linux-stable/include/linux/ftrace.h

1176 lines
39 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 14:07:57 +00:00
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Ftrace header. For implementation details beyond the random comments
* scattered below, see: Documentation/trace/ftrace-design.rst
*/
#ifndef _LINUX_FTRACE_H
#define _LINUX_FTRACE_H
#include <linux/trace_recursion.h>
#include <linux/trace_clock.h>
#include <linux/jump_label.h>
#include <linux/kallsyms.h>
#include <linux/linkage.h>
ftrace: graph of a single function This patch adds the file: /debugfs/tracing/set_graph_function which can be used along with the function graph tracer. When this file is empty, the function graph tracer will act as usual. When the file has a function in it, the function graph tracer will only trace that function. For example: # echo blk_unplug > /debugfs/tracing/set_graph_function # cat /debugfs/tracing/trace [...] ------------------------------------------ | 2) make-19003 => kjournald-2219 ------------------------------------------ 2) | blk_unplug() { 2) | dm_unplug_all() { 2) | dm_get_table() { 2) 1.381 us | _read_lock(); 2) 0.911 us | dm_table_get(); 2) 1. 76 us | _read_unlock(); 2) + 12.912 us | } 2) | dm_table_unplug_all() { 2) | blk_unplug() { 2) 0.778 us | generic_unplug_device(); 2) 2.409 us | } 2) 5.992 us | } 2) 0.813 us | dm_table_put(); 2) + 29. 90 us | } 2) + 34.532 us | } You can add up to 32 functions into this file. Currently we limit it to 32, but this may change with later improvements. To add another function, use the append '>>': # echo sys_read >> /debugfs/tracing/set_graph_function # cat /debugfs/tracing/set_graph_function blk_unplug sys_read Using the '>' will clear out the function and write anew: # echo sys_write > /debug/tracing/set_graph_function # cat /debug/tracing/set_graph_function sys_write Note, if you have function graph running while doing this, the small time between clearing it and updating it will cause the graph to record all functions. This should not be an issue because after it sets the filter, only those functions will be recorded from then on. If you need to only record a particular function then set this file first before starting the function graph tracer. In the future this side effect may be corrected. The set_graph_function file is similar to the set_ftrace_filter but it does not take wild cards nor does it allow for more than one function to be set with a single write. There is no technical reason why this is the case, I just do not have the time yet to implement that. Note, dynamic ftrace must be enabled for this to appear because it uses the dynamic ftrace records to match the name to the mcount call sites. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-03 20:36:57 +00:00
#include <linux/bitops.h>
#include <linux/ptrace.h>
#include <linux/ktime.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <asm/ftrace.h>
/*
* If the arch supports passing the variable contents of
* function_trace_op as the third parameter back from the
* mcount call, then the arch should define this as 1.
*/
#ifndef ARCH_SUPPORTS_FTRACE_OPS
#define ARCH_SUPPORTS_FTRACE_OPS 0
#endif
#ifdef CONFIG_TRACING
extern void ftrace_boot_snapshot(void);
#else
static inline void ftrace_boot_snapshot(void) { }
#endif
struct ftrace_ops;
struct ftrace_regs;
ftrace: Add DYNAMIC_FTRACE_WITH_CALL_OPS Architectures without dynamic ftrace trampolines incur an overhead when multiple ftrace_ops are enabled with distinct filters. in these cases, each call site calls a common trampoline which uses ftrace_ops_list_func() to iterate over all enabled ftrace functions, and so incurs an overhead relative to the size of this list (including RCU protection overhead). Architectures with dynamic ftrace trampolines avoid this overhead for call sites which have a single associated ftrace_ops. In these cases, the dynamic trampoline is customized to branch directly to the relevant ftrace function, avoiding the list overhead. On some architectures it's impractical and/or undesirable to implement dynamic ftrace trampolines. For example, arm64 has limited branch ranges and cannot always directly branch from a call site to an arbitrary address (e.g. from a kernel text address to an arbitrary module address). Calls from modules to core kernel text can be indirected via PLTs (allocated at module load time) to address this, but the same is not possible from calls from core kernel text. Using an indirect branch from a call site to an arbitrary trampoline is possible, but requires several more instructions in the function prologue (or immediately before it), and/or comes with far more complex requirements for patching. Instead, this patch adds a new option, where an architecture can associate each call site with a pointer to an ftrace_ops, placed at a fixed offset from the call site. A shared trampoline can recover this pointer and call ftrace_ops::func() without needing to go via ftrace_ops_list_func(), avoiding the associated overhead. This avoids issues with branch range limitations, and avoids the need to allocate and manipulate dynamic trampolines, making it far simpler to implement and maintain, while having similar performance characteristics. Note that this allows for dynamic ftrace_ops to be invoked directly from an architecture's ftrace_caller trampoline, whereas existing code forces the use of ftrace_ops_get_list_func(), which is in part necessary to permit the ftrace_ops to be freed once unregistered *and* to avoid branch/address-generation range limitation on some architectures (e.g. where ops->func is a module address, and may be outside of the direct branch range for callsites within the main kernel image). The CALL_OPS approach avoids this problems and is safe as: * The existing synchronization in ftrace_shutdown() using ftrace_shutdown() using synchronize_rcu_tasks_rude() (and synchronize_rcu_tasks()) ensures that no tasks hold a stale reference to an ftrace_ops (e.g. in the middle of the ftrace_caller trampoline, or while invoking ftrace_ops::func), when that ftrace_ops is unregistered. Arguably this could also be relied upon for the existing scheme, permitting dynamic ftrace_ops to be invoked directly when ops->func is in range, but this will require additional logic to handle branch range limitations, and is not handled by this patch. * Each callsite's ftrace_ops pointer literal can hold any valid kernel address, and is updated atomically. As an architecture's ftrace_caller trampoline will atomically load the ops pointer then dereference ops->func, there is no risk of invoking ops->func with a mismatches ops pointer, and updates to the ops pointer do not require special care. A subsequent patch will implement architectures support for arm64. There should be no functional change as a result of this patch alone. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org> Cc: Florent Revest <revest@chromium.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20230123134603.1064407-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2023-01-23 13:45:56 +00:00
struct dyn_ftrace;
tracing: arm64: Avoid missing-prototype warnings These are all tracing W=1 warnings in arm64 allmodconfig about missing prototypes: kernel/trace/trace_kprobe_selftest.c:7:5: error: no previous prototype for 'kprobe_trace_selftest_target' [-Werror=missing-pro totypes] kernel/trace/ftrace.c:329:5: error: no previous prototype for '__register_ftrace_function' [-Werror=missing-prototypes] kernel/trace/ftrace.c:372:5: error: no previous prototype for '__unregister_ftrace_function' [-Werror=missing-prototypes] kernel/trace/ftrace.c:4130:15: error: no previous prototype for 'arch_ftrace_match_adjust' [-Werror=missing-prototypes] kernel/trace/fgraph.c:243:15: error: no previous prototype for 'ftrace_return_to_handler' [-Werror=missing-prototypes] kernel/trace/fgraph.c:358:6: error: no previous prototype for 'ftrace_graph_sleep_time_control' [-Werror=missing-prototypes] arch/arm64/kernel/ftrace.c:460:6: error: no previous prototype for 'prepare_ftrace_return' [-Werror=missing-prototypes] arch/arm64/kernel/ptrace.c:2172:5: error: no previous prototype for 'syscall_trace_enter' [-Werror=missing-prototypes] arch/arm64/kernel/ptrace.c:2195:6: error: no previous prototype for 'syscall_trace_exit' [-Werror=missing-prototypes] Move the declarations to an appropriate header where they can be seen by the caller and callee, and make sure the headers are included where needed. Link: https://lore.kernel.org/linux-trace-kernel/20230517125215.930689-1-arnd@kernel.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Florent Revest <revest@chromium.org> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Catalin Marinas <catalin.marinas@arm.com> [ Fixed ftrace_return_to_handler() to handle CONFIG_HAVE_FUNCTION_GRAPH_RETVAL case ] Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-05-17 12:51:48 +00:00
char *arch_ftrace_match_adjust(char *str, const char *search);
#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL
struct fgraph_ret_regs;
unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs);
#else
unsigned long ftrace_return_to_handler(unsigned long frame_pointer);
#endif
#ifdef CONFIG_FUNCTION_TRACER
/*
* If the arch's mcount caller does not support all of ftrace's
* features, then it must call an indirect function that
* does. Or at least does enough to prevent any unwelcome side effects.
*
* Also define the function prototype that these architectures use
* to call the ftrace_ops_list_func().
*/
#if !ARCH_SUPPORTS_FTRACE_OPS
# define FTRACE_FORCE_LIST_FUNC 1
void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
#else
# define FTRACE_FORCE_LIST_FUNC 0
void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs);
#endif
ftrace: Add DYNAMIC_FTRACE_WITH_CALL_OPS Architectures without dynamic ftrace trampolines incur an overhead when multiple ftrace_ops are enabled with distinct filters. in these cases, each call site calls a common trampoline which uses ftrace_ops_list_func() to iterate over all enabled ftrace functions, and so incurs an overhead relative to the size of this list (including RCU protection overhead). Architectures with dynamic ftrace trampolines avoid this overhead for call sites which have a single associated ftrace_ops. In these cases, the dynamic trampoline is customized to branch directly to the relevant ftrace function, avoiding the list overhead. On some architectures it's impractical and/or undesirable to implement dynamic ftrace trampolines. For example, arm64 has limited branch ranges and cannot always directly branch from a call site to an arbitrary address (e.g. from a kernel text address to an arbitrary module address). Calls from modules to core kernel text can be indirected via PLTs (allocated at module load time) to address this, but the same is not possible from calls from core kernel text. Using an indirect branch from a call site to an arbitrary trampoline is possible, but requires several more instructions in the function prologue (or immediately before it), and/or comes with far more complex requirements for patching. Instead, this patch adds a new option, where an architecture can associate each call site with a pointer to an ftrace_ops, placed at a fixed offset from the call site. A shared trampoline can recover this pointer and call ftrace_ops::func() without needing to go via ftrace_ops_list_func(), avoiding the associated overhead. This avoids issues with branch range limitations, and avoids the need to allocate and manipulate dynamic trampolines, making it far simpler to implement and maintain, while having similar performance characteristics. Note that this allows for dynamic ftrace_ops to be invoked directly from an architecture's ftrace_caller trampoline, whereas existing code forces the use of ftrace_ops_get_list_func(), which is in part necessary to permit the ftrace_ops to be freed once unregistered *and* to avoid branch/address-generation range limitation on some architectures (e.g. where ops->func is a module address, and may be outside of the direct branch range for callsites within the main kernel image). The CALL_OPS approach avoids this problems and is safe as: * The existing synchronization in ftrace_shutdown() using ftrace_shutdown() using synchronize_rcu_tasks_rude() (and synchronize_rcu_tasks()) ensures that no tasks hold a stale reference to an ftrace_ops (e.g. in the middle of the ftrace_caller trampoline, or while invoking ftrace_ops::func), when that ftrace_ops is unregistered. Arguably this could also be relied upon for the existing scheme, permitting dynamic ftrace_ops to be invoked directly when ops->func is in range, but this will require additional logic to handle branch range limitations, and is not handled by this patch. * Each callsite's ftrace_ops pointer literal can hold any valid kernel address, and is updated atomically. As an architecture's ftrace_caller trampoline will atomically load the ops pointer then dereference ops->func, there is no risk of invoking ops->func with a mismatches ops pointer, and updates to the ops pointer do not require special care. A subsequent patch will implement architectures support for arm64. There should be no functional change as a result of this patch alone. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org> Cc: Florent Revest <revest@chromium.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20230123134603.1064407-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2023-01-23 13:45:56 +00:00
extern const struct ftrace_ops ftrace_nop_ops;
extern const struct ftrace_ops ftrace_list_ops;
struct ftrace_ops *ftrace_find_unique_ops(struct dyn_ftrace *rec);
#endif /* CONFIG_FUNCTION_TRACER */
/* Main tracing buffer and events set up */
#ifdef CONFIG_TRACING
void trace_init(void);
void early_trace_init(void);
#else
static inline void trace_init(void) { }
static inline void early_trace_init(void) { }
#endif
struct module;
struct ftrace_hash;
struct ftrace_direct_func;
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 12:35:38 +00:00
#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_MODULES) && \
defined(CONFIG_DYNAMIC_FTRACE)
const char *
ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
unsigned long *off, char **modname, char *sym);
#else
static inline const char *
ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
unsigned long *off, char **modname, char *sym)
{
return NULL;
}
#endif
#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
char *type, char *name,
char *module_name, int *exported);
#else
static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value,
char *type, char *name,
char *module_name, int *exported)
{
return -1;
}
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 12:35:38 +00:00
#endif
#ifdef CONFIG_FUNCTION_TRACER
extern int ftrace_enabled;
#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
struct ftrace_regs {
struct pt_regs regs;
};
#define arch_ftrace_get_regs(fregs) (&(fregs)->regs)
/*
* ftrace_regs_set_instruction_pointer() is to be defined by the architecture
* if to allow setting of the instruction pointer from the ftrace_regs when
* HAVE_DYNAMIC_FTRACE_WITH_ARGS is set and it supports live kernel patching.
*/
#define ftrace_regs_set_instruction_pointer(fregs, ip) do { } while (0)
#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs)
{
if (!fregs)
return NULL;
return arch_ftrace_get_regs(fregs);
}
/*
* When true, the ftrace_regs_{get,set}_*() functions may be used on fregs.
* Note: this can be true even when ftrace_get_regs() cannot provide a pt_regs.
*/
static __always_inline bool ftrace_regs_has_args(struct ftrace_regs *fregs)
{
if (IS_ENABLED(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS))
return true;
return ftrace_get_regs(fregs) != NULL;
}
#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
#define ftrace_regs_get_instruction_pointer(fregs) \
instruction_pointer(ftrace_get_regs(fregs))
#define ftrace_regs_get_argument(fregs, n) \
regs_get_kernel_argument(ftrace_get_regs(fregs), n)
#define ftrace_regs_get_stack_pointer(fregs) \
kernel_stack_pointer(ftrace_get_regs(fregs))
#define ftrace_regs_return_value(fregs) \
regs_return_value(ftrace_get_regs(fregs))
#define ftrace_regs_set_return_value(fregs, ret) \
regs_set_return_value(ftrace_get_regs(fregs), ret)
#define ftrace_override_function_with_return(fregs) \
override_function_with_return(ftrace_get_regs(fregs))
#define ftrace_regs_query_register_offset(name) \
regs_query_register_offset(name)
#endif
typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs);
ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
/*
* FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are
* set in the flags member.
* CONTROL, SAVE_REGS, SAVE_REGS_IF_SUPPORTED, RECURSION, STUB and
* IPMODIFY are a kind of attribute flags which can be set only before
* registering the ftrace_ops, and can not be modified while registered.
* Changing those attribute flags after registering ftrace_ops will
* cause unexpected results.
*
* ENABLED - set/unset when ftrace_ops is registered/unregistered
* DYNAMIC - set when ftrace_ops is registered to denote dynamically
* allocated ftrace_ops which need special care
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
* SAVE_REGS - The ftrace_ops wants regs saved at each function called
* and passed to the callback. If this flag is set, but the
* architecture does not support passing regs
* (CONFIG_DYNAMIC_FTRACE_WITH_REGS is not defined), then the
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
* ftrace_ops will fail to register, unless the next flag
* is set.
* SAVE_REGS_IF_SUPPORTED - This is the same as SAVE_REGS, but if the
* handler can handle an arch that does not save regs
* (the handler tests if regs == NULL), then it can set
* this flag instead. It will not fail registering the ftrace_ops
* but, the regs field will be NULL if the arch does not support
* passing regs to the handler.
* Note, if this flag is set, the SAVE_REGS flag will automatically
* get set upon registering the ftrace_ops, if the arch supports it.
* RECURSION - The ftrace_ops can set this to tell the ftrace infrastructure
* that the call back needs recursion protection. If it does
* not set this, then the ftrace infrastructure will assume
* that the callback can handle recursion on its own.
ftrace: Do not call stub functions in control loop The function tracing control loop used by perf spits out a warning if the called function is not a control function. This is because the control function references a per cpu allocated data structure on struct ftrace_ops that is not allocated for other types of functions. commit 0a016409e42 "ftrace: Optimize the function tracer list loop" Had an optimization done to all function tracing loops to optimize for a single registered ops. Unfortunately, this allows for a slight race when tracing starts or ends, where the stub function might be called after the current registered ops is removed. In this case we get the following dump: root# perf stat -e ftrace:function sleep 1 [ 74.339105] WARNING: at include/linux/ftrace.h:209 ftrace_ops_control_func+0xde/0xf0() [ 74.349522] Hardware name: PRIMERGY RX200 S6 [ 74.357149] Modules linked in: sg igb iTCO_wdt ptp pps_core iTCO_vendor_support i7core_edac dca lpc_ich i2c_i801 coretemp edac_core crc32c_intel mfd_core ghash_clmulni_intel dm_multipath acpi_power_meter pcspk r microcode vhost_net tun macvtap macvlan nfsd kvm_intel kvm auth_rpcgss nfs_acl lockd sunrpc uinput xfs libcrc32c sd_mod crc_t10dif sr_mod cdrom mgag200 i2c_algo_bit drm_kms_helper ttm qla2xxx mptsas ahci drm li bahci scsi_transport_sas mptscsih libata scsi_transport_fc i2c_core mptbase scsi_tgt dm_mirror dm_region_hash dm_log dm_mod [ 74.446233] Pid: 1377, comm: perf Tainted: G W 3.9.0-rc1 #1 [ 74.453458] Call Trace: [ 74.456233] [<ffffffff81062e3f>] warn_slowpath_common+0x7f/0xc0 [ 74.462997] [<ffffffff810fbc60>] ? rcu_note_context_switch+0xa0/0xa0 [ 74.470272] [<ffffffff811041a2>] ? __unregister_ftrace_function+0xa2/0x1a0 [ 74.478117] [<ffffffff81062e9a>] warn_slowpath_null+0x1a/0x20 [ 74.484681] [<ffffffff81102ede>] ftrace_ops_control_func+0xde/0xf0 [ 74.491760] [<ffffffff8162f400>] ftrace_call+0x5/0x2f [ 74.497511] [<ffffffff8162f400>] ? ftrace_call+0x5/0x2f [ 74.503486] [<ffffffff8162f400>] ? ftrace_call+0x5/0x2f [ 74.509500] [<ffffffff810fbc65>] ? synchronize_sched+0x5/0x50 [ 74.516088] [<ffffffff816254d5>] ? _cond_resched+0x5/0x40 [ 74.522268] [<ffffffff810fbc65>] ? synchronize_sched+0x5/0x50 [ 74.528837] [<ffffffff811041a2>] ? __unregister_ftrace_function+0xa2/0x1a0 [ 74.536696] [<ffffffff816254d5>] ? _cond_resched+0x5/0x40 [ 74.542878] [<ffffffff8162402d>] ? mutex_lock+0x1d/0x50 [ 74.548869] [<ffffffff81105c67>] unregister_ftrace_function+0x27/0x50 [ 74.556243] [<ffffffff8111eadf>] perf_ftrace_event_register+0x9f/0x140 [ 74.563709] [<ffffffff816254d5>] ? _cond_resched+0x5/0x40 [ 74.569887] [<ffffffff8162402d>] ? mutex_lock+0x1d/0x50 [ 74.575898] [<ffffffff8111e94e>] perf_trace_destroy+0x2e/0x50 [ 74.582505] [<ffffffff81127ba9>] tp_perf_event_destroy+0x9/0x10 [ 74.589298] [<ffffffff811295d0>] free_event+0x70/0x1a0 [ 74.595208] [<ffffffff8112a579>] perf_event_release_kernel+0x69/0xa0 [ 74.602460] [<ffffffff816254d5>] ? _cond_resched+0x5/0x40 [ 74.608667] [<ffffffff8112a640>] put_event+0x90/0xc0 [ 74.614373] [<ffffffff8112a740>] perf_release+0x10/0x20 [ 74.620367] [<ffffffff811a3044>] __fput+0xf4/0x280 [ 74.625894] [<ffffffff811a31de>] ____fput+0xe/0x10 [ 74.631387] [<ffffffff81083697>] task_work_run+0xa7/0xe0 [ 74.637452] [<ffffffff81014981>] do_notify_resume+0x71/0xb0 [ 74.643843] [<ffffffff8162fa92>] int_signal+0x12/0x17 To fix this a new ftrace_ops flag is added that denotes the ftrace_list_end ftrace_ops stub as just that, a stub. This flag is now checked in the control loop and the function is not called if the flag is set. Thanks to Jovi for not just reporting the bug, but also pointing out where the bug was in the code. Link: http://lkml.kernel.org/r/514A8855.7090402@redhat.com Link: http://lkml.kernel.org/r/1364377499-1900-15-git-send-email-jovi.zhangwei@huawei.com Tested-by: WANG Chao <chaowang@redhat.com> Reported-by: WANG Chao <chaowang@redhat.com> Reported-by: zhangwei(Jovi) <jovi.zhangwei@huawei.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-03-27 13:31:28 +00:00
* STUB - The ftrace_ops is just a place holder.
ftrace, kprobes: Fix a deadlock on ftrace_regex_lock Fix a deadlock on ftrace_regex_lock which happens when setting an enable_event trigger on dynamic kprobe event as below. ---- sh-2.05b# echo p vfs_symlink > kprobe_events sh-2.05b# echo vfs_symlink:enable_event:kprobes:p_vfs_symlink_0 > set_ftrace_filter ============================================= [ INFO: possible recursive locking detected ] 3.9.0+ #35 Not tainted --------------------------------------------- sh/72 is trying to acquire lock: (ftrace_regex_lock){+.+.+.}, at: [<ffffffff810ba6c1>] ftrace_set_hash+0x81/0x1f0 but task is already holding lock: (ftrace_regex_lock){+.+.+.}, at: [<ffffffff810b7cbd>] ftrace_regex_write.isra.29.part.30+0x3d/0x220 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(ftrace_regex_lock); lock(ftrace_regex_lock); *** DEADLOCK *** ---- To fix that, this introduces a finer regex_lock for each ftrace_ops. ftrace_regex_lock is too big of a lock which protects all filter/notrace_hash operations, but it doesn't need to be a global lock after supporting multiple ftrace_ops because each ftrace_ops has its own filter/notrace_hash. Link: http://lkml.kernel.org/r/20130509054417.30398.84254.stgit@mhiramat-M0-7522 Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Tom Zanussi <tom.zanussi@intel.com> Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> [ Added initialization flag and automate mutex initialization for non ftrace.c ftrace_probes. ] Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-05-09 05:44:17 +00:00
* INITIALIZED - The ftrace_ops has already been initialized (first use time
* register_ftrace_function() is called, it will initialized the ops)
* DELETED - The ops are being deleted, do not let them be registered again.
* ADDING - The ops is in the process of being added.
* REMOVING - The ops is in the process of being removed.
* MODIFYING - The ops is in the process of changing its filter functions.
ftrace/x86: Add dynamic allocated trampoline for ftrace_ops The current method of handling multiple function callbacks is to register a list function callback that calls all the other callbacks based on their hash tables and compare it to the function that the callback was called on. But this is very inefficient. For example, if you are tracing all functions in the kernel and then add a kprobe to a function such that the kprobe uses ftrace, the mcount trampoline will switch from calling the function trace callback to calling the list callback that will iterate over all registered ftrace_ops (in this case, the function tracer and the kprobes callback). That means for every function being traced it checks the hash of the ftrace_ops for function tracing and kprobes, even though the kprobes is only set at a single function. The kprobes ftrace_ops is checked for every function being traced! Instead of calling the list function for functions that are only being traced by a single callback, we can call a dynamically allocated trampoline that calls the callback directly. The function graph tracer already uses a direct call trampoline when it is being traced by itself but it is not dynamically allocated. It's trampoline is static in the kernel core. The infrastructure that called the function graph trampoline can also be used to call a dynamically allocated one. For now, only ftrace_ops that are not dynamically allocated can have a trampoline. That is, users such as function tracer or stack tracer. kprobes and perf allocate their ftrace_ops, and until there's a safe way to free the trampoline, it can not be used. The dynamically allocated ftrace_ops may, although, use the trampoline if the kernel is not compiled with CONFIG_PREEMPT. But that will come later. Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-07-03 03:23:31 +00:00
* ALLOC_TRAMP - A dynamic trampoline was allocated by the core code.
* The arch specific code sets this flag when it allocated a
* trampoline. This lets the arch know that it can update the
* trampoline in case the callback function changes.
* The ftrace_ops trampoline can be set by the ftrace users, and
* in such cases the arch must not modify it. Only the arch ftrace
* core code should set this flag.
* IPMODIFY - The ops can modify the IP register. This can only be set with
* SAVE_REGS. If another ops with this flag set is already registered
* for any of the functions that this ops will be registered for, then
* this ops will fail to register or set_filter_ip.
* PID - Is affected by set_ftrace_pid (allows filtering on those pids)
* RCU - Set when the ops can only be called when RCU is watching.
* TRACE_ARRAY - The ops->private points to a trace_array descriptor.
* PERMANENT - Set when the ops is permanent and should not be affected by
* ftrace_enabled.
* DIRECT - Used by the direct ftrace_ops helper for direct functions
* (internal ftrace only, should not be used by others)
*/
enum {
FTRACE_OPS_FL_ENABLED = BIT(0),
FTRACE_OPS_FL_DYNAMIC = BIT(1),
FTRACE_OPS_FL_SAVE_REGS = BIT(2),
FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = BIT(3),
FTRACE_OPS_FL_RECURSION = BIT(4),
FTRACE_OPS_FL_STUB = BIT(5),
FTRACE_OPS_FL_INITIALIZED = BIT(6),
FTRACE_OPS_FL_DELETED = BIT(7),
FTRACE_OPS_FL_ADDING = BIT(8),
FTRACE_OPS_FL_REMOVING = BIT(9),
FTRACE_OPS_FL_MODIFYING = BIT(10),
FTRACE_OPS_FL_ALLOC_TRAMP = BIT(11),
FTRACE_OPS_FL_IPMODIFY = BIT(12),
FTRACE_OPS_FL_PID = BIT(13),
FTRACE_OPS_FL_RCU = BIT(14),
FTRACE_OPS_FL_TRACE_ARRAY = BIT(15),
FTRACE_OPS_FL_PERMANENT = BIT(16),
FTRACE_OPS_FL_DIRECT = BIT(17),
};
#ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
#define FTRACE_OPS_FL_SAVE_ARGS FTRACE_OPS_FL_SAVE_REGS
#else
#define FTRACE_OPS_FL_SAVE_ARGS 0
#endif
ftrace: Allow IPMODIFY and DIRECT ops on the same function IPMODIFY (livepatch) and DIRECT (bpf trampoline) ops are both important users of ftrace. It is necessary to allow them work on the same function at the same time. First, DIRECT ops no longer specify IPMODIFY flag. Instead, DIRECT flag is handled together with IPMODIFY flag in __ftrace_hash_update_ipmodify(). Then, a callback function, ops_func, is added to ftrace_ops. This is used by ftrace core code to understand whether the DIRECT ops can share with an IPMODIFY ops. To share with IPMODIFY ops, the DIRECT ops need to implement the callback function and adjust the direct trampoline accordingly. If DIRECT ops is attached before the IPMODIFY ops, ftrace core code calls ENABLE_SHARE_IPMODIFY_PEER on the DIRECT ops before registering the IPMODIFY ops. If IPMODIFY ops is attached before the DIRECT ops, ftrace core code calls ENABLE_SHARE_IPMODIFY_SELF in __ftrace_hash_update_ipmodify. Owner of the DIRECT ops may return 0 if the DIRECT trampoline can share with IPMODIFY, so error code otherwise. The error code is propagated to register_ftrace_direct_multi so that onwer of the DIRECT trampoline can handle it properly. For more details, please refer to comment before enum ftrace_ops_cmd. Signed-off-by: Song Liu <song@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org> Link: https://lore.kernel.org/all/20220602193706.2607681-2-song@kernel.org/ Link: https://lore.kernel.org/all/20220718055449.3960512-1-song@kernel.org/ Link: https://lore.kernel.org/bpf/20220720002126.803253-3-song@kernel.org
2022-07-20 00:21:24 +00:00
/*
* FTRACE_OPS_CMD_* commands allow the ftrace core logic to request changes
* to a ftrace_ops. Note, the requests may fail.
*
* ENABLE_SHARE_IPMODIFY_SELF - enable a DIRECT ops to work on the same
* function as an ops with IPMODIFY. Called
* when the DIRECT ops is being registered.
* This is called with both direct_mutex and
* ftrace_lock are locked.
*
* ENABLE_SHARE_IPMODIFY_PEER - enable a DIRECT ops to work on the same
* function as an ops with IPMODIFY. Called
* when the other ops (the one with IPMODIFY)
* is being registered.
* This is called with direct_mutex locked.
*
* DISABLE_SHARE_IPMODIFY_PEER - disable a DIRECT ops to work on the same
* function as an ops with IPMODIFY. Called
* when the other ops (the one with IPMODIFY)
* is being unregistered.
* This is called with direct_mutex locked.
*/
enum ftrace_ops_cmd {
FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_SELF,
FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_PEER,
FTRACE_OPS_CMD_DISABLE_SHARE_IPMODIFY_PEER,
};
/*
* For most ftrace_ops_cmd,
* Returns:
* 0 - Success.
* Negative on failure. The return value is dependent on the
* callback.
*/
typedef int (*ftrace_ops_func_t)(struct ftrace_ops *op, enum ftrace_ops_cmd cmd);
ftrace: Allow ftrace_ops to use the hashes from other ops Currently the top level debug file system function tracer shares its ftrace_ops with the function graph tracer. This was thought to be fine because the tracers are not used together, as one can only enable function or function_graph tracer in the current_tracer file. But that assumption proved to be incorrect. The function profiler can use the function graph tracer when function tracing is enabled. Since all function graph users uses the function tracing ftrace_ops this causes a conflict and when a user enables both function profiling as well as the function tracer it will crash ftrace and disable it. The quick solution so far is to move them as separate ftrace_ops like it was earlier. The problem though is to synchronize the functions that are traced because both function and function_graph tracer are limited by the selections made in the set_ftrace_filter and set_ftrace_notrace files. To handle this, a new structure is made called ftrace_ops_hash. This structure will now hold the filter_hash and notrace_hash, and the ftrace_ops will point to this structure. That will allow two ftrace_ops to share the same hashes. Since most ftrace_ops do not share the hashes, and to keep allocation simple, the ftrace_ops structure will include both a pointer to the ftrace_ops_hash called func_hash, as well as the structure itself, called local_hash. When the ops are registered, the func_hash pointer will be initialized to point to the local_hash within the ftrace_ops structure. Some of the ftrace internal ftrace_ops will be initialized statically. This will allow for the function and function_graph tracer to have separate ops but still share the same hash tables that determine what functions they trace. Cc: stable@vger.kernel.org # 3.16 (apply after 3.17-rc4 is out) Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-08-15 21:23:02 +00:00
#ifdef CONFIG_DYNAMIC_FTRACE
/* The hash used to know what functions callbacks trace */
struct ftrace_ops_hash {
struct ftrace_hash __rcu *notrace_hash;
struct ftrace_hash __rcu *filter_hash;
ftrace: Allow ftrace_ops to use the hashes from other ops Currently the top level debug file system function tracer shares its ftrace_ops with the function graph tracer. This was thought to be fine because the tracers are not used together, as one can only enable function or function_graph tracer in the current_tracer file. But that assumption proved to be incorrect. The function profiler can use the function graph tracer when function tracing is enabled. Since all function graph users uses the function tracing ftrace_ops this causes a conflict and when a user enables both function profiling as well as the function tracer it will crash ftrace and disable it. The quick solution so far is to move them as separate ftrace_ops like it was earlier. The problem though is to synchronize the functions that are traced because both function and function_graph tracer are limited by the selections made in the set_ftrace_filter and set_ftrace_notrace files. To handle this, a new structure is made called ftrace_ops_hash. This structure will now hold the filter_hash and notrace_hash, and the ftrace_ops will point to this structure. That will allow two ftrace_ops to share the same hashes. Since most ftrace_ops do not share the hashes, and to keep allocation simple, the ftrace_ops structure will include both a pointer to the ftrace_ops_hash called func_hash, as well as the structure itself, called local_hash. When the ops are registered, the func_hash pointer will be initialized to point to the local_hash within the ftrace_ops structure. Some of the ftrace internal ftrace_ops will be initialized statically. This will allow for the function and function_graph tracer to have separate ops but still share the same hash tables that determine what functions they trace. Cc: stable@vger.kernel.org # 3.16 (apply after 3.17-rc4 is out) Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-08-15 21:23:02 +00:00
struct mutex regex_lock;
};
void ftrace_free_init_mem(void);
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 12:35:38 +00:00
void ftrace_free_mem(struct module *mod, void *start, void *end);
#else
static inline void ftrace_free_init_mem(void)
{
ftrace_boot_snapshot();
}
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 12:35:38 +00:00
static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { }
ftrace: Allow ftrace_ops to use the hashes from other ops Currently the top level debug file system function tracer shares its ftrace_ops with the function graph tracer. This was thought to be fine because the tracers are not used together, as one can only enable function or function_graph tracer in the current_tracer file. But that assumption proved to be incorrect. The function profiler can use the function graph tracer when function tracing is enabled. Since all function graph users uses the function tracing ftrace_ops this causes a conflict and when a user enables both function profiling as well as the function tracer it will crash ftrace and disable it. The quick solution so far is to move them as separate ftrace_ops like it was earlier. The problem though is to synchronize the functions that are traced because both function and function_graph tracer are limited by the selections made in the set_ftrace_filter and set_ftrace_notrace files. To handle this, a new structure is made called ftrace_ops_hash. This structure will now hold the filter_hash and notrace_hash, and the ftrace_ops will point to this structure. That will allow two ftrace_ops to share the same hashes. Since most ftrace_ops do not share the hashes, and to keep allocation simple, the ftrace_ops structure will include both a pointer to the ftrace_ops_hash called func_hash, as well as the structure itself, called local_hash. When the ops are registered, the func_hash pointer will be initialized to point to the local_hash within the ftrace_ops structure. Some of the ftrace internal ftrace_ops will be initialized statically. This will allow for the function and function_graph tracer to have separate ops but still share the same hash tables that determine what functions they trace. Cc: stable@vger.kernel.org # 3.16 (apply after 3.17-rc4 is out) Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-08-15 21:23:02 +00:00
#endif
/*
* Note, ftrace_ops can be referenced outside of RCU protection, unless
* the RCU flag is set. If ftrace_ops is allocated and not part of kernel
* core data, the unregistering of it will perform a scheduling on all CPUs
* to make sure that there are no more users. Depending on the load of the
* system that may take a bit of time.
*
* Any private data added must also take care not to be freed and if private
* data is added to a ftrace_ops that is in core code, the user of the
* ftrace_ops must perform a schedule_on_each_cpu() before freeing it.
*/
struct ftrace_ops {
ftrace_func_t func;
struct ftrace_ops __rcu *next;
unsigned long flags;
void *private;
ftrace_func_t saved_func;
#ifdef CONFIG_DYNAMIC_FTRACE
ftrace: Allow ftrace_ops to use the hashes from other ops Currently the top level debug file system function tracer shares its ftrace_ops with the function graph tracer. This was thought to be fine because the tracers are not used together, as one can only enable function or function_graph tracer in the current_tracer file. But that assumption proved to be incorrect. The function profiler can use the function graph tracer when function tracing is enabled. Since all function graph users uses the function tracing ftrace_ops this causes a conflict and when a user enables both function profiling as well as the function tracer it will crash ftrace and disable it. The quick solution so far is to move them as separate ftrace_ops like it was earlier. The problem though is to synchronize the functions that are traced because both function and function_graph tracer are limited by the selections made in the set_ftrace_filter and set_ftrace_notrace files. To handle this, a new structure is made called ftrace_ops_hash. This structure will now hold the filter_hash and notrace_hash, and the ftrace_ops will point to this structure. That will allow two ftrace_ops to share the same hashes. Since most ftrace_ops do not share the hashes, and to keep allocation simple, the ftrace_ops structure will include both a pointer to the ftrace_ops_hash called func_hash, as well as the structure itself, called local_hash. When the ops are registered, the func_hash pointer will be initialized to point to the local_hash within the ftrace_ops structure. Some of the ftrace internal ftrace_ops will be initialized statically. This will allow for the function and function_graph tracer to have separate ops but still share the same hash tables that determine what functions they trace. Cc: stable@vger.kernel.org # 3.16 (apply after 3.17-rc4 is out) Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-08-15 21:23:02 +00:00
struct ftrace_ops_hash local_hash;
struct ftrace_ops_hash *func_hash;
ftrace: Replace tramp_hash with old_*_hash to save space Allowing function callbacks to declare their own trampolines requires that each ftrace_ops that has a trampoline must have some sort of accounting that keeps track of which ops has a trampoline attached to a record. The easy way to solve this was to add a "tramp_hash" that created a hash entry for every function that a ops uses with a trampoline. But since we can have literally tens of thousands of functions being traced, that means we need tens of thousands of descriptors to map the ops to the function in the hash. This is quite expensive and can cause enabling and disabling the function graph tracer to take some time to start and stop. It can take up to several seconds to disable or enable all functions in the function graph tracer for this reason. The better approach albeit more complex, is to keep track of how ops are being enabled and disabled, and use that along with the counting of the number of ops attached to records, to determive what ops has a trampoline attached to a record at enabling and disabling of tracing. To do this, the tramp_hash has been replaced with an old_filter_hash and old_notrace_hash, which get the copy of the ops filter_hash and notrace_hash respectively. The old hashes is kept until the ops has been modified or removed and the old hashes are used with the logic of the accounting to determine the ops that have the trampoline of a record. The reason this has less of a footprint is due to the trick that an "empty" hash in the filter_hash means "all functions" and an empty hash in the notrace hash means "no functions" in the hash. This is much more efficienct, doesn't have the delay, and takes up much less memory, as we do not need to map all the functions but just figure out which functions are mapped at the time it is enabled or disabled. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-07-24 16:25:47 +00:00
struct ftrace_ops_hash old_hash;
ftrace: Optimize function graph to be called directly Function graph tracing is a bit different than the function tracers, as it is processed after either the ftrace_caller or ftrace_regs_caller and we only have one place to modify the jump to ftrace_graph_caller, the jump needs to happen after the restore of registeres. The function graph tracer is dependent on the function tracer, where even if the function graph tracing is going on by itself, the save and restore of registers is still done for function tracing regardless of if function tracing is happening, before it calls the function graph code. If there's no function tracing happening, it is possible to just call the function graph tracer directly, and avoid the wasted effort to save and restore regs for function tracing. This requires adding new flags to the dyn_ftrace records: FTRACE_FL_TRAMP FTRACE_FL_TRAMP_EN The first is set if the count for the record is one, and the ftrace_ops associated to that record has its own trampoline. That way the mcount code can call that trampoline directly. In the future, trampolines can be added to arbitrary ftrace_ops, where you can have two or more ftrace_ops registered to ftrace (like kprobes and perf) and if they are not tracing the same functions, then instead of doing a loop to check all registered ftrace_ops against their hashes, just call the ftrace_ops trampoline directly, which would call the registered ftrace_ops function directly. Without this patch perf showed: 0.05% hackbench [kernel.kallsyms] [k] ftrace_caller 0.05% hackbench [kernel.kallsyms] [k] arch_local_irq_save 0.05% hackbench [kernel.kallsyms] [k] native_sched_clock 0.04% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] preempt_trace 0.04% hackbench [kernel.kallsyms] [k] prepare_ftrace_return 0.04% hackbench [kernel.kallsyms] [k] __this_cpu_preempt_check 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller See that the ftrace_caller took up more time than the ftrace_graph_caller did. With this patch: 0.05% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] call_filter_check_discard 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller 0.04% hackbench [kernel.kallsyms] [k] sched_clock The ftrace_caller is no where to be found and ftrace_graph_caller still takes up the same percentage. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:56:17 +00:00
unsigned long trampoline;
unsigned long trampoline_size;
struct list_head list;
ftrace: Allow IPMODIFY and DIRECT ops on the same function IPMODIFY (livepatch) and DIRECT (bpf trampoline) ops are both important users of ftrace. It is necessary to allow them work on the same function at the same time. First, DIRECT ops no longer specify IPMODIFY flag. Instead, DIRECT flag is handled together with IPMODIFY flag in __ftrace_hash_update_ipmodify(). Then, a callback function, ops_func, is added to ftrace_ops. This is used by ftrace core code to understand whether the DIRECT ops can share with an IPMODIFY ops. To share with IPMODIFY ops, the DIRECT ops need to implement the callback function and adjust the direct trampoline accordingly. If DIRECT ops is attached before the IPMODIFY ops, ftrace core code calls ENABLE_SHARE_IPMODIFY_PEER on the DIRECT ops before registering the IPMODIFY ops. If IPMODIFY ops is attached before the DIRECT ops, ftrace core code calls ENABLE_SHARE_IPMODIFY_SELF in __ftrace_hash_update_ipmodify. Owner of the DIRECT ops may return 0 if the DIRECT trampoline can share with IPMODIFY, so error code otherwise. The error code is propagated to register_ftrace_direct_multi so that onwer of the DIRECT trampoline can handle it properly. For more details, please refer to comment before enum ftrace_ops_cmd. Signed-off-by: Song Liu <song@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org> Link: https://lore.kernel.org/all/20220602193706.2607681-2-song@kernel.org/ Link: https://lore.kernel.org/all/20220718055449.3960512-1-song@kernel.org/ Link: https://lore.kernel.org/bpf/20220720002126.803253-3-song@kernel.org
2022-07-20 00:21:24 +00:00
ftrace_ops_func_t ops_func;
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
unsigned long direct_call;
#endif
#endif
};
x86/ftrace: Have ftrace trampolines turn read-only at the end of system boot up Booting one of my machines, it triggered the following crash: Kernel/User page tables isolation: enabled ftrace: allocating 36577 entries in 143 pages Starting tracer 'function' BUG: unable to handle page fault for address: ffffffffa000005c #PF: supervisor write access in kernel mode #PF: error_code(0x0003) - permissions violation PGD 2014067 P4D 2014067 PUD 2015063 PMD 7b253067 PTE 7b252061 Oops: 0003 [#1] PREEMPT SMP PTI CPU: 0 PID: 0 Comm: swapper Not tainted 5.4.0-test+ #24 Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./To be filled by O.E.M., BIOS SDBLI944.86P 05/08/2007 RIP: 0010:text_poke_early+0x4a/0x58 Code: 34 24 48 89 54 24 08 e8 bf 72 0b 00 48 8b 34 24 48 8b 4c 24 08 84 c0 74 0b 48 89 df f3 a4 48 83 c4 10 5b c3 9c 58 fa 48 89 df <f3> a4 50 9d 48 83 c4 10 5b e9 d6 f9 ff ff 0 41 57 49 RSP: 0000:ffffffff82003d38 EFLAGS: 00010046 RAX: 0000000000000046 RBX: ffffffffa000005c RCX: 0000000000000005 RDX: 0000000000000005 RSI: ffffffff825b9a90 RDI: ffffffffa000005c RBP: ffffffffa000005c R08: 0000000000000000 R09: ffffffff8206e6e0 R10: ffff88807b01f4c0 R11: ffffffff8176c106 R12: ffffffff8206e6e0 R13: ffffffff824f2440 R14: 0000000000000000 R15: ffffffff8206eac0 FS: 0000000000000000(0000) GS:ffff88807d400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffa000005c CR3: 0000000002012000 CR4: 00000000000006b0 Call Trace: text_poke_bp+0x27/0x64 ? mutex_lock+0x36/0x5d arch_ftrace_update_trampoline+0x287/0x2d5 ? ftrace_replace_code+0x14b/0x160 ? ftrace_update_ftrace_func+0x65/0x6c __register_ftrace_function+0x6d/0x81 ftrace_startup+0x23/0xc1 register_ftrace_function+0x20/0x37 func_set_flag+0x59/0x77 __set_tracer_option.isra.19+0x20/0x3e trace_set_options+0xd6/0x13e apply_trace_boot_options+0x44/0x6d register_tracer+0x19e/0x1ac early_trace_init+0x21b/0x2c9 start_kernel+0x241/0x518 ? load_ucode_intel_bsp+0x21/0x52 secondary_startup_64+0xa4/0xb0 I was able to trigger it on other machines, when I added to the kernel command line of both "ftrace=function" and "trace_options=func_stack_trace". The cause is the "ftrace=function" would register the function tracer and create a trampoline, and it will set it as executable and read-only. Then the "trace_options=func_stack_trace" would then update the same trampoline to include the stack tracer version of the function tracer. But since the trampoline already exists, it updates it with text_poke_bp(). The problem is that text_poke_bp() called while system_state == SYSTEM_BOOTING, it will simply do a memcpy() and not the page mapping, as it would think that the text is still read-write. But in this case it is not, and we take a fault and crash. Instead, lets keep the ftrace trampolines read-write during boot up, and then when the kernel executable text is set to read-only, the ftrace trampolines get set to read-only as well. Link: https://lkml.kernel.org/r/20200430202147.4dc6e2de@oasis.local.home Cc: Ingo Molnar <mingo@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: stable@vger.kernel.org Fixes: 768ae4406a5c ("x86/ftrace: Use text_poke()") Acked-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2020-05-01 00:21:47 +00:00
extern struct ftrace_ops __rcu *ftrace_ops_list;
extern struct ftrace_ops ftrace_list_end;
/*
* Traverse the ftrace_ops_list, invoking all entries. The reason that we
x86/ftrace: Have ftrace trampolines turn read-only at the end of system boot up Booting one of my machines, it triggered the following crash: Kernel/User page tables isolation: enabled ftrace: allocating 36577 entries in 143 pages Starting tracer 'function' BUG: unable to handle page fault for address: ffffffffa000005c #PF: supervisor write access in kernel mode #PF: error_code(0x0003) - permissions violation PGD 2014067 P4D 2014067 PUD 2015063 PMD 7b253067 PTE 7b252061 Oops: 0003 [#1] PREEMPT SMP PTI CPU: 0 PID: 0 Comm: swapper Not tainted 5.4.0-test+ #24 Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./To be filled by O.E.M., BIOS SDBLI944.86P 05/08/2007 RIP: 0010:text_poke_early+0x4a/0x58 Code: 34 24 48 89 54 24 08 e8 bf 72 0b 00 48 8b 34 24 48 8b 4c 24 08 84 c0 74 0b 48 89 df f3 a4 48 83 c4 10 5b c3 9c 58 fa 48 89 df <f3> a4 50 9d 48 83 c4 10 5b e9 d6 f9 ff ff 0 41 57 49 RSP: 0000:ffffffff82003d38 EFLAGS: 00010046 RAX: 0000000000000046 RBX: ffffffffa000005c RCX: 0000000000000005 RDX: 0000000000000005 RSI: ffffffff825b9a90 RDI: ffffffffa000005c RBP: ffffffffa000005c R08: 0000000000000000 R09: ffffffff8206e6e0 R10: ffff88807b01f4c0 R11: ffffffff8176c106 R12: ffffffff8206e6e0 R13: ffffffff824f2440 R14: 0000000000000000 R15: ffffffff8206eac0 FS: 0000000000000000(0000) GS:ffff88807d400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffa000005c CR3: 0000000002012000 CR4: 00000000000006b0 Call Trace: text_poke_bp+0x27/0x64 ? mutex_lock+0x36/0x5d arch_ftrace_update_trampoline+0x287/0x2d5 ? ftrace_replace_code+0x14b/0x160 ? ftrace_update_ftrace_func+0x65/0x6c __register_ftrace_function+0x6d/0x81 ftrace_startup+0x23/0xc1 register_ftrace_function+0x20/0x37 func_set_flag+0x59/0x77 __set_tracer_option.isra.19+0x20/0x3e trace_set_options+0xd6/0x13e apply_trace_boot_options+0x44/0x6d register_tracer+0x19e/0x1ac early_trace_init+0x21b/0x2c9 start_kernel+0x241/0x518 ? load_ucode_intel_bsp+0x21/0x52 secondary_startup_64+0xa4/0xb0 I was able to trigger it on other machines, when I added to the kernel command line of both "ftrace=function" and "trace_options=func_stack_trace". The cause is the "ftrace=function" would register the function tracer and create a trampoline, and it will set it as executable and read-only. Then the "trace_options=func_stack_trace" would then update the same trampoline to include the stack tracer version of the function tracer. But since the trampoline already exists, it updates it with text_poke_bp(). The problem is that text_poke_bp() called while system_state == SYSTEM_BOOTING, it will simply do a memcpy() and not the page mapping, as it would think that the text is still read-write. But in this case it is not, and we take a fault and crash. Instead, lets keep the ftrace trampolines read-write during boot up, and then when the kernel executable text is set to read-only, the ftrace trampolines get set to read-only as well. Link: https://lkml.kernel.org/r/20200430202147.4dc6e2de@oasis.local.home Cc: Ingo Molnar <mingo@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: stable@vger.kernel.org Fixes: 768ae4406a5c ("x86/ftrace: Use text_poke()") Acked-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2020-05-01 00:21:47 +00:00
* can use rcu_dereference_raw_check() is that elements removed from this list
* are simply leaked, so there is no need to interact with a grace-period
* mechanism. The rcu_dereference_raw_check() calls are needed to handle
* concurrent insertions into the ftrace_ops_list.
x86/ftrace: Have ftrace trampolines turn read-only at the end of system boot up Booting one of my machines, it triggered the following crash: Kernel/User page tables isolation: enabled ftrace: allocating 36577 entries in 143 pages Starting tracer 'function' BUG: unable to handle page fault for address: ffffffffa000005c #PF: supervisor write access in kernel mode #PF: error_code(0x0003) - permissions violation PGD 2014067 P4D 2014067 PUD 2015063 PMD 7b253067 PTE 7b252061 Oops: 0003 [#1] PREEMPT SMP PTI CPU: 0 PID: 0 Comm: swapper Not tainted 5.4.0-test+ #24 Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./To be filled by O.E.M., BIOS SDBLI944.86P 05/08/2007 RIP: 0010:text_poke_early+0x4a/0x58 Code: 34 24 48 89 54 24 08 e8 bf 72 0b 00 48 8b 34 24 48 8b 4c 24 08 84 c0 74 0b 48 89 df f3 a4 48 83 c4 10 5b c3 9c 58 fa 48 89 df <f3> a4 50 9d 48 83 c4 10 5b e9 d6 f9 ff ff 0 41 57 49 RSP: 0000:ffffffff82003d38 EFLAGS: 00010046 RAX: 0000000000000046 RBX: ffffffffa000005c RCX: 0000000000000005 RDX: 0000000000000005 RSI: ffffffff825b9a90 RDI: ffffffffa000005c RBP: ffffffffa000005c R08: 0000000000000000 R09: ffffffff8206e6e0 R10: ffff88807b01f4c0 R11: ffffffff8176c106 R12: ffffffff8206e6e0 R13: ffffffff824f2440 R14: 0000000000000000 R15: ffffffff8206eac0 FS: 0000000000000000(0000) GS:ffff88807d400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffa000005c CR3: 0000000002012000 CR4: 00000000000006b0 Call Trace: text_poke_bp+0x27/0x64 ? mutex_lock+0x36/0x5d arch_ftrace_update_trampoline+0x287/0x2d5 ? ftrace_replace_code+0x14b/0x160 ? ftrace_update_ftrace_func+0x65/0x6c __register_ftrace_function+0x6d/0x81 ftrace_startup+0x23/0xc1 register_ftrace_function+0x20/0x37 func_set_flag+0x59/0x77 __set_tracer_option.isra.19+0x20/0x3e trace_set_options+0xd6/0x13e apply_trace_boot_options+0x44/0x6d register_tracer+0x19e/0x1ac early_trace_init+0x21b/0x2c9 start_kernel+0x241/0x518 ? load_ucode_intel_bsp+0x21/0x52 secondary_startup_64+0xa4/0xb0 I was able to trigger it on other machines, when I added to the kernel command line of both "ftrace=function" and "trace_options=func_stack_trace". The cause is the "ftrace=function" would register the function tracer and create a trampoline, and it will set it as executable and read-only. Then the "trace_options=func_stack_trace" would then update the same trampoline to include the stack tracer version of the function tracer. But since the trampoline already exists, it updates it with text_poke_bp(). The problem is that text_poke_bp() called while system_state == SYSTEM_BOOTING, it will simply do a memcpy() and not the page mapping, as it would think that the text is still read-write. But in this case it is not, and we take a fault and crash. Instead, lets keep the ftrace trampolines read-write during boot up, and then when the kernel executable text is set to read-only, the ftrace trampolines get set to read-only as well. Link: https://lkml.kernel.org/r/20200430202147.4dc6e2de@oasis.local.home Cc: Ingo Molnar <mingo@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: stable@vger.kernel.org Fixes: 768ae4406a5c ("x86/ftrace: Use text_poke()") Acked-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2020-05-01 00:21:47 +00:00
*
* Silly Alpha and silly pointer-speculation compiler optimizations!
*/
#define do_for_each_ftrace_op(op, list) \
op = rcu_dereference_raw_check(list); \
do
/*
* Optimized for just a single item in the list (as that is the normal case).
*/
#define while_for_each_ftrace_op(op) \
while (likely(op = rcu_dereference_raw_check((op)->next)) && \
unlikely((op) != &ftrace_list_end))
tracing/function-return-tracer: support for dynamic ftrace on function return tracer This patch adds the support for dynamic tracing on the function return tracer. The whole difference with normal dynamic function tracing is that we don't need to hook on a particular callback. The only pro that we want is to nop or set dynamically the calls to ftrace_caller (which is ftrace_return_caller here). Some security checks ensure that we are not trying to launch dynamic tracing for return tracing while normal function tracing is already running. An example of trace with getnstimeofday set as a filter: ktime_get_ts+0x22/0x50 -> getnstimeofday (2283 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1396 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1825 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1426 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1464 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1524 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1434 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1464 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1502 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1404 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1397 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1051 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1314 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1344 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1163 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1390 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1374 ns) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-16 05:02:06 +00:00
/*
* Type of the current tracing.
*/
enum ftrace_tracing_type_t {
FTRACE_TYPE_ENTER = 0, /* Hook the call of the function */
FTRACE_TYPE_RETURN, /* Hook the return of the function */
};
/* Current tracing type, default is FTRACE_TYPE_ENTER */
extern enum ftrace_tracing_type_t ftrace_tracing_type;
/*
* The ftrace_ops must be a static and should also
* be read_mostly. These functions do modify read_mostly variables
* so use them sparely. Never free an ftrace_op or modify the
* next pointer after it has been registered. Even after unregistering
* it, the next pointer may still be used internally.
*/
int register_ftrace_function(struct ftrace_ops *ops);
int unregister_ftrace_function(struct ftrace_ops *ops);
extern void ftrace_stub(unsigned long a0, unsigned long a1,
struct ftrace_ops *op, struct ftrace_regs *fregs);
int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs);
#else /* !CONFIG_FUNCTION_TRACER */
/*
* (un)register_ftrace_function must be a macro since the ops parameter
* must not be evaluated.
*/
#define register_ftrace_function(ops) ({ 0; })
#define unregister_ftrace_function(ops) ({ 0; })
static inline void ftrace_kill(void) { }
static inline void ftrace_free_init_mem(void) { }
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 12:35:38 +00:00
static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { }
static inline int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs)
{
return -EOPNOTSUPP;
}
#endif /* CONFIG_FUNCTION_TRACER */
ftrace: tracer for scheduler wakeup latency This patch adds the tracer that tracks the wakeup latency of the highest priority waking task. "wakeup" is added to /debugfs/tracing/available_tracers Also added to /debugfs/tracing tracing_max_latency holds the current max latency for the wakeup wakeup_thresh if set to other than zero, a log will be recorded for every wakeup that takes longer than the number entered in here (usecs for all counters) (deletes previous trace) Examples: (with ftrace_enabled = 0) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 26 us, #2/2, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/0-3 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / quilt-8551 0d..3 0us+: wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) quilt-8551 0d..4 26us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ (with ftrace_enabled = 1) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 -------------------------------------------------------------------- latency: 36 us, #45/45, CPU#0 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/1-5 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / bash-10653 1d..3 0us : wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) bash-10653 1d..3 1us : try_to_wake_up+0x271/0x2e7 <ffffffff80233dcf> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..2 2us : try_to_wake_up+0x296/0x2e7 <ffffffff80233df4> (update_rq_clock+0x9/0x20 <ffffffff802303f3>) bash-10653 1d..2 2us : update_rq_clock+0x1e/0x20 <ffffffff80230408> (__update_rq_clock+0xc/0x90 <ffffffff80230366>) bash-10653 1d..2 3us : __update_rq_clock+0x1b/0x90 <ffffffff80230375> (sched_clock+0x9/0x29 <ffffffff80214529>) bash-10653 1d..2 4us : try_to_wake_up+0x2a6/0x2e7 <ffffffff80233e04> (activate_task+0xc/0x3f <ffffffff8022ffca>) bash-10653 1d..2 4us : activate_task+0x2d/0x3f <ffffffff8022ffeb> (enqueue_task+0xe/0x66 <ffffffff8022ff66>) bash-10653 1d..2 5us : enqueue_task+0x5b/0x66 <ffffffff8022ffb3> (enqueue_task_rt+0x9/0x3c <ffffffff80233351>) bash-10653 1d..2 6us : try_to_wake_up+0x2ba/0x2e7 <ffffffff80233e18> (check_preempt_wakeup+0x12/0x99 <ffffffff80234f84>) [...] bash-10653 1d..5 33us : tracing_record_cmdline+0xcf/0xd4 <ffffffff80338aad> (_spin_unlock+0x9/0x33 <ffffffff8048d3ec>) bash-10653 1d..5 34us : _spin_unlock+0x19/0x33 <ffffffff8048d3fc> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..4 35us : wakeup_sched_switch+0x65/0x2ff <ffffffff80339f66> (_spin_lock_irqsave+0xc/0xa9 <ffffffff8048d08b>) bash-10653 1d..4 35us : _spin_lock_irqsave+0x19/0xa9 <ffffffff8048d098> (add_preempt_count+0xe/0x77 <ffffffff8023311a>) bash-10653 1d..4 36us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ The [...] was added here to not waste your email box space. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 19:20:42 +00:00
struct ftrace_func_entry {
struct hlist_node hlist;
unsigned long ip;
unsigned long direct; /* for direct lookup only */
};
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
extern int ftrace_direct_func_count;
unsigned long ftrace_find_rec_direct(unsigned long ip);
int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr);
int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr,
bool free_filters);
int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr);
int modify_ftrace_direct_nolock(struct ftrace_ops *ops, unsigned long addr);
ftrace: selftest: remove broken trace_direct_tramp The ftrace selftest code has a trace_direct_tramp() function which it uses as a direct call trampoline. This happens to work on x86, since the direct call's return address is in the usual place, and can be returned to via a RET, but in general the calling convention for direct calls is different from regular function calls, and requires a trampoline written in assembly. On s390, regular function calls place the return address in %r14, and an ftrace patch-site in an instrumented function places the trampoline's return address (which is within the instrumented function) in %r0, preserving the original %r14 value in-place. As a regular C function will return to the address in %r14, using a C function as the trampoline results in the trampoline returning to the caller of the instrumented function, skipping the body of the instrumented function. Note that the s390 issue is not detcted by the ftrace selftest code, as the instrumented function is trivial, and returning back into the caller happens to be equivalent. On arm64, regular function calls place the return address in x30, and an ftrace patch-site in an instrumented function saves this into r9 and places the trampoline's return address (within the instrumented function) in x30. A regular C function will return to the address in x30, but will not restore x9 into x30. Consequently, using a C function as the trampoline results in returning to the trampoline's return address having corrupted x30, such that when the instrumented function returns, it will return back into itself. To avoid future issues in this area, remove the trace_direct_tramp() function, and require that each architecture with direct calls provides a stub trampoline, named ftrace_stub_direct_tramp. This can be written to handle the architecture's trampoline calling convention, and in future could be used elsewhere (e.g. in the ftrace ops sample, to measure the overhead of direct calls), so we may as well always build it in. Link: https://lkml.kernel.org/r/20230321140424.345218-8-revest@chromium.org Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Li Huafei <lihuafei1@huawei.com> Cc: Xu Kuohai <xukuohai@huawei.com> Signed-off-by: Florent Revest <revest@chromium.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-03-21 14:04:24 +00:00
void ftrace_stub_direct_tramp(void);
#else
struct ftrace_ops;
# define ftrace_direct_func_count 0
static inline unsigned long ftrace_find_rec_direct(unsigned long ip)
{
return 0;
}
static inline int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
{
return -ENODEV;
}
static inline int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr,
bool free_filters)
{
return -ENODEV;
}
static inline int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
{
return -ENODEV;
}
static inline int modify_ftrace_direct_nolock(struct ftrace_ops *ops, unsigned long addr)
{
return -ENODEV;
}
/*
* This must be implemented by the architecture.
* It is the way the ftrace direct_ops helper, when called
* via ftrace (because there's other callbacks besides the
* direct call), can inform the architecture's trampoline that this
* routine has a direct caller, and what the caller is.
*
* For example, in x86, it returns the direct caller
* callback function via the regs->orig_ax parameter.
* Then in the ftrace trampoline, if this is set, it makes
* the return from the trampoline jump to the direct caller
* instead of going back to the function it just traced.
*/
static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs,
unsigned long addr) { }
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
#ifdef CONFIG_STACK_TRACER
extern int stack_tracer_enabled;
tracing: Cleanup stack trace code - Remove the extra array member of stack_dump_trace[] along with the ARRAY_SIZE - 1 initialization for struct stack_trace :: max_entries. Both are historical leftovers of no value. The stack tracer never exceeds the array and there is no extra storage requirement either. - Make variables which are only used in trace_stack.c static. - Simplify the enable/disable logic. - Rename stack_trace_print() as it's using the stack_trace_ namespace. Free the name up for stack trace related functions. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Steven Rostedt <rostedt@goodmis.org> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Alexander Potapenko <glider@google.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: linux-mm@kvack.org Cc: David Rientjes <rientjes@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: kasan-dev@googlegroups.com Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Akinobu Mita <akinobu.mita@gmail.com> Cc: Christoph Hellwig <hch@lst.de> Cc: iommu@lists.linux-foundation.org Cc: Robin Murphy <robin.murphy@arm.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Johannes Thumshirn <jthumshirn@suse.de> Cc: David Sterba <dsterba@suse.com> Cc: Chris Mason <clm@fb.com> Cc: Josef Bacik <josef@toxicpanda.com> Cc: linux-btrfs@vger.kernel.org Cc: dm-devel@redhat.com Cc: Mike Snitzer <snitzer@redhat.com> Cc: Alasdair Kergon <agk@redhat.com> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: intel-gfx@lists.freedesktop.org Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Cc: dri-devel@lists.freedesktop.org Cc: David Airlie <airlied@linux.ie> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Tom Zanussi <tom.zanussi@linux.intel.com> Cc: Miroslav Benes <mbenes@suse.cz> Cc: linux-arch@vger.kernel.org Link: https://lkml.kernel.org/r/20190425094801.230654524@linutronix.de
2019-04-25 09:44:54 +00:00
int stack_trace_sysctl(struct ctl_table *table, int write, void *buffer,
size_t *lenp, loff_t *ppos);
/* DO NOT MODIFY THIS VARIABLE DIRECTLY! */
DECLARE_PER_CPU(int, disable_stack_tracer);
/**
* stack_tracer_disable - temporarily disable the stack tracer
*
* There's a few locations (namely in RCU) where stack tracing
* cannot be executed. This function is used to disable stack
* tracing during those critical sections.
*
* This function must be called with preemption or interrupts
* disabled and stack_tracer_enable() must be called shortly after
* while preemption or interrupts are still disabled.
*/
static inline void stack_tracer_disable(void)
{
/* Preemption or interrupts must be disabled */
if (IS_ENABLED(CONFIG_DEBUG_PREEMPT))
WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
this_cpu_inc(disable_stack_tracer);
}
/**
* stack_tracer_enable - re-enable the stack tracer
*
* After stack_tracer_disable() is called, stack_tracer_enable()
* must be called shortly afterward.
*/
static inline void stack_tracer_enable(void)
{
if (IS_ENABLED(CONFIG_DEBUG_PREEMPT))
WARN_ON_ONCE(!preempt_count() || !irqs_disabled());
this_cpu_dec(disable_stack_tracer);
}
#else
static inline void stack_tracer_disable(void) { }
static inline void stack_tracer_enable(void) { }
#endif
ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 19:20:42 +00:00
#ifdef CONFIG_DYNAMIC_FTRACE
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 00:21:19 +00:00
void ftrace_arch_code_modify_prepare(void);
void ftrace_arch_code_modify_post_process(void);
enum ftrace_bug_type {
FTRACE_BUG_UNKNOWN,
FTRACE_BUG_INIT,
FTRACE_BUG_NOP,
FTRACE_BUG_CALL,
FTRACE_BUG_UPDATE,
};
extern enum ftrace_bug_type ftrace_bug_type;
/*
* Archs can set this to point to a variable that holds the value that was
* expected at the call site before calling ftrace_bug().
*/
extern const void *ftrace_expected;
void ftrace_bug(int err, struct dyn_ftrace *rec);
struct seq_file;
extern int ftrace_text_reserved(const void *start, const void *end);
struct ftrace_ops *ftrace_ops_trampoline(unsigned long addr);
bool is_ftrace_trampoline(unsigned long addr);
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
/*
* The dyn_ftrace record's flags field is split into two parts.
* the first part which is '0-FTRACE_REF_MAX' is a counter of
* the number of callbacks that have registered the function that
* the dyn_ftrace descriptor represents.
*
* The second part is a mask:
* ENABLED - the function is being traced
* REGS - the record wants the function to save regs
* REGS_EN - the function is set up to save regs.
* IPMODIFY - the record allows for the IP address to be changed.
ftrace: Add infrastructure for delayed enabling of module functions Qiu Peiyang pointed out that there's a race when enabling function tracing and loading a module. In order to make the modifications of converting nops in the prologue of functions into callbacks, the text needs to be converted from read-only to read-write. When enabling function tracing, the text permission is updated, the functions are modified, and then they are put back. When loading a module, the updates to convert function calls to mcount is done before the module text is set to read-only. But after it is done, the module text is visible by the function tracer. Thus we have the following race: CPU 0 CPU 1 ----- ----- start function tracing set text to read-write load_module add functions to ftrace set module text read-only update all functions to callbacks modify module functions too < Can't it's read-only > When this happens, ftrace detects the issue and disables itself till the next reboot. To fix this, a new DISABLED flag is added for ftrace records, which all module functions get when they are added. Then later, after the module code is all set, the records will have the DISABLED flag cleared, and they will be enabled if any callback wants all functions to be traced. Note, this doesn't add the delay to later. It simply changes the ftrace_module_init() to do both the setting of DISABLED records, and then immediately calls the enable code. This helps with testing this new code as it has the same behavior as previously. Another change will come after this to have the ftrace_module_enable() called after the text is set to read-only. Cc: Qiu Peiyang <peiyangx.qiu@intel.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2016-01-07 20:40:01 +00:00
* DISABLED - the record is not ready to be touched yet
* DIRECT - there is a direct function to call
ftrace: Add DYNAMIC_FTRACE_WITH_CALL_OPS Architectures without dynamic ftrace trampolines incur an overhead when multiple ftrace_ops are enabled with distinct filters. in these cases, each call site calls a common trampoline which uses ftrace_ops_list_func() to iterate over all enabled ftrace functions, and so incurs an overhead relative to the size of this list (including RCU protection overhead). Architectures with dynamic ftrace trampolines avoid this overhead for call sites which have a single associated ftrace_ops. In these cases, the dynamic trampoline is customized to branch directly to the relevant ftrace function, avoiding the list overhead. On some architectures it's impractical and/or undesirable to implement dynamic ftrace trampolines. For example, arm64 has limited branch ranges and cannot always directly branch from a call site to an arbitrary address (e.g. from a kernel text address to an arbitrary module address). Calls from modules to core kernel text can be indirected via PLTs (allocated at module load time) to address this, but the same is not possible from calls from core kernel text. Using an indirect branch from a call site to an arbitrary trampoline is possible, but requires several more instructions in the function prologue (or immediately before it), and/or comes with far more complex requirements for patching. Instead, this patch adds a new option, where an architecture can associate each call site with a pointer to an ftrace_ops, placed at a fixed offset from the call site. A shared trampoline can recover this pointer and call ftrace_ops::func() without needing to go via ftrace_ops_list_func(), avoiding the associated overhead. This avoids issues with branch range limitations, and avoids the need to allocate and manipulate dynamic trampolines, making it far simpler to implement and maintain, while having similar performance characteristics. Note that this allows for dynamic ftrace_ops to be invoked directly from an architecture's ftrace_caller trampoline, whereas existing code forces the use of ftrace_ops_get_list_func(), which is in part necessary to permit the ftrace_ops to be freed once unregistered *and* to avoid branch/address-generation range limitation on some architectures (e.g. where ops->func is a module address, and may be outside of the direct branch range for callsites within the main kernel image). The CALL_OPS approach avoids this problems and is safe as: * The existing synchronization in ftrace_shutdown() using ftrace_shutdown() using synchronize_rcu_tasks_rude() (and synchronize_rcu_tasks()) ensures that no tasks hold a stale reference to an ftrace_ops (e.g. in the middle of the ftrace_caller trampoline, or while invoking ftrace_ops::func), when that ftrace_ops is unregistered. Arguably this could also be relied upon for the existing scheme, permitting dynamic ftrace_ops to be invoked directly when ops->func is in range, but this will require additional logic to handle branch range limitations, and is not handled by this patch. * Each callsite's ftrace_ops pointer literal can hold any valid kernel address, and is updated atomically. As an architecture's ftrace_caller trampoline will atomically load the ops pointer then dereference ops->func, there is no risk of invoking ops->func with a mismatches ops pointer, and updates to the ops pointer do not require special care. A subsequent patch will implement architectures support for arm64. There should be no functional change as a result of this patch alone. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org> Cc: Florent Revest <revest@chromium.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20230123134603.1064407-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2023-01-23 13:45:56 +00:00
* CALL_OPS - the record can use callsite-specific ops
* CALL_OPS_EN - the function is set up to use callsite-specific ops
* TOUCHED - A callback was added since boot up
* MODIFIED - The function had IPMODIFY or DIRECT attached to it
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
*
* When a new ftrace_ops is registered and wants a function to save
* pt_regs, the rec->flags REGS is set. When the function has been
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
* set up to save regs, the REG_EN flag is set. Once a function
* starts saving regs it will do so until all ftrace_ops are removed
* from tracing that function.
*/
enum {
ftrace: Optimize function graph to be called directly Function graph tracing is a bit different than the function tracers, as it is processed after either the ftrace_caller or ftrace_regs_caller and we only have one place to modify the jump to ftrace_graph_caller, the jump needs to happen after the restore of registeres. The function graph tracer is dependent on the function tracer, where even if the function graph tracing is going on by itself, the save and restore of registers is still done for function tracing regardless of if function tracing is happening, before it calls the function graph code. If there's no function tracing happening, it is possible to just call the function graph tracer directly, and avoid the wasted effort to save and restore regs for function tracing. This requires adding new flags to the dyn_ftrace records: FTRACE_FL_TRAMP FTRACE_FL_TRAMP_EN The first is set if the count for the record is one, and the ftrace_ops associated to that record has its own trampoline. That way the mcount code can call that trampoline directly. In the future, trampolines can be added to arbitrary ftrace_ops, where you can have two or more ftrace_ops registered to ftrace (like kprobes and perf) and if they are not tracing the same functions, then instead of doing a loop to check all registered ftrace_ops against their hashes, just call the ftrace_ops trampoline directly, which would call the registered ftrace_ops function directly. Without this patch perf showed: 0.05% hackbench [kernel.kallsyms] [k] ftrace_caller 0.05% hackbench [kernel.kallsyms] [k] arch_local_irq_save 0.05% hackbench [kernel.kallsyms] [k] native_sched_clock 0.04% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] preempt_trace 0.04% hackbench [kernel.kallsyms] [k] prepare_ftrace_return 0.04% hackbench [kernel.kallsyms] [k] __this_cpu_preempt_check 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller See that the ftrace_caller took up more time than the ftrace_graph_caller did. With this patch: 0.05% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] call_filter_check_discard 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller 0.04% hackbench [kernel.kallsyms] [k] sched_clock The ftrace_caller is no where to be found and ftrace_graph_caller still takes up the same percentage. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:56:17 +00:00
FTRACE_FL_ENABLED = (1UL << 31),
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
FTRACE_FL_REGS = (1UL << 30),
ftrace: Optimize function graph to be called directly Function graph tracing is a bit different than the function tracers, as it is processed after either the ftrace_caller or ftrace_regs_caller and we only have one place to modify the jump to ftrace_graph_caller, the jump needs to happen after the restore of registeres. The function graph tracer is dependent on the function tracer, where even if the function graph tracing is going on by itself, the save and restore of registers is still done for function tracing regardless of if function tracing is happening, before it calls the function graph code. If there's no function tracing happening, it is possible to just call the function graph tracer directly, and avoid the wasted effort to save and restore regs for function tracing. This requires adding new flags to the dyn_ftrace records: FTRACE_FL_TRAMP FTRACE_FL_TRAMP_EN The first is set if the count for the record is one, and the ftrace_ops associated to that record has its own trampoline. That way the mcount code can call that trampoline directly. In the future, trampolines can be added to arbitrary ftrace_ops, where you can have two or more ftrace_ops registered to ftrace (like kprobes and perf) and if they are not tracing the same functions, then instead of doing a loop to check all registered ftrace_ops against their hashes, just call the ftrace_ops trampoline directly, which would call the registered ftrace_ops function directly. Without this patch perf showed: 0.05% hackbench [kernel.kallsyms] [k] ftrace_caller 0.05% hackbench [kernel.kallsyms] [k] arch_local_irq_save 0.05% hackbench [kernel.kallsyms] [k] native_sched_clock 0.04% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] preempt_trace 0.04% hackbench [kernel.kallsyms] [k] prepare_ftrace_return 0.04% hackbench [kernel.kallsyms] [k] __this_cpu_preempt_check 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller See that the ftrace_caller took up more time than the ftrace_graph_caller did. With this patch: 0.05% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] call_filter_check_discard 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller 0.04% hackbench [kernel.kallsyms] [k] sched_clock The ftrace_caller is no where to be found and ftrace_graph_caller still takes up the same percentage. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:56:17 +00:00
FTRACE_FL_REGS_EN = (1UL << 29),
FTRACE_FL_TRAMP = (1UL << 28),
FTRACE_FL_TRAMP_EN = (1UL << 27),
FTRACE_FL_IPMODIFY = (1UL << 26),
ftrace: Add infrastructure for delayed enabling of module functions Qiu Peiyang pointed out that there's a race when enabling function tracing and loading a module. In order to make the modifications of converting nops in the prologue of functions into callbacks, the text needs to be converted from read-only to read-write. When enabling function tracing, the text permission is updated, the functions are modified, and then they are put back. When loading a module, the updates to convert function calls to mcount is done before the module text is set to read-only. But after it is done, the module text is visible by the function tracer. Thus we have the following race: CPU 0 CPU 1 ----- ----- start function tracing set text to read-write load_module add functions to ftrace set module text read-only update all functions to callbacks modify module functions too < Can't it's read-only > When this happens, ftrace detects the issue and disables itself till the next reboot. To fix this, a new DISABLED flag is added for ftrace records, which all module functions get when they are added. Then later, after the module code is all set, the records will have the DISABLED flag cleared, and they will be enabled if any callback wants all functions to be traced. Note, this doesn't add the delay to later. It simply changes the ftrace_module_init() to do both the setting of DISABLED records, and then immediately calls the enable code. This helps with testing this new code as it has the same behavior as previously. Another change will come after this to have the ftrace_module_enable() called after the text is set to read-only. Cc: Qiu Peiyang <peiyangx.qiu@intel.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2016-01-07 20:40:01 +00:00
FTRACE_FL_DISABLED = (1UL << 25),
FTRACE_FL_DIRECT = (1UL << 24),
FTRACE_FL_DIRECT_EN = (1UL << 23),
ftrace: Add DYNAMIC_FTRACE_WITH_CALL_OPS Architectures without dynamic ftrace trampolines incur an overhead when multiple ftrace_ops are enabled with distinct filters. in these cases, each call site calls a common trampoline which uses ftrace_ops_list_func() to iterate over all enabled ftrace functions, and so incurs an overhead relative to the size of this list (including RCU protection overhead). Architectures with dynamic ftrace trampolines avoid this overhead for call sites which have a single associated ftrace_ops. In these cases, the dynamic trampoline is customized to branch directly to the relevant ftrace function, avoiding the list overhead. On some architectures it's impractical and/or undesirable to implement dynamic ftrace trampolines. For example, arm64 has limited branch ranges and cannot always directly branch from a call site to an arbitrary address (e.g. from a kernel text address to an arbitrary module address). Calls from modules to core kernel text can be indirected via PLTs (allocated at module load time) to address this, but the same is not possible from calls from core kernel text. Using an indirect branch from a call site to an arbitrary trampoline is possible, but requires several more instructions in the function prologue (or immediately before it), and/or comes with far more complex requirements for patching. Instead, this patch adds a new option, where an architecture can associate each call site with a pointer to an ftrace_ops, placed at a fixed offset from the call site. A shared trampoline can recover this pointer and call ftrace_ops::func() without needing to go via ftrace_ops_list_func(), avoiding the associated overhead. This avoids issues with branch range limitations, and avoids the need to allocate and manipulate dynamic trampolines, making it far simpler to implement and maintain, while having similar performance characteristics. Note that this allows for dynamic ftrace_ops to be invoked directly from an architecture's ftrace_caller trampoline, whereas existing code forces the use of ftrace_ops_get_list_func(), which is in part necessary to permit the ftrace_ops to be freed once unregistered *and* to avoid branch/address-generation range limitation on some architectures (e.g. where ops->func is a module address, and may be outside of the direct branch range for callsites within the main kernel image). The CALL_OPS approach avoids this problems and is safe as: * The existing synchronization in ftrace_shutdown() using ftrace_shutdown() using synchronize_rcu_tasks_rude() (and synchronize_rcu_tasks()) ensures that no tasks hold a stale reference to an ftrace_ops (e.g. in the middle of the ftrace_caller trampoline, or while invoking ftrace_ops::func), when that ftrace_ops is unregistered. Arguably this could also be relied upon for the existing scheme, permitting dynamic ftrace_ops to be invoked directly when ops->func is in range, but this will require additional logic to handle branch range limitations, and is not handled by this patch. * Each callsite's ftrace_ops pointer literal can hold any valid kernel address, and is updated atomically. As an architecture's ftrace_caller trampoline will atomically load the ops pointer then dereference ops->func, there is no risk of invoking ops->func with a mismatches ops pointer, and updates to the ops pointer do not require special care. A subsequent patch will implement architectures support for arm64. There should be no functional change as a result of this patch alone. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org> Cc: Florent Revest <revest@chromium.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20230123134603.1064407-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2023-01-23 13:45:56 +00:00
FTRACE_FL_CALL_OPS = (1UL << 22),
FTRACE_FL_CALL_OPS_EN = (1UL << 21),
FTRACE_FL_TOUCHED = (1UL << 20),
FTRACE_FL_MODIFIED = (1UL << 19),
};
#define FTRACE_REF_MAX_SHIFT 19
#define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1)
#define ftrace_rec_count(rec) ((rec)->flags & FTRACE_REF_MAX)
ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 19:20:42 +00:00
struct dyn_ftrace {
unsigned long ip; /* address of mcount call-site */
unsigned long flags;
struct dyn_arch_ftrace arch;
ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 19:20:42 +00:00
};
int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip,
int remove, int reset);
int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips,
unsigned int cnt, int remove, int reset);
int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset);
int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset);
void ftrace_set_global_filter(unsigned char *buf, int len, int reset);
void ftrace_set_global_notrace(unsigned char *buf, int len, int reset);
ftrace, perf: Add filter support for function trace event Adding support to filter function trace event via perf interface. It is now possible to use filter interface in the perf tool like: perf record -e ftrace:function --filter="(ip == mm_*)" ls The filter syntax is restricted to the the 'ip' field only, and following operators are accepted '==' '!=' '||', ending up with the filter strings like: ip == f1[, ]f2 ... || ip != f3[, ]f4 ... with comma ',' or space ' ' as a function separator. If the space ' ' is used as a separator, the right side of the assignment needs to be enclosed in double quotes '"', e.g.: perf record -e ftrace:function --filter '(ip == do_execve,sys_*,ext*)' ls perf record -e ftrace:function --filter '(ip == "do_execve,sys_*,ext*")' ls perf record -e ftrace:function --filter '(ip == "do_execve sys_* ext*")' ls The '==' operator adds trace filter with same effect as would be added via set_ftrace_filter file. The '!=' operator adds trace filter with same effect as would be added via set_ftrace_notrace file. The right side of the '!=', '==' operators is list of functions or regexp. to be added to filter separated by space. The '||' operator is used for connecting multiple filter definitions together. It is possible to have more than one '==' and '!=' operators within one filter string. Link: http://lkml.kernel.org/r/1329317514-8131-8-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa <jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-02-15 14:51:54 +00:00
void ftrace_free_filter(struct ftrace_ops *ops);
void ftrace_ops_set_global_filter(struct ftrace_ops *ops);
enum {
FTRACE_UPDATE_CALLS = (1 << 0),
FTRACE_DISABLE_CALLS = (1 << 1),
FTRACE_UPDATE_TRACE_FUNC = (1 << 2),
FTRACE_START_FUNC_RET = (1 << 3),
FTRACE_STOP_FUNC_RET = (1 << 4),
FTRACE_MAY_SLEEP = (1 << 5),
};
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
/*
* The FTRACE_UPDATE_* enum is used to pass information back
* from the ftrace_update_record() and ftrace_test_record()
* functions. These are called by the code update routines
* to find out what is to be done for a given function.
*
* IGNORE - The function is already what we want it to be
* MAKE_CALL - Start tracing the function
* MODIFY_CALL - Stop saving regs for the function
* MAKE_NOP - Stop tracing the function
*/
enum {
FTRACE_UPDATE_IGNORE,
FTRACE_UPDATE_MAKE_CALL,
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
FTRACE_UPDATE_MODIFY_CALL,
FTRACE_UPDATE_MAKE_NOP,
};
enum {
FTRACE_ITER_FILTER = (1 << 0),
FTRACE_ITER_NOTRACE = (1 << 1),
FTRACE_ITER_PRINTALL = (1 << 2),
FTRACE_ITER_DO_PROBES = (1 << 3),
FTRACE_ITER_PROBE = (1 << 4),
FTRACE_ITER_MOD = (1 << 5),
FTRACE_ITER_ENABLED = (1 << 6),
FTRACE_ITER_TOUCHED = (1 << 7),
ftrace: Show all functions with addresses in available_filter_functions_addrs Adding new available_filter_functions_addrs file that shows all available functions (same as available_filter_functions) together with addresses, like: # cat available_filter_functions_addrs | head ffffffff81000770 __traceiter_initcall_level ffffffff810007c0 __traceiter_initcall_start ffffffff81000810 __traceiter_initcall_finish ffffffff81000860 trace_initcall_finish_cb ... Note displayed address is the patch-site address and can differ from /proc/kallsyms address. It's useful to have address avilable for traceable symbols, so we don't need to allways cross check kallsyms with available_filter_functions (or the other way around) and have all the data in single file. For backwards compatibility reasons we can't change the existing available_filter_functions file output, but we need to add new file. The problem is that we need to do 2 passes: - through available_filter_functions and find out if the function is traceable - through /proc/kallsyms to get the address for traceable function Having available_filter_functions symbols together with addresses allow us to skip the kallsyms step and we are ok with the address in available_filter_functions_addr not being the function entry, because kprobe_multi uses fprobe and that handles both entry and patch-site address properly. We have 2 interfaces how to create kprobe_multi link: a) passing symbols to kernel 1) user gathers symbols and need to ensure that they are trace-able -> pass through available_filter_functions file 2) kernel takes those symbols and translates them to addresses through kallsyms api 3) addresses are passed to fprobe/ftrace through: register_fprobe_ips -> ftrace_set_filter_ips b) passing addresses to kernel 1) user gathers symbols and needs to ensure that they are trace-able -> pass through available_filter_functions file 2) user takes those symbols and translates them to addresses through /proc/kallsyms 3) addresses are passed to the kernel and kernel calls: register_fprobe_ips -> ftrace_set_filter_ips The new available_filter_functions_addrs file helps us with option b), because we can make 'b 1' and 'b 2' in one step - while filtering traceable functions, we get the address directly. Link: https://lore.kernel.org/linux-trace-kernel/20230611130029.1202298-1-jolsa@kernel.org Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Andrii Nakryiko <andrii.nakryiko@gmail.com> Tested-by: Jackie Liu <liuyun01@kylinos.cn> # x86 Suggested-by: Steven Rostedt (Google) <rostedt@goodmis.org> Suggested-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-06-11 13:00:29 +00:00
FTRACE_ITER_ADDRS = (1 << 8),
};
void arch_ftrace_update_code(int command);
x86/headers: Fix -Wmissing-prototypes warning When building the kernel with W=1 we get a lot of -Wmissing-prototypes warnings, which are trivial in nature and easy to fix - and which may mask some real future bugs if the prototypes get out of sync with the function definition. This patch fixes most of -Wmissing-prototypes warnings which are in the root directory of arch/x86/kernel, not including the subdirectories. These are the warnings fixed in this patch: arch/x86/kernel/signal.c:865:17: warning: no previous prototype for ‘sys32_x32_rt_sigreturn’ [-Wmissing-prototypes] arch/x86/kernel/signal_compat.c:164:6: warning: no previous prototype for ‘sigaction_compat_abi’ [-Wmissing-prototypes] arch/x86/kernel/traps.c:625:46: warning: no previous prototype for ‘sync_regs’ [-Wmissing-prototypes] arch/x86/kernel/traps.c:640:24: warning: no previous prototype for ‘fixup_bad_iret’ [-Wmissing-prototypes] arch/x86/kernel/traps.c:929:13: warning: no previous prototype for ‘trap_init’ [-Wmissing-prototypes] arch/x86/kernel/irq.c:270:28: warning: no previous prototype for ‘smp_x86_platform_ipi’ [-Wmissing-prototypes] arch/x86/kernel/irq.c:301:16: warning: no previous prototype for ‘smp_kvm_posted_intr_ipi’ [-Wmissing-prototypes] arch/x86/kernel/irq.c:314:16: warning: no previous prototype for ‘smp_kvm_posted_intr_wakeup_ipi’ [-Wmissing-prototypes] arch/x86/kernel/irq.c:328:16: warning: no previous prototype for ‘smp_kvm_posted_intr_nested_ipi’ [-Wmissing-prototypes] arch/x86/kernel/irq_work.c:16:28: warning: no previous prototype for ‘smp_irq_work_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/irqinit.c:79:13: warning: no previous prototype for ‘init_IRQ’ [-Wmissing-prototypes] arch/x86/kernel/quirks.c:672:13: warning: no previous prototype for ‘early_platform_quirks’ [-Wmissing-prototypes] arch/x86/kernel/tsc.c:1499:15: warning: no previous prototype for ‘calibrate_delay_is_known’ [-Wmissing-prototypes] arch/x86/kernel/process.c:653:13: warning: no previous prototype for ‘arch_post_acpi_subsys_init’ [-Wmissing-prototypes] arch/x86/kernel/process.c:717:15: warning: no previous prototype for ‘arch_randomize_brk’ [-Wmissing-prototypes] arch/x86/kernel/process.c:784:6: warning: no previous prototype for ‘do_arch_prctl_common’ [-Wmissing-prototypes] arch/x86/kernel/reboot.c:869:6: warning: no previous prototype for ‘nmi_panic_self_stop’ [-Wmissing-prototypes] arch/x86/kernel/smp.c:176:27: warning: no previous prototype for ‘smp_reboot_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/smp.c:260:28: warning: no previous prototype for ‘smp_reschedule_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/smp.c:281:28: warning: no previous prototype for ‘smp_call_function_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/smp.c:291:28: warning: no previous prototype for ‘smp_call_function_single_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/ftrace.c:840:6: warning: no previous prototype for ‘arch_ftrace_update_trampoline’ [-Wmissing-prototypes] arch/x86/kernel/ftrace.c:934:7: warning: no previous prototype for ‘arch_ftrace_trampoline_func’ [-Wmissing-prototypes] arch/x86/kernel/ftrace.c:946:6: warning: no previous prototype for ‘arch_ftrace_trampoline_free’ [-Wmissing-prototypes] arch/x86/kernel/crash.c:114:6: warning: no previous prototype for ‘crash_smp_send_stop’ [-Wmissing-prototypes] arch/x86/kernel/crash.c:351:5: warning: no previous prototype for ‘crash_setup_memmap_entries’ [-Wmissing-prototypes] arch/x86/kernel/crash.c:424:5: warning: no previous prototype for ‘crash_load_segments’ [-Wmissing-prototypes] arch/x86/kernel/machine_kexec_64.c:372:7: warning: no previous prototype for ‘arch_kexec_kernel_image_load’ [-Wmissing-prototypes] arch/x86/kernel/paravirt-spinlocks.c:12:16: warning: no previous prototype for ‘__native_queued_spin_unlock’ [-Wmissing-prototypes] arch/x86/kernel/paravirt-spinlocks.c:18:6: warning: no previous prototype for ‘pv_is_native_spin_unlock’ [-Wmissing-prototypes] arch/x86/kernel/paravirt-spinlocks.c:24:16: warning: no previous prototype for ‘__native_vcpu_is_preempted’ [-Wmissing-prototypes] arch/x86/kernel/paravirt-spinlocks.c:30:6: warning: no previous prototype for ‘pv_is_native_vcpu_is_preempted’ [-Wmissing-prototypes] arch/x86/kernel/kvm.c:258:1: warning: no previous prototype for ‘do_async_page_fault’ [-Wmissing-prototypes] arch/x86/kernel/jailhouse.c:200:6: warning: no previous prototype for ‘jailhouse_paravirt’ [-Wmissing-prototypes] arch/x86/kernel/check.c:91:13: warning: no previous prototype for ‘setup_bios_corruption_check’ [-Wmissing-prototypes] arch/x86/kernel/check.c:139:6: warning: no previous prototype for ‘check_for_bios_corruption’ [-Wmissing-prototypes] arch/x86/kernel/devicetree.c:32:13: warning: no previous prototype for ‘early_init_dt_scan_chosen_arch’ [-Wmissing-prototypes] arch/x86/kernel/devicetree.c:42:13: warning: no previous prototype for ‘add_dtb’ [-Wmissing-prototypes] arch/x86/kernel/devicetree.c:108:6: warning: no previous prototype for ‘x86_of_pci_init’ [-Wmissing-prototypes] arch/x86/kernel/devicetree.c:314:13: warning: no previous prototype for ‘x86_dtb_init’ [-Wmissing-prototypes] arch/x86/kernel/tracepoint.c:16:5: warning: no previous prototype for ‘trace_pagefault_reg’ [-Wmissing-prototypes] arch/x86/kernel/tracepoint.c:22:6: warning: no previous prototype for ‘trace_pagefault_unreg’ [-Wmissing-prototypes] arch/x86/kernel/head64.c:113:22: warning: no previous prototype for ‘__startup_64’ [-Wmissing-prototypes] arch/x86/kernel/head64.c:262:15: warning: no previous prototype for ‘__startup_secondary_64’ [-Wmissing-prototypes] arch/x86/kernel/head64.c:350:12: warning: no previous prototype for ‘early_make_pgtable’ [-Wmissing-prototypes] [ mingo: rewrote the changelog, fixed build errors. ] Signed-off-by: Yi Wang <wang.yi59@zte.com.cn> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: akataria@vmware.com Cc: akpm@linux-foundation.org Cc: andy.shevchenko@gmail.com Cc: anton@enomsg.org Cc: ard.biesheuvel@linaro.org Cc: bhe@redhat.com Cc: bhelgaas@google.com Cc: bp@alien8.de Cc: ccross@android.com Cc: devicetree@vger.kernel.org Cc: douly.fnst@cn.fujitsu.com Cc: dwmw@amazon.co.uk Cc: dyoung@redhat.com Cc: ebiederm@xmission.com Cc: frank.rowand@sony.com Cc: frowand.list@gmail.com Cc: ivan.gorinov@intel.com Cc: jailhouse-dev@googlegroups.com Cc: jan.kiszka@siemens.com Cc: jgross@suse.com Cc: jroedel@suse.de Cc: keescook@chromium.org Cc: kexec@lists.infradead.org Cc: konrad.wilk@oracle.com Cc: kvm@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-pci@vger.kernel.org Cc: luto@kernel.org Cc: m.mizuma@jp.fujitsu.com Cc: namit@vmware.com Cc: oleg@redhat.com Cc: pasha.tatashin@oracle.com Cc: pbonzini@redhat.com Cc: prarit@redhat.com Cc: pravin.shedge4linux@gmail.com Cc: rajvi.jingar@intel.com Cc: rkrcmar@redhat.com Cc: robh+dt@kernel.org Cc: robh@kernel.org Cc: rostedt@goodmis.org Cc: takahiro.akashi@linaro.org Cc: thomas.lendacky@amd.com Cc: tony.luck@intel.com Cc: up2wing@gmail.com Cc: virtualization@lists.linux-foundation.org Cc: zhe.he@windriver.com Cc: zhong.weidong@zte.com.cn Link: http://lkml.kernel.org/r/1542852249-19820-1-git-send-email-wang.yi59@zte.com.cn Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-11-22 02:04:09 +00:00
void arch_ftrace_update_trampoline(struct ftrace_ops *ops);
void *arch_ftrace_trampoline_func(struct ftrace_ops *ops, struct dyn_ftrace *rec);
void arch_ftrace_trampoline_free(struct ftrace_ops *ops);
struct ftrace_rec_iter;
struct ftrace_rec_iter *ftrace_rec_iter_start(void);
struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter);
struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter);
#define for_ftrace_rec_iter(iter) \
for (iter = ftrace_rec_iter_start(); \
iter; \
iter = ftrace_rec_iter_next(iter))
int ftrace_update_record(struct dyn_ftrace *rec, bool enable);
int ftrace_test_record(struct dyn_ftrace *rec, bool enable);
void ftrace_run_stop_machine(int command);
unsigned long ftrace_location(unsigned long ip);
unsigned long ftrace_location_range(unsigned long start, unsigned long end);
unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec);
unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec);
extern ftrace_func_t ftrace_trace_function;
int ftrace_regex_open(struct ftrace_ops *ops, int flag,
struct inode *inode, struct file *file);
ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos);
ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos);
int ftrace_regex_release(struct inode *inode, struct file *file);
void __init
ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable);
ftrace: dynamic enabling/disabling of function calls This patch adds a feature to dynamically replace the ftrace code with the jmps to allow a kernel with ftrace configured to run as fast as it can without it configured. The way this works, is on bootup (if ftrace is enabled), a ftrace function is registered to record the instruction pointer of all places that call the function. Later, if there's still any code to patch, a kthread is awoken (rate limited to at most once a second) that performs a stop_machine, and replaces all the code that was called with a jmp over the call to ftrace. It only replaces what was found the previous time. Typically the system reaches equilibrium quickly after bootup and there's no code patching needed at all. e.g. call ftrace /* 5 bytes */ is replaced with jmp 3f /* jmp is 2 bytes and we jump 3 forward */ 3: When we want to enable ftrace for function tracing, the IP recording is removed, and stop_machine is called again to replace all the locations of that were recorded back to the call of ftrace. When it is disabled, we replace the code back to the jmp. Allocation is done by the kthread. If the ftrace recording function is called, and we don't have any record slots available, then we simply skip that call. Once a second a new page (if needed) is allocated for recording new ftrace function calls. A large batch is allocated at boot up to get most of the calls there. Because we do this via stop_machine, we don't have to worry about another CPU executing a ftrace call as we modify it. But we do need to worry about NMI's so all functions that might be called via nmi must be annotated with notrace_nmi. When this code is configured in, the NMI code will not call notrace. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 19:20:42 +00:00
/* defined in arch */
extern int ftrace_dyn_arch_init(void);
extern void ftrace_replace_code(int enable);
extern int ftrace_update_ftrace_func(ftrace_func_t func);
extern void ftrace_caller(void);
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
extern void ftrace_regs_caller(void);
extern void ftrace_call(void);
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
extern void ftrace_regs_call(void);
extern void mcount_call(void);
void ftrace_modify_all_code(int command);
#ifndef FTRACE_ADDR
#define FTRACE_ADDR ((unsigned long)ftrace_caller)
#endif
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
ftrace: Optimize function graph to be called directly Function graph tracing is a bit different than the function tracers, as it is processed after either the ftrace_caller or ftrace_regs_caller and we only have one place to modify the jump to ftrace_graph_caller, the jump needs to happen after the restore of registeres. The function graph tracer is dependent on the function tracer, where even if the function graph tracing is going on by itself, the save and restore of registers is still done for function tracing regardless of if function tracing is happening, before it calls the function graph code. If there's no function tracing happening, it is possible to just call the function graph tracer directly, and avoid the wasted effort to save and restore regs for function tracing. This requires adding new flags to the dyn_ftrace records: FTRACE_FL_TRAMP FTRACE_FL_TRAMP_EN The first is set if the count for the record is one, and the ftrace_ops associated to that record has its own trampoline. That way the mcount code can call that trampoline directly. In the future, trampolines can be added to arbitrary ftrace_ops, where you can have two or more ftrace_ops registered to ftrace (like kprobes and perf) and if they are not tracing the same functions, then instead of doing a loop to check all registered ftrace_ops against their hashes, just call the ftrace_ops trampoline directly, which would call the registered ftrace_ops function directly. Without this patch perf showed: 0.05% hackbench [kernel.kallsyms] [k] ftrace_caller 0.05% hackbench [kernel.kallsyms] [k] arch_local_irq_save 0.05% hackbench [kernel.kallsyms] [k] native_sched_clock 0.04% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] preempt_trace 0.04% hackbench [kernel.kallsyms] [k] prepare_ftrace_return 0.04% hackbench [kernel.kallsyms] [k] __this_cpu_preempt_check 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller See that the ftrace_caller took up more time than the ftrace_graph_caller did. With this patch: 0.05% hackbench [kernel.kallsyms] [k] __buffer_unlock_commit 0.04% hackbench [kernel.kallsyms] [k] call_filter_check_discard 0.04% hackbench [kernel.kallsyms] [k] ftrace_graph_caller 0.04% hackbench [kernel.kallsyms] [k] sched_clock The ftrace_caller is no where to be found and ftrace_graph_caller still takes up the same percentage. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:56:17 +00:00
#ifndef FTRACE_GRAPH_ADDR
#define FTRACE_GRAPH_ADDR ((unsigned long)ftrace_graph_caller)
#endif
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
#ifndef FTRACE_REGS_ADDR
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
# define FTRACE_REGS_ADDR ((unsigned long)ftrace_regs_caller)
#else
# define FTRACE_REGS_ADDR FTRACE_ADDR
#endif
#endif
/*
* If an arch would like functions that are only traced
* by the function graph tracer to jump directly to its own
* trampoline, then they can define FTRACE_GRAPH_TRAMP_ADDR
* to be that address to jump to.
*/
#ifndef FTRACE_GRAPH_TRAMP_ADDR
#define FTRACE_GRAPH_TRAMP_ADDR ((unsigned long) 0)
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
extern void ftrace_graph_caller(void);
extern int ftrace_enable_ftrace_graph_caller(void);
extern int ftrace_disable_ftrace_graph_caller(void);
#else
static inline int ftrace_enable_ftrace_graph_caller(void) { return 0; }
static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; }
tracing/function-return-tracer: support for dynamic ftrace on function return tracer This patch adds the support for dynamic tracing on the function return tracer. The whole difference with normal dynamic function tracing is that we don't need to hook on a particular callback. The only pro that we want is to nop or set dynamically the calls to ftrace_caller (which is ftrace_return_caller here). Some security checks ensure that we are not trying to launch dynamic tracing for return tracing while normal function tracing is already running. An example of trace with getnstimeofday set as a filter: ktime_get_ts+0x22/0x50 -> getnstimeofday (2283 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1396 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1825 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1426 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1464 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1524 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1382 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1434 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1464 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1502 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1404 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1397 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1051 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1314 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1344 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1163 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1390 ns) ktime_get_ts+0x22/0x50 -> getnstimeofday (1374 ns) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-16 05:02:06 +00:00
#endif
ftrace: user update and disable dynamic ftrace daemon In dynamic ftrace, the mcount function starts off pointing to a stub function that just returns. On start up, the call to the stub is modified to point to a "record_ip" function. The job of the record_ip function is to add the function to a pre-allocated hash list. If the function is already there, it simply is ignored, otherwise it is added to the list. Later, a ftraced daemon wakes up and calls kstop_machine if any functions have been recorded, and changes the calls to the recorded functions to a simple nop. If no functions were recorded, the daemon goes back to sleep. The daemon wakes up once a second to see if it needs to update any newly recorded functions into nops. Usually it does not, but if a lot of code has been executed for the first time in the kernel, the ftraced daemon will call kstop_machine to update those into nops. The problem currently is that there's no way to stop the daemon from doing this, and it can cause unneeded latencies (800us which for some is bothersome). This patch adds a new file /debugfs/tracing/ftraced_enabled. If the daemon is active, reading this will return "enabled\n" and "disabled\n" when the daemon is not running. To disable the daemon, the user can echo "0" or "disable" into this file, and "1" or "enable" to re-enable the daemon. Since the daemon is used to convert the functions into nops to increase the performance of the system, I also added that anytime something is written into the ftraced_enabled file, kstop_machine will run if there are new functions that have been detected that need to be converted. This way the user can disable the daemon but still be able to control the conversion of the mcount calls to nops by simply, "echo 0 > /debugfs/tracing/ftraced_enabled" when they need to do more conversions. To see the number of converted functions: "cat /debugfs/tracing/dyn_ftrace_total_info" Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-28 00:48:37 +00:00
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 00:21:19 +00:00
/**
* ftrace_make_nop - convert code into nop
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 00:21:19 +00:00
* @mod: module structure if called by module load initialization
ftrace: add ftrace_init_nop() Architectures may need to perform special initialization of ftrace callsites, and today they do so by special-casing ftrace_make_nop() when the expected branch address is MCOUNT_ADDR. In some cases (e.g. for patchable-function-entry), we don't have an mcount-like symbol and don't want a synthetic MCOUNT_ADDR, but we may need to perform some initialization of callsites. To make it possible to separate initialization from runtime modification, and to handle cases without an mcount-like symbol, this patch adds an optional ftrace_init_nop() function that architectures can implement, which does not pass a branch address. Where an architecture does not provide ftrace_init_nop(), we will fall back to the existing behaviour of calling ftrace_make_nop() with MCOUNT_ADDR. At the same time, ftrace_code_disable() is renamed to ftrace_nop_initialize() to make it clearer that it is intended to intialize a callsite into a disabled state, and is not for disabling a callsite that has been runtime enabled. The kerneldoc description of rec arguments is updated to cover non-mcount callsites. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Miroslav Benes <mbenes@suse.cz> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Reviewed-by: Torsten Duwe <duwe@suse.de> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Tested-by: Sven Schnelle <svens@stackframe.org> Tested-by: Torsten Duwe <duwe@suse.de> Cc: Ingo Molnar <mingo@redhat.com>
2019-10-16 16:51:10 +00:00
* @rec: the call site record (e.g. mcount/fentry)
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 00:21:19 +00:00
* @addr: the address that the call site should be calling
*
* This is a very sensitive operation and great care needs
* to be taken by the arch. The operation should carefully
* read the location, check to see if what is read is indeed
* what we expect it to be, and then on success of the compare,
* it should write to the location.
*
* The code segment at @rec->ip should be a caller to @addr
*
* Return must be:
* 0 on success
* -EFAULT on error reading the location
* -EINVAL on a failed compare of the contents
* -EPERM on error writing to the location
* Any other value will be considered a failure.
*/
extern int ftrace_make_nop(struct module *mod,
struct dyn_ftrace *rec, unsigned long addr);
/**
* ftrace_need_init_nop - return whether nop call sites should be initialized
*
* Normally the compiler's -mnop-mcount generates suitable nops, so we don't
* need to call ftrace_init_nop() if the code is built with that flag.
* Architectures where this is not always the case may define their own
* condition.
*
* Return must be:
* 0 if ftrace_init_nop() should be called
* Nonzero if ftrace_init_nop() should not be called
*/
#ifndef ftrace_need_init_nop
#define ftrace_need_init_nop() (!__is_defined(CC_USING_NOP_MCOUNT))
#endif
ftrace: add ftrace_init_nop() Architectures may need to perform special initialization of ftrace callsites, and today they do so by special-casing ftrace_make_nop() when the expected branch address is MCOUNT_ADDR. In some cases (e.g. for patchable-function-entry), we don't have an mcount-like symbol and don't want a synthetic MCOUNT_ADDR, but we may need to perform some initialization of callsites. To make it possible to separate initialization from runtime modification, and to handle cases without an mcount-like symbol, this patch adds an optional ftrace_init_nop() function that architectures can implement, which does not pass a branch address. Where an architecture does not provide ftrace_init_nop(), we will fall back to the existing behaviour of calling ftrace_make_nop() with MCOUNT_ADDR. At the same time, ftrace_code_disable() is renamed to ftrace_nop_initialize() to make it clearer that it is intended to intialize a callsite into a disabled state, and is not for disabling a callsite that has been runtime enabled. The kerneldoc description of rec arguments is updated to cover non-mcount callsites. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Miroslav Benes <mbenes@suse.cz> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Reviewed-by: Torsten Duwe <duwe@suse.de> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Tested-by: Sven Schnelle <svens@stackframe.org> Tested-by: Torsten Duwe <duwe@suse.de> Cc: Ingo Molnar <mingo@redhat.com>
2019-10-16 16:51:10 +00:00
/**
* ftrace_init_nop - initialize a nop call site
* @mod: module structure if called by module load initialization
* @rec: the call site record (e.g. mcount/fentry)
*
* This is a very sensitive operation and great care needs
* to be taken by the arch. The operation should carefully
* read the location, check to see if what is read is indeed
* what we expect it to be, and then on success of the compare,
* it should write to the location.
*
* The code segment at @rec->ip should contain the contents created by
* the compiler
*
* Return must be:
* 0 on success
* -EFAULT on error reading the location
* -EINVAL on a failed compare of the contents
* -EPERM on error writing to the location
* Any other value will be considered a failure.
*/
#ifndef ftrace_init_nop
static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
{
return ftrace_make_nop(mod, rec, MCOUNT_ADDR);
}
#endif
/**
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 00:21:19 +00:00
* ftrace_make_call - convert a nop call site into a call to addr
ftrace: add ftrace_init_nop() Architectures may need to perform special initialization of ftrace callsites, and today they do so by special-casing ftrace_make_nop() when the expected branch address is MCOUNT_ADDR. In some cases (e.g. for patchable-function-entry), we don't have an mcount-like symbol and don't want a synthetic MCOUNT_ADDR, but we may need to perform some initialization of callsites. To make it possible to separate initialization from runtime modification, and to handle cases without an mcount-like symbol, this patch adds an optional ftrace_init_nop() function that architectures can implement, which does not pass a branch address. Where an architecture does not provide ftrace_init_nop(), we will fall back to the existing behaviour of calling ftrace_make_nop() with MCOUNT_ADDR. At the same time, ftrace_code_disable() is renamed to ftrace_nop_initialize() to make it clearer that it is intended to intialize a callsite into a disabled state, and is not for disabling a callsite that has been runtime enabled. The kerneldoc description of rec arguments is updated to cover non-mcount callsites. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Miroslav Benes <mbenes@suse.cz> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Reviewed-by: Torsten Duwe <duwe@suse.de> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Tested-by: Sven Schnelle <svens@stackframe.org> Tested-by: Torsten Duwe <duwe@suse.de> Cc: Ingo Molnar <mingo@redhat.com>
2019-10-16 16:51:10 +00:00
* @rec: the call site record (e.g. mcount/fentry)
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 00:21:19 +00:00
* @addr: the address that the call site should call
*
* This is a very sensitive operation and great care needs
* to be taken by the arch. The operation should carefully
* read the location, check to see if what is read is indeed
* what we expect it to be, and then on success of the compare,
* it should write to the location.
*
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 00:21:19 +00:00
* The code segment at @rec->ip should be a nop
*
* Return must be:
* 0 on success
* -EFAULT on error reading the location
* -EINVAL on a failed compare of the contents
* -EPERM on error writing to the location
* Any other value will be considered a failure.
*/
ftrace: pass module struct to arch dynamic ftrace functions Impact: allow archs more flexibility on dynamic ftrace implementations Dynamic ftrace has largly been developed on x86. Since x86 does not have the same limitations as other architectures, the ftrace interaction between the generic code and the architecture specific code was not flexible enough to handle some of the issues that other architectures have. Most notably, module trampolines. Due to the limited branch distance that archs make in calling kernel core code from modules, the module load code must create a trampoline to jump to what will make the larger jump into core kernel code. The problem arises when this happens to a call to mcount. Ftrace checks all code before modifying it and makes sure the current code is what it expects. Right now, there is not enough information to handle modifying module trampolines. This patch changes the API between generic dynamic ftrace code and the arch dependent code. There is now two functions for modifying code: ftrace_make_nop(mod, rec, addr) - convert the code at rec->ip into a nop, where the original text is calling addr. (mod is the module struct if called by module init) ftrace_make_caller(rec, addr) - convert the code rec->ip that should be a nop into a caller to addr. The record "rec" now has a new field called "arch" where the architecture can add any special attributes to each call site record. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-15 00:21:19 +00:00
extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
ftrace: Add DYNAMIC_FTRACE_WITH_CALL_OPS Architectures without dynamic ftrace trampolines incur an overhead when multiple ftrace_ops are enabled with distinct filters. in these cases, each call site calls a common trampoline which uses ftrace_ops_list_func() to iterate over all enabled ftrace functions, and so incurs an overhead relative to the size of this list (including RCU protection overhead). Architectures with dynamic ftrace trampolines avoid this overhead for call sites which have a single associated ftrace_ops. In these cases, the dynamic trampoline is customized to branch directly to the relevant ftrace function, avoiding the list overhead. On some architectures it's impractical and/or undesirable to implement dynamic ftrace trampolines. For example, arm64 has limited branch ranges and cannot always directly branch from a call site to an arbitrary address (e.g. from a kernel text address to an arbitrary module address). Calls from modules to core kernel text can be indirected via PLTs (allocated at module load time) to address this, but the same is not possible from calls from core kernel text. Using an indirect branch from a call site to an arbitrary trampoline is possible, but requires several more instructions in the function prologue (or immediately before it), and/or comes with far more complex requirements for patching. Instead, this patch adds a new option, where an architecture can associate each call site with a pointer to an ftrace_ops, placed at a fixed offset from the call site. A shared trampoline can recover this pointer and call ftrace_ops::func() without needing to go via ftrace_ops_list_func(), avoiding the associated overhead. This avoids issues with branch range limitations, and avoids the need to allocate and manipulate dynamic trampolines, making it far simpler to implement and maintain, while having similar performance characteristics. Note that this allows for dynamic ftrace_ops to be invoked directly from an architecture's ftrace_caller trampoline, whereas existing code forces the use of ftrace_ops_get_list_func(), which is in part necessary to permit the ftrace_ops to be freed once unregistered *and* to avoid branch/address-generation range limitation on some architectures (e.g. where ops->func is a module address, and may be outside of the direct branch range for callsites within the main kernel image). The CALL_OPS approach avoids this problems and is safe as: * The existing synchronization in ftrace_shutdown() using ftrace_shutdown() using synchronize_rcu_tasks_rude() (and synchronize_rcu_tasks()) ensures that no tasks hold a stale reference to an ftrace_ops (e.g. in the middle of the ftrace_caller trampoline, or while invoking ftrace_ops::func), when that ftrace_ops is unregistered. Arguably this could also be relied upon for the existing scheme, permitting dynamic ftrace_ops to be invoked directly when ops->func is in range, but this will require additional logic to handle branch range limitations, and is not handled by this patch. * Each callsite's ftrace_ops pointer literal can hold any valid kernel address, and is updated atomically. As an architecture's ftrace_caller trampoline will atomically load the ops pointer then dereference ops->func, there is no risk of invoking ops->func with a mismatches ops pointer, and updates to the ops pointer do not require special care. A subsequent patch will implement architectures support for arm64. There should be no functional change as a result of this patch alone. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org> Cc: Florent Revest <revest@chromium.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20230123134603.1064407-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2023-01-23 13:45:56 +00:00
#if defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) || \
defined(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
/**
* ftrace_modify_call - convert from one addr to another (no nop)
ftrace: add ftrace_init_nop() Architectures may need to perform special initialization of ftrace callsites, and today they do so by special-casing ftrace_make_nop() when the expected branch address is MCOUNT_ADDR. In some cases (e.g. for patchable-function-entry), we don't have an mcount-like symbol and don't want a synthetic MCOUNT_ADDR, but we may need to perform some initialization of callsites. To make it possible to separate initialization from runtime modification, and to handle cases without an mcount-like symbol, this patch adds an optional ftrace_init_nop() function that architectures can implement, which does not pass a branch address. Where an architecture does not provide ftrace_init_nop(), we will fall back to the existing behaviour of calling ftrace_make_nop() with MCOUNT_ADDR. At the same time, ftrace_code_disable() is renamed to ftrace_nop_initialize() to make it clearer that it is intended to intialize a callsite into a disabled state, and is not for disabling a callsite that has been runtime enabled. The kerneldoc description of rec arguments is updated to cover non-mcount callsites. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Miroslav Benes <mbenes@suse.cz> Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Reviewed-by: Torsten Duwe <duwe@suse.de> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Tested-by: Sven Schnelle <svens@stackframe.org> Tested-by: Torsten Duwe <duwe@suse.de> Cc: Ingo Molnar <mingo@redhat.com>
2019-10-16 16:51:10 +00:00
* @rec: the call site record (e.g. mcount/fentry)
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
* @old_addr: the address expected to be currently called to
* @addr: the address to change to
*
* This is a very sensitive operation and great care needs
* to be taken by the arch. The operation should carefully
* read the location, check to see if what is read is indeed
* what we expect it to be, and then on success of the compare,
* it should write to the location.
*
ftrace: Add DYNAMIC_FTRACE_WITH_CALL_OPS Architectures without dynamic ftrace trampolines incur an overhead when multiple ftrace_ops are enabled with distinct filters. in these cases, each call site calls a common trampoline which uses ftrace_ops_list_func() to iterate over all enabled ftrace functions, and so incurs an overhead relative to the size of this list (including RCU protection overhead). Architectures with dynamic ftrace trampolines avoid this overhead for call sites which have a single associated ftrace_ops. In these cases, the dynamic trampoline is customized to branch directly to the relevant ftrace function, avoiding the list overhead. On some architectures it's impractical and/or undesirable to implement dynamic ftrace trampolines. For example, arm64 has limited branch ranges and cannot always directly branch from a call site to an arbitrary address (e.g. from a kernel text address to an arbitrary module address). Calls from modules to core kernel text can be indirected via PLTs (allocated at module load time) to address this, but the same is not possible from calls from core kernel text. Using an indirect branch from a call site to an arbitrary trampoline is possible, but requires several more instructions in the function prologue (or immediately before it), and/or comes with far more complex requirements for patching. Instead, this patch adds a new option, where an architecture can associate each call site with a pointer to an ftrace_ops, placed at a fixed offset from the call site. A shared trampoline can recover this pointer and call ftrace_ops::func() without needing to go via ftrace_ops_list_func(), avoiding the associated overhead. This avoids issues with branch range limitations, and avoids the need to allocate and manipulate dynamic trampolines, making it far simpler to implement and maintain, while having similar performance characteristics. Note that this allows for dynamic ftrace_ops to be invoked directly from an architecture's ftrace_caller trampoline, whereas existing code forces the use of ftrace_ops_get_list_func(), which is in part necessary to permit the ftrace_ops to be freed once unregistered *and* to avoid branch/address-generation range limitation on some architectures (e.g. where ops->func is a module address, and may be outside of the direct branch range for callsites within the main kernel image). The CALL_OPS approach avoids this problems and is safe as: * The existing synchronization in ftrace_shutdown() using ftrace_shutdown() using synchronize_rcu_tasks_rude() (and synchronize_rcu_tasks()) ensures that no tasks hold a stale reference to an ftrace_ops (e.g. in the middle of the ftrace_caller trampoline, or while invoking ftrace_ops::func), when that ftrace_ops is unregistered. Arguably this could also be relied upon for the existing scheme, permitting dynamic ftrace_ops to be invoked directly when ops->func is in range, but this will require additional logic to handle branch range limitations, and is not handled by this patch. * Each callsite's ftrace_ops pointer literal can hold any valid kernel address, and is updated atomically. As an architecture's ftrace_caller trampoline will atomically load the ops pointer then dereference ops->func, there is no risk of invoking ops->func with a mismatches ops pointer, and updates to the ops pointer do not require special care. A subsequent patch will implement architectures support for arm64. There should be no functional change as a result of this patch alone. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org> Cc: Florent Revest <revest@chromium.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Link: https://lore.kernel.org/r/20230123134603.1064407-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2023-01-23 13:45:56 +00:00
* When using call ops, this is called when the associated ops change, even
* when (addr == old_addr).
*
ftrace/x86: Add separate function to save regs Add a way to have different functions calling different trampolines. If a ftrace_ops wants regs saved on the return, then have only the functions with ops registered to save regs. Functions registered by other ops would not be affected, unless the functions overlap. If one ftrace_ops registered functions A, B and C and another ops registered fucntions to save regs on A, and D, then only functions A and D would be saving regs. Function B and C would work as normal. Although A is registered by both ops: normal and saves regs; this is fine as saving the regs is needed to satisfy one of the ops that calls it but the regs are ignored by the other ops function. x86_64 implements the full regs saving, and i386 just passes a NULL for regs to satisfy the ftrace_ops passing. Where an arch must supply both regs and ftrace_ops parameters, even if regs is just NULL. It is OK for an arch to pass NULL regs. All function trace users that require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when registering the ftrace_ops. If the arch does not support saving regs then the ftrace_ops will fail to register. The flag FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the ftrace_ops from failing to register. In this case, the handler may either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS. If the arch supports passing regs it will set this macro and pass regs for ops that request them. All other archs will just pass NULL. Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org Cc: Alexander van Heukelum <heukelum@fastmail.fm> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-04-30 20:20:23 +00:00
* The code segment at @rec->ip should be a caller to @old_addr
*
* Return must be:
* 0 on success
* -EFAULT on error reading the location
* -EINVAL on a failed compare of the contents
* -EPERM on error writing to the location
* Any other value will be considered a failure.
*/
extern int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr);
#else
/* Should never be called */
static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr)
{
return -EINVAL;
}
#endif
extern int skip_trace(unsigned long ip);
ftrace/module: Hardcode ftrace_module_init() call into load_module() A race exists between module loading and enabling of function tracer. CPU 1 CPU 2 ----- ----- load_module() module->state = MODULE_STATE_COMING register_ftrace_function() mutex_lock(&ftrace_lock); ftrace_startup() update_ftrace_function(); ftrace_arch_code_modify_prepare() set_all_module_text_rw(); <enables-ftrace> ftrace_arch_code_modify_post_process() set_all_module_text_ro(); [ here all module text is set to RO, including the module that is loading!! ] blocking_notifier_call_chain(MODULE_STATE_COMING); ftrace_init_module() [ tries to modify code, but it's RO, and fails! ftrace_bug() is called] When this race happens, ftrace_bug() will produces a nasty warning and all of the function tracing features will be disabled until reboot. The simple solution is to treate module load the same way the core kernel is treated at boot. To hardcode the ftrace function modification of converting calls to mcount into nops. This is done in init/main.c there's no reason it could not be done in load_module(). This gives a better control of the changes and doesn't tie the state of the module to its notifiers as much. Ftrace is special, it needs to be treated as such. The reason this would work, is that the ftrace_module_init() would be called while the module is in MODULE_STATE_UNFORMED, which is ignored by the set_all_module_text_ro() call. Link: http://lkml.kernel.org/r/1395637826-3312-1-git-send-email-indou.takao@jp.fujitsu.com Reported-by: Takao Indoh <indou.takao@jp.fujitsu.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Cc: stable@vger.kernel.org # 2.6.38+ Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-04-24 14:40:12 +00:00
extern void ftrace_module_init(struct module *mod);
extern void ftrace_module_enable(struct module *mod);
extern void ftrace_release_mod(struct module *mod);
#else /* CONFIG_DYNAMIC_FTRACE */
static inline int skip_trace(unsigned long ip) { return 0; }
static inline void ftrace_module_init(struct module *mod) { }
static inline void ftrace_module_enable(struct module *mod) { }
static inline void ftrace_release_mod(struct module *mod) { }
static inline int ftrace_text_reserved(const void *start, const void *end)
{
return 0;
}
static inline unsigned long ftrace_location(unsigned long ip)
{
return 0;
}
/*
* Again users of functions that have ftrace_ops may not
* have them defined when ftrace is not enabled, but these
* functions may still be called. Use a macro instead of inline.
*/
#define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; })
#define ftrace_set_early_filter(ops, buf, enable) do { } while (0)
#define ftrace_set_filter_ip(ops, ip, remove, reset) ({ -ENODEV; })
#define ftrace_set_filter_ips(ops, ips, cnt, remove, reset) ({ -ENODEV; })
ftrace, perf: Add filter support for function trace event Adding support to filter function trace event via perf interface. It is now possible to use filter interface in the perf tool like: perf record -e ftrace:function --filter="(ip == mm_*)" ls The filter syntax is restricted to the the 'ip' field only, and following operators are accepted '==' '!=' '||', ending up with the filter strings like: ip == f1[, ]f2 ... || ip != f3[, ]f4 ... with comma ',' or space ' ' as a function separator. If the space ' ' is used as a separator, the right side of the assignment needs to be enclosed in double quotes '"', e.g.: perf record -e ftrace:function --filter '(ip == do_execve,sys_*,ext*)' ls perf record -e ftrace:function --filter '(ip == "do_execve,sys_*,ext*")' ls perf record -e ftrace:function --filter '(ip == "do_execve sys_* ext*")' ls The '==' operator adds trace filter with same effect as would be added via set_ftrace_filter file. The '!=' operator adds trace filter with same effect as would be added via set_ftrace_notrace file. The right side of the '!=', '==' operators is list of functions or regexp. to be added to filter separated by space. The '||' operator is used for connecting multiple filter definitions together. It is possible to have more than one '==' and '!=' operators within one filter string. Link: http://lkml.kernel.org/r/1329317514-8131-8-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa <jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-02-15 14:51:54 +00:00
#define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; })
#define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; })
#define ftrace_free_filter(ops) do { } while (0)
#define ftrace_ops_set_global_filter(ops) do { } while (0)
static inline ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos) { return -ENODEV; }
static inline ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos) { return -ENODEV; }
static inline int
ftrace_regex_release(struct inode *inode, struct file *file) { return -ENODEV; }
static inline bool is_ftrace_trampoline(unsigned long addr)
{
return false;
}
#endif /* CONFIG_DYNAMIC_FTRACE */
ftrace: tracer for scheduler wakeup latency This patch adds the tracer that tracks the wakeup latency of the highest priority waking task. "wakeup" is added to /debugfs/tracing/available_tracers Also added to /debugfs/tracing tracing_max_latency holds the current max latency for the wakeup wakeup_thresh if set to other than zero, a log will be recorded for every wakeup that takes longer than the number entered in here (usecs for all counters) (deletes previous trace) Examples: (with ftrace_enabled = 0) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 26 us, #2/2, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/0-3 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / quilt-8551 0d..3 0us+: wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) quilt-8551 0d..4 26us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ (with ftrace_enabled = 1) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 -------------------------------------------------------------------- latency: 36 us, #45/45, CPU#0 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/1-5 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / bash-10653 1d..3 0us : wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) bash-10653 1d..3 1us : try_to_wake_up+0x271/0x2e7 <ffffffff80233dcf> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..2 2us : try_to_wake_up+0x296/0x2e7 <ffffffff80233df4> (update_rq_clock+0x9/0x20 <ffffffff802303f3>) bash-10653 1d..2 2us : update_rq_clock+0x1e/0x20 <ffffffff80230408> (__update_rq_clock+0xc/0x90 <ffffffff80230366>) bash-10653 1d..2 3us : __update_rq_clock+0x1b/0x90 <ffffffff80230375> (sched_clock+0x9/0x29 <ffffffff80214529>) bash-10653 1d..2 4us : try_to_wake_up+0x2a6/0x2e7 <ffffffff80233e04> (activate_task+0xc/0x3f <ffffffff8022ffca>) bash-10653 1d..2 4us : activate_task+0x2d/0x3f <ffffffff8022ffeb> (enqueue_task+0xe/0x66 <ffffffff8022ff66>) bash-10653 1d..2 5us : enqueue_task+0x5b/0x66 <ffffffff8022ffb3> (enqueue_task_rt+0x9/0x3c <ffffffff80233351>) bash-10653 1d..2 6us : try_to_wake_up+0x2ba/0x2e7 <ffffffff80233e18> (check_preempt_wakeup+0x12/0x99 <ffffffff80234f84>) [...] bash-10653 1d..5 33us : tracing_record_cmdline+0xcf/0xd4 <ffffffff80338aad> (_spin_unlock+0x9/0x33 <ffffffff8048d3ec>) bash-10653 1d..5 34us : _spin_unlock+0x19/0x33 <ffffffff8048d3fc> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..4 35us : wakeup_sched_switch+0x65/0x2ff <ffffffff80339f66> (_spin_lock_irqsave+0xc/0xa9 <ffffffff8048d08b>) bash-10653 1d..4 35us : _spin_lock_irqsave+0x19/0xa9 <ffffffff8048d098> (add_preempt_count+0xe/0x77 <ffffffff8023311a>) bash-10653 1d..4 36us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ The [...] was added here to not waste your email box space. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 19:20:42 +00:00
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
#ifndef ftrace_graph_func
#define ftrace_graph_func ftrace_stub
#define FTRACE_OPS_GRAPH_STUB FTRACE_OPS_FL_STUB
#else
#define FTRACE_OPS_GRAPH_STUB 0
#endif
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
/* totally disable ftrace - can not re-enable after this */
void ftrace_kill(void);
static inline void tracer_disable(void)
{
#ifdef CONFIG_FUNCTION_TRACER
ftrace_enabled = 0;
#endif
}
/*
* Ftrace disable/restore without lock. Some synchronization mechanism
* must be used to prevent ftrace_enabled to be changed between
* disable/restore.
*/
static inline int __ftrace_enabled_save(void)
{
#ifdef CONFIG_FUNCTION_TRACER
int saved_ftrace_enabled = ftrace_enabled;
ftrace_enabled = 0;
return saved_ftrace_enabled;
#else
return 0;
#endif
}
static inline void __ftrace_enabled_restore(int enabled)
{
#ifdef CONFIG_FUNCTION_TRACER
ftrace_enabled = enabled;
#endif
}
/* All archs should have this, but we define it for consistency */
#ifndef ftrace_return_address0
# define ftrace_return_address0 __builtin_return_address(0)
#endif
/* Archs may use other ways for ADDR1 and beyond */
#ifndef ftrace_return_address
# ifdef CONFIG_FRAME_POINTER
# define ftrace_return_address(n) __builtin_return_address(n)
# else
# define ftrace_return_address(n) 0UL
# endif
#endif
#define CALLER_ADDR0 ((unsigned long)ftrace_return_address0)
#define CALLER_ADDR1 ((unsigned long)ftrace_return_address(1))
#define CALLER_ADDR2 ((unsigned long)ftrace_return_address(2))
#define CALLER_ADDR3 ((unsigned long)ftrace_return_address(3))
#define CALLER_ADDR4 ((unsigned long)ftrace_return_address(4))
#define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5))
#define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6))
ftrace: tracer for scheduler wakeup latency This patch adds the tracer that tracks the wakeup latency of the highest priority waking task. "wakeup" is added to /debugfs/tracing/available_tracers Also added to /debugfs/tracing tracing_max_latency holds the current max latency for the wakeup wakeup_thresh if set to other than zero, a log will be recorded for every wakeup that takes longer than the number entered in here (usecs for all counters) (deletes previous trace) Examples: (with ftrace_enabled = 0) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 Signed-off-by: Ingo Molnar <mingo@elte.hu> -------------------------------------------------------------------- latency: 26 us, #2/2, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/0-3 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / quilt-8551 0d..3 0us+: wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) quilt-8551 0d..4 26us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ (with ftrace_enabled = 1) ============ preemption latency trace v1.1.5 on 2.6.24-rc8 -------------------------------------------------------------------- latency: 36 us, #45/45, CPU#0 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2) ----------------- | task: migration/1-5 (uid:0 nice:-5 policy:1 rt_prio:99) ----------------- _------=> CPU# / _-----=> irqs-off | / _----=> need-resched || / _---=> hardirq/softirq ||| / _--=> preempt-depth |||| / ||||| delay cmd pid ||||| time | caller \ / ||||| \ | / bash-10653 1d..3 0us : wake_up_process+0x15/0x17 <ffffffff80233e80> (sched_exec+0xc9/0x100 <ffffffff80235343>) bash-10653 1d..3 1us : try_to_wake_up+0x271/0x2e7 <ffffffff80233dcf> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..2 2us : try_to_wake_up+0x296/0x2e7 <ffffffff80233df4> (update_rq_clock+0x9/0x20 <ffffffff802303f3>) bash-10653 1d..2 2us : update_rq_clock+0x1e/0x20 <ffffffff80230408> (__update_rq_clock+0xc/0x90 <ffffffff80230366>) bash-10653 1d..2 3us : __update_rq_clock+0x1b/0x90 <ffffffff80230375> (sched_clock+0x9/0x29 <ffffffff80214529>) bash-10653 1d..2 4us : try_to_wake_up+0x2a6/0x2e7 <ffffffff80233e04> (activate_task+0xc/0x3f <ffffffff8022ffca>) bash-10653 1d..2 4us : activate_task+0x2d/0x3f <ffffffff8022ffeb> (enqueue_task+0xe/0x66 <ffffffff8022ff66>) bash-10653 1d..2 5us : enqueue_task+0x5b/0x66 <ffffffff8022ffb3> (enqueue_task_rt+0x9/0x3c <ffffffff80233351>) bash-10653 1d..2 6us : try_to_wake_up+0x2ba/0x2e7 <ffffffff80233e18> (check_preempt_wakeup+0x12/0x99 <ffffffff80234f84>) [...] bash-10653 1d..5 33us : tracing_record_cmdline+0xcf/0xd4 <ffffffff80338aad> (_spin_unlock+0x9/0x33 <ffffffff8048d3ec>) bash-10653 1d..5 34us : _spin_unlock+0x19/0x33 <ffffffff8048d3fc> (sub_preempt_count+0xc/0x7a <ffffffff8023309e>) bash-10653 1d..4 35us : wakeup_sched_switch+0x65/0x2ff <ffffffff80339f66> (_spin_lock_irqsave+0xc/0xa9 <ffffffff8048d08b>) bash-10653 1d..4 35us : _spin_lock_irqsave+0x19/0xa9 <ffffffff8048d098> (add_preempt_count+0xe/0x77 <ffffffff8023311a>) bash-10653 1d..4 36us : sched_switch_callback+0x73/0x81 <ffffffff80338d2f> (schedule+0x483/0x6d5 <ffffffff8048b3ee>) vim:ft=help ============ The [...] was added here to not waste your email box space. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 19:20:42 +00:00
static __always_inline unsigned long get_lock_parent_ip(void)
{
unsigned long addr = CALLER_ADDR0;
if (!in_lock_functions(addr))
return addr;
addr = CALLER_ADDR1;
if (!in_lock_functions(addr))
return addr;
return CALLER_ADDR2;
}
tracing: Centralize preemptirq tracepoints and unify their usage This patch detaches the preemptirq tracepoints from the tracers and keeps it separate. Advantages: * Lockdep and irqsoff event can now run in parallel since they no longer have their own calls. * This unifies the usecase of adding hooks to an irqsoff and irqson event, and a preemptoff and preempton event. 3 users of the events exist: - Lockdep - irqsoff and preemptoff tracers - irqs and preempt trace events The unification cleans up several ifdefs and makes the code in preempt tracer and irqsoff tracers simpler. It gets rid of all the horrific ifdeferry around PROVE_LOCKING and makes configuration of the different users of the tracepoints more easy and understandable. It also gets rid of the time_* function calls from the lockdep hooks used to call into the preemptirq tracer which is not needed anymore. The negative delta in lines of code in this patch is quite large too. In the patch we introduce a new CONFIG option PREEMPTIRQ_TRACEPOINTS as a single point for registering probes onto the tracepoints. With this, the web of config options for preempt/irq toggle tracepoints and its users becomes: PREEMPT_TRACER PREEMPTIRQ_EVENTS IRQSOFF_TRACER PROVE_LOCKING | | \ | | \ (selects) / \ \ (selects) / TRACE_PREEMPT_TOGGLE ----> TRACE_IRQFLAGS \ / \ (depends on) / PREEMPTIRQ_TRACEPOINTS Other than the performance tests mentioned in the previous patch, I also ran the locking API test suite. I verified that all tests cases are passing. I also injected issues by not registering lockdep probes onto the tracepoints and I see failures to confirm that the probes are indeed working. This series + lockdep probes not registered (just to inject errors): [ 0.000000] hard-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] soft-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/12:FAILED|FAILED| ok | [ 0.000000] sirq-safe-A => hirqs-on/21:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + irqs-on/12:FAILED|FAILED| ok | [ 0.000000] soft-safe-A + irqs-on/12:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + irqs-on/21:FAILED|FAILED| ok | [ 0.000000] soft-safe-A + irqs-on/21:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + unsafe-B #1/123: ok | ok | ok | [ 0.000000] soft-safe-A + unsafe-B #1/123: ok | ok | ok | With this series + lockdep probes registered, all locking tests pass: [ 0.000000] hard-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] soft-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/12: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/21: ok | ok | ok | [ 0.000000] hard-safe-A + irqs-on/12: ok | ok | ok | [ 0.000000] soft-safe-A + irqs-on/12: ok | ok | ok | [ 0.000000] hard-safe-A + irqs-on/21: ok | ok | ok | [ 0.000000] soft-safe-A + irqs-on/21: ok | ok | ok | [ 0.000000] hard-safe-A + unsafe-B #1/123: ok | ok | ok | [ 0.000000] soft-safe-A + unsafe-B #1/123: ok | ok | ok | Link: http://lkml.kernel.org/r/20180730222423.196630-4-joel@joelfernandes.org Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2018-07-30 22:24:23 +00:00
#ifdef CONFIG_TRACE_PREEMPT_TOGGLE
extern void trace_preempt_on(unsigned long a0, unsigned long a1);
extern void trace_preempt_off(unsigned long a0, unsigned long a1);
#else
/*
* Use defines instead of static inlines because some arches will make code out
* of the CALLER_ADDR, when we really want these to be a real nop.
*/
# define trace_preempt_on(a0, a1) do { } while (0)
# define trace_preempt_off(a0, a1) do { } while (0)
#endif
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
extern void ftrace_init(void);
module/ftrace: handle patchable-function-entry When using patchable-function-entry, the compiler will record the callsites into a section named "__patchable_function_entries" rather than "__mcount_loc". Let's abstract this difference behind a new FTRACE_CALLSITE_SECTION, so that architectures don't have to handle this explicitly (e.g. with custom module linker scripts). As parisc currently handles this explicitly, it is fixed up accordingly, with its custom linker script removed. Since FTRACE_CALLSITE_SECTION is only defined when DYNAMIC_FTRACE is selected, the parisc module loading code is updated to only use the definition in that case. When DYNAMIC_FTRACE is not selected, modules shouldn't have this section, so this removes some redundant work in that case. To make sure that this is keep up-to-date for modules and the main kernel, a comment is added to vmlinux.lds.h, with the existing ifdeffery simplified for legibility. I built parisc generic-{32,64}bit_defconfig with DYNAMIC_FTRACE enabled, and verified that the section made it into the .ko files for modules. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Acked-by: Helge Deller <deller@gmx.de> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Torsten Duwe <duwe@suse.de> Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com> Tested-by: Sven Schnelle <svens@stackframe.org> Tested-by: Torsten Duwe <duwe@suse.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: Jessica Yu <jeyu@kernel.org> Cc: linux-parisc@vger.kernel.org
2019-10-16 17:17:11 +00:00
#ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY
#define FTRACE_CALLSITE_SECTION "__patchable_function_entries"
#else
#define FTRACE_CALLSITE_SECTION "__mcount_loc"
#endif
#else
static inline void ftrace_init(void) { }
#endif
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-25 23:57:25 +00:00
/*
* Structure that defines an entry function trace.
* It's already packed but the attribute "packed" is needed
* to remove extra padding at the end.
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-25 23:57:25 +00:00
*/
struct ftrace_graph_ent {
unsigned long func; /* Current function */
int depth;
} __packed;
/*
* Structure that defines a return function trace.
* It's already packed but the attribute "packed" is needed
* to remove extra padding at the end.
*/
struct ftrace_graph_ret {
unsigned long func; /* Current function */
function_graph: Support recording and printing the return value of function Analyzing system call failures with the function_graph tracer can be a time-consuming process, particularly when locating the kernel function that first returns an error in the trace logs. This change aims to simplify the process by recording the function return value to the 'retval' member of 'ftrace_graph_ret' and printing it when outputting the trace log. We have introduced new trace options: funcgraph-retval and funcgraph-retval-hex. The former controls whether to display the return value, while the latter controls the display format. Please note that even if a function's return type is void, a return value will still be printed. You can simply ignore it. This patch only establishes the fundamental infrastructure. Subsequent patches will make this feature available on some commonly used processor architectures. Here is an example: I attempted to attach the demo process to a cpu cgroup, but it failed: echo `pidof demo` > /sys/fs/cgroup/cpu/test/tasks -bash: echo: write error: Invalid argument The strace logs indicate that the write system call returned -EINVAL(-22): ... write(1, "273\n", 4) = -1 EINVAL (Invalid argument) ... To capture trace logs during a write system call, use the following commands: cd /sys/kernel/debug/tracing/ echo 0 > tracing_on echo > trace echo *sys_write > set_graph_function echo *spin* > set_graph_notrace echo *rcu* >> set_graph_notrace echo *alloc* >> set_graph_notrace echo preempt* >> set_graph_notrace echo kfree* >> set_graph_notrace echo $$ > set_ftrace_pid echo function_graph > current_tracer echo 1 > options/funcgraph-retval echo 0 > options/funcgraph-retval-hex echo 1 > tracing_on echo `pidof demo` > /sys/fs/cgroup/cpu/test/tasks echo 0 > tracing_on cat trace > ~/trace.log To locate the root cause, search for error code -22 directly in the file trace.log and identify the first function that returned -22. Once you have identified this function, examine its code to determine the root cause. For example, in the trace log below, cpu_cgroup_can_attach returned -22 first, so we can focus our analysis on this function to identify the root cause. ... 1) | cgroup_migrate() { 1) 0.651 us | cgroup_migrate_add_task(); /* = 0xffff93fcfd346c00 */ 1) | cgroup_migrate_execute() { 1) | cpu_cgroup_can_attach() { 1) | cgroup_taskset_first() { 1) 0.732 us | cgroup_taskset_next(); /* = 0xffff93fc8fb20000 */ 1) 1.232 us | } /* cgroup_taskset_first = 0xffff93fc8fb20000 */ 1) 0.380 us | sched_rt_can_attach(); /* = 0x0 */ 1) 2.335 us | } /* cpu_cgroup_can_attach = -22 */ 1) 4.369 us | } /* cgroup_migrate_execute = -22 */ 1) 7.143 us | } /* cgroup_migrate = -22 */ ... Link: https://lkml.kernel.org/r/1fc502712c981e0e6742185ba242992170ac9da8.1680954589.git.pengdonglin@sangfor.com.cn Tested-by: Florian Kauer <florian.kauer@linutronix.de> Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org> Signed-off-by: Donglin Peng <pengdonglin@sangfor.com.cn> Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2023-04-08 12:42:15 +00:00
#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
unsigned long retval;
#endif
int depth;
tracing/function-return-tracer: add the overrun field Impact: help to find the better depth of trace We decided to arbitrary define the depth of function return trace as "20". Perhaps this is not enough. To help finding an optimal depth, we measure now the overrun: the number of functions that have been missed for the current thread. By default this is not displayed, we have to do set a particular flag on the return tracer: echo overrun > /debug/tracing/trace_options And the overrun will be printed on the right. As the trace shows below, the current 20 depth is not enough. update_wall_time+0x37f/0x8c0 -> update_xtime_cache (345 ns) (Overruns: 2838) update_wall_time+0x384/0x8c0 -> clocksource_get_next (1141 ns) (Overruns: 2838) do_timer+0x23/0x100 -> update_wall_time (3882 ns) (Overruns: 2838) tick_do_update_jiffies64+0xbf/0x160 -> do_timer (5339 ns) (Overruns: 2838) tick_sched_timer+0x6a/0xf0 -> tick_do_update_jiffies64 (7209 ns) (Overruns: 2838) vgacon_set_cursor_size+0x98/0x120 -> native_io_delay (2613 ns) (Overruns: 274) vgacon_cursor+0x16e/0x1d0 -> vgacon_set_cursor_size (33151 ns) (Overruns: 274) set_cursor+0x5f/0x80 -> vgacon_cursor (36432 ns) (Overruns: 274) con_flush_chars+0x34/0x40 -> set_cursor (38790 ns) (Overruns: 274) release_console_sem+0x1ec/0x230 -> up (721 ns) (Overruns: 274) release_console_sem+0x225/0x230 -> wake_up_klogd (316 ns) (Overruns: 274) con_flush_chars+0x39/0x40 -> release_console_sem (2996 ns) (Overruns: 274) con_write+0x22/0x30 -> con_flush_chars (46067 ns) (Overruns: 274) n_tty_write+0x1cc/0x360 -> con_write (292670 ns) (Overruns: 274) smp_apic_timer_interrupt+0x2a/0x90 -> native_apic_mem_write (330 ns) (Overruns: 274) irq_enter+0x17/0x70 -> idle_cpu (413 ns) (Overruns: 274) smp_apic_timer_interrupt+0x2f/0x90 -> irq_enter (1525 ns) (Overruns: 274) ktime_get_ts+0x40/0x70 -> getnstimeofday (465 ns) (Overruns: 274) ktime_get_ts+0x60/0x70 -> set_normalized_timespec (436 ns) (Overruns: 274) ktime_get+0x16/0x30 -> ktime_get_ts (2501 ns) (Overruns: 274) hrtimer_interrupt+0x77/0x1a0 -> ktime_get (3439 ns) (Overruns: 274) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-17 02:22:41 +00:00
/* Number of functions that overran the depth limit for current task */
unsigned int overrun;
unsigned long long calltime;
unsigned long long rettime;
} __packed;
/* Type of the callback handlers for tracing function graph*/
typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */
typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */
extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
struct fgraph_ops {
trace_func_graph_ent_t entryfunc;
trace_func_graph_ret_t retfunc;
};
/*
* Stack of return addresses for functions
* of a thread.
* Used in struct thread_info
*/
struct ftrace_ret_stack {
unsigned long ret;
unsigned long func;
unsigned long long calltime;
#ifdef CONFIG_FUNCTION_PROFILER
unsigned long long subtime;
#endif
#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
function-graph: add stack frame test In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18 16:45:08 +00:00
unsigned long fp;
#endif
#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
unsigned long *retp;
#endif
};
/*
* Primary handler of a function return.
* It relays on ftrace_return_to_handler.
* Defined in entry_32/64.S
*/
extern void return_to_handler(void);
extern int
function_graph_enter(unsigned long ret, unsigned long func,
unsigned long frame_pointer, unsigned long *retp);
struct ftrace_ret_stack *
ftrace_graph_get_ret_stack(struct task_struct *task, int idx);
ftrace: Add ftrace_graph_ret_addr() stack unwinding helpers When function graph tracing is enabled for a function, ftrace modifies the stack by replacing the original return address with the address of a hook function (return_to_handler). Stack unwinders need a way to get the original return address. Add an arch-independent helper function for that named ftrace_graph_ret_addr(). This adds two variations of the function: one depends on HAVE_FUNCTION_GRAPH_RET_ADDR_PTR, and the other relies on an index state variable. The former is recommended because, in some cases, the latter can cause problems when the unwinder skips stack frames. It can get out of sync with the ret_stack index and wrong addresses can be reported for the stack trace. Once all arches have been ported to use HAVE_FUNCTION_GRAPH_RET_ADDR_PTR, we can get rid of the distinction. Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nilay Vaish <nilayvaish@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/36bd90f762fc5e5af3929e3797a68a64906421cf.1471607358.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-19 11:52:58 +00:00
unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
unsigned long ret, unsigned long *retp);
/*
* Sometimes we don't want to trace a function with the function
* graph tracer but we want them to keep traced by the usual function
* tracer if the function graph tracer is not configured.
*/
#define __notrace_funcgraph notrace
#define FTRACE_RETFUNC_DEPTH 50
#define FTRACE_RETSTACK_ALLOC_SIZE 32
extern int register_ftrace_graph(struct fgraph_ops *ops);
extern void unregister_ftrace_graph(struct fgraph_ops *ops);
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-25 23:57:25 +00:00
/**
* ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called
*
* ftrace_graph_stop() is called when a severe error is detected in
* the function graph tracing. This function is called by the critical
* paths of function graph to keep those paths from doing any more harm.
*/
DECLARE_STATIC_KEY_FALSE(kill_ftrace_graph);
static inline bool ftrace_graph_is_dead(void)
{
return static_branch_unlikely(&kill_ftrace_graph);
}
extern void ftrace_graph_stop(void);
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-25 23:57:25 +00:00
/* The current handlers in use */
extern trace_func_graph_ret_t ftrace_graph_return;
extern trace_func_graph_ent_t ftrace_graph_entry;
extern void ftrace_graph_init_task(struct task_struct *t);
extern void ftrace_graph_exit_task(struct task_struct *t);
ftrace: Fix memory leak with function graph and cpu hotplug When the fuction graph tracer starts, it needs to make a special stack for each task to save the real return values of the tasks. All running tasks have this stack created, as well as any new tasks. On CPU hot plug, the new idle task will allocate a stack as well when init_idle() is called. The problem is that cpu hotplug does not create a new idle_task. Instead it uses the idle task that existed when the cpu went down. ftrace_graph_init_task() will add a new ret_stack to the task that is given to it. Because a clone will make the task have a stack of its parent it does not check if the task's ret_stack is already NULL or not. When the CPU hotplug code starts a CPU up again, it will allocate a new stack even though one already existed for it. The solution is to treat the idle_task specially. In fact, the function_graph code already does, just not at init_idle(). Instead of using the ftrace_graph_init_task() for the idle task, which that function expects the task to be a clone, have a separate ftrace_graph_init_idle_task(). Also, we will create a per_cpu ret_stack that is used by the idle task. When we call ftrace_graph_init_idle_task() it will check if the idle task's ret_stack is NULL, if it is, then it will assign it the per_cpu ret_stack. Reported-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Suggested-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stable Tree <stable@kernel.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-02-11 02:26:13 +00:00
extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu);
static inline void pause_graph_tracing(void)
{
atomic_inc(&current->tracing_graph_pause);
}
static inline void unpause_graph_tracing(void)
{
atomic_dec(&current->tracing_graph_pause);
}
#else /* !CONFIG_FUNCTION_GRAPH_TRACER */
#define __notrace_funcgraph
static inline void ftrace_graph_init_task(struct task_struct *t) { }
static inline void ftrace_graph_exit_task(struct task_struct *t) { }
ftrace: Fix memory leak with function graph and cpu hotplug When the fuction graph tracer starts, it needs to make a special stack for each task to save the real return values of the tasks. All running tasks have this stack created, as well as any new tasks. On CPU hot plug, the new idle task will allocate a stack as well when init_idle() is called. The problem is that cpu hotplug does not create a new idle_task. Instead it uses the idle task that existed when the cpu went down. ftrace_graph_init_task() will add a new ret_stack to the task that is given to it. Because a clone will make the task have a stack of its parent it does not check if the task's ret_stack is already NULL or not. When the CPU hotplug code starts a CPU up again, it will allocate a new stack even though one already existed for it. The solution is to treat the idle_task specially. In fact, the function_graph code already does, just not at init_idle(). Instead of using the ftrace_graph_init_task() for the idle task, which that function expects the task to be a clone, have a separate ftrace_graph_init_idle_task(). Also, we will create a per_cpu ret_stack that is used by the idle task. When we call ftrace_graph_init_idle_task() it will check if the idle task's ret_stack is NULL, if it is, then it will assign it the per_cpu ret_stack. Reported-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Suggested-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stable Tree <stable@kernel.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-02-11 02:26:13 +00:00
static inline void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { }
/* Define as macros as fgraph_ops may not be defined */
#define register_ftrace_graph(ops) ({ -1; })
#define unregister_ftrace_graph(ops) do { } while (0)
ftrace: Add ftrace_graph_ret_addr() stack unwinding helpers When function graph tracing is enabled for a function, ftrace modifies the stack by replacing the original return address with the address of a hook function (return_to_handler). Stack unwinders need a way to get the original return address. Add an arch-independent helper function for that named ftrace_graph_ret_addr(). This adds two variations of the function: one depends on HAVE_FUNCTION_GRAPH_RET_ADDR_PTR, and the other relies on an index state variable. The former is recommended because, in some cases, the latter can cause problems when the unwinder skips stack frames. It can get out of sync with the ret_stack index and wrong addresses can be reported for the stack trace. Once all arches have been ported to use HAVE_FUNCTION_GRAPH_RET_ADDR_PTR, we can get rid of the distinction. Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nilay Vaish <nilayvaish@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/36bd90f762fc5e5af3929e3797a68a64906421cf.1471607358.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-19 11:52:58 +00:00
static inline unsigned long
ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret,
unsigned long *retp)
{
return ret;
}
static inline void pause_graph_tracing(void) { }
static inline void unpause_graph_tracing(void) { }
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
ftrace: graph of a single function This patch adds the file: /debugfs/tracing/set_graph_function which can be used along with the function graph tracer. When this file is empty, the function graph tracer will act as usual. When the file has a function in it, the function graph tracer will only trace that function. For example: # echo blk_unplug > /debugfs/tracing/set_graph_function # cat /debugfs/tracing/trace [...] ------------------------------------------ | 2) make-19003 => kjournald-2219 ------------------------------------------ 2) | blk_unplug() { 2) | dm_unplug_all() { 2) | dm_get_table() { 2) 1.381 us | _read_lock(); 2) 0.911 us | dm_table_get(); 2) 1. 76 us | _read_unlock(); 2) + 12.912 us | } 2) | dm_table_unplug_all() { 2) | blk_unplug() { 2) 0.778 us | generic_unplug_device(); 2) 2.409 us | } 2) 5.992 us | } 2) 0.813 us | dm_table_put(); 2) + 29. 90 us | } 2) + 34.532 us | } You can add up to 32 functions into this file. Currently we limit it to 32, but this may change with later improvements. To add another function, use the append '>>': # echo sys_read >> /debugfs/tracing/set_graph_function # cat /debugfs/tracing/set_graph_function blk_unplug sys_read Using the '>' will clear out the function and write anew: # echo sys_write > /debug/tracing/set_graph_function # cat /debug/tracing/set_graph_function sys_write Note, if you have function graph running while doing this, the small time between clearing it and updating it will cause the graph to record all functions. This should not be an issue because after it sets the filter, only those functions will be recorded from then on. If you need to only record a particular function then set this file first before starting the function graph tracer. In the future this side effect may be corrected. The set_graph_function file is similar to the set_ftrace_filter but it does not take wild cards nor does it allow for more than one function to be set with a single write. There is no technical reason why this is the case, I just do not have the time yet to implement that. Note, dynamic ftrace must be enabled for this to appear because it uses the dynamic ftrace records to match the name to the mcount call sites. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-03 20:36:57 +00:00
#ifdef CONFIG_TRACING
enum ftrace_dump_mode;
2024-02-23 08:31:26 +00:00
#define MAX_TRACER_SIZE 100
extern char ftrace_dump_on_oops[];
extern int ftrace_dump_on_oops_enabled(void);
extern int tracepoint_printk;
extern void disable_trace_on_warning(void);
extern int __disable_trace_on_warning;
int tracepoint_printk_sysctl(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos);
#else /* CONFIG_TRACING */
static inline void disable_trace_on_warning(void) { }
ftrace: graph of a single function This patch adds the file: /debugfs/tracing/set_graph_function which can be used along with the function graph tracer. When this file is empty, the function graph tracer will act as usual. When the file has a function in it, the function graph tracer will only trace that function. For example: # echo blk_unplug > /debugfs/tracing/set_graph_function # cat /debugfs/tracing/trace [...] ------------------------------------------ | 2) make-19003 => kjournald-2219 ------------------------------------------ 2) | blk_unplug() { 2) | dm_unplug_all() { 2) | dm_get_table() { 2) 1.381 us | _read_lock(); 2) 0.911 us | dm_table_get(); 2) 1. 76 us | _read_unlock(); 2) + 12.912 us | } 2) | dm_table_unplug_all() { 2) | blk_unplug() { 2) 0.778 us | generic_unplug_device(); 2) 2.409 us | } 2) 5.992 us | } 2) 0.813 us | dm_table_put(); 2) + 29. 90 us | } 2) + 34.532 us | } You can add up to 32 functions into this file. Currently we limit it to 32, but this may change with later improvements. To add another function, use the append '>>': # echo sys_read >> /debugfs/tracing/set_graph_function # cat /debugfs/tracing/set_graph_function blk_unplug sys_read Using the '>' will clear out the function and write anew: # echo sys_write > /debug/tracing/set_graph_function # cat /debug/tracing/set_graph_function sys_write Note, if you have function graph running while doing this, the small time between clearing it and updating it will cause the graph to record all functions. This should not be an issue because after it sets the filter, only those functions will be recorded from then on. If you need to only record a particular function then set this file first before starting the function graph tracer. In the future this side effect may be corrected. The set_graph_function file is similar to the set_ftrace_filter but it does not take wild cards nor does it allow for more than one function to be set with a single write. There is no technical reason why this is the case, I just do not have the time yet to implement that. Note, dynamic ftrace must be enabled for this to appear because it uses the dynamic ftrace records to match the name to the mcount call sites. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-03 20:36:57 +00:00
#endif /* CONFIG_TRACING */
#ifdef CONFIG_FTRACE_SYSCALLS
unsigned long arch_syscall_addr(int nr);
#endif /* CONFIG_FTRACE_SYSCALLS */
#endif /* _LINUX_FTRACE_H */