linux/kernel/kallsyms.c

963 lines
23 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* kallsyms.c: in-kernel printing of symbolic oopses and stack traces.
*
* Rewritten and vastly simplified by Rusty Russell for in-kernel
* module loader:
* Copyright 2002 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation
*
* ChangeLog:
*
* (25/Aug/2004) Paulo Marques <pmarques@grupopie.com>
* Changed the compression method from stem compression to "table lookup"
* compression (see scripts/kallsyms.c for a more complete description)
*/
#include <linux/kallsyms.h>
#include <linux/init.h>
#include <linux/seq_file.h>
#include <linux/fs.h>
#include <linux/kdb.h>
#include <linux/err.h>
#include <linux/proc_fs.h>
#include <linux/sched.h> /* for cond_resched */
#include <linux/ctype.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
#include <linux/filter.h>
ftrace: Save module init functions kallsyms symbols for tracing If function tracing is active when the module init functions are freed, then store them to be referenced by kallsyms. As module init functions can now be traced on module load, they were useless: ># echo ':mod:snd_seq' > set_ftrace_filter ># echo function > current_tracer ># modprobe snd_seq ># cat trace # tracer: function # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / delay # TASK-PID CPU# |||| TIMESTAMP FUNCTION # | | | |||| | | modprobe-2786 [000] .... 3189.037874: 0xffffffffa0860000 <-do_one_initcall modprobe-2786 [000] .... 3189.037876: 0xffffffffa086004d <-0xffffffffa086000f modprobe-2786 [000] .... 3189.037876: 0xffffffffa086010d <-0xffffffffa0860018 modprobe-2786 [000] .... 3189.037877: 0xffffffffa086011a <-0xffffffffa0860021 modprobe-2786 [000] .... 3189.037877: 0xffffffffa0860080 <-0xffffffffa086002a modprobe-2786 [000] .... 3189.039523: 0xffffffffa0860400 <-0xffffffffa0860033 modprobe-2786 [000] .... 3189.039523: 0xffffffffa086038a <-0xffffffffa086041c modprobe-2786 [000] .... 3189.039591: 0xffffffffa086038a <-0xffffffffa0860436 modprobe-2786 [000] .... 3189.039657: 0xffffffffa086038a <-0xffffffffa0860450 modprobe-2786 [000] .... 3189.039719: 0xffffffffa0860127 <-0xffffffffa086003c modprobe-2786 [000] .... 3189.039742: snd_seq_create_kernel_client <-0xffffffffa08601f6 When the output is shown, the kallsyms for the module init functions have already been freed, and the output of the trace can not convert them to their function names. Now this looks like this: # tracer: function # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / delay # TASK-PID CPU# |||| TIMESTAMP FUNCTION # | | | |||| | | modprobe-2463 [002] .... 174.243237: alsa_seq_init <-do_one_initcall modprobe-2463 [002] .... 174.243239: client_init_data <-alsa_seq_init modprobe-2463 [002] .... 174.243240: snd_sequencer_memory_init <-alsa_seq_init modprobe-2463 [002] .... 174.243240: snd_seq_queues_init <-alsa_seq_init modprobe-2463 [002] .... 174.243240: snd_sequencer_device_init <-alsa_seq_init modprobe-2463 [002] .... 174.244860: snd_seq_info_init <-alsa_seq_init modprobe-2463 [002] .... 174.244861: create_info_entry <-snd_seq_info_init modprobe-2463 [002] .... 174.244936: create_info_entry <-snd_seq_info_init modprobe-2463 [002] .... 174.245003: create_info_entry <-snd_seq_info_init modprobe-2463 [002] .... 174.245072: snd_seq_system_client_init <-alsa_seq_init modprobe-2463 [002] .... 174.245094: snd_seq_create_kernel_client <-snd_seq_system_client_init Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-09-01 20:35:38 +08:00
#include <linux/ftrace.h>
#include <linux/kprobes.h>
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
#include <linux/build_bug.h>
#include <linux/compiler.h>
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/bsearch.h>
#include <linux/btf_ids.h>
kallsyms: move declarations to internal header Patch series "Expose kallsyms data in vmcoreinfo note". The kernel can be configured to contain a lot of introspection or debugging information built-in, such as ORC for unwinding stack traces, BTF for type information, and of course kallsyms. Debuggers could use this information to navigate a core dump or live system, but they need to be able to find it. This patch series adds the necessary symbols into vmcoreinfo, which would allow a debugger to find and interpret the kallsyms table. Using the kallsyms data, the debugger can then lookup any symbol, allowing it to find ORC, BTF, or any other useful data. This would allow a live kernel, or core dump, to be debugged without any DWARF debuginfo. This is useful for many cases: the debuginfo may not have been generated, or you may not want to deploy the large files everywhere you need them. I've demonstrated a proof of concept for this at LSF/MM+BPF during a lighting talk. Using a work-in-progress branch of the drgn debugger, and an extended set of BTF generated by a patched version of dwarves, I've been able to open a core dump without any DWARF info and do basic tasks such as enumerating slab caches, block devices, tasks, and doing backtraces. I hope this series can be a first step toward a new possibility of "DWARFless debugging". Related discussion around the BTF side of this: https://lore.kernel.org/bpf/586a6288-704a-f7a7-b256-e18a675927df@oracle.com/T/#u Some work-in-progress branches using this feature: https://github.com/brenns10/dwarves/tree/remove_percpu_restriction_1 https://github.com/brenns10/drgn/tree/kallsyms_plus_btf This patch (of 2): To include kallsyms data in the vmcoreinfo note, we must make the symbol declarations visible outside of kallsyms.c. Move these to a new internal header file. Link: https://lkml.kernel.org/r/20220517000508.777145-1-stephen.s.brennan@oracle.com Link: https://lkml.kernel.org/r/20220517000508.777145-2-stephen.s.brennan@oracle.com Signed-off-by: Stephen Brennan <stephen.s.brennan@oracle.com> Acked-by: Baoquan He <bhe@redhat.com> Cc: Nick Desaulniers <ndesaulniers@google.com> Cc: Dave Young <dyoung@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Stephen Boyd <swboyd@chromium.org> Cc: Bixuan Cui <cuibixuan@huawei.com> Cc: David Vernet <void@manifault.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Sami Tolvanen <samitolvanen@google.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-05-17 08:05:07 +08:00
#include "kallsyms_internal.h"
/*
* Expand a compressed symbol data into the resulting uncompressed string,
* if uncompressed string is too long (>= maxlen), it will be truncated,
* given the offset to where the symbol is in the compressed stream.
*/
static unsigned int kallsyms_expand_symbol(unsigned int off,
char *result, size_t maxlen)
{
int len, skipped_first = 0;
const char *tptr;
const u8 *data;
/* Get the compressed symbol length from the first symbol byte. */
data = &kallsyms_names[off];
len = *data;
data++;
off++;
/* If MSB is 1, it is a "big" symbol, so needs an additional byte. */
if ((len & 0x80) != 0) {
len = (len & 0x7F) | (*data << 7);
data++;
off++;
}
/*
* Update the offset to return the offset for the next symbol on
* the compressed stream.
*/
off += len;
/*
* For every byte on the compressed symbol data, copy the table
* entry for that byte.
*/
while (len) {
tptr = &kallsyms_token_table[kallsyms_token_index[*data]];
data++;
len--;
while (*tptr) {
if (skipped_first) {
if (maxlen <= 1)
goto tail;
*result = *tptr;
result++;
maxlen--;
} else
skipped_first = 1;
tptr++;
}
}
tail:
if (maxlen)
*result = '\0';
/* Return to offset to the next symbol. */
return off;
}
/*
* Get symbol type information. This is encoded as a single char at the
* beginning of the symbol name.
*/
static char kallsyms_get_symbol_type(unsigned int off)
{
/*
* Get just the first code, look it up in the token table,
* and return the first char from this token.
*/
return kallsyms_token_table[kallsyms_token_index[kallsyms_names[off + 1]]];
}
/*
* Find the offset on the compressed stream given and index in the
* kallsyms array.
*/
static unsigned int get_symbol_offset(unsigned long pos)
{
const u8 *name;
int i, len;
/*
* Use the closest marker we have. We have markers every 256 positions,
* so that should be close enough.
*/
name = &kallsyms_names[kallsyms_markers[pos >> 8]];
/*
* Sequentially scan all the symbols up to the point we're searching
* for. Every symbol is stored in a [<len>][<len> bytes of data] format,
* so we just need to add the len to the current pointer for every
* symbol we wish to skip.
*/
for (i = 0; i < (pos & 0xFF); i++) {
len = *name;
/*
* If MSB is 1, it is a "big" symbol, so we need to look into
* the next byte (and skip it, too).
*/
if ((len & 0x80) != 0)
len = ((len & 0x7F) | (name[1] << 7)) + 1;
name = name + len + 1;
}
return name - kallsyms_names;
}
kallsyms: Add self-test facility Added test cases for basic functions and performance of functions kallsyms_lookup_name(), kallsyms_on_each_symbol() and kallsyms_on_each_match_symbol(). It also calculates the compression rate of the kallsyms compression algorithm for the current symbol set. The basic functions test begins by testing a set of symbols whose address values are known. Then, traverse all symbol addresses and find the corresponding symbol name based on the address. It's impossible to determine whether these addresses are correct, but we can use the above three functions along with the addresses to test each other. Due to the traversal operation of kallsyms_on_each_symbol() is too slow, only 60 symbols can be tested in one second, so let it test on average once every 128 symbols. The other two functions validate all symbols. If the basic functions test is passed, print only performance test results. If the test fails, print error information, but do not perform subsequent performance tests. Start self-test automatically after system startup if CONFIG_KALLSYMS_SELFTEST=y. Example of output content: (prefix 'kallsyms_selftest:' is omitted start --------------------------------------------------------- | nr_symbols | compressed size | original size | ratio(%) | |---------------------------------------------------------| | 107543 | 1357912 | 2407433 | 56.40 | --------------------------------------------------------- kallsyms_lookup_name() looked up 107543 symbols The time spent on each symbol is (ns): min=630, max=35295, avg=7353 kallsyms_on_each_symbol() traverse all: 11782628 ns kallsyms_on_each_match_symbol() traverse all: 9261 ns finish Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com> Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2022-11-15 16:33:48 +08:00
unsigned long kallsyms_sym_address(int idx)
kallsyms: add support for relative offsets in kallsyms address table Similar to how relative extables are implemented, it is possible to emit the kallsyms table in such a way that it contains offsets relative to some anchor point in the kernel image rather than absolute addresses. On 64-bit architectures, it cuts the size of the kallsyms address table in half, since offsets between kernel symbols can typically be expressed in 32 bits. This saves several hundreds of kilobytes of permanent .rodata on average. In addition, the kallsyms address table is no longer subject to dynamic relocation when CONFIG_RELOCATABLE is in effect, so the relocation work done after decompression now doesn't have to do relocation updates for all these values. This saves up to 24 bytes (i.e., the size of a ELF64 RELA relocation table entry) per value, which easily adds up to a couple of megabytes of uncompressed __init data on ppc64 or arm64. Even if these relocation entries typically compress well, the combined size reduction of 2.8 MB uncompressed for a ppc64_defconfig build (of which 2.4 MB is __init data) results in a ~500 KB space saving in the compressed image. Since it is useful for some architectures (like x86) to retain the ability to emit absolute values as well, this patch also adds support for capturing both absolute and relative values when KALLSYMS_ABSOLUTE_PERCPU is in effect, by emitting absolute per-cpu addresses as positive 32-bit values, and addresses relative to the lowest encountered relative symbol as negative values, which are subtracted from the runtime address of this base symbol to produce the actual address. Support for the above is enabled by default for all architectures except IA-64 and Tile-GX, whose symbols are too far apart to capture in this manner. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Tested-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Kees Cook <keescook@chromium.org> Tested-by: Kees Cook <keescook@chromium.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Ingo Molnar <mingo@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michal Marek <mmarek@suse.cz> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-16 05:58:19 +08:00
{
if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
return kallsyms_addresses[idx];
/* values are unsigned offsets if --absolute-percpu is not in effect */
if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU))
return kallsyms_relative_base + (u32)kallsyms_offsets[idx];
/* ...otherwise, positive offsets are absolute values */
if (kallsyms_offsets[idx] >= 0)
return kallsyms_offsets[idx];
/* ...and negative offsets are relative to kallsyms_relative_base - 1 */
return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
}
static bool cleanup_symbol_name(char *s)
{
char *res;
if (!IS_ENABLED(CONFIG_LTO_CLANG))
return false;
/*
* LLVM appends various suffixes for local functions and variables that
* must be promoted to global scope as part of LTO. This can break
* hooking of static functions with kprobes. '.' is not a valid
kallsyms: strip LTO-only suffixes from promoted global functions Commit 6eb4bd92c1ce ("kallsyms: strip LTO suffixes from static functions") stripped all function/variable suffixes started with '.' regardless of whether those suffixes are generated at LTO mode or not. In fact, as far as I know, in LTO mode, when a static function/variable is promoted to the global scope, '.llvm.<...>' suffix is added. The existing mechanism breaks live patch for a LTO kernel even if no <symbol>.llvm.<...> symbols are involved. For example, for the following kernel symbols: $ grep bpf_verifier_vlog /proc/kallsyms ffffffff81549f60 t bpf_verifier_vlog ffffffff8268b430 d bpf_verifier_vlog._entry ffffffff8282a958 d bpf_verifier_vlog._entry_ptr ffffffff82e12a1f d bpf_verifier_vlog.__already_done 'bpf_verifier_vlog' is a static function. '_entry', '_entry_ptr' and '__already_done' are static variables used inside 'bpf_verifier_vlog', so llvm promotes them to file-level static with prefix 'bpf_verifier_vlog.'. Note that the func-level to file-level static function promotion also happens without LTO. Given a symbol name 'bpf_verifier_vlog', with LTO kernel, current mechanism will return 4 symbols to live patch subsystem which current live patching subsystem cannot handle it. With non-LTO kernel, only one symbol is returned. In [1], we have a lengthy discussion, the suggestion is to separate two cases: (1). new symbols with suffix which are generated regardless of whether LTO is enabled or not, and (2). new symbols with suffix generated only when LTO is enabled. The cleanup_symbol_name() should only remove suffixes for case (2). Case (1) should not be changed so it can work uniformly with or without LTO. This patch removed LTO-only suffix '.llvm.<...>' so live patching and tracing should work the same way for non-LTO kernel. The cleanup_symbol_name() in scripts/kallsyms.c is also changed to have the same filtering pattern so both kernel and kallsyms tool have the same expectation on the order of symbols. [1] https://lore.kernel.org/live-patching/20230615170048.2382735-1-song@kernel.org/T/#u Fixes: 6eb4bd92c1ce ("kallsyms: strip LTO suffixes from static functions") Reported-by: Song Liu <song@kernel.org> Signed-off-by: Yonghong Song <yhs@fb.com> Reviewed-by: Zhen Lei <thunder.leizhen@huawei.com> Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Acked-by: Song Liu <song@kernel.org> Link: https://lore.kernel.org/r/20230628181926.4102448-1-yhs@fb.com Signed-off-by: Kees Cook <keescook@chromium.org>
2023-06-29 02:19:26 +08:00
* character in an identifier in C. Suffixes only in LLVM LTO observed:
* - foo.llvm.[0-9a-f]+
*/
kallsyms: strip LTO-only suffixes from promoted global functions Commit 6eb4bd92c1ce ("kallsyms: strip LTO suffixes from static functions") stripped all function/variable suffixes started with '.' regardless of whether those suffixes are generated at LTO mode or not. In fact, as far as I know, in LTO mode, when a static function/variable is promoted to the global scope, '.llvm.<...>' suffix is added. The existing mechanism breaks live patch for a LTO kernel even if no <symbol>.llvm.<...> symbols are involved. For example, for the following kernel symbols: $ grep bpf_verifier_vlog /proc/kallsyms ffffffff81549f60 t bpf_verifier_vlog ffffffff8268b430 d bpf_verifier_vlog._entry ffffffff8282a958 d bpf_verifier_vlog._entry_ptr ffffffff82e12a1f d bpf_verifier_vlog.__already_done 'bpf_verifier_vlog' is a static function. '_entry', '_entry_ptr' and '__already_done' are static variables used inside 'bpf_verifier_vlog', so llvm promotes them to file-level static with prefix 'bpf_verifier_vlog.'. Note that the func-level to file-level static function promotion also happens without LTO. Given a symbol name 'bpf_verifier_vlog', with LTO kernel, current mechanism will return 4 symbols to live patch subsystem which current live patching subsystem cannot handle it. With non-LTO kernel, only one symbol is returned. In [1], we have a lengthy discussion, the suggestion is to separate two cases: (1). new symbols with suffix which are generated regardless of whether LTO is enabled or not, and (2). new symbols with suffix generated only when LTO is enabled. The cleanup_symbol_name() should only remove suffixes for case (2). Case (1) should not be changed so it can work uniformly with or without LTO. This patch removed LTO-only suffix '.llvm.<...>' so live patching and tracing should work the same way for non-LTO kernel. The cleanup_symbol_name() in scripts/kallsyms.c is also changed to have the same filtering pattern so both kernel and kallsyms tool have the same expectation on the order of symbols. [1] https://lore.kernel.org/live-patching/20230615170048.2382735-1-song@kernel.org/T/#u Fixes: 6eb4bd92c1ce ("kallsyms: strip LTO suffixes from static functions") Reported-by: Song Liu <song@kernel.org> Signed-off-by: Yonghong Song <yhs@fb.com> Reviewed-by: Zhen Lei <thunder.leizhen@huawei.com> Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Acked-by: Song Liu <song@kernel.org> Link: https://lore.kernel.org/r/20230628181926.4102448-1-yhs@fb.com Signed-off-by: Kees Cook <keescook@chromium.org>
2023-06-29 02:19:26 +08:00
res = strstr(s, ".llvm.");
if (res) {
*res = '\0';
return true;
}
return false;
}
static int compare_symbol_name(const char *name, char *namebuf)
{
int ret;
ret = strcmp(name, namebuf);
if (!ret)
return ret;
if (cleanup_symbol_name(namebuf) && !strcmp(name, namebuf))
return 0;
return ret;
}
static unsigned int get_symbol_seq(int index)
{
unsigned int i, seq = 0;
for (i = 0; i < 3; i++)
seq = (seq << 8) | kallsyms_seqs_of_names[3 * index + i];
return seq;
}
static int kallsyms_lookup_names(const char *name,
unsigned int *start,
unsigned int *end)
{
int ret;
int low, mid, high;
unsigned int seq, off;
char namebuf[KSYM_NAME_LEN];
low = 0;
high = kallsyms_num_syms - 1;
while (low <= high) {
mid = low + (high - low) / 2;
seq = get_symbol_seq(mid);
off = get_symbol_offset(seq);
kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
ret = compare_symbol_name(name, namebuf);
if (ret > 0)
low = mid + 1;
else if (ret < 0)
high = mid - 1;
else
break;
}
if (low > high)
return -ESRCH;
low = mid;
while (low) {
seq = get_symbol_seq(low - 1);
off = get_symbol_offset(seq);
kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
if (compare_symbol_name(name, namebuf))
break;
low--;
}
*start = low;
if (end) {
high = mid;
while (high < kallsyms_num_syms - 1) {
seq = get_symbol_seq(high + 1);
off = get_symbol_offset(seq);
kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
if (compare_symbol_name(name, namebuf))
break;
high++;
}
*end = high;
}
return 0;
}
/* Lookup the address for this symbol. Returns 0 if not found. */
unsigned long kallsyms_lookup_name(const char *name)
{
int ret;
unsigned int i;
/* Skip the search for empty string. */
if (!*name)
return 0;
ret = kallsyms_lookup_names(name, &i, NULL);
if (!ret)
return kallsyms_sym_address(get_symbol_seq(i));
return module_kallsyms_lookup_name(name);
}
/*
* Iterate over all symbols in vmlinux. For symbols from modules use
* module_kallsyms_on_each_symbol instead.
*/
int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long),
void *data)
{
char namebuf[KSYM_NAME_LEN];
unsigned long i;
unsigned int off;
int ret;
for (i = 0, off = 0; i < kallsyms_num_syms; i++) {
off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
ret = fn(data, namebuf, kallsyms_sym_address(i));
if (ret != 0)
return ret;
livepatch: Avoid CPU hogging with cond_resched When initializing a 'struct klp_object' in klp_init_object_loaded(), and performing relocations in klp_resolve_symbols(), klp_find_object_symbol() is invoked to look up the address of a symbol in an already-loaded module (or vmlinux). This, in turn, calls kallsyms_on_each_symbol() or module_kallsyms_on_each_symbol() to find the address of the symbol that is being patched. It turns out that symbol lookups often take up the most CPU time when enabling and disabling a patch, and may hog the CPU and cause other tasks on that CPU's runqueue to starve -- even in paths where interrupts are enabled. For example, under certain workloads, enabling a KLP patch with many objects or functions may cause ksoftirqd to be starved, and thus for interrupts to be backlogged and delayed. This may end up causing TCP retransmits on the host where the KLP patch is being applied, and in general, may cause any interrupts serviced by softirqd to be delayed while the patch is being applied. So as to ensure that kallsyms_on_each_symbol() does not end up hogging the CPU, this patch adds a call to cond_resched() in kallsyms_on_each_symbol() and module_kallsyms_on_each_symbol(), which are invoked when doing a symbol lookup in vmlinux and a module respectively. Without this patch, if a live-patch is applied on a 36-core Intel host with heavy TCP traffic, a ~10x spike is observed in TCP retransmits while the patch is being applied. Additionally, collecting sched events with perf indicates that ksoftirqd is awakened ~1.3 seconds before it's eventually scheduled. With the patch, no increase in TCP retransmit events is observed, and ksoftirqd is scheduled shortly after it's awakened. Signed-off-by: David Vernet <void@manifault.com> Acked-by: Miroslav Benes <mbenes@suse.cz> Acked-by: Song Liu <song@kernel.org> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/20211229215646.830451-1-void@manifault.com
2021-12-30 05:56:47 +08:00
cond_resched();
}
return 0;
}
int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long),
const char *name, void *data)
{
int ret;
unsigned int i, start, end;
ret = kallsyms_lookup_names(name, &start, &end);
if (ret)
return 0;
for (i = start; !ret && i <= end; i++) {
ret = fn(data, kallsyms_sym_address(get_symbol_seq(i)));
cond_resched();
}
return ret;
}
static unsigned long get_symbol_pos(unsigned long addr,
unsigned long *symbolsize,
unsigned long *offset)
{
unsigned long symbol_start = 0, symbol_end = 0;
unsigned long i, low, high, mid;
/* This kernel should never had been booted. */
kallsyms: add support for relative offsets in kallsyms address table Similar to how relative extables are implemented, it is possible to emit the kallsyms table in such a way that it contains offsets relative to some anchor point in the kernel image rather than absolute addresses. On 64-bit architectures, it cuts the size of the kallsyms address table in half, since offsets between kernel symbols can typically be expressed in 32 bits. This saves several hundreds of kilobytes of permanent .rodata on average. In addition, the kallsyms address table is no longer subject to dynamic relocation when CONFIG_RELOCATABLE is in effect, so the relocation work done after decompression now doesn't have to do relocation updates for all these values. This saves up to 24 bytes (i.e., the size of a ELF64 RELA relocation table entry) per value, which easily adds up to a couple of megabytes of uncompressed __init data on ppc64 or arm64. Even if these relocation entries typically compress well, the combined size reduction of 2.8 MB uncompressed for a ppc64_defconfig build (of which 2.4 MB is __init data) results in a ~500 KB space saving in the compressed image. Since it is useful for some architectures (like x86) to retain the ability to emit absolute values as well, this patch also adds support for capturing both absolute and relative values when KALLSYMS_ABSOLUTE_PERCPU is in effect, by emitting absolute per-cpu addresses as positive 32-bit values, and addresses relative to the lowest encountered relative symbol as negative values, which are subtracted from the runtime address of this base symbol to produce the actual address. Support for the above is enabled by default for all architectures except IA-64 and Tile-GX, whose symbols are too far apart to capture in this manner. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Tested-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Kees Cook <keescook@chromium.org> Tested-by: Kees Cook <keescook@chromium.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Ingo Molnar <mingo@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michal Marek <mmarek@suse.cz> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-16 05:58:19 +08:00
if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
BUG_ON(!kallsyms_addresses);
else
BUG_ON(!kallsyms_offsets);
/* Do a binary search on the sorted kallsyms_addresses array. */
low = 0;
high = kallsyms_num_syms;
while (high - low > 1) {
mid = low + (high - low) / 2;
kallsyms: add support for relative offsets in kallsyms address table Similar to how relative extables are implemented, it is possible to emit the kallsyms table in such a way that it contains offsets relative to some anchor point in the kernel image rather than absolute addresses. On 64-bit architectures, it cuts the size of the kallsyms address table in half, since offsets between kernel symbols can typically be expressed in 32 bits. This saves several hundreds of kilobytes of permanent .rodata on average. In addition, the kallsyms address table is no longer subject to dynamic relocation when CONFIG_RELOCATABLE is in effect, so the relocation work done after decompression now doesn't have to do relocation updates for all these values. This saves up to 24 bytes (i.e., the size of a ELF64 RELA relocation table entry) per value, which easily adds up to a couple of megabytes of uncompressed __init data on ppc64 or arm64. Even if these relocation entries typically compress well, the combined size reduction of 2.8 MB uncompressed for a ppc64_defconfig build (of which 2.4 MB is __init data) results in a ~500 KB space saving in the compressed image. Since it is useful for some architectures (like x86) to retain the ability to emit absolute values as well, this patch also adds support for capturing both absolute and relative values when KALLSYMS_ABSOLUTE_PERCPU is in effect, by emitting absolute per-cpu addresses as positive 32-bit values, and addresses relative to the lowest encountered relative symbol as negative values, which are subtracted from the runtime address of this base symbol to produce the actual address. Support for the above is enabled by default for all architectures except IA-64 and Tile-GX, whose symbols are too far apart to capture in this manner. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Tested-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Kees Cook <keescook@chromium.org> Tested-by: Kees Cook <keescook@chromium.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Ingo Molnar <mingo@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michal Marek <mmarek@suse.cz> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-16 05:58:19 +08:00
if (kallsyms_sym_address(mid) <= addr)
low = mid;
else
high = mid;
}
/*
* Search for the first aliased symbol. Aliased
* symbols are symbols with the same address.
*/
kallsyms: add support for relative offsets in kallsyms address table Similar to how relative extables are implemented, it is possible to emit the kallsyms table in such a way that it contains offsets relative to some anchor point in the kernel image rather than absolute addresses. On 64-bit architectures, it cuts the size of the kallsyms address table in half, since offsets between kernel symbols can typically be expressed in 32 bits. This saves several hundreds of kilobytes of permanent .rodata on average. In addition, the kallsyms address table is no longer subject to dynamic relocation when CONFIG_RELOCATABLE is in effect, so the relocation work done after decompression now doesn't have to do relocation updates for all these values. This saves up to 24 bytes (i.e., the size of a ELF64 RELA relocation table entry) per value, which easily adds up to a couple of megabytes of uncompressed __init data on ppc64 or arm64. Even if these relocation entries typically compress well, the combined size reduction of 2.8 MB uncompressed for a ppc64_defconfig build (of which 2.4 MB is __init data) results in a ~500 KB space saving in the compressed image. Since it is useful for some architectures (like x86) to retain the ability to emit absolute values as well, this patch also adds support for capturing both absolute and relative values when KALLSYMS_ABSOLUTE_PERCPU is in effect, by emitting absolute per-cpu addresses as positive 32-bit values, and addresses relative to the lowest encountered relative symbol as negative values, which are subtracted from the runtime address of this base symbol to produce the actual address. Support for the above is enabled by default for all architectures except IA-64 and Tile-GX, whose symbols are too far apart to capture in this manner. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Tested-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Kees Cook <keescook@chromium.org> Tested-by: Kees Cook <keescook@chromium.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Ingo Molnar <mingo@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michal Marek <mmarek@suse.cz> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-16 05:58:19 +08:00
while (low && kallsyms_sym_address(low-1) == kallsyms_sym_address(low))
--low;
kallsyms: add support for relative offsets in kallsyms address table Similar to how relative extables are implemented, it is possible to emit the kallsyms table in such a way that it contains offsets relative to some anchor point in the kernel image rather than absolute addresses. On 64-bit architectures, it cuts the size of the kallsyms address table in half, since offsets between kernel symbols can typically be expressed in 32 bits. This saves several hundreds of kilobytes of permanent .rodata on average. In addition, the kallsyms address table is no longer subject to dynamic relocation when CONFIG_RELOCATABLE is in effect, so the relocation work done after decompression now doesn't have to do relocation updates for all these values. This saves up to 24 bytes (i.e., the size of a ELF64 RELA relocation table entry) per value, which easily adds up to a couple of megabytes of uncompressed __init data on ppc64 or arm64. Even if these relocation entries typically compress well, the combined size reduction of 2.8 MB uncompressed for a ppc64_defconfig build (of which 2.4 MB is __init data) results in a ~500 KB space saving in the compressed image. Since it is useful for some architectures (like x86) to retain the ability to emit absolute values as well, this patch also adds support for capturing both absolute and relative values when KALLSYMS_ABSOLUTE_PERCPU is in effect, by emitting absolute per-cpu addresses as positive 32-bit values, and addresses relative to the lowest encountered relative symbol as negative values, which are subtracted from the runtime address of this base symbol to produce the actual address. Support for the above is enabled by default for all architectures except IA-64 and Tile-GX, whose symbols are too far apart to capture in this manner. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Tested-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Kees Cook <keescook@chromium.org> Tested-by: Kees Cook <keescook@chromium.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Ingo Molnar <mingo@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michal Marek <mmarek@suse.cz> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-16 05:58:19 +08:00
symbol_start = kallsyms_sym_address(low);
/* Search for next non-aliased symbol. */
for (i = low + 1; i < kallsyms_num_syms; i++) {
kallsyms: add support for relative offsets in kallsyms address table Similar to how relative extables are implemented, it is possible to emit the kallsyms table in such a way that it contains offsets relative to some anchor point in the kernel image rather than absolute addresses. On 64-bit architectures, it cuts the size of the kallsyms address table in half, since offsets between kernel symbols can typically be expressed in 32 bits. This saves several hundreds of kilobytes of permanent .rodata on average. In addition, the kallsyms address table is no longer subject to dynamic relocation when CONFIG_RELOCATABLE is in effect, so the relocation work done after decompression now doesn't have to do relocation updates for all these values. This saves up to 24 bytes (i.e., the size of a ELF64 RELA relocation table entry) per value, which easily adds up to a couple of megabytes of uncompressed __init data on ppc64 or arm64. Even if these relocation entries typically compress well, the combined size reduction of 2.8 MB uncompressed for a ppc64_defconfig build (of which 2.4 MB is __init data) results in a ~500 KB space saving in the compressed image. Since it is useful for some architectures (like x86) to retain the ability to emit absolute values as well, this patch also adds support for capturing both absolute and relative values when KALLSYMS_ABSOLUTE_PERCPU is in effect, by emitting absolute per-cpu addresses as positive 32-bit values, and addresses relative to the lowest encountered relative symbol as negative values, which are subtracted from the runtime address of this base symbol to produce the actual address. Support for the above is enabled by default for all architectures except IA-64 and Tile-GX, whose symbols are too far apart to capture in this manner. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Tested-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Kees Cook <keescook@chromium.org> Tested-by: Kees Cook <keescook@chromium.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Ingo Molnar <mingo@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michal Marek <mmarek@suse.cz> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-16 05:58:19 +08:00
if (kallsyms_sym_address(i) > symbol_start) {
symbol_end = kallsyms_sym_address(i);
break;
}
}
/* If we found no next symbol, we use the end of the section. */
if (!symbol_end) {
if (is_kernel_inittext(addr))
symbol_end = (unsigned long)_einittext;
else if (IS_ENABLED(CONFIG_KALLSYMS_ALL))
symbol_end = (unsigned long)_end;
else
symbol_end = (unsigned long)_etext;
}
if (symbolsize)
*symbolsize = symbol_end - symbol_start;
if (offset)
*offset = addr - symbol_start;
return low;
}
/*
* Lookup an address but don't bother to find any names.
*/
int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize,
unsigned long *offset)
{
char namebuf[KSYM_NAME_LEN];
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
kallsyms: Don't let kallsyms_lookup_size_offset() fail on retrieving the first symbol An arm64 kernel configured with CONFIG_KPROBES=y CONFIG_KALLSYMS=y # CONFIG_KALLSYMS_ALL is not set CONFIG_KALLSYMS_BASE_RELATIVE=y reports the following kprobe failure: [ 0.032677] kprobes: failed to populate blacklist: -22 [ 0.033376] Please take care of using kprobes. It appears that kprobe fails to retrieve the symbol at address 0xffff000010081000, despite this symbol being in System.map: ffff000010081000 T __exception_text_start This symbol is part of the first group of aliases in the kallsyms_offsets array (symbol names generated using ugly hacks in scripts/kallsyms.c): kallsyms_offsets: .long 0x1000 // do_undefinstr .long 0x1000 // efi_header_end .long 0x1000 // _stext .long 0x1000 // __exception_text_start .long 0x12b0 // do_cp15instr Looking at the implementation of get_symbol_pos(), it returns the lowest index for aliasing symbols. In this case, it return 0. But kallsyms_lookup_size_offset() considers 0 as a failure, which is obviously wrong (there is definitely a valid symbol living there). In turn, the kprobe blacklisting stops abruptly, hence the original error. A CONFIG_KALLSYMS_ALL kernel wouldn't fail as there is always some random symbols at the beginning of this array, which are never looked up via kallsyms_lookup_size_offset. Fix it by considering that get_symbol_pos() is always successful (which is consistent with the other uses of this function). Fixes: ffc5089196446 ("[PATCH] Create kallsyms_lookup_size_offset()") Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Marc Zyngier <maz@kernel.org> Signed-off-by: Will Deacon <will@kernel.org>
2019-08-24 21:12:31 +08:00
if (is_ksym_addr(addr)) {
get_symbol_pos(addr, symbolsize, offset);
return 1;
}
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
return !!module_address_lookup(addr, symbolsize, offset, NULL, NULL, namebuf) ||
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
!!__bpf_address_lookup(addr, symbolsize, offset, namebuf);
}
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
static const char *kallsyms_lookup_buildid(unsigned long addr,
unsigned long *symbolsize,
unsigned long *offset, char **modname,
const unsigned char **modbuildid, char *namebuf)
{
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
const char *ret;
namebuf[KSYM_NAME_LEN - 1] = 0;
namebuf[0] = 0;
if (is_ksym_addr(addr)) {
unsigned long pos;
pos = get_symbol_pos(addr, symbolsize, offset);
/* Grab name */
kallsyms_expand_symbol(get_symbol_offset(pos),
namebuf, KSYM_NAME_LEN);
if (modname)
*modname = NULL;
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
if (modbuildid)
*modbuildid = NULL;
ret = namebuf;
goto found;
}
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
/* See if it's in a module or a BPF JITed image. */
ret = module_address_lookup(addr, symbolsize, offset,
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
modname, modbuildid, namebuf);
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
if (!ret)
ret = bpf_address_lookup(addr, symbolsize,
offset, modname, namebuf);
ftrace: Save module init functions kallsyms symbols for tracing If function tracing is active when the module init functions are freed, then store them to be referenced by kallsyms. As module init functions can now be traced on module load, they were useless: ># echo ':mod:snd_seq' > set_ftrace_filter ># echo function > current_tracer ># modprobe snd_seq ># cat trace # tracer: function # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / delay # TASK-PID CPU# |||| TIMESTAMP FUNCTION # | | | |||| | | modprobe-2786 [000] .... 3189.037874: 0xffffffffa0860000 <-do_one_initcall modprobe-2786 [000] .... 3189.037876: 0xffffffffa086004d <-0xffffffffa086000f modprobe-2786 [000] .... 3189.037876: 0xffffffffa086010d <-0xffffffffa0860018 modprobe-2786 [000] .... 3189.037877: 0xffffffffa086011a <-0xffffffffa0860021 modprobe-2786 [000] .... 3189.037877: 0xffffffffa0860080 <-0xffffffffa086002a modprobe-2786 [000] .... 3189.039523: 0xffffffffa0860400 <-0xffffffffa0860033 modprobe-2786 [000] .... 3189.039523: 0xffffffffa086038a <-0xffffffffa086041c modprobe-2786 [000] .... 3189.039591: 0xffffffffa086038a <-0xffffffffa0860436 modprobe-2786 [000] .... 3189.039657: 0xffffffffa086038a <-0xffffffffa0860450 modprobe-2786 [000] .... 3189.039719: 0xffffffffa0860127 <-0xffffffffa086003c modprobe-2786 [000] .... 3189.039742: snd_seq_create_kernel_client <-0xffffffffa08601f6 When the output is shown, the kallsyms for the module init functions have already been freed, and the output of the trace can not convert them to their function names. Now this looks like this: # tracer: function # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / delay # TASK-PID CPU# |||| TIMESTAMP FUNCTION # | | | |||| | | modprobe-2463 [002] .... 174.243237: alsa_seq_init <-do_one_initcall modprobe-2463 [002] .... 174.243239: client_init_data <-alsa_seq_init modprobe-2463 [002] .... 174.243240: snd_sequencer_memory_init <-alsa_seq_init modprobe-2463 [002] .... 174.243240: snd_seq_queues_init <-alsa_seq_init modprobe-2463 [002] .... 174.243240: snd_sequencer_device_init <-alsa_seq_init modprobe-2463 [002] .... 174.244860: snd_seq_info_init <-alsa_seq_init modprobe-2463 [002] .... 174.244861: create_info_entry <-snd_seq_info_init modprobe-2463 [002] .... 174.244936: create_info_entry <-snd_seq_info_init modprobe-2463 [002] .... 174.245003: create_info_entry <-snd_seq_info_init modprobe-2463 [002] .... 174.245072: snd_seq_system_client_init <-alsa_seq_init modprobe-2463 [002] .... 174.245094: snd_seq_create_kernel_client <-snd_seq_system_client_init Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2017-09-01 20:35:38 +08:00
if (!ret)
ret = ftrace_mod_address_lookup(addr, symbolsize,
offset, modname, namebuf);
found:
cleanup_symbol_name(namebuf);
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
return ret;
}
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
/*
* Lookup an address
* - modname is set to NULL if it's in the kernel.
* - We guarantee that the returned name is valid until we reschedule even if.
* It resides in a module.
* - We also guarantee that modname will be valid until rescheduled.
*/
const char *kallsyms_lookup(unsigned long addr,
unsigned long *symbolsize,
unsigned long *offset,
char **modname, char *namebuf)
{
return kallsyms_lookup_buildid(addr, symbolsize, offset, modname,
NULL, namebuf);
}
int lookup_symbol_name(unsigned long addr, char *symname)
{
int res;
symname[0] = '\0';
symname[KSYM_NAME_LEN - 1] = '\0';
if (is_ksym_addr(addr)) {
unsigned long pos;
pos = get_symbol_pos(addr, NULL, NULL);
/* Grab name */
kallsyms_expand_symbol(get_symbol_offset(pos),
symname, KSYM_NAME_LEN);
goto found;
}
/* See if it's in a module. */
res = lookup_module_symbol_name(addr, symname);
if (res)
return res;
found:
cleanup_symbol_name(symname);
return 0;
}
/* Look up a kernel symbol and return it in a text buffer. */
static int __sprint_symbol(char *buffer, unsigned long address,
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
int symbol_offset, int add_offset, int add_buildid)
{
char *modname;
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
const unsigned char *buildid;
const char *name;
unsigned long offset, size;
int len;
address += symbol_offset;
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
name = kallsyms_lookup_buildid(address, &size, &offset, &modname, &buildid,
buffer);
if (!name)
return sprintf(buffer, "0x%lx", address - symbol_offset);
if (name != buffer)
strcpy(buffer, name);
len = strlen(buffer);
offset -= symbol_offset;
if (add_offset)
len += sprintf(buffer + len, "+%#lx/%#lx", offset, size);
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
if (modname) {
len += sprintf(buffer + len, " [%s", modname);
#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID)
if (add_buildid && buildid) {
/* build ID should match length of sprintf */
#if IS_ENABLED(CONFIG_MODULES)
static_assert(sizeof(typeof_member(struct module, build_id)) == 20);
#endif
len += sprintf(buffer + len, " %20phN", buildid);
}
#endif
len += sprintf(buffer + len, "]");
}
return len;
}
/**
* sprint_symbol - Look up a kernel symbol and return it in a text buffer
* @buffer: buffer to be stored
* @address: address to lookup
*
* This function looks up a kernel symbol with @address and stores its name,
* offset, size and module name to @buffer if possible. If no symbol was found,
* just saves its @address as is.
*
* This function returns the number of bytes stored in @buffer.
*/
int sprint_symbol(char *buffer, unsigned long address)
{
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
return __sprint_symbol(buffer, address, 0, 1, 0);
}
EXPORT_SYMBOL_GPL(sprint_symbol);
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
/**
* sprint_symbol_build_id - Look up a kernel symbol and return it in a text buffer
* @buffer: buffer to be stored
* @address: address to lookup
*
* This function looks up a kernel symbol with @address and stores its name,
* offset, size, module name and module build ID to @buffer if possible. If no
* symbol was found, just saves its @address as is.
*
* This function returns the number of bytes stored in @buffer.
*/
int sprint_symbol_build_id(char *buffer, unsigned long address)
{
return __sprint_symbol(buffer, address, 0, 1, 1);
}
EXPORT_SYMBOL_GPL(sprint_symbol_build_id);
/**
* sprint_symbol_no_offset - Look up a kernel symbol and return it in a text buffer
* @buffer: buffer to be stored
* @address: address to lookup
*
* This function looks up a kernel symbol with @address and stores its name
* and module name to @buffer if possible. If no symbol was found, just saves
* its @address as is.
*
* This function returns the number of bytes stored in @buffer.
*/
int sprint_symbol_no_offset(char *buffer, unsigned long address)
{
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
return __sprint_symbol(buffer, address, 0, 0, 0);
}
EXPORT_SYMBOL_GPL(sprint_symbol_no_offset);
/**
* sprint_backtrace - Look up a backtrace symbol and return it in a text buffer
* @buffer: buffer to be stored
* @address: address to lookup
*
* This function is for stack backtrace and does the same thing as
* sprint_symbol() but with modified/decreased @address. If there is a
* tail-call to the function marked "noreturn", gcc optimized out code after
* the call so that the stack-saved return address could point outside of the
* caller. This function ensures that kallsyms will find the original caller
* by decreasing @address.
*
* This function returns the number of bytes stored in @buffer.
*/
int sprint_backtrace(char *buffer, unsigned long address)
{
module: add printk formats to add module build ID to stacktraces Let's make kernel stacktraces easier to identify by including the build ID[1] of a module if the stacktrace is printing a symbol from a module. This makes it simpler for developers to locate a kernel module's full debuginfo for a particular stacktrace. Combined with scripts/decode_stracktrace.sh, a developer can download the matching debuginfo from a debuginfod[2] server and find the exact file and line number for the functions plus offsets in a stacktrace that match the module. This is especially useful for pstore crash debugging where the kernel crashes are recorded in something like console-ramoops and the recovery kernel/modules are different or the debuginfo doesn't exist on the device due to space concerns (the debuginfo can be too large for space limited devices). Originally, I put this on the %pS format, but that was quickly rejected given that %pS is used in other places such as ftrace where build IDs aren't meaningful. There was some discussions on the list to put every module build ID into the "Modules linked in:" section of the stacktrace message but that quickly becomes very hard to read once you have more than three or four modules linked in. It also provides too much information when we don't expect each module to be traversed in a stacktrace. Having the build ID for modules that aren't important just makes things messy. Splitting it to multiple lines for each module quickly explodes the number of lines printed in an oops too, possibly wrapping the warning off the console. And finally, trying to stash away each module used in a callstack to provide the ID of each symbol printed is cumbersome and would require changes to each architecture to stash away modules and return their build IDs once unwinding has completed. Instead, we opt for the simpler approach of introducing new printk formats '%pS[R]b' for "pointer symbolic backtrace with module build ID" and '%pBb' for "pointer backtrace with module build ID" and then updating the few places in the architecture layer where the stacktrace is printed to use this new format. Before: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm] direct_entry+0x16c/0x1b4 [lkdtm] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 After: Call trace: lkdtm_WARNING+0x28/0x30 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] direct_entry+0x16c/0x1b4 [lkdtm 6c2215028606bda50de823490723dc4bc5bf46f9] full_proxy_write+0x74/0xa4 vfs_write+0xec/0x2e8 [akpm@linux-foundation.org: fix build with CONFIG_MODULES=n, tweak code layout] [rdunlap@infradead.org: fix build when CONFIG_MODULES is not set] Link: https://lkml.kernel.org/r/20210513171510.20328-1-rdunlap@infradead.org [akpm@linux-foundation.org: make kallsyms_lookup_buildid() static] [cuibixuan@huawei.com: fix build error when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20210525105049.34804-1-cuibixuan@huawei.com Link: https://lkml.kernel.org/r/20210511003845.2429846-6-swboyd@chromium.org Link: https://fedoraproject.org/wiki/Releases/FeatureBuildId [1] Link: https://sourceware.org/elfutils/Debuginfod.html [2] Signed-off-by: Stephen Boyd <swboyd@chromium.org> Signed-off-by: Bixuan Cui <cuibixuan@huawei.com> Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Evan Green <evgreen@chromium.org> Cc: Hsin-Yi Wang <hsinyi@chromium.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Matthew Wilcox <willy@infradead.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Young <dyoung@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Sasha Levin <sashal@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-08 09:09:20 +08:00
return __sprint_symbol(buffer, address, -1, 1, 0);
}
/**
* sprint_backtrace_build_id - Look up a backtrace symbol and return it in a text buffer
* @buffer: buffer to be stored
* @address: address to lookup
*
* This function is for stack backtrace and does the same thing as
* sprint_symbol() but with modified/decreased @address. If there is a
* tail-call to the function marked "noreturn", gcc optimized out code after
* the call so that the stack-saved return address could point outside of the
* caller. This function ensures that kallsyms will find the original caller
* by decreasing @address. This function also appends the module build ID to
* the @buffer if @address is within a kernel module.
*
* This function returns the number of bytes stored in @buffer.
*/
int sprint_backtrace_build_id(char *buffer, unsigned long address)
{
return __sprint_symbol(buffer, address, -1, 1, 1);
}
/* To avoid using get_symbol_offset for every symbol, we carry prefix along. */
struct kallsym_iter {
loff_t pos;
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
loff_t pos_mod_end;
loff_t pos_ftrace_mod_end;
loff_t pos_bpf_end;
unsigned long value;
unsigned int nameoff; /* If iterating in core kernel symbols. */
char type;
char name[KSYM_NAME_LEN];
char module_name[MODULE_NAME_LEN];
int exported;
int show_value;
};
static int get_ksymbol_mod(struct kallsym_iter *iter)
{
int ret = module_get_kallsym(iter->pos - kallsyms_num_syms,
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
&iter->value, &iter->type,
iter->name, iter->module_name,
&iter->exported);
if (ret < 0) {
iter->pos_mod_end = iter->pos;
return 0;
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
}
return 1;
}
/*
* ftrace_mod_get_kallsym() may also get symbols for pages allocated for ftrace
* purposes. In that case "__builtin__ftrace" is used as a module name, even
* though "__builtin__ftrace" is not a module.
*/
static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
{
int ret = ftrace_mod_get_kallsym(iter->pos - iter->pos_mod_end,
&iter->value, &iter->type,
iter->name, iter->module_name,
&iter->exported);
if (ret < 0) {
iter->pos_ftrace_mod_end = iter->pos;
return 0;
}
return 1;
}
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
static int get_ksymbol_bpf(struct kallsym_iter *iter)
{
int ret;
strscpy(iter->module_name, "bpf", MODULE_NAME_LEN);
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
iter->exported = 0;
ret = bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
&iter->value, &iter->type,
iter->name);
if (ret < 0) {
iter->pos_bpf_end = iter->pos;
return 0;
}
return 1;
}
/*
* This uses "__builtin__kprobes" as a module name for symbols for pages
* allocated for kprobes' purposes, even though "__builtin__kprobes" is not a
* module.
*/
static int get_ksymbol_kprobe(struct kallsym_iter *iter)
{
strscpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN);
iter->exported = 0;
return kprobe_get_kallsym(iter->pos - iter->pos_bpf_end,
&iter->value, &iter->type,
iter->name) < 0 ? 0 : 1;
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
}
/* Returns space to next name. */
static unsigned long get_ksymbol_core(struct kallsym_iter *iter)
{
unsigned off = iter->nameoff;
iter->module_name[0] = '\0';
kallsyms: add support for relative offsets in kallsyms address table Similar to how relative extables are implemented, it is possible to emit the kallsyms table in such a way that it contains offsets relative to some anchor point in the kernel image rather than absolute addresses. On 64-bit architectures, it cuts the size of the kallsyms address table in half, since offsets between kernel symbols can typically be expressed in 32 bits. This saves several hundreds of kilobytes of permanent .rodata on average. In addition, the kallsyms address table is no longer subject to dynamic relocation when CONFIG_RELOCATABLE is in effect, so the relocation work done after decompression now doesn't have to do relocation updates for all these values. This saves up to 24 bytes (i.e., the size of a ELF64 RELA relocation table entry) per value, which easily adds up to a couple of megabytes of uncompressed __init data on ppc64 or arm64. Even if these relocation entries typically compress well, the combined size reduction of 2.8 MB uncompressed for a ppc64_defconfig build (of which 2.4 MB is __init data) results in a ~500 KB space saving in the compressed image. Since it is useful for some architectures (like x86) to retain the ability to emit absolute values as well, this patch also adds support for capturing both absolute and relative values when KALLSYMS_ABSOLUTE_PERCPU is in effect, by emitting absolute per-cpu addresses as positive 32-bit values, and addresses relative to the lowest encountered relative symbol as negative values, which are subtracted from the runtime address of this base symbol to produce the actual address. Support for the above is enabled by default for all architectures except IA-64 and Tile-GX, whose symbols are too far apart to capture in this manner. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Tested-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Kees Cook <keescook@chromium.org> Tested-by: Kees Cook <keescook@chromium.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Ingo Molnar <mingo@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michal Marek <mmarek@suse.cz> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-16 05:58:19 +08:00
iter->value = kallsyms_sym_address(iter->pos);
iter->type = kallsyms_get_symbol_type(off);
off = kallsyms_expand_symbol(off, iter->name, ARRAY_SIZE(iter->name));
return off - iter->nameoff;
}
static void reset_iter(struct kallsym_iter *iter, loff_t new_pos)
{
iter->name[0] = '\0';
iter->nameoff = get_symbol_offset(new_pos);
iter->pos = new_pos;
if (new_pos == 0) {
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
iter->pos_mod_end = 0;
iter->pos_ftrace_mod_end = 0;
iter->pos_bpf_end = 0;
}
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
}
/*
* The end position (last + 1) of each additional kallsyms section is recorded
* in iter->pos_..._end as each section is added, and so can be used to
* determine which get_ksymbol_...() function to call next.
*/
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
static int update_iter_mod(struct kallsym_iter *iter, loff_t pos)
{
iter->pos = pos;
if ((!iter->pos_mod_end || iter->pos_mod_end > pos) &&
get_ksymbol_mod(iter))
return 1;
if ((!iter->pos_ftrace_mod_end || iter->pos_ftrace_mod_end > pos) &&
get_ksymbol_ftrace_mod(iter))
return 1;
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
if ((!iter->pos_bpf_end || iter->pos_bpf_end > pos) &&
get_ksymbol_bpf(iter))
return 1;
return get_ksymbol_kprobe(iter);
}
/* Returns false if pos at or past end of file. */
static int update_iter(struct kallsym_iter *iter, loff_t pos)
{
/* Module symbols can be accessed randomly. */
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 05:24:50 +08:00
if (pos >= kallsyms_num_syms)
return update_iter_mod(iter, pos);
/* If we're not on the desired position, reset to new position. */
if (pos != iter->pos)
reset_iter(iter, pos);
iter->nameoff += get_ksymbol_core(iter);
iter->pos++;
return 1;
}
static void *s_next(struct seq_file *m, void *p, loff_t *pos)
{
(*pos)++;
if (!update_iter(m->private, *pos))
return NULL;
return p;
}
static void *s_start(struct seq_file *m, loff_t *pos)
{
if (!update_iter(m->private, *pos))
return NULL;
return m->private;
}
static void s_stop(struct seq_file *m, void *p)
{
}
static int s_show(struct seq_file *m, void *p)
{
void *value;
struct kallsym_iter *iter = m->private;
/* Some debugging symbols have no name. Ignore them. */
if (!iter->name[0])
return 0;
value = iter->show_value ? (void *)iter->value : NULL;
if (iter->module_name[0]) {
char type;
/*
* Label it "global" if it is exported,
* "local" if not exported.
*/
type = iter->exported ? toupper(iter->type) :
tolower(iter->type);
seq_printf(m, "%px %c %s\t[%s]\n", value,
type, iter->name, iter->module_name);
} else
seq_printf(m, "%px %c %s\n", value,
iter->type, iter->name);
return 0;
}
static const struct seq_operations kallsyms_op = {
.start = s_start,
.next = s_next,
.stop = s_stop,
.show = s_show
};
#ifdef CONFIG_BPF_SYSCALL
struct bpf_iter__ksym {
__bpf_md_ptr(struct bpf_iter_meta *, meta);
__bpf_md_ptr(struct kallsym_iter *, ksym);
};
static int ksym_prog_seq_show(struct seq_file *m, bool in_stop)
{
struct bpf_iter__ksym ctx;
struct bpf_iter_meta meta;
struct bpf_prog *prog;
meta.seq = m;
prog = bpf_iter_get_info(&meta, in_stop);
if (!prog)
return 0;
ctx.meta = &meta;
ctx.ksym = m ? m->private : NULL;
return bpf_iter_run_prog(prog, &ctx);
}
static int bpf_iter_ksym_seq_show(struct seq_file *m, void *p)
{
return ksym_prog_seq_show(m, false);
}
static void bpf_iter_ksym_seq_stop(struct seq_file *m, void *p)
{
if (!p)
(void) ksym_prog_seq_show(m, true);
else
s_stop(m, p);
}
static const struct seq_operations bpf_iter_ksym_ops = {
.start = s_start,
.next = s_next,
.stop = bpf_iter_ksym_seq_stop,
.show = bpf_iter_ksym_seq_show,
};
static int bpf_iter_ksym_init(void *priv_data, struct bpf_iter_aux_info *aux)
{
struct kallsym_iter *iter = priv_data;
reset_iter(iter, 0);
/* cache here as in kallsyms_open() case; use current process
* credentials to tell BPF iterators if values should be shown.
*/
iter->show_value = kallsyms_show_value(current_cred());
return 0;
}
DEFINE_BPF_ITER_FUNC(ksym, struct bpf_iter_meta *meta, struct kallsym_iter *ksym)
static const struct bpf_iter_seq_info ksym_iter_seq_info = {
.seq_ops = &bpf_iter_ksym_ops,
.init_seq_private = bpf_iter_ksym_init,
.fini_seq_private = NULL,
.seq_priv_size = sizeof(struct kallsym_iter),
};
static struct bpf_iter_reg ksym_iter_reg_info = {
.target = "ksym",
.feature = BPF_ITER_RESCHED,
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__ksym, ksym),
PTR_TO_BTF_ID_OR_NULL },
},
.seq_info = &ksym_iter_seq_info,
};
BTF_ID_LIST(btf_ksym_iter_id)
BTF_ID(struct, kallsym_iter)
static int __init bpf_ksym_iter_register(void)
{
ksym_iter_reg_info.ctx_arg_info[0].btf_id = *btf_ksym_iter_id;
return bpf_iter_reg_target(&ksym_iter_reg_info);
}
late_initcall(bpf_ksym_iter_register);
#endif /* CONFIG_BPF_SYSCALL */
static int kallsyms_open(struct inode *inode, struct file *file)
{
/*
* We keep iterator in m->private, since normal case is to
* s_start from where we left off, so we avoid doing
* using get_symbol_offset for every symbol.
*/
struct kallsym_iter *iter;
iter = __seq_open_private(file, &kallsyms_op, sizeof(*iter));
if (!iter)
return -ENOMEM;
reset_iter(iter, 0);
/*
* Instead of checking this on every s_show() call, cache
* the result here at open time.
*/
iter->show_value = kallsyms_show_value(file->f_cred);
return 0;
}
#ifdef CONFIG_KGDB_KDB
const char *kdb_walk_kallsyms(loff_t *pos)
{
static struct kallsym_iter kdb_walk_kallsyms_iter;
if (*pos == 0) {
memset(&kdb_walk_kallsyms_iter, 0,
sizeof(kdb_walk_kallsyms_iter));
reset_iter(&kdb_walk_kallsyms_iter, 0);
}
while (1) {
if (!update_iter(&kdb_walk_kallsyms_iter, *pos))
return NULL;
++*pos;
/* Some debugging symbols have no name. Ignore them. */
if (kdb_walk_kallsyms_iter.name[0])
return kdb_walk_kallsyms_iter.name;
}
}
#endif /* CONFIG_KGDB_KDB */
static const struct proc_ops kallsyms_proc_ops = {
.proc_open = kallsyms_open,
.proc_read = seq_read,
.proc_lseek = seq_lseek,
.proc_release = seq_release_private,
};
static int __init kallsyms_init(void)
{
proc_create("kallsyms", 0444, NULL, &kallsyms_proc_ops);
return 0;
}
device_initcall(kallsyms_init);