[PATCH v4 5/6] KVM: selftests: Make arm64's MMIO ucall multi-VM friendly

[Sean Christopherson <seanjc@google.com>]

Fix a mostly-theoretical bug where ARM's ucall MMIO setup could result in
different VMs stomping on each other by cloberring the global pointer.

Fix the most obvious issue by saving the MMIO gpa into the VM.

A more subtle bug is that creating VMs in parallel (on multiple tasks)
could result in a VM using the wrong address.  Synchronizing a global to
a guest effectively snapshots the value on a per-VM basis, i.e. the
"global" is already prepped to work with multiple VMs, but setting the
global in the host and copying it to the guest needs to happen atomically.
To fix that bug, add atomic_sync_global_pointer_to_guest() to sync
"global" pointers that hold per-VM values, i.e. technically need to be
handled in a thread-safe manner.

Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 .../selftests/kvm/include/kvm_util_base.h     | 16 +++++++++++++++
 .../testing/selftests/kvm/lib/aarch64/ucall.c | 20 ++++++++++++++-----
 2 files changed, 31 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 24fde97f6121..9ec7fbe941aa 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -16,6 +16,7 @@
 #include <linux/kvm.h>
 #include "linux/rbtree.h"
 
+#include <asm/atomic.h>
 
 #include <sys/ioctl.h>
 
@@ -81,6 +82,7 @@ struct kvm_vm {
 	struct sparsebit *vpages_mapped;
 	bool has_irqchip;
 	bool pgd_created;
+	vm_paddr_t ucall_mmio_addr;
 	vm_paddr_t pgd;
 	vm_vaddr_t gdt;
 	vm_vaddr_t tss;
@@ -714,6 +716,20 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
 	memcpy(&(g), _p, sizeof(g));				\
 })
 
+/*
+ * Sync a global pointer to the guest that has a per-VM value, in which case
+ * writes to the host copy of the "global" must be serialized (in case a test
+ * is being truly crazy and spawning multiple VMs concurrently).
+ */
+#define atomic_sync_global_pointer_to_guest(vm, g, val) ({	\
+	typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g));	\
+								\
+	while (cmpxchg(&g, NULL, val))				\
+		;						\
+	memcpy(_p, &(g), sizeof(g));				\
+	WRITE_ONCE(g, NULL);					\
+})
+
 void assert_on_unhandled_exception(struct kvm_vcpu *vcpu);
 
 void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu,
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index f02ae27c3e43..acb47c813477 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -6,20 +6,30 @@
  */
 #include "kvm_util.h"
 
+/*
+ * This "global" holds different per-VM values, it must not be accessed from
+ * host code except to sync the guest value, and that must be done atomically.
+ */
 static vm_vaddr_t *ucall_exit_mmio_addr;
 
+static void ucall_set_mmio_addr(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
+{
+	vm->ucall_mmio_addr = mmio_gpa;
+
+	atomic_sync_global_pointer_to_guest(vm, ucall_exit_mmio_addr,
+					    (vm_vaddr_t *)mmio_gpa);
+}
+
 void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
 {
 	virt_pg_map(vm, mmio_gpa, mmio_gpa);
 
-	ucall_exit_mmio_addr = (vm_vaddr_t *)mmio_gpa;
-	sync_global_to_guest(vm, ucall_exit_mmio_addr);
+	ucall_set_mmio_addr(vm, mmio_gpa);
 }
 
 void ucall_arch_uninit(struct kvm_vm *vm)
 {
-	ucall_exit_mmio_addr = 0;
-	sync_global_to_guest(vm, ucall_exit_mmio_addr);
+	ucall_set_mmio_addr(vm, (vm_paddr_t)NULL);
 }
 
 void ucall_arch_do_ucall(vm_vaddr_t uc)
@@ -32,7 +42,7 @@ void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu)
 	struct kvm_run *run = vcpu->run;
 
 	if (run->exit_reason == KVM_EXIT_MMIO &&
-	    run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) {
+	    run->mmio.phys_addr == vcpu->vm->ucall_mmio_addr) {
 		vm_vaddr_t gva;
 
 		TEST_ASSERT(run->mmio.is_write && run->mmio.len == 8,
-- 
2.37.1.595.g718a3a8f04-goog