diff options
Diffstat (limited to 'arch/powerpc/platforms/powernv/opal.c')
| -rw-r--r-- | arch/powerpc/platforms/powernv/opal.c | 152 |
1 files changed, 103 insertions, 49 deletions
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index cad6b57ce494..65c79ecf5a4d 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -16,6 +16,7 @@ #include <linux/of.h> #include <linux/of_fdt.h> #include <linux/of_platform.h> +#include <linux/of_address.h> #include <linux/interrupt.h> #include <linux/notifier.h> #include <linux/slab.h> @@ -25,11 +26,17 @@ #include <linux/memblock.h> #include <linux/kthread.h> #include <linux/freezer.h> +#include <linux/printk.h> +#include <linux/kmsg_dump.h> +#include <linux/console.h> +#include <linux/sched/debug.h> #include <asm/machdep.h> #include <asm/opal.h> #include <asm/firmware.h> #include <asm/mce.h> +#include <asm/imc-pmu.h> +#include <asm/bug.h> #include "powernv.h" @@ -162,12 +169,9 @@ int __init early_init_dt_scan_recoverable_ranges(unsigned long node, sizeof(struct mcheck_recoverable_range); /* - * Allocate a buffer to hold the MC recoverable ranges. We would be - * accessing them in real mode, hence it needs to be within - * RMO region. + * Allocate a buffer to hold the MC recoverable ranges. */ - mc_recoverable_range =__va(memblock_alloc_base(size, __alignof__(u64), - ppc64_rma_size)); + mc_recoverable_range =__va(memblock_alloc(size, __alignof__(u64))); memset(mc_recoverable_range, 0, size); for (i = 0; i < mc_recoverable_range_len; i++) { @@ -422,24 +426,88 @@ static int opal_recover_mce(struct pt_regs *regs, /* Fatal machine check */ pr_err("Machine check interrupt is fatal\n"); recovered = 0; - } else if ((evt->severity == MCE_SEV_ERROR_SYNC) && - (user_mode(regs) && !is_global_init(current))) { + } + + if (!recovered && evt->severity == MCE_SEV_ERROR_SYNC) { /* - * For now, kill the task if we have received exception when - * in userspace. + * Try to kill processes if we get a synchronous machine check + * (e.g., one caused by execution of this instruction). This + * will devolve into a panic if we try to kill init or are in + * an interrupt etc. * * TODO: Queue up this address for hwpoisioning later. + * TODO: This is not quite right for d-side machine + * checks ->nip is not necessarily the important + * address. */ - _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); - recovered = 1; + if ((user_mode(regs))) { + _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); + recovered = 1; + } else if (die_will_crash()) { + /* + * die() would kill the kernel, so better to go via + * the platform reboot code that will log the + * machine check. + */ + recovered = 0; + } else { + die("Machine check", regs, SIGBUS); + recovered = 1; + } } + return recovered; } +void pnv_platform_error_reboot(struct pt_regs *regs, const char *msg) +{ + /* + * This is mostly taken from kernel/panic.c, but tries to do + * relatively minimal work. Don't use delay functions (TB may + * be broken), don't crash dump (need to set a firmware log), + * don't run notifiers. We do want to get some information to + * Linux console. + */ + console_verbose(); + bust_spinlocks(1); + pr_emerg("Hardware platform error: %s\n", msg); + if (regs) + show_regs(regs); + smp_send_stop(); + printk_safe_flush_on_panic(); + kmsg_dump(KMSG_DUMP_PANIC); + bust_spinlocks(0); + debug_locks_off(); + console_flush_on_panic(); + + /* + * Don't bother to shut things down because this will + * xstop the system. + */ + if (opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR, msg) + == OPAL_UNSUPPORTED) { + pr_emerg("Reboot type %d not supported for %s\n", + OPAL_REBOOT_PLATFORM_ERROR, msg); + } + + /* + * We reached here. There can be three possibilities: + * 1. We are running on a firmware level that do not support + * opal_cec_reboot2() + * 2. We are running on a firmware level that do not support + * OPAL_REBOOT_PLATFORM_ERROR reboot type. + * 3. We are running on FSP based system that does not need + * opal to trigger checkstop explicitly for error analysis. + * The FSP PRD component would have already got notified + * about this error through other channels. + */ + + ppc_md.restart(NULL); +} + int opal_machine_check(struct pt_regs *regs) { struct machine_check_event evt; - int ret; if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) return 0; @@ -455,43 +523,7 @@ int opal_machine_check(struct pt_regs *regs) if (opal_recover_mce(regs, &evt)) return 1; - /* - * Unrecovered machine check, we are heading to panic path. - * - * We may have hit this MCE in very early stage of kernel - * initialization even before opal-prd has started running. If - * this is the case then this MCE error may go un-noticed or - * un-analyzed if we go down panic path. We need to inform - * BMC/OCC about this error so that they can collect relevant - * data for error analysis before rebooting. - * Use opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR) to do so. - * This function may not return on BMC based system. - */ - ret = opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR, - "Unrecoverable Machine Check exception"); - if (ret == OPAL_UNSUPPORTED) { - pr_emerg("Reboot type %d not supported\n", - OPAL_REBOOT_PLATFORM_ERROR); - } - - /* - * We reached here. There can be three possibilities: - * 1. We are running on a firmware level that do not support - * opal_cec_reboot2() - * 2. We are running on a firmware level that do not support - * OPAL_REBOOT_PLATFORM_ERROR reboot type. - * 3. We are running on FSP based system that does not need opal - * to trigger checkstop explicitly for error analysis. The FSP - * PRD component would have already got notified about this - * error through other channels. - * - * If hardware marked this as an unrecoverable MCE, we are - * going to panic anyway. Even if it didn't, it's not safe to - * continue at this point, so we should explicitly panic. - */ - - panic("PowerNV Unrecovered Machine Check"); - return 0; + pnv_platform_error_reboot(regs, "Unrecoverable Machine Check exception"); } /* Early hmi handler called in real mode. */ @@ -720,6 +752,15 @@ static void opal_pdev_init(const char *compatible) of_platform_device_create(np, NULL, NULL); } +static void __init opal_imc_init_dev(void) +{ + struct device_node *np; + + np = of_find_compatible_node(NULL, NULL, IMC_DTB_COMPAT); + if (np) + of_platform_device_create(np, NULL, NULL); +} + static int kopald(void *unused) { unsigned long timeout = msecs_to_jiffies(opal_heartbeat) + 1; @@ -793,6 +834,9 @@ static int __init opal_init(void) /* Setup a heatbeat thread if requested by OPAL */ opal_init_heartbeat(); + /* Detect In-Memory Collection counters and create devices*/ + opal_imc_init_dev(); + /* Create leds platform devices */ leds = of_find_node_by_path("/ibm,opal/leds"); if (leds) { @@ -836,6 +880,15 @@ static int __init opal_init(void) /* Initialise OPAL kmsg dumper for flushing console on panic */ opal_kmsg_init(); + /* Initialise OPAL powercap interface */ + opal_powercap_init(); + + /* Initialise OPAL Power-Shifting-Ratio interface */ + opal_psr_init(); + + /* Initialise OPAL sensor groups */ + opal_sensor_groups_init(); + return 0; } machine_subsys_initcall(powernv, opal_init); @@ -952,6 +1005,7 @@ int opal_error_code(int rc) case OPAL_UNSUPPORTED: return -EIO; case OPAL_HARDWARE: return -EIO; case OPAL_INTERNAL_ERROR: return -EIO; + case OPAL_TIMEOUT: return -ETIMEDOUT; default: pr_err("%s: unexpected OPAL error %d\n", __func__, rc); return -EIO; |