diff options
Diffstat (limited to 'arch/powerpc/platforms/powernv/setup.c')
| -rw-r--r-- | arch/powerpc/platforms/powernv/setup.c | 124 |
1 files changed, 118 insertions, 6 deletions
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index e239dcfa224..d9b88fa7c5a 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -23,8 +23,11 @@ #include <linux/irq.h> #include <linux/seq_file.h> #include <linux/of.h> +#include <linux/of_fdt.h> #include <linux/interrupt.h> #include <linux/bug.h> +#include <linux/pci.h> +#include <linux/cpufreq.h> #include <asm/machdep.h> #include <asm/firmware.h> @@ -32,11 +35,14 @@ #include <asm/rtas.h> #include <asm/opal.h> #include <asm/kexec.h> +#include <asm/smp.h> #include "powernv.h" static void __init pnv_setup_arch(void) { + set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); + /* Initialize SMP */ pnv_smp_init(); @@ -96,11 +102,32 @@ static void pnv_show_cpuinfo(struct seq_file *m) of_node_put(root); } +static void pnv_prepare_going_down(void) +{ + /* + * Disable all notifiers from OPAL, we can't + * service interrupts anymore anyway + */ + opal_notifier_disable(); + + /* Soft disable interrupts */ + local_irq_disable(); + + /* + * Return secondary CPUs to firwmare if a flash update + * is pending otherwise we will get all sort of error + * messages about CPU being stuck etc.. This will also + * have the side effect of hard disabling interrupts so + * past this point, the kernel is effectively dead. + */ + opal_flash_term_callback(); +} + static void __noreturn pnv_restart(char *cmd) { long rc = OPAL_BUSY; - opal_notifier_disable(); + pnv_prepare_going_down(); while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_cec_reboot(); @@ -117,7 +144,7 @@ static void __noreturn pnv_power_off(void) { long rc = OPAL_BUSY; - opal_notifier_disable(); + pnv_prepare_going_down(); while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_cec_power_down(0); @@ -139,34 +166,94 @@ static void pnv_progress(char *s, unsigned short hex) { } +static int pnv_dma_set_mask(struct device *dev, u64 dma_mask) +{ + if (dev_is_pci(dev)) + return pnv_pci_dma_set_mask(to_pci_dev(dev), dma_mask); + return __dma_set_mask(dev, dma_mask); +} + static void pnv_shutdown(void) { /* Let the PCI code clear up IODA tables */ pnv_pci_shutdown(); - /* And unregister all OPAL interrupts so they don't fire - * up while we kexec + /* + * Stop OPAL activity: Unregister all OPAL interrupts so they + * don't fire up while we kexec and make sure all potentially + * DMA'ing ops are complete (such as dump retrieval). */ opal_shutdown(); } #ifdef CONFIG_KEXEC +static void pnv_kexec_wait_secondaries_down(void) +{ + int my_cpu, i, notified = -1; + + my_cpu = get_cpu(); + + for_each_online_cpu(i) { + uint8_t status; + int64_t rc; + + if (i == my_cpu) + continue; + + for (;;) { + rc = opal_query_cpu_status(get_hard_smp_processor_id(i), + &status); + if (rc != OPAL_SUCCESS || status != OPAL_THREAD_STARTED) + break; + barrier(); + if (i != notified) { + printk(KERN_INFO "kexec: waiting for cpu %d " + "(physical %d) to enter OPAL\n", + i, paca[i].hw_cpu_id); + notified = i; + } + } + } +} + static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) { xics_kexec_teardown_cpu(secondary); - /* Return secondary CPUs to firmware on OPAL v3 */ - if (firmware_has_feature(FW_FEATURE_OPALv3) && secondary) { + /* On OPAL v3, we return all CPUs to firmware */ + + if (!firmware_has_feature(FW_FEATURE_OPALv3)) + return; + + if (secondary) { + /* Return secondary CPUs to firmware on OPAL v3 */ mb(); get_paca()->kexec_state = KEXEC_STATE_REAL_MODE; mb(); /* Return the CPU to OPAL */ opal_return_cpu(); + } else if (crash_shutdown) { + /* + * On crash, we don't wait for secondaries to go + * down as they might be unreachable or hung, so + * instead we just wait a bit and move on. + */ + mdelay(1); + } else { + /* Primary waits for the secondaries to have reached OPAL */ + pnv_kexec_wait_secondaries_down(); } } #endif /* CONFIG_KEXEC */ +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +static unsigned long pnv_memory_block_size(void) +{ + return 256UL * 1024 * 1024; +} +#endif + static void __init pnv_setup_machdep_opal(void) { ppc_md.get_boot_time = opal_get_boot_time; @@ -176,6 +263,7 @@ static void __init pnv_setup_machdep_opal(void) ppc_md.power_off = pnv_power_off; ppc_md.halt = pnv_halt; ppc_md.machine_check_exception = opal_machine_check; + ppc_md.mce_check_early_recovery = opal_mce_check_early_recovery; } #ifdef CONFIG_PPC_POWERNV_RTAS @@ -213,6 +301,25 @@ static int __init pnv_probe(void) return 1; } +/* + * Returns the cpu frequency for 'cpu' in Hz. This is used by + * /proc/cpuinfo + */ +unsigned long pnv_get_proc_freq(unsigned int cpu) +{ + unsigned long ret_freq; + + ret_freq = cpufreq_quick_get(cpu) * 1000ul; + + /* + * If the backend cpufreq driver does not exist, + * then fallback to old way of reporting the clockrate. + */ + if (!ret_freq) + ret_freq = ppc_proc_freq; + return ret_freq; +} + define_machine(powernv) { .name = "PowerNV", .probe = pnv_probe, @@ -220,11 +327,16 @@ define_machine(powernv) { .setup_arch = pnv_setup_arch, .init_IRQ = pnv_init_IRQ, .show_cpuinfo = pnv_show_cpuinfo, + .get_proc_freq = pnv_get_proc_freq, .progress = pnv_progress, .machine_shutdown = pnv_shutdown, .power_save = power7_idle, .calibrate_decr = generic_calibrate_decr, + .dma_set_mask = pnv_dma_set_mask, #ifdef CONFIG_KEXEC .kexec_cpu_down = pnv_kexec_cpu_down, #endif +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE + .memory_block_size = pnv_memory_block_size, +#endif }; |