x86/ibt,bpf: Add ENDBR instructions to prologue and trampoline

With IBT enabled builds we need ENDBR instructions at indirect jump
target sites, since we start execution of the JIT'ed code through an
indirect jump, the very first instruction needs to be ENDBR.

Similarly, since eBPF tail-calls use indirect branches, their landing
site needs to be an ENDBR too.

The trampolines need similar adjustment.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Fixed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/20220308154318.464998838@infradead.org

arch/x86/net/bpf_jit_comp.c

@@ -46,6 +46,12 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 #define EMIT4_off32(b1, b2, b3, b4, off) \
 	do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
 
+#ifdef CONFIG_X86_KERNEL_IBT
+#define EMIT_ENDBR()	EMIT(gen_endbr(), 4)
+#else
+#define EMIT_ENDBR()
+#endif
+
 static bool is_imm8(int value)
 {
 	return value <= 127 && value >= -128;
@@ -241,7 +247,7 @@ struct jit_context {
 /* Number of bytes emit_patch() needs to generate instructions */
 #define X86_PATCH_SIZE		5
 /* Number of bytes that will be skipped on tailcall */
-#define X86_TAIL_CALL_OFFSET	11
+#define X86_TAIL_CALL_OFFSET	(11 + ENDBR_INSN_SIZE)
 
 static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
 {
@@ -286,6 +292,7 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
 	/* BPF trampoline can be made to work without these nops,
 	 * but let's waste 5 bytes for now and optimize later
 	 */
+	EMIT_ENDBR();
 	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
 	prog += X86_PATCH_SIZE;
 	if (!ebpf_from_cbpf) {
@@ -296,6 +303,10 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
 	}
 	EMIT1(0x55);             /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+
+	/* X86_TAIL_CALL_OFFSET is here */
+	EMIT_ENDBR();
+
 	/* sub rsp, rounded_stack_depth */
 	if (stack_depth)
 		EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
@@ -384,6 +395,13 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		/* BPF poking in modules is not supported */
 		return -EINVAL;
 
+	/*
+	 * See emit_prologue(), for IBT builds the trampoline hook is preceded
+	 * with an ENDBR instruction.
+	 */
+	if (is_endbr(*(u32 *)ip))
+		ip += ENDBR_INSN_SIZE;
+
 	return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true);
 }
 
@@ -2024,14 +2042,18 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 
 	ip_off = stack_size;
 
-	if (flags & BPF_TRAMP_F_SKIP_FRAME)
+	if (flags & BPF_TRAMP_F_SKIP_FRAME) {
 		/* skip patched call instruction and point orig_call to actual
 		 * body of the kernel function.
 		 */
+		if (is_endbr(*(u32 *)orig_call))
+			orig_call += ENDBR_INSN_SIZE;
 		orig_call += X86_PATCH_SIZE;
+	}
 
 	prog = image;
 
+	EMIT_ENDBR();
 	EMIT1(0x55);		 /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
 	EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */