--- /dev/null
+From 676caba86c8acd2fa2f65468b343481a7f360222 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 4 Jun 2025 00:55:33 +0000
+Subject: arm64/ptrace: Fix stack-out-of-bounds read in
+ regs_get_kernel_stack_nth()
+
+From: Tengda Wu <wutengda@huaweicloud.com>
+
+[ Upstream commit 39dfc971e42d886e7df01371cd1bef505076d84c ]
+
+KASAN reports a stack-out-of-bounds read in regs_get_kernel_stack_nth().
+
+Call Trace:
+[ 97.283505] BUG: KASAN: stack-out-of-bounds in regs_get_kernel_stack_nth+0xa8/0xc8
+[ 97.284677] Read of size 8 at addr ffff800089277c10 by task 1.sh/2550
+[ 97.285732]
+[ 97.286067] CPU: 7 PID: 2550 Comm: 1.sh Not tainted 6.6.0+ #11
+[ 97.287032] Hardware name: linux,dummy-virt (DT)
+[ 97.287815] Call trace:
+[ 97.288279] dump_backtrace+0xa0/0x128
+[ 97.288946] show_stack+0x20/0x38
+[ 97.289551] dump_stack_lvl+0x78/0xc8
+[ 97.290203] print_address_description.constprop.0+0x84/0x3c8
+[ 97.291159] print_report+0xb0/0x280
+[ 97.291792] kasan_report+0x84/0xd0
+[ 97.292421] __asan_load8+0x9c/0xc0
+[ 97.293042] regs_get_kernel_stack_nth+0xa8/0xc8
+[ 97.293835] process_fetch_insn+0x770/0xa30
+[ 97.294562] kprobe_trace_func+0x254/0x3b0
+[ 97.295271] kprobe_dispatcher+0x98/0xe0
+[ 97.295955] kprobe_breakpoint_handler+0x1b0/0x210
+[ 97.296774] call_break_hook+0xc4/0x100
+[ 97.297451] brk_handler+0x24/0x78
+[ 97.298073] do_debug_exception+0xac/0x178
+[ 97.298785] el1_dbg+0x70/0x90
+[ 97.299344] el1h_64_sync_handler+0xcc/0xe8
+[ 97.300066] el1h_64_sync+0x78/0x80
+[ 97.300699] kernel_clone+0x0/0x500
+[ 97.301331] __arm64_sys_clone+0x70/0x90
+[ 97.302084] invoke_syscall+0x68/0x198
+[ 97.302746] el0_svc_common.constprop.0+0x11c/0x150
+[ 97.303569] do_el0_svc+0x38/0x50
+[ 97.304164] el0_svc+0x44/0x1d8
+[ 97.304749] el0t_64_sync_handler+0x100/0x130
+[ 97.305500] el0t_64_sync+0x188/0x190
+[ 97.306151]
+[ 97.306475] The buggy address belongs to stack of task 1.sh/2550
+[ 97.307461] and is located at offset 0 in frame:
+[ 97.308257] __se_sys_clone+0x0/0x138
+[ 97.308910]
+[ 97.309241] This frame has 1 object:
+[ 97.309873] [48, 184) 'args'
+[ 97.309876]
+[ 97.310749] The buggy address belongs to the virtual mapping at
+[ 97.310749] [ffff800089270000, ffff800089279000) created by:
+[ 97.310749] dup_task_struct+0xc0/0x2e8
+[ 97.313347]
+[ 97.313674] The buggy address belongs to the physical page:
+[ 97.314604] page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x14f69a
+[ 97.315885] flags: 0x15ffffe00000000(node=1|zone=2|lastcpupid=0xfffff)
+[ 97.316957] raw: 015ffffe00000000 0000000000000000 dead000000000122 0000000000000000
+[ 97.318207] raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000
+[ 97.319445] page dumped because: kasan: bad access detected
+[ 97.320371]
+[ 97.320694] Memory state around the buggy address:
+[ 97.321511] ffff800089277b00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
+[ 97.322681] ffff800089277b80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
+[ 97.323846] >ffff800089277c00: 00 00 f1 f1 f1 f1 f1 f1 00 00 00 00 00 00 00 00
+[ 97.325023] ^
+[ 97.325683] ffff800089277c80: 00 00 00 00 00 00 00 00 00 f3 f3 f3 f3 f3 f3 f3
+[ 97.326856] ffff800089277d00: f3 f3 00 00 00 00 00 00 00 00 00 00 00 00 00 00
+
+This issue seems to be related to the behavior of some gcc compilers and
+was also fixed on the s390 architecture before:
+
+ commit d93a855c31b7 ("s390/ptrace: Avoid KASAN false positives in regs_get_kernel_stack_nth()")
+
+As described in that commit, regs_get_kernel_stack_nth() has confirmed that
+`addr` is on the stack, so reading the value at `*addr` should be allowed.
+Use READ_ONCE_NOCHECK() helper to silence the KASAN check for this case.
+
+Fixes: 0a8ea52c3eb1 ("arm64: Add HAVE_REGS_AND_STACK_ACCESS_API feature")
+Signed-off-by: Tengda Wu <wutengda@huaweicloud.com>
+Link: https://lore.kernel.org/r/20250604005533.1278992-1-wutengda@huaweicloud.com
+[will: Use '*addr' as the argument to READ_ONCE_NOCHECK()]
+Signed-off-by: Will Deacon <will@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ arch/arm64/kernel/ptrace.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
+index 8a95a013dfd3c..8fcf03968f111 100644
+--- a/arch/arm64/kernel/ptrace.c
++++ b/arch/arm64/kernel/ptrace.c
+@@ -140,7 +140,7 @@ unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
+
+ addr += n;
+ if (regs_within_kernel_stack(regs, (unsigned long)addr))
+- return *addr;
++ return READ_ONCE_NOCHECK(*addr);
+ else
+ return 0;
+ }
+--
+2.39.5
+
--- /dev/null
+From 84bb7bcb3aa6c702215cd9c90911e80199cd09fb Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 5 Jun 2025 12:31:45 +0200
+Subject: perf: Fix sample vs do_exit()
+
+From: Peter Zijlstra <peterz@infradead.org>
+
+[ Upstream commit 4f6fc782128355931527cefe3eb45338abd8ab39 ]
+
+Baisheng Gao reported an ARM64 crash, which Mark decoded as being a
+synchronous external abort -- most likely due to trying to access
+MMIO in bad ways.
+
+The crash further shows perf trying to do a user stack sample while in
+exit_mmap()'s tlb_finish_mmu() -- i.e. while tearing down the address
+space it is trying to access.
+
+It turns out that we stop perf after we tear down the userspace mm; a
+receipie for disaster, since perf likes to access userspace for
+various reasons.
+
+Flip this order by moving up where we stop perf in do_exit().
+
+Additionally, harden PERF_SAMPLE_CALLCHAIN and PERF_SAMPLE_STACK_USER
+to abort when the current task does not have an mm (exit_mm() makes
+sure to set current->mm = NULL; before commencing with the actual
+teardown). Such that CPU wide events don't trip on this same problem.
+
+Fixes: c5ebcedb566e ("perf: Add ability to attach user stack dump to sample")
+Reported-by: Baisheng Gao <baisheng.gao@unisoc.com>
+Suggested-by: Mark Rutland <mark.rutland@arm.com>
+Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
+Link: https://lkml.kernel.org/r/20250605110815.GQ39944@noisy.programming.kicks-ass.net
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ kernel/events/core.c | 7 +++++++
+ kernel/exit.c | 17 +++++++++--------
+ 2 files changed, 16 insertions(+), 8 deletions(-)
+
+diff --git a/kernel/events/core.c b/kernel/events/core.c
+index 7b97be4ed9d00..ecae7c7f895b9 100644
+--- a/kernel/events/core.c
++++ b/kernel/events/core.c
+@@ -6219,6 +6219,10 @@ perf_sample_ustack_size(u16 stack_size, u16 header_size,
+ if (!regs)
+ return 0;
+
++ /* No mm, no stack, no dump. */
++ if (!current->mm)
++ return 0;
++
+ /*
+ * Check if we fit in with the requested stack size into the:
+ * - TASK_SIZE
+@@ -6687,6 +6691,9 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
+ const u32 max_stack = event->attr.sample_max_stack;
+ struct perf_callchain_entry *callchain;
+
++ if (!current->mm)
++ user = false;
++
+ if (!kernel && !user)
+ return &__empty_callchain;
+
+diff --git a/kernel/exit.c b/kernel/exit.c
+index 56d3a099825fb..8cb4a82c4ed3a 100644
+--- a/kernel/exit.c
++++ b/kernel/exit.c
+@@ -844,6 +844,15 @@ void __noreturn do_exit(long code)
+ tsk->exit_code = code;
+ taskstats_exit(tsk, group_dead);
+
++ /*
++ * Since sampling can touch ->mm, make sure to stop everything before we
++ * tear it down.
++ *
++ * Also flushes inherited counters to the parent - before the parent
++ * gets woken up by child-exit notifications.
++ */
++ perf_event_exit_task(tsk);
++
+ exit_mm();
+
+ if (group_dead)
+@@ -861,14 +870,6 @@ void __noreturn do_exit(long code)
+ exit_thread(tsk);
+ exit_umh(tsk);
+
+- /*
+- * Flush inherited counters to the parent - before the parent
+- * gets woken up by child-exit notifications.
+- *
+- * because of cgroup mode, must be called before cgroup_exit()
+- */
+- perf_event_exit_task(tsk);
+-
+ sched_autogroup_exit_task(tsk);
+ cgroup_exit(tsk);
+
+--
+2.39.5
+
projects / thirdparty / kernel / stable-queue.git / commitdiff
