Merge tag 'kvm-x86-xen-6.9' of https://github.com/kvm-x86/linux into HEAD

KVM Xen and pfncache changes for 6.9:

 - Rip out the half-baked support for using gfn_to_pfn caches to manage pages
   that are "mapped" into guests via physical addresses.

 - Add support for using gfn_to_pfn caches with only a host virtual address,
   i.e. to bypass the "gfn" stage of the cache.  The primary use case is
   overlay pages, where the guest may change the gfn used to reference the
   overlay page, but the backing hva+pfn remains the same.

 - Add an ioctl() to allow mapping Xen's shared_info page using an hva instead
   of a gpa, so that userspace doesn't need to reconfigure and invalidate the
   cache/mapping if the guest changes the gpa (but userspace keeps the resolved
   hva the same).

 - When possible, use a single host TSC value when computing the deadline for
   Xen timers in order to improve the accuracy of the timer emulation.

 - Inject pending upcall events when the vCPU software-enables its APIC to fix
   a bug where an upcall can be lost (and to follow Xen's behavior).

 - Fall back to the slow path instead of warning if "fast" IRQ delivery of Xen
   events fails, e.g. if the guest has aliased xAPIC IDs.

 - Extend gfn_to_pfn_cache's mutex to cover (de)activation (in addition to
   refresh), and drop a now-redundant acquisition of xen_lock (that was
   protecting the shared_info cache) to fix a deadlock due to recursively
   acquiring xen_lock.

1 files changed, 50 insertions, 9 deletions

diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 9ec9ab60b63e..d2ea0435f4f7 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -62,6 +62,7 @@ enum {
 	TEST_POLL_TIMEOUT,
 	TEST_POLL_MASKED,
 	TEST_POLL_WAKE,
+	SET_VCPU_INFO,
 	TEST_TIMER_PAST,
 	TEST_LOCKING_SEND_RACE,
 	TEST_LOCKING_POLL_RACE,
@@ -321,6 +322,10 @@ static void guest_code(void)
 
 	GUEST_SYNC(TEST_POLL_WAKE);
 
+	/* Set the vcpu_info to point at exactly the place it already is to
+	 * make sure the attribute is functional. */
+	GUEST_SYNC(SET_VCPU_INFO);
+
 	/* A timer wake an *unmasked* port which should wake us with an
 	 * actual interrupt, while we're polling on a different port. */
 	ports[0]++;
@@ -389,6 +394,7 @@ static int cmp_timespec(struct timespec *a, struct timespec *b)
 		return 0;
 }
 
+static struct shared_info *shinfo;
 static struct vcpu_info *vinfo;
 static struct kvm_vcpu *vcpu;
 
@@ -404,20 +410,38 @@ static void *juggle_shinfo_state(void *arg)
 {
 	struct kvm_vm *vm = (struct kvm_vm *)arg;
 
-	struct kvm_xen_hvm_attr cache_activate = {
+	struct kvm_xen_hvm_attr cache_activate_gfn = {
 		.type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
 		.u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE
 	};
 
-	struct kvm_xen_hvm_attr cache_deactivate = {
+	struct kvm_xen_hvm_attr cache_deactivate_gfn = {
 		.type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
 		.u.shared_info.gfn = KVM_XEN_INVALID_GFN
 	};
 
+	struct kvm_xen_hvm_attr cache_activate_hva = {
+		.type = KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA,
+		.u.shared_info.hva = (unsigned long)shinfo
+	};
+
+	struct kvm_xen_hvm_attr cache_deactivate_hva = {
+		.type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
+		.u.shared_info.hva = 0
+	};
+
+	int xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM);
+
 	for (;;) {
-		__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_activate);
-		__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_deactivate);
+		__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_activate_gfn);
 		pthread_testcancel();
+		__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_deactivate_gfn);
+
+		if (xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA) {
+			__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_activate_hva);
+			pthread_testcancel();
+			__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_deactivate_hva);
+		}
 	}
 
 	return NULL;
@@ -442,6 +466,7 @@ int main(int argc, char *argv[])
 	bool do_runstate_flag = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG);
 	bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL);
 	bool do_evtchn_tests = do_eventfd_tests && !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_SEND);
+	bool has_shinfo_hva = !!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA);
 
 	clock_gettime(CLOCK_REALTIME, &min_ts);
 
@@ -452,7 +477,7 @@ int main(int argc, char *argv[])
 				    SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 3, 0);
 	virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 3);
 
-	struct shared_info *shinfo = addr_gpa2hva(vm, SHINFO_VADDR);
+	shinfo = addr_gpa2hva(vm, SHINFO_VADDR);
 
 	int zero_fd = open("/dev/zero", O_RDONLY);
 	TEST_ASSERT(zero_fd != -1, "Failed to open /dev/zero");
@@ -488,10 +513,16 @@ int main(int argc, char *argv[])
 			    "Failed to read back RUNSTATE_UPDATE_FLAG attr");
 	}
 
-	struct kvm_xen_hvm_attr ha = {
-		.type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
-		.u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE,
-	};
+	struct kvm_xen_hvm_attr ha = {};
+
+	if (has_shinfo_hva) {
+		ha.type = KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA;
+		ha.u.shared_info.hva = (unsigned long)shinfo;
+	} else {
+		ha.type = KVM_XEN_ATTR_TYPE_SHARED_INFO;
+		ha.u.shared_info.gfn = SHINFO_ADDR / PAGE_SIZE;
+	}
+
 	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &ha);
 
 	/*
@@ -862,6 +893,16 @@ int main(int argc, char *argv[])
 				alarm(1);
 				break;
 
+			case SET_VCPU_INFO:
+				if (has_shinfo_hva) {
+					struct kvm_xen_vcpu_attr vih = {
+						.type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA,
+						.u.hva = (unsigned long)vinfo
+					};
+					vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &vih);
+				}
+				break;
+
 			case TEST_TIMER_PAST:
 				TEST_ASSERT(!evtchn_irq_expected,
 					    "Expected event channel IRQ but it didn't happen");