From: Quentin Perret Date: Wed, 18 Dec 2024 19:40:51 +0000 (+0000) Subject: KVM: arm64: Introduce __pkvm_host_share_guest() X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=d0bd3e6570aee42766e7bd884734ae078667ea1e;p=users%2Fdwmw2%2Flinux.git KVM: arm64: Introduce __pkvm_host_share_guest() In preparation for handling guest stage-2 mappings at EL2, introduce a new pKVM hypercall allowing to share pages with non-protected guests. Tested-by: Fuad Tabba Reviewed-by: Fuad Tabba Signed-off-by: Quentin Perret Link: https://lore.kernel.org/r/20241218194059.3670226-11-qperret@google.com Signed-off-by: Marc Zyngier --- diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 89c0fac695516..449337f5b2a3b 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -65,6 +65,7 @@ enum __kvm_host_smccc_func { /* Hypercalls available after pKVM finalisation */ __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp, __KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp, + __KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest, __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc, __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run, __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context, diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index e18e9244d17a4..1246f1d01dbf6 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -771,6 +771,9 @@ struct kvm_vcpu_arch { /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; + /* Pages to top-up the pKVM/EL2 guest pool */ + struct kvm_hyp_memcache pkvm_memcache; + /* Virtual SError ESR to restore when HCR_EL2.VSE is set */ u64 vsesr_el2; diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h index 25038ac705d82..15b8956051b6c 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h @@ -39,6 +39,8 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages); int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages); int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages); int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages); +int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, + enum kvm_pgtable_prot prot); bool addr_is_memory(phys_addr_t phys); int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot); diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h index 2a5eabf4b753f..34233d5860607 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/memory.h +++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h @@ -46,6 +46,8 @@ struct hyp_page { /* Host (non-meta) state. Guarded by the host stage-2 lock. */ enum pkvm_page_state host_state : 8; + + u32 host_share_guest_count; }; extern u64 __hyp_vmemmap; @@ -68,7 +70,7 @@ static inline phys_addr_t hyp_virt_to_phys(void *addr) static inline struct hyp_page *hyp_phys_to_page(phys_addr_t phys) { - BUILD_BUG_ON(sizeof(struct hyp_page) != sizeof(u32)); + BUILD_BUG_ON(sizeof(struct hyp_page) != sizeof(u64)); return &hyp_vmemmap[hyp_phys_to_pfn(phys)]; } diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 95d78db315b3f..d659462fbf5d9 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -211,6 +211,39 @@ out: cpu_reg(host_ctxt, 1) = ret; } +static int pkvm_refill_memcache(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + return refill_memcache(&hyp_vcpu->vcpu.arch.pkvm_memcache, + host_vcpu->arch.pkvm_memcache.nr_pages, + &host_vcpu->arch.pkvm_memcache); +} + +static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, pfn, host_ctxt, 1); + DECLARE_REG(u64, gfn, host_ctxt, 2); + DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 3); + struct pkvm_hyp_vcpu *hyp_vcpu; + int ret = -EINVAL; + + if (!is_protected_kvm_enabled()) + goto out; + + hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); + if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu)) + goto out; + + ret = pkvm_refill_memcache(hyp_vcpu); + if (ret) + goto out; + + ret = __pkvm_host_share_guest(pfn, gfn, hyp_vcpu, prot); +out: + cpu_reg(host_ctxt, 1) = ret; +} + static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt) { DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1); @@ -420,6 +453,7 @@ static const hcall_t host_hcall[] = { HANDLE_FUNC(__pkvm_host_share_hyp), HANDLE_FUNC(__pkvm_host_unshare_hyp), + HANDLE_FUNC(__pkvm_host_share_guest), HANDLE_FUNC(__kvm_adjust_pc), HANDLE_FUNC(__kvm_vcpu_run), HANDLE_FUNC(__kvm_flush_vm_context), diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 12bb5445fe47e..fb9592e721cf8 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -867,6 +867,27 @@ static int hyp_complete_donation(u64 addr, return pkvm_create_mappings_locked(start, end, prot); } +static enum pkvm_page_state guest_get_page_state(kvm_pte_t pte, u64 addr) +{ + if (!kvm_pte_valid(pte)) + return PKVM_NOPAGE; + + return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)); +} + +static int __guest_check_page_state_range(struct pkvm_hyp_vcpu *vcpu, u64 addr, + u64 size, enum pkvm_page_state state) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + struct check_walk_data d = { + .desired = state, + .get_page_state = guest_get_page_state, + }; + + hyp_assert_lock_held(&vm->lock); + return check_page_state_range(&vm->pgt, addr, size, &d); +} + static int check_share(struct pkvm_mem_share *share) { const struct pkvm_mem_transition *tx = &share->tx; @@ -1349,3 +1370,54 @@ int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages) return ret; } + +int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu, + enum kvm_pgtable_prot prot) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + u64 phys = hyp_pfn_to_phys(pfn); + u64 ipa = hyp_pfn_to_phys(gfn); + struct hyp_page *page; + int ret; + + if (prot & ~KVM_PGTABLE_PROT_RWX) + return -EINVAL; + + ret = check_range_allowed_memory(phys, phys + PAGE_SIZE); + if (ret) + return ret; + + host_lock_component(); + guest_lock_component(vm); + + ret = __guest_check_page_state_range(vcpu, ipa, PAGE_SIZE, PKVM_NOPAGE); + if (ret) + goto unlock; + + page = hyp_phys_to_page(phys); + switch (page->host_state) { + case PKVM_PAGE_OWNED: + WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_OWNED)); + break; + case PKVM_PAGE_SHARED_OWNED: + if (page->host_share_guest_count) + break; + /* Only host to np-guest multi-sharing is tolerated */ + WARN_ON(1); + fallthrough; + default: + ret = -EPERM; + goto unlock; + } + + WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys, + pkvm_mkstate(prot, PKVM_PAGE_SHARED_BORROWED), + &vcpu->vcpu.arch.pkvm_memcache, 0)); + page->host_share_guest_count++; + +unlock: + guest_unlock_component(vm); + host_unlock_component(); + + return ret; +} diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 496d186efb03b..0109c36566c8b 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -795,6 +795,14 @@ int __pkvm_teardown_vm(pkvm_handle_t handle) /* Push the metadata pages to the teardown memcache */ for (idx = 0; idx < hyp_vm->nr_vcpus; ++idx) { struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vm->vcpus[idx]; + struct kvm_hyp_memcache *vcpu_mc = &hyp_vcpu->vcpu.arch.pkvm_memcache; + + while (vcpu_mc->nr_pages) { + void *addr = pop_hyp_memcache(vcpu_mc, hyp_phys_to_virt); + + push_hyp_memcache(mc, addr, hyp_virt_to_phys); + unmap_donated_memory_noclear(addr, PAGE_SIZE); + } teardown_donated_memory(mc, hyp_vcpu, sizeof(*hyp_vcpu)); }