nmi: provide the option to issue an NMI back trace to every cpu but current

Sometimes it is preferred not to use the trigger_all_cpu_backtrace()
routine when one wants to avoid capturing a back trace for current.  For
instance if one was previously captured recently.

This patch provides a new routine namely
trigger_allbutself_cpu_backtrace() which offers the flexibility to issue
an NMI to every cpu but current and capture a back trace accordingly.

Patch x86 and sparc to support new routine.

[dzickus@redhat.com: add stub in #else clause]
[dzickus@redhat.com: don't print message in single processor case, wrap with get/put_cpu based on Oleg's suggestion]
[sfr@canb.auug.org.au: undo C99ism]
Signed-off-by: Aaron Tomlin <atomlin@redhat.com>
Signed-off-by: Don Zickus <dzickus@redhat.com>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: Mateusz Guzik <mguzik@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h
index 375cffc..91d2193 100644 (file)
--- a/arch/sparc/include/asm/irq_64.h
+++ b/arch/sparc/include/asm/irq_64.h
@@ -89,7 +89,7 @@ static inline unsigned long get_softint(void)
        return retval;
 }
 
-void arch_trigger_all_cpu_backtrace(void);
+void arch_trigger_all_cpu_backtrace(bool);
 #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
 
 extern void *hardirq_stack[NR_CPUS];

diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index b2988f2..027e099 100644 (file)
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -239,7 +239,7 @@ static void __global_reg_poll(struct global_reg_snapshot *gp)
        }
 }
 
-void arch_trigger_all_cpu_backtrace(void)
+void arch_trigger_all_cpu_backtrace(bool include_self)
 {
        struct thread_info *tp = current_thread_info();
        struct pt_regs *regs = get_irq_regs();
@@ -251,16 +251,22 @@ void arch_trigger_all_cpu_backtrace(void)
 
        spin_lock_irqsave(&global_cpu_snapshot_lock, flags);
 
-       memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
-
        this_cpu = raw_smp_processor_id();
 
-       __global_reg_self(tp, regs, this_cpu);
+       memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
+
+       if (include_self)
+               __global_reg_self(tp, regs, this_cpu);
 
        smp_fetch_global_regs();
 
        for_each_online_cpu(cpu) {
-               struct global_reg_snapshot *gp = &global_cpu_snapshot[cpu].reg;
+               struct global_reg_snapshot *gp;
+
+               if (!include_self && cpu == this_cpu)
+                       continue;
+
+               gp = &global_cpu_snapshot[cpu].reg;
 
                __global_reg_poll(gp);
 
@@ -292,7 +298,7 @@ void arch_trigger_all_cpu_backtrace(void)
 
 static void sysrq_handle_globreg(int key)
 {
-       arch_trigger_all_cpu_backtrace();
+       arch_trigger_all_cpu_backtrace(true);
 }
 
 static struct sysrq_key_op sparc_globalreg_op = {

diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index cb6cfcd..a80cbb8 100644 (file)
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -43,7 +43,7 @@ extern int vector_used_by_percpu_irq(unsigned int vector);
 extern void init_ISA_irqs(void);
 
 #ifdef CONFIG_X86_LOCAL_APIC
-void arch_trigger_all_cpu_backtrace(void);
+void arch_trigger_all_cpu_backtrace(bool);
 #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
 #endif
 

diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index c3fcb5d..6a1e71b 100644 (file)
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -33,31 +33,41 @@ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
 /* "in progress" flag of arch_trigger_all_cpu_backtrace */
 static unsigned long backtrace_flag;
 
-void arch_trigger_all_cpu_backtrace(void)
+void arch_trigger_all_cpu_backtrace(bool include_self)
 {
        int i;
+       int cpu = get_cpu();
 
-       if (test_and_set_bit(0, &backtrace_flag))
+       if (test_and_set_bit(0, &backtrace_flag)) {
                /*
                 * If there is already a trigger_all_cpu_backtrace() in progress
                 * (backtrace_flag == 1), don't output double cpu dump infos.
                 */
+               put_cpu();
                return;
+       }
 
        cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
+       if (!include_self)
+               cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
 
-       printk(KERN_INFO "sending NMI to all CPUs:\n");
-       apic->send_IPI_all(NMI_VECTOR);
+       if (!cpumask_empty(to_cpumask(backtrace_mask))) {
+               pr_info("sending NMI to %s CPUs:\n",
+                       (include_self ? "all" : "other"));
+               apic->send_IPI_mask(to_cpumask(backtrace_mask), NMI_VECTOR);
+       }
 
        /* Wait for up to 10 seconds for all CPUs to do the backtrace */
        for (i = 0; i < 10 * 1000; i++) {
                if (cpumask_empty(to_cpumask(backtrace_mask)))
                        break;
                mdelay(1);
+               touch_softlockup_watchdog();
        }
 
        clear_bit(0, &backtrace_flag);
        smp_mb__after_atomic();
+       put_cpu();
 }
 
 static int

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 6a45fb5..a17ab63 100644 (file)
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -32,15 +32,24 @@ static inline void touch_nmi_watchdog(void)
 #ifdef arch_trigger_all_cpu_backtrace
 static inline bool trigger_all_cpu_backtrace(void)
 {
-       arch_trigger_all_cpu_backtrace();
+       arch_trigger_all_cpu_backtrace(true);
 
        return true;
 }
+static inline bool trigger_allbutself_cpu_backtrace(void)
+{
+       arch_trigger_all_cpu_backtrace(false);
+       return true;
+}
 #else
 static inline bool trigger_all_cpu_backtrace(void)
 {
        return false;
 }
+static inline bool trigger_allbutself_cpu_backtrace(void)
+{
+       return false;
+}
 #endif
 
 #ifdef CONFIG_LOCKUP_DETECTOR