i386: move kernel

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

80 files changed, 31661 insertions, 2 deletions

diff --git a/arch/x86/kernel/.gitignore b/arch/x86/kernel/.gitignore
new file mode 100644
index 00000000000..40836ad9079
--- /dev/null
+++ b/arch/x86/kernel/.gitignore
@@ -0,0 +1 @@
+vsyscall.lds
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
new file mode 100644
index 00000000000..577d08f4b8b
--- /dev/null
+++ b/arch/x86/kernel/Makefile
@@ -0,0 +1,5 @@
+ifeq ($(CONFIG_X86_32),y)
+include ${srctree}/arch/x86/kernel/Makefile_32
+else
+include ${srctree}/arch/x86_64/kernel/Makefile_64
+endif
diff --git a/arch/x86/kernel/Makefile_32 b/arch/x86/kernel/Makefile_32
new file mode 100644
index 00000000000..5096f486d38
--- /dev/null
+++ b/arch/x86/kernel/Makefile_32
@@ -0,0 +1,88 @@
+#
+# Makefile for the linux kernel.
+#
+
+extra-y := head_32.o init_task_32.o vmlinux.lds
+
+obj-y	:= process_32.o signal_32.o entry_32.o traps_32.o irq_32.o \
+		ptrace_32.o time_32.o ioport_32.o ldt_32.o setup_32.o i8259_32.o sys_i386_32.o \
+		pci-dma_32.o i386_ksyms_32.o i387_32.o bootflag.o e820_32.o\
+		quirks.o i8237.o topology.o alternative.o i8253_32.o tsc_32.o
+
+obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
+obj-y				+= ../../x86/kernel/cpu/
+obj-y				+= ../../x86/kernel/acpi/
+obj-$(CONFIG_X86_BIOS_REBOOT)	+= reboot_32.o
+obj-$(CONFIG_MCA)		+= mca_32.o
+obj-$(CONFIG_X86_MSR)		+= msr.o
+obj-$(CONFIG_X86_CPUID)		+= cpuid.o
+obj-$(CONFIG_MICROCODE)		+= microcode.o
+obj-$(CONFIG_APM)		+= apm_32.o
+obj-$(CONFIG_X86_SMP)		+= smp_32.o smpboot_32.o tsc_sync.o
+obj-$(CONFIG_SMP)		+= smpcommon_32.o
+obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline_32.o
+obj-$(CONFIG_X86_MPPARSE)	+= mpparse_32.o
+obj-$(CONFIG_X86_LOCAL_APIC)	+= apic_32.o nmi_32.o
+obj-$(CONFIG_X86_IO_APIC)	+= io_apic_32.o
+obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
+obj-$(CONFIG_KEXEC)		+= machine_kexec_32.o relocate_kernel_32.o crash_32.o
+obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_32.o
+obj-$(CONFIG_X86_NUMAQ)		+= numaq_32.o
+obj-$(CONFIG_X86_SUMMIT_NUMA)	+= summit_32.o
+obj-$(CONFIG_KPROBES)		+= kprobes_32.o
+obj-$(CONFIG_MODULES)		+= module_32.o
+obj-y				+= sysenter_32.o vsyscall_32.o
+obj-$(CONFIG_ACPI_SRAT) 	+= srat_32.o
+obj-$(CONFIG_EFI) 		+= efi_32.o efi_stub_32.o
+obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
+obj-$(CONFIG_VM86)		+= vm86_32.o
+obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
+obj-$(CONFIG_HPET_TIMER) 	+= hpet_32.o
+obj-$(CONFIG_K8_NB)		+= k8.o
+obj-$(CONFIG_MGEODE_LX)		+= geode_32.o
+
+obj-$(CONFIG_VMI)		+= vmi_32.o vmiclock_32.o
+obj-$(CONFIG_PARAVIRT)		+= paravirt_32.o
+obj-y				+= pcspeaker.o
+
+obj-$(CONFIG_SCx200)		+= scx200_32.o
+
+# vsyscall_32.o contains the vsyscall DSO images as __initdata.
+# We must build both images before we can assemble it.
+# Note: kbuild does not track this dependency due to usage of .incbin
+$(obj)/vsyscall_32.o: $(obj)/vsyscall-int80_32.so $(obj)/vsyscall-sysenter_32.so
+targets += $(foreach F,int80 sysenter,vsyscall-$F.o vsyscall-$F.so)
+targets += vsyscall-note_32.o vsyscall_32.lds
+
+# The DSO images are built using a special linker script.
+quiet_cmd_syscall = SYSCALL $@
+      cmd_syscall = $(CC) -m elf_i386 -nostdlib $(SYSCFLAGS_$(@F)) \
+		          -Wl,-T,$(filter-out FORCE,$^) -o $@
+
+export CPPFLAGS_vsyscall_32.lds += -P -C -U$(ARCH)
+
+vsyscall-flags = -shared -s -Wl,-soname=linux-gate.so.1 \
+		 $(call ld-option, -Wl$(comma)--hash-style=sysv)
+SYSCFLAGS_vsyscall-sysenter_32.so	= $(vsyscall-flags)
+SYSCFLAGS_vsyscall-int80_32.so	= $(vsyscall-flags)
+
+$(obj)/vsyscall-int80_32.so $(obj)/vsyscall-sysenter_32.so: \
+$(obj)/vsyscall-%.so: $(src)/vsyscall_32.lds \
+		      $(obj)/vsyscall-%.o $(obj)/vsyscall-note_32.o FORCE
+	$(call if_changed,syscall)
+
+# We also create a special relocatable object that should mirror the symbol
+# table and layout of the linked DSO.  With ld -R we can then refer to
+# these symbols in the kernel code rather than hand-coded addresses.
+extra-y += vsyscall-syms.o
+$(obj)/built-in.o: $(obj)/vsyscall-syms.o
+$(obj)/built-in.o: ld_flags += -R $(obj)/vsyscall-syms.o
+
+SYSCFLAGS_vsyscall-syms.o = -r
+$(obj)/vsyscall-syms.o: $(src)/vsyscall_32.lds \
+			$(obj)/vsyscall-sysenter_32.o $(obj)/vsyscall-note_32.o FORCE
+	$(call if_changed,syscall)
+
+k8-y                      += ../../x86_64/kernel/k8.o
+stacktrace-y		  += ../../x86_64/kernel/stacktrace.o
+
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
new file mode 100644
index 00000000000..bd72d94e713
--- /dev/null
+++ b/arch/x86/kernel/alternative.c
@@ -0,0 +1,450 @@
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/kprobes.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <asm/alternative.h>
+#include <asm/sections.h>
+#include <asm/pgtable.h>
+#include <asm/mce.h>
+#include <asm/nmi.h>
+
+#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 debug_alternative;
+
+static int __init debug_alt(char *str)
+{
+	debug_alternative = 1;
+	return 1;
+}
+__setup("debug-alternative", debug_alt);
+
+static int noreplace_smp;
+
+static int __init setup_noreplace_smp(char *str)
+{
+	noreplace_smp = 1;
+	return 1;
+}
+__setup("noreplace-smp", setup_noreplace_smp);
+
+#ifdef CONFIG_PARAVIRT
+static int noreplace_paravirt = 0;
+
+static int __init setup_noreplace_paravirt(char *str)
+{
+	noreplace_paravirt = 1;
+	return 1;
+}
+__setup("noreplace-paravirt", setup_noreplace_paravirt);
+#endif
+
+#define DPRINTK(fmt, args...) if (debug_alternative) \
+	printk(KERN_DEBUG fmt, args)
+
+#ifdef GENERIC_NOP1
+/* Use inline assembly to define this because the nops are defined
+   as inline assembly strings in the include files and we cannot
+   get them easily into strings. */
+asm("\t.data\nintelnops: "
+	GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
+	GENERIC_NOP7 GENERIC_NOP8);
+extern unsigned char intelnops[];
+static unsigned char *intel_nops[ASM_NOP_MAX+1] = {
+	NULL,
+	intelnops,
+	intelnops + 1,
+	intelnops + 1 + 2,
+	intelnops + 1 + 2 + 3,
+	intelnops + 1 + 2 + 3 + 4,
+	intelnops + 1 + 2 + 3 + 4 + 5,
+	intelnops + 1 + 2 + 3 + 4 + 5 + 6,
+	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+};
+#endif
+
+#ifdef K8_NOP1
+asm("\t.data\nk8nops: "
+	K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
+	K8_NOP7 K8_NOP8);
+extern unsigned char k8nops[];
+static unsigned char *k8_nops[ASM_NOP_MAX+1] = {
+	NULL,
+	k8nops,
+	k8nops + 1,
+	k8nops + 1 + 2,
+	k8nops + 1 + 2 + 3,
+	k8nops + 1 + 2 + 3 + 4,
+	k8nops + 1 + 2 + 3 + 4 + 5,
+	k8nops + 1 + 2 + 3 + 4 + 5 + 6,
+	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+};
+#endif
+
+#ifdef K7_NOP1
+asm("\t.data\nk7nops: "
+	K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
+	K7_NOP7 K7_NOP8);
+extern unsigned char k7nops[];
+static unsigned char *k7_nops[ASM_NOP_MAX+1] = {
+	NULL,
+	k7nops,
+	k7nops + 1,
+	k7nops + 1 + 2,
+	k7nops + 1 + 2 + 3,
+	k7nops + 1 + 2 + 3 + 4,
+	k7nops + 1 + 2 + 3 + 4 + 5,
+	k7nops + 1 + 2 + 3 + 4 + 5 + 6,
+	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+};
+#endif
+
+#ifdef CONFIG_X86_64
+
+extern char __vsyscall_0;
+static inline unsigned char** find_nop_table(void)
+{
+	return k8_nops;
+}
+
+#else /* CONFIG_X86_64 */
+
+static struct nop {
+	int cpuid;
+	unsigned char **noptable;
+} noptypes[] = {
+	{ X86_FEATURE_K8, k8_nops },
+	{ X86_FEATURE_K7, k7_nops },
+	{ -1, NULL }
+};
+
+static unsigned char** find_nop_table(void)
+{
+	unsigned char **noptable = intel_nops;
+	int i;
+
+	for (i = 0; noptypes[i].cpuid >= 0; i++) {
+		if (boot_cpu_has(noptypes[i].cpuid)) {
+			noptable = noptypes[i].noptable;
+			break;
+		}
+	}
+	return noptable;
+}
+
+#endif /* CONFIG_X86_64 */
+
+/* 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();
+
+	while (len > 0) {
+		unsigned int noplen = len;
+		if (noplen > ASM_NOP_MAX)
+			noplen = ASM_NOP_MAX;
+		memcpy(insns, noptable[noplen], noplen);
+		insns += noplen;
+		len -= noplen;
+	}
+}
+
+extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+extern u8 *__smp_locks[], *__smp_locks_end[];
+
+/* 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 assymetric systems where
+   APs have less capabilities than the boot processor are not handled.
+   Tough. Make sure you disable such features by hand. */
+
+void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
+{
+	struct alt_instr *a;
+	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;
+#ifdef CONFIG_X86_64
+		/* vsyscall code is not mapped yet. resolve it manually. */
+		if (instr >= (u8 *)VSYSCALL_START && instr < (u8*)VSYSCALL_END) {
+			instr = __va(instr - (u8*)VSYSCALL_START + (u8*)__pa_symbol(&__vsyscall_0));
+			DPRINTK("%s: vsyscall fixup: %p => %p\n",
+				__FUNCTION__, a->instr, instr);
+		}
+#endif
+		memcpy(insnbuf, a->replacement, a->replacementlen);
+		add_nops(insnbuf + a->replacementlen,
+			 a->instrlen - a->replacementlen);
+		text_poke(instr, insnbuf, a->instrlen);
+	}
+}
+
+#ifdef CONFIG_SMP
+
+static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
+{
+	u8 **ptr;
+
+	for (ptr = start; ptr < end; ptr++) {
+		if (*ptr < text)
+			continue;
+		if (*ptr > text_end)
+			continue;
+		text_poke(*ptr, ((unsigned char []){0xf0}), 1); /* add lock prefix */
+	};
+}
+
+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;
+		text_poke(*ptr, insn, 1);
+	};
+}
+
+struct smp_alt_module {
+	/* what is this ??? */
+	struct module	*mod;
+	char		*name;
+
+	/* ptrs to lock prefixes */
+	u8		**locks;
+	u8		**locks_end;
+
+	/* .text segment, needed to avoid patching init code ;) */
+	u8		*text;
+	u8		*text_end;
+
+	struct list_head next;
+};
+static LIST_HEAD(smp_alt_modules);
+static DEFINE_SPINLOCK(smp_alt);
+
+void alternatives_smp_module_add(struct module *mod, char *name,
+				 void *locks, void *locks_end,
+				 void *text,  void *text_end)
+{
+	struct smp_alt_module *smp;
+	unsigned long flags;
+
+	if (noreplace_smp)
+		return;
+
+	if (smp_alt_once) {
+		if (boot_cpu_has(X86_FEATURE_UP))
+			alternatives_smp_unlock(locks, locks_end,
+						text, text_end);
+		return;
+	}
+
+	smp = kzalloc(sizeof(*smp), GFP_KERNEL);
+	if (NULL == smp)
+		return; /* we'll run the (safe but slow) SMP code then ... */
+
+	smp->mod	= mod;
+	smp->name	= name;
+	smp->locks	= locks;
+	smp->locks_end	= locks_end;
+	smp->text	= text;
+	smp->text_end	= text_end;
+	DPRINTK("%s: locks %p -> %p, text %p -> %p, name %s\n",
+		__FUNCTION__, smp->locks, smp->locks_end,
+		smp->text, smp->text_end, smp->name);
+
+	spin_lock_irqsave(&smp_alt, flags);
+	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);
+	spin_unlock_irqrestore(&smp_alt, flags);
+}
+
+void alternatives_smp_module_del(struct module *mod)
+{
+	struct smp_alt_module *item;
+	unsigned long flags;
+
+	if (smp_alt_once || noreplace_smp)
+		return;
+
+	spin_lock_irqsave(&smp_alt, flags);
+	list_for_each_entry(item, &smp_alt_modules, next) {
+		if (mod != item->mod)
+			continue;
+		list_del(&item->next);
+		spin_unlock_irqrestore(&smp_alt, flags);
+		DPRINTK("%s: %s\n", __FUNCTION__, item->name);
+		kfree(item);
+		return;
+	}
+	spin_unlock_irqrestore(&smp_alt, flags);
+}
+
+void alternatives_smp_switch(int smp)
+{
+	struct smp_alt_module *mod;
+	unsigned long flags;
+
+#ifdef CONFIG_LOCKDEP
+	/*
+	 * A not yet fixed binutils section handling bug prevents
+	 * alternatives-replacement from working reliably, so turn
+	 * it off:
+	 */
+	printk("lockdep: not fixing up alternatives.\n");
+	return;
+#endif
+
+	if (noreplace_smp || smp_alt_once)
+		return;
+	BUG_ON(!smp && (num_online_cpus() > 1));
+
+	spin_lock_irqsave(&smp_alt, flags);
+	if (smp) {
+		printk(KERN_INFO "SMP alternatives: switching to SMP code\n");
+		clear_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
+		clear_bit(X86_FEATURE_UP, cpu_data[0].x86_capability);
+		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_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
+		set_bit(X86_FEATURE_UP, cpu_data[0].x86_capability);
+		list_for_each_entry(mod, &smp_alt_modules, next)
+			alternatives_smp_unlock(mod->locks, mod->locks_end,
+						mod->text, mod->text_end);
+	}
+	spin_unlock_irqrestore(&smp_alt, flags);
+}
+
+#endif
+
+#ifdef CONFIG_PARAVIRT
+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;
+
+	for (p = start; p < end; p++) {
+		unsigned int used;
+
+		BUG_ON(p->len > MAX_PATCH_LEN);
+		/* prep the buffer with the original instructions */
+		memcpy(insnbuf, p->instr, p->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 */
+		add_nops(