OpenCloudOS-Kernel/net/sctp/diag.c

532 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);
}
}
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));
sctp: fix kernel-infoleak for SCTP sockets syzbot reported a kernel infoleak [1] of 4 bytes. After analysis, it turned out r->idiag_expires is not initialized if inet_sctp_diag_fill() calls inet_diag_msg_common_fill() Make sure to clear idiag_timer/idiag_retrans/idiag_expires and let inet_diag_msg_sctpasoc_fill() fill them again if needed. [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:154 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x6ef/0x25a0 lib/iov_iter.c:668 instrument_copy_to_user include/linux/instrumented.h:121 [inline] copyout lib/iov_iter.c:154 [inline] _copy_to_iter+0x6ef/0x25a0 lib/iov_iter.c:668 copy_to_iter include/linux/uio.h:162 [inline] simple_copy_to_iter+0xf3/0x140 net/core/datagram.c:519 __skb_datagram_iter+0x2d5/0x11b0 net/core/datagram.c:425 skb_copy_datagram_iter+0xdc/0x270 net/core/datagram.c:533 skb_copy_datagram_msg include/linux/skbuff.h:3696 [inline] netlink_recvmsg+0x669/0x1c80 net/netlink/af_netlink.c:1977 sock_recvmsg_nosec net/socket.c:948 [inline] sock_recvmsg net/socket.c:966 [inline] __sys_recvfrom+0x795/0xa10 net/socket.c:2097 __do_sys_recvfrom net/socket.c:2115 [inline] __se_sys_recvfrom net/socket.c:2111 [inline] __x64_sys_recvfrom+0x19d/0x210 net/socket.c:2111 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:737 [inline] slab_alloc_node mm/slub.c:3247 [inline] __kmalloc_node_track_caller+0xe0c/0x1510 mm/slub.c:4975 kmalloc_reserve net/core/skbuff.c:354 [inline] __alloc_skb+0x545/0xf90 net/core/skbuff.c:426 alloc_skb include/linux/skbuff.h:1158 [inline] netlink_dump+0x3e5/0x16c0 net/netlink/af_netlink.c:2248 __netlink_dump_start+0xcf8/0xe90 net/netlink/af_netlink.c:2373 netlink_dump_start include/linux/netlink.h:254 [inline] inet_diag_handler_cmd+0x2e7/0x400 net/ipv4/inet_diag.c:1341 sock_diag_rcv_msg+0x24a/0x620 netlink_rcv_skb+0x40c/0x7e0 net/netlink/af_netlink.c:2494 sock_diag_rcv+0x63/0x80 net/core/sock_diag.c:277 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x1093/0x1360 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x14d9/0x1720 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] sock_write_iter+0x594/0x690 net/socket.c:1061 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+0x645/0xe00 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 2508 are uninitialized Memory access of size 2508 starts at ffff888114f9b000 Data copied to user address 00007f7fe09ff2e0 CPU: 1 PID: 3478 Comm: syz-executor306 Not tainted 5.17.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 8f840e47f190 ("sctp: add the sctp_diag.c file") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Vlad Yasevich <vyasevich@gmail.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Reviewed-by: Xin Long <lucien.xin@gmail.com> Link: https://lore.kernel.org/r/20220310001145.297371-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-03-10 08:11:45 +08:00
r->idiag_timer = 0;
r->idiag_retrans = 0;
r->idiag_expires = 0;
if (asoc) {
inet_diag_msg_sctpasoc_fill(r, sk, asoc);
} else {
inet_diag_msg_common_fill(r, sk);
r->idiag_state = sk->sk_state;
}
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(addrlen * asoc->peer.transport_count)
+ nla_total_size(addrlen * addrcnt)
+ nla_total_size(sizeof(struct inet_diag_msg))
+ inet_diag_msg_attrs_size()
+ nla_total_size(sizeof(struct inet_diag_meminfo))
+ 64;
}
static int sctp_sock_dump_one(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
{
struct sctp_association *assoc = tsp->asoc;
struct sctp_comm_param *commp = p;
struct sock *sk = ep->base.sk;
const struct inet_diag_req_v2 *req = commp->r;
struct sk_buff *skb = commp->skb;
struct sk_buff *rep;
int err;
err = sock_diag_check_cookie(sk, req->id.idiag_cookie);
if (err)
return err;
rep = nlmsg_new(inet_assoc_attr_size(assoc), GFP_KERNEL);
if (!rep)
return -ENOMEM;
lock_sock(sk);
if (ep != assoc->ep) {
err = -EAGAIN;
goto out;
}
err = inet_sctp_diag_fill(sk, assoc, rep, req, sk_user_ns(NETLINK_CB(skb).sk),
NETLINK_CB(skb).portid, commp->nlh->nlmsg_seq, 0,
commp->nlh, commp->net_admin);
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
goto out;
}
release_sock(sk);
return nlmsg_unicast(sock_net(skb->sk)->diag_nlsk, rep, NETLINK_CB(skb).portid);
out:
release_sock(sk);
kfree_skb(rep);
return err;
}
sctp: use call_rcu to free endpoint This patch is to delay the endpoint free by calling call_rcu() to fix another use-after-free issue in sctp_sock_dump(): BUG: KASAN: use-after-free in __lock_acquire+0x36d9/0x4c20 Call Trace: __lock_acquire+0x36d9/0x4c20 kernel/locking/lockdep.c:3218 lock_acquire+0x1ed/0x520 kernel/locking/lockdep.c:3844 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline] _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168 spin_lock_bh include/linux/spinlock.h:334 [inline] __lock_sock+0x203/0x350 net/core/sock.c:2253 lock_sock_nested+0xfe/0x120 net/core/sock.c:2774 lock_sock include/net/sock.h:1492 [inline] sctp_sock_dump+0x122/0xb20 net/sctp/diag.c:324 sctp_for_each_transport+0x2b5/0x370 net/sctp/socket.c:5091 sctp_diag_dump+0x3ac/0x660 net/sctp/diag.c:527 __inet_diag_dump+0xa8/0x140 net/ipv4/inet_diag.c:1049 inet_diag_dump+0x9b/0x110 net/ipv4/inet_diag.c:1065 netlink_dump+0x606/0x1080 net/netlink/af_netlink.c:2244 __netlink_dump_start+0x59a/0x7c0 net/netlink/af_netlink.c:2352 netlink_dump_start include/linux/netlink.h:216 [inline] inet_diag_handler_cmd+0x2ce/0x3f0 net/ipv4/inet_diag.c:1170 __sock_diag_cmd net/core/sock_diag.c:232 [inline] sock_diag_rcv_msg+0x31d/0x410 net/core/sock_diag.c:263 netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2477 sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:274 This issue occurs when asoc is peeled off and the old sk is freed after getting it by asoc->base.sk and before calling lock_sock(sk). To prevent the sk free, as a holder of the sk, ep should be alive when calling lock_sock(). This patch uses call_rcu() and moves sock_put and ep free into sctp_endpoint_destroy_rcu(), so that it's safe to try to hold the ep under rcu_read_lock in sctp_transport_traverse_process(). If sctp_endpoint_hold() returns true, it means this ep is still alive and we have held it and can continue to dump it; If it returns false, it means this ep is dead and can be freed after rcu_read_unlock, and we should skip it. In sctp_sock_dump(), after locking the sk, if this ep is different from tsp->asoc->ep, it means during this dumping, this asoc was peeled off before calling lock_sock(), and the sk should be skipped; If this ep is the same with tsp->asoc->ep, it means no peeloff happens on this asoc, and due to lock_sock, no peeloff will happen either until release_sock. Note that delaying endpoint free won't delay the port release, as the port release happens in sctp_endpoint_destroy() before calling call_rcu(). Also, freeing endpoint by call_rcu() makes it safe to access the sk by asoc->base.sk in sctp_assocs_seq_show() and sctp_rcv(). Thanks Jones to bring this issue up. v1->v2: - improve the changelog. - add kfree(ep) into sctp_endpoint_destroy_rcu(), as Jakub noticed. Reported-by: syzbot+9276d76e83e3bcde6c99@syzkaller.appspotmail.com Reported-by: Lee Jones <lee.jones@linaro.org> Fixes: d25adbeb0cdb ("sctp: fix an use-after-free issue in sctp_sock_dump") Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-12-24 02:04:30 +08:00
static int sctp_sock_dump(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
{
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);
sctp: use call_rcu to free endpoint This patch is to delay the endpoint free by calling call_rcu() to fix another use-after-free issue in sctp_sock_dump(): BUG: KASAN: use-after-free in __lock_acquire+0x36d9/0x4c20 Call Trace: __lock_acquire+0x36d9/0x4c20 kernel/locking/lockdep.c:3218 lock_acquire+0x1ed/0x520 kernel/locking/lockdep.c:3844 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline] _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168 spin_lock_bh include/linux/spinlock.h:334 [inline] __lock_sock+0x203/0x350 net/core/sock.c:2253 lock_sock_nested+0xfe/0x120 net/core/sock.c:2774 lock_sock include/net/sock.h:1492 [inline] sctp_sock_dump+0x122/0xb20 net/sctp/diag.c:324 sctp_for_each_transport+0x2b5/0x370 net/sctp/socket.c:5091 sctp_diag_dump+0x3ac/0x660 net/sctp/diag.c:527 __inet_diag_dump+0xa8/0x140 net/ipv4/inet_diag.c:1049 inet_diag_dump+0x9b/0x110 net/ipv4/inet_diag.c:1065 netlink_dump+0x606/0x1080 net/netlink/af_netlink.c:2244 __netlink_dump_start+0x59a/0x7c0 net/netlink/af_netlink.c:2352 netlink_dump_start include/linux/netlink.h:216 [inline] inet_diag_handler_cmd+0x2ce/0x3f0 net/ipv4/inet_diag.c:1170 __sock_diag_cmd net/core/sock_diag.c:232 [inline] sock_diag_rcv_msg+0x31d/0x410 net/core/sock_diag.c:263 netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2477 sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:274 This issue occurs when asoc is peeled off and the old sk is freed after getting it by asoc->base.sk and before calling lock_sock(sk). To prevent the sk free, as a holder of the sk, ep should be alive when calling lock_sock(). This patch uses call_rcu() and moves sock_put and ep free into sctp_endpoint_destroy_rcu(), so that it's safe to try to hold the ep under rcu_read_lock in sctp_transport_traverse_process(). If sctp_endpoint_hold() returns true, it means this ep is still alive and we have held it and can continue to dump it; If it returns false, it means this ep is dead and can be freed after rcu_read_unlock, and we should skip it. In sctp_sock_dump(), after locking the sk, if this ep is different from tsp->asoc->ep, it means during this dumping, this asoc was peeled off before calling lock_sock(), and the sk should be skipped; If this ep is the same with tsp->asoc->ep, it means no peeloff happens on this asoc, and due to lock_sock, no peeloff will happen either until release_sock. Note that delaying endpoint free won't delay the port release, as the port release happens in sctp_endpoint_destroy() before calling call_rcu(). Also, freeing endpoint by call_rcu() makes it safe to access the sk by asoc->base.sk in sctp_assocs_seq_show() and sctp_rcv(). Thanks Jones to bring this issue up. v1->v2: - improve the changelog. - add kfree(ep) into sctp_endpoint_destroy_rcu(), as Jakub noticed. Reported-by: syzbot+9276d76e83e3bcde6c99@syzkaller.appspotmail.com Reported-by: Lee Jones <lee.jones@linaro.org> Fixes: d25adbeb0cdb ("sctp: fix an use-after-free issue in sctp_sock_dump") Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-12-24 02:04:30 +08:00
if (ep != tsp->asoc->ep)
goto release;
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;
}
sctp: use call_rcu to free endpoint This patch is to delay the endpoint free by calling call_rcu() to fix another use-after-free issue in sctp_sock_dump(): BUG: KASAN: use-after-free in __lock_acquire+0x36d9/0x4c20 Call Trace: __lock_acquire+0x36d9/0x4c20 kernel/locking/lockdep.c:3218 lock_acquire+0x1ed/0x520 kernel/locking/lockdep.c:3844 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline] _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168 spin_lock_bh include/linux/spinlock.h:334 [inline] __lock_sock+0x203/0x350 net/core/sock.c:2253 lock_sock_nested+0xfe/0x120 net/core/sock.c:2774 lock_sock include/net/sock.h:1492 [inline] sctp_sock_dump+0x122/0xb20 net/sctp/diag.c:324 sctp_for_each_transport+0x2b5/0x370 net/sctp/socket.c:5091 sctp_diag_dump+0x3ac/0x660 net/sctp/diag.c:527 __inet_diag_dump+0xa8/0x140 net/ipv4/inet_diag.c:1049 inet_diag_dump+0x9b/0x110 net/ipv4/inet_diag.c:1065 netlink_dump+0x606/0x1080 net/netlink/af_netlink.c:2244 __netlink_dump_start+0x59a/0x7c0 net/netlink/af_netlink.c:2352 netlink_dump_start include/linux/netlink.h:216 [inline] inet_diag_handler_cmd+0x2ce/0x3f0 net/ipv4/inet_diag.c:1170 __sock_diag_cmd net/core/sock_diag.c:232 [inline] sock_diag_rcv_msg+0x31d/0x410 net/core/sock_diag.c:263 netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2477 sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:274 This issue occurs when asoc is peeled off and the old sk is freed after getting it by asoc->base.sk and before calling lock_sock(sk). To prevent the sk free, as a holder of the sk, ep should be alive when calling lock_sock(). This patch uses call_rcu() and moves sock_put and ep free into sctp_endpoint_destroy_rcu(), so that it's safe to try to hold the ep under rcu_read_lock in sctp_transport_traverse_process(). If sctp_endpoint_hold() returns true, it means this ep is still alive and we have held it and can continue to dump it; If it returns false, it means this ep is dead and can be freed after rcu_read_unlock, and we should skip it. In sctp_sock_dump(), after locking the sk, if this ep is different from tsp->asoc->ep, it means during this dumping, this asoc was peeled off before calling lock_sock(), and the sk should be skipped; If this ep is the same with tsp->asoc->ep, it means no peeloff happens on this asoc, and due to lock_sock, no peeloff will happen either until release_sock. Note that delaying endpoint free won't delay the port release, as the port release happens in sctp_endpoint_destroy() before calling call_rcu(). Also, freeing endpoint by call_rcu() makes it safe to access the sk by asoc->base.sk in sctp_assocs_seq_show() and sctp_rcv(). Thanks Jones to bring this issue up. v1->v2: - improve the changelog. - add kfree(ep) into sctp_endpoint_destroy_rcu(), as Jakub noticed. Reported-by: syzbot+9276d76e83e3bcde6c99@syzkaller.appspotmail.com Reported-by: Lee Jones <lee.jones@linaro.org> Fixes: d25adbeb0cdb ("sctp: fix an use-after-free issue in sctp_sock_dump") Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-12-24 02:04:30 +08:00
static int sctp_sock_filter(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
{
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 netlink_callback *cb,
const struct inet_diag_req_v2 *req)
{
struct sk_buff *skb = cb->skb;
struct net *net = sock_net(skb->sk);
const struct nlmsghdr *nlh = cb->nlh;
union sctp_addr laddr, paddr;
struct sctp_comm_param commp = {
.skb = skb,
.r = req,
.nlh = nlh,
.net_admin = netlink_net_capable(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_sock_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)
{
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;
sctp: use call_rcu to free endpoint This patch is to delay the endpoint free by calling call_rcu() to fix another use-after-free issue in sctp_sock_dump(): BUG: KASAN: use-after-free in __lock_acquire+0x36d9/0x4c20 Call Trace: __lock_acquire+0x36d9/0x4c20 kernel/locking/lockdep.c:3218 lock_acquire+0x1ed/0x520 kernel/locking/lockdep.c:3844 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline] _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168 spin_lock_bh include/linux/spinlock.h:334 [inline] __lock_sock+0x203/0x350 net/core/sock.c:2253 lock_sock_nested+0xfe/0x120 net/core/sock.c:2774 lock_sock include/net/sock.h:1492 [inline] sctp_sock_dump+0x122/0xb20 net/sctp/diag.c:324 sctp_for_each_transport+0x2b5/0x370 net/sctp/socket.c:5091 sctp_diag_dump+0x3ac/0x660 net/sctp/diag.c:527 __inet_diag_dump+0xa8/0x140 net/ipv4/inet_diag.c:1049 inet_diag_dump+0x9b/0x110 net/ipv4/inet_diag.c:1065 netlink_dump+0x606/0x1080 net/netlink/af_netlink.c:2244 __netlink_dump_start+0x59a/0x7c0 net/netlink/af_netlink.c:2352 netlink_dump_start include/linux/netlink.h:216 [inline] inet_diag_handler_cmd+0x2ce/0x3f0 net/ipv4/inet_diag.c:1170 __sock_diag_cmd net/core/sock_diag.c:232 [inline] sock_diag_rcv_msg+0x31d/0x410 net/core/sock_diag.c:263 netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2477 sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:274 This issue occurs when asoc is peeled off and the old sk is freed after getting it by asoc->base.sk and before calling lock_sock(sk). To prevent the sk free, as a holder of the sk, ep should be alive when calling lock_sock(). This patch uses call_rcu() and moves sock_put and ep free into sctp_endpoint_destroy_rcu(), so that it's safe to try to hold the ep under rcu_read_lock in sctp_transport_traverse_process(). If sctp_endpoint_hold() returns true, it means this ep is still alive and we have held it and can continue to dump it; If it returns false, it means this ep is dead and can be freed after rcu_read_unlock, and we should skip it. In sctp_sock_dump(), after locking the sk, if this ep is different from tsp->asoc->ep, it means during this dumping, this asoc was peeled off before calling lock_sock(), and the sk should be skipped; If this ep is the same with tsp->asoc->ep, it means no peeloff happens on this asoc, and due to lock_sock, no peeloff will happen either until release_sock. Note that delaying endpoint free won't delay the port release, as the port release happens in sctp_endpoint_destroy() before calling call_rcu(). Also, freeing endpoint by call_rcu() makes it safe to access the sk by asoc->base.sk in sctp_assocs_seq_show() and sctp_rcv(). Thanks Jones to bring this issue up. v1->v2: - improve the changelog. - add kfree(ep) into sctp_endpoint_destroy_rcu(), as Jakub noticed. Reported-by: syzbot+9276d76e83e3bcde6c99@syzkaller.appspotmail.com Reported-by: Lee Jones <lee.jones@linaro.org> Fixes: d25adbeb0cdb ("sctp: fix an use-after-free issue in sctp_sock_dump") Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-12-24 02:04:30 +08:00
sctp_transport_traverse_process(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);