21 files changed, 420 insertions, 47 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index cb648c84b327..56bac868cb91 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
 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/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 7f26c9a70a9e..523f147b2470 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1290,7 +1290,7 @@ void setup_local_APIC(void)
 	unsigned int value, queued;
 	int i, j, acked = 0;
 	unsigned long long tsc = 0, ntsc;
-	long long max_loops = cpu_khz;
+	long long max_loops = cpu_khz ? cpu_khz : 1000000;
 
 	if (cpu_has_tsc)
 		rdtscll(tsc);
@@ -1387,7 +1387,7 @@ void setup_local_APIC(void)
 			break;
 		}
 		if (queued) {
-			if (cpu_has_tsc) {
+			if (cpu_has_tsc && cpu_khz) {
 				rdtscll(ntsc);
 				max_loops = (cpu_khz << 10) - (ntsc - tsc);
 			} else
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8e28bf2fc3ef..3f27f5fd0847 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1141,7 +1141,7 @@ void syscall_init(void)
 	/* Flags to clear on syscall */
 	wrmsrl(MSR_SYSCALL_MASK,
 	       X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|
-	       X86_EFLAGS_IOPL|X86_EFLAGS_AC);
+	       X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 5cd9bfabd645..66746a880dec 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -153,6 +153,21 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 			setup_clear_cpu_cap(X86_FEATURE_ERMS);
 		}
 	}
+
+	/*
+	 * Intel Quark Core DevMan_001.pdf section 6.4.11
+	 * "The operating system also is required to invalidate (i.e., flush)
+	 *  the TLB when any changes are made to any of the page table entries.
+	 *  The operating system must reload CR3 to cause the TLB to be flushed"
+	 *
+	 * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should
+	 * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
+	 * to be modified
+	 */
+	if (c->x86 == 5 && c->x86_model == 9) {
+		pr_info("Disabling PGE capability bit\n");
+		setup_clear_cpu_cap(X86_FEATURE_PGE);
+	}
 }
 
 #ifdef CONFIG_X86_32
@@ -368,6 +383,13 @@ static void init_intel(struct cpuinfo_x86 *c)
 	detect_extended_topology(c);
 
 	l2 = init_intel_cacheinfo(c);
+
+	/* Detect legacy cache sizes if init_intel_cacheinfo did not */
+	if (l2 == 0) {
+		cpu_detect_cache_sizes(c);
+		l2 = c->x86_cache_size;
+	}
+
 	if (c->cpuid_level > 9) {
 		unsigned eax = cpuid_eax(10);
 		/* Check for version and the number of counters */
@@ -482,6 +504,13 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 	 */
 	if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0))
 		size = 256;
+
+	/*
+	 * Intel Quark SoC X1000 contains a 4-way set associative
+	 * 16K cache with a 16 byte cache line and 256 lines per tag
+	 */
+	if ((c->x86 == 5) && (c->x86_model == 9))
+		size = 16;
 	return size;
 }
 #endif
@@ -709,7 +738,8 @@ static const struct cpu_dev intel_cpu_dev = {
 			  [3] = "OverDrive PODP5V83",
 			  [4] = "Pentium MMX",
 			  [7] = "Mobile Pentium 75 - 200",
-			  [8] = "Mobile Pentium MMX"
+			  [8] = "Mobile Pentium MMX",
+			  [9] = "Quark SoC X1000",
 		  }
 		},
 		{ .family = 6, .model_names =
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 9f7ca266864a..832d05a914ba 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -26,6 +26,7 @@
 #include <asm/irq_regs.h>
 #include <asm/i8259.h>
 #include <asm/apic.h>
+#include <asm/timer.h>
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
@@ -105,6 +106,11 @@ static void __init ms_hyperv_init_platform(void)
 
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
 		clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
+
+#ifdef CONFIG_X86_IO_APIC
+	no_timer_check = 1;
+#endif
+
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index aa333d966886..1340ebfcb467 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1383,6 +1383,15 @@ again:
 	intel_pmu_lbr_read();
 
 	/*
+	 * CondChgd bit 63 doesn't mean any overflow status. Ignore
+	 * and clear the bit.
+	 */
+	if (__test_and_clear_bit(63, (unsigned long *)&status)) {
+		if (!status)
+			goto done;
+	}
+
+	/*
 	 * PEBS overflow sets bit 62 in the global status register
 	 */
 	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 5ad35ad94d0f..95700e52061d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -511,6 +511,7 @@ static int rapl_cpu_prepare(int cpu)
 	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
 	int phys_id = topology_physical_package_id(cpu);
 	u64 ms;
+	u64 msr_rapl_power_unit_bits;
 
 	if (pmu)
 		return 0;
@@ -518,6 +519,9 @@ static int rapl_cpu_prepare(int cpu)
 	if (phys_id < 0)
 		return -1;
 
+	if (!rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
+		return -1;
+
 	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
 	if (!pmu)
 		return -1;
@@ -531,8 +535,7 @@ static int rapl_cpu_prepare(int cpu)
 	 *
 	 * we cache in local PMU instance
 	 */
-	rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit);
-	pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL;
+	pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
 	pmu->pmu = &rapl_pmu_class;
 
 	/*
@@ -649,7 +652,9 @@ static int __init rapl_pmu_init(void)
 	get_online_cpus();
 
 	for_each_online_cpu(cpu) {
-		rapl_cpu_prepare(cpu);
+		ret = rapl_cpu_prepare(cpu);
+		if (ret)
+			goto out;
 		rapl_cpu_init(cpu);
 	}
 
@@ -672,6 +677,7 @@ static int __init rapl_pmu_init(void)
 		hweight32(rapl_cntr_mask),
 		ktime_to_ms(pmu->timer_interval));
 
+out:
 	put_online_cpus();
 
 	return 0;
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index bc4a088f9023..6d7d5a1260a6 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -203,18 +203,15 @@ static void __init intel_remapping_check(int num, int slot, int func)
 	revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
 
 	/*
- 	 * Revision 13 of all triggering devices id in this quirk have
-	 * a problem draining interrupts when irq remapping is enabled,
-	 * and should be flagged as broken.  Additionally revisions 0x12
-	 * and 0x22 of device id 0x3405 has this problem.
+	 * Revision <= 13 of all triggering devices id in this quirk
+	 * have a problem draining interrupts when irq remapping is
+	 * enabled, and should be flagged as broken. Additionally
+	 * revision 0x22 of device id 0x3405 has this problem.
 	 */
-	if (revision == 0x13)
+	if (revision <= 0x13)
 		set_irq_remapping_broken();
-	else if ((device == 0x3405) &&
-	    ((revision == 0x12) ||
-	     (revision == 0x22)))
+	else if (device == 0x3405 && revision == 0x22)
 		set_irq_remapping_broken();
-
 }
 
 /*
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index a2a4f4697889..c5a9cb94dee6 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -431,8 +431,9 @@ sysenter_past_esp:
 	jnz sysenter_audit
 sysenter_do_call:
 	cmpl $(NR_syscalls), %eax
-	jae syscall_badsys
+	jae sysenter_badsys
 	call *sys_call_table(,%eax,4)
+sysenter_after_call:
 	movl %eax,PT_EAX(%esp)
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_ANY)
@@ -513,6 +514,7 @@ ENTRY(system_call)
 	jae syscall_badsys
 syscall_call:
 	call *sys_call_table(,%eax,4)
+syscall_after_call:
 	movl %eax,PT_EAX(%esp)		# store the return value
 syscall_exit:
 	LOCKDEP_SYS_EXIT
@@ -527,6 +529,7 @@ 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 +540,7 @@ 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 +553,9 @@ 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 +597,7 @@ ldt_ss:
 	lss (%esp), %esp		/* switch to espfix segment */
 	CFI_ADJUST_CFA_OFFSET -8
 	jmp restore_nocheck
+#endif
 	CFI_ENDPROC
 ENDPROC(system_call)
 
@@ -687,8 +688,13 @@ syscall_fault:
 END(syscall_fault)
 
 syscall_badsys:
-	movl $-ENOSYS,PT_EAX(%esp)
-	jmp resume_userspace
+	movl $-ENOSYS,%eax
+	jmp syscall_after_call
+END(syscall_badsys)
+
+sysenter_badsys:
+	movl $-ENOSYS,%eax
+	jmp sysenter_after_call
 END(syscall_badsys)
 	CFI_ENDPROC
 /*
@@ -704,6 +710,7 @@ 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 +720,10 @@ 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 +734,7 @@ END(syscall_badsys)
 	/* switch to normal stack */
 	FIXUP_ESPFIX_STACK
 27:
+#endif
 .endm
 
 /*
@@ -1355,11 +1365,13 @@ 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 +1411,7 @@ 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 +1433,7 @@ 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..03cd2a8f6009 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.  */
@@ -1041,12 +1042,45 @@ restore_args:
 
 irq_return:
 	INTERRUPT_RETURN
-	_ASM_EXTABLE(irq_return, bad_iret)
 
-#ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
+	/*
+	 * 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 native_irq_return_ldt
+#endif
+
+native_irq_return_iret:
 	iretq
-	_ASM_EXTABLE(native_iret, bad_iret)
+	_ASM_EXTABLE(native_irq_return_iret, bad_iret)
+
+#ifdef CONFIG_X86_ESPFIX64
+native_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 native_irq_return_iret
 #endif
 
 	.section .fixup,"ax"
@@ -1110,9 +1144,40 @@ 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 $native_irq_return_iret,%rax
+	jne do_double_fault		/* This shouldn't happen... */
+	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 +1379,7 @@ 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 +1666,7 @@ error_sti:
  */
 error_kernelspace:
 	incl %ebx
-	leaq irq_return(%rip),%rcx
+	leaq native_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..94d857fb1033
--- /dev/null
+++ b/arch/x86/kernel/espfix_64.c
@@ -0,0 +1,208 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *   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_pmd(&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_pte(&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));
+	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/ftrace.c b/arch/x86/kernel/ftrace.c
index e6253195a301..1ffc32dbe450 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -659,8 +659,8 @@ ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
 		ret = -EPERM;
 		goto out;
 	}
-	run_sync();
  out:
+	run_sync();
 	return ret;
 
  fail_update:
diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c
index c3aae6672843..2e97b3cfa6c7 100644
--- a/arch/x86/kernel/iosf_mbi.c
+++ b/arch/x86/kernel/iosf_mbi.c
@@ -25,6 +25,10 @@
 
 #include <asm/iosf_mbi.h>
 
+#define PCI_DEVICE_ID_BAYTRAIL		0x0F00
+#define PCI_DEVICE_ID_BRASWELL		0x2280
+#define PCI_DEVICE_ID_QUARK_X1000	0x0958
+
 static DEFINE_SPINLOCK(iosf_mbi_lock);
 
 static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset)
@@ -177,6 +181,13 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask)
 }
 EXPORT_SYMBOL(iosf_mbi_modify);
 
+bool iosf_mbi_available(void)
+{
+	/* Mbi isn't hot-pluggable. No remove routine is provided */
+	return mbi_pdev;
+}
+EXPORT_SYMBOL(iosf_mbi_available);
+
 static int iosf_mbi_probe(struct pci_dev *pdev,
 			  const struct pci_device_id *unused)
 {
@@ -193,7 +204,9 @@ static int iosf_mbi_probe(struct pci_dev *pdev,
 }
 
 static DEFINE_PCI_DEVICE_TABLE(iosf_mbi_pci_ids) = {
-	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0F00) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) },
 	{ 0, },
 };
 MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids);
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ebc987398923..c37886d759cc 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -229,6 +229,11 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 		}
 	}
 
+	if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+		error = -EINVAL;
+		goto out_unlock;
+	}
+
 	fill_ldt(&ldt, &ldt_info);
 	if (oldmode)
 		ldt.avl = 0;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 3f08f34f93eb..a1da6737ba5b 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
 DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
 DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq");
 DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
-DEF_NATIVE(pv_cpu_ops, iret, "iretq");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
@@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_irq_ops, save_fl);
 		PATCH_SITE(pv_irq_ops, irq_enable);
 		PATCH_SITE(pv_irq_ops, irq_disable);
-		PATCH_SITE(pv_cpu_ops, iret);
 		PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret32);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret64);
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
index 2a26819bb6a8..80eab01c1a68 100644
--- a/arch/x86/kernel/resource.c
+++ b/arch/x86/kernel/resource.c
@@ -37,10 +37,12 @@ static void remove_e820_regions(struct resource *avail)
 
 void arch_remove_reservations(struct resource *avail)
 {
-	/* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */
+	/*
+	 * Trim out BIOS area (high 2MB) and E820 regions. We do not remove
+	 * the low 1MB unconditionally, as this area is needed for some ISA
+	 * cards requiring a memory range, e.g. the i82365 PCMCIA controller.
+	 */
 	if (avail->flags & IORESOURCE_MEM) {
-		if (avail->start < BIOS_END)
-			avail->start = BIOS_END;
 		resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END);
 
 		remove_e820_regions(avail);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 9e5de6813e1f..b88fc86309bc 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -673,6 +673,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		 * handler too.
 		 */
 		regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF);
+		/*
+		 * Ensure the signal handler starts with the new fpu state.
+		 */
+		if (used_math())
+			drop_init_fpu(current);
 	}
 	signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP));
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a32da804252e..682876533ed9 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -243,6 +243,13 @@ 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.
@@ -1280,6 +1287,9 @@ static void remove_siblinginfo(int cpu)
 
 	for_each_cpu(sibling, cpu_sibling_mask(cpu))
 		cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
+	for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
+		cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
+	cpumask_clear(cpu_llc_shared_mask(cpu));
 	cpumask_clear(cpu_sibling_mask(cpu));
 	cpumask_clear(cpu_core_mask(cpu));
 	c->phys_proc_id = 0;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index cfbe99f88830..de0290605903 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -921,9 +921,9 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 		tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
 		if (!(freq->flags & CPUFREQ_CONST_LOOPS))
 			mark_tsc_unstable("cpufreq changes");
-	}
 
-	set_cyc2ns_scale(tsc_khz, freq->cpu);
+		set_cyc2ns_scale(tsc_khz, freq->cpu);
+	}
 
 	return 0;
 }
@@ -1173,14 +1173,17 @@ void __init tsc_init(void)
 
 	x86_init.timers.tsc_pre_init();
 
-	if (!cpu_has_tsc)
+	if (!cpu_has_tsc) {
+		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 		return;
+	}
 
 	tsc_khz = x86_platform.calibrate_tsc();
 	cpu_khz = tsc_khz;
 
 	if (!tsc_khz) {
 		mark_tsc_unstable("could not calculate TSC khz");
+		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 		return;
 	}
 
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 1f96f9347ed9..09ce23ae370c 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -125,10 +125,10 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
 	if (!show_unhandled_signals)
 		return;
 
-	pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
-			      level, current->comm, task_pid_nr(current),
-			      message, regs->ip, regs->cs,
-			      regs->sp, regs->ax, regs->si, regs->di);
+	printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+			   level, current->comm, task_pid_nr(current),
+			   message, regs->ip, regs->cs,
+			   regs->sp, regs->ax, regs->si, regs->di);
 }
 
 static int addr_to_vsyscall_nr(unsigned long addr)
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index a4b451c6addf..dd50e26c58f6 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -268,8 +268,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
 		return -1;
 
-	drop_init_fpu(tsk);	/* trigger finit */
-
 	return 0;
 }
 
@@ -399,8 +397,11 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 			set_used_math();
 		}
 
-		if (use_eager_fpu())
+		if (use_eager_fpu()) {
+			preempt_disable();
 			math_state_restore();
+			preempt_enable();
+		}
 
 		return err;
 	} else {