From: Guo Ren <guoren@linux.alibaba.com>

If a crash happens on cpu3 and all interrupts are binding on cpu0, the
bad irq routing will cause a crash kernel which can't receive any irq.
Because crash kernel won't clean up all harts' PLIC enable bits in
enable registers. This patch is similar to 9141a003a491 ("ARM: 7316/1:
kexec: EOI active and mask all interrupts in kexec crash path") and
78fd584cdec0 ("arm64: kdump: implement machine_crash_shutdown()"), and
PowerPC also has the same mechanism.

Fixes: fba8a8674f68 ("RISC-V: Add kexec support")
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: AKASHI Takahiro <takahiro.akashi@linaro.org>
Cc: Nick Kossifidis <mick@ics.forth.gr>
---
 arch/riscv/kernel/machine_kexec.c | 35 +++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c
index ee79e6839b86..db41c676e5a2 100644
--- a/arch/riscv/kernel/machine_kexec.c
+++ b/arch/riscv/kernel/machine_kexec.c
@@ -15,6 +15,8 @@
 #include <linux/compiler.h>	/* For unreachable() */
 #include <linux/cpu.h>		/* For cpu_down() */
 #include <linux/reboot.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
 
 /*
  * kexec_image_info - Print received image details
@@ -154,6 +156,37 @@ void crash_smp_send_stop(void)
 	cpus_stopped = 1;
 }
 
+static void machine_kexec_mask_interrupts(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+
+	for_each_irq_desc(i, desc) {
+		struct irq_chip *chip;
+		int ret;
+
+		chip = irq_desc_get_chip(desc);
+		if (!chip)
+			continue;
+
+		/*
+		 * First try to remove the active state. If this
+		 * fails, try to EOI the interrupt.
+		 */
+		ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false);
+
+		if (ret && irqd_irq_inprogress(&desc->irq_data) &&
+		    chip->irq_eoi)
+			chip->irq_eoi(&desc->irq_data);
+
+		if (chip->irq_mask)
+			chip->irq_mask(&desc->irq_data);
+
+		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
+			chip->irq_disable(&desc->irq_data);
+	}
+}
+
 /*
  * machine_crash_shutdown - Prepare to kexec after a kernel crash
  *
@@ -169,6 +202,8 @@ machine_crash_shutdown(struct pt_regs *regs)
 	crash_smp_send_stop();
 
 	crash_save_cpu(regs, smp_processor_id());
+	machine_kexec_mask_interrupts();
+
 	pr_info("Starting crashdump kernel...\n");
 }
 
-- 
2.36.1

It is ok for me

Reviewed-by: Xianting Tian <xianting.tian@linux.alibaba.com>

在 2022/8/18 上午12:12, guoren@kernel.org 写道:
> From: Guo Ren <guoren@linux.alibaba.com>
>
> If a crash happens on cpu3 and all interrupts are binding on cpu0, the
> bad irq routing will cause a crash kernel which can't receive any irq.
> Because crash kernel won't clean up all harts' PLIC enable bits in
> enable registers. This patch is similar to 9141a003a491 ("ARM: 7316/1:
> kexec: EOI active and mask all interrupts in kexec crash path") and
> 78fd584cdec0 ("arm64: kdump: implement machine_crash_shutdown()"), and
> PowerPC also has the same mechanism.
>
> Fixes: fba8a8674f68 ("RISC-V: Add kexec support")
> Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
> Signed-off-by: Guo Ren <guoren@kernel.org>
> Cc: Will Deacon <will.deacon@arm.com>
> Cc: AKASHI Takahiro <takahiro.akashi@linaro.org>
> Cc: Nick Kossifidis <mick@ics.forth.gr>
> ---
>   arch/riscv/kernel/machine_kexec.c | 35 +++++++++++++++++++++++++++++++
>   1 file changed, 35 insertions(+)
>
> diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c
> index ee79e6839b86..db41c676e5a2 100644
> --- a/arch/riscv/kernel/machine_kexec.c
> +++ b/arch/riscv/kernel/machine_kexec.c
> @@ -15,6 +15,8 @@
>   #include <linux/compiler.h>	/* For unreachable() */
>   #include <linux/cpu.h>		/* For cpu_down() */
>   #include <linux/reboot.h>
> +#include <linux/interrupt.h>
> +#include <linux/irq.h>
>   
>   /*
>    * kexec_image_info - Print received image details
> @@ -154,6 +156,37 @@ void crash_smp_send_stop(void)
>   	cpus_stopped = 1;
>   }
>   
> +static void machine_kexec_mask_interrupts(void)
> +{
> +	unsigned int i;
> +	struct irq_desc *desc;
> +
> +	for_each_irq_desc(i, desc) {
> +		struct irq_chip *chip;
> +		int ret;
> +
> +		chip = irq_desc_get_chip(desc);
> +		if (!chip)
> +			continue;
> +
> +		/*
> +		 * First try to remove the active state. If this
> +		 * fails, try to EOI the interrupt.
> +		 */
> +		ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false);
> +
> +		if (ret && irqd_irq_inprogress(&desc->irq_data) &&
> +		    chip->irq_eoi)
> +			chip->irq_eoi(&desc->irq_data);
> +
> +		if (chip->irq_mask)
> +			chip->irq_mask(&desc->irq_data);
> +
> +		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
> +			chip->irq_disable(&desc->irq_data);
> +	}
> +}
> +
>   /*
>    * machine_crash_shutdown - Prepare to kexec after a kernel crash
>    *
> @@ -169,6 +202,8 @@ machine_crash_shutdown(struct pt_regs *regs)
>   	crash_smp_send_stop();
>   
>   	crash_save_cpu(regs, smp_processor_id());
> +	machine_kexec_mask_interrupts();
> +
>   	pr_info("Starting crashdump kernel...\n");
>   }
>