diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-07-04 01:32:22 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-07-04 01:32:22 +0300 |
commit | e8069f5a8e3bdb5fdeeff895780529388592ee7a (patch) | |
tree | ce35ab85db9b66a7e488707fccdb33ce54f696dd /arch/x86/kvm/mmu | |
parent | eded37770c9f80ecd5ba842359c4f1058d9812c3 (diff) | |
parent | 255006adb3da71bb75c334453786df781b415f54 (diff) | |
download | linux-e8069f5a8e3bdb5fdeeff895780529388592ee7a.tar.xz |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
"ARM64:
- Eager page splitting optimization for dirty logging, optionally
allowing for a VM to avoid the cost of hugepage 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.
RISC-V:
- Redirect AMO load/store misaligned traps to KVM guest
- Trap-n-emulate AIA in-kernel irqchip for KVM guest
- Svnapot support for KVM Guest
s390:
- New uvdevice secret API
- CMM selftest and fixes
- fix racy access to target CPU for diag 9c
x86:
- Fix missing/incorrect #GP checks on ENCLS
- Use standard mmu_notifier hooks for handling APIC access page
- Drop now unnecessary TR/TSS load after VM-Exit on AMD
- Print more descriptive information about the status of SEV and
SEV-ES during module load
- Add a test for splitting and reconstituting hugepages during and
after dirty logging
- Add support for CPU pinning in demand paging test
- Add support for AMD PerfMonV2, with a variety of cleanups and minor
fixes included along the way
- Add a "nx_huge_pages=never" option to effectively avoid creating NX
hugepage recovery threads (because nx_huge_pages=off can be toggled
at runtime)
- Move handling of PAT out of MTRR code and dedup SVM+VMX code
- Fix output of PIC poll command emulation when there's an interrupt
- Add a maintainer's handbook to document KVM x86 processes,
preferred coding style, testing expectations, etc.
- Misc cleanups, fixes and comments
Generic:
- Miscellaneous bugfixes and cleanups
Selftests:
- Generate dependency files so that partial rebuilds work as
expected"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (153 commits)
Documentation/process: Add a maintainer handbook for KVM x86
Documentation/process: Add a label for the tip tree handbook's coding style
KVM: arm64: Fix misuse of KVM_ARM_VCPU_POWER_OFF bit index
RISC-V: KVM: Remove unneeded semicolon
RISC-V: KVM: Allow Svnapot extension for Guest/VM
riscv: kvm: define vcpu_sbi_ext_pmu in header
RISC-V: KVM: Expose IMSIC registers as attributes of AIA irqchip
RISC-V: KVM: Add in-kernel virtualization of AIA IMSIC
RISC-V: KVM: Expose APLIC registers as attributes of AIA irqchip
RISC-V: KVM: Add in-kernel emulation of AIA APLIC
RISC-V: KVM: Implement device interface for AIA irqchip
RISC-V: KVM: Skeletal in-kernel AIA irqchip support
RISC-V: KVM: Set kvm_riscv_aia_nr_hgei to zero
RISC-V: KVM: Add APLIC related defines
RISC-V: KVM: Add IMSIC related defines
RISC-V: KVM: Implement guest external interrupt line management
KVM: x86: Remove PRIx* definitions as they are solely for user space
s390/uv: Update query for secret-UVCs
s390/uv: replace scnprintf with sysfs_emit
s390/uvdevice: Add 'Lock Secret Store' UVC
...
Diffstat (limited to 'arch/x86/kvm/mmu')
-rw-r--r-- | arch/x86/kvm/mmu/mmu.c | 53 | ||||
-rw-r--r-- | arch/x86/kvm/mmu/tdp_mmu.c | 5 |
2 files changed, 52 insertions, 6 deletions
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6eaa3d6994ae..ec169f5c7dce 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -58,6 +58,8 @@ extern bool itlb_multihit_kvm_mitigation; +static bool nx_hugepage_mitigation_hard_disabled; + int __read_mostly nx_huge_pages = -1; static uint __read_mostly nx_huge_pages_recovery_period_ms; #ifdef CONFIG_PREEMPT_RT @@ -67,12 +69,13 @@ static uint __read_mostly nx_huge_pages_recovery_ratio = 0; static uint __read_mostly nx_huge_pages_recovery_ratio = 60; #endif +static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp); static int set_nx_huge_pages(const char *val, const struct kernel_param *kp); static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp); static const struct kernel_param_ops nx_huge_pages_ops = { .set = set_nx_huge_pages, - .get = param_get_bool, + .get = get_nx_huge_pages, }; static const struct kernel_param_ops nx_huge_pages_recovery_param_ops = { @@ -1600,6 +1603,10 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) if (tdp_mmu_enabled) flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); + if (kvm_x86_ops.set_apic_access_page_addr && + range->slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) + kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); + return flush; } @@ -5797,6 +5804,14 @@ static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu vcpu_clear_mmio_info(vcpu, addr); + /* + * Walking and synchronizing SPTEs both assume they are operating in + * the context of the current MMU, and would need to be reworked if + * this is ever used to sync the guest_mmu, e.g. to emulate INVEPT. + */ + if (WARN_ON_ONCE(mmu != vcpu->arch.mmu)) + return; + if (!VALID_PAGE(root_hpa)) return; @@ -6844,6 +6859,14 @@ static void mmu_destroy_caches(void) kmem_cache_destroy(mmu_page_header_cache); } +static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp) +{ + if (nx_hugepage_mitigation_hard_disabled) + return sprintf(buffer, "never\n"); + + return param_get_bool(buffer, kp); +} + static bool get_nx_auto_mode(void) { /* Return true when CPU has the bug, and mitigations are ON */ @@ -6860,15 +6883,29 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) bool old_val = nx_huge_pages; bool new_val; + if (nx_hugepage_mitigation_hard_disabled) + return -EPERM; + /* In "auto" mode deploy workaround only if CPU has the bug. */ - if (sysfs_streq(val, "off")) + if (sysfs_streq(val, "off")) { new_val = 0; - else if (sysfs_streq(val, "force")) + } else if (sysfs_streq(val, "force")) { new_val = 1; - else if (sysfs_streq(val, "auto")) + } else if (sysfs_streq(val, "auto")) { new_val = get_nx_auto_mode(); - else if (kstrtobool(val, &new_val) < 0) + } else if (sysfs_streq(val, "never")) { + new_val = 0; + + mutex_lock(&kvm_lock); + if (!list_empty(&vm_list)) { + mutex_unlock(&kvm_lock); + return -EBUSY; + } + nx_hugepage_mitigation_hard_disabled = true; + mutex_unlock(&kvm_lock); + } else if (kstrtobool(val, &new_val) < 0) { return -EINVAL; + } __set_nx_huge_pages(new_val); @@ -7006,6 +7043,9 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel uint old_period, new_period; int err; + if (nx_hugepage_mitigation_hard_disabled) + return -EPERM; + was_recovery_enabled = calc_nx_huge_pages_recovery_period(&old_period); err = param_set_uint(val, kp); @@ -7164,6 +7204,9 @@ int kvm_mmu_post_init_vm(struct kvm *kvm) { int err; + if (nx_hugepage_mitigation_hard_disabled) + return 0; + err = kvm_vm_create_worker_thread(kvm, kvm_nx_huge_page_recovery_worker, 0, "kvm-nx-lpage-recovery", &kvm->arch.nx_huge_page_recovery_thread); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 08340219c35a..512163d52194 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -592,7 +592,10 @@ static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm, /* * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and - * does not hold the mmu_lock. + * does not hold the mmu_lock. On failure, i.e. if a different logical + * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with + * the current value, so the caller operates on fresh data, e.g. if it + * retries tdp_mmu_set_spte_atomic() */ if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) return -EBUSY; |