bpf,x86: add fsession support for x86_64

Add BPF_TRACE_FSESSION supporting to x86_64, including:

1. clear the return value in the stack before fentry to make the fentry
   of the fsession can only get 0 with bpf_get_func_ret().

2. clear all the session cookies' value in the stack.

2. store the index of the cookie to ctx[-1] before the calling to fsession

3. store the "is_return" flag to ctx[-1] before the calling to fexit of
   the fsession.

Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
Co-developed-by: Leon Hwang <leon.hwang@linux.dev>
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
Link: https://lore.kernel.org/r/20260124062008.8657-8-dongml2@chinatelecom.cn
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

arch/x86/net/bpf_jit_comp.c

@@ -3094,13 +3094,19 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
 
 static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
 		      struct bpf_tramp_links *tl, int stack_size,
-		      int run_ctx_off, bool save_ret,
+		      int run_ctx_off, int func_meta_off, bool save_ret,
-		      void *image, void *rw_image)
+		      void *image, void *rw_image, u64 func_meta,
+		      int cookie_off)
 {
-	int i;
+	int i, cur_cookie = (cookie_off - stack_size) / 8;
 	u8 *prog = *pprog;
 
 	for (i = 0; i < tl->nr_links; i++) {
+		if (tl->links[i]->link.prog->call_session_cookie) {
+			emit_store_stack_imm64(&prog, BPF_REG_0, -func_meta_off,
+				func_meta | (cur_cookie << BPF_TRAMP_COOKIE_INDEX_SHIFT));
+			cur_cookie--;
+		}
 		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size,
 				    run_ctx_off, save_ret, image, rw_image))
 			return -EINVAL;
@@ -3218,12 +3224,14 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 					 void *func_addr)
 {
 	int i, ret, nr_regs = m->nr_args, stack_size = 0;
-	int regs_off, nregs_off, ip_off, run_ctx_off, arg_stack_off, rbx_off;
+	int regs_off, func_meta_off, ip_off, run_ctx_off, arg_stack_off, rbx_off;
 	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
 	void *orig_call = func_addr;
+	int cookie_off, cookie_cnt;
 	u8 **branches = NULL;
+	u64 func_meta;
 	u8 *prog;
 	bool save_ret;
 
@@ -3259,7 +3267,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	 *                 [ ...             ]
 	 * RBP - regs_off  [ reg_arg1        ]  program's ctx pointer
 	 *
-	 * RBP - nregs_off [ regs count	     ]  always
+	 * RBP - func_meta_off [ regs count, etc ]  always
 	 *
 	 * RBP - ip_off    [ traced function ]  BPF_TRAMP_F_IP_ARG flag
 	 *
@@ -3282,15 +3290,20 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	stack_size += nr_regs * 8;
 	regs_off = stack_size;
 
-	/* regs count  */
+	/* function matedata, such as regs count  */
 	stack_size += 8;
-	nregs_off = stack_size;
+	func_meta_off = stack_size;
 
 	if (flags & BPF_TRAMP_F_IP_ARG)
 		stack_size += 8; /* room for IP address argument */
 
 	ip_off = stack_size;
 
+	cookie_cnt = bpf_fsession_cookie_cnt(tlinks);
+	/* room for session cookies */
+	stack_size += cookie_cnt * 8;
+	cookie_off = stack_size;
+
 	stack_size += 8;
 	rbx_off = stack_size;
 
@@ -3358,8 +3371,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	/* mov QWORD PTR [rbp - rbx_off], rbx */
 	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_6, -rbx_off);
 
+	func_meta = nr_regs;
 	/* Store number of argument registers of the traced function */
-	emit_store_stack_imm64(&prog, BPF_REG_0, -nregs_off, nr_regs);
+	emit_store_stack_imm64(&prog, BPF_REG_0, -func_meta_off, func_meta);
 
 	if (flags & BPF_TRAMP_F_IP_ARG) {
 		/* Store IP address of the traced function */
@@ -3378,9 +3392,18 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		}
 	}
 
+	if (bpf_fsession_cnt(tlinks)) {
+		/* clear all the session cookies' value */
+		for (int i = 0; i < cookie_cnt; i++)
+			emit_store_stack_imm64(&prog, BPF_REG_0, -cookie_off + 8 * i, 0);
+		/* clear the return value to make sure fentry always get 0 */
+		emit_store_stack_imm64(&prog, BPF_REG_0, -8, 0);
+	}
+
 	if (fentry->nr_links) {
-		if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off,
+		if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off, func_meta_off,
-			       flags & BPF_TRAMP_F_RET_FENTRY_RET, image, rw_image))
+			       flags & BPF_TRAMP_F_RET_FENTRY_RET, image, rw_image,
+			       func_meta, cookie_off))
 			return -EINVAL;
 	}
 
@@ -3440,9 +3463,14 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		}
 	}
 
+	/* set the "is_return" flag for fsession */
+	func_meta |= (1ULL << BPF_TRAMP_IS_RETURN_SHIFT);
+	if (bpf_fsession_cnt(tlinks))
+		emit_store_stack_imm64(&prog, BPF_REG_0, -func_meta_off, func_meta);
+
 	if (fexit->nr_links) {
-		if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off,
+		if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, func_meta_off,
-			       false, image, rw_image)) {
+			       false, image, rw_image, func_meta, cookie_off)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}