mm: thp: KVM: Explicitly check for THP when populating secondary MMU

Add a helper, is_transparent_hugepage(), to explicitly check whether a
compound page is a THP and use it when populating KVM's secondary MMU.
The explicit check fixes a bug where a remapped compound page, e.g. for
an XDP Rx socket, is mapped into a KVM guest and is mistaken for a THP,
which results in KVM incorrectly creating a huge page in its secondary
MMU.

Fixes: 936a5fe6e6148 ("thp: kvm mmu transparent hugepage support")
Reported-by: syzbot+c9d1fb51ac9d0d10c39d@syzkaller.appspotmail.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

6 files changed, 31 insertions, 9 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index db597f57cdc2..7eb21a22cc13 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3344,7 +3344,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 	 */
 	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
 	    !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL &&
-	    PageTransCompoundMap(pfn_to_page(pfn))) {
+	    kvm_is_transparent_hugepage(pfn)) {
 		unsigned long mask;
 
 		/*
@@ -5961,7 +5961,7 @@ restart:
 		 */
 		if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
 		    !kvm_is_zone_device_pfn(pfn) &&
-		    PageTransCompoundMap(pfn_to_page(pfn))) {
+		    kvm_is_transparent_hugepage(pfn)) {
 			pte_list_remove(rmap_head, sptep);
 
 			if (kvm_available_flush_tlb_with_range())
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 0b84e13e88e2..5aca3d1bdb32 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -160,6 +160,7 @@ extern unsigned long thp_get_unmapped_area(struct file *filp,
 
 extern void prep_transhuge_page(struct page *page);
 extern void free_transhuge_page(struct page *page);
+bool is_transparent_hugepage(struct page *page);
 
 bool can_split_huge_page(struct page *page, int *pextra_pins);
 int split_huge_page_to_list(struct page *page, struct list_head *list);
@@ -308,6 +309,11 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
 
 static inline void prep_transhuge_page(struct page *page) {}
 
+static inline bool is_transparent_hugepage(struct page *page)
+{
+	return false;
+}
+
 #define transparent_hugepage_flags 0UL
 
 #define thp_get_unmapped_area	NULL
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 48e139c293c2..46fdb7533678 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -976,6 +976,7 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
 
 bool kvm_is_reserved_pfn(kvm_pfn_t pfn);
 bool kvm_is_zone_device_pfn(kvm_pfn_t pfn);
+bool kvm_is_transparent_hugepage(kvm_pfn_t pfn);
 
 struct kvm_irq_ack_notifier {
 	struct hlist_node link;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 41a0fbddc96b..9b3ee79d0edf 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -527,6 +527,17 @@ void prep_transhuge_page(struct page *page)
 	set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
 }
 
+bool is_transparent_hugepage(struct page *page)
+{
+	if (!PageCompound(page))
+		return 0;
+
+	page = compound_head(page);
+	return is_huge_zero_page(page) ||
+	       page[1].compound_dtor == TRANSHUGE_PAGE_DTOR;
+}
+EXPORT_SYMBOL_GPL(is_transparent_hugepage);
+
 static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long len,
 		loff_t off, unsigned long flags, unsigned long size)
 {
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 0b32a904a1bb..dc8254bf30ea 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -1377,14 +1377,8 @@ static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap)
 {
 	kvm_pfn_t pfn = *pfnp;
 	gfn_t gfn = *ipap >> PAGE_SHIFT;
-	struct page *page = pfn_to_page(pfn);
 
-	/*
-	 * PageTransCompoundMap() returns true for THP and
-	 * hugetlbfs. Make sure the adjustment is done only for THP
-	 * pages.
-	 */
-	if (!PageHuge(page) && PageTransCompoundMap(page)) {
+	if (kvm_is_transparent_hugepage(pfn)) {
 		unsigned long mask;
 		/*
 		 * The address we faulted on is backed by a transparent huge
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index ffec9f427b55..64e9e9d65ed4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -191,6 +191,16 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
 	return true;
 }
 
+bool kvm_is_transparent_hugepage(kvm_pfn_t pfn)
+{
+	struct page *page = pfn_to_page(pfn);
+
+	if (!PageTransCompoundMap(page))
+		return false;
+
+	return is_transparent_hugepage(compound_head(page));
+}
+
 /*
  * Switches to specified vcpu, until a matching vcpu_put()
  */