diff options
author | Marc Zyngier <maz@kernel.org> | 2022-12-05 17:22:55 +0300 |
---|---|---|
committer | Marc Zyngier <maz@kernel.org> | 2022-12-05 17:22:55 +0300 |
commit | fe8e3f44c58760f0779813938ed465b3297db1ac (patch) | |
tree | f0d529b2e7bf99b662134ac7b1dc180a21d0a3b8 | |
parent | a937f37d85f3347a1b6de69990fcd214ce882886 (diff) | |
parent | 5e806c5812e8012a83496cf96bdba266b3aec428 (diff) | |
download | linux-fe8e3f44c58760f0779813938ed465b3297db1ac.tar.xz |
Merge branch kvm-arm64/parallel-faults into kvmarm-master/next
* kvm-arm64/parallel-faults:
: .
: Parallel stage-2 fault handling, courtesy of Oliver Upton.
: From the cover letter:
:
: "Presently KVM only takes a read lock for stage 2 faults if it believes
: the fault can be fixed by relaxing permissions on a PTE (write unprotect
: for dirty logging). Otherwise, stage 2 faults grab the write lock, which
: predictably can pile up all the vCPUs in a sufficiently large VM.
:
: Like the TDP MMU for x86, this series loosens the locking around
: manipulations of the stage 2 page tables to allow parallel faults. RCU
: and atomics are exploited to safely build/destroy the stage 2 page
: tables in light of multiple software observers."
: .
KVM: arm64: Reject shared table walks in the hyp code
KVM: arm64: Don't acquire RCU read lock for exclusive table walks
KVM: arm64: Take a pointer to walker data in kvm_dereference_pteref()
KVM: arm64: Handle stage-2 faults in parallel
KVM: arm64: Make table->block changes parallel-aware
KVM: arm64: Make leaf->leaf PTE changes parallel-aware
KVM: arm64: Make block->table PTE changes parallel-aware
KVM: arm64: Split init and set for table PTE
KVM: arm64: Atomically update stage 2 leaf attributes in parallel walks
KVM: arm64: Protect stage-2 traversal with RCU
KVM: arm64: Tear down unlinked stage-2 subtree after break-before-make
KVM: arm64: Use an opaque type for pteps
KVM: arm64: Add a helper to tear down unlinked stage-2 subtrees
KVM: arm64: Don't pass kvm_pgtable through kvm_pgtable_walk_data
KVM: arm64: Pass mm_ops through the visitor context
KVM: arm64: Stash observed pte value in visitor context
KVM: arm64: Combine visitor arguments into a context structure
Signed-off-by: Marc Zyngier <maz@kernel.org>
-rw-r--r-- | arch/arm64/include/asm/kvm_pgtable.h | 153 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/nvhe/mem_protect.c | 21 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/nvhe/setup.c | 22 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/pgtable.c | 631 | ||||
-rw-r--r-- | arch/arm64/kvm/mmu.c | 53 |
5 files changed, 508 insertions, 372 deletions
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 3252eb50ecfe..d5cb01f8dc06 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -85,6 +85,8 @@ 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 +105,7 @@ 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 +165,6 @@ 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 +172,34 @@ 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), }; -typedef int (*kvm_pgtable_visitor_fn_t)(u64 addr, u64 end, u32 level, - kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag, - void * const arg); +struct kvm_pgtable_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)(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 +214,94 @@ 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. @@ -325,6 +410,17 @@ 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 +429,7 @@ 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 +451,7 @@ 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/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 07f9dc9848ef..55326b1bd247 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -79,6 +79,11 @@ 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_kvm.mm_ops, addr, level); +} + static int prepare_s2_pool(void *pgt_pool_base) { unsigned long nr_pages, pfn; @@ -93,6 +98,7 @@ static int prepare_s2_pool(void *pgt_pool_base) host_kvm.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, @@ -251,7 +257,7 @@ 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); + prot, &host_s2_pool, 0); } /* @@ -417,18 +423,15 @@ struct check_walk_data { 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_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, diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index e8d4ea2fcfa0..1068338d77f3 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -186,18 +186,15 @@ 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 finalize_host_mappings_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) { - struct kvm_pgtable_mm_ops *mm_ops = arg; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; 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; /* @@ -205,14 +202,14 @@ static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level, * 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) + mm_ops->get_page(ctx->ptep); + if (visit != 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; @@ -220,7 +217,7 @@ 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); @@ -242,7 +239,6 @@ static int finalize_host_mappings(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, }; int i, ret; diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index cdf8e76b0be1..58dbe0ab567f 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -49,8 +49,13 @@ #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; @@ -64,20 +69,20 @@ 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 +93,7 @@ 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 +101,6 @@ 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 +108,7 @@ 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) @@ -142,16 +142,13 @@ 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 +169,47 @@ 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 +221,20 @@ 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 +243,12 @@ 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 +256,10 @@ 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 +268,10 @@ 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 +283,20 @@ 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; + + r = kvm_pgtable_walk_begin(walker); + if (r) + return r; - return _kvm_pgtable_walk(&walk_data); + r = _kvm_pgtable_walk(pgt, &walk_data); + kvm_pgtable_walk_end(walker); + + return r; } struct leaf_walk_data { @@ -292,13 +304,13 @@ 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 +341,6 @@ 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 +394,49 @@ 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 +446,6 @@ 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 +463,39 @@ 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 +505,10 @@ 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 +516,7 @@ 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 +524,7 @@ 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 +537,18 @@ 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 +558,10 @@ 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 +576,6 @@ 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 +683,92 @@ 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 +782,42 @@ 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 +827,43 @@ 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 +873,62 @@ 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 +952,13 @@ 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 +969,29 @@ 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 +1000,11 @@ 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 +1028,19 @@ 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 +1056,12 @@ 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 +1070,18 @@ 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 +1100,14 @@ 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 +1116,7 @@ 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 +1129,7 @@ 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 +1152,25 @@ 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 +1201,7 @@ 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 +1217,18 @@ 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) +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 +1240,33 @@ 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/mmu.c b/arch/arm64/kvm/mmu.c index 1ef0704420d9..0fe5945bc4fb 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)); @@ -640,7 +659,7 @@ 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, + .pgd = (kvm_pteref_t)kvm->mm->pgd, .ia_bits = vabits_actual, .start_level = (KVM_PGTABLE_MAX_LEVELS - CONFIG_PGTABLE_LEVELS), @@ -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, @@ -841,7 +861,7 @@ 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; @@ -1136,7 +1156,6 @@ 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; @@ -1171,8 +1190,6 @@ 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); } @@ -1271,15 +1288,7 @@ 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; @@ -1323,15 +1332,12 @@ 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 +1346,7 @@ 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; @@ -1549,7 +1552,7 @@ 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; } |