[PATCH] kdump: x86_64 kexec on panic

\r)

From: Vivek Goyal <vgoyal@in.ibm.com>

- Implementing the machine_crash_shutdown for x86_64 which will be called by
  crash_kexec (called in case of a panic, sysrq etc.).  Here we do things
  similar to i386.  Disable the interrupts, shootdown the cpus and shutdown
  LAPIC and IOAPIC.

Changes in this version:

- As the Eric's APIC initialization patches are reverted back, reintroducing
  LAPIC and IOAPIC shutdown.

- Added some comments on CPU hotplug, modified code as suggested by Andi
  kleen.

Signed-off-by: Murali M Chakravarthy <muralim@in.ibm.com>
Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/arch/x86_64/kernel/crash.c b/arch/x86_64/kernel/crash.c
index efe450760bbcbca25f38b4642843a14cd2ef99af..abc601f36b6eeca8fa16831f1ad238a45403f030 100644 (file)
--- a/arch/x86_64/kernel/crash.c
+++ b/arch/x86_64/kernel/crash.c
@@ -13,15 +13,85 @@
 #include <linux/smp.h>
 #include <linux/reboot.h>
 #include <linux/kexec.h>
+#include <linux/delay.h>
 
 #include <asm/processor.h>
 #include <asm/hardirq.h>
 #include <asm/nmi.h>
 #include <asm/hw_irq.h>
+#include <asm/mach_apic.h>
+
+/* This keeps a track of which one is crashing cpu. */
+static int crashing_cpu;
+
+#ifdef CONFIG_SMP
+static atomic_t waiting_for_crash_ipi;
+
+static int crash_nmi_callback(struct pt_regs *regs, int cpu)
+{
+       /*
+        * Don't do anything if this handler is invoked on crashing cpu.
+        * Otherwise, system will completely hang. Crashing cpu can get
+        * an NMI if system was initially booted with nmi_watchdog parameter.
+        */
+       if (cpu == crashing_cpu)
+               return 1;
+       local_irq_disable();
+
+       disable_local_APIC();
+       atomic_dec(&waiting_for_crash_ipi);
+       /* Assume hlt works */
+       for(;;)
+               asm("hlt");
+
+       return 1;
+}
+
+static void smp_send_nmi_allbutself(void)
+{
+       send_IPI_allbutself(APIC_DM_NMI);
+}
+
+/*
+ * This code is a best effort heuristic to get the
+ * other cpus to stop executing. So races with
+ * cpu hotplug shouldn't matter.
+ */
+
+static void nmi_shootdown_cpus(void)
+{
+       unsigned long msecs;
+
+       atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+       set_nmi_callback(crash_nmi_callback);
+
+       /*
+        * Ensure the new callback function is set before sending
+        * out the NMI
+        */
+       wmb();
+
+       smp_send_nmi_allbutself();
+
+       msecs = 1000; /* Wait at most a second for the other cpus to stop */
+       while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
+               mdelay(1);
+               msecs--;
+       }
+       /* Leave the nmi callback set */
+       disable_local_APIC();
+}
+#else
+static void nmi_shootdown_cpus(void)
+{
+       /* There are no cpus to shootdown */
+}
+#endif
 
 void machine_crash_shutdown(struct pt_regs *regs)
 {
-       /* This function is only called after the system
+       /*
+        * This function is only called after the system
         * has paniced or is otherwise in a critical state.
         * The minimum amount of code to allow a kexec'd kernel
         * to run successfully needs to happen here.
@@ -29,4 +99,18 @@ void machine_crash_shutdown(struct pt_regs *regs)
         * In practice this means shooting down the other cpus in
         * an SMP system.
         */
+       /* The kernel is broken so disable interrupts */
+       local_irq_disable();
+
+       /* Make a note of crashing cpu. Will be used in NMI callback.*/
+       crashing_cpu = smp_processor_id();
+       nmi_shootdown_cpus();
+
+       if(cpu_has_apic)
+                disable_local_APIC();
+
+#if defined(CONFIG_X86_IO_APIC)
+       disable_IO_APIC();
+#endif
+
 }