[v5] x86/tdx: Add kexec support

[PATCHv5 14/16] x86/smp: Add smp_ops.stop_this_cpu() callback

Posted by Kirill A. Shutemov 2 years ago

If the helper is defined, it is called instead of halt() to stop the CPU
at the end of stop_this_cpu() and on crash CPU shutdown.

ACPI MADT will use it to hand over the CPU to BIOS in order to be able
to wake it up again after kexec.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/include/asm/smp.h |  1 +
 arch/x86/kernel/process.c  | 20 +++++++++++++-------
 arch/x86/kernel/reboot.c   | 12 ++++++++----
 3 files changed, 22 insertions(+), 11 deletions(-)

diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 4fab2ed454f3..390d53fd34f9 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -38,6 +38,7 @@ struct smp_ops {
 	int (*cpu_disable)(void);
 	void (*cpu_die)(unsigned int cpu);
 	void (*play_dead)(void);
+	void (*stop_this_cpu)(void);
 
 	void (*send_call_func_ipi)(const struct cpumask *mask);
 	void (*send_call_func_single_ipi)(int cpu);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b6f4e8399fca..65c7971defd2 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -835,13 +835,19 @@ void __noreturn stop_this_cpu(void *dummy)
 	 */
 	cpumask_clear_cpu(cpu, &cpus_stop_mask);
 
-	for (;;) {
-		/*
-		 * Use native_halt() so that memory contents don't change
-		 * (stack usage and variables) after possibly issuing the
-		 * native_wbinvd() above.
-		 */
-		native_halt();
+	if (smp_ops.stop_this_cpu) {
+		smp_ops.stop_this_cpu();
+		unreachable();
+	} else {
+
+		for (;;) {
+			/*
+			 * Use native_halt() so that memory contents don't
+			 * change (stack usage and variables) after possibly
+			 * issuing the native_wbinvd() above.
+			 */
+			native_halt();
+		}
 	}
 }
 
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 16dde83df49a..738b3e810196 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -881,10 +881,14 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
 	cpu_emergency_disable_virtualization();
 
 	atomic_dec(&waiting_for_crash_ipi);
-	/* Assume hlt works */
-	halt();
-	for (;;)
-		cpu_relax();
+
+	if (smp_ops.stop_this_cpu) {
+		smp_ops.stop_this_cpu();
+	} else {
+		halt();
+		for (;;)
+			cpu_relax();
+	}
 
 	return NMI_HANDLED;
 }
-- 
2.41.0

[PATCHv5.1 14/16] x86/smp: Add smp_ops.stop_this_cpu() callback

Posted by Kirill A. Shutemov 2 years ago

If the helper is defined, it is called instead of halt() to stop the CPU
at the end of stop_this_cpu() and on crash CPU shutdown.

ACPI MADT will use it to hand over the CPU to BIOS in order to be able
to wake it up again after kexec.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---

 v5.1:
   - Fix build for !SMP;

---
 arch/x86/include/asm/smp.h |  1 +
 arch/x86/kernel/process.c  |  7 +++++++
 arch/x86/kernel/reboot.c   | 12 ++++++++----
 3 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 4fab2ed454f3..390d53fd34f9 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -38,6 +38,7 @@ struct smp_ops {
 	int (*cpu_disable)(void);
 	void (*cpu_die)(unsigned int cpu);
 	void (*play_dead)(void);
+	void (*stop_this_cpu)(void);
 
 	void (*send_call_func_ipi)(const struct cpumask *mask);
 	void (*send_call_func_single_ipi)(int cpu);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b6f4e8399fca..ea4c812c7bf3 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -835,6 +835,13 @@ void __noreturn stop_this_cpu(void *dummy)
 	 */
 	cpumask_clear_cpu(cpu, &cpus_stop_mask);
 
+#ifdef CONFIG_SMP
+	if (smp_ops.stop_this_cpu) {
+		smp_ops.stop_this_cpu();
+		unreachable();
+	}
+#endif
+
 	for (;;) {
 		/*
 		 * Use native_halt() so that memory contents don't change
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 16dde83df49a..738b3e810196 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -881,10 +881,14 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
 	cpu_emergency_disable_virtualization();
 
 	atomic_dec(&waiting_for_crash_ipi);
-	/* Assume hlt works */
-	halt();
-	for (;;)
-		cpu_relax();
+
+	if (smp_ops.stop_this_cpu) {
+		smp_ops.stop_this_cpu();
+	} else {
+		halt();
+		for (;;)
+			cpu_relax();
+	}
 
 	return NMI_HANDLED;
 }
-- 
2.41.0

Re: [PATCHv5.1 14/16] x86/smp: Add smp_ops.stop_this_cpu() callback

Posted by Huang, Kai 1 year, 11 months ago

On Mon, 2023-12-25 at 11:05 +0300, Kirill A. Shutemov wrote:
> If the helper is defined, it is called instead of halt() to stop the CPU
> at the end of stop_this_cpu() and on crash CPU shutdown.
> 
> ACPI MADT will use it to hand over the CPU to BIOS in order to be able
> to wake it up again after kexec.
> 
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> ---
> 
>  v5.1:
>    - Fix build for !SMP;
> 
> ---
>  arch/x86/include/asm/smp.h |  1 +
>  arch/x86/kernel/process.c  |  7 +++++++
>  arch/x86/kernel/reboot.c   | 12 ++++++++----
>  3 files changed, 16 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
> index 4fab2ed454f3..390d53fd34f9 100644
> --- a/arch/x86/include/asm/smp.h
> +++ b/arch/x86/include/asm/smp.h
> @@ -38,6 +38,7 @@ struct smp_ops {
>  	int (*cpu_disable)(void);
>  	void (*cpu_die)(unsigned int cpu);
>  	void (*play_dead)(void);
> +	void (*stop_this_cpu)(void);
>  
>  	void (*send_call_func_ipi)(const struct cpumask *mask);
>  	void (*send_call_func_single_ipi)(int cpu);
> diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
> index b6f4e8399fca..ea4c812c7bf3 100644
> --- a/arch/x86/kernel/process.c
> +++ b/arch/x86/kernel/process.c
> @@ -835,6 +835,13 @@ void __noreturn stop_this_cpu(void *dummy)
>  	 */
>  	cpumask_clear_cpu(cpu, &cpus_stop_mask);
>  
> +#ifdef CONFIG_SMP
> +	if (smp_ops.stop_this_cpu) {
> +		smp_ops.stop_this_cpu();
> +		unreachable();
> +	}
> +#endif

If I read correctly this will result in stop_this_cpu() having different
behaviour for SMP and !SMP build for TDX guest.  For example, AFAICT
machine_halt() also calls stop_this_cpu() on local cpu after it stops other
cpus.  So for the local cpu, in SMP build it will calls into BIOS's reset vector
but in !SMP it will call native_halt().

> +
>  	for (;;) {
>  		/*
>  		 * Use native_halt() so that memory contents don't change
> diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
> index 16dde83df49a..738b3e810196 100644
> --- a/arch/x86/kernel/reboot.c
> +++ b/arch/x86/kernel/reboot.c
> @@ -881,10 +881,14 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
>  	cpu_emergency_disable_virtualization();
>  
>  	atomic_dec(&waiting_for_crash_ipi);
> -	/* Assume hlt works */
> -	halt();
> -	for (;;)
> -		cpu_relax();
> +
> +	if (smp_ops.stop_this_cpu) {
> +		smp_ops.stop_this_cpu();

Could you explain why unreachable() is called in stop_this_cpu() but not here?

> +	} else {
> +		halt();
> +		for (;;)
> +			cpu_relax();
> +	}

Similar to stop_this_cpu(), if you also call unreachable() here, then I think
you can remove the 'else' here but directly calls halt() + cpu_relax() loop.

Re: [PATCHv5.1 14/16] x86/smp: Add smp_ops.stop_this_cpu() callback

Posted by kirill.shutemov@linux.intel.com 1 year, 11 months ago

On Mon, Jan 08, 2024 at 03:04:31AM +0000, Huang, Kai wrote:
> On Mon, 2023-12-25 at 11:05 +0300, Kirill A. Shutemov wrote:
> > If the helper is defined, it is called instead of halt() to stop the CPU
> > at the end of stop_this_cpu() and on crash CPU shutdown.
> > 
> > ACPI MADT will use it to hand over the CPU to BIOS in order to be able
> > to wake it up again after kexec.
> > 
> > Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> > ---
> > 
> >  v5.1:
> >    - Fix build for !SMP;
> > 
> > ---
> >  arch/x86/include/asm/smp.h |  1 +
> >  arch/x86/kernel/process.c  |  7 +++++++
> >  arch/x86/kernel/reboot.c   | 12 ++++++++----
> >  3 files changed, 16 insertions(+), 4 deletions(-)
> > 
> > diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
> > index 4fab2ed454f3..390d53fd34f9 100644
> > --- a/arch/x86/include/asm/smp.h
> > +++ b/arch/x86/include/asm/smp.h
> > @@ -38,6 +38,7 @@ struct smp_ops {
> >  	int (*cpu_disable)(void);
> >  	void (*cpu_die)(unsigned int cpu);
> >  	void (*play_dead)(void);
> > +	void (*stop_this_cpu)(void);
> >  
> >  	void (*send_call_func_ipi)(const struct cpumask *mask);
> >  	void (*send_call_func_single_ipi)(int cpu);
> > diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
> > index b6f4e8399fca..ea4c812c7bf3 100644
> > --- a/arch/x86/kernel/process.c
> > +++ b/arch/x86/kernel/process.c
> > @@ -835,6 +835,13 @@ void __noreturn stop_this_cpu(void *dummy)
> >  	 */
> >  	cpumask_clear_cpu(cpu, &cpus_stop_mask);
> >  
> > +#ifdef CONFIG_SMP
> > +	if (smp_ops.stop_this_cpu) {
> > +		smp_ops.stop_this_cpu();
> > +		unreachable();
> > +	}
> > +#endif
> 
> If I read correctly this will result in stop_this_cpu() having different
> behaviour for SMP and !SMP build for TDX guest.  For example, AFAICT
> machine_halt() also calls stop_this_cpu() on local cpu after it stops other
> cpus.  So for the local cpu, in SMP build it will calls into BIOS's reset vector
> but in !SMP it will call native_halt().

It doesn't make a difference in practice: both halt and giving CPU to
BIOS will be unrecoverable operation. Both are equally acceptable for
machine_halt().

> > +
> >  	for (;;) {
> >  		/*
> >  		 * Use native_halt() so that memory contents don't change
> > diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
> > index 16dde83df49a..738b3e810196 100644
> > --- a/arch/x86/kernel/reboot.c
> > +++ b/arch/x86/kernel/reboot.c
> > @@ -881,10 +881,14 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
> >  	cpu_emergency_disable_virtualization();
> >  
> >  	atomic_dec(&waiting_for_crash_ipi);
> > -	/* Assume hlt works */
> > -	halt();
> > -	for (;;)
> > -		cpu_relax();
> > +
> > +	if (smp_ops.stop_this_cpu) {
> > +		smp_ops.stop_this_cpu();
> 
> Could you explain why unreachable() is called in stop_this_cpu() but not here?

Compiler complained previously on stop_this_cpu() when it had halt() in
'else' case because the function is declared as __noreturn. I left
unreachable() after reworking it without 'else' to document the behaviour.

> > +	} else {
> > +		halt();
> > +		for (;;)
> > +			cpu_relax();
> > +	}
> 
> Similar to stop_this_cpu(), if you also call unreachable() here, then I think
> you can remove the 'else' here but directly calls halt() + cpu_relax() loop.

It doesn't make much difference to me. But okay, I will rework it the same
way in the next version.

-- 
  Kiryl Shutsemau / Kirill A. Shutemov

Re: [PATCHv5.1 14/16] x86/smp: Add smp_ops.stop_this_cpu() callback

Posted by Huang, Kai 1 year, 11 months ago

> > > @@ -835,6 +835,13 @@ void __noreturn stop_this_cpu(void *dummy)
> > >  	 */
> > >  	cpumask_clear_cpu(cpu, &cpus_stop_mask);
> > >  
> > > +#ifdef CONFIG_SMP
> > > +	if (smp_ops.stop_this_cpu) {
> > > +		smp_ops.stop_this_cpu();
> > > +		unreachable();
> > > +	}
> > > +#endif
> > 
> > If I read correctly this will result in stop_this_cpu() having different
> > behaviour for SMP and !SMP build for TDX guest.  For example, AFAICT
> > machine_halt() also calls stop_this_cpu() on local cpu after it stops other
> > cpus.  So for the local cpu, in SMP build it will calls into BIOS's reset vector
> > but in !SMP it will call native_halt().
> 
> It doesn't make a difference in practice: both halt and giving CPU to
> BIOS will be unrecoverable operation. Both are equally acceptable for
> machine_halt().
> 

OK fair enough. :-)