Re: [PATCH v4 5/5] tracing: convert sys_enter/exit to faultable tracepoints

From: Peter Zijlstra
Date: Mon Nov 20 2023 - 16:48:36 EST

Next message: Tomas Paukrt: "Re: [PATCH v3 2/2] dt-bindings: serial: Add option to enable RS485 mode via GPIO "
Previous message: Heiner Kallweit: "[PATCH v4 20/20] include/linux/i2c.h: remove I2C_CLASS_DDC support"
In reply to: Mathieu Desnoyers: "[PATCH v4 5/5] tracing: convert sys_enter/exit to faultable tracepoints"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

On Mon, Nov 20, 2023 at 03:54:18PM -0500, Mathieu Desnoyers wrote:

> diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
> index de753403cdaf..718a0723a0bc 100644
> --- a/kernel/trace/trace_syscalls.c
> +++ b/kernel/trace/trace_syscalls.c
> @@ -299,27 +299,33 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
> int syscall_nr;
> int size;
>
> + /*
> + * Probe called with preemption enabled (may_fault), but ring buffer and
> + * per-cpu data require preemption to be disabled.
> + */
> + preempt_disable_notrace();

guard(preempt_notrace)();

and ditch all the goto crap.

> +
> syscall_nr = trace_get_syscall_nr(current, regs);
> if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
> - return;
> + goto end;
>
> /* 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;
> + goto end;
>
> if (trace_trigger_soft_disabled(trace_file))
> - return;
> + goto end;
>
> sys_data = syscall_nr_to_meta(syscall_nr);
> if (!sys_data)
> - return;
> + goto end;
>
> size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
>
> entry = trace_event_buffer_reserve(&fbuffer, trace_file, size);
> if (!entry)
> - return;
> + goto end;
>
> entry = ring_buffer_event_data(fbuffer.event);
> entry->nr = syscall_nr;
> @@ -327,6 +333,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
> memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args);
>
> trace_event_buffer_commit(&fbuffer);
> +end:
> + preempt_enable_notrace();
> }
>
> static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
> @@ -338,31 +346,39 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
> struct trace_event_buffer fbuffer;
> int syscall_nr;
>
> + /*
> + * Probe called with preemption enabled (may_fault), but ring buffer and
> + * per-cpu data require preemption to be disabled.
> + */
> + preempt_disable_notrace();

Idem.

> +
> syscall_nr = trace_get_syscall_nr(current, regs);
> if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
> - return;
> + goto end;
>
> /* 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;
> + goto end;
>
> if (trace_trigger_soft_disabled(trace_file))
> - return;
> + goto end;
>
> sys_data = syscall_nr_to_meta(syscall_nr);
> if (!sys_data)
> - return;
> + goto end;
>
> entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry));
> if (!entry)
> - return;
> + goto end;
>
> entry = ring_buffer_event_data(fbuffer.event);
> entry->nr = syscall_nr;
> entry->ret = syscall_get_return_value(current, regs);
>
> trace_event_buffer_commit(&fbuffer);
> +end:
> + preempt_enable_notrace();
> }
>
> static int reg_event_syscall_enter(struct trace_event_file *file,
> @@ -377,7 +393,9 @@ static int reg_event_syscall_enter(struct trace_event_file *file,
> return -ENOSYS;
> mutex_lock(&syscall_trace_lock);
> if (!tr->sys_refcount_enter)
> - ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
> + ret = register_trace_prio_flags_sys_enter(ftrace_syscall_enter, tr,
> + TRACEPOINT_DEFAULT_PRIO,
> + TRACEPOINT_MAY_FAULT);
> if (!ret) {
> rcu_assign_pointer(tr->enter_syscall_files[num], file);
> tr->sys_refcount_enter++;
> @@ -415,7 +433,9 @@ static int reg_event_syscall_exit(struct trace_event_file *file,
> return -ENOSYS;
> mutex_lock(&syscall_trace_lock);
> if (!tr->sys_refcount_exit)
> - ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
> + ret = register_trace_prio_flags_sys_exit(ftrace_syscall_exit, tr,
> + TRACEPOINT_DEFAULT_PRIO,
> + TRACEPOINT_MAY_FAULT);
> if (!ret) {
> rcu_assign_pointer(tr->exit_syscall_files[num], file);
> tr->sys_refcount_exit++;

/me hands you a bucket of {}, free of charge.

> @@ -582,20 +602,26 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
> int rctx;
> int size;
>
> + /*
> + * Probe called with preemption enabled (may_fault), but ring buffer and
> + * per-cpu data require preemption to be disabled.
> + */
> + preempt_disable_notrace();

Again, guard(preempt_notrace)();

> +
> syscall_nr = trace_get_syscall_nr(current, regs);
> if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
> - return;
> + goto end;
> if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
> - return;
> + goto end;
>
> sys_data = syscall_nr_to_meta(syscall_nr);
> if (!sys_data)
> - return;
> + goto end;
>
> head = this_cpu_ptr(sys_data->enter_event->perf_events);
> valid_prog_array = bpf_prog_array_valid(sys_data->enter_event);
> if (!valid_prog_array && hlist_empty(head))
> - return;
> + goto end;
>
> /* get the size after alignment with the u32 buffer size field */
> size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
> @@ -604,7 +630,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
>
> rec = perf_trace_buf_alloc(size, NULL, &rctx);
> if (!rec)
> - return;
> + goto end;
>
> rec->nr = syscall_nr;
> syscall_get_arguments(current, regs, args);
> @@ -614,12 +640,14 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
> !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) ||
> hlist_empty(head)) {
> perf_swevent_put_recursion_context(rctx);
> - return;
> + goto end;
> }
>
> perf_trace_buf_submit(rec, size, rctx,
> sys_data->enter_event->event.type, 1, regs,
> head, NULL);
> +end:
> + preempt_enable_notrace();
> }
>
> static int perf_sysenter_enable(struct trace_event_call *call)
> @@ -631,7 +659,9 @@ static int perf_sysenter_enable(struct trace_event_call *call)
>
> mutex_lock(&syscall_trace_lock);
> if (!sys_perf_refcount_enter)
> - ret = register_trace_sys_enter(perf_syscall_enter, NULL);
> + ret = register_trace_prio_flags_sys_enter(perf_syscall_enter, NULL,
> + TRACEPOINT_DEFAULT_PRIO,
> + TRACEPOINT_MAY_FAULT);

More {}

> if (ret) {
> pr_info("event trace: Could not activate syscall entry trace point");
> } else {
> @@ -682,20 +712,26 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
> int rctx;
> int size;
>
> + /*
> + * Probe called with preemption enabled (may_fault), but ring buffer and
> + * per-cpu data require preemption to be disabled.
> + */
> + preempt_disable_notrace();

Guess?

> +
> syscall_nr = trace_get_syscall_nr(current, regs);
> if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
> - return;
> + goto end;
> if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
> - return;
> + goto end;
>
> sys_data = syscall_nr_to_meta(syscall_nr);
> if (!sys_data)
> - return;
> + goto end;
>
> head = this_cpu_ptr(sys_data->exit_event->perf_events);
> valid_prog_array = bpf_prog_array_valid(sys_data->exit_event);
> if (!valid_prog_array && hlist_empty(head))
> - return;
> + goto end;
>
> /* We can probably do that at build time */
> size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
> @@ -703,7 +739,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
>
> rec = perf_trace_buf_alloc(size, NULL, &rctx);
> if (!rec)
> - return;
> + goto end;
>
> rec->nr = syscall_nr;
> rec->ret = syscall_get_return_value(current, regs);
> @@ -712,11 +748,13 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
> !perf_call_bpf_exit(sys_data->exit_event, regs, rec)) ||
> hlist_empty(head)) {
> perf_swevent_put_recursion_context(rctx);
> - return;
> + goto end;
> }
>
> perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type,
> 1, regs, head, NULL);
> +end:
> + preempt_enable_notrace();
> }
>
> static int perf_sysexit_enable(struct trace_event_call *call)
> @@ -728,7 +766,9 @@ static int perf_sysexit_enable(struct trace_event_call *call)
>
> mutex_lock(&syscall_trace_lock);
> if (!sys_perf_refcount_exit)
> - ret = register_trace_sys_exit(perf_syscall_exit, NULL);
> + ret = register_trace_prio_flags_sys_exit(perf_syscall_exit, NULL,
> + TRACEPOINT_DEFAULT_PRIO,
> + TRACEPOINT_MAY_FAULT);

And yet more {}

> if (ret) {
> pr_info("event trace: Could not activate syscall exit trace point");
> } else {
> --
> 2.25.1
>

Next message: Tomas Paukrt: "Re: [PATCH v3 2/2] dt-bindings: serial: Add option to enable RS485 mode via GPIO "
Previous message: Heiner Kallweit: "[PATCH v4 20/20] include/linux/i2c.h: remove I2C_CLASS_DDC support"
In reply to: Mathieu Desnoyers: "[PATCH v4 5/5] tracing: convert sys_enter/exit to faultable tracepoints"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]