[PATCH 3.16 108/306] x86/panic: replace smp_send_stop() with kdump friendly version in panic path

[Ben Hutchings]

3.16.40-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Hidehiro Kawai <hidehiro.kawai.ez@xxxxxxxxxxx>

commit 0ee59413c967c35a6dd2dbdab605b4cd42025ee5 upstream.

Daniel Walker reported problems which happens when
crash_kexec_post_notifiers kernel option is enabled
(https://lkml.org/lkml/2015/6/24/44).

In that case, smp_send_stop() is called before entering kdump routines
which assume other CPUs are still online.  As the result, for x86, kdump
routines fail to save other CPUs' registers and disable virtualization
extensions.

To fix this problem, call a new kdump friendly function,
crash_smp_send_stop(), instead of the smp_send_stop() when
crash_kexec_post_notifiers is enabled.  crash_smp_send_stop() is a weak
function, and it just call smp_send_stop().  Architecture codes should
override it so that kdump can work appropriately.  This patch only
provides x86-specific version.

For Xen's PV kernel, just keep the current behavior.

NOTES:

- Right solution would be to place crash_smp_send_stop() before
  __crash_kexec() invocation in all cases and remove smp_send_stop(), but
  we can't do that until all architectures implement own
  crash_smp_send_stop()

- crash_smp_send_stop()-like work is still needed by
  machine_crash_shutdown() because crash_kexec() can be called without
  entering panic()

Fixes: f06e5153f4ae (kernel/panic.c: add "crash_kexec_post_notifiers" option)
Link: http://lkml.kernel.org/r/20160810080948.11028.15344.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@xxxxxxxxxxx>
Reported-by: Daniel Walker <dwalker@xxxxxxxxxx>
Cc: Dave Young <dyoung@xxxxxxxxxx>
Cc: Baoquan He <bhe@xxxxxxxxxx>
Cc: Vivek Goyal <vgoyal@xxxxxxxxxx>
Cc: Eric Biederman <ebiederm@xxxxxxxxxxxx>
Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Cc: Daniel Walker <dwalker@xxxxxxxxxx>
Cc: Xunlei Pang <xpang@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxx>
Cc: David Vrabel <david.vrabel@xxxxxxxxxx>
Cc: Toshi Kani <toshi.kani@xxxxxxx>
Cc: Ralf Baechle <ralf@xxxxxxxxxxxxxx>
Cc: David Daney <david.daney@xxxxxxxxxx>
Cc: Aaro Koskinen <aaro.koskinen@xxxxxx>
Cc: "Steven J. Hill" <steven.hill@xxxxxxxxxx>
Cc: Corey Minyard <cminyard@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
 arch/x86/include/asm/kexec.h |  1 +
 arch/x86/include/asm/smp.h   |  1 +
 arch/x86/kernel/crash.c      | 22 ++++++++++++++++++---
 arch/x86/kernel/smp.c        |  5 +++++
 kernel/panic.c               | 47 +++++++++++++++++++++++++++++++++++++-------
 5 files changed, 66 insertions(+), 10 deletions(-)

--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -165,6 +165,7 @@ struct kimage_arch {
 
 typedef void crash_vmclear_fn(void);
 extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
+extern void kdump_nmi_shootdown_cpus(void);
 
 #endif /* __ASSEMBLY__ */
 
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -69,6 +69,7 @@ struct smp_ops {
 	void (*smp_cpus_done)(unsigned max_cpus);
 
 	void (*stop_other_cpus)(int wait);
+	void (*crash_stop_other_cpus)(void);
 	void (*smp_send_reschedule)(int cpu);
 
 	int (*cpu_up)(unsigned cpu, struct task_struct *tidle);
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -82,7 +82,7 @@ static void kdump_nmi_callback(int cpu,
 	disable_local_APIC();
 }
 
-static void kdump_nmi_shootdown_cpus(void)
+void kdump_nmi_shootdown_cpus(void)
 {
 	in_crash_kexec = 1;
 	nmi_shootdown_cpus(kdump_nmi_callback);
@@ -90,8 +90,24 @@ static void kdump_nmi_shootdown_cpus(voi
 	disable_local_APIC();
 }
 
+/* Override the weak function in kernel/panic.c */
+void crash_smp_send_stop(void)
+{
+	static int cpus_stopped;
+
+	if (cpus_stopped)
+		return;
+
+	if (smp_ops.crash_stop_other_cpus)
+		smp_ops.crash_stop_other_cpus();
+	else
+		smp_send_stop();
+
+	cpus_stopped = 1;
+}
+
 #else
-static void kdump_nmi_shootdown_cpus(void)
+void crash_smp_send_stop(void)
 {
 	/* There are no cpus to shootdown */
 }
@@ -110,7 +126,7 @@ void native_machine_crash_shutdown(struc
 	/* The kernel is broken so disable interrupts */
 	local_irq_disable();
 
-	kdump_nmi_shootdown_cpus();
+	crash_smp_send_stop();
 
 	/*
 	 * VMCLEAR VMCSs loaded on this cpu if needed.
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -31,6 +31,8 @@
 #include <asm/apic.h>
 #include <asm/nmi.h>
 #include <asm/trace/irq_vectors.h>
+#include <asm/kexec.h>
+
 /*
  *	Some notes on x86 processor bugs affecting SMP operation:
  *
@@ -347,6 +349,9 @@ struct smp_ops smp_ops = {
 	.smp_cpus_done		= native_smp_cpus_done,
 
 	.stop_other_cpus	= native_stop_other_cpus,
+#if defined(CONFIG_KEXEC_CORE)
+	.crash_stop_other_cpus	= kdump_nmi_shootdown_cpus,
+#endif
 	.smp_send_reschedule	= native_smp_send_reschedule,
 
 	.cpu_up			= native_cpu_up,
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -60,6 +60,32 @@ void __weak panic_smp_self_stop(void)
 		cpu_relax();
 }
 
+/*
+ * Stop other CPUs in panic.  Architecture dependent code may override this
+ * with more suitable version.  For example, if the architecture supports
+ * crash dump, it should save registers of each stopped CPU and disable
+ * per-CPU features such as virtualization extensions.
+ */
+void __weak crash_smp_send_stop(void)
+{
+	static int cpus_stopped;
+
+	/*
+	 * This function can be called twice in panic path, but obviously
+	 * we execute this only once.
+	 */
+	if (cpus_stopped)
+		return;
+
+	/*
+	 * Note smp_send_stop is the usual smp shutdown function, which
+	 * unfortunately means it may not be hardened to work in a panic
+	 * situation.
+	 */
+	smp_send_stop();
+	cpus_stopped = 1;
+}
+
 /**
  *	panic - halt the system
  *	@fmt: The text string to print
@@ -117,15 +143,23 @@ void panic(const char *fmt, ...)
 	 * If we want to run this after calling panic_notifiers, pass
 	 * the "crash_kexec_post_notifiers" option to the kernel.
 	 */
-	if (!crash_kexec_post_notifiers)
+	if (!crash_kexec_post_notifiers) {
 		crash_kexec(NULL);
 
-	/*
-	 * Note smp_send_stop is the usual smp shutdown function, which
-	 * unfortunately means it may not be hardened to work in a panic
-	 * situation.
-	 */
-	smp_send_stop();
+		/*
+		 * Note smp_send_stop is the usual smp shutdown function, which
+		 * unfortunately means it may not be hardened to work in a
+		 * panic situation.
+		 */
+		smp_send_stop();
+	} else {
+		/*
+		 * If we want to do crash dump after notifier calls and
+		 * kmsg_dump, we will need architecture dependent extra
+		 * works in addition to stopping other CPUs.
+		 */
+		crash_smp_send_stop();
+	}
 
 	/*
 	 * Run any panic handlers, including those that might need to