Given that the entry_*.S changes for this functionality are somewhat
tricky, make sure the paths are tested every boot, instead of on the
rare occasion when we trip an INT3 while rewriting text.
Getting the INT3 frame setup even slightly wrong will make this come
unstuck something spectacular.
Requested-by: Andy Lutomirski <luto@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
arch/x86/kernel/alternative.c | 81 ++++++++++++++++++++++++++++++++++++++++---
1 file changed, 77 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 4db9c0d29bc1..2b853c2ab894 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -613,11 +613,83 @@ extern struct paravirt_patch_site __start_parainstructions[],
__stop_parainstructions[];
#endif /* CONFIG_PARAVIRT */
+/*
+ * Self-test for the INT3 based CALL emulation code.
+ *
+ * This exercises int3_emulate_call() to make sure INT3 pt_regs are set up
+ * properly and that there is a stack gap between the INT3 frame and the
+ * previous context. Without this gap doing a virtual PUSH on the interrupted
+ * stack would corrupt the INT3 IRET frame.
+ *
+ * See entry_{32,64}.S for more details.
+ */
+static void __init int3_magic(unsigned int *ptr)
+{
+ *ptr = 1;
+}
+
+extern __initdata unsigned long int3_selftest_ip; /* defined in asm below */
+
+static int __init
+int3_exception_notify(struct notifier_block *self, unsigned long val, void *data)
+{
+ struct die_args *args = data;
+ struct pt_regs *regs = args->regs;
+
+ if (!regs || user_mode(regs))
+ return NOTIFY_DONE;
+
+ if (val != DIE_INT3)
+ return NOTIFY_DONE;
+
+ if (regs->ip - INT3_INSN_SIZE != int3_selftest_ip)
+ return NOTIFY_DONE;
+
+ int3_emulate_call(regs, (unsigned long)&int3_magic);
+ return NOTIFY_STOP;
+}
+
+static void __init int3_selftest(void)
+{
+ static __initdata struct notifier_block int3_exception_nb = {
+ .notifier_call = int3_exception_notify,
+ .priority = INT_MAX-1, /* last */
+ };
+ unsigned int val = 0;
+
+ BUG_ON(register_die_notifier(&int3_exception_nb));
+
+ /*
+ * Basically: int3_magic(&val); but really complicated :-)
+ *
+ * Stick the address of the INT3 instruction into int3_selftest_ip,
+ * then trigger the INT3, padded with NOPs to match a CALL instruction
+ * length.
+ */
+ asm volatile ("1: int3; nop; nop; nop; nop\n\t"
+ ".pushsection .init.data,\"aw\"\n\t"
+ ".align " __ASM_SEL(4, 8) "\n\t"
+ ".type int3_selftest_ip, @object\n\t"
+ ".size int3_selftest_ip, " __ASM_SEL(4, 8) "\n\t"
+ "int3_selftest_ip:\n\t"
+ __ASM_SEL(.long, .quad) " 1b\n\t"
+ ".popsection\n\t"
+ : : __ASM_SEL_RAW(a, D) (&val) : "memory");
+
+ BUG_ON(val != 1);
+
+ unregister_die_notifier(&int3_exception_nb);
+}
+
void __init alternative_instructions(void)
{
- /* The patching is not fully atomic, so try to avoid local interruptions
- that might execute the to be patched code.
- Other CPUs are not running. */
+ int3_selftest();
+
+ /*
+ * The patching is not fully atomic, so try to avoid local
+ * interruptions that might execute the to be patched code.
+ * Other CPUs are not running.
+ */
stop_nmi();
/*
@@ -642,10 +714,11 @@ void __init alternative_instructions(void)
_text, _etext);
}
- if (!uniproc_patched || num_possible_cpus() == 1)
+ if (!uniproc_patched || num_possible_cpus() == 1) {
free_init_pages("SMP alternatives",
(unsigned long)__smp_locks,
(unsigned long)__smp_locks_end);
+ }
#endif
apply_paravirt(__parainstructions, __parainstructions_end);
