Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "s390:
   - implement diag318

  x86:
   - Report last CPU for debugging
   - Emulate smaller MAXPHYADDR in the guest than in the host
   - .noinstr and tracing fixes from Thomas
   - nested SVM page table switching optimization and fixes

  Generic:
   - Unify shadow MMU cache data structures across architectures"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (127 commits)
  KVM: SVM: Fix sev_pin_memory() error handling
  KVM: LAPIC: Set the TDCR settable bits
  KVM: x86: Specify max TDP level via kvm_configure_mmu()
  KVM: x86/mmu: Rename max_page_level to max_huge_page_level
  KVM: x86: Dynamically calculate TDP level from max level and MAXPHYADDR
  KVM: VXM: Remove temporary WARN on expected vs. actual EPTP level mismatch
  KVM: x86: Pull the PGD's level from the MMU instead of recalculating it
  KVM: VMX: Make vmx_load_mmu_pgd() static
  KVM: x86/mmu: Add separate helper for shadow NPT root page role calc
  KVM: VMX: Drop a duplicate declaration of construct_eptp()
  KVM: nSVM: Correctly set the shadow NPT root level in its MMU role
  KVM: Using macros instead of magic values
  MIPS: KVM: Fix build error caused by 'kvm_run' cleanup
  KVM: nSVM: remove nonsensical EXITINFO1 adjustment on nested NPF
  KVM: x86: Add a capability for GUEST_MAXPHYADDR < HOST_MAXPHYADDR support
  KVM: VMX: optimize #PF injection when MAXPHYADDR does not match
  KVM: VMX: Add guest physical address check in EPT violation and misconfig
  KVM: VMX: introduce vmx_need_pf_intercept
  KVM: x86: update exception bitmap on CPUID changes
  KVM: x86: rename update_bp_intercept to update_exception_bitmap
  ...

6 files changed, 41 insertions, 73 deletions

diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 07533795b8d2..275e7fd20310 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -67,12 +67,12 @@ static inline void kvm_set_cpu_l1tf_flush_l1d(void)
 	__this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 1);
 }
 
-static inline void kvm_clear_cpu_l1tf_flush_l1d(void)
+static __always_inline void kvm_clear_cpu_l1tf_flush_l1d(void)
 {
 	__this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 0);
 }
 
-static inline bool kvm_get_cpu_l1tf_flush_l1d(void)
+static __always_inline bool kvm_get_cpu_l1tf_flush_l1d(void)
 {
 	return __this_cpu_read(irq_stat.kvm_cpu_l1tf_flush_l1d);
 }
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index ff198fc2495e..a43366191212 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -632,6 +632,10 @@ DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR,	sysvec_acrn_hv_callback);
 DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR,	sysvec_xen_hvm_callback);
 #endif
 
+#ifdef CONFIG_KVM_GUEST
+DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR,	sysvec_kvm_asyncpf_interrupt);
+#endif
+
 #undef X86_TRAP_OTHER
 
 #endif
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index be5363b21540..5ab3af7275d8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -193,8 +193,6 @@ struct x86_exception;
 enum x86_intercept;
 enum x86_intercept_stage;
 
-#define KVM_NR_MEM_OBJS 40
-
 #define KVM_NR_DB_REGS	4
 
 #define DR6_BD		(1 << 13)
@@ -246,15 +244,6 @@ enum x86_intercept_stage;
 struct kvm_kernel_irq_routing_entry;
 
 /*
- * We don't want allocation failures within the mmu code, so we preallocate
- * enough memory for a single page fault in a cache.
- */
-struct kvm_mmu_memory_cache {
-	int nobjs;
-	void *objects[KVM_NR_MEM_OBJS];
-};
-
-/*
  * the pages used as guest page table on soft mmu are tracked by
  * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used
  * by indirect shadow page can not be more than 15 bits.
@@ -322,43 +311,6 @@ struct kvm_rmap_head {
 	unsigned long val;
 };
 
-struct kvm_mmu_page {
-	struct list_head link;
-	struct hlist_node hash_link;
-	struct list_head lpage_disallowed_link;
-
-	bool unsync;
-	u8 mmu_valid_gen;
-	bool mmio_cached;
-	bool lpage_disallowed; /* Can't be replaced by an equiv large page */
-
-	/*
-	 * The following two entries are used to key the shadow page in the
-	 * hash table.
-	 */
-	union kvm_mmu_page_role role;
-	gfn_t gfn;
-
-	u64 *spt;
-	/* hold the gfn of each spte inside spt */
-	gfn_t *gfns;
-	int root_count;          /* Currently serving as active root */
-	unsigned int unsync_children;
-	struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
-	DECLARE_BITMAP(unsync_child_bitmap, 512);
-
-#ifdef CONFIG_X86_32
-	/*
-	 * Used out of the mmu-lock to avoid reading spte values while an
-	 * update is in progress; see the comments in __get_spte_lockless().
-	 */
-	int clear_spte_count;
-#endif
-
-	/* Number of writes since the last time traversal visited this page.  */
-	atomic_t write_flooding_count;
-};
-
 struct kvm_pio_request {
 	unsigned long linear_rip;
 	unsigned long count;
@@ -384,6 +336,8 @@ struct kvm_mmu_root_info {
 
 #define KVM_MMU_NUM_PREV_ROOTS 3
 
+struct kvm_mmu_page;
+
 /*
  * x86 supports 4 paging modes (5-level 64-bit, 4-level 64-bit, 3-level 32-bit,
  * and 2-level 32-bit).  The kvm_mmu structure abstracts the details of the
@@ -580,6 +534,7 @@ struct kvm_vcpu_arch {
 	unsigned long cr3;
 	unsigned long cr4;
 	unsigned long cr4_guest_owned_bits;
+	unsigned long cr4_guest_rsvd_bits;
 	unsigned long cr8;
 	u32 host_pkru;
 	u32 pkru;
@@ -635,7 +590,8 @@ struct kvm_vcpu_arch {
 	struct kvm_mmu *walk_mmu;
 
 	struct kvm_mmu_memory_cache mmu_pte_list_desc_cache;
-	struct kvm_mmu_memory_cache mmu_page_cache;
+	struct kvm_mmu_memory_cache mmu_shadow_page_cache;
+	struct kvm_mmu_memory_cache mmu_gfn_array_cache;
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
 
 	/*
@@ -683,7 +639,7 @@ struct kvm_vcpu_arch {
 	struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES];
 
 	int maxphyaddr;
-	int tdp_level;
+	int max_tdp_level;
 
 	/* emulate context */
 
@@ -827,6 +783,9 @@ struct kvm_vcpu_arch {
 	/* Flush the L1 Data cache for L1TF mitigation on VMENTER */
 	bool l1tf_flush_l1d;
 
+	/* Host CPU on which VM-entry was most recently attempted */
+	unsigned int last_vmentry_cpu;
+
 	/* AMD MSRC001_0015 Hardware Configuration */
 	u64 msr_hwcr;
 };
@@ -1083,7 +1042,7 @@ struct kvm_x86_ops {
 	void (*hardware_unsetup)(void);
 	bool (*cpu_has_accelerated_tpr)(void);
 	bool (*has_emulated_msr)(u32 index);
-	void (*cpuid_update)(struct kvm_vcpu *vcpu);
+	void (*vcpu_after_set_cpuid)(struct kvm_vcpu *vcpu);
 
 	unsigned int vm_size;
 	int (*vm_init)(struct kvm *kvm);
@@ -1098,7 +1057,7 @@ struct kvm_x86_ops {
 	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
 
-	void (*update_bp_intercept)(struct kvm_vcpu *vcpu);
+	void (*update_exception_bitmap)(struct kvm_vcpu *vcpu);
 	int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
 	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
 	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
@@ -1174,10 +1133,10 @@ struct kvm_x86_ops {
 	int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr);
-	int (*get_tdp_level)(struct kvm_vcpu *vcpu);
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
 
-	void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, unsigned long cr3);
+	void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, unsigned long pgd,
+			     int pgd_level);
 
 	bool (*has_wbinvd_exit)(void);
 
@@ -1220,7 +1179,6 @@ struct kvm_x86_ops {
 	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
 					   struct kvm_memory_slot *slot,
 					   gfn_t offset, unsigned long mask);
-	int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
@@ -1281,6 +1239,7 @@ struct kvm_x86_nested_ops {
 			 struct kvm_nested_state __user *user_kvm_nested_state,
 			 struct kvm_nested_state *kvm_state);
 	bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
+	int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 	int (*enable_evmcs)(struct kvm_vcpu *vcpu,
 			    uint16_t *vmcs_version);
@@ -1304,7 +1263,7 @@ struct kvm_arch_async_pf {
 };
 
 extern u64 __read_mostly host_efer;
-
+extern bool __read_mostly allow_smaller_maxphyaddr;
 extern struct kvm_x86_ops kvm_x86_ops;
 
 #define __KVM_HAVE_ARCH_VM_ALLOC
@@ -1549,20 +1508,8 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid);
 void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, bool skip_tlb_flush,
 		     bool skip_mmu_sync);
 
-void kvm_configure_mmu(bool enable_tdp, int tdp_page_level);
-
-static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
-				  struct x86_exception *exception)
-{
-	return gpa;
-}
-
-static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
-{
-	struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);
-
-	return (struct kvm_mmu_page *)page_private(page);
-}
+void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level,
+		       int tdp_huge_page_level);
 
 static inline u16 kvm_read_ldt(void)
 {
@@ -1636,7 +1583,15 @@ asmlinkage void kvm_spurious_fault(void);
 	insn "\n\t"							\
 	"jmp	668f \n\t"						\
 	"667: \n\t"							\
+	"1: \n\t"							\
+	".pushsection .discard.instr_begin \n\t"			\
+	".long 1b - . \n\t"						\
+	".popsection \n\t"						\
 	"call	kvm_spurious_fault \n\t"				\
+	"1: \n\t"							\
+	".pushsection .discard.instr_end \n\t"				\
+	".long 1b - . \n\t"						\
+	".popsection \n\t"						\
 	"668: \n\t"							\
 	_ASM_EXTABLE(666b, 667b)
 
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 49d3a9edb06f..338119852512 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -4,6 +4,7 @@
 
 #include <asm/processor.h>
 #include <asm/alternative.h>
+#include <linux/interrupt.h>
 #include <uapi/asm/kvm_para.h>
 
 extern void kvmclock_init(void);
@@ -18,7 +19,7 @@ static inline bool kvm_check_and_clear_guest_paused(void)
 #endif /* CONFIG_KVM_GUEST */
 
 #define KVM_HYPERCALL \
-        ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL)
+        ALTERNATIVE("vmcall", "vmmcall", X86_FEATURE_VMMCALL)
 
 /* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall
  * instruction.  The hypervisor may replace it with something else but only the
diff --git a/arch/x86/include/asm/kvm_types.h b/arch/x86/include/asm/kvm_types.h
new file mode 100644
index 000000000000..08f1b57d3b62
--- /dev/null
+++ b/arch/x86/include/asm/kvm_types.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_KVM_TYPES_H
+#define _ASM_X86_KVM_TYPES_H
+
+#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE 40
+
+#endif /* _ASM_X86_KVM_TYPES_H */
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 444d6fd9a6d8..d86ab942219c 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -32,6 +32,7 @@ extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
 extern void __pv_init_lock_hash(void);
 extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
 extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
+extern bool nopvspin;
 
 #define	queued_spin_unlock queued_spin_unlock
 /**