[PATCH] check nmi watchdog is broken

A bug against an xSeries system showed up recently noting that the
check_nmi_watchdog() test was failing.

I have been investigating it and discovered in both i386 and x86_64 the
recent change to the routine to use the cpu_callin_map has uncovered a
problem.  Prior to that change, on an SMP box, the test was trivally
passing because all cpu's were found to not yet be online, but now with the
callin_map they are discovered, it goes on to test the counter and they
have not yet begun to increment, so it announces a CPU is stuck and bails
out.

On all the systems I have access to test, the announcement of failure is
also bougs...  by the time you can login and check /proc/interrupts, the
NMI count is happily incrementing on all CPUs.  Its just that the test is
being done too early.

I have tried moving the call to the test around a bit, and it was always
too early.  I finally hit on this proposed solution, it delays the routine
via a late_initcall(), seems like the right solution to me.

Signed-off-by: Adrian Bunk <bunk@stusta.de>
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/i386/kernel/apic.c b/arch/i386/kernel/apic.c
index e3879f7625c2e80a923bf12ede3dce08ca714d0a..d509836b70c356ec5c61df9cdb967cf5f5c753ba 100644 (file)
--- a/arch/i386/kernel/apic.c
+++ b/arch/i386/kernel/apic.c
@@ -1265,8 +1265,6 @@ int __init APIC_init_uniprocessor (void)
 
        setup_local_APIC();
 
-       if (nmi_watchdog == NMI_LOCAL_APIC)
-               check_nmi_watchdog();
 #ifdef CONFIG_X86_IO_APIC
        if (smp_found_config)
                if (!skip_ioapic_setup && nr_ioapics)

diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index 5e0d55be54357bbc4a1f232a1535b9276d9d876f..7a324e8b86f9c4b5f2cf8d9bc40a9426cbd21c0a 100644 (file)
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -2175,7 +2175,6 @@ static inline void check_timer(void)
                                disable_8259A_irq(0);
                                setup_nmi();
                                enable_8259A_irq(0);
-                               check_nmi_watchdog();
                        }
                        return;
                }
@@ -2198,7 +2197,6 @@ static inline void check_timer(void)
                                add_pin_to_irq(0, 0, pin2);
                        if (nmi_watchdog == NMI_IO_APIC) {
                                setup_nmi();
-                               check_nmi_watchdog();
                        }
                        return;
                }

diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index 2f89d000f9540b0e95b6f09b18858dee85c2f64c..2c0ee9c2d0204bc400ea92791c6cd2c23c4fd9de 100644 (file)
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -102,20 +102,21 @@ int nmi_active;
        (P4_CCCR_OVF_PMI0|P4_CCCR_THRESHOLD(15)|P4_CCCR_COMPLEMENT|     \
         P4_CCCR_COMPARE|P4_CCCR_REQUIRED|P4_CCCR_ESCR_SELECT(4)|P4_CCCR_ENABLE)
 
-int __init check_nmi_watchdog (void)
+static int __init check_nmi_watchdog(void)
 {
        unsigned int prev_nmi_count[NR_CPUS];
        int cpu;
 
-       printk(KERN_INFO "testing NMI watchdog ... ");
+       if (nmi_watchdog == NMI_NONE)
+               return 0;
+
+       printk(KERN_INFO "Testing NMI watchdog ... ");
 
        for (cpu = 0; cpu < NR_CPUS; cpu++)
                prev_nmi_count[cpu] = per_cpu(irq_stat, cpu).__nmi_count;
        local_irq_enable();
        mdelay((10*1000)/nmi_hz); // wait 10 ticks
 
-       /* FIXME: Only boot CPU is online at this stage.  Check CPUs
-           as they come up. */
        for (cpu = 0; cpu < NR_CPUS; cpu++) {
 #ifdef CONFIG_SMP
                /* Check cpu_callin_map here because that is set
@@ -139,6 +140,8 @@ int __init check_nmi_watchdog (void)
 
        return 0;
 }
+/* This needs to happen later in boot so counters are working */
+late_initcall(check_nmi_watchdog);
 
 static int __init setup_nmi_watchdog(char *str)
 {

diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index fd36d2f65f885e73a61c9fb131bcb1bf2a7e4aea..cbea7ac582e57a09fe919e4cc444c53a6a525ba4 100644 (file)
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -1089,9 +1089,6 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
                }
        }
 
-       if (nmi_watchdog == NMI_LOCAL_APIC)
-               check_nmi_watchdog();
-
        smpboot_setup_io_apic();
 
        setup_boot_APIC_clock();

diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c
index 29a257295484ee01c16d0ebdf1bfdbe2caeeb1d3..60be58617eb977e1620beda8e363ba9cfd9fc17c 100644 (file)
--- a/arch/x86_64/kernel/io_apic.c
+++ b/arch/x86_64/kernel/io_apic.c
@@ -1607,7 +1607,6 @@ static inline void check_timer(void)
                                disable_8259A_irq(0);
                                setup_nmi();
                                enable_8259A_irq(0);
-                               check_nmi_watchdog();
                        }
                        return;
                }
@@ -1627,7 +1626,6 @@ static inline void check_timer(void)
                        nmi_watchdog_default();
                        if (nmi_watchdog == NMI_IO_APIC) {
                                setup_nmi();
-                               check_nmi_watchdog();
                        }
                        return;
                }

diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index e00d4adec36bd22619a348af72242bf06d4204c7..61de0b34a01e850fedb824115b2e0560ed98ff59 100644 (file)
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -112,17 +112,20 @@ static __init int cpu_has_lapic(void)
        }       
 }
 
-int __init check_nmi_watchdog (void)
+static int __init check_nmi_watchdog (void)
 {
        int counts[NR_CPUS];
        int cpu;
 
+       if (nmi_watchdog == NMI_NONE)
+               return 0;
+
        if (nmi_watchdog == NMI_LOCAL_APIC && !cpu_has_lapic())  {
                nmi_watchdog = NMI_NONE;
                return -1; 
        }       
 
-       printk(KERN_INFO "testing NMI watchdog ... ");
+       printk(KERN_INFO "Testing NMI watchdog ... ");
 
        for (cpu = 0; cpu < NR_CPUS; cpu++)
                counts[cpu] = cpu_pda[cpu].__nmi_count; 
@@ -148,6 +151,8 @@ int __init check_nmi_watchdog (void)
 
        return 0;
 }
+/* Have this called later during boot so counters are updating */
+late_initcall(check_nmi_watchdog);
 
 int __init setup_nmi_watchdog(char *str)
 {

diff --git a/include/asm-i386/apic.h b/include/asm-i386/apic.h
index e1de67483f383e2e8bdb851b810d81c22ef11cab..a5810cf7b5783b9c156a33af77b1d1f0e960246e 100644 (file)
--- a/include/asm-i386/apic.h
+++ b/include/asm-i386/apic.h
@@ -109,7 +109,6 @@ extern int APIC_init_uniprocessor (void);
 extern void disable_APIC_timer(void);
 extern void enable_APIC_timer(void);
 
-extern int check_nmi_watchdog (void);
 extern void enable_NMI_through_LVT0 (void * dummy);
 
 extern unsigned int nmi_watchdog;

diff --git a/include/asm-x86_64/apic.h b/include/asm-x86_64/apic.h
index c025cc3ef7890c5377c684f6aaf73e485a8b8cdd..e4b1017b8b2b1cbb7208abcd123b38e49d0d3e46 100644 (file)
--- a/include/asm-x86_64/apic.h
+++ b/include/asm-x86_64/apic.h
@@ -99,7 +99,6 @@ extern void disable_APIC_timer(void);
 extern void enable_APIC_timer(void);
 extern void clustered_apic_check(void);
 
-extern int check_nmi_watchdog(void);
 extern void nmi_watchdog_default(void);
 extern int setup_nmi_watchdog(char *);