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/x86/kvm/mmu/tdp_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/x86/kvm/mmu/tdp_mmu.c')
| -rw-r--r-- | arch/x86/kvm/mmu/tdp_mmu.c | 43 |
1 files changed, 26 insertions, 17 deletions
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d90eb364d73a..0853370bd811 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -14,10 +14,10 @@ static bool __read_mostly tdp_mmu_enabled = false; module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644); /* Initializes the TDP MMU for the VM, if enabled. */ -void kvm_mmu_init_tdp_mmu(struct kvm *kvm) +bool kvm_mmu_init_tdp_mmu(struct kvm *kvm) { if (!tdp_enabled || !READ_ONCE(tdp_mmu_enabled)) - return; + return false; /* This should not be changed for the lifetime of the VM. */ kvm->arch.tdp_mmu_enabled = true; @@ -25,6 +25,8 @@ void kvm_mmu_init_tdp_mmu(struct kvm *kvm) INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages); + + return true; } static __always_inline void kvm_lockdep_assert_mmu_lock_held(struct kvm *kvm, @@ -335,7 +337,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, for (i = 0; i < PT64_ENT_PER_PAGE; i++) { sptep = rcu_dereference(pt) + i; - gfn = base_gfn + (i * KVM_PAGES_PER_HPAGE(level - 1)); + gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); if (shared) { /* @@ -377,12 +379,12 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, WRITE_ONCE(*sptep, REMOVED_SPTE); } handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn, - old_child_spte, REMOVED_SPTE, level - 1, + old_child_spte, REMOVED_SPTE, level, shared); } kvm_flush_remote_tlbs_with_address(kvm, gfn, - KVM_PAGES_PER_HPAGE(level)); + KVM_PAGES_PER_HPAGE(level + 1)); call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); } @@ -912,7 +914,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write, kvm_pfn_t pfn, bool prefault) { u64 new_spte; - int ret = 0; + int ret = RET_PF_FIXED; int make_spte_ret = 0; if (unlikely(is_noslot_pfn(pfn))) @@ -949,7 +951,11 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, int write, rcu_dereference(iter->sptep)); } - if (!prefault) + /* + * Increase pf_fixed in both RET_PF_EMULATE and RET_PF_FIXED to be + * consistent with legacy MMU behavior. + */ + if (ret != RET_PF_SPURIOUS) vcpu->stat.pf_fixed++; return ret; @@ -977,11 +983,6 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, int level; int req_level; - if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa))) - return RET_PF_RETRY; - if (WARN_ON(!is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa))) - return RET_PF_RETRY; - level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn, huge_page_disallowed, &req_level); @@ -1024,7 +1025,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, if (is_removed_spte(iter.old_spte)) break; - sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level); + sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level - 1); child_pt = sp->spt; new_spte = make_nonleaf_spte(child_pt, @@ -1462,15 +1463,22 @@ bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, * Returns true if an SPTE was set and a TLB flush is needed. */ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t gfn) + gfn_t gfn, int min_level) { struct tdp_iter iter; u64 new_spte; bool spte_set = false; + BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL); + rcu_read_lock(); - tdp_root_for_each_leaf_pte(iter, root, gfn, gfn + 1) { + for_each_tdp_pte_min_level(iter, root->spt, root->role.level, + min_level, gfn, gfn + 1) { + if (!is_shadow_present_pte(iter.old_spte) || + !is_last_spte(iter.old_spte, iter.level)) + continue; + if (!is_writable_pte(iter.old_spte)) break; @@ -1492,14 +1500,15 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root, * Returns true if an SPTE was set and a TLB flush is needed. */ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn) + struct kvm_memory_slot *slot, gfn_t gfn, + int min_level) { struct kvm_mmu_page *root; bool spte_set = false; lockdep_assert_held_write(&kvm->mmu_lock); for_each_tdp_mmu_root(kvm, root, slot->as_id) - spte_set |= write_protect_gfn(kvm, root, gfn); + spte_set |= write_protect_gfn(kvm, root, gfn, min_level); return spte_set; } |