OpenCloudOS-Kernel/net/sctp/diag.c

544 lines
14 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* SCTP kernel implementation
* (C) Copyright Red Hat Inc. 2017
*
* This file is part of the SCTP kernel implementation
*
* These functions implement sctp diag support.
*
* Please send any bug reports or fixes you make to the
* email addresched(es):
* lksctp developers <linux-sctp@vger.kernel.org>
*
* Written or modified by:
* Xin Long <lucien.xin@gmail.com>
*/
#include <linux/module.h>
#include <linux/inet_diag.h>
#include <linux/sock_diag.h>
#include <net/sctp/sctp.h>
static void sctp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
void *info);
/* define some functions to make asoc/ep fill look clean */
static void inet_diag_msg_sctpasoc_fill(struct inet_diag_msg *r,
struct sock *sk,
struct sctp_association *asoc)
{
union sctp_addr laddr, paddr;
struct dst_entry *dst;
struct timer_list *t3_rtx = &asoc->peer.primary_path->T3_rtx_timer;
laddr = list_entry(asoc->base.bind_addr.address_list.next,
struct sctp_sockaddr_entry, list)->a;
paddr = asoc->peer.primary_path->ipaddr;
dst = asoc->peer.primary_path->dst;
r->idiag_family = sk->sk_family;
r->id.idiag_sport = htons(asoc->base.bind_addr.port);
r->id.idiag_dport = htons(asoc->peer.port);
r->id.idiag_if = dst ? dst->dev->ifindex : 0;
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 = laddr.v6.sin6_addr;
*(struct in6_addr *)r->id.idiag_dst = paddr.v6.sin6_addr;
} 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] = laddr.v4.sin_addr.s_addr;
r->id.idiag_dst[0] = paddr.v4.sin_addr.s_addr;
}
r->idiag_state = asoc->state;
if (timer_pending(t3_rtx)) {
r->idiag_timer = SCTP_EVENT_TIMEOUT_T3_RTX;
r->idiag_retrans = asoc->rtx_data_chunks;
r->idiag_expires = jiffies_to_msecs(t3_rtx->expires - jiffies);
} else {
r->idiag_timer = 0;
r->idiag_retrans = 0;
r->idiag_expires = 0;
}
}
static int inet_diag_msg_sctpladdrs_fill(struct sk_buff *skb,
struct list_head *address_list)
{
struct sctp_sockaddr_entry *laddr;
int addrlen = sizeof(struct sockaddr_storage);
int addrcnt = 0;
struct nlattr *attr;
void *info = NULL;
list_for_each_entry_rcu(laddr, address_list, list)
addrcnt++;
attr = nla_reserve(skb, INET_DIAG_LOCALS, addrlen * addrcnt);
if (!attr)
return -EMSGSIZE;
info = nla_data(attr);
list_for_each_entry_rcu(laddr, address_list, list) {
sctp: Avoid out-of-bounds reads from address storage inet_diag_msg_sctp{,l}addr_fill() and sctp_get_sctp_info() copy sizeof(sockaddr_storage) bytes to fill in sockaddr structs used to export diagnostic information to userspace. However, the memory allocated to store sockaddr information is smaller than that and depends on the address family, so we leak up to 100 uninitialized bytes to userspace. Just use the size of the source structs instead, in all the three cases this is what userspace expects. Zero out the remaining memory. Unused bytes (i.e. when IPv4 addresses are used) in source structs sctp_sockaddr_entry and sctp_transport are already cleared by sctp_add_bind_addr() and sctp_transport_new(), respectively. Noticed while testing KASAN-enabled kernel with 'ss': [ 2326.885243] BUG: KASAN: slab-out-of-bounds in inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag] at addr ffff881be8779800 [ 2326.896800] Read of size 128 by task ss/9527 [ 2326.901564] CPU: 0 PID: 9527 Comm: ss Not tainted 4.11.0-22.el7a.x86_64 #1 [ 2326.909236] Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.4.3 01/17/2017 [ 2326.917585] Call Trace: [ 2326.920312] dump_stack+0x63/0x8d [ 2326.924014] kasan_object_err+0x21/0x70 [ 2326.928295] kasan_report+0x288/0x540 [ 2326.932380] ? inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag] [ 2326.938500] ? skb_put+0x8b/0xd0 [ 2326.942098] ? memset+0x31/0x40 [ 2326.945599] check_memory_region+0x13c/0x1a0 [ 2326.950362] memcpy+0x23/0x50 [ 2326.953669] inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag] [ 2326.959596] ? inet_diag_msg_sctpasoc_fill+0x460/0x460 [sctp_diag] [ 2326.966495] ? __lock_sock+0x102/0x150 [ 2326.970671] ? sock_def_wakeup+0x60/0x60 [ 2326.975048] ? remove_wait_queue+0xc0/0xc0 [ 2326.979619] sctp_diag_dump+0x44a/0x760 [sctp_diag] [ 2326.985063] ? sctp_ep_dump+0x280/0x280 [sctp_diag] [ 2326.990504] ? memset+0x31/0x40 [ 2326.994007] ? mutex_lock+0x12/0x40 [ 2326.997900] __inet_diag_dump+0x57/0xb0 [inet_diag] [ 2327.003340] ? __sys_sendmsg+0x150/0x150 [ 2327.007715] inet_diag_dump+0x4d/0x80 [inet_diag] [ 2327.012979] netlink_dump+0x1e6/0x490 [ 2327.017064] __netlink_dump_start+0x28e/0x2c0 [ 2327.021924] inet_diag_handler_cmd+0x189/0x1a0 [inet_diag] [ 2327.028045] ? inet_diag_rcv_msg_compat+0x1b0/0x1b0 [inet_diag] [ 2327.034651] ? inet_diag_dump_compat+0x190/0x190 [inet_diag] [ 2327.040965] ? __netlink_lookup+0x1b9/0x260 [ 2327.045631] sock_diag_rcv_msg+0x18b/0x1e0 [ 2327.050199] netlink_rcv_skb+0x14b/0x180 [ 2327.054574] ? sock_diag_bind+0x60/0x60 [ 2327.058850] sock_diag_rcv+0x28/0x40 [ 2327.062837] netlink_unicast+0x2e7/0x3b0 [ 2327.067212] ? netlink_attachskb+0x330/0x330 [ 2327.071975] ? kasan_check_write+0x14/0x20 [ 2327.076544] netlink_sendmsg+0x5be/0x730 [ 2327.080918] ? netlink_unicast+0x3b0/0x3b0 [ 2327.085486] ? kasan_check_write+0x14/0x20 [ 2327.090057] ? selinux_socket_sendmsg+0x24/0x30 [ 2327.095109] ? netlink_unicast+0x3b0/0x3b0 [ 2327.099678] sock_sendmsg+0x74/0x80 [ 2327.103567] ___sys_sendmsg+0x520/0x530 [ 2327.107844] ? __get_locked_pte+0x178/0x200 [ 2327.112510] ? copy_msghdr_from_user+0x270/0x270 [ 2327.117660] ? vm_insert_page+0x360/0x360 [ 2327.122133] ? vm_insert_pfn_prot+0xb4/0x150 [ 2327.126895] ? vm_insert_pfn+0x32/0x40 [ 2327.131077] ? vvar_fault+0x71/0xd0 [ 2327.134968] ? special_mapping_fault+0x69/0x110 [ 2327.140022] ? __do_fault+0x42/0x120 [ 2327.144008] ? __handle_mm_fault+0x1062/0x17a0 [ 2327.148965] ? __fget_light+0xa7/0xc0 [ 2327.153049] __sys_sendmsg+0xcb/0x150 [ 2327.157133] ? __sys_sendmsg+0xcb/0x150 [ 2327.161409] ? SyS_shutdown+0x140/0x140 [ 2327.165688] ? exit_to_usermode_loop+0xd0/0xd0 [ 2327.170646] ? __do_page_fault+0x55d/0x620 [ 2327.175216] ? __sys_sendmsg+0x150/0x150 [ 2327.179591] SyS_sendmsg+0x12/0x20 [ 2327.183384] do_syscall_64+0xe3/0x230 [ 2327.187471] entry_SYSCALL64_slow_path+0x25/0x25 [ 2327.192622] RIP: 0033:0x7f41d18fa3b0 [ 2327.196608] RSP: 002b:00007ffc3b731218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 2327.205055] RAX: ffffffffffffffda RBX: 00007ffc3b731380 RCX: 00007f41d18fa3b0 [ 2327.213017] RDX: 0000000000000000 RSI: 00007ffc3b731340 RDI: 0000000000000003 [ 2327.220978] RBP: 0000000000000002 R08: 0000000000000004 R09: 0000000000000040 [ 2327.228939] R10: 00007ffc3b730f30 R11: 0000000000000246 R12: 0000000000000003 [ 2327.236901] R13: 00007ffc3b731340 R14: 00007ffc3b7313d0 R15: 0000000000000084 [ 2327.244865] Object at ffff881be87797e0, in cache kmalloc-64 size: 64 [ 2327.251953] Allocated: [ 2327.254581] PID = 9484 [ 2327.257215] save_stack_trace+0x1b/0x20 [ 2327.261485] save_stack+0x46/0xd0 [ 2327.265179] kasan_kmalloc+0xad/0xe0 [ 2327.269165] kmem_cache_alloc_trace+0xe6/0x1d0 [ 2327.274138] sctp_add_bind_addr+0x58/0x180 [sctp] [ 2327.279400] sctp_do_bind+0x208/0x310 [sctp] [ 2327.284176] sctp_bind+0x61/0xa0 [sctp] [ 2327.288455] inet_bind+0x5f/0x3a0 [ 2327.292151] SYSC_bind+0x1a4/0x1e0 [ 2327.295944] SyS_bind+0xe/0x10 [ 2327.299349] do_syscall_64+0xe3/0x230 [ 2327.303433] return_from_SYSCALL_64+0x0/0x6a [ 2327.308194] Freed: [ 2327.310434] PID = 4131 [ 2327.313065] save_stack_trace+0x1b/0x20 [ 2327.317344] save_stack+0x46/0xd0 [ 2327.321040] kasan_slab_free+0x73/0xc0 [ 2327.325220] kfree+0x96/0x1a0 [ 2327.328530] dynamic_kobj_release+0x15/0x40 [ 2327.333195] kobject_release+0x99/0x1e0 [ 2327.337472] kobject_put+0x38/0x70 [ 2327.341266] free_notes_attrs+0x66/0x80 [ 2327.345545] mod_sysfs_teardown+0x1a5/0x270 [ 2327.350211] free_module+0x20/0x2a0 [ 2327.354099] SyS_delete_module+0x2cb/0x2f0 [ 2327.358667] do_syscall_64+0xe3/0x230 [ 2327.362750] return_from_SYSCALL_64+0x0/0x6a [ 2327.367510] Memory state around the buggy address: [ 2327.372855] ffff881be8779700: fc fc fc fc 00 00 00 00 00 00 00 00 fc fc fc fc [ 2327.380914] ffff881be8779780: fb fb fb fb fb fb fb fb fc fc fc fc 00 00 00 00 [ 2327.388972] >ffff881be8779800: 00 00 00 00 fc fc fc fc fb fb fb fb fb fb fb fb [ 2327.397031] ^ [ 2327.401792] ffff881be8779880: fc fc fc fc fb fb fb fb fb fb fb fb fc fc fc fc [ 2327.409850] ffff881be8779900: 00 00 00 00 00 04 fc fc fc fc fc fc 00 00 00 00 [ 2327.417907] ================================================================== This fixes CVE-2017-7558. References: https://bugzilla.redhat.com/show_bug.cgi?id=1480266 Fixes: 8f840e47f190 ("sctp: add the sctp_diag.c file") Cc: Xin Long <lucien.xin@gmail.com> Cc: Vlad Yasevich <vyasevich@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Reviewed-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-23 19:27:13 +08:00
memcpy(info, &laddr->a, sizeof(laddr->a));
memset(info + sizeof(laddr->a), 0, addrlen - sizeof(laddr->a));
info += addrlen;
}
return 0;
}
static int inet_diag_msg_sctpaddrs_fill(struct sk_buff *skb,
struct sctp_association *asoc)
{
int addrlen = sizeof(struct sockaddr_storage);
struct sctp_transport *from;
struct nlattr *attr;
void *info = NULL;
attr = nla_reserve(skb, INET_DIAG_PEERS,
addrlen * asoc->peer.transport_count);
if (!attr)
return -EMSGSIZE;
info = nla_data(attr);
list_for_each_entry(from, &asoc->peer.transport_addr_list,
transports) {
sctp: Avoid out-of-bounds reads from address storage inet_diag_msg_sctp{,l}addr_fill() and sctp_get_sctp_info() copy sizeof(sockaddr_storage) bytes to fill in sockaddr structs used to export diagnostic information to userspace. However, the memory allocated to store sockaddr information is smaller than that and depends on the address family, so we leak up to 100 uninitialized bytes to userspace. Just use the size of the source structs instead, in all the three cases this is what userspace expects. Zero out the remaining memory. Unused bytes (i.e. when IPv4 addresses are used) in source structs sctp_sockaddr_entry and sctp_transport are already cleared by sctp_add_bind_addr() and sctp_transport_new(), respectively. Noticed while testing KASAN-enabled kernel with 'ss': [ 2326.885243] BUG: KASAN: slab-out-of-bounds in inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag] at addr ffff881be8779800 [ 2326.896800] Read of size 128 by task ss/9527 [ 2326.901564] CPU: 0 PID: 9527 Comm: ss Not tainted 4.11.0-22.el7a.x86_64 #1 [ 2326.909236] Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.4.3 01/17/2017 [ 2326.917585] Call Trace: [ 2326.920312] dump_stack+0x63/0x8d [ 2326.924014] kasan_object_err+0x21/0x70 [ 2326.928295] kasan_report+0x288/0x540 [ 2326.932380] ? inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag] [ 2326.938500] ? skb_put+0x8b/0xd0 [ 2326.942098] ? memset+0x31/0x40 [ 2326.945599] check_memory_region+0x13c/0x1a0 [ 2326.950362] memcpy+0x23/0x50 [ 2326.953669] inet_sctp_diag_fill+0x42c/0x6c0 [sctp_diag] [ 2326.959596] ? inet_diag_msg_sctpasoc_fill+0x460/0x460 [sctp_diag] [ 2326.966495] ? __lock_sock+0x102/0x150 [ 2326.970671] ? sock_def_wakeup+0x60/0x60 [ 2326.975048] ? remove_wait_queue+0xc0/0xc0 [ 2326.979619] sctp_diag_dump+0x44a/0x760 [sctp_diag] [ 2326.985063] ? sctp_ep_dump+0x280/0x280 [sctp_diag] [ 2326.990504] ? memset+0x31/0x40 [ 2326.994007] ? mutex_lock+0x12/0x40 [ 2326.997900] __inet_diag_dump+0x57/0xb0 [inet_diag] [ 2327.003340] ? __sys_sendmsg+0x150/0x150 [ 2327.007715] inet_diag_dump+0x4d/0x80 [inet_diag] [ 2327.012979] netlink_dump+0x1e6/0x490 [ 2327.017064] __netlink_dump_start+0x28e/0x2c0 [ 2327.021924] inet_diag_handler_cmd+0x189/0x1a0 [inet_diag] [ 2327.028045] ? inet_diag_rcv_msg_compat+0x1b0/0x1b0 [inet_diag] [ 2327.034651] ? inet_diag_dump_compat+0x190/0x190 [inet_diag] [ 2327.040965] ? __netlink_lookup+0x1b9/0x260 [ 2327.045631] sock_diag_rcv_msg+0x18b/0x1e0 [ 2327.050199] netlink_rcv_skb+0x14b/0x180 [ 2327.054574] ? sock_diag_bind+0x60/0x60 [ 2327.058850] sock_diag_rcv+0x28/0x40 [ 2327.062837] netlink_unicast+0x2e7/0x3b0 [ 2327.067212] ? netlink_attachskb+0x330/0x330 [ 2327.071975] ? kasan_check_write+0x14/0x20 [ 2327.076544] netlink_sendmsg+0x5be/0x730 [ 2327.080918] ? netlink_unicast+0x3b0/0x3b0 [ 2327.085486] ? kasan_check_write+0x14/0x20 [ 2327.090057] ? selinux_socket_sendmsg+0x24/0x30 [ 2327.095109] ? netlink_unicast+0x3b0/0x3b0 [ 2327.099678] sock_sendmsg+0x74/0x80 [ 2327.103567] ___sys_sendmsg+0x520/0x530 [ 2327.107844] ? __get_locked_pte+0x178/0x200 [ 2327.112510] ? copy_msghdr_from_user+0x270/0x270 [ 2327.117660] ? vm_insert_page+0x360/0x360 [ 2327.122133] ? vm_insert_pfn_prot+0xb4/0x150 [ 2327.126895] ? vm_insert_pfn+0x32/0x40 [ 2327.131077] ? vvar_fault+0x71/0xd0 [ 2327.134968] ? special_mapping_fault+0x69/0x110 [ 2327.140022] ? __do_fault+0x42/0x120 [ 2327.144008] ? __handle_mm_fault+0x1062/0x17a0 [ 2327.148965] ? __fget_light+0xa7/0xc0 [ 2327.153049] __sys_sendmsg+0xcb/0x150 [ 2327.157133] ? __sys_sendmsg+0xcb/0x150 [ 2327.161409] ? SyS_shutdown+0x140/0x140 [ 2327.165688] ? exit_to_usermode_loop+0xd0/0xd0 [ 2327.170646] ? __do_page_fault+0x55d/0x620 [ 2327.175216] ? __sys_sendmsg+0x150/0x150 [ 2327.179591] SyS_sendmsg+0x12/0x20 [ 2327.183384] do_syscall_64+0xe3/0x230 [ 2327.187471] entry_SYSCALL64_slow_path+0x25/0x25 [ 2327.192622] RIP: 0033:0x7f41d18fa3b0 [ 2327.196608] RSP: 002b:00007ffc3b731218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 2327.205055] RAX: ffffffffffffffda RBX: 00007ffc3b731380 RCX: 00007f41d18fa3b0 [ 2327.213017] RDX: 0000000000000000 RSI: 00007ffc3b731340 RDI: 0000000000000003 [ 2327.220978] RBP: 0000000000000002 R08: 0000000000000004 R09: 0000000000000040 [ 2327.228939] R10: 00007ffc3b730f30 R11: 0000000000000246 R12: 0000000000000003 [ 2327.236901] R13: 00007ffc3b731340 R14: 00007ffc3b7313d0 R15: 0000000000000084 [ 2327.244865] Object at ffff881be87797e0, in cache kmalloc-64 size: 64 [ 2327.251953] Allocated: [ 2327.254581] PID = 9484 [ 2327.257215] save_stack_trace+0x1b/0x20 [ 2327.261485] save_stack+0x46/0xd0 [ 2327.265179] kasan_kmalloc+0xad/0xe0 [ 2327.269165] kmem_cache_alloc_trace+0xe6/0x1d0 [ 2327.274138] sctp_add_bind_addr+0x58/0x180 [sctp] [ 2327.279400] sctp_do_bind+0x208/0x310 [sctp] [ 2327.284176] sctp_bind+0x61/0xa0 [sctp] [ 2327.288455] inet_bind+0x5f/0x3a0 [ 2327.292151] SYSC_bind+0x1a4/0x1e0 [ 2327.295944] SyS_bind+0xe/0x10 [ 2327.299349] do_syscall_64+0xe3/0x230 [ 2327.303433] return_from_SYSCALL_64+0x0/0x6a [ 2327.308194] Freed: [ 2327.310434] PID = 4131 [ 2327.313065] save_stack_trace+0x1b/0x20 [ 2327.317344] save_stack+0x46/0xd0 [ 2327.321040] kasan_slab_free+0x73/0xc0 [ 2327.325220] kfree+0x96/0x1a0 [ 2327.328530] dynamic_kobj_release+0x15/0x40 [ 2327.333195] kobject_release+0x99/0x1e0 [ 2327.337472] kobject_put+0x38/0x70 [ 2327.341266] free_notes_attrs+0x66/0x80 [ 2327.345545] mod_sysfs_teardown+0x1a5/0x270 [ 2327.350211] free_module+0x20/0x2a0 [ 2327.354099] SyS_delete_module+0x2cb/0x2f0 [ 2327.358667] do_syscall_64+0xe3/0x230 [ 2327.362750] return_from_SYSCALL_64+0x0/0x6a [ 2327.367510] Memory state around the buggy address: [ 2327.372855] ffff881be8779700: fc fc fc fc 00 00 00 00 00 00 00 00 fc fc fc fc [ 2327.380914] ffff881be8779780: fb fb fb fb fb fb fb fb fc fc fc fc 00 00 00 00 [ 2327.388972] >ffff881be8779800: 00 00 00 00 fc fc fc fc fb fb fb fb fb fb fb fb [ 2327.397031] ^ [ 2327.401792] ffff881be8779880: fc fc fc fc fb fb fb fb fb fb fb fb fc fc fc fc [ 2327.409850] ffff881be8779900: 00 00 00 00 00 04 fc fc fc fc fc fc 00 00 00 00 [ 2327.417907] ================================================================== This fixes CVE-2017-7558. References: https://bugzilla.redhat.com/show_bug.cgi?id=1480266 Fixes: 8f840e47f190 ("sctp: add the sctp_diag.c file") Cc: Xin Long <lucien.xin@gmail.com> Cc: Vlad Yasevich <vyasevich@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Stefano Brivio <sbrivio@redhat.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Reviewed-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-23 19:27:13 +08:00
memcpy(info, &from->ipaddr, sizeof(from->ipaddr));
memset(info + sizeof(from->ipaddr), 0,
addrlen - sizeof(from->ipaddr));
info += addrlen;
}
return 0;
}
/* sctp asoc/ep fill*/
static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc,
struct sk_buff *skb,
const struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
int portid, u32 seq, u16 nlmsg_flags,
const struct nlmsghdr *unlh,
bool net_admin)
{
struct sctp_endpoint *ep = sctp_sk(sk)->ep;
struct list_head *addr_list;
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
int ext = req->idiag_ext;
struct sctp_infox infox;
void *info = NULL;
nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r),
nlmsg_flags);
if (!nlh)
return -EMSGSIZE;
r = nlmsg_data(nlh);
BUG_ON(!sk_fullsock(sk));
if (asoc) {
inet_diag_msg_sctpasoc_fill(r, sk, asoc);
} else {
inet_diag_msg_common_fill(r, sk);
r->idiag_state = sk->sk_state;
r->idiag_timer = 0;
r->idiag_retrans = 0;
}
if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin))
goto errout;
if (ext & (1 << (INET_DIAG_SKMEMINFO - 1))) {
u32 mem[SK_MEMINFO_VARS];
int amt;
if (asoc && asoc->ep->sndbuf_policy)
amt = asoc->sndbuf_used;
else
amt = sk_wmem_alloc_get(sk);
mem[SK_MEMINFO_WMEM_ALLOC] = amt;
if (asoc && asoc->ep->rcvbuf_policy)
amt = atomic_read(&asoc->rmem_alloc);
else
amt = sk_rmem_alloc_get(sk);
mem[SK_MEMINFO_RMEM_ALLOC] = amt;
mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
net: silence KCSAN warnings about sk->sk_backlog.len reads sk->sk_backlog.len can be written by BH handlers, and read from process contexts in a lockless way. Note the write side should also use WRITE_ONCE() or a variant. We need some agreement about the best way to do this. syzbot reported : BUG: KCSAN: data-race in tcp_add_backlog / tcp_grow_window.isra.0 write to 0xffff88812665f32c of 4 bytes by interrupt on cpu 1: sk_add_backlog include/net/sock.h:934 [inline] tcp_add_backlog+0x4a0/0xcc0 net/ipv4/tcp_ipv4.c:1737 tcp_v4_rcv+0x1aba/0x1bf0 net/ipv4/tcp_ipv4.c:1925 ip_protocol_deliver_rcu+0x51/0x470 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5004 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5118 netif_receive_skb_internal+0x59/0x190 net/core/dev.c:5208 napi_skb_finish net/core/dev.c:5671 [inline] napi_gro_receive+0x28f/0x330 net/core/dev.c:5704 receive_buf+0x284/0x30b0 drivers/net/virtio_net.c:1061 virtnet_receive drivers/net/virtio_net.c:1323 [inline] virtnet_poll+0x436/0x7d0 drivers/net/virtio_net.c:1428 napi_poll net/core/dev.c:6352 [inline] net_rx_action+0x3ae/0xa50 net/core/dev.c:6418 read to 0xffff88812665f32c of 4 bytes by task 7292 on cpu 0: tcp_space include/net/tcp.h:1373 [inline] tcp_grow_window.isra.0+0x6b/0x480 net/ipv4/tcp_input.c:413 tcp_event_data_recv+0x68f/0x990 net/ipv4/tcp_input.c:717 tcp_rcv_established+0xbfe/0xf50 net/ipv4/tcp_input.c:5618 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1542 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2427 release_sock+0x61/0x160 net/core/sock.c:2943 tcp_recvmsg+0x63b/0x1a30 net/ipv4/tcp.c:2181 inet_recvmsg+0xbb/0x250 net/ipv4/af_inet.c:838 sock_recvmsg_nosec net/socket.c:871 [inline] sock_recvmsg net/socket.c:889 [inline] sock_recvmsg+0x92/0xb0 net/socket.c:885 sock_read_iter+0x15f/0x1e0 net/socket.c:967 call_read_iter include/linux/fs.h:1864 [inline] new_sync_read+0x389/0x4f0 fs/read_write.c:414 __vfs_read+0xb1/0xc0 fs/read_write.c:427 vfs_read fs/read_write.c:461 [inline] vfs_read+0x143/0x2c0 fs/read_write.c:446 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 7292 Comm: syz-fuzzer Not tainted 5.3.0+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
2019-10-10 06:41:03 +08:00
mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
if (nla_put(skb, INET_DIAG_SKMEMINFO, sizeof(mem), &mem) < 0)
goto errout;
}
if (ext & (1 << (INET_DIAG_INFO - 1))) {
struct nlattr *attr;
attr = nla_reserve_64bit(skb, INET_DIAG_INFO,
sizeof(struct sctp_info),
INET_DIAG_PAD);
if (!attr)
goto errout;
info = nla_data(attr);
}
infox.sctpinfo = (struct sctp_info *)info;
infox.asoc = asoc;
sctp_diag_get_info(sk, r, &infox);
addr_list = asoc ? &asoc->base.bind_addr.address_list
: &ep->base.bind_addr.address_list;
if (inet_diag_msg_sctpladdrs_fill(skb, addr_list))
goto errout;
if (asoc && (ext & (1 << (INET_DIAG_CONG - 1))))
if (nla_put_string(skb, INET_DIAG_CONG, "reno") < 0)
goto errout;
if (asoc && inet_diag_msg_sctpaddrs_fill(skb, asoc))
goto errout;
nlmsg_end(skb, nlh);
return 0;
errout:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
/* callback and param */
struct sctp_comm_param {
struct sk_buff *skb;
struct netlink_callback *cb;
const struct inet_diag_req_v2 *r;
const struct nlmsghdr *nlh;
bool net_admin;
};
static size_t inet_assoc_attr_size(struct sctp_association *asoc)
{
int addrlen = sizeof(struct sockaddr_storage);
int addrcnt = 0;
struct sctp_sockaddr_entry *laddr;
list_for_each_entry_rcu(laddr, &asoc->base.bind_addr.address_list,
list)
addrcnt++;
return nla_total_size(sizeof(struct sctp_info))
+ nla_total_size(1) /* INET_DIAG_SHUTDOWN */
+ nla_total_size(1) /* INET_DIAG_TOS */
+ nla_total_size(1) /* INET_DIAG_TCLASS */
+ nla_total_size(4) /* INET_DIAG_MARK */
+ nla_total_size(4) /* INET_DIAG_CLASS_ID */
+ nla_total_size(addrlen * asoc->peer.transport_count)
+ nla_total_size(addrlen * addrcnt)
+ nla_total_size(sizeof(struct inet_diag_meminfo))
+ nla_total_size(sizeof(struct inet_diag_msg))
+ 64;
}
static int sctp_tsp_dump_one(struct sctp_transport *tsp, void *p)
{
struct sctp_association *assoc = tsp->asoc;
struct sock *sk = tsp->asoc->base.sk;
struct sctp_comm_param *commp = p;
struct sk_buff *in_skb = commp->skb;
const struct inet_diag_req_v2 *req = commp->r;
const struct nlmsghdr *nlh = commp->nlh;
struct net *net = sock_net(in_skb->sk);
struct sk_buff *rep;
int err;
err = sock_diag_check_cookie(sk, req->id.idiag_cookie);
if (err)
goto out;
err = -ENOMEM;
rep = nlmsg_new(inet_assoc_attr_size(assoc), GFP_KERNEL);
if (!rep)
goto out;
lock_sock(sk);
if (sk != assoc->base.sk) {
release_sock(sk);
sk = assoc->base.sk;
lock_sock(sk);
}
err = inet_sctp_diag_fill(sk, assoc, rep, req,
sk_user_ns(NETLINK_CB(in_skb).sk),
NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0, nlh,
commp->net_admin);
release_sock(sk);
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
kfree_skb(rep);
goto out;
}
err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
MSG_DONTWAIT);
if (err > 0)
err = 0;
out:
return err;
}
2017-09-15 11:02:21 +08:00
static int sctp_sock_dump(struct sctp_transport *tsp, void *p)
{
2017-09-15 11:02:21 +08:00
struct sctp_endpoint *ep = tsp->asoc->ep;
struct sctp_comm_param *commp = p;
2017-09-15 11:02:21 +08:00
struct sock *sk = ep->base.sk;
struct sk_buff *skb = commp->skb;
struct netlink_callback *cb = commp->cb;
const struct inet_diag_req_v2 *r = commp->r;
struct sctp_association *assoc;
int err = 0;
lock_sock(sk);
2017-09-15 11:02:21 +08:00
list_for_each_entry(assoc, &ep->asocs, asocs) {
if (cb->args[4] < cb->args[1])
goto next;
if (r->id.idiag_sport != htons(assoc->base.bind_addr.port) &&
r->id.idiag_sport)
goto next;
if (r->id.idiag_dport != htons(assoc->peer.port) &&
r->id.idiag_dport)
goto next;
if (!cb->args[3] &&
inet_sctp_diag_fill(sk, NULL, skb, r,
sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
NLM_F_MULTI, cb->nlh,
commp->net_admin) < 0) {
err = 1;
goto release;
}
cb->args[3] = 1;
if (inet_sctp_diag_fill(sk, assoc, skb, r,
sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, 0, cb->nlh,
commp->net_admin) < 0) {
err = 1;
goto release;
}
next:
cb->args[4]++;
}
cb->args[1] = 0;
cb->args[3] = 0;
cb->args[4] = 0;
release:
release_sock(sk);
return err;
}
2017-09-15 11:02:21 +08:00
static int sctp_sock_filter(struct sctp_transport *tsp, void *p)
{
struct sctp_endpoint *ep = tsp->asoc->ep;
struct sctp_comm_param *commp = p;
struct sock *sk = ep->base.sk;
const struct inet_diag_req_v2 *r = commp->r;
struct sctp_association *assoc =
list_entry(ep->asocs.next, struct sctp_association, asocs);
/* find the ep only once through the transports by this condition */
if (tsp->asoc != assoc)
2017-09-15 11:02:21 +08:00
return 0;
if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family)
2017-09-15 11:02:21 +08:00
return 0;
return 1;
}
static int sctp_ep_dump(struct sctp_endpoint *ep, void *p)
{
struct sctp_comm_param *commp = p;
struct sock *sk = ep->base.sk;
struct sk_buff *skb = commp->skb;
struct netlink_callback *cb = commp->cb;
const struct inet_diag_req_v2 *r = commp->r;
struct net *net = sock_net(skb->sk);
struct inet_sock *inet = inet_sk(sk);
int err = 0;
if (!net_eq(sock_net(sk), net))
goto out;
if (cb->args[4] < cb->args[1])
goto next;
if (!(r->idiag_states & TCPF_LISTEN) && !list_empty(&ep->asocs))
goto next;
if (r->sdiag_family != AF_UNSPEC &&
sk->sk_family != r->sdiag_family)
goto next;
if (r->id.idiag_sport != inet->inet_sport &&
r->id.idiag_sport)
goto next;
if (r->id.idiag_dport != inet->inet_dport &&
r->id.idiag_dport)
goto next;
if (inet_sctp_diag_fill(sk, NULL, skb, r,
sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
cb->nlh, commp->net_admin) < 0) {
err = 2;
goto out;
}
next:
cb->args[4]++;
out:
return err;
}
/* define the functions for sctp_diag_handler*/
static void sctp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
void *info)
{
struct sctp_infox *infox = (struct sctp_infox *)info;
if (infox->asoc) {
r->idiag_rqueue = atomic_read(&infox->asoc->rmem_alloc);
r->idiag_wqueue = infox->asoc->sndbuf_used;
} else {
r->idiag_rqueue = READ_ONCE(sk->sk_ack_backlog);
r->idiag_wqueue = READ_ONCE(sk->sk_max_ack_backlog);
}
if (infox->sctpinfo)
sctp_get_sctp_info(sk, infox->asoc, infox->sctpinfo);
}
static int sctp_diag_dump_one(struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
const struct inet_diag_req_v2 *req)
{
struct net *net = sock_net(in_skb->sk);
union sctp_addr laddr, paddr;
struct sctp_comm_param commp = {
.skb = in_skb,
.r = req,
.nlh = nlh,
.net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN),
};
if (req->sdiag_family == AF_INET) {
laddr.v4.sin_port = req->id.idiag_sport;
laddr.v4.sin_addr.s_addr = req->id.idiag_src[0];
laddr.v4.sin_family = AF_INET;
paddr.v4.sin_port = req->id.idiag_dport;
paddr.v4.sin_addr.s_addr = req->id.idiag_dst[0];
paddr.v4.sin_family = AF_INET;
} else {
laddr.v6.sin6_port = req->id.idiag_sport;
memcpy(&laddr.v6.sin6_addr, req->id.idiag_src,
sizeof(laddr.v6.sin6_addr));
laddr.v6.sin6_family = AF_INET6;
paddr.v6.sin6_port = req->id.idiag_dport;
memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst,
sizeof(paddr.v6.sin6_addr));
paddr.v6.sin6_family = AF_INET6;
}
return sctp_transport_lookup_process(sctp_tsp_dump_one,
net, &laddr, &paddr, &commp);
}
static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
const struct inet_diag_req_v2 *r, struct nlattr *bc)
{
u32 idiag_states = r->idiag_states;
struct net *net = sock_net(skb->sk);
struct sctp_comm_param commp = {
.skb = skb,
.cb = cb,
.r = r,
.net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN),
};
int pos = cb->args[2];
/* eps hashtable dumps
* args:
* 0 : if it will traversal listen sock
* 1 : to record the sock pos of this time's traversal
* 4 : to work as a temporary variable to traversal list
*/
if (cb->args[0] == 0) {
if (!(idiag_states & TCPF_LISTEN))
goto skip;
if (sctp_for_each_endpoint(sctp_ep_dump, &commp))
goto done;
skip:
cb->args[0] = 1;
cb->args[1] = 0;
cb->args[4] = 0;
}
/* asocs by transport hashtable dump
* args:
* 1 : to record the assoc pos of this time's traversal
* 2 : to record the transport pos of this time's traversal
* 3 : to mark if we have dumped the ep info of the current asoc
* 4 : to work as a temporary variable to traversal list
* 5 : to save the sk we get from travelsing the tsp list.
*/
if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE)))
goto done;
2017-09-15 11:02:21 +08:00
sctp_for_each_transport(sctp_sock_filter, sctp_sock_dump,
net, &pos, &commp);
cb->args[2] = pos;
done:
cb->args[1] = cb->args[4];
cb->args[4] = 0;
}
static const struct inet_diag_handler sctp_diag_handler = {
.dump = sctp_diag_dump,
.dump_one = sctp_diag_dump_one,
.idiag_get_info = sctp_diag_get_info,
.idiag_type = IPPROTO_SCTP,
.idiag_info_size = sizeof(struct sctp_info),
};
static int __init sctp_diag_init(void)
{
return inet_diag_register(&sctp_diag_handler);
}
static void __exit sctp_diag_exit(void)
{
inet_diag_unregister(&sctp_diag_handler);
}
module_init(sctp_diag_init);
module_exit(sctp_diag_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-132);