Tracing fixes and clean ups:

- Fix some missing-prototype warnings
 
 - Fix user events struct args (did not include size of struct)
   When creating a user event, the "struct" keyword is to denote
   that the size of the field will be passed in. But the parsing
   failed to handle this case.
 
 - Add selftest to struct sizes for user events
 
 - Fix sample code for direct trampolines.
   The sample code for direct trampolines attached to handle_mm_fault().
   But the prototype changed and the direct trampoline sample code
   was not updated. Direct trampolines needs to have the arguments correct
   otherwise it can fail or crash the system.
 
 - Remove unused ftrace_regs_caller_ret() prototype.
 
 - Quiet false positive of FORTIFY_SOURCE
   Due to backward compatibility, the structure used to save stack traces
   in the kernel had a fixed size of 8. This structure is exported to
   user space via the tracing format file. A change was made to allow
   more than 8 functions to be recorded, and user space now uses the
   size field to know how many functions are actually in the stack.
   But the structure still has size of 8 (even though it points into
   the ring buffer that has the required amount allocated to hold a
   full stack. This was fine until the fortifier noticed that the
   memcpy(&entry->caller, stack, size) was greater than the 8 functions
   and would complain at runtime about it. Hide this by using a pointer
   to the stack location on the ring buffer instead of using the address
   of the entry structure caller field.
 
 - Fix a deadloop in reading trace_pipe that was caused by a mismatch
   between ring_buffer_empty() returning false which then asked to
   read the data, but the read code uses rb_num_of_entries() that
   returned zero, and causing a infinite "retry".
 
 - Fix a warning caused by not using all pages allocated to store
   ftrace functions, where this can happen if the linker inserts a bunch of
   "NULL" entries, causing the accounting of how many pages needed
   to be off.
 
 - Fix histogram synthetic event crashing when the start event is
   removed and the end event is still using a variable from it.
 
 - Fix memory leak in freeing iter->temp in tracing_release_pipe()
 -----BEGIN PGP SIGNATURE-----
 
 iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCZLBF6hQccm9zdGVkdEBn
 b29kbWlzLm9yZwAKCRAp5XQQmuv6qkswAP4mhdoFFfNosM7+Sh/R4t31IxKZApm9
 M2Hf9jgvJ7b65AD/VV1XfO6skw2+5Yn9S4UyNE2MQaYxPwWpONcNFUzZ3Q8=
 =Nb+7
 -----END PGP SIGNATURE-----

Merge tag 'trace-v6.5-rc1-3' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing fixes from Steven Rostedt:

 - Fix some missing-prototype warnings

 - Fix user events struct args (did not include size of struct)

   When creating a user event, the "struct" keyword is to denote that
   the size of the field will be passed in. But the parsing failed to
   handle this case.

 - Add selftest to struct sizes for user events

 - Fix sample code for direct trampolines.

   The sample code for direct trampolines attached to handle_mm_fault().
   But the prototype changed and the direct trampoline sample code was
   not updated. Direct trampolines needs to have the arguments correct
   otherwise it can fail or crash the system.

 - Remove unused ftrace_regs_caller_ret() prototype.

 - Quiet false positive of FORTIFY_SOURCE

   Due to backward compatibility, the structure used to save stack
   traces in the kernel had a fixed size of 8. This structure is
   exported to user space via the tracing format file. A change was made
   to allow more than 8 functions to be recorded, and user space now
   uses the size field to know how many functions are actually in the
   stack.

   But the structure still has size of 8 (even though it points into the
   ring buffer that has the required amount allocated to hold a full
   stack.

   This was fine until the fortifier noticed that the
   memcpy(&entry->caller, stack, size) was greater than the 8 functions
   and would complain at runtime about it.

   Hide this by using a pointer to the stack location on the ring buffer
   instead of using the address of the entry structure caller field.

 - Fix a deadloop in reading trace_pipe that was caused by a mismatch
   between ring_buffer_empty() returning false which then asked to read
   the data, but the read code uses rb_num_of_entries() that returned
   zero, and causing a infinite "retry".

 - Fix a warning caused by not using all pages allocated to store ftrace
   functions, where this can happen if the linker inserts a bunch of
   "NULL" entries, causing the accounting of how many pages needed to be
   off.

 - Fix histogram synthetic event crashing when the start event is
   removed and the end event is still using a variable from it

 - Fix memory leak in freeing iter->temp in tracing_release_pipe()

* tag 'trace-v6.5-rc1-3' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  tracing: Fix memory leak of iter->temp when reading trace_pipe
  tracing/histograms: Add histograms to hist_vars if they have referenced variables
  tracing: Stop FORTIFY_SOURCE complaining about stack trace caller
  ftrace: Fix possible warning on checking all pages used in ftrace_process_locs()
  ring-buffer: Fix deadloop issue on reading trace_pipe
  tracing: arm64: Avoid missing-prototype warnings
  selftests/user_events: Test struct size match cases
  tracing/user_events: Fix struct arg size match check
  x86/ftrace: Remove unsued extern declaration ftrace_regs_caller_ret()
  arm64: ftrace: Add direct call trampoline samples support
  samples: ftrace: Save required argument registers in sample trampolines

arch/arm64/Kconfig

@@ -197,6 +197,8 @@ config ARM64
 		    !CC_OPTIMIZE_FOR_SIZE)
 	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
 		if DYNAMIC_FTRACE_WITH_ARGS
+	select HAVE_SAMPLE_FTRACE_DIRECT
+	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_FAST_GUP
 	select HAVE_FTRACE_MCOUNT_RECORD

arch/arm64/include/asm/ftrace.h

@@ -211,6 +211,10 @@ static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs
 {
 	return ret_regs->fp;
 }
+
+void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
+			   unsigned long frame_pointer);
+
 #endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER  */
 #endif
 

arch/arm64/include/asm/syscall.h

@@ -85,4 +85,7 @@ static inline int syscall_get_arch(struct task_struct *task)
 	return AUDIT_ARCH_AARCH64;
 }
 
+int syscall_trace_enter(struct pt_regs *regs);
+void syscall_trace_exit(struct pt_regs *regs);
+
 #endif	/* __ASM_SYSCALL_H */

arch/arm64/kernel/syscall.c

@@ -75,9 +75,6 @@ static inline bool has_syscall_work(unsigned long flags)
 	return unlikely(flags & _TIF_SYSCALL_WORK);
 }
 
-int syscall_trace_enter(struct pt_regs *regs);
-void syscall_trace_exit(struct pt_regs *regs);
-
 static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 			   const syscall_fn_t syscall_table[])
 {

arch/x86/kernel/ftrace.c

@@ -282,7 +282,6 @@ static inline void tramp_free(void *tramp) { }
 
 /* Defined as markers to the end of the ftrace default trampolines */
 extern void ftrace_regs_caller_end(void);
-extern void ftrace_regs_caller_ret(void);
 extern void ftrace_caller_end(void);
 extern void ftrace_caller_op_ptr(void);
 extern void ftrace_regs_caller_op_ptr(void);

include/linux/ftrace.h

@@ -41,6 +41,15 @@ struct ftrace_ops;
 struct ftrace_regs;
 struct dyn_ftrace;
 
+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

kernel/trace/fgraph.c

@@ -15,6 +15,7 @@
 #include <trace/events/sched.h>
 
 #include "ftrace_internal.h"
+#include "trace.h"
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 #define ASSIGN_OPS_HASH(opsname, val) \

kernel/trace/ftrace.c

@@ -3305,6 +3305,22 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count)
 	return cnt;
 }
 
+static void ftrace_free_pages(struct ftrace_page *pages)
+{
+	struct ftrace_page *pg = pages;
+
+	while (pg) {
+		if (pg->records) {
+			free_pages((unsigned long)pg->records, pg->order);
+			ftrace_number_of_pages -= 1 << pg->order;
+		}
+		pages = pg->next;
+		kfree(pg);
+		pg = pages;
+		ftrace_number_of_groups--;
+	}
+}
+
 static struct ftrace_page *
 ftrace_allocate_pages(unsigned long num_to_init)
 {
@@ -3343,17 +3359,7 @@ ftrace_allocate_pages(unsigned long num_to_init)
 	return start_pg;
 
  free_pages:
-	pg = start_pg;
-	while (pg) {
-		if (pg->records) {
-			free_pages((unsigned long)pg->records, pg->order);
-			ftrace_number_of_pages -= 1 << pg->order;
-		}
-		start_pg = pg->next;
-		kfree(pg);
-		pg = start_pg;
-		ftrace_number_of_groups--;
-	}
+	ftrace_free_pages(start_pg);
 	pr_info("ftrace: FAILED to allocate memory for functions\n");
 	return NULL;
 }
@@ -6471,9 +6477,11 @@ static int ftrace_process_locs(struct module *mod,
 			       unsigned long *start,
 			       unsigned long *end)
 {
+	struct ftrace_page *pg_unuse = NULL;
 	struct ftrace_page *start_pg;
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
+	unsigned long skipped = 0;
 	unsigned long count;
 	unsigned long *p;
 	unsigned long addr;
@@ -6536,8 +6544,10 @@ static int ftrace_process_locs(struct module *mod,
 		 * object files to satisfy alignments.
 		 * Skip any NULL pointers.
 		 */
-		if (!addr)
+		if (!addr) {
+			skipped++;
 			continue;
+		}
 
 		end_offset = (pg->index+1) * sizeof(pg->records[0]);
 		if (end_offset > PAGE_SIZE << pg->order) {
@@ -6551,8 +6561,10 @@ static int ftrace_process_locs(struct module *mod,
 		rec->ip = addr;
 	}
 
-	/* We should have used all pages */
-	WARN_ON(pg->next);
+	if (pg->next) {
+		pg_unuse = pg->next;
+		pg->next = NULL;
+	}
 
 	/* Assign the last page to ftrace_pages */
 	ftrace_pages = pg;
@@ -6574,6 +6586,11 @@ static int ftrace_process_locs(struct module *mod,
  out:
 	mutex_unlock(&ftrace_lock);
 
+	/* We should have used all pages unless we skipped some */
+	if (pg_unuse) {
+		WARN_ON(!skipped);
+		ftrace_free_pages(pg_unuse);
+	}
 	return ret;
 }
 

kernel/trace/ftrace_internal.h

@@ -2,6 +2,9 @@
 #ifndef _LINUX_KERNEL_FTRACE_INTERNAL_H
 #define  _LINUX_KERNEL_FTRACE_INTERNAL_H
 
+int __register_ftrace_function(struct ftrace_ops *ops);
+int __unregister_ftrace_function(struct ftrace_ops *ops);
+
 #ifdef CONFIG_FUNCTION_TRACER
 
 extern struct mutex ftrace_lock;
@@ -15,8 +18,6 @@ int ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs);
 
 #else /* !CONFIG_DYNAMIC_FTRACE */
 
-int __register_ftrace_function(struct ftrace_ops *ops);
-int __unregister_ftrace_function(struct ftrace_ops *ops);
 /* Keep as macros so we do not need to define the commands */
 # define ftrace_startup(ops, command)					\
 	({								\

kernel/trace/ring_buffer.c

@@ -5242,28 +5242,34 @@ unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu)
 }
 EXPORT_SYMBOL_GPL(ring_buffer_size);
 
+static void rb_clear_buffer_page(struct buffer_page *page)
+{
+	local_set(&page->write, 0);
+	local_set(&page->entries, 0);
+	rb_init_page(page->page);
+	page->read = 0;
+}
+
 static void
 rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 {
+	struct buffer_page *page;
+
 	rb_head_page_deactivate(cpu_buffer);
 
 	cpu_buffer->head_page
 		= list_entry(cpu_buffer->pages, struct buffer_page, list);
-	local_set(&cpu_buffer->head_page->write, 0);
-	local_set(&cpu_buffer->head_page->entries, 0);
-	local_set(&cpu_buffer->head_page->page->commit, 0);
-
-	cpu_buffer->head_page->read = 0;
+	rb_clear_buffer_page(cpu_buffer->head_page);
+	list_for_each_entry(page, cpu_buffer->pages, list) {
+		rb_clear_buffer_page(page);
+	}
 
 	cpu_buffer->tail_page = cpu_buffer->head_page;
 	cpu_buffer->commit_page = cpu_buffer->head_page;
 
 	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
 	INIT_LIST_HEAD(&cpu_buffer->new_pages);
-	local_set(&cpu_buffer->reader_page->write, 0);
-	local_set(&cpu_buffer->reader_page->entries, 0);
-	local_set(&cpu_buffer->reader_page->page->commit, 0);
-	cpu_buffer->reader_page->read = 0;
+	rb_clear_buffer_page(cpu_buffer->reader_page);
 
 	local_set(&cpu_buffer->entries_bytes, 0);
 	local_set(&cpu_buffer->overrun, 0);

kernel/trace/trace.c

@@ -3118,6 +3118,7 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 	struct ftrace_stack *fstack;
 	struct stack_entry *entry;
 	int stackidx;
+	void *ptr;
 
 	/*
 	 * Add one, for this function and the call to save_stack_trace()
@@ -3161,9 +3162,25 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 				    trace_ctx);
 	if (!event)
 		goto out;
-	entry = ring_buffer_event_data(event);
+	ptr = ring_buffer_event_data(event);
+	entry = ptr;
+
+	/*
+	 * For backward compatibility reasons, the entry->caller is an
+	 * array of 8 slots to store the stack. This is also exported
+	 * to user space. The amount allocated on the ring buffer actually
+	 * holds enough for the stack specified by nr_entries. This will
+	 * go into the location of entry->caller. Due to string fortifiers
+	 * checking the size of the destination of memcpy() it triggers
+	 * when it detects that size is greater than 8. To hide this from
+	 * the fortifiers, we use "ptr" and pointer arithmetic to assign caller.
+	 *
+	 * The below is really just:
+	 *   memcpy(&entry->caller, fstack->calls, size);
+	 */
+	ptr += offsetof(typeof(*entry), caller);
+	memcpy(ptr, fstack->calls, size);
 
-	memcpy(&entry->caller, fstack->calls, size);
 	entry->size = nr_entries;
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
@@ -6764,6 +6781,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 
 	free_cpumask_var(iter->started);
 	kfree(iter->fmt);
+	kfree(iter->temp);
 	mutex_destroy(&iter->mutex);
 	kfree(iter);
 

kernel/trace/trace_events_hist.c

@@ -6663,13 +6663,15 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 	if (get_named_trigger_data(trigger_data))
 		goto enable;
 
-	if (has_hist_vars(hist_data))
-		save_hist_vars(hist_data);
-
 	ret = create_actions(hist_data);
 	if (ret)
 		goto out_unreg;
 
+	if (has_hist_vars(hist_data) || hist_data->n_var_refs) {
+		if (save_hist_vars(hist_data))
+			goto out_unreg;
+	}
+
 	ret = tracing_map_init(hist_data->map);
 	if (ret)
 		goto out_unreg;

kernel/trace/trace_events_user.c

@@ -1317,6 +1317,9 @@ static int user_field_set_string(struct ftrace_event_field *field,
 	pos += snprintf(buf + pos, LEN_OR_ZERO, " ");
 	pos += snprintf(buf + pos, LEN_OR_ZERO, "%s", field->name);
 
+	if (str_has_prefix(field->type, "struct "))
+		pos += snprintf(buf + pos, LEN_OR_ZERO, " %d", field->size);
+
 	if (colon)
 		pos += snprintf(buf + pos, LEN_OR_ZERO, ";");
 

kernel/trace/trace_kprobe_selftest.c

@@ -1,4 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
+
+#include "trace_kprobe_selftest.h"
+
 /*
  * Function used during the kprobe self test. This function is in a separate
  * compile unit so it can be compile with CC_FLAGS_FTRACE to ensure that it

samples/ftrace/ftrace-direct-modify.c

@@ -2,7 +2,9 @@
 #include <linux/module.h>
 #include <linux/kthread.h>
 #include <linux/ftrace.h>
+#ifndef CONFIG_ARM64
 #include <asm/asm-offsets.h>
+#endif
 
 extern void my_direct_func1(void);
 extern void my_direct_func2(void);
@@ -96,6 +98,38 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_ARM64
+
+asm (
+"	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp1, @function\n"
+"	.globl		my_tramp1\n"
+"   my_tramp1:"
+"	bti	c\n"
+"	sub	sp, sp, #16\n"
+"	stp	x9, x30, [sp]\n"
+"	bl	my_direct_func1\n"
+"	ldp	x30, x9, [sp]\n"
+"	add	sp, sp, #16\n"
+"	ret	x9\n"
+"	.size		my_tramp1, .-my_tramp1\n"
+
+"	.type		my_tramp2, @function\n"
+"	.globl		my_tramp2\n"
+"   my_tramp2:"
+"	bti	c\n"
+"	sub	sp, sp, #16\n"
+"	stp	x9, x30, [sp]\n"
+"	bl	my_direct_func2\n"
+"	ldp	x30, x9, [sp]\n"
+"	add	sp, sp, #16\n"
+"	ret	x9\n"
+"	.size		my_tramp2, .-my_tramp2\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_ARM64 */
+
 #ifdef CONFIG_LOONGARCH
 
 asm (

samples/ftrace/ftrace-direct-multi-modify.c

@@ -2,7 +2,9 @@
 #include <linux/module.h>
 #include <linux/kthread.h>
 #include <linux/ftrace.h>
+#ifndef CONFIG_ARM64
 #include <asm/asm-offsets.h>
+#endif
 
 extern void my_direct_func1(unsigned long ip);
 extern void my_direct_func2(unsigned long ip);
@@ -103,6 +105,44 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_ARM64
+
+asm (
+"	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp1, @function\n"
+"	.globl		my_tramp1\n"
+"   my_tramp1:"
+"	bti	c\n"
+"	sub	sp, sp, #32\n"
+"	stp	x9, x30, [sp]\n"
+"	str	x0, [sp, #16]\n"
+"	mov	x0, x30\n"
+"	bl	my_direct_func1\n"
+"	ldp	x30, x9, [sp]\n"
+"	ldr	x0, [sp, #16]\n"
+"	add	sp, sp, #32\n"
+"	ret	x9\n"
+"	.size		my_tramp1, .-my_tramp1\n"
+
+"	.type		my_tramp2, @function\n"
+"	.globl		my_tramp2\n"
+"   my_tramp2:"
+"	bti	c\n"
+"	sub	sp, sp, #32\n"
+"	stp	x9, x30, [sp]\n"
+"	str	x0, [sp, #16]\n"
+"	mov	x0, x30\n"
+"	bl	my_direct_func2\n"
+"	ldp	x30, x9, [sp]\n"
+"	ldr	x0, [sp, #16]\n"
+"	add	sp, sp, #32\n"
+"	ret	x9\n"
+"	.size		my_tramp2, .-my_tramp2\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_ARM64 */
+
 #ifdef CONFIG_LOONGARCH
 #include <asm/asm.h>
 

samples/ftrace/ftrace-direct-multi.c

@@ -4,7 +4,9 @@
 #include <linux/mm.h> /* for handle_mm_fault() */
 #include <linux/ftrace.h>
 #include <linux/sched/stat.h>
+#ifndef CONFIG_ARM64
 #include <asm/asm-offsets.h>
+#endif
 
 extern void my_direct_func(unsigned long ip);
 
@@ -66,6 +68,29 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_ARM64
+
+asm (
+"	.pushsection	.text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
+"   my_tramp:"
+"	bti	c\n"
+"	sub	sp, sp, #32\n"
+"	stp	x9, x30, [sp]\n"
+"	str	x0, [sp, #16]\n"
+"	mov	x0, x30\n"
+"	bl	my_direct_func\n"
+"	ldp	x30, x9, [sp]\n"
+"	ldr	x0, [sp, #16]\n"
+"	add	sp, sp, #32\n"
+"	ret	x9\n"
+"	.size		my_tramp, .-my_tramp\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_ARM64 */
+
 #ifdef CONFIG_LOONGARCH
 
 #include <asm/asm.h>

samples/ftrace/ftrace-direct-too.c

@@ -3,16 +3,18 @@
 
 #include <linux/mm.h> /* for handle_mm_fault() */
 #include <linux/ftrace.h>
+#ifndef CONFIG_ARM64
 #include <asm/asm-offsets.h>
+#endif
 
-extern void my_direct_func(struct vm_area_struct *vma,
-			   unsigned long address, unsigned int flags);
+extern void my_direct_func(struct vm_area_struct *vma, unsigned long address,
+			   unsigned int flags, struct pt_regs *regs);
 
-void my_direct_func(struct vm_area_struct *vma,
-			unsigned long address, unsigned int flags)
+void my_direct_func(struct vm_area_struct *vma, unsigned long address,
+		    unsigned int flags, struct pt_regs *regs)
 {
-	trace_printk("handle mm fault vma=%p address=%lx flags=%x\n",
-		     vma, address, flags);
+	trace_printk("handle mm fault vma=%p address=%lx flags=%x regs=%p\n",
+		     vma, address, flags, regs);
 }
 
 extern void my_tramp(void *);
@@ -34,7 +36,9 @@ asm (
 "	pushq %rdi\n"
 "	pushq %rsi\n"
 "	pushq %rdx\n"
+"	pushq %rcx\n"
 "	call my_direct_func\n"
+"	popq %rcx\n"
 "	popq %rdx\n"
 "	popq %rsi\n"
 "	popq %rdi\n"
@@ -70,6 +74,30 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_ARM64
+
+asm (
+"	.pushsection	.text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
+"   my_tramp:"
+"	bti	c\n"
+"	sub	sp, sp, #48\n"
+"	stp	x9, x30, [sp]\n"
+"	stp	x0, x1, [sp, #16]\n"
+"	stp	x2, x3, [sp, #32]\n"
+"	bl	my_direct_func\n"
+"	ldp	x30, x9, [sp]\n"
+"	ldp	x0, x1, [sp, #16]\n"
+"	ldp	x2, x3, [sp, #32]\n"
+"	add	sp, sp, #48\n"
+"	ret	x9\n"
+"	.size		my_tramp, .-my_tramp\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_ARM64 */
+
 #ifdef CONFIG_LOONGARCH
 
 asm (

samples/ftrace/ftrace-direct.c

@@ -3,7 +3,9 @@
 
 #include <linux/sched.h> /* for wake_up_process() */
 #include <linux/ftrace.h>
+#ifndef CONFIG_ARM64
 #include <asm/asm-offsets.h>
+#endif
 
 extern void my_direct_func(struct task_struct *p);
 
@@ -63,6 +65,28 @@ asm (
 
 #endif /* CONFIG_S390 */
 
+#ifdef CONFIG_ARM64
+
+asm (
+"	.pushsection	.text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
+"   my_tramp:"
+"	bti	c\n"
+"	sub	sp, sp, #32\n"
+"	stp	x9, x30, [sp]\n"
+"	str	x0, [sp, #16]\n"
+"	bl	my_direct_func\n"
+"	ldp	x30, x9, [sp]\n"
+"	ldr	x0, [sp, #16]\n"
+"	add	sp, sp, #32\n"
+"	ret	x9\n"
+"	.size		my_tramp, .-my_tramp\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_ARM64 */
+
 #ifdef CONFIG_LOONGARCH
 
 asm (

tools/testing/selftests/user_events/dyn_test.c

@@ -217,6 +217,18 @@ TEST_F(user, matching) {
 	/* Types don't match */
 	TEST_NMATCH("__test_event u64 a; u64 b",
 		    "__test_event u32 a; u32 b");
+
+	/* Struct name and size matches */
+	TEST_MATCH("__test_event struct my_struct a 20",
+		   "__test_event struct my_struct a 20");
+
+	/* Struct name don't match */
+	TEST_NMATCH("__test_event struct my_struct a 20",
+		    "__test_event struct my_struct b 20");
+
+	/* Struct size don't match */
+	TEST_NMATCH("__test_event struct my_struct a 20",
+		    "__test_event struct my_struct a 21");
 }
 
 int main(int argc, char **argv)