lkml.org 
[lkml]   [2007]   [Jun]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[PATCH] Info dump on Oops or panic()
From: Joshua Wise <jwise@google.com>

Background:
When managing a large number of servers, as Google does, it's sometimes
useful to get an "at-a-glance" view of a machine when it crashes. When no
other post-mortem is possible, it's often useful to know how long the
machine has been powered on, which kernel it was running, and possibly
other information that a driver may have logged. Up until now, there was no
real way to do this other than to keep statistics outside to the machine.

Description:
This patch adds a call chain to be invoked when the system oopses or
panics. Traps have been added to i386 and x86_64 kernels, but it should be
trivial to add support for more architectures. Two sample notifiers have
been added -- an uptime printer, and a utsname printer for showing various
statistics about the running system.

Remaining issues:
* Is do_posix_clock_monotonic_gettime really the right API?
* Should this be on by default, or a disablable Kconfig entry?

Testing:
I accidentally built my testing kernel without the IDE drivers. It panic()ed
immediately, and informed me that my uptime was 0.38 seconds.

Credits:
This code was mainly written by Mike Waychison <mikew@google.com> and
Masoud Sharbiani <masouds@google.com>.

Patch:
This patch is against git 48d8d7ee5dd17c64833e0343ab4ae8ef01cc2648.

Signed-off-by: Joshua Wise <jwise@google.com>
Acked-by: Mike Waychison <mikew@google.com>

--

diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 06dfa65..42d4397 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -325,6 +325,8 @@ void show_regs(struct pt_regs * regs)
cr4 = read_cr4_safe();
printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4);
show_trace(NULL, regs, &regs->esp);
+
+ atomic_notifier_call_chain(&info_dumper_list, 0, NULL);
}

/*
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index 90da057..16668c2 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -341,6 +341,8 @@ void show_registers(struct pt_regs *regs
}
}
printk("\n");
+
+ atomic_notifier_call_chain(&info_dumper_list, 0, NULL);
}

int is_valid_bugaddr(unsigned long eip)
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 5909039..7b0619a 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -356,6 +356,7 @@ void show_regs(struct pt_regs *regs)
printk("CPU %d:", smp_processor_id());
__show_regs(regs);
show_trace(NULL, regs, (void *)(regs + 1));
+ atomic_notifier_call_chain(&info_dumper_list, 0, NULL);
}

/*
diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c
index aac1c0b..e443613 100644
--- a/arch/x86_64/kernel/traps.c
+++ b/arch/x86_64/kernel/traps.c
@@ -439,6 +439,8 @@ bad:
}
}
printk("\n");
+
+ atomic_notifier_call_chain(&info_dumper_list, 0, NULL);
}

int is_valid_bugaddr(unsigned long rip)
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 7a48525..2058e58 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -104,6 +104,7 @@ #define abs(x) ({ \
})

extern struct atomic_notifier_head panic_notifier_list;
+extern struct atomic_notifier_head info_dumper_list;
extern long (*panic_blink)(long time);
NORET_TYPE void panic(const char * fmt, ...)
__attribute__ ((NORET_AND format (printf, 1, 2)));
diff --git a/kernel/panic.c b/kernel/panic.c
index 623d182..8bae618 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -97,6 +97,7 @@ #ifdef CONFIG_SMP
#endif

atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
+ atomic_notifier_call_chain(&info_dumper_list, 0, NULL);

if (!panic_blink)
panic_blink = no_blink;
diff --git a/kernel/sys.c b/kernel/sys.c
index 872271c..5bbe926 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -98,6 +98,39 @@ struct pid *cad_pid;
EXPORT_SYMBOL(cad_pid);

/*
+ * Notifier list for kernel code which wants to printk hardware specific
+ * information at Oops or panic time.
+ */
+
+ATOMIC_NOTIFIER_HEAD(info_dumper_list);
+EXPORT_SYMBOL(info_dumper_list);
+
+/*
+ * Dump out UTS info on oops / panic.
+ */
+
+static int dump_utsname(struct notifier_block *self, unsigned long v, void *p)
+{
+ printk ("%s %s %s %s %s %s\n",
+ utsname()->sysname,
+ utsname()->nodename,
+ utsname()->release,
+ utsname()->version,
+ utsname()->machine,
+ utsname()->domainname);
+ return 0;
+}
+
+static struct notifier_block utsname_notifier;
+
+static int __init register_utsname_dump(void) {
+ utsname_notifier.notifier_call = dump_utsname;
+ atomic_notifier_chain_register(&info_dumper_list, &utsname_notifier);
+ return 0;
+}
+__initcall(register_utsname_dump);
+
+/*
* Notifier list for kernel code which wants to be called
* at shutdown. This is used to stop any idling DMA operations
* and the like.
diff --git a/kernel/time.c b/kernel/time.c
index f04791f..d5ae5e0 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -31,6 +31,7 @@ #include <linux/module.h>
#include <linux/timex.h>
#include <linux/capability.h>
#include <linux/errno.h>
+#include <linux/notifier.h>
#include <linux/syscalls.h>
#include <linux/security.h>
#include <linux/fs.h>
@@ -744,3 +745,33 @@ EXPORT_SYMBOL(get_jiffies_64);
#endif

EXPORT_SYMBOL(jiffies);
+
+/*
+ * Dump out uptime info on oops / panic.
+ *
+ * FIXME: Should I be just using get_jiffies64()? what if the lock there
+ * is damaged beyond any recognition?
+ */
+static int dump_uptime(struct notifier_block *self, unsigned long v, void *p)
+{
+ struct timespec uptime;
+ /* The logic below is very much like how kernel
+ * prepares /proc/uptime.
+ */
+ do_posix_clock_monotonic_gettime(&uptime);
+ printk("Uptime(seconds): %lu.%02lu\n",
+ (unsigned long) uptime.tv_sec,
+ (uptime.tv_nsec / (NSEC_PER_SEC / 100)));
+
+ return 0;
+}
+
+static struct notifier_block uptime_notifier;
+
+static int __init register_uptime_dump(void) {
+ uptime_notifier.notifier_call = dump_uptime;
+ atomic_notifier_chain_register(&info_dumper_list, &uptime_notifier);
+ return 0;
+}
+__initcall(register_uptime_dump);
+
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
\
 
 \ /
  Last update: 2007-06-29 00:09    [W:0.840 / U:0.120 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site