19 files changed, 107 insertions, 33 deletions

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a30316bf801a..163769d82475 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -638,8 +638,8 @@ static inline void entering_irq(void)
 
 static inline void entering_ack_irq(void)
 {
-	ack_APIC_irq();
 	entering_irq();
+	ack_APIC_irq();
 }
 
 static inline void ipi_entering_ack_irq(void)
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1514753fd435..bcd3d6199464 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -245,12 +245,13 @@ extern int force_personality32;
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	4096
 
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-#define ELF_ET_DYN_BASE		(TASK_SIZE / 3 * 2)
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is above 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE		(mmap_is_ia32() ? 0x000400000UL : \
+						  (TASK_SIZE / 3 * 2))
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports.  This could be done in user space,
@@ -278,7 +279,7 @@ struct task_struct;
 
 #define	ARCH_DLINFO_IA32						\
 do {									\
-	if (vdso32_enabled) {						\
+	if (VDSO_CURRENT_BASE) {					\
 		NEW_AUX_ENT(AT_SYSINFO,	VDSO_ENTRY);			\
 		NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE);	\
 	}								\
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index f8a29d2c97b0..e6a8613fbfb0 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -4,6 +4,7 @@
 #include <asm/page.h>
 #include <asm-generic/hugetlb.h>
 
+#define hugepages_supported() cpu_has_pse
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 1e3408e88604..59caa55fb9b5 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -136,6 +136,7 @@ struct irq_alloc_info {
 struct irq_cfg {
 	unsigned int		dest_apicid;
 	u8			vector;
+	u8			old_vector;
 };
 
 extern struct irq_cfg *irq_cfg(unsigned int irq);
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index de25aad07853..9016b4b70375 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -304,13 +304,13 @@ static inline unsigned type in##bwl##_p(int port)			\
 static inline void outs##bwl(int port, const void *addr, unsigned long count) \
 {									\
 	asm volatile("rep; outs" #bwl					\
-		     : "+S"(addr), "+c"(count) : "d"(port));		\
+		     : "+S"(addr), "+c"(count) : "d"(port) : "memory");	\
 }									\
 									\
 static inline void ins##bwl(int port, void *addr, unsigned long count)	\
 {									\
 	asm volatile("rep; ins" #bwl					\
-		     : "+D"(addr), "+c"(count) : "d"(port));		\
+		     : "+D"(addr), "+c"(count) : "d"(port) : "memory");	\
 }
 
 BUILDIO(b, b, char)
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index e9cd7befcb76..19d14ac23ef9 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/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 30cfd64295a0..9d2abb2a41d2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -41,7 +41,7 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
-#define KVM_HALT_POLL_NS_DEFAULT 500000
+#define KVM_HALT_POLL_NS_DEFAULT 400000
 
 #define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
 
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 34e62b1dcfce..712b24ed3a64 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_MICROCODE_H
 
 #include <linux/earlycpio.h>
+#include <linux/initrd.h>
 
 #define native_rdmsr(msr, val1, val2)			\
 do {							\
@@ -168,4 +169,29 @@ static inline void reload_early_microcode(void)			{ }
 static inline bool
 get_builtin_firmware(struct cpio_data *cd, const char *name)	{ return false; }
 #endif
+
+static inline unsigned long get_initrd_start(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+	return initrd_start;
+#else
+	return 0;
+#endif
+}
+
+static inline unsigned long get_initrd_start_addr(void)
+{
+#ifdef CONFIG_BLK_DEV_INITRD
+#ifdef CONFIG_X86_32
+	unsigned long *initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
+
+	return (unsigned long)__pa_nodebug(*initrd_start_p);
+#else
+	return get_initrd_start();
+#endif
+#else /* CONFIG_BLK_DEV_INITRD */
+	return 0;
+#endif
+}
+
 #endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 690b4027e17c..37db36fddc88 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -405,6 +405,8 @@
 #define MSR_IA32_TSC_ADJUST             0x0000003b
 #define MSR_IA32_BNDCFGS		0x00000d90
 
+#define MSR_IA32_BNDCFGS_RSVD		0x00000ffc
+
 #define MSR_IA32_XSS			0x00000da0
 
 #define FEATURE_CONTROL_LOCKED				(1<<0)
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index b94f6f64e23d..dbff1456d215 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -24,6 +24,7 @@
 #define _ASM_X86_MTRR_H
 
 #include <uapi/asm/mtrr.h>
+#include <asm/pat.h>
 
 
 /*
@@ -83,9 +84,12 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn)
 static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
 {
 }
+static inline void mtrr_bp_init(void)
+{
+	pat_disable("MTRRs disabled, skipping PAT initialization too.");
+}
 
 #define mtrr_ap_init() do {} while (0)
-#define mtrr_bp_init() do {} while (0)
 #define set_mtrr_aps_delayed_init() do {} while (0)
 #define mtrr_aps_init() do {} while (0)
 #define mtrr_bp_restore() do {} while (0)
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index ca6c228d5e62..fffb2794dd89 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -5,8 +5,9 @@
 #include <asm/pgtable_types.h>
 
 bool pat_enabled(void);
+void pat_disable(const char *reason);
 extern void pat_init(void);
-void pat_init_cache_modes(u64);
+extern void init_cache_modes(void);
 
 extern int reserve_memtype(u64 start, u64 end,
 		enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index fa1195dae425..164e3f8d3c3d 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock;
 extern int (*pcibios_enable_irq)(struct pci_dev *dev);
 extern void (*pcibios_disable_irq)(struct pci_dev *dev);
 
+extern bool mp_should_keep_irq(struct device *dev);
+
 struct pci_raw_ops {
 	int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
 						int reg, int len, u32 *val);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 7bcb861a04e5..5a2ed3ed2f26 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -165,6 +165,7 @@ struct x86_pmu_capability {
 #define GLOBAL_STATUS_ASIF				BIT_ULL(60)
 #define GLOBAL_STATUS_COUNTERS_FROZEN			BIT_ULL(59)
 #define GLOBAL_STATUS_LBRS_FROZEN			BIT_ULL(58)
+#define GLOBAL_STATUS_TRACE_TOPAPMI			BIT_ULL(55)
 
 /*
  * IBS cpuid feature detection
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index d8ce3ec816ab..6503526d7b24 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -72,8 +72,8 @@ static inline void arch_wmb_pmem(void)
  * @size:	number of bytes to write back
  *
  * Write back a cache range using the CLWB (cache line write back)
- * instruction.  This function requires explicit ordering with an
- * arch_wmb_pmem() call.  This API is internal to the x86 PMEM implementation.
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
  */
 static inline void __arch_wb_cache_pmem(void *vaddr, size_t size)
 {
@@ -87,15 +87,6 @@ static inline void __arch_wb_cache_pmem(void *vaddr, size_t size)
 		clwb(p);
 }
 
-/*
- * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
- * iterators, so for other types (bvec & kvec) we must do a cache write-back.
- */
-static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
-{
-	return iter_is_iovec(i) == false;
-}
-
 /**
  * arch_copy_from_iter_pmem - copy data from an iterator to PMEM
  * @addr:	PMEM destination address
@@ -114,8 +105,36 @@ static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
 	/* TODO: skip the write-back by always using non-temporal stores */
 	len = copy_from_iter_nocache(vaddr, bytes, i);
 
-	if (__iter_needs_pmem_wb(i))
-		__arch_wb_cache_pmem(vaddr, bytes);
+	/*
+	 * In the iovec case on x86_64 copy_from_iter_nocache() uses
+	 * non-temporal stores for the bulk of the transfer, but we need
+	 * to manually flush if the transfer is unaligned. A cached
+	 * memory copy is used when destination or size is not naturally
+	 * aligned. That is:
+	 *   - Require 8-byte alignment when size is 8 bytes or larger.
+	 *   - Require 4-byte alignment when size is 4 bytes.
+	 *
+	 * In the non-iovec case the entire destination needs to be
+	 * flushed.
+	 */
+	if (iter_is_iovec(i)) {
+		unsigned long flushed, dest = (unsigned long) addr;
+
+		if (bytes < 8) {
+			if (!IS_ALIGNED(dest, 4) || (bytes != 4))
+				__arch_wb_cache_pmem(addr, bytes);
+		} else {
+			if (!IS_ALIGNED(dest, 8)) {
+				dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+				__arch_wb_cache_pmem(addr, 1);
+			}
+
+			flushed = dest - (unsigned long) addr;
+			if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8))
+				__arch_wb_cache_pmem(addr + bytes - 1, 1);
+		}
+	} else
+		__arch_wb_cache_pmem(addr, bytes);
 
 	return len;
 }
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 7a6bed5c08bc..baad72e4c100 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -76,6 +76,8 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
 	u8 ret_flags;
 
 	version = src->version;
+	/* Make the latest version visible */
+	smp_rmb();
 
 	offset = pvclock_get_nsec_offset(src);
 	ret = src->system_time + offset;
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6df2029405a3..6433e28dc9c8 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -32,7 +32,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
 /* Initialize cr4 shadow for this CPU. */
 static inline void cr4_init_shadow(void)
 {
-	this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
+	this_cpu_write(cpu_tlbstate.cr4, __read_cr4_safe());
 }
 
 /* Set in this cpu's CR4. */
@@ -86,7 +86,14 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
 
 static inline void __native_flush_tlb(void)
 {
+	/*
+	 * If current->mm == NULL then we borrow a mm which may change during a
+	 * task switch and therefore we must not be preempted while we write CR3
+	 * back:
+	 */
+	preempt_disable();
 	native_write_cr3(native_read_cr3());
+	preempt_enable();
 }
 
 static inline void __native_flush_tlb_global_irq_disabled(void)
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 09b1b0ab94b7..b8c75f3aade8 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -332,7 +332,7 @@ do {									\
 #define __get_user_asm_u64(x, ptr, retval, errret) \
 	 __get_user_asm(x, ptr, retval, "q", "", "=r", errret)
 #define __get_user_asm_ex_u64(x, ptr) \
-	 __get_user_asm_ex(x, ptr, "q", "", "=r")
+	 __get_user_asm_ex(x, ptr, "q", "", "=&r")
 #endif
 
 #define __get_user_size(x, ptr, size, retval, errret)			\
@@ -375,13 +375,13 @@ do {									\
 	__chk_user_ptr(ptr);						\
 	switch (size) {							\
 	case 1:								\
-		__get_user_asm_ex(x, ptr, "b", "b", "=q");		\
+		__get_user_asm_ex(x, ptr, "b", "b", "=&q");		\
 		break;							\
 	case 2:								\
-		__get_user_asm_ex(x, ptr, "w", "w", "=r");		\
+		__get_user_asm_ex(x, ptr, "w", "w", "=&r");		\
 		break;							\
 	case 4:								\
-		__get_user_asm_ex(x, ptr, "l", "k", "=r");		\
+		__get_user_asm_ex(x, ptr, "l", "k", "=&r");		\
 		break;							\
 	case 8:								\
 		__get_user_asm_ex_u64(x, ptr);				\
@@ -395,7 +395,7 @@ do {									\
 	asm volatile("1:	mov"itype" %1,%"rtype"0\n"		\
 		     "2:\n"						\
 		     _ASM_EXTABLE_EX(1b, 2b)				\
-		     : ltype(x) : "m" (__m(addr)))
+		     : ltype(x) : "m" (__m(addr)), "0" (0))
 
 #define __put_user_nocheck(x, ptr, size)			\
 ({								\
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 4c20dd333412..85133b2b8e99 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -43,6 +43,7 @@
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
+#include <asm/smap.h>
 
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
@@ -213,10 +214,12 @@ privcmd_call(unsigned call,
 	__HYPERCALL_DECLS;
 	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
 
+	stac();
 	asm volatile("call *%[call]"
 		     : __HYPERCALL_5PARAM
 		     : [call] "a" (&hypercall_page[call])
 		     : __HYPERCALL_CLOBBER5);
+	clac();
 
 	return (long)__res;
 }
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 8b2d4bea9962..39171b3646bb 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -62,4 +62,6 @@ void xen_arch_register_cpu(int num);
 void xen_arch_unregister_cpu(int num);
 #endif
 
+extern void xen_set_iopl_mask(unsigned mask);
+
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */