Re: [PATCH v10 RESEND 3/9] riscv: sse: mask events during shutdown and kexec

[Himanshu Chauhan <himanshu.chauhan@oss.qualcomm.com>]

On Mon, Sep 21, 2026 at 07:15:00PM +0800, Zhanpeng Zhang wrote:
> SSE delivery is independent of normal S-mode interrupts. Firmware may also
> retain an event registration until Linux explicitly unregisters it. A hart
> must therefore stop accepting SSE events before Linux stops servicing the
> registered handler.
> 
> Mask SSE on the local hart before panic stop, CPU stop, restart, poweroff,
> and crash shutdown paths. This prevents firmware from entering Linux-owned
> handler state after the corresponding CPU or kernel context is no longer
> valid.
> 
> A crash kernel cannot identify or take ownership of registrations
> inherited from the crashed kernel. Reject a later normal kexec while such
> SSE state may still exist, rather than transferring unknown firmware state
> to another kernel.
> 
> Signed-off-by: Zhanpeng Zhang <zhangzhanpeng.jasper@bytedance.com>
> ---
>  arch/riscv/kernel/machine_kexec.c | 11 +++++++++++
>  arch/riscv/kernel/reset.c         | 18 ++++++++++++++++++
>  arch/riscv/kernel/smp.c           | 17 +++++++++++++++++
>  3 files changed, 46 insertions(+)
> 
> diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c
> index 738df176ff6f..24e7affae70b 100644
> --- a/arch/riscv/kernel/machine_kexec.c
> +++ b/arch/riscv/kernel/machine_kexec.c
> @@ -14,10 +14,13 @@
>  #include <asm/set_memory.h>	/* For set_memory_x() */
>  #include <linux/compiler.h>	/* For unreachable() */
>  #include <linux/cpu.h>		/* For cpu_down() */
> +#include <linux/crash_dump.h>
>  #include <linux/reboot.h>
>  #include <linux/interrupt.h>
>  #include <linux/irq.h>
>  
> +#include <asm/sse.h>
> +
>  /*
>   * machine_kexec_prepare - Initialize kexec
>   *
> @@ -36,6 +39,13 @@ machine_kexec_prepare(struct kimage *image)
>  	unsigned int control_code_buffer_sz = 0;
>  	int i = 0;
>  
> +	/* A crash kernel cannot tear down registrations inherited from firmware. */
> +	if (is_kdump_kernel() && image->type != KEXEC_TYPE_CRASH &&
> +	    riscv_sse_available()) {

I just realized. This rejects a normal kexec from any kdump kernel whenever firmware
merely advertises SSE, regardless of CONFIG_RISCV_SBI_SSE or whether anything is registered.
Can you check if its breaking kexec() with SSE just being advertised?

Also, there are some shasiko's comments worth addressing.

> +		pr_err("Normal kexec from a crash kernel is unsupported with SSE\n");
> +		return -EOPNOTSUPP;
> +	}
> +
>  	/* Find the Flattened Device Tree and save its physical address */
>  	for (i = 0; i < image->nr_segments; i++) {
>  		if (image->segment[i].memsz <= sizeof(fdt))
> @@ -127,6 +137,7 @@ void
>  machine_crash_shutdown(struct pt_regs *regs)
>  {
>  	local_irq_disable();
> +	riscv_sse_mask_current_hart();
>  
>  	/* shutdown non-crashing cpus */
>  	crash_smp_send_stop();
> diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c
> index 14eb08a6db85..fdab37e7ae52 100644
> --- a/arch/riscv/kernel/reset.c
> +++ b/arch/riscv/kernel/reset.c
> @@ -6,6 +6,20 @@
>  #include <linux/efi.h>
>  #include <linux/reboot.h>
>  #include <linux/pm.h>
> +#include <linux/smp.h>
> +
> +#include <asm/sse.h>
> +
> +#ifndef CONFIG_SMP
> +void __noreturn panic_smp_self_stop(void)
> +{
> +	riscv_sse_mask_current_hart();
This function call does SSE probe on every call. Wouldn't it be cheaper to do once?

Regards
Himanshu

> +	local_irq_disable();
> +
> +	for (;;)
> +		cpu_relax();
> +}
> +#endif
>  
>  static void __noreturn default_power_off(void)
>  {
> @@ -18,6 +32,8 @@ EXPORT_SYMBOL(pm_power_off);
>  
>  void machine_restart(char *cmd)
>  {
> +	riscv_sse_mask_current_hart();
> +
>  	/*
>  	 * UpdateCapsule() depends on the system being reset via ResetSystem().
>  	 */
> @@ -30,12 +46,14 @@ void machine_restart(char *cmd)
>  
>  void machine_halt(void)
>  {
> +	riscv_sse_mask_current_hart();
>  	do_kernel_power_off();
>  	default_power_off();
>  }
>  
>  void machine_power_off(void)
>  {
> +	riscv_sse_mask_current_hart();
>  	do_kernel_power_off();
>  	default_power_off();
>  }
> diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
> index fa66f9c97d74..7f0d4e7332f1 100644
> --- a/arch/riscv/kernel/smp.c
> +++ b/arch/riscv/kernel/smp.c
> @@ -23,10 +23,13 @@
>  #include <linux/irq.h>
>  #include <linux/irq_work.h>
>  #include <linux/nmi.h>
> +#include <linux/panic.h>
>  
>  #include <asm/tlbflush.h>
>  #include <asm/cacheflush.h>
>  #include <asm/cpu_ops.h>
> +#include <asm/sbi.h>
> +#include <asm/sse.h>
>  
>  enum ipi_message_type {
>  	IPI_RESCHEDULE,
> @@ -79,8 +82,18 @@ int riscv_hartid_to_cpuid(unsigned long hartid)
>  	return -ENOENT;
>  }
>  
> +void __noreturn panic_smp_self_stop(void)
> +{
> +	riscv_sse_mask_current_hart();
> +	local_irq_disable();
> +
> +	for (;;)
> +		cpu_relax();
> +}
> +
>  static void ipi_stop(void)
>  {
> +	riscv_sse_mask_current_hart();
>  	set_cpu_online(smp_processor_id(), false);
>  	while (1)
>  		wait_for_interrupt();
> @@ -91,6 +104,7 @@ static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0);
>  
>  static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
>  {
> +	riscv_sse_mask_current_hart();
>  	crash_save_cpu(regs, cpu);
>  
>  	atomic_dec(&waiting_for_crash_ipi);
> @@ -254,6 +268,8 @@ void smp_send_stop(void)
>  {
>  	unsigned long timeout;
>  
> +	riscv_sse_mask_current_hart();
> +
>  	if (num_online_cpus() > 1) {
>  		cpumask_t mask;
>  
> @@ -301,6 +317,7 @@ void crash_smp_send_stop(void)
>  		return;
>  
>  	cpus_stopped = 1;
> +	riscv_sse_mask_current_hart();
>  
>  	/*
>  	 * If this cpu is the only one alive at this point in time, online or
> -- 
> 2.50.1 (Apple Git-155)
>