[PATCH V4] kernel, add bug_on_warn

From: Prarit Bhargava
Date: Fri Oct 24 2014 - 08:54:19 EST


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
BUG(). 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 bug_on_warn kernel parameter and
/proc/sys/kernel/bug_on_warn calls BUG() in the warn_slowpath_common()
path. The function will still print out the location of the warning.

An example of the bug_on_warn output:

The first line below is from the WARN_ON() to output the WARN_ON()'s location.
After that the new BUG() call is displayed.

WARNING: CPU: 27 PID: 3204 at
/home/rhel7/redhat/debug/dummy-module/dummy-module.c:25 init_dummy+0x28/0x30
[dummy_module]()
bug_on_warn set, calling BUG()...
------------[ cut here ]------------
kernel BUG at kernel/panic.c:434!
invalid opcode: 0000 [#1] SMP
Modules linked in: dummy_module(OE+) sg nfsv3 rpcsec_gss_krb5 nfsv4
dns_resolver nfs fscache cfg80211 rfkill x86_pkg_temp_thermal intel_powerclamp
coretemp kvm_intel kvm crct10dif_pclmul crc32_pclmul crc32c_intel
ghash_clmulni_intel igb iTCO_wdt aesni_intel iTCO_vendor_support lrw gf128mul
sb_edac ptp edac_core glue_helper lpc_ich ioatdma pcspkr ablk_helper pps_core
i2c_i801 mfd_core cryptd dca shpchp ipmi_si wmi ipmi_msghandler acpi_cpufreq
nfsd auth_rpcgss nfs_acl lockd grace sunrpc xfs libcrc32c sr_mod cdrom sd_mod
mgag200 syscopyarea sysfillrect sysimgblt i2c_algo_bit drm_kms_helper isci ttm
drm libsas ahci libahci scsi_transport_sas libata i2c_core dm_mirror
dm_region_hash dm_log dm_mod
CPU: 27 PID: 3204 Comm: insmod Tainted: G OE 3.17.0+ #19
Hardware name: Intel Corporation S2600CP/S2600CP, BIOS
RMLSDP.86I.00.29.D696.1311111329 11/11/2013
task: ffff880034e75160 ti: ffff8807fc5ac000 task.ti: ffff8807fc5ac000
RIP: 0010:[<ffffffff81076b81>] [<ffffffff81076b81>] warn_slowpath_common+0xc1/0xd0
RSP: 0018:ffff8807fc5afc68 EFLAGS: 00010246
RAX: 0000000000000021 RBX: ffff8807fc5afcb0 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffff88081efee5f8 RDI: ffff88081efee5f8
RBP: ffff8807fc5afc98 R08: 0000000000000096 R09: 0000000000000000
R10: 0000000000000711 R11: ffff8807fc5af93e R12: ffffffffa0424070
R13: 0000000000000019 R14: ffffffffa0423068 R15: 0000000000000009
FS: 00007f2d4b034740(0000) GS:ffff88081efe0000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f2d4a99f3c0 CR3: 00000007fd88b000 CR4: 00000000001407e0
Stack:
ffff8807fc5afcb8 ffffffff8199f020 ffff88080e396160 0000000000000000
ffffffffa0423040 ffffffffa0425000 ffff8807fc5afd08 ffffffff81076be5
0000000000000008 ffffffffa0424053 ffff880700000018 ffff8807fc5afd18
Call Trace:
[<ffffffffa0423040>] ? dummy_greetings+0x40/0x40 [dummy_module]
[<ffffffff81076be5>] warn_slowpath_fmt+0x55/0x70
[<ffffffffa0423068>] init_dummy+0x28/0x30 [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
[<ffffffff8166ce29>] system_call_fastpath+0x12/0x17
Code: c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d c3 48 c7 c7 20 42 8a 81 31 c0 e8 fc
80 5e 00 eb 80 48 c7 c7 78 42 8a 81 31 c0 e8 ec 80 5e 00 <0f> 0b 66 66 66 66 2e
0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55
RIP [<ffffffff81076b81>] warn_slowpath_common+0xc1/0xd0
RSP <ffff8807fc5afc68>
---[ end trace 428218934a12088b ]---

Successfully tested by me.

Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Rusty Russell <rusty@xxxxxxxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@xxxxxxxxxxx>
Cc: Fabian Frederick <fabf@xxxxxxxxx>
Cc: vgoyal@xxxxxxxxxx
Cc: isimatu.yasuaki@xxxxxxxxxxxxxx
Cc: linux-doc@xxxxxxxxxxxxxxx
Cc: kexec@xxxxxxxxxxxxxxxxxxx
Cc: linux-api@xxxxxxxxxxxxxxx
Signed-off-by: Prarit Bhargava <prarit@xxxxxxxxxx>

[v2]: add /proc/sys/kernel/bug_on_warn, additional documentation, modify
!slowpath cases
[v3]: use proc_dointvec_minmax() in sysctl handler
[v4]: remove !slowpath cases, and add __read_mostly
---
Documentation/kdump/kdump.txt | 7 +++++++
Documentation/kernel-parameters.txt | 3 +++
Documentation/sysctl/kernel.txt | 12 ++++++++++++
include/linux/kernel.h | 1 +
include/uapi/linux/sysctl.h | 1 +
kernel/panic.c | 21 ++++++++++++++++++++-
kernel/sysctl.c | 9 +++++++++
kernel/sysctl_binary.c | 1 +
8 files changed, 54 insertions(+), 1 deletion(-)

diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
index 6c0b9f2..a04ed72 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, bug_on_warn, calls BUG() in all WARN() paths. This
+will cause a kdump to occur at the BUG() call. In cases where a user
+wants to specify this during runtime, /proc/sys/kernel/bug_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..aa1d319 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -553,6 +553,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
bttv.pll= See Documentation/video4linux/bttv/Insmod-options
bttv.tuner=

+ bug_on_warn BUG() instead of WARN(). Useful to cause kdump
+ on a WARN().
+
bulk_remove=off [PPC] This parameter disables the use of the pSeries
firmware feature for flushing multiple hpte entries
at a time.
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 57baff5..dcadcdc 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -23,6 +23,7 @@ show up in /proc/sys/kernel:
- auto_msgmni
- bootloader_type [ X86 only ]
- bootloader_version [ X86 only ]
+- bug_on_warn
- callhome [ S390 only ]
- cap_last_cap
- core_pattern
@@ -152,6 +153,17 @@ Documentation/x86/boot.txt for additional information.

==============================================================

+bug_on_warn:
+
+Calls BUG() 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 BUG() after printing out WARN() location.
+
+==============================================================
+
callhome:

Controls the kernel's callhome behavior in case of a kernel panic.
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 3d770f55..fc28bff 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -423,6 +423,7 @@ extern int panic_on_oops;
extern int panic_on_unrecovered_nmi;
extern int panic_on_io_nmi;
extern int sysctl_panic_on_stackoverflow;
+extern int bug_on_warn;
/*
* Only to be used by arch init code. If the user over-wrote the default
* CONFIG_PANIC_TIMEOUT, honor it.
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 43aaba1..2ba0a58 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_BUG_ON_WARN=77, /* int: call BUG() in WARN() functions */
};


diff --git a/kernel/panic.c b/kernel/panic.c
index d09dc5c..740d9ff 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 bug_on_warn __read_mostly;

int panic_timeout = CONFIG_PANIC_TIMEOUT;
EXPORT_SYMBOL_GPL(panic_timeout);
@@ -420,13 +421,24 @@ static void warn_slowpath_common(const char *file, int line, void *caller,
{
disable_trace_on_warning();

- pr_warn("------------[ cut here ]------------\n");
+ if (!bug_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 (bug_on_warn) {
+ pr_warn("bug_on_warn set, calling BUG()...\n");
+ /*
+ * A flood of WARN()s may occur. Prevent further WARN()s
+ * from panicking the system.
+ */
+ bug_on_warn = 0;
+ BUG();
+ }
+
print_modules();
dump_stack();
print_oops_end_marker();
@@ -501,3 +513,10 @@ static int __init oops_setup(char *s)
return 0;
}
early_param("oops", oops_setup);
+
+static int __init bug_on_warn_setup(char *s)
+{
+ bug_on_warn = 1;
+ return 0;
+}
+early_param("bug_on_warn", bug_on_warn_setup);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4aada6d..818cd31 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 = "bug_on_warn",
+ .data = &bug_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..28376bf 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_BUG_ON_WARN, "bug_on_warn" },
{}
};

--
1.7.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/