Merge tag 'ftrace-v6.14' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull ftrace updates from Steven Rostedt:

 - Have fprobes built on top of function graph infrastructure

   The fprobe logic is an optimized kprobe that uses ftrace to attach to
   functions when a probe is needed at the start or end of the function.
   The fprobe and kretprobe logic implements a similar method as the
   function graph tracer to trace the end of the function. That is to
   hijack the return address and jump to a trampoline to do the trace
   when the function exits. To do this, a shadow stack needs to be
   created to store the original return address. Fprobes and function
   graph do this slightly differently. Fprobes (and kretprobes) has
   slots per callsite that are reserved to save the return address. This
   is fine when just a few points are traced. But users of fprobes, such
   as BPF programs, are starting to add many more locations, and this
   method does not scale.

   The function graph tracer was created to trace all functions in the
   kernel. In order to do this, when function graph tracing is started,
   every task gets its own shadow stack to hold the return address that
   is going to be traced. The function graph tracer has been updated to
   allow multiple users to use its infrastructure. Now have fprobes be
   one of those users. This will also allow for the fprobe and kretprobe
   methods to trace the return address to become obsolete. With new
   technologies like CFI that need to know about these methods of
   hijacking the return address, going toward a solution that has only
   one method of doing this will make the kernel less complex.

 - Cleanup with guard() and free() helpers

   There were several places in the code that had a lot of "goto out" in
   the error paths to either unlock a lock or free some memory that was
   allocated. But this is error prone. Convert the code over to use the
   guard() and free() helpers that let the compiler unlock locks or free
   memory when the function exits.

 - Remove disabling of interrupts in the function graph tracer

   When function graph tracer was first introduced, it could race with
   interrupts and NMIs. To prevent that race, it would disable
   interrupts and not trace NMIs. But the code has changed to allow NMIs
   and also interrupts. This change was done a long time ago, but the
   disabling of interrupts was never removed. Remove the disabling of
   interrupts in the function graph tracer is it is not needed. This
   greatly improves its performance.

 - Allow the :mod: command to enable tracing module functions on the
   kernel command line.

   The function tracer already has a way to enable functions to be
   traced in modules by writing ":mod:<module>" into set_ftrace_filter.
   That will enable either all the functions for the module if it is
   loaded, or if it is not, it will cache that command, and when the
   module is loaded that matches <module>, its functions will be
   enabled. This also allows init functions to be traced. But currently
   events do not have that feature.

   Because enabling function tracing can be done very early at boot up
   (before scheduling is enabled), the commands that can be done when
   function tracing is started is limited. Having the ":mod:" command to
   trace module functions as they are loaded is very useful. Update the
   kernel command line function filtering to allow it.

* tag 'ftrace-v6.14' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (26 commits)
  ftrace: Implement :mod: cache filtering on kernel command line
  tracing: Adopt __free() and guard() for trace_fprobe.c
  bpf: Use ftrace_get_symaddr() for kprobe_multi probes
  ftrace: Add ftrace_get_symaddr to convert fentry_ip to symaddr
  Documentation: probes: Update fprobe on function-graph tracer
  selftests/ftrace: Add a test case for repeating register/unregister fprobe
  selftests: ftrace: Remove obsolate maxactive syntax check
  tracing/fprobe: Remove nr_maxactive from fprobe
  fprobe: Add fprobe_header encoding feature
  fprobe: Rewrite fprobe on function-graph tracer
  s390/tracing: Enable HAVE_FTRACE_GRAPH_FUNC
  ftrace: Add CONFIG_HAVE_FTRACE_GRAPH_FUNC
  bpf: Enable kprobe_multi feature if CONFIG_FPROBE is enabled
  tracing/fprobe: Enable fprobe events with CONFIG_DYNAMIC_FTRACE_WITH_ARGS
  tracing: Add ftrace_fill_perf_regs() for perf event
  tracing: Add ftrace_partial_regs() for converting ftrace_regs to pt_regs
  fprobe: Use ftrace_regs in fprobe exit handler
  fprobe: Use ftrace_regs in fprobe entry handler
  fgraph: Pass ftrace_regs to retfunc
  fgraph: Replace fgraph_ret_regs with ftrace_regs
  ...

13 files changed, 856 insertions, 484 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 74c2b1d43bb9..d570b8b9c0a9 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -31,9 +31,14 @@ config HAVE_FUNCTION_GRAPH_TRACER
 	help
 	  See Documentation/trace/ftrace-design.rst
 
-config HAVE_FUNCTION_GRAPH_RETVAL
+config HAVE_FUNCTION_GRAPH_FREGS
 	bool
 
+config HAVE_FTRACE_GRAPH_FUNC
+	bool
+	help
+	  True if ftrace_graph_func() is defined.
+
 config HAVE_DYNAMIC_FTRACE
 	bool
 	help
@@ -57,6 +62,12 @@ config HAVE_DYNAMIC_FTRACE_WITH_ARGS
 	 This allows for use of ftrace_regs_get_argument() and
 	 ftrace_regs_get_stack_pointer().
 
+config HAVE_FTRACE_REGS_HAVING_PT_REGS
+	bool
+	help
+	 If this is set, ftrace_regs has pt_regs, thus it can convert to
+	 pt_regs without allocating memory.
+
 config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
 	bool
 	help
@@ -232,7 +243,7 @@ config FUNCTION_GRAPH_TRACER
 
 config FUNCTION_GRAPH_RETVAL
 	bool "Kernel Function Graph Return Value"
-	depends on HAVE_FUNCTION_GRAPH_RETVAL
+	depends on HAVE_FUNCTION_GRAPH_FREGS
 	depends on FUNCTION_GRAPH_TRACER
 	default n
 	help
@@ -296,10 +307,9 @@ config DYNAMIC_FTRACE_WITH_ARGS
 
 config FPROBE
 	bool "Kernel Function Probe (fprobe)"
-	depends on FUNCTION_TRACER
-	depends on DYNAMIC_FTRACE_WITH_REGS
-	depends on HAVE_RETHOOK
-	select RETHOOK
+	depends on HAVE_FUNCTION_GRAPH_FREGS && HAVE_FTRACE_GRAPH_FUNC
+	depends on DYNAMIC_FTRACE_WITH_ARGS
+	select FUNCTION_GRAPH_TRACER
 	default n
 	help
 	  This option enables kernel function probe (fprobe) based on ftrace.
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 9f2f65767639..c462aca8b7e6 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2585,6 +2585,20 @@ struct user_syms {
 	char *buf;
 };
 
+#ifndef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS
+static DEFINE_PER_CPU(struct pt_regs, bpf_kprobe_multi_pt_regs);
+#define bpf_kprobe_multi_pt_regs_ptr()	this_cpu_ptr(&bpf_kprobe_multi_pt_regs)
+#else
+#define bpf_kprobe_multi_pt_regs_ptr()	(NULL)
+#endif
+
+static unsigned long ftrace_get_entry_ip(unsigned long fentry_ip)
+{
+	unsigned long ip = ftrace_get_symaddr(fentry_ip);
+
+	return ip ? : fentry_ip;
+}
+
 static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 cnt)
 {
 	unsigned long __user usymbol;
@@ -2779,7 +2793,7 @@ static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx)
 
 static int
 kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
-			   unsigned long entry_ip, struct pt_regs *regs,
+			   unsigned long entry_ip, struct ftrace_regs *fregs,
 			   bool is_return, void *data)
 {
 	struct bpf_kprobe_multi_run_ctx run_ctx = {
@@ -2791,6 +2805,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
 		.entry_ip = entry_ip,
 	};
 	struct bpf_run_ctx *old_run_ctx;
+	struct pt_regs *regs;
 	int err;
 
 	if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
@@ -2801,6 +2816,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
 
 	migrate_disable();
 	rcu_read_lock();
+	regs = ftrace_partial_regs(fregs, bpf_kprobe_multi_pt_regs_ptr());
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.session_ctx.run_ctx);
 	err = bpf_prog_run(link->link.prog, regs);
 	bpf_reset_run_ctx(old_run_ctx);
@@ -2814,26 +2830,28 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link,
 
 static int
 kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip,
-			  unsigned long ret_ip, struct pt_regs *regs,
+			  unsigned long ret_ip, struct ftrace_regs *fregs,
 			  void *data)
 {
 	struct bpf_kprobe_multi_link *link;
 	int err;
 
 	link = container_of(fp, struct bpf_kprobe_multi_link, fp);
-	err = kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, false, data);
+	err = kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip),
+					 fregs, false, data);
 	return is_kprobe_session(link->link.prog) ? err : 0;
 }
 
 static void
 kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip,
-			       unsigned long ret_ip, struct pt_regs *regs,
+			       unsigned long ret_ip, struct ftrace_regs *fregs,
 			       void *data)
 {
 	struct bpf_kprobe_multi_link *link;
 
 	link = container_of(fp, struct bpf_kprobe_multi_link, fp);
-	kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs, true, data);
+	kprobe_multi_link_prog_run(link, ftrace_get_entry_ip(fentry_ip),
+				   fregs, true, data);
 }
 
 static int symbols_cmp_r(const void *a, const void *b, const void *priv)
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 30e3ddc8a8a8..9e6b5a71555b 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -292,13 +292,15 @@ static inline unsigned long make_data_type_val(int idx, int size, int offset)
 }
 
 /* ftrace_graph_entry set to this to tell some archs to run function graph */
-static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops)
+static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops,
+		     struct ftrace_regs *fregs)
 {
 	return 0;
 }
 
 /* ftrace_graph_return set to this to tell some archs to run function graph */
-static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops)
+static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops,
+		       struct ftrace_regs *fregs)
 {
 }
 
@@ -520,13 +522,15 @@ int __weak ftrace_disable_ftrace_graph_caller(void)
 #endif
 
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace,
-			    struct fgraph_ops *gops)
+			    struct fgraph_ops *gops,
+			    struct ftrace_regs *fregs)
 {
 	return 0;
 }
 
 static void ftrace_graph_ret_stub(struct ftrace_graph_ret *trace,
-				  struct fgraph_ops *gops)
+				  struct fgraph_ops *gops,
+				  struct ftrace_regs *fregs)
 {
 }
 
@@ -644,14 +648,20 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
 #endif
 
 /* If the caller does not use ftrace, call this function. */
-int function_graph_enter(unsigned long ret, unsigned long func,
-			 unsigned long frame_pointer, unsigned long *retp)
+int function_graph_enter_regs(unsigned long ret, unsigned long func,
+			      unsigned long frame_pointer, unsigned long *retp,
+			      struct ftrace_regs *fregs)
 {
 	struct ftrace_graph_ent trace;
 	unsigned long bitmap = 0;
 	int offset;
+	int bit;
 	int i;
 
+	bit = ftrace_test_recursion_trylock(func, ret);
+	if (bit < 0)
+		return -EBUSY;
+
 	trace.func = func;
 	trace.depth = ++current->curr_ret_depth;
 
@@ -663,7 +673,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 	if (static_branch_likely(&fgraph_do_direct)) {
 		int save_curr_ret_stack = current->curr_ret_stack;
 
-		if (static_call(fgraph_func)(&trace, fgraph_direct_gops))
+		if (static_call(fgraph_func)(&trace, fgraph_direct_gops, fregs))
 			bitmap |= BIT(fgraph_direct_gops->idx);
 		else
 			/* Clear out any saved storage */
@@ -681,7 +691,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 
 			save_curr_ret_stack = current->curr_ret_stack;
 			if (ftrace_ops_test(&gops->ops, func, NULL) &&
-			    gops->entryfunc(&trace, gops))
+			    gops->entryfunc(&trace, gops, fregs))
 				bitmap |= BIT(i);
 			else
 				/* Clear out any saved storage */
@@ -697,12 +707,13 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 	 * flag, set that bit always.
 	 */
 	set_bitmap(current, offset, bitmap | BIT(0));
-
+	ftrace_test_recursion_unlock(bit);
 	return 0;
  out_ret:
 	current->curr_ret_stack -= FGRAPH_FRAME_OFFSET + 1;
  out:
 	current->curr_ret_depth--;
+	ftrace_test_recursion_unlock(bit);
 	return -EBUSY;
 }
 
@@ -792,15 +803,12 @@ static struct notifier_block ftrace_suspend_notifier = {
 	.notifier_call = ftrace_suspend_notifier_call,
 };
 
-/* fgraph_ret_regs is not defined without CONFIG_FUNCTION_GRAPH_RETVAL */
-struct fgraph_ret_regs;
-
 /*
  * Send the trace to the ring-buffer.
  * @return the original return address.
  */
-static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs,
-						unsigned long frame_pointer)
+static inline unsigned long
+__ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointer)
 {
 	struct ftrace_ret_stack *ret_stack;
 	struct ftrace_graph_ret trace;
@@ -819,8 +827,11 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 	}
 
 	trace.rettime = trace_clock_local();
+	if (fregs)
+		ftrace_regs_set_instruction_pointer(fregs, ret);
+
 #ifdef CONFIG_FUNCTION_GRAPH_RETVAL
-	trace.retval = fgraph_ret_regs_return_value(ret_regs);
+	trace.retval = ftrace_regs_get_return_value(fregs);
 #endif
 
 	bitmap = get_bitmap_bits(current, offset);
@@ -828,7 +839,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 #ifdef CONFIG_HAVE_STATIC_CALL
 	if (static_branch_likely(&fgraph_do_direct)) {
 		if (test_bit(fgraph_direct_gops->idx, &bitmap))
-			static_call(fgraph_retfunc)(&trace, fgraph_direct_gops);
+			static_call(fgraph_retfunc)(&trace, fgraph_direct_gops, fregs);
 	} else
 #endif
 	{
@@ -838,7 +849,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 			if (gops == &fgraph_stub)
 				continue;
 
-			gops->retfunc(&trace, gops);
+			gops->retfunc(&trace, gops, fregs);
 		}
 	}
 
@@ -855,14 +866,14 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 }
 
 /*
- * After all architecures have selected HAVE_FUNCTION_GRAPH_RETVAL, we can
- * leave only ftrace_return_to_handler(ret_regs).
+ * After all architecures have selected HAVE_FUNCTION_GRAPH_FREGS, we can
+ * leave only ftrace_return_to_handler(fregs).
  */
-#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL
-unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs)
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS
+unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs)
 {
-	return __ftrace_return_to_handler(ret_regs,
-				fgraph_ret_regs_frame_pointer(ret_regs));
+	return __ftrace_return_to_handler(fregs,
+				ftrace_regs_get_frame_pointer(fregs));
 }
 #else
 unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
@@ -1010,7 +1021,8 @@ void ftrace_graph_sleep_time_control(bool enable)
  * Simply points to ftrace_stub, but with the proper protocol.
  * Defined by the linker script in linux/vmlinux.lds.h
  */
-void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops);
+void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops,
+		       struct ftrace_regs *fregs);
 
 /* The callbacks that hook a function */
 trace_func_graph_ret_t ftrace_graph_return = ftrace_stub_graph;
@@ -1174,7 +1186,8 @@ void ftrace_graph_exit_task(struct task_struct *t)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 static int fgraph_pid_func(struct ftrace_graph_ent *trace,
-			   struct fgraph_ops *gops)
+			   struct fgraph_ops *gops,
+			   struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = gops->ops.private;
 	int pid;
@@ -1188,7 +1201,7 @@ static int fgraph_pid_func(struct ftrace_graph_ent *trace,
 			return 0;
 	}
 
-	return gops->saved_func(trace, gops);
+	return gops->saved_func(trace, gops, fregs);
 }
 
 void fgraph_update_pid_func(void)
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 9ff018245840..2560b312ad57 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -8,98 +8,224 @@
 #include <linux/fprobe.h>
 #include <linux/kallsyms.h>
 #include <linux/kprobes.h>
-#include <linux/rethook.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/sort.h>
 
+#include <asm/fprobe.h>
+
 #include "trace.h"
 
-struct fprobe_rethook_node {
-	struct rethook_node node;
-	unsigned long entry_ip;
-	unsigned long entry_parent_ip;
-	char data[];
-};
+#define FPROBE_IP_HASH_BITS 8
+#define FPROBE_IP_TABLE_SIZE (1 << FPROBE_IP_HASH_BITS)
 
-static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip,
-			struct ftrace_ops *ops, struct ftrace_regs *fregs)
-{
-	struct fprobe_rethook_node *fpr;
-	struct rethook_node *rh = NULL;
-	struct fprobe *fp;
-	void *entry_data = NULL;
-	int ret = 0;
+#define FPROBE_HASH_BITS 6
+#define FPROBE_TABLE_SIZE (1 << FPROBE_HASH_BITS)
 
-	fp = container_of(ops, struct fprobe, ops);
+#define SIZE_IN_LONG(x) ((x + sizeof(long) - 1) >> (sizeof(long) == 8 ? 3 : 2))
 
-	if (fp->exit_handler) {
-		rh = rethook_try_get(fp->rethook);
-		if (!rh) {
-			fp->nmissed++;
-			return;
-		}
-		fpr = container_of(rh, struct fprobe_rethook_node, node);
-		fpr->entry_ip = ip;
-		fpr->entry_parent_ip = parent_ip;
-		if (fp->entry_data_size)
-			entry_data = fpr->data;
+/*
+ * fprobe_table: hold 'fprobe_hlist::hlist' for checking the fprobe still
+ *   exists. The key is the address of fprobe instance.
+ * fprobe_ip_table: hold 'fprobe_hlist::array[*]' for searching the fprobe
+ *   instance related to the funciton address. The key is the ftrace IP
+ *   address.
+ *
+ * When unregistering the fprobe, fprobe_hlist::fp and fprobe_hlist::array[*].fp
+ * are set NULL and delete those from both hash tables (by hlist_del_rcu).
+ * After an RCU grace period, the fprobe_hlist itself will be released.
+ *
+ * fprobe_table and fprobe_ip_table can be accessed from either
+ *  - Normal hlist traversal and RCU add/del under 'fprobe_mutex' is held.
+ *  - RCU hlist traversal under disabling preempt
+ */
+static struct hlist_head fprobe_table[FPROBE_TABLE_SIZE];
+static struct hlist_head fprobe_ip_table[FPROBE_IP_TABLE_SIZE];
+static DEFINE_MUTEX(fprobe_mutex);
+
+/*
+ * Find first fprobe in the hlist. It will be iterated twice in the entry
+ * probe, once for correcting the total required size, the second time is
+ * calling back the user handlers.
+ * Thus the hlist in the fprobe_table must be sorted and new probe needs to
+ * be added *before* the first fprobe.
+ */
+static struct fprobe_hlist_node *find_first_fprobe_node(unsigned long ip)
+{
+	struct fprobe_hlist_node *node;
+	struct hlist_head *head;
+
+	head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)];
+	hlist_for_each_entry_rcu(node, head, hlist,
+				 lockdep_is_held(&fprobe_mutex)) {
+		if (node->addr == ip)
+			return node;
 	}
+	return NULL;
+}
+NOKPROBE_SYMBOL(find_first_fprobe_node);
 
-	if (fp->entry_handler)
-		ret = fp->entry_handler(fp, ip, parent_ip, ftrace_get_regs(fregs), entry_data);
+/* Node insertion and deletion requires the fprobe_mutex */
+static void insert_fprobe_node(struct fprobe_hlist_node *node)
+{
+	unsigned long ip = node->addr;
+	struct fprobe_hlist_node *next;
+	struct hlist_head *head;
 
-	/* If entry_handler returns !0, nmissed is not counted. */
-	if (rh) {
-		if (ret)
-			rethook_recycle(rh);
-		else
-			rethook_hook(rh, ftrace_get_regs(fregs), true);
+	lockdep_assert_held(&fprobe_mutex);
+
+	next = find_first_fprobe_node(ip);
+	if (next) {
+		hlist_add_before_rcu(&node->hlist, &next->hlist);
+		return;
 	}
+	head = &fprobe_ip_table[hash_ptr((void *)ip, FPROBE_IP_HASH_BITS)];
+	hlist_add_head_rcu(&node->hlist, head);
 }
 
-static void fprobe_handler(unsigned long ip, unsigned long parent_ip,
-		struct ftrace_ops *ops, struct ftrace_regs *fregs)
+/* Return true if there are synonims */
+static bool delete_fprobe_node(struct fprobe_hlist_node *node)
 {
-	struct fprobe *fp;
-	int bit;
+	lockdep_assert_held(&fprobe_mutex);
 
-	fp = container_of(ops, struct fprobe, ops);
-	if (fprobe_disabled(fp))
-		return;
+	WRITE_ONCE(node->fp, NULL);
+	hlist_del_rcu(&node->hlist);
+	return !!find_first_fprobe_node(node->addr);
+}
 
-	/* recursion detection has to go before any traceable function and
-	 * all functions before this point should be marked as notrace
-	 */
-	bit = ftrace_test_recursion_trylock(ip, parent_ip);
-	if (bit < 0) {
-		fp->nmissed++;
-		return;
+/* Check existence of the fprobe */
+static bool is_fprobe_still_exist(struct fprobe *fp)
+{
+	struct hlist_head *head;
+	struct fprobe_hlist *fph;
+
+	head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)];
+	hlist_for_each_entry_rcu(fph, head, hlist,
+				 lockdep_is_held(&fprobe_mutex)) {
+		if (fph->fp == fp)
+			return true;
 	}
-	__fprobe_handler(ip, parent_ip, ops, fregs);
-	ftrace_test_recursion_unlock(bit);
+	return false;
+}
+NOKPROBE_SYMBOL(is_fprobe_still_exist);
+
+static int add_fprobe_hash(struct fprobe *fp)
+{
+	struct fprobe_hlist *fph = fp->hlist_array;
+	struct hlist_head *head;
+
+	lockdep_assert_held(&fprobe_mutex);
+
+	if (WARN_ON_ONCE(!fph))
+		return -EINVAL;
+
+	if (is_fprobe_still_exist(fp))
+		return -EEXIST;
+
+	head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)];
+	hlist_add_head_rcu(&fp->hlist_array->hlist, head);
+	return 0;
+}
+
+static int del_fprobe_hash(struct fprobe *fp)
+{
+	struct fprobe_hlist *fph = fp->hlist_array;
 
+	lockdep_assert_held(&fprobe_mutex);
+
+	if (WARN_ON_ONCE(!fph))
+		return -EINVAL;
+
+	if (!is_fprobe_still_exist(fp))
+		return -ENOENT;
+
+	fph->fp = NULL;
+	hlist_del_rcu(&fph->hlist);
+	return 0;
 }
-NOKPROBE_SYMBOL(fprobe_handler);
 
-static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
-				  struct ftrace_ops *ops, struct ftrace_regs *fregs)
+#ifdef ARCH_DEFINE_ENCODE_FPROBE_HEADER
+
+/* The arch should encode fprobe_header info into one unsigned long */
+#define FPROBE_HEADER_SIZE_IN_LONG	1
+
+static inline bool write_fprobe_header(unsigned long *stack,
+					struct fprobe *fp, unsigned int size_words)
 {
+	if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD ||
+			 !arch_fprobe_header_encodable(fp)))
+		return false;
+
+	*stack = arch_encode_fprobe_header(fp, size_words);
+	return true;
+}
+
+static inline void read_fprobe_header(unsigned long *stack,
+					struct fprobe **fp, unsigned int *size_words)
+{
+	*fp = arch_decode_fprobe_header_fp(*stack);
+	*size_words = arch_decode_fprobe_header_size(*stack);
+}
+
+#else
+
+/* Generic fprobe_header */
+struct __fprobe_header {
 	struct fprobe *fp;
-	int bit;
+	unsigned long size_words;
+} __packed;
 
-	fp = container_of(ops, struct fprobe, ops);
-	if (fprobe_disabled(fp))
-		return;
+#define FPROBE_HEADER_SIZE_IN_LONG	SIZE_IN_LONG(sizeof(struct __fprobe_header))
 
-	/* recursion detection has to go before any traceable function and
-	 * all functions called before this point should be marked as notrace
-	 */
-	bit = ftrace_test_recursion_trylock(ip, parent_ip);
-	if (bit < 0) {
-		fp->nmissed++;
-		return;
-	}
+static inline bool write_fprobe_header(unsigned long *stack,
+					struct fprobe *fp, unsigned int size_words)
+{
+	struct __fprobe_header *fph = (struct __fprobe_header *)stack;
+
+	if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD))
+		return false;
+
+	fph->fp = fp;
+	fph->size_words = size_words;
+	return true;
+}
+
+static inline void read_fprobe_header(unsigned long *stack,
+					struct fprobe **fp, unsigned int *size_words)
+{
+	struct __fprobe_header *fph = (struct __fprobe_header *)stack;
+
+	*fp = fph->fp;
+	*size_words = fph->size_words;
+}
+
+#endif
+
+/*
+ * fprobe shadow stack management:
+ * Since fprobe shares a single fgraph_ops, it needs to share the stack entry
+ * among the probes on the same function exit. Note that a new probe can be
+ * registered before a target function is returning, we can not use the hash
+ * table to find the corresponding probes. Thus the probe address is stored on
+ * the shadow stack with its entry data size.
+ *
+ */
+static inline int __fprobe_handler(unsigned long ip, unsigned long parent_ip,
+				   struct fprobe *fp, struct ftrace_regs *fregs,
+				   void *data)
+{
+	if (!fp->entry_handler)
+		return 0;
+
+	return fp->entry_handler(fp, ip, parent_ip, fregs, data);
+}
 
+static inline int __fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
+					  struct fprobe *fp, struct ftrace_regs *fregs,
+					  void *data)
+{
+	int ret;
 	/*
 	 * This user handler is shared with other kprobes and is not expected to be
 	 * called recursively. So if any other kprobe handler is running, this will
@@ -108,44 +234,183 @@ static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,
 	 */
 	if (unlikely(kprobe_running())) {
 		fp->nmissed++;
-		goto recursion_unlock;
+		return 0;
 	}
 
 	kprobe_busy_begin();
-	__fprobe_handler(ip, parent_ip, ops, fregs);
+	ret = __fprobe_handler(ip, parent_ip, fp, fregs, data);
 	kprobe_busy_end();
-
-recursion_unlock:
-	ftrace_test_recursion_unlock(bit);
+	return ret;
 }
 
-static void fprobe_exit_handler(struct rethook_node *rh, void *data,
-				unsigned long ret_ip, struct pt_regs *regs)
+static int fprobe_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops,
+			struct ftrace_regs *fregs)
 {
-	struct fprobe *fp = (struct fprobe *)data;
-	struct fprobe_rethook_node *fpr;
-	int bit;
+	struct fprobe_hlist_node *node, *first;
+	unsigned long *fgraph_data = NULL;
+	unsigned long func = trace->func;
+	unsigned long ret_ip;
+	int reserved_words;
+	struct fprobe *fp;
+	int used, ret;
 
-	if (!fp || fprobe_disabled(fp))
-		return;
+	if (WARN_ON_ONCE(!fregs))
+		return 0;
 
-	fpr = container_of(rh, struct fprobe_rethook_node, node);
+	first = node = find_first_fprobe_node(func);
+	if (unlikely(!first))
+		return 0;
+
+	reserved_words = 0;
+	hlist_for_each_entry_from_rcu(node, hlist) {
+		if (node->addr != func)
+			break;
+		fp = READ_ONCE(node->fp);
+		if (!fp || !fp->exit_handler)
+			continue;
+		/*
+		 * Since fprobe can be enabled until the next loop, we ignore the
+		 * fprobe's disabled flag in this loop.
+		 */
+		reserved_words +=
+			FPROBE_HEADER_SIZE_IN_LONG + SIZE_IN_LONG(fp->entry_data_size);
+	}
+	node = first;
+	if (reserved_words) {
+		fgraph_data = fgraph_reserve_data(gops->idx, reserved_words * sizeof(long));
+		if (unlikely(!fgraph_data)) {
+			hlist_for_each_entry_from_rcu(node, hlist) {
+				if (node->addr != func)
+					break;
+				fp = READ_ONCE(node->fp);
+				if (fp && !fprobe_disabled(fp))
+					fp->nmissed++;
+			}
+			return 0;
+		}
+	}
 
 	/*
-	 * we need to assure no calls to traceable functions in-between the
-	 * end of fprobe_handler and the beginning of fprobe_exit_handler.
+	 * TODO: recursion detection has been done in the fgraph. Thus we need
+	 * to add a callback to increment missed counter.
 	 */
-	bit = ftrace_test_recursion_trylock(fpr->entry_ip, fpr->entry_parent_ip);
-	if (bit < 0) {
-		fp->nmissed++;
+	ret_ip = ftrace_regs_get_return_address(fregs);
+	used = 0;
+	hlist_for_each_entry_from_rcu(node, hlist) {
+		int data_size;
+		void *data;
+
+		if (node->addr != func)
+			break;
+		fp = READ_ONCE(node->fp);
+		if (!fp || fprobe_disabled(fp))
+			continue;
+
+		data_size = fp->entry_data_size;
+		if (data_size && fp->exit_handler)
+			data = fgraph_data + used + FPROBE_HEADER_SIZE_IN_LONG;
+		else
+			data = NULL;
+
+		if (fprobe_shared_with_kprobes(fp))
+			ret = __fprobe_kprobe_handler(func, ret_ip, fp, fregs, data);
+		else
+			ret = __fprobe_handler(func, ret_ip, fp, fregs, data);
+
+		/* If entry_handler returns !0, nmissed is not counted but skips exit_handler. */
+		if (!ret && fp->exit_handler) {
+			int size_words = SIZE_IN_LONG(data_size);
+
+			if (write_fprobe_header(&fgraph_data[used], fp, size_words))
+				used += FPROBE_HEADER_SIZE_IN_LONG + size_words;
+		}
+	}
+	if (used < reserved_words)
+		memset(fgraph_data + used, 0, reserved_words - used);
+
+	/* If any exit_handler is set, data must be used. */
+	return used != 0;
+}
+NOKPROBE_SYMBOL(fprobe_entry);
+
+static void fprobe_return(struct ftrace_graph_ret *trace,
+			  struct fgraph_ops *gops,
+			  struct ftrace_regs *fregs)
+{
+	unsigned long *fgraph_data = NULL;
+	unsigned long ret_ip;
+	struct fprobe *fp;
+	int size, curr;
+	int size_words;
+
+	fgraph_data = (unsigned long *)fgraph_retrieve_data(gops->idx, &size);
+	if (WARN_ON_ONCE(!fgraph_data))
 		return;
+	size_words = SIZE_IN_LONG(size);
+	ret_ip = ftrace_regs_get_instruction_pointer(fregs);
+
+	preempt_disable();
+
+	curr = 0;
+	while (size_words > curr) {
+		read_fprobe_header(&fgraph_data[curr], &fp, &size);
+		if (!fp)
+			break;
+		curr += FPROBE_HEADER_SIZE_IN_LONG;
+		if (is_fprobe_still_exist(fp) && !fprobe_disabled(fp)) {
+			if (WARN_ON_ONCE(curr + size > size_words))
+				break;
+			fp->exit_handler(fp, trace->func, ret_ip, fregs,
+					 size ? fgraph_data + curr : NULL);
+		}
+		curr += size;
 	}
+	preempt_enable();
+}
+NOKPROBE_SYMBOL(fprobe_return);
+
+static struct fgraph_ops fprobe_graph_ops = {
+	.entryfunc	= fprobe_entry,
+	.retfunc	= fprobe_return,
+};
+static int fprobe_graph_active;
 
-	fp->exit_handler(fp, fpr->entry_ip, ret_ip, regs,
-			 fp->entry_data_size ? (void *)fpr->data : NULL);
-	ftrace_test_recursion_unlock(bit);
+/* Add @addrs to the ftrace filter and register fgraph if needed. */
+static int fprobe_graph_add_ips(unsigned long *addrs, int num)
+{
+	int ret;
+
+	lockdep_assert_held(&fprobe_mutex);
+
+	ret = ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 0, 0);
+	if (ret)
+		return ret;
+
+	if (!fprobe_graph_active) {
+		ret = register_ftrace_graph(&fprobe_graph_ops);
+		if (WARN_ON_ONCE(ret)) {
+			ftrace_free_filter(&fprobe_graph_ops.ops);
+			return ret;
+		}
+	}
+	fprobe_graph_active++;
+	return 0;
+}
+
+/* Remove @addrs from the ftrace filter and unregister fgraph if possible. */
+static void fprobe_graph_remove_ips(unsigned long *addrs, int num)
+{
+	lockdep_assert_held(&fprobe_mutex);
+
+	fprobe_graph_active--;
+	if (!fprobe_graph_active) {
+		/* Q: should we unregister it ? */
+		unregister_ftrace_graph(&fprobe_graph_ops);
+		return;
+	}
+
+	ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0);
 }
-NOKPROBE_SYMBOL(fprobe_exit_handler);
 
 static int symbols_cmp(const void *a, const void *b)
 {
@@ -175,53 +440,97 @@ static unsigned long *get_ftrace_locations(const char **syms, int num)
 	return ERR_PTR(-ENOENT);
 }
 
-static void fprobe_init(struct fprobe *fp)
-{
-	fp->nmissed = 0;
-	if (fprobe_shared_with_kprobes(fp))
-		fp->ops.func = fprobe_kprobe_handler;
-	else
-		fp->ops.func = fprobe_handler;
-	fp->ops.flags |= FTRACE_OPS_FL_SAVE_REGS;
-}
+struct filter_match_data {
+	const char *filter;
+	const char *notfilter;
+	size_t index;
+	size_t size;
+	unsigned long *addrs;
+};
 
-static int fprobe_init_rethook(struct fprobe *fp, int num)
+static int filter_match_callback(void *data, const char *name, unsigned long addr)
 {
-	int size;
+	struct filter_match_data *match = data;
 
-	if (!fp->exit_handler) {
-		fp->rethook = NULL;
+	if (!glob_match(match->filter, name) ||
+	    (match->notfilter && glob_match(match->notfilter, name)))
 		return 0;
-	}
 
-	/* Initialize rethook if needed */
-	if (fp->nr_maxactive)
-		num = fp->nr_maxactive;
-	else
-		num *= num_possible_cpus() * 2;
-	if (num <= 0)
-		return -EINVAL;
+	if (!ftrace_location(addr))
+		return 0;
+
+	if (match->addrs)
+		match->addrs[match->index] = addr;
 
-	size = sizeof(struct fprobe_rethook_node) + fp->entry_data_size;
+	match->index++;
+	return match->index == match->size;
+}
 
-	/* Initialize rethook */
-	fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, size, num);
-	if (IS_ERR(fp->rethook))
-		return PTR_ERR(fp->rethook);
+/*
+ * Make IP list from the filter/no-filter glob patterns.
+ * Return the number of matched symbols, or -ENOENT.
+ */
+static int ip_list_from_filter(const char *filter,