Currently, almost all archs (x86, arm64, mips...) support fast call
of crash_kexec() when "regs && kexec_should_crash()" is true. But
RISC-V not, it can only enter crash system via panic(). However panic()
doesn't pass the regs of the real accident scene to crash_kexec(),
it caused we can't get accurate backtrace via gdb,
$ riscv64-linux-gnu-gdb vmlinux vmcore
Reading symbols from vmlinux...
[New LWP 95]
#0 console_unlock () at kernel/printk/printk.c:2557
2557 if (do_cond_resched)
(gdb) bt
#0 console_unlock () at kernel/printk/printk.c:2557
#1 0x0000000000000000 in ?? ()
With the patch we can get the accurate backtrace,
$ riscv64-linux-gnu-gdb vmlinux vmcore
Reading symbols from vmlinux...
[New LWP 95]
#0 0xffffffe00063a4e0 in test_thread (data=<optimized out>) at drivers/test_crash.c:81
81 *(int *)p = 0xdead;
(gdb)
(gdb) bt
#0 0xffffffe00064d5c0 in test_thread (data=<optimized out>) at drivers/test_crash.c:81
#1 0x0000000000000000 in ?? ()
Test code to produce NULL address dereference in test_crash.c,
void *p = NULL;
*(int *)p = 0xdead;
Fixes: 76d2a0493a17 ("RISC-V: Init and Halt Code")
Reviewed-by: Guo Ren <[email protected]>
Signed-off-by: Xianting Tian <[email protected]>
---
Changes from v1:
- simplify the commit message
Changes from v2:
- add fixup in title
---
arch/riscv/kernel/traps.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index b40426509244..39d0f8bba4b4 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -16,6 +16,7 @@
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/irq.h>
+#include <linux/kexec.h>
#include <asm/asm-prototypes.h>
#include <asm/bug.h>
@@ -44,6 +45,9 @@ void die(struct pt_regs *regs, const char *str)
ret = notify_die(DIE_OOPS, str, regs, 0, regs->cause, SIGSEGV);
+ if (regs && kexec_should_crash(current))
+ crash_kexec(regs);
+
bust_spinlocks(0);
add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
spin_unlock_irq(&die_lock);
--
2.17.1
On 2022/6/6 20:37, Xianting Tian wrote:
> Currently, almost all archs (x86, arm64, mips...) support fast call
> of crash_kexec() when "regs && kexec_should_crash()" is true. But
> RISC-V not, it can only enter crash system via panic(). However panic()
> doesn't pass the regs of the real accident scene to crash_kexec(),
> it caused we can't get accurate backtrace via gdb,
> $ riscv64-linux-gnu-gdb vmlinux vmcore
> Reading symbols from vmlinux...
> [New LWP 95]
> #0 console_unlock () at kernel/printk/printk.c:2557
> 2557 if (do_cond_resched)
> (gdb) bt
> #0 console_unlock () at kernel/printk/printk.c:2557
> #1 0x0000000000000000 in ?? ()
>
> With the patch we can get the accurate backtrace,
> $ riscv64-linux-gnu-gdb vmlinux vmcore
> Reading symbols from vmlinux...
> [New LWP 95]
> #0 0xffffffe00063a4e0 in test_thread (data=<optimized out>) at drivers/test_crash.c:81
> 81 *(int *)p = 0xdead;
> (gdb)
> (gdb) bt
> #0 0xffffffe00064d5c0 in test_thread (data=<optimized out>) at drivers/test_crash.c:81
> #1 0x0000000000000000 in ?? ()
>
> Test code to produce NULL address dereference in test_crash.c,
> void *p = NULL;
> *(int *)p = 0xdead;
>
> Fixes: 76d2a0493a17 ("RISC-V: Init and Halt Code")
> Reviewed-by: Guo Ren <[email protected]>
> Signed-off-by: Xianting Tian <[email protected]>
> ---
> Changes from v1:
> - simplify the commit message
> Changes from v2:
> - add fixup in title
> ---
> arch/riscv/kernel/traps.c | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
> index b40426509244..39d0f8bba4b4 100644
> --- a/arch/riscv/kernel/traps.c
> +++ b/arch/riscv/kernel/traps.c
> @@ -16,6 +16,7 @@
> #include <linux/mm.h>
> #include <linux/module.h>
> #include <linux/irq.h>
> +#include <linux/kexec.h>
>
> #include <asm/asm-prototypes.h>
> #include <asm/bug.h>
> @@ -44,6 +45,9 @@ void die(struct pt_regs *regs, const char *str)
>
> ret = notify_die(DIE_OOPS, str, regs, 0, regs->cause, SIGSEGV);
>
> + if (regs && kexec_should_crash(current))
> + crash_kexec(regs);
> +
It seems that the regs won't be null, right? except that,
Reviewed-by: Kefeng Wang <[email protected]>
> bust_spinlocks(0);
> add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
> spin_unlock_irq(&die_lock);
在 2022/6/7 上午9:21, Kefeng Wang 写道:
>
> On 2022/6/6 20:37, Xianting Tian wrote:
>> Currently, almost all archs (x86, arm64, mips...) support fast call
>> of crash_kexec() when "regs && kexec_should_crash()" is true. But
>> RISC-V not, it can only enter crash system via panic(). However panic()
>> doesn't pass the regs of the real accident scene to crash_kexec(),
>> it caused we can't get accurate backtrace via gdb,
>> $ riscv64-linux-gnu-gdb vmlinux vmcore
>> Reading symbols from vmlinux...
>> [New LWP 95]
>> #0 console_unlock () at kernel/printk/printk.c:2557
>> 2557 if (do_cond_resched)
>> (gdb) bt
>> #0 console_unlock () at kernel/printk/printk.c:2557
>> #1 0x0000000000000000 in ?? ()
>>
>> With the patch we can get the accurate backtrace,
>> $ riscv64-linux-gnu-gdb vmlinux vmcore
>> Reading symbols from vmlinux...
>> [New LWP 95]
>> #0 0xffffffe00063a4e0 in test_thread (data=<optimized out>) at
>> drivers/test_crash.c:81
>> 81 *(int *)p = 0xdead;
>> (gdb)
>> (gdb) bt
>> #0 0xffffffe00064d5c0 in test_thread (data=<optimized out>) at
>> drivers/test_crash.c:81
>> #1 0x0000000000000000 in ?? ()
>>
>> Test code to produce NULL address dereference in test_crash.c,
>> void *p = NULL;
>> *(int *)p = 0xdead;
>>
>> Fixes: 76d2a0493a17 ("RISC-V: Init and Halt Code")
>> Reviewed-by: Guo Ren <[email protected]>
>> Signed-off-by: Xianting Tian <[email protected]>
>> ---
>> Changes from v1:
>> - simplify the commit message
>> Changes from v2:
>> - add fixup in title
>> ---
>> arch/riscv/kernel/traps.c | 4 ++++
>> 1 file changed, 4 insertions(+)
>>
>> diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
>> index b40426509244..39d0f8bba4b4 100644
>> --- a/arch/riscv/kernel/traps.c
>> +++ b/arch/riscv/kernel/traps.c
>> @@ -16,6 +16,7 @@
>> #include <linux/mm.h>
>> #include <linux/module.h>
>> #include <linux/irq.h>
>> +#include <linux/kexec.h>
>> #include <asm/asm-prototypes.h>
>> #include <asm/bug.h>
>> @@ -44,6 +45,9 @@ void die(struct pt_regs *regs, const char *str)
>> ret = notify_die(DIE_OOPS, str, regs, 0, regs->cause, SIGSEGV);
>> + if (regs && kexec_should_crash(current))
>> + crash_kexec(regs);
>> +
>
> It seems that the regs won't be null, right? except that,
Autually both regs won't be null, But if it is triggered by panic() ,
the regs are got via riscv_crash_save_regs(), which are the regs of that
moment, but not the real accident scene.
>
> Reviewed-by: Kefeng Wang <[email protected]>
>
>> bust_spinlocks(0);
>> add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
>> spin_unlock_irq(&die_lock);
Hi Xianting,
On Fri, Jun 17, 2022 at 2:40 PM Xianting Tian
<[email protected]> wrote:
>
> Hi Palmer
>
> Will you apply this patch for 5.19?
Maybe we could update tile with [PATCH v3] RISC-V: Fixup fast call of
crash_kexec() for a V4.
It's a fixup not feature, that would mislead maintainer. And add
"Reviewed-by: Kefeng Wang".
>
> thanks
>
> 在 2022/6/7 上午9:46, Xianting Tian 写道:
> >
> > 在 2022/6/7 上午9:21, Kefeng Wang 写道:
> >>
> >> On 2022/6/6 20:37, Xianting Tian wrote:
> >>> Currently, almost all archs (x86, arm64, mips...) support fast call
> >>> of crash_kexec() when "regs && kexec_should_crash()" is true. But
> >>> RISC-V not, it can only enter crash system via panic(). However panic()
> >>> doesn't pass the regs of the real accident scene to crash_kexec(),
> >>> it caused we can't get accurate backtrace via gdb,
> >>> $ riscv64-linux-gnu-gdb vmlinux vmcore
> >>> Reading symbols from vmlinux...
> >>> [New LWP 95]
> >>> #0 console_unlock () at kernel/printk/printk.c:2557
> >>> 2557 if (do_cond_resched)
> >>> (gdb) bt
> >>> #0 console_unlock () at kernel/printk/printk.c:2557
> >>> #1 0x0000000000000000 in ?? ()
> >>>
> >>> With the patch we can get the accurate backtrace,
> >>> $ riscv64-linux-gnu-gdb vmlinux vmcore
> >>> Reading symbols from vmlinux...
> >>> [New LWP 95]
> >>> #0 0xffffffe00063a4e0 in test_thread (data=<optimized out>) at
> >>> drivers/test_crash.c:81
> >>> 81 *(int *)p = 0xdead;
> >>> (gdb)
> >>> (gdb) bt
> >>> #0 0xffffffe00064d5c0 in test_thread (data=<optimized out>) at
> >>> drivers/test_crash.c:81
> >>> #1 0x0000000000000000 in ?? ()
> >>>
> >>> Test code to produce NULL address dereference in test_crash.c,
> >>> void *p = NULL;
> >>> *(int *)p = 0xdead;
> >>>
> >>> Fixes: 76d2a0493a17 ("RISC-V: Init and Halt Code")
> >>> Reviewed-by: Guo Ren <[email protected]>
> >>> Signed-off-by: Xianting Tian <[email protected]>
> >>> ---
> >>> Changes from v1:
> >>> - simplify the commit message
> >>> Changes from v2:
> >>> - add fixup in title
> >>> ---
> >>> arch/riscv/kernel/traps.c | 4 ++++
> >>> 1 file changed, 4 insertions(+)
> >>>
> >>> diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
> >>> index b40426509244..39d0f8bba4b4 100644
> >>> --- a/arch/riscv/kernel/traps.c
> >>> +++ b/arch/riscv/kernel/traps.c
> >>> @@ -16,6 +16,7 @@
> >>> #include <linux/mm.h>
> >>> #include <linux/module.h>
> >>> #include <linux/irq.h>
> >>> +#include <linux/kexec.h>
> >>> #include <asm/asm-prototypes.h>
> >>> #include <asm/bug.h>
> >>> @@ -44,6 +45,9 @@ void die(struct pt_regs *regs, const char *str)
> >>> ret = notify_die(DIE_OOPS, str, regs, 0, regs->cause, SIGSEGV);
> >>> + if (regs && kexec_should_crash(current))
> >>> + crash_kexec(regs);
> >>> +
> >>
> >> It seems that the regs won't be null, right? except that,
> >
> > Autually both regs won't be null, But if it is triggered by panic() ,
> > the regs are got via riscv_crash_save_regs(), which are the regs of
> > that moment, but not the real accident scene.
> >
> >>
> >> Reviewed-by: Kefeng Wang <[email protected]>
> >>
> >>> bust_spinlocks(0);
> >>> add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
> >>> spin_unlock_irq(&die_lock);
--
Best Regards
Guo Ren
ML: https://lore.kernel.org/linux-csky/
Hi Palmer
Will you apply this patch for 5.19?
thanks
在 2022/6/7 上午9:46, Xianting Tian 写道:
>
> 在 2022/6/7 上午9:21, Kefeng Wang 写道:
>>
>> On 2022/6/6 20:37, Xianting Tian wrote:
>>> Currently, almost all archs (x86, arm64, mips...) support fast call
>>> of crash_kexec() when "regs && kexec_should_crash()" is true. But
>>> RISC-V not, it can only enter crash system via panic(). However panic()
>>> doesn't pass the regs of the real accident scene to crash_kexec(),
>>> it caused we can't get accurate backtrace via gdb,
>>> $ riscv64-linux-gnu-gdb vmlinux vmcore
>>> Reading symbols from vmlinux...
>>> [New LWP 95]
>>> #0 console_unlock () at kernel/printk/printk.c:2557
>>> 2557 if (do_cond_resched)
>>> (gdb) bt
>>> #0 console_unlock () at kernel/printk/printk.c:2557
>>> #1 0x0000000000000000 in ?? ()
>>>
>>> With the patch we can get the accurate backtrace,
>>> $ riscv64-linux-gnu-gdb vmlinux vmcore
>>> Reading symbols from vmlinux...
>>> [New LWP 95]
>>> #0 0xffffffe00063a4e0 in test_thread (data=<optimized out>) at
>>> drivers/test_crash.c:81
>>> 81 *(int *)p = 0xdead;
>>> (gdb)
>>> (gdb) bt
>>> #0 0xffffffe00064d5c0 in test_thread (data=<optimized out>) at
>>> drivers/test_crash.c:81
>>> #1 0x0000000000000000 in ?? ()
>>>
>>> Test code to produce NULL address dereference in test_crash.c,
>>> void *p = NULL;
>>> *(int *)p = 0xdead;
>>>
>>> Fixes: 76d2a0493a17 ("RISC-V: Init and Halt Code")
>>> Reviewed-by: Guo Ren <[email protected]>
>>> Signed-off-by: Xianting Tian <[email protected]>
>>> ---
>>> Changes from v1:
>>> - simplify the commit message
>>> Changes from v2:
>>> - add fixup in title
>>> ---
>>> arch/riscv/kernel/traps.c | 4 ++++
>>> 1 file changed, 4 insertions(+)
>>>
>>> diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
>>> index b40426509244..39d0f8bba4b4 100644
>>> --- a/arch/riscv/kernel/traps.c
>>> +++ b/arch/riscv/kernel/traps.c
>>> @@ -16,6 +16,7 @@
>>> #include <linux/mm.h>
>>> #include <linux/module.h>
>>> #include <linux/irq.h>
>>> +#include <linux/kexec.h>
>>> #include <asm/asm-prototypes.h>
>>> #include <asm/bug.h>
>>> @@ -44,6 +45,9 @@ void die(struct pt_regs *regs, const char *str)
>>> ret = notify_die(DIE_OOPS, str, regs, 0, regs->cause, SIGSEGV);
>>> + if (regs && kexec_should_crash(current))
>>> + crash_kexec(regs);
>>> +
>>
>> It seems that the regs won't be null, right? except that,
>
> Autually both regs won't be null, But if it is triggered by panic() ,
> the regs are got via riscv_crash_save_regs(), which are the regs of
> that moment, but not the real accident scene.
>
>>
>> Reviewed-by: Kefeng Wang <[email protected]>
>>
>>> bust_spinlocks(0);
>>> add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
>>> spin_unlock_irq(&die_lock);