From 81f5c6f5db37bf2360b64c304b27b8f499b48367 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 29 Jan 2019 16:38:16 -0800 Subject: bpf: btf: allow typedef func_proto Current implementation does not allow typedef func_proto. But it is actually allowed. -bash-4.4$ cat t.c typedef int (f) (int); f *g; -bash-4.4$ clang -O2 -g -c -target bpf t.c -Xclang -target-feature -Xclang +dwarfris -bash-4.4$ pahole -JV t.o File t.o: [1] PTR (anon) type_id=2 [2] TYPEDEF f type_id=3 [3] FUNC_PROTO (anon) return=4 args=(4 (anon)) [4] INT int size=4 bit_offset=0 nr_bits=32 encoding=SIGNED -bash-4.4$ This patch related btf verifier to allow such (typedef func_proto) patterns. Fixes: 2667a2626f4d ("bpf: btf: Add BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO") Acked-by: Martin KaFai Lau Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- kernel/bpf/btf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index befe570be5ba..c57bd10340ed 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1459,7 +1459,8 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, /* "typedef void new_void", "const void"...etc */ if (!btf_type_is_void(next_type) && - !btf_type_is_fwd(next_type)) { + !btf_type_is_fwd(next_type) && + !btf_type_is_func_proto(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } -- cgit v1.2.3-70-g09d2 From 6cab5e90ab2bd323c9f3811b6c70a4687df51e27 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 28 Jan 2019 18:43:34 -0800 Subject: bpf: run bpf programs with preemption disabled Disabled preemption is necessary for proper access to per-cpu maps from BPF programs. But the sender side of socket filters didn't have preemption disabled: unix_dgram_sendmsg->sk_filter->sk_filter_trim_cap->bpf_prog_run_save_cb->BPF_PROG_RUN and a combination of af_packet with tun device didn't disable either: tpacket_snd->packet_direct_xmit->packet_pick_tx_queue->ndo_select_queue-> tun_select_queue->tun_ebpf_select_queue->bpf_prog_run_clear_cb->BPF_PROG_RUN Disable preemption before executing BPF programs (both classic and extended). Reported-by: Jann Horn Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 21 ++++++++++++++++++--- kernel/bpf/cgroup.c | 2 +- 2 files changed, 19 insertions(+), 4 deletions(-) (limited to 'kernel/bpf') diff --git a/include/linux/filter.h b/include/linux/filter.h index ad106d845b22..e532fcc6e4b5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -591,8 +591,8 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb) return qdisc_skb_cb(skb)->data; } -static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, - struct sk_buff *skb) +static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; @@ -611,15 +611,30 @@ static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, return res; } +static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) +{ + u32 res; + + preempt_disable(); + res = __bpf_prog_run_save_cb(prog, skb); + preempt_enable(); + return res; +} + static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); + u32 res; if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); - return BPF_PROG_RUN(prog, skb); + preempt_disable(); + res = BPF_PROG_RUN(prog, skb); + preempt_enable(); + return res; } static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ab612fe9862f..d17d05570a3f 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -572,7 +572,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, bpf_compute_and_save_data_end(skb, &saved_data_end); ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, - bpf_prog_run_save_cb); + __bpf_prog_run_save_cb); bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); skb->sk = save_sk; -- cgit v1.2.3-70-g09d2 From a89fac57b5d080771efd4d71feaae19877cf68f0 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 30 Jan 2019 18:12:43 -0800 Subject: bpf: fix lockdep false positive in percpu_freelist Lockdep warns about false positive: [ 12.492084] 00000000e6b28347 (&head->lock){+...}, at: pcpu_freelist_push+0x2a/0x40 [ 12.492696] but this lock was taken by another, HARDIRQ-safe lock in the past: [ 12.493275] (&rq->lock){-.-.} [ 12.493276] [ 12.493276] [ 12.493276] and interrupts could create inverse lock ordering between them. [ 12.493276] [ 12.494435] [ 12.494435] other info that might help us debug this: [ 12.494979] Possible interrupt unsafe locking scenario: [ 12.494979] [ 12.495518] CPU0 CPU1 [ 12.495879] ---- ---- [ 12.496243] lock(&head->lock); [ 12.496502] local_irq_disable(); [ 12.496969] lock(&rq->lock); [ 12.497431] lock(&head->lock); [ 12.497890] [ 12.498104] lock(&rq->lock); [ 12.498368] [ 12.498368] *** DEADLOCK *** [ 12.498368] [ 12.498837] 1 lock held by dd/276: [ 12.499110] #0: 00000000c58cb2ee (rcu_read_lock){....}, at: trace_call_bpf+0x5e/0x240 [ 12.499747] [ 12.499747] the shortest dependencies between 2nd lock and 1st lock: [ 12.500389] -> (&rq->lock){-.-.} { [ 12.500669] IN-HARDIRQ-W at: [ 12.500934] _raw_spin_lock+0x2f/0x40 [ 12.501373] scheduler_tick+0x4c/0xf0 [ 12.501812] update_process_times+0x40/0x50 [ 12.502294] tick_periodic+0x27/0xb0 [ 12.502723] tick_handle_periodic+0x1f/0x60 [ 12.503203] timer_interrupt+0x11/0x20 [ 12.503651] __handle_irq_event_percpu+0x43/0x2c0 [ 12.504167] handle_irq_event_percpu+0x20/0x50 [ 12.504674] handle_irq_event+0x37/0x60 [ 12.505139] handle_level_irq+0xa7/0x120 [ 12.505601] handle_irq+0xa1/0x150 [ 12.506018] do_IRQ+0x77/0x140 [ 12.506411] ret_from_intr+0x0/0x1d [ 12.506834] _raw_spin_unlock_irqrestore+0x53/0x60 [ 12.507362] __setup_irq+0x481/0x730 [ 12.507789] setup_irq+0x49/0x80 [ 12.508195] hpet_time_init+0x21/0x32 [ 12.508644] x86_late_time_init+0xb/0x16 [ 12.509106] start_kernel+0x390/0x42a [ 12.509554] secondary_startup_64+0xa4/0xb0 [ 12.510034] IN-SOFTIRQ-W at: [ 12.510305] _raw_spin_lock+0x2f/0x40 [ 12.510772] try_to_wake_up+0x1c7/0x4e0 [ 12.511220] swake_up_locked+0x20/0x40 [ 12.511657] swake_up_one+0x1a/0x30 [ 12.512070] rcu_process_callbacks+0xc5/0x650 [ 12.512553] __do_softirq+0xe6/0x47b [ 12.512978] irq_exit+0xc3/0xd0 [ 12.513372] smp_apic_timer_interrupt+0xa9/0x250 [ 12.513876] apic_timer_interrupt+0xf/0x20 [ 12.514343] default_idle+0x1c/0x170 [ 12.514765] do_idle+0x199/0x240 [ 12.515159] cpu_startup_entry+0x19/0x20 [ 12.515614] start_kernel+0x422/0x42a [ 12.516045] secondary_startup_64+0xa4/0xb0 [ 12.516521] INITIAL USE at: [ 12.516774] _raw_spin_lock_irqsave+0x38/0x50 [ 12.517258] rq_attach_root+0x16/0xd0 [ 12.517685] sched_init+0x2f2/0x3eb [ 12.518096] start_kernel+0x1fb/0x42a [ 12.518525] secondary_startup_64+0xa4/0xb0 [ 12.518986] } [ 12.519132] ... key at: [] __key.71384+0x0/0x8 [ 12.519649] ... acquired at: [ 12.519892] pcpu_freelist_pop+0x7b/0xd0 [ 12.520221] bpf_get_stackid+0x1d2/0x4d0 [ 12.520563] ___bpf_prog_run+0x8b4/0x11a0 [ 12.520887] [ 12.521008] -> (&head->lock){+...} { [ 12.521292] HARDIRQ-ON-W at: [ 12.521539] _raw_spin_lock+0x2f/0x40 [ 12.521950] pcpu_freelist_push+0x2a/0x40 [ 12.522396] bpf_get_stackid+0x494/0x4d0 [ 12.522828] ___bpf_prog_run+0x8b4/0x11a0 [ 12.523296] INITIAL USE at: [ 12.523537] _raw_spin_lock+0x2f/0x40 [ 12.523944] pcpu_freelist_populate+0xc0/0x120 [ 12.524417] htab_map_alloc+0x405/0x500 [ 12.524835] __do_sys_bpf+0x1a3/0x1a90 [ 12.525253] do_syscall_64+0x4a/0x180 [ 12.525659] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 12.526167] } [ 12.526311] ... key at: [] __key.13130+0x0/0x8 [ 12.526812] ... acquired at: [ 12.527047] __lock_acquire+0x521/0x1350 [ 12.527371] lock_acquire+0x98/0x190 [ 12.527680] _raw_spin_lock+0x2f/0x40 [ 12.527994] pcpu_freelist_push+0x2a/0x40 [ 12.528325] bpf_get_stackid+0x494/0x4d0 [ 12.528645] ___bpf_prog_run+0x8b4/0x11a0 [ 12.528970] [ 12.529092] [ 12.529092] stack backtrace: [ 12.529444] CPU: 0 PID: 276 Comm: dd Not tainted 5.0.0-rc3-00018-g2fa53f892422 #475 [ 12.530043] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 [ 12.530750] Call Trace: [ 12.530948] dump_stack+0x5f/0x8b [ 12.531248] check_usage_backwards+0x10c/0x120 [ 12.531598] ? ___bpf_prog_run+0x8b4/0x11a0 [ 12.531935] ? mark_lock+0x382/0x560 [ 12.532229] mark_lock+0x382/0x560 [ 12.532496] ? print_shortest_lock_dependencies+0x180/0x180 [ 12.532928] __lock_acquire+0x521/0x1350 [ 12.533271] ? find_get_entry+0x17f/0x2e0 [ 12.533586] ? find_get_entry+0x19c/0x2e0 [ 12.533902] ? lock_acquire+0x98/0x190 [ 12.534196] lock_acquire+0x98/0x190 [ 12.534482] ? pcpu_freelist_push+0x2a/0x40 [ 12.534810] _raw_spin_lock+0x2f/0x40 [ 12.535099] ? pcpu_freelist_push+0x2a/0x40 [ 12.535432] pcpu_freelist_push+0x2a/0x40 [ 12.535750] bpf_get_stackid+0x494/0x4d0 [ 12.536062] ___bpf_prog_run+0x8b4/0x11a0 It has been explained that is a false positive here: https://lkml.org/lkml/2018/7/25/756 Recap: - stackmap uses pcpu_freelist - The lock in pcpu_freelist is a percpu lock - stackmap is only used by tracing bpf_prog - A tracing bpf_prog cannot be run if another bpf_prog has already been running (ensured by the percpu bpf_prog_active counter). Eric pointed out that this lockdep splats stops other legit lockdep splats in selftests/bpf/test_progs.c. Fix this by calling local_irq_save/restore for stackmap. Another false positive had also been worked around by calling local_irq_save in commit 89ad2fa3f043 ("bpf: fix lockdep splat"). That commit added unnecessary irq_save/restore to fast path of bpf hash map. irqs are already disabled at that point, since htab is holding per bucket spin_lock with irqsave. Let's reduce overhead for htab by introducing __pcpu_freelist_push/pop function w/o irqsave and convert pcpu_freelist_push/pop to irqsave to be used elsewhere (right now only in stackmap). It stops lockdep false positive in stackmap with a bit of acceptable overhead. Fixes: 557c0c6e7df8 ("bpf: convert stackmap to pre-allocation") Reported-by: Naresh Kamboju Reported-by: Eric Dumazet Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/hashtab.c | 4 ++-- kernel/bpf/percpu_freelist.c | 41 +++++++++++++++++++++++++++++------------ kernel/bpf/percpu_freelist.h | 4 ++++ 3 files changed, 35 insertions(+), 14 deletions(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 4b7c76765d9d..f9274114c88d 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -686,7 +686,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) } if (htab_is_prealloc(htab)) { - pcpu_freelist_push(&htab->freelist, &l->fnode); + __pcpu_freelist_push(&htab->freelist, &l->fnode); } else { atomic_dec(&htab->count); l->htab = htab; @@ -748,7 +748,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, } else { struct pcpu_freelist_node *l; - l = pcpu_freelist_pop(&htab->freelist); + l = __pcpu_freelist_pop(&htab->freelist); if (!l) return ERR_PTR(-E2BIG); l_new = container_of(l, struct htab_elem, fnode); diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c index 673fa6fe2d73..0c1b4ba9e90e 100644 --- a/kernel/bpf/percpu_freelist.c +++ b/kernel/bpf/percpu_freelist.c @@ -28,8 +28,8 @@ void pcpu_freelist_destroy(struct pcpu_freelist *s) free_percpu(s->freelist); } -static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head, - struct pcpu_freelist_node *node) +static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head, + struct pcpu_freelist_node *node) { raw_spin_lock(&head->lock); node->next = head->first; @@ -37,12 +37,22 @@ static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head, raw_spin_unlock(&head->lock); } -void pcpu_freelist_push(struct pcpu_freelist *s, +void __pcpu_freelist_push(struct pcpu_freelist *s, struct pcpu_freelist_node *node) { struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist); - __pcpu_freelist_push(head, node); + ___pcpu_freelist_push(head, node); +} + +void pcpu_freelist_push(struct pcpu_freelist *s, + struct pcpu_freelist_node *node) +{ + unsigned long flags; + + local_irq_save(flags); + __pcpu_freelist_push(s, node); + local_irq_restore(flags); } void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, @@ -63,7 +73,7 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, for_each_possible_cpu(cpu) { again: head = per_cpu_ptr(s->freelist, cpu); - __pcpu_freelist_push(head, buf); + ___pcpu_freelist_push(head, buf); i++; buf += elem_size; if (i == nr_elems) @@ -74,14 +84,12 @@ again: local_irq_restore(flags); } -struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) +struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) { struct pcpu_freelist_head *head; struct pcpu_freelist_node *node; - unsigned long flags; int orig_cpu, cpu; - local_irq_save(flags); orig_cpu = cpu = raw_smp_processor_id(); while (1) { head = per_cpu_ptr(s->freelist, cpu); @@ -89,16 +97,25 @@ struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) node = head->first; if (node) { head->first = node->next; - raw_spin_unlock_irqrestore(&head->lock, flags); + raw_spin_unlock(&head->lock); return node; } raw_spin_unlock(&head->lock); cpu = cpumask_next(cpu, cpu_possible_mask); if (cpu >= nr_cpu_ids) cpu = 0; - if (cpu == orig_cpu) { - local_irq_restore(flags); + if (cpu == orig_cpu) return NULL; - } } } + +struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) +{ + struct pcpu_freelist_node *ret; + unsigned long flags; + + local_irq_save(flags); + ret = __pcpu_freelist_pop(s); + local_irq_restore(flags); + return ret; +} diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h index 3049aae8ea1e..c3960118e617 100644 --- a/kernel/bpf/percpu_freelist.h +++ b/kernel/bpf/percpu_freelist.h @@ -22,8 +22,12 @@ struct pcpu_freelist_node { struct pcpu_freelist_node *next; }; +/* pcpu_freelist_* do spin_lock_irqsave. */ void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *); struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *); +/* __pcpu_freelist_* do spin_lock only. caller must disable irqs. */ +void __pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *); +struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *); void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, u32 nr_elems); int pcpu_freelist_init(struct pcpu_freelist *); -- cgit v1.2.3-70-g09d2 From 7c4cd051add3d00bbff008a133c936c515eaa8fe Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 30 Jan 2019 18:12:45 -0800 Subject: bpf: Fix syscall's stackmap lookup potential deadlock The map_lookup_elem used to not acquiring spinlock in order to optimize the reader. It was true until commit 557c0c6e7df8 ("bpf: convert stackmap to pre-allocation") The syscall's map_lookup_elem(stackmap) calls bpf_stackmap_copy(). bpf_stackmap_copy() may find the elem no longer needed after the copy is done. If that is the case, pcpu_freelist_push() saves this elem for reuse later. This push requires a spinlock. If a tracing bpf_prog got run in the middle of the syscall's map_lookup_elem(stackmap) and this tracing bpf_prog is calling bpf_get_stackid(stackmap) which also requires the same pcpu_freelist's spinlock, it may end up with a dead lock situation as reported by Eric Dumazet in https://patchwork.ozlabs.org/patch/1030266/ The situation is the same as the syscall's map_update_elem() which needs to acquire the pcpu_freelist's spinlock and could race with tracing bpf_prog. Hence, this patch fixes it by protecting bpf_stackmap_copy() with this_cpu_inc(bpf_prog_active) to prevent tracing bpf_prog from running. A later syscall's map_lookup_elem commit f1a2e44a3aec ("bpf: add queue and stack maps") also acquires a spinlock and races with tracing bpf_prog similarly. Hence, this patch is forward looking and protects the majority of the map lookups. bpf_map_offload_lookup_elem() is the exception since it is for network bpf_prog only (i.e. never called by tracing bpf_prog). Fixes: 557c0c6e7df8 ("bpf: convert stackmap to pre-allocation") Reported-by: Eric Dumazet Acked-by: Alexei Starovoitov Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/syscall.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b155cd17c1bd..8577bb7f8be6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -713,8 +713,13 @@ static int map_lookup_elem(union bpf_attr *attr) if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_lookup_elem(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + goto done; + } + + preempt_disable(); + this_cpu_inc(bpf_prog_active); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); @@ -744,7 +749,10 @@ static int map_lookup_elem(union bpf_attr *attr) } rcu_read_unlock(); } + this_cpu_dec(bpf_prog_active); + preempt_enable(); +done: if (err) goto free_value; -- cgit v1.2.3-70-g09d2 From d623876646be119439999a229a2c3ce30fd197fb Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 8 Feb 2019 22:25:54 -0800 Subject: bpf: Fix narrow load on a bpf_sock returned from sk_lookup() By adding this test to test_verifier: { "reference tracking: access sk->src_ip4 (narrow load)", .insns = { BPF_SK_LOOKUP, BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, src_ip4) + 2), BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), BPF_EMIT_CALL(BPF_FUNC_sk_release), BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = ACCEPT, }, The above test loads 2 bytes from sk->src_ip4 where sk is obtained by bpf_sk_lookup_tcp(). It hits an internal verifier error from convert_ctx_accesses(): [root@arch-fb-vm1 bpf]# ./test_verifier 665 665 Failed to load prog 'Invalid argument'! 0: (b7) r2 = 0 1: (63) *(u32 *)(r10 -8) = r2 2: (7b) *(u64 *)(r10 -16) = r2 3: (7b) *(u64 *)(r10 -24) = r2 4: (7b) *(u64 *)(r10 -32) = r2 5: (7b) *(u64 *)(r10 -40) = r2 6: (7b) *(u64 *)(r10 -48) = r2 7: (bf) r2 = r10 8: (07) r2 += -48 9: (b7) r3 = 36 10: (b7) r4 = 0 11: (b7) r5 = 0 12: (85) call bpf_sk_lookup_tcp#84 13: (bf) r6 = r0 14: (15) if r0 == 0x0 goto pc+3 R0=sock(id=1,off=0,imm=0) R6=sock(id=1,off=0,imm=0) R10=fp0,call_-1 fp-8=????0000 fp-16=0000mmmm fp-24=mmmmmmmm fp-32=mmmmmmmm fp-40=mmmmmmmm fp-48=mmmmmmmm refs=1 15: (69) r2 = *(u16 *)(r0 +26) 16: (bf) r1 = r6 17: (85) call bpf_sk_release#86 18: (95) exit from 14 to 18: safe processed 20 insns (limit 131072), stack depth 48 bpf verifier is misconfigured Summary: 0 PASSED, 0 SKIPPED, 1 FAILED The bpf_sock_is_valid_access() is expecting src_ip4 can be narrowly loaded (meaning load any 1 or 2 bytes of the src_ip4) by marking info->ctx_field_size. However, this marked ctx_field_size is not used. This patch fixes it. Due to the recent refactoring in test_verifier, this new test will be added to the bpf-next branch (together with the bpf_tcp_sock patchset) to avoid merge conflict. Fixes: c64b7983288e ("bpf: Add PTR_TO_SOCKET verifier type") Cc: Joe Stringer Signed-off-by: Martin KaFai Lau Acked-by: Joe Stringer Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 56674a7c3778..8f295b790297 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1617,12 +1617,13 @@ static int check_flow_keys_access(struct bpf_verifier_env *env, int off, return 0; } -static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, - int size, enum bpf_access_type t) +static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, + u32 regno, int off, int size, + enum bpf_access_type t) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; - struct bpf_insn_access_aux info; + struct bpf_insn_access_aux info = {}; if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", @@ -1636,6 +1637,8 @@ static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, return -EACCES; } + env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; + return 0; } @@ -2032,7 +2035,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn verbose(env, "cannot write into socket\n"); return -EACCES; } - err = check_sock_access(env, regno, off, size, t); + err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else { -- cgit v1.2.3-70-g09d2 From 3defaf2f15b2bfd86c6664181ac009e91985f8ac Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sun, 10 Feb 2019 12:52:35 -0800 Subject: bpf: fix lockdep false positive in stackmap Lockdep warns about false positive: [ 11.211460] ------------[ cut here ]------------ [ 11.211936] DEBUG_LOCKS_WARN_ON(depth <= 0) [ 11.211985] WARNING: CPU: 0 PID: 141 at ../kernel/locking/lockdep.c:3592 lock_release+0x1ad/0x280 [ 11.213134] Modules linked in: [ 11.214954] RIP: 0010:lock_release+0x1ad/0x280 [ 11.223508] Call Trace: [ 11.223705] [ 11.223874] ? __local_bh_enable+0x7a/0x80 [ 11.224199] up_read+0x1c/0xa0 [ 11.224446] do_up_read+0x12/0x20 [ 11.224713] irq_work_run_list+0x43/0x70 [ 11.225030] irq_work_run+0x26/0x50 [ 11.225310] smp_irq_work_interrupt+0x57/0x1f0 [ 11.225662] irq_work_interrupt+0xf/0x20 since rw_semaphore is released in a different task vs task that locked the sema. It is expected behavior. Fix the warning with up_read_non_owner() and rwsem_release() annotation. Fixes: bae77c5eb5b2 ("bpf: enable stackmap with build_id in nmi context") Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/stackmap.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index d43b14535827..950ab2f28922 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -44,7 +44,7 @@ static void do_up_read(struct irq_work *entry) struct stack_map_irq_work *work; work = container_of(entry, struct stack_map_irq_work, irq_work); - up_read(work->sem); + up_read_non_owner(work->sem); work->sem = NULL; } @@ -338,6 +338,12 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, } else { work->sem = ¤t->mm->mmap_sem; irq_work_queue(&work->irq_work); + /* + * The irq_work will release the mmap_sem with + * up_read_non_owner(). The rwsem_release() is called + * here to release the lock from lockdep's perspective. + */ + rwsem_release(¤t->mm->mmap_sem.dep_map, 1, _RET_IP_); } } -- cgit v1.2.3-70-g09d2 From 7c0cdf0b3940f63d9777c3fcf250a2f83859ca54 Mon Sep 17 00:00:00 2001 From: Alban Crequy Date: Fri, 22 Feb 2019 14:19:08 +0100 Subject: bpf, lpm: fix lookup bug in map_delete_elem trie_delete_elem() was deleting an entry even though it was not matching if the prefixlen was correct. This patch adds a check on matchlen. Reproducer: $ sudo bpftool map create /sys/fs/bpf/mylpm type lpm_trie key 8 value 1 entries 128 name mylpm flags 1 $ sudo bpftool map update pinned /sys/fs/bpf/mylpm key hex 10 00 00 00 aa bb cc dd value hex 01 $ sudo bpftool map dump pinned /sys/fs/bpf/mylpm key: 10 00 00 00 aa bb cc dd value: 01 Found 1 element $ sudo bpftool map delete pinned /sys/fs/bpf/mylpm key hex 10 00 00 00 ff ff ff ff $ echo $? 0 $ sudo bpftool map dump pinned /sys/fs/bpf/mylpm Found 0 elements A similar reproducer is added in the selftests. Without the patch: $ sudo ./tools/testing/selftests/bpf/test_lpm_map test_lpm_map: test_lpm_map.c:485: test_lpm_delete: Assertion `bpf_map_delete_elem(map_fd, key) == -1 && errno == ENOENT' failed. Aborted With the patch: test_lpm_map runs without errors. Fixes: e454cf595853 ("bpf: Implement map_delete_elem for BPF_MAP_TYPE_LPM_TRIE") Cc: Craig Gallek Signed-off-by: Alban Crequy Acked-by: Craig Gallek Signed-off-by: Daniel Borkmann --- kernel/bpf/lpm_trie.c | 1 + tools/testing/selftests/bpf/test_lpm_map.c | 10 ++++++++++ 2 files changed, 11 insertions(+) (limited to 'kernel/bpf') diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index abf1002080df..93a5cbbde421 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -471,6 +471,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key) } if (!node || node->prefixlen != key->prefixlen || + node->prefixlen != matchlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) { ret = -ENOENT; goto out; diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c index 147e34cfceb7..02d7c871862a 100644 --- a/tools/testing/selftests/bpf/test_lpm_map.c +++ b/tools/testing/selftests/bpf/test_lpm_map.c @@ -474,6 +474,16 @@ static void test_lpm_delete(void) assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 && errno == ENOENT); + key->prefixlen = 30; // unused prefix so far + inet_pton(AF_INET, "192.255.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == -1 && + errno == ENOENT); + + key->prefixlen = 16; // same prefix as the root node + inet_pton(AF_INET, "192.255.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == -1 && + errno == ENOENT); + /* assert initial lookup */ key->prefixlen = 32; inet_pton(AF_INET, "192.168.0.1", key->data); -- cgit v1.2.3-70-g09d2