bpf/tracing: fix a deadlock in perf_event_detach_bpf_prog

syzbot reported a possible deadlock in perf_event_detach_bpf_prog.
The error details:
  ======================================================
  WARNING: possible circular locking dependency detected
  4.16.0-rc7+ #3 Not tainted
  ------------------------------------------------------
  syz-executor7/24531 is trying to acquire lock:
   (bpf_event_mutex){+.+.}, at: [<000000008a849b07>] perf_event_detach_bpf_prog+0x92/0x3d0 kernel/trace/bpf_trace.c:854

  but task is already holding lock:
   (&mm->mmap_sem){++++}, at: [<0000000038768f87>] vm_mmap_pgoff+0x198/0x280 mm/util.c:353

  which lock already depends on the new lock.

  the existing dependency chain (in reverse order) is:

  -> #1 (&mm->mmap_sem){++++}:
       __might_fault+0x13a/0x1d0 mm/memory.c:4571
       _copy_to_user+0x2c/0xc0 lib/usercopy.c:25
       copy_to_user include/linux/uaccess.h:155 [inline]
       bpf_prog_array_copy_info+0xf2/0x1c0 kernel/bpf/core.c:1694
       perf_event_query_prog_array+0x1c7/0x2c0 kernel/trace/bpf_trace.c:891
       _perf_ioctl kernel/events/core.c:4750 [inline]
       perf_ioctl+0x3e1/0x1480 kernel/events/core.c:4770
       vfs_ioctl fs/ioctl.c:46 [inline]
       do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:686
       SYSC_ioctl fs/ioctl.c:701 [inline]
       SyS_ioctl+0x8f/0xc0 fs/ioctl.c:692
       do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
       entry_SYSCALL_64_after_hwframe+0x42/0xb7

  -> #0 (bpf_event_mutex){+.+.}:
       lock_acquire+0x1d5/0x580 kernel/locking/lockdep.c:3920
       __mutex_lock_common kernel/locking/mutex.c:756 [inline]
       __mutex_lock+0x16f/0x1a80 kernel/locking/mutex.c:893
       mutex_lock_nested+0x16/0x20 kernel/locking/mutex.c:908
       perf_event_detach_bpf_prog+0x92/0x3d0 kernel/trace/bpf_trace.c:854
       perf_event_free_bpf_prog kernel/events/core.c:8147 [inline]
       _free_event+0xbdb/0x10f0 kernel/events/core.c:4116
       put_event+0x24/0x30 kernel/events/core.c:4204
       perf_mmap_close+0x60d/0x1010 kernel/events/core.c:5172
       remove_vma+0xb4/0x1b0 mm/mmap.c:172
       remove_vma_list mm/mmap.c:2490 [inline]
       do_munmap+0x82a/0xdf0 mm/mmap.c:2731
       mmap_region+0x59e/0x15a0 mm/mmap.c:1646
       do_mmap+0x6c0/0xe00 mm/mmap.c:1483
       do_mmap_pgoff include/linux/mm.h:2223 [inline]
       vm_mmap_pgoff+0x1de/0x280 mm/util.c:355
       SYSC_mmap_pgoff mm/mmap.c:1533 [inline]
       SyS_mmap_pgoff+0x462/0x5f0 mm/mmap.c:1491
       SYSC_mmap arch/x86/kernel/sys_x86_64.c:100 [inline]
       SyS_mmap+0x16/0x20 arch/x86/kernel/sys_x86_64.c:91
       do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
       entry_SYSCALL_64_after_hwframe+0x42/0xb7

  other info that might help us debug this:

   Possible unsafe locking scenario:

         CPU0                    CPU1
         ----                    ----
    lock(&mm->mmap_sem);
                                 lock(bpf_event_mutex);
                                 lock(&mm->mmap_sem);
    lock(bpf_event_mutex);

   *** DEADLOCK ***
  ======================================================

The bug is introduced by Commit f371b304f12e ("bpf/tracing: allow
user space to query prog array on the same tp") where copy_to_user,
which requires mm->mmap_sem, is called inside bpf_event_mutex lock.
At the same time, during perf_event file descriptor close,
mm->mmap_sem is held first and then subsequent
perf_event_detach_bpf_prog needs bpf_event_mutex lock.
Such a senario caused a deadlock.

As suggested by Daniel, moving copy_to_user out of the
bpf_event_mutex lock should fix the problem.

Fixes: f371b304f12e ("bpf/tracing: allow user space to query prog array on the same tp")
Reported-by: syzbot+dc5ca0e4c9bfafaf2bae@syzkaller.appspotmail.com
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 21 insertions, 4 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index d88e96d4e12c..56ba0f2a01db 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -977,6 +977,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
 {
         struct perf_event_query_bpf __user *uquery = info;
         struct perf_event_query_bpf query = {};
+        u32 *ids, prog_cnt, ids_len;
         int ret;
 
         if (!capable(CAP_SYS_ADMIN))
@@ -985,16 +986,32 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
                 return -EINVAL;
         if (copy_from_user(&query, uquery, sizeof(query)))
                 return -EFAULT;
-        if (query.ids_len > BPF_TRACE_MAX_PROGS)
+
+        ids_len = query.ids_len;
+        if (ids_len > BPF_TRACE_MAX_PROGS)
                 return -E2BIG;
+        ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN);
+        if (!ids)
+                return -ENOMEM;
+        /*
+         * The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which
+         * is required when user only wants to check for uquery->prog_cnt.
+         * There is no need to check for it since the case is handled
+         * gracefully in bpf_prog_array_copy_info.
+         */
 
         mutex_lock(&bpf_event_mutex);
         ret = bpf_prog_array_copy_info(event->tp_event->prog_array,
-                                       uquery->ids,
-                                       query.ids_len,
-                                       &uquery->prog_cnt);
+                                       ids,
+                                       ids_len,
+                                       &prog_cnt);
         mutex_unlock(&bpf_event_mutex);
 
+        if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) ||
+            copy_to_user(uquery->ids, ids, ids_len * sizeof(u32)))
+                ret = -EFAULT;
+
+        kfree(ids);
         return ret;
 }