The patch titled
ppc64: soft reset fixes
has been removed from the -mm tree. Its filename is
ppc64-soft-reset-fixes.patch
This patch was probably dropped from -mm because
it has now been merged into a subsystem tree or
into Linus's tree, or because it was folded into
its parent patch in the -mm tree.
From: David Wilder <dwilder@xxxxxxxxxx>
For the crash scenario, when a CPU hangs with interrupts disabled and the
other CPUs panic or user invoked kdump boot using sysrq-c. In this case,
the hung CPU can not be stopped and causes the kdump boot not successful.
This case can be treated as complete system hang and asks the user to
activate soft-reset if all secondary CPUs are not stopped.
Signed-off-by: Haren Myneni <haren@xxxxxxxxxx>
Signed-off-by: David Wilder <dwilder@xxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
arch/powerpc/kernel/crash.c | 150 +++++++++++++++++++++++++++-------
arch/powerpc/kernel/traps.c | 26 ++---
include/asm-powerpc/kexec.h | 5 -
include/linux/kexec.h | 1
4 files changed, 137 insertions(+), 45 deletions(-)
diff -puN arch/powerpc/kernel/crash.c~ppc64-soft-reset-fixes arch/powerpc/kernel/crash.c
--- devel/arch/powerpc/kernel/crash.c~ppc64-soft-reset-fixes 2006-04-17 21:48:07.000000000 -0700
+++ devel-akpm/arch/powerpc/kernel/crash.c 2006-04-17 21:48:07.000000000 -0700
@@ -23,9 +23,11 @@
#include <linux/elfcore.h>
#include <linux/init.h>
#include <linux/types.h>
+#include <linux/irq.h>
#include <asm/processor.h>
#include <asm/machdep.h>
+#include <asm/kexec.h>
#include <asm/kdump.h>
#include <asm/lmb.h>
#include <asm/firmware.h>
@@ -40,6 +42,7 @@
/* This keeps a track of which one is crashing cpu. */
int crashing_cpu = -1;
+static cpumask_t cpus_in_crash = CPU_MASK_NONE;
static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
size_t data_len)
@@ -97,34 +100,66 @@ static void crash_save_this_cpu(struct p
}
#ifdef CONFIG_SMP
-static atomic_t waiting_for_crash_ipi;
+static atomic_t enter_on_soft_reset = ATOMIC_INIT(0);
void crash_ipi_callback(struct pt_regs *regs)
{
int cpu = smp_processor_id();
- if (cpu == crashing_cpu)
- return;
-
if (!cpu_online(cpu))
return;
- if (ppc_md.kexec_cpu_down)
- ppc_md.kexec_cpu_down(1, 1);
-
local_irq_disable();
+ if (!cpu_isset(cpu, cpus_in_crash))
+ crash_save_this_cpu(regs, cpu);
+ cpu_set(cpu, cpus_in_crash);
+
+ /*
+ * Entered via soft-reset - could be the kdump
+ * process is invoked using soft-reset or user activated
+ * it if some CPU did not respond to an IPI.
+ * For soft-reset, the secondary CPU can enter this func
+ * twice. 1 - using IPI, and 2. soft-reset.
+ * Tell the kexec CPU that entered via soft-reset and ready
+ * to go down.
+ */
+ if (cpu_isset(cpu, cpus_in_sr)) {
+ cpu_clear(cpu, cpus_in_sr);
+ atomic_inc(&enter_on_soft_reset);
+ }
+
+ /*
+ * Starting the kdump boot.
+ * This barrier is needed to make sure that all CPUs are stopped.
+ * If not, soft-reset will be invoked to bring other CPUs.
+ */
+ while (!cpu_isset(crashing_cpu, cpus_in_crash))
+ cpu_relax();
- crash_save_this_cpu(regs, cpu);
- atomic_dec(&waiting_for_crash_ipi);
+ if (ppc_md.kexec_cpu_down)
+ ppc_md.kexec_cpu_down(1, 1);
kexec_smp_wait();
/* NOTREACHED */
}
-static void crash_kexec_prepare_cpus(void)
+/*
+ * Wait until all CPUs are entered via soft-reset.
+ */
+static void crash_soft_reset_check(int cpu)
+{
+ unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */
+
+ cpu_clear(cpu, cpus_in_sr);
+ while (atomic_read(&enter_on_soft_reset) != ncpus)
+ cpu_relax();
+}
+
+
+static void crash_kexec_prepare_cpus(int cpu)
{
unsigned int msecs;
- atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+ unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */
crash_send_ipi(crash_ipi_callback);
smp_wmb();
@@ -132,14 +167,13 @@ static void crash_kexec_prepare_cpus(voi
/*
* FIXME: Until we will have the way to stop other CPUSs reliabally,
* the crash CPU will send an IPI and wait for other CPUs to
- * respond. If not, proceed the kexec boot even though we failed to
- * capture other CPU states.
+ * respond.
* Delay of at least 10 seconds.
*/
- printk(KERN_ALERT "Sending IPI to other cpus...\n");
+ printk(KERN_EMERG "Sending IPI to other cpus...\n");
msecs = 10000;
- while ((atomic_read(&waiting_for_crash_ipi) > 0) && (--msecs > 0)) {
- barrier();
+ while ((cpus_weight(cpus_in_crash) < ncpus) && (--msecs > 0)) {
+ cpu_relax();
mdelay(1);
}
@@ -148,18 +182,71 @@ static void crash_kexec_prepare_cpus(voi
/*
* FIXME: In case if we do not get all CPUs, one possibility: ask the
* user to do soft reset such that we get all.
- * IPI handler is already set by the panic cpu initially. Therefore,
- * all cpus could invoke this handler from die() and the panic CPU
- * will call machine_kexec() directly from this handler to do
- * kexec boot.
- */
- if (atomic_read(&waiting_for_crash_ipi))
- printk(KERN_ALERT "done waiting: %d cpus not responding\n",
- atomic_read(&waiting_for_crash_ipi));
+ * Soft-reset will be used until better mechanism is implemented.
+ */
+ if (cpus_weight(cpus_in_crash) < ncpus) {
+ printk(KERN_EMERG "done waiting: %d cpu(s) not responding\n",
+ ncpus - cpus_weight(cpus_in_crash));
+ printk(KERN_EMERG "Activate soft-reset to stop other cpu(s)\n");
+ cpus_in_sr = CPU_MASK_NONE;
+ atomic_set(&enter_on_soft_reset, 0);
+ while (cpus_weight(cpus_in_crash) < ncpus)
+ cpu_relax();
+ }
+ /*
+ * Make sure all CPUs are entered via soft-reset if the kdump is
+ * invoked using soft-reset.
+ */
+ if (cpu_isset(cpu, cpus_in_sr))
+ crash_soft_reset_check(cpu);
/* Leave the IPI callback set */
}
+
+/*
+ * This function will be called by secondary cpus or by kexec cpu
+ * if soft-reset is activated to stop some CPUs.
+ */
+void crash_kexec_secondary(struct pt_regs *regs)
+{
+ int cpu = smp_processor_id();
+ unsigned long flags;
+ int msecs = 5;
+
+ local_irq_save(flags);
+ /* Wait 5ms if the kexec CPU is not entered yet. */
+ while (crashing_cpu < 0) {
+ if (--msecs < 0) {
+ /*
+ * Either kdump image is not loaded or
+ * kdump process is not started - Probably xmon
+ * exited using 'x'(exit and recover) or
+ * kexec_should_crash() failed for all running tasks.
+ */
+ cpu_clear(cpu, cpus_in_sr);
+ local_irq_restore(flags);
+ return;
+ }
+ mdelay(1);
+ cpu_relax();
+ }
+ if (cpu == crashing_cpu) {
+ /*
+ * Panic CPU will enter this func only via soft-reset.
+ * Wait until all secondary CPUs entered and
+ * then start kexec boot.
+ */
+ crash_soft_reset_check(cpu);
+ cpu_set(crashing_cpu, cpus_in_crash);
+ if (ppc_md.kexec_cpu_down)
+ ppc_md.kexec_cpu_down(1, 0);
+ machine_kexec(kexec_crash_image);
+ /* NOTREACHED */
+ }
+ crash_ipi_callback(regs);
+}
+
#else
-static void crash_kexec_prepare_cpus(void)
+static void crash_kexec_prepare_cpus(int cpu)
{
/*
* move the secondarys to us so that we can copy
@@ -170,6 +257,10 @@ static void crash_kexec_prepare_cpus(voi
smp_release_cpus();
}
+void crash_kexec_secondary(struct pt_regs *regs)
+{
+ cpus_in_sr = CPU_MASK_NONE;
+}
#endif
void default_machine_crash_shutdown(struct pt_regs *regs)
@@ -185,15 +276,14 @@ void default_machine_crash_shutdown(stru
* The kernel is broken so disable interrupts.
*/
local_irq_disable();
-
- if (ppc_md.kexec_cpu_down)
- ppc_md.kexec_cpu_down(1, 0);
-
/*
* Make a note of crashing cpu. Will be used in machine_kexec
* such that another IPI will not be sent.
*/
crashing_cpu = smp_processor_id();
- crash_kexec_prepare_cpus();
crash_save_this_cpu(regs, crashing_cpu);
+ crash_kexec_prepare_cpus(crashing_cpu);
+ cpu_set(crashing_cpu, cpus_in_crash);
+ if (ppc_md.kexec_cpu_down)
+ ppc_md.kexec_cpu_down(1, 0);
}
diff -puN arch/powerpc/kernel/traps.c~ppc64-soft-reset-fixes arch/powerpc/kernel/traps.c
--- devel/arch/powerpc/kernel/traps.c~ppc64-soft-reset-fixes 2006-04-17 21:48:07.000000000 -0700
+++ devel-akpm/arch/powerpc/kernel/traps.c 2006-04-17 21:48:07.000000000 -0700
@@ -51,9 +51,13 @@
#include <asm/firmware.h>
#include <asm/processor.h>
#endif
+#include <asm/kexec.h>
#ifdef CONFIG_PPC64 /* XXX */
#define _IO_BASE pci_io_base
+#ifdef CONFIG_KEXEC
+cpumask_t cpus_in_sr = CPU_MASK_NONE;
+#endif
#endif
#ifdef CONFIG_DEBUGGER
@@ -96,7 +100,7 @@ static DEFINE_SPINLOCK(die_lock);
int die(const char *str, struct pt_regs *regs, long err)
{
- static int die_counter, crash_dump_start = 0;
+ static int die_counter;
if (debugger(regs))
return 1;
@@ -128,21 +132,11 @@ int die(const char *str, struct pt_regs
print_modules();
show_regs(regs);
bust_spinlocks(0);
+ spin_unlock_irq(&die_lock);
- if (!crash_dump_start && kexec_should_crash(current)) {
- crash_dump_start = 1;
- spin_unlock_irq(&die_lock);
+ if (kexec_should_crash(current))
crash_kexec(regs);
- /* NOTREACHED */
- }
- spin_unlock_irq(&die_lock);
- if (crash_dump_start)
- /*
- * Only for soft-reset: Other CPUs will be responded to an IPI
- * sent by first kexec CPU.
- */
- for(;;)
- ;
+ crash_kexec_secondary(regs);
if (in_interrupt())
panic("Fatal exception in interrupt");
@@ -206,6 +200,10 @@ void system_reset_exception(struct pt_re
return;
}
+#ifdef CONFIG_KEXEC
+ cpu_set(smp_processor_id(), cpus_in_sr);
+#endif
+
die("System Reset", regs, SIGABRT);
/* Must die if the interrupt is not recoverable */
diff -puN include/asm-powerpc/kexec.h~ppc64-soft-reset-fixes include/asm-powerpc/kexec.h
--- devel/include/asm-powerpc/kexec.h~ppc64-soft-reset-fixes 2006-04-17 21:48:07.000000000 -0700
+++ devel-akpm/include/asm-powerpc/kexec.h 2006-04-17 21:48:07.000000000 -0700
@@ -114,6 +114,7 @@ extern void kexec_smp_wait(void); /* get
extern void __init kexec_setup(void);
extern int crashing_cpu;
extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *));
+extern cpumask_t cpus_in_sr;
#endif /* __powerpc64 __ */
struct kimage;
@@ -123,8 +124,10 @@ extern int default_machine_kexec_prepare
extern void default_machine_crash_shutdown(struct pt_regs *regs);
extern void machine_kexec_simple(struct kimage *image);
-
+extern void crash_kexec_secondary(struct pt_regs *regs);
#endif /* ! __ASSEMBLY__ */
+#else
+static inline void crash_kexec_secondary(struct pt_regs *regs) { }
#endif /* CONFIG_KEXEC */
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_KEXEC_H */
diff -puN include/linux/kexec.h~ppc64-soft-reset-fixes include/linux/kexec.h
--- devel/include/linux/kexec.h~ppc64-soft-reset-fixes 2006-04-17 21:48:07.000000000 -0700
+++ devel-akpm/include/linux/kexec.h 2006-04-17 21:48:07.000000000 -0700
@@ -106,6 +106,7 @@ extern struct page *kimage_alloc_control
extern void crash_kexec(struct pt_regs *);
int kexec_should_crash(struct task_struct *);
extern struct kimage *kexec_image;
+extern struct kimage *kexec_crash_image;
#define KEXEC_ON_CRASH 0x00000001
#define KEXEC_ARCH_MASK 0xffff0000
_
Patches currently in -mm which might be from dwilder@xxxxxxxxxx are
ppc64-soft-reset-fixes.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
