i386: Make patching more robust, fix paravirt issue

Commit 19d36ccdc34f5ed444f8a6af0cbfdb6790eb1177 "x86: Fix alternatives
and kprobes to remap write-protected kernel text" uses code which is
being patched for patching.

In particular, paravirt_ops does patching in two stages: first it
calls paravirt_ops.patch, then it fills any remaining instructions
with nop_out().  nop_out calls text_poke() which calls
lookup_address() which calls pgd_val() (aka paravirt_ops.pgd_val):
that call site is one of the places we patch.

If we always do patching as one single call to text_poke(), we only
need make sure we're not patching the memcpy in text_poke itself.
This means the prototype to paravirt_ops.patch needs to change, to
marshal the new code into a buffer rather than patching in place as it
does now.  It also means all patching goes through text_poke(), which
is known to be safe (apply_alternatives is also changed to make a
single patch).

AK: fix compilation on x86-64 (bad rusty!)
AK: fix boot on x86-64 (sigh)
AK: merged with other patches

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 21 insertions, 12 deletions

diff --git a/arch/i386/kernel/alternative.c b/arch/i386/kernel/alternative.c
index c85598acb8fd..27a6b0c9a7cc 100644
--- a/arch/i386/kernel/alternative.c
+++ b/arch/i386/kernel/alternative.c
@@ -11,6 +11,8 @@
 #include <asm/mce.h>
 #include <asm/nmi.h>
 
+#define MAX_PATCH_LEN (255-1)
+
 #ifdef CONFIG_HOTPLUG_CPU
 static int smp_alt_once;
 
@@ -148,7 +150,8 @@ static unsigned char** find_nop_table(void)
 
 #endif /* CONFIG_X86_64 */
 
-static void nop_out(void *insns, unsigned int len)
+/* Use this to add nops to a buffer, then text_poke the whole buffer. */
+static void add_nops(void *insns, unsigned int len)
 {
         unsigned char **noptable = find_nop_table();
 
@@ -156,7 +159,7 @@ static void nop_out(void *insns, unsigned int len)
                 unsigned int noplen = len;
                 if (noplen > ASM_NOP_MAX)
                         noplen = ASM_NOP_MAX;
-                text_poke(insns, noptable[noplen], noplen);
+                memcpy(insns, noptable[noplen], noplen);
                 insns += noplen;
                 len -= noplen;
         }
@@ -174,15 +177,15 @@ extern u8 *__smp_locks[], *__smp_locks_end[];
 void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
         struct alt_instr *a;
-        u8 *instr;
-        int diff;
+        char insnbuf[MAX_PATCH_LEN];
 
         DPRINTK("%s: alt table %p -> %p\n", __FUNCTION__, start, end);
         for (a = start; a < end; a++) {
+                u8 *instr = a->instr;
                 BUG_ON(a->replacementlen > a->instrlen);
+                BUG_ON(a->instrlen > sizeof(insnbuf));
                 if (!boot_cpu_has(a->cpuid))
                         continue;
-                instr = a->instr;
 #ifdef CONFIG_X86_64
                 /* vsyscall code is not mapped yet. resolve it manually. */
                 if (instr >= (u8 *)VSYSCALL_START && instr < (u8*)VSYSCALL_END) {
@@ -191,9 +194,10 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
                                 __FUNCTION__, a->instr, instr);
                 }
 #endif
-                memcpy(instr, a->replacement, a->replacementlen);
-                diff = a->instrlen - a->replacementlen;
-                nop_out(instr + a->replacementlen, diff);
+                memcpy(insnbuf, a->replacement, a->replacementlen);
+                add_nops(insnbuf + a->replacementlen,
+                         a->instrlen - a->replacementlen);
+                text_poke(instr, insnbuf, a->instrlen);
         }
 }
 
@@ -215,16 +219,18 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
 static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end)
 {
         u8 **ptr;
+        char insn[1];
 
         if (noreplace_smp)
                 return;
 
+        add_nops(insn, 1);
         for (ptr = start; ptr < end; ptr++) {
                 if (*ptr < text)
                         continue;
                 if (*ptr > text_end)
                         continue;
-                nop_out(*ptr, 1);
+                text_poke(*ptr, insn, 1);
         };
 }
 
@@ -351,6 +357,7 @@ void apply_paravirt(struct paravirt_patch_site *start,
                     struct paravirt_patch_site *end)
 {
         struct paravirt_patch_site *p;
+        char insnbuf[MAX_PATCH_LEN];
 
         if (noreplace_paravirt)
                 return;
@@ -358,13 +365,15 @@ void apply_paravirt(struct paravirt_patch_site *start,
         for (p = start; p < end; p++) {
                 unsigned int used;
 
-                used = paravirt_ops.patch(p->instrtype, p->clobbers, p->instr,
-                                          p->len);
+                BUG_ON(p->len > MAX_PATCH_LEN);
+                used = paravirt_ops.patch(p->instrtype, p->clobbers, insnbuf,
+                                          (unsigned long)p->instr, p->len);
 
                 BUG_ON(used > p->len);
 
                 /* Pad the rest with nops */
-                nop_out(p->instr + used, p->len - used);
+                add_nops(insnbuf + used, p->len - used);
+                text_poke(p->instr, insnbuf, p->len);
         }
 }
 extern struct paravirt_patch_site __start_parainstructions[],