Merge tag 'v4.9.36' into linux-linaro-lsk-v4.9

 This is the 4.9.36 stable release

30 files changed, 200 insertions, 72 deletions

diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index 8f9a69c..efe5399 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -121,7 +121,7 @@
 &i2c3 {
 	clock-frequency = <400000>;
 	at24@50 {
-		compatible = "at24,24c02";
+		compatible = "atmel,24c64";
 		readonly;
 		reg = <0x50>;
 	};
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index e920dd8..f989145 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -222,6 +222,14 @@ static int _omap_device_notifier_call(struct notifier_block *nb,
 				dev_err(dev, "failed to idle\n");
 		}
 		break;
+	case BUS_NOTIFY_BIND_DRIVER:
+		od = to_omap_device(pdev);
+		if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED) &&
+		    pm_runtime_status_suspended(dev)) {
+			od->_driver_status = BUS_NOTIFY_BIND_DRIVER;
+			pm_runtime_set_active(dev);
+		}
+		break;
 	case BUS_NOTIFY_ADD_DEVICE:
 		if (pdev->dev.of_node)
 			omap_device_build_from_dt(pdev);
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 5cbfd9f..f7c7413 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1211,15 +1211,15 @@ void __init adjust_lowmem_bounds(void)
 
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
+	if (!memblock_limit)
+		memblock_limit = arm_lowmem_limit;
+
 	/*
 	 * Round the memblock limit down to a pmd size.  This
 	 * helps to ensure that we will allocate memory from the
 	 * last full pmd, which should be mapped.
 	 */
-	if (memblock_limit)
-		memblock_limit = round_down(memblock_limit, PMD_SIZE);
-	if (!memblock_limit)
-		memblock_limit = arm_lowmem_limit;
+	memblock_limit = round_down(memblock_limit, PMD_SIZE);
 
 	if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) {
 		if (memblock_end_of_DRAM() > arm_lowmem_limit) {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
index e6e3491..f150a4c 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
@@ -85,6 +85,18 @@
 	status = "okay";
 	pinctrl-0 = <&eth_pins>;
 	pinctrl-names = "default";
+	phy-handle = <&eth_phy0>;
+
+	mdio {
+		compatible = "snps,dwmac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		eth_phy0: ethernet-phy@0 {
+			reg = <0>;
+			eee-broken-1000t;
+		};
+	};
 };
 
 &ir {
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index e517088..de04879 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -22,9 +22,9 @@
 #define ACPI_MADT_GICC_LENGTH	\
 	(acpi_gbl_FADT.header.revision < 6 ? 76 : 80)
 
-#define BAD_MADT_GICC_ENTRY(entry, end)						\
-	(!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) ||	\
-	 (entry)->header.length != ACPI_MADT_GICC_LENGTH)
+#define BAD_MADT_GICC_ENTRY(entry, end)					\
+	(!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH ||	\
+	(unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end))
 
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 446f6c4..3a43011 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -164,22 +164,25 @@ lr	.req	x30		// link register
 
 /*
  * Pseudo-ops for PC-relative adr/ldr/str <reg>, <symbol> where
- * <symbol> is within the range +/- 4 GB of the PC.
+ * <symbol> is within the range +/- 4 GB of the PC when running
+ * in core kernel context. In module context, a movz/movk sequence
+ * is used, since modules may be loaded far away from the kernel
+ * when KASLR is in effect.
  */
 	/*
 	 * @dst: destination register (64 bit wide)
 	 * @sym: name of the symbol
-	 * @tmp: optional scratch register to be used if <dst> == sp, which
-	 *       is not allowed in an adrp instruction
 	 */
-	.macro	adr_l, dst, sym, tmp=
-	.ifb	\tmp
+	.macro	adr_l, dst, sym
+#ifndef MODULE
 	adrp	\dst, \sym
 	add	\dst, \dst, :lo12:\sym
-	.else
-	adrp	\tmp, \sym
-	add	\dst, \tmp, :lo12:\sym
-	.endif
+#else
+	movz	\dst, #:abs_g3:\sym
+	movk	\dst, #:abs_g2_nc:\sym
+	movk	\dst, #:abs_g1_nc:\sym
+	movk	\dst, #:abs_g0_nc:\sym
+#endif
 	.endm
 
 	/*
@@ -190,6 +193,7 @@ lr	.req	x30		// link register
 	 *       the address
 	 */
 	.macro	ldr_l, dst, sym, tmp=
+#ifndef MODULE
 	.ifb	\tmp
 	adrp	\dst, \sym
 	ldr	\dst, [\dst, :lo12:\sym]
@@ -197,6 +201,15 @@ lr	.req	x30		// link register
 	adrp	\tmp, \sym
 	ldr	\dst, [\tmp, :lo12:\sym]
 	.endif
+#else
+	.ifb	\tmp
+	adr_l	\dst, \sym
+	ldr	\dst, [\dst]
+	.else
+	adr_l	\tmp, \sym
+	ldr	\dst, [\tmp]
+	.endif
+#endif
 	.endm
 
 	/*
@@ -206,8 +219,13 @@ lr	.req	x30		// link register
 	 *       while <src> needs to be preserved.
 	 */
 	.macro	str_l, src, sym, tmp
+#ifndef MODULE
 	adrp	\tmp, \sym
 	str	\src, [\tmp, :lo12:\sym]
+#else
+	adr_l	\tmp, \sym
+	str	\src, [\tmp]
+#endif
 	.endm
 
 	/*
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 11f2890..d1e6b51 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -1010,7 +1010,7 @@ static bool have_cpu_die(void)
 #ifdef CONFIG_HOTPLUG_CPU
 	int any_cpu = raw_smp_processor_id();
 
-	if (cpu_ops[any_cpu]->cpu_die)
+	if (cpu_ops[any_cpu] && cpu_ops[any_cpu]->cpu_die)
 		return true;
 #endif
 	return false;
diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S
index 7791840..db07793 100644
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -11,6 +11,7 @@
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
 #include <asm/compiler.h>
+#include <asm/irqflags.h>
 #include <asm/regdef.h>
 #include <asm/mipsregs.h>
 #include <asm/stackframe.h>
@@ -137,6 +138,7 @@ work_pending:
 	andi	t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS
 	beqz	t0, work_notifysig
 work_resched:
+	TRACE_IRQS_OFF
 	jal	schedule
 
 	local_irq_disable		# make sure need_resched and
@@ -173,6 +175,7 @@ syscall_exit_work:
 	beqz	t0, work_pending	# trace bit set?
 	local_irq_enable		# could let syscall_trace_leave()
 					# call schedule() instead
+	TRACE_IRQS_ON
 	move	a0, sp
 	jal	syscall_trace_leave
 	b	resume_userspace
diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S
index cf05220..d1bb506 100644
--- a/arch/mips/kernel/head.S
+++ b/arch/mips/kernel/head.S
@@ -106,8 +106,8 @@ NESTED(kernel_entry, 16, sp)			# kernel entry point
 	beq		t0, t1, dtb_found
 #endif
 	li		t1, -2
-	beq		a0, t1, dtb_found
 	move		t2, a1
+	beq		a0, t1, dtb_found
 
 	li		t2, 0
 dtb_found:
diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c
index 7cf653e..60c4d45 100644
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -56,7 +56,6 @@ DECLARE_BITMAP(state_support, CPS_PM_STATE_COUNT);
  * state. Actually per-core rather than per-CPU.
  */
 static DEFINE_PER_CPU_ALIGNED(u32*, ready_count);
-static DEFINE_PER_CPU_ALIGNED(void*, ready_count_alloc);
 
 /* Indicates online CPUs coupled with the current CPU */
 static DEFINE_PER_CPU_ALIGNED(cpumask_t, online_coupled);
@@ -642,7 +641,6 @@ static int cps_pm_online_cpu(unsigned int cpu)
 {
 	enum cps_pm_state state;
 	unsigned core = cpu_data[cpu].core;
-	unsigned dlinesz = cpu_data[cpu].dcache.linesz;
 	void *entry_fn, *core_rc;
 
 	for (state = CPS_PM_NC_WAIT; state < CPS_PM_STATE_COUNT; state++) {
@@ -662,16 +660,11 @@ static int cps_pm_online_cpu(unsigned int cpu)
 	}
 
 	if (!per_cpu(ready_count, core)) {
-		core_rc = kmalloc(dlinesz * 2, GFP_KERNEL);
+		core_rc = kmalloc(sizeof(u32), GFP_KERNEL);
 		if (!core_rc) {
 			pr_err("Failed allocate core %u ready_count\n", core);
 			return -ENOMEM;
 		}
-		per_cpu(ready_count_alloc, core) = core_rc;
-
-		/* Ensure ready_count is aligned to a cacheline boundary */
-		core_rc += dlinesz - 1;
-		core_rc = (void *)((unsigned long)core_rc & ~(dlinesz - 1));
 		per_cpu(ready_count, core) = core_rc;
 	}
 
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index ec87ef9..b0b29cb 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -199,6 +199,8 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 {
 	struct pt_regs regs;
 	mm_segment_t old_fs = get_fs();
+
+	regs.cp0_status = KSU_KERNEL;
 	if (sp) {
 		regs.regs[29] = (unsigned long)sp;
 		regs.regs[31] = 0;
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index f257316..e5bfbf6 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -298,9 +298,17 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 	 *
 	 * For pHyp, we have to enable IO for log retrieval. Otherwise,
 	 * 0xFF's is always returned from PCI config space.
+	 *
+	 * When the @severity is EEH_LOG_PERM, the PE is going to be
+	 * removed. Prior to that, the drivers for devices included in
+	 * the PE will be closed. The drivers rely on working IO path
+	 * to bring the devices to quiet state. Otherwise, PCI traffic
+	 * from those devices after they are removed is like to cause
+	 * another unexpected EEH error.
 	 */
 	if (!(pe->type & EEH_PE_PHB)) {
-		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG))
+		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG) ||
+		    severity == EEH_LOG_PERM)
 			eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
 
 		/*
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index d7697ab..8e136b8 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -15,7 +15,9 @@
 	BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\
 	asm volatile(							\
 		"	lctlg	%1,%2,%0\n"				\
-		: : "Q" (*(addrtype *)(&array)), "i" (low), "i" (high));\
+		:							\
+		: "Q" (*(addrtype *)(&array)), "i" (low), "i" (high)	\
+		: "memory");						\
 }
 
 #define __ctl_store(array, low, high) {					\
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index e1b1ce6..5cbf03c 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -1021,7 +1021,7 @@ static void __init alloc_one_queue(unsigned long *pa_ptr, unsigned long qmask)
 	unsigned long order = get_order(size);
 	unsigned long p;
 
-	p = __get_free_pages(GFP_KERNEL, order);
+	p = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
 	if (!p) {
 		prom_printf("SUN4V: Error, cannot allocate queue.\n");
 		prom_halt();
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 496fa92..d44fb80 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2051,6 +2051,73 @@ void sun4v_resum_overflow(struct pt_regs *regs)
 	atomic_inc(&sun4v_resum_oflow_cnt);
 }
 
+/* Given a set of registers, get the virtual addressi that was being accessed
+ * by the faulting instructions at tpc.
+ */
+static unsigned long sun4v_get_vaddr(struct pt_regs *regs)
+{
+	unsigned int insn;
+
+	if (!copy_from_user(&insn, (void __user *)regs->tpc, 4)) {
+		return compute_effective_address(regs, insn,
+						 (insn >> 25) & 0x1f);
+	}
+	return 0;
+}
+
+/* Attempt to handle non-resumable errors generated from userspace.
+ * Returns true if the signal was handled, false otherwise.
+ */
+bool sun4v_nonresum_error_user_handled(struct pt_regs *regs,
+				  struct sun4v_error_entry *ent) {
+
+	unsigned int attrs = ent->err_attrs;
+
+	if (attrs & SUN4V_ERR_ATTRS_MEMORY) {
+		unsigned long addr = ent->err_raddr;
+		siginfo_t info;
+
+		if (addr == ~(u64)0) {
+			/* This seems highly unlikely to ever occur */
+			pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory error detected in unknown location!\n");
+		} else {
+			unsigned long page_cnt = DIV_ROUND_UP(ent->err_size,
+							      PAGE_SIZE);
+
+			/* Break the unfortunate news. */
+			pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory failed at %016lX\n",
+				 addr);
+			pr_emerg("SUN4V NON-RECOVERABLE ERROR:   Claiming %lu ages.\n",
+				 page_cnt);
+
+			while (page_cnt-- > 0) {
+				if (pfn_valid(addr >> PAGE_SHIFT))
+					get_page(pfn_to_page(addr >> PAGE_SHIFT));
+				addr += PAGE_SIZE;
+			}
+		}
+		info.si_signo = SIGKILL;
+		info.si_errno = 0;
+		info.si_trapno = 0;
+		force_sig_info(info.si_signo, &info, current);
+
+		return true;
+	}
+	if (attrs & SUN4V_ERR_ATTRS_PIO) {
+		siginfo_t info;
+
+		info.si_signo = SIGBUS;
+		info.si_code = BUS_ADRERR;
+		info.si_addr = (void __user *)sun4v_get_vaddr(regs);
+		force_sig_info(info.si_signo, &info, current);
+
+		return true;
+	}
+
+	/* Default to doing nothing */
+	return false;
+}
+
 /* We run with %pil set to PIL_NORMAL_MAX and PSTATE_IE enabled in %pstate.
  * Log the event, clear the first word of the entry, and die.
  */
@@ -2075,6 +2142,12 @@ void sun4v_nonresum_error(struct pt_regs *regs, unsigned long offset)
 
 	put_cpu();
 
+	if (!(regs->tstate & TSTATE_PRIV) &&
+	    sun4v_nonresum_error_user_handled(regs, &local_copy)) {
+		/* DON'T PANIC: This userspace error was handled. */
+		return;
+	}
+
 #ifdef CONFIG_PCI
 	/* Check for the special PCI poke sequence. */
 	if (pci_poke_in_progress && pci_poke_cpu == cpu) {
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index a66854d..6de58f1 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -430,9 +430,6 @@ void choose_random_location(unsigned long input,
 {
 	unsigned long random_addr, min_addr;
 
-	/* By default, keep output position unchanged. */
-	*virt_addr = *output;
-
 	if (cmdline_find_option_bool("nokaslr")) {
 		warn("KASLR disabled: 'nokaslr' on cmdline.");
 		return;
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index b3c5a5f0..c945acd 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -338,7 +338,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 				  unsigned long output_len)
 {
 	const unsigned long kernel_total_size = VO__end - VO__text;
-	unsigned long virt_addr = (unsigned long)output;
+	unsigned long virt_addr = LOAD_PHYSICAL_ADDR;
 
 	/* Retain x86 boot parameters pointer passed from startup_32/64. */
 	boot_params = rmode;
@@ -397,7 +397,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 #ifndef CONFIG_RELOCATABLE
 	if ((unsigned long)output != LOAD_PHYSICAL_ADDR)
 		error("Destination address does not match LOAD_PHYSICAL_ADDR");
-	if ((unsigned long)output != virt_addr)
+	if (virt_addr != LOAD_PHYSICAL_ADDR)
 		error("Destination virtual address changed when not relocatable");
 #endif
 
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 1c8355e..766a521 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -81,8 +81,6 @@ static inline void choose_random_location(unsigned long input,
 					  unsigned long output_size,
 					  unsigned long *virt_addr)
 {
-	/* No change from existing output location. */
-	*virt_addr = *output;
 }
 #endif
 
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 38623e2..9604b25 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -505,6 +505,10 @@ int x86_pmu_hw_config(struct perf_event *event)
 
 		if (event->attr.precise_ip > precise)
 			return -EOPNOTSUPP;
+
+		/* There's no sense in having PEBS for non sampling events: */
+		if (!is_sampling_event(event))
+			return -EINVAL;
 	}
 	/*
 	 * check that PEBS LBR correction does not conflict with
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 3bdb917..f0f197f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3164,13 +3164,16 @@ static void intel_pmu_cpu_starting(int cpu)
 
 	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
 		for_each_cpu(i, topology_sibling_cpumask(cpu)) {
+			struct cpu_hw_events *sibling;
 			struct intel_excl_cntrs *c;
 
-			c = per_cpu(cpu_hw_events, i).excl_cntrs;
+			sibling = &per_cpu(cpu_hw_events, i);
+			c = sibling->excl_cntrs;
 			if (c && c->core_id == core_id) {
 				cpuc->kfree_on_online[1] = cpuc->excl_cntrs;
 				cpuc->excl_cntrs = c;
-				cpuc->excl_thread_id = 1;
+				if (!sibling->excl_thread_id)
+					cpuc->excl_thread_id = 1;
 				break;
 			}
 		}
@@ -3975,7 +3978,7 @@ __init int intel_pmu_init(void)
 		     x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC);
 		x86_pmu.num_counters = INTEL_PMC_MAX_GENERIC;
 	}
-	x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+	x86_pmu.intel_ctrl = (1ULL << x86_pmu.num_counters) - 1;
 
 	if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED) {
 		WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 2724277..afe8024 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2686,7 +2686,7 @@ static struct intel_uncore_type *hswep_msr_uncores[] = {
 
 void hswep_uncore_cpu_init(void)
 {
-	int pkg = topology_phys_to_logical_pkg(0);
+	int pkg = boot_cpu_data.logical_proc_id;
 
 	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index e9cd7be..19d14ac 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -221,6 +221,9 @@ struct x86_emulate_ops {
 	void (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
 			  u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
 	void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
+
+	unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
+	void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags);
 };
 
 typedef u32 __attribute__((vector_size(16))) sse128_t;
@@ -290,7 +293,6 @@ struct x86_emulate_ctxt {
 
 	/* interruptibility state, as a result of execution of STI or MOV SS */
 	int interruptibility;
-	int emul_flags;
 
 	bool perm_ok; /* do not check permissions if true */
 	bool ud;	/* inject an #UD if host doesn't support insn */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index eea88fe..6e57edf 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -694,6 +694,7 @@ unsigned long native_calibrate_tsc(void)
 			crystal_khz = 24000;	/* 24.0 MHz */
 			break;
 		case INTEL_FAM6_SKYLAKE_X:
+		case INTEL_FAM6_ATOM_DENVERTON:
 			crystal_khz = 25000;	/* 25.0 MHz */
 			break;
 		case INTEL_FAM6_ATOM_GOLDMONT:
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 9f676ad..de36660 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2543,7 +2543,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
 	u64 smbase;
 	int ret;
 
-	if ((ctxt->emul_flags & X86EMUL_SMM_MASK) == 0)
+	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
 		return emulate_ud(ctxt);
 
 	/*
@@ -2592,11 +2592,11 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
 		return X86EMUL_UNHANDLEABLE;
 	}
 
-	if ((ctxt->emul_flags & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
 		ctxt->ops->set_nmi_mask(ctxt, false);
 
-	ctxt->emul_flags &= ~X86EMUL_SMM_INSIDE_NMI_MASK;
-	ctxt->emul_flags &= ~X86EMUL_SMM_MASK;
+	ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
+		~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
 	return X86EMUL_CONTINUE;
 }
 
@@ -5312,6 +5312,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 	const struct x86_emulate_ops *ops = ctxt->ops;
 	int rc = X86EMUL_CONTINUE;
 	int saved_dst_type = ctxt->dst.type;
+	unsigned emul_flags;
 
 	ctxt->mem_read.pos = 0;
 
@@ -5326,6 +5327,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 		goto done;
 	}
 
+	emul_flags = ctxt->ops->get_hflags(ctxt);
 	if (unlikely(ctxt->d &
 		     (No64|Undefined|Sse|Mmx|Intercept|CheckPerm|Priv|Prot|String))) {
 		if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) ||
@@ -5359,7 +5361,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 				fetch_possible_mmx_operand(ctxt, &ctxt->dst);
 		}
 
-		if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) {
+		if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) {
 			rc = emulator_check_intercept(ctxt, ctxt->intercept,
 						      X86_ICPT_PRE_EXCEPT);
 			if (rc != X86EMUL_CONTINUE)
@@ -5388,7 +5390,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 				goto done;
 		}
 
-		if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
+		if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
 			rc = emulator_check_intercept(ctxt, ctxt->intercept,
 						      X86_ICPT_POST_EXCEPT);
 			if (rc != X86EMUL_CONTINUE)
@@ -5442,7 +5444,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 
 special_insn:
 
-	if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
+	if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
 		rc = emulator_check_intercept(ctxt, ctxt->intercept,
 					      X86_ICPT_POST_MEMACCESS);
 		if (rc != X86EMUL_CONTINUE)
diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c
index 9d4a850..5ab4a36 100644
--- a/arch/x86/kvm/pmu_intel.c
+++ b/arch/x86/kvm/pmu_intel.c
@@ -294,7 +294,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 			((u64)1 << edx.split.bit_width_fixed) - 1;
 	}
 
-	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
+	pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) |
 		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
 	pmu->global_ctrl_mask = ~pmu->global_ctrl;
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 89b98e0..04e6bbb 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2455,7 +2455,7 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
 	if (!(vmcs12->exception_bitmap & (1u << nr)))
 		return 0;
 
-	nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
+	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 			  vmcs_read32(VM_EXIT_INTR_INFO),
 			  vmcs_readl(EXIT_QUALIFICATION));
 	return 1;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 62cde4f..3dbcb09 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4999,6 +4999,8 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector,
 
 	if (var.unusable) {
 		memset(desc, 0, sizeof(*desc));
+		if (base3)
+			*base3 = 0;
 		return false;
 	}
 
@@ -5154,6 +5156,16 @@ static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked)
 	kvm_x86_ops->set_nmi_mask(emul_to_vcpu(ctxt), masked);
 }
 
+static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
+{
+	return emul_to_vcpu(ctxt)->arch.hflags;
+}
+
+static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
+{
+	kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+}
+
 static const struct x86_emulate_ops emulate_ops = {
 	.read_gpr            = emulator_read_gpr,
 	.write_gpr           = emulator_write_gpr,
@@ -5193,6 +5205,8 @@ static const struct x86_emulate_ops emulate_ops = {
 	.intercept           = emulator_intercept,
 	.get_cpuid           = emulator_get_cpuid,
 	.set_nmi_mask        = emulator_set_nmi_mask,
+	.get_hflags          = emulator_get_hflags,
+	.set_hflags          = emulator_set_hflags,
 };
 
 static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
@@ -5245,7 +5259,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 	BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK);
 	BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
 	BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK);
-	ctxt->emul_flags = vcpu->arch.hflags;
 
 	init_decode_cache(ctxt);
 	vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
@@ -5636,8 +5649,6 @@ restart:
 		unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
-		if (vcpu->arch.hflags != ctxt->emul_flags)
-			kvm_set_hflags(vcpu, ctxt->emul_flags);
 		kvm_rip_write(vcpu, ctxt->eip);
 		if (r == EMULATE_DONE)
 			kvm_vcpu_check_singlestep(vcpu, rflags, &r);
@@ -6111,7 +6122,8 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt)
 
 	kvm_x86_ops->patch_hypercall(vcpu, instruction);
 
-	return emulator_write_emulated(ctxt, rip, instruction, 3, NULL);
+	return emulator_write_emulated(ctxt, rip, instruction, 3,
+		&ctxt->exception);
 }
 
 static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 14b9dd7..9a324fc 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -94,10 +94,10 @@ __setup("noexec32=", nonx32_setup);
  */
 void sync_global_pgds(unsigned long start, unsigned long end, int removed)
 {
-	unsigned long address;
+	unsigned long addr;
 
-	for (address = start; address <= end; address += PGDIR_SIZE) {
-		const pgd_t *pgd_ref = pgd_offset_k(address);
+	for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
+		const pgd_t *pgd_ref = pgd_offset_k(addr);
 		struct page *page;
 
 		/*
@@ -113,7 +113,7 @@ void sync_global_pgds(unsigned long start, unsigned long end, int removed)
 			pgd_t *pgd;
 			spinlock_t *pgt_lock;
 
-			pgd = (pgd_t *)page_address(page) + pgd_index(address);
+			pgd = (pgd_t *)page_address(page) + pgd_index(addr);
 			/* the pgt_lock only for Xen */
 			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
 			spin_lock(pgt_lock);
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index e4f8009..a75103e 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -293,7 +293,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
 	 * We were not able to extract an address from the instruction,
 	 * probably because there was something invalid in it.
 	 */
-	if (info->si_addr == (void *)-1) {
+	if (info->si_addr == (void __user *)-1) {
 		err = -EINVAL;
 		goto err_out;
 	}
@@ -525,15 +525,7 @@ int mpx_handle_bd_fault(void)
 	if (!kernel_managing_mpx_tables(current->mm))
 		return -EINVAL;
 
-	if (do_mpx_bt_fault()) {
-		force_sig(SIGSEGV, current);
-		/*
-		 * The force_sig() is essentially "handling" this
-		 * exception, so we do not pass up the error
-		 * from do_mpx_bt_fault().
-		 */
-	}
-	return 0;
+	return do_mpx_bt_fault();
 }
 
 /*
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index a7655f6..75fb011 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -263,8 +263,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 {
 	struct flush_tlb_info info;
 
-	if (end == 0)
-		end = start + PAGE_SIZE;
 	info.flush_mm = mm;
 	info.flush_start = start;
 	info.flush_end = end;
@@ -393,7 +391,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
 	}
 
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, start, 0UL);
+		flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE);
 
 	preempt_enable();
 }