From 65d7aa7311bf3a61e7c3075d07ba0e7849fb2eee Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 26 Apr 2024 16:16:18 -0700 Subject: [PATCH 1/5] bpf: Add BPF_PROG_TYPE_CGROUP_SKB attach type enforcement in BPF_LINK_CREATE mainline inclusion from mainline-v6.10-rc1 commit 543576ec15b17c0c93301ac8297333c7b6e84ac7 category: bugfix issue: NA CVE: CVE-2024-38564 Signed-off-by: yaowenrui --------------------------------------- bpf_prog_attach uses attach_type_to_prog_type to enforce proper attach type for BPF_PROG_TYPE_CGROUP_SKB. link_create uses bpf_prog_get and relies on bpf_prog_attach_check_attach_type to properly verify prog_type <> attach_type association. Add missing attach_type enforcement for the link_create case. Otherwise, it's currently possible to attach cgroup_skb prog types to other cgroup hooks. Fixes: af6eea57437a ("bpf: Implement bpf_link-based cgroup BPF program attachment") Link: https://lore.kernel.org/bpf/0000000000004792a90615a1dde0@google.com/ Reported-by: syzbot+838346b979830606c854@syzkaller.appspotmail.com Signed-off-by: Stanislav Fomichev Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20240426231621.2716876-2-sdf@google.com Signed-off-by: Martin KaFai Lau Signed-off-by: yaowenrui --- kernel/bpf/syscall.c | 53 +++++++++++++++++++++++++------------------- 1 file changed, 30 insertions(+), 23 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index aaad2dce2be6..ec424fba0020 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2906,29 +2906,6 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) return err; } -static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, - enum bpf_attach_type attach_type) -{ - switch (prog->type) { - case BPF_PROG_TYPE_CGROUP_SOCK: - case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: - case BPF_PROG_TYPE_CGROUP_SOCKOPT: - case BPF_PROG_TYPE_SK_LOOKUP: - return attach_type == prog->expected_attach_type ? 0 : -EINVAL; - case BPF_PROG_TYPE_CGROUP_SKB: - if (!capable(CAP_NET_ADMIN)) - /* cg-skb progs can be loaded by unpriv user. - * check permissions at attach time. - */ - return -EPERM; - return prog->enforce_expected_attach_type && - prog->expected_attach_type != attach_type ? - -EINVAL : 0; - default: - return 0; - } -} - static enum bpf_prog_type attach_type_to_prog_type(enum bpf_attach_type attach_type) { @@ -2983,6 +2960,36 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) } } +static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, + enum bpf_attach_type attach_type) +{ + enum bpf_prog_type ptype; + + switch (prog->type) { + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + case BPF_PROG_TYPE_SK_LOOKUP: + return attach_type == prog->expected_attach_type ? 0 : -EINVAL; + case BPF_PROG_TYPE_CGROUP_SKB: + if (!capable(CAP_NET_ADMIN)) + /* cg-skb progs can be loaded by unpriv user. + * check permissions at attach time. + */ + return -EPERM; + + ptype = attach_type_to_prog_type(attach_type); + if (prog->type != ptype) + return -EINVAL; + + return prog->enforce_expected_attach_type && + prog->expected_attach_type != attach_type ? + -EINVAL : 0; + default: + return 0; + } +} + #define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd #define BPF_F_ATTACH_MASK \ -- Gitee From a3f6884a42de1720eb4681b311762511bc0f548f Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Fri, 10 May 2024 03:28:59 +0800 Subject: [PATCH 2/5] ftrace: Fix possible use-after-free issue in ftrace_location() mainline inclusion from mainline-v6.10-rc1 commit e60b613df8b6253def41215402f72986fee3fc8d category: bugfix issue: NA CVE: CVE-2024-38588 Signed-off-by: yaowenrui --------------------------------------- KASAN reports a bug: BUG: KASAN: use-after-free in ftrace_location+0x90/0x120 Read of size 8 at addr ffff888141d40010 by task insmod/424 CPU: 8 PID: 424 Comm: insmod Tainted: G W 6.9.0-rc2+ [...] Call Trace: dump_stack_lvl+0x68/0xa0 print_report+0xcf/0x610 kasan_report+0xb5/0xe0 ftrace_location+0x90/0x120 register_kprobe+0x14b/0xa40 kprobe_init+0x2d/0xff0 [kprobe_example] do_one_initcall+0x8f/0x2d0 do_init_module+0x13a/0x3c0 load_module+0x3082/0x33d0 init_module_from_file+0xd2/0x130 __x64_sys_finit_module+0x306/0x440 do_syscall_64+0x68/0x140 entry_SYSCALL_64_after_hwframe+0x71/0x79 The root cause is that, in lookup_rec(), ftrace record of some address is being searched in ftrace pages of some module, but those ftrace pages at the same time is being freed in ftrace_release_mod() as the corresponding module is being deleted: CPU1 | CPU2 register_kprobes() { | delete_module() { check_kprobe_address_safe() { | arch_check_ftrace_location() { | ftrace_location() { | lookup_rec() // USE! | ftrace_release_mod() // Free! To fix this issue: 1. Hold rcu lock as accessing ftrace pages in ftrace_location_range(); 2. Use ftrace_location_range() instead of lookup_rec() in ftrace_location(); 3. Call synchronize_rcu() before freeing any ftrace pages both in ftrace_process_locs()/ftrace_release_mod()/ftrace_free_mem(). Link: https://lore.kernel.org/linux-trace-kernel/20240509192859.1273558-1-zhengyejian1@huawei.com Cc: stable@vger.kernel.org Cc: Cc: Cc: Fixes: ae6aa16fdc16 ("kprobes: introduce ftrace based optimization") Suggested-by: Steven Rostedt Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) Signed-off-by: yaowenrui --- kernel/trace/ftrace.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 31fec924b7c4..8dcac51b492b 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1566,12 +1566,15 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end) unsigned long ftrace_location_range(unsigned long start, unsigned long end) { struct dyn_ftrace *rec; + unsigned long ip = 0; + rcu_read_lock(); rec = lookup_rec(start, end); if (rec) - return rec->ip; + ip = rec->ip; + rcu_read_unlock(); - return 0; + return ip; } /** @@ -6299,6 +6302,8 @@ static int ftrace_process_locs(struct module *mod, /* We should have used all pages unless we skipped some */ if (pg_unuse) { WARN_ON(!skipped); + /* Need to synchronize with ftrace_location_range() */ + synchronize_rcu(); ftrace_free_pages(pg_unuse); } return ret; @@ -6481,6 +6486,9 @@ void ftrace_release_mod(struct module *mod) out_unlock: mutex_unlock(&ftrace_lock); + /* Need to synchronize with ftrace_location_range() */ + if (tmp_page) + synchronize_rcu(); for (pg = tmp_page; pg; pg = tmp_page) { /* Needs to be called outside of ftrace_lock */ @@ -6803,6 +6811,7 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) unsigned long start = (unsigned long)(start_ptr); unsigned long end = (unsigned long)(end_ptr); struct ftrace_page **last_pg = &ftrace_pages_start; + struct ftrace_page *tmp_page = NULL; struct ftrace_page *pg; struct dyn_ftrace *rec; struct dyn_ftrace key; @@ -6846,12 +6855,8 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) ftrace_update_tot_cnt--; if (!pg->index) { *last_pg = pg->next; - if (pg->records) { - free_pages((unsigned long)pg->records, pg->order); - ftrace_number_of_pages -= 1 << pg->order; - } - ftrace_number_of_groups--; - kfree(pg); + pg->next = tmp_page; + tmp_page = pg; pg = container_of(last_pg, struct ftrace_page, next); if (!(*last_pg)) ftrace_pages = pg; @@ -6868,6 +6873,11 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) clear_func_from_hashes(func); kfree(func); } + /* Need to synchronize with ftrace_location_range() */ + if (tmp_page) { + synchronize_rcu(); + ftrace_free_pages(tmp_page); + } } void __init ftrace_free_init_mem(void) -- Gitee From 2aec86c4e995872b840a33198d232c19d517b3f1 Mon Sep 17 00:00:00 2001 From: Nikita Kiryushin Date: Wed, 27 Mar 2024 20:47:47 +0300 Subject: [PATCH 3/5] rcu-tasks: Fix show_rcu_tasks_trace_gp_kthread buffer overflow mainline inclusion from mainline-v6.10-rc1 commit cc5645fddb0ce28492b15520306d092730dffa48 category: bugfix issue: NA CVE: CVE-2024-38577 Signed-off-by: yaowenrui --------------------------------------- There is a possibility of buffer overflow in show_rcu_tasks_trace_gp_kthread() if counters, passed to sprintf() are huge. Counter numbers, needed for this are unrealistically high, but buffer overflow is still possible. Use snprintf() with buffer size instead of sprintf(). Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: edf3775f0ad6 ("rcu-tasks: Add count for idle tasks on offline CPUs") Signed-off-by: Nikita Kiryushin Reviewed-by: Steven Rostedt (Google) Signed-off-by: Paul E. McKenney Signed-off-by: Uladzislau Rezki (Sony) Signed-off-by: yaowenrui --- kernel/rcu/tasks.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index c5624ab0580c..9d1fd8024a9f 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -1238,7 +1238,7 @@ static void show_rcu_tasks_trace_gp_kthread(void) { char buf[64]; - sprintf(buf, "N%d h:%lu/%lu/%lu", atomic_read(&trc_n_readers_need_end), + snprintf(buf,sizeof(buf), "N%d h:%lu/%lu/%lu", atomic_read(&trc_n_readers_need_end), data_race(n_heavy_reader_ofl_updates), data_race(n_heavy_reader_updates), data_race(n_heavy_reader_attempts)); -- Gitee From 3ef131ff1ab3e26907e25a53962e6337647b912d Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Fri, 17 May 2024 15:40:08 +0200 Subject: [PATCH 4/5] ring-buffer: Fix a race between readers and resize checks stable inclusion from stable-5.10.219 commit 1e160196042cac946798ac192a0bc3398f1aa66b category: bugfix issue: NA CVE: CVE-2024-38601 Signed-off-by: yaowenrui --------------------------------------- commit c2274b908db05529980ec056359fae916939fdaa upstream. The reader code in rb_get_reader_page() swaps a new reader page into the ring buffer by doing cmpxchg on old->list.prev->next to point it to the new page. Following that, if the operation is successful, old->list.next->prev gets updated too. This means the underlying doubly-linked list is temporarily inconsistent, page->prev->next or page->next->prev might not be equal back to page for some page in the ring buffer. The resize operation in ring_buffer_resize() can be invoked in parallel. It calls rb_check_pages() which can detect the described inconsistency and stop further tracing: [ 190.271762] ------------[ cut here ]------------ [ 190.271771] WARNING: CPU: 1 PID: 6186 at kernel/trace/ring_buffer.c:1467 rb_check_pages.isra.0+0x6a/0xa0 [ 190.271789] Modules linked in: [...] [ 190.271991] Unloaded tainted modules: intel_uncore_frequency(E):1 skx_edac(E):1 [ 190.272002] CPU: 1 PID: 6186 Comm: cmd.sh Kdump: loaded Tainted: G E 6.9.0-rc6-default #5 158d3e1e6d0b091c34c3b96bfd99a1c58306d79f [ 190.272011] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552c-rebuilt.opensuse.org 04/01/2014 [ 190.272015] RIP: 0010:rb_check_pages.isra.0+0x6a/0xa0 [ 190.272023] Code: [...] [ 190.272028] RSP: 0018:ffff9c37463abb70 EFLAGS: 00010206 [ 190.272034] RAX: ffff8eba04b6cb80 RBX: 0000000000000007 RCX: ffff8eba01f13d80 [ 190.272038] RDX: ffff8eba01f130c0 RSI: ffff8eba04b6cd00 RDI: ffff8eba0004c700 [ 190.272042] RBP: ffff8eba0004c700 R08: 0000000000010002 R09: 0000000000000000 [ 190.272045] R10: 00000000ffff7f52 R11: ffff8eba7f600000 R12: ffff8eba0004c720 [ 190.272049] R13: ffff8eba00223a00 R14: 0000000000000008 R15: ffff8eba067a8000 [ 190.272053] FS: 00007f1bd64752c0(0000) GS:ffff8eba7f680000(0000) knlGS:0000000000000000 [ 190.272057] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 190.272061] CR2: 00007f1bd6662590 CR3: 000000010291e001 CR4: 0000000000370ef0 [ 190.272070] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 190.272073] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 190.272077] Call Trace: [ 190.272098] [ 190.272189] ring_buffer_resize+0x2ab/0x460 [ 190.272199] __tracing_resize_ring_buffer.part.0+0x23/0xa0 [ 190.272206] tracing_resize_ring_buffer+0x65/0x90 [ 190.272216] tracing_entries_write+0x74/0xc0 [ 190.272225] vfs_write+0xf5/0x420 [ 190.272248] ksys_write+0x67/0xe0 [ 190.272256] do_syscall_64+0x82/0x170 [ 190.272363] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 190.272373] RIP: 0033:0x7f1bd657d263 [ 190.272381] Code: [...] [ 190.272385] RSP: 002b:00007ffe72b643f8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 190.272391] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007f1bd657d263 [ 190.272395] RDX: 0000000000000002 RSI: 0000555a6eb538e0 RDI: 0000000000000001 [ 190.272398] RBP: 0000555a6eb538e0 R08: 000000000000000a R09: 0000000000000000 [ 190.272401] R10: 0000555a6eb55190 R11: 0000000000000246 R12: 00007f1bd6662500 [ 190.272404] R13: 0000000000000002 R14: 00007f1bd6667c00 R15: 0000000000000002 [ 190.272412] [ 190.272414] ---[ end trace 0000000000000000 ]--- Note that ring_buffer_resize() calls rb_check_pages() only if the parent trace_buffer has recording disabled. Recent commit d78ab792705c ("tracing: Stop current tracer when resizing buffer") causes that it is now always the case which makes it more likely to experience this issue. The window to hit this race is nonetheless very small. To help reproducing it, one can add a delay loop in rb_get_reader_page(): ret = rb_head_page_replace(reader, cpu_buffer->reader_page); if (!ret) goto spin; for (unsigned i = 0; i < 1U << 26; i++) /* inserted delay loop */ __asm__ __volatile__ ("" : : : "memory"); rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list; .. and then run the following commands on the target system: echo 1 > /sys/kernel/tracing/events/sched/sched_switch/enable while true; do echo 16 > /sys/kernel/tracing/buffer_size_kb; sleep 0.1 echo 8 > /sys/kernel/tracing/buffer_size_kb; sleep 0.1 done & while true; do for i in /sys/kernel/tracing/per_cpu/*; do timeout 0.1 cat $i/trace_pipe; sleep 0.2 done done To fix the problem, make sure ring_buffer_resize() doesn't invoke rb_check_pages() concurrently with a reader operating on the same ring_buffer_per_cpu by taking its cpu_buffer->reader_lock. Link: https://lore.kernel.org/linux-trace-kernel/20240517134008.24529-3-petr.pavlu@suse.com Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Fixes: 659f451ff213 ("ring-buffer: Add integrity check at end of iter read") Signed-off-by: Petr Pavlu [ Fixed whitespace ] Signed-off-by: Steven Rostedt (Google) Signed-off-by: Greg Kroah-Hartman Signed-off-by: yaowenrui --- kernel/trace/ring_buffer.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 0938222b4598..9aad6526946c 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1463,6 +1463,11 @@ static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer, * * As a safety measure we check to make sure the data pages have not * been corrupted. + * + * Callers of this function need to guarantee that the list of pages doesn't get + * modified during the check. In particular, if it's possible that the function + * is invoked with concurrent readers which can swap in a new reader page then + * the caller should take cpu_buffer->reader_lock. */ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) { @@ -2185,8 +2190,12 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, */ synchronize_rcu(); for_each_buffer_cpu(buffer, cpu) { + unsigned long flags; + cpu_buffer = buffer->buffers[cpu]; + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); rb_check_pages(cpu_buffer); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } atomic_dec(&buffer->record_disabled); } -- Gitee From 826803e325c5ea854780448480af8119fd046c6e Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 9 May 2024 01:14:46 -0700 Subject: [PATCH 5/5] af_unix: Fix data races in unix_release_sock/unix_stream_sendmsg stable inclusion from stable-5.10.219 commit 4d51845d734a4c5d079e56e0916f936a55e15055 category: bugfix issue: NA CVE: CVE-2024-38596 Signed-off-by: yaowenrui --------------------------------------- [ Upstream commit 540bf24fba16b88c1b3b9353927204b4f1074e25 ] A data-race condition has been identified in af_unix. In one data path, the write function unix_release_sock() atomically writes to sk->sk_shutdown using WRITE_ONCE. However, on the reader side, unix_stream_sendmsg() does not read it atomically. Consequently, this issue is causing the following KCSAN splat to occur: BUG: KCSAN: data-race in unix_release_sock / unix_stream_sendmsg write (marked) to 0xffff88867256ddbb of 1 bytes by task 7270 on cpu 28: unix_release_sock (net/unix/af_unix.c:640) unix_release (net/unix/af_unix.c:1050) sock_close (net/socket.c:659 net/socket.c:1421) __fput (fs/file_table.c:422) __fput_sync (fs/file_table.c:508) __se_sys_close (fs/open.c:1559 fs/open.c:1541) __x64_sys_close (fs/open.c:1541) x64_sys_call (arch/x86/entry/syscall_64.c:33) do_syscall_64 (arch/x86/entry/common.c:?) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) read to 0xffff88867256ddbb of 1 bytes by task 989 on cpu 14: unix_stream_sendmsg (net/unix/af_unix.c:2273) __sock_sendmsg (net/socket.c:730 net/socket.c:745) ____sys_sendmsg (net/socket.c:2584) __sys_sendmmsg (net/socket.c:2638 net/socket.c:2724) __x64_sys_sendmmsg (net/socket.c:2753 net/socket.c:2750 net/socket.c:2750) x64_sys_call (arch/x86/entry/syscall_64.c:33) do_syscall_64 (arch/x86/entry/common.c:?) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) value changed: 0x01 -> 0x03 The line numbers are related to commit dd5a440a31fa ("Linux 6.9-rc7"). Commit e1d09c2c2f57 ("af_unix: Fix data races around sk->sk_shutdown.") addressed a comparable issue in the past regarding sk->sk_shutdown. However, it overlooked resolving this particular data path. This patch only offending unix_stream_sendmsg() function, since the other reads seem to be protected by unix_state_lock() as discussed in Link: https://lore.kernel.org/all/20240508173324.53565-1-kuniyu@amazon.com/ Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Breno Leitao Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20240509081459.2807828-1-leitao@debian.org Signed-off-by: Jakub Kicinski Signed-off-by: Sasha Levin Signed-off-by: yaowenrui --- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 237488b1b58b..75d7221cd8cf 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1920,7 +1920,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto out_err; } - if (sk->sk_shutdown & SEND_SHUTDOWN) + if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) goto pipe_err; while (sent < len) { -- Gitee