Merge branch 'linux-3.4.35' into rel-17

Bug 1243631

Change-Id: I915826047b2e20f0ad0a7d75df295c6cbf6e5b0a

15 files changed, 251 insertions, 53 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 73ef56c5a8b3..bda833c5f6ce 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -160,7 +160,7 @@ static const unsigned char * const k7_nops[ASM_NOP_MAX+2] =
 #endif
 
 #ifdef P6_NOP1
-static const unsigned char  __initconst_or_module p6nops[] =
+static const unsigned char p6nops[] =
 {
 	P6_NOP1,
 	P6_NOP2,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 991e315f4227..db31a2cfc9a9 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -20,18 +20,19 @@ static int set_x2apic_phys_mode(char *arg)
 }
 early_param("x2apic_phys", set_x2apic_phys_mode);
 
-static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+static bool x2apic_fadt_phys(void)
 {
-	if (x2apic_phys)
-		return x2apic_enabled();
-	else if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
-		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL) &&
-		x2apic_enabled()) {
+	if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
+		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
 		printk(KERN_DEBUG "System requires x2apic physical mode\n");
-		return 1;
+		return true;
 	}
-	else
-		return 0;
+	return false;
+}
+
+static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys());
 }
 
 static void
@@ -114,7 +115,7 @@ static void init_x2apic_ldr(void)
 
 static int x2apic_phys_probe(void)
 {
-	if (x2apic_mode && x2apic_phys)
+	if (x2apic_mode && (x2apic_phys || x2apic_fadt_phys()))
 		return 1;
 
 	return apic == &apic_x2apic_phys;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 146bb6218eec..a9c8a46dd7d3 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -598,6 +598,34 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		}
 	}
 
+	/*
+	 * The way access filter has a performance penalty on some workloads.
+	 * Disable it on the affected CPUs.
+	 */
+	if ((c->x86 == 0x15) &&
+	    (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
+		u64 val;
+
+		if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) {
+			val |= 0x1E;
+			checking_wrmsrl(0xc0011021, val);
+		}
+	}
+
+	/*
+	 * The way access filter has a performance penalty on some workloads.
+	 * Disable it on the affected CPUs.
+	 */
+	if ((c->x86 == 0x15) &&
+	    (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
+		u64 val;
+
+		if (!rdmsrl_safe(0xc0011021, &val) && !(val & 0x1E)) {
+			val |= 0x1E;
+			checking_wrmsrl(0xc0011021, val);
+		}
+	}
+
 	cpu_detect_cache_sizes(c);
 
 	/* Multi core CPU? */
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 0a630dd4b620..646d192b18a2 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -68,7 +68,8 @@ static void __init ms_hyperv_init_platform(void)
 	printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n",
 	       ms_hyperv.features, ms_hyperv.hints);
 
-	clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
+	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
+		clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 62d61e9976eb..298dc000378a 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1076,6 +1076,9 @@ void __init memblock_x86_fill(void)
 		memblock_add(ei->addr, ei->size);
 	}
 
+	/* throw away partial pages */
+	memblock_trim_memory(PAGE_SIZE);
+
 	memblock_dump_all();
 }
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 7b784f4ef1e4..2af4ccd88d16 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1025,7 +1025,7 @@ ENTRY(xen_sysenter_target)
 
 ENTRY(xen_hypervisor_callback)
 	CFI_STARTPROC
-	pushl_cfi $0
+	pushl_cfi $-1 /* orig_ax = -1 => not a system call */
 	SAVE_ALL
 	TRACE_IRQS_OFF
 
@@ -1067,14 +1067,15 @@ ENTRY(xen_failsafe_callback)
 2:	mov 8(%esp),%es
 3:	mov 12(%esp),%fs
 4:	mov 16(%esp),%gs
+	/* EAX == 0 => Category 1 (Bad segment)
+	   EAX != 0 => Category 2 (Bad IRET) */
 	testl %eax,%eax
 	popl_cfi %eax
 	lea 16(%esp),%esp
 	CFI_ADJUST_CFA_OFFSET -16
 	jz 5f
-	addl $16,%esp
-	jmp iret_exc		# EAX != 0 => Category 2 (Bad IRET)
-5:	pushl_cfi $0		# EAX == 0 => Category 1 (Bad segment)
+	jmp iret_exc
+5:	pushl_cfi $-1 /* orig_ax = -1 => not a system call */
 	SAVE_ALL
 	jmp ret_from_exception
 	CFI_ENDPROC
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index cdc79b5cfcd9..bd6f59203b5f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1351,7 +1351,7 @@ ENTRY(xen_failsafe_callback)
 	CFI_RESTORE r11
 	addq $0x30,%rsp
 	CFI_ADJUST_CFA_OFFSET -0x30
-	pushq_cfi $0
+	pushq_cfi $-1 /* orig_ax = -1 => not a system call */
 	SAVE_ALL
 	jmp error_exit
 	CFI_ENDPROC
diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c
index 48d9d4ea1020..992f442ca155 100644
--- a/arch/x86/kernel/head.c
+++ b/arch/x86/kernel/head.c
@@ -5,8 +5,6 @@
 #include <asm/setup.h>
 #include <asm/bios_ebda.h>
 
-#define BIOS_LOWMEM_KILOBYTES 0x413
-
 /*
  * The BIOS places the EBDA/XBDA at the top of conventional
  * memory, and usually decreases the reported amount of
@@ -16,17 +14,30 @@
  * chipset: reserve a page before VGA to prevent PCI prefetch
  * into it (errata #56). Usually the page is reserved anyways,
  * unless you have no PS/2 mouse plugged in.
+ *
+ * This functions is deliberately very conservative.  Losing
+ * memory in the bottom megabyte is rarely a problem, as long
+ * as we have enough memory to install the trampoline.  Using
+ * memory that is in use by the BIOS or by some DMA device
+ * the BIOS didn't shut down *is* a big problem.
  */
+
+#define BIOS_LOWMEM_KILOBYTES	0x413
+#define LOWMEM_CAP		0x9f000U	/* Absolute maximum */
+#define INSANE_CUTOFF		0x20000U	/* Less than this = insane */
+
 void __init reserve_ebda_region(void)
 {
 	unsigned int lowmem, ebda_addr;
 
-	/* To determine the position of the EBDA and the */
-	/* end of conventional memory, we need to look at */
-	/* the BIOS data area. In a paravirtual environment */
-	/* that area is absent. We'll just have to assume */
-	/* that the paravirt case can handle memory setup */
-	/* correctly, without our help. */
+	/*
+	 * To determine the position of the EBDA and the
+	 * end of conventional memory, we need to look at
+	 * the BIOS data area. In a paravirtual environment
+	 * that area is absent. We'll just have to assume
+	 * that the paravirt case can handle memory setup
+	 * correctly, without our help.
+	 */
 	if (paravirt_enabled())
 		return;
 
@@ -37,19 +48,23 @@ void __init reserve_ebda_region(void)
 	/* start of EBDA area */
 	ebda_addr = get_bios_ebda();
 
-	/* Fixup: bios puts an EBDA in the top 64K segment */
-	/* of conventional memory, but does not adjust lowmem. */
-	if ((lowmem - ebda_addr) <= 0x10000)
-		lowmem = ebda_addr;
+	/*
+	 * Note: some old Dells seem to need 4k EBDA without
+	 * reporting so, so just consider the memory above 0x9f000
+	 * to be off limits (bugzilla 2990).
+	 */
+
+	/* If the EBDA address is below 128K, assume it is bogus */
+	if (ebda_addr < INSANE_CUTOFF)
+		ebda_addr = LOWMEM_CAP;
 
-	/* Fixup: bios does not report an EBDA at all. */
-	/* Some old Dells seem to need 4k anyhow (bugzilla 2990) */
-	if ((ebda_addr == 0) && (lowmem >= 0x9f000))
-		lowmem = 0x9f000;
+	/* If lowmem is less than 128K, assume it is bogus */
+	if (lowmem < INSANE_CUTOFF)
+		lowmem = LOWMEM_CAP;
 
-	/* Paranoia: should never happen, but... */
-	if ((lowmem == 0) || (lowmem >= 0x100000))
-		lowmem = 0x9f000;
+	/* Use the lower of the lowmem and EBDA markers as the cutoff */
+	lowmem = min(lowmem, ebda_addr);
+	lowmem = min(lowmem, LOWMEM_CAP); /* Absolute cap */
 
 	/* reserve all memory between lowmem and the 1MB mark */
 	memblock_reserve(lowmem, 0x100000 - lowmem);
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ad0de0c2714e..2861b4cafd2e 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -431,7 +431,7 @@ void hpet_msi_unmask(struct irq_data *data)
 
 	/* unmask it */
 	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
-	cfg |= HPET_TN_FSB;
+	cfg |= HPET_TN_ENABLE | HPET_TN_FSB;
 	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 
@@ -442,7 +442,7 @@ void hpet_msi_mask(struct irq_data *data)
 
 	/* mask it */
 	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
-	cfg &= ~HPET_TN_FSB;
+	cfg &= ~(HPET_TN_ENABLE | HPET_TN_FSB);
 	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 8a2ce8fd41c0..5d8cf0d6796c 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -97,6 +97,7 @@ static unsigned int verify_ucode_size(int cpu, u32 patch_size,
 #define F1XH_MPB_MAX_SIZE 2048
 #define F14H_MPB_MAX_SIZE 1824
 #define F15H_MPB_MAX_SIZE 4096
+#define F16H_MPB_MAX_SIZE 3458
 
 	switch (c->x86) {
 	case 0x14:
@@ -105,6 +106,9 @@ static unsigned int verify_ucode_size(int cpu, u32 patch_size,
 	case 0x15:
 		max_size = F15H_MPB_MAX_SIZE;
 		break;
+	case 0x16:
+		max_size = F16H_MPB_MAX_SIZE;
+		break;
 	default:
 		max_size = F1XH_MPB_MAX_SIZE;
 		break;
@@ -143,11 +147,12 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr,
 				  unsigned int *current_size)
 {
 	struct microcode_header_amd *mc_hdr;
-	unsigned int actual_size;
+	unsigned int actual_size, patch_size;
 	u16 equiv_cpu_id;
 
 	/* size of the current patch we're staring at */
-	*current_size = *(u32 *)(ucode_ptr + 4) + SECTION_HDR_SIZE;
+	patch_size = *(u32 *)(ucode_ptr + 4);
+	*current_size = patch_size + SECTION_HDR_SIZE;
 
 	equiv_cpu_id = find_equiv_id();
 	if (!equiv_cpu_id)
@@ -174,7 +179,7 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr,
 	/*
 	 * now that the header looks sane, verify its size
 	 */
-	actual_size = verify_ucode_size(cpu, *current_size, leftover_size);
+	actual_size = verify_ucode_size(cpu, patch_size, leftover_size);
 	if (!actual_size)
 		return 0;
 
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index eb113693f043..8563b64e18cf 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -174,6 +174,9 @@ static int msr_open(struct inode *inode, struct file *file)
 	unsigned int cpu;
 	struct cpuinfo_x86 *c;
 
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
 	cpu = iminor(file->f_path.dentry->d_inode);
 	if (cpu >= nr_cpu_ids || !cpu_online(cpu))
 		return -ENXIO;	/* No such CPU */
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index cf1178332bc0..c4410fb4938f 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,6 +21,7 @@
 #include <linux/signal.h>
 #include <linux/perf_event.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/module.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -165,6 +166,35 @@ static inline bool invalid_selector(u16 value)
 
 #define FLAG_MASK		FLAG_MASK_32
 
+/*
+ * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
+ * when it traps.  The previous stack will be directly underneath the saved
+ * registers, and 'sp/ss' won't even have been saved. Thus the '&regs->sp'.
+ *
+ * Now, if the stack is empty, '&regs->sp' is out of range. In this
+ * case we try to take the previous stack. To always return a non-null
+ * stack pointer we fall back to regs as stack if no previous stack
+ * exists.
+ *
+ * This is valid only for kernel mode traps.
+ */
+unsigned long kernel_stack_pointer(struct pt_regs *regs)
+{
+	unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1);
+	unsigned long sp = (unsigned long)&regs->sp;
+	struct thread_info *tinfo;
+
+	if (context == (sp & ~(THREAD_SIZE - 1)))
+		return sp;
+
+	tinfo = (struct thread_info *)context;
+	if (tinfo->previous_esp)
+		return tinfo->previous_esp;
+
+	return (unsigned long)regs;
+}
+EXPORT_SYMBOL_GPL(kernel_stack_pointer);
+
 static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
 {
 	BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 3034ee5afb0f..df1b604c0c1f 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -619,7 +619,7 @@ static void native_machine_emergency_restart(void)
 			break;
 
 		case BOOT_EFI:
-			if (efi_enabled)
+			if (efi_enabled(EFI_RUNTIME_SERVICES))
 				efi.reset_system(reboot_mode ?
 						 EFI_RESET_WARM :
 						 EFI_RESET_COLD,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d6c956e674cc..dc29333e1bb9 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -621,6 +621,83 @@ static __init void reserve_ibft_region(void)
 
 static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
 
+static bool __init snb_gfx_workaround_needed(void)
+{
+#ifdef CONFIG_PCI
+	int i;
+	u16 vendor, devid;
+	static const u16 snb_ids[] = {
+		0x0102,
+		0x0112,
+		0x0122,
+		0x0106,
+		0x0116,
+		0x0126,
+		0x010a,
+	};
+
+	/* Assume no if something weird is going on with PCI */
+	if (!early_pci_allowed())
+		return false;
+
+	vendor = read_pci_config_16(0, 2, 0, PCI_VENDOR_ID);
+	if (vendor != 0x8086)
+		return false;
+
+	devid = read_pci_config_16(0, 2, 0, PCI_DEVICE_ID);
+	for (i = 0; i < ARRAY_SIZE(snb_ids); i++)
+		if (devid == snb_ids[i])
+			return true;
+#endif
+
+	return false;
+}
+
+/*
+ * Sandy Bridge graphics has trouble with certain ranges, exclude
+ * them from allocation.
+ */
+static void __init trim_snb_memory(void)
+{
+	static const unsigned long bad_pages[] = {
+		0x20050000,
+		0x20110000,
+		0x20130000,
+		0x20138000,
+		0x40004000,
+	};
+	int i;
+
+	if (!snb_gfx_workaround_needed())
+		return;
+
+	printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n");
+
+	/*
+	 * Reserve all memory below the 1 MB mark that has not
+	 * already been reserved.
+	 */
+	memblock_reserve(0, 1<<20);
+
+	for (i = 0; i < ARRAY_SIZE(bad_pages); i++) {
+		if (memblock_reserve(bad_pages[i], PAGE_SIZE))
+			printk(KERN_WARNING "failed to reserve 0x%08lx\n",
+			       bad_pages[i]);
+	}
+}
+
+/*
+ * Here we put platform-specific memory range workarounds, i.e.
+ * memory known to be corrupt or otherwise in need to be reserved on
+ * specific platforms.
+ *
+ * If this gets used more widely it could use a real dispatch mechanism.
+ */
+static void __init trim_platform_memory_ranges(void)
+{
+	trim_snb_memory();
+}
+
 static void __init trim_bios_range(void)
 {
 	/*
@@ -641,6 +718,7 @@ static void __init trim_bios_range(void)
 	 * take them out.
 	 */
 	e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
+
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
@@ -741,15 +819,15 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_EFI
 	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL32", 4)) {
-		efi_enabled = 1;
-		efi_64bit = false;
+		set_bit(EFI_BOOT, &x86_efi_facility);
 	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL64", 4)) {
-		efi_enabled = 1;
-		efi_64bit = true;
+		set_bit(EFI_BOOT, &x86_efi_facility);
+		set_bit(EFI_64BIT, &x86_efi_facility);
 	}
-	if (efi_enabled && efi_memblock_x86_reserve_range())
-		efi_enabled = 0;
+
+	if (efi_enabled(EFI_BOOT))
+		efi_memblock_x86_reserve_range();
 #endif
 
 	x86_init.oem.arch_setup();
@@ -822,7 +900,7 @@ void __init setup_arch(char **cmdline_p)
 
 	finish_e820_parsing();
 
-	if (efi_enabled)
+	if (efi_enabled(EFI_BOOT))
 		efi_init();
 
 	dmi_scan_machine();
@@ -905,7 +983,7 @@ void __init setup_arch(char **cmdline_p)
 	 * The EFI specification says that boot service code won't be called
 	 * after ExitBootServices(). This is, in fact, a lie.
 	 */
-	if (efi_enabled)
+	if (efi_enabled(EFI_MEMMAP))
 		efi_reserve_boot_services();
 
 	/* preallocate 4k for mptable mpc */
@@ -920,6 +998,8 @@ void __init setup_arch(char **cmdline_p)
 
 	setup_trampolines();
 
+	trim_platform_memory_ranges();
+
 	init_gbpages();
 
 	/* max_pfn_mapped is updated here */
@@ -928,8 +1008,22 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_X86_64
 	if (max_pfn > max_low_pfn) {
-		max_pfn_mapped = init_memory_mapping(1UL<<32,
-						     max_pfn<<PAGE_SHIFT);
+		int i;
+		unsigned long start, end;
+		unsigned long start_pfn, end_pfn;
+
+		for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn,
+							 NULL) {
+
+			end = PFN_PHYS(end_pfn);
+			if (end <= (1UL<<32))
+				continue;
+
+			start = PFN_PHYS(start_pfn);
+			max_pfn_mapped = init_memory_mapping(
+						max((1UL<<32), start), end);
+		}
+
 		/* can we preseve max_low_pfn ?*/
 		max_low_pfn = max_pfn;
 	}
@@ -1027,7 +1121,7 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
-	if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
+	if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
 		conswitchp = &vga_con;
 #elif defined(CONFIG_DUMMY_CONSOLE)
 	conswitchp = &dummy_con;
@@ -1042,6 +1136,18 @@ void __init setup_arch(char **cmdline_p)
 	mcheck_init();
 
 	arch_init_ideal_nops();
+
+#ifdef CONFIG_EFI
+	/* Once setup is done above, unmap the EFI memory map on
+	 * mismatched firmware/kernel archtectures since there is no
+	 * support for runtime services.
+	 */
+	if (efi_enabled(EFI_BOOT) &&
+	    IS_ENABLED(CONFIG_X86_64) != efi_enabled(EFI_64BIT)) {
+		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+		efi_unmap_memmap();
+	}
+#endif
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 6e1e406038c2..849cdcf2e76a 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -66,6 +66,8 @@
 #include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
+#include <asm/i387.h>
+#include <asm/fpu-internal.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
 #include <linux/mc146818rtc.h>
@@ -851,6 +853,9 @@ int __cpuinit native_cpu_up(unsigned int cpu)
 
 	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
 
+	/* the FPU context is blank, nobody can own it */
+	__cpu_disable_lazy_restore(cpu);
+
 	err = do_boot_cpu(apicid, cpu);
 	if (err) {
 		pr_debug("do_boot_cpu failed %d\n", err);