Merge tag 'trace-v6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing updates from Steven Rostedt:

 - Addition of faultable tracepoints

   There's a tracepoint attached to both a system call entry and exit.
   This location is known to allow page faults. The tracepoints are
   called under an rcu_read_lock() which does not allow faults that can
   sleep. This limits the ability of tracepoint handlers to page fault
   in user space system call parameters. Now these tracepoints have been
   made "faultable", allowing the callbacks to fault in user space
   parameters and record them.

   Note, only the infrastructure has been implemented. The consumers
   (perf, ftrace, BPF) now need to have their code modified to allow
   faults.

 - Fix up of BPF code for the tracepoint faultable logic

 - Update tracepoints to use the new static branch API

 - Remove trace_*_rcuidle() variants and the SRCU protection they used

 - Remove unused TRACE_EVENT_FL_FILTERED logic

 - Replace strncpy() with strscpy() and memcpy()

 - Use replace per_cpu_ptr(smp_processor_id()) with this_cpu_ptr()

 - Fix perf events to not duplicate samples when tracing is enabled

 - Replace atomic64_add_return(1, counter) with
   atomic64_inc_return(counter)

 - Make stack trace buffer 4K instead of PAGE_SIZE

 - Remove TRACE_FLAG_IRQS_NOSUPPORT flag as it was never used

 - Get the true return address for function tracer when function graph
   tracer is also running.

   When function_graph trace is running along with function tracer, the
   parent function of the function tracer sometimes is
   "return_to_handler", which is the function graph trampoline to record
   the exit of the function. Use existing logic that calls into the
   fgraph infrastructure to find the real return address.

 - Remove (un)regfunc pointers out of tracepoint structure

 - Added last minute bug fix for setting pending modules in stack
   function filter.

     echo "write*:mod:ext3" > /sys/kernel/tracing/stack_trace_filter

   Would cause a kernel NULL dereference.

 - Minor clean ups

* tag 'trace-v6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (31 commits)
  ftrace: Fix regression with module command in stack_trace_filter
  tracing: Fix function name for trampoline
  ftrace: Get the true parent ip for function tracer
  tracing: Remove redundant check on field->field in histograms
  bpf: ensure RCU Tasks Trace GP for sleepable raw tracepoint BPF links
  bpf: decouple BPF link/attach hook and BPF program sleepable semantics
  bpf: put bpf_link's program when link is safe to be deallocated
  tracing: Replace strncpy() with strscpy() when copying comm
  tracing: Add might_fault() check in __DECLARE_TRACE_SYSCALL
  tracing: Fix syscall tracepoint use-after-free
  tracing: Introduce tracepoint_is_faultable()
  tracing: Introduce tracepoint extended structure
  tracing: Remove TRACE_FLAG_IRQS_NOSUPPORT
  tracing: Replace multiple deprecated strncpy with memcpy
  tracing: Make percpu stack trace buffer invariant to PAGE_SIZE
  tracing: Use atomic64_inc_return() in trace_clock_counter()
  trace/trace_event_perf: remove duplicate samples on the first tracepoint event
  tracing/bpf: Add might_fault check to syscall probes
  tracing/perf: Add might_fault check to syscall probes
  tracing/ftrace: Add might_fault check to syscall probes
  ...

1 files changed, 36 insertions, 45 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 103b30b1c73b..3ef047ed9705 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -593,19 +593,6 @@ int tracing_check_open_get_tr(struct trace_array *tr)
 	return 0;
 }
 
-int call_filter_check_discard(struct trace_event_call *call, void *rec,
-			      struct trace_buffer *buffer,
-			      struct ring_buffer_event *event)
-{
-	if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
-	    !filter_match_preds(call->filter, rec)) {
-		__trace_event_discard_commit(buffer, event);
-		return 1;
-	}
-
-	return 0;
-}
-
 /**
  * trace_find_filtered_pid - check if a pid exists in a filtered_pid list
  * @filtered_pids: The list of pids to check
@@ -988,7 +975,8 @@ static inline void trace_access_lock_init(void)
 #endif
 
 #ifdef CONFIG_STACKTRACE
-static void __ftrace_trace_stack(struct trace_buffer *buffer,
+static void __ftrace_trace_stack(struct trace_array *tr,
+				 struct trace_buffer *buffer,
 				 unsigned int trace_ctx,
 				 int skip, struct pt_regs *regs);
 static inline void ftrace_trace_stack(struct trace_array *tr,
@@ -997,7 +985,8 @@ static inline void ftrace_trace_stack(struct trace_array *tr,
 				      int skip, struct pt_regs *regs);
 
 #else
-static inline void __ftrace_trace_stack(struct trace_buffer *buffer,
+static inline void __ftrace_trace_stack(struct trace_array *tr,
+					struct trace_buffer *buffer,
 					unsigned int trace_ctx,
 					int skip, struct pt_regs *regs)
 {
@@ -1934,7 +1923,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	max_data->critical_start = data->critical_start;
 	max_data->critical_end = data->critical_end;
 
-	strncpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
+	strscpy(max_data->comm, tsk->comm);
 	max_data->pid = tsk->pid;
 	/*
 	 * If tsk == current, then use current_uid(), as that does not use
@@ -2908,7 +2897,6 @@ void
 trace_function(struct trace_array *tr, unsigned long ip, unsigned long
 	       parent_ip, unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_function;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct ftrace_entry *entry;
@@ -2921,11 +2909,9 @@ trace_function(struct trace_array *tr, unsigned long ip, unsigned long
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	if (!call_filter_check_discard(call, entry, buffer, event)) {
-		if (static_branch_unlikely(&trace_function_exports_enabled))
-			ftrace_exports(event, TRACE_EXPORT_FUNCTION);
-		__buffer_unlock_commit(buffer, event);
-	}
+	if (static_branch_unlikely(&trace_function_exports_enabled))
+		ftrace_exports(event, TRACE_EXPORT_FUNCTION);
+	__buffer_unlock_commit(buffer, event);
 }
 
 #ifdef CONFIG_STACKTRACE
@@ -2933,7 +2919,7 @@ trace_function(struct trace_array *tr, unsigned long ip, unsigned long
 /* Allow 4 levels of nesting: normal, softirq, irq, NMI */
 #define FTRACE_KSTACK_NESTING	4
 
-#define FTRACE_KSTACK_ENTRIES	(PAGE_SIZE / FTRACE_KSTACK_NESTING)
+#define FTRACE_KSTACK_ENTRIES	(SZ_4K / FTRACE_KSTACK_NESTING)
 
 struct ftrace_stack {
 	unsigned long		calls[FTRACE_KSTACK_ENTRIES];
@@ -2947,11 +2933,11 @@ struct ftrace_stacks {
 static DEFINE_PER_CPU(struct ftrace_stacks, ftrace_stacks);
 static DEFINE_PER_CPU(int, ftrace_stack_reserve);
 
-static void __ftrace_trace_stack(struct trace_buffer *buffer,
+static void __ftrace_trace_stack(struct trace_array *tr,
+				 struct trace_buffer *buffer,
 				 unsigned int trace_ctx,
 				 int skip, struct pt_regs *regs)
 {
-	struct trace_event_call *call = &event_kernel_stack;
 	struct ring_buffer_event *event;
 	unsigned int size, nr_entries;
 	struct ftrace_stack *fstack;
@@ -2994,6 +2980,20 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 		nr_entries = stack_trace_save(fstack->calls, size, skip);
 	}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/* Mark entry of stack trace as trampoline code */
+	if (tr->ops && tr->ops->trampoline) {
+		unsigned long tramp_start = tr->ops->trampoline;
+		unsigned long tramp_end = tramp_start + tr->ops->trampoline_size;
+		unsigned long *calls = fstack->calls;
+
+		for (int i = 0; i < nr_entries; i++) {
+			if (calls[i] >= tramp_start && calls[i] < tramp_end)
+				calls[i] = FTRACE_TRAMPOLINE_MARKER;
+		}
+	}
+#endif
+
 	event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
 				    struct_size(entry, caller, nr_entries),
 				    trace_ctx);
@@ -3005,8 +3005,7 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 	memcpy(&entry->caller, fstack->calls,
 	       flex_array_size(entry, caller, nr_entries));
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		__buffer_unlock_commit(buffer, event);
+	__buffer_unlock_commit(buffer, event);
 
  out:
 	/* Again, don't let gcc optimize things here */
@@ -3024,7 +3023,7 @@ static inline void ftrace_trace_stack(struct trace_array *tr,
 	if (!(tr->trace_flags & TRACE_ITER_STACKTRACE))
 		return;
 
-	__ftrace_trace_stack(buffer, trace_ctx, skip, regs);
+	__ftrace_trace_stack(tr, buffer, trace_ctx, skip, regs);
 }
 
 void __trace_stack(struct trace_array *tr, unsigned int trace_ctx,
@@ -3033,7 +3032,7 @@ void __trace_stack(struct trace_array *tr, unsigned int trace_ctx,
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 
 	if (rcu_is_watching()) {
-		__ftrace_trace_stack(buffer, trace_ctx, skip, NULL);
+		__ftrace_trace_stack(tr, buffer, trace_ctx, skip, NULL);
 		return;
 	}
 
@@ -3050,7 +3049,7 @@ void __trace_stack(struct trace_array *tr, unsigned int trace_ctx,
 		return;
 
 	ct_irq_enter_irqson();
-	__ftrace_trace_stack(buffer, trace_ctx, skip, NULL);
+	__ftrace_trace_stack(tr, buffer, trace_ctx, skip, NULL);
 	ct_irq_exit_irqson();
 }
 
@@ -3067,8 +3066,8 @@ void trace_dump_stack(int skip)
 	/* Skip 1 to skip this function. */
 	skip++;
 #endif
-	__ftrace_trace_stack(printk_trace->array_buffer.buffer,
-			     tracing_gen_ctx(), skip, NULL);
+	__ftrace_trace_stack(printk_trace, printk_trace->array_buffer.buffer,
+				tracing_gen_ctx(), skip, NULL);
 }
 EXPORT_SYMBOL_GPL(trace_dump_stack);
 
@@ -3079,7 +3078,6 @@ static void
 ftrace_trace_userstack(struct trace_array *tr,
 		       struct trace_buffer *buffer, unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_user_stack;
 	struct ring_buffer_event *event;
 	struct userstack_entry *entry;
 
@@ -3113,8 +3111,7 @@ ftrace_trace_userstack(struct trace_array *tr,
 	memset(&entry->caller, 0, sizeof(entry->caller));
 
 	stack_trace_save_user(entry->caller, FTRACE_STACK_ENTRIES);
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		__buffer_unlock_commit(buffer, event);
+	__buffer_unlock_commit(buffer, event);
 
  out_drop_count:
 	__this_cpu_dec(user_stack_count);
@@ -3283,7 +3280,6 @@ static void trace_printk_start_stop_comm(int enabled)
  */
 int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 {
-	struct trace_event_call *call = &event_bprint;
 	struct ring_buffer_event *event;
 	struct trace_buffer *buffer;
 	struct trace_array *tr = READ_ONCE(printk_trace);
@@ -3327,10 +3323,8 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, tbuffer, sizeof(u32) * len);
-	if (!call_filter_check_discard(call, entry, buffer, event)) {
-		__buffer_unlock_commit(buffer, event);
-		ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL);
-	}
+	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL);
 
 out:
 	ring_buffer_nest_end(buffer);
@@ -3350,7 +3344,6 @@ static int
 __trace_array_vprintk(struct trace_buffer *buffer,
 		      unsigned long ip, const char *fmt, va_list args)
 {
-	struct trace_event_call *call = &event_print;
 	struct ring_buffer_event *event;
 	int len = 0, size;
 	struct print_entry *entry;
@@ -3385,10 +3378,8 @@ __trace_array_vprintk(struct trace_buffer *buffer,
 	entry->ip = ip;
 
 	memcpy(&entry->buf, tbuffer, len + 1);
-	if (!call_filter_check_discard(call, entry, buffer, event)) {
-		__buffer_unlock_commit(buffer, event);
-		ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL);
-	}
+	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL);
 
 out:
 	ring_buffer_nest_end(buffer);