#define MAX_PATCH_LEN (255-1)
-#ifdef CONFIG_HOTPLUG_CPU
-static int smp_alt_once;
-
-static int __init bootonly(char *str)
-{
- smp_alt_once = 1;
- return 1;
-}
-__setup("smp-alt-boot", bootonly);
-#else
-#define smp_alt_once 1
-#endif
-
static int __initdata_or_module debug_alternative;
static int __init debug_alt(char *str)
__setup("noreplace-paravirt", setup_noreplace_paravirt);
#endif
-#define DPRINTK(fmt, args...) if (debug_alternative) \
- printk(KERN_DEBUG fmt, args)
+#define DPRINTK(fmt, args...) \
+do { \
+ if (debug_alternative) \
+ printk(KERN_DEBUG "%s: " fmt "\n", __func__, ##args); \
+} while (0)
+
+#define DUMP_BYTES(buf, len, fmt, args...) \
+do { \
+ if (unlikely(debug_alternative)) { \
+ int j; \
+ \
+ if (!(len)) \
+ break; \
+ \
+ printk(KERN_DEBUG fmt, ##args); \
+ for (j = 0; j < (len) - 1; j++) \
+ printk(KERN_CONT "%02hhx ", buf[j]); \
+ printk(KERN_CONT "%02hhx\n", buf[j]); \
+ } \
+} while (0)
/*
* Each GENERIC_NOPX is of X bytes, and defined as an array of bytes
#endif
#ifdef P6_NOP1
-static const unsigned char __initconst_or_module p6nops[] =
+static const unsigned char p6nops[] =
{
P6_NOP1,
P6_NOP2,
ideal_nops = intel_nops;
#endif
}
-
+ break;
default:
#ifdef CONFIG_X86_64
ideal_nops = k8_nops;
extern s32 __smp_locks[], __smp_locks_end[];
void *text_poke_early(void *addr, const void *opcode, size_t len);
-/* Replace instructions with better alternatives for this CPU type.
- This runs before SMP is initialized to avoid SMP problems with
- self modifying code. This implies that asymmetric systems where
- APs have less capabilities than the boot processor are not handled.
- Tough. Make sure you disable such features by hand. */
+/*
+ * Are we looking at a near JMP with a 1 or 4-byte displacement.
+ */
+static inline bool is_jmp(const u8 opcode)
+{
+ return opcode == 0xeb || opcode == 0xe9;
+}
+
+static void __init_or_module
+recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf)
+{
+ u8 *next_rip, *tgt_rip;
+ s32 n_dspl, o_dspl;
+ int repl_len;
+
+ if (a->replacementlen != 5)
+ return;
+
+ o_dspl = *(s32 *)(insnbuf + 1);
+
+ /* next_rip of the replacement JMP */
+ next_rip = repl_insn + a->replacementlen;
+ /* target rip of the replacement JMP */
+ tgt_rip = next_rip + o_dspl;
+ n_dspl = tgt_rip - orig_insn;
+
+ DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl);
+
+ if (tgt_rip - orig_insn >= 0) {
+ if (n_dspl - 2 <= 127)
+ goto two_byte_jmp;
+ else
+ goto five_byte_jmp;
+ /* negative offset */
+ } else {
+ if (((n_dspl - 2) & 0xff) == (n_dspl - 2))
+ goto two_byte_jmp;
+ else
+ goto five_byte_jmp;
+ }
+
+two_byte_jmp:
+ n_dspl -= 2;
+
+ insnbuf[0] = 0xeb;
+ insnbuf[1] = (s8)n_dspl;
+ add_nops(insnbuf + 2, 3);
+
+ repl_len = 2;
+ goto done;
+
+five_byte_jmp:
+ n_dspl -= 5;
+
+ insnbuf[0] = 0xe9;
+ *(s32 *)&insnbuf[1] = n_dspl;
+
+ repl_len = 5;
+
+done:
+
+ DPRINTK("final displ: 0x%08x, JMP 0x%lx",
+ n_dspl, (unsigned long)orig_insn + n_dspl + repl_len);
+}
+
+static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr)
+{
+ add_nops(instr + (a->instrlen - a->padlen), a->padlen);
+
+ DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ",
+ instr, a->instrlen - a->padlen, a->padlen);
+}
+/*
+ * Replace instructions with better alternatives for this CPU type. This runs
+ * before SMP is initialized to avoid SMP problems with self modifying code.
+ * This implies that asymmetric systems where APs have less capabilities than
+ * the boot processor are not handled. Tough. Make sure you disable such
+ * features by hand.
+ */
void __init_or_module apply_alternatives(struct alt_instr *start,
struct alt_instr *end)
{
u8 *instr, *replacement;
u8 insnbuf[MAX_PATCH_LEN];
- DPRINTK("%s: alt table %p -> %p\n", __func__, start, end);
+ DPRINTK("alt table %p -> %p", start, end);
/*
* The scan order should be from start to end. A later scanned
- * alternative code can overwrite a previous scanned alternative code.
+ * alternative code can overwrite previously scanned alternative code.
* Some kernel functions (e.g. memcpy, memset, etc) use this order to
* patch code.
*
* order.
*/
for (a = start; a < end; a++) {
+ int insnbuf_sz = 0;
+
instr = (u8 *)&a->instr_offset + a->instr_offset;
replacement = (u8 *)&a->repl_offset + a->repl_offset;
- BUG_ON(a->replacementlen > a->instrlen);
BUG_ON(a->instrlen > sizeof(insnbuf));
BUG_ON(a->cpuid >= NCAPINTS*32);
- if (!boot_cpu_has(a->cpuid))
+ if (!boot_cpu_has(a->cpuid)) {
+ if (a->padlen > 1)
+ optimize_nops(a, instr);
+
continue;
+ }
+
+ DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d)",
+ a->cpuid >> 5,
+ a->cpuid & 0x1f,
+ instr, a->instrlen,
+ replacement, a->replacementlen);
+
+ DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr);
+ DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement);
memcpy(insnbuf, replacement, a->replacementlen);
+ insnbuf_sz = a->replacementlen;
/* 0xe8 is a relative jump; fix the offset. */
- if (*insnbuf == 0xe8 && a->replacementlen == 5)
- *(s32 *)(insnbuf + 1) += replacement - instr;
+ if (*insnbuf == 0xe8 && a->replacementlen == 5) {
+ *(s32 *)(insnbuf + 1) += replacement - instr;
+ DPRINTK("Fix CALL offset: 0x%x, CALL 0x%lx",
+ *(s32 *)(insnbuf + 1),
+ (unsigned long)instr + *(s32 *)(insnbuf + 1) + 5);
+ }
+
+ if (a->replacementlen && is_jmp(replacement[0]))
+ recompute_jump(a, instr, replacement, insnbuf);
- add_nops(insnbuf + a->replacementlen,
- a->instrlen - a->replacementlen);
+ if (a->instrlen > a->replacementlen) {
+ add_nops(insnbuf + a->replacementlen,
+ a->instrlen - a->replacementlen);
+ insnbuf_sz += a->instrlen - a->replacementlen;
+ }
+ DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr);
- text_poke_early(instr, insnbuf, a->instrlen);
+ text_poke_early(instr, insnbuf, insnbuf_sz);
}
}
#ifdef CONFIG_SMP
-
static void alternatives_smp_lock(const s32 *start, const s32 *end,
u8 *text, u8 *text_end)
{
{
const s32 *poff;
- if (noreplace_smp)
- return;
-
mutex_lock(&text_mutex);
for (poff = start; poff < end; poff++) {
u8 *ptr = (u8 *)poff + *poff;
};
static LIST_HEAD(smp_alt_modules);
static DEFINE_MUTEX(smp_alt);
-static int smp_mode = 1; /* protected by smp_alt */
+static bool uniproc_patched = false; /* protected by smp_alt */
void __init_or_module alternatives_smp_module_add(struct module *mod,
char *name,
{
struct smp_alt_module *smp;
- if (noreplace_smp)
- return;
+ mutex_lock(&smp_alt);
+ if (!uniproc_patched)
+ goto unlock;
- if (smp_alt_once) {
- if (boot_cpu_has(X86_FEATURE_UP))
- alternatives_smp_unlock(locks, locks_end,
- text, text_end);
- return;
- }
+ if (num_possible_cpus() == 1)
+ /* Don't bother remembering, we'll never have to undo it. */
+ goto smp_unlock;
smp = kzalloc(sizeof(*smp), GFP_KERNEL);
if (NULL == smp)
- return; /* we'll run the (safe but slow) SMP code then ... */
+ /* we'll run the (safe but slow) SMP code then ... */
+ goto unlock;
smp->mod = mod;
smp->name = name;
smp->locks_end = locks_end;
smp->text = text;
smp->text_end = text_end;
- DPRINTK("%s: locks %p -> %p, text %p -> %p, name %s\n",
- __func__, smp->locks, smp->locks_end,
+ DPRINTK("locks %p -> %p, text %p -> %p, name %s\n",
+ smp->locks, smp->locks_end,
smp->text, smp->text_end, smp->name);
- mutex_lock(&smp_alt);
list_add_tail(&smp->next, &smp_alt_modules);
- if (boot_cpu_has(X86_FEATURE_UP))
- alternatives_smp_unlock(smp->locks, smp->locks_end,
- smp->text, smp->text_end);
+smp_unlock:
+ alternatives_smp_unlock(locks, locks_end, text, text_end);
+unlock:
mutex_unlock(&smp_alt);
}
{
struct smp_alt_module *item;
- if (smp_alt_once || noreplace_smp)
- return;
-
mutex_lock(&smp_alt);
list_for_each_entry(item, &smp_alt_modules, next) {
if (mod != item->mod)
continue;
list_del(&item->next);
- mutex_unlock(&smp_alt);
- DPRINTK("%s: %s\n", __func__, item->name);
kfree(item);
- return;
+ break;
}
mutex_unlock(&smp_alt);
}
-bool skip_smp_alternatives;
-void alternatives_smp_switch(int smp)
+void alternatives_enable_smp(void)
{
struct smp_alt_module *mod;
printk("lockdep: fixing up alternatives.\n");
#endif
- if (noreplace_smp || smp_alt_once || skip_smp_alternatives)
- return;
- BUG_ON(!smp && (num_online_cpus() > 1));
+ /* Why bother if there are no other CPUs? */
+ BUG_ON(num_possible_cpus() == 1);
mutex_lock(&smp_alt);
- /*
- * Avoid unnecessary switches because it forces JIT based VMs to
- * throw away all cached translations, which can be quite costly.
- */
- if (smp == smp_mode) {
- /* nothing */
- } else if (smp) {
+ if (uniproc_patched) {
printk(KERN_INFO "SMP alternatives: switching to SMP code\n");
+ BUG_ON(num_online_cpus() != 1);
clear_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
clear_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
list_for_each_entry(mod, &smp_alt_modules, next)
alternatives_smp_lock(mod->locks, mod->locks_end,
mod->text, mod->text_end);
- } else {
- printk(KERN_INFO "SMP alternatives: switching to UP code\n");
- set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
- set_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
- list_for_each_entry(mod, &smp_alt_modules, next)
- alternatives_smp_unlock(mod->locks, mod->locks_end,
- mod->text, mod->text_end);
+ uniproc_patched = false;
}
- smp_mode = smp;
mutex_unlock(&smp_alt);
}
return 0;
}
-#endif
+#endif /* CONFIG_SMP */
#ifdef CONFIG_PARAVIRT
void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
apply_alternatives(__alt_instructions, __alt_instructions_end);
- /* switch to patch-once-at-boottime-only mode and free the
- * tables in case we know the number of CPUs will never ever
- * change */
-#ifdef CONFIG_HOTPLUG_CPU
- if (num_possible_cpus() < 2)
- smp_alt_once = 1;
-#endif
-
#ifdef CONFIG_SMP
- if (smp_alt_once) {
- if (1 == num_possible_cpus()) {
- printk(KERN_INFO "SMP alternatives: switching to UP code\n");
- set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
- set_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
-
- alternatives_smp_unlock(__smp_locks, __smp_locks_end,
- _text, _etext);
- }
- } else {
+ /* Patch to UP if other cpus not imminent. */
+ if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) {
+ uniproc_patched = true;
alternatives_smp_module_add(NULL, "core kernel",
__smp_locks, __smp_locks_end,
_text, _etext);
-
- /* Only switch to UP mode if we don't immediately boot others */
- if (num_present_cpus() == 1 || setup_max_cpus <= 1)
- alternatives_smp_switch(0);
}
-#endif
- apply_paravirt(__parainstructions, __parainstructions_end);
- if (smp_alt_once)
+ 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);
restart_nmi();
}
atomic_set(&stop_machine_first, 1);
wrote_text = 0;
- __stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+ __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask);
}
git.openpandora.org / pandora-kernel.git / blobdiff