Merge remote-tracking branch 'origin/x86/espfix' into x86/vdso

Merge x86/espfix into x86/vdso, due to changes in the vdso setup code
that otherwise cause conflicts.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

21 files changed, 352 insertions, 34 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index f4d96000d33a..491ef3e59850 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-y			+= syscall_$(BITS).o vsyscall_gtod.o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o
 obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
+obj-$(CONFIG_X86_ESPFIX64)	+= espfix_64.o
 obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 3a2ae4c88948..31368207837c 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -31,7 +31,7 @@ static char temp_stack[4096];
  *
  * Wrapper around acpi_enter_sleep_state() to be called by assmebly.
  */
-acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state)
+acpi_status asmlinkage __visible x86_acpi_enter_sleep_state(u8 state)
 {
 	return acpi_enter_sleep_state(state);
 }
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index d23aa82e7a7b..992060e09897 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2189,7 +2189,7 @@ void send_cleanup_vector(struct irq_cfg *cfg)
 	cfg->move_in_progress = 0;
 }
 
-asmlinkage void smp_irq_move_cleanup_interrupt(void)
+asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 {
 	unsigned vector, me;
 
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index d921b7ee6595..36a1bb6d1ee0 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -429,14 +429,14 @@ static inline void __smp_thermal_interrupt(void)
 	smp_thermal_vector();
 }
 
-asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
+asmlinkage __visible void smp_thermal_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	__smp_thermal_interrupt();
 	exiting_ack_irq();
 }
 
-asmlinkage void smp_trace_thermal_interrupt(struct pt_regs *regs)
+asmlinkage __visible void smp_trace_thermal_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	trace_thermal_apic_entry(THERMAL_APIC_VECTOR);
diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c
index fe6b1c86645b..7245980186ee 100644
--- a/arch/x86/kernel/cpu/mcheck/threshold.c
+++ b/arch/x86/kernel/cpu/mcheck/threshold.c
@@ -24,14 +24,14 @@ static inline void __smp_threshold_interrupt(void)
 	mce_threshold_vector();
 }
 
-asmlinkage void smp_threshold_interrupt(void)
+asmlinkage __visible void smp_threshold_interrupt(void)
 {
 	entering_irq();
 	__smp_threshold_interrupt();
 	exiting_ack_irq();
 }
 
-asmlinkage void smp_trace_threshold_interrupt(void)
+asmlinkage __visible void smp_trace_threshold_interrupt(void)
 {
 	entering_irq();
 	trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR);
diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c
index 384df5105fbc..136ac74dee82 100644
--- a/arch/x86/kernel/cpu/rdrand.c
+++ b/arch/x86/kernel/cpu/rdrand.c
@@ -27,6 +27,7 @@
 static int __init x86_rdrand_setup(char *s)
 {
 	setup_clear_cpu_cap(X86_FEATURE_RDRAND);
+	setup_clear_cpu_cap(X86_FEATURE_RDSEED);
 	return 1;
 }
 __setup("nordrand", x86_rdrand_setup);
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 6e2537c32190..6cda0baeac9d 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -17,6 +17,7 @@
 #include <asm/dma.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>
+#include <asm/hpet.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/irq_remapping.h>
@@ -530,6 +531,15 @@ static void __init intel_graphics_stolen(int num, int slot, int func)
 	}
 }
 
+static void __init force_disable_hpet(int num, int slot, int func)
+{
+#ifdef CONFIG_HPET_TIMER
+	boot_hpet_disable = 1;
+	pr_info("x86/hpet: Will disable the HPET for this platform because it's not reliable\n");
+#endif
+}
+
+
 #define QFLAG_APPLY_ONCE 	0x1
 #define QFLAG_APPLIED		0x2
 #define QFLAG_DONE		(QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -567,6 +577,12 @@ static struct chipset early_qrk[] __initdata = {
 	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
 	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID,
 	  QFLAG_APPLY_ONCE, intel_graphics_stolen },
+	/*
+	 * HPET on current version of Baytrail platform has accuracy
+	 * problems, disable it for now:
+	 */
+	{ PCI_VENDOR_ID_INTEL, 0x0f00,
+		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
 	{}
 };
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index a2a4f4697889..98313ffaae6a 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -527,6 +527,7 @@ syscall_exit:
 restore_all:
 	TRACE_IRQS_IRET
 restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
 	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS, SS and CS
 	# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
 	# are returning to the kernel.
@@ -537,6 +538,7 @@ restore_all_notrace:
 	cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
 	CFI_REMEMBER_STATE
 	je ldt_ss			# returning to user-space with LDT SS
+#endif
 restore_nocheck:
 	RESTORE_REGS 4			# skip orig_eax/error_code
 irq_return:
@@ -549,13 +551,9 @@ ENTRY(iret_exc)
 .previous
 	_ASM_EXTABLE(irq_return,iret_exc)
 
+#ifdef CONFIG_X86_ESPFIX32
 	CFI_RESTORE_STATE
 ldt_ss:
-	larl PT_OLDSS(%esp), %eax
-	jnz restore_nocheck
-	testl $0x00400000, %eax		# returning to 32bit stack?
-	jnz restore_nocheck		# allright, normal return
-
 #ifdef CONFIG_PARAVIRT
 	/*
 	 * The kernel can't run on a non-flat stack if paravirt mode
@@ -597,6 +595,7 @@ ldt_ss:
 	lss (%esp), %esp		/* switch to espfix segment */
 	CFI_ADJUST_CFA_OFFSET -8
 	jmp restore_nocheck
+#endif
 	CFI_ENDPROC
 ENDPROC(system_call)
 
@@ -704,6 +703,7 @@ END(syscall_badsys)
  * the high word of the segment base from the GDT and swiches to the
  * normal stack and adjusts ESP with the matching offset.
  */
+#ifdef CONFIG_X86_ESPFIX32
 	/* fixup the stack */
 	mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
 	mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
@@ -713,8 +713,10 @@ END(syscall_badsys)
 	pushl_cfi %eax
 	lss (%esp), %esp		/* switch to the normal stack segment */
 	CFI_ADJUST_CFA_OFFSET -8
+#endif
 .endm
 .macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
 	movl %ss, %eax
 	/* see if on espfix stack */
 	cmpw $__ESPFIX_SS, %ax
@@ -725,6 +727,7 @@ END(syscall_badsys)
 	/* switch to normal stack */
 	FIXUP_ESPFIX_STACK
 27:
+#endif
 .endm
 
 /*
@@ -1355,11 +1358,13 @@ END(debug)
 ENTRY(nmi)
 	RING0_INT_FRAME
 	ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
 	pushl_cfi %eax
 	movl %ss, %eax
 	cmpw $__ESPFIX_SS, %ax
 	popl_cfi %eax
 	je nmi_espfix_stack
+#endif
 	cmpl $ia32_sysenter_target,(%esp)
 	je nmi_stack_fixup
 	pushl_cfi %eax
@@ -1399,6 +1404,7 @@ nmi_debug_stack_check:
 	FIX_STACK 24, nmi_stack_correct, 1
 	jmp nmi_stack_correct
 
+#ifdef CONFIG_X86_ESPFIX32
 nmi_espfix_stack:
 	/* We have a RING0_INT_FRAME here.
 	 *
@@ -1420,6 +1426,7 @@ nmi_espfix_stack:
 	lss 12+4(%esp), %esp		# back to espfix stack
 	CFI_ADJUST_CFA_OFFSET -24
 	jmp irq_return
+#endif
 	CFI_ENDPROC
 END(nmi)
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1e96c3628bf2..da0b9bdcc32e 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -58,6 +58,7 @@
 #include <asm/asm.h>
 #include <asm/context_tracking.h>
 #include <asm/smap.h>
+#include <asm/pgtable_types.h>
 #include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
@@ -1040,8 +1041,18 @@ restore_args:
 	RESTORE_ARGS 1,8,1
 
 irq_return:
+	/*
+	 * Are we returning to a stack segment from the LDT?  Note: in
+	 * 64-bit mode SS:RSP on the exception stack is always valid.
+	 */
+#ifdef CONFIG_X86_ESPFIX64
+	testb $4,(SS-RIP)(%rsp)
+	jnz irq_return_ldt
+#endif
+
+irq_return_iret:
 	INTERRUPT_RETURN
-	_ASM_EXTABLE(irq_return, bad_iret)
+	_ASM_EXTABLE(irq_return_iret, bad_iret)
 
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
@@ -1049,6 +1060,32 @@ ENTRY(native_iret)
 	_ASM_EXTABLE(native_iret, bad_iret)
 #endif
 
+#ifdef CONFIG_X86_ESPFIX64
+irq_return_ldt:
+	pushq_cfi %rax
+	pushq_cfi %rdi
+	SWAPGS
+	movq PER_CPU_VAR(espfix_waddr),%rdi
+	movq %rax,(0*8)(%rdi)	/* RAX */
+	movq (2*8)(%rsp),%rax	/* RIP */
+	movq %rax,(1*8)(%rdi)
+	movq (3*8)(%rsp),%rax	/* CS */
+	movq %rax,(2*8)(%rdi)
+	movq (4*8)(%rsp),%rax	/* RFLAGS */
+	movq %rax,(3*8)(%rdi)
+	movq (6*8)(%rsp),%rax	/* SS */
+	movq %rax,(5*8)(%rdi)
+	movq (5*8)(%rsp),%rax	/* RSP */
+	movq %rax,(4*8)(%rdi)
+	andl $0xffff0000,%eax
+	popq_cfi %rdi
+	orq PER_CPU_VAR(espfix_stack),%rax
+	SWAPGS
+	movq %rax,%rsp
+	popq_cfi %rax
+	jmp irq_return_iret
+#endif
+
 	.section .fixup,"ax"
 bad_iret:
 	/*
@@ -1110,9 +1147,45 @@ ENTRY(retint_kernel)
 	call preempt_schedule_irq
 	jmp exit_intr
 #endif
-
 	CFI_ENDPROC
 END(common_interrupt)
+
+	/*
+	 * If IRET takes a fault on the espfix stack, then we
+	 * end up promoting it to a doublefault.  In that case,
+	 * modify the stack to make it look like we just entered
+	 * the #GP handler from user space, similar to bad_iret.
+	 */
+#ifdef CONFIG_X86_ESPFIX64
+	ALIGN
+__do_double_fault:
+	XCPT_FRAME 1 RDI+8
+	movq RSP(%rdi),%rax		/* Trap on the espfix stack? */
+	sarq $PGDIR_SHIFT,%rax
+	cmpl $ESPFIX_PGD_ENTRY,%eax
+	jne do_double_fault		/* No, just deliver the fault */
+	cmpl $__KERNEL_CS,CS(%rdi)
+	jne do_double_fault
+	movq RIP(%rdi),%rax
+	cmpq $irq_return_iret,%rax
+#ifdef CONFIG_PARAVIRT
+	je 1f
+	cmpq $native_iret,%rax
+#endif
+	jne do_double_fault		/* This shouldn't happen... */
+1:
+	movq PER_CPU_VAR(kernel_stack),%rax
+	subq $(6*8-KERNEL_STACK_OFFSET),%rax	/* Reset to original stack */
+	movq %rax,RSP(%rdi)
+	movq $0,(%rax)			/* Missing (lost) #GP error code */
+	movq $general_protection,RIP(%rdi)
+	retq
+	CFI_ENDPROC
+END(__do_double_fault)
+#else
+# define __do_double_fault do_double_fault
+#endif
+
 /*
  * End of kprobes section
  */
@@ -1314,7 +1387,7 @@ zeroentry overflow do_overflow
 zeroentry bounds do_bounds
 zeroentry invalid_op do_invalid_op
 zeroentry device_not_available do_device_not_available
-paranoiderrorentry double_fault do_double_fault
+paranoiderrorentry double_fault __do_double_fault
 zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun
 errorentry invalid_TSS do_invalid_TSS
 errorentry segment_not_present do_segment_not_present
@@ -1601,7 +1674,7 @@ error_sti:
  */
 error_kernelspace:
 	incl %ebx
-	leaq irq_return(%rip),%rcx
+	leaq irq_return_iret(%rip),%rcx
 	cmpq %rcx,RIP+8(%rsp)
 	je error_swapgs
 	movl %ecx,%eax	/* zero extend */
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
new file mode 100644
index 000000000000..6afbb16e9b79
--- /dev/null
+++ b/arch/x86/kernel/espfix_64.c
@@ -0,0 +1,209 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *   Copyright 2014 Intel Corporation; author: H. Peter Anvin
+ *
+ *   This program is free software; you can redistribute it and/or modify it
+ *   under the terms and conditions of the GNU General Public License,
+ *   version 2, as published by the Free Software Foundation.
+ *
+ *   This program is distributed in the hope it will be useful, but WITHOUT
+ *   ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ *   FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ *   more details.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * The IRET instruction, when returning to a 16-bit segment, only
+ * restores the bottom 16 bits of the user space stack pointer.  This
+ * causes some 16-bit software to break, but it also leaks kernel state
+ * to user space.
+ *
+ * This works around this by creating percpu "ministacks", each of which
+ * is mapped 2^16 times 64K apart.  When we detect that the return SS is
+ * on the LDT, we copy the IRET frame to the ministack and use the
+ * relevant alias to return to userspace.  The ministacks are mapped
+ * readonly, so if the IRET fault we promote #GP to #DF which is an IST
+ * vector and thus has its own stack; we then do the fixup in the #DF
+ * handler.
+ *
+ * This file sets up the ministacks and the related page tables.  The
+ * actual ministack invocation is in entry_64.S.
+ */
+
+#include <linux/init.h>
+#include <linux/init_task.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/gfp.h>
+#include <linux/random.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/setup.h>
+#include <asm/espfix.h>
+
+/*
+ * Note: we only need 6*8 = 48 bytes for the espfix stack, but round
+ * it up to a cache line to avoid unnecessary sharing.
+ */
+#define ESPFIX_STACK_SIZE	(8*8UL)
+#define ESPFIX_STACKS_PER_PAGE	(PAGE_SIZE/ESPFIX_STACK_SIZE)
+
+/* There is address space for how many espfix pages? */
+#define ESPFIX_PAGE_SPACE	(1UL << (PGDIR_SHIFT-PAGE_SHIFT-16))
+
+#define ESPFIX_MAX_CPUS		(ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE)
+#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS
+# error "Need more than one PGD for the ESPFIX hack"
+#endif
+
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+
+/* This contains the *bottom* address of the espfix stack */
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+/* Initialization mutex - should this be a spinlock? */
+static DEFINE_MUTEX(espfix_init_mutex);
+
+/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */
+#define ESPFIX_MAX_PAGES  DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE)
+static void *espfix_pages[ESPFIX_MAX_PAGES];
+
+static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD]
+	__aligned(PAGE_SIZE);
+
+static unsigned int page_random, slot_random;
+
+/*
+ * This returns the bottom address of the espfix stack for a specific CPU.
+ * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case
+ * we have to account for some amount of padding at the end of each page.
+ */
+static inline unsigned long espfix_base_addr(unsigned int cpu)
+{
+	unsigned long page, slot;
+	unsigned long addr;
+
+	page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random;
+	slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE;
+	addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE);
+	addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16);
+	addr += ESPFIX_BASE_ADDR;
+	return addr;
+}
+
+#define PTE_STRIDE        (65536/PAGE_SIZE)
+#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE)
+#define ESPFIX_PMD_CLONES PTRS_PER_PMD
+#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES))
+
+#define PGTABLE_PROT	  ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX)
+
+static void init_espfix_random(void)
+{
+	unsigned long rand;
+
+	/*
+	 * This is run before the entropy pools are initialized,
+	 * but this is hopefully better than nothing.
+	 */
+	if (!arch_get_random_long(&rand)) {
+		/* The constant is an arbitrary large prime */
+		rdtscll(rand);
+		rand *= 0xc345c6b72fd16123UL;
+	}
+
+	slot_random = rand % ESPFIX_STACKS_PER_PAGE;
+	page_random = (rand / ESPFIX_STACKS_PER_PAGE)
+		& (ESPFIX_PAGE_SPACE - 1);
+}
+
+void __init init_espfix_bsp(void)
+{
+	pgd_t *pgd_p;
+	pteval_t ptemask;
+
+	ptemask = __supported_pte_mask;
+
+	/* Install the espfix pud into the kernel page directory */
+	pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
+	pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
+
+	/* Randomize the locations */
+	init_espfix_random();
+
+	/* The rest is the same as for any other processor */
+	init_espfix_ap();
+}
+
+void init_espfix_ap(void)
+{
+	unsigned int cpu, page;
+	unsigned long addr;
+	pud_t pud, *pud_p;
+	pmd_t pmd, *pmd_p;
+	pte_t pte, *pte_p;
+	int n;
+	void *stack_page;
+	pteval_t ptemask;
+
+	/* We only have to do this once... */
+	if (likely(this_cpu_read(espfix_stack)))
+		return;		/* Already initialized */
+
+	cpu = smp_processor_id();
+	addr = espfix_base_addr(cpu);
+	page = cpu/ESPFIX_STACKS_PER_PAGE;
+
+	/* Did another CPU already set this up? */
+	stack_page = ACCESS_ONCE(espfix_pages[page]);
+	if (likely(stack_page))
+		goto done;
+
+	mutex_lock(&espfix_init_mutex);
+
+	/* Did we race on the lock? */
+	stack_page = ACCESS_ONCE(espfix_pages[page]);
+	if (stack_page)
+		goto unlock_done;
+
+	ptemask = __supported_pte_mask;
+
+	pud_p = &espfix_pud_page[pud_index(addr)];
+	pud = *pud_p;
+	if (!pud_present(pud)) {
+		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
+		paravirt_alloc_pud(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
+			set_pud(&pud_p[n], pud);
+	}
+
+	pmd_p = pmd_offset(&pud, addr);
+	pmd = *pmd_p;
+	if (!pmd_present(pmd)) {
+		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
+		paravirt_alloc_pmd(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
+			set_pmd(&pmd_p[n], pmd);
+	}
+
+	pte_p = pte_offset_kernel(&pmd, addr);
+	stack_page = (void *)__get_free_page(GFP_KERNEL);
+	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
+	paravirt_alloc_pte(&init_mm, __pa(stack_page) >> PAGE_SHIFT);
+	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
+		set_pte(&pte_p[n*PTE_STRIDE], pte);
+
+	/* Job is done for this CPU and any CPU which shares this page */
+	ACCESS_ONCE(espfix_pages[page]) = stack_page;
+
+unlock_done:
+	mutex_unlock(&espfix_init_mutex);
+done:
+	this_cpu_write(espfix_stack, addr);
+	this_cpu_write(espfix_waddr, (unsigned long)stack_page
+		       + (addr & ~PAGE_MASK));
+}
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index c61a14a4a310..d6c1b9836995 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -29,7 +29,7 @@ static void __init i386_default_early_setup(void)
 	reserve_ebda_region();
 }
 
-asmlinkage void __init i386_start_kernel(void)
+asmlinkage __visible void __init i386_start_kernel(void)
 {
 	sanitize_boot_params(&boot_params);
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 85126ccbdf6b..068054f4bf20 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -137,7 +137,7 @@ static void __init copy_bootdata(char *real_mode_data)
 	}
 }
 
-asmlinkage void __init x86_64_start_kernel(char * real_mode_data)
+asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 {
 	int i;
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index bbc15a0362d2..a9777bb5b5a0 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -85,7 +85,7 @@ static inline void hpet_clear_mapping(void)
 /*
  * HPET command line enable / disable
  */
-static int boot_hpet_disable;
+int boot_hpet_disable;
 int hpet_force_user;
 static int hpet_verbose;
 
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index af1d14a9ebda..c37886d759cc 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -229,16 +229,10 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 		}
 	}
 
-	/*
-	 * On x86-64 we do not support 16-bit segments due to
-	 * IRET leaking the high bits of the kernel stack address.
-	 */
-#ifdef CONFIG_X86_64
-	if (!ldt_info.seg_32bit) {
+	if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
 		error = -EINVAL;
 		goto out_unlock;
 	}
-#endif
 
 	fill_ldt(&ldt, &ldt_info);
 	if (oldmode)
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9c0280f93d05..898d077617a9 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -52,7 +52,7 @@
 
 asmlinkage extern void ret_from_fork(void);
 
-asmlinkage DEFINE_PER_CPU(unsigned long, old_rsp);
+__visible DEFINE_PER_CPU(unsigned long, old_rsp);
 
 /* Prints also some state that isn't saved in the pt_regs */
 void __show_regs(struct pt_regs *regs, int all)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 3399d3a99730..52b1157c53eb 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -191,6 +191,16 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 		},
 	},
 
+	/* Certec */
+	{       /* Handle problems with rebooting on Certec BPC600 */
+		.callback = set_pci_reboot,
+		.ident = "Certec BPC600",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Certec"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "BPC600"),
+		},
+	},
+
 	/* Dell */
 	{	/* Handle problems with rebooting on Dell DXP061 */
 		.callback = set_bios_reboot,
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 7c3a5a61f2e4..be8e1bde07aa 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -168,7 +168,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
  * this function calls the 'stop' function on all other CPUs in the system.
  */
 
-asmlinkage void smp_reboot_interrupt(void)
+asmlinkage __visible void smp_reboot_interrupt(void)
 {
 	ack_APIC_irq();
 	irq_enter();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 34826934d4a7..5d93ac1b72db 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -244,6 +244,13 @@ static void notrace start_secondary(void *unused)
 	check_tsc_sync_target();
 
 	/*
+	 * Enable the espfix hack for this CPU
+	 */
+#ifdef CONFIG_X86_ESPFIX64
+	init_espfix_ap();
+#endif
+
+	/*
 	 * We need to hold vector_lock so there the set of online cpus
 	 * does not change while we are assigning vectors to cpus.  Holding
 	 * this lock ensures we don't half assign or remove an irq from a cpu.
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 57409f6b8c62..f73b5d435bdc 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -357,7 +357,7 @@ exit:
  * for scheduling or signal handling. The actual stack switch is done in
  * entry.S
  */
-asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
+asmlinkage __visible __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
 {
 	struct pt_regs *regs = eregs;
 	/* Did already sync */
@@ -601,11 +601,11 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
 #endif
 }
 
-asmlinkage void __attribute__((weak)) smp_thermal_interrupt(void)
+asmlinkage __visible void __attribute__((weak)) smp_thermal_interrupt(void)
 {
 }
 
-asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void)
+asmlinkage __visible void __attribute__((weak)) smp_threshold_interrupt(void)
 {
 }
 
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index 5edc34b5b951..b99b9ad8540c 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -36,7 +36,7 @@ static int irq_routing_comply = 1;
  * and vice versa.
  */
 
-asmlinkage unsigned long vsmp_save_fl(void)
+asmlinkage __visible unsigned long vsmp_save_fl(void)
 {
 	unsigned long flags = native_save_fl();
 
@@ -56,7 +56,7 @@ __visible void vsmp_restore_fl(unsigned long flags)
 }
 PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl);
 
-asmlinkage void vsmp_irq_disable(void)
+asmlinkage __visible void vsmp_irq_disable(void)
 {
 	unsigned long flags = native_save_fl();
 
@@ -64,7 +64,7 @@ asmlinkage void vsmp_irq_disable(void)
 }
 PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable);
 
-asmlinkage void vsmp_irq_enable(void)
+asmlinkage __visible void vsmp_irq_enable(void)
 {
 	unsigned long flags = native_save_fl();
 
diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c
index f9c6e56e14b5..9531fbb123ba 100644
--- a/arch/x86/kernel/vsyscall_gtod.c
+++ b/arch/x86/kernel/vsyscall_gtod.c
@@ -43,7 +43,7 @@ void update_vsyscall(struct timekeeper *tk)
 	vdata->monotonic_time_sec	= tk->xtime_sec
 					+ tk->wall_to_monotonic.tv_sec;
 	vdata->monotonic_time_snsec	= tk->xtime_nsec
-					+ (tk->wall_to_monotonic.tv_nsec
+					+ ((u64)tk->wall_to_monotonic.tv_nsec
 						<< tk->shift);
 	while (vdata->monotonic_time_snsec >=
 					(((u64)NSEC_PER_SEC) << tk->shift)) {