18 files changed, 96 insertions, 114 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index bdcdb3b3a219..84c00592d359 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -100,7 +100,6 @@ obj-$(CONFIG_HPET_TIMER) 	+= hpet.o
 obj-$(CONFIG_APB_TIMER)		+= apb_timer.o
 
 obj-$(CONFIG_AMD_NB)		+= amd_nb.o
-obj-$(CONFIG_DEBUG_RODATA_TEST)	+= test_rodata.o
 obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
 
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvmclock.o
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 63ff468a7986..82dfe32faaf4 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -695,7 +695,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info)
 	return -1;
 }
 
-static struct dma_map_ops gart_dma_ops = {
+static const struct dma_map_ops gart_dma_ops = {
 	.map_sg				= gart_map_sg,
 	.unmap_sg			= gart_unmap_sg,
 	.map_page			= gart_map_page,
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 015bbf30e3e3..c61aec7e65f4 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -82,7 +82,7 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	if (domain == NULL)
 		return -ENOSYS;
 
-	return pci_msi_domain_alloc_irqs(domain, dev, nvec, type);
+	return msi_domain_alloc_irqs(domain, &dev->dev, nvec);
 }
 
 void native_teardown_msi_irq(unsigned int irq)
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 210927ee2e74..99332f550c48 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -13,6 +13,10 @@ static char syscalls_ia32[] = {
 #include <asm/syscalls_32.h>
 };
 
+#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+#include <asm/kvm_para.h>
+#endif
+
 int main(void)
 {
 #ifdef CONFIG_PARAVIRT
@@ -22,6 +26,11 @@ int main(void)
 	BLANK();
 #endif
 
+#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS)
+	OFFSET(KVM_STEAL_TIME_preempted, kvm_steal_time, preempted);
+	BLANK();
+#endif
+
 #define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry)
 	ENTRY(bx);
 	ENTRY(cx);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f07005e6f461..c64ca5929cb5 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1510,7 +1510,7 @@ void cpu_init(void)
 	for (i = 0; i <= IO_BITMAP_LONGS; i++)
 		t->io_bitmap[i] = ~0UL;
 
-	atomic_inc(&init_mm.mm_count);
+	mmgrab(&init_mm);
 	me->active_mm = &init_mm;
 	BUG_ON(me->mm);
 	enter_lazy_tlb(&init_mm, me);
@@ -1561,7 +1561,7 @@ void cpu_init(void)
 	/*
 	 * Set up and load the per-CPU TSS and LDT
 	 */
-	atomic_inc(&init_mm.mm_count);
+	mmgrab(&init_mm);
 	curr->active_mm = &init_mm;
 	BUG_ON(curr->mm);
 	enter_lazy_tlb(&init_mm, curr);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 65e20c97e04b..b5375b9497b3 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -133,26 +133,6 @@ static uint32_t  __init ms_hyperv_platform(void)
 	return 0;
 }
 
-static u64 read_hv_clock(struct clocksource *arg)
-{
-	u64 current_tick;
-	/*
-	 * Read the partition counter to get the current tick count. This count
-	 * is set to 0 when the partition is created and is incremented in
-	 * 100 nanosecond units.
-	 */
-	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
-	return current_tick;
-}
-
-static struct clocksource hyperv_cs = {
-	.name		= "hyperv_clocksource",
-	.rating		= 400, /* use this when running on Hyperv*/
-	.read		= read_hv_clock,
-	.mask		= CLOCKSOURCE_MASK(64),
-	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
-};
-
 static unsigned char hv_get_nmi_reason(void)
 {
 	return 0;
@@ -180,6 +160,11 @@ static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs)
 
 static void __init ms_hyperv_init_platform(void)
 {
+	int hv_host_info_eax;
+	int hv_host_info_ebx;
+	int hv_host_info_ecx;
+	int hv_host_info_edx;
+
 	/*
 	 * Extract the features and hints
 	 */
@@ -190,6 +175,21 @@ static void __init ms_hyperv_init_platform(void)
 	pr_info("HyperV: features 0x%x, hints 0x%x\n",
 		ms_hyperv.features, ms_hyperv.hints);
 
+	/*
+	 * Extract host information.
+	 */
+	if (cpuid_eax(HVCPUID_VENDOR_MAXFUNCTION) >= HVCPUID_VERSION) {
+		hv_host_info_eax = cpuid_eax(HVCPUID_VERSION);
+		hv_host_info_ebx = cpuid_ebx(HVCPUID_VERSION);
+		hv_host_info_ecx = cpuid_ecx(HVCPUID_VERSION);
+		hv_host_info_edx = cpuid_edx(HVCPUID_VERSION);
+
+		pr_info("Hyper-V Host Build:%d-%d.%d-%d-%d.%d\n",
+			hv_host_info_eax, hv_host_info_ebx >> 16,
+			hv_host_info_ebx & 0xFFFF, hv_host_info_ecx,
+			hv_host_info_edx >> 24, hv_host_info_edx & 0xFFFFFF);
+	}
+
 #ifdef CONFIG_X86_LOCAL_APIC
 	if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) {
 		/*
@@ -208,9 +208,6 @@ static void __init ms_hyperv_init_platform(void)
 			     "hv_nmi_unknown");
 #endif
 
-	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
@@ -227,6 +224,13 @@ static void __init ms_hyperv_init_platform(void)
 	 */
 	if (efi_enabled(EFI_BOOT))
 		x86_platform.get_nmi_reason = hv_get_nmi_reason;
+
+#if IS_ENABLED(CONFIG_HYPERV)
+	/*
+	 * Setup the hook to get control post apic initialization.
+	 */
+	x86_platform.apic_post_init = hyperv_init;
+#endif
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 589b3193f102..b01bc8517450 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -16,6 +16,7 @@
 #include <linux/syscalls.h>
 #include <linux/bitmap.h>
 #include <asm/syscalls.h>
+#include <asm/desc.h>
 
 /*
  * this changes the io permissions bitmap in the current task.
@@ -45,6 +46,10 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
 		memset(bitmap, 0xff, IO_BITMAP_BYTES);
 		t->io_bitmap_ptr = bitmap;
 		set_thread_flag(TIF_IO_BITMAP);
+
+		preempt_disable();
+		refresh_TR();
+		preempt_enable();
 	}
 
 	/*
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 099fcba4981d..14f65a5f938e 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -589,7 +589,8 @@ out:
 	local_irq_restore(flags);
 }
 
-__visible bool __kvm_vcpu_is_preempted(int cpu)
+#ifdef CONFIG_X86_32
+__visible bool __kvm_vcpu_is_preempted(long cpu)
 {
 	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
 
@@ -597,6 +598,29 @@ __visible bool __kvm_vcpu_is_preempted(int cpu)
 }
 PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
 
+#else
+
+#include <asm/asm-offsets.h>
+
+extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
+
+/*
+ * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
+ * restoring to/from the stack.
+ */
+asm(
+".pushsection .text;"
+".global __raw_callee_save___kvm_vcpu_is_preempted;"
+".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
+"__raw_callee_save___kvm_vcpu_is_preempted:"
+"movq	__per_cpu_offset(,%rdi,8), %rax;"
+"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
+"setne	%al;"
+"ret;"
+".popsection");
+
+#endif
+
 /*
  * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
  */
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 542710b99f52..bae6ea6cfb94 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -28,6 +28,7 @@
 
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
+#include <asm/kvmclock.h>
 
 static int kvmclock __ro_after_init = 1;
 static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
@@ -49,6 +50,7 @@ struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
 {
 	return hv_clock;
 }
+EXPORT_SYMBOL_GPL(pvclock_pvti_cpu0_va);
 
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
@@ -174,13 +176,14 @@ bool kvm_check_and_clear_guest_paused(void)
 	return ret;
 }
 
-static struct clocksource kvm_clock = {
+struct clocksource kvm_clock = {
 	.name = "kvm-clock",
 	.read = kvm_clock_get_cycles,
 	.rating = 400,
 	.mask = CLOCKSOURCE_MASK(64),
 	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
 };
+EXPORT_SYMBOL_GPL(kvm_clock);
 
 int kvm_register_clock(char *txt)
 {
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 6259327f3454..8f2d1c9d43a8 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -20,7 +20,7 @@ bool pv_is_native_spin_unlock(void)
 		__raw_callee_save___native_queued_spin_unlock;
 }
 
-__visible bool __native_vcpu_is_preempted(int cpu)
+__visible bool __native_vcpu_is_preempted(long cpu)
 {
 	return false;
 }
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index a1bfba0f7234..4797e87b0fb6 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -425,6 +425,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
 	.pmd_clear = native_pmd_clear,
 #endif
 	.set_pud = native_set_pud,
+	.set_pud_at = native_set_pud_at,
 
 	.pmd_val = PTE_IDENT,
 	.make_pmd = PTE_IDENT,
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index d47517941bbc..0c150c06fa5a 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -478,7 +478,7 @@ static void calgary_free_coherent(struct device *dev, size_t size,
 	free_pages((unsigned long)vaddr, get_order(size));
 }
 
-static struct dma_map_ops calgary_dma_ops = {
+static const struct dma_map_ops calgary_dma_ops = {
 	.alloc = calgary_alloc_coherent,
 	.free = calgary_free_coherent,
 	.map_sg = calgary_map_sg,
@@ -1177,7 +1177,7 @@ static int __init calgary_init(void)
 		tbl = find_iommu_table(&dev->dev);
 
 		if (translation_enabled(tbl))
-			dev->dev.archdata.dma_ops = &calgary_dma_ops;
+			dev->dev.dma_ops = &calgary_dma_ops;
 	}
 
 	return ret;
@@ -1201,7 +1201,7 @@ error:
 		calgary_disable_translation(dev);
 		calgary_free_bus(dev);
 		pci_dev_put(dev); /* Undo calgary_init_one()'s pci_dev_get() */
-		dev->dev.archdata.dma_ops = NULL;
+		dev->dev.dma_ops = NULL;
 	} while (1);
 
 	return ret;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index d30c37750765..3a216ec869cd 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -17,7 +17,7 @@
 
 static int forbid_dac __read_mostly;
 
-struct dma_map_ops *dma_ops = &nommu_dma_ops;
+const struct dma_map_ops *dma_ops = &nommu_dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 static int iommu_sac_force __read_mostly;
@@ -91,7 +91,8 @@ again:
 	page = NULL;
 	/* CMA can be used only in the context which permits sleeping */
 	if (gfpflags_allow_blocking(flag)) {
-		page = dma_alloc_from_contiguous(dev, count, get_order(size));
+		page = dma_alloc_from_contiguous(dev, count, get_order(size),
+						 flag);
 		if (page && page_to_phys(page) + size > dma_mask) {
 			dma_release_from_contiguous(dev, page, count);
 			page = NULL;
@@ -214,7 +215,7 @@ early_param("iommu", iommu_setup);
 
 int dma_supported(struct device *dev, u64 mask)
 {
-	struct dma_map_ops *ops = get_dma_ops(dev);
+	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 #ifdef CONFIG_PCI
 	if (mask > 0xffffffff && forbid_dac > 0) {
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 00e71ce396a8..a88952ef371c 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -88,7 +88,7 @@ static void nommu_sync_sg_for_device(struct device *dev,
 	flush_write_buffers();
 }
 
-struct dma_map_ops nommu_dma_ops = {
+const struct dma_map_ops nommu_dma_ops = {
 	.alloc			= dma_generic_alloc_coherent,
 	.free			= dma_generic_free_coherent,
 	.map_sg			= nommu_map_sg,
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 410efb2c7b80..1e23577e17cf 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -45,7 +45,7 @@ void x86_swiotlb_free_coherent(struct device *dev, size_t size,
 		dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs);
 }
 
-static struct dma_map_ops swiotlb_dma_ops = {
+static const struct dma_map_ops swiotlb_dma_ops = {
 	.mapping_error = swiotlb_dma_mapping_error,
 	.alloc = x86_swiotlb_alloc_coherent,
 	.free = x86_swiotlb_free_coherent,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b615a1113f58..7780efa635b9 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -32,6 +32,7 @@
 #include <asm/mce.h>
 #include <asm/vm86.h>
 #include <asm/switch_to.h>
+#include <asm/desc.h>
 
 /*
  * per-CPU TSS segments. Threads are completely 'soft' on Linux,
@@ -64,6 +65,9 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 };
 EXPORT_PER_CPU_SYMBOL(cpu_tss);
 
+DEFINE_PER_CPU(bool, need_tr_refresh);
+EXPORT_PER_CPU_SYMBOL_GPL(need_tr_refresh);
+
 /*
  * this gets called so that we can store lazy state into memory and copy the
  * current task into the new thread.
@@ -209,6 +213,12 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		 */
 		memcpy(tss->io_bitmap, next->io_bitmap_ptr,
 		       max(prev->io_bitmap_max, next->io_bitmap_max));
+
+		/*
+		 * Make sure that the TSS limit is correct for the CPU
+		 * to notice the IO bitmap.
+		 */
+		refresh_TR();
 	} else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
 		/*
 		 * Clear any possible leftover bits:
diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c
deleted file mode 100644
index 222e84e2432e..000000000000
--- a/arch/x86/kernel/test_rodata.c
+++ /dev/null
@@ -1,75 +0,0 @@
-/*
- * test_rodata.c: functional test for mark_rodata_ro function
- *
- * (C) Copyright 2008 Intel Corporation
- * Author: Arjan van de Ven <arjan@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-#include <asm/cacheflush.h>
-#include <asm/sections.h>
-#include <asm/asm.h>
-
-int rodata_test(void)
-{
-	unsigned long result;
-	unsigned long start, end;
-
-	/* test 1: read the value */
-	/* If this test fails, some previous testrun has clobbered the state */
-	if (!rodata_test_data) {
-		printk(KERN_ERR "rodata_test: test 1 fails (start data)\n");
-		return -ENODEV;
-	}
-
-	/* test 2: write to the variable; this should fault */
-	/*
-	 * If this test fails, we managed to overwrite the data
-	 *
-	 * This is written in assembly to be able to catch the
-	 * exception that is supposed to happen in the correct
-	 * case
-	 */
-
-	result = 1;
-	asm volatile(
-		"0:	mov %[zero],(%[rodata_test])\n"
-		"	mov %[zero], %[rslt]\n"
-		"1:\n"
-		".section .fixup,\"ax\"\n"
-		"2:	jmp 1b\n"
-		".previous\n"
-		_ASM_EXTABLE(0b,2b)
-		: [rslt] "=r" (result)
-		: [rodata_test] "r" (&rodata_test_data), [zero] "r" (0UL)
-	);
-
-
-	if (!result) {
-		printk(KERN_ERR "rodata_test: test data was not read only\n");
-		return -ENODEV;
-	}
-
-	/* test 3: check the value hasn't changed */
-	/* If this test fails, we managed to overwrite the data */
-	if (!rodata_test_data) {
-		printk(KERN_ERR "rodata_test: Test 3 fails (end data)\n");
-		return -ENODEV;
-	}
-	/* test 4: check if the rodata section is 4Kb aligned */
-	start = (unsigned long)__start_rodata;
-	end = (unsigned long)__end_rodata;
-	if (start & (PAGE_SIZE - 1)) {
-		printk(KERN_ERR "rodata_test: .rodata is not 4k aligned\n");
-		return -ENODEV;
-	}
-	if (end & (PAGE_SIZE - 1)) {
-		printk(KERN_ERR "rodata_test: .rodata end is not 4k aligned\n");
-		return -ENODEV;
-	}
-
-	return 0;
-}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index e79f15f108a8..ad0118fbce90 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -346,6 +346,7 @@ SECTIONS
 	/DISCARD/ : {
 		*(.eh_frame)
 		*(__func_stack_frame_non_standard)
+		*(__unreachable)
 	}
 }