summaryrefslogtreecommitdiff
path: root/kernel/trace/trace_syscalls.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace/trace_syscalls.c')
-rw-r--r--kernel/trace/trace_syscalls.c99
1 files changed, 57 insertions, 42 deletions
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index d85a2f0f316b..46aab0ab9350 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -154,7 +154,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags,
goto end;
/* parameter types */
- if (tr->trace_flags & TRACE_ITER_VERBOSE)
+ if (tr && tr->trace_flags & TRACE_ITER_VERBOSE)
trace_seq_printf(s, "%s ", entry->types[i]);
/* parameter values */
@@ -201,8 +201,6 @@ print_syscall_exit(struct trace_iterator *iter, int flags,
return trace_handle_return(s);
}
-extern char *__bad_type_size(void);
-
#define SYSCALL_FIELD(_type, _name) { \
.type = #_type, .name = #_name, \
.size = sizeof(_type), .align = __alignof__(_type), \
@@ -296,14 +294,18 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
struct trace_event_file *trace_file;
struct syscall_trace_enter *entry;
struct syscall_metadata *sys_data;
- struct ring_buffer_event *event;
- struct trace_buffer *buffer;
- unsigned long irq_flags;
+ struct trace_event_buffer fbuffer;
unsigned long args[6];
- int pc;
int syscall_nr;
int size;
+ /*
+ * Syscall probe called with preemption enabled, but the ring
+ * buffer and per-cpu data require preemption to be disabled.
+ */
+ might_fault();
+ guard(preempt_notrace)();
+
syscall_nr = trace_get_syscall_nr(current, regs);
if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
@@ -322,22 +324,16 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
- local_save_flags(irq_flags);
- pc = preempt_count();
-
- buffer = tr->array_buffer.buffer;
- event = trace_buffer_lock_reserve(buffer,
- sys_data->enter_event->event.type, size, irq_flags, pc);
- if (!event)
+ entry = trace_event_buffer_reserve(&fbuffer, trace_file, size);
+ if (!entry)
return;
- entry = ring_buffer_event_data(event);
+ entry = ring_buffer_event_data(fbuffer.event);
entry->nr = syscall_nr;
syscall_get_arguments(current, regs, args);
memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args);
- event_trigger_unlock_commit(trace_file, buffer, event, entry,
- irq_flags, pc);
+ trace_event_buffer_commit(&fbuffer);
}
static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
@@ -346,12 +342,16 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
struct trace_event_file *trace_file;
struct syscall_trace_exit *entry;
struct syscall_metadata *sys_data;
- struct ring_buffer_event *event;
- struct trace_buffer *buffer;
- unsigned long irq_flags;
- int pc;
+ struct trace_event_buffer fbuffer;
int syscall_nr;
+ /*
+ * Syscall probe called with preemption enabled, but the ring
+ * buffer and per-cpu data require preemption to be disabled.
+ */
+ might_fault();
+ guard(preempt_notrace)();
+
syscall_nr = trace_get_syscall_nr(current, regs);
if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
@@ -368,22 +368,15 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
if (!sys_data)
return;
- local_save_flags(irq_flags);
- pc = preempt_count();
-
- buffer = tr->array_buffer.buffer;
- event = trace_buffer_lock_reserve(buffer,
- sys_data->exit_event->event.type, sizeof(*entry),
- irq_flags, pc);
- if (!event)
+ entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry));
+ if (!entry)
return;
- entry = ring_buffer_event_data(event);
+ entry = ring_buffer_event_data(fbuffer.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);
+ trace_event_buffer_commit(&fbuffer);
}
static int reg_event_syscall_enter(struct trace_event_file *file,
@@ -576,12 +569,16 @@ static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *re
struct syscall_trace_enter *rec)
{
struct syscall_tp_t {
- unsigned long long regs;
- unsigned long syscall_nr;
+ struct trace_entry ent;
+ int syscall_nr;
unsigned long args[SYSCALL_DEFINE_MAXARGS];
- } param;
+ } __aligned(8) param;
int i;
+ BUILD_BUG_ON(sizeof(param.ent) < sizeof(void *));
+
+ /* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. &param) */
+ perf_fetch_caller_regs(regs);
*(struct pt_regs **)&param = regs;
param.syscall_nr = rec->nr;
for (i = 0; i < sys_data->nb_args; i++)
@@ -593,6 +590,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
{
struct syscall_metadata *sys_data;
struct syscall_trace_enter *rec;
+ struct pt_regs *fake_regs;
struct hlist_head *head;
unsigned long args[6];
bool valid_prog_array;
@@ -600,6 +598,13 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
int rctx;
int size;
+ /*
+ * Syscall probe called with preemption enabled, but the ring
+ * buffer and per-cpu data require preemption to be disabled.
+ */
+ might_fault();
+ guard(preempt_notrace)();
+
syscall_nr = trace_get_syscall_nr(current, regs);
if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
@@ -620,7 +625,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
size = ALIGN(size + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- rec = perf_trace_buf_alloc(size, NULL, &rctx);
+ rec = perf_trace_buf_alloc(size, &fake_regs, &rctx);
if (!rec)
return;
@@ -629,7 +634,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
memcpy(&rec->args, args, sizeof(unsigned long) * sys_data->nb_args);
if ((valid_prog_array &&
- !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) ||
+ !perf_call_bpf_enter(sys_data->enter_event, fake_regs, sys_data, rec)) ||
hlist_empty(head)) {
perf_swevent_put_recursion_context(rctx);
return;
@@ -678,11 +683,13 @@ static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *reg
struct syscall_trace_exit *rec)
{
struct syscall_tp_t {
- unsigned long long regs;
- unsigned long syscall_nr;
+ struct trace_entry ent;
+ int syscall_nr;
unsigned long ret;
- } param;
+ } __aligned(8) param;
+ /* bpf prog requires 'regs' to be the first member in the ctx (a.k.a. &param) */
+ perf_fetch_caller_regs(regs);
*(struct pt_regs **)&param = regs;
param.syscall_nr = rec->nr;
param.ret = rec->ret;
@@ -693,12 +700,20 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
{
struct syscall_metadata *sys_data;
struct syscall_trace_exit *rec;
+ struct pt_regs *fake_regs;
struct hlist_head *head;
bool valid_prog_array;
int syscall_nr;
int rctx;
int size;
+ /*
+ * Syscall probe called with preemption enabled, but the ring
+ * buffer and per-cpu data require preemption to be disabled.
+ */
+ might_fault();
+ guard(preempt_notrace)();
+
syscall_nr = trace_get_syscall_nr(current, regs);
if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
@@ -718,7 +733,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
- rec = perf_trace_buf_alloc(size, NULL, &rctx);
+ rec = perf_trace_buf_alloc(size, &fake_regs, &rctx);
if (!rec)
return;
@@ -726,7 +741,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
rec->ret = syscall_get_return_value(current, regs);
if ((valid_prog_array &&
- !perf_call_bpf_exit(sys_data->exit_event, regs, rec)) ||
+ !perf_call_bpf_exit(sys_data->exit_event, fake_regs, rec)) ||
hlist_empty(head)) {
perf_swevent_put_recursion_context(rctx);
return;
generated by cgit (git 2.34.1) at 2025-07-24 07:08:51 +0000