Merge branch 'linus' into x86/urgent, to refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

12 files changed, 87 insertions, 121 deletions

diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index fb97cf7c4137..fab4df16a3c4 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -12,38 +12,23 @@
 #include <asm/user32.h>
 #include <asm/unistd.h>
 
+#include <asm-generic/compat.h>
+
 #define COMPAT_USER_HZ		100
 #define COMPAT_UTS_MACHINE	"i686\0\0"
 
-typedef u32		compat_size_t;
-typedef s32		compat_ssize_t;
-typedef s32		compat_clock_t;
-typedef s32		compat_pid_t;
 typedef u16		__compat_uid_t;
 typedef u16		__compat_gid_t;
 typedef u32		__compat_uid32_t;
 typedef u32		__compat_gid32_t;
 typedef u16		compat_mode_t;
-typedef u32		compat_ino_t;
 typedef u16		compat_dev_t;
-typedef s32		compat_off_t;
-typedef s64		compat_loff_t;
 typedef u16		compat_nlink_t;
 typedef u16		compat_ipc_pid_t;
-typedef s32		compat_daddr_t;
 typedef u32		compat_caddr_t;
 typedef __kernel_fsid_t	compat_fsid_t;
-typedef s32		compat_timer_t;
-typedef s32		compat_key_t;
-
-typedef s32		compat_int_t;
-typedef s32		compat_long_t;
 typedef s64 __attribute__((aligned(4))) compat_s64;
-typedef u32		compat_uint_t;
-typedef u32		compat_ulong_t;
-typedef u32		compat_u32;
 typedef u64 __attribute__((aligned(4))) compat_u64;
-typedef u32		compat_uptr_t;
 
 struct compat_stat {
 	compat_dev_t	st_dev;
@@ -240,6 +225,6 @@ static inline bool in_compat_syscall(void)
 
 struct compat_siginfo;
 int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
-		const siginfo_t *from, bool x32_ABI);
+		const kernel_siginfo_t *from, bool x32_ABI);
 
 #endif /* _ASM_X86_COMPAT_H */
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 5ed826da5e07..7469d321f072 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -13,75 +13,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
-/*
- * If the arch doesn't supply something else, assume that hugepage
- * size aligned regions are ok without further preparation.
- */
-static inline int prepare_hugepage_range(struct file *file,
-			unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-					  unsigned long addr, unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	return ptep_get_and_clear(mm, addr, ptep);
-}
-
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
-{
-	ptep_clear_flush(vma, addr, ptep);
-}
-
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
-
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 5f26962eff42..67ed72f31cc2 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -45,6 +45,8 @@ struct vcpu_data {
 
 #ifdef CONFIG_IRQ_REMAP
 
+extern raw_spinlock_t irq_2_ir_lock;
+
 extern bool irq_remapping_cap(enum irq_remap_cap cap);
 extern void set_irq_remapping_broken(void);
 extern int irq_remapping_prepare(void);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 09b2e3e2cf1b..55e51ff7e421 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -102,7 +102,15 @@
 #define UNMAPPED_GVA (~(gpa_t)0)
 
 /* KVM Hugepage definitions for x86 */
-#define KVM_NR_PAGE_SIZES	3
+enum {
+	PT_PAGE_TABLE_LEVEL   = 1,
+	PT_DIRECTORY_LEVEL    = 2,
+	PT_PDPE_LEVEL         = 3,
+	/* set max level to the biggest one */
+	PT_MAX_HUGEPAGE_LEVEL = PT_PDPE_LEVEL,
+};
+#define KVM_NR_PAGE_SIZES	(PT_MAX_HUGEPAGE_LEVEL - \
+				 PT_PAGE_TABLE_LEVEL + 1)
 #define KVM_HPAGE_GFN_SHIFT(x)	(((x) - 1) * 9)
 #define KVM_HPAGE_SHIFT(x)	(PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x))
 #define KVM_HPAGE_SIZE(x)	(1UL << KVM_HPAGE_SHIFT(x))
@@ -177,6 +185,7 @@ enum {
 
 #define DR6_BD		(1 << 13)
 #define DR6_BS		(1 << 14)
+#define DR6_BT		(1 << 15)
 #define DR6_RTM		(1 << 16)
 #define DR6_FIXED_1	0xfffe0ff0
 #define DR6_INIT	0xffff0ff0
@@ -247,7 +256,7 @@ struct kvm_mmu_memory_cache {
  * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp.
  */
 union kvm_mmu_page_role {
-	unsigned word;
+	u32 word;
 	struct {
 		unsigned level:4;
 		unsigned cr4_pae:1;
@@ -273,6 +282,34 @@ union kvm_mmu_page_role {
 	};
 };
 
+union kvm_mmu_extended_role {
+/*
+ * This structure complements kvm_mmu_page_role caching everything needed for
+ * MMU configuration. If nothing in both these structures changed, MMU
+ * re-configuration can be skipped. @valid bit is set on first usage so we don't
+ * treat all-zero structure as valid data.
+ */
+	u32 word;
+	struct {
+		unsigned int valid:1;
+		unsigned int execonly:1;
+		unsigned int cr0_pg:1;
+		unsigned int cr4_pse:1;
+		unsigned int cr4_pke:1;
+		unsigned int cr4_smap:1;
+		unsigned int cr4_smep:1;
+		unsigned int cr4_la57:1;
+	};
+};
+
+union kvm_mmu_role {
+	u64 as_u64;
+	struct {
+		union kvm_mmu_page_role base;
+		union kvm_mmu_extended_role ext;
+	};
+};
+
 struct kvm_rmap_head {
 	unsigned long val;
 };
@@ -280,18 +317,18 @@ struct kvm_rmap_head {
 struct kvm_mmu_page {
 	struct list_head link;
 	struct hlist_node hash_link;
+	bool unsync;
 
 	/*
 	 * The following two entries are used to key the shadow page in the
 	 * hash table.
 	 */
-	gfn_t gfn;
 	union kvm_mmu_page_role role;
+	gfn_t gfn;
 
 	u64 *spt;
 	/* hold the gfn of each spte inside spt */
 	gfn_t *gfns;
-	bool unsync;
 	int root_count;          /* Currently serving as active root */
 	unsigned int unsync_children;
 	struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
@@ -360,7 +397,7 @@ struct kvm_mmu {
 	void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			   u64 *spte, const void *pte);
 	hpa_t root_hpa;
-	union kvm_mmu_page_role base_role;
+	union kvm_mmu_role mmu_role;
 	u8 root_level;
 	u8 shadow_root_level;
 	u8 ept_ad;
@@ -490,7 +527,7 @@ struct kvm_vcpu_hv {
 	struct kvm_hyperv_exit exit;
 	struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT];
 	DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
-	cpumask_t tlb_lush;
+	cpumask_t tlb_flush;
 };
 
 struct kvm_vcpu_arch {
@@ -534,7 +571,13 @@ struct kvm_vcpu_arch {
 	 * the paging mode of the l1 guest. This context is always used to
 	 * handle faults.
 	 */
-	struct kvm_mmu mmu;
+	struct kvm_mmu *mmu;
+
+	/* Non-nested MMU for L1 */
+	struct kvm_mmu root_mmu;
+
+	/* L1 MMU when running nested */
+	struct kvm_mmu guest_mmu;
 
 	/*
 	 * Paging state of an L2 guest (used for nested npt)
@@ -585,6 +628,8 @@ struct kvm_vcpu_arch {
 		bool has_error_code;
 		u8 nr;
 		u32 error_code;
+		unsigned long payload;
+		bool has_payload;
 		u8 nested_apf;
 	} exception;
 
@@ -781,6 +826,9 @@ struct kvm_hv {
 	u64 hv_reenlightenment_control;
 	u64 hv_tsc_emulation_control;
 	u64 hv_tsc_emulation_status;
+
+	/* How many vCPUs have VP index != vCPU index */
+	atomic_t num_mismatched_vp_indexes;
 };
 
 enum kvm_irqchip_mode {
@@ -871,6 +919,7 @@ struct kvm_arch {
 	bool x2apic_broadcast_quirk_disabled;
 
 	bool guest_can_read_msr_platform_info;
+	bool exception_payload_enabled;
 };
 
 struct kvm_vm_stat {
@@ -1133,6 +1182,9 @@ struct kvm_x86_ops {
 	int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
 
 	int (*get_msr_feature)(struct kvm_msr_entry *entry);
+
+	int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu,
+				   uint16_t *vmcs_version);
 };
 
 struct kvm_arch_async_pf {
@@ -1170,7 +1222,6 @@ void kvm_mmu_module_exit(void);
 
 void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_mmu_create(struct kvm_vcpu *vcpu);
-void kvm_mmu_setup(struct kvm_vcpu *vcpu);
 void kvm_mmu_init_vm(struct kvm *kvm);
 void kvm_mmu_uninit_vm(struct kvm *kvm);
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
@@ -1324,7 +1375,8 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
-void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, ulong roots_to_free);
+void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+			ulong roots_to_free);
 gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
 			   struct x86_exception *exception);
 gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h
index 61eb4b63c5ec..d0b1434fb0b6 100644
--- a/arch/x86/include/asm/mpx.h
+++ b/arch/x86/include/asm/mpx.h
@@ -57,8 +57,14 @@
 #define MPX_BNDCFG_ADDR_MASK	(~((1UL<<MPX_BNDCFG_TAIL)-1))
 #define MPX_BNDSTA_ERROR_CODE	0x3
 
+struct mpx_fault_info {
+	void __user *addr;
+	void __user *lower;
+	void __user *upper;
+};
+
 #ifdef CONFIG_X86_INTEL_MPX
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs);
+int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs);
 int mpx_handle_bd_fault(void);
 static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
 {
@@ -78,9 +84,9 @@ void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
 unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len,
 		unsigned long flags);
 #else
-static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
+static inline int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs)
 {
-	return NULL;
+	return -EINVAL;
 }
 static inline int mpx_handle_bd_fault(void)
 {
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index f236bcd5485d..143c99499531 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -293,7 +293,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 #define arch_has_block_step()	(boot_cpu_data.x86 >= 6)
 #endif
 
-#define ARCH_HAS_USER_SINGLE_STEP_INFO
+#define ARCH_HAS_USER_SINGLE_STEP_REPORT
 
 /*
  * When hitting ptrace_stop(), we cannot return using SYSRET because
diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h
index 7bd92db09e8d..54133017267c 100644
--- a/arch/x86/include/asm/trace/mpx.h
+++ b/arch/x86/include/asm/trace/mpx.h
@@ -11,12 +11,12 @@
 
 TRACE_EVENT(mpx_bounds_register_exception,
 
-	TP_PROTO(void *addr_referenced,
+	TP_PROTO(void __user *addr_referenced,
 		 const struct mpx_bndreg *bndreg),
 	TP_ARGS(addr_referenced, bndreg),
 
 	TP_STRUCT__entry(
-		__field(void *, addr_referenced)
+		__field(void __user *, addr_referenced)
 		__field(u64, lower_bound)
 		__field(u64, upper_bound)
 	),
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 51c4eee00732..dc4ed8bc2382 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -24,6 +24,7 @@
 #  include <asm/unistd_64.h>
 #  include <asm/unistd_64_x32.h>
 #  define __ARCH_WANT_COMPAT_SYS_TIME
+#  define __ARCH_WANT_SYS_UTIME32
 #  define __ARCH_WANT_COMPAT_SYS_PREADV64
 #  define __ARCH_WANT_COMPAT_SYS_PWRITEV64
 #  define __ARCH_WANT_COMPAT_SYS_PREADV64V2
@@ -31,13 +32,13 @@
 
 # endif
 
+# define __ARCH_WANT_NEW_STAT
 # define __ARCH_WANT_OLD_READDIR
 # define __ARCH_WANT_OLD_STAT
 # define __ARCH_WANT_SYS_ALARM
 # define __ARCH_WANT_SYS_FADVISE64
 # define __ARCH_WANT_SYS_GETHOSTNAME
 # define __ARCH_WANT_SYS_GETPGRP
-# define __ARCH_WANT_SYS_LLSEEK
 # define __ARCH_WANT_SYS_NICE
 # define __ARCH_WANT_SYS_OLDUMOUNT
 # define __ARCH_WANT_SYS_OLD_GETRLIMIT
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index e05e0d309244..1fc7a0d1e877 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -40,7 +40,7 @@ static inline int cpu_has_vmx(void)
  */
 static inline void cpu_vmxoff(void)
 {
-	asm volatile (ASM_VMX_VMXOFF : : : "cc");
+	asm volatile ("vmxoff");
 	cr4_clear_bits(X86_CR4_VMXE);
 }
 
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 9527ba5d62da..ade0f153947d 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -503,19 +503,6 @@ enum vmcs_field {
 
 #define VMX_EPT_IDENTITY_PAGETABLE_ADDR		0xfffbc000ul
 
-
-#define ASM_VMX_VMCLEAR_RAX       ".byte 0x66, 0x0f, 0xc7, 0x30"
-#define ASM_VMX_VMLAUNCH          ".byte 0x0f, 0x01, 0xc2"
-#define ASM_VMX_VMRESUME          ".byte 0x0f, 0x01, 0xc3"
-#define ASM_VMX_VMPTRLD_RAX       ".byte 0x0f, 0xc7, 0x30"
-#define ASM_VMX_VMREAD_RDX_RAX    ".byte 0x0f, 0x78, 0xd0"
-#define ASM_VMX_VMWRITE_RAX_RDX   ".byte 0x0f, 0x79, 0xd0"
-#define ASM_VMX_VMWRITE_RSP_RDX   ".byte 0x0f, 0x79, 0xd4"
-#define ASM_VMX_VMXOFF            ".byte 0x0f, 0x01, 0xc4"
-#define ASM_VMX_VMXON_RAX         ".byte 0xf3, 0x0f, 0xc7, 0x30"
-#define ASM_VMX_INVEPT		  ".byte 0x66, 0x0f, 0x38, 0x80, 0x08"
-#define ASM_VMX_INVVPID		  ".byte 0x66, 0x0f, 0x38, 0x81, 0x08"
-
 struct vmx_msr_entry {
 	u32 index;
 	u32 reserved;
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index fd23d5778ea1..dabfcf7c3941 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -288,6 +288,7 @@ struct kvm_reinject_control {
 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
 #define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
 #define KVM_VCPUEVENT_VALID_SMM		0x00000008
+#define KVM_VCPUEVENT_VALID_PAYLOAD	0x00000010
 
 /* Interrupt shadow states */
 #define KVM_X86_SHADOW_INT_MOV_SS	0x01
@@ -299,7 +300,7 @@ struct kvm_vcpu_events {
 		__u8 injected;
 		__u8 nr;
 		__u8 has_error_code;
-		__u8 pad;
+		__u8 pending;
 		__u32 error_code;
 	} exception;
 	struct {
@@ -322,7 +323,9 @@ struct kvm_vcpu_events {
 		__u8 smm_inside_nmi;
 		__u8 latched_init;
 	} smi;
-	__u32 reserved[9];
+	__u8 reserved[27];
+	__u8 exception_has_payload;
+	__u64 exception_payload;
 };
 
 /* for KVM_GET/SET_DEBUGREGS */
@@ -381,6 +384,7 @@ struct kvm_sync_regs {
 
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
+#define KVM_STATE_NESTED_EVMCS		0x00000004
 
 #define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_SMM_VMXON	0x00000002
diff --git a/arch/x86/include/uapi/asm/siginfo.h b/arch/x86/include/uapi/asm/siginfo.h
index b3d157957177..6642d8be40c4 100644
--- a/arch/x86/include/uapi/asm/siginfo.h
+++ b/arch/x86/include/uapi/asm/siginfo.h
@@ -7,8 +7,6 @@
 typedef long long __kernel_si_clock_t __attribute__((aligned(4)));
 #  define __ARCH_SI_CLOCK_T		__kernel_si_clock_t
 #  define __ARCH_SI_ATTRIBUTES		__attribute__((aligned(8)))
-# else /* x86-64 */
-#  define __ARCH_SI_PREAMBLE_SIZE	(4 * sizeof(int))
 # endif
 #endif