kernel, add bug_on_warn
Subsystems (6)
PATCH v2 1/1 kernel, add bug_on_warn
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, which 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.
[v2]: add /proc/sys/kernel/bug_on_warn, additional documentation, modify
!slowpath cases
--- Documentation/kdump/kdump.txt | 7 +++++++ Documentation/kernel-parameters.txt | 3 +++ Documentation/sysctl/kernel.txt | 12 ++++++++++++ include/asm-generic/bug.h | 12 ++++++++++-- include/linux/kernel.h | 1 + include/uapi/linux/sysctl.h | 1 + kernel/panic.c | 21 ++++++++++++++++++++- kernel/sysctl.c | 7 +++++++ kernel/sysctl_binary.c | 1 + 9 files changed, 62 insertions(+), 3 deletions(-)
Documentation/kdump/kdump.txt +7 -0
@@ -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 =======
Documentation/kernel-parameters.txt +3 -0
@@ -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.
Documentation/sysctl/kernel.txt +12 -0
@@ -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.
include/asm-generic/bug.h +10 -2
@@ -75,10 +75,18 @@ extern void warn_slowpath_null(const char *file, const int line); #define __WARN_printf_taint(taint, arg...) \ warn_slowpath_fmt_taint(__FILE__, __LINE__, taint, arg)#else -#define __WARN () __WARN_TAINT(TAINT_WARN) +#define check_bug_on_warn () \ + do { \ + if (bug_on_warn) \ + BUG(); \ + } while (0) + +#define __WARN () \ + do { __WARN_TAINT(TAINT_WARN); check_bug_on_warn(); } while (0) + #define __WARN_printf(arg...) do { printk(arg); __WARN(); } while (0) #define __WARN_printf_taint(taint, arg...) \ - do { printk(arg); __WARN_TAINT(taint); } while (0) + do { printk(arg); __WARN_TAINT(taint); check_bug_on_warn(); } while (0)#endif #ifndef WARN_ON
include/linux/kernel.h +1 -0
@@ -422,6 +422,7 @@ 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.
include/uapi/linux/sysctl.h +1 -0
@@ -153,6 +153,7 @@ enumKERN_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 */ };
kernel/panic.c +20 -1
@@ -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;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);
kernel/sysctl.c +7 -0
@@ -1103,6 +1103,13 @@ 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, + }, { } };
kernel/sysctl_binary.c +1 -0
@@ -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" }, {} };
Signature · 1 line
1.7.9.3
Quoted 108 lines · Prarit Bhargava
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 aBUG(). This makes debugging easier in that I can now test the actual image theWARN()was seen on and I do not have to engage in remote debugging.This patch adds a
bug_on_warnkernel parameter, which callsBUG()in thewarn_slowpath_common()path. The function will still print out the location of the warning.An example of the
bug_on_warnoutput:The first line below is from the
WARN_ON()to output the WARN_ON()'s location. After that the newBUG()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_resolvernfs fscache cfg80211 rfkillx86_pkg_temp_thermalintel_powerclampcoretempkvm_intelkvmcrct10dif_pclmulcrc32_pclmulcrc32c_intelghash_clmulni_inteligbiTCO_wdtaesni_inteliTCO_vendor_supportlrw gf128mulsb_edacptpedac_coreglue_helperlpc_ichioatdma pcspkrablk_helperpps_corei2c_i801mfd_corecryptd dca shpchpipmi_siwmiipmi_msghandleracpi_cpufreqnfsdauth_rpcgssnfs_acllockd grace sunrpc xfs libcrc32csr_modcdromsd_modmgag200 syscopyarea sysfillrect sysimgblti2c_algo_bitdrm_kms_helperisci ttm drm libsas ahci libahciscsi_transport_saslibatai2c_coredm_mirrordm_region_hashdm_logdm_modCPU: 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 fc80 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 <[email protected]>Cc Andrew Morton <[email protected]>Cc Rusty Russell <[email protected]>Cc "H. Peter Anvin" <[email protected]>Cc Andi Kleen <[email protected]>Cc Masami Hiramatsu <[email protected]>Cc Fabian Frederick <[email protected]>Signed-off-by Prarit Bhargava <[email protected]>[v2]: add
/proc/sys/kernel/bug_on_warn, additional documentation, modify
!slowpath cases--- Documentation/kdump/kdump.txt | 7 +++++++ Documentation/kernel-parameters.txt | 3 +++ Documentation/sysctl/kernel.txt | 12 ++++++++++++ include/asm-generic/bug.h | 12 ++++++++++-- include/linux/kernel.h | 1 + include/uapi/linux/sysctl.h | 1 + kernel/panic.c | 21 ++++++++++++++++++++- kernel/sysctl.c | 7 +++++++ kernel/sysctl_binary.c | 1 + 9 files changed, 62 insertions(+), 3 deletions(-)Documentation/kdump/kdump.txt +0
-0
Documentation/kdump/kdump.txt format. Crash is available on Dave Anderson's site at the following URL: · line 480
Quoted 10 lines
Documentation/kdump/kdump.txt +7
-0@@ -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.
What about during early boot?
I'd recommend you use core_param(). Less code, and can be set on commandline.
Cheers,
Rusty.
Quoted 112 lines · Rusty Russell
Quoted 111 lines · Prarit Bhargava
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 aBUG(). This makes debugging easier in that I can now test the actual image theWARN()was seen on and I do not have to engage in remote debugging.This patch adds a
bug_on_warnkernel parameter, which callsBUG()in thewarn_slowpath_common()path. The function will still print out the location of the warning.An example of the
bug_on_warnoutput:The first line below is from the
WARN_ON()to output the WARN_ON()'s location. After that the newBUG()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_resolvernfs fscache cfg80211 rfkillx86_pkg_temp_thermalintel_powerclampcoretempkvm_intelkvmcrct10dif_pclmulcrc32_pclmulcrc32c_intelghash_clmulni_inteligbiTCO_wdtaesni_inteliTCO_vendor_supportlrw gf128mulsb_edacptpedac_coreglue_helperlpc_ichioatdma pcspkrablk_helperpps_corei2c_i801mfd_corecryptd dca shpchpipmi_siwmiipmi_msghandleracpi_cpufreqnfsdauth_rpcgssnfs_acllockd grace sunrpc xfs libcrc32csr_modcdromsd_modmgag200 syscopyarea sysfillrect sysimgblti2c_algo_bitdrm_kms_helperisci ttm drm libsas ahci libahciscsi_transport_saslibatai2c_coredm_mirrordm_region_hashdm_logdm_modCPU: 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 fc80 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 <[email protected]>Cc Andrew Morton <[email protected]>Cc Rusty Russell <[email protected]>Cc "H. Peter Anvin" <[email protected]>Cc Andi Kleen <[email protected]>Cc Masami Hiramatsu <[email protected]>Cc Fabian Frederick <[email protected]>Signed-off-by Prarit Bhargava <[email protected]>[v2]: add
/proc/sys/kernel/bug_on_warn, additional documentation, modify
!slowpath cases--- Documentation/kdump/kdump.txt | 7 +++++++ Documentation/kernel-parameters.txt | 3 +++ Documentation/sysctl/kernel.txt | 12 ++++++++++++ include/asm-generic/bug.h | 12 ++++++++++-- include/linux/kernel.h | 1 + include/uapi/linux/sysctl.h | 1 + kernel/panic.c | 21 ++++++++++++++++++++- kernel/sysctl.c | 7 +++++++ kernel/sysctl_binary.c | 1 + 9 files changed, 62 insertions(+), 3 deletions(-)Documentation/kdump/kdump.txt +0
-0@@ -471,6 +471,13 @@ format. Crash is available on Dave Anderson's site at the following URL: http://people.redhat.com/~anderson/
Quoted 9 lines
Documentation/kdump/kdump.txt format. Crash is available on Dave Anderson's site at the following URL: · line 480
Quoted 7 lines
Documentation/kdump/kdump.txt +7
-0+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.What about during early boot?
Hi Rusty,
I really don't have a use case for this in early boot. The kernel boots, the initramfs, and then we run whatever init (systemd in my case). A systemd script configures kexec for kdump and that point kdump is "armed". Doing a bug_on_warn before this will simply result in a panicked system. I don't get any "new" information FWIW as I get a stack trace, etc., in both the WARN() and BUG() cases.
Quoted 3 lines
I'd recommend you use
core_param(). Less code, and can be set on commandline.
Is that a general request, or is it dependent on the answer above? Of course I have no problem doing it either way.
P.
Quoted 19 lines · Prarit Bhargava
Quoted 8 lines · Rusty Russell
Quoted 5 lines · Prarit Bhargava
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.What about during early boot?
Hi Rusty,
I really don't have a use case for this in early boot. The kernel boots, the initramfs, and then we run whatever init (systemd in my case). A systemd script configures kexec for kdump and that point kdump is "armed". Doing a
bug_on_warnbefore this will simply result in a panicked system. I don't get any "new" information FWIW as I get a stack trace, etc., in both theWARN()andBUG()cases.Quoted 1 line
Quoted 5 lines
Quoted 2 lines
I'd recommend you use
core_param(). Less code, and can be set on commandline.Is that a general request, or is it dependent on the answer above? Of course I have no problem doing it either way.
Oops, I read your initial patch too lightly: I see you added both a sysctl (which I saw) and an early_param (which I didn't).
I still think it should be a core_param, like so (untested!):
Documentation/kdump/kdump.txt +7 -0
@@ -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, /sys/module/kernel/bug_on_warn can be +set to 1 to achieve the same behaviour. Contact =======
Documentation/kernel-parameters.txt +3 -0
@@ -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.
include/asm-generic/bug.h +10 -2
@@ -75,10 +75,18 @@ extern void warn_slowpath_null(const char *file, const int line); #define __WARN_printf_taint(taint, arg...) \ warn_slowpath_fmt_taint(__FILE__, __LINE__, taint, arg)#else -#define __WARN () __WARN_TAINT(TAINT_WARN) +#define check_bug_on_warn () \ + do { \ + if (bug_on_warn) \ + BUG(); \ + } while (0) + +#define __WARN () \ + do { __WARN_TAINT(TAINT_WARN); check_bug_on_warn(); } while (0) + #define __WARN_printf(arg...) do { printk(arg); __WARN(); } while (0) #define __WARN_printf_taint(taint, arg...) \ - do { printk(arg); __WARN_TAINT(taint); } while (0) + do { printk(arg); __WARN_TAINT(taint); check_bug_on_warn(); } while (0)#endif #ifndef WARN_ON
include/linux/kernel.h +1 -0
@@ -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 bool bug_on_warn;/* * Only to be used by arch init code. If the user over-wrote the default * CONFIG_PANIC_TIMEOUT, honor it.
kernel/panic.c +14 -1
@@ -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; +bool bug_on_warn;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 = false; +BUG (); + } +print_modules ();dump_stack ();print_oops_end_marker ();
@@ -484,6 +496,7 @@ EXPORT_SYMBOL(__stack_chk_fail);core_param (panic, panic_timeout, int,0644 );core_param (pause_on_oops, pause_on_oops, int,0644 ); +core_param (bug_on_warn, bug_on_warn, bool,0644 );static int __init setup_crash_kexec_post_notifiers (char *s) {
Quoted 20 lines · Rusty Russell
Quoted 19 lines · Prarit Bhargava
Quoted 8 lines · Rusty Russell
Quoted 5 lines · Prarit Bhargava
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.What about during early boot?
Hi Rusty,
I really don't have a use case for this in early boot. The kernel boots, the initramfs, and then we run whatever init (systemd in my case). A systemd script configures kexec for kdump and that point kdump is "armed". Doing a
bug_on_warnbefore this will simply result in a panicked system. I don't get any "new" information FWIW as I get a stack trace, etc., in both theWARN()andBUG()cases.Quoted 1 line
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
I'd recommend you use
core_param(). Less code, and can be set on commandline.
Yeah, I was just starting to do this and then I saw Hedi's comment about disabling panic_on_warn during kdump to avoid a situation where the kdump kernel bogus panics on a warn.
So that makes the setup function look like:
static int __init panic_on_warn_setup(char *s)
{
/* Enabling this on a kdump kernel could cause a bogus panic. */
if (!is_kdump_kernel())
panic_on_warn = 1;
return 0;
}early_param("panic_on_warn", panic_on_warn_setup);
... so I dunno if core_param would work here :(. It would have been nice if it did.
P.
Quoted 268 lines · Prarit Bhargava
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 aBUG(). This makes debugging easier in that I can now test the actual image theWARN()was seen on and I do not have to engage in remote debugging.This patch adds a
bug_on_warnkernel parameter, which callsBUG()in thewarn_slowpath_common()path. The function will still print out the location of the warning.An example of the
bug_on_warnoutput:The first line below is from the
WARN_ON()to output the WARN_ON()'s location. After that the newBUG()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_resolvernfs fscache cfg80211 rfkillx86_pkg_temp_thermalintel_powerclampcoretempkvm_intelkvmcrct10dif_pclmulcrc32_pclmulcrc32c_intelghash_clmulni_inteligbiTCO_wdtaesni_inteliTCO_vendor_supportlrw gf128mulsb_edacptpedac_coreglue_helperlpc_ichioatdma pcspkrablk_helperpps_corei2c_i801mfd_corecryptd dca shpchpipmi_siwmiipmi_msghandleracpi_cpufreqnfsdauth_rpcgssnfs_acllockd grace sunrpc xfs libcrc32csr_modcdromsd_modmgag200 syscopyarea sysfillrect sysimgblti2c_algo_bitdrm_kms_helperisci ttm drm libsas ahci libahciscsi_transport_saslibatai2c_coredm_mirrordm_region_hashdm_logdm_modCPU: 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 fc80 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 <[email protected]>Cc Andrew Morton <akpm-de/[email protected]>Cc Rusty Russell <rusty-8n+1lVoiYb80n/[email protected]>Cc "H. Peter Anvin" <[email protected]>Cc Andi Kleen <ak-VuQAYsv1563Yd54FQh9/[email protected]>Cc Masami Hiramatsu <[email protected]>Cc Fabian Frederick <[email protected]>Signed-off-by Prarit Bhargava <[email protected]>[v2]: add
/proc/sys/kernel/bug_on_warn, additional documentation, modify
!slowpath cases--- Documentation/kdump/kdump.txt | 7 +++++++ Documentation/kernel-parameters.txt | 3 +++ Documentation/sysctl/kernel.txt | 12 ++++++++++++ include/asm-generic/bug.h | 12 ++++++++++-- include/linux/kernel.h | 1 + include/uapi/linux/sysctl.h | 1 + kernel/panic.c | 21 ++++++++++++++++++++- kernel/sysctl.c | 7 +++++++ kernel/sysctl_binary.c | 1 + 9 files changed, 62 insertions(+), 3 deletions(-)Documentation/kdump/kdump.txt +7
-0@@ -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 =======Documentation/kernel-parameters.txt +3
-0@@ -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.Documentation/sysctl/kernel.txt +12
-0@@ -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.include/asm-generic/bug.h +10
-2@@ -75,10 +75,18 @@ extern void warn_slowpath_null(const char *file, const int line); #define __WARN_printf_taint(taint, arg...) \ warn_slowpath_fmt_taint(__FILE__, __LINE__, taint, arg)#else -#define __WARN () __WARN_TAINT(TAINT_WARN) +#define check_bug_on_warn () \ + do { \ + if (bug_on_warn) \ + BUG(); \ + } while (0) + +#define __WARN () \ + do { __WARN_TAINT(TAINT_WARN); check_bug_on_warn(); } while (0) + #define __WARN_printf(arg...) do { printk(arg); __WARN(); } while (0) #define __WARN_printf_taint(taint, arg...) \ - do { printk(arg); __WARN_TAINT(taint); } while (0) + do { printk(arg); __WARN_TAINT(taint); check_bug_on_warn(); } while (0)#endif #ifndef WARN_ON include/linux/kernel.h +1
-0@@ -422,6 +422,7 @@ 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. include/uapi/linux/sysctl.h +1
-0@@ -153,6 +153,7 @@ enumKERN_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 */ };kernel/panic.c +20
-1@@ -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;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);kernel/sysctl.c +0
-0
kernel/sysctl.c static struct ctl_table kern_table[] = { · line 1112
Quoted 10 lines
kernel/sysctl.c +6
-0@@ -1103,6 +1103,13 @@ 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,
How about use:
+ .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one,
Document says as follows but it can set other vaule.
kernel/sysctl.c static struct ctl_table kern_table[] = { · line 1115
Quoted 3 lines
kernel/sysctl.c +3
-0+0: only WARN(), default behaviour. + +1: call BUG() after printing out WARN() location.
Thanks,
Yasuaki Ishimatsu
Quoted 17 lines
kernel/sysctl.c +1
-0+ }, { } };kernel/sysctl_binary.c +1
-0@@ -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" }, {} };