There have been several times where I have had to rebuild a kernel to cause a panic when hitting a WARN() in the code in order to get a crash dump from a system. Sometimes this is easy to do, other times (such as in the case of a remote admin) it is not trivial to send new images to the user. A much easier method would be a switch to change the WARN() over to a panic. This makes debugging easier in that I can now test the actual image the WARN() was seen on and I do not have to engage in remote debugging. This patch adds a panic_on_warn kernel parameter and /proc/sys/kernel/panic_on_warn calls panic() in the warn_slowpath_common() path. The function will still print out the location of the warning. An example of the panic_on_warn output: The first line below is from the WARN_ON() to output the WARN_ON()'s location. After that the panic() output is displayed. WARNING: CPU: 30 PID: 11698 at /home/prarit/dummy_module/dummy-module.c:25 init_dummy+0x1f/0x30 [dummy_module]() Kernel panic - not syncing: panic_on_warn set ... CPU: 30 PID: 11698 Comm: insmod Tainted: G W OE 3.17.0+ #57 Hardware name: Intel Corporation S2600CP/S2600CP, BIOS RMLSDP.86I.00.29.D696.1311111329 11/11/2013 0000000000000000 000000008e3f87df ffff88080f093c38 ffffffff81665190 0000000000000000 ffffffff818aea3d ffff88080f093cb8 ffffffff8165e2ec ffffffff00000008 ffff88080f093cc8 ffff88080f093c68 000000008e3f87df Call Trace: [<ffffffff81665190>] dump_stack+0x46/0x58 [<ffffffff8165e2ec>] panic+0xd0/0x204 [<ffffffffa038e05f>] ? init_dummy+0x1f/0x30 [dummy_module] [<ffffffff81076b90>] warn_slowpath_common+0xd0/0xd0 [<ffffffffa038e040>] ? dummy_greetings+0x40/0x40 [dummy_module] [<ffffffff81076c8a>] warn_slowpath_null+0x1a/0x20 [<ffffffffa038e05f>] init_dummy+0x1f/0x30 [dummy_module] [<ffffffff81002144>] do_one_initcall+0xd4/0x210 [<ffffffff811b52c2>] ? __vunmap+0xc2/0x110 [<ffffffff810f8889>] load_module+0x16a9/0x1b30 [<ffffffff810f3d30>] ? store_uevent+0x70/0x70 [<ffffffff810f49b9>] ? copy_module_from_fd.isra.44+0x129/0x180 [<ffffffff810f8ec6>] SyS_finit_module+0xa6/0xd0 [<ffffffff8166cf29>] system_call_fastpath+0x12/0x17 Successfully tested by me. Cc: Jonathan Corbet <corbet at lwn.net> Cc: Andrew Morton <akpm at linux-foundation.org> Cc: Rusty Russell <rusty at rustcorp.com.au> Cc: "H. Peter Anvin" <hpa at zytor.com> Cc: Andi Kleen <ak at linux.intel.com> Cc: Masami Hiramatsu <masami.hiramatsu.pt at hitachi.com> Cc: Fabian Frederick <fabf at skynet.be> Cc: vgoyal at redhat.com Cc: isimatu.yasuaki at jp.fujitsu.com Cc: jbaron at akamai.com Cc: linux-doc at vger.kernel.org Cc: kexec at lists.infradead.org Cc: linux-api at vger.kernel.org Signed-off-by: Prarit Bhargava <prarit at redhat.com> [v2]: add /proc/sys/kernel/panic_on_warn, additional documentation, modify !slowpath cases [v3]: use proc_dointvec_minmax() in sysctl handler [v4]: remove !slowpath cases, and add __read_mostly [v5]: change to panic_on_warn, re-alphabetize Documentation/sysctl/kernel.txt [v6]: fix typo in kernel/sysctl_binary.c --- Documentation/kdump/kdump.txt | 7 ++++++ Documentation/kernel-parameters.txt | 3 +++ Documentation/sysctl/kernel.txt | 40 +++++++++++++++++++++++------------ include/linux/kernel.h | 1 + include/uapi/linux/sysctl.h | 1 + kernel/panic.c | 20 +++++++++++++++++- kernel/sysctl.c | 9 ++++++++ kernel/sysctl_binary.c | 1 + 8 files changed, 67 insertions(+), 15 deletions(-) diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt index 6c0b9f2..bc4bd5a 100644 --- a/Documentation/kdump/kdump.txt +++ b/Documentation/kdump/kdump.txt @@ -471,6 +471,13 @@ format. Crash is available on Dave Anderson's site at the following URL: http://people.redhat.com/~anderson/ +Trigger Kdump on WARN() +======================= + +The kernel parameter, panic_on_warn, calls panic() in all WARN() paths. This +will cause a kdump to occur at the panic() call. In cases where a user wants +to specify this during runtime, /proc/sys/kernel/panic_on_warn can be set to 1 +to achieve the same behaviour. Contact ======= diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 74339c5..262ff3b 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2495,6 +2495,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted. timeout < 0: reboot immediately Format: <timeout> + panic_on_warn panic() instead of WARN(). Useful to cause kdump + on a WARN(). + crash_kexec_post_notifiers Run kdump after running panic-notifiers and dumping kmsg. This only for the users who doubt kdump always diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 57baff5..b5d0c85 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -54,8 +54,9 @@ show up in /proc/sys/kernel: - overflowuid - panic - panic_on_oops -- panic_on_unrecovered_nmi - panic_on_stackoverflow +- panic_on_unrecovered_nmi +- panic_on_warn - pid_max - powersave-nap [ PPC only ] - printk @@ -527,19 +528,6 @@ the recommended setting is 60. ============================================================== -panic_on_unrecovered_nmi: - -The default Linux behaviour on an NMI of either memory or unknown is -to continue operation. For many environments such as scientific -computing it is preferable that the box is taken out and the error -dealt with than an uncorrected parity/ECC error get propagated. - -A small number of systems do generate NMI's for bizarre random reasons -such as power management so the default is off. That sysctl works like -the existing panic controls already in that directory. - -============================================================== - panic_on_oops: Controls the kernel's behaviour when an oops or BUG is encountered. @@ -563,6 +551,30 @@ This file shows up if CONFIG_DEBUG_STACKOVERFLOW is enabled. ============================================================== +panic_on_unrecovered_nmi: + +The default Linux behaviour on an NMI of either memory or unknown is +to continue operation. For many environments such as scientific +computing it is preferable that the box is taken out and the error +dealt with than an uncorrected parity/ECC error get propagated. + +A small number of systems do generate NMI's for bizarre random reasons +such as power management so the default is off. That sysctl works like +the existing panic controls already in that directory. + +============================================================== + +panic_on_warn: + +Calls panic() in the WARN() path when set to 1. This is useful to avoid +a kernel rebuild when attempting to kdump at the location of a WARN(). + +0: only WARN(), default behaviour. + +1: call panic() after printing out WARN() location. + +============================================================== + perf_cpu_time_max_percent: Hints to the kernel how much CPU time it should be allowed to diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 3d770f55..d60d31d 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -422,6 +422,7 @@ extern int panic_timeout; extern int panic_on_oops; extern int panic_on_unrecovered_nmi; extern int panic_on_io_nmi; +extern int panic_on_warn; extern int sysctl_panic_on_stackoverflow; /* * Only to be used by arch init code. If the user over-wrote the default diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 43aaba1..0956373 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -153,6 +153,7 @@ enum KERN_MAX_LOCK_DEPTH=74, /* int: rtmutex's maximum lock depth */ KERN_NMI_WATCHDOG=75, /* int: enable/disable nmi watchdog */ KERN_PANIC_ON_NMI=76, /* int: whether we will panic on an unrecovered */ + KERN_PANIC_ON_WARN=77, /* int: call panic() in WARN() functions */ }; diff --git a/kernel/panic.c b/kernel/panic.c index d09dc5c..2ab2168 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -33,6 +33,7 @@ static int pause_on_oops; static int pause_on_oops_flag; static DEFINE_SPINLOCK(pause_on_oops_lock); static bool crash_kexec_post_notifiers; +int panic_on_warn __read_mostly; int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); @@ -420,13 +421,23 @@ static void warn_slowpath_common(const char *file, int line, void *caller, { disable_trace_on_warning(); - pr_warn("------------[ cut here ]------------\n"); + if (!panic_on_warn) + pr_warn("------------[ cut here ]------------\n"); pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS()\n", raw_smp_processor_id(), current->pid, file, line, caller); if (args) vprintk(args->fmt, args->args); + if (panic_on_warn) { + /* + * A flood of WARN()s may occur. Prevent further WARN()s + * from panicking the system. + */ + panic_on_warn = 0; + panic("panic_on_warn set ... \n"); + } + print_modules(); dump_stack(); print_oops_end_marker(); @@ -501,3 +512,10 @@ static int __init oops_setup(char *s) return 0; } early_param("oops", oops_setup); + +static int __init panic_on_warn_setup(char *s) +{ + panic_on_warn = 1; + return 0; +} +early_param("panic_on_warn", panic_on_warn_setup); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 4aada6d..38deafa 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1103,6 +1103,15 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif + { + .procname = "panic_on_warn", + .data = &panic_on_warn, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, { } }; diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 9a4f750..7e7746a 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -137,6 +137,7 @@ static const struct bin_table bin_kern_table[] = { { CTL_INT, KERN_COMPAT_LOG, "compat-log" }, { CTL_INT, KERN_MAX_LOCK_DEPTH, "max_lock_depth" }, { CTL_INT, KERN_PANIC_ON_NMI, "panic_on_unrecovered_nmi" }, + { CTL_INT, KERN_PANIC_ON_WARN, "panic_on_warn" }, {} }; -- 1.7.9.3