From 98671a0fd1f14e4a518ee06b19037c20014900eb Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Jan 2025 17:22:45 -0800 Subject: bpf: unify VM_WRITE vs VM_MAYWRITE use in BPF map mmaping logic For all BPF maps we ensure that VM_MAYWRITE is cleared when memory-mapping BPF map contents as initially read-only VMA. This is because in some cases BPF verifier relies on the underlying data to not be modified afterwards by user space, so once something is mapped read-only, it shouldn't be re-mmap'ed as read-write. As such, it's not necessary to check VM_MAYWRITE in bpf_map_mmap() and map->ops->map_mmap() callbacks: VM_WRITE should be consistently set for read-write mappings, and if VM_WRITE is not set, there is no way for user space to upgrade read-only mapping to read-write one. This patch cleans up this VM_WRITE vs VM_MAYWRITE handling within bpf_map_mmap(), which is an entry point for any BPF map mmap()-ing logic. We also drop unnecessary sanitization of VM_MAYWRITE in BPF ringbuf's map_mmap() callback implementation, as it is already performed by common code in bpf_map_mmap(). Note, though, that in bpf_map_mmap_{open,close}() callbacks we can't drop VM_MAYWRITE use, because it's possible (and is outside of subsystem's control) to have initially read-write memory mapping, which is subsequently dropped to read-only by user space through mprotect(). In such case, from BPF verifier POV it's read-write data throughout the lifetime of BPF map, and is counted as "active writer". But its VMAs will start out as VM_WRITE|VM_MAYWRITE, then mprotect() can change it to just VM_MAYWRITE (and no VM_WRITE), so when its finally munmap()'ed and bpf_map_mmap_close() is called, vm_flags will be just VM_MAYWRITE, but we still need to decrement active writer count with bpf_map_write_active_dec() as it's still considered to be a read-write mapping by the rest of BPF subsystem. Similar reasoning applies to bpf_map_mmap_open(), which is called whenever mmap(), munmap(), and/or mprotect() forces mm subsystem to split original VMA into multiple discontiguous VMAs. Memory-mapping handling is a bit tricky, yes. Cc: Jann Horn Cc: Suren Baghdasaryan Cc: Shakeel Butt Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20250129012246.1515826-1-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- kernel/bpf/syscall.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0daf098e3207..9bec3dce421f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1065,15 +1065,21 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; vm_flags_clear(vma, VM_MAYEXEC); + /* If mapping is read-only, then disallow potentially re-mapping with + * PROT_WRITE by dropping VM_MAYWRITE flag. This VM_MAYWRITE clearing + * means that as far as BPF map's memory-mapped VMAs are concerned, + * VM_WRITE and VM_MAYWRITE and equivalent, if one of them is set, + * both should be set, so we can forget about VM_MAYWRITE and always + * check just VM_WRITE + */ if (!(vma->vm_flags & VM_WRITE)) - /* disallow re-mapping with PROT_WRITE */ vm_flags_clear(vma, VM_MAYWRITE); err = map->ops->map_mmap(map, vma); if (err) goto out; - if (vma->vm_flags & VM_MAYWRITE) + if (vma->vm_flags & VM_WRITE) bpf_map_write_active_inc(map); out: mutex_unlock(&map->freeze_mutex); -- cgit v1.2.3 From bc27c52eea189e8f7492d40739b7746d67b65beb Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 28 Jan 2025 17:22:46 -0800 Subject: 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 Link: https://lore.kernel.org/r/20250129012246.1515826-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- kernel/bpf/syscall.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 9bec3dce421f..14d6e99459d3 100644 --- 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; } -- cgit v1.2.3 From 5644c6b50ffee0a56c1e01430a8c88e34decb120 Mon Sep 17 00:00:00 2001 From: Yan Zhai Date: Sun, 9 Feb 2025 23:22:35 -0800 Subject: bpf: skip non exist keys in generic_map_lookup_batch The generic_map_lookup_batch currently returns EINTR if it fails with ENOENT and retries several times on bpf_map_copy_value. The next batch would start from the same location, presuming it's a transient issue. This is incorrect if a map can actually have "holes", i.e. "get_next_key" can return a key that does not point to a valid value. At least the array of maps type may contain such holes legitly. Right now these holes show up, generic batch lookup cannot proceed any more. It will always fail with EINTR errors. Rather, do not retry in generic_map_lookup_batch. If it finds a non existing element, skip to the next key. This simple solution comes with a price that transient errors may not be recovered, and the iteration might cycle back to the first key under parallel deletion. For example, Hou Tao pointed out a following scenario: For LPM trie map: (1) ->map_get_next_key(map, prev_key, key) returns a valid key (2) bpf_map_copy_value() return -ENOMENT It means the key must be deleted concurrently. (3) goto next_key It swaps the prev_key and key (4) ->map_get_next_key(map, prev_key, key) again prev_key points to a non-existing key, for LPM trie it will treat just like prev_key=NULL case, the returned key will be duplicated. With the retry logic, the iteration can continue to the key next to the deleted one. But if we directly skip to the next key, the iteration loop would restart from the first key for the lpm_trie type. However, not all races may be recovered. For example, if current key is deleted after instead of before bpf_map_copy_value, or if the prev_key also gets deleted, then the loop will still restart from the first key for lpm_tire anyway. For generic lookup it might be better to stay simple, i.e. just skip to the next key. To guarantee that the output keys are not duplicated, it is better to implement map type specific batch operations, which can properly lock the trie and synchronize with concurrent mutators. Fixes: cb4d03ab499d ("bpf: Add generic support for lookup batch op") Closes: https://lore.kernel.org/bpf/Z6JXtA1M5jAZx8xD@debian.debian/ Signed-off-by: Yan Zhai Acked-by: Hou Tao Link: https://lore.kernel.org/r/85618439eea75930630685c467ccefeac0942e2b.1739171594.git.yan@cloudflare.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/syscall.c | 18 +++++------------- 1 file changed, 5 insertions(+), 13 deletions(-) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 14d6e99459d3..548ec1c46b78 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1977,8 +1977,6 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file, return err; } -#define MAP_LOOKUP_RETRIES 3 - int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -1988,8 +1986,8 @@ int generic_map_lookup_batch(struct bpf_map *map, void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); void *buf, *buf_prevkey, *prev_key, *key, *value; - int err, retry = MAP_LOOKUP_RETRIES; u32 value_size, cp, max_count; + int err; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; @@ -2035,14 +2033,8 @@ int generic_map_lookup_batch(struct bpf_map *map, err = bpf_map_copy_value(map, key, value, attr->batch.elem_flags); - if (err == -ENOENT) { - if (retry) { - retry--; - continue; - } - err = -EINTR; - break; - } + if (err == -ENOENT) + goto next_key; if (err) goto free_buf; @@ -2057,12 +2049,12 @@ int generic_map_lookup_batch(struct bpf_map *map, goto free_buf; } + cp++; +next_key: if (!prev_key) prev_key = buf_prevkey; swap(prev_key, key); - retry = MAP_LOOKUP_RETRIES; - cp++; cond_resched(); } -- cgit v1.2.3