 0000000000000004 R11: 0000000000000246 R12: 0000000000402130 R13: 00000000004021c0 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:143 [inline] kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:126 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:80 slab_alloc_node mm/slub.c:2907 [inline] __kmalloc_node_track_caller+0x9aa/0x12f0 mm/slub.c:4511 __kmalloc_reserve net/core/skbuff.c:142 [inline] __alloc_skb+0x35f/0xb30 net/core/skbuff.c:210 alloc_skb include/linux/skbuff.h:1094 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1176 [inline] netlink_sendmsg+0xdb9/0x1840 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc82/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d1/0x820 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 3f935c75eb52 ("inet_diag: support for wider protocol numbers") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Christoph Paasch <cpaasch@apple.com> Cc: Mat Martineau <mathew.j.martineau@linux.intel.com> Acked-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-09-21 22:27:20 +08:00
err = inet_diag_parse_attrs(nlh, hdrlen, dump_data.req_nlas);
if (err)
return err;
protocol = inet_diag_get_protocol(req, &dump_data);
handler = inet_diag_lock_handler(protocol);
if (IS_ERR(handler)) {
err = PTR_ERR(handler);
} else if (cmd == SOCK_DIAG_BY_FAMILY) {
struct netlink_callback cb = {
.nlh = nlh,
.skb = in_skb,
.data = &dump_data,
};
err = handler->dump_one(&cb, req);
} else if (cmd == SOCK_DESTROY && handler->destroy) {
err = handler->destroy(in_skb, req);
} else {
err = -EOPNOTSUPP;
}
inet_diag_unlock_handler(handler);
return err;
}
static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits)
{
int words = bits >> 5;
bits &= 0x1f;
if (words) {
if (memcmp(a1, a2, words << 2))
return 0;
}
if (bits) {
__be32 w1, w2;
__be32 mask;
w1 = a1[words];
w2 = a2[words];
mask = htonl((0xffffffff) << (32 - bits));
if ((w1 ^ w2) & mask)
return 0;
}
return 1;
}
static int inet_diag_bc_run(const struct nlattr *_bc,
const struct inet_diag_entry *entry)
{
const void *bc = nla_data(_bc);
int len = nla_len(_bc);
while (len > 0) {
int yes = 1;
const struct inet_diag_bc_op *op = bc;
switch (op->code) {
case INET_DIAG_BC_NOP:
break;
case INET_DIAG_BC_JMP:
yes = 0;
break;
case INET_DIAG_BC_S_EQ:
yes = entry->sport == op[1].no;
break;
case INET_DIAG_BC_S_GE:
yes = entry->sport >= op[1].no;
break;
case INET_DIAG_BC_S_LE:
yes = entry->sport <= op[1].no;
break;
case INET_DIAG_BC_D_EQ:
yes = entry->dport == op[1].no;
break;
case INET_DIAG_BC_D_GE:
yes = entry->dport >= op[1].no;
break;
case INET_DIAG_BC_D_LE:
yes = entry->dport <= op[1].no;
break;
case INET_DIAG_BC_AUTO:
yes = !(entry->userlocks & SOCK_BINDPORT_LOCK);
break;
case INET_DIAG_BC_S_COND:
case INET_DIAG_BC_D_COND: {
const struct inet_diag_hostcond *cond;
const __be32 *addr;
cond = (const struct inet_diag_hostcond *)(op + 1);
if (cond->port != -1 &&
cond->port != (op->code == INET_DIAG_BC_S_COND ?
entry->sport : entry->dport)) {
yes = 0;
break;
}
if (op->code == INET_DIAG_BC_S_COND)
addr = entry->saddr;
else
addr = entry->daddr;
if (cond->family != AF_UNSPEC &&
cond->family != entry->family) {
if (entry->family == AF_INET6 &&
cond->family == AF_INET) {
if (addr[0] == 0 && addr[1] == 0 &&
addr[2] == htonl(0xffff) &&
bitstring_match(addr + 3,
cond->addr,
cond->prefix_len))
break;
}
yes = 0;
break;
}
if (cond->prefix_len == 0)
break;
if (bitstring_match(addr, cond->addr,
cond->prefix_len))
break;
yes = 0;
break;
}
case INET_DIAG_BC_DEV_COND: {
u32 ifindex;
ifindex = *((const u32 *)(op + 1));
if (ifindex != entry->ifindex)
yes = 0;
break;
}
case INET_DIAG_BC_MARK_COND: {
struct inet_diag_markcond *cond;
cond = (struct inet_diag_markcond *)(op + 1);
if ((entry->mark & cond->mask) != cond->mark)
yes = 0;
break;
}
#ifdef CONFIG_SOCK_CGROUP_DATA
case INET_DIAG_BC_CGROUP_COND: {
u64 cgroup_id;
cgroup_id = get_unaligned((const u64 *)(op + 1));
if (cgroup_id != entry->cgroup_id)
yes = 0;
break;
}
#endif
}
if (yes) {
len -= op->yes;
bc += op->yes;
} else {
len -= op->no;
bc += op->no;
}
}
return len == 0;
}
/* This helper is available for all sockets (ESTABLISH, TIMEWAIT, SYN_RECV)
*/
static void entry_fill_addrs(struct inet_diag_entry *entry,
const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6) {
entry->saddr = sk->sk_v6_rcv_saddr.s6_addr32;
entry->daddr = sk->sk_v6_daddr.s6_addr32;
} else
#endif
{
entry->saddr = &sk->sk_rcv_saddr;
entry->daddr = &sk->sk_daddr;
}
}
int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk)
{
struct inet_sock *inet = inet_sk(sk);
struct inet_diag_entry entry;
if (!bc)
return 1;
entry.family = sk->sk_family;
entry_fill_addrs(&entry, sk);
entry.sport = inet->inet_num;
entry.dport = ntohs(inet->inet_dport);
entry.ifindex = sk->sk_bound_dev_if;
entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0;
if (sk_fullsock(sk))
entry.mark = sk->sk_mark;
else if (sk->sk_state == TCP_NEW_SYN_RECV)
entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark;
else if (sk->sk_state == TCP_TIME_WAIT)
entry.mark = inet_twsk(sk)->tw_mark;
else
entry.mark = 0;
#ifdef CONFIG_SOCK_CGROUP_DATA
entry.cgroup_id = sk_fullsock(sk) ?
cgroup_id(sock_cgroup_ptr(&sk->sk_cgrp_data)) : 0;
#endif
return inet_diag_bc_run(bc, &entry);
}
EXPORT_SYMBOL_GPL(inet_diag_bc_sk);
static int valid_cc(const void *bc, int len, int cc)
{
while (len >= 0) {
const struct inet_diag_bc_op *op = bc;
if (cc > len)
return 0;
if (cc == len)
return 1;
if (op->yes < 4 || op->yes & 3)
return 0;
len -= op->yes;
bc += op->yes;
}
return 0;
}
/* data is u32 ifindex */
static bool valid_devcond(const struct inet_diag_bc_op *op, int len,
int *min_len)
{
/* Check ifindex space. */
*min_len += sizeof(u32);
if (len < *min_len)
return false;
return true;
}
/* Validate an inet_diag_hostcond. */
static bool valid_hostcond(const struct inet_diag_bc_op *op, int len,
int *min_len)
{
struct inet_diag_hostcond *cond;
int addr_len;
/* Check hostcond space. */
*min_len += sizeof(struct inet_diag_hostcond);
if (len < *min_len)
return false;
cond = (struct inet_diag_hostcond *)(op + 1);
/* Check address family and address length. */
switch (cond->family) {
case AF_UNSPEC:
addr_len = 0;
break;
case AF_INET:
addr_len = sizeof(struct in_addr);
break;
case AF_INET6:
addr_len = sizeof(struct in6_addr);
break;
default:
return false;
}
*min_len += addr_len;
if (len < *min_len)
return false;
/* Check prefix length (in bits) vs address length (in bytes). */
if (cond->prefix_len > 8 * addr_len)
return false;
return true;
}
/* Validate a port comparison operator. */
static bool valid_port_comparison(const struct inet_diag_bc_op *op,
int len, int *min_len)
{
/* Port comparisons put the port in a follow-on inet_diag_bc_op. */
*min_len += sizeof(struct inet_diag_bc_op);
if (len < *min_len)
return false;
return true;
}
static bool valid_markcond(const struct inet_diag_bc_op *op, int len,
int *min_len)
{
*min_len += sizeof(struct inet_diag_markcond);
return len >= *min_len;
}
#ifdef CONFIG_SOCK_CGROUP_DATA
static bool valid_cgroupcond(const struct inet_diag_bc_op *op, int len,
int *min_len)
{
*min_len += sizeof(u64);
return len >= *min_len;
}
#endif
static int inet_diag_bc_audit(const struct nlattr *attr,
const struct sk_buff *skb)
{
bool net_admin = netlink_net_capable(skb, CAP_NET_ADMIN);
const void *bytecode, *bc;
int bytecode_len, len;
if (!attr || nla_len(attr) < sizeof(struct inet_diag_bc_op))
return -EINVAL;
bytecode = bc = nla_data(attr);
len = bytecode_len = nla_len(attr);
while (len > 0) {
int min_len = sizeof(struct inet_diag_bc_op);
const struct inet_diag_bc_op *op = bc;
switch (op->code) {
case INET_DIAG_BC_S_COND:
case INET_DIAG_BC_D_COND:
if (!valid_hostcond(bc, len, &min_len))
return -EINVAL;
break;
case INET_DIAG_BC_DEV_COND:
if (!valid_devcond(bc, len, &min_len))
return -EINVAL;
break;
case INET_DIAG_BC_S_EQ:
case INET_DIAG_BC_S_GE:
case INET_DIAG_BC_S_LE:
case INET_DIAG_BC_D_EQ:
case INET_DIAG_BC_D_GE:
case INET_DIAG_BC_D_LE:
if (!valid_port_comparison(bc, len, &min_len))
return -EINVAL;
break;
case INET_DIAG_BC_MARK_COND:
if (!net_admin)
return -EPERM;
if (!valid_markcond(bc, len, &min_len))
return -EINVAL;
break;
#ifdef CONFIG_SOCK_CGROUP_DATA
case INET_DIAG_BC_CGROUP_COND:
if (!valid_cgroupcond(bc, len, &min_len))
return -EINVAL;
break;
#endif
case INET_DIAG_BC_AUTO:
case INET_DIAG_BC_JMP:
case INET_DIAG_BC_NOP:
break;
default:
return -EINVAL;
}
if (op->code != INET_DIAG_BC_NOP) {
if (op->no < min_len || op->no > len + 4 || op->no & 3)
return -EINVAL;
if (op->no < len &&
!valid_cc(bytecode, bytecode_len, len - op->no))
return -EINVAL;
}
if (op->yes < min_len || op->yes > len + 4 || op->yes & 3)
return -EINVAL;
bc += op->yes;
len -= op->yes;
}
return len == 0 ? 0 : -EINVAL;
}
static void twsk_build_assert(void)
{
BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_family) !=
offsetof(struct sock, sk_family));
BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_num) !=
offsetof(struct inet_sock, inet_num));
BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_dport) !=
offsetof(struct inet_sock, inet_dport));
BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_rcv_saddr) !=
offsetof(struct inet_sock, inet_rcv_saddr));
BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_daddr) !=
offsetof(struct inet_sock, inet_daddr));
#if IS_ENABLED(CONFIG_IPV6)
BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_rcv_saddr) !=
offsetof(struct sock, sk_v6_rcv_saddr));
BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_v6_daddr) !=
offsetof(struct sock, sk_v6_daddr));
#endif
}
void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
struct netlink_callback *cb,
const struct inet_diag_req_v2 *r)
{
bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
struct inet_diag_dump_data *cb_data = cb->data;
struct net *net = sock_net(skb->sk);
u32 idiag_states = r->idiag_states;
int i, num, s_i, s_num;
struct nlattr *bc;
struct sock *sk;
bc = cb_data->inet_diag_nla_bc;
if (idiag_states & TCPF_SYN_RECV)
idiag_states |= TCPF_NEW_SYN_RECV;
s_i = cb->args[1];
s_num = num = cb->args[2];
if (cb->args[0] == 0) {
if (!(idiag_states & TCPF_LISTEN) || r->id.idiag_dport)
goto skip_listen_ht;
for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
struct inet_listen_hashbucket *ilb;
struct hlist_nulls_node *node;
num = 0;
ilb = &hashinfo->listening_hash[i];
spin_lock(&ilb->lock);
sk_nulls_for_each(sk, node, &ilb->nulls_head) {
struct inet_sock *inet = inet_sk(sk);
if (!net_eq(sock_net(sk), net))
continue;
if (num < s_num) {
num++;
continue;
}
if (r->sdiag_family != AF_UNSPEC &&
sk->sk_family != r->sdiag_family)
goto next_listen;
if (r->id.idiag_sport != inet->inet_sport &&
r->id.idiag_sport)
goto next_listen;
if (!inet_diag_bc_sk(bc, sk))
goto next_listen;
if (inet_sk_diag_fill(sk, inet_csk(sk), skb,
cb, r, NLM_F_MULTI,
net_admin) < 0) {
spin_unlock(&ilb->lock);
goto done;
}
next_listen:
++num;
}
spin_unlock(&ilb->lock);
s_num = 0;
}
skip_listen_ht:
cb->args[0] = 1;
s_i = num = s_num = 0;
}
if (!(idiag_states & ~TCPF_LISTEN))
goto out;
#define SKARR_SZ 16
for (i = s_i; i <= hashinfo->ehash_mask; i++) {
struct inet_ehash_bucket *head = &hashinfo->ehash[i];
spinlock_t *lock = inet_ehash_lockp(hashinfo, i);
struct hlist_nulls_node *node;
struct sock *sk_arr[SKARR_SZ];
int num_arr[SKARR_SZ];
int idx, accum, res;
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 15:22:02 +08:00
if (hlist_nulls_empty(&head->chain))
continue;
if (i > s_i)
s_num = 0;
next_chunk:
num = 0;
accum = 0;
spin_lock_bh(lock);
sk_nulls_for_each(sk, node, &head->chain) {
int state;
if (!net_eq(sock_net(sk), net))
continue;
if (num < s_num)
goto next_normal;
state = (sk->sk_state == TCP_TIME_WAIT) ?
inet_twsk(sk)->tw_substate : sk->sk_state;
if (!(idiag_states & (1 << state)))
goto next_normal;
if (r->sdiag_family != AF_UNSPEC &&
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 15:22:02 +08:00
sk->sk_family != r->sdiag_family)
goto next_normal;
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 15:22:02 +08:00
if (r->id.idiag_sport != htons(sk->sk_num) &&
r->id.idiag_sport)
goto next_normal;
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 15:22:02 +08:00
if (r->id.idiag_dport != sk->sk_dport &&
r->id.idiag_dport)
goto next_normal;
twsk_build_assert();
if (!inet_diag_bc_sk(bc, sk))
goto next_normal;
tcp: fix a race in inet_diag_dump_icsk() Alexei reported use after frees in inet_diag_dump_icsk() [1] Because we use refcount_set() when various sockets are setup and inserted into ehash, we also need to make sure inet_diag_dump_icsk() wont race with the refcount_set() operations. Jonathan Lemon sent a patch changing net_twsk_hashdance() but other spots would need risky changes. Instead, fix inet_diag_dump_icsk() as this bug came with linux-4.10 only. [1] Quoting Alexei : First something iterating over sockets finds already freed tw socket: refcount_t: increment on 0; use-after-free. WARNING: CPU: 2 PID: 2738 at lib/refcount.c:153 refcount_inc+0x26/0x30 RIP: 0010:refcount_inc+0x26/0x30 RSP: 0018:ffffc90004c8fbc0 EFLAGS: 00010282 RAX: 000000000000002b RBX: 0000000000000000 RCX: 0000000000000000 RDX: ffff88085ee9d680 RSI: ffff88085ee954c8 RDI: ffff88085ee954c8 RBP: ffff88010ecbd2c0 R08: 0000000000000000 R09: 000000000000174c R10: ffffffff81e7c5a0 R11: 0000000000000000 R12: 0000000000000000 R13: ffff8806ba9bf210 R14: ffffffff82304600 R15: ffff88010ecbd328 FS: 00007f81f5a7d700(0000) GS:ffff88085ee80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f81e2a95000 CR3: 000000069b2eb006 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: inet_diag_dump_icsk+0x2b3/0x4e0 [inet_diag] // sock_hold(sk); in net/ipv4/inet_diag.c:1002 ? kmalloc_large_node+0x37/0x70 ? __kmalloc_node_track_caller+0x1cb/0x260 ? __alloc_skb+0x72/0x1b0 ? __kmalloc_reserve.isra.40+0x2e/0x80 __inet_diag_dump+0x3b/0x80 [inet_diag] netlink_dump+0x116/0x2a0 netlink_recvmsg+0x205/0x3c0 sock_read_iter+0x89/0xd0 __vfs_read+0xf7/0x140 vfs_read+0x8a/0x140 SyS_read+0x3f/0xa0 do_syscall_64+0x5a/0x100 then a minute later twsk timer fires and hits two bad refcnts for this freed socket: refcount_t: decrement hit 0; leaking memory. WARNING: CPU: 31 PID: 0 at lib/refcount.c:228 refcount_dec+0x2e/0x40 Modules linked in: RIP: 0010:refcount_dec+0x2e/0x40 RSP: 0018:ffff88085f5c3ea8 EFLAGS: 00010296 RAX: 000000000000002c RBX: ffff88010ecbd2c0 RCX: 000000000000083f RDX: 0000000000000000 RSI: 00000000000000f6 RDI: 000000000000003f RBP: ffffc90003c77280 R08: 0000000000000000 R09: 00000000000017d3 R10: ffffffff81e7c5a0 R11: 0000000000000000 R12: ffffffff82ad2d80 R13: ffffffff8182de00 R14: ffff88085f5c3ef8 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88085f5c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fbe42685250 CR3: 0000000002209001 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> inet_twsk_kill+0x9d/0xc0 // inet_twsk_bind_unhash(tw, hashinfo); call_timer_fn+0x29/0x110 run_timer_softirq+0x36b/0x3a0 refcount_t: underflow; use-after-free. WARNING: CPU: 31 PID: 0 at lib/refcount.c:187 refcount_sub_and_test+0x46/0x50 RIP: 0010:refcount_sub_and_test+0x46/0x50 RSP: 0018:ffff88085f5c3eb8 EFLAGS: 00010296 RAX: 0000000000000026 RBX: ffff88010ecbd2c0 RCX: 000000000000083f RDX: 0000000000000000 RSI: 00000000000000f6 RDI: 000000000000003f RBP: ffff88010ecbd358 R08: 0000000000000000 R09: 000000000000185b R10: ffffffff81e7c5a0 R11: 0000000000000000 R12: ffff88010ecbd358 R13: ffffffff8182de00 R14: ffff88085f5c3ef8 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88085f5c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fbe42685250 CR3: 0000000002209001 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> inet_twsk_put+0x12/0x20 // inet_twsk_put(tw); call_timer_fn+0x29/0x110 run_timer_softirq+0x36b/0x3a0 Fixes: 67db3e4bfbc9 ("tcp: no longer hold ehash lock while calling tcp_get_info()") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Alexei Starovoitov <ast@kernel.org> Cc: Jonathan Lemon <jonathan.lemon@gmail.com> Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-12-21 07:28:56 +08:00
if (!refcount_inc_not_zero(&sk->sk_refcnt))
goto next_normal;
num_arr[accum] = num;
sk_arr[accum] = sk;
if (++accum == SKARR_SZ)
break;
next_normal:
++num;
}
spin_unlock_bh(lock);
res = 0;
for (idx = 0; idx < accum; idx++) {
if (res >= 0) {
res = sk_diag_fill(sk_arr[idx], skb, cb, r,
NLM_F_MULTI, net_admin);
if (res < 0)
num = num_arr[idx];
}
sock_gen_put(sk_arr[idx]);
}
if (res < 0)
break;
cond_resched();
if (accum == SKARR_SZ) {
s_num = num + 1;
goto next_chunk;
}
}
done:
cb->args[1] = i;
cb->args[2] = num;
out:
;
}
EXPORT_SYMBOL_GPL(inet_diag_dump_icsk);
static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
const struct inet_diag_req_v2 *r)
{
struct inet_diag_dump_data *cb_data = cb->data;
const struct inet_diag_handler *handler;
bpf: inet_diag: Dump bpf_sk_storages in inet_diag_dump() This patch will dump out the bpf_sk_storages of a sk if the request has the INET_DIAG_REQ_SK_BPF_STORAGES nlattr. An array of SK_DIAG_BPF_STORAGE_REQ_MAP_FD can be specified in INET_DIAG_REQ_SK_BPF_STORAGES to select which bpf_sk_storage to dump. If no map_fd is specified, all bpf_sk_storages of a sk will be dumped. bpf_sk_storages can be added to the system at runtime. It is difficult to find a proper static value for cb->min_dump_alloc. This patch learns the nlattr size required to dump the bpf_sk_storages of a sk. If it happens to be the very first nlmsg of a dump and it cannot fit the needed bpf_sk_storages, it will try to expand the skb by "pskb_expand_head()". Instead of expanding it in inet_sk_diag_fill(), it is expanded at a sleepable context in __inet_diag_dump() so __GFP_DIRECT_RECLAIM can be used. In __inet_diag_dump(), it will retry as long as the skb is empty and the cb->min_dump_alloc becomes larger than before. cb->min_dump_alloc is bounded by KMALLOC_MAX_SIZE. The min_dump_alloc is also changed from 'u16' to 'u32' to accommodate a sk that may have a few large bpf_sk_storages. The updated cb->min_dump_alloc will also be used to allocate the skb in the next dump. This logic already exists in netlink_dump(). Here is the sample output of a locally modified 'ss' and it could be made more readable by using BTF later: [root@arch-fb-vm1 ~]# ss --bpf-map-id 14 --bpf-map-id 13 -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] [root@arch-fb-vm1 ~]# ~/devshare/github/iproute2/misc/ss --bpf-maps -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:Port Process ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200225230427.1976129-1-kafai@fb.com
2020-02-26 07:04:27 +08:00
u32 prev_min_dump_alloc;
int protocol, err = 0;
protocol = inet_diag_get_protocol(r, cb_data);
bpf: inet_diag: Dump bpf_sk_storages in inet_diag_dump() This patch will dump out the bpf_sk_storages of a sk if the request has the INET_DIAG_REQ_SK_BPF_STORAGES nlattr. An array of SK_DIAG_BPF_STORAGE_REQ_MAP_FD can be specified in INET_DIAG_REQ_SK_BPF_STORAGES to select which bpf_sk_storage to dump. If no map_fd is specified, all bpf_sk_storages of a sk will be dumped. bpf_sk_storages can be added to the system at runtime. It is difficult to find a proper static value for cb->min_dump_alloc. This patch learns the nlattr size required to dump the bpf_sk_storages of a sk. If it happens to be the very first nlmsg of a dump and it cannot fit the needed bpf_sk_storages, it will try to expand the skb by "pskb_expand_head()". Instead of expanding it in inet_sk_diag_fill(), it is expanded at a sleepable context in __inet_diag_dump() so __GFP_DIRECT_RECLAIM can be used. In __inet_diag_dump(), it will retry as long as the skb is empty and the cb->min_dump_alloc becomes larger than before. cb->min_dump_alloc is bounded by KMALLOC_MAX_SIZE. The min_dump_alloc is also changed from 'u16' to 'u32' to accommodate a sk that may have a few large bpf_sk_storages. The updated cb->min_dump_alloc will also be used to allocate the skb in the next dump. This logic already exists in netlink_dump(). Here is the sample output of a locally modified 'ss' and it could be made more readable by using BTF later: [root@arch-fb-vm1 ~]# ss --bpf-map-id 14 --bpf-map-id 13 -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] [root@arch-fb-vm1 ~]# ~/devshare/github/iproute2/misc/ss --bpf-maps -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:Port Process ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200225230427.1976129-1-kafai@fb.com
2020-02-26 07:04:27 +08:00
again:
prev_min_dump_alloc = cb->min_dump_alloc;
handler = inet_diag_lock_handler(protocol);
if (!IS_ERR(handler))
handler->dump(skb, cb, r);
else
err = PTR_ERR(handler);
inet_diag_unlock_handler(handler);
bpf: inet_diag: Dump bpf_sk_storages in inet_diag_dump() This patch will dump out the bpf_sk_storages of a sk if the request has the INET_DIAG_REQ_SK_BPF_STORAGES nlattr. An array of SK_DIAG_BPF_STORAGE_REQ_MAP_FD can be specified in INET_DIAG_REQ_SK_BPF_STORAGES to select which bpf_sk_storage to dump. If no map_fd is specified, all bpf_sk_storages of a sk will be dumped. bpf_sk_storages can be added to the system at runtime. It is difficult to find a proper static value for cb->min_dump_alloc. This patch learns the nlattr size required to dump the bpf_sk_storages of a sk. If it happens to be the very first nlmsg of a dump and it cannot fit the needed bpf_sk_storages, it will try to expand the skb by "pskb_expand_head()". Instead of expanding it in inet_sk_diag_fill(), it is expanded at a sleepable context in __inet_diag_dump() so __GFP_DIRECT_RECLAIM can be used. In __inet_diag_dump(), it will retry as long as the skb is empty and the cb->min_dump_alloc becomes larger than before. cb->min_dump_alloc is bounded by KMALLOC_MAX_SIZE. The min_dump_alloc is also changed from 'u16' to 'u32' to accommodate a sk that may have a few large bpf_sk_storages. The updated cb->min_dump_alloc will also be used to allocate the skb in the next dump. This logic already exists in netlink_dump(). Here is the sample output of a locally modified 'ss' and it could be made more readable by using BTF later: [root@arch-fb-vm1 ~]# ss --bpf-map-id 14 --bpf-map-id 13 -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] [root@arch-fb-vm1 ~]# ~/devshare/github/iproute2/misc/ss --bpf-maps -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:Port Process ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200225230427.1976129-1-kafai@fb.com
2020-02-26 07:04:27 +08:00
/* The skb is not large enough to fit one sk info and
* inet_sk_diag_fill() has requested for a larger skb.
*/
if (!skb->len && cb->min_dump_alloc > prev_min_dump_alloc) {
err = pskb_expand_head(skb, 0, cb->min_dump_alloc, GFP_KERNEL);
if (!err)
goto again;
}
return err ? : skb->len;
}
static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
return __inet_diag_dump(skb, cb, nlmsg_data(cb->nlh));
}
static int __inet_diag_dump_start(struct netlink_callback *cb, int hdrlen)
{
const struct nlmsghdr *nlh = cb->nlh;
struct inet_diag_dump_data *cb_data;
struct sk_buff *skb = cb->skb;
struct nlattr *nla;
int err;
cb_data = kzalloc(sizeof(*cb_data), GFP_KERNEL);
if (!cb_data)
return -ENOMEM;
inet_diag: validate INET_DIAG_REQ_PROTOCOL attribute User space could send an invalid INET_DIAG_REQ_PROTOCOL attribute as caught by syzbot. BUG: KMSAN: uninit-value in inet_diag_lock_handler net/ipv4/inet_diag.c:55 [inline] BUG: KMSAN: uninit-value in __inet_diag_dump+0x58c/0x720 net/ipv4/inet_diag.c:1147 CPU: 0 PID: 8505 Comm: syz-executor174 Not tainted 5.9.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x21c/0x280 lib/dump_stack.c:118 kmsan_report+0xf7/0x1e0 mm/kmsan/kmsan_report.c:122 __msan_warning+0x58/0xa0 mm/kmsan/kmsan_instr.c:219 inet_diag_lock_handler net/ipv4/inet_diag.c:55 [inline] __inet_diag_dump+0x58c/0x720 net/ipv4/inet_diag.c:1147 inet_diag_dump_compat+0x2a5/0x380 net/ipv4/inet_diag.c:1254 netlink_dump+0xb73/0x1cb0 net/netlink/af_netlink.c:2246 __netlink_dump_start+0xcf2/0xea0 net/netlink/af_netlink.c:2354 netlink_dump_start include/linux/netlink.h:246 [inline] inet_diag_rcv_msg_compat+0x5da/0x6c0 net/ipv4/inet_diag.c:1288 sock_diag_rcv_msg+0x24f/0x620 net/core/sock_diag.c:256 netlink_rcv_skb+0x6d7/0x7e0 net/netlink/af_netlink.c:2470 sock_diag_rcv+0x63/0x80 net/core/sock_diag.c:275 netlink_unicast_kernel net/netlink/af_netlink.c:1304 [inline] netlink_unicast+0x11c8/0x1490 net/netlink/af_netlink.c:1330 netlink_sendmsg+0x173a/0x1840 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc82/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d1/0x820 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x441389 Code: e8 fc ab 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 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 0f 83 1b 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fff3b02ce98 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441389 RDX: 0000000000000000 RSI: 0000000020001500 RDI: 0000000000000003 RBP: 00000000006cb018 R08: 00000000004002c8 R09: 00000000004002c8 R10: 0000000000000004 R11: 0000000000000246 R12: 0000000000402130 R13: 00000000004021c0 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:143 [inline] kmsan_internal_poison_shadow+0x66/0xd0 mm/kmsan/kmsan.c:126 kmsan_slab_alloc+0x8a/0xe0 mm/kmsan/kmsan_hooks.c:80 slab_alloc_node mm/slub.c:2907 [inline] __kmalloc_node_track_caller+0x9aa/0x12f0 mm/slub.c:4511 __kmalloc_reserve net/core/skbuff.c:142 [inline] __alloc_skb+0x35f/0xb30 net/core/skbuff.c:210 alloc_skb include/linux/skbuff.h:1094 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1176 [inline] netlink_sendmsg+0xdb9/0x1840 net/netlink/af_netlink.c:1894 sock_sendmsg_nosec net/socket.c:651 [inline] sock_sendmsg net/socket.c:671 [inline] ____sys_sendmsg+0xc82/0x1240 net/socket.c:2353 ___sys_sendmsg net/socket.c:2407 [inline] __sys_sendmsg+0x6d1/0x820 net/socket.c:2440 __do_sys_sendmsg net/socket.c:2449 [inline] __se_sys_sendmsg+0x97/0xb0 net/socket.c:2447 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2447 do_syscall_64+0x9f/0x140 arch/x86/entry/common.c:48 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fixes: 3f935c75eb52 ("inet_diag: support for wider protocol numbers") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Christoph Paasch <cpaasch@apple.com> Cc: Mat Martineau <mathew.j.martineau@linux.intel.com> Acked-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-09-21 22:27:20 +08:00
err = inet_diag_parse_attrs(nlh, hdrlen, cb_data->req_nlas);
if (err) {
kfree(cb_data);
return err;
}
nla = cb_data->inet_diag_nla_bc;
if (nla) {
err = inet_diag_bc_audit(nla, skb);
if (err) {
kfree(cb_data);
return err;
}
}
bpf: inet_diag: Dump bpf_sk_storages in inet_diag_dump() This patch will dump out the bpf_sk_storages of a sk if the request has the INET_DIAG_REQ_SK_BPF_STORAGES nlattr. An array of SK_DIAG_BPF_STORAGE_REQ_MAP_FD can be specified in INET_DIAG_REQ_SK_BPF_STORAGES to select which bpf_sk_storage to dump. If no map_fd is specified, all bpf_sk_storages of a sk will be dumped. bpf_sk_storages can be added to the system at runtime. It is difficult to find a proper static value for cb->min_dump_alloc. This patch learns the nlattr size required to dump the bpf_sk_storages of a sk. If it happens to be the very first nlmsg of a dump and it cannot fit the needed bpf_sk_storages, it will try to expand the skb by "pskb_expand_head()". Instead of expanding it in inet_sk_diag_fill(), it is expanded at a sleepable context in __inet_diag_dump() so __GFP_DIRECT_RECLAIM can be used. In __inet_diag_dump(), it will retry as long as the skb is empty and the cb->min_dump_alloc becomes larger than before. cb->min_dump_alloc is bounded by KMALLOC_MAX_SIZE. The min_dump_alloc is also changed from 'u16' to 'u32' to accommodate a sk that may have a few large bpf_sk_storages. The updated cb->min_dump_alloc will also be used to allocate the skb in the next dump. This logic already exists in netlink_dump(). Here is the sample output of a locally modified 'ss' and it could be made more readable by using BTF later: [root@arch-fb-vm1 ~]# ss --bpf-map-id 14 --bpf-map-id 13 -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] [root@arch-fb-vm1 ~]# ~/devshare/github/iproute2/misc/ss --bpf-maps -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:Port Process ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200225230427.1976129-1-kafai@fb.com
2020-02-26 07:04:27 +08:00
nla = cb_data->inet_diag_nla_bpf_stgs;
if (nla) {
struct bpf_sk_storage_diag *bpf_stg_diag;
bpf_stg_diag = bpf_sk_storage_diag_alloc(nla);
if (IS_ERR(bpf_stg_diag)) {
kfree(cb_data);
return PTR_ERR(bpf_stg_diag);
}
cb_data->bpf_stg_diag = bpf_stg_diag;
}
cb->data = cb_data;
return 0;
}
static int inet_diag_dump_start(struct netlink_callback *cb)
{
return __inet_diag_dump_start(cb, sizeof(struct inet_diag_req_v2));
}
static int inet_diag_dump_start_compat(struct netlink_callback *cb)
{
return __inet_diag_dump_start(cb, sizeof(struct inet_diag_req));
}
static int inet_diag_dump_done(struct netlink_callback *cb)
{
bpf: inet_diag: Dump bpf_sk_storages in inet_diag_dump() This patch will dump out the bpf_sk_storages of a sk if the request has the INET_DIAG_REQ_SK_BPF_STORAGES nlattr. An array of SK_DIAG_BPF_STORAGE_REQ_MAP_FD can be specified in INET_DIAG_REQ_SK_BPF_STORAGES to select which bpf_sk_storage to dump. If no map_fd is specified, all bpf_sk_storages of a sk will be dumped. bpf_sk_storages can be added to the system at runtime. It is difficult to find a proper static value for cb->min_dump_alloc. This patch learns the nlattr size required to dump the bpf_sk_storages of a sk. If it happens to be the very first nlmsg of a dump and it cannot fit the needed bpf_sk_storages, it will try to expand the skb by "pskb_expand_head()". Instead of expanding it in inet_sk_diag_fill(), it is expanded at a sleepable context in __inet_diag_dump() so __GFP_DIRECT_RECLAIM can be used. In __inet_diag_dump(), it will retry as long as the skb is empty and the cb->min_dump_alloc becomes larger than before. cb->min_dump_alloc is bounded by KMALLOC_MAX_SIZE. The min_dump_alloc is also changed from 'u16' to 'u32' to accommodate a sk that may have a few large bpf_sk_storages. The updated cb->min_dump_alloc will also be used to allocate the skb in the next dump. This logic already exists in netlink_dump(). Here is the sample output of a locally modified 'ss' and it could be made more readable by using BTF later: [root@arch-fb-vm1 ~]# ss --bpf-map-id 14 --bpf-map-id 13 -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:PortProcess ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] [root@arch-fb-vm1 ~]# ~/devshare/github/iproute2/misc/ss --bpf-maps -t6an 'dst [::1]:8989' State Recv-Q Send-Q Local Address:Port Peer Address:Port Process ESTAB 0 0 [::1]:51072 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] ESTAB 0 0 [::1]:51070 [::1]:8989 bpf_map_id:14 value:[ 3feb ] bpf_map_id:13 value:[ 3f ] bpf_map_id:12 value:[ 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000... total:65407 ] Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200225230427.1976129-1-kafai@fb.com
2020-02-26 07:04:27 +08:00
struct inet_diag_dump_data *cb_data = cb->data;
bpf_sk_storage_diag_free(cb_data->bpf_stg_diag);
kfree(cb->data);
return 0;
}
static int inet_diag_type2proto(int type)
{
switch (type) {
case TCPDIAG_GETSOCK:
return IPPROTO_TCP;
case DCCPDIAG_GETSOCK:
return IPPROTO_DCCP;
default:
return 0;
}
}
static int inet_diag_dump_compat(struct sk_buff *skb,
struct netlink_callback *cb)
{
struct inet_diag_req *rc = nlmsg_data(cb->nlh);
struct inet_diag_req_v2 req;
req.sdiag_family = AF_UNSPEC; /* compatibility */
req.sdiag_protocol = inet_diag_type2proto(cb->nlh->nlmsg_type);
req.idiag_ext = rc->idiag_ext;
req.idiag_states = rc->idiag_states;
req.id = rc->id;
return __inet_diag_dump(skb, cb, &req);
}
static int inet_diag_get_exact_compat(struct sk_buff *in_skb,
const struct nlmsghdr *nlh)
{
struct inet_diag_req *rc = nlmsg_data(nlh);
struct inet_diag_req_v2 req;
req.sdiag_family = rc->idiag_family;
req.sdiag_protocol = inet_diag_type2proto(nlh->nlmsg_type);
req.idiag_ext = rc->idiag_ext;
req.idiag_states = rc->idiag_states;
req.id = rc->id;
return inet_diag_cmd_exact(SOCK_DIAG_BY_FAMILY, in_skb, nlh,
sizeof(struct inet_diag_req), &req);
}
static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh)
{
int hdrlen = sizeof(struct inet_diag_req);
struct net *net = sock_net(skb->sk);
if (nlh->nlmsg_type >= INET_DIAG_GETSOCK_MAX ||
nlmsg_len(nlh) < hdrlen)
return -EINVAL;
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.start = inet_diag_dump_start_compat,
.done = inet_diag_dump_done,
.dump = inet_diag_dump_compat,
};
return netlink_dump_start(net->diag_nlsk, skb, nlh, &c);
}
return inet_diag_get_exact_compat(skb, nlh);
}
static int inet_diag_handler_cmd(struct sk_buff *skb, struct nlmsghdr *h)
{
int hdrlen = sizeof(struct inet_diag_req_v2);
struct net *net = sock_net(skb->sk);
if (nlmsg_len(h) < hdrlen)
return -EINVAL;
if (h->nlmsg_type == SOCK_DIAG_BY_FAMILY &&
h->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.start = inet_diag_dump_start,
.done = inet_diag_dump_done,
.dump = inet_diag_dump,
};
return netlink_dump_start(net->diag_nlsk, skb, h, &c);
}
return inet_diag_cmd_exact(h->nlmsg_type, skb, h, hdrlen,
nlmsg_data(h));
}
static
int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk)
{
const struct inet_diag_handler *handler;
struct nlmsghdr *nlh;
struct nlattr *attr;
struct inet_diag_msg *r;
void *info = NULL;
int err = 0;
nlh = nlmsg_put(skb, 0, 0, SOCK_DIAG_BY_FAMILY, sizeof(*r), 0);
if (!nlh)
return -ENOMEM;
r = nlmsg_data(nlh);
memset(r, 0, sizeof(*r));
inet_diag_msg_common_fill(r, sk);
if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_STREAM)
r->id.idiag_sport = inet_sk(sk)->inet_sport;
r->idiag_state = sk->sk_state;
if ((err = nla_put_u8(skb, INET_DIAG_PROTOCOL, sk->sk_protocol))) {
nlmsg_cancel(skb, nlh);
return err;
}
handler = inet_diag_lock_handler(sk->sk_protocol);
if (IS_ERR(handler)) {
inet_diag_unlock_handler(handler);
nlmsg_cancel(skb, nlh);
return PTR_ERR(handler);
}
attr = handler->idiag_info_size
? nla_reserve_64bit(skb, INET_DIAG_INFO,
handler->idiag_info_size,
INET_DIAG_PAD)
: NULL;
if (attr)
info = nla_data(attr);
handler->idiag_get_info(sk, r, info);
inet_diag_unlock_handler(handler);
nlmsg_end(skb, nlh);
return 0;
}
static const struct sock_diag_handler inet_diag_handler = {
.family = AF_INET,
.dump = inet_diag_handler_cmd,
.get_info = inet_diag_handler_get_info,
.destroy = inet_diag_handler_cmd,
};
static const struct sock_diag_handler inet6_diag_handler = {
.family = AF_INET6,
.dump = inet_diag_handler_cmd,
.get_info = inet_diag_handler_get_info,
.destroy = inet_diag_handler_cmd,
};
int inet_diag_register(const struct inet_diag_handler *h)
{
const __u16 type = h->idiag_type;
int err = -EINVAL;
if (type >= IPPROTO_MAX)
goto out;
mutex_lock(&inet_diag_table_mutex);
err = -EEXIST;
if (!inet_diag_table[type]) {
inet_diag_table[type] = h;
err = 0;
}
mutex_unlock(&inet_diag_table_mutex);
out:
return err;
}
EXPORT_SYMBOL_GPL(inet_diag_register);
void inet_diag_unregister(const struct inet_diag_handler *h)
{
const __u16 type = h->idiag_type;
if (type >= IPPROTO_MAX)
return;
mutex_lock(&inet_diag_table_mutex);
inet_diag_table[type] = NULL;
mutex_unlock(&inet_diag_table_mutex);
}
EXPORT_SYMBOL_GPL(inet_diag_unregister);
static int __init inet_diag_init(void)
{
const int inet_diag_table_size = (IPPROTO_MAX *
sizeof(struct inet_diag_handler *));
int err = -ENOMEM;
inet_diag_table = kzalloc(inet_diag_table_size, GFP_KERNEL);
if (!inet_diag_table)
goto out;
err = sock_diag_register(&inet_diag_handler);
if (err)
goto out_free_nl;
err = sock_diag_register(&inet6_diag_handler);
if (err)
goto out_free_inet;
sock_diag_register_inet_compat(inet_diag_rcv_msg_compat);
out:
return err;
out_free_inet:
sock_diag_unregister(&inet_diag_handler);
out_free_nl:
kfree(inet_diag_table);
goto out;
}
static void __exit inet_diag_exit(void)
{
sock_diag_unregister(&inet6_diag_handler);
sock_diag_unregister(&inet_diag_handler);
sock_diag_unregister_inet_compat(inet_diag_rcv_msg_compat);
kfree(inet_diag_table);
}
module_init(inet_diag_init);
module_exit(inet_diag_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2 /* AF_INET */);
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10 /* AF_INET6 */);