Merge branch 'kvm-amd-fixes' into HEAD

13 files changed, 155 insertions, 66 deletions

diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index ff6f3ca649b3..dd17c2da1af5 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -44,6 +44,7 @@ unsigned int x86_stepping(unsigned int sig);
 extern void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c);
 extern void switch_to_sld(unsigned long tifn);
 extern bool handle_user_split_lock(struct pt_regs *regs, long error_code);
+extern bool handle_guest_split_lock(unsigned long ip);
 #else
 static inline void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c) {}
 static inline void switch_to_sld(unsigned long tifn) {}
@@ -51,5 +52,10 @@ static inline bool handle_user_split_lock(struct pt_regs *regs, long error_code)
 {
 	return false;
 }
+
+static inline bool handle_guest_split_lock(unsigned long ip)
+{
+	return false;
+}
 #endif
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
index f71a0cce9373..430fca13bb56 100644
--- a/arch/x86/include/asm/dwarf2.h
+++ b/arch/x86/include/asm/dwarf2.h
@@ -6,15 +6,6 @@
 #warning "asm/dwarf2.h should be only included in pure assembly files"
 #endif
 
-/*
- * Macros for dwarf2 CFI unwind table entries.
- * See "as.info" for details on these pseudo ops. Unfortunately
- * they are only supported in very new binutils, so define them
- * away for older version.
- */
-
-#ifdef CONFIG_AS_CFI
-
 #define CFI_STARTPROC		.cfi_startproc
 #define CFI_ENDPROC		.cfi_endproc
 #define CFI_DEF_CFA		.cfi_def_cfa
@@ -30,13 +21,6 @@
 #define CFI_UNDEFINED		.cfi_undefined
 #define CFI_ESCAPE		.cfi_escape
 
-#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME	.cfi_signal_frame
-#else
-#define CFI_SIGNAL_FRAME
-#endif
-
-#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__)
 #ifndef BUILD_VDSO
 	/*
 	 * Emit CFI data in .debug_frame sections, not .eh_frame sections.
@@ -53,33 +37,5 @@
 	  */
 	.cfi_sections .eh_frame, .debug_frame
 #endif
-#endif
-
-#else
-
-/*
- * Due to the structure of pre-exisiting code, don't use assembler line
- * comment character # to ignore the arguments. Instead, use a dummy macro.
- */
-.macro cfi_ignore a=0, b=0, c=0, d=0
-.endm
-
-#define CFI_STARTPROC		cfi_ignore
-#define CFI_ENDPROC		cfi_ignore
-#define CFI_DEF_CFA		cfi_ignore
-#define CFI_DEF_CFA_REGISTER	cfi_ignore
-#define CFI_DEF_CFA_OFFSET	cfi_ignore
-#define CFI_ADJUST_CFA_OFFSET	cfi_ignore
-#define CFI_OFFSET		cfi_ignore
-#define CFI_REL_OFFSET		cfi_ignore
-#define CFI_REGISTER		cfi_ignore
-#define CFI_RESTORE		cfi_ignore
-#define CFI_REMEMBER_STATE	cfi_ignore
-#define CFI_RESTORE_STATE	cfi_ignore
-#define CFI_UNDEFINED		cfi_ignore
-#define CFI_ESCAPE		cfi_ignore
-#define CFI_SIGNAL_FRAME	cfi_ignore
-
-#endif
 
 #endif /* _ASM_X86_DWARF2_H */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index cdcf48d52a12..8391c115c0ec 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -178,8 +178,10 @@ extern void efi_free_boot_services(void);
 extern pgd_t * __init efi_uv1_memmap_phys_prolog(void);
 extern void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd);
 
+/* kexec external ABI */
 struct efi_setup_data {
 	u64 fw_vendor;
+	u64 __unused;
 	u64 tables;
 	u64 smbios;
 	u64 reserved[8];
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 92abc1e42bfc..29336574d0bc 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -376,6 +376,7 @@ struct hv_tsc_emulation_status {
 #define HVCALL_SEND_IPI_EX			0x0015
 #define HVCALL_POST_MESSAGE			0x005c
 #define HVCALL_SIGNAL_EVENT			0x005d
+#define HVCALL_RETARGET_INTERRUPT		0x007e
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0
 
@@ -405,6 +406,8 @@ enum HV_GENERIC_SET_FORMAT {
 	HV_GENERIC_SET_ALL,
 };
 
+#define HV_PARTITION_ID_SELF                    ((u64)-1)
+
 #define HV_HYPERCALL_RESULT_MASK	GENMASK_ULL(15, 0)
 #define HV_HYPERCALL_FAST_BIT		BIT(16)
 #define HV_HYPERCALL_VARHEAD_OFFSET	17
@@ -909,4 +912,42 @@ struct hv_tlb_flush_ex {
 struct hv_partition_assist_pg {
 	u32 tlb_lock_count;
 };
+
+union hv_msi_entry {
+	u64 as_uint64;
+	struct {
+		u32 address;
+		u32 data;
+	} __packed;
+};
+
+struct hv_interrupt_entry {
+	u32 source;			/* 1 for MSI(-X) */
+	u32 reserved1;
+	union hv_msi_entry msi_entry;
+} __packed;
+
+/*
+ * flags for hv_device_interrupt_target.flags
+ */
+#define HV_DEVICE_INTERRUPT_TARGET_MULTICAST		1
+#define HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET	2
+
+struct hv_device_interrupt_target {
+	u32 vector;
+	u32 flags;
+	union {
+		u64 vp_mask;
+		struct hv_vpset vp_set;
+	};
+} __packed;
+
+/* HvRetargetDeviceInterrupt hypercall */
+struct hv_retarget_device_interrupt {
+	u64 partition_id;		/* use "self" */
+	u64 device_id;
+	struct hv_interrupt_entry int_entry;
+	u64 reserved2;
+	struct hv_device_interrupt_target int_target;
+} __packed __aligned(8);
 #endif
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a239a297be33..b3a5da27c2a5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -583,6 +583,7 @@ struct kvm_vcpu_arch {
 	unsigned long cr4;
 	unsigned long cr4_guest_owned_bits;
 	unsigned long cr8;
+	u32 host_pkru;
 	u32 pkru;
 	u32 hflags;
 	u64 efer;
@@ -1098,8 +1099,6 @@ struct kvm_x86_ops {
 	void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 	void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 	void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
-	u64 (*get_dr6)(struct kvm_vcpu *vcpu);
-	void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value);
 	void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu);
 	void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value);
 	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
@@ -1463,6 +1462,7 @@ bool kvm_rdpmc(struct kvm_vcpu *vcpu);
 
 void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
+void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload);
 void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
@@ -1682,8 +1682,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
 static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq)
 {
 	/* We can only post Fixed and LowPrio IRQs */
-	return (irq->delivery_mode == dest_Fixed ||
-		irq->delivery_mode == dest_LowestPrio);
+	return (irq->delivery_mode == APIC_DM_FIXED ||
+		irq->delivery_mode == APIC_DM_LOWEST);
 }
 
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 6685e1218959..7063b5a43220 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -41,7 +41,7 @@ struct microcode_amd {
 	unsigned int			mpb[0];
 };
 
-#define PATCH_MAX_SIZE PAGE_SIZE
+#define PATCH_MAX_SIZE (3 * PAGE_SIZE)
 
 #ifdef CONFIG_MICROCODE_AMD
 extern void __init load_ucode_amd_bsp(unsigned int family);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index edc2c581704a..1c42ecbe75cb 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 #include <linux/nmi.h>
+#include <linux/msi.h>
 #include <asm/io.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/nospec-branch.h>
@@ -242,6 +243,13 @@ bool hv_vcpu_is_preempted(int vcpu);
 static inline void hv_apic_init(void) {}
 #endif
 
+static inline void hv_set_msi_entry_from_desc(union hv_msi_entry *msi_entry,
+					      struct msi_desc *msi_desc)
+{
+	msi_entry->address = msi_desc->msg.address_lo;
+	msi_entry->data = msi_desc->msg.data;
+}
+
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
 static inline void hyperv_setup_mmu_ops(void) {}
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index c85e15010f48..a506a411474d 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -35,9 +35,7 @@
 
 #define PAGE_OFFSET		((unsigned long)__PAGE_OFFSET)
 
-#define VM_DATA_DEFAULT_FLAGS \
-	(((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
-	 VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_TSK_EXEC
 
 #define __PHYSICAL_START	ALIGN(CONFIG_PHYSICAL_START, \
 				      CONFIG_PHYSICAL_ALIGN)
@@ -73,9 +71,6 @@ static inline phys_addr_t get_max_mapped(void)
 
 bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn);
 
-extern unsigned long init_memory_mapping(unsigned long start,
-					 unsigned long end);
-
 extern void initmem_init(void);
 
 #endif	/* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index afda66a6d325..4d02e64af1b3 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -25,6 +25,7 @@
 #include <asm/x86_init.h>
 #include <asm/fpu/xstate.h>
 #include <asm/fpu/api.h>
+#include <asm-generic/pgtable_uffd.h>
 
 extern pgd_t early_top_pgt[PTRS_PER_PGD];
 int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
@@ -313,6 +314,23 @@ static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear)
 	return native_make_pte(v & ~clear);
 }
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+static inline int pte_uffd_wp(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_UFFD_WP;
+}
+
+static inline pte_t pte_mkuffd_wp(pte_t pte)
+{
+	return pte_set_flags(pte, _PAGE_UFFD_WP);
+}
+
+static inline pte_t pte_clear_uffd_wp(pte_t pte)
+{
+	return pte_clear_flags(pte, _PAGE_UFFD_WP);
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
 static inline pte_t pte_mkclean(pte_t pte)
 {
 	return pte_clear_flags(pte, _PAGE_DIRTY);
@@ -392,6 +410,23 @@ static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
 	return native_make_pmd(v & ~clear);
 }
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+static inline int pmd_uffd_wp(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_UFFD_WP;
+}
+
+static inline pmd_t pmd_mkuffd_wp(pmd_t pmd)
+{
+	return pmd_set_flags(pmd, _PAGE_UFFD_WP);
+}
+
+static inline pmd_t pmd_clear_uffd_wp(pmd_t pmd)
+{
+	return pmd_clear_flags(pmd, _PAGE_UFFD_WP);
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
 static inline pmd_t pmd_mkold(pmd_t pmd)
 {
 	return pmd_clear_flags(pmd, _PAGE_ACCESSED);
@@ -825,7 +860,10 @@ static inline unsigned long pmd_index(unsigned long address)
  *
  * this function returns the index of the entry in the pte page which would
  * control the given virtual address
+ *
+ * Also define macro so we can test if pte_index is defined for arch.
  */
+#define pte_index pte_index
 static inline unsigned long pte_index(unsigned long address)
 {
 	return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
@@ -1043,6 +1081,9 @@ static inline void __meminit init_trampoline_default(void)
 
 void __init poking_init(void);
 
+unsigned long init_memory_mapping(unsigned long start,
+				  unsigned long end, pgprot_t prot);
+
 # ifdef CONFIG_RANDOMIZE_MEMORY
 void __meminit init_trampoline(void);
 # else
@@ -1374,6 +1415,38 @@ static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
 #endif
 #endif
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+static inline pte_t pte_swp_mkuffd_wp(pte_t pte)
+{
+	return pte_set_flags(pte, _PAGE_SWP_UFFD_WP);
+}
+
+static inline int pte_swp_uffd_wp(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_SWP_UFFD_WP;
+}
+
+static inline pte_t pte_swp_clear_uffd_wp(pte_t pte)
+{
+	return pte_clear_flags(pte, _PAGE_SWP_UFFD_WP);
+}
+
+static inline pmd_t pmd_swp_mkuffd_wp(pmd_t pmd)
+{
+	return pmd_set_flags(pmd, _PAGE_SWP_UFFD_WP);
+}
+
+static inline int pmd_swp_uffd_wp(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_SWP_UFFD_WP;
+}
+
+static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd)
+{
+	return pmd_clear_flags(pmd, _PAGE_SWP_UFFD_WP);
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
 #define PKRU_AD_BIT 0x1
 #define PKRU_WD_BIT 0x2
 #define PKRU_BITS_PER_PKEY 2
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 0b6c4042942a..df1373415f11 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -189,7 +189,7 @@ extern void sync_global_pgds(unsigned long start, unsigned long end);
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
- * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|X|SD|0| <- swp entry
+ * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|F|SD|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above
@@ -197,9 +197,15 @@ extern void sync_global_pgds(unsigned long start, unsigned long end);
  * erratum where they can be incorrectly set by hardware on
  * non-present PTEs.
  *
+ * SD Bits 1-4 are not used in non-present format and available for
+ * special use described below:
+ *
  * SD (1) in swp entry is used to store soft dirty bit, which helps us
  * remember soft dirty over page migration
  *
+ * F (2) in swp entry is used to record when a pagetable is
+ * writeprotected by userfaultfd WP support.
+ *
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.
  *
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 65c2ecd730c5..b6606fe6cfdf 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -32,6 +32,7 @@
 
 #define _PAGE_BIT_SPECIAL	_PAGE_BIT_SOFTW1
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_SOFTW1
+#define _PAGE_BIT_UFFD_WP	_PAGE_BIT_SOFTW2 /* userfaultfd wrprotected */
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
 #define _PAGE_BIT_DEVMAP	_PAGE_BIT_SOFTW4
 
@@ -100,6 +101,14 @@
 #define _PAGE_SWP_SOFT_DIRTY	(_AT(pteval_t, 0))
 #endif
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+#define _PAGE_UFFD_WP		(_AT(pteval_t, 1) << _PAGE_BIT_UFFD_WP)
+#define _PAGE_SWP_UFFD_WP	_PAGE_USER
+#else
+#define _PAGE_UFFD_WP		(_AT(pteval_t, 0))
+#define _PAGE_SWP_UFFD_WP	(_AT(pteval_t, 0))
+#endif
+
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #define _PAGE_DEVMAP	(_AT(u64, 1) << _PAGE_BIT_DEVMAP)
@@ -118,7 +127,8 @@
  */
 #define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
 			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |	\
-			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC)
+			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC |  \
+			 _PAGE_UFFD_WP)
 #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
 /*
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 950532ccbc4a..ec2c0a094b5d 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -34,6 +34,7 @@
  * The caller is required to take care of these.
  */
 
+int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot);
 int _set_memory_uc(unsigned long addr, int numpages);
 int _set_memory_wc(unsigned long addr, int numpages);
 int _set_memory_wt(unsigned long addr, int numpages);
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index d61ddf3d052b..0c4e5b5e3852 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -11,8 +11,6 @@
  * Based on Ingo Molnar and Zach Brown's respective MMX and SSE routines
  */
 
-#ifdef CONFIG_AS_AVX
-
 #include <linux/compiler.h>
 #include <asm/fpu/api.h>
 
@@ -170,11 +168,4 @@ do { \
 #define AVX_SELECT(FASTEST) \
 	(boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_OSXSAVE) ? &xor_block_avx : FASTEST)
 
-#else
-
-#define AVX_XOR_SPEED {}
-
-#define AVX_SELECT(FASTEST) (FASTEST)
-
-#endif
 #endif