Merge tag 'kvmarm-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for Linux 6.6

- Add support for TLB range invalidation of Stage-2 page tables,
  avoiding unnecessary invalidations. Systems that do not implement
  range invalidation still rely on a full invalidation when dealing
  with large ranges.

- Add infrastructure for forwarding traps taken from a L2 guest to
  the L1 guest, with L0 acting as the dispatcher, another baby step
  towards the full nested support.

- Simplify the way we deal with the (long deprecated) 'CPU target',
  resulting in a much needed cleanup.

- Fix another set of PMU bugs, both on the guest and host sides,
  as we seem to never have any shortage of those...

- Relax the alignment requirements of EL2 VA allocations for
  non-stack allocations, as we were otherwise wasting a lot of that
  precious VA space.

- The usual set of non-functional cleanups, although I note the lack
  of spelling fixes...

2 files changed, 30 insertions, 8 deletions

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index b74916de5183..484d0873061c 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -62,9 +62,6 @@ config HAVE_KVM_CPU_RELAX_INTERCEPT
 config KVM_VFIO
        bool
 
-config HAVE_KVM_ARCH_TLB_FLUSH_ALL
-       bool
-
 config HAVE_KVM_INVALID_WAKEUPS
        bool
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5bbb5612b207..6986402b246f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -345,7 +345,6 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
 }
 EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request);
 
-#ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
 	++kvm->stat.generic.remote_tlb_flush_requests;
@@ -361,12 +360,38 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 	 * kvm_make_all_cpus_request() reads vcpu->mode. We reuse that
 	 * barrier here.
 	 */
-	if (!kvm_arch_flush_remote_tlb(kvm)
+	if (!kvm_arch_flush_remote_tlbs(kvm)
 	    || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
 		++kvm->stat.generic.remote_tlb_flush;
 }
 EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
-#endif
+
+void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages)
+{
+	if (!kvm_arch_flush_remote_tlbs_range(kvm, gfn, nr_pages))
+		return;
+
+	/*
+	 * Fall back to a flushing entire TLBs if the architecture range-based
+	 * TLB invalidation is unsupported or can't be performed for whatever
+	 * reason.
+	 */
+	kvm_flush_remote_tlbs(kvm);
+}
+
+void kvm_flush_remote_tlbs_memslot(struct kvm *kvm,
+				   const struct kvm_memory_slot *memslot)
+{
+	/*
+	 * All current use cases for flushing the TLBs for a specific memslot
+	 * are related to dirty logging, and many do the TLB flush out of
+	 * mmu_lock. The interaction between the various operations on memslot
+	 * must be serialized by slots_locks to ensure the TLB flush from one
+	 * operation is observed by any other operation on the same memslot.
+	 */
+	lockdep_assert_held(&kvm->slots_lock);
+	kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages);
+}
 
 static void kvm_flush_shadow_all(struct kvm *kvm)
 {
@@ -2180,7 +2205,7 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 	}
 
 	if (flush)
-		kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
+		kvm_flush_remote_tlbs_memslot(kvm, memslot);
 
 	if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
 		return -EFAULT;
@@ -2297,7 +2322,7 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	KVM_MMU_UNLOCK(kvm);
 
 	if (flush)
-		kvm_arch_flush_remote_tlbs_memslot(kvm, memslot);
+		kvm_flush_remote_tlbs_memslot(kvm, memslot);
 
 	return 0;
 }