diff options
Diffstat (limited to 'arch/arm64')
45 files changed, 2787 insertions, 995 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 7cb7d635fbcc..cf6d1cd8b6dc 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1988,6 +1988,7 @@ config ARM64_MTE depends on ARM64_PAN select ARCH_HAS_SUBPAGE_FAULTS select ARCH_USES_HIGH_VMA_FLAGS + select ARCH_USES_PG_ARCH_X help Memory Tagging (part of the ARMv8.5 Extensions) provides architectural support for run-time, always-on detection of diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 8aa8492dafc0..0df3fc3a0173 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -135,7 +135,7 @@ * 40 bits wide (T0SZ = 24). Systems with a PARange smaller than 40 bits are * not known to exist and will break with this configuration. * - * The VTCR_EL2 is configured per VM and is initialised in kvm_arm_setup_stage2(). + * The VTCR_EL2 is configured per VM and is initialised in kvm_init_stage2_mmu. * * Note that when using 4K pages, we concatenate two first level page tables * together. With 16K pages, we concatenate 16 first level page tables. @@ -340,9 +340,13 @@ * We have * PAR [PA_Shift - 1 : 12] = PA [PA_Shift - 1 : 12] * HPFAR [PA_Shift - 9 : 4] = FIPA [PA_Shift - 1 : 12] + * + * Always assume 52 bit PA since at this point, we don't know how many PA bits + * the page table has been set up for. This should be safe since unused address + * bits in PAR are res0. */ #define PAR_TO_HPFAR(par) \ - (((par) & GENMASK_ULL(PHYS_MASK_SHIFT - 1, 12)) >> 8) + (((par) & GENMASK_ULL(52 - 1, 12)) >> 8) #define ECN(x) { ESR_ELx_EC_##x, #x } diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 53035763e48e..43c3bc0f9544 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -76,6 +76,9 @@ enum __kvm_host_smccc_func { __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs, __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs, __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_init_traps, + __KVM_HOST_SMCCC_FUNC___pkvm_init_vm, + __KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu, + __KVM_HOST_SMCCC_FUNC___pkvm_teardown_vm, }; #define DECLARE_KVM_VHE_SYM(sym) extern char sym[] @@ -106,7 +109,7 @@ enum __kvm_host_smccc_func { #define per_cpu_ptr_nvhe_sym(sym, cpu) \ ({ \ unsigned long base, off; \ - base = kvm_arm_hyp_percpu_base[cpu]; \ + base = kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu]; \ off = (unsigned long)&CHOOSE_NVHE_SYM(sym) - \ (unsigned long)&CHOOSE_NVHE_SYM(__per_cpu_start); \ base ? (typeof(CHOOSE_NVHE_SYM(sym))*)(base + off) : NULL; \ @@ -211,7 +214,7 @@ DECLARE_KVM_HYP_SYM(__kvm_hyp_vector); #define __kvm_hyp_init CHOOSE_NVHE_SYM(__kvm_hyp_init) #define __kvm_hyp_vector CHOOSE_HYP_SYM(__kvm_hyp_vector) -extern unsigned long kvm_arm_hyp_percpu_base[NR_CPUS]; +extern unsigned long kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[]; DECLARE_KVM_NVHE_SYM(__per_cpu_start); DECLARE_KVM_NVHE_SYM(__per_cpu_end); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index fd34ab155d0b..35a159d131b5 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -73,6 +73,63 @@ u32 __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu); +struct kvm_hyp_memcache { + phys_addr_t head; + unsigned long nr_pages; +}; + +static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc, + phys_addr_t *p, + phys_addr_t (*to_pa)(void *virt)) +{ + *p = mc->head; + mc->head = to_pa(p); + mc->nr_pages++; +} + +static inline void *pop_hyp_memcache(struct kvm_hyp_memcache *mc, + void *(*to_va)(phys_addr_t phys)) +{ + phys_addr_t *p = to_va(mc->head); + + if (!mc->nr_pages) + return NULL; + + mc->head = *p; + mc->nr_pages--; + + return p; +} + +static inline int __topup_hyp_memcache(struct kvm_hyp_memcache *mc, + unsigned long min_pages, + void *(*alloc_fn)(void *arg), + phys_addr_t (*to_pa)(void *virt), + void *arg) +{ + while (mc->nr_pages < min_pages) { + phys_addr_t *p = alloc_fn(arg); + + if (!p) + return -ENOMEM; + push_hyp_memcache(mc, p, to_pa); + } + + return 0; +} + +static inline void __free_hyp_memcache(struct kvm_hyp_memcache *mc, + void (*free_fn)(void *virt, void *arg), + void *(*to_va)(phys_addr_t phys), + void *arg) +{ + while (mc->nr_pages) + free_fn(pop_hyp_memcache(mc, to_va), arg); +} + +void free_hyp_memcache(struct kvm_hyp_memcache *mc); +int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages); + struct kvm_vmid { atomic64_t id; }; @@ -115,6 +172,13 @@ struct kvm_smccc_features { unsigned long vendor_hyp_bmap; }; +typedef unsigned int pkvm_handle_t; + +struct kvm_protected_vm { + pkvm_handle_t handle; + struct kvm_hyp_memcache teardown_mc; +}; + struct kvm_arch { struct kvm_s2_mmu mmu; @@ -163,9 +227,19 @@ struct kvm_arch { u8 pfr0_csv2; u8 pfr0_csv3; + struct { + u8 imp:4; + u8 unimp:4; + } dfr0_pmuver; /* Hypercall features firmware registers' descriptor */ struct kvm_smccc_features smccc_feat; + + /* + * For an untrusted host VM, 'pkvm.handle' is used to lookup + * the associated pKVM instance in the hypervisor. + */ + struct kvm_protected_vm pkvm; }; struct kvm_vcpu_fault_info { @@ -925,8 +999,6 @@ int kvm_set_ipa_limit(void); #define __KVM_HAVE_ARCH_VM_ALLOC struct kvm *kvm_arch_alloc_vm(void); -int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type); - static inline bool kvm_vm_is_protected(struct kvm *kvm) { return false; diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index aa7fa2a08f06..6797eafe7890 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -123,4 +123,7 @@ extern u64 kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val); +extern unsigned long kvm_nvhe_sym(__icache_flags); +extern unsigned int kvm_nvhe_sym(kvm_arm_vmid_bits); + #endif /* __ARM64_KVM_HYP_H__ */ diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 7784081088e7..e4a7e6369499 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -166,7 +166,7 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, void free_hyp_pgds(void); void stage2_unmap_vm(struct kvm *kvm); -int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu); +int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type); void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu); int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, phys_addr_t pa, unsigned long size, bool writable); diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 3252eb50ecfe..63f81b27a4e3 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -42,6 +42,8 @@ typedef u64 kvm_pte_t; #define KVM_PTE_ADDR_MASK GENMASK(47, PAGE_SHIFT) #define KVM_PTE_ADDR_51_48 GENMASK(15, 12) +#define KVM_PHYS_INVALID (-1ULL) + static inline bool kvm_pte_valid(kvm_pte_t pte) { return pte & KVM_PTE_VALID; @@ -57,6 +59,18 @@ static inline u64 kvm_pte_to_phys(kvm_pte_t pte) return pa; } +static inline kvm_pte_t kvm_phys_to_pte(u64 pa) +{ + kvm_pte_t pte = pa & KVM_PTE_ADDR_MASK; + + if (PAGE_SHIFT == 16) { + pa &= GENMASK(51, 48); + pte |= FIELD_PREP(KVM_PTE_ADDR_51_48, pa >> 48); + } + + return pte; +} + static inline u64 kvm_granule_shift(u32 level) { /* Assumes KVM_PGTABLE_MAX_LEVELS is 4 */ @@ -85,6 +99,8 @@ static inline bool kvm_level_supports_block_mapping(u32 level) * allocation is physically contiguous. * @free_pages_exact: Free an exact number of memory pages previously * allocated by zalloc_pages_exact. + * @free_removed_table: Free a removed paging structure by unlinking and + * dropping references. * @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 @@ -103,6 +119,7 @@ struct kvm_pgtable_mm_ops { void* (*zalloc_page)(void *arg); void* (*zalloc_pages_exact)(size_t size); void (*free_pages_exact)(void *addr, size_t size); + void (*free_removed_table)(void *addr, u32 level); void (*get_page)(void *addr); void (*put_page)(void *addr); int (*page_count)(void *addr); @@ -162,29 +179,6 @@ typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end, enum kvm_pgtable_prot prot); /** - * 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. - * @mm_ops: Memory management callbacks. - * @mmu: Stage-2 KVM MMU struct. Unused for stage-1 page-tables. - * @flags: Stage-2 page-table flags. - * @force_pte_cb: Function that returns true if page level mappings must - * be used instead of block mappings. - */ -struct kvm_pgtable { - u32 ia_bits; - u32 start_level; - kvm_pte_t *pgd; - struct kvm_pgtable_mm_ops *mm_ops; - - /* Stage-2 only */ - struct kvm_s2_mmu *mmu; - enum kvm_pgtable_stage2_flags flags; - kvm_pgtable_force_pte_cb_t force_pte_cb; -}; - -/** * enum kvm_pgtable_walk_flags - Flags to control a depth-first page-table walk. * @KVM_PGTABLE_WALK_LEAF: Visit leaf entries, including invalid * entries. @@ -192,17 +186,34 @@ struct kvm_pgtable { * children. * @KVM_PGTABLE_WALK_TABLE_POST: Visit table entries after their * children. + * @KVM_PGTABLE_WALK_SHARED: Indicates the page-tables may be shared + * with other software walkers. */ 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), + KVM_PGTABLE_WALK_SHARED = BIT(3), +}; + +struct kvm_pgtable_visit_ctx { + kvm_pte_t *ptep; + kvm_pte_t old; + void *arg; + struct kvm_pgtable_mm_ops *mm_ops; + u64 addr; + u64 end; + u32 level; + enum kvm_pgtable_walk_flags flags; }; -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); +typedef int (*kvm_pgtable_visitor_fn_t)(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit); + +static inline bool kvm_pgtable_walk_shared(const struct kvm_pgtable_visit_ctx *ctx) +{ + return ctx->flags & KVM_PGTABLE_WALK_SHARED; +} /** * struct kvm_pgtable_walker - Hook into a page-table walk. @@ -217,6 +228,94 @@ struct kvm_pgtable_walker { const enum kvm_pgtable_walk_flags flags; }; +/* + * RCU cannot be used in a non-kernel context such as the hyp. As such, page + * table walkers used in hyp do not call into RCU and instead use other + * synchronization mechanisms (such as a spinlock). + */ +#if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__) + +typedef kvm_pte_t *kvm_pteref_t; + +static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walker, + kvm_pteref_t pteref) +{ + return pteref; +} + +static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) +{ + /* + * Due to the lack of RCU (or a similar protection scheme), only + * non-shared table walkers are allowed in the hypervisor. + */ + if (walker->flags & KVM_PGTABLE_WALK_SHARED) + return -EPERM; + + return 0; +} + +static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker) {} + +static inline bool kvm_pgtable_walk_lock_held(void) +{ + return true; +} + +#else + +typedef kvm_pte_t __rcu *kvm_pteref_t; + +static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walker, + kvm_pteref_t pteref) +{ + return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED)); +} + +static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) +{ + if (walker->flags & KVM_PGTABLE_WALK_SHARED) + rcu_read_lock(); + + return 0; +} + +static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker) +{ + if (walker->flags & KVM_PGTABLE_WALK_SHARED) + rcu_read_unlock(); +} + +static inline bool kvm_pgtable_walk_lock_held(void) +{ + return rcu_read_lock_held(); +} + +#endif + +/** + * 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. + * @mm_ops: Memory management callbacks. + * @mmu: Stage-2 KVM MMU struct. Unused for stage-1 page-tables. + * @flags: Stage-2 page-table flags. + * @force_pte_cb: Function that returns true if page level mappings must + * be used instead of block mappings. + */ +struct kvm_pgtable { + u32 ia_bits; + u32 start_level; + kvm_pteref_t pgd; + struct kvm_pgtable_mm_ops *mm_ops; + + /* Stage-2 only */ + struct kvm_s2_mmu *mmu; + enum kvm_pgtable_stage2_flags flags; + kvm_pgtable_force_pte_cb_t force_pte_cb; +}; + /** * kvm_pgtable_hyp_init() - Initialise a hypervisor stage-1 page-table. * @pgt: Uninitialised page-table structure to initialise. @@ -297,6 +396,14 @@ u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size); u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift); /** + * kvm_pgtable_stage2_pgd_size() - Helper to compute size of a stage-2 PGD + * @vtcr: Content of the VTCR register. + * + * Return: the size (in bytes) of the stage-2 PGD + */ +size_t kvm_pgtable_stage2_pgd_size(u64 vtcr); + +/** * __kvm_pgtable_stage2_init() - Initialise a guest stage-2 page-table. * @pgt: Uninitialised page-table structure to initialise. * @mmu: S2 MMU context for this S2 translation @@ -325,6 +432,17 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt); /** + * kvm_pgtable_stage2_free_removed() - Free a removed stage-2 paging structure. + * @mm_ops: Memory management callbacks. + * @pgtable: Unlinked stage-2 paging structure to be freed. + * @level: Level of the stage-2 paging structure to be freed. + * + * 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_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level); + +/** * 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. @@ -333,6 +451,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt); * @prot: Permissions and attributes for the mapping. * @mc: Cache of pre-allocated and zeroed memory from which to allocate * page-table pages. + * @flags: Flags to control the page-table walk (ex. a shared walk) * * 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 @@ -354,7 +473,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt); */ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot, - void *mc); + void *mc, enum kvm_pgtable_walk_flags flags); /** * kvm_pgtable_stage2_set_owner() - Unmap and annotate pages in the IPA space to diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h index 9f4ad2a8df59..01129b0d4c68 100644 --- a/arch/arm64/include/asm/kvm_pkvm.h +++ b/arch/arm64/include/asm/kvm_pkvm.h @@ -9,11 +9,49 @@ #include <linux/memblock.h> #include <asm/kvm_pgtable.h> +/* Maximum number of VMs that can co-exist under pKVM. */ +#define KVM_MAX_PVMS 255 + #define HYP_MEMBLOCK_REGIONS 128 +int pkvm_init_host_vm(struct kvm *kvm); +int pkvm_create_hyp_vm(struct kvm *kvm); +void pkvm_destroy_hyp_vm(struct kvm *kvm); + extern struct memblock_region kvm_nvhe_sym(hyp_memory)[]; extern unsigned int kvm_nvhe_sym(hyp_memblock_nr); +static inline unsigned long +hyp_vmemmap_memblock_size(struct memblock_region *reg, size_t vmemmap_entry_size) +{ + unsigned long nr_pages = reg->size >> PAGE_SHIFT; + unsigned long start, end; + + start = (reg->base >> PAGE_SHIFT) * vmemmap_entry_size; + end = start + nr_pages * vmemmap_entry_size; + start = ALIGN_DOWN(start, PAGE_SIZE); + end = ALIGN(end, PAGE_SIZE); + + return end - start; +} + +static inline unsigned long hyp_vmemmap_pages(size_t vmemmap_entry_size) +{ + unsigned long res = 0, i; + + for (i = 0; i < kvm_nvhe_sym(hyp_memblock_nr); i++) { + res += hyp_vmemmap_memblock_size(&kvm_nvhe_sym(hyp_memory)[i], + vmemmap_entry_size); + } + + return res >> PAGE_SHIFT; +} + +static inline unsigned long hyp_vm_table_pages(void) +{ + return PAGE_ALIGN(KVM_MAX_PVMS * sizeof(void *)) >> PAGE_SHIFT; +} + static inline unsigned long __hyp_pgtable_max_pages(unsigned long nr_pages) { unsigned long total = 0, i; diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h index 760c62f8e22f..20dd06d70af5 100644 --- a/arch/arm64/include/asm/mte.h +++ b/arch/arm64/include/asm/mte.h @@ -25,7 +25,7 @@ unsigned long mte_copy_tags_to_user(void __user *to, void *from, unsigned long n); int mte_save_tags(struct page *page); void mte_save_page_tags(const void *page_addr, void *tag_storage); -bool mte_restore_tags(swp_entry_t entry, struct page *page); +void mte_restore_tags(swp_entry_t entry, struct page *page); void mte_restore_page_tags(void *page_addr, const void *tag_storage); void mte_invalidate_tags(int type, pgoff_t offset); void mte_invalidate_tags_area(int type); @@ -36,6 +36,58 @@ void mte_free_tag_storage(char *storage); /* track which pages have valid allocation tags */ #define PG_mte_tagged PG_arch_2 +/* simple lock to avoid multiple threads tagging the same page */ +#define PG_mte_lock PG_arch_3 + +static inline void set_page_mte_tagged(struct page *page) +{ + /* + * Ensure that the tags written prior to this function are visible + * before the page flags update. + */ + smp_wmb(); + set_bit(PG_mte_tagged, &page->flags); +} + +static inline bool page_mte_tagged(struct page *page) +{ + bool ret = test_bit(PG_mte_tagged, &page->flags); + + /* + * If the page is tagged, ensure ordering with a likely subsequent + * read of the tags. + */ + if (ret) + smp_rmb(); + return ret; +} + +/* + * Lock the page for tagging and return 'true' if the page can be tagged, + * 'false' if already tagged. PG_mte_tagged is never cleared and therefore the + * locking only happens once for page initialisation. + * + * The page MTE lock state: + * + * Locked: PG_mte_lock && !PG_mte_tagged + * Unlocked: !PG_mte_lock || PG_mte_tagged + * + * Acquire semantics only if the page is tagged (returning 'false'). + */ +static inline bool try_page_mte_tagging(struct page *page) +{ + if (!test_and_set_bit(PG_mte_lock, &page->flags)) + return true; + + /* + * The tags are either being initialised or may have been initialised + * already. Check if the PG_mte_tagged flag has been set or wait + * otherwise. + */ + smp_cond_load_acquire(&page->flags, VAL & (1UL << PG_mte_tagged)); + + return false; +} void mte_zero_clear_page_tags(void *addr); void mte_sync_tags(pte_t old_pte, pte_t pte); @@ -56,6 +108,17 @@ size_t mte_probe_user_range(const char __user *uaddr, size_t size); /* unused if !CONFIG_ARM64_MTE, silence the compiler */ #define PG_mte_tagged 0 +static inline void set_page_mte_tagged(struct page *page) +{ +} +static inline bool page_mte_tagged(struct page *page) +{ + return false; +} +static inline bool try_page_mte_tagging(struct page *page) +{ + return false; +} static inline void mte_zero_clear_page_tags(void *addr) { } diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b3faf7582a53..6914add66bcf 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1046,8 +1046,8 @@ static inline void arch_swap_invalidate_area(int type) #define __HAVE_ARCH_SWAP_RESTORE static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) { - if (system_supports_mte() && mte_restore_tags(entry, &folio->page)) - set_bit(PG_mte_tagged, &folio->flags); + if (system_supports_mte()) + mte_restore_tags(entry, &folio->page); } #endif /* CONFIG_ARM64_MTE */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 316917b98707..a7a857f1784d 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -43,6 +43,7 @@ #define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 +#define KVM_DIRTY_LOG_PAGE_OFFSET 64 #define KVM_REG_SIZE(id) \ (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 7e76e1fda2a1..a77315b338e6 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2076,8 +2076,10 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) * Clear the tags in the zero page. This needs to be done via the * linear map which has the Tagged attribute. */ - if (!test_and_set_bit(PG_mte_tagged, &ZERO_PAGE(0)->flags)) + if (try_page_mte_tagging(ZERO_PAGE(0))) { mte_clear_page_tags(lm_alias(empty_zero_page)); + set_page_mte_tagged(ZERO_PAGE(0)); + } kasan_init_hw_tags_cpu(); } diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c index 27ef7ad3ffd2..353009d7f307 100644 --- a/arch/arm64/kernel/elfcore.c +++ b/arch/arm64/kernel/elfcore.c @@ -47,7 +47,7 @@ static int mte_dump_tag_range(struct coredump_params *cprm, * Pages mapped in user space as !pte_access_permitted() (e.g. * PROT_EXEC only) may not have the PG_mte_tagged flag set. */ - if (!test_bit(PG_mte_tagged, &page->flags)) { + if (!page_mte_tagged(page)) { put_page(page); dump_skip(cprm, MTE_PAGE_TAG_STORAGE); continue; diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index af5df48ba915..788597a6b6a2 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -271,7 +271,7 @@ static int swsusp_mte_save_tags(void) if (!page) continue; - if (!test_bit(PG_mte_tagged, &page->flags)) + if (!page_mte_tagged(page)) continue; ret = save_tags(page, pfn); diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index f31130ba0233..d0e9bb5c91fc 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -63,12 +63,6 @@ KVM_NVHE_ALIAS(nvhe_hyp_panic_handler); /* Vectors installed by hyp-init on reset HVC. */ KVM_NVHE_ALIAS(__hyp_stub_vectors); -/* Kernel symbol used by icache_is_vpipt(). */ -KVM_NVHE_ALIAS(__icache_flags); - -/* VMID bits set by the KVM VMID allocator */ -KVM_NVHE_ALIAS(kvm_arm_vmid_bits); - /* Static keys which are set if a vGIC trap should be handled in hyp. */ KVM_NVHE_ALIAS(vgic_v2_cpuif_trap); KVM_NVHE_ALIAS(vgic_v3_cpuif_trap); @@ -84,9 +78,6 @@ KVM_NVHE_ALIAS(gic_nonsecure_priorities); KVM_NVHE_ALIAS(__start___kvm_ex_table); KVM_NVHE_ALIAS(__stop___kvm_ex_table); -/* Array containing bases of nVHE per-CPU memory regions. */ -KVM_NVHE_ALIAS(kvm_arm_hyp_percpu_base); - /* PMU available static key */ #ifdef CONFIG_HW_PERF_EVENTS KVM_NVHE_ALIAS(kvm_arm_pmu_available); @@ -103,12 +94,6 @@ KVM_NVHE_ALIAS_HYP(__memcpy, __pi_memcpy); KVM_NVHE_ALIAS_HYP(__memset, __pi_memset); #endif -/* Kernel memory sections */ -KVM_NVHE_ALIAS(__start_rodata); -KVM_NVHE_ALIAS(__end_rodata); -KVM_NVHE_ALIAS(__bss_start); -KVM_NVHE_ALIAS(__bss_stop); - /* Hyp memory sections */ KVM_NVHE_ALIAS(__hyp_idmap_text_start); KVM_NVHE_ALIAS(__hyp_idmap_text_end); diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index 7467217c1eaf..f5bcb0dc6267 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -41,19 +41,17 @@ static void mte_sync_page_tags(struct page *page, pte_t old_pte, if (check_swap && is_swap_pte(old_pte)) { swp_entry_t entry = pte_to_swp_entry(old_pte); - if (!non_swap_entry(entry) && mte_restore_tags(entry, page)) - return; + if (!non_swap_entry(entry)) + mte_restore_tags(entry, page); } if (!pte_is_tagged) return; - /* - * Test PG_mte_tagged again in case it was racing with another - * set_pte_at(). - */ - if (!test_and_set_bit(PG_mte_tagged, &page->flags)) + if (try_page_mte_tagging(page)) { mte_clear_page_tags(page_address(page)); + set_page_mte_tagged(page); + } } void mte_sync_tags(pte_t old_pte, pte_t pte) @@ -69,9 +67,11 @@ void mte_sync_tags(pte_t old_pte, pte_t pte) /* if PG_mte_tagged is set, tags have already been initialised */ for (i = 0; i < nr_pages; i++, page++) { - if (!test_bit(PG_mte_tagged, &page->flags)) + if (!page_mte_tagged(page)) { mte_sync_page_tags(page, old_pte, check_swap, pte_is_tagged); + set_page_mte_tagged(page); + } } /* ensure the tags are visible before the PTE is set */ @@ -96,8 +96,7 @@ int memcmp_pages(struct page *page1, struct page *page2) * pages is tagged, set_pte_at() may zero or change the tags of the * other page via mte_sync_tags(). */ - if (test_bit(PG_mte_tagged, &page1->flags) || - test_bit(PG_mte_tagged, &page2->flags)) + if (page_mte_tagged(page1) || page_mte_tagged(page2)) return addr1 != addr2; return ret; @@ -454,7 +453,7 @@ static int __access_remote_tags(struct mm_struct *mm, unsigned long addr, put_page(page); break; } - WARN_ON_ONCE(!test_bit(PG_mte_tagged, &page->flags)); + WARN_ON_ONCE(!page_mte_tagged(page)); /* limit access to the end of the page */ offset = offset_in_page(addr); diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 815cc118c675..05da3c8f7e88 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -32,6 +32,8 @@ menuconfig KVM select KVM_VFIO select HAVE_KVM_EVENTFD select HAVE_KVM_IRQFD + select HAVE_KVM_DIRTY_RING_ACQ_REL + select NEED_KVM_DIRTY_RING_WITH_BITMAP select HAVE_KVM_MSI select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQ_ROUTING diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 94d33e296e10..9c5573bc4614 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -37,6 +37,7 @@ #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> #include <asm/kvm_mmu.h> +#include <asm/kvm_pkvm.h> #include <asm/kvm_emulate.h> #include <asm/sections.h> @@ -50,7 +51,6 @@ DEFINE_STATIC_KEY_FALSE(kvm_protected_mode_initialized); DECLARE_KVM_HYP_PER_CPU(unsigned long, kvm_hyp_vector); DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); -unsigned long kvm_arm_hyp_percpu_base[NR_CPUS]; DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params); static bool vgic_present; @@ -138,24 +138,24 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { int ret; - ret = kvm_arm_setup_stage2(kvm, type); - if (ret) - return ret; - - ret = kvm_init_stage2_mmu(kvm, &kvm->arch.mmu); + ret = kvm_share_hyp(kvm, kvm + 1); if (ret) return ret; - ret = kvm_share_hyp(kvm, kvm + 1); + ret = pkvm_init_host_vm(kvm); if (ret) - goto out_free_stage2_pgd; + goto err_unshare_kvm; if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL)) { ret = -ENOMEM; - goto out_free_stage2_pgd; + goto err_unshare_kvm; } cpumask_copy(kvm->arch.supported_cpus, cpu_possible_mask); + ret = kvm_init_stage2_mmu(kvm, &kvm->arch.mmu, type); + if (ret) + goto err_free_cpumask; + kvm_vgic_early_init(kvm); /* The maximum number of VCPUs is limited by the host's GIC model */ @@ -164,9 +164,18 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) set_default_spectre(kvm); kvm_arm_init_hypercalls(kvm); - return ret; -out_free_stage2_pgd: - kvm_free_stage2_pgd(&kvm->arch.mmu); + /* + * Initialise the default PMUver before there is a chance to + * create an actual PMU. + */ + kvm->arch.dfr0_pmuver.imp = kvm_arm_pmu_get_pmuver_limit(); + + return 0; + +err_free_cpumask: + free_cpumask_var(kvm->arch.supported_cpus); +err_unshare_kvm: + kvm_unshare_hyp(kvm, kvm + 1); return ret; } @@ -187,6 +196,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_vgic_destroy(kvm); + if (is_protected_kvm_enabled()) + pkvm_destroy_hyp_vm(kvm); + kvm_destroy_vcpus(kvm); kvm_unshare_hyp(kvm, kvm + 1); @@ -569,6 +581,12 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) if (ret) return ret; + if (is_protected_kvm_enabled()) { + ret = pkvm_create_hyp_vm(kvm); + if (ret) + return ret; + } + if (!irqchip_in_kernel(kvm)) { /* * Tell the rest of the code that there are userspace irqchip @@ -746,6 +764,9 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_SUSPEND, vcpu)) return kvm_vcpu_suspend(vcpu); + + if (kvm_dirty_ring_check_request(vcpu)) + return 0; } return 1; @@ -1518,7 +1539,7 @@ static int kvm_init_vector_slots(void) return 0; } -static void cpu_prepare_hyp_mode(int cpu) +static void cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) { struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu); unsigned long tcr; @@ -1534,23 +1555,9 @@ static void cpu_prepare_hyp_mode(int cpu) params->mair_el2 = read_sysreg(mair_el1); - /* - * The ID map may be configured to use an extended virtual address - * range. This is only the case if system RAM is out of range for the - * currently configured page size and VA_BITS, in which case we will - * also need the extended virtual range for the HYP ID map, or we won't - * be able to enable the EL2 MMU. - * - * However, at EL2, there is only one TTBR register, and we can't switch - * between translation tables *and* update TCR_EL2.T0SZ at the same - * time. Bottom line: we need to use the extended range with *both* our - * translation tables. - * - * So use the same T0SZ value we use for the ID map. - */ tcr = (read_sysreg(tcr_el1) & TCR_EL2_MASK) | TCR_EL2_RES1; tcr &= ~TCR_T0SZ_MASK; - tcr |= (idmap_t0sz & GENMASK(TCR_TxSZ_WIDTH - 1, 0)) << TCR_T0SZ_OFFSET; + tcr |= TCR_T0SZ(hyp_va_bits); params->tcr_el2 = tcr; params->pgd_pa = kvm_mmu_get_httbr(); @@ -1844,13 +1851,13 @@ static void teardown_hyp_mode(void) free_hyp_pgds(); for_each_possible_cpu(cpu) { free_page(per_cpu(kvm_arm_hyp_stack_page, cpu)); - free_pages(kvm_arm_hyp_percpu_base[cpu], nvhe_percpu_order()); + free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order()); } } static int do_pkvm_init(u32 hyp_va_bits) { - void *per_cpu_base = kvm_ksym_ref(kvm_arm_hyp_percpu_base); + void *per_cpu_base = kvm_ksym_ref(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)); int ret; preempt_disable(); @@ -1870,11 +1877,8 @@ static int do_pkvm_init(u32 hyp_va_bits) return ret; } -static int kvm_hyp_init_protection(u32 hyp_va_bits) +static void kvm_hyp_init_symbols(void) { - void *addr = phys_to_virt(hyp_mem_base); - int ret; - kvm_nvhe_sym(id_aa64pfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); kvm_nvhe_sym(id_aa64pfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); kvm_nvhe_sym(id_aa64isar0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR0_EL1); @@ -1883,6 +1887,14 @@ static int kvm_hyp_init_protection(u32 hyp_va_bits) kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR2_EL1); + kvm_nvhe_sym(__icache_flags) = __icache_flags; + kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits; +} + +static int kvm_hyp_init_protection(u32 hyp_va_bits) +{ + void *addr = phys_to_virt(hyp_mem_base); + int ret; ret = create_hyp_mappings(addr, addr + hyp_mem_size, PAGE_HYP); if (ret) @@ -1950,7 +1962,7 @@ static int init_hyp_mode(void) page_addr = page_address(page); memcpy(page_addr, CHOOSE_NVHE_SYM(__per_cpu_start), nvhe_percpu_size()); - kvm_arm_hyp_percpu_base[cpu] = (unsigned long)page_addr; + kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu] = (unsigned long)page_addr; } /* @@ -2043,7 +2055,7 @@ static int init_hyp_mode(void) } for_each_possible_cpu(cpu) { - char *percpu_begin = (char *)kvm_arm_hyp_percpu_base[cpu]; + char *percpu_begin = (char *)kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu]; char *percpu_end = percpu_begin + nvhe_percpu_size(); /* Map Hyp percpu pages */ @@ -2054,9 +2066,11 @@ static int init_hyp_mode(void) } /* Prepare the CPU initialization parameters */ - cpu_prepare_hyp_mode(cpu); + cpu_prepare_hyp_mode(cpu, hyp_va_bits); } + kvm_hyp_init_symbols(); + if (is_protected_kvm_enabled()) { init_cpu_logical_map(); @@ -2064,9 +2078,7 @@ static int init_hyp_mode(void) err = -ENODEV; goto out_err; } - } - if (is_protected_kvm_enabled()) { err = kvm_hyp_init_protection(hyp_va_bits); if (err) { kvm_err("Failed to init hyp memory protection\n"); @@ -2130,6 +2142,11 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr) return NULL; } +bool kvm_arch_irqchip_in_kernel(struct kvm *kvm) +{ + return irqchip_in_kernel(kvm); +} + bool kvm_arch_has_irq_bypass(void) { return true; diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 2ff13a3f8479..5626ddb540ce 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -1059,7 +1059,7 @@ long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, maddr = page_address(page); if (!write) { - if (test_bit(PG_mte_tagged, &page->flags)) + if (page_mte_tagged(page)) num_tags = mte_copy_tags_to_user(tags, maddr, MTE_GRANULES_PER_PAGE); else @@ -1068,15 +1068,19 @@ long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, clear_user(tags, MTE_GRANULES_PER_PAGE); kvm_release_pfn_clean(pfn); } else { + /* + * Only locking to serialise with a concurrent + * set_pte_at() in the VMM but still overriding the + * tags, hence ignoring the return value. + */ + try_page_mte_tagging(page); num_tags = mte_copy_tags_from_user(maddr, tags, MTE_GRANULES_PER_PAGE); - /* - * Set the flag after checking the write - * completed fully - */ - if (num_tags == MTE_GRANULES_PER_PAGE) - set_bit(PG_mte_tagged, &page->flags); + /* uaccess failed, don't leave stale tags */ + if (num_tags != MTE_GRANULES_PER_PAGE) + mte_clear_page_tags(page); + set_page_mte_tagged(page); kvm_release_pfn_dirty(pfn); } diff --git a/arch/arm64/kvm/hyp/hyp-constants.c b/arch/arm64/kvm/hyp/hyp-constants.c index b3742a6691e8..b257a3b4bfc5 100644 --- a/arch/arm64/kvm/hyp/hyp-constants.c +++ b/arch/arm64/kvm/hyp/hyp-constants.c @@ -2,9 +2,12 @@ #include <linux/kbuild.h> #include <nvhe/memory.h> +#include <nvhe/pkvm.h> int main(void) { DEFINE(STRUCT_HYP_PAGE_SIZE, sizeof(struct hyp_page)); + DEFINE(PKVM_HYP_VM_SIZE, sizeof(struct pkvm_hyp_vm)); + DEFINE(PKVM_HYP_VCPU_SIZE, sizeof(struct pkvm_hyp_vcpu)); return 0; } diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h index 80e99836eac7..b7bdbe63deed 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h @@ -8,8 +8,10 @@ #define __KVM_NVHE_MEM_PROTECT__ #include <linux/kvm_host.h> #include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> #include <asm/kvm_pgtable.h> #include <asm/virt.h> +#include <nvhe/pkvm.h> #include <nvhe/spinlock.h> /* @@ -43,30 +45,45 @@ static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot) return prot & PKVM_PAGE_STATE_PROT_MASK; } -struct host_kvm { +struct host_mmu { struct kvm_arch arch; struct kvm_pgtable pgt; struct kvm_pgtable_mm_ops mm_ops; hyp_spinlock_t lock; }; -extern struct host_kvm host_kvm; +extern struct host_mmu host_mmu; -extern const u8 pkvm_hyp_id; +/* This corresponds to page-table locking order */ +enum pkvm_component_id { + PKVM_ID_HOST, + PKVM_ID_HYP, +}; + +extern unsigned long hyp_nr_cpus; int __pkvm_prot_finalize(void); int __pkvm_host_share_hyp(u64 pfn); int __pkvm_host_unshare_hyp(u64 pfn); +int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages); +int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages); bool addr_is_memory(phys_addr_t phys); int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot); int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id); int kvm_host_prepare_stage2(void *pgt_pool_base); +int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd); void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt); +int hyp_pin_shared_mem(void *from, void *to); +void hyp_unpin_shared_mem(void *from, void *to); +void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc); +int refill_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages, + struct kvm_hyp_memcache *host_mc); + static __always_inline void __load_host_stage2(void) { if (static_branch_likely(&kvm_protected_mode_initialized)) - __load_stage2(&host_kvm.arch.mmu, &host_kvm.arch); + __load_stage2(&host_mmu.arch.mmu, &host_mmu.arch); else write_sysreg(0, vttbr_el2); } diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h index 592b7edb3edb..ab205c4d6774 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/memory.h +++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h @@ -38,6 +38,10 @@ static inline phys_addr_t hyp_virt_to_phys(void *addr) #define hyp_page_to_virt(page) __hyp_va(hyp_page_to_phys(page)) #define hyp_page_to_pool(page) (((struct hyp_page *)page)->pool) +/* + * Refcounting for 'struct hyp_page'. + * hyp_pool::lock must be held if atomic access to the refcount is required. + */ static inline int hyp_page_count(void *addr) { struct hyp_page *p = hyp_virt_to_page(addr); @@ -45,4 +49,27 @@ static inline int hyp_page_count(void *addr) return p->refcount; } +static inline void hyp_page_ref_inc(struct hyp_page *p) +{ + BUG_ON(p->refcount == USHRT_MAX); + p->refcount++; +} + +static inline void hyp_page_ref_dec(struct hyp_page *p) +{ + BUG_ON(!p->refcount); + p->refcount--; +} + +static inline int hyp_page_ref_dec_and_test(struct hyp_page *p) +{ + hyp_page_ref_dec(p); + return (p->refcount == 0); +} + +static inline void hyp_set_page_refcounted(struct hyp_page *p) +{ + BUG_ON(p->refcount); + p->refcount = 1; +} #endif /* __KVM_HYP_MEMORY_H */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/mm.h b/arch/arm64/kvm/hyp/include/nvhe/mm.h index 42d8eb9bfe72..d5ec972b5c1e 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/mm.h +++ b/arch/arm64/kvm/hyp/include/nvhe/mm.h @@ -13,9 +13,13 @@ extern struct kvm_pgtable pkvm_pgtable; extern hyp_spinlock_t pkvm_pgd_lock; +int hyp_create_pcpu_fixmap(void); +void *hyp_fixmap_map(phys_addr_t phys); +void hyp_fixmap_unmap(void); + int hyp_create_idmap(u32 hyp_va_bits); int hyp_map_vectors(void); -int hyp_back_vmemmap(phys_addr_t phys, unsigned long size, phys_addr_t back); +int hyp_back_vmemmap(phys_addr_t back); int pkvm_cpu_set_vector(enum arm64_hyp_spectre_vector slot); int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot); int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot); @@ -24,16 +28,4 @@ int __pkvm_create_private_mapping(phys_addr_t phys, size_t size, unsigned long *haddr); int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr); -static inline void hyp_vmemmap_range(phys_addr_t phys, unsigned long size, - unsigned long *start, unsigned long *end) -{ - unsigned long nr_pages = size >> PAGE_SHIFT; - struct hyp_page *p = hyp_phys_to_page(phys); - - *start = (unsigned long)p; - *end = *start + nr_pages * sizeof(struct hyp_page); - *start = ALIGN_DOWN(*start, PAGE_SIZE); - *end = ALIGN(*end, PAGE_SIZE); -} - #endif /* __KVM_HYP_MM_H */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h new file mode 100644 index 000000000000..82b3d62538a6 --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Google LLC + * Author: Fuad Tabba <tabba@google.com> + */ + +#ifndef __ARM64_KVM_NVHE_PKVM_H__ +#define __ARM64_KVM_NVHE_PKVM_H__ + +#include <asm/kvm_pkvm.h> + +#include <nvhe/gfp.h> +#include <nvhe/spinlock.h> + +/* + * Holds the relevant data for maintaining the vcpu state completely at hyp. + */ +struct pkvm_hyp_vcpu { + struct kvm_vcpu vcpu; + + /* Backpointer to the host's (untrusted) vCPU instance. */ + struct kvm_vcpu *host_vcpu; +}; + +/* + * Holds the relevant data for running a protected vm. + */ +struct pkvm_hyp_vm { + struct kvm kvm; + + /* Backpointer to the host's (untrusted) KVM instance. */ + struct kvm *host_kvm; + + /* The guest's stage-2 page-table managed by the hypervisor. */ + struct kvm_pgtable pgt; + struct kvm_pgtable_mm_ops mm_ops; + struct hyp_pool pool; + hyp_spinlock_t lock; + + /* + * The number of vcpus initialized and ready to run. + * Modifying this is protected by 'vm_table_lock'. + */ + unsigned int nr_vcpus; + + /* Array of the hyp vCPU structures for this VM. */ + struct pkvm_hyp_vcpu *vcpus[]; +}; + +static inline struct pkvm_hyp_vm * +pkvm_hyp_vcpu_to_hyp_vm(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + return container_of(hyp_vcpu->vcpu.kvm, struct pkvm_hyp_vm, kvm); +} + +void pkvm_hyp_vm_table_init(void *tbl); + +int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva, + unsigned long pgd_hva); +int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu, + unsigned long vcpu_hva); +int __pkvm_teardown_vm(pkvm_handle_t handle); + +struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle, + unsigned int vcpu_idx); +void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu); + +#endif /* __ARM64_KVM_NVHE_PKVM_H__ */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/spinlock.h b/arch/arm64/kvm/hyp/include/nvhe/spinlock.h index 4652fd04bdbe..7c7ea8c55405 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/spinlock.h +++ b/arch/arm64/kvm/hyp/include/nvhe/spinlock.h @@ -28,9 +28,17 @@ typedef union hyp_spinlock { }; } hyp_spinlock_t; +#define __HYP_SPIN_LOCK_INITIALIZER \ + { .__val = 0 } + +#define __HYP_SPIN_LOCK_UNLOCKED \ + ((hyp_spinlock_t) __HYP_SPIN_LOCK_INITIALIZER) + +#define DEFINE_HYP_SPINLOCK(x) hyp_spinlock_t x = __HYP_SPIN_LOCK_UNLOCKED + #define hyp_spin_lock_init(l) \ do { \ - *(l) = (hyp_spinlock_t){ .__val = 0 }; \ + *(l) = __HYP_SPIN_LOCK_UNLOCKED; \ } while (0) static inline void hyp_spin_lock(hyp_spinlock_t *lock) diff --git a/arch/arm64/kvm/hyp/nvhe/cache.S b/arch/arm64/kvm/hyp/nvhe/cache.S index 0c367eb5f4e2..85936c17ae40 100644 --- a/arch/arm64/kvm/hyp/nvhe/cache.S +++ b/arch/arm64/kvm/hyp/nvhe/cache.S @@ -12,3 +12,14 @@ SYM_FUNC_START(__pi_dcache_clean_inval_poc) ret SYM_FUNC_END(__pi_dcache_clean_inval_poc) SYM_FUNC_ALIAS(dcache_clean_inval_poc, __pi_dcache_clean_inval_poc) + +SYM_FUNC_START(__pi_icache_inval_pou) +alternative_if ARM64_HAS_CACHE_DIC + isb + ret +alternative_else_nop_endif + + invalidate_icache_by_line x0, x1, x2, x3 + ret +SYM_FUNC_END(__pi_icache_inval_pou) +SYM_FUNC_ALIAS(icache_inval_pou, __pi_icache_inval_pou) diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 3cea4b6ac23e..728e01d4536b 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -15,17 +15,93 @@ #include <nvhe/mem_protect.h> #include <nvhe/mm.h> +#include <nvhe/pkvm.h> #include <nvhe/trap_handler.h> DEFINE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params); void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt); +static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + hyp_vcpu->vcpu.arch.ctxt = host_vcpu->arch.ctxt; + + hyp_vcpu->vcpu.arch.sve_state = kern_hyp_va(host_vcpu->arch.sve_state); + hyp_vcpu->vcpu.arch.sve_max_vl = host_vcpu->arch.sve_max_vl; + + hyp_vcpu->vcpu.arch.hw_mmu = host_vcpu->arch.hw_mmu; + + hyp_vcpu->vcpu.arch.hcr_el2 = host_vcpu->arch.hcr_el2; + hyp_vcpu->vcpu.arch.mdcr_el2 = host_vcpu->arch.mdcr_el2; + hyp_vcpu->vcpu.arch.cptr_el2 = host_vcpu->arch.cptr_el2; + + hyp_vcpu->vcpu.arch.iflags = host_vcpu->arch.iflags; + hyp_vcpu->vcpu.arch.fp_state = host_vcpu->arch.fp_state; + + hyp_vcpu->vcpu.arch.debug_ptr = kern_hyp_va(host_vcpu->arch.debug_ptr); + hyp_vcpu->vcpu.arch.host_fpsimd_state = host_vcpu->arch.host_fpsimd_state; + + hyp_vcpu->vcpu.arch.vsesr_el2 = host_vcpu->arch.vsesr_el2; + + hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3 = host_vcpu->arch.vgic_cpu.vgic_v3; +} + +static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + struct vgic_v3_cpu_if *hyp_cpu_if = &hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3; + struct vgic_v3_cpu_if *host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3; + unsigned int i; + + host_vcpu->arch.ctxt = hyp_vcpu->vcpu.arch.ctxt; + + host_vcpu->arch.hcr_el2 = hyp_vcpu->vcpu.arch.hcr_el2; + host_vcpu->arch.cptr_el2 = hyp_vcpu->vcpu.arch.cptr_el2; + + host_vcpu->arch.fault = hyp_vcpu->vcpu.arch.fault; + + host_vcpu->arch.iflags = hyp_vcpu->vcpu.arch.iflags; + host_vcpu->arch.fp_state = hyp_vcpu->vcpu.arch.fp_state; + + host_cpu_if->vgic_hcr = hyp_cpu_if->vgic_hcr; + for (i = 0; i < hyp_cpu_if->used_lrs; ++i) + host_cpu_if->vgic_lr[i] = hyp_cpu_if->vgic_lr[i]; +} + static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) { - DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1); + DECLARE_REG(struct kvm_vcpu *, host_vcpu, host_ctxt, 1); + int ret; - cpu_reg(host_ctxt, 1) = __kvm_vcpu_run(kern_hyp_va(vcpu)); + host_vcpu = kern_hyp_va(host_vcpu); + + if (unlikely(is_protected_kvm_enabled())) { + struct pkvm_hyp_vcpu *hyp_vcpu; + struct kvm *host_kvm; + + host_kvm = kern_hyp_va(host_vcpu->kvm); + hyp_vcpu = pkvm_load_hyp_vcpu(host_kvm->arch.pkvm.handle, + host_vcpu->vcpu_idx); + if (!hyp_vcpu) { + ret = -EINVAL; + goto out; + } + + flush_hyp_vcpu(hyp_vcpu); + + ret = __kvm_vcpu_run(&hyp_vcpu->vcpu); + + sync_hyp_vcpu(hyp_vcpu); + pkvm_put_hyp_vcpu(hyp_vcpu); + } else { + /* The host is fully trusted, run its vCPU directly. */ + ret = __kvm_vcpu_run(host_vcpu); + } + +out: + cpu_reg(host_ctxt, 1) = ret; } static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt) @@ -191,6 +267,33 @@ static void handle___pkvm_vcpu_init_traps(struct kvm_cpu_context *host_ctxt) __pkvm_vcpu_init_traps(kern_hyp_va(vcpu)); } +static void handle___pkvm_init_vm(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm *, host_kvm, host_ctxt, 1); + DECLARE_REG(unsigned long, vm_hva, host_ctxt, 2); + DECLARE_REG(unsigned long, pgd_hva, host_ctxt, 3); + + host_kvm = kern_hyp_va(host_kvm); + cpu_reg(host_ctxt, 1) = __pkvm_init_vm(host_kvm, vm_hva, pgd_hva); +} + +static void handle___pkvm_init_vcpu(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + DECLARE_REG(struct kvm_vcpu *, host_vcpu, host_ctxt, 2); + DECLARE_REG(unsigned long, vcpu_hva, host_ctxt, 3); + + host_vcpu = kern_hyp_va(host_vcpu); + cpu_reg(host_ctxt, 1) = __pkvm_init_vcpu(handle, host_vcpu, vcpu_hva); +} + +static void handle___pkvm_teardown_vm(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + + cpu_reg(host_ctxt, 1) = __pkvm_teardown_vm(handle); +} + typedef void (*hcall_t)(struct kvm_cpu_context *); #define HANDLE_FUNC(x) [__KVM_HOST_SMCCC_FUNC_##x] = (hcall_t)handle_##x @@ -220,6 +323,9 @@ static const hcall_t host_hcall[] = { HANDLE_FUNC(__vgic_v3_save_aprs), HANDLE_FUNC(__vgic_v3_restore_aprs), HANDLE_FUNC(__pkvm_vcpu_init_traps), + HANDLE_FUNC(__pkvm_init_vm), + HANDLE_FUNC(__pkvm_init_vcpu), + HANDLE_FUNC(__pkvm_teardown_vm), }; static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c index 9f54833af400..04d194583f1e 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c @@ -23,6 +23,8 @@ u64 cpu_logical_map(unsigned int cpu) return hyp_cpu_logical_map[cpu]; } +unsigned long __ro_after_init kvm_arm_hyp_percpu_base[NR_CPUS]; + unsigned long __hyp_per_cpu_offset(unsigned int cpu) { unsigned long *cpu_base_array; diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 07f9dc9848ef..552653fa18be 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -21,21 +21,33 @@ #define KVM_HOST_S2_FLAGS (KVM_PGTABLE_S2_NOFWB | KVM_PGTABLE_S2_IDMAP) -extern unsigned long hyp_nr_cpus; -struct host_kvm host_kvm; +struct host_mmu host_mmu; static struct hyp_pool host_s2_pool; -const u8 pkvm_hyp_id = 1; +static DEFINE_PER_CPU(struct pkvm_hyp_vm *, __current_vm); +#define current_vm (*this_cpu_ptr(&__current_vm)) + +static void guest_lock_component(struct pkvm_hyp_vm *vm) +{ + hyp_spin_lock(&vm->lock); + current_vm = vm; +} + +static void guest_unlock_component(struct pkvm_hyp_vm *vm) +{ + current_vm = NULL; + hyp_spin_unlock(&vm->lock); +} static void host_lock_component(void) { - hyp_spin_lock(&host_kvm.lock); + hyp_spin_lock(&host_mmu.lock); } static void host_unlock_component(void) { - hyp_spin_unlock(&host_kvm.lock); + hyp_spin_unlock(&host_mmu.lock); } static void hyp_lock_component(void) @@ -79,6 +91,11 @@ static void host_s2_put_page(void *addr) hyp_put_page(&host_s2_pool, addr); } +static void host_s2_free_removed_table(void *addr, u32 level) +{ + kvm_pgtable_stage2_free_removed(&host_mmu.mm_ops, addr, level); +} + static int prepare_s2_pool(void *pgt_pool_base) { unsigned long nr_pages, pfn; @@ -90,9 +107,10 @@ static int prepare_s2_pool(void *pgt_pool_base) if (ret) return ret; - host_kvm.mm_ops = (struct kvm_pgtable_mm_ops) { + host_mmu.mm_ops = (struct kvm_pgtable_mm_ops) { .zalloc_pages_exact = host_s2_zalloc_pages_exact, .zalloc_page = host_s2_zalloc_page, + .free_removed_table = host_s2_free_removed_table, .phys_to_virt = hyp_phys_to_virt, .virt_to_phys = hyp_virt_to_phys, .page_count = hyp_page_count, @@ -111,7 +129,7 @@ static void prepare_host_vtcr(void) parange = kvm_get_parange(id_aa64mmfr0_el1_sys_val); phys_shift = id_aa64mmfr0_parange_to_phys_shift(parange); - host_kvm.arch.vtcr = kvm_get_vtcr(id_aa64mmfr0_el1_sys_val, + host_mmu.arch.vtcr = kvm_get_vtcr(id_aa64mmfr0_el1_sys_val, id_aa64mmfr1_el1_sys_val, phys_shift); } @@ -119,45 +137,170 @@ static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot pr int kvm_host_prepare_stage2(void *pgt_pool_base) { - struct kvm_s2_mmu *mmu = &host_kvm.arch.mmu; + struct kvm_s2_mmu *mmu = &host_mmu.arch.mmu; int ret; prepare_host_vtcr(); - hyp_spin_lock_init(&host_kvm.lock); - mmu->arch = &host_kvm.arch; + hyp_spin_lock_init(&host_mmu.lock); + mmu->arch = &host_mmu.arch; ret = prepare_s2_pool(pgt_pool_base); if (ret) return ret; - ret = __kvm_pgtable_stage2_init(&host_kvm.pgt, mmu, - &host_kvm.mm_ops, KVM_HOST_S2_FLAGS, + ret = __kvm_pgtable_stage2_init(&host_mmu.pgt, mmu, + &host_mmu.mm_ops, KVM_HOST_S2_FLAGS, host_stage2_force_pte_cb); if (ret) return ret; - mmu->pgd_phys = __hyp_pa(host_kvm.pgt.pgd); - mmu->pgt = &host_kvm.pgt; + mmu->pgd_phys = __hyp_pa(host_mmu.pgt.pgd); + mmu->pgt = &host_mmu.pgt; atomic64_set(&mmu->vmid.id, 0); return 0; } +static bool guest_stage2_force_pte_cb(u64 addr, u64 end, + enum kvm_pgtable_prot prot) +{ + return true; +} + +static void *guest_s2_zalloc_pages_exact(size_t size) +{ + void *addr = hyp_alloc_pages(¤t_vm->pool, get_order(size)); + + WARN_ON(size != (PAGE_SIZE << get_order(size))); + hyp_split_page(hyp_virt_to_page(addr)); + + return addr; +} + +static void guest_s2_free_pages_exact(void *addr, unsigned long size) +{ + u8 order = get_order(size); + unsigned int i; + + for (i = 0; i < (1 << order); i++) + hyp_put_page(¤t_vm->pool, addr + (i * PAGE_SIZE)); +} + +static void *guest_s2_zalloc_page(void *mc) +{ + struct hyp_page *p; + void *addr; + + addr = hyp_alloc_pages(¤t_vm->pool, 0); + if (addr) + return addr; + + addr = pop_hyp_memcache(mc, hyp_phys_to_virt); + if (!addr) + return addr; + + memset(addr, 0, PAGE_SIZE); + p = hyp_virt_to_page(addr); + memset(p, 0, sizeof(*p)); + p->refcount = 1; + + return addr; +} + +static void guest_s2_get_page(void *addr) +{ + hyp_get_page(¤t_vm->pool, addr); +} + +static void guest_s2_put_page(void *addr) +{ + hyp_put_page(¤t_vm->pool, addr); +} + +static void clean_dcache_guest_page(void *va, size_t size) +{ + __clean_dcache_guest_page(hyp_fixmap_map(__hyp_pa(va)), size); + hyp_fixmap_unmap(); +} + +static void invalidate_icache_guest_page(void *va, size_t size) +{ + __invalidate_icache_guest_page(hyp_fixmap_map(__hyp_pa(va)), size); + hyp_fixmap_unmap(); +} + +int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd) +{ + struct kvm_s2_mmu *mmu = &vm->kvm.arch.mmu; + unsigned long nr_pages; + int ret; + + nr_pages = kvm_pgtable_stage2_pgd_size(vm->kvm.arch.vtcr) >> PAGE_SHIFT; + ret = hyp_pool_init(&vm->pool, hyp_virt_to_pfn(pgd), nr_pages, 0); + if (ret) + return ret; + + hyp_spin_lock_init(&vm->lock); + vm->mm_ops = (struct kvm_pgtable_mm_ops) { + .zalloc_pages_exact = guest_s2_zalloc_pages_exact, + .free_pages_exact = guest_s2_free_pages_exact, + .zalloc_page = guest_s2_zalloc_page, + .phys_to_virt = hyp_phys_to_virt, + .virt_to_phys = hyp_virt_to_phys, + .page_count = hyp_page_count, + .get_page = guest_s2_get_page, + .put_page = guest_s2_put_page, + .dcache_clean_inval_poc = clean_dcache_guest_page, + .icache_inval_pou = invalidate_icache_guest_page, + }; + + guest_lock_component(vm); + ret = __kvm_pgtable_stage2_init(mmu->pgt, mmu, &vm->mm_ops, 0, + guest_stage2_force_pte_cb); + guest_unlock_component(vm); + if (ret) + return ret; + + vm->kvm.arch.mmu.pgd_phys = __hyp_pa(vm->pgt.pgd); + + return 0; +} + +void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc) +{ + void *addr; + + /* Dump all pgtable pages in the hyp_pool */ + guest_lock_component(vm); + kvm_pgtable_stage2_destroy(&vm->pgt); + vm->kvm.arch.mmu.pgd_phys = 0ULL; + guest_unlock_component(vm); + + /* Drain the hyp_pool into the memcache */ + addr = hyp_alloc_pages(&vm->pool, 0); + while (addr) { + memset(hyp_virt_to_page(addr), 0, sizeof(struct hyp_page)); + push_hyp_memcache(mc, addr, hyp_virt_to_phys); + WARN_ON(__pkvm_hyp_donate_host(hyp_virt_to_pfn(addr), 1)); + addr = hyp_alloc_pages(&vm->pool, 0); + } +} + int __pkvm_prot_finalize(void) { - struct kvm_s2_mmu *mmu = &host_kvm.arch.mmu; + struct kvm_s2_mmu *mmu = &host_mmu.arch.mmu; struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params); if (params->hcr_el2 & HCR_VM) return -EPERM; params->vttbr = kvm_get_vttbr(mmu); - params->vtcr = host_kvm.arch.vtcr; + params->vtcr = host_mmu.arch.vtcr; params->hcr_el2 |= HCR_VM; kvm_flush_dcache_to_poc(params, sizeof(*params)); write_sysreg(params->hcr_el2, hcr_el2); - __load_stage2(&host_kvm.arch.mmu, &host_kvm.arch); + __load_stage2(&host_mmu.arch.mmu, &host_mmu.arch); /* * Make sure to have an ISB before the TLB maintenance below but only @@ -175,7 +318,7 @@ int __pkvm_prot_finalize(void) static int host_stage2_unmap_dev_all(void) { - struct kvm_pgtable *pgt = &host_kvm.pgt; + struct kvm_pgtable *pgt = &host_mmu.pgt; struct memblock_region *reg; u64 addr = 0; int i, ret; @@ -195,7 +338,7 @@ struct kvm_mem_range { u64 end; }; -static bool find_mem_range(phys_addr_t addr, struct kvm_mem_range *range) +static struct memblock_region *find_mem_range(phys_addr_t addr, struct kvm_mem_range *range) { int cur, left = 0, right = hyp_memblock_nr; struct memblock_region *reg; @@ -218,18 +361,28 @@ static bool find_mem_range(phys_addr_t addr, struct kvm_mem_range *range) } else { range->start = reg->base; range->end = end; - return true; + return reg; } } - return false; + return NULL; } bool addr_is_memory(phys_addr_t phys) { struct kvm_mem_range range; - return find_mem_range(phys, &range); + return !!find_mem_range(phys, &range); +} + +static bool addr_is_allowed_memory(phys_addr_t phys) +{ + struct memblock_region *reg; + struct kvm_mem_range range; + + reg = find_mem_range(phys, &range); + + return reg && !(reg->flags & MEMBLOCK_NOMAP); } static bool is_in_mem_range(u64 addr, struct kvm_mem_range *range) @@ -250,8 +403,8 @@ static bool range_is_memory(u64 start, u64 end) static inline int __host_stage2_idmap(u64 start, u64 end, enum kvm_pgtable_prot prot) { - return kvm_pgtable_stage2_map(&host_kvm.pgt, start, end - start, start, - prot, &host_s2_pool); + return kvm_pgtable_stage2_map(&host_mmu.pgt, start, end - start, start, + prot, &host_s2_pool, 0); } /* @@ -263,7 +416,7 @@ static inline int __host_stage2_idmap(u64 start, u64 end, #define host_stage2_try(fn, ...) \ ({ \ int __ret; \ - hyp_assert_lock_held(&host_kvm.lock); \ + hyp_assert_lock_held(&host_mmu.lock); \ __ret = fn(__VA_ARGS__); \ if (__ret == -ENOMEM) { \ __ret = host_stage2_unmap_dev_all(); \ @@ -286,8 +439,8 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range) u32 level; int ret; - hyp_assert_lock_held(&host_kvm.lock); - ret = kvm_pgtable_get_leaf(&host_kvm.pgt, addr, &pte, &level); + hyp_assert_lock_held(&host_mmu.lock); + ret = kvm_pgtable_get_leaf(&host_mmu.pgt, addr, &pte, &level); if (ret) return ret; @@ -319,7 +472,7 @@ int host_stage2_idmap_locked(phys_addr_t addr, u64 size, int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id) { - return host_stage2_try(kvm_pgtable_stage2_set_owner, &host_kvm.pgt, + return host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt, addr, size, &host_s2_pool, owner_id); } @@ -348,7 +501,7 @@ static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot pr static int host_stage2_idmap(u64 addr) { struct kvm_mem_range range; - bool is_memory = find_mem_range(addr, &range); + bool is_memory = !!find_mem_range(addr, &range); enum kvm_pgtable_prot prot; int ret; @@ -380,12 +533,6 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt) BUG_ON(ret && ret != -EAGAIN); } -/* This corresponds to locking order */ -enum pkvm_component_id { - PKVM_ID_HOST, - PKVM_ID_HYP, -}; - struct pkvm_mem_transition { u64 nr_pages; @@ -399,6 +546,9 @@ struct pkvm_mem_transition { /* Address in the completer's address space */ u64 completer_addr; } host; + struct { + u64 completer_addr; + } hyp; }; } initiator; @@ -412,23 +562,24 @@ struct pkvm_mem_share { const enum kvm_pgtable_prot completer_prot; }; +struct pkvm_mem_donation { + const struct pkvm_mem_transition tx; +}; + struct check_walk_data { enum pkvm_page_state desired; enum pkvm_page_state (*get_page_state)(kvm_pte_t pte); }; -static int __check_page_state_visitor(u64 addr, u64 end, u32 level, - kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag, - void * const arg) +static int __check_page_state_visitor(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) { - struct check_walk_data *d = arg; - kvm_pte_t pte = *ptep; + struct check_walk_data *d = ctx->arg; - if (kvm_pte_valid(pte) && !addr_is_memory(kvm_pte_to_phys(pte))) + if (kvm_pte_valid(ctx->old) && !addr_is_allowed_memory(kvm_pte_to_phys(ctx->old))) return -EINVAL; - return d->get_page_state(pte) == d->desired ? 0 : -EPERM; + return d->get_page_state(ctx->old) == d->desired ? 0 : -EPERM; } static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size, @@ -459,8 +610,8 @@ static int __host_check_page_state_range(u64 addr, u64 size, .get_page_state = host_get_page_state, }; - hyp_assert_lock_held(&host_kvm.lock); - return check_page_state_range(&host_kvm.pgt, addr, size, &d); + hyp_assert_lock_held(&host_mmu.lock); + return check_page_state_range(&host_mmu.pgt, addr, size, &d); } static int __host_set_page_state_range(u64 addr, u64 size, @@ -511,6 +662,46 @@ static int host_initiate_unshare(u64 *completer_addr, return __host_set_page_state_range(addr, size, PKVM_PAGE_OWNED); } +static int host_initiate_donation(u64 *completer_addr, + const struct pkvm_mem_transition *tx) +{ + u8 owner_id = tx->completer.id; + u64 size = tx->nr_pages * PAGE_SIZE; + + *completer_addr = tx->initiator.host.completer_addr; + return host_stage2_set_owner_locked(tx->initiator.addr, size, owner_id); +} + +static bool __host_ack_skip_pgtable_check(const struct pkvm_mem_transition *tx) +{ + return !(IS_ENABLED(CONFIG_NVHE_EL2_DEBUG) || + tx->initiator.id != PKVM_ID_HYP); +} + +static int __host_ack_transition(u64 addr, const struct pkvm_mem_transition *tx, + enum pkvm_page_state state) +{ + u64 size = tx->nr_pages * PAGE_SIZE; + + if (__host_ack_skip_pgtable_check(tx)) + return 0; + + return __host_check_page_state_range(addr, size, state); +} + +static int host_ack_donation(u64 addr, const struct pkvm_mem_transition *tx) +{ + return __host_ack_transition(addr, tx, PKVM_NOPAGE); +} + +static int host_complete_donation(u64 addr, const struct pkvm_mem_transition *tx) +{ + u64 size = tx->nr_pages * PAGE_SIZE; + u8 host_id = tx->completer.id; + + return host_stage2_set_owner_locked(addr, size, host_id); +} + static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte) { if (!kvm_pte_valid(pte)) @@ -531,6 +722,27 @@ static int __hyp_check_page_state_range(u64 addr, u64 size, return check_page_state_range(&pkvm_pgtable, addr, size, &d); } +static int hyp_request_donation(u64 *completer_addr, + const struct pkvm_mem_transition *tx) +{ + u64 size = tx->nr_pages * PAGE_SIZE; + u64 addr = tx->initiator.addr; + + *completer_addr = tx->initiator.hyp.completer_addr; + return __hyp_check_page_state_range(addr, size, PKVM_PAGE_OWNED); +} + +static int hyp_initiate_donation(u64 *completer_addr, + const struct pkvm_mem_transition *tx) +{ + u64 size = tx->nr_pages * PAGE_SIZE; + int ret; + + *completer_addr = tx->initiator.hyp.completer_addr; + ret = kvm_pgtable_hyp_unmap(&pkvm_pgtable, tx->initiator.addr, size); + return (ret != size) ? -EFAULT : 0; +} + static bool __hyp_ack_skip_pgtable_check(const struct pkvm_mem_transition *tx) { return !(IS_ENABLED(CONFIG_NVHE_EL2_DEBUG) || @@ -555,6 +767,9 @@ static int hyp_ack_unshare(u64 addr, const struct pkvm_mem_transition *tx) { u64 size = tx->nr_pages * PAGE_SIZE; + if (tx->initiator.id == PKVM_ID_HOST && hyp_page_count((void *)addr)) + return -EBUSY; + if (__hyp_ack_skip_pgtable_check(tx)) return 0; @@ -562,6 +777,16 @@ static int hyp_ack_unshare(u64 addr, const struct pkvm_mem_transition *tx) PKVM_PAGE_SHARED_BORROWED); } +static int hyp_ack_donation(u64 addr, const struct pkvm_mem_transition *tx) +{ + u64 size = tx->nr_pages * PAGE_SIZE; + + if (__hyp_ack_skip_pgtable_check(tx)) + return 0; + + return __hyp_check_page_state_range(addr, size, PKVM_NOPAGE); +} + static int hyp_complete_share(u64 addr, const struct pkvm_mem_transition *tx, enum kvm_pgtable_prot perms) { @@ -580,6 +805,15 @@ static int hyp_complete_unshare(u64 addr, const struct pkvm_mem_transition *tx) return (ret != size) ? -EFAULT : 0; } +static int hyp_complete_donation(u64 addr, + const struct pkvm_mem_transition *tx) +{ + void *start = (void *)addr, *end = start + (tx->nr_pages * PAGE_SIZE); + enum kvm_pgtable_prot prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_OWNED); + + return pkvm_create_mappings_locked(start, end, prot); +} + static int check_share(struct pkvm_mem_share *share) { const struct pkvm_mem_transition *tx = &share->tx; @@ -732,6 +966,94 @@ static int do_unshare(struct pkvm_mem_share *share) return WARN_ON(__do_unshare(share)); } +static int check_donation(struct pkvm_mem_donation *donation) +{ + const struct pkvm_mem_transition *tx = &donation->tx; + u64 completer_addr; + int ret; + + switch (tx->initiator.id) { + case PKVM_ID_HOST: + ret = host_request_owned_transition(&completer_addr, tx); + break; + case PKVM_ID_HYP: + ret = hyp_request_donation(&completer_addr, tx); + break; + default: + ret = -EINVAL; + } + + if (ret) + return ret; + + switch (tx->completer.id) { + case PKVM_ID_HOST: + ret = host_ack_donation(completer_addr, tx); + break; + case PKVM_ID_HYP: + ret = hyp_ack_donation(completer_addr, tx); + break; + default: + ret = -EINVAL; + } + + return ret; +} + +static int __do_donate(struct pkvm_mem_donation *donation) +{ + const struct pkvm_mem_transition *tx = &donation->tx; + u64 completer_addr; + int ret; + + switch (tx->initiator.id) { + case PKVM_ID_HOST: + ret = host_initiate_donation(&completer_addr, tx); + break; + case PKVM_ID_HYP: + ret = hyp_initiate_donation(&completer_addr, tx); + break; + default: + ret = -EINVAL; + } + + if (ret) + return ret; + + switch (tx->completer.id) { + case PKVM_ID_HOST: + ret = host_complete_donation(completer_addr, tx); + break; + case PKVM_ID_HYP: + ret = hyp_complete_donation(completer_addr, tx); + break; + default: + ret = -EINVAL; + } + + return ret; +} + +/* + * do_donate(): + * + * The page owner transfers ownership to another component, losing access + * as a consequence. + * + * Initiator: OWNED => NOPAGE + * Completer: NOPAGE => OWNED + */ +static int do_donate(struct pkvm_mem_donation *donation) +{ + int ret; + + ret = check_donation(donation); + if (ret) + return ret; + + return WARN_ON(__do_donate(donation)); +} + int __pkvm_host_share_hyp(u64 pfn) { int ret; @@ -797,3 +1119,112 @@ int __pkvm_host_unshare_hyp(u64 pfn) return ret; } + +int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages) +{ + int ret; + u64 host_addr = hyp_pfn_to_phys(pfn); + u64 hyp_addr = (u64)__hyp_va(host_addr); + struct pkvm_mem_donation donation = { + .tx = { + .nr_pages = nr_pages, + .initiator = { + .id = PKVM_ID_HOST, + .addr = host_addr, + .host = { + .completer_addr = hyp_addr, + }, + }, + .completer = { + .id = PKVM_ID_HYP, + }, + }, + }; + + host_lock_component(); + hyp_lock_component(); + + ret = do_donate(&donation); + + hyp_unlock_component(); + host_unlock_component(); + + return ret; +} + +int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages) +{ + int ret; + u64 host_addr = hyp_pfn_to_phys(pfn); + u64 hyp_addr = (u64)__hyp_va(host_addr); + struct pkvm_mem_donation donation = { + .tx = { + .nr_pages = nr_pages, + .initiator = { + .id = PKVM_ID_HYP, + .addr = hyp_addr, + .hyp = { + .completer_addr = host_addr, + }, + }, + .completer = { + .id = PKVM_ID_HOST, + }, + }, + }; + + host_lock_component(); + hyp_lock_component(); + + ret = do_donate(&donation); + + hyp_unlock_component(); + host_unlock_component(); + + return ret; +} + +int hyp_pin_shared_mem(void *from, void *to) +{ + u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE); + u64 end = PAGE_ALIGN((u64)to); + u64 size = end - start; + int ret; + + host_lock_component(); + hyp_lock_component(); + + ret = __host_check_page_state_range(__hyp_pa(start), size, + PKVM_PAGE_SHARED_OWNED); + if (ret) + goto unlock; + + ret = __hyp_check_page_state_range(start, size, + PKVM_PAGE_SHARED_BORROWED); + if (ret) + goto unlock; + + for (cur = start; cur < end; cur += PAGE_SIZE) + hyp_page_ref_inc(hyp_virt_to_page(cur)); + +unlock: + hyp_unlock_component(); + host_unlock_component(); + + return ret; +} + +void hyp_unpin_shared_mem(void *from, void *to) +{ + u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE); + u64 end = PAGE_ALIGN((u64)to); + + host_lock_component(); + hyp_lock_component(); + + for (cur = start; cur < end; cur += PAGE_SIZE) + hyp_page_ref_dec(hyp_virt_to_page(cur)); + + hyp_unlock_component(); + host_unlock_component(); +} diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c index 96193cb31a39..318298eb3d6b 100644 --- a/arch/arm64/kvm/hyp/nvhe/mm.c +++ b/arch/arm64/kvm/hyp/nvhe/mm.c @@ -14,6 +14,7 @@ #include <nvhe/early_alloc.h> #include <nvhe/gfp.h> #include <nvhe/memory.h> +#include <nvhe/mem_protect.h> #include <nvhe/mm.h> #include <nvhe/spinlock.h> @@ -25,6 +26,12 @@ unsigned int hyp_memblock_nr; static u64 __io_map_base; +struct hyp_fixmap_slot { + u64 addr; + kvm_pte_t *ptep; +}; +static DEFINE_PER_CPU(struct hyp_fixmap_slot, fixmap_slots); + static int __pkvm_create_mappings(unsigned long start, unsigned long size, unsigned long phys, enum kvm_pgtable_prot prot) { @@ -129,13 +136,36 @@ int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot) return ret; } -int hyp_back_vmemmap(phys_addr_t phys, unsigned long size, phys_addr_t back) +int hyp_back_vmemmap(phys_addr_t back) { - unsigned long start, end; + unsigned long i, start, size, end = 0; + int ret; - hyp_vmemmap_range(phys, size, &start, &end); + for (i = 0; i < hyp_memblock_nr; i++) { + start = hyp_memory[i].base; + start = ALIGN_DOWN((u64)hyp_phys_to_page(start), PAGE_SIZE); + /* + * The begining of the hyp_vmemmap region for the current + * memblock may already be backed by the page backing the end + * the previous region, so avoid mapping it twice. + */ + start = max(start, end); + + end = hyp_memory[i].base + hyp_memory[i].size; + end = PAGE_ALIGN((u64)hyp_phys_to_page(end)); + if (start >= end) + continue; + + size = end - start; + ret = __pkvm_create_mappings(start, size, back, PAGE_HYP); + if (ret) + return ret; + + memset(hyp_phys_to_virt(back), 0, size); + back += size; + } - return __pkvm_create_mappings(start, end - start, back, PAGE_HYP); + return 0; } static void *__hyp_bp_vect_base; @@ -189,6 +219,102 @@ int hyp_map_vectors(void) return 0; } +void *hyp_fixmap_map(phys_addr_t phys) +{ + struct hyp_fixmap_slot *slot = this_cpu_ptr(&fixmap_slots); + kvm_pte_t pte, *ptep = slot->ptep; + + pte = *ptep; + pte &= ~kvm_phys_to_pte(KVM_PHYS_INVALID); + pte |= kvm_phys_to_pte(phys) | KVM_PTE_VALID; + WRITE_ONCE(*ptep, pte); + dsb(ishst); + + return (void *)slot->addr; +} + +static void fixmap_clear_slot(struct hyp_fixmap_slot *slot) +{ + kvm_pte_t *ptep = slot->ptep; + u64 addr = slot->addr; + + WRITE_ONCE(*ptep, *ptep & ~KVM_PTE_VALID); + + /* + * Irritatingly, the architecture requires that we use inner-shareable + * broadcast TLB invalidation here in case another CPU speculates + * through our fixmap and decides to create an "amalagamation of the + * values held in the TLB" due to the apparent lack of a + * break-before-make sequence. + * + * https://lore.kernel.org/kvm/20221017115209.2099-1-will@kernel.org/T/#mf10dfbaf1eaef9274c581b81c53758918c1d0f03 + */ + dsb(ishst); + __tlbi_level(vale2is, __TLBI_VADDR(addr, 0), (KVM_PGTABLE_MAX_LEVELS - 1)); + dsb(ish); + isb(); +} + +void hyp_fixmap_unmap(void) +{ + fixmap_clear_slot(this_cpu_ptr(&fixmap_slots)); +} + +static int __create_fixmap_slot_cb(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + struct hyp_fixmap_slot *slot = per_cpu_ptr(&fixmap_slots, (u64)ctx->arg); + + if (!kvm_pte_valid(ctx->old) || ctx->level != KVM_PGTABLE_MAX_LEVELS - 1) + return -EINVAL; + + slot->addr = ctx->addr; + slot->ptep = ctx->ptep; + + /* + * Clear the PTE, but keep the page-table page refcount elevated to + * prevent it from ever being freed. This lets us manipulate the PTEs + * by hand safely without ever needing to allocate memory. + */ + fixmap_clear_slot(slot); + + return 0; +} + +static int create_fixmap_slot(u64 addr, u64 cpu) +{ + struct kvm_pgtable_walker walker = { + .cb = __create_fixmap_slot_cb, + .flags = KVM_PGTABLE_WALK_LEAF, + .arg = (void *)cpu, + }; + + return kvm_pgtable_walk(&pkvm_pgtable, addr, PAGE_SIZE, &walker); +} + +int hyp_create_pcpu_fixmap(void) +{ + unsigned long addr, i; + int ret; + + for (i = 0; i < hyp_nr_cpus; i++) { + ret = pkvm_alloc_private_va_range(PAGE_SIZE, &addr); + if (ret) + return ret; + + ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr, PAGE_SIZE, + __hyp_pa(__hyp_bss_start), PAGE_HYP); + if (ret) + return ret; + + ret = create_fixmap_slot(addr, i); + if (ret) + return ret; + } + + return 0; +} + int hyp_create_idmap(u32 hyp_va_bits) { unsigned long start, end; @@ -213,3 +339,36 @@ int hyp_create_idmap(u32 hyp_va_bits) return __pkvm_create_mappings(start, end - start, start, PAGE_HYP_EXEC); } + +static void *admit_host_page(void *arg) +{ + struct kvm_hyp_memcache *host_mc = arg; + + if (!host_mc->nr_pages) + return NULL; + + /* + * The host still owns the pages in its memcache, so we need to go + * through a full host-to-hyp donation cycle to change it. Fortunately, + * __pkvm_host_donate_hyp() takes care of races for us, so if it + * succeeds we're good to go. + */ + if (__pkvm_host_donate_hyp(hyp_phys_to_pfn(host_mc->head), 1)) + return NULL; + + return pop_hyp_memcache(host_mc, hyp_phys_to_virt); +} + +/* Refill our local memcache by poping pages from the one provided by the host. */ +int refill_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages, + struct kvm_hyp_memcache *host_mc) +{ + struct kvm_hyp_memcache tmp = *host_mc; + int ret; + + ret = __topup_hyp_memcache(mc, min_pages, admit_host_page, + hyp_virt_to_phys, &tmp); + *host_mc = tmp; + + return ret; +} diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c index d40f0b30b534..803ba3222e75 100644 --- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c +++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c @@ -93,11 +93,16 @@ static inline struct hyp_page *node_to_page(struct list_head *node) static void __hyp_attach_page(struct hyp_pool *pool, struct hyp_page *p) { + phys_addr_t phys = hyp_page_to_phys(p); unsigned short order = p->order; struct hyp_page *buddy; memset(hyp_page_to_virt(p), 0, PAGE_SIZE << p->order); + /* Skip coalescing for 'external' pages being freed into the pool. */ + if (phys < pool->range_start || phys >= pool->range_end) + goto insert; + /* * Only the first struct hyp_page of a high-order page (otherwise known * as the 'head') should have p->order set. The non-head pages should @@ -116,6 +121,7 @@ static void __hyp_attach_page(struct hyp_pool *pool, p = min(p, buddy); } +insert: /* Mark the new head, and insert it */ p->order = order; page_add_to_list(p, &pool->free_area[order]); @@ -144,25 +150,6 @@ static struct hyp_page *__hyp_extract_page(struct hyp_pool *pool, return p; } -static inline void hyp_page_ref_inc(struct hyp_page *p) -{ - BUG_ON(p->refcount == USHRT_MAX); - p->refcount++; -} - -static inline int hyp_page_ref_dec_and_test(struct hyp_page *p) -{ - BUG_ON(!p->refcount); - p->refcount--; - return (p->refcount == 0); -} - -static inline void hyp_set_page_refcounted(struct hyp_page *p) -{ - BUG_ON(p->refcount); - p->refcount = 1; -} - static void __hyp_put_page(struct hyp_pool *pool, struct hyp_page *p) { if (hyp_page_ref_dec_and_test(p)) @@ -249,10 +236,8 @@ int hyp_pool_init(struct hyp_pool *pool, u64 pfn, unsigned int nr_pages, /* Init the vmemmap portion */ p = hyp_phys_to_page(phys); - for (i = 0; i < nr_pages; i++) { - p[i].order = 0; + for (i = 0; i < nr_pages; i++) hyp_set_page_refcounted(&p[i]); - } /* Attach the unused pages to the buddy tree */ for (i = reserved_pages; i < nr_pages; i++) diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 85d3b7ae720f..a06ece14a6d8 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -7,8 +7,17 @@ #include <linux/kvm_host.h> #include <linux/mm.h> #include <nvhe/fixed_config.h> +#include <nvhe/mem_protect.h> +#include <nvhe/memory.h> +#include <nvhe/pkvm.h> #include <nvhe/trap_handler.h> +/* Used by icache_is_vpipt(). */ +unsigned long __icache_flags; + +/* Used by kvm_get_vttbr(). */ +unsigned int kvm_arm_vmid_bits; + /* * Set trap register values based on features in ID_AA64PFR0. */ @@ -183,3 +192,430 @@ void __pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu) pvm_init_traps_aa64mmfr0(vcpu); pvm_init_traps_aa64mmfr1(vcpu); } + +/* + * Start the VM table handle at the offset defined instead of at 0. + * Mainly for sanity checking and debugging. + */ +#define HANDLE_OFFSET 0x1000 + +static unsigned int vm_handle_to_idx(pkvm_handle_t handle) +{ + return handle - HANDLE_OFFSET; +} + +static pkvm_handle_t idx_to_vm_handle(unsigned int idx) +{ + return idx + HANDLE_OFFSET; +} + +/* + * Spinlock for protecting state related to the VM table. Protects writes + * to 'vm_table' and 'nr_table_entries' as well as reads and writes to + * 'last_hyp_vcpu_lookup'. + */ +static DEFINE_HYP_SPINLOCK(vm_table_lock); + +/* + * The table of VM entries for protected VMs in hyp. + * Allocated at hyp initialization and setup. + */ +static struct pkvm_hyp_vm **vm_table; + +void pkvm_hyp_vm_table_init(void *tbl) +{ + WARN_ON(vm_table); + vm_table = tbl; +} + +/* + * Return the hyp vm structure corresponding to the handle. + */ +static struct pkvm_hyp_vm *get_vm_by_handle(pkvm_handle_t handle) +{ + unsigned int idx = vm_handle_to_idx(handle); + + if (unlikely(idx >= KVM_MAX_PVMS)) + return NULL; + + return vm_table[idx]; +} + +struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle, + unsigned int vcpu_idx) +{ + struct pkvm_hyp_vcpu *hyp_vcpu = NULL; + struct pkvm_hyp_vm *hyp_vm; + + hyp_spin_lock(&vm_table_lock); + hyp_vm = get_vm_by_handle(handle); + if (!hyp_vm || hyp_vm->nr_vcpus <= vcpu_idx) + goto unlock; + + hyp_vcpu = hyp_vm->vcpus[vcpu_idx]; + hyp_page_ref_inc(hyp_virt_to_page(hyp_vm)); +unlock: + hyp_spin_unlock(&vm_table_lock); + return hyp_vcpu; +} + +void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct pkvm_hyp_vm *hyp_vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu); + + hyp_spin_lock(&vm_table_lock); + hyp_page_ref_dec(hyp_virt_to_page(hyp_vm)); + hyp_spin_unlock(&vm_table_lock); +} + +static void unpin_host_vcpu(struct kvm_vcpu *host_vcpu) +{ + if (host_vcpu) + hyp_unpin_shared_mem(host_vcpu, host_vcpu + 1); +} + +static void unpin_host_vcpus(struct pkvm_hyp_vcpu *hyp_vcpus[], + unsigned int nr_vcpus) +{ + int i; + + for (i = 0; i < nr_vcpus; i++) + unpin_host_vcpu(hyp_vcpus[i]->host_vcpu); +} + +static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm, + unsigned int nr_vcpus) +{ + hyp_vm->host_kvm = host_kvm; + hyp_vm->kvm.created_vcpus = nr_vcpus; + hyp_vm->kvm.arch.vtcr = host_mmu.arch.vtcr; +} + +static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu, + struct pkvm_hyp_vm *hyp_vm, + struct kvm_vcpu *host_vcpu, + unsigned int vcpu_idx) +{ + int ret = 0; + + if (hyp_pin_shared_mem(host_vcpu, host_vcpu + 1)) + return -EBUSY; + + if (host_vcpu->vcpu_idx != vcpu_idx) { + ret = -EINVAL; + goto done; + } + + hyp_vcpu->host_vcpu = host_vcpu; + + hyp_vcpu->vcpu.kvm = &hyp_vm->kvm; + hyp_vcpu->vcpu.vcpu_id = READ_ONCE(host_vcpu->vcpu_id); + hyp_vcpu->vcpu.vcpu_idx = vcpu_idx; + + hyp_vcpu->vcpu.arch.hw_mmu = &hyp_vm->kvm.arch.mmu; + hyp_vcpu->vcpu.arch.cflags = READ_ONCE(host_vcpu->arch.cflags); +done: + if (ret) + unpin_host_vcpu(host_vcpu); + return ret; +} + +static int find_free_vm_table_entry(struct kvm *host_kvm) +{ + int i; + + for (i = 0; i < KVM_MAX_PVMS; ++i) { + if (!vm_table[i]) + return i; + } + + return -ENOMEM; +} + +/* + * Allocate a VM table entry and insert a pointer to the new vm. + * + * Return a unique handle to the protected VM on success, + * negative error code on failure. + */ +static pkvm_handle_t insert_vm_table_entry(struct kvm *host_kvm, + struct pkvm_hyp_vm *hyp_vm) +{ + struct kvm_s2_mmu *mmu = &hyp_vm->kvm.arch.mmu; + int idx; + + hyp_assert_lock_held(&vm_table_lock); + + /* + * Initializing protected state might have failed, yet a malicious + * host could trigger this function. Thus, ensure that 'vm_table' + * exists. + */ + if (unlikely(!vm_table)) + return -EINVAL; + + idx = find_free_vm_table_entry(host_kvm); + if (idx < 0) + return idx; + + hyp_vm->kvm.arch.pkvm.handle = idx_to_vm_handle(idx); + + /* VMID 0 is reserved for the host */ + atomic64_set(&mmu->vmid.id, idx + 1); + + mmu->arch = &hyp_vm->kvm.arch; + mmu->pgt = &hyp_vm->pgt; + + vm_table[idx] = hyp_vm; + return hyp_vm->kvm.arch.pkvm.handle; +} + +/* + * Deallocate and remove the VM table entry corresponding to the handle. + */ +static void remove_vm_table_entry(pkvm_handle_t handle) +{ + hyp_assert_lock_held(&vm_table_lock); + vm_table[vm_handle_to_idx(handle)] = NULL; +} + +static size_t pkvm_get_hyp_vm_size(unsigned int nr_vcpus) +{ + return size_add(sizeof(struct pkvm_hyp_vm), + size_mul(sizeof(struct pkvm_hyp_vcpu *), nr_vcpus)); +} + +static void *map_donated_memory_noclear(unsigned long host_va, size_t size) +{ + void *va = (void *)kern_hyp_va(host_va); + + if (!PAGE_ALIGNED(va)) + return NULL; + + if (__pkvm_host_donate_hyp(hyp_virt_to_pfn(va), + PAGE_ALIGN(size) >> PAGE_SHIFT)) + return NULL; + + return va; +} + +static void *map_donated_memory(unsigned long host_va, size_t size) +{ + void *va = map_donated_memory_noclear(host_va, size); + + if (va) + memset(va, 0, size); + + return va; +} + +static void __unmap_donated_memory(void *va, size_t size) +{ + WARN_ON(__pkvm_hyp_donate_host(hyp_virt_to_pfn(va), + PAGE_ALIGN(size) >> PAGE_SHIFT)); +} + +static void unmap_donated_memory(void *va, size_t size) +{ + if (!va) + return; + + memset(va, 0, size); + __unmap_donated_memory(va, size); +} + +static void unmap_donated_memory_noclear(void *va, size_t size) +{ + if (!va) + return; + + __unmap_donated_memory(va, size); +} + +/* + * Initialize the hypervisor copy of the protected VM state using the + * memory donated by the host. + * + * Unmaps the donated memory from the host at stage 2. + * + * host_kvm: A pointer to the host's struct kvm. + * vm_hva: The host va of the area being donated for the VM state. + * Must be page aligned. + * pgd_hva: The host va of the area being donated for the stage-2 PGD for + * the VM. Must be page aligned. Its size is implied by the VM's + * VTCR. + * + * Return a unique handle to the protected VM on success, + * negative error code on failure. + */ +int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva, + unsigned long pgd_hva) +{ + struct pkvm_hyp_vm *hyp_vm = NULL; + size_t vm_size, pgd_size; + unsigned int nr_vcpus; + void *pgd = NULL; + int ret; + + ret = hyp_pin_shared_mem(host_kvm, host_kvm + 1); + if (ret) + return ret; + + nr_vcpus = READ_ONCE(host_kvm->created_vcpus); + if (nr_vcpus < 1) { + ret = -EINVAL; + goto err_unpin_kvm; + } + + vm_size = pkvm_get_hyp_vm_size(nr_vcpus); + pgd_size = kvm_pgtable_stage2_pgd_size(host_mmu.arch.vtcr); + + ret = -ENOMEM; + + hyp_vm = map_donated_memory(vm_hva, vm_size); + if (!hyp_vm) + goto err_remove_mappings; + + pgd = map_donated_memory_noclear(pgd_hva, pgd_size); + if (!pgd) + goto err_remove_mappings; + + init_pkvm_hyp_vm(host_kvm, hyp_vm, nr_vcpus); + + hyp_spin_lock(&vm_table_lock); + ret = insert_vm_table_entry(host_kvm, hyp_vm); + if (ret < 0) + goto err_unlock; + + ret = kvm_guest_prepare_stage2(hyp_vm, pgd); + if (ret) + goto err_remove_vm_table_entry; + hyp_spin_unlock(&vm_table_lock); + + return hyp_vm->kvm.arch.pkvm.handle; + +err_remove_vm_table_entry: + remove_vm_table_entry(hyp_vm->kvm.arch.pkvm.handle); +err_unlock: + hyp_spin_unlock(&vm_table_lock); +err_remove_mappings: + unmap_donated_memory(hyp_vm, vm_size); + unmap_donated_memory(pgd, pgd_size); +err_unpin_kvm: + hyp_unpin_shared_mem(host_kvm, host_kvm + 1); + return ret; +} + +/* + * Initialize the hypervisor copy of the protected vCPU state using the + * memory donated by the host. + * + * handle: The handle for the protected vm. + * host_vcpu: A pointer to the corresponding host vcpu. + * vcpu_hva: The host va of the area being donated for the vcpu state. + * Must be page aligned. The size of the area must be equal to + * the page-aligned size of 'struct pkvm_hyp_vcpu'. + * Return 0 on success, negative error code on failure. + */ +int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu, + unsigned long vcpu_hva) +{ + struct pkvm_hyp_vcpu *hyp_vcpu; + struct pkvm_hyp_vm *hyp_vm; + unsigned int idx; + int ret; + + hyp_vcpu = map_donated_memory(vcpu_hva, sizeof(*hyp_vcpu)); + if (!hyp_vcpu) + return -ENOMEM; + + hyp_spin_lock(&vm_table_lock); + + hyp_vm = get_vm_by_handle(handle); + if (!hyp_vm) { + ret = -ENOENT; + goto unlock; + } + + idx = hyp_vm->nr_vcpus; + if (idx >= hyp_vm->kvm.created_vcpus) { + ret = -EINVAL; + goto unlock; + } + + ret = init_pkvm_hyp_vcpu(hyp_vcpu, hyp_vm, host_vcpu, idx); + if (ret) + goto unlock; + + hyp_vm->vcpus[idx] = hyp_vcpu; + hyp_vm->nr_vcpus++; +unlock: + hyp_spin_unlock(&vm_table_lock); + + if (ret) + unmap_donated_memory(hyp_vcpu, sizeof(*hyp_vcpu)); + + return ret; +} + +static void +teardown_donated_memory(struct kvm_hyp_memcache *mc, void *addr, size_t size) +{ + size = PAGE_ALIGN(size); + memset(addr, 0, size); + + for (void *start = addr; start < addr + size; start += PAGE_SIZE) + push_hyp_memcache(mc, start, hyp_virt_to_phys); + + unmap_donated_memory_noclear(addr, size); +} + +int __pkvm_teardown_vm(pkvm_handle_t handle) +{ + struct kvm_hyp_memcache *mc; + struct pkvm_hyp_vm *hyp_vm; + struct kvm *host_kvm; + unsigned int idx; + size_t vm_size; + int err; + + hyp_spin_lock(&vm_table_lock); + hyp_vm = get_vm_by_handle(handle); + if (!hyp_vm) { + err = -ENOENT; + goto err_unlock; + } + + if (WARN_ON(hyp_page_count(hyp_vm))) { + err = -EBUSY; + goto err_unlock; + } + + host_kvm = hyp_vm->host_kvm; + + /* Ensure the VMID is clean before it can be reallocated */ + __kvm_tlb_flush_vmid(&hyp_vm->kvm.arch.mmu); + remove_vm_table_entry(handle); + hyp_spin_unlock(&vm_table_lock); + + /* Reclaim guest pages (including page-table pages) */ + mc = &host_kvm->arch.pkvm.teardown_mc; + reclaim_guest_pages(hyp_vm, mc); + unpin_host_vcpus(hyp_vm->vcpus, hyp_vm->nr_vcpus); + + /* Push the metadata pages to the teardown memcache */ + for (idx = 0; idx < hyp_vm->nr_vcpus; ++idx) { + struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vm->vcpus[idx]; + + teardown_donated_memory(mc, hyp_vcpu, sizeof(*hyp_vcpu)); + } + + vm_size = pkvm_get_hyp_vm_size(hyp_vm->kvm.created_vcpus); + teardown_donated_memory(mc, hyp_vm, vm_size); + hyp_unpin_shared_mem(host_kvm, host_kvm + 1); + return 0; + +err_unlock: + hyp_spin_unlock(&vm_table_lock); + return err; +} diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index e8d4ea2fcfa0..110f04627785 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -16,6 +16,7 @@ #include <nvhe/memory.h> #include <nvhe/mem_protect.h> #include <nvhe/mm.h> +#include <nvhe/pkvm.h> #include <nvhe/trap_handler.h> unsigned long hyp_nr_cpus; @@ -24,6 +25,7 @@ unsigned long hyp_nr_cpus; (unsigned long)__per_cpu_start) static void *vmemmap_base; +static void *vm_table_base; static void *hyp_pgt_base; static void *host_s2_pgt_base; static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; @@ -31,16 +33,20 @@ static struct hyp_pool hpool; static int divide_memory_pool(void *virt, unsigned long size) { - unsigned long vstart, vend, nr_pages; + unsigned long nr_pages; hyp_early_alloc_init(virt, size); - hyp_vmemmap_range(__hyp_pa(virt), size, &vstart, &vend); - nr_pages = (vend - vstart) >> PAGE_SHIFT; + nr_pages = hyp_vmemmap_pages(sizeof(struct hyp_page)); vmemmap_base = hyp_early_alloc_contig(nr_pages); if (!vmemmap_base) return -ENOMEM; + nr_pages = hyp_vm_table_pages(); + vm_table_base = hyp_early_alloc_contig(nr_pages); + if (!vm_table_base) + return -ENOMEM; + nr_pages = hyp_s1_pgtable_pages(); hyp_pgt_base = hyp_early_alloc_contig(nr_pages); if (!hyp_pgt_base) @@ -78,7 +84,7 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size, if (ret) return ret; - ret = hyp_back_vmemmap(phys, size, hyp_virt_to_phys(vmemmap_base)); + ret = hyp_back_vmemmap(hyp_virt_to_phys(vmemmap_base)); if (ret) return ret; @@ -138,20 +144,17 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size, } /* - * Map the host's .bss and .rodata sections RO in the hypervisor, but - * transfer the ownership from the host to the hypervisor itself to - * make sure it can't be donated or shared with another entity. + * Map the host sections RO in the hypervisor, but transfer the + * ownership from the host to the hypervisor itself to make sure they + * can't be donated or shared with another entity. * * The ownership transition requires matching changes in the host * stage-2. This will be done later (see finalize_host_mappings()) once * the hyp_vmemmap is addressable. */ prot = pkvm_mkstate(PAGE_HYP_RO, PKVM_PAGE_SHARED_OWNED); - ret = pkvm_create_mappings(__start_rodata, __end_rodata, prot); - if (ret) - return ret; - - ret = pkvm_create_mappings(__hyp_bss_end, __bss_stop, prot); + ret = pkvm_create_mappings(&kvm_vgic_global_state, + &kvm_vgic_global_state + 1, prot); if (ret) return ret; @@ -186,33 +189,20 @@ static void hpool_put_page(void *addr) hyp_put_page(&hpool, addr); } -static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level, - kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag, - void * const arg) +static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) { - struct kvm_pgtable_mm_ops *mm_ops = arg; enum kvm_pgtable_prot prot; enum pkvm_page_state state; - kvm_pte_t pte = *ptep; phys_addr_t phys; - if (!kvm_pte_valid(pte)) + if (!kvm_pte_valid(ctx->old)) return 0; - /* - * Fix-up the refcount for the page-table pages as the early allocator - * was unable to access the hyp_vmemmap and so the buddy allocator has - * initialised the refcount to '1'. - */ - mm_ops->get_page(ptep); - if (flag != KVM_PGTABLE_WALK_LEAF) - return 0; - - if (level != (KVM_PGTABLE_MAX_LEVELS - 1)) + if (ctx->level != (KVM_PGTABLE_MAX_LEVELS - 1)) return -EINVAL; - phys = kvm_pte_to_phys(pte); + phys = kvm_pte_to_phys(ctx->old); if (!addr_is_memory(phys)) return -EINVAL; @@ -220,10 +210,10 @@ static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level, * Adjust the host stage-2 mappings to match the ownership attributes * configured in the hypervisor stage-1. */ - state = pkvm_getstate(kvm_pgtable_hyp_pte_prot(pte)); + state = pkvm_getstate(kvm_pgtable_hyp_pte_prot(ctx->old)); switch (state) { case PKVM_PAGE_OWNED: - return host_stage2_set_owner_locked(phys, PAGE_SIZE, pkvm_hyp_id); + return host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HYP); case PKVM_PAGE_SHARED_OWNED: prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_BORROWED); break; @@ -237,12 +227,25 @@ static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level, return host_stage2_idmap_locked(phys, PAGE_SIZE, prot); } -static int finalize_host_mappings(void) +static int fix_hyp_pgtable_refcnt_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + /* + * Fix-up the refcount for the page-table pages as the early allocator + * was unable to access the hyp_vmemmap and so the buddy allocator has + * initialised the refcount to '1'. + */ + if (kvm_pte_valid(ctx->old)) + ctx->mm_ops->get_page(ctx->ptep); + + return 0; +} + +static int fix_host_ownership(void) { struct kvm_pgtable_walker walker = { - .cb = finalize_host_mappings_walker, - .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, - .arg = pkvm_pgtable.mm_ops, + .cb = fix_host_ownership_walker, + .flags = KVM_PGTABLE_WALK_LEAF, }; int i, ret; @@ -258,6 +261,18 @@ static int finalize_host_mappings(void) return 0; } +static int fix_hyp_pgtable_refcnt(void) +{ + struct kvm_pgtable_walker walker = { + .cb = fix_hyp_pgtable_refcnt_walker, + .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, + .arg = pkvm_pgtable.mm_ops, + }; + + return kvm_pgtable_walk(&pkvm_pgtable, 0, BIT(pkvm_pgtable.ia_bits), + &walker); +} + void __noreturn __pkvm_init_finalise(void) { struct kvm_host_data *host_data = this_cpu_ptr(&kvm_host_data); @@ -287,10 +302,19 @@ void __noreturn __pkvm_init_finalise(void) }; pkvm_pgtable.mm_ops = &pkvm_pgtable_mm_ops; - ret = finalize_host_mappings(); + ret = fix_host_ownership(); + if (ret) + goto out; + + ret = fix_hyp_pgtable_refcnt(); + if (ret) + goto out; + + ret = hyp_create_pcpu_fixmap(); if (ret) goto out; + pkvm_hyp_vm_table_init(vm_table_base); out: /* * We tail-called to here from handle___pkvm_init() and will not return, diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index cdf8e76b0be1..b11cf2c618a6 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -49,35 +49,38 @@ #define KVM_INVALID_PTE_OWNER_MASK GENMASK(9, 2) #define KVM_MAX_OWNER_ID 1 +/* + * Used to indicate a pte for which a 'break-before-make' sequence is in + * progress. + */ +#define KVM_INVALID_PTE_LOCKED BIT(10) + struct kvm_pgtable_walk_data { - struct kvm_pgtable *pgt; struct kvm_pgtable_walker *walker; u64 addr; u64 end; }; -#define KVM_PHYS_INVALID (-1ULL) - static bool kvm_phys_is_valid(u64 phys) { return phys < BIT(id_aa64mmfr0_parange_to_phys_shift(ID_AA64MMFR0_EL1_PARANGE_MAX)); } -static bool kvm_block_mapping_supported(u64 addr, u64 end, u64 phys, u32 level) +static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys) { - u64 granule = kvm_granule_size(level); + u64 granule = kvm_granule_size(ctx->level); - if (!kvm_level_supports_block_mapping(level)) + if (!kvm_level_supports_block_mapping(ctx->level)) return false; - if (granule > (end - addr)) + if (granule > (ctx->end - ctx->addr)) return false; if (kvm_phys_is_valid(phys) && !IS_ALIGNED(phys, granule)) return false; - return IS_ALIGNED(addr, granule); + return IS_ALIGNED(ctx->addr, granule); } static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, u32 level) @@ -88,7 +91,7 @@ static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, u32 level) return (data->addr >> shift) & mask; } -static u32 __kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr) +static u32 kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr) { u64 shift = kvm_granule_shift(pgt->start_level - 1); /* May underflow */ u64 mask = BIT(pgt->ia_bits) - 1; @@ -96,11 +99,6 @@ static u32 __kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr) return (addr & mask) >> shift; } -static u32 kvm_pgd_page_idx(struct kvm_pgtable_walk_data *data) -{ - return __kvm_pgd_page_idx(data->pgt, data->addr); -} - static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level) { struct kvm_pgtable pgt = { @@ -108,7 +106,7 @@ static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level) .start_level = start_level, }; - return __kvm_pgd_page_idx(&pgt, -1ULL) + 1; + return kvm_pgd_page_idx(&pgt, -1ULL) + 1; } static bool kvm_pte_table(kvm_pte_t pte, u32 level) @@ -122,16 +120,6 @@ static bool kvm_pte_table(kvm_pte_t pte, u32 level) return FIELD_GET(KVM_PTE_TYPE, pte) == KVM_PTE_TYPE_TABLE; } -static kvm_pte_t kvm_phys_to_pte(u64 pa) -{ - kvm_pte_t pte = pa & KVM_PTE_ADDR_MASK; - - if (PAGE_SHIFT == 16) - pte |= FIELD_PREP(KVM_PTE_ADDR_51_48, pa >> 48); - - return pte; -} - static kvm_pte_t *kvm_pte_follow(kvm_pte_t pte, struct kvm_pgtable_mm_ops *mm_ops) { return mm_ops->phys_to_virt(kvm_pte_to_phys(pte)); @@ -142,16 +130,13 @@ static void kvm_clear_pte(kvm_pte_t *ptep) WRITE_ONCE(*ptep, 0); } -static void kvm_set_table_pte(kvm_pte_t *ptep, kvm_pte_t *childp, - struct kvm_pgtable_mm_ops *mm_ops) +static kvm_pte_t kvm_init_table_pte(kvm_pte_t *childp, struct kvm_pgtable_mm_ops *mm_ops) { - kvm_pte_t old = *ptep, pte = kvm_phys_to_pte(mm_ops->virt_to_phys(childp)); + kvm_pte_t pte = kvm_phys_to_pte(mm_ops->virt_to_phys(childp)); pte |= FIELD_PREP(KVM_PTE_TYPE, KVM_PTE_TYPE_TABLE); pte |= KVM_PTE_VALID; - - WARN_ON(kvm_pte_valid(old)); - smp_store_release(ptep, pte); + return pte; } static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, u32 level) @@ -172,36 +157,47 @@ static kvm_pte_t kvm_init_invalid_leaf_owner(u8 owner_id) return FIELD_PREP(KVM_INVALID_PTE_OWNER_MASK, owner_id); } -static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, u64 addr, - u32 level, kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag) +static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, + const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_walker *walker = data->walker; - return walker->cb(addr, data->end, level, ptep, flag, walker->arg); + + /* Ensure the appropriate lock is held (e.g. RCU lock for stage-2 MMU) */ + WARN_ON_ONCE(kvm_pgtable_walk_shared(ctx) && !kvm_pgtable_walk_lock_held()); + return walker->cb(ctx, visit); } static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, - kvm_pte_t *pgtable, u32 level); + struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level); static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, - kvm_pte_t *ptep, u32 level) + struct kvm_pgtable_mm_ops *mm_ops, + kvm_pteref_t pteref, u32 level) { - int ret = 0; - u64 addr = data->addr; - kvm_pte_t *childp, pte = *ptep; - bool table = kvm_pte_table(pte, level); enum kvm_pgtable_walk_flags flags = data->walker->flags; + kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref); + struct kvm_pgtable_visit_ctx ctx = { + .ptep = ptep, + .old = READ_ONCE(*ptep), + .arg = data->walker->arg, + .mm_ops = mm_ops, + .addr = data->addr, + .end = data->end, + .level = level, + .flags = flags, + }; + int ret = 0; + kvm_pteref_t childp; + bool table = kvm_pte_table(ctx.old, level); - if (table && (flags & KVM_PGTABLE_WALK_TABLE_PRE)) { - ret = kvm_pgtable_visitor_cb(data, addr, level, ptep, - KVM_PGTABLE_WALK_TABLE_PRE); - } + if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE)) + ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_PRE); - if (!table && (flags & KVM_PGTABLE_WALK_LEAF)) { - ret = kvm_pgtable_visitor_cb(data, addr, level, ptep, - KVM_PGTABLE_WALK_LEAF); - pte = *ptep; - table = kvm_pte_table(pte, level); + if (!table && (ctx.flags & KVM_PGTABLE_WALK_LEAF)) { + ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_LEAF); + ctx.old = READ_ONCE(*ptep); + table = kvm_pte_table(ctx.old, level); } if (ret) @@ -213,22 +209,20 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, goto out; } - childp = kvm_pte_follow(pte, data->pgt->mm_ops); - ret = __kvm_pgtable_walk(data, childp, level + 1); + childp = (kvm_pteref_t)kvm_pte_follow(ctx.old, mm_ops); + ret = __kvm_pgtable_walk(data, mm_ops, childp, level + 1); if (ret) goto out; - if (flags & KVM_PGTABLE_WALK_TABLE_POST) { - ret = kvm_pgtable_visitor_cb(data, addr, level, ptep, - KVM_PGTABLE_WALK_TABLE_POST); - } + if (ctx.flags & KVM_PGTABLE_WALK_TABLE_POST) + ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_POST); out: return ret; } static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, - kvm_pte_t *pgtable, u32 level) + struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level) { u32 idx; int ret = 0; @@ -237,12 +231,12 @@ static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, return -EINVAL; for (idx = kvm_pgtable_idx(data, level); idx < PTRS_PER_PTE; ++idx) { - kvm_pte_t *ptep = &pgtable[idx]; + kvm_pteref_t pteref = &pgtable[idx]; if (data->addr >= data->end) break; - ret = __kvm_pgtable_visit(data, ptep, level); + ret = __kvm_pgtable_visit(data, mm_ops, pteref, level); if (ret) break; } @@ -250,11 +244,10 @@ static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, return ret; } -static int _kvm_pgtable_walk(struct kvm_pgtable_walk_data *data) +static int _kvm_pgtable_walk(struct kvm_pgtable *pgt, struct kvm_pgtable_walk_data *data) { u32 idx; int ret = 0; - struct kvm_pgtable *pgt = data->pgt; u64 limit = BIT(pgt->ia_bits); if (data->addr > limit || data->end > limit) @@ -263,10 +256,10 @@ static int _kvm_pgtable_walk(struct kvm_pgtable_walk_data *data) if (!pgt->pgd) return -EINVAL; - for (idx = kvm_pgd_page_idx(data); data->addr < data->end; ++idx) { - kvm_pte_t *ptep = &pgt->pgd[idx * PTRS_PER_PTE]; + for (idx = kvm_pgd_page_idx(pgt, data->addr); data->addr < data->end; ++idx) { + kvm_pteref_t pteref = &pgt->pgd[idx * PTRS_PER_PTE]; - ret = __kvm_pgtable_walk(data, ptep, pgt->start_level); + ret = __kvm_pgtable_walk(data, pgt->mm_ops, pteref, pgt->start_level); if (ret) break; } @@ -278,13 +271,20 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_pgtable_walker *walker) { struct kvm_pgtable_walk_data walk_data = { - .pgt = pgt, .addr = ALIGN_DOWN(addr, PAGE_SIZE), .end = PAGE_ALIGN(walk_data.addr + size), .walker = walker, }; + int r; - return _kvm_pgtable_walk(&walk_data); + r = kvm_pgtable_walk_begin(walker); + if (r) + return r; + + r = _kvm_pgtable_walk(pgt, &walk_data); + kvm_pgtable_walk_end(walker); + + return r; } struct leaf_walk_data { @@ -292,13 +292,13 @@ struct leaf_walk_data { u32 level; }; -static int leaf_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag, void * const arg) +static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) { - struct leaf_walk_data *data = arg; + struct leaf_walk_data *data = ctx->arg; - data->pte = *ptep; - data->level = level; + data->pte = ctx->old; + data->level = ctx->level; return 0; } @@ -329,7 +329,6 @@ int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, struct hyp_map_data { u64 phys; kvm_pte_t attr; - struct kvm_pgtable_mm_ops *mm_ops; }; static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep) @@ -383,47 +382,49 @@ enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte) return prot; } -static bool hyp_map_walker_try_leaf(u64 addr, u64 end, u32 level, - kvm_pte_t *ptep, struct hyp_map_data *data) +static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, + struct hyp_map_data *data) { - kvm_pte_t new, old = *ptep; - u64 granule = kvm_granule_size(level), phys = data->phys; + kvm_pte_t new; + u64 granule = kvm_granule_size(ctx->level), phys = data->phys; - if (!kvm_block_mapping_supported(addr, end, phys, level)) + if (!kvm_block_mapping_supported(ctx, phys)) return false; data->phys += granule; - new = kvm_init_valid_leaf_pte(phys, data->attr, level); - if (old == new) + new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); + if (ctx->old == new) return true; - if (!kvm_pte_valid(old)) - data->mm_ops->get_page(ptep); - else if (WARN_ON((old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) + if (!kvm_pte_valid(ctx->old)) + ctx->mm_ops->get_page(ctx->ptep); + else if (WARN_ON((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) return false; - smp_store_release(ptep, new); + smp_store_release(ctx->ptep, new); return true; } -static int hyp_map_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag, void * const arg) +static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) { - kvm_pte_t *childp; - struct hyp_map_data *data = arg; - struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; + kvm_pte_t *childp, new; + struct hyp_map_data *data = ctx->arg; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; - if (hyp_map_walker_try_leaf(addr, end, level, ptep, arg)) + if (hyp_map_walker_try_leaf(ctx, data)) return 0; - if (WARN_ON(level == KVM_PGTABLE_MAX_LEVELS - 1)) + if (WARN_ON(ctx->level == KVM_PGTABLE_MAX_LEVELS - 1)) return -EINVAL; childp = (kvm_pte_t *)mm_ops->zalloc_page(NULL); if (!childp) return -ENOMEM; - kvm_set_table_pte(ptep, childp, mm_ops); - mm_ops->get_page(ptep); + new = kvm_init_table_pte(childp, mm_ops); + mm_ops->get_page(ctx->ptep); + smp_store_release(ctx->ptep, new); + return 0; } @@ -433,7 +434,6 @@ int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, int ret; struct hyp_map_data map_data = { .phys = ALIGN_DOWN(phys, PAGE_SIZE), - .mm_ops = pgt->mm_ops, }; struct kvm_pgtable_walker walker = { .cb = hyp_map_walker, @@ -451,44 +451,39 @@ int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, return ret; } -struct hyp_unmap_data { - u64 unmapped; - struct kvm_pgtable_mm_ops *mm_ops; -}; - -static int hyp_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag, void * const arg) +static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) { - kvm_pte_t pte = *ptep, *childp = NULL; - u64 granule = kvm_granule_size(level); - struct hyp_unmap_data *data = arg; - struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; + kvm_pte_t *childp = NULL; + u64 granule = kvm_granule_size(ctx->level); + u64 *unmapped = ctx->arg; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; - if (!kvm_pte_valid(pte)) + if (!kvm_pte_valid(ctx->old)) return -EINVAL; - if (kvm_pte_table(pte, level)) { - childp = kvm_pte_follow(pte, mm_ops); + if (kvm_pte_table(ctx->old, ctx->level)) { + childp = kvm_pte_follow(ctx->old, mm_ops); if (mm_ops->page_count(childp) != 1) return 0; - kvm_clear_pte(ptep); + kvm_clear_pte(ctx->ptep); dsb(ishst); - __tlbi_level(vae2is, __TLBI_VADDR(addr, 0), level); + __tlbi_level(vae2is, __TLBI_VADDR(ctx->addr, 0), ctx->level); } else { - if (end - addr < granule) + if (ctx->end - ctx->addr < granule) return -EINVAL; - kvm_clear_pte(ptep); + kvm_clear_pte(ctx->ptep); dsb(ishst); - __tlbi_level(vale2is, __TLBI_VADDR(addr, 0), level); - data->unmapped += granule; + __tlbi_level(vale2is, __TLBI_VADDR(ctx->addr, 0), ctx->level); + *unmapped += granule; } dsb(ish); isb(); - mm_ops->put_page(ptep); + mm_ops->put_page(ctx->ptep); if (childp) mm_ops->put_page(childp); @@ -498,12 +493,10 @@ static int hyp_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) { - struct hyp_unmap_data unmap_data = { - .mm_ops = pgt->mm_ops, - }; + u64 unmapped = 0; struct kvm_pgtable_walker walker = { .cb = hyp_unmap_walker, - .arg = &unmap_data, + .arg = &unmapped, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, }; @@ -511,7 +504,7 @@ u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) return 0; kvm_pgtable_walk(pgt, addr, size, &walker); - return unmap_data.unmapped; + return unmapped; } int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, @@ -519,7 +512,7 @@ int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, { u64 levels = ARM64_HW_PGTABLE_LEVELS(va_bits); - pgt->pgd = (kvm_pte_t *)mm_ops->zalloc_page(NULL); + pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_page(NULL); if (!pgt->pgd) return -ENOMEM; @@ -532,19 +525,18 @@ int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, return 0; } -static int hyp_free_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag, void * const arg) +static int hyp_free_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) { - struct kvm_pgtable_mm_ops *mm_ops = arg; - kvm_pte_t pte = *ptep; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; - if (!kvm_pte_valid(pte)) + if (!kvm_pte_valid(ctx->old)) return 0; - mm_ops->put_page(ptep); + mm_ops->put_page(ctx->ptep); - if (kvm_pte_table(pte, level)) - mm_ops->put_page(kvm_pte_follow(pte, mm_ops)); + if (kvm_pte_table(ctx->old, ctx->level)) + mm_ops->put_page(kvm_pte_follow(ctx->old, mm_ops)); return 0; } @@ -554,11 +546,10 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) struct kvm_pgtable_walker walker = { .cb = hyp_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, - .arg = pgt->mm_ops, }; WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); - pgt->mm_ops->put_page(pgt->pgd); + pgt->mm_ops->put_page(kvm_dereference_pteref(&walker, pgt->pgd)); pgt->pgd = NULL; } @@ -573,8 +564,6 @@ struct stage2_map_data { struct kvm_s2_mmu *mmu; void *memcache; - struct kvm_pgtable_mm_ops *mm_ops; - /* Force mappings to page granularity */ bool force_pte; }; @@ -682,19 +671,92 @@ static bool stage2_pte_is_counted(kvm_pte_t pte) return !!pte; } -static void stage2_put_pte(kvm_pte_t *ptep, struct kvm_s2_mmu *mmu, u64 addr, - u32 level, struct kvm_pgtable_mm_ops *mm_ops) +static bool stage2_pte_is_locked(kvm_pte_t pte) +{ + return !kvm_pte_valid(pte) && (pte & KVM_INVALID_PTE_LOCKED); +} + +static bool stage2_try_set_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new) +{ + if (!kvm_pgtable_walk_shared(ctx)) { + WRITE_ONCE(*ctx->ptep, new); + return true; + } + + return cmpxchg(ctx->ptep, ctx->old, new) == ctx->old; +} + +/** + * stage2_try_break_pte() - Invalidates a pte according to the + * 'break-before-make' requirements of the + * architecture. + * + * @ctx: context of the visited pte. + * @mmu: stage-2 mmu + * + * Returns: true if the pte was successfully broken. + * + * If the removed pte was valid, performs the necessary serialization and TLB + * invalidation for the old value. For counted ptes, drops the reference count + * on the containing table page. + */ +static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx, + struct kvm_s2_mmu *mmu) +{ + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + + if (stage2_pte_is_locked(ctx->old)) { + /* + * Should never occur if this walker has exclusive access to the + * page tables. + */ + WARN_ON(!kvm_pgtable_walk_shared(ctx)); + return false; + } + + if (!stage2_try_set_pte(ctx, KVM_INVALID_PTE_LOCKED)) + return false; + + /* + * Perform the appropriate TLB invalidation based on the evicted pte + * value (if any). + */ + if (kvm_pte_table(ctx->old, ctx->level)) + kvm_call_hyp(__kvm_tlb_flush_vmid, mmu); + else if (kvm_pte_valid(ctx->old)) + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level); + + if (stage2_pte_is_counted(ctx->old)) + mm_ops->put_page(ctx->ptep); + + return true; +} + +static void stage2_make_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new) +{ + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + + WARN_ON(!stage2_pte_is_locked(*ctx->ptep)); + + if (stage2_pte_is_counted(new)) + mm_ops->get_page(ctx->ptep); + + smp_store_release(ctx->ptep, new); +} + +static void stage2_put_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s2_mmu *mmu, + struct kvm_pgtable_mm_ops *mm_ops) { /* * Clear the existing PTE, and perform break-before-make with * TLB maintenance if it was valid. */ - if (kvm_pte_valid(*ptep)) { - kvm_clear_pte(ptep); - kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, addr, level); + if (kvm_pte_valid(ctx->old)) { + kvm_clear_pte(ctx->ptep); + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level); } - mm_ops->put_page(ptep); + mm_ops->put_page(ctx->ptep); } static bool stage2_pte_cacheable(struct kvm_pgtable *pgt, kvm_pte_t pte) @@ -708,44 +770,42 @@ static bool stage2_pte_executable(kvm_pte_t pte) return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN); } -static bool stage2_leaf_mapping_allowed(u64 addr, u64 end, u32 level, +static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { - if (data->force_pte && (level < (KVM_PGTABLE_MAX_LEVELS - 1))) + if (data->force_pte && (ctx->level < (KVM_PGTABLE_MAX_LEVELS - 1))) return false; - return kvm_block_mapping_supported(addr, end, data->phys, level); + return kvm_block_mapping_supported(ctx, data->phys); } -static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level, - kvm_pte_t *ptep, +static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { - kvm_pte_t new, old = *ptep; - u64 granule = kvm_granule_size(level), phys = data->phys; + kvm_pte_t new; + u64 granule = kvm_granule_size(ctx->level), phys = data->phys; struct kvm_pgtable *pgt = data->mmu->pgt; - struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; - if (!stage2_leaf_mapping_allowed(addr, end, level, data)) + if (!stage2_leaf_mapping_allowed(ctx, data)) return -E2BIG; if (kvm_phys_is_valid(phys)) - new = kvm_init_valid_leaf_pte(phys, data->attr, level); + new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); else new = kvm_init_invalid_leaf_owner(data->owner_id); - if (stage2_pte_is_counted(old)) { - /* - * Skip updating the PTE if we are trying to recreate the exact - * same mapping or only change the access permissions. Instead, - * the vCPU will exit one more time from guest if still needed - * and then go through the path of relaxing permissions. - */ - if (!stage2_pte_needs_update(old, new)) - return -EAGAIN; + /* + * Skip updating the PTE if we are trying to recreate the exact + * same mapping or only change the access permissions. Instead, + * the vCPU will exit one more time from guest if still needed + * and then go through the path of relaxing permissions. + */ + if (!stage2_pte_needs_update(ctx->old, new)) + return -EAGAIN; - stage2_put_pte(ptep, data->mmu, addr, level, mm_ops); - } + if (!stage2_try_break_pte(ctx, data->mmu)) + return -EAGAIN; /* Perform CMOs before installation of the guest stage-2 PTE */ if (mm_ops->dcache_clean_inval_poc && stage2_pte_cacheable(pgt, new)) @@ -755,56 +815,43 @@ static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level, if (mm_ops->icache_inval_pou && stage2_pte_executable(new)) mm_ops->icache_inval_pou(kvm_pte_follow(new, mm_ops), granule); - smp_store_release(ptep, new); - if (stage2_pte_is_counted(new)) - mm_ops->get_page(ptep); + stage2_make_pte(ctx, new); + if (kvm_phys_is_valid(phys)) data->phys += granule; return 0; } -static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level, - kvm_pte_t *ptep, +static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { - if (data->anchor) - return 0; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + kvm_pte_t *childp = kvm_pte_follow(ctx->old, mm_ops); + int ret; - if (!stage2_leaf_mapping_allowed(addr, end, level, data)) + if (!stage2_leaf_mapping_allowed(ctx, data)) return 0; - data->childp = kvm_pte_follow(*ptep, data->mm_ops); - kvm_clear_pte(ptep); + ret = stage2_map_walker_try_leaf(ctx, data); + if (ret) + return ret; - /* - * Invalidate the whole stage-2, as we may have numerous leaf - * entries below us which would otherwise need invalidating - * individually. - */ - kvm_call_hyp(__kvm_tlb_flush_vmid, data->mmu); - data->anchor = ptep; + mm_ops->free_removed_table(childp, ctx->level); return 0; } -static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, +static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { - struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; - kvm_pte_t *childp, pte = *ptep; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + kvm_pte_t *childp, new; int ret; - if (data->anchor) { - if (stage2_pte_is_counted(pte)) - mm_ops->put_page(ptep); - - return 0; - } - - ret = stage2_map_walker_try_leaf(addr, end, level, ptep, data); + ret = stage2_map_walker_try_leaf(ctx, data); if (ret != -E2BIG) return ret; - if (WARN_ON(level == KVM_PGTABLE_MAX_LEVELS - 1)) + if (WARN_ON(ctx->level == KVM_PGTABLE_MAX_LEVELS - 1)) return -EINVAL; if (!data->memcache) @@ -814,99 +861,62 @@ static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, if (!childp) return -ENOMEM; + if (!stage2_try_break_pte(ctx, data->mmu)) { + mm_ops->put_page(childp); + return -EAGAIN; + } + /* * If we've run into an existing block mapping then replace it with * a table. Accesses beyond 'end' that fall within the new table * will be mapped lazily. */ - if (stage2_pte_is_counted(pte)) - stage2_put_pte(ptep, data->mmu, addr, level, mm_ops); - - kvm_set_table_pte(ptep, childp, mm_ops); - mm_ops->get_page(ptep); + new = kvm_init_table_pte(childp, mm_ops); + stage2_make_pte(ctx, new); return 0; } -static int stage2_map_walk_table_post(u64 addr, u64 end, u32 level, - kvm_pte_t *ptep, - struct stage2_map_data *data) -{ - struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; - kvm_pte_t *childp; - int ret = 0; - - if (!data->anchor) - return 0; - - if (data->anchor == ptep) { - childp = data->childp; - data->anchor = NULL; - data->childp = NULL; - ret = stage2_map_walk_leaf(addr, end, level, ptep, data); - } else { - childp = kvm_pte_follow(*ptep, mm_ops); - } - - mm_ops->put_page(childp); - mm_ops->put_page(ptep); - - return ret; -} - /* - * This is a little fiddly, as we use all three of the walk flags. The idea - * is that the TABLE_PRE callback runs for table entries on the way down, - * looking for table entries which we could conceivably replace with a - * block entry for this mapping. If it finds one, then it sets the 'anchor' - * field in 'struct stage2_map_data' to point at the table entry, before - * clearing the entry to zero and descending into the now detached table. + * The TABLE_PRE callback runs for table entries on the way down, looking + * for table entries which we could conceivably replace with a block entry + * for this mapping. If it finds one it replaces the entry and calls + * kvm_pgtable_mm_ops::free_removed_table() to tear down the detached table. * - * The behaviour of the LEAF callback then depends on whether or not the - * anchor has been set. If not, then we're not using a block mapping higher - * up the table and we perform the mapping at the existing leaves instead. - * If, on the other hand, the anchor _is_ set, then we drop references to - * all valid leaves so that the pages beneath the anchor can be freed. - * - * Finally, the TABLE_POST callback does nothing if the anchor has not - * been set, but otherwise frees the page-table pages while walking back up - * the page-table, installing the block entry when it revisits the anchor - * pointer and clearing the anchor to NULL. + * Otherwise, the LEAF callback performs the mapping at the existing leaves + * instead. */ -static int stage2_map_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag, void * const arg) +static int stage2_map_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) { - struct stage2_map_data *data = arg; + struct stage2_map_data *data = ctx->arg; - switch (flag) { + switch (visit) { case KVM_PGTABLE_WALK_TABLE_PRE: - return stage2_map_walk_table_pre(addr, end, level, ptep, data); + return stage2_map_walk_table_pre(ctx, data); case KVM_PGTABLE_WALK_LEAF: - return stage2_map_walk_leaf(addr, end, level, ptep, data); - case KVM_PGTABLE_WALK_TABLE_POST: - return stage2_map_walk_table_post(addr, end, level, ptep, data); + return stage2_map_walk_leaf(ctx, data); + default: + return -EINVAL; } - - return -EINVAL; } int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot, - void *mc) + void *mc, enum kvm_pgtable_walk_flags flags) { int ret; struct stage2_map_data map_data = { .phys = ALIGN_DOWN(phys, PAGE_SIZE), .mmu = pgt->mmu, .memcache = mc, - .mm_ops = pgt->mm_ops, .force_pte = pgt->force_pte_cb && pgt->force_pte_cb(addr, addr + size, prot), }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, - .flags = KVM_PGTABLE_WALK_TABLE_PRE | - KVM_PGTABLE_WALK_LEAF | - KVM_PGTABLE_WALK_TABLE_POST, + .flags = flags | + KVM_PGTABLE_WALK_TABLE_PRE | + KVM_PGTABLE_WALK_LEAF, .arg = &map_data, }; @@ -930,15 +940,13 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size, .phys = KVM_PHYS_INVALID, .mmu = pgt->mmu, .memcache = mc, - .mm_ops = pgt->mm_ops, .owner_id = owner_id, .force_pte = true, }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, .flags = KVM_PGTABLE_WALK_TABLE_PRE | - KVM_PGTABLE_WALK_LEAF | - KVM_PGTABLE_WALK_TABLE_POST, + KVM_PGTABLE_WALK_LEAF, .arg = &map_data, }; @@ -949,30 +957,29 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size, return ret; } -static int stage2_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag, - void * const arg) +static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) { - struct kvm_pgtable *pgt = arg; + struct kvm_pgtable *pgt = ctx->arg; struct kvm_s2_mmu *mmu = pgt->mmu; - struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; - kvm_pte_t pte = *ptep, *childp = NULL; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + kvm_pte_t *childp = NULL; bool need_flush = false; - if (!kvm_pte_valid(pte)) { - if (stage2_pte_is_counted(pte)) { - kvm_clear_pte(ptep); - mm_ops->put_page(ptep); + if (!kvm_pte_valid(ctx->old)) { + if (stage2_pte_is_counted(ctx->old)) { + kvm_clear_pte(ctx->ptep); + mm_ops->put_page(ctx->ptep); } return 0; } - if (kvm_pte_table(pte, level)) { - childp = kvm_pte_follow(pte, mm_ops); + if (kvm_pte_table(ctx->old, ctx->level)) { + childp = kvm_pte_follow(ctx->old, mm_ops); if (mm_ops->page_count(childp) != 1) return 0; - } else if (stage2_pte_cacheable(pgt, pte)) { + } else if (stage2_pte_cacheable(pgt, ctx->old)) { need_flush = !stage2_has_fwb(pgt); } @@ -981,11 +988,11 @@ static int stage2_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, * block entry and rely on the remaining portions being faulted * back lazily. */ - stage2_put_pte(ptep, mmu, addr, level, mm_ops); + stage2_put_pte(ctx, mmu, mm_ops); if (need_flush && mm_ops->dcache_clean_inval_poc) - mm_ops->dcache_clean_inval_poc(kvm_pte_follow(pte, mm_ops), - kvm_granule_size(level)); + mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops), + kvm_granule_size(ctx->level)); if (childp) mm_ops->put_page(childp); @@ -1009,21 +1016,19 @@ struct stage2_attr_data { kvm_pte_t attr_clr; kvm_pte_t pte; u32 level; - struct kvm_pgtable_mm_ops *mm_ops; }; -static int stage2_attr_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag, - void * const arg) +static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) { - kvm_pte_t pte = *ptep; - struct stage2_attr_data *data = arg; - struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; + kvm_pte_t pte = ctx->old; + struct stage2_attr_data *data = ctx->arg; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; - if (!kvm_pte_valid(pte)) + if (!kvm_pte_valid(ctx->old)) return 0; - data->level = level; + data->level = ctx->level; data->pte = pte; pte &= ~data->attr_clr; pte |= data->attr_set; @@ -1039,10 +1044,12 @@ static int stage2_attr_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, * stage-2 PTE if we are going to add executable permission. */ if (mm_ops->icache_inval_pou && - stage2_pte_executable(pte) && !stage2_pte_executable(*ptep)) + stage2_pte_executable(pte) && !stage2_pte_executable(ctx->old)) mm_ops->icache_inval_pou(kvm_pte_follow(pte, mm_ops), - kvm_granule_size(level)); - WRITE_ONCE(*ptep, pte); + kvm_granule_size(ctx->level)); + + if (!stage2_try_set_pte(ctx, pte)) + return -EAGAIN; } return 0; @@ -1051,19 +1058,18 @@ static int stage2_attr_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr, u64 size, kvm_pte_t attr_set, kvm_pte_t attr_clr, kvm_pte_t *orig_pte, - u32 *level) + u32 *level, enum kvm_pgtable_walk_flags flags) { int ret; kvm_pte_t attr_mask = KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI; struct stage2_attr_data data = { .attr_set = attr_set & attr_mask, .attr_clr = attr_clr & attr_mask, - .mm_ops = pgt->mm_ops, }; struct kvm_pgtable_walker walker = { .cb = stage2_attr_walker, .arg = &data, - .flags = KVM_PGTABLE_WALK_LEAF, + .flags = flags | KVM_PGTABLE_WALK_LEAF, }; ret = kvm_pgtable_walk(pgt, addr, size, &walker); @@ -1082,14 +1088,14 @@ 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, NULL); + NULL, NULL, 0); } kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr) { kvm_pte_t pte = 0; stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0, - &pte, NULL); + &pte, NULL, 0); dsb(ishst); return pte; } @@ -1098,7 +1104,7 @@ kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr) { kvm_pte_t pte = 0; stage2_update_leaf_attrs(pgt, addr, 1, 0, KVM_PTE_LEAF_ATTR_LO_S2_AF, - &pte, NULL); + &pte, NULL, 0); /* * "But where's the TLBI?!", you scream. * "Over in the core code", I sigh. @@ -1111,7 +1117,7 @@ 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_pte_t pte = 0; - stage2_update_leaf_attrs(pgt, addr, 1, 0, 0, &pte, NULL); + stage2_update_leaf_attrs(pgt, addr, 1, 0, 0, &pte, NULL, 0); return pte & KVM_PTE_LEAF_ATTR_LO_S2_AF; } @@ -1134,26 +1140,25 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, 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, &level); + ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, + KVM_PGTABLE_WALK_SHARED); if (!ret) kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, pgt->mmu, addr, level); 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) +static int stage2_flush_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) { - struct kvm_pgtable *pgt = arg; + struct kvm_pgtable *pgt = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; - kvm_pte_t pte = *ptep; - if (!kvm_pte_valid(pte) || !stage2_pte_cacheable(pgt, pte)) + if (!kvm_pte_valid(ctx->old) || !stage2_pte_cacheable(pgt, ctx->old)) return 0; if (mm_ops->dcache_clean_inval_poc) - mm_ops->dcache_clean_inval_poc(kvm_pte_follow(pte, mm_ops), - kvm_granule_size(level)); + mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops), + kvm_granule_size(ctx->level)); return 0; } @@ -1184,7 +1189,7 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0; pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE; - pgt->pgd = mm_ops->zalloc_pages_exact(pgd_sz); + pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_pages_exact(pgd_sz); if (!pgt->pgd) return -ENOMEM; @@ -1200,20 +1205,27 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, return 0; } -static int stage2_free_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag, - void * const arg) +size_t kvm_pgtable_stage2_pgd_size(u64 vtcr) +{ + u32 ia_bits = VTCR_EL2_IPA(vtcr); + u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr); + u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0; + + return kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE; +} + +static int stage2_free_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) { - struct kvm_pgtable_mm_ops *mm_ops = arg; - kvm_pte_t pte = *ptep; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; - if (!stage2_pte_is_counted(pte)) + if (!stage2_pte_is_counted(ctx->old)) return 0; - mm_ops->put_page(ptep); + mm_ops->put_page(ctx->ptep); - if (kvm_pte_table(pte, level)) - mm_ops->put_page(kvm_pte_follow(pte, mm_ops)); + if (kvm_pte_table(ctx->old, ctx->level)) + mm_ops->put_page(kvm_pte_follow(ctx->old, mm_ops)); return 0; } @@ -1225,11 +1237,33 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) .cb = stage2_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, - .arg = pgt->mm_ops, }; WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE; - pgt->mm_ops->free_pages_exact(pgt->pgd, pgd_sz); + pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz); pgt->pgd = NULL; } + +void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level) +{ + kvm_pteref_t ptep = (kvm_pteref_t)pgtable; + struct kvm_pgtable_walker walker = { + .cb = stage2_free_walker, + .flags = KVM_PGTABLE_WALK_LEAF | + KVM_PGTABLE_WALK_TABLE_POST, + }; + struct kvm_pgtable_walk_data data = { + .walker = &walker, + + /* + * At this point the IPA really doesn't matter, as the page + * table being traversed has already been removed from the stage + * 2. Set an appropriate range to cover the entire page table. + */ + .addr = 0, + .end = kvm_granule_size(level), + }; + + WARN_ON(__kvm_pgtable_walk(&data, mm_ops, ptep, level + 1)); +} diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile index 96bec0ecf9dd..3b9e5464b5b3 100644 --- a/arch/arm64/kvm/hyp/vhe/Makefile +++ b/arch/arm64/kvm/hyp/vhe/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # -# Makefile for Kernel-based Virtual Machine module, HYP/nVHE part +# Makefile for Kernel-based Virtual Machine module, HYP/VHE part # asflags-y := -D__KVM_VHE_HYPERVISOR__ diff --git a/arch/arm64/kvm/irq.h b/arch/arm64/kvm/irq.h deleted file mode 100644 index 0d257de42c10..000000000000 --- a/arch/arm64/kvm/irq.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * irq.h: in kernel interrupt controller related definitions - * Copyright (c) 2016 Red Hat, Inc. - * - * This header is included by irqchip.c. However, on ARM, interrupt - * controller declarations are located in include/kvm/arm_vgic.h since - * they are mostly shared between arm and arm64. - */ - -#ifndef __IRQ_H -#define __IRQ_H - -#include <kvm/arm_vgic.h> - -#endif diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 60ee3d9f01f8..31d7fa4c7c14 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -128,6 +128,25 @@ static void kvm_s2_free_pages_exact(void *virt, size_t size) free_pages_exact(virt, size); } +static struct kvm_pgtable_mm_ops kvm_s2_mm_ops; + +static void stage2_free_removed_table_rcu_cb(struct rcu_head *head) +{ + struct page *page = container_of(head, struct page, rcu_head); + void *pgtable = page_to_virt(page); + u32 level = page_private(page); + + kvm_pgtable_stage2_free_removed(&kvm_s2_mm_ops, pgtable, level); +} + +static void stage2_free_removed_table(void *addr, u32 level) +{ + struct page *page = virt_to_page(addr); + + set_page_private(page, (unsigned long)level); + call_rcu(&page->rcu_head, stage2_free_removed_table_rcu_cb); +} + static void kvm_host_get_page(void *addr) { get_page(virt_to_page(addr)); @@ -640,8 +659,8 @@ static struct kvm_pgtable_mm_ops kvm_user_mm_ops = { static int get_user_mapping_size(struct kvm *kvm, u64 addr) { struct kvm_pgtable pgt = { - .pgd = (kvm_pte_t *)kvm->mm->pgd, - .ia_bits = VA_BITS, + .pgd = (kvm_pteref_t)kvm->mm->pgd, + .ia_bits = vabits_actual, .start_level = (KVM_PGTABLE_MAX_LEVELS - CONFIG_PGTABLE_LEVELS), .mm_ops = &kvm_user_mm_ops, @@ -662,6 +681,7 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = { .zalloc_page = stage2_memcache_zalloc_page, .zalloc_pages_exact = kvm_s2_zalloc_pages_exact, .free_pages_exact = kvm_s2_free_pages_exact, + .free_removed_table = stage2_free_removed_table, .get_page = kvm_host_get_page, .put_page = kvm_s2_put_page, .page_count = kvm_host_page_count, @@ -675,15 +695,42 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = { * kvm_init_stage2_mmu - Initialise a S2 MMU structure * @kvm: The pointer to the KVM structure * @mmu: The pointer to the s2 MMU structure + * @type: The machine type of the virtual machine * * Allocates only the stage-2 HW PGD level table(s). * Note we don't need locking here as this is only called when the VM is * created, which can only be done once. */ -int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu) +int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type) { + u32 kvm_ipa_limit = get_kvm_ipa_limit(); int cpu, err; struct kvm_pgtable *pgt; + u64 mmfr0, mmfr1; + u32 phys_shift; + + if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK) + return -EINVAL; + + phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type); + if (is_protected_kvm_enabled()) { + phys_shift = kvm_ipa_limit; + } else if (phys_shift) { + if (phys_shift > kvm_ipa_limit || + phys_shift < ARM64_MIN_PARANGE_BITS) + return -EINVAL; + } else { + phys_shift = KVM_PHYS_SHIFT; + if (phys_shift > kvm_ipa_limit) { + pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n", + current->comm); + return -EINVAL; + } + } + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); + kvm->arch.vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift); if (mmu->pgt != NULL) { kvm_err("kvm_arch already initialized?\n"); @@ -807,6 +854,32 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu) } } +static void hyp_mc_free_fn(void *addr, void *unused) +{ + free_page((unsigned long)addr); +} + +static void *hyp_mc_alloc_fn(void *unused) +{ + return (void *)__get_free_page(GFP_KERNEL_ACCOUNT); +} + +void free_hyp_memcache(struct kvm_hyp_memcache *mc) +{ + if (is_protected_kvm_enabled()) + __free_hyp_memcache(mc, hyp_mc_free_fn, + kvm_host_va, NULL); +} + +int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages) +{ + if (!is_protected_kvm_enabled()) + return 0; + + return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn, + kvm_host_pa, NULL); +} + /** * kvm_phys_addr_ioremap - map a device range to guest IPA * @@ -841,7 +914,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, write_lock(&kvm->mmu_lock); ret = kvm_pgtable_stage2_map(pgt, addr, PAGE_SIZE, pa, prot, - &cache); + &cache, 0); write_unlock(&kvm->mmu_lock); if (ret) break; @@ -1091,32 +1164,26 @@ static int get_vma_page_shift(struct vm_area_struct *vma, unsigned long hva) * - mmap_lock protects between a VM faulting a page in and the VMM performing * an mprotect() to add VM_MTE */ -static int sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn, - unsigned long size) +static void sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn, + unsigned long size) { unsigned long i, nr_pages = size >> PAGE_SHIFT; - struct page *page; + struct page *page = pfn_to_page(pfn); if (!kvm_has_mte(kvm)) - return 0; - - /* - * pfn_to_online_page() is used to reject ZONE_DEVICE pages - * that may not support tags. - */ - page = pfn_to_online_page(pfn); - - if (!page) - return -EFAULT; + return; for (i = 0; i < nr_pages; i++, page++) { - if (!test_bit(PG_mte_tagged, &page->flags)) { + if (try_page_mte_tagging(page)) { mte_clear_page_tags(page_address(page)); - set_bit(PG_mte_tagged, &page->flags); + set_page_mte_tagged(page); } } +} - return 0; +static bool kvm_vma_mte_allowed(struct vm_area_struct *vma) +{ + return vma->vm_flags & VM_MTE_ALLOWED; } static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, @@ -1127,7 +1194,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, bool write_fault, writable, force_pte = false; bool exec_fault; bool device = false; - bool shared; unsigned long mmu_seq; struct kvm *kvm = vcpu->kvm; struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; @@ -1136,7 +1202,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, gfn_t gfn; kvm_pfn_t pfn; bool logging_active = memslot_is_logging(memslot); - bool use_read_lock = false; unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu); unsigned long vma_pagesize, fault_granule; enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R; @@ -1171,14 +1236,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (logging_active) { force_pte = true; vma_shift = PAGE_SHIFT; - use_read_lock = (fault_status == FSC_PERM && write_fault && - fault_granule == PAGE_SIZE); } else { vma_shift = get_vma_page_shift(vma, hva); } - shared = (vma->vm_flags & VM_SHARED); - switch (vma_shift) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SHIFT: @@ -1239,7 +1300,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, */ smp_rmb(); - pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, + pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL, write_fault, &writable, NULL); if (pfn == KVM_PFN_ERR_HWPOISON) { kvm_send_hwpoison_signal(hva, vma_shift); @@ -1271,15 +1332,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (exec_fault && device) return -ENOEXEC; - /* - * To reduce MMU contentions and enhance concurrency during dirty - * logging dirty logging, only acquire read lock for permission - * relaxation. - */ - if (use_read_lock) - read_lock(&kvm->mmu_lock); - else - write_lock(&kvm->mmu_lock); + read_lock(&kvm->mmu_lock); pgt = vcpu->arch.hw_mmu->pgt; if (mmu_invalidate_retry(kvm, mmu_seq)) goto out_unlock; @@ -1298,13 +1351,13 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, } if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) { - /* Check the VMM hasn't introduced a new VM_SHARED VMA */ - if (!shared) - ret = sanitise_mte_tags(kvm, pfn, vma_pagesize); - else + /* Check the VMM hasn't introduced a new disallowed VMA */ + if (kvm_vma_mte_allowed(vma)) { + sanitise_mte_tags(kvm, pfn, vma_pagesize); + } else { ret = -EFAULT; - if (ret) goto out_unlock; + } } if (writable) @@ -1323,15 +1376,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * permissions only if vma_pagesize equals fault_granule. Otherwise, * kvm_pgtable_stage2_map() should be called to change block size. */ - if (fault_status == FSC_PERM && vma_pagesize == fault_granule) { + if (fault_status == FSC_PERM && vma_pagesize == fault_granule) ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot); - } else { - WARN_ONCE(use_read_lock, "Attempted stage-2 map outside of write lock\n"); - + else ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize, __pfn_to_phys(pfn), prot, - memcache); - } + memcache, KVM_PGTABLE_WALK_SHARED); /* Mark the page dirty only if the fault is handled successfully */ if (writable && !ret) { @@ -1340,10 +1390,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, } out_unlock: - if (use_read_lock) - read_unlock(&kvm->mmu_lock); - else - write_unlock(&kvm->mmu_lock); + read_unlock(&kvm->mmu_lock); kvm_set_pfn_accessed(pfn); kvm_release_pfn_clean(pfn); return ret != -EAGAIN ? ret : 0; @@ -1526,15 +1573,18 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { kvm_pfn_t pfn = pte_pfn(range->pte); - int ret; if (!kvm->arch.mmu.pgt) return false; WARN_ON(range->end - range->start != 1); - ret = sanitise_mte_tags(kvm, pfn, PAGE_SIZE); - if (ret) + /* + * If the page isn't tagged, defer to user_mem_abort() for sanitising + * the MTE tags. The S2 pte should have been unmapped by + * mmu_notifier_invalidate_range_end(). + */ + if (kvm_has_mte(kvm) && !page_mte_tagged(pfn_to_page(pfn))) return false; /* @@ -1549,7 +1599,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) */ kvm_pgtable_stage2_map(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT, PAGE_SIZE, __pfn_to_phys(pfn), - KVM_PGTABLE_PROT_R, NULL); + KVM_PGTABLE_PROT_R, NULL, 0); return false; } @@ -1618,6 +1668,8 @@ static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = { int kvm_mmu_init(u32 *hyp_va_bits) { int err; + u32 idmap_bits; + u32 kernel_bits; hyp_idmap_start = __pa_symbol(__hyp_idmap_text_start); hyp_idmap_start = ALIGN_DOWN(hyp_idmap_start, PAGE_SIZE); @@ -1631,7 +1683,31 @@ int kvm_mmu_init(u32 *hyp_va_bits) */ BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK); - *hyp_va_bits = 64 - ((idmap_t0sz & TCR_T0SZ_MASK) >> TCR_T0SZ_OFFSET); + /* + * The ID map may be configured to use an extended virtual address + * range. This is only the case if system RAM is out of range for the + * currently configured page size and VA_BITS_MIN, in which case we will + * also need the extended virtual range for the HYP ID map, or we won't + * be able to enable the EL2 MMU. + * + * However, in some cases the ID map may be configured for fewer than + * the number of VA bits used by the regular kernel stage 1. This + * happens when VA_BITS=52 and the kernel image is placed in PA space + * below 48 bits. + * + * At EL2, there is only one TTBR register, and we can't switch between + * translation tables *and* update TCR_EL2.T0SZ at the same time. Bottom + * line: we need to use the extended range with *both* our translation + * tables. + * + * So use the maximum of the idmap VA bits and the regular kernel stage + * 1 VA bits to assure that the hypervisor can both ID map its code page + * and map any kernel memory. + */ + idmap_bits = 64 - ((idmap_t0sz & TCR_T0SZ_MASK) >> TCR_T0SZ_OFFSET); + kernel_bits = vabits_actual; + *hyp_va_bits = max(idmap_bits, kernel_bits); + kvm_debug("Using %u-bit virtual addresses at EL2\n", *hyp_va_bits); kvm_debug("IDMAP page: %lx\n", hyp_idmap_start); kvm_debug("HYP VA range: %lx:%lx\n", @@ -1740,12 +1816,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (!vma) break; - /* - * VM_SHARED mappings are not allowed with MTE to avoid races - * when updating the PG_mte_tagged page flag, see - * sanitise_mte_tags for more details. - */ - if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED) { + if (kvm_has_mte(kvm) && !kvm_vma_mte_allowed(vma)) { ret = -EINVAL; break; } diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c index ebecb7c045f4..cf56958b1492 100644 --- a/arch/arm64/kvm/pkvm.c +++ b/arch/arm64/kvm/pkvm.c @@ -6,6 +6,7 @@ #include <linux/kvm_host.h> #include <linux/memblock.h> +#include <linux/mutex.h> #include <linux/sort.h> #include <asm/kvm_pkvm.h> @@ -53,7 +54,7 @@ static int __init register_memblock_regions(void) void __init kvm_hyp_reserve(void) { - u64 nr_pages, prev, hyp_mem_pages = 0; + u64 hyp_mem_pages = 0; int ret; if (!is_hyp_mode_available() || is_kernel_in_hyp_mode()) @@ -71,21 +72,8 @@ void __init kvm_hyp_reserve(void) hyp_mem_pages += hyp_s1_pgtable_pages(); hyp_mem_pages += host_s2_pgtable_pages(); - - /* - * The hyp_vmemmap needs to be backed by pages, but these pages - * themselves need to be present in the vmemmap, so compute the number - * of pages needed by looking for a fixed point. - */ - nr_pages = 0; - do { - prev = nr_pages; - nr_pages = hyp_mem_pages + prev; - nr_pages = DIV_ROUND_UP(nr_pages * STRUCT_HYP_PAGE_SIZE, - PAGE_SIZE); - nr_pages += __hyp_pgtable_max_pages(nr_pages); - } while (nr_pages != prev); - hyp_mem_pages += nr_pages; + hyp_mem_pages += hyp_vm_table_pages(); + hyp_mem_pages += hyp_vmemmap_pages(STRUCT_HYP_PAGE_SIZE); /* * Try to allocate a PMD-aligned region to reduce TLB pressure once @@ -107,3 +95,121 @@ void __init kvm_hyp_reserve(void) kvm_info("Reserved %lld MiB at 0x%llx\n", hyp_mem_size >> 20, hyp_mem_base); } + +/* + * Allocates and donates memory for hypervisor VM structs at EL2. + * + * Allocates space for the VM state, which includes the hyp vm as well as + * the hyp vcpus. + * + * Stores an opaque handler in the kvm struct for future reference. + * + * Return 0 on success, negative error code on failure. + */ +static int __pkvm_create_hyp_vm(struct kvm *host_kvm) +{ + size_t pgd_sz, hyp_vm_sz, hyp_vcpu_sz; + struct kvm_vcpu *host_vcpu; + pkvm_handle_t handle; + void *pgd, *hyp_vm; + unsigned long idx; + int ret; + + if (host_kvm->created_vcpus < 1) + return -EINVAL; + + pgd_sz = kvm_pgtable_stage2_pgd_size(host_kvm->arch.vtcr); + + /* + * The PGD pages will be reclaimed using a hyp_memcache which implies + * page granularity. So, use alloc_pages_exact() to get individual + * refcounts. + */ + pgd = alloc_pages_exact(pgd_sz, GFP_KERNEL_ACCOUNT); + if (!pgd) + return -ENOMEM; + + /* Allocate memory to donate to hyp for vm and vcpu pointers. */ + hyp_vm_sz = PAGE_ALIGN(size_add(PKVM_HYP_VM_SIZE, + size_mul(sizeof(void *), + host_kvm->created_vcpus))); + hyp_vm = alloc_pages_exact(hyp_vm_sz, GFP_KERNEL_ACCOUNT); + if (!hyp_vm) { + ret = -ENOMEM; + goto free_pgd; + } + + /* Donate the VM memory to hyp and let hyp initialize it. */ + ret = kvm_call_hyp_nvhe(__pkvm_init_vm, host_kvm, hyp_vm, pgd); + if (ret < 0) + goto free_vm; + + handle = ret; + + host_kvm->arch.pkvm.handle = handle; + + /* Donate memory for the vcpus at hyp and initialize it. */ + hyp_vcpu_sz = PAGE_ALIGN(PKVM_HYP_VCPU_SIZE); + kvm_for_each_vcpu(idx, host_vcpu, host_kvm) { + void *hyp_vcpu; + + /* Indexing of the vcpus to be sequential starting at 0. */ + if (WARN_ON(host_vcpu->vcpu_idx != idx)) { + ret = -EINVAL; + goto destroy_vm; + } + + hyp_vcpu = alloc_pages_exact(hyp_vcpu_sz, GFP_KERNEL_ACCOUNT); + if (!hyp_vcpu) { + ret = -ENOMEM; + goto destroy_vm; + } + + ret = kvm_call_hyp_nvhe(__pkvm_init_vcpu, handle, host_vcpu, + hyp_vcpu); + if (ret) { + free_pages_exact(hyp_vcpu, hyp_vcpu_sz); + goto destroy_vm; + } + } + + return 0; + +destroy_vm: + pkvm_destroy_hyp_vm(host_kvm); + return ret; +free_vm: + free_pages_exact(hyp_vm, hyp_vm_sz); +free_pgd: + free_pages_exact(pgd, pgd_sz); + return ret; +} + +int pkvm_create_hyp_vm(struct kvm *host_kvm) +{ + int ret = 0; + + mutex_lock(&host_kvm->lock); + if (!host_kvm->arch.pkvm.handle) + ret = __pkvm_create_hyp_vm(host_kvm); + mutex_unlock(&host_kvm->lock); + + return ret; +} + +void pkvm_destroy_hyp_vm(struct kvm *host_kvm) +{ + if (host_kvm->arch.pkvm.handle) { + WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm, + host_kvm->arch.pkvm.handle)); + } + + host_kvm->arch.pkvm.handle = 0; + free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc); +} + +int pkvm_init_host_vm(struct kvm *host_kvm) +{ + mutex_init(&host_kvm->lock); + return 0; +} diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 0003c7d37533..24908400e190 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -15,16 +15,25 @@ #include <kvm/arm_pmu.h> #include <kvm/arm_vgic.h> +#define PERF_ATTR_CFG1_COUNTER_64BIT BIT(0) + DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available); static LIST_HEAD(arm_pmus); static DEFINE_MUTEX(arm_pmus_lock); -static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx); -static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx); -static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc); +static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc); +static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc); + +static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc) +{ + return container_of(pmc, struct kvm_vcpu, arch.pmu.pmc[pmc->idx]); +} -#define PERF_ATTR_CFG1_KVM_PMU_CHAINED 0x1 +static struct kvm_pmc *kvm_vcpu_idx_to_pmc(struct kvm_vcpu *vcpu, int cnt_idx) +{ + return &vcpu->arch.pmu.pmc[cnt_idx]; +} static u32 kvm_pmu_event_mask(struct kvm *kvm) { @@ -47,113 +56,46 @@ static u32 kvm_pmu_event_mask(struct kvm *kvm) } /** - * kvm_pmu_idx_is_64bit - determine if select_idx is a 64bit counter - * @vcpu: The vcpu pointer - * @select_idx: The counter index + * kvm_pmc_is_64bit - determine if counter is 64bit + * @pmc: counter context */ -static bool kvm_pmu_idx_is_64bit(struct kvm_vcpu *vcpu, u64 select_idx) +static bool kvm_pmc_is_64bit(struct kvm_pmc *pmc) { - return (select_idx == ARMV8_PMU_CYCLE_IDX && - __vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_LC); + return (pmc->idx == ARMV8_PMU_CYCLE_IDX || + kvm_pmu_is_3p5(kvm_pmc_to_vcpu(pmc))); } -static struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc) +static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc) { - struct kvm_pmu *pmu; - struct kvm_vcpu_arch *vcpu_arch; + u64 val = __vcpu_sys_reg(kvm_pmc_to_vcpu(pmc), PMCR_EL0); - pmc -= pmc->idx; - pmu = container_of(pmc, struct kvm_pmu, pmc[0]); - vcpu_arch = container_of(pmu, struct kvm_vcpu_arch, pmu); - return container_of(vcpu_arch, struct kvm_vcpu, arch); + return (pmc->idx < ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LP)) || + (pmc->idx == ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LC)); } -/** - * kvm_pmu_pmc_is_chained - determine if the pmc is chained - * @pmc: The PMU counter pointer - */ -static bool kvm_pmu_pmc_is_chained(struct kvm_pmc *pmc) +static bool kvm_pmu_counter_can_chain(struct kvm_pmc *pmc) { - struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); - - return test_bit(pmc->idx >> 1, vcpu->arch.pmu.chained); + return (!(pmc->idx & 1) && (pmc->idx + 1) < ARMV8_PMU_CYCLE_IDX && + !kvm_pmc_has_64bit_overflow(pmc)); } -/** - * kvm_pmu_idx_is_high_counter - determine if select_idx is a high/low counter - * @select_idx: The counter index - */ -static bool kvm_pmu_idx_is_high_counter(u64 select_idx) -{ - return select_idx & 0x1; -} - -/** - * kvm_pmu_get_canonical_pmc - obtain the canonical pmc - * @pmc: The PMU counter pointer - * - * When a pair of PMCs are chained together we use the low counter (canonical) - * to hold the underlying perf event. - */ -static struct kvm_pmc *kvm_pmu_get_canonical_pmc(struct kvm_pmc *pmc) -{ - if (kvm_pmu_pmc_is_chained(pmc) && - kvm_pmu_idx_is_high_counter(pmc->idx)) - return pmc - 1; - - return pmc; -} -static struct kvm_pmc *kvm_pmu_get_alternate_pmc(struct kvm_pmc *pmc) +static u32 counter_index_to_reg(u64 idx) { - if (kvm_pmu_idx_is_high_counter(pmc->idx)) - return pmc - 1; - else - return pmc + 1; + return (idx == ARMV8_PMU_CYCLE_IDX) ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + idx; } -/** - * kvm_pmu_idx_has_chain_evtype - determine if the event type is chain - * @vcpu: The vcpu pointer - * @select_idx: The counter index - */ -static bool kvm_pmu_idx_has_chain_evtype(struct kvm_vcpu *vcpu, u64 select_idx) +static u32 counter_index_to_evtreg(u64 idx) { - u64 eventsel, reg; - - select_idx |= 0x1; - - if (select_idx == ARMV8_PMU_CYCLE_IDX) - return false; - - reg = PMEVTYPER0_EL0 + select_idx; - eventsel = __vcpu_sys_reg(vcpu, reg) & kvm_pmu_event_mask(vcpu->kvm); - - return eventsel == ARMV8_PMUV3_PERFCTR_CHAIN; + return (idx == ARMV8_PMU_CYCLE_IDX) ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + idx; } -/** - * kvm_pmu_get_pair_counter_value - get PMU counter value - * @vcpu: The vcpu pointer - * @pmc: The PMU counter pointer - */ -static u64 kvm_pmu_get_pair_counter_value(struct kvm_vcpu *vcpu, - struct kvm_pmc *pmc) +static u64 kvm_pmu_get_pmc_value(struct kvm_pmc *pmc) { - u64 counter, counter_high, reg, enabled, running; - - if (kvm_pmu_pmc_is_chained(pmc)) { - pmc = kvm_pmu_get_canonical_pmc(pmc); - reg = PMEVCNTR0_EL0 + pmc->idx; + struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); + u64 counter, reg, enabled, running; - counter = __vcpu_sys_reg(vcpu, reg); - counter_high = __vcpu_sys_reg(vcpu, reg + 1); - - counter = lower_32_bits(counter) | (counter_high << 32); - } else { - reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX) - ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx; - counter = __vcpu_sys_reg(vcpu, reg); - } + reg = counter_index_to_reg(pmc->idx); + counter = __vcpu_sys_reg(vcpu, reg); /* * The real counter value is equal to the value of counter register plus @@ -163,6 +105,9 @@ static u64 kvm_pmu_get_pair_counter_value(struct kvm_vcpu *vcpu, counter += perf_event_read_value(pmc->perf_event, &enabled, &running); + if (!kvm_pmc_is_64bit(pmc)) + counter = lower_32_bits(counter); + return counter; } @@ -173,22 +118,37 @@ static u64 kvm_pmu_get_pair_counter_value(struct kvm_vcpu *vcpu, */ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) { - u64 counter; - struct kvm_pmu *pmu = &vcpu->arch.pmu; - struct kvm_pmc *pmc = &pmu->pmc[select_idx]; - if (!kvm_vcpu_has_pmu(vcpu)) return 0; - counter = kvm_pmu_get_pair_counter_value(vcpu, pmc); + return kvm_pmu_get_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx)); +} - if (kvm_pmu_pmc_is_chained(pmc) && - kvm_pmu_idx_is_high_counter(select_idx)) - counter = upper_32_bits(counter); - else if (select_idx != ARMV8_PMU_CYCLE_IDX) - counter = lower_32_bits(counter); +static void kvm_pmu_set_pmc_value(struct kvm_pmc *pmc, u64 val, bool force) +{ + struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); + u64 reg; - return counter; + kvm_pmu_release_perf_event(pmc); + + reg = counter_index_to_reg(pmc->idx); + + if (vcpu_mode_is_32bit(vcpu) && pmc->idx != ARMV8_PMU_CYCLE_IDX && + !force) { + /* + * Even with PMUv3p5, AArch32 cannot write to the top + * 32bit of the counters. The only possible course of + * action is to use PMCR.P, which will reset them to + * 0 (the only use of the 'force' parameter). + */ + val = __vcpu_sys_reg(vcpu, reg) & GENMASK(63, 32); + val |= lower_32_bits(val); + } + + __vcpu_sys_reg(vcpu, reg) = val; + + /* Recreate the perf event to reflect the updated sample_period */ + kvm_pmu_create_perf_event(pmc); } /** @@ -199,17 +159,10 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) */ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) { - u64 reg; - if (!kvm_vcpu_has_pmu(vcpu)) return; - reg = (select_idx == ARMV8_PMU_CYCLE_IDX) - ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx; - __vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx); - - /* Recreate the perf event to reflect the updated sample_period */ - kvm_pmu_create_perf_event(vcpu, select_idx); + kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx), val, false); } /** @@ -218,7 +171,6 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) */ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) { - pmc = kvm_pmu_get_canonical_pmc(pmc); if (pmc->perf_event) { perf_event_disable(pmc->perf_event); perf_event_release_kernel(pmc->perf_event); @@ -232,29 +184,20 @@ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) * * If this counter has been configured to monitor some event, release it here. */ -static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc) +static void kvm_pmu_stop_counter(struct kvm_pmc *pmc) { - u64 counter, reg, val; + struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); + u64 reg, val; - pmc = kvm_pmu_get_canonical_pmc(pmc); if (!pmc->perf_event) return; - counter = kvm_pmu_get_pair_counter_value(vcpu, pmc); + val = kvm_pmu_get_pmc_value(pmc); - if (pmc->idx == ARMV8_PMU_CYCLE_IDX) { - reg = PMCCNTR_EL0; - val = counter; - } else { - reg = PMEVCNTR0_EL0 + pmc->idx; - val = lower_32_bits(counter); - } + reg = counter_index_to_reg(pmc->idx); __vcpu_sys_reg(vcpu, reg) = val; - if (kvm_pmu_pmc_is_chained(pmc)) - __vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter); - kvm_pmu_release_perf_event(pmc); } @@ -280,13 +223,10 @@ void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) { unsigned long mask = kvm_pmu_valid_counter_mask(vcpu); - struct kvm_pmu *pmu = &vcpu->arch.pmu; int i; for_each_set_bit(i, &mask, 32) - kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]); - - bitmap_zero(vcpu->arch.pmu.chained, ARMV8_PMU_MAX_COUNTER_PAIRS); + kvm_pmu_stop_counter(kvm_vcpu_idx_to_pmc(vcpu, i)); } /** @@ -297,10 +237,9 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) { int i; - struct kvm_pmu *pmu = &vcpu->arch.pmu; for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) - kvm_pmu_release_perf_event(&pmu->pmc[i]); + kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, i)); irq_work_sync(&vcpu->arch.pmu.overflow_work); } @@ -325,9 +264,6 @@ u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu) void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) { int i; - struct kvm_pmu *pmu = &vcpu->arch.pmu; - struct kvm_pmc *pmc; - if (!kvm_vcpu_has_pmu(vcpu)) return; @@ -335,17 +271,16 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) return; for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { + struct kvm_pmc *pmc; + if (!(val & BIT(i))) continue; - pmc = &pmu->pmc[i]; - - /* A change in the enable state may affect the chain state */ - kvm_pmu_update_pmc_chained(vcpu, i); - kvm_pmu_create_perf_event(vcpu, i); + pmc = kvm_vcpu_idx_to_pmc(vcpu, i); - /* At this point, pmc must be the canonical */ - if (pmc->perf_event) { + if (!pmc->perf_event) { + kvm_pmu_create_perf_event(pmc); + } else { perf_event_enable(pmc->perf_event); if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) kvm_debug("fail to enable perf event\n"); @@ -363,23 +298,18 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) { int i; - struct kvm_pmu *pmu = &vcpu->arch.pmu; - struct kvm_pmc *pmc; if (!kvm_vcpu_has_pmu(vcpu) || !val) return; for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { + struct kvm_pmc *pmc; + if (!(val & BIT(i))) continue; - pmc = &pmu->pmc[i]; - - /* A change in the enable state may affect the chain state */ - kvm_pmu_update_pmc_chained(vcpu, i); - kvm_pmu_create_perf_event(vcpu, i); + pmc = kvm_vcpu_idx_to_pmc(vcpu, i); - /* At this point, pmc must be the canonical */ if (pmc->perf_event) perf_event_disable(pmc->perf_event); } @@ -476,14 +406,69 @@ void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) static void kvm_pmu_perf_overflow_notify_vcpu(struct irq_work *work) { struct kvm_vcpu *vcpu; - struct kvm_pmu *pmu; - - pmu = container_of(work, struct kvm_pmu, overflow_work); - vcpu = kvm_pmc_to_vcpu(pmu->pmc); + vcpu = container_of(work, struct kvm_vcpu, arch.pmu.overflow_work); kvm_vcpu_kick(vcpu); } +/* + * Perform an increment on any of the counters described in @mask, + * generating the overflow if required, and propagate it as a chained + * event if possible. + */ +static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu, + unsigned long mask, u32 event) +{ + int i; + + if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) + return; + + /* Weed out disabled counters */ + mask &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); + + for_each_set_bit(i, &mask, ARMV8_PMU_CYCLE_IDX) { + struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i); + u64 type, reg; + + /* Filter on event type */ + type = __vcpu_sys_reg(vcpu, counter_index_to_evtreg(i)); + type &= kvm_pmu_event_mask(vcpu->kvm); + if (type != event) + continue; + + /* Increment this counter */ + reg = __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) + 1; + if (!kvm_pmc_is_64bit(pmc)) + reg = lower_32_bits(reg); + __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) = reg; + + /* No overflow? move on */ + if (kvm_pmc_has_64bit_overflow(pmc) ? reg : lower_32_bits(reg)) + continue; + + /* Mark overflow */ + __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i); + + if (kvm_pmu_counter_can_chain(pmc)) + kvm_pmu_counter_increment(vcpu, BIT(i + 1), + ARMV8_PMUV3_PERFCTR_CHAIN); + } +} + +/* Compute the sample period for a given counter value */ +static u64 compute_period(struct kvm_pmc *pmc, u64 counter) +{ + u64 val; + + if (kvm_pmc_is_64bit(pmc) && kvm_pmc_has_64bit_overflow(pmc)) + val = (-counter) & GENMASK(63, 0); + else + val = (-counter) & GENMASK(31, 0); + + return val; +} + /** * When the perf event overflows, set the overflow status and inform the vcpu. */ @@ -503,10 +488,7 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event, * Reset the sample period to the architectural limit, * i.e. the point where the counter overflows. */ - period = -(local64_read(&perf_event->count)); - - if (!kvm_pmu_idx_is_64bit(vcpu, pmc->idx)) - period &= GENMASK(31, 0); + period = compute_period(pmc, local64_read(&perf_event->count)); local64_set(&perf_event->hw.period_left, 0); perf_event->attr.sample_period = period; @@ -514,6 +496,10 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event, __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx); + if (kvm_pmu_counter_can_chain(pmc)) + kvm_pmu_counter_increment(vcpu, BIT(idx + 1), + ARMV8_PMUV3_PERFCTR_CHAIN); + if (kvm_pmu_overflow_status(vcpu)) { kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); @@ -533,50 +519,7 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event, */ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; - int i; - - if (!kvm_vcpu_has_pmu(vcpu)) - return; - - if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) - return; - - /* Weed out disabled counters */ - val &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); - - for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++) { - u64 type, reg; - - if (!(val & BIT(i))) - continue; - - /* PMSWINC only applies to ... SW_INC! */ - type = __vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i); - type &= kvm_pmu_event_mask(vcpu->kvm); - if (type != ARMV8_PMUV3_PERFCTR_SW_INCR) - continue; - - /* increment this even SW_INC counter */ - reg = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1; - reg = lower_32_bits(reg); - __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) = reg; - - if (reg) /* no overflow on the low part */ - continue; - - if (kvm_pmu_pmc_is_chained(&pmu->pmc[i])) { - /* increment the high counter */ - reg = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i + 1) + 1; - reg = lower_32_bits(reg); - __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i + 1) = reg; - if (!reg) /* mark overflow on the high counter */ - __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i + 1); - } else { - /* mark overflow on low counter */ - __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i); - } - } + kvm_pmu_counter_increment(vcpu, val, ARMV8_PMUV3_PERFCTR_SW_INCR); } /** @@ -591,6 +534,12 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) if (!kvm_vcpu_has_pmu(vcpu)) return; + /* Fixup PMCR_EL0 to reconcile the PMU version and the LP bit */ + if (!kvm_pmu_is_3p5(vcpu)) + val &= ~ARMV8_PMU_PMCR_LP; + + __vcpu_sys_reg(vcpu, PMCR_EL0) = val; + if (val & ARMV8_PMU_PMCR_E) { kvm_pmu_enable_counter_mask(vcpu, __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); @@ -606,49 +555,44 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) unsigned long mask = kvm_pmu_valid_counter_mask(vcpu); mask &= ~BIT(ARMV8_PMU_CYCLE_IDX); for_each_set_bit(i, &mask, 32) - kvm_pmu_set_counter_value(vcpu, i, 0); + kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true); } } -static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx) +static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc) { + struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); return (__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) && - (__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(select_idx)); + (__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx)); } /** * kvm_pmu_create_perf_event - create a perf event for a counter - * @vcpu: The vcpu pointer - * @select_idx: The number of selected counter + * @pmc: Counter context */ -static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx) +static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc) { + struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc); struct arm_pmu *arm_pmu = vcpu->kvm->arch.arm_pmu; - struct kvm_pmu *pmu = &vcpu->arch.pmu; - struct kvm_pmc *pmc; struct perf_event *event; struct perf_event_attr attr; - u64 eventsel, counter, reg, data; + u64 eventsel, reg, data; - /* - * For chained counters the event type and filtering attributes are - * obtained from the low/even counter. We also use this counter to - * determine if the event is enabled/disabled. - */ - pmc = kvm_pmu_get_canonical_pmc(&pmu->pmc[select_idx]); - - reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX) - ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + pmc->idx; + reg = counter_index_to_evtreg(pmc->idx); data = __vcpu_sys_reg(vcpu, reg); - kvm_pmu_stop_counter(vcpu, pmc); + kvm_pmu_stop_counter(pmc); if (pmc->idx == ARMV8_PMU_CYCLE_IDX) eventsel = ARMV8_PMUV3_PERFCTR_CPU_CYCLES; else eventsel = data & kvm_pmu_event_mask(vcpu->kvm); - /* Software increment event doesn't need to be backed by a perf event */ - if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR) + /* + * Neither SW increment nor chained events need to be backed + * by a perf event. + */ + if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR || + eventsel == ARMV8_PMUV3_PERFCTR_CHAIN) return; /* @@ -663,37 +607,25 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx) attr.type = arm_pmu->pmu.type; attr.size = sizeof(attr); attr.pinned = 1; - attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, pmc->idx); + attr.disabled = !kvm_pmu_counter_is_enabled(pmc); attr.exclude_user = data & ARMV8_PMU_EXCLUDE_EL0 ? 1 : 0; attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0; attr.exclude_hv = 1; /* Don't count EL2 events */ attr.exclude_host = 1; /* Don't count host events */ attr.config = eventsel; - counter = kvm_pmu_get_pair_counter_value(vcpu, pmc); - - if (kvm_pmu_pmc_is_chained(pmc)) { - /** - * The initial sample period (overflow count) of an event. For - * chained counters we only support overflow interrupts on the - * high counter. - */ - attr.sample_period = (-counter) & GENMASK(63, 0); - attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED; + /* + * If counting with a 64bit counter, advertise it to the perf + * code, carefully dealing with the initial sample period + * which also depends on the overflow. + */ + if (kvm_pmc_is_64bit(pmc)) + attr.config1 |= PERF_ATTR_CFG1_COUNTER_64BIT; - event = perf_event_create_kernel_counter(&attr, -1, current, - kvm_pmu_perf_overflow, - pmc + 1); - } else { - /* The initial sample period (overflow count) of an event. */ - if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx)) - attr.sample_period = (-counter) & GENMASK(63, 0); - else - attr.sample_period = (-counter) & GENMASK(31, 0); + attr.sample_period = compute_period(pmc, kvm_pmu_get_pmc_value(pmc)); - event = perf_event_create_kernel_counter(&attr, -1, current, + event = perf_event_create_kernel_counter(&attr, -1, current, kvm_pmu_perf_overflow, pmc); - } if (IS_ERR(event)) { pr_err_once("kvm: pmu event creation failed %ld\n", @@ -705,41 +637,6 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx) } /** - * kvm_pmu_update_pmc_chained - update chained bitmap - * @vcpu: The vcpu pointer - * @select_idx: The number of selected counter - * - * Update the chained bitmap based on the event type written in the - * typer register and the enable state of the odd register. - */ -static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx) -{ - struct kvm_pmu *pmu = &vcpu->arch.pmu; - struct kvm_pmc *pmc = &pmu->pmc[select_idx], *canonical_pmc; - bool new_state, old_state; - - old_state = kvm_pmu_pmc_is_chained(pmc); - new_state = kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx) && - kvm_pmu_counter_is_enabled(vcpu, pmc->idx | 0x1); - - if (old_state == new_state) - return; - - canonical_pmc = kvm_pmu_get_canonical_pmc(pmc); - kvm_pmu_stop_counter(vcpu, canonical_pmc); - if (new_state) { - /* - * During promotion from !chained to chained we must ensure - * the adjacent counter is stopped and its event destroyed - */ - kvm_pmu_stop_counter(vcpu, kvm_pmu_get_alternate_pmc(pmc)); - set_bit(pmc->idx >> 1, vcpu->arch.pmu.chained); - return; - } - clear_bit(pmc->idx >> 1, vcpu->arch.pmu.chained); -} - -/** * kvm_pmu_set_counter_event_type - set selected counter to monitor some event * @vcpu: The vcpu pointer * @data: The data guest writes to PMXEVTYPER_EL0 @@ -752,6 +649,7 @@ static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx) void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, u64 select_idx) { + struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, select_idx); u64 reg, mask; if (!kvm_vcpu_has_pmu(vcpu)) @@ -761,20 +659,19 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, mask &= ~ARMV8_PMU_EVTYPE_EVENT; mask |= kvm_pmu_event_mask(vcpu->kvm); - reg = (select_idx == ARMV8_PMU_CYCLE_IDX) - ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + select_idx; + reg = counter_index_to_evtreg(pmc->idx); __vcpu_sys_reg(vcpu, reg) = data & mask; - kvm_pmu_update_pmc_chained(vcpu, select_idx); - kvm_pmu_create_perf_event(vcpu, select_idx); + kvm_pmu_create_perf_event(pmc); } void kvm_host_pmu_init(struct arm_pmu *pmu) { struct arm_pmu_entry *entry; - if (pmu->pmuver == 0 || pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF) + if (pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_NI || + pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF) return; mutex_lock(&arm_pmus_lock); @@ -827,7 +724,7 @@ static struct arm_pmu *kvm_pmu_probe_armpmu(void) if (event->pmu) { pmu = to_arm_pmu(event->pmu); - if (pmu->pmuver == 0 || + if (pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_NI || pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF) pmu = NULL; } @@ -849,6 +746,8 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) if (!pmceid1) { val = read_sysreg(pmceid0_el0); + /* always support CHAIN */ + val |= BIT(ARMV8_PMUV3_PERFCTR_CHAIN); base = 0; } else { val = read_sysreg(pmceid1_el0); @@ -1150,3 +1049,14 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) return -ENXIO; } + +u8 kvm_arm_pmu_get_pmuver_limit(void) +{ + u64 tmp; + + tmp = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1); + tmp = cpuid_feature_cap_perfmon_field(tmp, + ID_AA64DFR0_EL1_PMUVer_SHIFT, + ID_AA64DFR0_EL1_PMUVer_V3P5); + return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp); +} diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 5ae18472205a..e0267f672b8a 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -395,32 +395,3 @@ int kvm_set_ipa_limit(void) return 0; } - -int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type) -{ - u64 mmfr0, mmfr1; - u32 phys_shift; - - if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK) - return -EINVAL; - - phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type); - if (phys_shift) { - if (phys_shift > kvm_ipa_limit || - phys_shift < ARM64_MIN_PARANGE_BITS) - return -EINVAL; - } else { - phys_shift = KVM_PHYS_SHIFT; - if (phys_shift > kvm_ipa_limit) { - pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n", - current->comm); - return -EINVAL; - } - } - - mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); - mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); - kvm->arch.vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift); - - return 0; -} diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 608e4f25161d..d5ee52d6bf73 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -639,22 +639,18 @@ static void reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { - u64 pmcr, val; + u64 pmcr; /* No PMU available, PMCR_EL0 may UNDEF... */ if (!kvm_arm_support_pmu_v3()) return; - pmcr = read_sysreg(pmcr_el0); - /* - * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN - * except PMCR.E resetting to zero. - */ - val = ((pmcr & ~ARMV8_PMU_PMCR_MASK) - | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E); + /* Only preserve PMCR_EL0.N, and reset the rest to 0 */ + pmcr = read_sysreg(pmcr_el0) & ARMV8_PMU_PMCR_N_MASK; if (!kvm_supports_32bit_el0()) - val |= ARMV8_PMU_PMCR_LC; - __vcpu_sys_reg(vcpu, r->reg) = val; + pmcr |= ARMV8_PMU_PMCR_LC; + + __vcpu_sys_reg(vcpu, r->reg) = pmcr; } static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags) @@ -697,13 +693,15 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return false; if (p->is_write) { - /* Only update writeable bits of PMCR */ + /* + * Only update writeable bits of PMCR (continuing into + * kvm_pmu_handle_pmcr() as well) + */ val = __vcpu_sys_reg(vcpu, PMCR_EL0); val &= ~ARMV8_PMU_PMCR_MASK; val |= p->regval & ARMV8_PMU_PMCR_MASK; if (!kvm_supports_32bit_el0()) val |= ARMV8_PMU_PMCR_LC; - __vcpu_sys_reg(vcpu, PMCR_EL0) = val; kvm_pmu_handle_pmcr(vcpu, val); kvm_vcpu_pmu_restore_guest(vcpu); } else { @@ -1062,6 +1060,40 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu, return true; } +static u8 vcpu_pmuver(const struct kvm_vcpu *vcpu) +{ + if (kvm_vcpu_has_pmu(vcpu)) + return vcpu->kvm->arch.dfr0_pmuver.imp; + + return vcpu->kvm->arch.dfr0_pmuver.unimp; +} + +static u8 perfmon_to_pmuver(u8 perfmon) +{ + switch (perfmon) { + case ID_DFR0_EL1_PerfMon_PMUv3: + return ID_AA64DFR0_EL1_PMUVer_IMP; + case ID_DFR0_EL1_PerfMon_IMPDEF: + return ID_AA64DFR0_EL1_PMUVer_IMP_DEF; + default: + /* Anything ARMv8.1+ and NI have the same value. For now. */ + return perfmon; + } +} + +static u8 pmuver_to_perfmon(u8 pmuver) +{ + switch (pmuver) { + case ID_AA64DFR0_EL1_PMUVer_IMP: + return ID_DFR0_EL1_PerfMon_PMUv3; + case ID_AA64DFR0_EL1_PMUVer_IMP_DEF: + return ID_DFR0_EL1_PerfMon_IMPDEF; + default: + /* Anything ARMv8.1+ and NI have the same value. For now. */ + return pmuver; + } +} + /* Read a sanitised cpufeature ID register by sys_reg_desc */ static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r) { @@ -1111,18 +1143,17 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r /* Limit debug to ARMv8.0 */ val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer); val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer), 6); - /* Limit guests to PMUv3 for ARMv8.4 */ - val = cpuid_feature_cap_perfmon_field(val, - ID_AA64DFR0_EL1_PMUVer_SHIFT, - kvm_vcpu_has_pmu(vcpu) ? ID_AA64DFR0_EL1_PMUVer_V3P4 : 0); + /* Set PMUver to the required version */ + val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer); + val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), + vcpu_pmuver(vcpu)); /* Hide SPE from guests */ val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMSVer); break; case SYS_ID_DFR0_EL1: - /* Limit guests to PMUv3 for ARMv8.4 */ - val = cpuid_feature_cap_perfmon_field(val, - ID_DFR0_EL1_PerfMon_SHIFT, - kvm_vcpu_has_pmu(vcpu) ? ID_DFR0_EL1_PerfMon_PMUv3p4 : 0); + val &= ~ARM64_FEATURE_MASK(ID_DFR0_EL1_PerfMon); + val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_DFR0_EL1_PerfMon), + pmuver_to_perfmon(vcpu_pmuver(vcpu))); break; } @@ -1222,6 +1253,85 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, return 0; } +static int set_id_aa64dfr0_el1(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd, + u64 val) +{ + u8 pmuver, host_pmuver; + bool valid_pmu; + + host_pmuver = kvm_arm_pmu_get_pmuver_limit(); + + /* + * Allow AA64DFR0_EL1.PMUver to be set from userspace as long + * as it doesn't promise more than what the HW gives us. We + * allow an IMPDEF PMU though, only if no PMU is supported + * (KVM backward compatibility handling). + */ + pmuver = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), val); + if ((pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF && pmuver > host_pmuver)) + return -EINVAL; + + valid_pmu = (pmuver != 0 && pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF); + + /* Make sure view register and PMU support do match */ + if (kvm_vcpu_has_pmu(vcpu) != valid_pmu) + return -EINVAL; + + /* We can only differ with PMUver, and anything else is an error */ + val ^= read_id_reg(vcpu, rd); + val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer); + if (val) + return -EINVAL; + + if (valid_pmu) + vcpu->kvm->arch.dfr0_pmuver.imp = pmuver; + else + vcpu->kvm->arch.dfr0_pmuver.unimp = pmuver; + + return 0; +} + +static int set_id_dfr0_el1(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd, + u64 val) +{ + u8 perfmon, host_perfmon; + bool valid_pmu; + + host_perfmon = pmuver_to_perfmon(kvm_arm_pmu_get_pmuver_limit()); + + /* + * Allow DFR0_EL1.PerfMon to be set from userspace as long as + * it doesn't promise more than what the HW gives us on the + * AArch64 side (as everything is emulated with that), and + * that this is a PMUv3. + */ + perfmon = FIELD_GET(ARM64_FEATURE_MASK(ID_DFR0_EL1_PerfMon), val); + if ((perfmon != ID_DFR0_EL1_PerfMon_IMPDEF && perfmon > host_perfmon) || + (perfmon != 0 && perfmon < ID_DFR0_EL1_PerfMon_PMUv3)) + return -EINVAL; + + valid_pmu = (perfmon != 0 && perfmon != ID_DFR0_EL1_PerfMon_IMPDEF); + + /* Make sure view register and PMU support do match */ + if (kvm_vcpu_has_pmu(vcpu) != valid_pmu) + return -EINVAL; + + /* We can only differ with PerfMon, and anything else is an error */ + val ^= read_id_reg(vcpu, rd); + val &= ~ARM64_FEATURE_MASK(ID_DFR0_EL1_PerfMon); + if (val) + return -EINVAL; + + if (valid_pmu) + vcpu->kvm->arch.dfr0_pmuver.imp = perfmon_to_pmuver(perfmon); + else + vcpu->kvm->arch.dfr0_pmuver.unimp = perfmon_to_pmuver(perfmon); + + return 0; +} + /* * cpufeature ID register user accessors * @@ -1443,7 +1553,9 @@ static const struct sys_reg_desc sys_reg_descs[] = { /* CRm=1 */ AA32_ID_SANITISED(ID_PFR0_EL1), AA32_ID_SANITISED(ID_PFR1_EL1), - AA32_ID_SANITISED(ID_DFR0_EL1), + { SYS_DESC(SYS_ID_DFR0_EL1), .access = access_id_reg, + .get_user = get_id_reg, .set_user = set_id_dfr0_el1, + .visibility = aa32_id_visibility, }, ID_HIDDEN(ID_AFR0_EL1), AA32_ID_SANITISED(ID_MMFR0_EL1), AA32_ID_SANITISED(ID_MMFR1_EL1), @@ -1483,7 +1595,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_UNALLOCATED(4,7), /* CRm=5 */ - ID_SANITISED(ID_AA64DFR0_EL1), + { SYS_DESC(SYS_ID_AA64DFR0_EL1), .access = access_id_reg, + .get_user = get_id_reg, .set_user = set_id_aa64dfr0_el1, }, ID_SANITISED(ID_AA64DFR1_EL1), ID_UNALLOCATED(5,2), ID_UNALLOCATED(5,3), diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 733b53055f97..94a666dd1443 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2743,6 +2743,7 @@ static int vgic_its_has_attr(struct kvm_device *dev, static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); + struct vgic_dist *dist = &kvm->arch.vgic; int ret = 0; if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */ @@ -2762,7 +2763,9 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) vgic_its_reset(kvm, its); break; case KVM_DEV_ARM_ITS_SAVE_TABLES: + dist->save_its_tables_in_progress = true; ret = abi->save_tables(its); + dist->save_its_tables_in_progress = false; break; case KVM_DEV_ARM_ITS_RESTORE_TABLES: ret = abi->restore_tables(its); @@ -2775,6 +2778,23 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) return ret; } +/* + * kvm_arch_allow_write_without_running_vcpu - allow writing guest memory + * without the running VCPU when dirty ring is enabled. + * + * The running VCPU is required to track dirty guest pages when dirty ring + * is enabled. Otherwise, the backup bitmap should be used to track the + * dirty guest pages. When vgic/its tables are being saved, the backup + * bitmap is used to track the dirty guest pages due to the missed running + * VCPU in the period. + */ +bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + + return dist->save_its_tables_in_progress; +} + static int vgic_its_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index 24913271e898..8dd5a8fe64b4 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -21,9 +21,12 @@ void copy_highpage(struct page *to, struct page *from) copy_page(kto, kfrom); - if (system_supports_mte() && test_bit(PG_mte_tagged, &from->flags)) { - set_bit(PG_mte_tagged, &to->flags); + if (system_supports_mte() && page_mte_tagged(from)) { + page_kasan_tag_reset(to); + /* It's a new page, shouldn't have been tagged yet */ + WARN_ON_ONCE(!try_page_mte_tagging(to)); mte_copy_page_tags(kto, kfrom); + set_page_mte_tagged(to); } } EXPORT_SYMBOL(copy_highpage); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 3eb2825d08cf..596f46dabe4e 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -943,6 +943,8 @@ struct page *alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, void tag_clear_highpage(struct page *page) { + /* Newly allocated page, shouldn't have been tagged yet */ + WARN_ON_ONCE(!try_page_mte_tagging(page)); mte_zero_clear_page_tags(page_address(page)); - set_bit(PG_mte_tagged, &page->flags); + set_page_mte_tagged(page); } diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c index bed803d8e158..cd508ba80ab1 100644 --- a/arch/arm64/mm/mteswap.c +++ b/arch/arm64/mm/mteswap.c @@ -24,7 +24,7 @@ int mte_save_tags(struct page *page) { void *tag_storage, *ret; - if (!test_bit(PG_mte_tagged, &page->flags)) + if (!page_mte_tagged(page)) return 0; tag_storage = mte_allocate_tag_storage(); @@ -46,21 +46,17 @@ int mte_save_tags(struct page *page) return 0; } -bool mte_restore_tags(swp_entry_t entry, struct page *page) +void mte_restore_tags(swp_entry_t entry, struct page *page) { void *tags = xa_load(&mte_pages, entry.val); if (!tags) - return false; + return; - /* - * Test PG_mte_tagged again in case it was racing with another - * set_pte_at(). - */ - if (!test_and_set_bit(PG_mte_tagged, &page->flags)) + if (try_page_mte_tagging(page)) { mte_restore_page_tags(page_address(page), tags); - - return true; + set_page_mte_tagged(page); + } } void mte_invalidate_tags(int type, pgoff_t offset) |