From 12ba6c990fab50fe568f3ad8715e81e356552428 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Mon, 23 Sep 2013 16:25:03 -0500 Subject: [PATCH] x86/UV: Add kdump to UV NMI handler If a system has hung and it no longer responds to external events, this patch adds the capability of doing a standard kdump and system reboot then triggered by the system NMI command. It is enabled when the nmi action is changed to "kdump" and the kernel is built with CONFIG_KEXEC enabled. Signed-off-by: Mike Travis Reviewed-by: Dimitri Sivanich Reviewed-by: Hedi Berriche Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Jason Wessel Link: http://lkml.kernel.org/r/20130923212500.660567460@asylum.americas.sgi.com Signed-off-by: Ingo Molnar --- arch/x86/platform/uv/uv_nmi.c | 41 +++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 4efcde1b9d54..2579fbd6b95c 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -21,6 +21,7 @@ #include #include +#include #include #include #include @@ -70,6 +71,7 @@ static atomic_t uv_in_nmi; static atomic_t uv_nmi_cpu = ATOMIC_INIT(-1); static atomic_t uv_nmi_cpus_in_nmi = ATOMIC_INIT(-1); static atomic_t uv_nmi_slave_continue; +static atomic_t uv_nmi_kexec_failed; static cpumask_var_t uv_nmi_cpu_mask; /* Values for uv_nmi_slave_continue */ @@ -143,6 +145,7 @@ module_param_named(retry_count, uv_nmi_retry_count, int, 0644); * Valid NMI Actions: * "dump" - dump process stack for each cpu * "ips" - dump IP info for each cpu + * "kdump" - do crash dump */ static char uv_nmi_action[8] = "dump"; module_param_string(action, uv_nmi_action, sizeof(uv_nmi_action), 0644); @@ -496,6 +499,40 @@ static void uv_nmi_touch_watchdogs(void) touch_nmi_watchdog(); } +#if defined(CONFIG_KEXEC) +static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) +{ + /* Call crash to dump system state */ + if (master) { + pr_emerg("UV: NMI executing crash_kexec on CPU%d\n", cpu); + crash_kexec(regs); + + pr_emerg("UV: crash_kexec unexpectedly returned, "); + if (!kexec_crash_image) { + pr_cont("crash kernel not loaded\n"); + atomic_set(&uv_nmi_kexec_failed, 1); + uv_nmi_sync_exit(1); + return; + } + pr_cont("kexec busy, stalling cpus while waiting\n"); + } + + /* If crash exec fails the slaves should return, otherwise stall */ + while (atomic_read(&uv_nmi_kexec_failed) == 0) + mdelay(10); + + /* Crash kernel most likely not loaded, return in an orderly fashion */ + uv_nmi_sync_exit(0); +} + +#else /* !CONFIG_KEXEC */ +static inline void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) +{ + if (master) + pr_err("UV: NMI kdump: KEXEC not supported in this kernel\n"); +} +#endif /* !CONFIG_KEXEC */ + /* * UV NMI handler */ @@ -517,6 +554,10 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) /* Indicate we are the first CPU into the NMI handler */ master = (atomic_read(&uv_nmi_cpu) == cpu); + /* If NMI action is "kdump", then attempt to do it */ + if (uv_nmi_action_is("kdump")) + uv_nmi_kdump(cpu, master, regs); + /* Pause as all cpus enter the NMI handler */ uv_nmi_wait(master); -- 2.34.1