From f2c67a3e60d1071b65848efaa8c3b66c363dd025 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 25 Jul 2023 10:42:05 +0200 Subject: [PATCH 1/5] bpf: Disable preemption in bpf_perf_event_output The nesting protection in bpf_perf_event_output relies on disabled preemption, which is guaranteed for kprobes and tracepoints. However bpf_perf_event_output can be also called from uprobes context through bpf_prog_run_array_sleepable function which disables migration, but keeps preemption enabled. This can cause task to be preempted by another one inside the nesting protection and lead eventually to two tasks using same perf_sample_data buffer and cause crashes like: kernel tried to execute NX-protected page - exploit attempt? (uid: 0) BUG: unable to handle page fault for address: ffffffff82be3eea ... Call Trace: ? __die+0x1f/0x70 ? page_fault_oops+0x176/0x4d0 ? exc_page_fault+0x132/0x230 ? asm_exc_page_fault+0x22/0x30 ? perf_output_sample+0x12b/0x910 ? perf_event_output+0xd0/0x1d0 ? bpf_perf_event_output+0x162/0x1d0 ? bpf_prog_c6271286d9a4c938_krava1+0x76/0x87 ? __uprobe_perf_func+0x12b/0x540 ? uprobe_dispatcher+0x2c4/0x430 ? uprobe_notify_resume+0x2da/0xce0 ? atomic_notifier_call_chain+0x7b/0x110 ? exit_to_user_mode_prepare+0x13e/0x290 ? irqentry_exit_to_user_mode+0x5/0x30 ? asm_exc_int3+0x35/0x40 Fixing this by disabling preemption in bpf_perf_event_output. Cc: stable@vger.kernel.org Fixes: 8c7dcb84e3b7 ("bpf: implement sleepable uprobes by chaining gps") Acked-by: Hou Tao Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20230725084206.580930-2-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- kernel/trace/bpf_trace.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 5f2dcabad202..bf18a53731b0 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -661,8 +661,7 @@ static DEFINE_PER_CPU(int, bpf_trace_nest_level); BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, u64, flags, void *, data, u64, size) { - struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds); - int nest_level = this_cpu_inc_return(bpf_trace_nest_level); + struct bpf_trace_sample_data *sds; struct perf_raw_record raw = { .frag = { .size = size, @@ -670,7 +669,11 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, }, }; struct perf_sample_data *sd; - int err; + int nest_level, err; + + preempt_disable(); + sds = this_cpu_ptr(&bpf_trace_sds); + nest_level = this_cpu_inc_return(bpf_trace_nest_level); if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) { err = -EBUSY; @@ -688,9 +691,9 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, perf_sample_save_raw_data(sd, &raw); err = __bpf_perf_event_output(regs, map, flags, sd); - out: this_cpu_dec(bpf_trace_nest_level); + preempt_enable(); return err; } From d62cc390c2e99ae267ffe4b8d7e2e08b6c758c32 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 25 Jul 2023 10:42:06 +0200 Subject: [PATCH 2/5] bpf: Disable preemption in bpf_event_output We received report [1] of kernel crash, which is caused by using nesting protection without disabled preemption. The bpf_event_output can be called by programs executed by bpf_prog_run_array_cg function that disabled migration but keeps preemption enabled. This can cause task to be preempted by another one inside the nesting protection and lead eventually to two tasks using same perf_sample_data buffer and cause crashes like: BUG: kernel NULL pointer dereference, address: 0000000000000001 #PF: supervisor instruction fetch in kernel mode #PF: error_code(0x0010) - not-present page ... ? perf_output_sample+0x12a/0x9a0 ? finish_task_switch.isra.0+0x81/0x280 ? perf_event_output+0x66/0xa0 ? bpf_event_output+0x13a/0x190 ? bpf_event_output_data+0x22/0x40 ? bpf_prog_dfc84bbde731b257_cil_sock4_connect+0x40a/0xacb ? xa_load+0x87/0xe0 ? __cgroup_bpf_run_filter_sock_addr+0xc1/0x1a0 ? release_sock+0x3e/0x90 ? sk_setsockopt+0x1a1/0x12f0 ? udp_pre_connect+0x36/0x50 ? inet_dgram_connect+0x93/0xa0 ? __sys_connect+0xb4/0xe0 ? udp_setsockopt+0x27/0x40 ? __pfx_udp_push_pending_frames+0x10/0x10 ? __sys_setsockopt+0xdf/0x1a0 ? __x64_sys_connect+0xf/0x20 ? do_syscall_64+0x3a/0x90 ? entry_SYSCALL_64_after_hwframe+0x72/0xdc Fixing this by disabling preemption in bpf_event_output. [1] https://github.com/cilium/cilium/issues/26756 Cc: stable@vger.kernel.org Reported-by: Oleg "livelace" Popov Closes: https://github.com/cilium/cilium/issues/26756 Fixes: 2a916f2f546c ("bpf: Use migrate_disable/enable in array macros and cgroup/lirc code.") Acked-by: Hou Tao Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20230725084206.580930-3-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- kernel/trace/bpf_trace.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index bf18a53731b0..bd1a42b23f3f 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -718,7 +718,6 @@ static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { - int nest_level = this_cpu_inc_return(bpf_event_output_nest_level); struct perf_raw_frag frag = { .copy = ctx_copy, .size = ctx_size, @@ -735,8 +734,12 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, }; struct perf_sample_data *sd; struct pt_regs *regs; + int nest_level; u64 ret; + preempt_disable(); + nest_level = this_cpu_inc_return(bpf_event_output_nest_level); + if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) { ret = -EBUSY; goto out; @@ -751,6 +754,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, ret = __bpf_perf_event_output(regs, map, flags, sd); out: this_cpu_dec(bpf_event_output_nest_level); + preempt_enable(); return ret; } From bcc29b7f5af6797702c2306a7aacb831fc5ce9cb Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Tue, 25 Jul 2023 10:33:30 +0800 Subject: [PATCH 3/5] bpf: Add length check for SK_DIAG_BPF_STORAGE_REQ_MAP_FD parsing The nla_for_each_nested parsing in function bpf_sk_storage_diag_alloc does not check the length of the nested attribute. This can lead to an out-of-attribute read and allow a malformed nlattr (e.g., length 0) to be viewed as a 4 byte integer. This patch adds an additional check when the nlattr is getting counted. This makes sure the latter nla_get_u32 can access the attributes with the correct length. Fixes: 1ed4d92458a9 ("bpf: INET_DIAG support in bpf_sk_storage") Suggested-by: Jakub Kicinski Signed-off-by: Lin Ma Reviewed-by: Jakub Kicinski Link: https://lore.kernel.org/r/20230725023330.422856-1-linma@zju.edu.cn Signed-off-by: Martin KaFai Lau --- net/core/bpf_sk_storage.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index d4172534dfa8..cca7594be92e 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -496,8 +496,11 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) return ERR_PTR(-EPERM); nla_for_each_nested(nla, nla_stgs, rem) { - if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) + if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) { + if (nla_len(nla) != sizeof(u32)) + return ERR_PTR(-EINVAL); nr_maps++; + } } diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL); From 640a604585aa30f93e39b17d4d6ba69fcb1e66c9 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Sat, 29 Jul 2023 17:51:06 +0800 Subject: [PATCH 4/5] bpf, cpumap: Make sure kthread is running before map update returns The following warning was reported when running stress-mode enabled xdp_redirect_cpu with some RT threads: ------------[ cut here ]------------ WARNING: CPU: 4 PID: 65 at kernel/bpf/cpumap.c:135 CPU: 4 PID: 65 Comm: kworker/4:1 Not tainted 6.5.0-rc2+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) Workqueue: events cpu_map_kthread_stop RIP: 0010:put_cpu_map_entry+0xda/0x220 ...... Call Trace: ? show_regs+0x65/0x70 ? __warn+0xa5/0x240 ...... ? put_cpu_map_entry+0xda/0x220 cpu_map_kthread_stop+0x41/0x60 process_one_work+0x6b0/0xb80 worker_thread+0x96/0x720 kthread+0x1a5/0x1f0 ret_from_fork+0x3a/0x70 ret_from_fork_asm+0x1b/0x30 The root cause is the same as commit 436901649731 ("bpf: cpumap: Fix memory leak in cpu_map_update_elem"). The kthread is stopped prematurely by kthread_stop() in cpu_map_kthread_stop(), and kthread() doesn't call cpu_map_kthread_run() at all but XDP program has already queued some frames or skbs into ptr_ring. So when __cpu_map_ring_cleanup() checks the ptr_ring, it will find it was not emptied and report a warning. An alternative fix is to use __cpu_map_ring_cleanup() to drop these pending frames or skbs when kthread_stop() returns -EINTR, but it may confuse the user, because these frames or skbs have been handled correctly by XDP program. So instead of dropping these frames or skbs, just make sure the per-cpu kthread is running before __cpu_map_entry_alloc() returns. After apply the fix, the error handle for kthread_stop() will be unnecessary because it will always return 0, so just remove it. Fixes: 6710e1126934 ("bpf: introduce new bpf cpu map type BPF_MAP_TYPE_CPUMAP") Signed-off-by: Hou Tao Reviewed-by: Pu Lehui Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20230729095107.1722450-2-houtao@huaweicloud.com Signed-off-by: Martin KaFai Lau --- kernel/bpf/cpumap.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 6ae02be7a48e..7eeb20025164 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -73,6 +74,7 @@ struct bpf_cpu_map_entry { struct rcu_head rcu; struct work_struct kthread_stop_wq; + struct completion kthread_running; }; struct bpf_cpu_map { @@ -153,7 +155,6 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) static void cpu_map_kthread_stop(struct work_struct *work) { struct bpf_cpu_map_entry *rcpu; - int err; rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); @@ -163,14 +164,7 @@ static void cpu_map_kthread_stop(struct work_struct *work) rcu_barrier(); /* kthread_stop will wake_up_process and wait for it to complete */ - err = kthread_stop(rcpu->kthread); - if (err) { - /* kthread_stop may be called before cpu_map_kthread_run - * is executed, so we need to release the memory related - * to rcpu. - */ - put_cpu_map_entry(rcpu); - } + kthread_stop(rcpu->kthread); } static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, @@ -298,11 +292,11 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, return nframes; } - static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; + complete(&rcpu->kthread_running); set_current_state(TASK_INTERRUPTIBLE); /* When kthread gives stop order, then rcpu have been disconnected @@ -467,6 +461,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, goto free_ptr_ring; /* Setup kthread */ + init_completion(&rcpu->kthread_running); rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, "cpumap/%d/map:%d", cpu, map->id); @@ -480,6 +475,12 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, kthread_bind(rcpu->kthread, cpu); wake_up_process(rcpu->kthread); + /* Make sure kthread has been running, so kthread_stop() will not + * stop the kthread prematurely and all pending frames or skbs + * will be handled by the kthread before kthread_stop() returns. + */ + wait_for_completion(&rcpu->kthread_running); + return rcpu; free_prog: From 7c62b75cd1a792e14b037fa4f61f9b18914e7de1 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Sat, 29 Jul 2023 17:51:07 +0800 Subject: [PATCH 5/5] bpf, cpumap: Handle skb as well when clean up ptr_ring The following warning was reported when running xdp_redirect_cpu with both skb-mode and stress-mode enabled: ------------[ cut here ]------------ Incorrect XDP memory type (-2128176192) usage WARNING: CPU: 7 PID: 1442 at net/core/xdp.c:405 Modules linked in: CPU: 7 PID: 1442 Comm: kworker/7:0 Tainted: G 6.5.0-rc2+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) Workqueue: events __cpu_map_entry_free RIP: 0010:__xdp_return+0x1e4/0x4a0 ...... Call Trace: ? show_regs+0x65/0x70 ? __warn+0xa5/0x240 ? __xdp_return+0x1e4/0x4a0 ...... xdp_return_frame+0x4d/0x150 __cpu_map_entry_free+0xf9/0x230 process_one_work+0x6b0/0xb80 worker_thread+0x96/0x720 kthread+0x1a5/0x1f0 ret_from_fork+0x3a/0x70 ret_from_fork_asm+0x1b/0x30 The reason for the warning is twofold. One is due to the kthread cpu_map_kthread_run() is stopped prematurely. Another one is __cpu_map_ring_cleanup() doesn't handle skb mode and treats skbs in ptr_ring as XDP frames. Prematurely-stopped kthread will be fixed by the preceding patch and ptr_ring will be empty when __cpu_map_ring_cleanup() is called. But as the comments in __cpu_map_ring_cleanup() said, handling and freeing skbs in ptr_ring as well to "catch any broken behaviour gracefully". Fixes: 11941f8a8536 ("bpf: cpumap: Implement generic cpumap") Signed-off-by: Hou Tao Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20230729095107.1722450-3-houtao@huaweicloud.com Signed-off-by: Martin KaFai Lau --- kernel/bpf/cpumap.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 7eeb20025164..286ab3db0fde 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -131,11 +131,17 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring) * invoked cpu_map_kthread_stop(). Catch any broken behaviour * gracefully and warn once. */ - struct xdp_frame *xdpf; + void *ptr; - while ((xdpf = ptr_ring_consume(ring))) - if (WARN_ON_ONCE(xdpf)) - xdp_return_frame(xdpf); + while ((ptr = ptr_ring_consume(ring))) { + WARN_ON_ONCE(1); + if (unlikely(__ptr_test_bit(0, &ptr))) { + __ptr_clear_bit(0, &ptr); + kfree_skb(ptr); + continue; + } + xdp_return_frame(ptr); + } } static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)