diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-06-28 15:40:51 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-06-28 15:40:51 -0700 |
commit | 36824f198c621cebeb22966b5e244378fa341295 (patch) | |
tree | ee1e358a4ed0cd022ae12b4b7ba1fa3d0e5746d5 /arch/arm64/kvm/mmu.c | |
parent | 9840cfcb97fc8b6aa7b36cec3cc3fd763f14052e (diff) | |
parent | b8917b4ae44d1b945f6fba3d8ee6777edb44633b (diff) |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
"This covers all architectures (except MIPS) so I don't expect any
other feature pull requests this merge window.
ARM:
- Add MTE support in guests, complete with tag save/restore interface
- Reduce the impact of CMOs by moving them in the page-table code
- Allow device block mappings at stage-2
- Reduce the footprint of the vmemmap in protected mode
- Support the vGIC on dumb systems such as the Apple M1
- Add selftest infrastructure to support multiple configuration and
apply that to PMU/non-PMU setups
- Add selftests for the debug architecture
- The usual crop of PMU fixes
PPC:
- Support for the H_RPT_INVALIDATE hypercall
- Conversion of Book3S entry/exit to C
- Bug fixes
S390:
- new HW facilities for guests
- make inline assembly more robust with KASAN and co
x86:
- Allow userspace to handle emulation errors (unknown instructions)
- Lazy allocation of the rmap (host physical -> guest physical
address)
- Support for virtualizing TSC scaling on VMX machines
- Optimizations to avoid shattering huge pages at the beginning of
live migration
- Support for initializing the PDPTRs without loading them from
memory
- Many TLB flushing cleanups
- Refuse to load if two-stage paging is available but NX is not (this
has been a requirement in practice for over a year)
- A large series that separates the MMU mode (WP/SMAP/SMEP etc.) from
CR0/CR4/EFER, using the MMU mode everywhere once it is computed
from the CPU registers
- Use PM notifier to notify the guest about host suspend or hibernate
- Support for passing arguments to Hyper-V hypercalls using XMM
registers
- Support for Hyper-V TLB flush hypercalls and enlightened MSR bitmap
on AMD processors
- Hide Hyper-V hypercalls that are not included in the guest CPUID
- Fixes for live migration of virtual machines that use the Hyper-V
"enlightened VMCS" optimization of nested virtualization
- Bugfixes (not many)
Generic:
- Support for retrieving statistics without debugfs
- Cleanups for the KVM selftests API"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (314 commits)
KVM: x86: rename apic_access_page_done to apic_access_memslot_enabled
kvm: x86: disable the narrow guest module parameter on unload
selftests: kvm: Allows userspace to handle emulation errors.
kvm: x86: Allow userspace to handle emulation errors
KVM: x86/mmu: Let guest use GBPAGES if supported in hardware and TDP is on
KVM: x86/mmu: Get CR4.SMEP from MMU, not vCPU, in shadow page fault
KVM: x86/mmu: Get CR0.WP from MMU, not vCPU, in shadow page fault
KVM: x86/mmu: Drop redundant rsvd bits reset for nested NPT
KVM: x86/mmu: Optimize and clean up so called "last nonleaf level" logic
KVM: x86: Enhance comments for MMU roles and nested transition trickiness
KVM: x86/mmu: WARN on any reserved SPTE value when making a valid SPTE
KVM: x86/mmu: Add helpers to do full reserved SPTE checks w/ generic MMU
KVM: x86/mmu: Use MMU's role to determine PTTYPE
KVM: x86/mmu: Collapse 32-bit PAE and 64-bit statements for helpers
KVM: x86/mmu: Add a helper to calculate root from role_regs
KVM: x86/mmu: Add helper to update paging metadata
KVM: x86/mmu: Don't update nested guest's paging bitmasks if CR0.PG=0
KVM: x86/mmu: Consolidate reset_rsvds_bits_mask() calls
KVM: x86/mmu: Use MMU role_regs to get LA57, and drop vCPU LA57 helper
KVM: x86/mmu: Get nested MMU's root level from the MMU's role
...
Diffstat (limited to 'arch/arm64/kvm/mmu.c')
-rw-r--r-- | arch/arm64/kvm/mmu.c | 196 |
1 files changed, 133 insertions, 63 deletions
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index c10207fed2f3..57292dc5ce35 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -126,6 +126,16 @@ static void *kvm_host_va(phys_addr_t phys) return __va(phys); } +static void clean_dcache_guest_page(void *va, size_t size) +{ + __clean_dcache_guest_page(va, size); +} + +static void invalidate_icache_guest_page(void *va, size_t size) +{ + __invalidate_icache_guest_page(va, size); +} + /* * Unmapping vs dcache management: * @@ -432,6 +442,8 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = { .page_count = kvm_host_page_count, .phys_to_virt = kvm_host_va, .virt_to_phys = kvm_host_pa, + .dcache_clean_inval_poc = clean_dcache_guest_page, + .icache_inval_pou = invalidate_icache_guest_page, }; /** @@ -693,16 +705,6 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } -static void clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size) -{ - __clean_dcache_guest_page(pfn, size); -} - -static void invalidate_icache_guest_page(kvm_pfn_t pfn, unsigned long size) -{ - __invalidate_icache_guest_page(pfn, size); -} - static void kvm_send_hwpoison_signal(unsigned long address, short lsb) { send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current); @@ -822,6 +824,74 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot, return PAGE_SIZE; } +static int get_vma_page_shift(struct vm_area_struct *vma, unsigned long hva) +{ + unsigned long pa; + + if (is_vm_hugetlb_page(vma) && !(vma->vm_flags & VM_PFNMAP)) + return huge_page_shift(hstate_vma(vma)); + + if (!(vma->vm_flags & VM_PFNMAP)) + return PAGE_SHIFT; + + VM_BUG_ON(is_vm_hugetlb_page(vma)); + + pa = (vma->vm_pgoff << PAGE_SHIFT) + (hva - vma->vm_start); + +#ifndef __PAGETABLE_PMD_FOLDED + if ((hva & (PUD_SIZE - 1)) == (pa & (PUD_SIZE - 1)) && + ALIGN_DOWN(hva, PUD_SIZE) >= vma->vm_start && + ALIGN(hva, PUD_SIZE) <= vma->vm_end) + return PUD_SHIFT; +#endif + + if ((hva & (PMD_SIZE - 1)) == (pa & (PMD_SIZE - 1)) && + ALIGN_DOWN(hva, PMD_SIZE) >= vma->vm_start && + ALIGN(hva, PMD_SIZE) <= vma->vm_end) + return PMD_SHIFT; + + return PAGE_SHIFT; +} + +/* + * The page will be mapped in stage 2 as Normal Cacheable, so the VM will be + * able to see the page's tags and therefore they must be initialised first. If + * PG_mte_tagged is set, tags have already been initialised. + * + * The race in the test/set of the PG_mte_tagged flag is handled by: + * - preventing VM_SHARED mappings in a memslot with MTE preventing two VMs + * racing to santise the same page + * - mmap_lock protects between a VM faulting a page in and the VMM performing + * an mprotect() to add VM_MTE + */ +static int sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn, + unsigned long size) +{ + unsigned long i, nr_pages = size >> PAGE_SHIFT; + struct page *page; + + if (!kvm_has_mte(kvm)) + return 0; + + /* + * pfn_to_online_page() is used to reject ZONE_DEVICE pages + * that may not support tags. + */ + page = pfn_to_online_page(pfn); + + if (!page) + return -EFAULT; + + for (i = 0; i < nr_pages; i++, page++) { + if (!test_bit(PG_mte_tagged, &page->flags)) { + mte_clear_page_tags(page_address(page)); + set_bit(PG_mte_tagged, &page->flags); + } + } + + return 0; +} + static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_memory_slot *memslot, unsigned long hva, unsigned long fault_status) @@ -830,6 +900,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, bool write_fault, writable, force_pte = false; bool exec_fault; bool device = false; + bool shared; unsigned long mmu_seq; struct kvm *kvm = vcpu->kvm; struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; @@ -853,7 +924,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return -EFAULT; } - /* Let's check if we will get back a huge page backed by hugetlbfs */ + /* + * Let's check if we will get back a huge page backed by hugetlbfs, or + * get block mapping for device MMIO region. + */ mmap_read_lock(current->mm); vma = find_vma_intersection(current->mm, hva, hva + 1); if (unlikely(!vma)) { @@ -862,17 +936,19 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return -EFAULT; } - if (is_vm_hugetlb_page(vma)) - vma_shift = huge_page_shift(hstate_vma(vma)); - else - vma_shift = PAGE_SHIFT; - - if (logging_active || - (vma->vm_flags & VM_PFNMAP)) { + /* + * logging_active is guaranteed to never be true for VM_PFNMAP + * memslots. + */ + if (logging_active) { force_pte = true; vma_shift = PAGE_SHIFT; + } else { + vma_shift = get_vma_page_shift(vma, hva); } + shared = (vma->vm_flags & VM_PFNMAP); + switch (vma_shift) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SHIFT: @@ -943,8 +1019,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return -EFAULT; if (kvm_is_device_pfn(pfn)) { + /* + * If the page was identified as device early by looking at + * the VMA flags, vma_pagesize is already representing the + * largest quantity we can map. If instead it was mapped + * via gfn_to_pfn_prot(), vma_pagesize is set to PAGE_SIZE + * and must not be upgraded. + * + * In both cases, we don't let transparent_hugepage_adjust() + * change things at the last minute. + */ device = true; - force_pte = true; } else if (logging_active && !write_fault) { /* * Only actually map the page as writable if this was a write @@ -965,19 +1050,25 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * If we are not forced to use page mapping, check if we are * backed by a THP and thus use block mapping if possible. */ - if (vma_pagesize == PAGE_SIZE && !force_pte) + if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) vma_pagesize = transparent_hugepage_adjust(memslot, hva, &pfn, &fault_ipa); + + if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) { + /* Check the VMM hasn't introduced a new VM_SHARED VMA */ + if (!shared) + ret = sanitise_mte_tags(kvm, pfn, vma_pagesize); + else + ret = -EFAULT; + if (ret) + goto out_unlock; + } + if (writable) prot |= KVM_PGTABLE_PROT_W; - if (fault_status != FSC_PERM && !device) - clean_dcache_guest_page(pfn, vma_pagesize); - - if (exec_fault) { + if (exec_fault) prot |= KVM_PGTABLE_PROT_X; - invalidate_icache_guest_page(pfn, vma_pagesize); - } if (device) prot |= KVM_PGTABLE_PROT_DEVICE; @@ -1168,19 +1259,22 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { kvm_pfn_t pfn = pte_pfn(range->pte); + int ret; if (!kvm->arch.mmu.pgt) return false; WARN_ON(range->end - range->start != 1); - /* - * We've moved a page around, probably through CoW, so let's treat it - * just like a translation fault and clean the cache to the PoC. - */ - clean_dcache_guest_page(pfn, PAGE_SIZE); + ret = sanitise_mte_tags(kvm, pfn, PAGE_SIZE); + if (ret) + return false; /* + * We've moved a page around, probably through CoW, so let's treat + * it just like a translation fault and the map handler will clean + * the cache to the PoC. + * * The MMU notifiers will have unmapped a huge PMD before calling * ->change_pte() (which in turn calls kvm_set_spte_gfn()) and * therefore we never need to clear out a huge PMD through this @@ -1346,7 +1440,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, { hva_t hva = mem->userspace_addr; hva_t reg_end = hva + mem->memory_size; - bool writable = !(mem->flags & KVM_MEM_READONLY); int ret = 0; if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && @@ -1363,8 +1456,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, mmap_read_lock(current->mm); /* * A memory region could potentially cover multiple VMAs, and any holes - * between them, so iterate over all of them to find out if we can map - * any of them right now. + * between them, so iterate over all of them. * * +--------------------------------------------+ * +---------------+----------------+ +----------------+ @@ -1375,51 +1467,29 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, */ do { struct vm_area_struct *vma; - hva_t vm_start, vm_end; vma = find_vma_intersection(current->mm, hva, reg_end); if (!vma) break; /* - * Take the intersection of this VMA with the memory region + * VM_SHARED mappings are not allowed with MTE to avoid races + * when updating the PG_mte_tagged page flag, see + * sanitise_mte_tags for more details. */ - vm_start = max(hva, vma->vm_start); - vm_end = min(reg_end, vma->vm_end); + if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED) + return -EINVAL; if (vma->vm_flags & VM_PFNMAP) { - gpa_t gpa = mem->guest_phys_addr + - (vm_start - mem->userspace_addr); - phys_addr_t pa; - - pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT; - pa += vm_start - vma->vm_start; - /* IO region dirty page logging not allowed */ if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; - goto out; - } - - ret = kvm_phys_addr_ioremap(kvm, gpa, pa, - vm_end - vm_start, - writable); - if (ret) break; + } } - hva = vm_end; + hva = min(reg_end, vma->vm_end); } while (hva < reg_end); - if (change == KVM_MR_FLAGS_ONLY) - goto out; - - spin_lock(&kvm->mmu_lock); - if (ret) - unmap_stage2_range(&kvm->arch.mmu, mem->guest_phys_addr, mem->memory_size); - else if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) - stage2_flush_memslot(kvm, memslot); - spin_unlock(&kvm->mmu_lock); -out: mmap_read_unlock(current->mm); return ret; } |