[PATCH RFC 13/19] KVM: x86: hyper-v: Direct TLB flush

[Vitaly Kuznetsov]

Handle Direct TLB flush requests from L2 by going through all vCPUs
and checking whether there are vCPUs running the same VM_ID with a
VP_ID specified in the requests. Perform synthetic exit to L2 upon
finish.

Note, while checking VM_ID/VP_ID of running vCPUs seem to be a bit
racy, we count on the fact that KVM flushes the whole L2 VPID upon
transition. Also, KVM_REQ_HV_TLB_FLUSH request needs to be done upon
transition between L1 and L2 to make sure all pending requests are
always processed.

Note, while nVMX/nSVM code does not handle VMCALL/VMMCALL from L2 yet.

Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
---
 arch/x86/kvm/hyperv.c | 65 ++++++++++++++++++++++++++++++++++++-------
 arch/x86/kvm/trace.h  | 21 ++++++++------
 2 files changed, 68 insertions(+), 18 deletions(-)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index b88e44a126b8..865b4d9a26fe 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -34,6 +34,7 @@
 #include <linux/eventfd.h>
 
 #include <asm/apicdef.h>
+#include <asm/mshyperv.h>
 #include <trace/events/kvm.h>
 
 #include "trace.h"
@@ -1863,8 +1864,8 @@ static inline int hv_tlb_flush_ring_free(struct kvm_vcpu_hv *hv_vcpu,
 	return read_idx - write_idx - 1;
 }
 
-static void hv_tlb_flush_ring_enqueue(struct kvm_vcpu *vcpu, bool flush_all,
-				      u64 *entries, int count)
+static void hv_tlb_flush_ring_enqueue(struct kvm_vcpu *vcpu, bool direct,
+				      bool flush_all, u64 *entries, int count)
 {
 	struct kvm_vcpu_hv_tlbflush_ring *tlb_flush_ring;
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
@@ -1875,7 +1876,7 @@ static void hv_tlb_flush_ring_enqueue(struct kvm_vcpu *vcpu, bool flush_all,
 	if (!hv_vcpu)
 		return;
 
-	tlb_flush_ring = &hv_vcpu->tlb_flush_ring[0];
+	tlb_flush_ring = direct ? &hv_vcpu->tlb_flush_ring[1] : &hv_vcpu->tlb_flush_ring[0];
 
 	spin_lock_irqsave(&tlb_flush_ring->write_lock, flags);
 
@@ -2010,7 +2011,8 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 		}
 
 		trace_kvm_hv_flush_tlb(flush.processor_mask,
-				       flush.address_space, flush.flags);
+				       flush.address_space, flush.flags,
+				       is_guest_mode(vcpu));
 
 		valid_bank_mask = BIT_ULL(0);
 		sparse_banks[0] = flush.processor_mask;
@@ -2041,7 +2043,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 		trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask,
 					  flush_ex.hv_vp_set.format,
 					  flush_ex.address_space,
-					  flush_ex.flags);
+					  flush_ex.flags, is_guest_mode(vcpu));
 
 		valid_bank_mask = flush_ex.hv_vp_set.valid_bank_mask;
 		all_cpus = flush_ex.hv_vp_set.format !=
@@ -2080,19 +2082,45 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 	 * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't
 	 * analyze it here, flush TLB regardless of the specified address space.
 	 */
-	if (all_cpus) {
+	if (all_cpus && !is_guest_mode(vcpu)) {
 		kvm_for_each_vcpu(i, v, kvm)
-			hv_tlb_flush_ring_enqueue(v, all_addr, entries, hc->rep_cnt);
+			hv_tlb_flush_ring_enqueue(v, false, all_addr, entries, hc->rep_cnt);
 
 		kvm_make_all_cpus_request(kvm, KVM_REQ_HV_TLB_FLUSH);
-	} else {
+	} else if (!is_guest_mode(vcpu)) {
 		sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, vcpu_mask);
 
 		for_each_set_bit(i, vcpu_mask, KVM_MAX_VCPUS) {
 			v = kvm_get_vcpu(kvm, i);
 			if (!v)
 				continue;
-			hv_tlb_flush_ring_enqueue(v, all_addr, entries, hc->rep_cnt);
+			hv_tlb_flush_ring_enqueue(v, false, all_addr, entries, hc->rep_cnt);
+		}
+
+		kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, vcpu_mask);
+	} else {
+		struct kvm_vcpu_hv *hv_v;
+
+		bitmap_zero(vcpu_mask, KVM_MAX_VCPUS);
+
+		kvm_for_each_vcpu(i, v, kvm) {
+			hv_v = to_hv_vcpu(v);
+
+			/*
+			 * TLB is fully flushed on L2 VM change: either by KVM
+			 * (on a eVMPTR switch) or by L1 hypervisor (in case it
+			 * re-purposes the active eVMCS for a different VM/VP).
+			 */
+			if (!hv_v || hv_v->nested.vm_id != hv_vcpu->nested.vm_id)
+				continue;
+
+			if (!all_cpus &&
+			    !hv_is_vp_in_sparse_set(hv_v->nested.vp_id, valid_bank_mask,
+						    sparse_banks))
+				continue;
+
+			__set_bit(i, vcpu_mask);
+			hv_tlb_flush_ring_enqueue(v, true, all_addr, entries, hc->rep_cnt);
 		}
 
 		kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, vcpu_mask);
@@ -2280,10 +2308,27 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
 
 static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
 {
+	int ret;
+
 	trace_kvm_hv_hypercall_done(result);
 	kvm_hv_hypercall_set_result(vcpu, result);
 	++vcpu->stat.hypercalls;
-	return kvm_skip_emulated_instruction(vcpu);
+	ret = kvm_skip_emulated_instruction(vcpu);
+
+	if (unlikely(hv_result_success(result) && is_guest_mode(vcpu)
+		     && kvm_hv_is_tlb_flush_hcall(vcpu))) {
+		struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+		u32 tlb_lock_count;
+
+		if (unlikely(kvm_read_guest(vcpu->kvm, hv_vcpu->nested.pa_page_gpa,
+					    &tlb_lock_count, sizeof(tlb_lock_count))))
+			kvm_inject_gp(vcpu, 0);
+
+		if (tlb_lock_count)
+			kvm_x86_ops.nested_ops->post_hv_direct_flush(vcpu);
+	}
+
+	return ret;
 }
 
 static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 193f5ba930d1..82e1646b9433 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1477,38 +1477,41 @@ TRACE_EVENT(kvm_hv_timer_state,
  * Tracepoint for kvm_hv_flush_tlb.
  */
 TRACE_EVENT(kvm_hv_flush_tlb,
-	TP_PROTO(u64 processor_mask, u64 address_space, u64 flags),
-	TP_ARGS(processor_mask, address_space, flags),
+	TP_PROTO(u64 processor_mask, u64 address_space, u64 flags, bool direct),
+	TP_ARGS(processor_mask, address_space, flags, direct),
 
 	TP_STRUCT__entry(
 		__field(u64, processor_mask)
 		__field(u64, address_space)
 		__field(u64, flags)
+		__field(bool, direct)
 	),
 
 	TP_fast_assign(
 		__entry->processor_mask = processor_mask;
 		__entry->address_space = address_space;
 		__entry->flags = flags;
+		__entry->direct = direct;
 	),
 
-	TP_printk("processor_mask 0x%llx address_space 0x%llx flags 0x%llx",
+	TP_printk("processor_mask 0x%llx address_space 0x%llx flags 0x%llx %s",
 		  __entry->processor_mask, __entry->address_space,
-		  __entry->flags)
+		  __entry->flags, __entry->direct ? "(direct)" : "")
 );
 
 /*
  * Tracepoint for kvm_hv_flush_tlb_ex.
  */
 TRACE_EVENT(kvm_hv_flush_tlb_ex,
-	TP_PROTO(u64 valid_bank_mask, u64 format, u64 address_space, u64 flags),
-	TP_ARGS(valid_bank_mask, format, address_space, flags),
+	TP_PROTO(u64 valid_bank_mask, u64 format, u64 address_space, u64 flags, bool direct),
+	TP_ARGS(valid_bank_mask, format, address_space, flags, direct),
 
 	TP_STRUCT__entry(
 		__field(u64, valid_bank_mask)
 		__field(u64, format)
 		__field(u64, address_space)
 		__field(u64, flags)
+		__field(bool, direct)
 	),
 
 	TP_fast_assign(
@@ -1516,12 +1519,14 @@ TRACE_EVENT(kvm_hv_flush_tlb_ex,
 		__entry->format = format;
 		__entry->address_space = address_space;
 		__entry->flags = flags;
+		__entry->direct = direct;
 	),
 
 	TP_printk("valid_bank_mask 0x%llx format 0x%llx "
-		  "address_space 0x%llx flags 0x%llx",
+		  "address_space 0x%llx flags 0x%llx %s",
 		  __entry->valid_bank_mask, __entry->format,
-		  __entry->address_space, __entry->flags)
+		  __entry->address_space, __entry->flags,
+		  __entry->direct ? "(direct)" : "")
 );
 
 /*
-- 
2.35.1