x86/optprobe: Fix OPTPROBE vs UACCESS

While looking at an objtool UACCESS warning, it suddenly occurred to me
that it is entirely possible to have an OPTPROBE right in the middle of
an UACCESS region.

In this case we must of course clear FLAGS.AC while running the KPROBE.
Luckily the trampoline already saves/restores [ER]FLAGS, so all we need
to do is inject a CLAC. Unfortunately we cannot use ALTERNATIVE() in the
trampoline text, so we have to frob that manually.

Fixes: ca0bbc70f147 ("sched/x86_64: Don't save flags on context switch")
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Masami Hiramatsu <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

Author: Peter Zijlstra

arch/x86/include/asm/kprobes.h

@@ -36,6 +36,7 @@ typedef u8 kprobe_opcode_t;
 
 /* optinsn template addresses */
 extern __visible kprobe_opcode_t optprobe_template_entry[];
+extern __visible kprobe_opcode_t optprobe_template_clac[];
 extern __visible kprobe_opcode_t optprobe_template_val[];
 extern __visible kprobe_opcode_t optprobe_template_call[];
 extern __visible kprobe_opcode_t optprobe_template_end[];

arch/x86/kernel/kprobes/opt.c

@@ -71,6 +71,21 @@ unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)
 	return (unsigned long)buf;
 }
 
+static void synthesize_clac(kprobe_opcode_t *addr)
+{
+	/*
+	 * Can't be static_cpu_has() due to how objtool treats this feature bit.
+	 * This isn't a fast path anyway.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_SMAP))
+		return;
+
+	/* Replace the NOP3 with CLAC */
+	addr[0] = 0x0f;
+	addr[1] = 0x01;
+	addr[2] = 0xca;
+}
+
 /* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */
 static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val)
 {
@@ -92,6 +107,9 @@ asm (
 			/* We don't bother saving the ss register */
 			"	pushq %rsp\n"
 			"	pushfq\n"
+			".global optprobe_template_clac\n"
+			"optprobe_template_clac:\n"
+			ASM_NOP3
 			SAVE_REGS_STRING
 			"	movq %rsp, %rsi\n"
 			".global optprobe_template_val\n"
@@ -111,6 +129,9 @@ asm (
 #else /* CONFIG_X86_32 */
 			"	pushl %esp\n"
 			"	pushfl\n"
+			".global optprobe_template_clac\n"
+			"optprobe_template_clac:\n"
+			ASM_NOP3
 			SAVE_REGS_STRING
 			"	movl %esp, %edx\n"
 			".global optprobe_template_val\n"
@@ -134,6 +155,8 @@ asm (
 void optprobe_template_func(void);
 STACK_FRAME_NON_STANDARD(optprobe_template_func);
 
+#define TMPL_CLAC_IDX \
+	((long)optprobe_template_clac - (long)optprobe_template_entry)
 #define TMPL_MOVE_IDX \
 	((long)optprobe_template_val - (long)optprobe_template_entry)
 #define TMPL_CALL_IDX \
@@ -389,6 +412,8 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
 	op->optinsn.size = ret;
 	len = TMPL_END_IDX + op->optinsn.size;
 
+	synthesize_clac(buf + TMPL_CLAC_IDX);
+
 	/* Set probe information */
 	synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op);