[PATCH bpf-next v4 00/27] x86/ftrace/bpf: Add batch support for direct/tracing attach

@@ -251,7 +251,6 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	 * If ORIG_RAX is anything but zero, make this a call to that.
 	 * See arch_ftrace_set_direct_caller().
 	 */
-	movq ORIG_RAX(%rsp), %rax
 	testq	%rax, %rax
 SYM_INNER_LABEL(ftrace_regs_caller_jmp, SYM_L_GLOBAL)
 	jnz	1f

@@ -625,12 +625,10 @@ int ftrace_disable_ftrace_graph_caller(void)
  * Hook the return address and push it in the stack of return addrs
  * in current thread info.
  */
-void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
+void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 			   unsigned long frame_pointer)
 {
 	unsigned long return_hooker = (unsigned long)&return_to_handler;
-	unsigned long old;
-	int faulted;
 
 	/*
 	 * When resuming from suspend-to-ram, this function can be indirectly

@@ -650,37 +648,7 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
-	/*
-	 * Protect against fault, even if it shouldn't
-	 * happen. This tool is too much intrusive to
-	 * ignore such a protection.
-	 */
-	asm volatile(
-		"1: " _ASM_MOV " (%[parent]), %[old]\n"
-		"2: " _ASM_MOV " %[return_hooker], (%[parent])\n"
-		"   movl $0, %[faulted]\n"
-		"3:\n"
-
-		".section .fixup, \"ax\"\n"
-		"4: movl $1, %[faulted]\n"
-		"   jmp 3b\n"
-		".previous\n"
-
-		_ASM_EXTABLE(1b, 4b)
-		_ASM_EXTABLE(2b, 4b)
-
-		: [old] "=&r" (old), [faulted] "=r" (faulted)
-		: [parent] "r" (parent), [return_hooker] "r" (return_hooker)
-		: "memory"
-	);
-
-	if (unlikely(faulted)) {
-		ftrace_graph_stop();
-		WARN_ON(1);
-		return;
-	}
-
-	if (function_graph_enter(old, self_addr, frame_pointer, parent))
-		*parent = old;
+	if (!function_graph_enter(*parent, ip, frame_pointer, parent))
+		*parent = return_hooker;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */

@@ -57,6 +57,13 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs)
 
 #define ftrace_instruction_pointer_set(fregs, _ip)	\
 	do { (fregs)->regs.ip = (_ip); } while (0)
+
+struct ftrace_ops;
+#define ftrace_graph_func ftrace_graph_func
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs);
+#else
+#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE

@@ -65,8 +72,6 @@ struct dyn_arch_ftrace {
 	/* No extra data needed for x86 */
 };
 
-#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR
-
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */

@@ -527,7 +527,7 @@ static void *addr_from_call(void *ptr)
 	return ptr + CALL_INSN_SIZE + call.disp;
 }
 
-void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
+void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 			   unsigned long frame_pointer);
 
 /*

@@ -541,7 +541,8 @@ static void *static_tramp_func(struct ftrace_ops *ops, struct dyn_ftrace *rec)
 	void *ptr;
 
 	if (ops && ops->trampoline) {
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) && \
+	defined(CONFIG_FUNCTION_GRAPH_TRACER)
 		/*
 		 * We only know about function graph tracer setting as static
 		 * trampoline.

@@ -589,8 +590,9 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-extern void ftrace_graph_call(void);
 
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+extern void ftrace_graph_call(void);
 static const char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
 {
 	return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr);

@@ -618,7 +620,17 @@ int ftrace_disable_ftrace_graph_caller(void)
 
 	return ftrace_mod_jmp(ip, &ftrace_stub);
 }
+#else /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return 0;
+}
 
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return 0;
+}
+#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
 #endif /* !CONFIG_DYNAMIC_FTRACE */
 
 /*

@@ -629,6 +641,7 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 			   unsigned long frame_pointer)
 {
 	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	int bit;
 
 	/*
 	 * When resuming from suspend-to-ram, this function can be indirectly

@@ -648,7 +661,25 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
+	bit = ftrace_test_recursion_trylock(ip, *parent);
+	if (bit < 0)
+		return;
+
 	if (!function_graph_enter(*parent, ip, frame_pointer, parent))
 		*parent = return_hooker;
+
+	ftrace_test_recursion_unlock(bit);
+}
+
+#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+	struct pt_regs *regs = &fregs->regs;
+	unsigned long *stack = (unsigned long *)kernel_stack_pointer(regs);
+
+	prepare_ftrace_return(ip, (unsigned long *)stack, 0);
 }
+#endif
+
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */

@@ -174,11 +174,6 @@ SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL)
 SYM_FUNC_END(ftrace_caller);
 
 SYM_FUNC_START(ftrace_epilogue)
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
-	jmp ftrace_stub
-#endif
-
 /*
  * This is weak to keep gas from relaxing the jumps.
  * It is also used to copy the retq for trampolines.

@@ -288,15 +283,6 @@ SYM_FUNC_START(__fentry__)
 	cmpq $ftrace_stub, ftrace_trace_function
 	jnz trace
 
-fgraph_trace:
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	cmpq $ftrace_stub, ftrace_graph_return
-	jnz ftrace_graph_caller
-
-	cmpq $ftrace_graph_entry_stub, ftrace_graph_entry
-	jnz ftrace_graph_caller
-#endif
-
 SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL)
 	retq
 

@@ -314,25 +300,12 @@ trace:
 	CALL_NOSPEC r8
 	restore_mcount_regs
 
-	jmp fgraph_trace
+	jmp ftrace_stub
 SYM_FUNC_END(__fentry__)
 EXPORT_SYMBOL(__fentry__)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-SYM_FUNC_START(ftrace_graph_caller)
-	/* Saves rbp into %rdx and fills first parameter  */
-	save_mcount_regs
-
-	leaq MCOUNT_REG_SIZE+8(%rsp), %rsi
-	movq $0, %rdx	/* No framepointers needed */
-	call	prepare_ftrace_return
-
-	restore_mcount_regs
-
-	retq
-SYM_FUNC_END(ftrace_graph_caller)
-
 SYM_FUNC_START(return_to_handler)
 	subq  $24, %rsp
 

@@ -614,6 +614,12 @@ void ftrace_modify_all_code(int command);
 extern void ftrace_graph_caller(void);
 extern int ftrace_enable_ftrace_graph_caller(void);
 extern int ftrace_disable_ftrace_graph_caller(void);
+#ifndef ftrace_graph_func
+#define ftrace_graph_func ftrace_stub
+#define FTRACE_OPS_GRAPH_STUB FTRACE_OPS_FL_STUB
+#else
+#define FTRACE_OPS_GRAPH_STUB 0
+#endif
 #else
 static inline int ftrace_enable_ftrace_graph_caller(void) { return 0; }
 static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; }

@@ -115,6 +115,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 {
 	struct ftrace_graph_ent trace;
 
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
 	/*
 	 * Skip graph tracing if the return location is served by direct trampoline,
 	 * since call sequence and return addresses are unpredictable anyway.

@@ -124,6 +125,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 	if (ftrace_direct_func_count &&
 	    ftrace_find_rec_direct(ret - MCOUNT_INSN_SIZE))
 		return -EBUSY;
+#endif
 	trace.func = func;
 	trace.depth = ++current->curr_ret_depth;
 

@@ -333,10 +335,10 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 #endif /* HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */
 
 static struct ftrace_ops graph_ops = {
-	.func			= ftrace_stub,
+	.func			= ftrace_graph_func,
 	.flags			= FTRACE_OPS_FL_INITIALIZED |
 				   FTRACE_OPS_FL_PID |
-				   FTRACE_OPS_FL_STUB,
+				   FTRACE_OPS_GRAPH_STUB,
 #ifdef FTRACE_GRAPH_TRAMP_ADDR
 	.trampoline		= FTRACE_GRAPH_TRAMP_ADDR,
 	/* trampoline_size is only needed for dynamically allocated tramps */

@@ -750,6 +750,8 @@ static struct fgraph_ops fgraph_ops __initdata  = {
 	.retfunc		= &trace_graph_return,
 };
 
+noinline __noclone static void trace_direct_tramp(void) { }
+
 /*
  * Pretty much the same than for the function tracer from which the selftest
  * has been borrowed.

@@ -760,6 +762,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 {
 	int ret;
 	unsigned long count;
+	char *func_name __maybe_unused;
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 	if (ftrace_filter_param) {

@@ -808,8 +811,52 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 		goto out;
 	}
 
-	/* Don't test dynamic tracing, the function tracer already did */
+#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+	tracing_reset_online_cpus(&tr->array_buffer);
+	set_graph_array(tr);
 
+	/*
+	 * Some archs *cough*PowerPC*cough* add characters to the
+	 * start of the function names. We simply put a '*' to
+	 * accommodate them.
+	 */
+	func_name = "*" __stringify(DYN_FTRACE_TEST_NAME);
+	ftrace_set_global_filter(func_name, strlen(func_name), 1);
+
+	/*
+	 * Register direct function together with graph tracer
+	 * and make sure we get graph trace.
+	 */
+	ret = register_ftrace_direct((unsigned long) DYN_FTRACE_TEST_NAME,
+				     (unsigned long) trace_direct_tramp);
+	if (ret)
+		goto out;
+
+	ret = register_ftrace_graph(&fgraph_ops);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		goto out;
+	}
+
+	DYN_FTRACE_TEST_NAME();
+
+	count = 0;
+
+	tracing_stop();
+	/* check the trace buffer */
+	ret = trace_test_buffer(&tr->array_buffer, &count);
+
+	unregister_ftrace_graph(&fgraph_ops);
+
+	tracing_start();
+
+	if (!ret && !count) {
+		ret = -1;
+		goto out;
+	}
+#endif
+
+	/* Don't test dynamic tracing, the function tracer already did */
 out:
 	/* Stop it if we failed */
 	if (ret)

@@ -2394,6 +2394,39 @@ unsigned long ftrace_find_rec_direct(unsigned long ip)
 	return entry->direct;
 }
 
+static struct ftrace_func_entry*
+ftrace_add_rec_direct(unsigned long ip, unsigned long addr,
+		      struct ftrace_hash **free_hash)
+{
+	struct ftrace_func_entry *entry;
+
+	if (ftrace_hash_empty(direct_functions) ||
+	    direct_functions->count > 2 * (1 << direct_functions->size_bits)) {
+		struct ftrace_hash *new_hash;
+		int size = ftrace_hash_empty(direct_functions) ? 0 :
+			direct_functions->count + 1;
+
+		if (size < 32)
+			size = 32;
+
+		new_hash = dup_hash(direct_functions, size);
+		if (!new_hash)
+			return NULL;
+
+		*free_hash = direct_functions;
+		direct_functions = new_hash;
+	}
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return NULL;
+
+	entry->ip = ip;
+	entry->direct = addr;
+	__add_hash_entry(direct_functions, entry);
+	return entry;
+}
+
 static void call_direct_funcs(unsigned long ip, unsigned long pip,
 			      struct ftrace_ops *ops, struct ftrace_regs *fregs)
 {

@@ -5110,27 +5143,6 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
 	}
 
 	ret = -ENOMEM;
-	if (ftrace_hash_empty(direct_functions) ||
-	    direct_functions->count > 2 * (1 << direct_functions->size_bits)) {
-		struct ftrace_hash *new_hash;
-		int size = ftrace_hash_empty(direct_functions) ? 0 :
-			direct_functions->count + 1;
-
-		if (size < 32)
-			size = 32;
-
-		new_hash = dup_hash(direct_functions, size);
-		if (!new_hash)
-			goto out_unlock;
-
-		free_hash = direct_functions;
-		direct_functions = new_hash;
-	}
-
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry)
-		goto out_unlock;
-
 	direct = ftrace_find_direct_func(addr);
 	if (!direct) {
 		direct = ftrace_alloc_direct_func(addr);

@@ -5140,9 +5152,9 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr)
 		}
 	}
 
-	entry->ip = ip;
-	entry->direct = addr;
-	__add_hash_entry(direct_functions, entry);
+	entry = ftrace_add_rec_direct(ip, addr, &free_hash);
+	if (!entry)
+		goto out_unlock;
 
 	ret = ftrace_set_filter_ip(&direct_ops, ip, 0, 0);
 	if (ret)

@@ -316,6 +316,8 @@ int ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
 				unsigned long old_addr,
 				unsigned long new_addr);
 unsigned long ftrace_find_rec_direct(unsigned long ip);
+int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
+int unregister_ftrace_direct_multi(struct ftrace_ops *ops);
 #else
 # define ftrace_direct_func_count 0
 static inline int register_ftrace_direct(unsigned long ip, unsigned long addr)

@@ -346,6 +348,14 @@ static inline unsigned long ftrace_find_rec_direct(unsigned long ip)
 {
 	return 0;
 }
+int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	return -ENODEV;
+}
+int unregister_ftrace_direct_multi(struct ftrace_ops *ops)
+{
+	return -ENODEV;
+}
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS

@@ -5407,6 +5407,117 @@ int modify_ftrace_direct(unsigned long ip,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(modify_ftrace_direct);
+
+#define MULTI_FLAGS (FTRACE_OPS_FL_IPMODIFY | FTRACE_OPS_FL_DIRECT | \
+		     FTRACE_OPS_FL_SAVE_REGS)
+
+static int check_direct_multi(struct ftrace_ops *ops)
+{
+	if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED))
+		return -EINVAL;
+	if ((ops->flags & MULTI_FLAGS) != MULTI_FLAGS)
+		return -EINVAL;
+	return 0;
+}
+
+int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	struct ftrace_hash *hash, *free_hash = NULL;
+	struct ftrace_func_entry *entry, *new;
+	int err = -EBUSY, size, i;
+
+	if (ops->func || ops->trampoline)
+		return -EINVAL;
+	if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED))
+		return -EINVAL;
+	if (ops->flags & FTRACE_OPS_FL_ENABLED)
+		return -EINVAL;
+
+	hash = ops->func_hash->filter_hash;
+	if (ftrace_hash_empty(hash))
+		return -EINVAL;
+
+	mutex_lock(&direct_mutex);
+
+	/* Make sure requested entries are not already registered.. */
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+			if (ftrace_find_rec_direct(entry->ip))
+				goto out_unlock;
+		}
+	}
+
+	/* ... and insert them to direct_functions hash. */
+	err = -ENOMEM;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+			new = ftrace_add_rec_direct(entry->ip, addr, &free_hash);
+			if (!new)
+				goto out_remove;
+			entry->direct = addr;
+		}
+	}
+
+	ops->func = call_direct_funcs;
+	ops->flags = MULTI_FLAGS;
+	ops->trampoline = FTRACE_REGS_ADDR;
+
+	err = register_ftrace_function(ops);
+
+ out_remove:
+	if (err) {
+		for (i = 0; i < size; i++) {
+			hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+				new = __ftrace_lookup_ip(direct_functions, entry->ip);
+				if (new) {
+					remove_hash_entry(direct_functions, new);
+					kfree(new);
+				}
+			}
+		}
+	}
+
+ out_unlock:
+	mutex_unlock(&direct_mutex);
+
+	if (free_hash) {
+		synchronize_rcu_tasks();
+		free_ftrace_hash(free_hash);
+	}
+	return err;
+}
+EXPORT_SYMBOL_GPL(register_ftrace_direct_multi);
+
+int unregister_ftrace_direct_multi(struct ftrace_ops *ops)
+{
+	struct ftrace_hash *hash = ops->func_hash->filter_hash;
+	struct ftrace_func_entry *entry, *new;
+	int err, size, i;
+
+	if (check_direct_multi(ops))
+		return -EINVAL;
+	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return -EINVAL;
+
+	mutex_lock(&direct_mutex);
+	err = unregister_ftrace_function(ops);
+
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
+			new = __ftrace_lookup_ip(direct_functions, entry->ip);
+			if (new) {
+				remove_hash_entry(direct_functions, new);
+				kfree(new);
+			}
+		}
+	}
+
+	mutex_unlock(&direct_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi);
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 /**

@@ -318,6 +318,8 @@ int ftrace_modify_direct_caller(struct ftrace_func_entry *entry,
 unsigned long ftrace_find_rec_direct(unsigned long ip);
 int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
 int unregister_ftrace_direct_multi(struct ftrace_ops *ops);
+int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr);
+
 #else
 # define ftrace_direct_func_count 0
 static inline int register_ftrace_direct(unsigned long ip, unsigned long addr)

@@ -356,6 +358,10 @@ int unregister_ftrace_direct_multi(struct ftrace_ops *ops)
 {
 	return -ENODEV;
 }
+int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	return -ENODEV;
+}
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS

@@ -5518,6 +5518,49 @@ int unregister_ftrace_direct_multi(struct ftrace_ops *ops)
 	return err;
 }
 EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi);
+
+int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
+{
+	struct ftrace_hash *hash = ops->func_hash->filter_hash;
+	struct ftrace_func_entry *entry, *iter;
+	int i, size;
+	int err;
+
+	if (check_direct_multi(ops))
+		return -EINVAL;
+	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+		return -EINVAL;
+
+	mutex_lock(&direct_mutex);
+	mutex_lock(&ftrace_lock);
+
+	/*
+	 * Shutdown the ops, change 'direct' pointer for each
+	 * ops entry in direct_functions hash and startup the
+	 * ops back again.
+	 */
+	err = ftrace_shutdown(ops, 0);
+	if (err)
+		goto out_unlock;
+
+	size = 1 << hash->size_bits;
+	for (i = 0; i < size; i++) {
+		hlist_for_each_entry(iter, &hash->buckets[i], hlist) {
+			entry = __ftrace_lookup_ip(direct_functions, iter->ip);
+			if (!entry)
+				continue;
+			entry->direct = addr;
+		}
+	}
+
+	err = ftrace_startup(ops, 0);
+
+ out_unlock:
+	mutex_unlock(&ftrace_lock);
+	mutex_unlock(&direct_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(modify_ftrace_direct_multi);
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
 /**

@@ -3,6 +3,7 @@
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct.o
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-too.o
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-modify.o
+obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-multi.o
 
 CFLAGS_sample-trace-array.o := -I$(src)
 obj-$(CONFIG_SAMPLE_TRACE_ARRAY) += sample-trace-array.o

@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/module.h>
+
+#include <linux/mm.h> /* for handle_mm_fault() */
+#include <linux/ftrace.h>
+#include <linux/sched/stat.h>
+
+void my_direct_func(unsigned long ip)
+{
+	trace_printk("ip %lx\n", ip);
+}
+
+extern void my_tramp(void *);
+
+asm (
+"	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
+"   my_tramp:"
+"	pushq %rbp\n"
+"	movq %rsp, %rbp\n"
+"	pushq %rdi\n"
+"	movq 8(%rbp), %rdi\n"
+"	call my_direct_func\n"
+"	popq %rdi\n"
+"	leave\n"
+"	ret\n"
+"	.size		my_tramp, .-my_tramp\n"
+"	.popsection\n"
+);
+
+static struct ftrace_ops direct;
+
+static int __init ftrace_direct_multi_init(void)
+{
+	ftrace_set_filter_ip(&direct, (unsigned long) wake_up_process, 0, 0);
+	ftrace_set_filter_ip(&direct, (unsigned long) schedule, 0, 0);
+
+	return register_ftrace_direct_multi(&direct, (unsigned long) my_tramp);
+}
+
+static void __exit ftrace_direct_multi_exit(void)
+{
+	unregister_ftrace_direct_multi(&direct);
+}
+
+module_init(ftrace_direct_multi_init);
+module_exit(ftrace_direct_multi_exit);
+
+MODULE_AUTHOR("Jiri Olsa");
+MODULE_DESCRIPTION("Example use case of using register_ftrace_direct_multi()");
+MODULE_LICENSE("GPL");

@@ -865,6 +865,7 @@ struct bpf_prog_aux {
 	bool func_proto_unreliable;
 	bool sleepable;
 	bool tail_call_reachable;
+	bool multi_func;
 	struct hlist_node tramp_hlist;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;

@@ -1110,6 +1110,13 @@ enum bpf_link_type {
  */
 #define BPF_F_SLEEPABLE		(1U << 4)
 
+/* If BPF_F_MULTI_FUNC is used in BPF_PROG_LOAD command, the verifier does
+ * not expect BTF ID for the program, instead it assumes it's function
+ * with 6 u64 arguments. No trampoline is created for the program. Such
+ * program can be attached to multiple functions.
+ */
+#define BPF_F_MULTI_FUNC	(1U << 5)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *

@@ -31,6 +31,7 @@
 #include <linux/bpf-netns.h>
 #include <linux/rcupdate_trace.h>
 #include <linux/memcontrol.h>
+#include <linux/btf_ids.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
 			  (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \

@@ -2012,7 +2013,8 @@ static int
 bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 			   enum bpf_attach_type expected_attach_type,
 			   struct btf *attach_btf, u32 btf_id,
-			   struct bpf_prog *dst_prog)
+			   struct bpf_prog *dst_prog,
+			   bool multi_func)
 {
 	if (btf_id) {
 		if (btf_id > BTF_MAX_TYPE)

@@ -2032,6 +2034,14 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 		}
 	}
 
+	if (multi_func) {
+		if (prog_type != BPF_PROG_TYPE_TRACING)
+			return -EINVAL;
+		if (!attach_btf || btf_id)
+			return -EINVAL;
+		return 0;
+	}
+
 	if (attach_btf && (!btf_id || dst_prog))
 		return -EINVAL;
 

@@ -2155,6 +2165,16 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
 	}
 }
 
+#define DEFINE_BPF_MULTI_FUNC(args...)			\
+	extern int bpf_multi_func(args);		\
+	int __init bpf_multi_func(args) { return 0; }
+
+DEFINE_BPF_MULTI_FUNC(unsigned long a1, unsigned long a2,
+		      unsigned long a3, unsigned long a4,
+		      unsigned long a5, unsigned long a6)
+
+BTF_ID_LIST_SINGLE(bpf_multi_func_btf_id, func, bpf_multi_func)
+
 /* last field in 'union bpf_attr' used by this command */
 #define	BPF_PROG_LOAD_LAST_FIELD fd_array
 

@@ -2165,6 +2185,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 	struct btf *attach_btf = NULL;
 	int err;
 	char license[128];
+	bool multi_func;
 	bool is_gpl;
 
 	if (CHECK_ATTR(BPF_PROG_LOAD))

@@ -2174,7 +2195,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 				 BPF_F_ANY_ALIGNMENT |
 				 BPF_F_TEST_STATE_FREQ |
 				 BPF_F_SLEEPABLE |
-				 BPF_F_TEST_RND_HI32))
+				 BPF_F_TEST_RND_HI32 |
+				 BPF_F_MULTI_FUNC))
 		return -EINVAL;
 
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&

@@ -2205,6 +2227,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 	if (is_perfmon_prog_type(type) && !perfmon_capable())
 		return -EPERM;
 
+	multi_func = attr->prog_flags & BPF_F_MULTI_FUNC;
+
 	/* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog
 	 * or btf, we need to check which one it is
 	 */

@@ -2223,7 +2247,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 				return -ENOTSUPP;
 			}
 		}
-	} else if (attr->attach_btf_id) {
+	} else if (attr->attach_btf_id || multi_func) {
 		/* fall back to vmlinux BTF, if BTF type ID is specified */
 		attach_btf = bpf_get_btf_vmlinux();
 		if (IS_ERR(attach_btf))

@@ -2236,7 +2260,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 	bpf_prog_load_fixup_attach_type(attr);
 	if (bpf_prog_load_check_attach(type, attr->expected_attach_type,
 				       attach_btf, attr->attach_btf_id,
-				       dst_prog)) {
+				       dst_prog, multi_func)) {
 		if (dst_prog)
 			bpf_prog_put(dst_prog);
 		if (attach_btf)

@@ -2256,10 +2280,11 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 
 	prog->expected_attach_type = attr->expected_attach_type;
 	prog->aux->attach_btf = attach_btf;
-	prog->aux->attach_btf_id = attr->attach_btf_id;
+	prog->aux->attach_btf_id = multi_func ? bpf_multi_func_btf_id[0] : attr->attach_btf_id;
 	prog->aux->dst_prog = dst_prog;
 	prog->aux->offload_requested = !!attr->prog_ifindex;
 	prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
+	prog->aux->multi_func = multi_func;
 
 	err = security_bpf_prog_alloc(prog->aux);
 	if (err)

@@ -13628,7 +13628,8 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		if (!bpf_iter_prog_supported(prog))
 			return -EINVAL;
 		return 0;
-	}
+	} else if (prog->aux->multi_func)
+		return prog->type == BPF_PROG_TYPE_TRACING ? 0 : -EINVAL;
 
 	if (prog->type == BPF_PROG_TYPE_LSM) {
 		ret = bpf_lsm_verify_prog(&env->log, prog);

@@ -1110,6 +1110,13 @@ enum bpf_link_type {
  */
 #define BPF_F_SLEEPABLE		(1U << 4)
 
+/* If BPF_F_MULTI_FUNC is used in BPF_PROG_LOAD command, the verifier does
+ * not expect BTF ID for the program, instead it assumes it's function
+ * with 6 u64 arguments. No trampoline is created for the program. Such
+ * program can be attached to multiple functions.
+ */
+#define BPF_F_MULTI_FUNC	(1U << 5)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *

@@ -656,6 +656,11 @@ struct bpf_tramp_image {
 	};
 };
 
+struct bpf_tramp_node {
+	struct hlist_node hlist;
+	struct bpf_prog *prog;
+};
+
 struct bpf_trampoline {
 	/* hlist for trampoline_table */
 	struct hlist_node hlist;

@@ -717,8 +722,8 @@ static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
 	return bpf_func(ctx, insnsi);
 }
 #ifdef CONFIG_BPF_JIT
-int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
-int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
+int bpf_trampoline_link_prog(struct bpf_tramp_node *node, struct bpf_trampoline *tr);
+int bpf_trampoline_unlink_prog(struct bpf_tramp_node *node, struct bpf_trampoline *tr);
 struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);

@@ -767,12 +772,12 @@ void bpf_ksym_del(struct bpf_ksym *ksym);
 int bpf_jit_charge_modmem(u32 pages);
 void bpf_jit_uncharge_modmem(u32 pages);
 #else
-static inline int bpf_trampoline_link_prog(struct bpf_prog *prog,
+static inline int bpf_trampoline_link_prog(struct bpf_tramp_node *node,
 					   struct bpf_trampoline *tr)
 {
 	return -ENOTSUPP;
 }
-static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog,
+static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_node *node,
 					     struct bpf_trampoline *tr)
 {
 	return -ENOTSUPP;

@@ -866,7 +871,7 @@ struct bpf_prog_aux {
 	bool sleepable;
 	bool tail_call_reachable;
 	bool multi_func;
-	struct hlist_node tramp_hlist;
+	struct bpf_tramp_node tramp_node;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
 	/* function name for valid attach_btf_id */

@@ -104,6 +104,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 	fp->aux = aux;
 	fp->aux->prog = fp;
 	fp->jit_requested = ebpf_jit_enabled();
+	fp->aux->tramp_node.prog = fp;
 
 	INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
 	mutex_init(&fp->aux->used_maps_mutex);

@@ -2625,7 +2625,7 @@ static void bpf_tracing_link_release(struct bpf_link *link)
 	struct bpf_tracing_link *tr_link =
 		container_of(link, struct bpf_tracing_link, link);
 
-	WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog,
+	WARN_ON_ONCE(bpf_trampoline_unlink_prog(&link->prog->aux->tramp_node,
 						tr_link->trampoline));
 
 	bpf_trampoline_put(tr_link->trampoline);

@@ -2813,7 +2813,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 	if (err)
 		goto out_unlock;
 
-	err = bpf_trampoline_link_prog(prog, tr);
+	err = bpf_trampoline_link_prog(&prog->aux->tramp_node, tr);
 	if (err) {
 		bpf_link_cleanup(&link_primer);
 		link = NULL;

@@ -174,8 +174,8 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
 static struct bpf_tramp_progs *
 bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_arg)
 {
-	const struct bpf_prog_aux *aux;
 	struct bpf_tramp_progs *tprogs;
+	struct bpf_tramp_node *node;
 	struct bpf_prog **progs;
 	int kind;
 

@@ -189,9 +189,9 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_a
 		*total += tr->progs_cnt[kind];
 		progs = tprogs[kind].progs;
 
-		hlist_for_each_entry(aux, &tr->progs_hlist[kind], tramp_hlist) {
-			*ip_arg |= aux->prog->call_get_func_ip;
-			*progs++ = aux->prog;
+		hlist_for_each_entry(node, &tr->progs_hlist[kind], hlist) {
+			*ip_arg |= node->prog->call_get_func_ip;
+			*progs++ = node->prog;
 		}
 	}
 	return tprogs;

@@ -410,8 +410,9 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog)
 	}
 }
 
-int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
+int bpf_trampoline_link_prog(struct bpf_tramp_node *node, struct bpf_trampoline *tr)
 {
+	struct bpf_prog *prog = node->prog;
 	enum bpf_tramp_prog_type kind;
 	int err = 0;
 	int cnt;

@@ -441,16 +442,16 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 		err = -E2BIG;
 		goto out;
 	}
-	if (!hlist_unhashed(&prog->aux->tramp_hlist)) {
+	if (!hlist_unhashed(&node->hlist)) {
 		/* prog already linked */
 		err = -EBUSY;
 		goto out;
 	}
-	hlist_add_head(&prog->aux->tramp_hlist, &tr->progs_hlist[kind]);
+	hlist_add_head(&node->hlist, &tr->progs_hlist[kind]);
 	tr->progs_cnt[kind]++;
 	err = bpf_trampoline_update(tr);
 	if (err) {
-		hlist_del_init(&prog->aux->tramp_hlist);
+		hlist_del_init(&node->hlist);
 		tr->progs_cnt[kind]--;
 	}
 out:

@@ -459,8 +460,9 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 }
 
 /* bpf_trampoline_unlink_prog() should never fail. */
-int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
+int bpf_trampoline_unlink_prog(struct bpf_tramp_node *node, struct bpf_trampoline *tr)
 {
+	struct bpf_prog *prog = node->prog;
 	enum bpf_tramp_prog_type kind;
 	int err;
 

@@ -473,7 +475,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 		tr->extension_prog = NULL;
 		goto out;
 	}
-	hlist_del_init(&prog->aux->tramp_hlist);
+	hlist_del_init(&node->hlist);
 	tr->progs_cnt[kind]--;
 	err = bpf_trampoline_update(tr);
 out:

@@ -58,11 +58,22 @@ void bpf_image_ksym_del(struct bpf_ksym *ksym)
 			   PAGE_SIZE, true, ksym->name);
 }
 
+static void bpf_trampoline_init(struct bpf_trampoline *tr, u64 key)
+{
+	int i;
+
+	tr->key = key;
+	INIT_HLIST_NODE(&tr->hlist);
+	refcount_set(&tr->refcnt, 1);
+	mutex_init(&tr->mutex);
+	for (i = 0; i < BPF_TRAMP_MAX; i++)
+		INIT_HLIST_HEAD(&tr->progs_hlist[i]);
+}
+
 static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 {
 	struct bpf_trampoline *tr;
 	struct hlist_head *head;
-	int i;
 
 	mutex_lock(&trampoline_mutex);
 	head = &trampoline_table[hash_64(key, TRAMPOLINE_HASH_BITS)];