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

Pull kvm updates from Paolo Bonzini:
 "This covers all architectures (except MIPS) so I don't expect any
  other feature pull requests this merge window.

  ARM:

   - Add MTE support in guests, complete with tag save/restore interface

   - Reduce the impact of CMOs by moving them in the page-table code

   - Allow device block mappings at stage-2

   - Reduce the footprint of the vmemmap in protected mode

   - Support the vGIC on dumb systems such as the Apple M1

   - Add selftest infrastructure to support multiple configuration and
     apply that to PMU/non-PMU setups

   - Add selftests for the debug architecture

   - The usual crop of PMU fixes

  PPC:

   - Support for the H_RPT_INVALIDATE hypercall

   - Conversion of Book3S entry/exit to C

   - Bug fixes

  S390:

   - new HW facilities for guests

   - make inline assembly more robust with KASAN and co

  x86:

   - Allow userspace to handle emulation errors (unknown instructions)

   - Lazy allocation of the rmap (host physical -> guest physical
     address)

   - Support for virtualizing TSC scaling on VMX machines

   - Optimizations to avoid shattering huge pages at the beginning of
     live migration

   - Support for initializing the PDPTRs without loading them from
     memory

   - Many TLB flushing cleanups

   - Refuse to load if two-stage paging is available but NX is not (this
     has been a requirement in practice for over a year)

   - A large series that separates the MMU mode (WP/SMAP/SMEP etc.) from
     CR0/CR4/EFER, using the MMU mode everywhere once it is computed
     from the CPU registers

   - Use PM notifier to notify the guest about host suspend or hibernate

   - Support for passing arguments to Hyper-V hypercalls using XMM
     registers

   - Support for Hyper-V TLB flush hypercalls and enlightened MSR bitmap
     on AMD processors

   - Hide Hyper-V hypercalls that are not included in the guest CPUID

   - Fixes for live migration of virtual machines that use the Hyper-V
     "enlightened VMCS" optimization of nested virtualization

   - Bugfixes (not many)

  Generic:

   - Support for retrieving statistics without debugfs

   - Cleanups for the KVM selftests API"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (314 commits)
  KVM: x86: rename apic_access_page_done to apic_access_memslot_enabled
  kvm: x86: disable the narrow guest module parameter on unload
  selftests: kvm: Allows userspace to handle emulation errors.
  kvm: x86: Allow userspace to handle emulation errors
  KVM: x86/mmu: Let guest use GBPAGES if supported in hardware and TDP is on
  KVM: x86/mmu: Get CR4.SMEP from MMU, not vCPU, in shadow page fault
  KVM: x86/mmu: Get CR0.WP from MMU, not vCPU, in shadow page fault
  KVM: x86/mmu: Drop redundant rsvd bits reset for nested NPT
  KVM: x86/mmu: Optimize and clean up so called "last nonleaf level" logic
  KVM: x86: Enhance comments for MMU roles and nested transition trickiness
  KVM: x86/mmu: WARN on any reserved SPTE value when making a valid SPTE
  KVM: x86/mmu: Add helpers to do full reserved SPTE checks w/ generic MMU
  KVM: x86/mmu: Use MMU's role to determine PTTYPE
  KVM: x86/mmu: Collapse 32-bit PAE and 64-bit statements for helpers
  KVM: x86/mmu: Add a helper to calculate root from role_regs
  KVM: x86/mmu: Add helper to update paging metadata
  KVM: x86/mmu: Don't update nested guest's paging bitmasks if CR0.PG=0
  KVM: x86/mmu: Consolidate reset_rsvds_bits_mask() calls
  KVM: x86/mmu: Use MMU role_regs to get LA57, and drop vCPU LA57 helper
  KVM: x86/mmu: Get nested MMU's root level from the MMU's role
  ...

10 files changed, 139 insertions, 40 deletions

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 692c9049befa..d436831dd706 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -12,7 +12,8 @@
 #include <asm/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
-#define HCR_ATA		(UL(1) << 56)
+#define HCR_ATA_SHIFT	56
+#define HCR_ATA		(UL(1) << HCR_ATA_SHIFT)
 #define HCR_FWB		(UL(1) << 46)
 #define HCR_API		(UL(1) << 41)
 #define HCR_APK		(UL(1) << 40)
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 01b9857757f2..fd418955e31e 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -84,6 +84,9 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 	if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) ||
 	    vcpu_el1_is_32bit(vcpu))
 		vcpu->arch.hcr_el2 |= HCR_TID2;
+
+	if (kvm_has_mte(vcpu->kvm))
+		vcpu->arch.hcr_el2 |= HCR_ATA;
 }
 
 static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 7cd7d5c8c4bc..41911585ae0c 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -46,6 +46,7 @@
 #define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
 #define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
 #define KVM_REQ_RELOAD_GICv4	KVM_ARCH_REQ(4)
+#define KVM_REQ_RELOAD_PMU	KVM_ARCH_REQ(5)
 
 #define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
 				     KVM_DIRTY_LOG_INITIALLY_SET)
@@ -132,6 +133,9 @@ struct kvm_arch {
 
 	u8 pfr0_csv2;
 	u8 pfr0_csv3;
+
+	/* Memory Tagging Extension enabled for the guest */
+	bool mte_enabled;
 };
 
 struct kvm_vcpu_fault_info {
@@ -206,6 +210,12 @@ enum vcpu_sysreg {
 	CNTP_CVAL_EL0,
 	CNTP_CTL_EL0,
 
+	/* Memory Tagging Extension registers */
+	RGSR_EL1,	/* Random Allocation Tag Seed Register */
+	GCR_EL1,	/* Tag Control Register */
+	TFSR_EL1,	/* Tag Fault Status Register (EL1) */
+	TFSRE0_EL1,	/* Tag Fault Status Register (EL0) */
+
 	/* 32bit specific registers. Keep them at the end of the range */
 	DACR32_EL2,	/* Domain Access Control Register */
 	IFSR32_EL2,	/* Instruction Fault Status Register */
@@ -556,16 +566,11 @@ static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
 }
 
 struct kvm_vm_stat {
-	ulong remote_tlb_flush;
+	struct kvm_vm_stat_generic generic;
 };
 
 struct kvm_vcpu_stat {
-	u64 halt_successful_poll;
-	u64 halt_attempted_poll;
-	u64 halt_poll_success_ns;
-	u64 halt_poll_fail_ns;
-	u64 halt_poll_invalid;
-	u64 halt_wakeup;
+	struct kvm_vcpu_stat_generic generic;
 	u64 hvc_exit_stat;
 	u64 wfe_exit_stat;
 	u64 wfi_exit_stat;
@@ -721,6 +726,9 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
 int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);
 
+long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
+				struct kvm_arm_copy_mte_tags *copy_tags);
+
 /* 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);
@@ -769,6 +777,7 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 #define kvm_arm_vcpu_sve_finalized(vcpu) \
 	((vcpu)->arch.flags & KVM_ARM64_VCPU_SVE_FINALIZED)
 
+#define kvm_has_mte(kvm) (system_supports_mte() && (kvm)->arch.mte_enabled)
 #define kvm_vcpu_has_pmu(vcpu)					\
 	(test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features))
 
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index f4cbfa9025a8..b52c5c4b9a3d 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -188,10 +188,8 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 	return (vcpu_read_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
 }
 
-static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
+static inline void __clean_dcache_guest_page(void *va, size_t size)
 {
-	void *va = page_address(pfn_to_page(pfn));
-
 	/*
 	 * With FWB, we ensure that the guest always accesses memory using
 	 * cacheable attributes, and we don't have to clean to PoC when
@@ -204,18 +202,14 @@ static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
 	kvm_flush_dcache_to_poc(va, size);
 }
 
-static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn,
-						  unsigned long size)
+static inline void __invalidate_icache_guest_page(void *va, size_t size)
 {
 	if (icache_is_aliasing()) {
 		/* any kind of VIPT cache */
 		icache_inval_all_pou();
 	} else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) {
 		/* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
-		void *va = page_address(pfn_to_page(pfn));
-
-		icache_inval_pou((unsigned long)va,
-					(unsigned long)va + size);
+		icache_inval_pou((unsigned long)va, (unsigned long)va + size);
 	}
 }
 
diff --git a/arch/arm64/include/asm/kvm_mte.h b/arch/arm64/include/asm/kvm_mte.h
new file mode 100644
index 000000000000..de002636eb1f
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_mte.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2021 ARM Ltd.
+ */
+#ifndef __ASM_KVM_MTE_H
+#define __ASM_KVM_MTE_H
+
+#ifdef __ASSEMBLY__
+
+#include <asm/sysreg.h>
+
+#ifdef CONFIG_ARM64_MTE
+
+.macro mte_switch_to_guest g_ctxt, h_ctxt, reg1
+alternative_if_not ARM64_MTE
+	b	.L__skip_switch\@
+alternative_else_nop_endif
+	mrs	\reg1, hcr_el2
+	tbz	\reg1, #(HCR_ATA_SHIFT), .L__skip_switch\@
+
+	mrs_s	\reg1, SYS_RGSR_EL1
+	str	\reg1, [\h_ctxt, #CPU_RGSR_EL1]
+	mrs_s	\reg1, SYS_GCR_EL1
+	str	\reg1, [\h_ctxt, #CPU_GCR_EL1]
+
+	ldr	\reg1, [\g_ctxt, #CPU_RGSR_EL1]
+	msr_s	SYS_RGSR_EL1, \reg1
+	ldr	\reg1, [\g_ctxt, #CPU_GCR_EL1]
+	msr_s	SYS_GCR_EL1, \reg1
+
+.L__skip_switch\@:
+.endm
+
+.macro mte_switch_to_hyp g_ctxt, h_ctxt, reg1
+alternative_if_not ARM64_MTE
+	b	.L__skip_switch\@
+alternative_else_nop_endif
+	mrs	\reg1, hcr_el2
+	tbz	\reg1, #(HCR_ATA_SHIFT), .L__skip_switch\@
+
+	mrs_s	\reg1, SYS_RGSR_EL1
+	str	\reg1, [\g_ctxt, #CPU_RGSR_EL1]
+	mrs_s	\reg1, SYS_GCR_EL1
+	str	\reg1, [\g_ctxt, #CPU_GCR_EL1]
+
+	ldr	\reg1, [\h_ctxt, #CPU_RGSR_EL1]
+	msr_s	SYS_RGSR_EL1, \reg1
+	ldr	\reg1, [\h_ctxt, #CPU_GCR_EL1]
+	msr_s	SYS_GCR_EL1, \reg1
+
+	isb
+
+.L__skip_switch\@:
+.endm
+
+#else /* !CONFIG_ARM64_MTE */
+
+.macro mte_switch_to_guest g_ctxt, h_ctxt, reg1
+.endm
+
+.macro mte_switch_to_hyp g_ctxt, h_ctxt, reg1
+.endm
+
+#endif /* CONFIG_ARM64_MTE */
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_KVM_MTE_H */
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index c3674c47d48c..f004c0115d89 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -27,23 +27,29 @@ typedef u64 kvm_pte_t;
 
 /**
  * struct kvm_pgtable_mm_ops - Memory management callbacks.
- * @zalloc_page:	Allocate a single zeroed memory page. The @arg parameter
- *			can be used by the walker to pass a memcache. The
- *			initial refcount of the page is 1.
- * @zalloc_pages_exact:	Allocate an exact number of zeroed memory pages. The
- *			@size parameter is in bytes, and is rounded-up to the
- *			next page boundary. The resulting allocation is
- *			physically contiguous.
- * @free_pages_exact:	Free an exact number of memory pages previously
- *			allocated by zalloc_pages_exact.
- * @get_page:		Increment the refcount on a page.
- * @put_page:		Decrement the refcount on a page. When the refcount
- *			reaches 0 the page is automatically freed.
- * @page_count:		Return the refcount of a page.
- * @phys_to_virt:	Convert a physical address into a virtual address mapped
- *			in the current context.
- * @virt_to_phys:	Convert a virtual address mapped in the current context
- *			into a physical address.
+ * @zalloc_page:		Allocate a single zeroed memory page.
+ *				The @arg parameter can be used by the walker
+ *				to pass a memcache. The initial refcount of
+ *				the page is 1.
+ * @zalloc_pages_exact:		Allocate an exact number of zeroed memory pages.
+ *				The @size parameter is in bytes, and is rounded
+ *				up to the next page boundary. The resulting
+ *				allocation is physically contiguous.
+ * @free_pages_exact:		Free an exact number of memory pages previously
+ *				allocated by zalloc_pages_exact.
+ * @get_page:			Increment the refcount on a page.
+ * @put_page:			Decrement the refcount on a page. When the
+ *				refcount reaches 0 the page is automatically
+ *				freed.
+ * @page_count:			Return the refcount of a page.
+ * @phys_to_virt:		Convert a physical address into a virtual
+ *				address	mapped in the current context.
+ * @virt_to_phys:		Convert a virtual address mapped in the current
+ *				context into a physical address.
+ * @dcache_clean_inval_poc:	Clean and invalidate the data cache to the PoC
+ *				for the	specified memory address range.
+ * @icache_inval_pou:		Invalidate the instruction cache to the PoU
+ *				for the specified memory address range.
  */
 struct kvm_pgtable_mm_ops {
 	void*		(*zalloc_page)(void *arg);
@@ -54,6 +60,8 @@ struct kvm_pgtable_mm_ops {
 	int		(*page_count)(void *addr);
 	void*		(*phys_to_virt)(phys_addr_t phys);
 	phys_addr_t	(*virt_to_phys)(void *addr);
+	void		(*dcache_clean_inval_poc)(void *addr, size_t size);
+	void		(*icache_inval_pou)(void *addr, size_t size);
 };
 
 /**
diff --git a/arch/arm64/include/asm/mte-def.h b/arch/arm64/include/asm/mte-def.h
index cf241b0f0a42..626d359b396e 100644
--- a/arch/arm64/include/asm/mte-def.h
+++ b/arch/arm64/include/asm/mte-def.h
@@ -7,6 +7,7 @@
 
 #define MTE_GRANULE_SIZE	UL(16)
 #define MTE_GRANULE_MASK	(~(MTE_GRANULE_SIZE - 1))
+#define MTE_GRANULES_PER_PAGE	(PAGE_SIZE / MTE_GRANULE_SIZE)
 #define MTE_TAG_SHIFT		56
 #define MTE_TAG_SIZE		4
 #define MTE_TAG_MASK		GENMASK((MTE_TAG_SHIFT + (MTE_TAG_SIZE - 1)), MTE_TAG_SHIFT)
diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
index 67bf259ae768..58c7f80f5596 100644
--- a/arch/arm64/include/asm/mte.h
+++ b/arch/arm64/include/asm/mte.h
@@ -38,7 +38,7 @@ void mte_free_tag_storage(char *storage);
 #define PG_mte_tagged	PG_arch_2
 
 void mte_zero_clear_page_tags(void *addr);
-void mte_sync_tags(pte_t *ptep, pte_t pte);
+void mte_sync_tags(pte_t old_pte, pte_t pte);
 void mte_copy_page_tags(void *kto, const void *kfrom);
 void mte_thread_init_user(void);
 void mte_thread_switch(struct task_struct *next);
@@ -57,7 +57,7 @@ int mte_ptrace_copy_tags(struct task_struct *child, long request,
 static inline void mte_zero_clear_page_tags(void *addr)
 {
 }
-static inline void mte_sync_tags(pte_t *ptep, pte_t pte)
+static inline void mte_sync_tags(pte_t old_pte, pte_t pte)
 {
 }
 static inline void mte_copy_page_tags(void *kto, const void *kfrom)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 11e60d0cd9b6..c0ba8cdfa10a 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -314,9 +314,25 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
 		__sync_icache_dcache(pte);
 
-	if (system_supports_mte() &&
-	    pte_present(pte) && pte_tagged(pte) && !pte_special(pte))
-		mte_sync_tags(ptep, pte);
+	/*
+	 * If the PTE would provide user space access to the tags associated
+	 * with it then ensure that the MTE tags are synchronised.  Although
+	 * pte_access_permitted() returns false for exec only mappings, they
+	 * don't expose tags (instruction fetches don't check tags).
+	 */
+	if (system_supports_mte() && pte_access_permitted(pte, false) &&
+	    !pte_special(pte)) {
+		pte_t old_pte = READ_ONCE(*ptep);
+		/*
+		 * We only need to synchronise if the new PTE has tags enabled
+		 * or if swapping in (in which case another mapping may have
+		 * set tags in the past even if this PTE isn't tagged).
+		 * (!pte_none() && !pte_present()) is an open coded version of
+		 * is_swap_pte()
+		 */
+		if (pte_tagged(pte) || (!pte_none(old_pte) && !pte_present(old_pte)))
+			mte_sync_tags(old_pte, pte);
+	}
 
 	__check_racy_pte_update(mm, ptep, pte);
 
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 9ea84bcddf85..7b9c3acba684 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -651,7 +651,8 @@
 
 #define INIT_SCTLR_EL2_MMU_ON						\
 	(SCTLR_ELx_M  | SCTLR_ELx_C | SCTLR_ELx_SA | SCTLR_ELx_I |	\
-	 SCTLR_ELx_IESB | SCTLR_ELx_WXN | ENDIAN_SET_EL2 | SCTLR_EL2_RES1)
+	 SCTLR_ELx_IESB | SCTLR_ELx_WXN | ENDIAN_SET_EL2 |		\
+	 SCTLR_ELx_ITFSB | SCTLR_EL2_RES1)
 
 #define INIT_SCTLR_EL2_MMU_OFF \
 	(SCTLR_EL2_RES1 | ENDIAN_SET_EL2)