forked from Minki/linux
b24413180f
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>
814 lines
20 KiB
C
814 lines
20 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <trace/syscall.h>
|
|
#include <trace/events/syscalls.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h> /* for MODULE_NAME_LEN via KSYM_SYMBOL_LEN */
|
|
#include <linux/ftrace.h>
|
|
#include <linux/perf_event.h>
|
|
#include <asm/syscall.h>
|
|
|
|
#include "trace_output.h"
|
|
#include "trace.h"
|
|
|
|
static DEFINE_MUTEX(syscall_trace_lock);
|
|
|
|
static int syscall_enter_register(struct trace_event_call *event,
|
|
enum trace_reg type, void *data);
|
|
static int syscall_exit_register(struct trace_event_call *event,
|
|
enum trace_reg type, void *data);
|
|
|
|
static struct list_head *
|
|
syscall_get_enter_fields(struct trace_event_call *call)
|
|
{
|
|
struct syscall_metadata *entry = call->data;
|
|
|
|
return &entry->enter_fields;
|
|
}
|
|
|
|
extern struct syscall_metadata *__start_syscalls_metadata[];
|
|
extern struct syscall_metadata *__stop_syscalls_metadata[];
|
|
|
|
static struct syscall_metadata **syscalls_metadata;
|
|
|
|
#ifndef ARCH_HAS_SYSCALL_MATCH_SYM_NAME
|
|
static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
|
|
{
|
|
/*
|
|
* Only compare after the "sys" prefix. Archs that use
|
|
* syscall wrappers may have syscalls symbols aliases prefixed
|
|
* with ".SyS" or ".sys" instead of "sys", leading to an unwanted
|
|
* mismatch.
|
|
*/
|
|
return !strcmp(sym + 3, name + 3);
|
|
}
|
|
#endif
|
|
|
|
#ifdef ARCH_TRACE_IGNORE_COMPAT_SYSCALLS
|
|
/*
|
|
* Some architectures that allow for 32bit applications
|
|
* to run on a 64bit kernel, do not map the syscalls for
|
|
* the 32bit tasks the same as they do for 64bit tasks.
|
|
*
|
|
* *cough*x86*cough*
|
|
*
|
|
* In such a case, instead of reporting the wrong syscalls,
|
|
* simply ignore them.
|
|
*
|
|
* For an arch to ignore the compat syscalls it needs to
|
|
* define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS as well as
|
|
* define the function arch_trace_is_compat_syscall() to let
|
|
* the tracing system know that it should ignore it.
|
|
*/
|
|
static int
|
|
trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs)
|
|
{
|
|
if (unlikely(arch_trace_is_compat_syscall(regs)))
|
|
return -1;
|
|
|
|
return syscall_get_nr(task, regs);
|
|
}
|
|
#else
|
|
static inline int
|
|
trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs)
|
|
{
|
|
return syscall_get_nr(task, regs);
|
|
}
|
|
#endif /* ARCH_TRACE_IGNORE_COMPAT_SYSCALLS */
|
|
|
|
static __init struct syscall_metadata *
|
|
find_syscall_meta(unsigned long syscall)
|
|
{
|
|
struct syscall_metadata **start;
|
|
struct syscall_metadata **stop;
|
|
char str[KSYM_SYMBOL_LEN];
|
|
|
|
|
|
start = __start_syscalls_metadata;
|
|
stop = __stop_syscalls_metadata;
|
|
kallsyms_lookup(syscall, NULL, NULL, NULL, str);
|
|
|
|
if (arch_syscall_match_sym_name(str, "sys_ni_syscall"))
|
|
return NULL;
|
|
|
|
for ( ; start < stop; start++) {
|
|
if ((*start)->name && arch_syscall_match_sym_name(str, (*start)->name))
|
|
return *start;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
static struct syscall_metadata *syscall_nr_to_meta(int nr)
|
|
{
|
|
if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
|
|
return NULL;
|
|
|
|
return syscalls_metadata[nr];
|
|
}
|
|
|
|
const char *get_syscall_name(int syscall)
|
|
{
|
|
struct syscall_metadata *entry;
|
|
|
|
entry = syscall_nr_to_meta(syscall);
|
|
if (!entry)
|
|
return NULL;
|
|
|
|
return entry->name;
|
|
}
|
|
|
|
static enum print_line_t
|
|
print_syscall_enter(struct trace_iterator *iter, int flags,
|
|
struct trace_event *event)
|
|
{
|
|
struct trace_array *tr = iter->tr;
|
|
struct trace_seq *s = &iter->seq;
|
|
struct trace_entry *ent = iter->ent;
|
|
struct syscall_trace_enter *trace;
|
|
struct syscall_metadata *entry;
|
|
int i, syscall;
|
|
|
|
trace = (typeof(trace))ent;
|
|
syscall = trace->nr;
|
|
entry = syscall_nr_to_meta(syscall);
|
|
|
|
if (!entry)
|
|
goto end;
|
|
|
|
if (entry->enter_event->event.type != ent->type) {
|
|
WARN_ON_ONCE(1);
|
|
goto end;
|
|
}
|
|
|
|
trace_seq_printf(s, "%s(", entry->name);
|
|
|
|
for (i = 0; i < entry->nb_args; i++) {
|
|
|
|
if (trace_seq_has_overflowed(s))
|
|
goto end;
|
|
|
|
/* parameter types */
|
|
if (tr->trace_flags & TRACE_ITER_VERBOSE)
|
|
trace_seq_printf(s, "%s ", entry->types[i]);
|
|
|
|
/* parameter values */
|
|
trace_seq_printf(s, "%s: %lx%s", entry->args[i],
|
|
trace->args[i],
|
|
i == entry->nb_args - 1 ? "" : ", ");
|
|
}
|
|
|
|
trace_seq_putc(s, ')');
|
|
end:
|
|
trace_seq_putc(s, '\n');
|
|
|
|
return trace_handle_return(s);
|
|
}
|
|
|
|
static enum print_line_t
|
|
print_syscall_exit(struct trace_iterator *iter, int flags,
|
|
struct trace_event *event)
|
|
{
|
|
struct trace_seq *s = &iter->seq;
|
|
struct trace_entry *ent = iter->ent;
|
|
struct syscall_trace_exit *trace;
|
|
int syscall;
|
|
struct syscall_metadata *entry;
|
|
|
|
trace = (typeof(trace))ent;
|
|
syscall = trace->nr;
|
|
entry = syscall_nr_to_meta(syscall);
|
|
|
|
if (!entry) {
|
|
trace_seq_putc(s, '\n');
|
|
goto out;
|
|
}
|
|
|
|
if (entry->exit_event->event.type != ent->type) {
|
|
WARN_ON_ONCE(1);
|
|
return TRACE_TYPE_UNHANDLED;
|
|
}
|
|
|
|
trace_seq_printf(s, "%s -> 0x%lx\n", entry->name,
|
|
trace->ret);
|
|
|
|
out:
|
|
return trace_handle_return(s);
|
|
}
|
|
|
|
extern char *__bad_type_size(void);
|
|
|
|
#define SYSCALL_FIELD(type, field, name) \
|
|
sizeof(type) != sizeof(trace.field) ? \
|
|
__bad_type_size() : \
|
|
#type, #name, offsetof(typeof(trace), field), \
|
|
sizeof(trace.field), is_signed_type(type)
|
|
|
|
static int __init
|
|
__set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
|
|
{
|
|
int i;
|
|
int pos = 0;
|
|
|
|
/* When len=0, we just calculate the needed length */
|
|
#define LEN_OR_ZERO (len ? len - pos : 0)
|
|
|
|
pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
|
|
for (i = 0; i < entry->nb_args; i++) {
|
|
pos += snprintf(buf + pos, LEN_OR_ZERO, "%s: 0x%%0%zulx%s",
|
|
entry->args[i], sizeof(unsigned long),
|
|
i == entry->nb_args - 1 ? "" : ", ");
|
|
}
|
|
pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
|
|
|
|
for (i = 0; i < entry->nb_args; i++) {
|
|
pos += snprintf(buf + pos, LEN_OR_ZERO,
|
|
", ((unsigned long)(REC->%s))", entry->args[i]);
|
|
}
|
|
|
|
#undef LEN_OR_ZERO
|
|
|
|
/* return the length of print_fmt */
|
|
return pos;
|
|
}
|
|
|
|
static int __init set_syscall_print_fmt(struct trace_event_call *call)
|
|
{
|
|
char *print_fmt;
|
|
int len;
|
|
struct syscall_metadata *entry = call->data;
|
|
|
|
if (entry->enter_event != call) {
|
|
call->print_fmt = "\"0x%lx\", REC->ret";
|
|
return 0;
|
|
}
|
|
|
|
/* First: called with 0 length to calculate the needed length */
|
|
len = __set_enter_print_fmt(entry, NULL, 0);
|
|
|
|
print_fmt = kmalloc(len + 1, GFP_KERNEL);
|
|
if (!print_fmt)
|
|
return -ENOMEM;
|
|
|
|
/* Second: actually write the @print_fmt */
|
|
__set_enter_print_fmt(entry, print_fmt, len + 1);
|
|
call->print_fmt = print_fmt;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void __init free_syscall_print_fmt(struct trace_event_call *call)
|
|
{
|
|
struct syscall_metadata *entry = call->data;
|
|
|
|
if (entry->enter_event == call)
|
|
kfree(call->print_fmt);
|
|
}
|
|
|
|
static int __init syscall_enter_define_fields(struct trace_event_call *call)
|
|
{
|
|
struct syscall_trace_enter trace;
|
|
struct syscall_metadata *meta = call->data;
|
|
int ret;
|
|
int i;
|
|
int offset = offsetof(typeof(trace), args);
|
|
|
|
ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr),
|
|
FILTER_OTHER);
|
|
if (ret)
|
|
return ret;
|
|
|
|
for (i = 0; i < meta->nb_args; i++) {
|
|
ret = trace_define_field(call, meta->types[i],
|
|
meta->args[i], offset,
|
|
sizeof(unsigned long), 0,
|
|
FILTER_OTHER);
|
|
offset += sizeof(unsigned long);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int __init syscall_exit_define_fields(struct trace_event_call *call)
|
|
{
|
|
struct syscall_trace_exit trace;
|
|
int ret;
|
|
|
|
ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr),
|
|
FILTER_OTHER);
|
|
if (ret)
|
|
return ret;
|
|
|
|
ret = trace_define_field(call, SYSCALL_FIELD(long, ret, ret),
|
|
FILTER_OTHER);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
|
|
{
|
|
struct trace_array *tr = data;
|
|
struct trace_event_file *trace_file;
|
|
struct syscall_trace_enter *entry;
|
|
struct syscall_metadata *sys_data;
|
|
struct ring_buffer_event *event;
|
|
struct ring_buffer *buffer;
|
|
unsigned long irq_flags;
|
|
int pc;
|
|
int syscall_nr;
|
|
int size;
|
|
|
|
syscall_nr = trace_get_syscall_nr(current, regs);
|
|
if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
|
|
return;
|
|
|
|
/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
|
|
trace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]);
|
|
if (!trace_file)
|
|
return;
|
|
|
|
if (trace_trigger_soft_disabled(trace_file))
|
|
return;
|
|
|
|
sys_data = syscall_nr_to_meta(syscall_nr);
|
|
if (!sys_data)
|
|
return;
|
|
|
|
size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
|
|
|
|
local_save_flags(irq_flags);
|
|
pc = preempt_count();
|
|
|
|
buffer = tr->trace_buffer.buffer;
|
|
event = trace_buffer_lock_reserve(buffer,
|
|
sys_data->enter_event->event.type, size, irq_flags, pc);
|
|
if (!event)
|
|
return;
|
|
|
|
entry = ring_buffer_event_data(event);
|
|
entry->nr = syscall_nr;
|
|
syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
|
|
|
|
event_trigger_unlock_commit(trace_file, buffer, event, entry,
|
|
irq_flags, pc);
|
|
}
|
|
|
|
static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
|
|
{
|
|
struct trace_array *tr = data;
|
|
struct trace_event_file *trace_file;
|
|
struct syscall_trace_exit *entry;
|
|
struct syscall_metadata *sys_data;
|
|
struct ring_buffer_event *event;
|
|
struct ring_buffer *buffer;
|
|
unsigned long irq_flags;
|
|
int pc;
|
|
int syscall_nr;
|
|
|
|
syscall_nr = trace_get_syscall_nr(current, regs);
|
|
if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
|
|
return;
|
|
|
|
/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
|
|
trace_file = rcu_dereference_sched(tr->exit_syscall_files[syscall_nr]);
|
|
if (!trace_file)
|
|
return;
|
|
|
|
if (trace_trigger_soft_disabled(trace_file))
|
|
return;
|
|
|
|
sys_data = syscall_nr_to_meta(syscall_nr);
|
|
if (!sys_data)
|
|
return;
|
|
|
|
local_save_flags(irq_flags);
|
|
pc = preempt_count();
|
|
|
|
buffer = tr->trace_buffer.buffer;
|
|
event = trace_buffer_lock_reserve(buffer,
|
|
sys_data->exit_event->event.type, sizeof(*entry),
|
|
irq_flags, pc);
|
|
if (!event)
|
|
return;
|
|
|
|
entry = ring_buffer_event_data(event);
|
|
entry->nr = syscall_nr;
|
|
entry->ret = syscall_get_return_value(current, regs);
|
|
|
|
event_trigger_unlock_commit(trace_file, buffer, event, entry,
|
|
irq_flags, pc);
|
|
}
|
|
|
|
static int reg_event_syscall_enter(struct trace_event_file *file,
|
|
struct trace_event_call *call)
|
|
{
|
|
struct trace_array *tr = file->tr;
|
|
int ret = 0;
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
|
|
return -ENOSYS;
|
|
mutex_lock(&syscall_trace_lock);
|
|
if (!tr->sys_refcount_enter)
|
|
ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
|
|
if (!ret) {
|
|
rcu_assign_pointer(tr->enter_syscall_files[num], file);
|
|
tr->sys_refcount_enter++;
|
|
}
|
|
mutex_unlock(&syscall_trace_lock);
|
|
return ret;
|
|
}
|
|
|
|
static void unreg_event_syscall_enter(struct trace_event_file *file,
|
|
struct trace_event_call *call)
|
|
{
|
|
struct trace_array *tr = file->tr;
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
|
|
return;
|
|
mutex_lock(&syscall_trace_lock);
|
|
tr->sys_refcount_enter--;
|
|
RCU_INIT_POINTER(tr->enter_syscall_files[num], NULL);
|
|
if (!tr->sys_refcount_enter)
|
|
unregister_trace_sys_enter(ftrace_syscall_enter, tr);
|
|
mutex_unlock(&syscall_trace_lock);
|
|
}
|
|
|
|
static int reg_event_syscall_exit(struct trace_event_file *file,
|
|
struct trace_event_call *call)
|
|
{
|
|
struct trace_array *tr = file->tr;
|
|
int ret = 0;
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
|
|
return -ENOSYS;
|
|
mutex_lock(&syscall_trace_lock);
|
|
if (!tr->sys_refcount_exit)
|
|
ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
|
|
if (!ret) {
|
|
rcu_assign_pointer(tr->exit_syscall_files[num], file);
|
|
tr->sys_refcount_exit++;
|
|
}
|
|
mutex_unlock(&syscall_trace_lock);
|
|
return ret;
|
|
}
|
|
|
|
static void unreg_event_syscall_exit(struct trace_event_file *file,
|
|
struct trace_event_call *call)
|
|
{
|
|
struct trace_array *tr = file->tr;
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
|
|
return;
|
|
mutex_lock(&syscall_trace_lock);
|
|
tr->sys_refcount_exit--;
|
|
RCU_INIT_POINTER(tr->exit_syscall_files[num], NULL);
|
|
if (!tr->sys_refcount_exit)
|
|
unregister_trace_sys_exit(ftrace_syscall_exit, tr);
|
|
mutex_unlock(&syscall_trace_lock);
|
|
}
|
|
|
|
static int __init init_syscall_trace(struct trace_event_call *call)
|
|
{
|
|
int id;
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
if (num < 0 || num >= NR_syscalls) {
|
|
pr_debug("syscall %s metadata not mapped, disabling ftrace event\n",
|
|
((struct syscall_metadata *)call->data)->name);
|
|
return -ENOSYS;
|
|
}
|
|
|
|
if (set_syscall_print_fmt(call) < 0)
|
|
return -ENOMEM;
|
|
|
|
id = trace_event_raw_init(call);
|
|
|
|
if (id < 0) {
|
|
free_syscall_print_fmt(call);
|
|
return id;
|
|
}
|
|
|
|
return id;
|
|
}
|
|
|
|
struct trace_event_functions enter_syscall_print_funcs = {
|
|
.trace = print_syscall_enter,
|
|
};
|
|
|
|
struct trace_event_functions exit_syscall_print_funcs = {
|
|
.trace = print_syscall_exit,
|
|
};
|
|
|
|
struct trace_event_class __refdata event_class_syscall_enter = {
|
|
.system = "syscalls",
|
|
.reg = syscall_enter_register,
|
|
.define_fields = syscall_enter_define_fields,
|
|
.get_fields = syscall_get_enter_fields,
|
|
.raw_init = init_syscall_trace,
|
|
};
|
|
|
|
struct trace_event_class __refdata event_class_syscall_exit = {
|
|
.system = "syscalls",
|
|
.reg = syscall_exit_register,
|
|
.define_fields = syscall_exit_define_fields,
|
|
.fields = LIST_HEAD_INIT(event_class_syscall_exit.fields),
|
|
.raw_init = init_syscall_trace,
|
|
};
|
|
|
|
unsigned long __init __weak arch_syscall_addr(int nr)
|
|
{
|
|
return (unsigned long)sys_call_table[nr];
|
|
}
|
|
|
|
void __init init_ftrace_syscalls(void)
|
|
{
|
|
struct syscall_metadata *meta;
|
|
unsigned long addr;
|
|
int i;
|
|
|
|
syscalls_metadata = kcalloc(NR_syscalls, sizeof(*syscalls_metadata),
|
|
GFP_KERNEL);
|
|
if (!syscalls_metadata) {
|
|
WARN_ON(1);
|
|
return;
|
|
}
|
|
|
|
for (i = 0; i < NR_syscalls; i++) {
|
|
addr = arch_syscall_addr(i);
|
|
meta = find_syscall_meta(addr);
|
|
if (!meta)
|
|
continue;
|
|
|
|
meta->syscall_nr = i;
|
|
syscalls_metadata[i] = meta;
|
|
}
|
|
}
|
|
|
|
#ifdef CONFIG_PERF_EVENTS
|
|
|
|
static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls);
|
|
static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
|
|
static int sys_perf_refcount_enter;
|
|
static int sys_perf_refcount_exit;
|
|
|
|
static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs,
|
|
struct syscall_metadata *sys_data,
|
|
struct syscall_trace_enter *rec) {
|
|
struct syscall_tp_t {
|
|
unsigned long long regs;
|
|
unsigned long syscall_nr;
|
|
unsigned long args[SYSCALL_DEFINE_MAXARGS];
|
|
} param;
|
|
int i;
|
|
|
|
*(struct pt_regs **)¶m = regs;
|
|
param.syscall_nr = rec->nr;
|
|
for (i = 0; i < sys_data->nb_args; i++)
|
|
param.args[i] = rec->args[i];
|
|
return trace_call_bpf(prog, ¶m);
|
|
}
|
|
|
|
static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
|
|
{
|
|
struct syscall_metadata *sys_data;
|
|
struct syscall_trace_enter *rec;
|
|
struct hlist_head *head;
|
|
struct bpf_prog *prog;
|
|
int syscall_nr;
|
|
int rctx;
|
|
int size;
|
|
|
|
syscall_nr = trace_get_syscall_nr(current, regs);
|
|
if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
|
|
return;
|
|
if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
|
|
return;
|
|
|
|
sys_data = syscall_nr_to_meta(syscall_nr);
|
|
if (!sys_data)
|
|
return;
|
|
|
|
prog = READ_ONCE(sys_data->enter_event->prog);
|
|
head = this_cpu_ptr(sys_data->enter_event->perf_events);
|
|
if (!prog && hlist_empty(head))
|
|
return;
|
|
|
|
/* get the size after alignment with the u32 buffer size field */
|
|
size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
|
|
size = ALIGN(size + sizeof(u32), sizeof(u64));
|
|
size -= sizeof(u32);
|
|
|
|
rec = perf_trace_buf_alloc(size, NULL, &rctx);
|
|
if (!rec)
|
|
return;
|
|
|
|
rec->nr = syscall_nr;
|
|
syscall_get_arguments(current, regs, 0, sys_data->nb_args,
|
|
(unsigned long *)&rec->args);
|
|
|
|
if ((prog && !perf_call_bpf_enter(prog, regs, sys_data, rec)) ||
|
|
hlist_empty(head)) {
|
|
perf_swevent_put_recursion_context(rctx);
|
|
return;
|
|
}
|
|
|
|
perf_trace_buf_submit(rec, size, rctx,
|
|
sys_data->enter_event->event.type, 1, regs,
|
|
head, NULL, NULL);
|
|
}
|
|
|
|
static int perf_sysenter_enable(struct trace_event_call *call)
|
|
{
|
|
int ret = 0;
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
|
|
mutex_lock(&syscall_trace_lock);
|
|
if (!sys_perf_refcount_enter)
|
|
ret = register_trace_sys_enter(perf_syscall_enter, NULL);
|
|
if (ret) {
|
|
pr_info("event trace: Could not activate syscall entry trace point");
|
|
} else {
|
|
set_bit(num, enabled_perf_enter_syscalls);
|
|
sys_perf_refcount_enter++;
|
|
}
|
|
mutex_unlock(&syscall_trace_lock);
|
|
return ret;
|
|
}
|
|
|
|
static void perf_sysenter_disable(struct trace_event_call *call)
|
|
{
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
|
|
mutex_lock(&syscall_trace_lock);
|
|
sys_perf_refcount_enter--;
|
|
clear_bit(num, enabled_perf_enter_syscalls);
|
|
if (!sys_perf_refcount_enter)
|
|
unregister_trace_sys_enter(perf_syscall_enter, NULL);
|
|
mutex_unlock(&syscall_trace_lock);
|
|
}
|
|
|
|
static int perf_call_bpf_exit(struct bpf_prog *prog, struct pt_regs *regs,
|
|
struct syscall_trace_exit *rec) {
|
|
struct syscall_tp_t {
|
|
unsigned long long regs;
|
|
unsigned long syscall_nr;
|
|
unsigned long ret;
|
|
} param;
|
|
|
|
*(struct pt_regs **)¶m = regs;
|
|
param.syscall_nr = rec->nr;
|
|
param.ret = rec->ret;
|
|
return trace_call_bpf(prog, ¶m);
|
|
}
|
|
|
|
static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
|
|
{
|
|
struct syscall_metadata *sys_data;
|
|
struct syscall_trace_exit *rec;
|
|
struct hlist_head *head;
|
|
struct bpf_prog *prog;
|
|
int syscall_nr;
|
|
int rctx;
|
|
int size;
|
|
|
|
syscall_nr = trace_get_syscall_nr(current, regs);
|
|
if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
|
|
return;
|
|
if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
|
|
return;
|
|
|
|
sys_data = syscall_nr_to_meta(syscall_nr);
|
|
if (!sys_data)
|
|
return;
|
|
|
|
prog = READ_ONCE(sys_data->exit_event->prog);
|
|
head = this_cpu_ptr(sys_data->exit_event->perf_events);
|
|
if (!prog && hlist_empty(head))
|
|
return;
|
|
|
|
/* We can probably do that at build time */
|
|
size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
|
|
size -= sizeof(u32);
|
|
|
|
rec = perf_trace_buf_alloc(size, NULL, &rctx);
|
|
if (!rec)
|
|
return;
|
|
|
|
rec->nr = syscall_nr;
|
|
rec->ret = syscall_get_return_value(current, regs);
|
|
|
|
if ((prog && !perf_call_bpf_exit(prog, regs, rec)) ||
|
|
hlist_empty(head)) {
|
|
perf_swevent_put_recursion_context(rctx);
|
|
return;
|
|
}
|
|
|
|
perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type,
|
|
1, regs, head, NULL, NULL);
|
|
}
|
|
|
|
static int perf_sysexit_enable(struct trace_event_call *call)
|
|
{
|
|
int ret = 0;
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
|
|
mutex_lock(&syscall_trace_lock);
|
|
if (!sys_perf_refcount_exit)
|
|
ret = register_trace_sys_exit(perf_syscall_exit, NULL);
|
|
if (ret) {
|
|
pr_info("event trace: Could not activate syscall exit trace point");
|
|
} else {
|
|
set_bit(num, enabled_perf_exit_syscalls);
|
|
sys_perf_refcount_exit++;
|
|
}
|
|
mutex_unlock(&syscall_trace_lock);
|
|
return ret;
|
|
}
|
|
|
|
static void perf_sysexit_disable(struct trace_event_call *call)
|
|
{
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
|
|
mutex_lock(&syscall_trace_lock);
|
|
sys_perf_refcount_exit--;
|
|
clear_bit(num, enabled_perf_exit_syscalls);
|
|
if (!sys_perf_refcount_exit)
|
|
unregister_trace_sys_exit(perf_syscall_exit, NULL);
|
|
mutex_unlock(&syscall_trace_lock);
|
|
}
|
|
|
|
#endif /* CONFIG_PERF_EVENTS */
|
|
|
|
static int syscall_enter_register(struct trace_event_call *event,
|
|
enum trace_reg type, void *data)
|
|
{
|
|
struct trace_event_file *file = data;
|
|
|
|
switch (type) {
|
|
case TRACE_REG_REGISTER:
|
|
return reg_event_syscall_enter(file, event);
|
|
case TRACE_REG_UNREGISTER:
|
|
unreg_event_syscall_enter(file, event);
|
|
return 0;
|
|
|
|
#ifdef CONFIG_PERF_EVENTS
|
|
case TRACE_REG_PERF_REGISTER:
|
|
return perf_sysenter_enable(event);
|
|
case TRACE_REG_PERF_UNREGISTER:
|
|
perf_sysenter_disable(event);
|
|
return 0;
|
|
case TRACE_REG_PERF_OPEN:
|
|
case TRACE_REG_PERF_CLOSE:
|
|
case TRACE_REG_PERF_ADD:
|
|
case TRACE_REG_PERF_DEL:
|
|
return 0;
|
|
#endif
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static int syscall_exit_register(struct trace_event_call *event,
|
|
enum trace_reg type, void *data)
|
|
{
|
|
struct trace_event_file *file = data;
|
|
|
|
switch (type) {
|
|
case TRACE_REG_REGISTER:
|
|
return reg_event_syscall_exit(file, event);
|
|
case TRACE_REG_UNREGISTER:
|
|
unreg_event_syscall_exit(file, event);
|
|
return 0;
|
|
|
|
#ifdef CONFIG_PERF_EVENTS
|
|
case TRACE_REG_PERF_REGISTER:
|
|
return perf_sysexit_enable(event);
|
|
case TRACE_REG_PERF_UNREGISTER:
|
|
perf_sysexit_disable(event);
|
|
return 0;
|
|
case TRACE_REG_PERF_OPEN:
|
|
case TRACE_REG_PERF_CLOSE:
|
|
case TRACE_REG_PERF_ADD:
|
|
case TRACE_REG_PERF_DEL:
|
|
return 0;
|
|
#endif
|
|
}
|
|
return 0;
|
|
}
|