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

Pull kvm updates from Paolo Bonzini:
 "RISCV:

   - Use common KVM implementation of MMU memory caches

   - SBI v0.2 support for Guest

   - Initial KVM selftests support

   - Fix to avoid spurious virtual interrupts after clearing hideleg CSR

   - Update email address for Anup and Atish

  ARM:

   - Simplification of the 'vcpu first run' by integrating it into KVM's
     'pid change' flow

   - Refactoring of the FP and SVE state tracking, also leading to a
     simpler state and less shared data between EL1 and EL2 in the nVHE
     case

   - Tidy up the header file usage for the nvhe hyp object

   - New HYP unsharing mechanism, finally allowing pages to be unmapped
     from the Stage-1 EL2 page-tables

   - Various pKVM cleanups around refcounting and sharing

   - A couple of vgic fixes for bugs that would trigger once the vcpu
     xarray rework is merged, but not sooner

   - Add minimal support for ARMv8.7's PMU extension

   - Rework kvm_pgtable initialisation ahead of the NV work

   - New selftest for IRQ injection

   - Teach selftests about the lack of default IPA space and page sizes

   - Expand sysreg selftest to deal with Pointer Authentication

   - The usual bunch of cleanups and doc update

  s390:

   - fix sigp sense/start/stop/inconsistency

   - cleanups

  x86:

   - Clean up some function prototypes more

   - improved gfn_to_pfn_cache with proper invalidation, used by Xen
     emulation

   - add KVM_IRQ_ROUTING_XEN_EVTCHN and event channel delivery

   - completely remove potential TOC/TOU races in nested SVM consistency
     checks

   - update some PMCs on emulated instructions

   - Intel AMX support (joint work between Thomas and Intel)

   - large MMU cleanups

   - module parameter to disable PMU virtualization

   - cleanup register cache

   - first part of halt handling cleanups

   - Hyper-V enlightened MSR bitmap support for nested hypervisors

  Generic:

   - clean up Makefiles

   - introduce CONFIG_HAVE_KVM_DIRTY_RING

   - optimize memslot lookup using a tree

   - optimize vCPU array usage by converting to xarray"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (268 commits)
  x86/fpu: Fix inline prefix warnings
  selftest: kvm: Add amx selftest
  selftest: kvm: Move struct kvm_x86_state to header
  selftest: kvm: Reorder vcpu_load_state steps for AMX
  kvm: x86: Disable interception for IA32_XFD on demand
  x86/fpu: Provide fpu_sync_guest_vmexit_xfd_state()
  kvm: selftests: Add support for KVM_CAP_XSAVE2
  kvm: x86: Add support for getting/setting expanded xstate buffer
  x86/fpu: Add uabi_size to guest_fpu
  kvm: x86: Add CPUID support for Intel AMX
  kvm: x86: Add XCR0 support for Intel AMX
  kvm: x86: Disable RDMSR interception of IA32_XFD_ERR
  kvm: x86: Emulate IA32_XFD_ERR for guest
  kvm: x86: Intercept #NM for saving IA32_XFD_ERR
  x86/fpu: Prepare xfd_err in struct fpu_guest
  kvm: x86: Add emulation for IA32_XFD
  x86/fpu: Provide fpu_update_guest_xfd() for IA32_XFD emulation
  kvm: x86: Enable dynamic xfeatures at KVM_SET_CPUID2
  x86/fpu: Provide fpu_enable_guest_xfd_features() for KVM
  x86/fpu: Add guest support to xfd_enable_feature()
  ...

9 files changed, 123 insertions, 35 deletions

diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 50d5e4de244c..d5b0386ef765 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -63,6 +63,7 @@ enum __kvm_host_smccc_func {
 
 	/* Hypercalls available after pKVM finalisation */
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
 	__KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
 	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index f4871e47b2d0..d62405ce3e6d 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -41,6 +41,8 @@ void kvm_inject_vabt(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 
+void kvm_vcpu_wfi(struct kvm_vcpu *vcpu);
+
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
 	return !(vcpu->arch.hcr_el2 & HCR_RW);
@@ -386,7 +388,7 @@ static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
 		*vcpu_cpsr(vcpu) |= PSR_AA32_E_BIT;
 	} else {
 		u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
-		sctlr |= (1 << 25);
+		sctlr |= SCTLR_ELx_EE;
 		vcpu_write_sys_reg(vcpu, sctlr, SCTLR_EL1);
 	}
 }
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 541e7a813eb8..5bc01e62c08a 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -26,7 +26,6 @@
 #include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
-#include <asm/thread_info.h>
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
@@ -298,9 +297,6 @@ struct kvm_vcpu_arch {
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
 
-	/* State of various workarounds, see kvm_asm.h for bit assignment */
-	u64 workaround_flags;
-
 	/* Miscellaneous vcpu state flags */
 	u64 flags;
 
@@ -321,8 +317,8 @@ struct kvm_vcpu_arch {
 	struct kvm_guest_debug_arch vcpu_debug_state;
 	struct kvm_guest_debug_arch external_debug_state;
 
-	struct thread_info *host_thread_info;	/* hyp VA */
 	struct user_fpsimd_state *host_fpsimd_state;	/* hyp VA */
+	struct task_struct *parent_task;
 
 	struct {
 		/* {Break,watch}point registers */
@@ -367,9 +363,6 @@ struct kvm_vcpu_arch {
 	int target;
 	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);
 
-	/* Detect first run of a vcpu */
-	bool has_run_once;
-
 	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
 	u64 vsesr_el2;
 
@@ -411,20 +404,17 @@ struct kvm_vcpu_arch {
 #define KVM_ARM64_DEBUG_DIRTY		(1 << 0)
 #define KVM_ARM64_FP_ENABLED		(1 << 1) /* guest FP regs loaded */
 #define KVM_ARM64_FP_HOST		(1 << 2) /* host FP regs loaded */
-#define KVM_ARM64_HOST_SVE_IN_USE	(1 << 3) /* backup for host TIF_SVE */
 #define KVM_ARM64_HOST_SVE_ENABLED	(1 << 4) /* SVE enabled for EL0 */
 #define KVM_ARM64_GUEST_HAS_SVE		(1 << 5) /* SVE exposed to guest */
 #define KVM_ARM64_VCPU_SVE_FINALIZED	(1 << 6) /* SVE config completed */
 #define KVM_ARM64_GUEST_HAS_PTRAUTH	(1 << 7) /* PTRAUTH exposed to guest */
 #define KVM_ARM64_PENDING_EXCEPTION	(1 << 8) /* Exception pending */
+/*
+ * Overlaps with KVM_ARM64_EXCEPT_MASK on purpose so that it can't be
+ * set together with an exception...
+ */
+#define KVM_ARM64_INCREMENT_PC		(1 << 9) /* Increment PC */
 #define KVM_ARM64_EXCEPT_MASK		(7 << 9) /* Target EL/MODE */
-#define KVM_ARM64_DEBUG_STATE_SAVE_SPE	(1 << 12) /* Save SPE context if active  */
-#define KVM_ARM64_DEBUG_STATE_SAVE_TRBE	(1 << 13) /* Save TRBE context if active  */
-
-#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \
-				 KVM_GUESTDBG_USE_SW_BP | \
-				 KVM_GUESTDBG_USE_HW | \
-				 KVM_GUESTDBG_SINGLESTEP)
 /*
  * When KVM_ARM64_PENDING_EXCEPTION is set, KVM_ARM64_EXCEPT_MASK can
  * take the following values:
@@ -442,11 +432,14 @@ struct kvm_vcpu_arch {
 #define KVM_ARM64_EXCEPT_AA64_EL1	(0 << 11)
 #define KVM_ARM64_EXCEPT_AA64_EL2	(1 << 11)
 
-/*
- * Overlaps with KVM_ARM64_EXCEPT_MASK on purpose so that it can't be
- * set together with an exception...
- */
-#define KVM_ARM64_INCREMENT_PC		(1 << 9) /* Increment PC */
+#define KVM_ARM64_DEBUG_STATE_SAVE_SPE	(1 << 12) /* Save SPE context if active  */
+#define KVM_ARM64_DEBUG_STATE_SAVE_TRBE	(1 << 13) /* Save TRBE context if active  */
+#define KVM_ARM64_FP_FOREIGN_FPSTATE	(1 << 14)
+
+#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \
+				 KVM_GUESTDBG_USE_SW_BP | \
+				 KVM_GUESTDBG_USE_HW | \
+				 KVM_GUESTDBG_SINGLESTEP)
 
 #define vcpu_has_sve(vcpu) (system_supports_sve() &&			\
 			    ((vcpu)->arch.flags & KVM_ARM64_GUEST_HAS_SVE))
@@ -606,6 +599,8 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
 void kvm_arm_halt_guest(struct kvm *kvm);
 void kvm_arm_resume_guest(struct kvm *kvm);
 
+#define vcpu_has_run_once(vcpu)	!!rcu_access_pointer((vcpu)->pid)
+
 #ifndef __KVM_NVHE_HYPERVISOR__
 #define kvm_call_hyp_nvhe(f, ...)						\
 	({								\
@@ -724,7 +719,6 @@ void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu);
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
-static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
 
 void kvm_arm_init_debug(void);
 void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu);
@@ -744,8 +738,10 @@ long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
 /* Guest/host FPSIMD coordination helpers */
 int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu);
+void kvm_vcpu_unshare_task_fp(struct kvm_vcpu *vcpu);
 
 static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr)
 {
@@ -756,12 +752,7 @@ static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr)
 void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu);
 
-#ifdef CONFIG_KVM /* Avoid conflicts with core headers if CONFIG_KVM=n */
-static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
-{
-	return kvm_arch_vcpu_run_map_fp(vcpu);
-}
-
+#ifdef CONFIG_KVM
 void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr);
 void kvm_clr_pmu_events(u32 clr);
 
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 5afd14ab15b9..462882f356c7 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -90,7 +90,6 @@ void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu);
 
 void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
-void __sve_save_state(void *sve_pffr, u32 *fpsr);
 void __sve_restore_state(void *sve_pffr, u32 *fpsr);
 
 #ifndef __KVM_NVHE_HYPERVISOR__
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 02d378887743..81839e9a8a24 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -150,6 +150,8 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v)
 #include <asm/kvm_pgtable.h>
 #include <asm/stage2_pgtable.h>
 
+int kvm_share_hyp(void *from, void *to);
+void kvm_unshare_hyp(void *from, void *to);
 int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot);
 int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
 			   void __iomem **kaddr,
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 027783829584..9f339dffbc1a 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -252,6 +252,27 @@ int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
 			enum kvm_pgtable_prot prot);
 
 /**
+ * kvm_pgtable_hyp_unmap() - Remove a mapping from a hypervisor stage-1 page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_hyp_init().
+ * @addr:	Virtual address from which to remove the mapping.
+ * @size:	Size of the mapping.
+ *
+ * The offset of @addr within a page is ignored, @size is rounded-up to
+ * the next page boundary and @phys is rounded-down to the previous page
+ * boundary.
+ *
+ * TLB invalidation is performed for each page-table entry cleared during the
+ * unmapping operation and the reference count for the page-table page
+ * containing the cleared entry is decremented, with unreferenced pages being
+ * freed. The unmapping operation will stop early if it encounters either an
+ * invalid page-table entry or a valid block mapping which maps beyond the range
+ * being unmapped.
+ *
+ * Return: Number of bytes unmapped, which may be 0.
+ */
+u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
+
+/**
  * kvm_get_vtcr() - Helper to construct VTCR_EL2
  * @mmfr0:	Sanitized value of SYS_ID_AA64MMFR0_EL1 register.
  * @mmfr1:	Sanitized value of SYS_ID_AA64MMFR1_EL1 register.
@@ -270,8 +291,7 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift);
 /**
  * __kvm_pgtable_stage2_init() - Initialise a guest stage-2 page-table.
  * @pgt:	Uninitialised page-table structure to initialise.
- * @arch:	Arch-specific KVM structure representing the guest virtual
- *		machine.
+ * @mmu:	S2 MMU context for this S2 translation
  * @mm_ops:	Memory management callbacks.
  * @flags:	Stage-2 configuration flags.
  * @force_pte_cb: Function that returns true if page level mappings must
@@ -279,13 +299,13 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift);
  *
  * Return: 0 on success, negative error code on failure.
  */
-int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_arch *arch,
+int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 			      struct kvm_pgtable_mm_ops *mm_ops,
 			      enum kvm_pgtable_stage2_flags flags,
 			      kvm_pgtable_force_pte_cb_t force_pte_cb);
 
-#define kvm_pgtable_stage2_init(pgt, arch, mm_ops) \
-	__kvm_pgtable_stage2_init(pgt, arch, mm_ops, 0, NULL)
+#define kvm_pgtable_stage2_init(pgt, mmu, mm_ops) \
+	__kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL)
 
 /**
  * kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table.
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
new file mode 100644
index 000000000000..9f4ad2a8df59
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 - Google LLC
+ * Author: Quentin Perret <qperret@google.com>
+ */
+#ifndef __ARM64_KVM_PKVM_H__
+#define __ARM64_KVM_PKVM_H__
+
+#include <linux/memblock.h>
+#include <asm/kvm_pgtable.h>
+
+#define HYP_MEMBLOCK_REGIONS 128
+
+extern struct memblock_region kvm_nvhe_sym(hyp_memory)[];
+extern unsigned int kvm_nvhe_sym(hyp_memblock_nr);
+
+static inline unsigned long __hyp_pgtable_max_pages(unsigned long nr_pages)
+{
+	unsigned long total = 0, i;
+
+	/* Provision the worst case scenario */
+	for (i = 0; i < KVM_PGTABLE_MAX_LEVELS; i++) {
+		nr_pages = DIV_ROUND_UP(nr_pages, PTRS_PER_PTE);
+		total += nr_pages;
+	}
+
+	return total;
+}
+
+static inline unsigned long __hyp_pgtable_total_pages(void)
+{
+	unsigned long res = 0, i;
+
+	/* Cover all of memory with page-granularity */
+	for (i = 0; i < kvm_nvhe_sym(hyp_memblock_nr); i++) {
+		struct memblock_region *reg = &kvm_nvhe_sym(hyp_memory)[i];
+		res += __hyp_pgtable_max_pages(reg->size >> PAGE_SHIFT);
+	}
+
+	return res;
+}
+
+static inline unsigned long hyp_s1_pgtable_pages(void)
+{
+	unsigned long res;
+
+	res = __hyp_pgtable_total_pages();
+
+	/* Allow 1 GiB for private mappings */
+	res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT);
+
+	return res;
+}
+
+static inline unsigned long host_s2_pgtable_pages(void)
+{
+	unsigned long res;
+
+	/*
+	 * Include an extra 16 pages to safely upper-bound the worst case of
+	 * concatenated pgds.
+	 */
+	res = __hyp_pgtable_total_pages() + 16;
+
+	/* Allow 1 GiB for MMIO mappings */
+	res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT);
+
+	return res;
+}
+
+#endif	/* __ARM64_KVM_PKVM_H__ */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index e9c30859f80c..48f8466a4be9 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -15,6 +15,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/refcount.h>
+#include <asm/cpufeature.h>
 
 typedef struct {
 	atomic64_t	id;
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 4704f5893458..898bee0004ae 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -953,6 +953,7 @@
 #define ID_AA64DFR0_PMUVER_8_1		0x4
 #define ID_AA64DFR0_PMUVER_8_4		0x5
 #define ID_AA64DFR0_PMUVER_8_5		0x6
+#define ID_AA64DFR0_PMUVER_8_7		0x7
 #define ID_AA64DFR0_PMUVER_IMP_DEF	0xf
 
 #define ID_AA64DFR0_PMSVER_8_2		0x1