For now, the "nop" will be replaced with a "call" instruction when a
function is hooked by the ftrace. However, sometimes the "call" can break
the RSB and introduce extra overhead. Therefore, introduce the flag
FTRACE_OPS_FL_JMP, which indicate that the ftrace_ops should be called
with a "jmp" instead of "call". For now, it is only used by the direct
call case.

When a direct ftrace_ops is marked with FTRACE_OPS_FL_JMP, the last bit of
the ops->direct_call will be set to 1. Therefore, we can tell if we should
use "jmp" for the callback in ftrace_call_replace().

Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
---
v3:
- reject if the addr is already "jmp" in register_ftrace_direct() and
  __modify_ftrace_direct()
---
 include/linux/ftrace.h | 33 +++++++++++++++++++++++++++++++++
 kernel/trace/Kconfig   | 12 ++++++++++++
 kernel/trace/ftrace.c  | 17 ++++++++++++++++-
 3 files changed, 61 insertions(+), 1 deletion(-)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 07f8c309e432..015dd1049bea 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -359,6 +359,7 @@ enum {
 	FTRACE_OPS_FL_DIRECT			= BIT(17),
 	FTRACE_OPS_FL_SUBOP			= BIT(18),
 	FTRACE_OPS_FL_GRAPH			= BIT(19),
+	FTRACE_OPS_FL_JMP			= BIT(20),
 };
 
 #ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
@@ -577,6 +578,38 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs,
 						 unsigned long addr) { }
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP
+static inline bool ftrace_is_jmp(unsigned long addr)
+{
+	return addr & 1;
+}
+
+static inline unsigned long ftrace_jmp_set(unsigned long addr)
+{
+	return addr | 1UL;
+}
+
+static inline unsigned long ftrace_jmp_get(unsigned long addr)
+{
+	return addr & ~1UL;
+}
+#else
+static inline bool ftrace_is_jmp(unsigned long addr)
+{
+	return false;
+}
+
+static inline unsigned long ftrace_jmp_set(unsigned long addr)
+{
+	return addr;
+}
+
+static inline unsigned long ftrace_jmp_get(unsigned long addr)
+{
+	return addr;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_JMP */
+
 #ifdef CONFIG_STACK_TRACER
 
 int stack_trace_sysctl(const struct ctl_table *table, int write, void *buffer,
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index d2c79da81e4f..4661b9e606e0 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -80,6 +80,12 @@ config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
 	  If the architecture generates __patchable_function_entries sections
 	  but does not want them included in the ftrace locations.
 
+config HAVE_DYNAMIC_FTRACE_WITH_JMP
+	bool
+	help
+	  If the architecture supports to replace the __fentry__ with a
+	  "jmp" instruction.
+
 config HAVE_SYSCALL_TRACEPOINTS
 	bool
 	help
@@ -330,6 +336,12 @@ config DYNAMIC_FTRACE_WITH_ARGS
 	depends on DYNAMIC_FTRACE
 	depends on HAVE_DYNAMIC_FTRACE_WITH_ARGS
 
+config DYNAMIC_FTRACE_WITH_JMP
+	def_bool y
+	depends on DYNAMIC_FTRACE
+	depends on DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	depends on HAVE_DYNAMIC_FTRACE_WITH_JMP
+
 config FPROBE
 	bool "Kernel Function Probe (fprobe)"
 	depends on HAVE_FUNCTION_GRAPH_FREGS && HAVE_FTRACE_GRAPH_FUNC
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 59cfacb8a5bb..bbb37c0f8c6c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5951,7 +5951,8 @@ static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long
 	for (i = 0; i < size; i++) {
 		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
 			del = __ftrace_lookup_ip(direct_functions, entry->ip);
-			if (del && del->direct == addr) {
+			if (del && ftrace_jmp_get(del->direct) ==
+				   ftrace_jmp_get(addr)) {
 				remove_hash_entry(direct_functions, del);
 				kfree(del);
 			}
@@ -6016,8 +6017,15 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 	if (ftrace_hash_empty(hash))
 		return -EINVAL;
 
+	/* This is a "raw" address, and this should never happen. */
+	if (WARN_ON_ONCE(ftrace_is_jmp(addr)))
+		return -EINVAL;
+
 	mutex_lock(&direct_mutex);
 
+	if (ops->flags & FTRACE_OPS_FL_JMP)
+		addr = ftrace_jmp_set(addr);
+
 	/* Make sure requested entries are not already registered.. */
 	size = 1 << hash->size_bits;
 	for (i = 0; i < size; i++) {
@@ -6138,6 +6146,13 @@ __modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 
 	lockdep_assert_held_once(&direct_mutex);
 
+	/* This is a "raw" address, and this should never happen. */
+	if (WARN_ON_ONCE(ftrace_is_jmp(addr)))
+		return -EINVAL;
+
+	if (ops->flags & FTRACE_OPS_FL_JMP)
+		addr = ftrace_jmp_set(addr);
+
 	/* Enable the tmp_ops to have the same functions as the direct ops */
 	ftrace_ops_init(&tmp_ops);
 	tmp_ops.func_hash = ops->func_hash;
-- 
2.51.2

Implement the DYNAMIC_FTRACE_WITH_JMP for x86_64. In ftrace_call_replace,
we will use JMP32_INSN_OPCODE instead of CALL_INSN_OPCODE if the address
should use "jmp".

Meanwhile, adjust the direct call in the ftrace_regs_caller. The RSB is
balanced in the "jmp" mode. Take the function "foo" for example:

 original_caller:
 call foo -> foo:
         call fentry -> fentry:
                 [do ftrace callbacks ]
                 move tramp_addr to stack
                 RET -> tramp_addr
                         tramp_addr:
                         [..]
                         call foo_body -> foo_body:
                                 [..]
                                 RET -> back to tramp_addr
                         [..]
                         RET -> back to original_caller

Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
---
 arch/x86/Kconfig            |  1 +
 arch/x86/kernel/ftrace.c    |  7 ++++++-
 arch/x86/kernel/ftrace_64.S | 12 +++++++++++-
 3 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fa3b616af03a..462250a20311 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -230,6 +230,7 @@ config X86
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS	if X86_64
 	select HAVE_FTRACE_REGS_HAVING_PT_REGS	if X86_64
 	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	select HAVE_DYNAMIC_FTRACE_WITH_JMP	if X86_64
 	select HAVE_SAMPLE_FTRACE_DIRECT	if X86_64
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI	if X86_64
 	select HAVE_EBPF_JIT
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 4450acec9390..0543b57f54ee 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -74,7 +74,12 @@ static const char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 	 * No need to translate into a callthunk. The trampoline does
 	 * the depth accounting itself.
 	 */
-	return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr);
+	if (ftrace_is_jmp(addr)) {
+		addr = ftrace_jmp_get(addr);
+		return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr);
+	} else {
+		return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr);
+	}
 }
 
 static int ftrace_verify_code(unsigned long ip, const char *old_code)
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 823dbdd0eb41..a132608265f6 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -285,8 +285,18 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	RET
 
+1:
+	testb	$1, %al
+	jz	2f
+	andq $0xfffffffffffffffe, %rax
+	movq %rax, MCOUNT_REG_SIZE+8(%rsp)
+	restore_mcount_regs
+	/* Restore flags */
+	popfq
+	RET
+
 	/* Swap the flags with orig_rax */
-1:	movq MCOUNT_REG_SIZE(%rsp), %rdi
+2:	movq MCOUNT_REG_SIZE(%rsp), %rdi
 	movq %rdi, MCOUNT_REG_SIZE-8(%rsp)
 	movq %rax, MCOUNT_REG_SIZE(%rsp)
 
-- 
2.51.2

Some places calculate the origin_call by checking if
BPF_TRAMP_F_SKIP_FRAME is set. However, it should use
BPF_TRAMP_F_ORIG_STACK for this propose. Just fix them.

Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/riscv/net/bpf_jit_comp64.c | 2 +-
 arch/x86/net/bpf_jit_comp.c     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 45cbc7c6fe49..21c70ae3296b 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1131,7 +1131,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
 	store_args(nr_arg_slots, args_off, ctx);
 
 	/* skip to actual body of traced function */
-	if (flags & BPF_TRAMP_F_SKIP_FRAME)
+	if (flags & BPF_TRAMP_F_ORIG_STACK)
 		orig_call += RV_FENTRY_NINSNS * 4;
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 36a0d4db9f68..808d4343f6cf 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -3289,7 +3289,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 
 	arg_stack_off = stack_size;
 
-	if (flags & BPF_TRAMP_F_SKIP_FRAME) {
+	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		/* skip patched call instruction and point orig_call to actual
 		 * body of the kernel function.
 		 */
-- 
2.51.2

In the origin call case, if BPF_TRAMP_F_SKIP_FRAME is not set, it means
that the trampoline is not called, but "jmp".

Introduce the function bpf_trampoline_use_jmp() to check if the trampoline
is in "jmp" mode.

Do some adjustment on the "jmp" mode for the x86_64. The main adjustment
that we make is for the stack parameter passing case, as the stack
alignment logic changes in the "jmp" mode without the "rip". What's more,
the location of the parameters on the stack also changes.

Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
---
v2:
- rename bpf_trampoline_need_jmp() to bpf_trampoline_use_jmp()
---
 arch/x86/net/bpf_jit_comp.c | 16 +++++++++++-----
 include/linux/bpf.h         | 12 ++++++++++++
 2 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 808d4343f6cf..632a83381c2d 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -2847,9 +2847,10 @@ static int get_nr_used_regs(const struct btf_func_model *m)
 }
 
 static void save_args(const struct btf_func_model *m, u8 **prog,
-		      int stack_size, bool for_call_origin)
+		      int stack_size, bool for_call_origin, u32 flags)
 {
 	int arg_regs, first_off = 0, nr_regs = 0, nr_stack_slots = 0;
+	bool use_jmp = bpf_trampoline_use_jmp(flags);
 	int i, j;
 
 	/* Store function arguments to stack.
@@ -2890,7 +2891,7 @@ static void save_args(const struct btf_func_model *m, u8 **prog,
 			 */
 			for (j = 0; j < arg_regs; j++) {
 				emit_ldx(prog, BPF_DW, BPF_REG_0, BPF_REG_FP,
-					 nr_stack_slots * 8 + 0x18);
+					 nr_stack_slots * 8 + 16 + (!use_jmp) * 8);
 				emit_stx(prog, BPF_DW, BPF_REG_FP, BPF_REG_0,
 					 -stack_size);
 
@@ -3284,7 +3285,12 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		 * should be 16-byte aligned. Following code depend on
 		 * that stack_size is already 8-byte aligned.
 		 */
-		stack_size += (stack_size % 16) ? 0 : 8;
+		if (bpf_trampoline_use_jmp(flags)) {
+			/* no rip in the "jmp" case */
+			stack_size += (stack_size % 16) ? 8 : 0;
+		} else {
+			stack_size += (stack_size % 16) ? 0 : 8;
+		}
 	}
 
 	arg_stack_off = stack_size;
@@ -3344,7 +3350,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -ip_off);
 	}
 
-	save_args(m, &prog, regs_off, false);
+	save_args(m, &prog, regs_off, false, flags);
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		/* arg1: mov rdi, im */
@@ -3377,7 +3383,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		restore_regs(m, &prog, regs_off);
-		save_args(m, &prog, arg_stack_off, true);
+		save_args(m, &prog, arg_stack_off, true, flags);
 
 		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) {
 			/* Before calling the original function, load the
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 09d5dc541d1c..4187b7578580 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1264,6 +1264,18 @@ typedef void (*bpf_trampoline_exit_t)(struct bpf_prog *prog, u64 start,
 bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog);
 bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog);
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP
+static inline bool bpf_trampoline_use_jmp(u64 flags)
+{
+	return flags & BPF_TRAMP_F_CALL_ORIG && !(flags & BPF_TRAMP_F_SKIP_FRAME);
+}
+#else
+static inline bool bpf_trampoline_use_jmp(u64 flags)
+{
+	return false;
+}
+#endif
+
 struct bpf_ksym {
 	unsigned long		 start;
 	unsigned long		 end;
-- 
2.51.2

In the origin logic, the bpf_arch_text_poke() assume that the old and new
instructions have the same opcode. However, they can have different opcode
if we want to replace a "call" insn with a "jmp" insn.

Therefore, add the new function parameter "old_t" along with the "new_t",
which are used to indicate the old and new poke type. Meanwhile, adjust
the implement of bpf_arch_text_poke() for all the archs.

"BPF_MOD_NOP" is added to make the code more readable. In
bpf_arch_text_poke(), we still check if the new and old address is NULL to
determine if nop insn should be used, which I think is more safe.

Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
---
v3:
- fix compile error in powerpc

v2:
- add new function parameter to bpf_arch_text_poke instead of introduce
  bpf_arch_text_poke_type()
---
 arch/arm64/net/bpf_jit_comp.c   | 14 ++++++-------
 arch/loongarch/net/bpf_jit.c    |  9 +++++---
 arch/powerpc/net/bpf_jit_comp.c | 10 +++++----
 arch/riscv/net/bpf_jit_comp64.c |  9 +++++---
 arch/s390/net/bpf_jit_comp.c    |  7 ++++---
 arch/x86/net/bpf_jit_comp.c     | 37 +++++++++++++++++++--------------
 include/linux/bpf.h             |  6 ++++--
 kernel/bpf/core.c               |  5 +++--
 kernel/bpf/trampoline.c         | 20 ++++++++++++------
 9 files changed, 71 insertions(+), 46 deletions(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 0c9a50a1e73e..c64df579b7e0 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -2923,8 +2923,9 @@ static int gen_branch_or_nop(enum aarch64_insn_branch_type type, void *ip,
  * The dummy_tramp is used to prevent another CPU from jumping to unknown
  * locations during the patching process, making the patching process easier.
  */
-int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
-		       void *old_addr, void *new_addr)
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
+		       enum bpf_text_poke_type new_t, void *old_addr,
+		       void *new_addr)
 {
 	int ret;
 	u32 old_insn;
@@ -2968,14 +2969,13 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
 		    !poking_bpf_entry))
 		return -EINVAL;
 
-	if (poke_type == BPF_MOD_CALL)
-		branch_type = AARCH64_INSN_BRANCH_LINK;
-	else
-		branch_type = AARCH64_INSN_BRANCH_NOLINK;
-
+	branch_type = old_t == BPF_MOD_CALL ? AARCH64_INSN_BRANCH_LINK :
+					      AARCH64_INSN_BRANCH_NOLINK;
 	if (gen_branch_or_nop(branch_type, ip, old_addr, plt, &old_insn) < 0)
 		return -EFAULT;
 
+	branch_type = new_t == BPF_MOD_CALL ? AARCH64_INSN_BRANCH_LINK :
+					      AARCH64_INSN_BRANCH_NOLINK;
 	if (gen_branch_or_nop(branch_type, ip, new_addr, plt, &new_insn) < 0)
 		return -EFAULT;
 
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index cbe53d0b7fb0..2e7dacbbef5c 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -1284,11 +1284,12 @@ void *bpf_arch_text_copy(void *dst, void *src, size_t len)
 	return ret ? ERR_PTR(-EINVAL) : dst;
 }
 
-int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
-		       void *old_addr, void *new_addr)
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
+		       enum bpf_text_poke_type new_t, void *old_addr,
+		       void *new_addr)
 {
 	int ret;
-	bool is_call = (poke_type == BPF_MOD_CALL);
+	bool is_call;
 	u32 old_insns[LOONGARCH_LONG_JUMP_NINSNS] = {[0 ... 4] = INSN_NOP};
 	u32 new_insns[LOONGARCH_LONG_JUMP_NINSNS] = {[0 ... 4] = INSN_NOP};
 
@@ -1298,6 +1299,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
 	if (!is_bpf_text_address((unsigned long)ip))
 		return -ENOTSUPP;
 
+	is_call = old_t == BPF_MOD_CALL;
 	ret = emit_jump_or_nops(old_addr, ip, old_insns, is_call);
 	if (ret)
 		return ret;
@@ -1305,6 +1307,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
 	if (memcmp(ip, old_insns, LOONGARCH_LONG_JUMP_NBYTES))
 		return -EFAULT;
 
+	is_call = new_t == BPF_MOD_CALL;
 	ret = emit_jump_or_nops(new_addr, ip, new_insns, is_call);
 	if (ret)
 		return ret;
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 88ad5ba7b87f..5e976730b2f5 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -1107,8 +1107,9 @@ static void do_isync(void *info __maybe_unused)
  * execute isync (or some CSI) so that they don't go back into the
  * trampoline again.
  */
-int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
-		       void *old_addr, void *new_addr)
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
+		       enum bpf_text_poke_type new_t, void *old_addr,
+		       void *new_addr)
 {
 	unsigned long bpf_func, bpf_func_end, size, offset;
 	ppc_inst_t old_inst, new_inst;
@@ -1119,7 +1120,6 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
 		return -EOPNOTSUPP;
 
 	bpf_func = (unsigned long)ip;
-	branch_flags = poke_type == BPF_MOD_CALL ? BRANCH_SET_LINK : 0;
 
 	/* We currently only support poking bpf programs */
 	if (!__bpf_address_lookup(bpf_func, &size, &offset, name)) {
@@ -1132,7 +1132,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
 	 * an unconditional branch instruction at im->ip_after_call
 	 */
 	if (offset) {
-		if (poke_type != BPF_MOD_JUMP) {
+		if (old_t == BPF_MOD_CALL || new_t == BPF_MOD_CALL) {
 			pr_err("%s (0x%lx): calls are not supported in bpf prog body\n", __func__,
 			       bpf_func);
 			return -EOPNOTSUPP;
@@ -1166,6 +1166,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
 	}
 
 	old_inst = ppc_inst(PPC_RAW_NOP());
+	branch_flags = old_t == BPF_MOD_CALL ? BRANCH_SET_LINK : 0;
 	if (old_addr) {
 		if (is_offset_in_branch_range(ip - old_addr))
 			create_branch(&old_inst, ip, (unsigned long)old_addr, branch_flags);
@@ -1174,6 +1175,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
 				      branch_flags);
 	}
 	new_inst = ppc_inst(PPC_RAW_NOP());
+	branch_flags = new_t == BPF_MOD_CALL ? BRANCH_SET_LINK : 0;
 	if (new_addr) {
 		if (is_offset_in_branch_range(ip - new_addr))
 			create_branch(&new_inst, ip, (unsigned long)new_addr, branch_flags);
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 21c70ae3296b..5f9457e910e8 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -852,17 +852,19 @@ static int gen_jump_or_nops(void *target, void *ip, u32 *insns, bool is_call)
 	return emit_jump_and_link(is_call ? RV_REG_T0 : RV_REG_ZERO, rvoff, false, &ctx);
 }
 
-int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
-		       void *old_addr, void *new_addr)
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
+		       enum bpf_text_poke_type new_t, void *old_addr,
+		       void *new_addr)
 {
 	u32 old_insns[RV_FENTRY_NINSNS], new_insns[RV_FENTRY_NINSNS];
-	bool is_call = poke_type == BPF_MOD_CALL;
+	bool is_call;
 	int ret;
 
 	if (!is_kernel_text((unsigned long)ip) &&
 	    !is_bpf_text_address((unsigned long)ip))
 		return -ENOTSUPP;
 
+	is_call = old_t == BPF_MOD_CALL;
 	ret = gen_jump_or_nops(old_addr, ip, old_insns, is_call);
 	if (ret)
 		return ret;
@@ -870,6 +872,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type poke_type,
 	if (memcmp(ip, old_insns, RV_FENTRY_NBYTES))
 		return -EFAULT;
 
+	is_call = new_t == BPF_MOD_CALL;
 	ret = gen_jump_or_nops(new_addr, ip, new_insns, is_call);
 	if (ret)
 		return ret;
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index cf461d76e9da..a2072cabba76 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -2413,8 +2413,9 @@ bool bpf_jit_supports_far_kfunc_call(void)
 	return true;
 }
 
-int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
-		       void *old_addr, void *new_addr)
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
+		       enum bpf_text_poke_type new_t, void *old_addr,
+		       void *new_addr)
 {
 	struct bpf_plt expected_plt, current_plt, new_plt, *plt;
 	struct {
@@ -2431,7 +2432,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	if (insn.opc != (0xc004 | (old_addr ? 0xf0 : 0)))
 		return -EINVAL;
 
-	if (t == BPF_MOD_JUMP &&
+	if ((new_t == BPF_MOD_JUMP || old_t == BPF_MOD_JUMP) &&
 	    insn.disp == ((char *)new_addr - (char *)ip) >> 1) {
 		/*
 		 * The branch already points to the destination,
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 632a83381c2d..b69dc7194e2c 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -597,7 +597,8 @@ static int emit_jump(u8 **pprog, void *func, void *ip)
 	return emit_patch(pprog, func, ip, 0xE9);
 }
 
-static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
+static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
+				enum bpf_text_poke_type new_t,
 				void *old_addr, void *new_addr)
 {
 	const u8 *nop_insn = x86_nops[5];
@@ -607,9 +608,9 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	int ret;
 
 	memcpy(old_insn, nop_insn, X86_PATCH_SIZE);
-	if (old_addr) {
+	if (old_t != BPF_MOD_NOP && old_addr) {
 		prog = old_insn;
-		ret = t == BPF_MOD_CALL ?
+		ret = old_t == BPF_MOD_CALL ?
 		      emit_call(&prog, old_addr, ip) :
 		      emit_jump(&prog, old_addr, ip);
 		if (ret)
@@ -617,9 +618,9 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	}
 
 	memcpy(new_insn, nop_insn, X86_PATCH_SIZE);
-	if (new_addr) {
+	if (new_t != BPF_MOD_NOP && new_addr) {
 		prog = new_insn;
-		ret = t == BPF_MOD_CALL ?
+		ret = new_t == BPF_MOD_CALL ?
 		      emit_call(&prog, new_addr, ip) :
 		      emit_jump(&prog, new_addr, ip);
 		if (ret)
@@ -640,8 +641,9 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	return ret;
 }
 
-int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
-		       void *old_addr, void *new_addr)
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
+		       enum bpf_text_poke_type new_t, void *old_addr,
+		       void *new_addr)
 {
 	if (!is_kernel_text((long)ip) &&
 	    !is_bpf_text_address((long)ip))
@@ -655,7 +657,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	if (is_endbr(ip))
 		ip += ENDBR_INSN_SIZE;
 
-	return __bpf_arch_text_poke(ip, t, old_addr, new_addr);
+	return __bpf_arch_text_poke(ip, old_t, new_t, old_addr, new_addr);
 }
 
 #define EMIT_LFENCE()	EMIT3(0x0F, 0xAE, 0xE8)
@@ -897,12 +899,13 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
 		target = array->ptrs[poke->tail_call.key];
 		if (target) {
 			ret = __bpf_arch_text_poke(poke->tailcall_target,
-						   BPF_MOD_JUMP, NULL,
+						   BPF_MOD_NOP, BPF_MOD_JUMP,
+						   NULL,
 						   (u8 *)target->bpf_func +
 						   poke->adj_off);
 			BUG_ON(ret < 0);
 			ret = __bpf_arch_text_poke(poke->tailcall_bypass,
-						   BPF_MOD_JUMP,
+						   BPF_MOD_JUMP, BPF_MOD_NOP,
 						   (u8 *)poke->tailcall_target +
 						   X86_PATCH_SIZE, NULL);
 			BUG_ON(ret < 0);
@@ -3985,6 +3988,7 @@ void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
 			       struct bpf_prog *new, struct bpf_prog *old)
 {
 	u8 *old_addr, *new_addr, *old_bypass_addr;
+	enum bpf_text_poke_type t;
 	int ret;
 
 	old_bypass_addr = old ? NULL : poke->bypass_addr;
@@ -3997,21 +4001,22 @@ void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
 	 * the kallsyms check.
 	 */
 	if (new) {
+		t = old_addr ? BPF_MOD_JUMP : BPF_MOD_NOP;
 		ret = __bpf_arch_text_poke(poke->tailcall_target,
-					   BPF_MOD_JUMP,
+					   t, BPF_MOD_JUMP,
 					   old_addr, new_addr);
 		BUG_ON(ret < 0);
 		if (!old) {
 			ret = __bpf_arch_text_poke(poke->tailcall_bypass,
-						   BPF_MOD_JUMP,
+						   BPF_MOD_JUMP, BPF_MOD_NOP,
 						   poke->bypass_addr,
 						   NULL);
 			BUG_ON(ret < 0);
 		}
 	} else {
+		t = old_bypass_addr ? BPF_MOD_JUMP : BPF_MOD_NOP;
 		ret = __bpf_arch_text_poke(poke->tailcall_bypass,
-					   BPF_MOD_JUMP,
-					   old_bypass_addr,
+					   t, BPF_MOD_JUMP, old_bypass_addr,
 					   poke->bypass_addr);
 		BUG_ON(ret < 0);
 		/* let other CPUs finish the execution of program
@@ -4020,9 +4025,9 @@ void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
 		 */
 		if (!ret)
 			synchronize_rcu();
+		t = old_addr ? BPF_MOD_JUMP : BPF_MOD_NOP;
 		ret = __bpf_arch_text_poke(poke->tailcall_target,
-					   BPF_MOD_JUMP,
-					   old_addr, NULL);
+					   t, BPF_MOD_NOP, old_addr, NULL);
 		BUG_ON(ret < 0);
 	}
 }
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4187b7578580..d5e2af29c7c8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3708,12 +3708,14 @@ static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
 #endif /* CONFIG_INET */
 
 enum bpf_text_poke_type {
+	BPF_MOD_NOP,
 	BPF_MOD_CALL,
 	BPF_MOD_JUMP,
 };
 
-int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
-		       void *addr1, void *addr2);
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
+		       enum bpf_text_poke_type new_t, void *old_addr,
+		       void *new_addr);
 
 void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
 			       struct bpf_prog *new, struct bpf_prog *old);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ef4448f18aad..c8ae6ab31651 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -3150,8 +3150,9 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to,
 	return -EFAULT;
 }
 
-int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
-			      void *addr1, void *addr2)
+int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
+			      enum bpf_text_poke_type new_t, void *old_addr,
+			      void *new_addr)
 {
 	return -ENOTSUPP;
 }
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 04104397c432..0230ad19533e 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -183,7 +183,8 @@ static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
 	if (tr->func.ftrace_managed)
 		ret = unregister_ftrace_direct(tr->fops, (long)old_addr, false);
 	else
-		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL);
+		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, BPF_MOD_NOP,
+					 old_addr, NULL);
 
 	return ret;
 }
@@ -200,7 +201,10 @@ static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_ad
 		else
 			ret = modify_ftrace_direct_nolock(tr->fops, (long)new_addr);
 	} else {
-		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr);
+		ret = bpf_arch_text_poke(ip,
+					 old_addr ? BPF_MOD_CALL : BPF_MOD_NOP,
+					 new_addr ? BPF_MOD_CALL : BPF_MOD_NOP,
+					 old_addr, new_addr);
 	}
 	return ret;
 }
@@ -225,7 +229,8 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
 			return ret;
 		ret = register_ftrace_direct(tr->fops, (long)new_addr);
 	} else {
-		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr);
+		ret = bpf_arch_text_poke(ip, BPF_MOD_NOP, BPF_MOD_CALL,
+					 NULL, new_addr);
 	}
 
 	return ret;
@@ -336,8 +341,9 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im)
 	 * call_rcu_tasks() is not necessary.
 	 */
 	if (im->ip_after_call) {
-		int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_JUMP,
-					     NULL, im->ip_epilogue);
+		int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_NOP,
+					     BPF_MOD_JUMP, NULL,
+					     im->ip_epilogue);
 		WARN_ON(err);
 		if (IS_ENABLED(CONFIG_TASKS_RCU))
 			call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
@@ -570,7 +576,8 @@ static int __bpf_trampoline_link_prog(struct bpf_tramp_link *link,
 		if (err)
 			return err;
 		tr->extension_prog = link->link.prog;
-		return bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL,
+		return bpf_arch_text_poke(tr->func.addr, BPF_MOD_NOP,
+					  BPF_MOD_JUMP, NULL,
 					  link->link.prog->bpf_func);
 	}
 	if (cnt >= BPF_MAX_TRAMP_LINKS)
@@ -618,6 +625,7 @@ static int __bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
 	if (kind == BPF_TRAMP_REPLACE) {
 		WARN_ON_ONCE(!tr->extension_prog);
 		err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP,
+					 BPF_MOD_NOP,
 					 tr->extension_prog->bpf_func, NULL);
 		tr->extension_prog = NULL;
 		guard(mutex)(&tgt_prog->aux->ext_mutex);
-- 
2.51.2

Implement the "jmp" mode for the bpf trampoline. For the ftrace_managed
case, we need only to set the FTRACE_OPS_FL_JMP on the tr->fops if "jmp"
is needed.

For the bpf poke case, we will check the origin poke type with the
"origin_flags", and current poke type with "tr->flags". The function
bpf_trampoline_update_fentry() is introduced to do the job.

The "jmp" mode will only be enabled with CONFIG_DYNAMIC_FTRACE_WITH_JMP
enabled and BPF_TRAMP_F_SHARE_IPMODIFY is not set. With
BPF_TRAMP_F_SHARE_IPMODIFY, we need to get the origin call ip from the
stack, so we can't use the "jmp" mode.

Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
---
v3:
- wrap the write to tr->fops->flags with CONFIG_DYNAMIC_FTRACE_WITH_JMP
- reset BPF_TRAMP_F_SKIP_FRAME when the second try of modify_fentry in
  bpf_trampoline_update()

v2:
- rename bpf_text_poke to bpf_trampoline_update_fentry
- remove the BPF_TRAMP_F_JMPED and check the current mode with the origin
  flags instead.
---
 kernel/bpf/trampoline.c | 75 +++++++++++++++++++++++++++++++----------
 1 file changed, 58 insertions(+), 17 deletions(-)

diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 0230ad19533e..976d89011b15 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -175,24 +175,42 @@ static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
 	return tr;
 }
 
-static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
+static int bpf_trampoline_update_fentry(struct bpf_trampoline *tr, u32 orig_flags,
+					void *old_addr, void *new_addr)
 {
+	enum bpf_text_poke_type new_t = BPF_MOD_CALL, old_t = BPF_MOD_CALL;
 	void *ip = tr->func.addr;
+
+	if (!new_addr)
+		new_t = BPF_MOD_NOP;
+	else if (bpf_trampoline_use_jmp(tr->flags))
+		new_t = BPF_MOD_JUMP;
+
+	if (!old_addr)
+		old_t = BPF_MOD_NOP;
+	else if (bpf_trampoline_use_jmp(orig_flags))
+		old_t = BPF_MOD_JUMP;
+
+	return bpf_arch_text_poke(ip, old_t, new_t, old_addr, new_addr);
+}
+
+static int unregister_fentry(struct bpf_trampoline *tr, u32 orig_flags,
+			     void *old_addr)
+{
 	int ret;
 
 	if (tr->func.ftrace_managed)
 		ret = unregister_ftrace_direct(tr->fops, (long)old_addr, false);
 	else
-		ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, BPF_MOD_NOP,
-					 old_addr, NULL);
+		ret = bpf_trampoline_update_fentry(tr, orig_flags, old_addr, NULL);
 
 	return ret;
 }
 
-static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr,
+static int modify_fentry(struct bpf_trampoline *tr, u32 orig_flags,
+			 void *old_addr, void *new_addr,
 			 bool lock_direct_mutex)
 {
-	void *ip = tr->func.addr;
 	int ret;
 
 	if (tr->func.ftrace_managed) {
@@ -201,10 +219,8 @@ static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_ad
 		else
 			ret = modify_ftrace_direct_nolock(tr->fops, (long)new_addr);
 	} else {
-		ret = bpf_arch_text_poke(ip,
-					 old_addr ? BPF_MOD_CALL : BPF_MOD_NOP,
-					 new_addr ? BPF_MOD_CALL : BPF_MOD_NOP,
-					 old_addr, new_addr);
+		ret = bpf_trampoline_update_fentry(tr, orig_flags, old_addr,
+						   new_addr);
 	}
 	return ret;
 }
@@ -229,8 +245,7 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
 			return ret;
 		ret = register_ftrace_direct(tr->fops, (long)new_addr);
 	} else {
-		ret = bpf_arch_text_poke(ip, BPF_MOD_NOP, BPF_MOD_CALL,
-					 NULL, new_addr);
+		ret = bpf_trampoline_update_fentry(tr, 0, NULL, new_addr);
 	}
 
 	return ret;
@@ -416,7 +431,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
 		return PTR_ERR(tlinks);
 
 	if (total == 0) {
-		err = unregister_fentry(tr, tr->cur_image->image);
+		err = unregister_fentry(tr, orig_flags, tr->cur_image->image);
 		bpf_tramp_image_put(tr->cur_image);
 		tr->cur_image = NULL;
 		goto out;
@@ -440,9 +455,20 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 again:
-	if ((tr->flags & BPF_TRAMP_F_SHARE_IPMODIFY) &&
-	    (tr->flags & BPF_TRAMP_F_CALL_ORIG))
-		tr->flags |= BPF_TRAMP_F_ORIG_STACK;
+	if (tr->flags & BPF_TRAMP_F_CALL_ORIG) {
+		if (tr->flags & BPF_TRAMP_F_SHARE_IPMODIFY) {
+			/* The BPF_TRAMP_F_SKIP_FRAME can be cleared in the
+			 * first try, reset it in the second try.
+			 */
+			tr->flags |= BPF_TRAMP_F_ORIG_STACK | BPF_TRAMP_F_SKIP_FRAME;
+		} else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_JMP)) {
+			/* Use "jmp" instead of "call" for the trampoline
+			 * in the origin call case, and we don't need to
+			 * skip the frame.
+			 */
+			tr->flags &= ~BPF_TRAMP_F_SKIP_FRAME;
+		}
+	}
 #endif
 
 	size = arch_bpf_trampoline_size(&tr->func.model, tr->flags,
@@ -473,10 +499,18 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
 	if (err)
 		goto out_free;
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP
+	if (bpf_trampoline_use_jmp(tr->flags))
+		tr->fops->flags |= FTRACE_OPS_FL_JMP;
+	else
+		tr->fops->flags &= ~FTRACE_OPS_FL_JMP;
+#endif
+
 	WARN_ON(tr->cur_image && total == 0);
 	if (tr->cur_image)
 		/* progs already running at this address */
-		err = modify_fentry(tr, tr->cur_image->image, im->image, lock_direct_mutex);
+		err = modify_fentry(tr, orig_flags, tr->cur_image->image,
+				    im->image, lock_direct_mutex);
 	else
 		/* first time registering */
 		err = register_fentry(tr, im->image);
@@ -499,8 +533,15 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
 	tr->cur_image = im;
 out:
 	/* If any error happens, restore previous flags */
-	if (err)
+	if (err) {
 		tr->flags = orig_flags;
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP
+		if (bpf_trampoline_use_jmp(tr->flags))
+			tr->fops->flags |= FTRACE_OPS_FL_JMP;
+		else
+			tr->fops->flags &= ~FTRACE_OPS_FL_JMP;
+#endif
+	}
 	kfree(tlinks);
 	return err;
 
-- 
2.51.2