Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "This is a large update by KVM standards, including AMD PSP (Platform
  Security Processor, aka "AMD Secure Technology") and ARM CoreSight
  (debug and trace) changes.

  ARM:

   - CoreSight: Add support for ETE and TRBE

   - Stage-2 isolation for the host kernel when running in protected
     mode

   - Guest SVE support when running in nVHE mode

   - Force W^X hypervisor mappings in nVHE mode

   - ITS save/restore for guests using direct injection with GICv4.1

   - nVHE panics now produce readable backtraces

   - Guest support for PTP using the ptp_kvm driver

   - Performance improvements in the S2 fault handler

  x86:

   - AMD PSP driver changes

   - Optimizations and cleanup of nested SVM code

   - AMD: Support for virtual SPEC_CTRL

   - Optimizations of the new MMU code: fast invalidation, zap under
     read lock, enable/disably dirty page logging under read lock

   - /dev/kvm API for AMD SEV live migration (guest API coming soon)

   - support SEV virtual machines sharing the same encryption context

   - support SGX in virtual machines

   - add a few more statistics

   - improved directed yield heuristics

   - Lots and lots of cleanups

  Generic:

   - Rework of MMU notifier interface, simplifying and optimizing the
     architecture-specific code

   - a handful of "Get rid of oprofile leftovers" patches

   - Some selftests improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (379 commits)
  KVM: selftests: Speed up set_memory_region_test
  selftests: kvm: Fix the check of return value
  KVM: x86: Take advantage of kvm_arch_dy_has_pending_interrupt()
  KVM: SVM: Skip SEV cache flush if no ASIDs have been used
  KVM: SVM: Remove an unnecessary prototype declaration of sev_flush_asids()
  KVM: SVM: Drop redundant svm_sev_enabled() helper
  KVM: SVM: Move SEV VMCB tracking allocation to sev.c
  KVM: SVM: Explicitly check max SEV ASID during sev_hardware_setup()
  KVM: SVM: Unconditionally invoke sev_hardware_teardown()
  KVM: SVM: Enable SEV/SEV-ES functionality by default (when supported)
  KVM: SVM: Condition sev_enabled and sev_es_enabled on CONFIG_KVM_AMD_SEV=y
  KVM: SVM: Append "_enabled" to module-scoped SEV/SEV-ES control variables
  KVM: SEV: Mask CPUID[0x8000001F].eax according to supported features
  KVM: SVM: Move SEV module params/variables to sev.c
  KVM: SVM: Disable SEV/SEV-ES if NPT is disabled
  KVM: SVM: Free sev_asid_bitmap during init if SEV setup fails
  KVM: SVM: Zero out the VMCB array used to track SEV ASID association
  x86/sev: Drop redundant and potentially misleading 'sev_enabled'
  KVM: x86: Move reverse CPUID helpers to separate header file
  KVM: x86: Rename GPR accessors to make mode-aware variants the defaults
  ...

1 files changed, 57 insertions, 12 deletions

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index bb2752d78fe3..81edbd23d371 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -17,6 +17,7 @@
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
 #include <asm/barrier.h>
+#include <linux/atomic.h>
 
 #include "kvm_util.h"
 #include "test_util.h"
@@ -137,12 +138,20 @@ static uint64_t host_clear_count;
 static uint64_t host_track_next_count;
 
 /* Whether dirty ring reset is requested, or finished */
-static sem_t dirty_ring_vcpu_stop;
-static sem_t dirty_ring_vcpu_cont;
+static sem_t sem_vcpu_stop;
+static sem_t sem_vcpu_cont;
+/*
+ * This is only set by main thread, and only cleared by vcpu thread.  It is
+ * used to request vcpu thread to stop at the next GUEST_SYNC, since GUEST_SYNC
+ * is the only place that we'll guarantee both "dirty bit" and "dirty data"
+ * will match.  E.g., SIG_IPI won't guarantee that if the vcpu is interrupted
+ * after setting dirty bit but before the data is written.
+ */
+static atomic_t vcpu_sync_stop_requested;
 /*
  * This is updated by the vcpu thread to tell the host whether it's a
  * ring-full event.  It should only be read until a sem_wait() of
- * dirty_ring_vcpu_stop and before vcpu continues to run.
+ * sem_vcpu_stop and before vcpu continues to run.
  */
 static bool dirty_ring_vcpu_ring_full;
 /*
@@ -234,6 +243,17 @@ static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
 }
 
+/* Should only be called after a GUEST_SYNC */
+static void vcpu_handle_sync_stop(void)
+{
+	if (atomic_read(&vcpu_sync_stop_requested)) {
+		/* It means main thread is sleeping waiting */
+		atomic_set(&vcpu_sync_stop_requested, false);
+		sem_post(&sem_vcpu_stop);
+		sem_wait_until(&sem_vcpu_cont);
+	}
+}
+
 static void default_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 {
 	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
@@ -244,6 +264,8 @@ static void default_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 	TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC,
 		    "Invalid guest sync status: exit_reason=%s\n",
 		    exit_reason_str(run->exit_reason));
+
+	vcpu_handle_sync_stop();
 }
 
 static bool dirty_ring_supported(void)
@@ -301,13 +323,13 @@ static void dirty_ring_wait_vcpu(void)
 {
 	/* This makes sure that hardware PML cache flushed */
 	vcpu_kick();
-	sem_wait_until(&dirty_ring_vcpu_stop);
+	sem_wait_until(&sem_vcpu_stop);
 }
 
 static void dirty_ring_continue_vcpu(void)
 {
 	pr_info("Notifying vcpu to continue\n");
-	sem_post(&dirty_ring_vcpu_cont);
+	sem_post(&sem_vcpu_cont);
 }
 
 static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot,
@@ -361,11 +383,11 @@ static void dirty_ring_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 		/* Update the flag first before pause */
 		WRITE_ONCE(dirty_ring_vcpu_ring_full,
 			   run->exit_reason == KVM_EXIT_DIRTY_RING_FULL);
-		sem_post(&dirty_ring_vcpu_stop);
+		sem_post(&sem_vcpu_stop);
 		pr_info("vcpu stops because %s...\n",
 			dirty_ring_vcpu_ring_full ?
 			"dirty ring is full" : "vcpu is kicked out");
-		sem_wait_until(&dirty_ring_vcpu_cont);
+		sem_wait_until(&sem_vcpu_cont);
 		pr_info("vcpu continues now.\n");
 	} else {
 		TEST_ASSERT(false, "Invalid guest sync status: "
@@ -377,7 +399,7 @@ static void dirty_ring_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 static void dirty_ring_before_vcpu_join(void)
 {
 	/* Kick another round of vcpu just to make sure it will quit */
-	sem_post(&dirty_ring_vcpu_cont);
+	sem_post(&sem_vcpu_cont);
 }
 
 struct log_mode {
@@ -505,9 +527,8 @@ static void *vcpu_worker(void *data)
 	 */
 	sigmask->len = 8;
 	pthread_sigmask(0, NULL, sigset);
+	sigdelset(sigset, SIG_IPI);
 	vcpu_ioctl(vm, VCPU_ID, KVM_SET_SIGNAL_MASK, sigmask);
-	sigaddset(sigset, SIG_IPI);
-	pthread_sigmask(SIG_BLOCK, sigset, NULL);
 
 	sigemptyset(sigset);
 	sigaddset(sigset, SIG_IPI);
@@ -768,7 +789,25 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		usleep(p->interval * 1000);
 		log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX,
 					     bmap, host_num_pages);
+
+		/*
+		 * See vcpu_sync_stop_requested definition for details on why
+		 * we need to stop vcpu when verify data.
+		 */
+		atomic_set(&vcpu_sync_stop_requested, true);
+		sem_wait_until(&sem_vcpu_stop);
+		/*
+		 * NOTE: for dirty ring, it's possible that we didn't stop at
+		 * GUEST_SYNC but instead we stopped because ring is full;
+		 * that's okay too because ring full means we're only missing
+		 * the flush of the last page, and since we handle the last
+		 * page specially verification will succeed anyway.
+		 */
+		assert(host_log_mode == LOG_MODE_DIRTY_RING ||
+		       atomic_read(&vcpu_sync_stop_requested) == false);
 		vm_dirty_log_verify(mode, bmap);
+		sem_post(&sem_vcpu_cont);
+
 		iteration++;
 		sync_global_to_guest(vm, iteration);
 	}
@@ -818,9 +857,10 @@ int main(int argc, char *argv[])
 		.interval = TEST_HOST_LOOP_INTERVAL,
 	};
 	int opt, i;
+	sigset_t sigset;
 
-	sem_init(&dirty_ring_vcpu_stop, 0, 0);
-	sem_init(&dirty_ring_vcpu_cont, 0, 0);
+	sem_init(&sem_vcpu_stop, 0, 0);
+	sem_init(&sem_vcpu_cont, 0, 0);
 
 	guest_modes_append_default();
 
@@ -876,6 +916,11 @@ int main(int argc, char *argv[])
 
 	srandom(time(0));
 
+	/* Ensure that vCPU threads start with SIG_IPI blocked.  */
+	sigemptyset(&sigset);
+	sigaddset(&sigset, SIG_IPI);
+	pthread_sigmask(SIG_BLOCK, &sigset, NULL);
+
 	if (host_log_mode_option == LOG_MODE_ALL) {
 		/* Run each log mode */
 		for (i = 0; i < LOG_MODE_NUM; i++) {