[tip:x86/platform] x86/platform/UV: Add basic CPU NMI health check

[tip-bot for travis@xxxxxxx]

Commit-ID:  278c9b099b2fc0cc0a51de95a1dcefcf54ca2183
Gitweb:     http://git.kernel.org/tip/278c9b099b2fc0cc0a51de95a1dcefcf54ca2183
Author:     travis@xxxxxxx <travis@xxxxxxx>
AuthorDate: Wed, 25 Jan 2017 10:35:20 -0600
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Wed, 1 Feb 2017 10:20:59 +0100

x86/platform/UV: Add basic CPU NMI health check

Add a low impact health check triggered by the system NMI command
that essentially checks which CPUs are responding to external NMI's.

Signed-off-by: Mike Travis <travis@xxxxxxx>
Reviewed-by: Russ Anderson <rja@xxxxxxx>
Reviewed-by: Alex Thorlton <athorlton@xxxxxxx>
Acked-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Acked-by: Dimitri Sivanich <sivanich@xxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/20170125163517.756690240@xxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/platform/uv/uv_nmi.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index df7b092..8a4aa5b 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -176,6 +176,7 @@ module_param_named(debug, uv_nmi_debug, int, 0644);
  *  "kdump"	- do crash dump
  *  "kdb"	- enter KDB (default)
  *  "kgdb"	- enter KGDB
+ *  "health"	- check if CPUs respond to NMI
  */
 static char uv_nmi_action[8] = "kdb";
 module_param_string(action, uv_nmi_action, sizeof(uv_nmi_action), 0644);
@@ -571,6 +572,22 @@ static void uv_nmi_sync_exit(int master)
 	}
 }
 
+/* Current "health" check is to check which CPU's are responsive */
+static void uv_nmi_action_health(int cpu, struct pt_regs *regs, int master)
+{
+	if (master) {
+		int in = atomic_read(&uv_nmi_cpus_in_nmi);
+		int out = num_online_cpus() - in;
+
+		pr_alert("UV: NMI CPU health check (non-responding:%d)\n", out);
+		atomic_set(&uv_nmi_slave_continue, SLAVE_EXIT);
+	} else {
+		while (!atomic_read(&uv_nmi_slave_continue))
+			cpu_relax();
+	}
+	uv_nmi_sync_exit(master);
+}
+
 /* Walk through cpu list and dump state of each */
 static void uv_nmi_dump_state(int cpu, struct pt_regs *regs, int master)
 {
@@ -747,7 +764,9 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 	uv_nmi_wait(master);
 
 	/* Process actions other than "kdump": */
-	if (uv_nmi_action_is("ips") || uv_nmi_action_is("dump")) {
+	if (uv_nmi_action_is("health")) {
+		uv_nmi_action_health(cpu, regs, master);
+	} else if (uv_nmi_action_is("ips") || uv_nmi_action_is("dump")) {
 		uv_nmi_dump_state(cpu, regs, master);
 	} else if (uv_nmi_action_is("kdb") || uv_nmi_action_is("kgdb")) {
 		uv_call_kgdb_kdb(cpu, regs, master);