mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-13 22:14:20 +08:00
3370155737
We have a number of systems industry-wide that have a subset of their
functionality that works as follows:
1. Receive a message from local kmsg, serial console, or netconsole;
2. Apply a set of rules to classify the message;
3. Do something based on this classification (like scheduling a
remediation for the machine), rinse, and repeat.
As a couple of examples of places we have this implemented just inside
Facebook, although this isn't a Facebook-specific problem, we have this
inside our netconsole processing (for alarm classification), and as part
of our machine health checking. We use these messages to determine
fairly important metrics around production health, and it's important
that we get them right.
While for some kinds of issues we have counters, tracepoints, or metrics
with a stable interface which can reliably indicate the issue, in order
to react to production issues quickly we need to work with the interface
which most kernel developers naturally use when developing: printk.
Most production issues come from unexpected phenomena, and as such
usually the code in question doesn't have easily usable tracepoints or
other counters available for the specific problem being mitigated. We
have a number of lines of monitoring defence against problems in
production (host metrics, process metrics, service metrics, etc), and
where it's not feasible to reliably monitor at another level, this kind
of pragmatic netconsole monitoring is essential.
As one would expect, monitoring using printk is rather brittle for a
number of reasons -- most notably that the message might disappear
entirely in a new version of the kernel, or that the message may change
in some way that the regex or other classification methods start to
silently fail.
One factor that makes this even harder is that, under normal operation,
many of these messages are never expected to be hit. For example, there
may be a rare hardware bug which one wants to detect if it was to ever
happen again, but its recurrence is not likely or anticipated. This
precludes using something like checking whether the printk in question
was printed somewhere fleetwide recently to determine whether the
message in question is still present or not, since we don't anticipate
that it should be printed anywhere, but still need to monitor for its
future presence in the long-term.
This class of issue has happened on a number of occasions, causing
unhealthy machines with hardware issues to remain in production for
longer than ideal. As a recent example, some monitoring around
blk_update_request fell out of date and caused semi-broken machines to
remain in production for longer than would be desirable.
Searching through the codebase to find the message is also extremely
fragile, because many of the messages are further constructed beyond
their callsite (eg. btrfs_printk and other module-specific wrappers,
each with their own functionality). Even if they aren't, guessing the
format and formulation of the underlying message based on the aesthetics
of the message emitted is not a recipe for success at scale, and our
previous issues with fleetwide machine health checking demonstrate as
much.
This provides a solution to the issue of silently changed or deleted
printks: we record pointers to all printk format strings known at
compile time into a new .printk_index section, both in vmlinux and
modules. At runtime, this can then be iterated by looking at
<debugfs>/printk/index/<module>, which emits the following format, both
readable by humans and able to be parsed by machines:
$ head -1 vmlinux; shuf -n 5 vmlinux
# <level[,flags]> filename:line function "format"
<5> block/blk-settings.c:661 disk_stack_limits "%s: Warning: Device %s is misaligned\n"
<4> kernel/trace/trace.c:8296 trace_create_file "Could not create tracefs '%s' entry\n"
<6> arch/x86/kernel/hpet.c:144 _hpet_print_config "hpet: %s(%d):\n"
<6> init/do_mounts.c:605 prepare_namespace "Waiting for root device %s...\n"
<6> drivers/acpi/osl.c:1410 acpi_no_auto_serialize_setup "ACPI: auto-serialization disabled\n"
This mitigates the majority of cases where we have a highly-specific
printk which we want to match on, as we can now enumerate and check
whether the format changed or the printk callsite disappeared entirely
in userspace. This allows us to catch changes to printks we monitor
earlier and decide what to do about it before it becomes problematic.
There is no additional runtime cost for printk callers or printk itself,
and the assembly generated is exactly the same.
Signed-off-by: Chris Down <chris@chrisdown.name>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Jessica Yu <jeyu@kernel.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: John Ogness <john.ogness@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kees Cook <keescook@chromium.org>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Tested-by: Petr Mladek <pmladek@suse.com>
Reported-by: kernel test robot <lkp@intel.com>
Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Acked-by: Jessica Yu <jeyu@kernel.org> # for module.{c,h}
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/e42070983637ac5e384f17fbdbe86d19c7b212a5.1623775748.git.chris@chrisdown.name
124 lines
3.1 KiB
ArmAsm
124 lines
3.1 KiB
ArmAsm
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* linux/arch/arm/lib/backtrace.S
|
|
*
|
|
* Copyright (C) 1995, 1996 Russell King
|
|
*
|
|
* 27/03/03 Ian Molton Clean up CONFIG_CPU
|
|
*/
|
|
#include <linux/kern_levels.h>
|
|
#include <linux/linkage.h>
|
|
#include <asm/assembler.h>
|
|
.text
|
|
|
|
@ fp is 0 or stack frame
|
|
|
|
#define frame r4
|
|
#define sv_fp r5
|
|
#define sv_pc r6
|
|
#define mask r7
|
|
#define offset r8
|
|
#define loglvl r9
|
|
|
|
ENTRY(c_backtrace)
|
|
|
|
#if !defined(CONFIG_FRAME_POINTER) || !defined(CONFIG_PRINTK)
|
|
ret lr
|
|
ENDPROC(c_backtrace)
|
|
#else
|
|
stmfd sp!, {r4 - r9, lr} @ Save an extra register so we have a location...
|
|
movs frame, r0 @ if frame pointer is zero
|
|
beq no_frame @ we have no stack frames
|
|
mov loglvl, r2
|
|
|
|
tst r1, #0x10 @ 26 or 32-bit mode?
|
|
ARM( moveq mask, #0xfc000003 )
|
|
THUMB( moveq mask, #0xfc000000 )
|
|
THUMB( orreq mask, #0x03 )
|
|
movne mask, #0 @ mask for 32-bit
|
|
|
|
1: stmfd sp!, {pc} @ calculate offset of PC stored
|
|
ldr r0, [sp], #4 @ by stmfd for this CPU
|
|
adr r1, 1b
|
|
sub offset, r0, r1
|
|
|
|
/*
|
|
* Stack frame layout:
|
|
* optionally saved caller registers (r4 - r10)
|
|
* saved fp
|
|
* saved sp
|
|
* saved lr
|
|
* frame => saved pc
|
|
* optionally saved arguments (r0 - r3)
|
|
* saved sp => <next word>
|
|
*
|
|
* Functions start with the following code sequence:
|
|
* mov ip, sp
|
|
* stmfd sp!, {r0 - r3} (optional)
|
|
* corrected pc => stmfd sp!, {..., fp, ip, lr, pc}
|
|
*/
|
|
for_each_frame: tst frame, mask @ Check for address exceptions
|
|
bne no_frame
|
|
|
|
1001: ldr sv_pc, [frame, #0] @ get saved pc
|
|
1002: ldr sv_fp, [frame, #-12] @ get saved fp
|
|
|
|
sub sv_pc, sv_pc, offset @ Correct PC for prefetching
|
|
bic sv_pc, sv_pc, mask @ mask PC/LR for the mode
|
|
|
|
1003: ldr r2, [sv_pc, #-4] @ if stmfd sp!, {args} exists,
|
|
ldr r3, .Ldsi+4 @ adjust saved 'pc' back one
|
|
teq r3, r2, lsr #11 @ instruction
|
|
subne r0, sv_pc, #4 @ allow for mov
|
|
subeq r0, sv_pc, #8 @ allow for mov + stmia
|
|
|
|
ldr r1, [frame, #-4] @ get saved lr
|
|
mov r2, frame
|
|
bic r1, r1, mask @ mask PC/LR for the mode
|
|
mov r3, loglvl
|
|
bl dump_backtrace_entry
|
|
|
|
ldr r1, [sv_pc, #-4] @ if stmfd sp!, {args} exists,
|
|
ldr r3, .Ldsi+4
|
|
teq r3, r1, lsr #11
|
|
ldreq r0, [frame, #-8] @ get sp
|
|
subeq r0, r0, #4 @ point at the last arg
|
|
mov r2, loglvl
|
|
bleq dump_backtrace_stm @ dump saved registers
|
|
|
|
1004: ldr r1, [sv_pc, #0] @ if stmfd sp!, {..., fp, ip, lr, pc}
|
|
ldr r3, .Ldsi @ instruction exists,
|
|
teq r3, r1, lsr #11
|
|
subeq r0, frame, #16
|
|
mov r2, loglvl
|
|
bleq dump_backtrace_stm @ dump saved registers
|
|
|
|
teq sv_fp, #0 @ zero saved fp means
|
|
beq no_frame @ no further frames
|
|
|
|
cmp sv_fp, frame @ next frame must be
|
|
mov frame, sv_fp @ above the current frame
|
|
bhi for_each_frame
|
|
|
|
1006: adr r0, .Lbad
|
|
mov r1, loglvl
|
|
mov r2, frame
|
|
bl _printk
|
|
no_frame: ldmfd sp!, {r4 - r9, pc}
|
|
ENDPROC(c_backtrace)
|
|
|
|
.pushsection __ex_table,"a"
|
|
.align 3
|
|
.long 1001b, 1006b
|
|
.long 1002b, 1006b
|
|
.long 1003b, 1006b
|
|
.long 1004b, 1006b
|
|
.popsection
|
|
|
|
.Lbad: .asciz "%sBacktrace aborted due to bad frame pointer <%p>\n"
|
|
.align
|
|
.Ldsi: .word 0xe92dd800 >> 11 @ stmfd sp!, {... fp, ip, lr, pc}
|
|
.word 0xe92d0000 >> 11 @ stmfd sp!, {}
|
|
|
|
#endif
|