x86/retpoline,kprobes: Skip optprobe check for indirect jumps with retpolines and IBT

The kprobes optimization check can_optimize() calls
insn_is_indirect_jump() to detect indirect jump instructions in
a target function. If any is found, creating an optprobe is disallowed
in the function because the jump could be from a jump table and could
potentially land in the middle of the target optprobe.

With retpolines, insn_is_indirect_jump() additionally looks for calls to
indirect thunks which the compiler potentially used to replace original
jumps. This extra check is however unnecessary because jump tables are
disabled when the kernel is built with retpolines. The same is currently
the case with IBT.

Based on this observation, remove the logic to look for calls to
indirect thunks and skip the check for indirect jumps altogether if the
kernel is built with retpolines or IBT. Remove subsequently the symbols
__indirect_thunk_start and __indirect_thunk_end which are no longer
needed.

Dropping this logic indirectly fixes a problem where the range
[__indirect_thunk_start, __indirect_thunk_end] wrongly included also the
return thunk. It caused that machines which used the return thunk as
a mitigation and didn't have it patched by any alternative ended up not
being able to use optprobes in any regular function.

Fixes: 0b53c374b9ef ("x86/retpoline: Use -mfunction-return")
Suggested-by: Peter Zijlstra (Intel) <[e-mail]>
Suggested-by: Masami Hiramatsu (Google) <[e-mail]>
Signed-off-by: Petr Pavlu <[e-mail]>
Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Signed-off-by: Borislav Petkov (AMD) <[e-mail]>
Acked-by: Masami Hiramatsu (Google) <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

arch/x86/include/asm/nospec-branch.h

···
 	SPEC_STORE_BYPASS_SECCOMP,
 };
 
-extern char __indirect_thunk_start[];
-extern char __indirect_thunk_end[];
-
 static __always_inline
 void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
 {

arch/x86/kernel/kprobes/opt.c

···
 }
 
 /* Check whether insn is indirect jump */
-static int __insn_is_indirect_jump(struct insn *insn)
+static int insn_is_indirect_jump(struct insn *insn)
 {
 	return ((insn->opcode.bytes[0] == 0xff &&
 		(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
···
 	target = (unsigned long)insn->next_byte + insn->immediate.value;
 
 	return (start <= target && target <= start + len);
-}
-
-static int insn_is_indirect_jump(struct insn *insn)
-{
-	int ret = __insn_is_indirect_jump(insn);
-
-#ifdef CONFIG_RETPOLINE
-	/*
-	 * Jump to x86_indirect_thunk_* is treated as an indirect jump.
-	 * Note that even with CONFIG_RETPOLINE=y, the kernel compiled with
-	 * older gcc may use indirect jump. So we add this check instead of
-	 * replace indirect-jump check.
-	 */
-	if (!ret)
-		ret = insn_jump_into_range(insn,
-				(unsigned long)__indirect_thunk_start,
-				(unsigned long)__indirect_thunk_end -
-				(unsigned long)__indirect_thunk_start);
-#endif
-	return ret;
 }
 
 /* Decode whole function to ensure any instructions don't jump into target */
···
 		/* Recover address */
 		insn.kaddr = (void *)addr;
 		insn.next_byte = (void *)(addr + insn.length);
-		/* Check any instructions don't jump into target */
-		if (insn_is_indirect_jump(&insn) ||
-		    insn_jump_into_range(&insn, paddr + INT3_INSN_SIZE,
+		/*
+		 * Check any instructions don't jump into target, indirectly or
+		 * directly.
+		 *
+		 * The indirect case is present to handle a code with jump
+		 * tables. When the kernel uses retpolines, the check should in
+		 * theory additionally look for jumps to indirect thunks.
+		 * However, the kernel built with retpolines or IBT has jump
+		 * tables disabled so the check can be skipped altogether.
+		 */
+		if (!IS_ENABLED(CONFIG_RETPOLINE) &&
+		    !IS_ENABLED(CONFIG_X86_KERNEL_IBT) &&
+		    insn_is_indirect_jump(&insn))
+			return 0;
+		if (insn_jump_into_range(&insn, paddr + INT3_INSN_SIZE,
 					 DISP32_SIZE))
 			return 0;
 		addr += insn.length;

arch/x86/kernel/vmlinux.lds.S

···
 		KPROBES_TEXT
 		SOFTIRQENTRY_TEXT
 #ifdef CONFIG_RETPOLINE
-		__indirect_thunk_start = .;
 		*(.text..__x86.indirect_thunk)
 		*(.text..__x86.return_thunk)
-		__indirect_thunk_end = .;
 #endif
 		STATIC_CALL_TEXT
 

tools/perf/util/thread-stack.c

···
 
 static bool is_x86_retpoline(const char *name)
 {
-	const char *p = strstr(name, "__x86_indirect_thunk_");
-
-	return p == name || !strcmp(name, "__indirect_thunk_start");
+	return strstr(name, "__x86_indirect_thunk_") == name;
 }
 
 /*