From dfc7a7769ab7f2a2f629c673717ef1fa7b63aa42 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 21:56:31 +0000 Subject: [PATCH 01/17] KVM: arm64: Combine visitor arguments into a context structure Passing new arguments by value to the visitor callbacks is extremely inflexible for stuffing new parameters used by only some of the visitors. Use a context structure instead and pass the pointer through to the visitor callback. While at it, redefine the 'flags' parameter to the visitor to contain the bit indicating the phase of the walk. Pass the entire set of flags through the context structure such that the walker can communicate additional state to the visitor callback. No functional change intended. Signed-off-by: Oliver Upton Reviewed-by: Ben Gardon Reviewed-by: Gavin Shan Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107215644.1895162-2-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 15 +- arch/arm64/kvm/hyp/nvhe/mem_protect.c | 10 +- arch/arm64/kvm/hyp/nvhe/setup.c | 16 +- arch/arm64/kvm/hyp/pgtable.c | 269 +++++++++++++------------- 4 files changed, 154 insertions(+), 156 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 3252eb50ecfe..607f9bb8aab4 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -199,10 +199,17 @@ enum kvm_pgtable_walk_flags { KVM_PGTABLE_WALK_TABLE_POST = BIT(2), }; -typedef int (*kvm_pgtable_visitor_fn_t)(u64 addr, u64 end, u32 level, - kvm_pte_t *ptep, - enum kvm_pgtable_walk_flags flag, - void * const arg); +struct kvm_pgtable_visit_ctx { + kvm_pte_t *ptep; + void *arg; + 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); /** * struct kvm_pgtable_walker - Hook into a page-table walk. diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 1e78acf9662e..8f5b6a36a039 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -417,13 +417,11 @@ 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; + kvm_pte_t pte = *ctx->ptep; if (kvm_pte_valid(pte) && !addr_is_memory(kvm_pte_to_phys(pte))) return -EINVAL; diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index e8d4ea2fcfa0..a293cf5eba1b 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -186,15 +186,13 @@ 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->arg; enum kvm_pgtable_prot prot; enum pkvm_page_state state; - kvm_pte_t pte = *ptep; + kvm_pte_t pte = *ctx->ptep; phys_addr_t phys; if (!kvm_pte_valid(pte)) @@ -205,11 +203,11 @@ 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); diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index cdf8e76b0be1..900c8b9c0cfc 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -64,20 +64,20 @@ 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) @@ -172,12 +172,12 @@ 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); + return walker->cb(ctx, visit); } static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, @@ -186,20 +186,24 @@ static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, kvm_pte_t *ptep, u32 level) { + enum kvm_pgtable_walk_flags flags = data->walker->flags; + struct kvm_pgtable_visit_ctx ctx = { + .ptep = ptep, + .arg = data->walker->arg, + .addr = data->addr, + .end = data->end, + .level = level, + .flags = flags, + }; 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; - 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); + if (!table && (ctx.flags & KVM_PGTABLE_WALK_LEAF)) { + ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_LEAF); pte = *ptep; table = kvm_pte_table(pte, level); } @@ -218,10 +222,8 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, 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; @@ -292,13 +294,13 @@ 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->ptep; + data->level = ctx->level; return 0; } @@ -383,47 +385,47 @@ 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, old = *ctx->ptep; + 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); + new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); if (old == new) return true; if (!kvm_pte_valid(old)) - data->mm_ops->get_page(ptep); + data->mm_ops->get_page(ctx->ptep); else if (WARN_ON((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 hyp_map_data *data = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = data->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); + kvm_set_table_pte(ctx->ptep, childp, mm_ops); + mm_ops->get_page(ctx->ptep); return 0; } @@ -456,39 +458,39 @@ struct hyp_unmap_data { 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; + kvm_pte_t pte = *ctx->ptep, *childp = NULL; + u64 granule = kvm_granule_size(ctx->level); + struct hyp_unmap_data *data = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; if (!kvm_pte_valid(pte)) return -EINVAL; - if (kvm_pte_table(pte, level)) { + if (kvm_pte_table(pte, ctx->level)) { childp = kvm_pte_follow(pte, 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); + __tlbi_level(vale2is, __TLBI_VADDR(ctx->addr, 0), ctx->level); data->unmapped += granule; } dsb(ish); isb(); - mm_ops->put_page(ptep); + mm_ops->put_page(ctx->ptep); if (childp) mm_ops->put_page(childp); @@ -532,18 +534,18 @@ 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->arg; + kvm_pte_t pte = *ctx->ptep; if (!kvm_pte_valid(pte)) return 0; - mm_ops->put_page(ptep); + mm_ops->put_page(ctx->ptep); - if (kvm_pte_table(pte, level)) + if (kvm_pte_table(pte, ctx->level)) mm_ops->put_page(kvm_pte_follow(pte, mm_ops)); return 0; @@ -682,19 +684,19 @@ 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 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->ptep)) { + 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) @@ -708,29 +710,28 @@ 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, old = *ctx->ptep; + 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; - 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); @@ -744,7 +745,7 @@ static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level, if (!stage2_pte_needs_update(old, new)) return -EAGAIN; - stage2_put_pte(ptep, data->mmu, addr, level, mm_ops); + stage2_put_pte(ctx, data->mmu, mm_ops); } /* Perform CMOs before installation of the guest stage-2 PTE */ @@ -755,26 +756,25 @@ 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); + smp_store_release(ctx->ptep, new); if (stage2_pte_is_counted(new)) - mm_ops->get_page(ptep); + mm_ops->get_page(ctx->ptep); 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; - 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); + data->childp = kvm_pte_follow(*ctx->ptep, data->mm_ops); + kvm_clear_pte(ctx->ptep); /* * Invalidate the whole stage-2, as we may have numerous leaf @@ -782,29 +782,29 @@ static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level, * individually. */ kvm_call_hyp(__kvm_tlb_flush_vmid, data->mmu); - data->anchor = ptep; + data->anchor = ctx->ptep; 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; + kvm_pte_t *childp, pte = *ctx->ptep; int ret; if (data->anchor) { if (stage2_pte_is_counted(pte)) - mm_ops->put_page(ptep); + mm_ops->put_page(ctx->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) @@ -820,16 +820,15 @@ static int stage2_map_walk_leaf(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, * will be mapped lazily. */ if (stage2_pte_is_counted(pte)) - stage2_put_pte(ptep, data->mmu, addr, level, mm_ops); + stage2_put_pte(ctx, data->mmu, mm_ops); - kvm_set_table_pte(ptep, childp, mm_ops); - mm_ops->get_page(ptep); + kvm_set_table_pte(ctx->ptep, childp, mm_ops); + mm_ops->get_page(ctx->ptep); return 0; } -static int stage2_map_walk_table_post(u64 addr, u64 end, u32 level, - kvm_pte_t *ptep, +static int stage2_map_walk_table_post(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; @@ -839,17 +838,17 @@ static int stage2_map_walk_table_post(u64 addr, u64 end, u32 level, if (!data->anchor) return 0; - if (data->anchor == ptep) { + if (data->anchor == ctx->ptep) { childp = data->childp; data->anchor = NULL; data->childp = NULL; - ret = stage2_map_walk_leaf(addr, end, level, ptep, data); + ret = stage2_map_walk_leaf(ctx, data); } else { - childp = kvm_pte_follow(*ptep, mm_ops); + childp = kvm_pte_follow(*ctx->ptep, mm_ops); } mm_ops->put_page(childp); - mm_ops->put_page(ptep); + mm_ops->put_page(ctx->ptep); return ret; } @@ -873,18 +872,18 @@ static int stage2_map_walk_table_post(u64 addr, u64 end, u32 level, * the page-table, installing the block entry when it revisits the anchor * pointer and clearing the anchor to NULL. */ -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); + return stage2_map_walk_leaf(ctx, data); case KVM_PGTABLE_WALK_TABLE_POST: - return stage2_map_walk_table_post(addr, end, level, ptep, data); + return stage2_map_walk_table_post(ctx, data); } return -EINVAL; @@ -949,25 +948,24 @@ 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; + kvm_pte_t pte = *ctx->ptep, *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); + kvm_clear_pte(ctx->ptep); + mm_ops->put_page(ctx->ptep); } return 0; } - if (kvm_pte_table(pte, level)) { + if (kvm_pte_table(pte, ctx->level)) { childp = kvm_pte_follow(pte, mm_ops); if (mm_ops->page_count(childp) != 1) @@ -981,11 +979,11 @@ 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)); + kvm_granule_size(ctx->level)); if (childp) mm_ops->put_page(childp); @@ -1012,18 +1010,17 @@ struct stage2_attr_data { 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; + kvm_pte_t pte = *ctx->ptep; + struct stage2_attr_data *data = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; if (!kvm_pte_valid(pte)) return 0; - data->level = level; + data->level = ctx->level; data->pte = pte; pte &= ~data->attr_clr; pte |= data->attr_set; @@ -1039,10 +1036,10 @@ 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->ptep)) mm_ops->icache_inval_pou(kvm_pte_follow(pte, mm_ops), - kvm_granule_size(level)); - WRITE_ONCE(*ptep, pte); + kvm_granule_size(ctx->level)); + WRITE_ONCE(*ctx->ptep, pte); } return 0; @@ -1140,20 +1137,19 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, 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; + kvm_pte_t pte = *ctx->ptep; if (!kvm_pte_valid(pte) || !stage2_pte_cacheable(pgt, pte)) 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)); + kvm_granule_size(ctx->level)); return 0; } @@ -1200,19 +1196,18 @@ 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->arg; + kvm_pte_t pte = *ctx->ptep; if (!stage2_pte_is_counted(pte)) return 0; - mm_ops->put_page(ptep); + mm_ops->put_page(ctx->ptep); - if (kvm_pte_table(pte, level)) + if (kvm_pte_table(pte, ctx->level)) mm_ops->put_page(kvm_pte_follow(pte, mm_ops)); return 0; From 83844a2317ecad935f6735abd854e4bf3f757040 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 21:56:32 +0000 Subject: [PATCH 02/17] KVM: arm64: Stash observed pte value in visitor context Rather than reading the ptep all over the shop, read the ptep once from __kvm_pgtable_visit() and stick it in the visitor context. Reread the ptep after visiting a leaf in case the callback installed a new table underneath. No functional change intended. Signed-off-by: Oliver Upton Reviewed-by: Ben Gardon Reviewed-by: Gavin Shan Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107215644.1895162-3-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 1 + arch/arm64/kvm/hyp/nvhe/mem_protect.c | 5 +- arch/arm64/kvm/hyp/nvhe/setup.c | 7 +-- arch/arm64/kvm/hyp/pgtable.c | 86 +++++++++++++-------------- 4 files changed, 48 insertions(+), 51 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 607f9bb8aab4..14d4b68a1e92 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -201,6 +201,7 @@ enum kvm_pgtable_walk_flags { struct kvm_pgtable_visit_ctx { kvm_pte_t *ptep; + kvm_pte_t old; void *arg; u64 addr; u64 end; diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 8f5b6a36a039..d21d1b08a055 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -421,12 +421,11 @@ static int __check_page_state_visitor(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { struct check_walk_data *d = ctx->arg; - kvm_pte_t pte = *ctx->ptep; - 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 a293cf5eba1b..6af443c9d78e 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -192,10 +192,9 @@ static int finalize_host_mappings_walker(const struct kvm_pgtable_visit_ctx *ctx struct kvm_pgtable_mm_ops *mm_ops = ctx->arg; enum kvm_pgtable_prot prot; enum pkvm_page_state state; - kvm_pte_t pte = *ctx->ptep; phys_addr_t phys; - if (!kvm_pte_valid(pte)) + if (!kvm_pte_valid(ctx->old)) return 0; /* @@ -210,7 +209,7 @@ static int finalize_host_mappings_walker(const struct kvm_pgtable_visit_ctx *ctx 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; @@ -218,7 +217,7 @@ static int finalize_host_mappings_walker(const struct kvm_pgtable_visit_ctx *ctx * 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); diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 900c8b9c0cfc..fb3696b3a997 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -189,6 +189,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, enum kvm_pgtable_walk_flags flags = data->walker->flags; struct kvm_pgtable_visit_ctx ctx = { .ptep = ptep, + .old = READ_ONCE(*ptep), .arg = data->walker->arg, .addr = data->addr, .end = data->end, @@ -196,16 +197,16 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, .flags = flags, }; int ret = 0; - kvm_pte_t *childp, pte = *ptep; - bool table = kvm_pte_table(pte, level); + kvm_pte_t *childp; + bool table = kvm_pte_table(ctx.old, level); if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE)) ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_PRE); if (!table && (ctx.flags & KVM_PGTABLE_WALK_LEAF)) { ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_LEAF); - pte = *ptep; - table = kvm_pte_table(pte, level); + ctx.old = READ_ONCE(*ptep); + table = kvm_pte_table(ctx.old, level); } if (ret) @@ -217,7 +218,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, goto out; } - childp = kvm_pte_follow(pte, data->pgt->mm_ops); + childp = kvm_pte_follow(ctx.old, data->pgt->mm_ops); ret = __kvm_pgtable_walk(data, childp, level + 1); if (ret) goto out; @@ -299,7 +300,7 @@ static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx, { struct leaf_walk_data *data = ctx->arg; - data->pte = *ctx->ptep; + data->pte = ctx->old; data->level = ctx->level; return 0; @@ -388,7 +389,7 @@ enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte) static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct hyp_map_data *data) { - kvm_pte_t new, old = *ctx->ptep; + kvm_pte_t new; u64 granule = kvm_granule_size(ctx->level), phys = data->phys; if (!kvm_block_mapping_supported(ctx, phys)) @@ -396,11 +397,11 @@ static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, data->phys += granule; new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); - if (old == new) + if (ctx->old == new) return true; - if (!kvm_pte_valid(old)) + if (!kvm_pte_valid(ctx->old)) data->mm_ops->get_page(ctx->ptep); - else if (WARN_ON((old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) + else if (WARN_ON((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) return false; smp_store_release(ctx->ptep, new); @@ -461,16 +462,16 @@ struct hyp_unmap_data { static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { - kvm_pte_t pte = *ctx->ptep, *childp = NULL; + kvm_pte_t *childp = NULL; u64 granule = kvm_granule_size(ctx->level); struct hyp_unmap_data *data = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; - if (!kvm_pte_valid(pte)) + if (!kvm_pte_valid(ctx->old)) return -EINVAL; - if (kvm_pte_table(pte, ctx->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; @@ -538,15 +539,14 @@ 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 = ctx->arg; - kvm_pte_t pte = *ctx->ptep; - if (!kvm_pte_valid(pte)) + if (!kvm_pte_valid(ctx->old)) return 0; mm_ops->put_page(ctx->ptep); - if (kvm_pte_table(pte, ctx->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; } @@ -691,7 +691,7 @@ static void stage2_put_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s * Clear the existing PTE, and perform break-before-make with * TLB maintenance if it was valid. */ - if (kvm_pte_valid(*ctx->ptep)) { + if (kvm_pte_valid(ctx->old)) { kvm_clear_pte(ctx->ptep); kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level); } @@ -722,7 +722,7 @@ static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx, static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { - kvm_pte_t new, old = *ctx->ptep; + 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; @@ -735,14 +735,14 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, else new = kvm_init_invalid_leaf_owner(data->owner_id); - if (stage2_pte_is_counted(old)) { + if (stage2_pte_is_counted(ctx->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)) + if (!stage2_pte_needs_update(ctx->old, new)) return -EAGAIN; stage2_put_pte(ctx, data->mmu, mm_ops); @@ -773,7 +773,7 @@ static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx, if (!stage2_leaf_mapping_allowed(ctx, data)) return 0; - data->childp = kvm_pte_follow(*ctx->ptep, data->mm_ops); + data->childp = kvm_pte_follow(ctx->old, data->mm_ops); kvm_clear_pte(ctx->ptep); /* @@ -790,11 +790,11 @@ 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 = *ctx->ptep; + kvm_pte_t *childp; int ret; if (data->anchor) { - if (stage2_pte_is_counted(pte)) + if (stage2_pte_is_counted(ctx->old)) mm_ops->put_page(ctx->ptep); return 0; @@ -819,7 +819,7 @@ static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, * a table. Accesses beyond 'end' that fall within the new table * will be mapped lazily. */ - if (stage2_pte_is_counted(pte)) + if (stage2_pte_is_counted(ctx->old)) stage2_put_pte(ctx, data->mmu, mm_ops); kvm_set_table_pte(ctx->ptep, childp, mm_ops); @@ -844,7 +844,7 @@ static int stage2_map_walk_table_post(const struct kvm_pgtable_visit_ctx *ctx, data->childp = NULL; ret = stage2_map_walk_leaf(ctx, data); } else { - childp = kvm_pte_follow(*ctx->ptep, mm_ops); + childp = kvm_pte_follow(ctx->old, mm_ops); } mm_ops->put_page(childp); @@ -954,23 +954,23 @@ static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, 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 = *ctx->ptep, *childp = NULL; + kvm_pte_t *childp = NULL; bool need_flush = false; - if (!kvm_pte_valid(pte)) { - if (stage2_pte_is_counted(pte)) { + 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, ctx->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); } @@ -982,7 +982,7 @@ static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, 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), + mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops), kvm_granule_size(ctx->level)); if (childp) @@ -1013,11 +1013,11 @@ struct stage2_attr_data { static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { - kvm_pte_t pte = *ctx->ptep; + kvm_pte_t pte = ctx->old; struct stage2_attr_data *data = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; - if (!kvm_pte_valid(pte)) + if (!kvm_pte_valid(ctx->old)) return 0; data->level = ctx->level; @@ -1036,7 +1036,7 @@ static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx, * stage-2 PTE if we are going to add executable permission. */ if (mm_ops->icache_inval_pou && - stage2_pte_executable(pte) && !stage2_pte_executable(*ctx->ptep)) + stage2_pte_executable(pte) && !stage2_pte_executable(ctx->old)) mm_ops->icache_inval_pou(kvm_pte_follow(pte, mm_ops), kvm_granule_size(ctx->level)); WRITE_ONCE(*ctx->ptep, pte); @@ -1142,13 +1142,12 @@ static int stage2_flush_walker(const struct kvm_pgtable_visit_ctx *ctx, { struct kvm_pgtable *pgt = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; - kvm_pte_t pte = *ctx->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), + mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops), kvm_granule_size(ctx->level)); return 0; } @@ -1200,15 +1199,14 @@ 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 = ctx->arg; - kvm_pte_t pte = *ctx->ptep; - if (!stage2_pte_is_counted(pte)) + if (!stage2_pte_is_counted(ctx->old)) return 0; mm_ops->put_page(ctx->ptep); - if (kvm_pte_table(pte, ctx->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; } From 2a611c7f87f26cca405da63a57f06d0e4dc14240 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 21:56:33 +0000 Subject: [PATCH 03/17] KVM: arm64: Pass mm_ops through the visitor context As a prerequisite for getting visitors off of struct kvm_pgtable, pass mm_ops through the visitor context. No functional change intended. Signed-off-by: Oliver Upton Reviewed-by: Ben Gardon Reviewed-by: Gavin Shan Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107215644.1895162-4-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 1 + arch/arm64/kvm/hyp/nvhe/setup.c | 3 +- arch/arm64/kvm/hyp/pgtable.c | 63 +++++++++++----------------- 3 files changed, 26 insertions(+), 41 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 14d4b68a1e92..a752793482cb 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -203,6 +203,7 @@ 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; diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 6af443c9d78e..1068338d77f3 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -189,7 +189,7 @@ static void hpool_put_page(void *addr) 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 = ctx->arg; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; enum kvm_pgtable_prot prot; enum pkvm_page_state state; phys_addr_t phys; @@ -239,7 +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 fb3696b3a997..db25e81a9890 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -181,9 +181,10 @@ static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, } 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_pte_t *pgtable, u32 level); static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, + struct kvm_pgtable_mm_ops *mm_ops, kvm_pte_t *ptep, u32 level) { enum kvm_pgtable_walk_flags flags = data->walker->flags; @@ -191,6 +192,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, .ptep = ptep, .old = READ_ONCE(*ptep), .arg = data->walker->arg, + .mm_ops = mm_ops, .addr = data->addr, .end = data->end, .level = level, @@ -218,8 +220,8 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, goto out; } - childp = kvm_pte_follow(ctx.old, data->pgt->mm_ops); - ret = __kvm_pgtable_walk(data, childp, level + 1); + childp = kvm_pte_follow(ctx.old, mm_ops); + ret = __kvm_pgtable_walk(data, mm_ops, childp, level + 1); if (ret) goto out; @@ -231,7 +233,7 @@ out: } 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_pte_t *pgtable, u32 level) { u32 idx; int ret = 0; @@ -245,7 +247,7 @@ static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, if (data->addr >= data->end) break; - ret = __kvm_pgtable_visit(data, ptep, level); + ret = __kvm_pgtable_visit(data, mm_ops, ptep, level); if (ret) break; } @@ -269,7 +271,7 @@ static int _kvm_pgtable_walk(struct kvm_pgtable_walk_data *data) for (idx = kvm_pgd_page_idx(data); data->addr < data->end; ++idx) { kvm_pte_t *ptep = &pgt->pgd[idx * PTRS_PER_PTE]; - ret = __kvm_pgtable_walk(data, ptep, pgt->start_level); + ret = __kvm_pgtable_walk(data, pgt->mm_ops, ptep, pgt->start_level); if (ret) break; } @@ -332,7 +334,6 @@ 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) @@ -400,7 +401,7 @@ static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, if (ctx->old == new) return true; if (!kvm_pte_valid(ctx->old)) - data->mm_ops->get_page(ctx->ptep); + ctx->mm_ops->get_page(ctx->ptep); else if (WARN_ON((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) return false; @@ -413,7 +414,7 @@ static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx, { kvm_pte_t *childp; struct hyp_map_data *data = ctx->arg; - struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (hyp_map_walker_try_leaf(ctx, data)) return 0; @@ -436,7 +437,6 @@ 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, @@ -454,18 +454,13 @@ 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(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { kvm_pte_t *childp = NULL; u64 granule = kvm_granule_size(ctx->level); - struct hyp_unmap_data *data = ctx->arg; - struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; + u64 *unmapped = ctx->arg; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) return -EINVAL; @@ -486,7 +481,7 @@ static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, kvm_clear_pte(ctx->ptep); dsb(ishst); __tlbi_level(vale2is, __TLBI_VADDR(ctx->addr, 0), ctx->level); - data->unmapped += granule; + *unmapped += granule; } dsb(ish); @@ -501,12 +496,10 @@ static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, 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, }; @@ -514,7 +507,7 @@ 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, @@ -538,7 +531,7 @@ int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, 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 = ctx->arg; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) return 0; @@ -556,7 +549,6 @@ 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)); @@ -575,8 +567,6 @@ 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; }; @@ -725,7 +715,7 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, 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(ctx, data)) return -E2BIG; @@ -773,7 +763,7 @@ static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx, if (!stage2_leaf_mapping_allowed(ctx, data)) return 0; - data->childp = kvm_pte_follow(ctx->old, data->mm_ops); + data->childp = kvm_pte_follow(ctx->old, ctx->mm_ops); kvm_clear_pte(ctx->ptep); /* @@ -789,7 +779,7 @@ static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx, 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; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; kvm_pte_t *childp; int ret; @@ -831,7 +821,7 @@ static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, static int stage2_map_walk_table_post(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { - struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; kvm_pte_t *childp; int ret = 0; @@ -898,7 +888,6 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, .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 = { @@ -929,7 +918,6 @@ 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, }; @@ -953,7 +941,7 @@ static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, { struct kvm_pgtable *pgt = ctx->arg; struct kvm_s2_mmu *mmu = pgt->mmu; - struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; kvm_pte_t *childp = NULL; bool need_flush = false; @@ -1007,7 +995,6 @@ 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(const struct kvm_pgtable_visit_ctx *ctx, @@ -1015,7 +1002,7 @@ static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx, { kvm_pte_t pte = ctx->old; struct stage2_attr_data *data = ctx->arg; - struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!kvm_pte_valid(ctx->old)) return 0; @@ -1055,7 +1042,6 @@ static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr, 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, @@ -1198,7 +1184,7 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, 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 = ctx->arg; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; if (!stage2_pte_is_counted(ctx->old)) return 0; @@ -1218,7 +1204,6 @@ 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)); From fa002e8e79b3f980455ba585c1f47b26680de5b9 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 21:56:34 +0000 Subject: [PATCH 04/17] KVM: arm64: Don't pass kvm_pgtable through kvm_pgtable_walk_data In order to tear down page tables from outside the context of kvm_pgtable (such as an RCU callback), stop passing a pointer through kvm_pgtable_walk_data. No functional change intended. Signed-off-by: Oliver Upton Reviewed-by: Ben Gardon Reviewed-by: Gavin Shan Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107215644.1895162-5-oliver.upton@linux.dev --- arch/arm64/kvm/hyp/pgtable.c | 18 +++++------------- 1 file changed, 5 insertions(+), 13 deletions(-) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index db25e81a9890..93989b750a26 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -50,7 +50,6 @@ #define KVM_MAX_OWNER_ID 1 struct kvm_pgtable_walk_data { - struct kvm_pgtable *pgt; struct kvm_pgtable_walker *walker; u64 addr; @@ -88,7 +87,7 @@ 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 +95,6 @@ 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 +102,7 @@ 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) @@ -255,11 +249,10 @@ 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) @@ -268,7 +261,7 @@ 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) { + for (idx = kvm_pgd_page_idx(pgt, data->addr); data->addr < data->end; ++idx) { kvm_pte_t *ptep = &pgt->pgd[idx * PTRS_PER_PTE]; ret = __kvm_pgtable_walk(data, pgt->mm_ops, ptep, pgt->start_level); @@ -283,13 +276,12 @@ 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, }; - return _kvm_pgtable_walk(&walk_data); + return _kvm_pgtable_walk(pgt, &walk_data); } struct leaf_walk_data { From 8e94e1252cc054bb31fd3e9a15235cd831970ec1 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 21:56:35 +0000 Subject: [PATCH 05/17] KVM: arm64: Add a helper to tear down unlinked stage-2 subtrees A subsequent change to KVM will move the tear down of an unlinked stage-2 subtree out of the critical path of the break-before-make sequence. Introduce a new helper for tearing down unlinked stage-2 subtrees. Leverage the existing stage-2 free walkers to do so, with a deep call into __kvm_pgtable_walk() as the subtree is no longer reachable from the root. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107215644.1895162-6-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 11 +++++++++++ arch/arm64/kvm/hyp/pgtable.c | 23 +++++++++++++++++++++++ 2 files changed, 34 insertions(+) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index a752793482cb..93b1feeaebab 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -333,6 +333,17 @@ 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*(). diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 93989b750a26..363a5cce7e1a 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -1203,3 +1203,26 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) pgt->mm_ops->free_pages_exact(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_pte_t *ptep = (kvm_pte_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)); +} From 6b91b8f95cadd3441c056182daf9024475ac4a91 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 21:56:36 +0000 Subject: [PATCH 06/17] KVM: arm64: Use an opaque type for pteps Use an opaque type for pteps and require visitors explicitly dereference the pointer before using. Protecting page table memory with RCU requires that KVM dereferences RCU-annotated pointers before using. However, RCU is not available for use in the nVHE hypervisor and the opaque type can be conditionally annotated with RCU for the stage-2 MMU. Call the type a 'pteref' to avoid a naming collision with raw pteps. No functional change intended. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107215644.1895162-7-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 9 ++++++++- arch/arm64/kvm/hyp/pgtable.c | 27 ++++++++++++++------------- arch/arm64/kvm/mmu.c | 2 +- 3 files changed, 23 insertions(+), 15 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 93b1feeaebab..cbd2851eefc1 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -37,6 +37,13 @@ static inline u64 kvm_get_parange(u64 mmfr0) typedef u64 kvm_pte_t; +typedef kvm_pte_t *kvm_pteref_t; + +static inline kvm_pte_t *kvm_dereference_pteref(kvm_pteref_t pteref, bool shared) +{ + return pteref; +} + #define KVM_PTE_VALID BIT(0) #define KVM_PTE_ADDR_MASK GENMASK(47, PAGE_SHIFT) @@ -175,7 +182,7 @@ typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end, struct kvm_pgtable { u32 ia_bits; u32 start_level; - kvm_pte_t *pgd; + kvm_pteref_t pgd; struct kvm_pgtable_mm_ops *mm_ops; /* Stage-2 only */ diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 363a5cce7e1a..7511494537e5 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -175,13 +175,14 @@ static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, } static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, - struct kvm_pgtable_mm_ops *mm_ops, 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, struct kvm_pgtable_mm_ops *mm_ops, - kvm_pte_t *ptep, u32 level) + kvm_pteref_t pteref, u32 level) { enum kvm_pgtable_walk_flags flags = data->walker->flags; + kvm_pte_t *ptep = kvm_dereference_pteref(pteref, false); struct kvm_pgtable_visit_ctx ctx = { .ptep = ptep, .old = READ_ONCE(*ptep), @@ -193,7 +194,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, .flags = flags, }; int ret = 0; - kvm_pte_t *childp; + kvm_pteref_t childp; bool table = kvm_pte_table(ctx.old, level); if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE)) @@ -214,7 +215,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, goto out; } - childp = kvm_pte_follow(ctx.old, mm_ops); + 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; @@ -227,7 +228,7 @@ out: } static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, - struct kvm_pgtable_mm_ops *mm_ops, kvm_pte_t *pgtable, u32 level) + struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, u32 level) { u32 idx; int ret = 0; @@ -236,12 +237,12 @@ 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, mm_ops, ptep, level); + ret = __kvm_pgtable_visit(data, mm_ops, pteref, level); if (ret) break; } @@ -262,9 +263,9 @@ static int _kvm_pgtable_walk(struct kvm_pgtable *pgt, struct kvm_pgtable_walk_da return -EINVAL; for (idx = kvm_pgd_page_idx(pgt, data->addr); data->addr < data->end; ++idx) { - kvm_pte_t *ptep = &pgt->pgd[idx * PTRS_PER_PTE]; + kvm_pteref_t pteref = &pgt->pgd[idx * PTRS_PER_PTE]; - ret = __kvm_pgtable_walk(data, pgt->mm_ops, ptep, pgt->start_level); + ret = __kvm_pgtable_walk(data, pgt->mm_ops, pteref, pgt->start_level); if (ret) break; } @@ -507,7 +508,7 @@ 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; @@ -544,7 +545,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) }; 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(pgt->pgd, false)); pgt->pgd = NULL; } @@ -1157,7 +1158,7 @@ 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; @@ -1200,7 +1201,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) 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(pgt->pgd, false), pgd_sz); pgt->pgd = NULL; } diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 60ee3d9f01f8..5e197ae190ef 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -640,7 +640,7 @@ 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 = VA_BITS, .start_level = (KVM_PGTABLE_MAX_LEVELS - CONFIG_PGTABLE_LEVELS), From 5c359cca1faf6d7671537fe1c240e8668467864d Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 21:56:37 +0000 Subject: [PATCH 07/17] KVM: arm64: Tear down unlinked stage-2 subtree after break-before-make The break-before-make sequence is a bit annoying as it opens a window wherein memory is unmapped from the guest. KVM should replace the PTE as quickly as possible and avoid unnecessary work in between. Presently, the stage-2 map walker tears down a removed table before installing a block mapping when coalescing a table into a block. As the removed table is no longer visible to hardware walkers after the DSB+TLBI, it is possible to move the remaining cleanup to happen after installing the new PTE. Reshuffle the stage-2 map walker to install the new block entry in the pre-order callback. Unwire all of the teardown logic and replace it with a call to kvm_pgtable_stage2_free_removed() after fixing the PTE. The post-order visitor is now completely unnecessary, so drop it. Finally, touch up the comments to better represent the now simplified map walker. Note that the call to tear down the unlinked stage-2 is indirected as a subsequent change will use an RCU callback to trigger tear down. RCU is not available to pKVM, so there is a need to use different implementations on pKVM and non-pKVM VMs. Signed-off-by: Oliver Upton Reviewed-by: Ben Gardon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107215644.1895162-8-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 3 + arch/arm64/kvm/hyp/nvhe/mem_protect.c | 6 ++ arch/arm64/kvm/hyp/pgtable.c | 85 +++++++-------------------- arch/arm64/kvm/mmu.c | 8 +++ 4 files changed, 39 insertions(+), 63 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index cbd2851eefc1..e70cf57b719e 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -92,6 +92,8 @@ 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 @@ -110,6 +112,7 @@ 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); diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index d21d1b08a055..735769886b55 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, diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 7511494537e5..7c9782347570 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -750,13 +750,13 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, 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(ctx, data)) return 0; - data->childp = kvm_pte_follow(ctx->old, ctx->mm_ops); kvm_clear_pte(ctx->ptep); /* @@ -765,8 +765,13 @@ static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx, * individually. */ kvm_call_hyp(__kvm_tlb_flush_vmid, data->mmu); - data->anchor = ctx->ptep; - return 0; + + ret = stage2_map_walker_try_leaf(ctx, data); + + mm_ops->put_page(ctx->ptep); + mm_ops->free_removed_table(childp, ctx->level); + + return ret; } static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, @@ -776,13 +781,6 @@ static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t *childp; int ret; - if (data->anchor) { - if (stage2_pte_is_counted(ctx->old)) - mm_ops->put_page(ctx->ptep); - - return 0; - } - ret = stage2_map_walker_try_leaf(ctx, data); if (ret != -E2BIG) return ret; @@ -811,49 +809,14 @@ static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, return 0; } -static int stage2_map_walk_table_post(const struct kvm_pgtable_visit_ctx *ctx, - struct stage2_map_data *data) -{ - struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; - kvm_pte_t *childp; - int ret = 0; - - if (!data->anchor) - return 0; - - if (data->anchor == ctx->ptep) { - childp = data->childp; - data->anchor = NULL; - data->childp = NULL; - ret = stage2_map_walk_leaf(ctx, data); - } else { - childp = kvm_pte_follow(ctx->old, mm_ops); - } - - mm_ops->put_page(childp); - mm_ops->put_page(ctx->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(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) @@ -865,11 +828,9 @@ static int stage2_map_walker(const struct kvm_pgtable_visit_ctx *ctx, return stage2_map_walk_table_pre(ctx, data); case KVM_PGTABLE_WALK_LEAF: return stage2_map_walk_leaf(ctx, data); - case KVM_PGTABLE_WALK_TABLE_POST: - return stage2_map_walk_table_post(ctx, data); + default: + return -EINVAL; } - - return -EINVAL; } int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, @@ -886,8 +847,7 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, 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, }; @@ -917,8 +877,7 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size, 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, }; @@ -1207,7 +1166,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level) { - kvm_pte_t *ptep = (kvm_pte_t *)pgtable; + kvm_pteref_t ptep = (kvm_pteref_t)pgtable; struct kvm_pgtable_walker walker = { .cb = stage2_free_walker, .flags = KVM_PGTABLE_WALK_LEAF | @@ -1225,5 +1184,5 @@ void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pg .end = kvm_granule_size(level), }; - WARN_ON(__kvm_pgtable_walk(&data, mm_ops, ptep, 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 5e197ae190ef..73ae908eb5d9 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -128,6 +128,13 @@ 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(void *addr, u32 level) +{ + kvm_pgtable_stage2_free_removed(&kvm_s2_mm_ops, addr, level); +} + static void kvm_host_get_page(void *addr) { get_page(virt_to_page(addr)); @@ -662,6 +669,7 @@ 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, From c3119ae45dfb6038ca458ab5ba7a9fba2810845b Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 21:56:38 +0000 Subject: [PATCH 08/17] KVM: arm64: Protect stage-2 traversal with RCU Use RCU to safely walk the stage-2 page tables in parallel. Acquire and release the RCU read lock when traversing the page tables. Defer the freeing of table memory to an RCU callback. Indirect the calls into RCU and provide stubs for hypervisor code, as RCU is not available in such a context. The RCU protection doesn't amount to much at the moment, as readers are already protected by the read-write lock (all walkers that free table memory take the write lock). Nonetheless, a subsequent change will futher relax the locking requirements around the stage-2 MMU, thereby depending on RCU. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107215644.1895162-9-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 49 ++++++++++++++++++++++++++++ arch/arm64/kvm/hyp/pgtable.c | 10 +++++- arch/arm64/kvm/mmu.c | 14 +++++++- 3 files changed, 71 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index e70cf57b719e..7634b6964779 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -37,6 +37,13 @@ static inline u64 kvm_get_parange(u64 mmfr0) typedef u64 kvm_pte_t; +/* + * 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(kvm_pteref_t pteref, bool shared) @@ -44,6 +51,40 @@ static inline kvm_pte_t *kvm_dereference_pteref(kvm_pteref_t pteref, bool shared return pteref; } +static inline void kvm_pgtable_walk_begin(void) {} +static inline void kvm_pgtable_walk_end(void) {} + +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(kvm_pteref_t pteref, bool shared) +{ + return rcu_dereference_check(pteref, !shared); +} + +static inline void kvm_pgtable_walk_begin(void) +{ + rcu_read_lock(); +} + +static inline void kvm_pgtable_walk_end(void) +{ + rcu_read_unlock(); +} + +static inline bool kvm_pgtable_walk_lock_held(void) +{ + return rcu_read_lock_held(); +} + +#endif + #define KVM_PTE_VALID BIT(0) #define KVM_PTE_ADDR_MASK GENMASK(47, PAGE_SHIFT) @@ -202,11 +243,14 @@ 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 { @@ -223,6 +267,11 @@ struct kvm_pgtable_visit_ctx { 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. * @cb: Callback function to invoke during the walk. diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 7c9782347570..d8d963521d4e 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -171,6 +171,9 @@ static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, enum kvm_pgtable_walk_flags visit) { struct kvm_pgtable_walker *walker = data->walker; + + /* 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); } @@ -281,8 +284,13 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, .end = PAGE_ALIGN(walk_data.addr + size), .walker = walker, }; + int r; - return _kvm_pgtable_walk(pgt, &walk_data); + kvm_pgtable_walk_begin(); + r = _kvm_pgtable_walk(pgt, &walk_data); + kvm_pgtable_walk_end(); + + return r; } struct leaf_walk_data { diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 73ae908eb5d9..52e042399ba5 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -130,9 +130,21 @@ static void kvm_s2_free_pages_exact(void *virt, size_t 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) { - kvm_pgtable_stage2_free_removed(&kvm_s2_mm_ops, addr, 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) From ca5de2448c3b4c018fe3d6223df8b59068be1cd7 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 21:56:39 +0000 Subject: [PATCH 09/17] KVM: arm64: Atomically update stage 2 leaf attributes in parallel walks The stage2 attr walker is already used for parallel walks. Since commit f783ef1c0e82 ("KVM: arm64: Add fast path to handle permission relaxation during dirty logging"), KVM acquires the read lock when write-unprotecting a PTE. However, the walker only uses a simple store to update the PTE. This is safe as the only possible race is with hardware updates to the access flag, which is benign. However, a subsequent change to KVM will allow more changes to the stage 2 page tables to be done in parallel. Prepare the stage 2 attribute walker by performing atomic updates to the PTE when walking in parallel. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107215644.1895162-10-oliver.upton@linux.dev --- arch/arm64/kvm/hyp/pgtable.c | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index d8d963521d4e..a34e2050f931 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -185,7 +185,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, kvm_pteref_t pteref, u32 level) { enum kvm_pgtable_walk_flags flags = data->walker->flags; - kvm_pte_t *ptep = kvm_dereference_pteref(pteref, false); + kvm_pte_t *ptep = kvm_dereference_pteref(pteref, flags & KVM_PGTABLE_WALK_SHARED); struct kvm_pgtable_visit_ctx ctx = { .ptep = ptep, .old = READ_ONCE(*ptep), @@ -675,6 +675,16 @@ static bool stage2_pte_is_counted(kvm_pte_t pte) return !!pte; } +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; +} + static void stage2_put_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops) { @@ -986,7 +996,9 @@ static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx, stage2_pte_executable(pte) && !stage2_pte_executable(ctx->old)) mm_ops->icache_inval_pou(kvm_pte_follow(pte, mm_ops), kvm_granule_size(ctx->level)); - WRITE_ONCE(*ctx->ptep, pte); + + if (!stage2_try_set_pte(ctx, pte)) + return -EAGAIN; } return 0; @@ -995,7 +1007,7 @@ static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx, 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; @@ -1006,7 +1018,7 @@ static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr, 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); @@ -1025,14 +1037,14 @@ 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; } @@ -1041,7 +1053,7 @@ 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. @@ -1054,7 +1066,7 @@ 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; } @@ -1077,7 +1089,8 @@ 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; From 331aa3a0547d1c794587e0df374d13b16645e832 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 21:56:40 +0000 Subject: [PATCH 10/17] KVM: arm64: Split init and set for table PTE Create a helper to initialize a table and directly call smp_store_release() to install it (for now). Prepare for a subsequent change that generalizes PTE writes with a helper. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107215644.1895162-11-oliver.upton@linux.dev --- arch/arm64/kvm/hyp/pgtable.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index a34e2050f931..f4dd77c6c97d 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -136,16 +136,13 @@ 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) @@ -413,7 +410,7 @@ static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit) { - kvm_pte_t *childp; + kvm_pte_t *childp, new; struct hyp_map_data *data = ctx->arg; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; @@ -427,8 +424,10 @@ static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx, if (!childp) return -ENOMEM; - kvm_set_table_pte(ctx->ptep, childp, mm_ops); + new = kvm_init_table_pte(childp, mm_ops); mm_ops->get_page(ctx->ptep); + smp_store_release(ctx->ptep, new); + return 0; } @@ -796,7 +795,7 @@ 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 = ctx->mm_ops; - kvm_pte_t *childp; + kvm_pte_t *childp, new; int ret; ret = stage2_map_walker_try_leaf(ctx, data); @@ -821,8 +820,9 @@ static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, if (stage2_pte_is_counted(ctx->old)) stage2_put_pte(ctx, data->mmu, mm_ops); - kvm_set_table_pte(ctx->ptep, childp, mm_ops); + new = kvm_init_table_pte(childp, mm_ops); mm_ops->get_page(ctx->ptep); + smp_store_release(ctx->ptep, new); return 0; } From 0ab12f3574db6cb432917a667f9392a88e8f0dfc Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 21:58:55 +0000 Subject: [PATCH 11/17] KVM: arm64: Make block->table PTE changes parallel-aware In order to service stage-2 faults in parallel, stage-2 table walkers must take exclusive ownership of the PTE being worked on. An additional requirement of the architecture is that software must perform a 'break-before-make' operation when changing the block size used for mapping memory. Roll these two concepts together into helpers for performing a 'break-before-make' sequence. Use a special PTE value to indicate a PTE has been locked by a software walker. Additionally, use an atomic compare-exchange to 'break' the PTE when the stage-2 page tables are possibly shared with another software walker. Elide the DSB + TLBI if the evicted PTE was invalid (and thus not subject to break-before-make). All of the atomics do nothing for now, as the stage-2 walker isn't fully ready to perform parallel walks. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107215855.1895367-1-oliver.upton@linux.dev --- arch/arm64/kvm/hyp/pgtable.c | 80 +++++++++++++++++++++++++++++++++--- 1 file changed, 75 insertions(+), 5 deletions(-) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index f4dd77c6c97d..b9f0d792b8d9 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -49,6 +49,12 @@ #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_walker *walker; @@ -674,6 +680,11 @@ static bool stage2_pte_is_counted(kvm_pte_t pte) return !!pte; } +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)) { @@ -684,6 +695,64 @@ static bool stage2_try_set_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_ 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) { @@ -812,17 +881,18 @@ static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, 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(ctx->old)) - stage2_put_pte(ctx, data->mmu, mm_ops); - new = kvm_init_table_pte(childp, mm_ops); - mm_ops->get_page(ctx->ptep); - smp_store_release(ctx->ptep, new); + stage2_make_pte(ctx, new); return 0; } From 946fbfdf336b811479e024136c7cabc00157b6b9 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 21:59:34 +0000 Subject: [PATCH 12/17] KVM: arm64: Make leaf->leaf PTE changes parallel-aware Convert stage2_map_walker_try_leaf() to use the new break-before-make helpers, thereby making the handler parallel-aware. As before, avoid the break-before-make if recreating the existing mapping. Additionally, retry execution if another vCPU thread is modifying the same PTE. Signed-off-by: Oliver Upton Reviewed-by: Ben Gardon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107215934.1895478-1-oliver.upton@linux.dev --- arch/arm64/kvm/hyp/pgtable.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index b9f0d792b8d9..238f29389617 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -804,18 +804,17 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, else new = kvm_init_invalid_leaf_owner(data->owner_id); - if (stage2_pte_is_counted(ctx->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(ctx->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(ctx, data->mmu, 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)) @@ -825,9 +824,8 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, 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(ctx->ptep, new); - if (stage2_pte_is_counted(new)) - mm_ops->get_page(ctx->ptep); + stage2_make_pte(ctx, new); + if (kvm_phys_is_valid(phys)) data->phys += granule; return 0; From af87fc03cfdf6893011df419588d27acdfb9c197 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 22:00:06 +0000 Subject: [PATCH 13/17] KVM: arm64: Make table->block changes parallel-aware stage2_map_walker_try_leaf() and friends now handle stage-2 PTEs generically, and perform the correct flush when a table PTE is removed. Additionally, they've been made parallel-aware, using an atomic break to take ownership of the PTE. Stop clearing the PTE in the pre-order callback and instead let stage2_map_walker_try_leaf() deal with it. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107220006.1895572-1-oliver.upton@linux.dev --- arch/arm64/kvm/hyp/pgtable.c | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 238f29389617..f814422ef795 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -841,21 +841,12 @@ static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx, if (!stage2_leaf_mapping_allowed(ctx, data)) return 0; - kvm_clear_pte(ctx->ptep); - - /* - * 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); - ret = stage2_map_walker_try_leaf(ctx, data); + if (ret) + return ret; - mm_ops->put_page(ctx->ptep); mm_ops->free_removed_table(childp, ctx->level); - - return ret; + return 0; } static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, From 1577cb5823cefdff4416f272a88143ee933d97f5 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 7 Nov 2022 22:00:33 +0000 Subject: [PATCH 14/17] KVM: arm64: Handle stage-2 faults in parallel The stage-2 map walker has been made parallel-aware, and as such can be called while only holding the read side of the MMU lock. Rip out the conditional locking in user_mem_abort() and instead grab the read lock. Continue to take the write lock from other callsites to kvm_pgtable_stage2_map(). Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221107220033.1895655-1-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 3 ++- arch/arm64/kvm/hyp/nvhe/mem_protect.c | 2 +- arch/arm64/kvm/hyp/pgtable.c | 5 +++-- arch/arm64/kvm/mmu.c | 31 ++++++--------------------- 4 files changed, 13 insertions(+), 28 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 7634b6964779..a874ce0ce7b5 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -412,6 +412,7 @@ void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pg * @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 @@ -433,7 +434,7 @@ void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pg */ 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 735769886b55..f6d82bf33ce1 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -257,7 +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); } /* diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index f814422ef795..5bca9610d040 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -912,7 +912,7 @@ static int stage2_map_walker(const struct kvm_pgtable_visit_ctx *ctx, 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 = { @@ -923,7 +923,8 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, - .flags = KVM_PGTABLE_WALK_TABLE_PRE | + .flags = flags | + KVM_PGTABLE_WALK_TABLE_PRE | KVM_PGTABLE_WALK_LEAF, .arg = &map_data, }; diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 52e042399ba5..410c2a37fe32 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -861,7 +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; @@ -1156,7 +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; @@ -1191,8 +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); } @@ -1291,15 +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; @@ -1343,15 +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) { @@ -1360,10 +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; @@ -1569,7 +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; } From 3a5154c723ba5ceb9ce374a7307e03263c03fd29 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 18 Nov 2022 18:22:20 +0000 Subject: [PATCH 15/17] KVM: arm64: Take a pointer to walker data in kvm_dereference_pteref() Rather than passing through the state of the KVM_PGTABLE_WALK_SHARED flag, just take a pointer to the whole walker structure instead. Move around struct kvm_pgtable and the RCU indirection such that the associated ifdeffery remains in one place while ensuring the walker + flags definitions precede their use. No functional change intended. Signed-off-by: Oliver Upton Acked-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221118182222.3932898-2-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 144 ++++++++++++++------------- arch/arm64/kvm/hyp/pgtable.c | 6 +- 2 files changed, 76 insertions(+), 74 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index a874ce0ce7b5..f23af693e3c5 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -37,54 +37,6 @@ static inline u64 kvm_get_parange(u64 mmfr0) typedef u64 kvm_pte_t; -/* - * 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(kvm_pteref_t pteref, bool shared) -{ - return pteref; -} - -static inline void kvm_pgtable_walk_begin(void) {} -static inline void kvm_pgtable_walk_end(void) {} - -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(kvm_pteref_t pteref, bool shared) -{ - return rcu_dereference_check(pteref, !shared); -} - -static inline void kvm_pgtable_walk_begin(void) -{ - rcu_read_lock(); -} - -static inline void kvm_pgtable_walk_end(void) -{ - rcu_read_unlock(); -} - -static inline bool kvm_pgtable_walk_lock_held(void) -{ - return rcu_read_lock_held(); -} - -#endif - #define KVM_PTE_VALID BIT(0) #define KVM_PTE_ADDR_MASK GENMASK(47, PAGE_SHIFT) @@ -212,29 +164,6 @@ enum kvm_pgtable_prot { 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_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; -}; - /** * enum kvm_pgtable_walk_flags - Flags to control a depth-first page-table walk. * @KVM_PGTABLE_WALK_LEAF: Visit leaf entries, including invalid @@ -285,6 +214,79 @@ 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 void kvm_pgtable_walk_begin(void) {} +static inline void kvm_pgtable_walk_end(void) {} + +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 void kvm_pgtable_walk_begin(void) +{ + rcu_read_lock(); +} + +static inline void kvm_pgtable_walk_end(void) +{ + 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. diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 5bca9610d040..b5b91a882836 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -188,7 +188,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, kvm_pteref_t pteref, u32 level) { enum kvm_pgtable_walk_flags flags = data->walker->flags; - kvm_pte_t *ptep = kvm_dereference_pteref(pteref, flags & KVM_PGTABLE_WALK_SHARED); + kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref); struct kvm_pgtable_visit_ctx ctx = { .ptep = ptep, .old = READ_ONCE(*ptep), @@ -558,7 +558,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) }; WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); - pgt->mm_ops->put_page(kvm_dereference_pteref(pgt->pgd, false)); + pgt->mm_ops->put_page(kvm_dereference_pteref(&walker, pgt->pgd)); pgt->pgd = NULL; } @@ -1241,7 +1241,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) 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(kvm_dereference_pteref(pgt->pgd, false), pgd_sz); + pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz); pgt->pgd = NULL; } From b7833bf202e3068abb77c642a0843f696e9c8d38 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 18 Nov 2022 18:22:21 +0000 Subject: [PATCH 16/17] KVM: arm64: Don't acquire RCU read lock for exclusive table walks Marek reported a BUG resulting from the recent parallel faults changes, as the hyp stage-1 map walker attempted to allocate table memory while holding the RCU read lock: BUG: sleeping function called from invalid context at include/linux/sched/mm.h:274 in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 1, name: swapper/0 preempt_count: 0, expected: 0 RCU nest depth: 1, expected: 0 2 locks held by swapper/0/1: #0: ffff80000a8a44d0 (kvm_hyp_pgd_mutex){+.+.}-{3:3}, at: __create_hyp_mappings+0x80/0xc4 #1: ffff80000a927720 (rcu_read_lock){....}-{1:2}, at: kvm_pgtable_walk+0x0/0x1f4 CPU: 2 PID: 1 Comm: swapper/0 Not tainted 6.1.0-rc3+ #5918 Hardware name: Raspberry Pi 3 Model B (DT) Call trace: dump_backtrace.part.0+0xe4/0xf0 show_stack+0x18/0x40 dump_stack_lvl+0x8c/0xb8 dump_stack+0x18/0x34 __might_resched+0x178/0x220 __might_sleep+0x48/0xa0 prepare_alloc_pages+0x178/0x1a0 __alloc_pages+0x9c/0x109c alloc_page_interleave+0x1c/0xc4 alloc_pages+0xec/0x160 get_zeroed_page+0x1c/0x44 kvm_hyp_zalloc_page+0x14/0x20 hyp_map_walker+0xd4/0x134 kvm_pgtable_visitor_cb.isra.0+0x38/0x5c __kvm_pgtable_walk+0x1a4/0x220 kvm_pgtable_walk+0x104/0x1f4 kvm_pgtable_hyp_map+0x80/0xc4 __create_hyp_mappings+0x9c/0xc4 kvm_mmu_init+0x144/0x1cc kvm_arch_init+0xe4/0xef4 kvm_init+0x3c/0x3d0 arm_init+0x20/0x30 do_one_initcall+0x74/0x400 kernel_init_freeable+0x2e0/0x350 kernel_init+0x24/0x130 ret_from_fork+0x10/0x20 Since the hyp stage-1 table walkers are serialized by kvm_hyp_pgd_mutex, RCU protection really doesn't add anything. Don't acquire the RCU read lock for an exclusive walk. Reported-by: Marek Szyprowski Signed-off-by: Oliver Upton Acked-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221118182222.3932898-3-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 14 ++++++++------ arch/arm64/kvm/hyp/pgtable.c | 4 ++-- 2 files changed, 10 insertions(+), 8 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index f23af693e3c5..4b6b52ebc11c 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -229,8 +229,8 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke return pteref; } -static inline void kvm_pgtable_walk_begin(void) {} -static inline void kvm_pgtable_walk_end(void) {} +static inline void kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) {} +static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker) {} static inline bool kvm_pgtable_walk_lock_held(void) { @@ -247,14 +247,16 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED)); } -static inline void kvm_pgtable_walk_begin(void) +static inline void kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) { - rcu_read_lock(); + if (walker->flags & KVM_PGTABLE_WALK_SHARED) + rcu_read_lock(); } -static inline void kvm_pgtable_walk_end(void) +static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker) { - rcu_read_unlock(); + if (walker->flags & KVM_PGTABLE_WALK_SHARED) + rcu_read_unlock(); } static inline bool kvm_pgtable_walk_lock_held(void) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index b5b91a882836..d6f3753cb87e 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -289,9 +289,9 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, }; int r; - kvm_pgtable_walk_begin(); + kvm_pgtable_walk_begin(walker); r = _kvm_pgtable_walk(pgt, &walk_data); - kvm_pgtable_walk_end(); + kvm_pgtable_walk_end(walker); return r; } From 5e806c5812e8012a83496cf96bdba266b3aec428 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 18 Nov 2022 18:22:22 +0000 Subject: [PATCH 17/17] KVM: arm64: Reject shared table walks in the hyp code Exclusive table walks are the only supported table walk in the hyp, as there is no construct like RCU available in the hypervisor code. Reject any attempt to do a shared table walk by returning an error and allowing the caller to clean up the mess. Suggested-by: Will Deacon Signed-off-by: Oliver Upton Acked-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221118182222.3932898-4-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 17 +++++++++++++++-- arch/arm64/kvm/hyp/pgtable.c | 5 ++++- 2 files changed, 19 insertions(+), 3 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 4b6b52ebc11c..d5cb01f8dc06 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -229,7 +229,18 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke return pteref; } -static inline void kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) {} +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) @@ -247,10 +258,12 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED)); } -static inline void kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) +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) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index d6f3753cb87e..58dbe0ab567f 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -289,7 +289,10 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, }; int r; - kvm_pgtable_walk_begin(walker); + r = kvm_pgtable_walk_begin(walker); + if (r) + return r; + r = _kvm_pgtable_walk(pgt, &walk_data); kvm_pgtable_walk_end(walker);