From 34d11a440c6167133201b7374065b59f259730d7 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 10 Nov 2021 09:25:56 -0800 Subject: bpf: Fix inner map state pruning regression. Introduction of map_uid made two lookups from outer map to be distinct. That distinction is only necessary when inner map has an embedded timer. Otherwise it will make the verifier state pruning to be conservative which will cause complex programs to hit 1M insn_processed limit. Tighten map_uid logic to apply to inner maps with timers only. Fixes: 3e8ce29850f1 ("bpf: Prevent pointer mismatch in bpf_timer_init.") Reported-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Tested-by: Lorenz Bauer Link: https://lore.kernel.org/bpf/CACAyw99hVEJFoiBH_ZGyy=+oO-jyydoz6v1DeKPKs2HVsUH28w@mail.gmail.com Link: https://lore.kernel.org/bpf/20211110172556.20754-1-alexei.starovoitov@gmail.com --- kernel/bpf/verifier.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 890b3ec375a3..aab7482ed1c3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1151,7 +1151,8 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) /* transfer reg's id which is unique for every map_lookup_elem * as UID of the inner map. */ - reg->map_uid = reg->id; + if (map_value_has_timer(map->inner_map_meta)) + reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || -- cgit v1.2.3 From 5e0bc3082e2e403ac0753e099c2b01446bb35578 Mon Sep 17 00:00:00 2001 From: Dmitrii Banshchikov Date: Sat, 13 Nov 2021 18:22:26 +0400 Subject: bpf: Forbid bpf_ktime_get_coarse_ns and bpf_timer_* in tracing progs Use of bpf_ktime_get_coarse_ns() and bpf_timer_* helpers in tracing progs may result in locking issues. bpf_ktime_get_coarse_ns() uses ktime_get_coarse_ns() time accessor that isn't safe for any context: ====================================================== WARNING: possible circular locking dependency detected 5.15.0-syzkaller #0 Not tainted ------------------------------------------------------ syz-executor.4/14877 is trying to acquire lock: ffffffff8cb30008 (tk_core.seq.seqcount){----}-{0:0}, at: ktime_get_coarse_ts64+0x25/0x110 kernel/time/timekeeping.c:2255 but task is already holding lock: ffffffff90dbf200 (&obj_hash[i].lock){-.-.}-{2:2}, at: debug_object_deactivate+0x61/0x400 lib/debugobjects.c:735 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&obj_hash[i].lock){-.-.}-{2:2}: lock_acquire+0x19f/0x4d0 kernel/locking/lockdep.c:5625 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0xd1/0x120 kernel/locking/spinlock.c:162 __debug_object_init+0xd9/0x1860 lib/debugobjects.c:569 debug_hrtimer_init kernel/time/hrtimer.c:414 [inline] debug_init kernel/time/hrtimer.c:468 [inline] hrtimer_init+0x20/0x40 kernel/time/hrtimer.c:1592 ntp_init_cmos_sync kernel/time/ntp.c:676 [inline] ntp_init+0xa1/0xad kernel/time/ntp.c:1095 timekeeping_init+0x512/0x6bf kernel/time/timekeeping.c:1639 start_kernel+0x267/0x56e init/main.c:1030 secondary_startup_64_no_verify+0xb1/0xbb -> #0 (tk_core.seq.seqcount){----}-{0:0}: check_prev_add kernel/locking/lockdep.c:3051 [inline] check_prevs_add kernel/locking/lockdep.c:3174 [inline] validate_chain+0x1dfb/0x8240 kernel/locking/lockdep.c:3789 __lock_acquire+0x1382/0x2b00 kernel/locking/lockdep.c:5015 lock_acquire+0x19f/0x4d0 kernel/locking/lockdep.c:5625 seqcount_lockdep_reader_access+0xfe/0x230 include/linux/seqlock.h:103 ktime_get_coarse_ts64+0x25/0x110 kernel/time/timekeeping.c:2255 ktime_get_coarse include/linux/timekeeping.h:120 [inline] ktime_get_coarse_ns include/linux/timekeeping.h:126 [inline] ____bpf_ktime_get_coarse_ns kernel/bpf/helpers.c:173 [inline] bpf_ktime_get_coarse_ns+0x7e/0x130 kernel/bpf/helpers.c:171 bpf_prog_a99735ebafdda2f1+0x10/0xb50 bpf_dispatcher_nop_func include/linux/bpf.h:721 [inline] __bpf_prog_run include/linux/filter.h:626 [inline] bpf_prog_run include/linux/filter.h:633 [inline] BPF_PROG_RUN_ARRAY include/linux/bpf.h:1294 [inline] trace_call_bpf+0x2cf/0x5d0 kernel/trace/bpf_trace.c:127 perf_trace_run_bpf_submit+0x7b/0x1d0 kernel/events/core.c:9708 perf_trace_lock+0x37c/0x440 include/trace/events/lock.h:39 trace_lock_release+0x128/0x150 include/trace/events/lock.h:58 lock_release+0x82/0x810 kernel/locking/lockdep.c:5636 __raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:149 [inline] _raw_spin_unlock_irqrestore+0x75/0x130 kernel/locking/spinlock.c:194 debug_hrtimer_deactivate kernel/time/hrtimer.c:425 [inline] debug_deactivate kernel/time/hrtimer.c:481 [inline] __run_hrtimer kernel/time/hrtimer.c:1653 [inline] __hrtimer_run_queues+0x2f9/0xa60 kernel/time/hrtimer.c:1749 hrtimer_interrupt+0x3b3/0x1040 kernel/time/hrtimer.c:1811 local_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1086 [inline] __sysvec_apic_timer_interrupt+0xf9/0x270 arch/x86/kernel/apic/apic.c:1103 sysvec_apic_timer_interrupt+0x8c/0xb0 arch/x86/kernel/apic/apic.c:1097 asm_sysvec_apic_timer_interrupt+0x12/0x20 __raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:152 [inline] _raw_spin_unlock_irqrestore+0xd4/0x130 kernel/locking/spinlock.c:194 try_to_wake_up+0x702/0xd20 kernel/sched/core.c:4118 wake_up_process kernel/sched/core.c:4200 [inline] wake_up_q+0x9a/0xf0 kernel/sched/core.c:953 futex_wake+0x50f/0x5b0 kernel/futex/waitwake.c:184 do_futex+0x367/0x560 kernel/futex/syscalls.c:127 __do_sys_futex kernel/futex/syscalls.c:199 [inline] __se_sys_futex+0x401/0x4b0 kernel/futex/syscalls.c:180 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae There is a possible deadlock with bpf_timer_* set of helpers: hrtimer_start() lock_base(); trace_hrtimer...() perf_event() bpf_run() bpf_timer_start() hrtimer_start() lock_base() <- DEADLOCK Forbid use of bpf_ktime_get_coarse_ns() and bpf_timer_* helpers in BPF_PROG_TYPE_KPROBE, BPF_PROG_TYPE_TRACEPOINT, BPF_PROG_TYPE_PERF_EVENT and BPF_PROG_TYPE_RAW_TRACEPOINT prog types. Fixes: d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper") Fixes: b00628b1c7d5 ("bpf: Introduce bpf timers.") Reported-by: syzbot+43fd005b5a1b4d10781e@syzkaller.appspotmail.com Signed-off-by: Dmitrii Banshchikov Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211113142227.566439-2-me@ubique.spb.ru --- kernel/bpf/cgroup.c | 2 ++ kernel/bpf/helpers.c | 2 -- kernel/bpf/verifier.c | 7 +++++++ kernel/trace/bpf_trace.c | 2 -- net/core/filter.c | 6 ++++++ net/ipv4/bpf_tcp_ca.c | 2 ++ 6 files changed, 17 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 2ca643af9a54..43eb3501721b 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1809,6 +1809,8 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sysctl_get_new_value_proto; case BPF_FUNC_sysctl_set_new_value: return &bpf_sysctl_set_new_value_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return cgroup_base_func_proto(func_id, prog); } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1ffd469c217f..649f07623df6 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1364,8 +1364,6 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; - case BPF_FUNC_ktime_get_coarse_ns: - return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index aab7482ed1c3..65d2f93b7030 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -11632,6 +11632,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } } + if (map_value_has_timer(map)) { + if (is_tracing_prog_type(prog_type)) { + verbose(env, "tracing progs cannot use bpf_timer yet\n"); + return -EINVAL; + } + } + if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7396488793ff..ae9755037b7e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1111,8 +1111,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; - case BPF_FUNC_ktime_get_coarse_ns: - return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: diff --git a/net/core/filter.c b/net/core/filter.c index e471c9b09670..6102f093d59a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7162,6 +7162,8 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_cg_sock_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } @@ -10327,6 +10329,8 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, return &sk_reuseport_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } @@ -10833,6 +10837,8 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skc_to_unix_sock: func = &bpf_skc_to_unix_sock_proto; break; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 2cf02b4d77fb..4bb9401b0a3f 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -205,6 +205,8 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, offsetof(struct tcp_congestion_ops, release)) return &bpf_sk_getsockopt_proto; return NULL; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } -- cgit v1.2.3 From 353050be4c19e102178ccc05988101887c25ae53 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 9 Nov 2021 18:48:08 +0000 Subject: bpf: Fix toctou on read-only map's constant scalar tracking Commit a23740ec43ba ("bpf: Track contents of read-only maps as scalars") is checking whether maps are read-only both from BPF program side and user space side, and then, given their content is constant, reading out their data via map->ops->map_direct_value_addr() which is then subsequently used as known scalar value for the register, that is, it is marked as __mark_reg_known() with the read value at verification time. Before a23740ec43ba, the register content was marked as an unknown scalar so the verifier could not make any assumptions about the map content. The current implementation however is prone to a TOCTOU race, meaning, the value read as known scalar for the register is not guaranteed to be exactly the same at a later point when the program is executed, and as such, the prior made assumptions of the verifier with regards to the program will be invalid which can cause issues such as OOB access, etc. While the BPF_F_RDONLY_PROG map flag is always fixed and required to be specified at map creation time, the map->frozen property is initially set to false for the map given the map value needs to be populated, e.g. for global data sections. Once complete, the loader "freezes" the map from user space such that no subsequent updates/deletes are possible anymore. For the rest of the lifetime of the map, this freeze one-time trigger cannot be undone anymore after a successful BPF_MAP_FREEZE cmd return. Meaning, any new BPF_* cmd calls which would update/delete map entries will be rejected with -EPERM since map_get_sys_perms() removes the FMODE_CAN_WRITE permission. This also means that pending update/delete map entries must still complete before this guarantee is given. This corner case is not an issue for loaders since they create and prepare such program private map in successive steps. However, a malicious user is able to trigger this TOCTOU race in two different ways: i) via userfaultfd, and ii) via batched updates. For i) userfaultfd is used to expand the competition interval, so that map_update_elem() can modify the contents of the map after map_freeze() and bpf_prog_load() were executed. This works, because userfaultfd halts the parallel thread which triggered a map_update_elem() at the time where we copy key/value from the user buffer and this already passed the FMODE_CAN_WRITE capability test given at that time the map was not "frozen". Then, the main thread performs the map_freeze() and bpf_prog_load(), and once that had completed successfully, the other thread is woken up to complete the pending map_update_elem() which then changes the map content. For ii) the idea of the batched update is similar, meaning, when there are a large number of updates to be processed, it can increase the competition interval between the two. It is therefore possible in practice to modify the contents of the map after executing map_freeze() and bpf_prog_load(). One way to fix both i) and ii) at the same time is to expand the use of the map's map->writecnt. The latter was introduced in fc9702273e2e ("bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY") and further refined in 1f6cb19be2e2 ("bpf: Prevent re-mmap()'ing BPF map as writable for initially r/o mapping") with the rationale to make a writable mmap()'ing of a map mutually exclusive with read-only freezing. The counter indicates writable mmap() mappings and then prevents/fails the freeze operation. Its semantics can be expanded beyond just mmap() by generally indicating ongoing write phases. This would essentially span any parallel regular and batched flavor of update/delete operation and then also have map_freeze() fail with -EBUSY. For the check_mem_access() in the verifier we expand upon the bpf_map_is_rdonly() check ensuring that all last pending writes have completed via bpf_map_write_active() test. Once the map->frozen is set and bpf_map_write_active() indicates a map->writecnt of 0 only then we are really guaranteed to use the map's data as known constants. For map->frozen being set and pending writes in process of still being completed we fall back to marking that register as unknown scalar so we don't end up making assumptions about it. With this, both TOCTOU reproducers from i) and ii) are fixed. Note that the map->writecnt has been converted into a atomic64 in the fix in order to avoid a double freeze_mutex mutex_{un,}lock() pair when updating map->writecnt in the various map update/delete BPF_* cmd flavors. Spanning the freeze_mutex over entire map update/delete operations in syscall side would not be possible due to then causing everything to be serialized. Similarly, something like synchronize_rcu() after setting map->frozen to wait for update/deletes to complete is not possible either since it would also have to span the user copy which can sleep. On the libbpf side, this won't break d66562fba1ce ("libbpf: Add BPF object skeleton support") as the anonymous mmap()-ed "map initialization image" is remapped as a BPF map-backed mmap()-ed memory where for .rodata it's non-writable. Fixes: a23740ec43ba ("bpf: Track contents of read-only maps as scalars") Reported-by: w1tcher.bupt@gmail.com Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 ++- kernel/bpf/syscall.c | 57 ++++++++++++++++++++++++++++++++------------------- kernel/bpf/verifier.c | 17 ++++++++++++++- 3 files changed, 54 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f715e8863f4d..e7a163a3146b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -193,7 +193,7 @@ struct bpf_map { atomic64_t usercnt; struct work_struct work; struct mutex freeze_mutex; - u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */ + atomic64_t writecnt; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -1419,6 +1419,7 @@ void bpf_map_put(struct bpf_map *map); void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); +bool bpf_map_write_active(const struct bpf_map *map); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 50f96ea4452a..1033ee8c0caf 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -132,6 +132,21 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } +static void bpf_map_write_active_inc(struct bpf_map *map) +{ + atomic64_inc(&map->writecnt); +} + +static void bpf_map_write_active_dec(struct bpf_map *map) +{ + atomic64_dec(&map->writecnt); +} + +bool bpf_map_write_active(const struct bpf_map *map) +{ + return atomic64_read(&map->writecnt) != 0; +} + static u32 bpf_map_value_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || @@ -601,11 +616,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt++; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_inc(map); } /* called for all unmapped memory region (including initial) */ @@ -613,11 +625,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt--; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_dec(map); } static const struct vm_operations_struct bpf_map_default_vmops = { @@ -668,7 +677,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) goto out; if (vma->vm_flags & VM_MAYWRITE) - map->writecnt++; + bpf_map_write_active_inc(map); out: mutex_unlock(&map->freeze_mutex); return err; @@ -1139,6 +1148,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; @@ -1174,6 +1184,7 @@ free_value: free_key: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1196,6 +1207,7 @@ static int map_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; @@ -1226,6 +1238,7 @@ static int map_delete_elem(union bpf_attr *attr) out: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1533,6 +1546,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; @@ -1597,6 +1611,7 @@ free_value: free_key: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1624,8 +1639,7 @@ static int map_freeze(const union bpf_attr *attr) } mutex_lock(&map->freeze_mutex); - - if (map->writecnt) { + if (bpf_map_write_active(map)) { err = -EBUSY; goto err_put; } @@ -4171,6 +4185,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr, union bpf_attr __user *uattr, int cmd) { + bool has_read = cmd == BPF_MAP_LOOKUP_BATCH || + cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; + bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; int err, ufd; struct fd f; @@ -4183,16 +4200,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr, map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if ((cmd == BPF_MAP_LOOKUP_BATCH || - cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) && - !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { + if (has_write) + bpf_map_write_active_inc(map); + if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } - - if (cmd != BPF_MAP_LOOKUP_BATCH && - !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -4205,8 +4219,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr, BPF_DO_BATCH(map->ops->map_update_batch); else BPF_DO_BATCH(map->ops->map_delete_batch); - err_put: + if (has_write) + bpf_map_write_active_dec(map); fdput(f); return err; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 65d2f93b7030..50efda51515b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4056,7 +4056,22 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) static bool bpf_map_is_rdonly(const struct bpf_map *map) { - return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen; + /* A map is considered read-only if the following condition are true: + * + * 1) BPF program side cannot change any of the map content. The + * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map + * and was set at map creation time. + * 2) The map value(s) have been initialized from user space by a + * loader and then "frozen", such that no new map update/delete + * operations from syscall side are possible for the rest of + * the map's lifetime from that point onwards. + * 3) Any parallel/pending map update/delete operations from syscall + * side have been completed. Only after that point, it's safe to + * assume that map value(s) are immutable. + */ + return (map->map_flags & BPF_F_RDONLY_PROG) && + READ_ONCE(map->frozen) && + !bpf_map_write_active(map); } static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) -- cgit v1.2.3