[PATCH] x86/platform/uv: Add more to secondary cpu kdump info

* [PATCH] x86/platform/uv: Add more to secondary cpu kdump info
@ 2021-03-11 15:10 Mike Travis
  2021-04-12 17:48 ` [tip: x86/platform] x86/platform/uv: Add more to secondary CPU " tip-bot2 for Georges Aureau
  2021-04-16 10:56 ` tip-bot2 for Georges Aureau
  0 siblings, 2 replies; 3+ messages in thread
From: Mike Travis @ 2021-03-11 15:10 UTC (permalink / raw)
  To: Borislav_Petkov_, Thomas_Gleixner_, Ingo_Molnar_, Steve_Wahl_, x86
  Cc: Georges Aureau, Mike Travis, Dimitri_Sivanich_, Russ_Anderson_,
	Darren_Hart_, Andy_Shevchenko_, H._Peter_Anvin_,
	platform-driver-x86, linux-kernel

From: Georges Aureau <georges.aureau@hpe.com>

Add call to run_crash_ipi_callback() to gather more info of what the
secondary cpus were doing to help with failure analysis.

Excerpt from Georges:
'It is only changing where crash secondaries will be stalling after having
taken care of properly laying down "crash note regs". Please note that
"crash note regs" are a key piece of data used by crash dump debuggers
to provide a reliable backtrace of running processors.'

Secondary change pursuant to a5f526ec:
	change master/slave to main/secondary

Signed-off-by: Georges Aureau <georges.aureau@hpe.com>
Signed-off-by: Mike Travis <mike.travis@hpe.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
---
 arch/x86/platform/uv/uv_nmi.c | 39 +++++++++++++++++++++--------------
 1 file changed, 24 insertions(+), 15 deletions(-)

diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index eafc530c8767..f83810f7bcc2 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -24,6 +24,7 @@
 #include <asm/kdebug.h>
 #include <asm/local64.h>
 #include <asm/nmi.h>
+#include <asm/reboot.h>
 #include <asm/traps.h>
 #include <asm/uv/uv.h>
 #include <asm/uv/uv_hub.h>
@@ -834,34 +835,42 @@ static void uv_nmi_touch_watchdogs(void)
 	touch_nmi_watchdog();
 }
 
-static atomic_t uv_nmi_kexec_failed;
-
 #if defined(CONFIG_KEXEC_CORE)
-static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs)
+static atomic_t uv_nmi_kexec_failed;
+static void uv_nmi_kdump(int cpu, int main, struct pt_regs *regs)
 {
+	/* Check if kdump kernel loaded for both main and secondary CPUs */
+	if (!kexec_crash_image) {
+		if (main)
+			pr_err("UV: NMI error: kdump kernel not loaded\n");
+		return;
+	}
+
 	/* Call crash to dump system state */
-	if (master) {
+	if (main) {
 		pr_emerg("UV: NMI executing crash_kexec on CPU%d\n", cpu);
 		crash_kexec(regs);
 
-		pr_emerg("UV: crash_kexec unexpectedly returned, ");
+		pr_emerg("UV: crash_kexec unexpectedly returned\n");
 		atomic_set(&uv_nmi_kexec_failed, 1);
-		if (!kexec_crash_image) {
-			pr_cont("crash kernel not loaded\n");
-			return;
+
+	} else { /* secondary */
+
+		/* If kdump kernel fails, secondaries will exit this loop */
+		while (atomic_read(&uv_nmi_kexec_failed) == 0) {
+
+			/* Once shootdown cpus starts, they do not return */
+			run_crash_ipi_callback(regs);
+
+			mdelay(10);
 		}
-		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);
 }
 
 #else /* !CONFIG_KEXEC_CORE */
-static inline void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs)
+static inline void uv_nmi_kdump(int cpu, int main, struct pt_regs *regs)
 {
-	if (master)
+	if (main)
 		pr_err("UV: NMI kdump: KEXEC not supported in this kernel\n");
 	atomic_set(&uv_nmi_kexec_failed, 1);
 }
-- 
2.21.0


^ permalink raw reply related	[flat|nested] 3+ messages in thread