x86: Fix code patching for paravirt-alternatives on 486

As reported in <http://bugs.debian.org/511703> and
<http://bugs.debian.org/515982>, kernels with paravirt-alternatives
enabled crash in text_poke_early() on at least some 486-class
processors.

The problem is that text_poke_early() itself uses inline functions
affected by paravirt-alternatives and so will modify instructions that
have already been prefetched.  Pentium and later processors will
invalidate the prefetched instructions in this case, but 486-class
processors do not.

Change sync_core() to limit prefetching on 486-class (and 386-class)
processors, and move the call to sync_core() above the call to the
modifiable local_irq_restore().

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
LKML-Reference: <1252547631.3423.134.camel@localhost>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

2 files changed, 14 insertions, 4 deletions

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c7768269b1cf..2db56c57a281 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -703,13 +703,23 @@ static inline void cpu_relax(void)
         rep_nop();
 }
 
-/* Stop speculative execution: */
+/* Stop speculative execution and prefetching of modified code. */
 static inline void sync_core(void)
 {
         int tmp;
 
-        asm volatile("cpuid" : "=a" (tmp) : "0" (1)
-                     : "ebx", "ecx", "edx", "memory");
+#if defined(CONFIG_M386) || defined(CONFIG_M486)
+        if (boot_cpu_data.x86 < 5)
+                /* There is no speculative execution.
+                 * jmp is a barrier to prefetching. */
+                asm volatile("jmp 1f\n1:\n" ::: "memory");
+        else
+#endif
+                /* cpuid is a barrier to speculative execution.
+                 * Prefetched instructions are automatically
+                 * invalidated when modified. */
+                asm volatile("cpuid" : "=a" (tmp) : "0" (1)
+                             : "ebx", "ecx", "edx", "memory");
 }
 
 static inline void __monitor(const void *eax, unsigned long ecx,
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index f57658702571..b8ebd0b689b1 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -490,8 +490,8 @@ void *text_poke_early(void *addr, const void *opcode, size_t len)
         unsigned long flags;
         local_irq_save(flags);
         memcpy(addr, opcode, len);
-        local_irq_restore(flags);
         sync_core();
+        local_irq_restore(flags);
         /* Could also do a CLFLUSH here to speed up CPU recovery; but
            that causes hangs on some VIA CPUs. */
         return addr;