From: Hariprasad Nellitheertha This patch contains the code for stopping the other cpus and snapshotting their register values before doing the kexec reboot. Signed off by Hariprasad Nellitheertha Signed-off-by: Andrew Morton --- 25-akpm/arch/i386/kernel/Makefile | 1 25-akpm/arch/i386/kernel/crash_dump.c | 105 ++++++++++++++++++++ 25-akpm/arch/i386/kernel/machine_kexec.c | 4 25-akpm/arch/i386/kernel/smp.c | 13 ++ 25-akpm/include/asm-i386/crash_dump.h | 44 ++++++++ 25-akpm/include/asm-i386/mach-default/irq_vectors.h | 1 25-akpm/include/asm-i386/smp.h | 1 7 files changed, 167 insertions(+), 2 deletions(-) diff -puN /dev/null arch/i386/kernel/crash_dump.c --- /dev/null 2003-09-15 06:40:47.000000000 -0700 +++ 25-akpm/arch/i386/kernel/crash_dump.c 2004-11-18 23:48:15.384210576 -0800 @@ -0,0 +1,105 @@ +/* + * Architecture specific (i386) functions for kexec based crash dumps. + * + * Created by: Hariprasad Nellitheertha (hari@in.ibm.com) + * + * Copyright (C) IBM Corporation, 2004. All rights reserved. + * + */ + +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +struct pt_regs crash_smp_regs[NR_CPUS]; +long crash_smp_current_task[NR_CPUS]; + +#ifdef CONFIG_SMP +static atomic_t waiting_for_dump_ipi; +static int crash_dump_expect_ipi[NR_CPUS]; +extern void crash_dump_send_ipi(void); +extern void stop_this_cpu(void *); + +static int crash_dump_nmi_callback(struct pt_regs *regs, int cpu) +{ + if (!crash_dump_expect_ipi[cpu]) + return 0; + + crash_dump_expect_ipi[cpu] = 0; + crash_dump_save_this_cpu(regs, cpu); + atomic_dec(&waiting_for_dump_ipi); + + stop_this_cpu(NULL); + + return 1; +} + +void __crash_dump_stop_cpus(void) +{ + int i, cpu, other_cpus; + + preempt_disable(); + cpu = smp_processor_id(); + other_cpus = num_online_cpus()-1; + + if (other_cpus > 0) { + atomic_set(&waiting_for_dump_ipi, other_cpus); + + for (i = 0; i < NR_CPUS; i++) + crash_dump_expect_ipi[i] = (i != cpu && cpu_online(i)); + + set_nmi_callback(crash_dump_nmi_callback); + /* Ensure the new callback function is set before sending + * out the IPI + */ + wmb(); + + crash_dump_send_ipi(); + while (atomic_read(&waiting_for_dump_ipi) > 0) + cpu_relax(); + + unset_nmi_callback(); + } else { + local_irq_disable(); + disable_local_APIC(); + local_irq_enable(); + } + preempt_enable(); +} +#else +void __crash_dump_stop_cpus(void) {} +#endif + +void crash_get_current_regs(struct pt_regs *regs) +{ + __asm__ __volatile__("movl %%ebx,%0" : "=m"(regs->ebx)); + __asm__ __volatile__("movl %%ecx,%0" : "=m"(regs->ecx)); + __asm__ __volatile__("movl %%edx,%0" : "=m"(regs->edx)); + __asm__ __volatile__("movl %%esi,%0" : "=m"(regs->esi)); + __asm__ __volatile__("movl %%edi,%0" : "=m"(regs->edi)); + __asm__ __volatile__("movl %%ebp,%0" : "=m"(regs->ebp)); + __asm__ __volatile__("movl %%eax,%0" : "=m"(regs->eax)); + __asm__ __volatile__("movl %%esp,%0" : "=m"(regs->esp)); + __asm__ __volatile__("movw %%ss, %%ax;" :"=a"(regs->xss)); + __asm__ __volatile__("movw %%cs, %%ax;" :"=a"(regs->xcs)); + __asm__ __volatile__("movw %%ds, %%ax;" :"=a"(regs->xds)); + __asm__ __volatile__("movw %%es, %%ax;" :"=a"(regs->xes)); + __asm__ __volatile__("pushfl; popl %0" :"=m"(regs->eflags)); + + regs->eip = (unsigned long)current_text_addr(); +} + +void crash_dump_save_this_cpu(struct pt_regs *regs, int cpu) +{ + crash_smp_current_task[cpu] = (long)current; + crash_smp_regs[cpu] = *regs; +} + diff -puN arch/i386/kernel/machine_kexec.c~crashdump-register-snapshotting-before-kexec-boot arch/i386/kernel/machine_kexec.c --- 25/arch/i386/kernel/machine_kexec.c~crashdump-register-snapshotting-before-kexec-boot 2004-11-18 23:48:15.373212248 -0800 +++ 25-akpm/arch/i386/kernel/machine_kexec.c 2004-11-18 23:48:15.385210424 -0800 @@ -16,6 +16,7 @@ #include #include #include +#include static inline unsigned long read_cr3(void) { @@ -194,6 +195,9 @@ void machine_kexec(struct kimage *image) unsigned long reboot_code_buffer; relocate_new_kernel_t rnk; + crash_dump_stop_cpus(); + crash_dump_save_registers(); + /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); diff -puN arch/i386/kernel/Makefile~crashdump-register-snapshotting-before-kexec-boot arch/i386/kernel/Makefile --- 25/arch/i386/kernel/Makefile~crashdump-register-snapshotting-before-kexec-boot 2004-11-18 23:48:15.375211944 -0800 +++ 25-akpm/arch/i386/kernel/Makefile 2004-11-18 23:48:15.385210424 -0800 @@ -25,6 +25,7 @@ obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-$(CONFIG_X86_LOCAL_APIC) += apic.o nmi.o obj-$(CONFIG_X86_IO_APIC) += io_apic.o obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o +obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_X86_NUMAQ) += numaq.o obj-$(CONFIG_X86_SUMMIT_NUMA) += summit.o obj-$(CONFIG_KPROBES) += kprobes.o diff -puN arch/i386/kernel/smp.c~crashdump-register-snapshotting-before-kexec-boot arch/i386/kernel/smp.c --- 25/arch/i386/kernel/smp.c~crashdump-register-snapshotting-before-kexec-boot 2004-11-18 23:48:15.376211792 -0800 +++ 25-akpm/arch/i386/kernel/smp.c 2004-11-18 23:48:15.386210272 -0800 @@ -143,6 +143,9 @@ void __send_IPI_shortcut(unsigned int sh */ cfg = __prepare_ICR(shortcut, vector); + if (vector == CRASH_DUMP_VECTOR) + cfg = (cfg&~APIC_VECTOR_MASK)|APIC_DM_NMI; + /* * Send the IPI. The write to APIC_ICR fires this off. */ @@ -221,6 +224,9 @@ inline void send_IPI_mask_sequence(cpuma */ cfg = __prepare_ICR(0, vector); + if (vector == CRASH_DUMP_VECTOR) + cfg = (cfg&~APIC_VECTOR_MASK)|APIC_DM_NMI; + /* * Send the IPI. The write to APIC_ICR fires this off. */ @@ -489,6 +495,11 @@ void smp_send_reschedule(int cpu) send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR); } +void crash_dump_send_ipi(void) +{ + send_IPI_allbutself(CRASH_DUMP_VECTOR); +} + /* * Structure and data for smp_call_function(). This is designed to minimise * static memory requirements. It also looks cleaner. @@ -565,7 +576,7 @@ int smp_call_function (void (*func) (voi return 0; } -static void stop_this_cpu (void * dummy) +void stop_this_cpu (void * dummy) { /* * Remove this CPU: diff -puN include/asm-i386/crash_dump.h~crashdump-register-snapshotting-before-kexec-boot include/asm-i386/crash_dump.h --- 25/include/asm-i386/crash_dump.h~crashdump-register-snapshotting-before-kexec-boot 2004-11-18 23:48:15.377211640 -0800 +++ 25-akpm/include/asm-i386/crash_dump.h 2004-11-18 23:48:15.387210120 -0800 @@ -1,5 +1,7 @@ /* asm-i386/crash_dump.h */ #include +#include +#include #ifdef CONFIG_CRASH_DUMP extern unsigned int dump_enabled; @@ -9,6 +11,12 @@ extern void __crash_relocate_mem(unsigne extern unsigned long __init find_max_low_pfn(void); extern void __init find_max_pfn(void); +extern struct pt_regs crash_smp_regs[NR_CPUS]; +extern long crash_smp_current_task[NR_CPUS]; +extern void crash_dump_save_this_cpu(struct pt_regs *, int); +extern void __crash_dump_stop_cpus(void); +extern void crash_get_current_regs(struct pt_regs *regs); + #define CRASH_BACKUP_BASE ((unsigned long)CONFIG_BACKUP_BASE * 0x100000) #define CRASH_BACKUP_SIZE ((unsigned long)CONFIG_BACKUP_SIZE * 0x100000) #define CRASH_RELOCATE_SIZE 0xa0000 @@ -30,11 +38,45 @@ static inline void crash_reserve_bootmem { if (!dump_enabled) { reserve_bootmem(CRASH_BACKUP_BASE, - CRASH_BACKUP_SIZE + CRASH_RELOCATE_SIZE); + CRASH_BACKUP_SIZE + CRASH_RELOCATE_SIZE + PAGE_SIZE); } } + +static inline void crash_dump_stop_cpus(void) +{ + int cpu; + + if (!crashed) + return; + + cpu = smp_processor_id(); + + crash_smp_current_task[cpu] = (long)current; + crash_get_current_regs(&crash_smp_regs[cpu]); + + /* This also captures the register states of the other cpus */ + __crash_dump_stop_cpus(); +#if defined(CONFIG_X86_IO_APIC) + disable_IO_APIC(); +#endif +#if defined(CONFIG_X86_LOCAL_APIC) + disconnect_bsp_APIC(); +#endif +} + +static inline void crash_dump_save_registers(void) +{ + void *addr; + + addr = __va(CRASH_BACKUP_BASE + CRASH_BACKUP_SIZE + CRASH_RELOCATE_SIZE); + memcpy(addr, crash_smp_regs, (sizeof(struct pt_regs)*NR_CPUS)); + addr += sizeof(struct pt_regs)*NR_CPUS; + memcpy(addr, crash_smp_current_task, (sizeof(long)*NR_CPUS)); +} #else #define crash_relocate_mem() do { } while(0) #define set_saved_max_pfn() do { } while(0) #define crash_reserve_bootmem() do { } while(0) +#define crash_dump_stop_cpus() do { } while(0) +#define crash_dump_save_registers() do { } while(0) #endif diff -puN include/asm-i386/mach-default/irq_vectors.h~crashdump-register-snapshotting-before-kexec-boot include/asm-i386/mach-default/irq_vectors.h --- 25/include/asm-i386/mach-default/irq_vectors.h~crashdump-register-snapshotting-before-kexec-boot 2004-11-18 23:48:15.379211336 -0800 +++ 25-akpm/include/asm-i386/mach-default/irq_vectors.h 2004-11-18 23:48:15.387210120 -0800 @@ -48,6 +48,7 @@ #define INVALIDATE_TLB_VECTOR 0xfd #define RESCHEDULE_VECTOR 0xfc #define CALL_FUNCTION_VECTOR 0xfb +#define CRASH_DUMP_VECTOR 0xfa #define THERMAL_APIC_VECTOR 0xf0 /* diff -puN include/asm-i386/smp.h~crashdump-register-snapshotting-before-kexec-boot include/asm-i386/smp.h --- 25/include/asm-i386/smp.h~crashdump-register-snapshotting-before-kexec-boot 2004-11-18 23:48:15.380211184 -0800 +++ 25-akpm/include/asm-i386/smp.h 2004-11-18 23:48:15.387210120 -0800 @@ -41,6 +41,7 @@ extern void smp_message_irq(int cpl, voi extern void smp_invalidate_rcv(void); /* Process an NMI */ extern void (*mtrr_hook) (void); extern void zap_low_mappings (void); +extern void stop_this_cpu(void *); #define MAX_APICID 256 extern u8 x86_cpu_to_apicid[]; _