summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/lapic.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-09-28 09:20:14 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2024-09-28 09:20:14 -0700
commit3efc57369a0ce8f76bf0804f7e673982384e4ac9 (patch)
tree13c88bd843f45b11fa923780e315127a828bf2b0 /arch/x86/kvm/lapic.c
parente08d227840bb9366c6321ae1e480b37ba5eec29b (diff)
parentefbc6bd090f48ccf64f7a8dd5daea775821d57ec (diff)
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull x86 kvm updates from Paolo Bonzini: "x86: - KVM currently invalidates the entirety of the page tables, not just those for the memslot being touched, when a memslot is moved or deleted. This does not traditionally have particularly noticeable overhead, but Intel's TDX will require the guest to re-accept private pages if they are dropped from the secure EPT, which is a non starter. Actually, the only reason why this is not already being done is a bug which was never fully investigated and caused VM instability with assigned GeForce GPUs, so allow userspace to opt into the new behavior. - Advertise AVX10.1 to userspace (effectively prep work for the "real" AVX10 functionality that is on the horizon) - Rework common MSR handling code to suppress errors on userspace accesses to unsupported-but-advertised MSRs This will allow removing (almost?) all of KVM's exemptions for userspace access to MSRs that shouldn't exist based on the vCPU model (the actual cleanup is non-trivial future work) - Rework KVM's handling of x2APIC ICR, again, because AMD (x2AVIC) splits the 64-bit value into the legacy ICR and ICR2 storage, whereas Intel (APICv) stores the entire 64-bit value at the ICR offset - Fix a bug where KVM would fail to exit to userspace if one was triggered by a fastpath exit handler - Add fastpath handling of HLT VM-Exit to expedite re-entering the guest when there's already a pending wake event at the time of the exit - Fix a WARN caused by RSM entering a nested guest from SMM with invalid guest state, by forcing the vCPU out of guest mode prior to signalling SHUTDOWN (the SHUTDOWN hits the VM altogether, not the nested guest) - Overhaul the "unprotect and retry" logic to more precisely identify cases where retrying is actually helpful, and to harden all retry paths against putting the guest into an infinite retry loop - Add support for yielding, e.g. to honor NEED_RESCHED, when zapping rmaps in the shadow MMU - Refactor pieces of the shadow MMU related to aging SPTEs in prepartion for adding multi generation LRU support in KVM - Don't stuff the RSB after VM-Exit when RETPOLINE=y and AutoIBRS is enabled, i.e. when the CPU has already flushed the RSB - Trace the per-CPU host save area as a VMCB pointer to improve readability and cleanup the retrieval of the SEV-ES host save area - Remove unnecessary accounting of temporary nested VMCB related allocations - Set FINAL/PAGE in the page fault error code for EPT violations if and only if the GVA is valid. If the GVA is NOT valid, there is no guest-side page table walk and so stuffing paging related metadata is nonsensical - Fix a bug where KVM would incorrectly synthesize a nested VM-Exit instead of emulating posted interrupt delivery to L2 - Add a lockdep assertion to detect unsafe accesses of vmcs12 structures - Harden eVMCS loading against an impossible NULL pointer deref (really truly should be impossible) - Minor SGX fix and a cleanup - Misc cleanups Generic: - Register KVM's cpuhp and syscore callbacks when enabling virtualization in hardware, as the sole purpose of said callbacks is to disable and re-enable virtualization as needed - Enable virtualization when KVM is loaded, not right before the first VM is created Together with the previous change, this simplifies a lot the logic of the callbacks, because their very existence implies virtualization is enabled - Fix a bug that results in KVM prematurely exiting to userspace for coalesced MMIO/PIO in many cases, clean up the related code, and add a testcase - Fix a bug in kvm_clear_guest() where it would trigger a buffer overflow _if_ the gpa+len crosses a page boundary, which thankfully is guaranteed to not happen in the current code base. Add WARNs in more helpers that read/write guest memory to detect similar bugs Selftests: - Fix a goof that caused some Hyper-V tests to be skipped when run on bare metal, i.e. NOT in a VM - Add a regression test for KVM's handling of SHUTDOWN for an SEV-ES guest - Explicitly include one-off assets in .gitignore. Past Sean was completely wrong about not being able to detect missing .gitignore entries - Verify userspace single-stepping works when KVM happens to handle a VM-Exit in its fastpath - Misc cleanups" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (127 commits) Documentation: KVM: fix warning in "make htmldocs" s390: Enable KVM_S390_UCONTROL config in debug_defconfig selftests: kvm: s390: Add VM run test case KVM: SVM: let alternatives handle the cases when RSB filling is required KVM: VMX: Set PFERR_GUEST_{FINAL,PAGE}_MASK if and only if the GVA is valid KVM: x86/mmu: Use KVM_PAGES_PER_HPAGE() instead of an open coded equivalent KVM: x86/mmu: Add KVM_RMAP_MANY to replace open coded '1' and '1ul' literals KVM: x86/mmu: Fold mmu_spte_age() into kvm_rmap_age_gfn_range() KVM: x86/mmu: Morph kvm_handle_gfn_range() into an aging specific helper KVM: x86/mmu: Honor NEED_RESCHED when zapping rmaps and blocking is allowed KVM: x86/mmu: Add a helper to walk and zap rmaps for a memslot KVM: x86/mmu: Plumb a @can_yield parameter into __walk_slot_rmaps() KVM: x86/mmu: Move walk_slot_rmaps() up near for_each_slot_rmap_range() KVM: x86/mmu: WARN on MMIO cache hit when emulating write-protected gfn KVM: x86/mmu: Detect if unprotect will do anything based on invalid_list KVM: x86/mmu: Subsume kvm_mmu_unprotect_page() into the and_retry() version KVM: x86: Rename reexecute_instruction()=>kvm_unprotect_and_retry_on_failure() KVM: x86: Update retry protection fields when forcing retry on emulation failure KVM: x86: Apply retry protection to "unprotect on failure" path KVM: x86: Check EMULTYPE_WRITE_PF_TO_SP before unprotecting gfn ...
Diffstat (limited to 'arch/x86/kvm/lapic.c')
-rw-r--r--arch/x86/kvm/lapic.c84
1 files changed, 57 insertions, 27 deletions
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 5bb481aefcbc..2098dc689088 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1944,7 +1944,7 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
u64 ns = 0;
ktime_t expire;
struct kvm_vcpu *vcpu = apic->vcpu;
- unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz;
+ u32 this_tsc_khz = vcpu->arch.virtual_tsc_khz;
unsigned long flags;
ktime_t now;
@@ -2453,6 +2453,43 @@ void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
+#define X2APIC_ICR_RESERVED_BITS (GENMASK_ULL(31, 20) | GENMASK_ULL(17, 16) | BIT(13))
+
+int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data)
+{
+ if (data & X2APIC_ICR_RESERVED_BITS)
+ return 1;
+
+ /*
+ * The BUSY bit is reserved on both Intel and AMD in x2APIC mode, but
+ * only AMD requires it to be zero, Intel essentially just ignores the
+ * bit. And if IPI virtualization (Intel) or x2AVIC (AMD) is enabled,
+ * the CPU performs the reserved bits checks, i.e. the underlying CPU
+ * behavior will "win". Arbitrarily clear the BUSY bit, as there is no
+ * sane way to provide consistent behavior with respect to hardware.
+ */
+ data &= ~APIC_ICR_BUSY;
+
+ kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32));
+ if (kvm_x86_ops.x2apic_icr_is_split) {
+ kvm_lapic_set_reg(apic, APIC_ICR, data);
+ kvm_lapic_set_reg(apic, APIC_ICR2, data >> 32);
+ } else {
+ kvm_lapic_set_reg64(apic, APIC_ICR, data);
+ }
+ trace_kvm_apic_write(APIC_ICR, data);
+ return 0;
+}
+
+static u64 kvm_x2apic_icr_read(struct kvm_lapic *apic)
+{
+ if (kvm_x86_ops.x2apic_icr_is_split)
+ return (u64)kvm_lapic_get_reg(apic, APIC_ICR) |
+ (u64)kvm_lapic_get_reg(apic, APIC_ICR2) << 32;
+
+ return kvm_lapic_get_reg64(apic, APIC_ICR);
+}
+
/* emulate APIC access in a trap manner */
void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
{
@@ -2470,7 +2507,7 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
* maybe-unecessary write, and both are in the noise anyways.
*/
if (apic_x2apic_mode(apic) && offset == APIC_ICR)
- kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR));
+ WARN_ON_ONCE(kvm_x2apic_icr_write(apic, kvm_x2apic_icr_read(apic)));
else
kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset));
}
@@ -2922,14 +2959,13 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
}
}
-int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
+void kvm_apic_ack_interrupt(struct kvm_vcpu *vcpu, int vector)
{
- int vector = kvm_apic_has_interrupt(vcpu);
struct kvm_lapic *apic = vcpu->arch.apic;
u32 ppr;
- if (vector == -1)
- return -1;
+ if (WARN_ON_ONCE(vector < 0 || !apic))
+ return;
/*
* We get here even with APIC virtualization enabled, if doing
@@ -2957,8 +2993,8 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
__apic_update_ppr(apic, &ppr);
}
- return vector;
}
+EXPORT_SYMBOL_GPL(kvm_apic_ack_interrupt);
static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
struct kvm_lapic_state *s, bool set)
@@ -2990,18 +3026,22 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
/*
* In x2APIC mode, the LDR is fixed and based on the id. And
- * ICR is internally a single 64-bit register, but needs to be
- * split to ICR+ICR2 in userspace for backwards compatibility.
+ * if the ICR is _not_ split, ICR is internally a single 64-bit
+ * register, but needs to be split to ICR+ICR2 in userspace for
+ * backwards compatibility.
*/
- if (set) {
+ if (set)
*ldr = kvm_apic_calc_x2apic_ldr(x2apic_id);
- icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) |
- (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32;
- __kvm_lapic_set_reg64(s->regs, APIC_ICR, icr);
- } else {
- icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR);
- __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32);
+ if (!kvm_x86_ops.x2apic_icr_is_split) {
+ if (set) {
+ icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) |
+ (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32;
+ __kvm_lapic_set_reg64(s->regs, APIC_ICR, icr);
+ } else {
+ icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR);
+ __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32);
+ }
}
}
@@ -3194,22 +3234,12 @@ int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
return 0;
}
-int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data)
-{
- data &= ~APIC_ICR_BUSY;
-
- kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32));
- kvm_lapic_set_reg64(apic, APIC_ICR, data);
- trace_kvm_apic_write(APIC_ICR, data);
- return 0;
-}
-
static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data)
{
u32 low;
if (reg == APIC_ICR) {
- *data = kvm_lapic_get_reg64(apic, APIC_ICR);
+ *data = kvm_x2apic_icr_read(apic);
return 0;
}