From 1da6c4d9140cb7c13e87667dc4e1488d6c8fc10f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 25 Mar 2019 15:54:43 +0100 Subject: bpf: fix use after free in bpf_evict_inode syzkaller was able to generate the following UAF in bpf: BUG: KASAN: use-after-free in lookup_last fs/namei.c:2269 [inline] BUG: KASAN: use-after-free in path_lookupat.isra.43+0x9f8/0xc00 fs/namei.c:2318 Read of size 1 at addr ffff8801c4865c47 by task syz-executor2/9423 CPU: 0 PID: 9423 Comm: syz-executor2 Not tainted 4.20.0-rc1-next-20181109+ #110 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+0x244/0x39d lib/dump_stack.c:113 print_address_description.cold.7+0x9/0x1ff mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report.cold.8+0x242/0x309 mm/kasan/report.c:412 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:430 lookup_last fs/namei.c:2269 [inline] path_lookupat.isra.43+0x9f8/0xc00 fs/namei.c:2318 filename_lookup+0x26a/0x520 fs/namei.c:2348 user_path_at_empty+0x40/0x50 fs/namei.c:2608 user_path include/linux/namei.h:62 [inline] do_mount+0x180/0x1ff0 fs/namespace.c:2980 ksys_mount+0x12d/0x140 fs/namespace.c:3258 __do_sys_mount fs/namespace.c:3272 [inline] __se_sys_mount fs/namespace.c:3269 [inline] __x64_sys_mount+0xbe/0x150 fs/namespace.c:3269 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457569 Code: fd b3 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 cb b3 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fde6ed96c78 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 0000000000457569 RDX: 0000000020000040 RSI: 0000000020000000 RDI: 0000000000000000 RBP: 000000000072bf00 R08: 0000000020000340 R09: 0000000000000000 R10: 0000000000200000 R11: 0000000000000246 R12: 00007fde6ed976d4 R13: 00000000004c2c24 R14: 00000000004d4990 R15: 00000000ffffffff Allocated by task 9424: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] kasan_kmalloc+0xc7/0xe0 mm/kasan/kasan.c:553 __do_kmalloc mm/slab.c:3722 [inline] __kmalloc_track_caller+0x157/0x760 mm/slab.c:3737 kstrdup+0x39/0x70 mm/util.c:49 bpf_symlink+0x26/0x140 kernel/bpf/inode.c:356 vfs_symlink+0x37a/0x5d0 fs/namei.c:4127 do_symlinkat+0x242/0x2d0 fs/namei.c:4154 __do_sys_symlink fs/namei.c:4173 [inline] __se_sys_symlink fs/namei.c:4171 [inline] __x64_sys_symlink+0x59/0x80 fs/namei.c:4171 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 9425: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/kasan.c:521 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528 __cache_free mm/slab.c:3498 [inline] kfree+0xcf/0x230 mm/slab.c:3817 bpf_evict_inode+0x11f/0x150 kernel/bpf/inode.c:565 evict+0x4b9/0x980 fs/inode.c:558 iput_final fs/inode.c:1550 [inline] iput+0x674/0xa90 fs/inode.c:1576 do_unlinkat+0x733/0xa30 fs/namei.c:4069 __do_sys_unlink fs/namei.c:4110 [inline] __se_sys_unlink fs/namei.c:4108 [inline] __x64_sys_unlink+0x42/0x50 fs/namei.c:4108 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe In this scenario path lookup under RCU is racing with the final unlink in case of symlinks. As Linus puts it in his analysis: [...] We actually RCU-delay the inode freeing itself, but when we do the final iput(), the "evict()" function is called synchronously. Now, the simple fix would seem to just RCU-delay the kfree() of the symlink data in bpf_evict_inode(). Maybe that's the right thing to do. [...] Al suggested to piggy-back on the ->destroy_inode() callback in order to implement RCU deferral there which can then kfree() the inode->i_link eventually right before putting inode back into inode cache. By reusing free_inode_nonrcu() from there we can avoid the need for our own inode cache and just reuse generic one as we currently do. And in-fact on top of all this we should just get rid of the bpf_evict_inode() entirely. This means truncate_inode_pages_final() and clear_inode() will then simply be called by the fs core via evict(). Dropping the reference should really only be done when inode is unhashed and nothing reachable anymore, so it's better also moved into the final ->destroy_inode() callback. Fixes: 0f98621bef5d ("bpf, inode: add support for symlinks and fix mtime/ctime") Reported-by: syzbot+fb731ca573367b7f6564@syzkaller.appspotmail.com Reported-by: syzbot+a13e5ead792d6df37818@syzkaller.appspotmail.com Reported-by: syzbot+7a8ba368b47fdefca61e@syzkaller.appspotmail.com Suggested-by: Al Viro Analyzed-by: Linus Torvalds Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Linus Torvalds Acked-by: Al Viro Link: https://lore.kernel.org/lkml/0000000000006946d2057bbd0eef@google.com/T/ --- kernel/bpf/inode.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 2ada5e21dfa6..4a8f390a2b82 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -554,19 +554,6 @@ struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type typ } EXPORT_SYMBOL(bpf_prog_get_type_path); -static void bpf_evict_inode(struct inode *inode) -{ - enum bpf_type type; - - truncate_inode_pages_final(&inode->i_data); - clear_inode(inode); - - if (S_ISLNK(inode->i_mode)) - kfree(inode->i_link); - if (!bpf_inode_type(inode, &type)) - bpf_any_put(inode->i_private, type); -} - /* * Display the mount options in /proc/mounts. */ @@ -579,11 +566,28 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) return 0; } +static void bpf_destroy_inode_deferred(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + enum bpf_type type; + + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_link); + if (!bpf_inode_type(inode, &type)) + bpf_any_put(inode->i_private, type); + free_inode_nonrcu(inode); +} + +static void bpf_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, bpf_destroy_inode_deferred); +} + static const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, - .evict_inode = bpf_evict_inode, + .destroy_inode = bpf_destroy_inode, }; enum { -- cgit v1.2.3 From 927cb78177ae3773d0d27404566a93cb8e88890c Mon Sep 17 00:00:00 2001 From: Paul Chaignon Date: Wed, 20 Mar 2019 13:58:27 +0100 Subject: bpf: remove incorrect 'verifier bug' warning The BPF verifier checks the maximum number of call stack frames twice, first in the main CFG traversal (do_check) and then in a subsequent traversal (check_max_stack_depth). If the second check fails, it logs a 'verifier bug' warning and errors out, as the number of call stack frames should have been verified already. However, the second check may fail without indicating a verifier bug: if the excessive function calls reside in dead code, the main CFG traversal may not visit them; the subsequent traversal visits all instructions, including dead code. This case raises the question of how invalid dead code should be treated. This patch implements the conservative option and rejects such code. Signed-off-by: Paul Chaignon Tested-by: Xiao Han Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fd502c1f71eb..6c5a41f7f338 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1897,8 +1897,9 @@ continue_func: } frame++; if (frame >= MAX_CALL_FRAMES) { - WARN_ONCE(1, "verifier bug. Call stack is too deep\n"); - return -EFAULT; + verbose(env, "the call stack of %d frames is too deep !\n", + frame); + return -E2BIG; } goto process_func; } -- cgit v1.2.3 From 7dd47617114921fdd8c095509e5e7b4373cc44a1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 26 Mar 2019 22:51:02 +0100 Subject: watchdog: Respect watchdog cpumask on CPU hotplug The rework of the watchdog core to use cpu_stop_work broke the watchdog cpumask on CPU hotplug. The watchdog_enable/disable() functions are now called unconditionally from the hotplug callback, i.e. even on CPUs which are not in the watchdog cpumask. As a consequence the watchdog can become unstoppable. Only invoke them when the plugged CPU is in the watchdog cpumask. Fixes: 9cf57731b63e ("watchdog/softlockup: Replace "watchdog/%u" threads with cpu_stop_work") Reported-by: Maxime Coquelin Signed-off-by: Thomas Gleixner Tested-by: Maxime Coquelin Cc: Peter Zijlstra Cc: Oleg Nesterov Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Don Zickus Cc: Ricardo Neri Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1903262245490.1789@nanos.tec.linutronix.de --- kernel/watchdog.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 403c9bd90413..6a5787233113 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -554,13 +554,15 @@ static void softlockup_start_all(void) int lockup_detector_online_cpu(unsigned int cpu) { - watchdog_enable(cpu); + if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) + watchdog_enable(cpu); return 0; } int lockup_detector_offline_cpu(unsigned int cpu) { - watchdog_disable(cpu); + if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) + watchdog_disable(cpu); return 0; } -- cgit v1.2.3 From 206b92353c839c0b27a0b9bec24195f93fd6cf7a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 26 Mar 2019 17:36:05 +0100 Subject: cpu/hotplug: Prevent crash when CPU bringup fails on CONFIG_HOTPLUG_CPU=n Tianyu reported a crash in a CPU hotplug teardown callback when booting a kernel which has CONFIG_HOTPLUG_CPU disabled with the 'nosmt' boot parameter. It turns out that the SMP=y CONFIG_HOTPLUG_CPU=n case has been broken forever in case that a bringup callback fails. Unfortunately this issue was not recognized when the CPU hotplug code was reworked, so the shortcoming just stayed in place. When a bringup callback fails, the CPU hotplug code rolls back the operation and takes the CPU offline. The 'nosmt' command line argument uses a bringup failure to abort the bringup of SMT sibling CPUs. This partial bringup is required due to the MCE misdesign on Intel CPUs. With CONFIG_HOTPLUG_CPU=y the rollback works perfectly fine, but CONFIG_HOTPLUG_CPU=n lacks essential mechanisms to exercise the low level teardown of a CPU including the synchronizations in various facilities like RCU, NOHZ and others. As a consequence the teardown callbacks which must be executed on the outgoing CPU within stop machine with interrupts disabled are executed on the control CPU in interrupt enabled and preemptible context causing the kernel to crash and burn. The pre state machine code has a different failure mode which is more subtle and resulting in a less obvious use after free crash because the control side frees resources which are still in use by the undead CPU. But this is not a x86 only problem. Any architecture which supports the SMP=y HOTPLUG_CPU=n combination suffers from the same issue. It's just less likely to be triggered because in 99.99999% of the cases all bringup callbacks succeed. The easy solution of making HOTPLUG_CPU mandatory for SMP is not working on all architectures as the following architectures have either no hotplug support at all or not all subarchitectures support it: alpha, arc, hexagon, openrisc, riscv, sparc (32bit), mips (partial). Crashing the kernel in such a situation is not an acceptable state either. Implement a minimal rollback variant by limiting the teardown to the point where all regular teardown callbacks have been invoked and leave the CPU in the 'dead' idle state. This has the following consequences: - the CPU is brought down to the point where the stop_machine takedown would happen. - the CPU stays there forever and is idle - The CPU is cleared in the CPU active mask, but not in the CPU online mask which is a legit state. - Interrupts are not forced away from the CPU - All facilities which only look at online mask would still see it, but that is the case during normal hotplug/unplug operations as well. It's just a (way) longer time frame. This will expose issues, which haven't been exposed before or only seldom, because now the normally transient state of being non active but online is a permanent state. In testing this exposed already an issue vs. work queues where the vmstat code schedules work on the almost dead CPU which ends up in an unbound workqueue and triggers 'preemtible context' warnings. This is not a problem of this change, it merily exposes an already existing issue. Still this is better than crashing fully without a chance to debug it. This is mainly thought as workaround for those architectures which do not support HOTPLUG_CPU. All others should enforce HOTPLUG_CPU for SMP. Fixes: 2e1a3483ce74 ("cpu/hotplug: Split out the state walk into functions") Reported-by: Tianyu Lan Signed-off-by: Thomas Gleixner Tested-by: Tianyu Lan Acked-by: Greg Kroah-Hartman Cc: Konrad Wilk Cc: Josh Poimboeuf Cc: Mukesh Ojha Cc: Peter Zijlstra Cc: Jiri Kosina Cc: Rik van Riel Cc: Andy Lutomirski Cc: Micheal Kelley Cc: "K. Y. Srinivasan" Cc: Linus Torvalds Cc: Borislav Petkov Cc: K. Y. Srinivasan Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20190326163811.503390616@linutronix.de --- kernel/cpu.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cpu.c b/kernel/cpu.c index 025f419d16f6..6754f3ecfd94 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -564,6 +564,20 @@ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } +static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) +{ + if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return true; + /* + * When CPU hotplug is disabled, then taking the CPU down is not + * possible because takedown_cpu() and the architecture and + * subsystem specific mechanisms are not available. So the CPU + * which would be completely unplugged again needs to stay around + * in the current state. + */ + return st->state <= CPUHP_BRINGUP_CPU; +} + static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { @@ -574,8 +588,10 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, st->state++; ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); if (ret) { - st->target = prev_state; - undo_cpu_up(cpu, st); + if (can_rollback_cpu(st)) { + st->target = prev_state; + undo_cpu_up(cpu, st); + } break; } } -- cgit v1.2.3 From fcfc2aa0185f4a731d05a21e9f359968fdfd02e7 Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Thu, 28 Mar 2019 20:44:13 -0700 Subject: ptrace: take into account saved_sigmask in PTRACE{GET,SET}SIGMASK There are a few system calls (pselect, ppoll, etc) which replace a task sigmask while they are running in a kernel-space When a task calls one of these syscalls, the kernel saves a current sigmask in task->saved_sigmask and sets a syscall sigmask. On syscall-exit-stop, ptrace traps a task before restoring the saved_sigmask, so PTRACE_GETSIGMASK returns the syscall sigmask and PTRACE_SETSIGMASK does nothing, because its sigmask is replaced by saved_sigmask, when the task returns to user-space. This patch fixes this problem. PTRACE_GETSIGMASK returns saved_sigmask if it's set. PTRACE_SETSIGMASK drops the TIF_RESTORE_SIGMASK flag. Link: http://lkml.kernel.org/r/20181120060616.6043-1-avagin@gmail.com Fixes: 29000caecbe8 ("ptrace: add ability to get/set signal-blocked mask") Signed-off-by: Andrei Vagin Acked-by: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/ptrace.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 771e93f9c43f..6f357f4fc859 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -29,6 +29,7 @@ #include #include #include +#include /* * Access another process' address space via ptrace. @@ -924,18 +925,26 @@ int ptrace_request(struct task_struct *child, long request, ret = ptrace_setsiginfo(child, &siginfo); break; - case PTRACE_GETSIGMASK: + case PTRACE_GETSIGMASK: { + sigset_t *mask; + if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } - if (copy_to_user(datavp, &child->blocked, sizeof(sigset_t))) + if (test_tsk_restore_sigmask(child)) + mask = &child->saved_sigmask; + else + mask = &child->blocked; + + if (copy_to_user(datavp, mask, sizeof(sigset_t))) ret = -EFAULT; else ret = 0; break; + } case PTRACE_SETSIGMASK: { sigset_t new_set; @@ -961,6 +970,8 @@ int ptrace_request(struct task_struct *child, long request, child->blocked = new_set; spin_unlock_irq(&child->sighand->siglock); + clear_tsk_restore_sigmask(child); + ret = 0; break; } -- cgit v1.2.3 From 676e4a6fe703f2dae699ee9d56f14516f9ada4ea Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Fri, 29 Mar 2019 10:18:00 +0100 Subject: xdp: fix cpumap redirect SKB creation bug We want to avoid leaking pointer info from xdp_frame (that is placed in top of frame) like commit 6dfb970d3dbd ("xdp: avoid leaking info stored in frame data on page reuse"), and followup commit 97e19cce05e5 ("bpf: reserve xdp_frame size in xdp headroom") that reserve this headroom. These changes also affected how cpumap constructed SKBs, as xdpf->headroom size changed, the skb data starting point were in-effect shifted with 32 bytes (sizeof xdp_frame). This was still okay, as the cpumap frame_size calculation also included xdpf->headroom which were reduced by same amount. A bug was introduced in commit 77ea5f4cbe20 ("bpf/cpumap: make sure frame_size for build_skb is aligned if headroom isn't"), where the xdpf->headroom became part of the SKB_DATA_ALIGN rounding up. This round-up to find the frame_size is in principle still correct as it does not exceed the 2048 bytes frame_size (which is max for ixgbe and i40e), but the 32 bytes offset of pkt_data_start puts this over the 2048 bytes limit. This cause skb_shared_info to spill into next frame. It is a little hard to trigger, as the SKB need to use above 15 skb_shinfo->frags[] as far as I calculate. This does happen in practise for TCP streams when skb_try_coalesce() kicks in. KASAN can be used to detect these wrong memory accesses, I've seen: BUG: KASAN: use-after-free in skb_try_coalesce+0x3cb/0x760 BUG: KASAN: wild-memory-access in skb_release_data+0xe2/0x250 Driver veth also construct a SKB from xdp_frame in this way, but is not affected, as it doesn't reserve/deduct the room (used by xdp_frame) from the SKB headroom. Instead is clears the pointers via xdp_scrub_frame(), and allows SKB to use this area. The fix in this patch is to do like veth and instead allow SKB to (re)use the area occupied by xdp_frame, by clearing via xdp_scrub_frame(). (This does kill the idea of the SKB being able to access (mem) info from this area, but I guess it was a bad idea anyhow, and it was already killed by the veth changes.) Fixes: 77ea5f4cbe20 ("bpf/cpumap: make sure frame_size for build_skb is aligned if headroom isn't") Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov --- kernel/bpf/cpumap.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 8974b3755670..3c18260403dd 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -162,10 +162,14 @@ static void cpu_map_kthread_stop(struct work_struct *work) static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { + unsigned int hard_start_headroom; unsigned int frame_size; void *pkt_data_start; struct sk_buff *skb; + /* Part of headroom was reserved to xdpf */ + hard_start_headroom = sizeof(struct xdp_frame) + xdpf->headroom; + /* build_skb need to place skb_shared_info after SKB end, and * also want to know the memory "truesize". Thus, need to * know the memory frame size backing xdp_buff. @@ -183,15 +187,15 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * is not at a fixed memory location, with mixed length * packets, which is bad for cache-line hotness. */ - frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) + + frame_size = SKB_DATA_ALIGN(xdpf->len + hard_start_headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - pkt_data_start = xdpf->data - xdpf->headroom; + pkt_data_start = xdpf->data - hard_start_headroom; skb = build_skb(pkt_data_start, frame_size); if (!skb) return NULL; - skb_reserve(skb, xdpf->headroom); + skb_reserve(skb, hard_start_headroom); __skb_put(skb, xdpf->len); if (xdpf->metasize) skb_metadata_set(skb, xdpf->metasize); @@ -205,6 +209,9 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * - RX ring dev queue index (skb_record_rx_queue) */ + /* Allow SKB to reuse area used by xdp_frame */ + xdp_scrub_frame(xdpf); + return skb; } -- cgit v1.2.3 From 556a888a14afe27164191955618990fb3ccc9aad Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Sat, 30 Mar 2019 03:12:32 +0100 Subject: signal: don't silently convert SI_USER signals to non-current pidfd The current sys_pidfd_send_signal() silently turns signals with explicit SI_USER context that are sent to non-current tasks into signals with kernel-generated siginfo. This is unlike do_rt_sigqueueinfo(), which returns -EPERM in this case. If a user actually wants to send a signal with kernel-provided siginfo, they can do that with pidfd_send_signal(pidfd, sig, NULL, 0); so allowing this case is unnecessary. Instead of silently replacing the siginfo, just bail out with an error; this is consistent with other interfaces and avoids special-casing behavior based on security checks. Fixes: 3eb39f47934f ("signal: add pidfd_send_signal() syscall") Signed-off-by: Jann Horn Signed-off-by: Christian Brauner --- kernel/signal.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index b7953934aa99..f98448cf2def 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3605,16 +3605,11 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, if (unlikely(sig != kinfo.si_signo)) goto err; + /* Only allow sending arbitrary signals to yourself. */ + ret = -EPERM; if ((task_pid(current) != pid) && - (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) { - /* Only allow sending arbitrary signals to yourself. */ - ret = -EPERM; - if (kinfo.si_code != SI_USER) - goto err; - - /* Turn this into a regular kill signal. */ - prepare_kill_siginfo(sig, &kinfo); - } + (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) + goto err; } else { prepare_kill_siginfo(sig, &kinfo); } -- cgit v1.2.3