From 64aee2a965cf2954a038b5522f11d2cd2f0f8f3e Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 22 Jun 2017 15:41:38 +0100 Subject: perf/core: Fix group {cpu,task} validation Regardless of which events form a group, it does not make sense for the events to target different tasks and/or CPUs, as this leaves the group inconsistent and impossible to schedule. The core perf code assumes that these are consistent across (successfully intialised) groups. Core perf code only verifies this when moving SW events into a HW context. Thus, we can violate this requirement for pure SW groups and pure HW groups, unless the relevant PMU driver happens to perform this verification itself. These mismatched groups subsequently wreak havoc elsewhere. For example, we handle watchpoints as SW events, and reserve watchpoint HW on a per-CPU basis at pmu::event_init() time to ensure that any event that is initialised is guaranteed to have a slot at pmu::add() time. However, the core code only checks the group leader's cpu filter (via event_filter_match()), and can thus install follower events onto CPUs violating thier (mismatched) CPU filters, potentially installing them into a CPU without sufficient reserved slots. This can be triggered with the below test case, resulting in warnings from arch backends. #define _GNU_SOURCE #include #include #include #include #include #include #include static int perf_event_open(struct perf_event_attr *attr, pid_t pid, int cpu, int group_fd, unsigned long flags) { return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); } char watched_char; struct perf_event_attr wp_attr = { .type = PERF_TYPE_BREAKPOINT, .bp_type = HW_BREAKPOINT_RW, .bp_addr = (unsigned long)&watched_char, .bp_len = 1, .size = sizeof(wp_attr), }; int main(int argc, char *argv[]) { int leader, ret; cpu_set_t cpus; /* * Force use of CPU0 to ensure our CPU0-bound events get scheduled. */ CPU_ZERO(&cpus); CPU_SET(0, &cpus); ret = sched_setaffinity(0, sizeof(cpus), &cpus); if (ret) { printf("Unable to set cpu affinity\n"); return 1; } /* open leader event, bound to this task, CPU0 only */ leader = perf_event_open(&wp_attr, 0, 0, -1, 0); if (leader < 0) { printf("Couldn't open leader: %d\n", leader); return 1; } /* * Open a follower event that is bound to the same task, but a * different CPU. This means that the group should never be possible to * schedule. */ ret = perf_event_open(&wp_attr, 0, 1, leader, 0); if (ret < 0) { printf("Couldn't open mismatched follower: %d\n", ret); return 1; } else { printf("Opened leader/follower with mismastched CPUs\n"); } /* * Open as many independent events as we can, all bound to the same * task, CPU0 only. */ do { ret = perf_event_open(&wp_attr, 0, 0, -1, 0); } while (ret >= 0); /* * Force enable/disble all events to trigger the erronoeous * installation of the follower event. */ printf("Opened all events. Toggling..\n"); for (;;) { prctl(PR_TASK_PERF_EVENTS_DISABLE, 0, 0, 0, 0); prctl(PR_TASK_PERF_EVENTS_ENABLE, 0, 0, 0, 0); } return 0; } Fix this by validating this requirement regardless of whether we're moving events. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Zhou Chengming Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1498142498-15758-1-git-send-email-mark.rutland@arm.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 39 +++++++++++++++++++-------------------- 1 file changed, 19 insertions(+), 20 deletions(-) (limited to 'kernel/events') diff --git a/kernel/events/core.c b/kernel/events/core.c index ee20d4c546b5..3504125871d2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10032,28 +10032,27 @@ SYSCALL_DEFINE5(perf_event_open, goto err_context; /* - * Do not allow to attach to a group in a different - * task or CPU context: + * Make sure we're both events for the same CPU; + * grouping events for different CPUs is broken; since + * you can never concurrently schedule them anyhow. */ - if (move_group) { - /* - * Make sure we're both on the same task, or both - * per-cpu events. - */ - if (group_leader->ctx->task != ctx->task) - goto err_context; + if (group_leader->cpu != event->cpu) + goto err_context; - /* - * Make sure we're both events for the same CPU; - * grouping events for different CPUs is broken; since - * you can never concurrently schedule them anyhow. - */ - if (group_leader->cpu != event->cpu) - goto err_context; - } else { - if (group_leader->ctx != ctx) - goto err_context; - } + /* + * Make sure we're both on the same task, or both + * per-CPU events. + */ + if (group_leader->ctx->task != ctx->task) + goto err_context; + + /* + * Do not allow to attach to a group in a different task + * or CPU context. If we're moving SW events, we'll fix + * this up later, so allow that. + */ + if (!move_group && group_leader->ctx != ctx) + goto err_context; /* * Only a group leader can be exclusive or pinned -- cgit v1.2.3 From 355627f518978b5167256d27492fe0b343aaf2f2 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 31 Aug 2017 16:15:26 -0700 Subject: mm, uprobes: fix multiple free of ->uprobes_state.xol_area Commit 7c051267931a ("mm, fork: make dup_mmap wait for mmap_sem for write killable") made it possible to kill a forking task while it is waiting to acquire its ->mmap_sem for write, in dup_mmap(). However, it was overlooked that this introduced an new error path before the new mm_struct's ->uprobes_state.xol_area has been set to NULL after being copied from the old mm_struct by the memcpy in dup_mm(). For a task that has previously hit a uprobe tracepoint, this resulted in the 'struct xol_area' being freed multiple times if the task was killed at just the right time while forking. Fix it by setting ->uprobes_state.xol_area to NULL in mm_init() rather than in uprobe_dup_mmap(). With CONFIG_UPROBE_EVENTS=y, the bug can be reproduced by the same C program given by commit 2b7e8665b4ff ("fork: fix incorrect fput of ->exe_file causing use-after-free"), provided that a uprobe tracepoint has been set on the fork_thread() function. For example: $ gcc reproducer.c -o reproducer -lpthread $ nm reproducer | grep fork_thread 0000000000400719 t fork_thread $ echo "p $PWD/reproducer:0x719" > /sys/kernel/debug/tracing/uprobe_events $ echo 1 > /sys/kernel/debug/tracing/events/uprobes/enable $ ./reproducer Here is the use-after-free reported by KASAN: BUG: KASAN: use-after-free in uprobe_clear_state+0x1c4/0x200 Read of size 8 at addr ffff8800320a8b88 by task reproducer/198 CPU: 1 PID: 198 Comm: reproducer Not tainted 4.13.0-rc7-00015-g36fde05f3fb5 #255 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-20170228_101828-anatol 04/01/2014 Call Trace: dump_stack+0xdb/0x185 print_address_description+0x7e/0x290 kasan_report+0x23b/0x350 __asan_report_load8_noabort+0x19/0x20 uprobe_clear_state+0x1c4/0x200 mmput+0xd6/0x360 do_exit+0x740/0x1670 do_group_exit+0x13f/0x380 get_signal+0x597/0x17d0 do_signal+0x99/0x1df0 exit_to_usermode_loop+0x166/0x1e0 syscall_return_slowpath+0x258/0x2c0 entry_SYSCALL_64_fastpath+0xbc/0xbe ... Allocated by task 199: save_stack_trace+0x1b/0x20 kasan_kmalloc+0xfc/0x180 kmem_cache_alloc_trace+0xf3/0x330 __create_xol_area+0x10f/0x780 uprobe_notify_resume+0x1674/0x2210 exit_to_usermode_loop+0x150/0x1e0 prepare_exit_to_usermode+0x14b/0x180 retint_user+0x8/0x20 Freed by task 199: save_stack_trace+0x1b/0x20 kasan_slab_free+0xa8/0x1a0 kfree+0xba/0x210 uprobe_clear_state+0x151/0x200 mmput+0xd6/0x360 copy_process.part.8+0x605f/0x65d0 _do_fork+0x1a5/0xbd0 SyS_clone+0x19/0x20 do_syscall_64+0x22f/0x660 return_from_SYSCALL_64+0x0/0x7a Note: without KASAN, you may instead see a "Bad page state" message, or simply a general protection fault. Link: http://lkml.kernel.org/r/20170830033303.17927-1-ebiggers3@gmail.com Fixes: 7c051267931a ("mm, fork: make dup_mmap wait for mmap_sem for write killable") Signed-off-by: Eric Biggers Reported-by: Oleg Nesterov Acked-by: Oleg Nesterov Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Dmitry Vyukov Cc: Ingo Molnar Cc: Konstantin Khlebnikov Cc: Mark Rutland Cc: Michal Hocko Cc: Peter Zijlstra Cc: Vlastimil Babka Cc: [4.7+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/events/uprobes.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/events') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 0e137f98a50c..267f6ef91d97 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1262,8 +1262,6 @@ void uprobe_end_dup_mmap(void) void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm) { - newmm->uprobes_state.xol_area = NULL; - if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) { set_bit(MMF_HAS_UPROBES, &newmm->flags); /* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */ -- cgit v1.2.3