X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=arch%2Fpowerpc%2Fkernel%2Fcrash.c;h=b537cfa4e09b167d383cc8a908790dfd3560127f;hb=489244498ec99c949ecbd7105299066cff283dcd;hp=5f248e3fdf821abfc71a3041a3569762c2d4807d;hpb=bf785ee0aeea7a3e717cb1e11df4135b6cbde7da;p=pandora-kernel.git diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 5f248e3fdf82..b537cfa4e09b 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -22,10 +22,13 @@ #include #include #include +#include #include +#include #include #include +#include #include #include #include @@ -40,6 +43,7 @@ /* This keeps a track of which one is crashing cpu. */ int crashing_cpu = -1; +static cpumask_t cpus_in_crash = CPU_MASK_NONE; static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data, size_t data_len) @@ -84,7 +88,10 @@ static void crash_save_this_cpu(struct pt_regs *regs, int cpu) * squirrelled away. ELF notes happen to provide * all of that that no need to invent something new. */ - buf = &crash_notes[cpu][0]; + buf = (u32*)per_cpu_ptr(crash_notes, cpu); + if (!buf) + return; + memset(&prstatus, 0, sizeof(prstatus)); prstatus.pr_pid = current->pid; elf_core_copy_regs(&prstatus.pr_reg, regs); @@ -93,105 +100,67 @@ static void crash_save_this_cpu(struct pt_regs *regs, int cpu) final_note(buf); } -/* FIXME Merge this with xmon_save_regs ?? */ -static inline void crash_get_current_regs(struct pt_regs *regs) -{ - unsigned long tmp1, tmp2; - - __asm__ __volatile__ ( - "std 0,0(%2)\n" - "std 1,8(%2)\n" - "std 2,16(%2)\n" - "std 3,24(%2)\n" - "std 4,32(%2)\n" - "std 5,40(%2)\n" - "std 6,48(%2)\n" - "std 7,56(%2)\n" - "std 8,64(%2)\n" - "std 9,72(%2)\n" - "std 10,80(%2)\n" - "std 11,88(%2)\n" - "std 12,96(%2)\n" - "std 13,104(%2)\n" - "std 14,112(%2)\n" - "std 15,120(%2)\n" - "std 16,128(%2)\n" - "std 17,136(%2)\n" - "std 18,144(%2)\n" - "std 19,152(%2)\n" - "std 20,160(%2)\n" - "std 21,168(%2)\n" - "std 22,176(%2)\n" - "std 23,184(%2)\n" - "std 24,192(%2)\n" - "std 25,200(%2)\n" - "std 26,208(%2)\n" - "std 27,216(%2)\n" - "std 28,224(%2)\n" - "std 29,232(%2)\n" - "std 30,240(%2)\n" - "std 31,248(%2)\n" - "mfmsr %0\n" - "std %0, 264(%2)\n" - "mfctr %0\n" - "std %0, 280(%2)\n" - "mflr %0\n" - "std %0, 288(%2)\n" - "bl 1f\n" - "1: mflr %1\n" - "std %1, 256(%2)\n" - "mtlr %0\n" - "mfxer %0\n" - "std %0, 296(%2)\n" - : "=&r" (tmp1), "=&r" (tmp2) - : "b" (regs)); -} - -/* We may have saved_regs from where the error came from - * or it is NULL if via a direct panic(). - */ -static void crash_save_self(struct pt_regs *saved_regs) -{ - struct pt_regs regs; - int cpu; - - cpu = smp_processor_id(); - if (saved_regs) - memcpy(®s, saved_regs, sizeof(regs)); - else - crash_get_current_regs(®s); - crash_save_this_cpu(®s, cpu); -} - #ifdef CONFIG_SMP -static atomic_t waiting_for_crash_ipi; +static atomic_t enter_on_soft_reset = ATOMIC_INIT(0); void crash_ipi_callback(struct pt_regs *regs) { int cpu = smp_processor_id(); - if (cpu == crashing_cpu) - return; - if (!cpu_online(cpu)) return; - if (ppc_md.kexec_cpu_down) - ppc_md.kexec_cpu_down(1, 1); - local_irq_disable(); + if (!cpu_isset(cpu, cpus_in_crash)) + crash_save_this_cpu(regs, cpu); + cpu_set(cpu, cpus_in_crash); - crash_save_this_cpu(regs, cpu); - atomic_dec(&waiting_for_crash_ipi); + /* + * Entered via soft-reset - could be the kdump + * process is invoked using soft-reset or user activated + * it if some CPU did not respond to an IPI. + * For soft-reset, the secondary CPU can enter this func + * twice. 1 - using IPI, and 2. soft-reset. + * Tell the kexec CPU that entered via soft-reset and ready + * to go down. + */ + if (cpu_isset(cpu, cpus_in_sr)) { + cpu_clear(cpu, cpus_in_sr); + atomic_inc(&enter_on_soft_reset); + } + + /* + * Starting the kdump boot. + * This barrier is needed to make sure that all CPUs are stopped. + * If not, soft-reset will be invoked to bring other CPUs. + */ + while (!cpu_isset(crashing_cpu, cpus_in_crash)) + cpu_relax(); + + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(1, 1); kexec_smp_wait(); /* NOTREACHED */ } -static void crash_kexec_prepare_cpus(void) +/* + * Wait until all CPUs are entered via soft-reset. + */ +static void crash_soft_reset_check(int cpu) +{ + unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */ + + cpu_clear(cpu, cpus_in_sr); + while (atomic_read(&enter_on_soft_reset) != ncpus) + cpu_relax(); +} + + +static void crash_kexec_prepare_cpus(int cpu) { unsigned int msecs; - atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); + unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */ crash_send_ipi(crash_ipi_callback); smp_wmb(); @@ -199,12 +168,13 @@ static void crash_kexec_prepare_cpus(void) /* * FIXME: Until we will have the way to stop other CPUSs reliabally, * the crash CPU will send an IPI and wait for other CPUs to - * respond. If not, proceed the kexec boot even though we failed to - * capture other CPU states. + * respond. + * Delay of at least 10 seconds. */ - msecs = 1000000; - while ((atomic_read(&waiting_for_crash_ipi) > 0) && (--msecs > 0)) { - barrier(); + printk(KERN_EMERG "Sending IPI to other cpus...\n"); + msecs = 10000; + while ((cpus_weight(cpus_in_crash) < ncpus) && (--msecs > 0)) { + cpu_relax(); mdelay(1); } @@ -213,18 +183,71 @@ static void crash_kexec_prepare_cpus(void) /* * FIXME: In case if we do not get all CPUs, one possibility: ask the * user to do soft reset such that we get all. - * IPI handler is already set by the panic cpu initially. Therefore, - * all cpus could invoke this handler from die() and the panic CPU - * will call machine_kexec() directly from this handler to do - * kexec boot. + * Soft-reset will be used until better mechanism is implemented. */ - if (atomic_read(&waiting_for_crash_ipi)) - printk(KERN_ALERT "done waiting: %d cpus not responding\n", - atomic_read(&waiting_for_crash_ipi)); + if (cpus_weight(cpus_in_crash) < ncpus) { + printk(KERN_EMERG "done waiting: %d cpu(s) not responding\n", + ncpus - cpus_weight(cpus_in_crash)); + printk(KERN_EMERG "Activate soft-reset to stop other cpu(s)\n"); + cpus_in_sr = CPU_MASK_NONE; + atomic_set(&enter_on_soft_reset, 0); + while (cpus_weight(cpus_in_crash) < ncpus) + cpu_relax(); + } + /* + * Make sure all CPUs are entered via soft-reset if the kdump is + * invoked using soft-reset. + */ + if (cpu_isset(cpu, cpus_in_sr)) + crash_soft_reset_check(cpu); /* Leave the IPI callback set */ } + +/* + * This function will be called by secondary cpus or by kexec cpu + * if soft-reset is activated to stop some CPUs. + */ +void crash_kexec_secondary(struct pt_regs *regs) +{ + int cpu = smp_processor_id(); + unsigned long flags; + int msecs = 5; + + local_irq_save(flags); + /* Wait 5ms if the kexec CPU is not entered yet. */ + while (crashing_cpu < 0) { + if (--msecs < 0) { + /* + * Either kdump image is not loaded or + * kdump process is not started - Probably xmon + * exited using 'x'(exit and recover) or + * kexec_should_crash() failed for all running tasks. + */ + cpu_clear(cpu, cpus_in_sr); + local_irq_restore(flags); + return; + } + mdelay(1); + cpu_relax(); + } + if (cpu == crashing_cpu) { + /* + * Panic CPU will enter this func only via soft-reset. + * Wait until all secondary CPUs entered and + * then start kexec boot. + */ + crash_soft_reset_check(cpu); + cpu_set(crashing_cpu, cpus_in_crash); + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(1, 0); + machine_kexec(kexec_crash_image); + /* NOTREACHED */ + } + crash_ipi_callback(regs); +} + #else -static void crash_kexec_prepare_cpus(void) +static void crash_kexec_prepare_cpus(int cpu) { /* * move the secondarys to us so that we can copy @@ -235,13 +258,19 @@ static void crash_kexec_prepare_cpus(void) smp_release_cpus(); } +void crash_kexec_secondary(struct pt_regs *regs) +{ + cpus_in_sr = CPU_MASK_NONE; +} #endif void default_machine_crash_shutdown(struct pt_regs *regs) { + unsigned int irq; + /* * This function is only called after the system - * has paniced or is otherwise in a critical state. + * has panicked or is otherwise in a critical state. * The minimum amount of code to allow a kexec'd kernel * to run successfully needs to happen here. * @@ -251,14 +280,24 @@ void default_machine_crash_shutdown(struct pt_regs *regs) */ local_irq_disable(); - if (ppc_md.kexec_cpu_down) - ppc_md.kexec_cpu_down(1, 0); + for_each_irq(irq) { + struct irq_desc *desc = irq_descp(irq); + + if (desc->status & IRQ_INPROGRESS) + desc->handler->end(irq); + + if (!(desc->status & IRQ_DISABLED)) + desc->handler->disable(irq); + } /* * Make a note of crashing cpu. Will be used in machine_kexec * such that another IPI will not be sent. */ crashing_cpu = smp_processor_id(); - crash_kexec_prepare_cpus(); - crash_save_self(regs); + crash_save_this_cpu(regs, crashing_cpu); + crash_kexec_prepare_cpus(crashing_cpu); + cpu_set(crashing_cpu, cpus_in_crash); + if (ppc_md.kexec_cpu_down) + ppc_md.kexec_cpu_down(1, 0); }