Merge patch series "riscv: kexec: Fxiup crash_save percpu and machine_kexec_mask_interrupts"

guoren@kernel.org <guoren@kernel.org> says:

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

Current riscv kexec can't crash_save percpu states and disable
interrupts properly. The patch series fix them, make kexec work correct.

* b4-shazam-merge:
  riscv: kexec: Fixup crash_smp_send_stop without multi cores
  riscv: kexec: Fixup irq controller broken in kexec crash path

Link: https://lore.kernel.org/r/20221020141603.2856206-1-guoren@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

1 files changed, 35 insertions, 11 deletions

diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c
index ee79e6839b86..2d139b724bc8 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
@@ -138,20 +140,35 @@ void machine_shutdown(void)
 #endif
 }
 
-/* Override the weak function in kernel/panic.c */
-void crash_smp_send_stop(void)
+static void machine_kexec_mask_interrupts(void)
 {
-	static int cpus_stopped;
+	unsigned int i;
+	struct irq_desc *desc;
 
-	/*
-	 * This function can be called twice in panic path, but obviously
-	 * we execute this only once.
-	 */
-	if (cpus_stopped)
-		return;
+	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);
 
-	smp_send_stop();
-	cpus_stopped = 1;
+		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);
+	}
 }
 
 /*
@@ -169,6 +186,8 @@ 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");
 }
 
@@ -195,6 +214,11 @@ machine_kexec(struct kimage *image)
 	void *control_code_buffer = page_address(image->control_code_page);
 	riscv_kexec_method kexec_method = NULL;
 
+#ifdef CONFIG_SMP
+	WARN(smp_crash_stop_failed(),
+		"Some CPUs may be stale, kdump will be unreliable.\n");
+#endif
+
 	if (image->type != KEXEC_TYPE_CRASH)
 		kexec_method = control_code_buffer;
 	else