Revision 49054556289e8787501630b7c7a9d407da02e296 authored by Paolo Abeni on 29 September 2021, 09:59:17 UTC, committed by David S. Miller on 30 September 2021, 12:06:47 UTC
Syzkaller reported a false positive deadlock involving the nl socket lock and the subflow socket lock: MPTCP: kernel_bind error, err=-98 ============================================ WARNING: possible recursive locking detected 5.15.0-rc1-syzkaller #0 Not tainted -------------------------------------------- syz-executor998/6520 is trying to acquire lock: ffff8880795718a0 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738 but task is already holding lock: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline] ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(k-sk_lock-AF_INET); lock(k-sk_lock-AF_INET); *** DEADLOCK *** May be due to missing lock nesting notation 3 locks held by syz-executor998/6520: #0: ffffffff8d176c50 (cb_lock){++++}-{3:3}, at: genl_rcv+0x15/0x40 net/netlink/genetlink.c:802 #1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_lock net/netlink/genetlink.c:33 [inline] #1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_rcv_msg+0x3e0/0x580 net/netlink/genetlink.c:790 #2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline] #2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720 stack backtrace: CPU: 1 PID: 6520 Comm: syz-executor998 Not tainted 5.15.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_deadlock_bug kernel/locking/lockdep.c:2944 [inline] check_deadlock kernel/locking/lockdep.c:2987 [inline] validate_chain kernel/locking/lockdep.c:3776 [inline] __lock_acquire.cold+0x149/0x3ab kernel/locking/lockdep.c:5015 lock_acquire kernel/locking/lockdep.c:5625 [inline] lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5590 lock_sock_fast+0x36/0x100 net/core/sock.c:3229 mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738 inet_release+0x12e/0x280 net/ipv4/af_inet.c:431 __sock_release net/socket.c:649 [inline] sock_release+0x87/0x1b0 net/socket.c:677 mptcp_pm_nl_create_listen_socket+0x238/0x2c0 net/mptcp/pm_netlink.c:900 mptcp_nl_cmd_add_addr+0x359/0x930 net/mptcp/pm_netlink.c:1170 genl_family_rcv_msg_doit+0x228/0x320 net/netlink/genetlink.c:731 genl_family_rcv_msg net/netlink/genetlink.c:775 [inline] genl_rcv_msg+0x328/0x580 net/netlink/genetlink.c:792 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2504 genl_rcv+0x24/0x40 net/netlink/genetlink.c:803 netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1340 netlink_sendmsg+0x86d/0xdb0 net/netlink/af_netlink.c:1929 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 sock_no_sendpage+0x101/0x150 net/core/sock.c:2980 kernel_sendpage.part.0+0x1a0/0x340 net/socket.c:3504 kernel_sendpage net/socket.c:3501 [inline] sock_sendpage+0xe5/0x140 net/socket.c:1003 pipe_to_sendpage+0x2ad/0x380 fs/splice.c:364 splice_from_pipe_feed fs/splice.c:418 [inline] __splice_from_pipe+0x43e/0x8a0 fs/splice.c:562 splice_from_pipe fs/splice.c:597 [inline] generic_splice_sendpage+0xd4/0x140 fs/splice.c:746 do_splice_from fs/splice.c:767 [inline] direct_splice_actor+0x110/0x180 fs/splice.c:936 splice_direct_to_actor+0x34b/0x8c0 fs/splice.c:891 do_splice_direct+0x1b3/0x280 fs/splice.c:979 do_sendfile+0xae9/0x1240 fs/read_write.c:1249 __do_sys_sendfile64 fs/read_write.c:1314 [inline] __se_sys_sendfile64 fs/read_write.c:1300 [inline] __x64_sys_sendfile64+0x1cc/0x210 fs/read_write.c:1300 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f215cb69969 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 14 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc96bb3868 EFLAGS: 00000246 ORIG_RAX: 0000000000000028 RAX: ffffffffffffffda RBX: 00007f215cbad072 RCX: 00007f215cb69969 RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000005 RBP: 0000000000000000 R08: 00007ffc96bb3a08 R09: 00007ffc96bb3a08 R10: 0000000100000002 R11: 0000000000000246 R12: 00007ffc96bb387c R13: 431bde82d7b634db R14: 0000000000000000 R15: 0000000000000000 the problem originates from uncorrect lock annotation in the mptcp code and is only visible since commit 2dcb96bacce3 ("net: core: Correct the sock::sk_lock.owned lockdep annotations"), but is present since the port-based endpoint support initial implementation. This patch addresses the issue introducing a nested variant of lock_sock_fast() and using it in the relevant code path. Fixes: 1729cf186d8a ("mptcp: create the listening socket for new port") Fixes: 2dcb96bacce3 ("net: core: Correct the sock::sk_lock.owned lockdep annotations") Suggested-by: Thomas Gleixner <tglx@linutronix.de> Reported-and-tested-by: syzbot+1dd53f7a89b299d59eaf@syzkaller.appspotmail.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent d88fd1b
cpu_rmap.c
// SPDX-License-Identifier: GPL-2.0-only
/*
* cpu_rmap.c: CPU affinity reverse-map support
* Copyright 2011 Solarflare Communications Inc.
*/
#include <linux/cpu_rmap.h>
#include <linux/interrupt.h>
#include <linux/export.h>
/*
* These functions maintain a mapping from CPUs to some ordered set of
* objects with CPU affinities. This can be seen as a reverse-map of
* CPU affinity. However, we do not assume that the object affinities
* cover all CPUs in the system. For those CPUs not directly covered
* by object affinities, we attempt to find a nearest object based on
* CPU topology.
*/
/**
* alloc_cpu_rmap - allocate CPU affinity reverse-map
* @size: Number of objects to be mapped
* @flags: Allocation flags e.g. %GFP_KERNEL
*/
struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
{
struct cpu_rmap *rmap;
unsigned int cpu;
size_t obj_offset;
/* This is a silly number of objects, and we use u16 indices. */
if (size > 0xffff)
return NULL;
/* Offset of object pointer array from base structure */
obj_offset = ALIGN(offsetof(struct cpu_rmap, near[nr_cpu_ids]),
sizeof(void *));
rmap = kzalloc(obj_offset + size * sizeof(rmap->obj[0]), flags);
if (!rmap)
return NULL;
kref_init(&rmap->refcount);
rmap->obj = (void **)((char *)rmap + obj_offset);
/* Initially assign CPUs to objects on a rota, since we have
* no idea where the objects are. Use infinite distance, so
* any object with known distance is preferable. Include the
* CPUs that are not present/online, since we definitely want
* any newly-hotplugged CPUs to have some object assigned.
*/
for_each_possible_cpu(cpu) {
rmap->near[cpu].index = cpu % size;
rmap->near[cpu].dist = CPU_RMAP_DIST_INF;
}
rmap->size = size;
return rmap;
}
EXPORT_SYMBOL(alloc_cpu_rmap);
/**
* cpu_rmap_release - internal reclaiming helper called from kref_put
* @ref: kref to struct cpu_rmap
*/
static void cpu_rmap_release(struct kref *ref)
{
struct cpu_rmap *rmap = container_of(ref, struct cpu_rmap, refcount);
kfree(rmap);
}
/**
* cpu_rmap_get - internal helper to get new ref on a cpu_rmap
* @rmap: reverse-map allocated with alloc_cpu_rmap()
*/
static inline void cpu_rmap_get(struct cpu_rmap *rmap)
{
kref_get(&rmap->refcount);
}
/**
* cpu_rmap_put - release ref on a cpu_rmap
* @rmap: reverse-map allocated with alloc_cpu_rmap()
*/
int cpu_rmap_put(struct cpu_rmap *rmap)
{
return kref_put(&rmap->refcount, cpu_rmap_release);
}
EXPORT_SYMBOL(cpu_rmap_put);
/* Reevaluate nearest object for given CPU, comparing with the given
* neighbours at the given distance.
*/
static bool cpu_rmap_copy_neigh(struct cpu_rmap *rmap, unsigned int cpu,
const struct cpumask *mask, u16 dist)
{
int neigh;
for_each_cpu(neigh, mask) {
if (rmap->near[cpu].dist > dist &&
rmap->near[neigh].dist <= dist) {
rmap->near[cpu].index = rmap->near[neigh].index;
rmap->near[cpu].dist = dist;
return true;
}
}
return false;
}
#ifdef DEBUG
static void debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix)
{
unsigned index;
unsigned int cpu;
pr_info("cpu_rmap %p, %s:\n", rmap, prefix);
for_each_possible_cpu(cpu) {
index = rmap->near[cpu].index;
pr_info("cpu %d -> obj %u (distance %u)\n",
cpu, index, rmap->near[cpu].dist);
}
}
#else
static inline void
debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix)
{
}
#endif
/**
* cpu_rmap_add - add object to a rmap
* @rmap: CPU rmap allocated with alloc_cpu_rmap()
* @obj: Object to add to rmap
*
* Return index of object.
*/
int cpu_rmap_add(struct cpu_rmap *rmap, void *obj)
{
u16 index;
BUG_ON(rmap->used >= rmap->size);
index = rmap->used++;
rmap->obj[index] = obj;
return index;
}
EXPORT_SYMBOL(cpu_rmap_add);
/**
* cpu_rmap_update - update CPU rmap following a change of object affinity
* @rmap: CPU rmap to update
* @index: Index of object whose affinity changed
* @affinity: New CPU affinity of object
*/
int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,
const struct cpumask *affinity)
{
cpumask_var_t update_mask;
unsigned int cpu;
if (unlikely(!zalloc_cpumask_var(&update_mask, GFP_KERNEL)))
return -ENOMEM;
/* Invalidate distance for all CPUs for which this used to be
* the nearest object. Mark those CPUs for update.
*/
for_each_online_cpu(cpu) {
if (rmap->near[cpu].index == index) {
rmap->near[cpu].dist = CPU_RMAP_DIST_INF;
cpumask_set_cpu(cpu, update_mask);
}
}
debug_print_rmap(rmap, "after invalidating old distances");
/* Set distance to 0 for all CPUs in the new affinity mask.
* Mark all CPUs within their NUMA nodes for update.
*/
for_each_cpu(cpu, affinity) {
rmap->near[cpu].index = index;
rmap->near[cpu].dist = 0;
cpumask_or(update_mask, update_mask,
cpumask_of_node(cpu_to_node(cpu)));
}
debug_print_rmap(rmap, "after updating neighbours");
/* Update distances based on topology */
for_each_cpu(cpu, update_mask) {
if (cpu_rmap_copy_neigh(rmap, cpu,
topology_sibling_cpumask(cpu), 1))
continue;
if (cpu_rmap_copy_neigh(rmap, cpu,
topology_core_cpumask(cpu), 2))
continue;
if (cpu_rmap_copy_neigh(rmap, cpu,
cpumask_of_node(cpu_to_node(cpu)), 3))
continue;
/* We could continue into NUMA node distances, but for now
* we give up.
*/
}
debug_print_rmap(rmap, "after copying neighbours");
free_cpumask_var(update_mask);
return 0;
}
EXPORT_SYMBOL(cpu_rmap_update);
/* Glue between IRQ affinity notifiers and CPU rmaps */
struct irq_glue {
struct irq_affinity_notify notify;
struct cpu_rmap *rmap;
u16 index;
};
/**
* free_irq_cpu_rmap - free a CPU affinity reverse-map used for IRQs
* @rmap: Reverse-map allocated with alloc_irq_cpu_map(), or %NULL
*
* Must be called in process context, before freeing the IRQs.
*/
void free_irq_cpu_rmap(struct cpu_rmap *rmap)
{
struct irq_glue *glue;
u16 index;
if (!rmap)
return;
for (index = 0; index < rmap->used; index++) {
glue = rmap->obj[index];
irq_set_affinity_notifier(glue->notify.irq, NULL);
}
cpu_rmap_put(rmap);
}
EXPORT_SYMBOL(free_irq_cpu_rmap);
/**
* irq_cpu_rmap_notify - callback for IRQ subsystem when IRQ affinity updated
* @notify: struct irq_affinity_notify passed by irq/manage.c
* @mask: cpu mask for new SMP affinity
*
* This is executed in workqueue context.
*/
static void
irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
{
struct irq_glue *glue =
container_of(notify, struct irq_glue, notify);
int rc;
rc = cpu_rmap_update(glue->rmap, glue->index, mask);
if (rc)
pr_warn("irq_cpu_rmap_notify: update failed: %d\n", rc);
}
/**
* irq_cpu_rmap_release - reclaiming callback for IRQ subsystem
* @ref: kref to struct irq_affinity_notify passed by irq/manage.c
*/
static void irq_cpu_rmap_release(struct kref *ref)
{
struct irq_glue *glue =
container_of(ref, struct irq_glue, notify.kref);
cpu_rmap_put(glue->rmap);
kfree(glue);
}
/**
* irq_cpu_rmap_add - add an IRQ to a CPU affinity reverse-map
* @rmap: The reverse-map
* @irq: The IRQ number
*
* This adds an IRQ affinity notifier that will update the reverse-map
* automatically.
*
* Must be called in process context, after the IRQ is allocated but
* before it is bound with request_irq().
*/
int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq)
{
struct irq_glue *glue = kzalloc(sizeof(*glue), GFP_KERNEL);
int rc;
if (!glue)
return -ENOMEM;
glue->notify.notify = irq_cpu_rmap_notify;
glue->notify.release = irq_cpu_rmap_release;
glue->rmap = rmap;
cpu_rmap_get(rmap);
glue->index = cpu_rmap_add(rmap, glue);
rc = irq_set_affinity_notifier(irq, &glue->notify);
if (rc) {
cpu_rmap_put(glue->rmap);
kfree(glue);
}
return rc;
}
EXPORT_SYMBOL(irq_cpu_rmap_add);
Computing file changes ...