| Message ID | 9bc011f03f5dd30fc66178461d303d3ec1b7ac35.1465502767.git.geoff@infradead.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
Geoff, On Thu, Jun 09, 2016 at 08:08:44PM +0000, Geoff Levand wrote: > From: AKASHI Takahiro <takahiro.akashi@linaro.org> > > Primary kernel calls machine_crash_shutdown() to shut down non-boot cpus > and save registers' status in per-cpu ELF notes before starting crash > dump kernel. See kernel_kexec(). > Even if not all secondary cpus have shut down, we do kdump anyway. > > As we don't have to make non-boot(crashed) cpus offline (to preserve > correct status of cpus at crash dump) before shutting down, this patch > also adds a variant of smp_send_stop(). > > Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org> > --- > arch/arm64/include/asm/hardirq.h | 2 +- > arch/arm64/include/asm/kexec.h | 41 +++++++++++++++++++++++++- > arch/arm64/include/asm/smp.h | 4 +++ > arch/arm64/kernel/machine_kexec.c | 56 +++++++++++++++++++++++++++++++++-- > arch/arm64/kernel/smp.c | 61 +++++++++++++++++++++++++++++++++++++++ > 5 files changed, 159 insertions(+), 5 deletions(-) > > diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h > index 8740297..1473fc2 100644 > --- a/arch/arm64/include/asm/hardirq.h > +++ b/arch/arm64/include/asm/hardirq.h > @@ -20,7 +20,7 @@ > #include <linux/threads.h> > #include <asm/irq.h> > > -#define NR_IPI 6 > +#define NR_IPI 7 > > typedef struct { > unsigned int __softirq_pending; > diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h > index 04744dc..600b960 100644 > --- a/arch/arm64/include/asm/kexec.h > +++ b/arch/arm64/include/asm/kexec.h > @@ -40,7 +40,46 @@ > static inline void crash_setup_regs(struct pt_regs *newregs, > struct pt_regs *oldregs) > { > - /* Empty routine needed to avoid build errors. */ > + if (oldregs) { > + memcpy(newregs, oldregs, sizeof(*newregs)); > + } else { > + u64 tmp1, tmp2; > + > + __asm__ __volatile__ ( > + "stp x0, x1, [%2, #16 * 0]\n" > + "stp x2, x3, [%2, #16 * 1]\n" > + "stp x4, x5, [%2, #16 * 2]\n" > + "stp x6, x7, [%2, #16 * 3]\n" > + "stp x8, x9, [%2, #16 * 4]\n" > + "stp x10, x11, [%2, #16 * 5]\n" > + "stp x12, x13, [%2, #16 * 6]\n" > + "stp x14, x15, [%2, #16 * 7]\n" > + "stp x16, x17, [%2, #16 * 8]\n" > + "stp x18, x19, [%2, #16 * 9]\n" > + "stp x20, x21, [%2, #16 * 10]\n" > + "stp x22, x23, [%2, #16 * 11]\n" > + "stp x24, x25, [%2, #16 * 12]\n" > + "stp x26, x27, [%2, #16 * 13]\n" > + "stp x28, x29, [%2, #16 * 14]\n" > + "mov %0, sp\n" > + "stp x30, %0, [%2, #16 * 15]\n" > + > + "/* faked current PSTATE */\n" > + "mrs %0, CurrentEL\n" > + "mrs %1, DAIF\n" > + "orr %0, %0, %1\n" > + "mrs %1, NZCV\n" > + "orr %0, %0, %1\n" > + > + /* pc */ > + "adr %1, 1f\n" > + "1:" > + "stp %1, %0, [%2, #16 * 16]\n" > + : "=r" (tmp1), "=r" (tmp2), "+r" (newregs) > + : > + : "memory" > + ); > + } > } > > #endif /* __ASSEMBLY__ */ > diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h > index 38712f4..979154a 100644 > --- a/arch/arm64/include/asm/smp.h > +++ b/arch/arm64/include/asm/smp.h > @@ -134,6 +134,10 @@ static inline void cpu_panic_kernel(void) > */ > bool cpus_are_stuck_in_kernel(void); > > +#ifdef CONFIG_KEXEC_CORE > +extern void smp_send_crash_stop(void); > +#endif > + > #endif /* ifndef __ASSEMBLY__ */ > > #endif /* ifndef __ASM_SMP_H */ > diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c > index 0a8b04d..93588b2 100644 > --- a/arch/arm64/kernel/machine_kexec.c > +++ b/arch/arm64/kernel/machine_kexec.c > @@ -10,6 +10,9 @@ > */ > > #include <linux/highmem.h> > +#include <linux/interrupt.h> > +#include <linux/irq.h> > +#include <linux/kernel.h> > #include <linux/kexec.h> > #include <linux/libfdt_env.h> > #include <linux/of_fdt.h> > @@ -28,6 +31,7 @@ > extern const unsigned char arm64_relocate_new_kernel[]; > extern const unsigned long arm64_relocate_new_kernel_size; > > +bool in_crash_kexec; > static unsigned long kimage_start; > > /** > @@ -179,7 +183,8 @@ void machine_kexec(struct kimage *kimage) > /* > * New cpus may have become stuck_in_kernel after we loaded the image. > */ > - BUG_ON(cpus_are_stuck_in_kernel() && (num_online_cpus() > 1)); > + BUG_ON(cpus_are_stuck_in_kernel() && (num_online_cpus() > 1) && > + !WARN_ON(in_crash_kexec)); > > reboot_code_buffer_phys = page_to_phys(kimage->control_code_page); > reboot_code_buffer = kmap(kimage->control_code_page); > @@ -236,13 +241,58 @@ void machine_kexec(struct kimage *kimage) > * relocation is complete. > */ > > - cpu_soft_restart(1, reboot_code_buffer_phys, kimage->head, > + cpu_soft_restart(in_crash_kexec, reboot_code_buffer_phys, kimage->head, => !in_crash_kexec Please let me recognize any changes you made clearly if you modified my part in the patchset before posting it. Thanks, -Takahiro AKASHI > kimage_start, 0); > > BUG(); /* Should never get here. */ > } > > +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 - shutdown non-crashing cpus and save registers > + */ > void machine_crash_shutdown(struct pt_regs *regs) > { > - /* Empty routine needed to avoid build errors. */ > + local_irq_disable(); > + > + in_crash_kexec = true; > + > + /* shutdown non-crashing cpus */ > + smp_send_crash_stop(); > + > + /* for crashing cpu */ > + crash_save_cpu(regs, smp_processor_id()); > + machine_kexec_mask_interrupts(); > + > + pr_info("Starting crashdump kernel...\n"); > } > diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c > index d0bcd55..f6461ef 100644 > --- a/arch/arm64/kernel/smp.c > +++ b/arch/arm64/kernel/smp.c > @@ -37,6 +37,7 @@ > #include <linux/completion.h> > #include <linux/of.h> > #include <linux/irq_work.h> > +#include <linux/kexec.h> > > #include <asm/alternative.h> > #include <asm/atomic.h> > @@ -71,6 +72,7 @@ enum ipi_msg_type { > IPI_RESCHEDULE, > IPI_CALL_FUNC, > IPI_CPU_STOP, > + IPI_CPU_CRASH_STOP, > IPI_TIMER, > IPI_IRQ_WORK, > IPI_WAKEUP > @@ -726,6 +728,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = { > S(IPI_RESCHEDULE, "Rescheduling interrupts"), > S(IPI_CALL_FUNC, "Function call interrupts"), > S(IPI_CPU_STOP, "CPU stop interrupts"), > + S(IPI_CPU_CRASH_STOP, "CPU stop (for crash dump) interrupts"), > S(IPI_TIMER, "Timer broadcast interrupts"), > S(IPI_IRQ_WORK, "IRQ work interrupts"), > S(IPI_WAKEUP, "CPU wake-up interrupts"), > @@ -800,6 +803,28 @@ static void ipi_cpu_stop(unsigned int cpu) > cpu_relax(); > } > > +#ifdef CONFIG_KEXEC_CORE > +static atomic_t waiting_for_crash_ipi; > + > +static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) > +{ > + crash_save_cpu(regs, cpu); > + > + atomic_dec(&waiting_for_crash_ipi); > + > + local_irq_disable(); > + > +#ifdef CONFIG_HOTPLUG_CPU > + if (cpu_ops[cpu]->cpu_die) > + cpu_ops[cpu]->cpu_die(cpu); > +#endif > + > + /* just in case */ > + while (1) > + wfi(); > +} > +#endif > + > /* > * Main handler for inter-processor interrupts > */ > @@ -830,6 +855,14 @@ void handle_IPI(int ipinr, struct pt_regs *regs) > irq_exit(); > break; > > +#ifdef CONFIG_KEXEC_CORE > + case IPI_CPU_CRASH_STOP: > + irq_enter(); > + ipi_cpu_crash_stop(cpu, regs); > + > + unreachable(); > +#endif > + > #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST > case IPI_TIMER: > irq_enter(); > @@ -902,6 +935,34 @@ void smp_send_stop(void) > cpumask_pr_args(cpu_online_mask)); > } > > +#ifdef CONFIG_KEXEC_CORE > +void smp_send_crash_stop(void) > +{ > + cpumask_t mask; > + unsigned long timeout; > + > + if (num_online_cpus() == 1) > + return; > + > + cpumask_copy(&mask, cpu_online_mask); > + cpumask_clear_cpu(smp_processor_id(), &mask); > + > + atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); > + > + pr_crit("SMP: stopping secondary CPUs\n"); > + smp_cross_call(&mask, IPI_CPU_CRASH_STOP); > + > + /* Wait up to one second for other CPUs to stop */ > + timeout = USEC_PER_SEC; > + while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--) > + udelay(1); > + > + if (atomic_read(&waiting_for_crash_ipi) > 0) > + pr_warning("SMP: failed to stop secondary CPUs %*pbl\n", > + cpumask_pr_args(cpu_online_mask)); > +} > +#endif > + > /* > * not supported here > */ > -- > 2.5.0 > >
On Tue, 2016-06-14 at 16:13 +0900, AKASHI Takahiro wrote: > On Thu, Jun 09, 2016 at 08:08:44PM +0000, Geoff Levand wrote: > > > > -> > > > cpu_soft_restart(1, reboot_code_buffer_phys, kimage->head, > > +> > > > cpu_soft_restart(in_crash_kexec, reboot_code_buffer_phys, kimage->head, > > => !in_crash_kexec > > Please let me recognize any changes you made clearly if you modified my part > in the patchset before posting it. I pushed out a new branch kexec-v18.1 with this fix. Thanks for checking! -Geoff
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h index 8740297..1473fc2 100644 --- a/arch/arm64/include/asm/hardirq.h +++ b/arch/arm64/include/asm/hardirq.h @@ -20,7 +20,7 @@ #include <linux/threads.h> #include <asm/irq.h> -#define NR_IPI 6 +#define NR_IPI 7 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h index 04744dc..600b960 100644 --- a/arch/arm64/include/asm/kexec.h +++ b/arch/arm64/include/asm/kexec.h @@ -40,7 +40,46 @@ static inline void crash_setup_regs(struct pt_regs *newregs, struct pt_regs *oldregs) { - /* Empty routine needed to avoid build errors. */ + if (oldregs) { + memcpy(newregs, oldregs, sizeof(*newregs)); + } else { + u64 tmp1, tmp2; + + __asm__ __volatile__ ( + "stp x0, x1, [%2, #16 * 0]\n" + "stp x2, x3, [%2, #16 * 1]\n" + "stp x4, x5, [%2, #16 * 2]\n" + "stp x6, x7, [%2, #16 * 3]\n" + "stp x8, x9, [%2, #16 * 4]\n" + "stp x10, x11, [%2, #16 * 5]\n" + "stp x12, x13, [%2, #16 * 6]\n" + "stp x14, x15, [%2, #16 * 7]\n" + "stp x16, x17, [%2, #16 * 8]\n" + "stp x18, x19, [%2, #16 * 9]\n" + "stp x20, x21, [%2, #16 * 10]\n" + "stp x22, x23, [%2, #16 * 11]\n" + "stp x24, x25, [%2, #16 * 12]\n" + "stp x26, x27, [%2, #16 * 13]\n" + "stp x28, x29, [%2, #16 * 14]\n" + "mov %0, sp\n" + "stp x30, %0, [%2, #16 * 15]\n" + + "/* faked current PSTATE */\n" + "mrs %0, CurrentEL\n" + "mrs %1, DAIF\n" + "orr %0, %0, %1\n" + "mrs %1, NZCV\n" + "orr %0, %0, %1\n" + + /* pc */ + "adr %1, 1f\n" + "1:" + "stp %1, %0, [%2, #16 * 16]\n" + : "=r" (tmp1), "=r" (tmp2), "+r" (newregs) + : + : "memory" + ); + } } #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index 38712f4..979154a 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -134,6 +134,10 @@ static inline void cpu_panic_kernel(void) */ bool cpus_are_stuck_in_kernel(void); +#ifdef CONFIG_KEXEC_CORE +extern void smp_send_crash_stop(void); +#endif + #endif /* ifndef __ASSEMBLY__ */ #endif /* ifndef __ASM_SMP_H */ diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 0a8b04d..93588b2 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -10,6 +10,9 @@ */ #include <linux/highmem.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/kernel.h> #include <linux/kexec.h> #include <linux/libfdt_env.h> #include <linux/of_fdt.h> @@ -28,6 +31,7 @@ extern const unsigned char arm64_relocate_new_kernel[]; extern const unsigned long arm64_relocate_new_kernel_size; +bool in_crash_kexec; static unsigned long kimage_start; /** @@ -179,7 +183,8 @@ void machine_kexec(struct kimage *kimage) /* * New cpus may have become stuck_in_kernel after we loaded the image. */ - BUG_ON(cpus_are_stuck_in_kernel() && (num_online_cpus() > 1)); + BUG_ON(cpus_are_stuck_in_kernel() && (num_online_cpus() > 1) && + !WARN_ON(in_crash_kexec)); reboot_code_buffer_phys = page_to_phys(kimage->control_code_page); reboot_code_buffer = kmap(kimage->control_code_page); @@ -236,13 +241,58 @@ void machine_kexec(struct kimage *kimage) * relocation is complete. */ - cpu_soft_restart(1, reboot_code_buffer_phys, kimage->head, + cpu_soft_restart(in_crash_kexec, reboot_code_buffer_phys, kimage->head, kimage_start, 0); BUG(); /* Should never get here. */ } +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 - shutdown non-crashing cpus and save registers + */ void machine_crash_shutdown(struct pt_regs *regs) { - /* Empty routine needed to avoid build errors. */ + local_irq_disable(); + + in_crash_kexec = true; + + /* shutdown non-crashing cpus */ + smp_send_crash_stop(); + + /* for crashing cpu */ + crash_save_cpu(regs, smp_processor_id()); + machine_kexec_mask_interrupts(); + + pr_info("Starting crashdump kernel...\n"); } diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index d0bcd55..f6461ef 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -37,6 +37,7 @@ #include <linux/completion.h> #include <linux/of.h> #include <linux/irq_work.h> +#include <linux/kexec.h> #include <asm/alternative.h> #include <asm/atomic.h> @@ -71,6 +72,7 @@ enum ipi_msg_type { IPI_RESCHEDULE, IPI_CALL_FUNC, IPI_CPU_STOP, + IPI_CPU_CRASH_STOP, IPI_TIMER, IPI_IRQ_WORK, IPI_WAKEUP @@ -726,6 +728,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = { S(IPI_RESCHEDULE, "Rescheduling interrupts"), S(IPI_CALL_FUNC, "Function call interrupts"), S(IPI_CPU_STOP, "CPU stop interrupts"), + S(IPI_CPU_CRASH_STOP, "CPU stop (for crash dump) interrupts"), S(IPI_TIMER, "Timer broadcast interrupts"), S(IPI_IRQ_WORK, "IRQ work interrupts"), S(IPI_WAKEUP, "CPU wake-up interrupts"), @@ -800,6 +803,28 @@ static void ipi_cpu_stop(unsigned int cpu) cpu_relax(); } +#ifdef CONFIG_KEXEC_CORE +static atomic_t waiting_for_crash_ipi; + +static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) +{ + crash_save_cpu(regs, cpu); + + atomic_dec(&waiting_for_crash_ipi); + + local_irq_disable(); + +#ifdef CONFIG_HOTPLUG_CPU + if (cpu_ops[cpu]->cpu_die) + cpu_ops[cpu]->cpu_die(cpu); +#endif + + /* just in case */ + while (1) + wfi(); +} +#endif + /* * Main handler for inter-processor interrupts */ @@ -830,6 +855,14 @@ void handle_IPI(int ipinr, struct pt_regs *regs) irq_exit(); break; +#ifdef CONFIG_KEXEC_CORE + case IPI_CPU_CRASH_STOP: + irq_enter(); + ipi_cpu_crash_stop(cpu, regs); + + unreachable(); +#endif + #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST case IPI_TIMER: irq_enter(); @@ -902,6 +935,34 @@ void smp_send_stop(void) cpumask_pr_args(cpu_online_mask)); } +#ifdef CONFIG_KEXEC_CORE +void smp_send_crash_stop(void) +{ + cpumask_t mask; + unsigned long timeout; + + if (num_online_cpus() == 1) + return; + + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + + atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); + + pr_crit("SMP: stopping secondary CPUs\n"); + smp_cross_call(&mask, IPI_CPU_CRASH_STOP); + + /* Wait up to one second for other CPUs to stop */ + timeout = USEC_PER_SEC; + while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--) + udelay(1); + + if (atomic_read(&waiting_for_crash_ipi) > 0) + pr_warning("SMP: failed to stop secondary CPUs %*pbl\n", + cpumask_pr_args(cpu_online_mask)); +} +#endif + /* * not supported here */