From 024f4b2e1f874934943eb2d3d288ebc52c79f55c Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Mon, 17 Oct 2022 10:01:57 +0100
Subject: [PATCH] arm64: entry: avoid kprobe recursion
Git-commit: 024f4b2e1f874934943eb2d3d288ebc52c79f55c
Patch-mainline: v6.1-rc4
References: git-fixes

The cortex_a76_erratum_1463225_debug_handler() function is called when
handling debug exceptions (and synchronous exceptions from BRK
instructions), and so is called when a probed function executes. If the
compiler does not inline cortex_a76_erratum_1463225_debug_handler(), it
can be probed.

If cortex_a76_erratum_1463225_debug_handler() is probed, any debug
exception or software breakpoint exception will result in recursive
exceptions leading to a stack overflow. This can be triggered with the
ftrace multiple_probes selftest, and as per the example splat below.

This is a regression caused by commit:

  6459b8469753e9fe ("arm64: entry: consolidate Cortex-A76 erratum 1463225 workaround")

... which removed the NOKPROBE_SYMBOL() annotation associated with the
function.

My intent was that cortex_a76_erratum_1463225_debug_handler() would be
inlined into its caller, el1_dbg(), which is marked noinstr and cannot
be probed. Mark cortex_a76_erratum_1463225_debug_handler() as
__always_inline to ensure this.

Example splat prior to this patch (with recursive entries elided):

| # echo p cortex_a76_erratum_1463225_debug_handler > /sys/kernel/debug/tracing/kprobe_events
| # echo p do_el0_svc >> /sys/kernel/debug/tracing/kprobe_events
| # echo 1 > /sys/kernel/debug/tracing/events/kprobes/enable
| Insufficient stack space to handle exception!
| ESR: 0x0000000096000047 -- DABT (current EL)
| FAR: 0xffff800009cefff0
| Task stack:     [0xffff800009cf0000..0xffff800009cf4000]
| IRQ stack:      [0xffff800008000000..0xffff800008004000]
| Overflow stack: [0xffff00007fbc00f0..0xffff00007fbc10f0]
| CPU: 0 PID: 145 Comm: sh Not tainted 6.0.0 #2
| Hardware name: linux,dummy-virt (DT)
| pstate: 604003c5 (nZCv DAIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
| pc : arm64_enter_el1_dbg+0x4/0x20
| lr : el1_dbg+0x24/0x5c
| sp : ffff800009cf0000
| x29: ffff800009cf0000 x28: ffff000002c74740 x27: 0000000000000000
| x26: 0000000000000000 x25: 0000000000000000 x24: 0000000000000000
| x23: 00000000604003c5 x22: ffff80000801745c x21: 0000aaaac95ac068
| x20: 00000000f2000004 x19: ffff800009cf0040 x18: 0000000000000000
| x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000
| x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000
| x11: 0000000000000010 x10: ffff800008c87190 x9 : ffff800008ca00d0
| x8 : 000000000000003c x7 : 0000000000000000 x6 : 0000000000000000
| x5 : 0000000000000000 x4 : 0000000000000000 x3 : 00000000000043a4
| x2 : 00000000f2000004 x1 : 00000000f2000004 x0 : ffff800009cf0040
| Kernel panic - not syncing: kernel stack overflow
| CPU: 0 PID: 145 Comm: sh Not tainted 6.0.0 #2
| Hardware name: linux,dummy-virt (DT)
| Call trace:
|  dump_backtrace+0xe4/0x104
|  show_stack+0x18/0x4c
|  dump_stack_lvl+0x64/0x7c
|  dump_stack+0x18/0x38
|  panic+0x14c/0x338
|  test_taint+0x0/0x2c
|  panic_bad_stack+0x104/0x118
|  handle_bad_stack+0x34/0x48
|  __bad_stack+0x78/0x7c
|  arm64_enter_el1_dbg+0x4/0x20
|  el1h_64_sync_handler+0x40/0x98
|  el1h_64_sync+0x64/0x68
|  cortex_a76_erratum_1463225_debug_handler+0x0/0x34
...
|  el1h_64_sync_handler+0x40/0x98
|  el1h_64_sync+0x64/0x68
|  cortex_a76_erratum_1463225_debug_handler+0x0/0x34
...
|  el1h_64_sync_handler+0x40/0x98
|  el1h_64_sync+0x64/0x68
|  cortex_a76_erratum_1463225_debug_handler+0x0/0x34
|  el1h_64_sync_handler+0x40/0x98
|  el1h_64_sync+0x64/0x68
|  do_el0_svc+0x0/0x28
|  el0t_64_sync_handler+0x84/0xf0
|  el0t_64_sync+0x18c/0x190
| Kernel Offset: disabled
| CPU features: 0x0080,00005021,19001080
| Memory Limit: none
| ---[ end Kernel panic - not syncing: kernel stack overflow ]---

With this patch, cortex_a76_erratum_1463225_debug_handler() is inlined
into el1_dbg(), and el1_dbg() cannot be probed:

| # echo p cortex_a76_erratum_1463225_debug_handler > /sys/kernel/debug/tracing/kprobe_events
| sh: write error: No such file or directory
| # grep -w cortex_a76_erratum_1463225_debug_handler /proc/kallsyms | wc -l
| 0
| # echo p el1_dbg > /sys/kernel/debug/tracing/kprobe_events
| sh: write error: Invalid argument
| # grep -w el1_dbg /proc/kallsyms | wc -l
| 1

Fixes: 6459b8469753 ("arm64: entry: consolidate Cortex-A76 erratum 1463225 workaround")
Cc: <stable@vger.kernel.org> # 5.12.x
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20221017090157.2881408-1-mark.rutland@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Takashi Iwai <tiwai@suse.de>

---
 arch/arm64/kernel/entry-common.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 9173fad279af..27369fa1c032 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -329,7 +329,8 @@ static void cortex_a76_erratum_1463225_svc_handler(void)
 	__this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 0);
 }
 
-static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
+static __always_inline bool
+cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
 {
 	if (!__this_cpu_read(__in_cortex_a76_erratum_1463225_wa))
 		return false;
-- 
2.35.3