bpf, x86: Emit ENDBR for indirect jump targets

On CPUs that support CET/IBT, the indirect jump selftest triggers
a kernel panic because the indirect jump targets lack ENDBR
instructions.

To fix it, emit an ENDBR instruction to each indirect jump target. Since
the ENDBR instruction shifts the position of original jited instructions,
fix the instruction address calculation wherever the addresses are used.

For reference, below is a sample panic log.

 Missing ENDBR: bpf_prog_2e5f1c71c13ac3e0_big_jump_table+0x97/0xe1
 ------------[ cut here ]------------
 kernel BUG at arch/x86/kernel/cet.c:133!
 Oops: invalid opcode: 0000 [#1] SMP NOPTI

 ...

  ? 0xffffffffc00fb258
  ? bpf_prog_2e5f1c71c13ac3e0_big_jump_table+0x97/0xe1
  bpf_prog_test_run_syscall+0x110/0x2f0
  ? fdget+0xba/0xe0
  __sys_bpf+0xe4b/0x2590
  ? __kmalloc_node_track_caller_noprof+0x1c7/0x680
  ? bpf_prog_test_run_syscall+0x215/0x2f0
  __x64_sys_bpf+0x21/0x30
  do_syscall_64+0x85/0x620
  ? bpf_prog_test_run_syscall+0x1e2/0x2f0

Fixes: 493d9e0 ("bpf, x86: add support for indirect jumps")
Reviewed-by: Anton Protopopov <a.s.protopopov@gmail.com> # v8
Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com> # v12
Acked-by: Leon Hwang <leon.hwang@linux.dev>
Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Link: https://lore.kernel.org/r/20260416064341.151802-5-xukuohai@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Author: Xu Kuohai

arch/x86/net/bpf_jit_comp.c

@@ -58,8 +58,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 #define EMIT_ENDBR()		EMIT(gen_endbr(), 4)
 #define EMIT_ENDBR_POISON()	EMIT(gen_endbr_poison(), 4)
 #else
-#define EMIT_ENDBR()
-#define EMIT_ENDBR_POISON()
+#define EMIT_ENDBR()		do { } while (0)
+#define EMIT_ENDBR_POISON()	do { } while (0)
 #endif
 
 static bool is_imm8(int value)
@@ -1649,8 +1649,8 @@ static int emit_spectre_bhb_barrier(u8 **pprog, u8 *ip,
 	return 0;
 }
 
-static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image,
-		  int oldproglen, struct jit_context *ctx, bool jmp_padding)
+static int do_jit(struct bpf_verifier_env *env, struct bpf_prog *bpf_prog, int *addrs, u8 *image,
+		  u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding)
 {
 	bool tail_call_reachable = bpf_prog->aux->tail_call_reachable;
 	struct bpf_insn *insn = bpf_prog->insnsi;
@@ -1663,7 +1663,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 	void __percpu *priv_stack_ptr;
 	int i, excnt = 0;
 	int ilen, proglen = 0;
-	u8 *prog = temp;
+	u8 *ip, *prog = temp;
 	u32 stack_depth;
 	int err;
 
@@ -1734,6 +1734,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 				dst_reg = X86_REG_R9;
 		}
 
+		if (bpf_insn_is_indirect_target(env, bpf_prog, i - 1))
+			EMIT_ENDBR();
+
+		ip = image + addrs[i - 1] + (prog - temp);
+
 		switch (insn->code) {
 			/* ALU */
 		case BPF_ALU | BPF_ADD | BPF_X:
@@ -2440,8 +2445,6 @@ st:			if (is_imm8(insn->off))
 
 			/* call */
 		case BPF_JMP | BPF_CALL: {
-			u8 *ip = image + addrs[i - 1];
-
 			func = (u8 *) __bpf_call_base + imm32;
 			if (src_reg == BPF_PSEUDO_CALL && tail_call_reachable) {
 				LOAD_TAIL_CALL_CNT_PTR(stack_depth);
@@ -2465,7 +2468,8 @@ st:			if (is_imm8(insn->off))
 			if (imm32)
 				emit_bpf_tail_call_direct(bpf_prog,
 							  &bpf_prog->aux->poke_tab[imm32 - 1],
-							  &prog, image + addrs[i - 1],
+							  &prog,
+							  ip,
 							  callee_regs_used,
 							  stack_depth,
 							  ctx);
@@ -2474,7 +2478,7 @@ st:			if (is_imm8(insn->off))
 							    &prog,
 							    callee_regs_used,
 							    stack_depth,
-							    image + addrs[i - 1],
+							    ip,
 							    ctx);
 			break;
 
@@ -2639,7 +2643,7 @@ st:			if (is_imm8(insn->off))
 			break;
 
 		case BPF_JMP | BPF_JA | BPF_X:
-			emit_indirect_jump(&prog, insn->dst_reg, image + addrs[i - 1]);
+			emit_indirect_jump(&prog, insn->dst_reg, ip);
 			break;
 		case BPF_JMP | BPF_JA:
 		case BPF_JMP32 | BPF_JA:
@@ -2729,8 +2733,6 @@ st:			if (is_imm8(insn->off))
 			ctx->cleanup_addr = proglen;
 			if (bpf_prog_was_classic(bpf_prog) &&
 			    !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN)) {
-				u8 *ip = image + addrs[i - 1];
-
 				if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog))
 					return -EINVAL;
 			}
@@ -3791,7 +3793,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr
 	for (pass = 0; pass < MAX_PASSES || image; pass++) {
 		if (!padding && pass >= PADDING_PASSES)
 			padding = true;
-		proglen = do_jit(prog, addrs, image, rw_image, oldproglen, &ctx, padding);
+		proglen = do_jit(env, prog, addrs, image, rw_image, oldproglen, &ctx, padding);
 		if (proglen <= 0) {
 out_image:
 			image = NULL;