From c50eb518e262fa06bd334e6eec172eaf5d7a5bd9 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 29 Oct 2020 00:19:24 -0700 Subject: bpf: Use separate lockdep class for each hashtab If a hashtab is accessed in both NMI and non-NMI contexts, it may cause deadlock in bucket->lock. LOCKDEP NMI warning highlighted this issue: ./test_progs -t stacktrace [ 74.828970] [ 74.828971] ================================ [ 74.828972] WARNING: inconsistent lock state [ 74.828973] 5.9.0-rc8+ #275 Not tainted [ 74.828974] -------------------------------- [ 74.828975] inconsistent {INITIAL USE} -> {IN-NMI} usage. [ 74.828976] taskset/1174 [HC2[2]:SC0[0]:HE0:SE1] takes: [ 74.828977] ffffc90000ee96b0 (&htab->buckets[i].raw_lock){....}-{2:2}, at: htab_map_update_elem+0x271/0x5a0 [ 74.828981] {INITIAL USE} state was registered at: [ 74.828982] lock_acquire+0x137/0x510 [ 74.828983] _raw_spin_lock_irqsave+0x43/0x90 [ 74.828984] htab_map_update_elem+0x271/0x5a0 [ 74.828984] 0xffffffffa0040b34 [ 74.828985] trace_call_bpf+0x159/0x310 [ 74.828986] perf_trace_run_bpf_submit+0x5f/0xd0 [ 74.828987] perf_trace_urandom_read+0x1be/0x220 [ 74.828988] urandom_read_nowarn.isra.0+0x26f/0x380 [ 74.828989] vfs_read+0xf8/0x280 [ 74.828989] ksys_read+0xc9/0x160 [ 74.828990] do_syscall_64+0x33/0x40 [ 74.828991] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 74.828992] irq event stamp: 1766 [ 74.828993] hardirqs last enabled at (1765): [] asm_exc_page_fault+0x1e/0x30 [ 74.828994] hardirqs last disabled at (1766): [] irqentry_enter+0x37/0x60 [ 74.828995] softirqs last enabled at (856): [] fpu__clear+0xac/0x120 [ 74.828996] softirqs last disabled at (854): [] fpu__clear+0x20/0x120 [ 74.828997] [ 74.828998] other info that might help us debug this: [ 74.828999] Possible unsafe locking scenario: [ 74.828999] [ 74.829000] CPU0 [ 74.829001] ---- [ 74.829001] lock(&htab->buckets[i].raw_lock); [ 74.829003] [ 74.829004] lock(&htab->buckets[i].raw_lock); [ 74.829006] [ 74.829006] *** DEADLOCK *** [ 74.829007] [ 74.829008] 1 lock held by taskset/1174: [ 74.829008] #0: ffff8883ec3fd020 (&cpuctx_lock){-...}-{2:2}, at: perf_event_task_tick+0x101/0x650 [ 74.829012] [ 74.829013] stack backtrace: [ 74.829014] CPU: 0 PID: 1174 Comm: taskset Not tainted 5.9.0-rc8+ #275 [ 74.829015] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 [ 74.829016] Call Trace: [ 74.829016] [ 74.829017] dump_stack+0x9a/0xd0 [ 74.829018] lock_acquire+0x461/0x510 [ 74.829019] ? lock_release+0x6b0/0x6b0 [ 74.829020] ? stack_map_get_build_id_offset+0x45e/0x800 [ 74.829021] ? htab_map_update_elem+0x271/0x5a0 [ 74.829022] ? rcu_read_lock_held_common+0x1a/0x50 [ 74.829022] ? rcu_read_lock_held+0x5f/0xb0 [ 74.829023] _raw_spin_lock_irqsave+0x43/0x90 [ 74.829024] ? htab_map_update_elem+0x271/0x5a0 [ 74.829025] htab_map_update_elem+0x271/0x5a0 [ 74.829026] bpf_prog_1fd9e30e1438d3c5_oncpu+0x9c/0xe88 [ 74.829027] bpf_overflow_handler+0x127/0x320 [ 74.829028] ? perf_event_text_poke_output+0x4d0/0x4d0 [ 74.829029] ? sched_clock_cpu+0x18/0x130 [ 74.829030] __perf_event_overflow+0xae/0x190 [ 74.829030] handle_pmi_common+0x34c/0x470 [ 74.829031] ? intel_pmu_save_and_restart+0x90/0x90 [ 74.829032] ? lock_acquire+0x3f8/0x510 [ 74.829033] ? lock_release+0x6b0/0x6b0 [ 74.829034] intel_pmu_handle_irq+0x11e/0x240 [ 74.829034] perf_event_nmi_handler+0x40/0x60 [ 74.829035] nmi_handle+0x110/0x360 [ 74.829036] ? __intel_pmu_enable_all.constprop.0+0x72/0xf0 [ 74.829037] default_do_nmi+0x6b/0x170 [ 74.829038] exc_nmi+0x106/0x130 [ 74.829038] end_repeat_nmi+0x16/0x55 [ 74.829039] RIP: 0010:__intel_pmu_enable_all.constprop.0+0x72/0xf0 [ 74.829042] Code: 2f 1f 03 48 8d bb b8 0c 00 00 e8 29 09 41 00 48 ... [ 74.829043] RSP: 0000:ffff8880a604fc90 EFLAGS: 00000002 [ 74.829044] RAX: 000000070000000f RBX: ffff8883ec2195a0 RCX: 000000000000038f [ 74.829045] RDX: 0000000000000007 RSI: ffffffff82e72c20 RDI: ffff8883ec21a258 [ 74.829046] RBP: 000000070000000f R08: ffffffff8101b013 R09: fffffbfff0a7982d [ 74.829047] R10: ffffffff853cc167 R11: fffffbfff0a7982c R12: 0000000000000000 [ 74.829049] R13: ffff8883ec3f0af0 R14: ffff8883ec3fd120 R15: ffff8883e9c92098 [ 74.829049] ? intel_pmu_lbr_enable_all+0x43/0x240 [ 74.829050] ? __intel_pmu_enable_all.constprop.0+0x72/0xf0 [ 74.829051] ? __intel_pmu_enable_all.constprop.0+0x72/0xf0 [ 74.829052] [ 74.829053] perf_event_task_tick+0x48d/0x650 [ 74.829054] scheduler_tick+0x129/0x210 [ 74.829054] update_process_times+0x37/0x70 [ 74.829055] tick_sched_handle.isra.0+0x35/0x90 [ 74.829056] tick_sched_timer+0x8f/0xb0 [ 74.829057] __hrtimer_run_queues+0x364/0x7d0 [ 74.829058] ? tick_sched_do_timer+0xa0/0xa0 [ 74.829058] ? enqueue_hrtimer+0x1e0/0x1e0 [ 74.829059] ? recalibrate_cpu_khz+0x10/0x10 [ 74.829060] ? ktime_get_update_offsets_now+0x1a3/0x360 [ 74.829061] hrtimer_interrupt+0x1bb/0x360 [ 74.829062] ? rcu_read_lock_sched_held+0xa1/0xd0 [ 74.829063] __sysvec_apic_timer_interrupt+0xed/0x3d0 [ 74.829064] sysvec_apic_timer_interrupt+0x3f/0xd0 [ 74.829064] ? asm_sysvec_apic_timer_interrupt+0xa/0x20 [ 74.829065] asm_sysvec_apic_timer_interrupt+0x12/0x20 [ 74.829066] RIP: 0033:0x7fba18d579b4 [ 74.829068] Code: 74 54 44 0f b6 4a 04 41 83 e1 0f 41 80 f9 ... [ 74.829069] RSP: 002b:00007ffc9ba69570 EFLAGS: 00000206 [ 74.829071] RAX: 00007fba192084c0 RBX: 00007fba18c24d28 RCX: 00000000000007a4 [ 74.829072] RDX: 00007fba18c30488 RSI: 0000000000000000 RDI: 000000000000037b [ 74.829073] RBP: 00007fba18ca5760 R08: 00007fba18c248fc R09: 00007fba18c94c30 [ 74.829074] R10: 000000000000002f R11: 0000000000073c30 R12: 00007ffc9ba695e0 [ 74.829075] R13: 00000000000003f3 R14: 00007fba18c21ac8 R15: 00000000000058d6 However, such warning should not apply across multiple hashtabs. The system will not deadlock if one hashtab is used in NMI, while another hashtab is used in non-NMI. Use separate lockdep class for each hashtab, so that we don't get this false alert. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201029071925.3103400-2-songliubraving@fb.com --- kernel/bpf/hashtab.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'kernel/bpf/hashtab.c') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 1815e97d4c9c..278da031c91a 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -99,6 +99,7 @@ struct bpf_htab { u32 n_buckets; /* number of hash buckets */ u32 elem_size; /* size of each element in bytes */ u32 hashrnd; + struct lock_class_key lockdep_key; }; /* each htab element is struct htab_elem + key + value */ @@ -136,12 +137,18 @@ static void htab_init_buckets(struct bpf_htab *htab) { unsigned i; + lockdep_register_key(&htab->lockdep_key); for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); - if (htab_use_raw_lock(htab)) + if (htab_use_raw_lock(htab)) { raw_spin_lock_init(&htab->buckets[i].raw_lock); - else + lockdep_set_class(&htab->buckets[i].raw_lock, + &htab->lockdep_key); + } else { spin_lock_init(&htab->buckets[i].lock); + lockdep_set_class(&htab->buckets[i].lock, + &htab->lockdep_key); + } } } @@ -1312,6 +1319,7 @@ static void htab_map_free(struct bpf_map *map) free_percpu(htab->extra_elems); bpf_map_area_free(htab->buckets); + lockdep_unregister_key(&htab->lockdep_key); kfree(htab); } -- cgit v1.2.3 From 20b6cc34ea74b6a84599c1f8a70f3315b56a1883 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 29 Oct 2020 00:19:25 -0700 Subject: bpf: Avoid hashtab deadlock with map_locked If a hashtab is accessed in both non-NMI and NMI context, the system may deadlock on bucket->lock. Fix this issue with percpu counter map_locked. map_locked rejects concurrent access to the same bucket from the same CPU. To reduce memory overhead, map_locked is not added per bucket. Instead, 8 percpu counters are added to each hashtab. buckets are assigned to these counters based on the lower bits of its hash. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20201029071925.3103400-3-songliubraving@fb.com --- kernel/bpf/hashtab.c | 114 ++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 82 insertions(+), 32 deletions(-) (limited to 'kernel/bpf/hashtab.c') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 278da031c91a..da59ba978d17 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -86,6 +86,9 @@ struct bucket { }; }; +#define HASHTAB_MAP_LOCK_COUNT 8 +#define HASHTAB_MAP_LOCK_MASK (HASHTAB_MAP_LOCK_COUNT - 1) + struct bpf_htab { struct bpf_map map; struct bucket *buckets; @@ -100,6 +103,7 @@ struct bpf_htab { u32 elem_size; /* size of each element in bytes */ u32 hashrnd; struct lock_class_key lockdep_key; + int __percpu *map_locked[HASHTAB_MAP_LOCK_COUNT]; }; /* each htab element is struct htab_elem + key + value */ @@ -152,26 +156,41 @@ static void htab_init_buckets(struct bpf_htab *htab) } } -static inline unsigned long htab_lock_bucket(const struct bpf_htab *htab, - struct bucket *b) +static inline int htab_lock_bucket(const struct bpf_htab *htab, + struct bucket *b, u32 hash, + unsigned long *pflags) { unsigned long flags; + hash = hash & HASHTAB_MAP_LOCK_MASK; + + migrate_disable(); + if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) { + __this_cpu_dec(*(htab->map_locked[hash])); + migrate_enable(); + return -EBUSY; + } + if (htab_use_raw_lock(htab)) raw_spin_lock_irqsave(&b->raw_lock, flags); else spin_lock_irqsave(&b->lock, flags); - return flags; + *pflags = flags; + + return 0; } static inline void htab_unlock_bucket(const struct bpf_htab *htab, - struct bucket *b, + struct bucket *b, u32 hash, unsigned long flags) { + hash = hash & HASHTAB_MAP_LOCK_MASK; if (htab_use_raw_lock(htab)) raw_spin_unlock_irqrestore(&b->raw_lock, flags); else spin_unlock_irqrestore(&b->lock, flags); + __this_cpu_dec(*(htab->map_locked[hash])); + migrate_enable(); } static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node); @@ -429,8 +448,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); struct bpf_htab *htab; + int err, i; u64 cost; - int err; htab = kzalloc(sizeof(*htab), GFP_USER); if (!htab) @@ -487,6 +506,13 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (!htab->buckets) goto free_charge; + for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) { + htab->map_locked[i] = __alloc_percpu_gfp(sizeof(int), + sizeof(int), GFP_USER); + if (!htab->map_locked[i]) + goto free_map_locked; + } + if (htab->map.map_flags & BPF_F_ZERO_SEED) htab->hashrnd = 0; else @@ -497,7 +523,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (prealloc) { err = prealloc_init(htab); if (err) - goto free_buckets; + goto free_map_locked; if (!percpu && !lru) { /* lru itself can remove the least used element, so @@ -513,7 +539,9 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) free_prealloc: prealloc_destroy(htab); -free_buckets: +free_map_locked: + for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) + free_percpu(htab->map_locked[i]); bpf_map_area_free(htab->buckets); free_charge: bpf_map_charge_finish(&htab->map.memory); @@ -694,12 +722,15 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) struct hlist_nulls_node *n; unsigned long flags; struct bucket *b; + int ret; tgt_l = container_of(node, struct htab_elem, lru_node); b = __select_bucket(htab, tgt_l->hash); head = &b->head; - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, tgt_l->hash, &flags); + if (ret) + return false; hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l == tgt_l) { @@ -707,7 +738,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) break; } - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, tgt_l->hash, flags); return l == tgt_l; } @@ -979,7 +1010,9 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, */ } - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, hash, &flags); + if (ret) + return ret; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1020,7 +1053,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, } ret = 0; err: - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, hash, flags); return ret; } @@ -1058,7 +1091,9 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, return -ENOMEM; memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size); - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, hash, &flags); + if (ret) + return ret; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1077,7 +1112,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, ret = 0; err: - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, hash, flags); if (ret) bpf_lru_push_free(&htab->lru, &l_new->lru_node); @@ -1112,7 +1147,9 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, b = __select_bucket(htab, hash); head = &b->head; - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, hash, &flags); + if (ret) + return ret; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1135,7 +1172,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, } ret = 0; err: - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, hash, flags); return ret; } @@ -1175,7 +1212,9 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, return -ENOMEM; } - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, hash, &flags); + if (ret) + return ret; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1197,7 +1236,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, } ret = 0; err: - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, hash, flags); if (l_new) bpf_lru_push_free(&htab->lru, &l_new->lru_node); return ret; @@ -1225,7 +1264,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) struct htab_elem *l; unsigned long flags; u32 hash, key_size; - int ret = -ENOENT; + int ret; WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); @@ -1235,17 +1274,20 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, hash, &flags); + if (ret) + return ret; l = lookup_elem_raw(head, hash, key, key_size); if (l) { hlist_nulls_del_rcu(&l->hash_node); free_htab_elem(htab, l); - ret = 0; + } else { + ret = -ENOENT; } - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, hash, flags); return ret; } @@ -1257,7 +1299,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) struct htab_elem *l; unsigned long flags; u32 hash, key_size; - int ret = -ENOENT; + int ret; WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); @@ -1267,16 +1309,18 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - flags = htab_lock_bucket(htab, b); + ret = htab_lock_bucket(htab, b, hash, &flags); + if (ret) + return ret; l = lookup_elem_raw(head, hash, key, key_size); - if (l) { + if (l) hlist_nulls_del_rcu(&l->hash_node); - ret = 0; - } + else + ret = -ENOENT; - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, hash, flags); if (l) bpf_lru_push_free(&htab->lru, &l->lru_node); return ret; @@ -1302,6 +1346,7 @@ static void delete_all_elements(struct bpf_htab *htab) static void htab_map_free(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + int i; /* bpf_free_used_maps() or close(map_fd) will trigger this map_free callback. * bpf_free_used_maps() is called after bpf prog is no longer executing. @@ -1320,6 +1365,8 @@ static void htab_map_free(struct bpf_map *map) free_percpu(htab->extra_elems); bpf_map_area_free(htab->buckets); lockdep_unregister_key(&htab->lockdep_key); + for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) + free_percpu(htab->map_locked[i]); kfree(htab); } @@ -1423,8 +1470,11 @@ again_nocopy: b = &htab->buckets[batch]; head = &b->head; /* do not grab the lock unless need it (bucket_cnt > 0). */ - if (locked) - flags = htab_lock_bucket(htab, b); + if (locked) { + ret = htab_lock_bucket(htab, b, batch, &flags); + if (ret) + goto next_batch; + } bucket_cnt = 0; hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) @@ -1441,7 +1491,7 @@ again_nocopy: /* Note that since bucket_cnt > 0 here, it is implicit * that the locked was grabbed, so release it. */ - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, batch, flags); rcu_read_unlock(); bpf_enable_instrumentation(); goto after_loop; @@ -1452,7 +1502,7 @@ again_nocopy: /* Note that since bucket_cnt > 0 here, it is implicit * that the locked was grabbed, so release it. */ - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, batch, flags); rcu_read_unlock(); bpf_enable_instrumentation(); kvfree(keys); @@ -1505,7 +1555,7 @@ again_nocopy: dst_val += value_size; } - htab_unlock_bucket(htab, b, flags); + htab_unlock_bucket(htab, b, batch, flags); locked = false; while (node_to_free) { -- cgit v1.2.3 From 8aaeed81fcb917b5cf4976932c5baefa1471128b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 2 Nov 2020 03:41:00 -0800 Subject: bpf: Fix error path in htab_map_alloc() syzbot was able to trigger a use-after-free in htab_map_alloc() [1] htab_map_alloc() lacks a call to lockdep_unregister_key() in its error path. lockdep_register_key() and lockdep_unregister_key() can not fail, it seems better to use them right after htab allocation and before htab freeing, avoiding more goto/labels in htab_map_alloc() [1] BUG: KASAN: use-after-free in lockdep_register_key+0x356/0x3e0 kernel/locking/lockdep.c:1182 Read of size 8 at addr ffff88805fa67ad8 by task syz-executor.3/2356 CPU: 1 PID: 2356 Comm: syz-executor.3 Not tainted 5.9.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x107/0x163 lib/dump_stack.c:118 print_address_description.constprop.0.cold+0xae/0x4c8 mm/kasan/report.c:385 __kasan_report mm/kasan/report.c:545 [inline] kasan_report.cold+0x1f/0x37 mm/kasan/report.c:562 lockdep_register_key+0x356/0x3e0 kernel/locking/lockdep.c:1182 htab_init_buckets kernel/bpf/hashtab.c:144 [inline] htab_map_alloc+0x6c5/0x14a0 kernel/bpf/hashtab.c:521 find_and_alloc_map kernel/bpf/syscall.c:122 [inline] map_create kernel/bpf/syscall.c:825 [inline] __do_sys_bpf+0xa80/0x5180 kernel/bpf/syscall.c:4381 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x45deb9 Code: 0d b4 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 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 0f 83 db b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f0eafee1c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000141 RAX: ffffffffffffffda RBX: 0000000000001a00 RCX: 000000000045deb9 RDX: 0000000000000040 RSI: 0000000020000040 RDI: 405a020000000000 RBP: 000000000118bf60 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000118bf2c R13: 00007ffd3cf9eabf R14: 00007f0eafee29c0 R15: 000000000118bf2c Allocated by task 2053: kasan_save_stack+0x1b/0x40 mm/kasan/common.c:48 kasan_set_track mm/kasan/common.c:56 [inline] __kasan_kmalloc.constprop.0+0xc2/0xd0 mm/kasan/common.c:461 kmalloc include/linux/slab.h:554 [inline] kzalloc include/linux/slab.h:666 [inline] htab_map_alloc+0xdf/0x14a0 kernel/bpf/hashtab.c:454 find_and_alloc_map kernel/bpf/syscall.c:122 [inline] map_create kernel/bpf/syscall.c:825 [inline] __do_sys_bpf+0xa80/0x5180 kernel/bpf/syscall.c:4381 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 2053: kasan_save_stack+0x1b/0x40 mm/kasan/common.c:48 kasan_set_track+0x1c/0x30 mm/kasan/common.c:56 kasan_set_free_info+0x1b/0x30 mm/kasan/generic.c:355 __kasan_slab_free+0x102/0x140 mm/kasan/common.c:422 slab_free_hook mm/slub.c:1544 [inline] slab_free_freelist_hook+0x5d/0x150 mm/slub.c:1577 slab_free mm/slub.c:3142 [inline] kfree+0xdb/0x360 mm/slub.c:4124 htab_map_alloc+0x3f9/0x14a0 kernel/bpf/hashtab.c:549 find_and_alloc_map kernel/bpf/syscall.c:122 [inline] map_create kernel/bpf/syscall.c:825 [inline] __do_sys_bpf+0xa80/0x5180 kernel/bpf/syscall.c:4381 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The buggy address belongs to the object at ffff88805fa67800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 728 bytes inside of 1024-byte region [ffff88805fa67800, ffff88805fa67c00) The buggy address belongs to the page: page:000000003c5582c4 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x5fa60 head:000000003c5582c4 order:3 compound_mapcount:0 compound_pincount:0 flags: 0xfff00000010200(slab|head) raw: 00fff00000010200 ffffea0000bc1200 0000000200000002 ffff888010041140 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88805fa67980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88805fa67a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88805fa67b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88805fa67b80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: c50eb518e262 ("bpf: Use separate lockdep class for each hashtab") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20201102114100.3103180-1-eric.dumazet@gmail.com --- kernel/bpf/hashtab.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel/bpf/hashtab.c') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index da59ba978d17..23f73d4649c9 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -141,7 +141,6 @@ static void htab_init_buckets(struct bpf_htab *htab) { unsigned i; - lockdep_register_key(&htab->lockdep_key); for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); if (htab_use_raw_lock(htab)) { @@ -455,6 +454,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (!htab) return ERR_PTR(-ENOMEM); + lockdep_register_key(&htab->lockdep_key); + bpf_map_init_from_attr(&htab->map, attr); if (percpu_lru) { @@ -546,6 +547,7 @@ free_map_locked: free_charge: bpf_map_charge_finish(&htab->map.memory); free_htab: + lockdep_unregister_key(&htab->lockdep_key); kfree(htab); return ERR_PTR(err); } @@ -1364,9 +1366,9 @@ static void htab_map_free(struct bpf_map *map) free_percpu(htab->extra_elems); bpf_map_area_free(htab->buckets); - lockdep_unregister_key(&htab->lockdep_key); for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) free_percpu(htab->map_locked[i]); + lockdep_unregister_key(&htab->lockdep_key); kfree(htab); } -- cgit v1.2.3 From c6bde958a62b8ca5ee8d2c1fe429aec4ad54efad Mon Sep 17 00:00:00 2001 From: Florian Lehner Date: Thu, 29 Oct 2020 21:14:42 +0100 Subject: bpf: Lift hashtab key_size limit Currently key_size of hashtab is limited to MAX_BPF_STACK. As the key of hashtab can also be a value from a per cpu map it can be larger than MAX_BPF_STACK. The use-case for this patch originates to implement allow/disallow lists for files and file paths. The maximum length of file paths is defined by PATH_MAX with 4096 chars including nul. This limit exceeds MAX_BPF_STACK. Changelog: v5: - Fix cast overflow v4: - Utilize BPF skeleton in tests - Rebase v3: - Rebase v2: - Add a test for bpf side Signed-off-by: Florian Lehner Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20201029201442.596690-1-dev@der-flo.net --- kernel/bpf/hashtab.c | 16 +++----- .../selftests/bpf/prog_tests/hash_large_key.c | 43 +++++++++++++++++++++ .../selftests/bpf/progs/test_hash_large_key.c | 44 ++++++++++++++++++++++ tools/testing/selftests/bpf/test_maps.c | 3 +- 4 files changed, 94 insertions(+), 12 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/hash_large_key.c create mode 100644 tools/testing/selftests/bpf/progs/test_hash_large_key.c (limited to 'kernel/bpf/hashtab.c') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 23f73d4649c9..7bf18d92af41 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -415,17 +415,11 @@ static int htab_map_alloc_check(union bpf_attr *attr) attr->value_size == 0) return -EINVAL; - if (attr->key_size > MAX_BPF_STACK) - /* eBPF programs initialize keys on stack, so they cannot be - * larger than max stack size - */ - return -E2BIG; - - if (attr->value_size >= KMALLOC_MAX_SIZE - - MAX_BPF_STACK - sizeof(struct htab_elem)) - /* if value_size is bigger, the user space won't be able to - * access the elements via bpf syscall. This check also makes - * sure that the elem_size doesn't overflow and it's + if ((u64)attr->key_size + attr->value_size >= KMALLOC_MAX_SIZE - + sizeof(struct htab_elem)) + /* if key_size + value_size is bigger, the user space won't be + * able to access the elements via bpf syscall. This check + * also makes sure that the elem_size doesn't overflow and it's * kmalloc-able later in htab_map_update_elem() */ return -E2BIG; diff --git a/tools/testing/selftests/bpf/prog_tests/hash_large_key.c b/tools/testing/selftests/bpf/prog_tests/hash_large_key.c new file mode 100644 index 000000000000..34684c0fc76d --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/hash_large_key.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include "test_hash_large_key.skel.h" + +void test_hash_large_key(void) +{ + int err, value = 21, duration = 0, hash_map_fd; + struct test_hash_large_key *skel; + + struct bigelement { + int a; + char b[4096]; + long long c; + } key; + bzero(&key, sizeof(key)); + + skel = test_hash_large_key__open_and_load(); + if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n")) + return; + + hash_map_fd = bpf_map__fd(skel->maps.hash_map); + if (CHECK(hash_map_fd < 0, "bpf_map__fd", "failed\n")) + goto cleanup; + + err = test_hash_large_key__attach(skel); + if (CHECK(err, "attach_raw_tp", "err %d\n", err)) + goto cleanup; + + err = bpf_map_update_elem(hash_map_fd, &key, &value, BPF_ANY); + if (CHECK(err, "bpf_map_update_elem", "errno=%d\n", errno)) + goto cleanup; + + key.c = 1; + err = bpf_map_lookup_elem(hash_map_fd, &key, &value); + if (CHECK(err, "bpf_map_lookup_elem", "errno=%d\n", errno)) + goto cleanup; + + CHECK_FAIL(value != 42); + +cleanup: + test_hash_large_key__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_hash_large_key.c b/tools/testing/selftests/bpf/progs/test_hash_large_key.c new file mode 100644 index 000000000000..473a22794a62 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_hash_large_key.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 2); + __type(key, struct bigelement); + __type(value, __u32); +} hash_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct bigelement); +} key_map SEC(".maps"); + +struct bigelement { + int a; + char b[4096]; + long long c; +}; + +SEC("raw_tracepoint/sys_enter") +int bpf_hash_large_key_test(void *ctx) +{ + int zero = 0, err = 1, value = 42; + struct bigelement *key; + + key = bpf_map_lookup_elem(&key_map, &zero); + if (!key) + return 0; + + key->c = 1; + if (bpf_map_update_elem(&hash_map, key, &value, BPF_ANY)) + return 0; + + return 0; +} + diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 0d92ebcb335d..0ad3e6305ff0 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1223,9 +1223,10 @@ out_map_in_map: static void test_map_large(void) { + struct bigkey { int a; - char b[116]; + char b[4096]; long long c; } key; int fd, i, value; -- cgit v1.2.3