[V6.1 PATCH 5/6] x86/nmi: Fix to save registers for crash dump on external NMI broadcast

[Hidehiro Kawai]

Now, multiple CPUs can receive external NMI simultaneously by
specifying "apic_extnmi=all" as an boot option.  When we take a
crash dump by using external NMI with this option, we fail to save
register values into the crash dump.  This happens as follows:

  CPU 0                              CPU 1
  ================================   =============================
  receive an external NMI
  default_do_nmi()                   receive an external NMI
    spin_lock(&nmi_reason_lock)      default_do_nmi()
    io_check_error()                   spin_lock(&nmi_reason_lock)
      panic()                            busy loop
      ...
        kdump_nmi_shootdown_cpus()
          issue NMI IPI -----------> blocked until IRET
                                         busy loop...

  Here, since CPU 1 is in NMI context, additional NMI from CPU 0
  is blocked until CPU 1 executes IRET.  However, CPU 1 never
  executes IRET, so the NMI is not handled and the callback function
  to save registers is never called.

To solve this issue, we check if the IPI for crash dumping was
issued while waiting for nmi_reason_lock to be released, and if so,
call its callback function directly.  If the IPI is not issued (e.g.
kdump is disabled), the actual behavior doesn't change.

V6.1:
- Reintroduce the UP version of run_crash_ipi_callback to fix build
  error for CONFIG_SMP=n and CONFIG_DEBUG_SPINLOCK=y case

V6:
- Separated from the former patch `panic/x86: Allow cpus to save
  registers even if they are looping in NMI context'
- Fix comments
- Remove unneeded UP version of poll_crash_ipi_and_calback
- Rename poll_crash_ipi_and_callback to run_crash_ipi_callback

Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@xxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
---
 arch/x86/include/asm/reboot.h |    1 +
 arch/x86/kernel/nmi.c         |   11 ++++++++++-
 arch/x86/kernel/reboot.c      |   22 +++++++++++++++++-----
 3 files changed, 28 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index a82c4f1..2cb1cc2 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -25,5 +25,6 @@ void __noreturn machine_real_restart(unsigned int type);
 
 typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
 void nmi_shootdown_cpus(nmi_shootdown_cb callback);
+void run_crash_ipi_callback(struct pt_regs *regs);
 
 #endif /* _ASM_X86_REBOOT_H */
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 5e00de7..cbfa0b5 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -29,6 +29,7 @@
 #include <asm/mach_traps.h>
 #include <asm/nmi.h>
 #include <asm/x86_init.h>
+#include <asm/reboot.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
@@ -357,7 +358,15 @@ static void default_do_nmi(struct pt_regs *regs)
 	}
 
 	/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
-	raw_spin_lock(&nmi_reason_lock);
+	/*
+	 * Another CPU may be processing panic routines while holding
+	 * nmi_reason_lock.  Check if the CPU issued the IPI for crash
+	 * dumping, and if so, call its callback directly.  If there is
+	 * no CPU preparing crash dump, we simply loop here without doing
+	 * special things.
+	 */
+	while (!raw_spin_trylock(&nmi_reason_lock))
+		run_crash_ipi_callback(regs);
 	reason = x86_platform.get_nmi_reason();
 
 	if (reason & NMI_REASON_MASK) {
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 1da1302..8a184e3 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -793,17 +793,25 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 	/* Leave the nmi callback set */
 }
 
+/*
+ * Wait for the crash dumping IPI to be issued, and then call its callback
+ * directly.  This function is used when we have already been in NMI handler.
+ */
+void run_crash_ipi_callback(struct pt_regs *regs)
+{
+	if (crash_ipi_issued)
+		crash_nmi_callback(0, regs); /* Don't return */
+}
+
 /* Override the weak function in kernel/panic.c */
 void nmi_panic_self_stop(struct pt_regs *regs)
 {
 	while (1) {
 		/*
-		 * Wait for the crash dumping IPI to be issued, and then
-		 * call its callback directly.
+		 * If there is no CPU preparing crash dump, we simply loop
+		 * here without doing special things.
 		 */
-		if (READ_ONCE(crash_ipi_issued))
-			crash_nmi_callback(0, regs); /* Don't return */
-
+		run_crash_ipi_callback(regs);
 		cpu_relax();
 	}
 }
@@ -813,4 +821,8 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 {
 	/* No other CPUs to shoot down */
 }
+
+void run_crash_ipi_callback(struct pt_regs *regs)
+{
+}
 #endif


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/