KVM: arm64: Rewrite page-table code and fault handling

index 662b0c99a63d..4a24ebdc6fc6 100644
@@ -1489,19 +1489,17 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 		ret = kvm_mmu_topup_memory_cache(&cache,
 						 kvm_mmu_cache_min_pages(kvm));
 		if (ret)
-			goto out;
+			break;
 		spin_lock(&kvm->mmu_lock);
 		ret = stage2_set_pte(&kvm->arch.mmu, &cache, addr, &pte,
 				     KVM_S2PTE_FLAG_IS_IOMAP);
 		spin_unlock(&kvm->mmu_lock);
 		if (ret)
-			goto out;
+			break;
 
 		pfn++;
 	}
 
-out:
-	kvm_mmu_free_memory_cache(&cache);
 	return ret;
 }
 

index 189839c3706a..0f078b1920ff 100644
@@ -141,8 +141,6 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
 
-void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
-
 phys_addr_t kvm_mmu_get_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
 int kvm_mmu_init(void);

index 691d21e4c717..c958c8f03144 100644
@@ -283,7 +283,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.has_run_once && unlikely(!irqchip_in_kernel(vcpu->kvm)))
 		static_branch_dec(&userspace_irqchip_in_use);
 
-	kvm_mmu_free_memory_caches(vcpu);
+	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_pmu_vcpu_destroy(vcpu);
 

index 4a24ebdc6fc6..9bc1a5d5a310 100644
@@ -2322,11 +2322,6 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 				 kvm_test_age_hva_handler, NULL);
 }
 
-void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu)
-{
-	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
-}
-
 phys_addr_t kvm_mmu_get_httbr(void)
 {
 	if (__kvm_cpu_uses_extended_idmap())

new file mode 100644
index 000000000000..51ccbbb0efae
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020 Google LLC
+ * Author: Will Deacon <[email protected]>
+ */
+
+#ifndef __ARM64_KVM_PGTABLE_H__
+#define __ARM64_KVM_PGTABLE_H__
+
+#include <linux/bits.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+
+typedef u64 kvm_pte_t;
+
+/**
+ * struct kvm_pgtable - KVM page-table.
+ * @ia_bits:		Maximum input address size, in bits.
+ * @start_level:	Level at which the page-table walk starts.
+ * @pgd:		Pointer to the first top-level entry of the page-table.
+ * @mmu:		Stage-2 KVM MMU struct. Unused for stage-1 page-tables.
+ */
+struct kvm_pgtable {
+	u32					ia_bits;
+	u32					start_level;
+	kvm_pte_t				*pgd;
+
+	/* Stage-2 only */
+	struct kvm_s2_mmu			*mmu;
+};
+
+/**
+ * enum kvm_pgtable_prot - Page-table permissions and attributes.
+ * @KVM_PGTABLE_PROT_R:		Read permission.
+ * @KVM_PGTABLE_PROT_W:		Write permission.
+ * @KVM_PGTABLE_PROT_X:		Execute permission.
+ * @KVM_PGTABLE_PROT_DEVICE:	Device attributes.
+ */
+enum kvm_pgtable_prot {
+	KVM_PGTABLE_PROT_R			= BIT(0),
+	KVM_PGTABLE_PROT_W			= BIT(1),
+	KVM_PGTABLE_PROT_X			= BIT(2),
+
+	KVM_PGTABLE_PROT_DEVICE			= BIT(3),
+};
+
+/**
+ * enum kvm_pgtable_walk_flags - Flags to control a depth-first page-table walk.
+ * @KVM_PGTABLE_WALK_LEAF:		Visit leaf entries, including invalid
+ *					entries.
+ * @KVM_PGTABLE_WALK_TABLE_PRE:		Visit table entries before their
+ *					children.
+ * @KVM_PGTABLE_WALK_TABLE_POST:	Visit table entries after their
+ *					children.
+ */
+enum kvm_pgtable_walk_flags {
+	KVM_PGTABLE_WALK_LEAF			= BIT(0),
+	KVM_PGTABLE_WALK_TABLE_PRE		= BIT(1),
+	KVM_PGTABLE_WALK_TABLE_POST		= BIT(2),
+};
+
+typedef int (*kvm_pgtable_visitor_fn_t)(u64 addr, u64 end, u32 level,
+					kvm_pte_t *ptep,
+					enum kvm_pgtable_walk_flags flag,
+					void * const arg);
+
+/**
+ * struct kvm_pgtable_walker - Hook into a page-table walk.
+ * @cb:		Callback function to invoke during the walk.
+ * @arg:	Argument passed to the callback function.
+ * @flags:	Bitwise-OR of flags to identify the entry types on which to
+ *		invoke the callback function.
+ */
+struct kvm_pgtable_walker {
+	const kvm_pgtable_visitor_fn_t		cb;
+	void * const				arg;
+	const enum kvm_pgtable_walk_flags	flags;
+};
+
+/**
+ * kvm_pgtable_walk() - Walk a page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_*_init().
+ * @addr:	Input address for the start of the walk.
+ * @size:	Size of the range to walk.
+ * @walker:	Walker callback description.
+ *
+ * The walker will walk the page-table entries corresponding to the input
+ * address range specified, visiting entries according to the walker flags.
+ * Invalid entries are treated as leaf entries. Leaf entries are reloaded
+ * after invoking the walker callback, allowing the walker to descend into
+ * a newly installed table.
+ *
+ * Returning a negative error code from the walker callback function will
+ * terminate the walk immediately with the same error code.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
+		     struct kvm_pgtable_walker *walker);
+
+#endif	/* __ARM64_KVM_PGTABLE_H__ */

290 lines not on this page · raw message

index 51ccbbb0efae..ec9f98527dcc 100644
@@ -77,6 +77,40 @@ struct kvm_pgtable_walker {
 	const enum kvm_pgtable_walk_flags	flags;
 };
 
+/**
+ * kvm_pgtable_hyp_init() - Initialise a hypervisor stage-1 page-table.
+ * @pgt:	Uninitialised page-table structure to initialise.
+ * @va_bits:	Maximum virtual address bits.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits);
+
+/**
+ * kvm_pgtable_hyp_destroy() - Destroy an unused hypervisor stage-1 page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_hyp_init().
+ *
+ * The page-table is assumed to be unreachable by any hardware walkers prior
+ * to freeing and therefore no TLB invalidation is performed.
+ */
+void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt);
+
+/**
+ * kvm_pgtable_hyp_map() - Install a mapping in a hypervisor stage-1 page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_hyp_init().
+ * @addr:	Virtual address at which to place the mapping.
+ * @size:	Size of the mapping.
+ * @phys:	Physical address of the memory to map.
+ * @prot:	Permissions and attributes for the mapping.
+ *
+ * If device attributes are not explicitly requested in @prot, then the
+ * mapping will be normal, cacheable.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
+			enum kvm_pgtable_prot prot);
+
 /**
  * kvm_pgtable_walk() - Walk a page-table.
  * @pgt:	Page-table structure initialised by kvm_pgtable_*_init().

142 lines not on this page · raw message

index 0f078b1920ff..42fb50cfe0d8 100644
@@ -43,16 +43,6 @@
  *	HYP_VA_MIN = 1 << (VA_BITS - 1)
  * HYP_VA_MAX = HYP_VA_MIN + (1 << (VA_BITS - 1)) - 1
  *
- * This of course assumes that the trampoline page exists within the
- * VA_BITS range. If it doesn't, then it means we're in the odd case
- * where the kernel idmap (as well as HYP) uses more levels than the
- * kernel runtime page tables (as seen when the kernel is configured
- * for 4k pages, 39bits VA, and yet memory lives just above that
- * limit, forcing the idmap to use 4 levels of page tables while the
- * kernel itself only uses 3). In this particular case, it doesn't
- * matter which side of VA_BITS we use, as we're guaranteed not to
- * conflict with anything.
- *
  * When using VHE, there are no separate hyp mappings and all KVM
  * functionality is already mapped as part of the main kernel
  * mappings, and none of this applies in that case.

@@ -123,9 +113,10 @@ static inline bool kvm_page_empty(void *ptr)
 	return page_count(ptr_page) == 1;
 }
 
+#include <asm/kvm_pgtable.h>
 #include <asm/stage2_pgtable.h>
 
-int create_hyp_mappings(void *from, void *to, pgprot_t prot);
+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,
 			   void __iomem **haddr);

@@ -144,8 +135,6 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
 phys_addr_t kvm_mmu_get_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
 int kvm_mmu_init(void);
-void kvm_clear_hyp_idmap(void);
-
 #define kvm_mk_pmd(ptep)					\
 	__pmd(__phys_to_pmd_val(__pa(ptep)) | PMD_TYPE_TABLE)
 #define kvm_mk_pud(pmdp)					\

@@ -263,25 +252,6 @@ static inline bool kvm_s2pud_young(pud_t pud)
 	return pud_young(pud);
 }
 
-#define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
-
-#ifdef __PAGETABLE_PMD_FOLDED
-#define hyp_pmd_table_empty(pmdp) (0)
-#else
-#define hyp_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
-#endif
-
-#ifdef __PAGETABLE_PUD_FOLDED
-#define hyp_pud_table_empty(pudp) (0)
-#else
-#define hyp_pud_table_empty(pudp) kvm_page_empty(pudp)
-#endif
-
-#ifdef __PAGETABLE_P4D_FOLDED
-#define hyp_p4d_table_empty(p4dp) (0)
-#else
-#define hyp_p4d_table_empty(p4dp) kvm_page_empty(p4dp)
-#endif
 
 struct kvm;
 

@@ -350,50 +320,6 @@ static inline void __kvm_flush_dcache_pud(pud_t pud)
 void kvm_set_way_flush(struct kvm_vcpu *vcpu);
 void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
 
-static inline bool __kvm_cpu_uses_extended_idmap(void)
-{
-	return __cpu_uses_extended_idmap_level();
-}
-
-static inline unsigned long __kvm_idmap_ptrs_per_pgd(void)
-{
-	return idmap_ptrs_per_pgd;
-}
-
-/*
- * Can't use pgd_populate here, because the extended idmap adds an extra level
- * above CONFIG_PGTABLE_LEVELS (which is 2 or 3 if we're using the extended
- * idmap), and pgd_populate is only available if CONFIG_PGTABLE_LEVELS = 4.
- */
-static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
-				       pgd_t *hyp_pgd,
-				       pgd_t *merged_hyp_pgd,
-				       unsigned long hyp_idmap_start)
-{
-	int idmap_idx;
-	u64 pgd_addr;
-
-	/*
-	 * Use the first entry to access the HYP mappings. It is
-	 * guaranteed to be free, otherwise we wouldn't use an
-	 * extended idmap.
-	 */
-	VM_BUG_ON(pgd_val(merged_hyp_pgd[0]));
-	pgd_addr = __phys_to_pgd_val(__pa(hyp_pgd));
-	merged_hyp_pgd[0] = __pgd(pgd_addr | PMD_TYPE_TABLE);
-
-	/*
-	 * Create another extended level entry that points to the boot HYP map,
-	 * which contains an ID mapping of the HYP init code. We essentially
-	 * merge the boot and runtime HYP maps by doing so, but they don't
-	 * overlap anyway, so this is fine.
-	 */
-	idmap_idx = hyp_idmap_start >> VA_BITS;
-	VM_BUG_ON(pgd_val(merged_hyp_pgd[idmap_idx]));
-	pgd_addr = __phys_to_pgd_val(__pa(boot_hyp_pgd));
-	merged_hyp_pgd[idmap_idx] = __pgd(pgd_addr | PMD_TYPE_TABLE);
-}
-
 static inline unsigned int kvm_get_vmid_bits(void)
 {
 	int reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);

index ec9f98527dcc..2af84ab78cb8 100644
@@ -44,6 +44,11 @@ enum kvm_pgtable_prot {
 	KVM_PGTABLE_PROT_DEVICE			= BIT(3),
 };
 
+#define PAGE_HYP		(KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W)
+#define PAGE_HYP_EXEC		(KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_X)
+#define PAGE_HYP_RO		(KVM_PGTABLE_PROT_R)
+#define PAGE_HYP_DEVICE		(PAGE_HYP | KVM_PGTABLE_PROT_DEVICE)
+
 /**
  * enum kvm_pgtable_walk_flags - Flags to control a depth-first page-table walk.
  * @KVM_PGTABLE_WALK_LEAF:		Visit leaf entries, including invalid

index d400a4d9aee2..1a989353144e 100644
@@ -194,12 +194,6 @@
  */
 #define PTE_S2_MEMATTR(t)	(_AT(pteval_t, (t)) << 2)
 
-/*
- * EL2/HYP PTE/PMD definitions
- */
-#define PMD_HYP			PMD_SECT_USER
-#define PTE_HYP			PTE_USER
-
 /*
  * Highest possible physical address supported.
  */

index 4d867c6446c4..88acd7e1cd05 100644
@@ -56,7 +56,6 @@ extern bool arm64_use_ng_mappings;
 #define PROT_SECT_NORMAL_EXEC	(PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
 
 #define _PAGE_DEFAULT		(_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
-#define _HYP_PAGE_DEFAULT	_PAGE_DEFAULT
 
 #define PAGE_KERNEL		__pgprot(PROT_NORMAL)
 #define PAGE_KERNEL_RO		__pgprot((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)

@@ -64,11 +63,6 @@ extern bool arm64_use_ng_mappings;
 #define PAGE_KERNEL_EXEC	__pgprot(PROT_NORMAL & ~PTE_PXN)
 #define PAGE_KERNEL_EXEC_CONT	__pgprot((PROT_NORMAL & ~PTE_PXN) | PTE_CONT)
 
-#define PAGE_HYP		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
-#define PAGE_HYP_EXEC		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
-#define PAGE_HYP_RO		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
-#define PAGE_HYP_DEVICE		__pgprot(_PROT_DEFAULT | PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_HYP | PTE_HYP_XN)
-
 #define PAGE_S2_MEMATTR(attr)						\
 	({								\
 		u64 __val;						\

521 lines not on this page · raw message

index e52c927aade5..0b7c702b2151 100644
@@ -81,6 +81,7 @@ struct kvm_s2_mmu {
 	 */
 	pgd_t		*pgd;
 	phys_addr_t	pgd_phys;
+	struct kvm_pgtable *pgt;
 
 	/* The last vcpu id that ran on each physical CPU */
 	int __percpu *last_vcpu_ran;

index 2af84ab78cb8..3389f978d573 100644
@@ -116,6 +116,24 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt);
 int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
 			enum kvm_pgtable_prot prot);
 
+/**
+ * kvm_pgtable_stage2_init() - Initialise a guest stage-2 page-table.
+ * @pgt:	Uninitialised page-table structure to initialise.
+ * @kvm:	KVM structure representing the guest virtual machine.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm *kvm);
+
+/**
+ * kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init().
+ *
+ * The page-table is assumed to be unreachable by any hardware walkers prior
+ * to freeing and therefore no TLB invalidation is performed.
+ */
+void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
+
 /**
  * kvm_pgtable_walk() - Walk a page-table.
  * @pgt:	Page-table structure initialised by kvm_pgtable_*_init().

54 lines not on this page · raw message

96 lines not on this page · raw message

index 3389f978d573..8ab0d5f43817 100644
@@ -134,6 +134,45 @@ int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm *kvm);
  */
 void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
 
+/**
+ * kvm_pgtable_stage2_map() - Install a mapping in a guest stage-2 page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init().
+ * @addr:	Intermediate physical address at which to place the mapping.
+ * @size:	Size of the mapping.
+ * @phys:	Physical address of the memory to map.
+ * @prot:	Permissions and attributes for the mapping.
+ * @mc:		Cache of pre-allocated GFP_PGTABLE_USER memory from which to
+ *		allocate page-table pages.
+ *
+ * If device attributes are not explicitly requested in @prot, then the
+ * mapping will be normal, cacheable.
+ *
+ * Note that this function will both coalesce existing table entries and split
+ * existing block mappings, relying on page-faults to fault back areas outside
+ * of the new mapping lazily.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
+			   u64 phys, enum kvm_pgtable_prot prot,
+			   struct kvm_mmu_memory_cache *mc);
+
+/**
+ * kvm_pgtable_stage2_unmap() - Remove a mapping from a guest stage-2 page-table.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init().
+ * @addr:	Intermediate physical address from which to remove the mapping.
+ * @size:	Size of the mapping.
+ *
+ * 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. Unmapping a cacheable page will ensure that it is clean to the PoC if
+ * FWB is not supported by the CPU.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
+
 /**
  * kvm_pgtable_walk() - Walk a page-table.
  * @pgt:	Page-table structure initialised by kvm_pgtable_*_init().

278 lines not on this page · raw message

index 41ee8f3c0369..6f65d3841ec9 100644
@@ -439,18 +439,6 @@ struct stage2_map_data {
 	struct kvm_mmu_memory_cache	*memcache;
 };
 
-static kvm_pte_t *stage2_memcache_alloc_page(struct stage2_map_data *data)
-{
-	kvm_pte_t *ptep = NULL;
-	struct kvm_mmu_memory_cache *mc = data->memcache;
-
-	/* Allocated with GFP_PGTABLE_USER, so no need to zero */
-	if (mc && mc->nobjs)
-		ptep = mc->objects[--mc->nobjs];
-
-	return ptep;
-}
-
 static int stage2_map_set_prot_attr(enum kvm_pgtable_prot prot,
 				    struct stage2_map_data *data)
 {

@@ -531,7 +519,7 @@ static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
 	if (WARN_ON(level == KVM_PGTABLE_MAX_LEVELS - 1))
 		return -EINVAL;
 
-	childp = stage2_memcache_alloc_page(data);
+	childp = kvm_mmu_memory_cache_alloc(data->memcache);
 	if (!childp)
 		return -ENOMEM;
 

index fdca6b69944b..d0c440e2622d 100644
@@ -1154,32 +1154,28 @@ static int stage2_pudp_test_and_clear_young(pud_t *pud)
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			  phys_addr_t pa, unsigned long size, bool writable)
 {
-	phys_addr_t addr, end;
+	phys_addr_t addr;
 	int ret = 0;
-	unsigned long pfn;
 	struct kvm_mmu_memory_cache cache = { 0, __GFP_ZERO, NULL, };
+	struct kvm_pgtable *pgt = kvm->arch.mmu.pgt;
+	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_DEVICE |
+				     KVM_PGTABLE_PROT_R |
+				     (writable ? KVM_PGTABLE_PROT_W : 0);
 
-	end = (guest_ipa + size + PAGE_SIZE - 1) & PAGE_MASK;
-	pfn = __phys_to_pfn(pa);
-
-	for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) {
-		pte_t pte = kvm_pfn_pte(pfn, PAGE_S2_DEVICE);
-
-		if (writable)
-			pte = kvm_s2pte_mkwrite(pte);
-
+	for (addr = guest_ipa; addr < guest_ipa + size; addr += PAGE_SIZE) {
 		ret = kvm_mmu_topup_memory_cache(&cache,
 						 kvm_mmu_cache_min_pages(kvm));
 		if (ret)
 			break;
+
 		spin_lock(&kvm->mmu_lock);
-		ret = stage2_set_pte(&kvm->arch.mmu, &cache, addr, &pte,
-				     KVM_S2PTE_FLAG_IS_IOMAP);
+		ret = kvm_pgtable_stage2_map(pgt, addr, PAGE_SIZE, pa, prot,
+					     &cache);
 		spin_unlock(&kvm->mmu_lock);
 		if (ret)
 			break;
 
-		pfn++;
+		pa += PAGE_SIZE;
 	}
 
 	return ret;

index d0c440e2622d..eb1ba29fd4e7 100644
@@ -1910,28 +1910,27 @@ int kvm_unmap_hva_range(struct kvm *kvm,
 
 static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
-	pte_t *pte = (pte_t *)data;
+	kvm_pfn_t *pfn = (kvm_pfn_t *)data;
 
 	WARN_ON(size != PAGE_SIZE);
+
 	/*
-	 * We can always call stage2_set_pte with KVM_S2PTE_FLAG_LOGGING_ACTIVE
-	 * flag clear because MMU notifiers will have unmapped a huge PMD before
-	 * calling ->change_pte() (which in turn calls kvm_set_spte_hva()) and
-	 * therefore stage2_set_pte() never needs to clear out a huge PMD
-	 * through this calling path.
+	 * The MMU notifiers will have unmapped a huge PMD before calling
+	 * ->change_pte() (which in turn calls kvm_set_spte_hva()) and
+	 * therefore we never need to clear out a huge PMD through this
+	 * calling path and a memcache is not required.
 	 */
-	stage2_set_pte(&kvm->arch.mmu, NULL, gpa, pte, 0);
+	kvm_pgtable_stage2_map(kvm->arch.mmu.pgt, gpa, PAGE_SIZE,
+			       __pfn_to_phys(*pfn), KVM_PGTABLE_PROT_R, NULL);
 	return 0;
 }
 
-
 int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
 	unsigned long end = hva + PAGE_SIZE;
 	kvm_pfn_t pfn = pte_pfn(pte);
-	pte_t stage2_pte;
 
-	if (!kvm->arch.mmu.pgd)
+	if (!kvm->arch.mmu.pgt)
 		return 0;
 
 	trace_kvm_set_spte_hva(hva);

@@ -1941,9 +1940,7 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 	 * just like a translation fault and clean the cache to the PoC.
 	 */
 	clean_dcache_guest_page(pfn, PAGE_SIZE);
-	stage2_pte = kvm_pfn_pte(pfn, PAGE_S2);
-	handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte);
-
+	handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &pfn);
 	return 0;
 }
 

index eb1ba29fd4e7..f4cc2c657091 100644
@@ -39,6 +39,33 @@ static bool is_iomap(unsigned long flags)
 	return flags & KVM_S2PTE_FLAG_IS_IOMAP;
 }
 
+/*
+ * Release kvm_mmu_lock periodically if the memory region is large. Otherwise,
+ * we may see kernel panics with CONFIG_DETECT_HUNG_TASK,
+ * CONFIG_LOCKUP_DETECTOR, CONFIG_LOCKDEP. Additionally, holding the lock too
+ * long will also starve other vCPUs. We have to also make sure that the page
+ * tables are not freed while we released the lock.
+ */
+#define stage2_apply_range(kvm, addr, end, fn, resched)			\
+({									\
+	int ret;							\
+	struct kvm *__kvm = (kvm);					\
+	bool __resched = (resched);					\
+	u64 next, __addr = (addr), __end = (end);			\
+	do {								\
+		struct kvm_pgtable *pgt = __kvm->arch.mmu.pgt;		\
+		if (!pgt)						\
+			break;						\
+		next = stage2_pgd_addr_end(__kvm, __addr, __end);	\
+		ret = fn(pgt, __addr, next - __addr);			\
+		if (ret)						\
+			break;						\
+		if (__resched && next != __end)				\
+			cond_resched_lock(&__kvm->mmu_lock);		\
+	} while (__addr = next, __addr != __end);			\
+	ret;								\
+})
+
 static bool memslot_is_logging(struct kvm_memory_slot *memslot)
 {
 	return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);

@@ -220,8 +247,8 @@ static inline void kvm_pgd_populate(pgd_t *pgdp, p4d_t *p4dp)
  * end up writing old data to disk.
  *
  * This is why right after unmapping a page/section and invalidating
- * the corresponding TLBs, we call kvm_flush_dcache_p*() to make sure
- * the IO subsystem will never hit in the cache.
+ * the corresponding TLBs, we flush to make sure the IO subsystem will
+ * never hit in the cache.
  *
  * This is all avoided on systems that have ARM64_HAS_STAGE2_FWB, as
  * we then fully enforce cacheability of RAM, no matter what the guest

@@ -344,32 +371,12 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
 				 u64 size, bool may_block)
 {
 	struct kvm *kvm = mmu->kvm;
-	pgd_t *pgd;
-	phys_addr_t addr = start, end = start + size;
-	phys_addr_t next;
+	phys_addr_t end = start + size;
 
 	assert_spin_locked(&kvm->mmu_lock);
 	WARN_ON(size & ~PAGE_MASK);
-
-	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
-	do {
-		/*
-		 * Make sure the page table is still active, as another thread
-		 * could have possibly freed the page table, while we released
-		 * the lock.
-		 */
-		if (!READ_ONCE(mmu->pgd))
-			break;
-		next = stage2_pgd_addr_end(kvm, addr, end);
-		if (!stage2_pgd_none(kvm, *pgd))
-			unmap_stage2_p4ds(mmu, pgd, addr, next);
-		/*
-		 * If the range is too large, release the kvm->mmu_lock
-		 * to prevent starvation and lockup detector warnings.
-		 */
-		if (may_block && next != end)
-			cond_resched_lock(&kvm->mmu_lock);
-	} while (pgd++, addr = next, addr != end);
+	WARN_ON(stage2_apply_range(kvm, start, end, kvm_pgtable_stage2_unmap,
+				   may_block));
 }
 
 static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)

index 8ab0d5f43817..ae56534f87a0 100644
@@ -173,6 +173,44 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
  */
 int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
 
+/**
+ * kvm_pgtable_stage2_mkyoung() - Set the access flag in a page-table entry.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init().
+ * @addr:	Intermediate physical address to identify the page-table entry.
+ *
+ * If there is a valid, leaf page-table entry used to translate @addr, then
+ * set the access flag in that entry.
+ *
+ * Return: The old page-table entry prior to setting the flag, 0 on failure.
+ */
+kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr);
+
+/**
+ * kvm_pgtable_stage2_mkold() - Clear the access flag in a page-table entry.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init().
+ * @addr:	Intermediate physical address to identify the page-table entry.
+ *
+ * If there is a valid, leaf page-table entry used to translate @addr, then
+ * clear the access flag in that entry.
+ *
+ * Note that it is the caller's responsibility to invalidate the TLB after
+ * calling this function to ensure that the updated permissions are visible
+ * to the CPUs.
+ *
+ * Return: The old page-table entry prior to clearing the flag, 0 on failure.
+ */
+kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr);
+
+/**
+ * kvm_pgtable_stage2_is_young() - Test whether a page-table entry has the
+ *				   access flag set.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init().
+ * @addr:	Intermediate physical address to identify the page-table entry.
+ *
+ * Return: True if the page-table entry has the access flag set, false otherwise.
+ */
+bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr);
+
 /**
  * kvm_pgtable_walk() - Walk a page-table.
  * @pgt:	Page-table structure initialised by kvm_pgtable_*_init().

92 lines not on this page · raw message

index f4cc2c657091..98815f6b8471 100644
@@ -1697,46 +1697,23 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	return ret;
 }
 
-/*
- * Resolve the access fault by making the page young again.
- * Note that because the faulting entry is guaranteed not to be
- * cached in the TLB, we don't need to invalidate anything.
- * Only the HW Access Flag updates are supported for Stage 2 (no DBM),
- * so there is no need for atomic (pte|pmd)_mkyoung operations.
- */
+/* Resolve the access fault by making the page young again. */
 static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 {
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-	kvm_pfn_t pfn;
-	bool pfn_valid = false;
+	pte_t pte;
+	kvm_pte_t kpte;
+	struct kvm_s2_mmu *mmu;
 
 	trace_kvm_access_fault(fault_ipa);
 
 	spin_lock(&vcpu->kvm->mmu_lock);
-
-	if (!stage2_get_leaf_entry(vcpu->arch.hw_mmu, fault_ipa, &pud, &pmd, &pte))
-		goto out;
-
-	if (pud) {		/* HugeTLB */
-		*pud = kvm_s2pud_mkyoung(*pud);
-		pfn = kvm_pud_pfn(*pud);
-		pfn_valid = true;
-	} else	if (pmd) {	/* THP, HugeTLB */
-		*pmd = pmd_mkyoung(*pmd);
-		pfn = pmd_pfn(*pmd);
-		pfn_valid = true;
-	} else {
-		*pte = pte_mkyoung(*pte);	/* Just a page... */
-		pfn = pte_pfn(*pte);
-		pfn_valid = true;
-	}
-
-out:
+	mmu = vcpu->arch.hw_mmu;
+	kpte = kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa);
 	spin_unlock(&vcpu->kvm->mmu_lock);
-	if (pfn_valid)
-		kvm_set_pfn_accessed(pfn);
+
+	pte = __pte(kpte);
+	if (pte_valid(pte))
+		kvm_set_pfn_accessed(pte_pfn(pte));
 }
 
 /**

@@ -1953,38 +1930,19 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 
 static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
+	pte_t pte;
+	kvm_pte_t kpte;
 
 	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
-	if (!stage2_get_leaf_entry(&kvm->arch.mmu, gpa, &pud, &pmd, &pte))
-		return 0;
-
-	if (pud)
-		return stage2_pudp_test_and_clear_young(pud);
-	else if (pmd)
-		return stage2_pmdp_test_and_clear_young(pmd);
-	else
-		return stage2_ptep_test_and_clear_young(pte);
+	kpte = kvm_pgtable_stage2_mkold(kvm->arch.mmu.pgt, gpa);
+	pte = __pte(kpte);
+	return pte_valid(pte) && pte_young(pte);
 }
 
 static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
 	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE);
-	if (!stage2_get_leaf_entry(&kvm->arch.mmu, gpa, &pud, &pmd, &pte))
-		return 0;
-
-	if (pud)
-		return kvm_s2pud_young(*pud);
-	else if (pmd)
-		return pmd_young(*pmd);
-	else
-		return pte_young(*pte);
+	return kvm_pgtable_stage2_is_young(kvm->arch.mmu.pgt, gpa);
 }
 
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)

index ae56534f87a0..0c96b78d791d 100644
@@ -173,6 +173,21 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
  */
 int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
 
+/**
+ * kvm_pgtable_stage2_wrprotect() - Write-protect guest stage-2 address range
+ *                                  without TLB invalidation.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init().
+ * @addr:	Intermediate physical address from which to write-protect,
+ * @size:	Size of the range.
+ *
+ * Note that it is the caller's responsibility to invalidate the TLB after
+ * calling this function to ensure that the updated permissions are visible
+ * to the CPUs.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size);
+
 /**
  * kvm_pgtable_stage2_mkyoung() - Set the access flag in a page-table entry.
  * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init().

index 30713eb773e0..c218651f8eba 100644
@@ -726,6 +726,12 @@ static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr,
 	return 0;
 }
 
+int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
+{
+	return stage2_update_leaf_attrs(pgt, addr, size, 0,
+					KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W, NULL);
+}
+
 kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr)
 {
 	kvm_pte_t pte = 0;

index 98815f6b8471..60f021430fcc 100644
@@ -66,6 +66,9 @@ static bool is_iomap(unsigned long flags)
 	ret;								\
 })
 
+#define stage2_apply_range_resched(kvm, addr, end, fn)			\
+	stage2_apply_range(kvm, addr, end, fn, true)
+
 static bool memslot_is_logging(struct kvm_memory_slot *memslot)
 {
 	return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);

@@ -1293,27 +1296,7 @@ static void  stage2_wp_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
 static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
 {
 	struct kvm *kvm = mmu->kvm;
-	pgd_t *pgd;
-	phys_addr_t next;
-
-	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
-	do {
-		/*
-		 * Release kvm_mmu_lock periodically if the memory region is
-		 * large. Otherwise, we may see kernel panics with
-		 * CONFIG_DETECT_HUNG_TASK, CONFIG_LOCKUP_DETECTOR,
-		 * CONFIG_LOCKDEP. Additionally, holding the lock too long
-		 * will also starve other vCPUs. We have to also make sure
-		 * that the page tables are not freed while we released
-		 * the lock.
-		 */
-		cond_resched_lock(&kvm->mmu_lock);
-		if (!READ_ONCE(mmu->pgd))
-			break;
-		next = stage2_pgd_addr_end(kvm, addr, end);
-		if (stage2_pgd_present(kvm, *pgd))
-			stage2_wp_p4ds(mmu, pgd, addr, next);
-	} while (pgd++, addr = next, addr != end);
+	stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_wrprotect);
 }
 
 /**

index 0c96b78d791d..ea823fe31913 100644
@@ -226,6 +226,18 @@ kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr);
  */
 bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr);
 
+/**
+ * kvm_pgtable_stage2_flush_range() - Clean and invalidate data cache to Point
+ * 				      of Coherency for guest stage-2 address
+ *				      range.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init().
+ * @addr:	Intermediate physical address from which to flush.
+ * @size:	Size of the range.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size);
+
 /**
  * kvm_pgtable_walk() - Walk a page-table.
  * @pgt:	Page-table structure initialised by kvm_pgtable_*_init().

index c218651f8eba..75887185f1e2 100644
@@ -762,6 +762,32 @@ bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr)
 	return pte & KVM_PTE_LEAF_ATTR_LO_S2_AF;
 }
 
+static int stage2_flush_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
+			       enum kvm_pgtable_walk_flags flag,
+			       void * const arg)
+{
+	kvm_pte_t pte = *ptep;
+
+	if (!kvm_pte_valid(pte) || !stage2_pte_cacheable(pte))
+		return 0;
+
+	stage2_flush_dcache(kvm_pte_follow(pte), kvm_granule_size(level));
+	return 0;
+}
+
+int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
+{
+	struct kvm_pgtable_walker walker = {
+		.cb	= stage2_flush_walker,
+		.flags	= KVM_PGTABLE_WALK_LEAF,
+	};
+
+	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
+		return 0;
+
+	return kvm_pgtable_walk(pgt, addr, size, &walker);
+}
+
 int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm *kvm)
 {
 	size_t pgd_sz;

index 60f021430fcc..7b569bb1314f 100644
@@ -455,21 +455,10 @@ static void stage2_flush_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd,
 static void stage2_flush_memslot(struct kvm *kvm,
 				 struct kvm_memory_slot *memslot)
 {
-	struct kvm_s2_mmu *mmu = &kvm->arch.mmu;
 	phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
 	phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
-	phys_addr_t next;
-	pgd_t *pgd;
-
-	pgd = mmu->pgd + stage2_pgd_index(kvm, addr);
-	do {
-		next = stage2_pgd_addr_end(kvm, addr, end);
-		if (!stage2_pgd_none(kvm, *pgd))
-			stage2_flush_p4ds(mmu, pgd, addr, next);
 
-		if (next != end)
-			cond_resched_lock(&kvm->mmu_lock);
-	} while (pgd++, addr = next, addr != end);
+	stage2_apply_range_resched(kvm, addr, end, kvm_pgtable_stage2_flush);
 }
 
 /**

index ea823fe31913..0d7077c34152 100644
@@ -216,6 +216,23 @@ kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr);
  */
 kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr);
 
+/**
+ * kvm_pgtable_stage2_relax_perms() - Relax the permissions enforced by a
+ *				      page-table entry.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init().
+ * @addr:	Intermediate physical address to identify the page-table entry.
+ * @prot:	Additional permissions to grant for the mapping.
+ *
+ * If there is a valid, leaf page-table entry used to translate @addr, then
+ * relax the permissions in that entry according to the read, write and
+ * execute permissions specified by @prot. No permissions are removed, and
+ * TLB invalidation is performed after updating the entry.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
+				   enum kvm_pgtable_prot prot);
+
 /**
  * kvm_pgtable_stage2_is_young() - Test whether a page-table entry has the
  *				   access flag set.

index 75887185f1e2..6e8ca1ec12b4 100644
@@ -762,6 +762,26 @@ bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr)
 	return pte & KVM_PTE_LEAF_ATTR_LO_S2_AF;
 }
 
+int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
+				   enum kvm_pgtable_prot prot)
+{
+	int ret;
+	kvm_pte_t set = 0, clr = 0;
+
+	if (prot & KVM_PGTABLE_PROT_R)
+		set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R;
+
+	if (prot & KVM_PGTABLE_PROT_W)
+		set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W;
+
+	if (prot & KVM_PGTABLE_PROT_X)
+		clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN;
+
+	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL);
+	kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, pgt->mmu, addr, 0);
+	return ret;
+}
+
 static int stage2_flush_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
 			       enum kvm_pgtable_walk_flags flag,
 			       void * const arg)

index 7b569bb1314f..c2b27935ca46 100644
@@ -1490,7 +1490,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 {
 	int ret;
 	bool write_fault, writable, force_pte = false;
-	bool exec_fault, needs_exec;
+	bool exec_fault;
+	bool device = false;
 	unsigned long mmu_seq;
 	gfn_t gfn = fault_ipa >> PAGE_SHIFT;
 	struct kvm *kvm = vcpu->kvm;

@@ -1498,10 +1499,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	struct vm_area_struct *vma;
 	short vma_shift;
 	kvm_pfn_t pfn;
-	pgprot_t mem_type = PAGE_S2;
 	bool logging_active = memslot_is_logging(memslot);
-	unsigned long vma_pagesize, flags = 0;
-	struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
+	unsigned long vma_pagesize;
+	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
+	struct kvm_pgtable *pgt;
 
 	write_fault = kvm_is_write_fault(vcpu);
 	exec_fault = kvm_vcpu_trap_is_iabt(vcpu);

@@ -1534,22 +1535,16 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		vma_pagesize = PAGE_SIZE;
 	}
 
-	/*
-	 * The stage2 has a minimum of 2 level table (For arm64 see
-	 * kvm_arm_setup_stage2()). Hence, we are guaranteed that we can
-	 * use PMD_SIZE huge mappings (even when the PMD is folded into PGD).
-	 * As for PUD huge maps, we must make sure that we have at least
-	 * 3 levels, i.e, PMD is not folded.
-	 */
-	if (vma_pagesize == PMD_SIZE ||
-	    (vma_pagesize == PUD_SIZE && kvm_stage2_has_pmd(kvm)))
+	if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE)
 		gfn = (fault_ipa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT;
 	mmap_read_unlock(current->mm);
 
-	/* We need minimum second+third level pages */
-	ret = kvm_mmu_topup_memory_cache(memcache, kvm_mmu_cache_min_pages(kvm));
-	if (ret)
-		return ret;
+	if (fault_status != FSC_PERM) {
+		ret = kvm_mmu_topup_memory_cache(memcache,
+						 kvm_mmu_cache_min_pages(kvm));
+		if (ret)
+			return ret;
+	}
 
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	/*

@@ -1572,28 +1567,20 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 
 	if (kvm_is_device_pfn(pfn)) {
-		mem_type = PAGE_S2_DEVICE;
-		flags |= KVM_S2PTE_FLAG_IS_IOMAP;
-	} else if (logging_active) {
-		/*
-		 * Faults on pages in a memslot with logging enabled
-		 * should not be mapped with huge pages (it introduces churn
-		 * and performance degradation), so force a pte mapping.
-		 */
-		flags |= KVM_S2_FLAG_LOGGING_ACTIVE;
-
+		device = true;
+	} else if (logging_active && !write_fault) {
 		/*
 		 * Only actually map the page as writable if this was a write
 		 * fault.
 		 */
-		if (!write_fault)
-			writable = false;
+		writable = false;
 	}
 
-	if (exec_fault && is_iomap(flags))
+	if (exec_fault && device)
 		return -ENOEXEC;
 
 	spin_lock(&kvm->mmu_lock);
+	pgt = vcpu->arch.hw_mmu->pgt;
 	if (mmu_notifier_retry(kvm, mmu_seq))
 		goto out_unlock;
 

@@ -1604,62 +1591,31 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (vma_pagesize == PAGE_SIZE && !force_pte)
 		vma_pagesize = transparent_hugepage_adjust(memslot, hva,
 							   &pfn, &fault_ipa);
-	if (writable)
+	if (writable) {
+		prot |= KVM_PGTABLE_PROT_W;
 		kvm_set_pfn_dirty(pfn);
+		mark_page_dirty(kvm, gfn);
+	}
 
-	if (fault_status != FSC_PERM && !is_iomap(flags))
+	if (fault_status != FSC_PERM && !device)
 		clean_dcache_guest_page(pfn, vma_pagesize);
 
-	if (exec_fault)
+	if (exec_fault) {
+		prot |= KVM_PGTABLE_PROT_X;
 		invalidate_icache_guest_page(pfn, vma_pagesize);
+	}
 
-	/*
-	 * If we took an execution fault we have made the
-	 * icache/dcache coherent above and should now let the s2
-	 * mapping be executable.
-	 *
-	 * Write faults (!exec_fault && FSC_PERM) are orthogonal to
-	 * execute permissions, and we preserve whatever we have.
-	 */
-	needs_exec = exec_fault ||
-		(fault_status == FSC_PERM &&
-		 stage2_is_exec(mmu, fault_ipa, vma_pagesize));
-
-	if (vma_pagesize == PUD_SIZE) {
-		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
-
-		new_pud = kvm_pud_mkhuge(new_pud);
-		if (writable)
-			new_pud = kvm_s2pud_mkwrite(new_pud);
-
-		if (needs_exec)
-			new_pud = kvm_s2pud_mkexec(new_pud);
-
-		ret = stage2_set_pud_huge(mmu, memcache, fault_ipa, &new_pud);
-	} else if (vma_pagesize == PMD_SIZE) {
-		pmd_t new_pmd = kvm_pfn_pmd(pfn, mem_type);
-
-		new_pmd = kvm_pmd_mkhuge(new_pmd);
-
-		if (writable)
-			new_pmd = kvm_s2pmd_mkwrite(new_pmd);
-
-		if (needs_exec)
-			new_pmd = kvm_s2pmd_mkexec(new_pmd);
+	if (device)
+		prot |= KVM_PGTABLE_PROT_DEVICE;
+	else if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
+		prot |= KVM_PGTABLE_PROT_X;
 
-		ret = stage2_set_pmd_huge(mmu, memcache, fault_ipa, &new_pmd);
+	if (fault_status == FSC_PERM) {
+		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
 	} else {
-		pte_t new_pte = kvm_pfn_pte(pfn, mem_type);
-
-		if (writable) {
-			new_pte = kvm_s2pte_mkwrite(new_pte);
-			mark_page_dirty(kvm, gfn);
-		}
-
-		if (needs_exec)
-			new_pte = kvm_s2pte_mkexec(new_pte);
-
-		ret = stage2_set_pte(mmu, memcache, fault_ipa, &new_pte, flags);
+		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
+					     __pfn_to_phys(pfn), prot,
+					     memcache);
 	}
 
 out_unlock:

index c2b27935ca46..c34117cc7f59 100644
@@ -1812,7 +1812,7 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *dat
 int kvm_unmap_hva_range(struct kvm *kvm,
 			unsigned long start, unsigned long end, unsigned flags)
 {
-	if (!kvm->arch.mmu.pgd)
+	if (!kvm->arch.mmu.pgt)
 		return 0;
 
 	trace_kvm_unmap_hva_range(start, end);

@@ -1875,7 +1875,7 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *
 
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
-	if (!kvm->arch.mmu.pgd)
+	if (!kvm->arch.mmu.pgt)
 		return 0;
 	trace_kvm_age_hva(start, end);
 	return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);

@@ -1883,7 +1883,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 {
-	if (!kvm->arch.mmu.pgd)
+	if (!kvm->arch.mmu.pgt)
 		return 0;
 	trace_kvm_test_age_hva(hva);
 	return handle_hva_to_gpa(kvm, hva, hva + PAGE_SIZE,

index 42fb50cfe0d8..13ff00d9f16d 100644
@@ -135,123 +135,6 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
 phys_addr_t kvm_mmu_get_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
 int kvm_mmu_init(void);
-#define kvm_mk_pmd(ptep)					\
-	__pmd(__phys_to_pmd_val(__pa(ptep)) | PMD_TYPE_TABLE)
-#define kvm_mk_pud(pmdp)					\
-	__pud(__phys_to_pud_val(__pa(pmdp)) | PMD_TYPE_TABLE)
-#define kvm_mk_p4d(pmdp)					\
-	__p4d(__phys_to_p4d_val(__pa(pmdp)) | PUD_TYPE_TABLE)
-
-#define kvm_set_pud(pudp, pud)		set_pud(pudp, pud)
-
-#define kvm_pfn_pte(pfn, prot)		pfn_pte(pfn, prot)
-#define kvm_pfn_pmd(pfn, prot)		pfn_pmd(pfn, prot)
-#define kvm_pfn_pud(pfn, prot)		pfn_pud(pfn, prot)
-
-#define kvm_pud_pfn(pud)		pud_pfn(pud)
-
-#define kvm_pmd_mkhuge(pmd)		pmd_mkhuge(pmd)
-#define kvm_pud_mkhuge(pud)		pud_mkhuge(pud)
-
-static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
-{
-	pte_val(pte) |= PTE_S2_RDWR;
-	return pte;
-}
-
-static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd)
-{
-	pmd_val(pmd) |= PMD_S2_RDWR;
-	return pmd;
-}
-
-static inline pud_t kvm_s2pud_mkwrite(pud_t pud)
-{
-	pud_val(pud) |= PUD_S2_RDWR;
-	return pud;
-}
-
-static inline pte_t kvm_s2pte_mkexec(pte_t pte)
-{
-	pte_val(pte) &= ~PTE_S2_XN;
-	return pte;
-}
-
-static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd)
-{
-	pmd_val(pmd) &= ~PMD_S2_XN;
-	return pmd;
-}
-
-static inline pud_t kvm_s2pud_mkexec(pud_t pud)
-{
-	pud_val(pud) &= ~PUD_S2_XN;
-	return pud;
-}
-
-static inline void kvm_set_s2pte_readonly(pte_t *ptep)
-{
-	pteval_t old_pteval, pteval;
-
-	pteval = READ_ONCE(pte_val(*ptep));
-	do {
-		old_pteval = pteval;
-		pteval &= ~PTE_S2_RDWR;
-		pteval |= PTE_S2_RDONLY;
-		pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
-	} while (pteval != old_pteval);
-}
-
-static inline bool kvm_s2pte_readonly(pte_t *ptep)
-{
-	return (READ_ONCE(pte_val(*ptep)) & PTE_S2_RDWR) == PTE_S2_RDONLY;
-}
-
-static inline bool kvm_s2pte_exec(pte_t *ptep)
-{
-	return !(READ_ONCE(pte_val(*ptep)) & PTE_S2_XN);
-}
-
-static inline void kvm_set_s2pmd_readonly(pmd_t *pmdp)
-{
-	kvm_set_s2pte_readonly((pte_t *)pmdp);
-}
-
-static inline bool kvm_s2pmd_readonly(pmd_t *pmdp)
-{
-	return kvm_s2pte_readonly((pte_t *)pmdp);
-}
-
-static inline bool kvm_s2pmd_exec(pmd_t *pmdp)
-{
-	return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN);
-}
-
-static inline void kvm_set_s2pud_readonly(pud_t *pudp)
-{
-	kvm_set_s2pte_readonly((pte_t *)pudp);
-}
-
-static inline bool kvm_s2pud_readonly(pud_t *pudp)
-{
-	return kvm_s2pte_readonly((pte_t *)pudp);
-}
-
-static inline bool kvm_s2pud_exec(pud_t *pudp)
-{
-	return !(READ_ONCE(pud_val(*pudp)) & PUD_S2_XN);
-}
-
-static inline pud_t kvm_s2pud_mkyoung(pud_t pud)
-{
-	return pud_mkyoung(pud);
-}
-
-static inline bool kvm_s2pud_young(pud_t pud)
-{
-	return pud_young(pud);
-}
-
 
 struct kvm;
 

@@ -293,30 +176,6 @@ static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn,
 	}
 }
 
-static inline void __kvm_flush_dcache_pte(pte_t pte)
-{
-	if (!cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
-		struct page *page = pte_page(pte);
-		kvm_flush_dcache_to_poc(page_address(page), PAGE_SIZE);
-	}
-}
-
-static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
-{
-	if (!cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
-		struct page *page = pmd_page(pmd);
-		kvm_flush_dcache_to_poc(page_address(page), PMD_SIZE);
-	}
-}
-
-static inline void __kvm_flush_dcache_pud(pud_t pud)
-{
-	if (!cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
-		struct page *page = pud_page(pud);
-		kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE);
-	}
-}
-
 void kvm_set_way_flush(struct kvm_vcpu *vcpu);
 void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
 

index 1a989353144e..bb97d464f42b 100644
@@ -172,23 +172,6 @@
 #define PTE_ATTRINDX(t)		(_AT(pteval_t, (t)) << 2)
 #define PTE_ATTRINDX_MASK	(_AT(pteval_t, 7) << 2)
 
-/*
- * 2nd stage PTE definitions
- */
-#define PTE_S2_RDONLY		(_AT(pteval_t, 1) << 6)   /* HAP[2:1] */
-#define PTE_S2_RDWR		(_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
-#define PTE_S2_XN		(_AT(pteval_t, 2) << 53)  /* XN[1:0] */
-#define PTE_S2_SW_RESVD		(_AT(pteval_t, 15) << 55) /* Reserved for SW */
-
-#define PMD_S2_RDONLY		(_AT(pmdval_t, 1) << 6)   /* HAP[2:1] */
-#define PMD_S2_RDWR		(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
-#define PMD_S2_XN		(_AT(pmdval_t, 2) << 53)  /* XN[1:0] */
-#define PMD_S2_SW_RESVD		(_AT(pmdval_t, 15) << 55) /* Reserved for SW */
-
-#define PUD_S2_RDONLY		(_AT(pudval_t, 1) << 6)   /* HAP[2:1] */
-#define PUD_S2_RDWR		(_AT(pudval_t, 3) << 6)   /* HAP[2:1] */
-#define PUD_S2_XN		(_AT(pudval_t, 2) << 53)  /* XN[1:0] */
-
 /*
  * Memory Attribute override for Stage-2 (MemAttr[3:0])
  */

index 88acd7e1cd05..8f094c43072a 100644
@@ -73,19 +73,6 @@ extern bool arm64_use_ng_mappings;
 		__val;							\
 	 })
 
-#define PAGE_S2_XN							\
-	({								\
-		u64 __val;						\
-		if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))		\
-			__val = 0;					\
-		else							\
-			__val = PTE_S2_XN;				\
-		__val;							\
-	})
-
-#define PAGE_S2			__pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(NORMAL) | PTE_S2_RDONLY | PAGE_S2_XN)
-#define PAGE_S2_DEVICE		__pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN)
-
 #define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
 /* shared+writable pages are clean by default, hence PTE_RDONLY|PTE_WRITE */
 #define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)

237 lines not on this page · raw message

796 lines not on this page · raw message

index 0b7c702b2151..41caf29bd93c 100644
@@ -79,7 +79,6 @@ struct kvm_s2_mmu {
 	 * for vEL1/EL0 with vHCR_EL2.VM == 0.  In that case, we use the
 	 * canonical stage-2 page tables.
 	 */
-	pgd_t		*pgd;
 	phys_addr_t	pgd_phys;
 	struct kvm_pgtable *pgt;
 

index 8e64fecfb2f0..19f05fecea41 100644
@@ -384,7 +384,6 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
 	mmu->kvm = kvm;
 	mmu->pgt = pgt;
 	mmu->pgd_phys = __pa(pgt->pgd);
-	mmu->pgd = (void *)pgt->pgd;
 	mmu->vmid.vmid_gen = 0;
 	return 0;
 

@@ -470,7 +469,6 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
 	spin_lock(&kvm->mmu_lock);
 	pgt = mmu->pgt;
 	if (pgt) {
-		mmu->pgd = NULL;
 		mmu->pgd_phys = 0;
 		mmu->pgt = NULL;
 		free_percpu(mmu->last_vcpu_ran);

index ee33875c5c2a..471ee9234e40 100644
@@ -339,7 +339,7 @@ u32 get_kvm_ipa_limit(void)
 
 int kvm_set_ipa_limit(void)
 {
-	unsigned int ipa_max, pa_max, va_max, parange, tgran_2;
+	unsigned int parange, tgran_2;
 	u64 mmfr0;
 
 	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);

@@ -376,38 +376,10 @@ int kvm_set_ipa_limit(void)
 		break;
 	}
 
-	pa_max = id_aa64mmfr0_parange_to_phys_shift(parange);
-
-	/* Clamp the IPA limit to the PA size supported by the kernel */
-	ipa_max = (pa_max > PHYS_MASK_SHIFT) ? PHYS_MASK_SHIFT : pa_max;
-	/*
-	 * Since our stage2 table is dependent on the stage1 page table code,
-	 * we must always honor the following condition:
-	 *
-	 *  Number of levels in Stage1 >= Number of levels in Stage2.
-	 *
-	 * So clamp the ipa limit further down to limit the number of levels.
-	 * Since we can concatenate upto 16 tables at entry level, we could
-	 * go upto 4bits above the maximum VA addressable with the current
-	 * number of levels.
-	 */
-	va_max = PGDIR_SHIFT + PAGE_SHIFT - 3;
-	va_max += 4;
-
-	if (va_max < ipa_max)
-		ipa_max = va_max;
-
-	/*
-	 * If the final limit is lower than the real physical address
-	 * limit of the CPUs, report the reason.
-	 */
-	if (ipa_max < pa_max)
-		pr_info("kvm: Limiting the IPA size due to kernel %s Address limit\n",
-			(va_max < pa_max) ? "Virtual" : "Physical");
-
-	WARN(ipa_max < KVM_PHYS_SHIFT,
-	     "KVM IPA limit (%d bit) is smaller than default size\n", ipa_max);
-	kvm_ipa_limit = ipa_max;
+	kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange);
+	WARN(kvm_ipa_limit < KVM_PHYS_SHIFT,
+	     "KVM IPA limit (%d bit) is smaller than default size\n",
+	     kvm_ipa_limit);
 	kvm_info("IPA Size Limit: %dbits\n", kvm_ipa_limit);
 
 	return 0;