diff mbox series

riscv: stacktrace: pin the task's stack in get_wchan

Message ID 20210723082226.7b7b4707@xhacker (mailing list archive)
State New, archived
Headers show
Series riscv: stacktrace: pin the task's stack in get_wchan | expand

Commit Message

Jisheng Zhang July 23, 2021, 12:22 a.m. UTC
From: Jisheng Zhang <jszhang@kernel.org>

Pin the task's stack before calling walk_stackframe() in get_wchan().
This can fix the panic as reported by Andreas when CONFIG_VMAP_STACK=y:

[   65.609696] Unable to handle kernel paging request at virtual address ffffffd0003bbde8
[   65.610460] Oops [#1]
[   65.610626] Modules linked in: virtio_blk virtio_mmio rtc_goldfish btrfs blake2b_generic libcrc32c xor raid6_pq sg dm_multipath dm_mod scsi_dh_rdac scsi_dh_emc scsi_dh_alua efivarfs
[   65.611670] CPU: 2 PID: 1 Comm: systemd Not tainted 5.14.0-rc1-1.g34fe32a-default #1 openSUSE Tumbleweed (unreleased) c62f7109153e5a0897ee58ba52393ad99b070fd2
[   65.612334] Hardware name: riscv-virtio,qemu (DT)
[   65.613008] epc : get_wchan+0x5c/0x88
[   65.613334]  ra : get_wchan+0x42/0x88
[   65.613625] epc : ffffffff800048a4 ra : ffffffff8000488a sp : ffffffd00021bb90
[   65.614008]  gp : ffffffff817709f8 tp : ffffffe07fe91b80 t0 : 00000000000001f8
[   65.614411]  t1 : 0000000000020000 t2 : 0000000000000000 s0 : ffffffd00021bbd0
[   65.614818]  s1 : ffffffd0003bbdf0 a0 : 0000000000000001 a1 : 0000000000000002
[   65.615237]  a2 : ffffffff81618008 a3 : 0000000000000000 a4 : 0000000000000000
[   65.615637]  a5 : ffffffd0003bc000 a6 : 0000000000000002 a7 : ffffffe27d370000
[   65.616022]  s2 : ffffffd0003bbd90 s3 : ffffffff8071a81e s4 : 0000000000003fff
[   65.616407]  s5 : ffffffffffffc000 s6 : 0000000000000000 s7 : ffffffff81618008
[   65.616845]  s8 : 0000000000000001 s9 : 0000000180000040 s10: 0000000000000000
[   65.617248]  s11: 000000000000016b t3 : 000000ff00000000 t4 : 0c6aec92de5e3fd7
[   65.617672]  t5 : fff78f60608fcfff t6 : 0000000000000078
[   65.618088] status: 0000000000000120 badaddr: ffffffd0003bbde8 cause: 000000000000000d
[   65.618621] [<ffffffff800048a4>] get_wchan+0x5c/0x88
[   65.619008] [<ffffffff8022da88>] do_task_stat+0x7a2/0xa46
[   65.619325] [<ffffffff8022e87e>] proc_tgid_stat+0xe/0x16
[   65.619637] [<ffffffff80227dd6>] proc_single_show+0x46/0x96
[   65.619979] [<ffffffff801ccb1e>] seq_read_iter+0x190/0x31e
[   65.620341] [<ffffffff801ccd70>] seq_read+0xc4/0x104
[   65.620633] [<ffffffff801a6bfe>] vfs_read+0x6a/0x112
[   65.620922] [<ffffffff801a701c>] ksys_read+0x54/0xbe
[   65.621206] [<ffffffff801a7094>] sys_read+0xe/0x16
[   65.621474] [<ffffffff8000303e>] ret_from_syscall+0x0/0x2
[   65.622169] ---[ end trace f24856ed2b8789c5 ]---
[   65.622832] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
---
 arch/riscv/kernel/stacktrace.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

Comments

Palmer Dabbelt July 24, 2021, 12:58 a.m. UTC | #1
On Thu, 22 Jul 2021 17:22:26 PDT (-0700), jszhang3@mail.ustc.edu.cn wrote:
> From: Jisheng Zhang <jszhang@kernel.org>
>
> Pin the task's stack before calling walk_stackframe() in get_wchan().
> This can fix the panic as reported by Andreas when CONFIG_VMAP_STACK=y:
>
> [   65.609696] Unable to handle kernel paging request at virtual address ffffffd0003bbde8
> [   65.610460] Oops [#1]
> [   65.610626] Modules linked in: virtio_blk virtio_mmio rtc_goldfish btrfs blake2b_generic libcrc32c xor raid6_pq sg dm_multipath dm_mod scsi_dh_rdac scsi_dh_emc scsi_dh_alua efivarfs
> [   65.611670] CPU: 2 PID: 1 Comm: systemd Not tainted 5.14.0-rc1-1.g34fe32a-default #1 openSUSE Tumbleweed (unreleased) c62f7109153e5a0897ee58ba52393ad99b070fd2
> [   65.612334] Hardware name: riscv-virtio,qemu (DT)
> [   65.613008] epc : get_wchan+0x5c/0x88
> [   65.613334]  ra : get_wchan+0x42/0x88
> [   65.613625] epc : ffffffff800048a4 ra : ffffffff8000488a sp : ffffffd00021bb90
> [   65.614008]  gp : ffffffff817709f8 tp : ffffffe07fe91b80 t0 : 00000000000001f8
> [   65.614411]  t1 : 0000000000020000 t2 : 0000000000000000 s0 : ffffffd00021bbd0
> [   65.614818]  s1 : ffffffd0003bbdf0 a0 : 0000000000000001 a1 : 0000000000000002
> [   65.615237]  a2 : ffffffff81618008 a3 : 0000000000000000 a4 : 0000000000000000
> [   65.615637]  a5 : ffffffd0003bc000 a6 : 0000000000000002 a7 : ffffffe27d370000
> [   65.616022]  s2 : ffffffd0003bbd90 s3 : ffffffff8071a81e s4 : 0000000000003fff
> [   65.616407]  s5 : ffffffffffffc000 s6 : 0000000000000000 s7 : ffffffff81618008
> [   65.616845]  s8 : 0000000000000001 s9 : 0000000180000040 s10: 0000000000000000
> [   65.617248]  s11: 000000000000016b t3 : 000000ff00000000 t4 : 0c6aec92de5e3fd7
> [   65.617672]  t5 : fff78f60608fcfff t6 : 0000000000000078
> [   65.618088] status: 0000000000000120 badaddr: ffffffd0003bbde8 cause: 000000000000000d
> [   65.618621] [<ffffffff800048a4>] get_wchan+0x5c/0x88
> [   65.619008] [<ffffffff8022da88>] do_task_stat+0x7a2/0xa46
> [   65.619325] [<ffffffff8022e87e>] proc_tgid_stat+0xe/0x16
> [   65.619637] [<ffffffff80227dd6>] proc_single_show+0x46/0x96
> [   65.619979] [<ffffffff801ccb1e>] seq_read_iter+0x190/0x31e
> [   65.620341] [<ffffffff801ccd70>] seq_read+0xc4/0x104
> [   65.620633] [<ffffffff801a6bfe>] vfs_read+0x6a/0x112
> [   65.620922] [<ffffffff801a701c>] ksys_read+0x54/0xbe
> [   65.621206] [<ffffffff801a7094>] sys_read+0xe/0x16
> [   65.621474] [<ffffffff8000303e>] ret_from_syscall+0x0/0x2
> [   65.622169] ---[ end trace f24856ed2b8789c5 ]---
> [   65.622832] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b
>
> Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
> ---
>  arch/riscv/kernel/stacktrace.c | 6 +++++-
>  1 file changed, 5 insertions(+), 1 deletion(-)
>
> diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
> index ff467b98c3e3..ac7593607fa6 100644
> --- a/arch/riscv/kernel/stacktrace.c
> +++ b/arch/riscv/kernel/stacktrace.c
> @@ -132,8 +132,12 @@ unsigned long get_wchan(struct task_struct *task)
>  {
>  	unsigned long pc = 0;
>
> -	if (likely(task && task != current && !task_is_running(task)))
> +	if (likely(task && task != current && !task_is_running(task))) {
> +		if (!try_get_task_stack(task))
> +			return 0;
>  		walk_stackframe(task, NULL, save_wchan, &pc);
> +		put_task_stack(task);
> +	}
>  	return pc;
>  }

Thanks, this is on fixes.
diff mbox series

Patch

diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index ff467b98c3e3..ac7593607fa6 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -132,8 +132,12 @@  unsigned long get_wchan(struct task_struct *task)
 {
 	unsigned long pc = 0;
 
-	if (likely(task && task != current && !task_is_running(task)))
+	if (likely(task && task != current && !task_is_running(task))) {
+		if (!try_get_task_stack(task))
+			return 0;
 		walk_stackframe(task, NULL, save_wchan, &pc);
+		put_task_stack(task);
+	}
 	return pc;
 }