[RFC PATCH v2 07/19] KVM: x86: Make memory attribute helpers more generic

[Mickaël Salaün]

To make it useful for other use cases such as Heki, remove the private
memory optimizations.

I guess we could try to infer the applied attributes to get back these
optimizations when it makes sense, but let's keep this simple for now.

Main changes:

- Replace slots_lock with slots_arch_lock to make it callable from a KVM
  hypercall.

- Move this mutex lock into kvm_vm_ioctl_set_mem_attributes() to make it
  easier to use with other locks.

- Export kvm_vm_set_mem_attributes().

- Remove the kvm_arch_pre_set_memory_attributes() and
  kvm_arch_post_set_memory_attributes() KVM_MEMORY_ATTRIBUTE_PRIVATE
  optimizations.

Cc: Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Madhavan T. Venkataraman <madvenka@xxxxxxxxxxxxxxxxxxx>
Cc: Sean Christopherson <seanjc@xxxxxxxxxx>
Cc: Yu Zhang <yu.c.zhang@xxxxxxxxxxxxxxx>
Signed-off-by: Mickaël Salaün <mic@xxxxxxxxxxx>
---

Changes since v1:
* New patch
---
 arch/x86/kvm/mmu/mmu.c   | 23 -----------------------
 include/linux/kvm_host.h |  2 ++
 virt/kvm/kvm_main.c      | 19 ++++++++++---------
 3 files changed, 12 insertions(+), 32 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 7e053973125c..4d378d308762 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7251,20 +7251,6 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
 bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 					struct kvm_gfn_range *range)
 {
-	/*
-	 * Zap SPTEs even if the slot can't be mapped PRIVATE.  KVM x86 only
-	 * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM
-	 * can simply ignore such slots.  But if userspace is making memory
-	 * PRIVATE, then KVM must prevent the guest from accessing the memory
-	 * as shared.  And if userspace is making memory SHARED and this point
-	 * is reached, then at least one page within the range was previously
-	 * PRIVATE, i.e. the slot's possible hugepage ranges are changing.
-	 * Zapping SPTEs in this case ensures KVM will reassess whether or not
-	 * a hugepage can be used for affected ranges.
-	 */
-	if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
-		return false;
-
 	return kvm_unmap_gfn_range(kvm, range);
 }
 
@@ -7313,15 +7299,6 @@ bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
 	lockdep_assert_held_write(&kvm->mmu_lock);
 	lockdep_assert_held(&kvm->slots_lock);
 
-	/*
-	 * Calculate which ranges can be mapped with hugepages even if the slot
-	 * can't map memory PRIVATE.  KVM mustn't create a SHARED hugepage over
-	 * a range that has PRIVATE GFNs, and conversely converting a range to
-	 * SHARED may now allow hugepages.
-	 */
-	if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm)))
-		return false;
-
 	/*
 	 * The sequence matters here: upper levels consume the result of lower
 	 * level's scanning.
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ec32af17add8..85b8648fd892 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2396,6 +2396,8 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
 					struct kvm_gfn_range *range);
 bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
 					 struct kvm_gfn_range *range);
+int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+			      unsigned long attributes);
 
 static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
 {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 23633984142f..0096ccfbb609 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2552,7 +2552,7 @@ static bool kvm_pre_set_memory_attributes(struct kvm *kvm,
 }
 
 /* Set @attributes for the gfn range [@start, @end). */
-static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
 				     unsigned long attributes)
 {
 	struct kvm_mmu_notifier_range pre_set_range = {
@@ -2577,11 +2577,11 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
 
 	entry = attributes ? xa_mk_value(attributes) : NULL;
 
-	mutex_lock(&kvm->slots_lock);
+	lockdep_assert_held(&kvm->slots_arch_lock);
 
 	/* Nothing to do if the entire range as the desired attributes. */
 	if (kvm_range_has_memory_attributes(kvm, start, end, attributes))
-		goto out_unlock;
+		return r;
 
 	/*
 	 * Reserve memory ahead of time to avoid having to deal with failures
@@ -2590,7 +2590,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
 	for (i = start; i < end; i++) {
 		r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT);
 		if (r)
-			goto out_unlock;
+			return r;
 	}
 
 	kvm_handle_gfn_range(kvm, &pre_set_range);
@@ -2602,15 +2602,13 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
 	}
 
 	kvm_handle_gfn_range(kvm, &post_set_range);
-
-out_unlock:
-	mutex_unlock(&kvm->slots_lock);
-
 	return r;
 }
+
 static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm,
 					   struct kvm_memory_attributes *attrs)
 {
+	int r;
 	gfn_t start, end;
 
 	/* flags is currently not used. */
@@ -2633,7 +2631,10 @@ static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm,
 	 */
 	BUILD_BUG_ON(sizeof(attrs->attributes) != sizeof(unsigned long));
 
-	return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes);
+	mutex_lock(&kvm->slots_arch_lock);
+	r = kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes);
+	mutex_unlock(&kvm->slots_arch_lock);
+	return r;
 }
 #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
 
-- 
2.42.1