diff options
author | Paolo Bonzini <pbonzini@redhat.com> | 2023-07-01 14:04:29 +0300 |
---|---|---|
committer | Paolo Bonzini <pbonzini@redhat.com> | 2023-07-01 14:04:29 +0300 |
commit | cc744042d90809ccb7cac7f9fb773f5c9cb9f835 (patch) | |
tree | ff26add0ac2a17b15bb7b789f276623aae7e8201 /arch/arm64/kvm/hyp/pgtable.c | |
parent | b5396271eab4ec28f0d27ff48e1b151b7b824295 (diff) | |
parent | 192df2aa0113ddddee2a93e453ff46610807b425 (diff) | |
download | linux-cc744042d90809ccb7cac7f9fb773f5c9cb9f835.tar.xz |
Merge tag 'kvmarm-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 updates for 6.5
- Eager page splitting optimization for dirty logging, optionally
allowing for a VM to avoid the cost of block splitting in the stage-2
fault path.
- Arm FF-A proxy for pKVM, allowing a pKVM host to safely interact with
services that live in the Secure world. pKVM intervenes on FF-A calls
to guarantee the host doesn't misuse memory donated to the hyp or a
pKVM guest.
- Support for running the split hypervisor with VHE enabled, known as
'hVHE' mode. This is extremely useful for testing the split
hypervisor on VHE-only systems, and paves the way for new use cases
that depend on having two TTBRs available at EL2.
- Generalized framework for configurable ID registers from userspace.
KVM/arm64 currently prevents arbitrary CPU feature set configuration
from userspace, but the intent is to relax this limitation and allow
userspace to select a feature set consistent with the CPU.
- Enable the use of Branch Target Identification (FEAT_BTI) in the
hypervisor.
- Use a separate set of pointer authentication keys for the hypervisor
when running in protected mode, as the host is untrusted at runtime.
- Ensure timer IRQs are consistently released in the init failure
paths.
- Avoid trapping CTR_EL0 on systems with Enhanced Virtualization Traps
(FEAT_EVT), as it is a register commonly read from userspace.
- Erratum workaround for the upcoming AmpereOne part, which has broken
hardware A/D state management.
As a consequence of the hVHE series reworking the arm64 software
features framework, the for-next/module-alloc branch from the arm64 tree
comes along for the ride.
Diffstat (limited to 'arch/arm64/kvm/hyp/pgtable.c')
-rw-r--r-- | arch/arm64/kvm/hyp/pgtable.c | 228 |
1 files changed, 207 insertions, 21 deletions
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 95dae02ccc2e..aa740a974e02 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -21,8 +21,10 @@ #define KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX GENMASK(4, 2) #define KVM_PTE_LEAF_ATTR_LO_S1_AP GENMASK(7, 6) -#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RO 3 -#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RW 1 +#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RO \ + ({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 2 : 3; }) +#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RW \ + ({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 0 : 1; }) #define KVM_PTE_LEAF_ATTR_LO_S1_SH GENMASK(9, 8) #define KVM_PTE_LEAF_ATTR_LO_S1_SH_IS 3 #define KVM_PTE_LEAF_ATTR_LO_S1_AF BIT(10) @@ -34,7 +36,7 @@ #define KVM_PTE_LEAF_ATTR_LO_S2_SH_IS 3 #define KVM_PTE_LEAF_ATTR_LO_S2_AF BIT(10) -#define KVM_PTE_LEAF_ATTR_HI GENMASK(63, 51) +#define KVM_PTE_LEAF_ATTR_HI GENMASK(63, 50) #define KVM_PTE_LEAF_ATTR_HI_SW GENMASK(58, 55) @@ -42,6 +44,8 @@ #define KVM_PTE_LEAF_ATTR_HI_S2_XN BIT(54) +#define KVM_PTE_LEAF_ATTR_HI_S1_GP BIT(50) + #define KVM_PTE_LEAF_ATTR_S2_PERMS (KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R | \ KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | \ KVM_PTE_LEAF_ATTR_HI_S2_XN) @@ -63,6 +67,16 @@ struct kvm_pgtable_walk_data { const u64 end; }; +static bool kvm_pgtable_walk_skip_bbm_tlbi(const struct kvm_pgtable_visit_ctx *ctx) +{ + return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_BBM_TLBI); +} + +static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx) +{ + return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_CMO); +} + static bool kvm_phys_is_valid(u64 phys) { return phys < BIT(id_aa64mmfr0_parange_to_phys_shift(ID_AA64MMFR0_EL1_PARANGE_MAX)); @@ -386,6 +400,9 @@ static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep) if (device) return -EINVAL; + + if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && system_supports_bti()) + attr |= KVM_PTE_LEAF_ATTR_HI_S1_GP; } else { attr |= KVM_PTE_LEAF_ATTR_HI_S1_XN; } @@ -623,10 +640,18 @@ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift) #ifdef CONFIG_ARM64_HW_AFDBM /* * Enable the Hardware Access Flag management, unconditionally - * on all CPUs. The features is RES0 on CPUs without the support - * and must be ignored by the CPUs. + * on all CPUs. In systems that have asymmetric support for the feature + * this allows KVM to leverage hardware support on the subset of cores + * that implement the feature. + * + * The architecture requires VTCR_EL2.HA to be RES0 (thus ignored by + * hardware) on implementations that do not advertise support for the + * feature. As such, setting HA unconditionally is safe, unless you + * happen to be running on a design that has unadvertised support for + * HAFDBS. Here be dragons. */ - vtcr |= VTCR_EL2_HA; + if (!cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38)) + vtcr |= VTCR_EL2_HA; #endif /* CONFIG_ARM64_HW_AFDBM */ /* Set the vmid bits */ @@ -755,14 +780,17 @@ static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx, 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 (!kvm_pgtable_walk_skip_bbm_tlbi(ctx)) { + /* + * 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); @@ -869,11 +897,13 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, return -EAGAIN; /* Perform CMOs before installation of the guest stage-2 PTE */ - if (mm_ops->dcache_clean_inval_poc && stage2_pte_cacheable(pgt, new)) + if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->dcache_clean_inval_poc && + stage2_pte_cacheable(pgt, new)) mm_ops->dcache_clean_inval_poc(kvm_pte_follow(new, mm_ops), - granule); + granule); - if (mm_ops->icache_inval_pou && stage2_pte_executable(new)) + if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->icache_inval_pou && + stage2_pte_executable(new)) mm_ops->icache_inval_pou(kvm_pte_follow(new, mm_ops), granule); stage2_make_pte(ctx, new); @@ -895,7 +925,7 @@ static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx, if (ret) return ret; - mm_ops->free_removed_table(childp, ctx->level); + mm_ops->free_unlinked_table(childp, ctx->level); return 0; } @@ -940,7 +970,7 @@ static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, * 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. + * kvm_pgtable_mm_ops::free_unlinked_table() to tear down the detached table. * * Otherwise, the LEAF callback performs the mapping at the existing leaves * instead. @@ -1209,7 +1239,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED); if (!ret) - kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, pgt->mmu, addr, level); + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level); return ret; } @@ -1242,6 +1272,162 @@ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size) return kvm_pgtable_walk(pgt, addr, size, &walker); } +kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, + u64 phys, u32 level, + enum kvm_pgtable_prot prot, + void *mc, bool force_pte) +{ + struct stage2_map_data map_data = { + .phys = phys, + .mmu = pgt->mmu, + .memcache = mc, + .force_pte = force_pte, + }; + struct kvm_pgtable_walker walker = { + .cb = stage2_map_walker, + .flags = KVM_PGTABLE_WALK_LEAF | + KVM_PGTABLE_WALK_SKIP_BBM_TLBI | + KVM_PGTABLE_WALK_SKIP_CMO, + .arg = &map_data, + }; + /* + * The input address (.addr) is irrelevant for walking an + * unlinked table. Construct an ambiguous IA range to map + * kvm_granule_size(level) worth of memory. + */ + struct kvm_pgtable_walk_data data = { + .walker = &walker, + .addr = 0, + .end = kvm_granule_size(level), + }; + struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; + kvm_pte_t *pgtable; + int ret; + + if (!IS_ALIGNED(phys, kvm_granule_size(level))) + return ERR_PTR(-EINVAL); + + ret = stage2_set_prot_attr(pgt, prot, &map_data.attr); + if (ret) + return ERR_PTR(ret); + + pgtable = mm_ops->zalloc_page(mc); + if (!pgtable) + return ERR_PTR(-ENOMEM); + + ret = __kvm_pgtable_walk(&data, mm_ops, (kvm_pteref_t)pgtable, + level + 1); + if (ret) { + kvm_pgtable_stage2_free_unlinked(mm_ops, pgtable, level); + mm_ops->put_page(pgtable); + return ERR_PTR(ret); + } + + return pgtable; +} + +/* + * Get the number of page-tables needed to replace a block with a + * fully populated tree up to the PTE entries. Note that @level is + * interpreted as in "level @level entry". + */ +static int stage2_block_get_nr_page_tables(u32 level) +{ + switch (level) { + case 1: + return PTRS_PER_PTE + 1; + case 2: + return 1; + case 3: + return 0; + default: + WARN_ON_ONCE(level < KVM_PGTABLE_MIN_BLOCK_LEVEL || + level >= KVM_PGTABLE_MAX_LEVELS); + return -EINVAL; + }; +} + +static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + struct kvm_mmu_memory_cache *mc = ctx->arg; + struct kvm_s2_mmu *mmu; + kvm_pte_t pte = ctx->old, new, *childp; + enum kvm_pgtable_prot prot; + u32 level = ctx->level; + bool force_pte; + int nr_pages; + u64 phys; + + /* No huge-pages exist at the last level */ + if (level == KVM_PGTABLE_MAX_LEVELS - 1) + return 0; + + /* We only split valid block mappings */ + if (!kvm_pte_valid(pte)) + return 0; + + nr_pages = stage2_block_get_nr_page_tables(level); + if (nr_pages < 0) + return nr_pages; + + if (mc->nobjs >= nr_pages) { + /* Build a tree mapped down to the PTE granularity. */ + force_pte = true; + } else { + /* + * Don't force PTEs, so create_unlinked() below does + * not populate the tree up to the PTE level. The + * consequence is that the call will require a single + * page of level 2 entries at level 1, or a single + * page of PTEs at level 2. If we are at level 1, the + * PTEs will be created recursively. + */ + force_pte = false; + nr_pages = 1; + } + + if (mc->nobjs < nr_pages) + return -ENOMEM; + + mmu = container_of(mc, struct kvm_s2_mmu, split_page_cache); + phys = kvm_pte_to_phys(pte); + prot = kvm_pgtable_stage2_pte_prot(pte); + + childp = kvm_pgtable_stage2_create_unlinked(mmu->pgt, phys, + level, prot, mc, force_pte); + if (IS_ERR(childp)) + return PTR_ERR(childp); + + if (!stage2_try_break_pte(ctx, mmu)) { + kvm_pgtable_stage2_free_unlinked(mm_ops, childp, level); + mm_ops->put_page(childp); + return -EAGAIN; + } + + /* + * Note, the contents of the page table are guaranteed to be made + * visible before the new PTE is assigned because stage2_make_pte() + * writes the PTE using smp_store_release(). + */ + new = kvm_init_table_pte(childp, mm_ops); + stage2_make_pte(ctx, new); + dsb(ishst); + return 0; +} + +int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, + struct kvm_mmu_memory_cache *mc) +{ + struct kvm_pgtable_walker walker = { + .cb = stage2_split_walker, + .flags = KVM_PGTABLE_WALK_LEAF, + .arg = mc, + }; + + return kvm_pgtable_walk(pgt, addr, size, &walker); +} int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops, @@ -1311,7 +1497,7 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) pgt->pgd = NULL; } -void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level) +void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level) { kvm_pteref_t ptep = (kvm_pteref_t)pgtable; struct kvm_pgtable_walker walker = { |