Skip to contentSkip to conversation

riscv: kexec: Fxiup crash_save percpu and machine_kexec_mask_interrupts

PATCH Superseded [email protected] 2 participants 6 messages Sep 21, 2022 – Sep 24, 2022

Subsystems (4)

v4 of 6 Superseded Latest is v6 →

lore
Share & tools
lore
#0 lore raw

v4 cover riscv: kexec: Fxiup crash_save percpu and machine_kexec_mask_interrupts

From: Guo Ren <[email protected]>

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

Also cleanup arm64, x86 declarations in asm/smp.h.

Changlogs:

v4:
- Add cpu_ops[cpu]->cpu_stop() in ipi_cpu_crash_stop
- Wording optimization in comments

V3:
https://lore.kernel.org/linux-riscv/[email protected]/
- Fixup compile problem with !SMP, which reported by [email protected]
- Cleanup declarations in asm/smp.h
- Add reviewed-by

V2:
https://lore.kernel.org/linux-riscv/[email protected]/
- Add Fixes tags
- Remove extern from bool smp_crash_stop_failed(void)

V1:
https://lore.kernel.org/linux-riscv/[email protected]/

Guo Ren (3):
riscv: kexec: Fixup irq controller broken in kexec crash path
riscv: kexec: Fixup crash_smp_send_stop without multi cores
arch: crash: Remove duplicate declaration in smp.h

 arch/arm64/include/asm/smp.h      |  1 -
 arch/riscv/include/asm/smp.h      |  3 +
 arch/riscv/kernel/machine_kexec.c | 46 +++++++++++----
 arch/riscv/kernel/smp.c           | 97 ++++++++++++++++++++++++++++++-
 arch/x86/include/asm/crash.h      |  1 -
 5 files changed, 133 insertions(+), 15 deletions(-)
Signature · 7 lines
2.36.1


_______________________________________________
linux-riscv mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-riscv
#1 lore raw

PATCH v4 1/3 riscv: kexec: Fixup irq controller broken in kexec crash path

From: Guo Ren <[email protected]>

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")
Cc Nick Kossifidis <[email protected]>
Cc Palmer Dabbelt <[email protected]>
---
 arch/riscv/kernel/machine_kexec.c | 35 +++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)
arch/riscv/kernel/machine_kexec.c +35 -0
index ee79e6839b86..db41c676e5a2 100644
@@ -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");
 }
 
Signature · 7 lines
2.36.1


_______________________________________________
linux-riscv mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-riscv
#2 lore raw

PATCH v4 2/3 riscv: kexec: Fixup crash_smp_send_stop without multi cores

In reply to [email protected]

From: Guo Ren <[email protected]>

Current crash_smp_send_stop is the same as the generic one in kernel/panic and misses crash_save_cpu in percpu. This patch is inspired by 78fd584cdec0 ("arm64: kdump: implement machine_crash_shutdown()") and adds the same mechanism for riscv.

Fixes ad943893d5f1 ("RISC-V: Fixup schedule out issue in machine_crash_shutdown()")
Cc Nick Kossifidis <[email protected]>
---
 arch/riscv/include/asm/smp.h      |  3 +
 arch/riscv/kernel/machine_kexec.c | 21 ++-----
 arch/riscv/kernel/smp.c           | 97 ++++++++++++++++++++++++++++++-
 3 files changed, 103 insertions(+), 18 deletions(-)
arch/riscv/include/asm/smp.h +3 -0
index d3443be7eedc..3831b638ecab 100644
@@ -50,6 +50,9 @@ void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops);
 /* Clear IPI for current CPU */
 void riscv_clear_ipi(void);
 
+/* Check other CPUs stop or not */
+bool smp_crash_stop_failed(void);
+
 /* Secondary hart entry */
 asmlinkage void smp_callin(void);
 
arch/riscv/kernel/machine_kexec.c +5 -16
index db41c676e5a2..2d139b724bc8 100644
@@ -140,22 +140,6 @@ void machine_shutdown(void)
 #endif
 }
 
-/* Override the weak function in kernel/panic.c */
-void crash_smp_send_stop(void)
-{
-	static int cpus_stopped;
-
-	/*
-	 * This function can be called twice in panic path, but obviously
-	 * we execute this only once.
-	 */
-	if (cpus_stopped)
-		return;
-
-	smp_send_stop();
-	cpus_stopped = 1;
-}
-
 static void machine_kexec_mask_interrupts(void)
 {
 	unsigned int i;
@@ -230,6 +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
arch/riscv/kernel/smp.c +95 -2

144 lines not on this page · raw message

Signature · 7 lines
2.36.1


_______________________________________________
linux-riscv mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-riscv
#3 lore raw

PATCH v4 3/3 arch: crash: Remove duplicate declaration in smp.h

In reply to [email protected]

From: Guo Ren <[email protected]>

Remove crash_smp_send_stop declarations in arm64, x86 asm/smp.h which has been done in include/linux/smp.h.

---
 arch/arm64/include/asm/smp.h | 1 -
 arch/x86/include/asm/crash.h | 1 -
 2 files changed, 2 deletions(-)
arch/arm64/include/asm/smp.h +0 -1
index fc55f5a57a06..a108ac93fd8f 100644
@@ -141,7 +141,6 @@ static inline void cpu_panic_kernel(void)
  */
 bool cpus_are_stuck_in_kernel(void);
 
-extern void crash_smp_send_stop(void);
 extern bool smp_crash_stop_failed(void);
 extern void panic_smp_self_stop(void);
 
arch/x86/include/asm/crash.h +0 -1
index 8b6bd63530dc..6a9be4907c82 100644
@@ -7,6 +7,5 @@ struct kimage;
 int crash_load_segments(struct kimage *image);
 int crash_setup_memmap_entries(struct kimage *image,
 		struct boot_params *params);
-void crash_smp_send_stop(void);
 
 #endif /* _ASM_X86_CRASH_H */
Signature · 7 lines
2.36.1


_______________________________________________
linux-riscv mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-riscv
Reviewed-by on v4 3/3
#4 lore raw

Re: [PATCH V4 3/3] arch: crash: Remove duplicate declaration in smp.h

Am Mittwoch, 21. September 2022, 05:31:34 CEST schrieb [email protected]:

Quoted 4 lines

From: Guo Ren <[email protected]>

Remove crash_smp_send_stop declarations in arm64, x86 asm/smp.h which has been done in include/linux/smp.h.

nit: the commit message could reference the commit that brought in the generic declarations, which was

	6f1f942cd5fb ("smp: kernel/panic.c - silence warnings")

other than that

Quoted 34 lines
---
 arch/arm64/include/asm/smp.h | 1 -
 arch/x86/include/asm/crash.h | 1 -
 2 files changed, 2 deletions(-)
arch/arm64/include/asm/smp.h +0 -1
index fc55f5a57a06..a108ac93fd8f 100644
@@ -141,7 +141,6 @@ static inline void cpu_panic_kernel(void)
  */
 bool cpus_are_stuck_in_kernel(void);
 
-extern void crash_smp_send_stop(void);
 extern bool smp_crash_stop_failed(void);
 extern void panic_smp_self_stop(void);
 
arch/x86/include/asm/crash.h +0 -1
index 8b6bd63530dc..6a9be4907c82 100644
@@ -7,6 +7,5 @@ struct kimage;
 int crash_load_segments(struct kimage *image);
 int crash_setup_memmap_entries(struct kimage *image,
 		struct boot_params *params);
-void crash_smp_send_stop(void);
 
 #endif /* _ASM_X86_CRASH_H */
author
#5 lore raw

Re: [PATCH V4 3/3] arch: crash: Remove duplicate declaration in smp.h

Quoted 10 lines · Heiko Stuebner

Am Mittwoch, 21. September 2022, 05:31:34 CEST schrieb [email protected]:

Quoted 4 lines

From: Guo Ren <[email protected]>

Remove crash_smp_send_stop declarations in arm64, x86 asm/smp.h which has been done in include/linux/smp.h.

nit: the commit message could reference the commit that brought in the generic declarations, which was

        6f1f942cd5fb ("smp: kernel/panic.c - silence warnings")

Good advice, thx.

Quoted 43 lines

other than that

Quoted 34 lines
---
 arch/arm64/include/asm/smp.h | 1 -
 arch/x86/include/asm/crash.h | 1 -
 2 files changed, 2 deletions(-)
arch/arm64/include/asm/smp.h +0 -1
index fc55f5a57a06..a108ac93fd8f 100644
@@ -141,7 +141,6 @@ static inline void cpu_panic_kernel(void)
  */
 bool cpus_are_stuck_in_kernel(void);
 
-extern void crash_smp_send_stop(void);
 extern bool smp_crash_stop_failed(void);
 extern void panic_smp_self_stop(void);
 
arch/x86/include/asm/crash.h +0 -1
index 8b6bd63530dc..6a9be4907c82 100644
@@ -7,6 +7,5 @@ struct kimage;
 int crash_load_segments(struct kimage *image);
 int crash_setup_memmap_entries(struct kimage *image,
              struct boot_params *params);
-void crash_smp_send_stop(void);
 
 #endif /* _ASM_X86_CRASH_H */
Signature · 2 lines
Best Regards
 Guo Ren