bpf: avoid holding freeze_mutex during mmap operation

We use map->freeze_mutex to prevent races between map_freeze() and
memory mapping BPF map contents with writable permissions. The way we
naively do this means we'll hold freeze_mutex for entire duration of all
the mm and VMA manipulations, which is completely unnecessary. This can
potentially also lead to deadlocks, as reported by syzbot in [0].

So, instead, hold freeze_mutex only during writeability checks, bump
(proactively) "write active" count for the map, unlock the mutex and
proceed with mmap logic. And only if something went wrong during mmap
logic, then undo that "write active" counter increment.

  [0] https://lore.kernel.org/bpf/678dcbc9.050a0220.303755.0066.GAE@google.com/

Fixes: fc9702273e2e ("bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY")
Reported-by: syzbot+4dc041c686b7c816a71e@syzkaller.appspotmail.com
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20250129012246.1515826-2-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9bec3dce421f0b8a8c1a886f4d7efb53c306ea0b..14d6e99459d320d9b2a60782204c77535a0919f1 100644 (file)
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1035,7 +1035,7 @@ static const struct vm_operations_struct bpf_map_default_vmops = {
 static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
 {
        struct bpf_map *map = filp->private_data;
-       int err;
+       int err = 0;
 
        if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record))
                return -ENOTSUPP;
@@ -1059,7 +1059,12 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
                        err = -EACCES;
                        goto out;
                }
+               bpf_map_write_active_inc(map);
        }
+out:
+       mutex_unlock(&map->freeze_mutex);
+       if (err)
+               return err;
 
        /* set default open/close callbacks */
        vma->vm_ops = &bpf_map_default_vmops;
@@ -1076,13 +1081,11 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
                vm_flags_clear(vma, VM_MAYWRITE);
 
        err = map->ops->map_mmap(map, vma);
-       if (err)
-               goto out;
+       if (err) {
+               if (vma->vm_flags & VM_WRITE)
+                       bpf_map_write_active_dec(map);
+       }
 
-       if (vma->vm_flags & VM_WRITE)
-               bpf_map_write_active_inc(map);
-out:
-       mutex_unlock(&map->freeze_mutex);
        return err;
 }