KVM: MMU: try to fix up page faults before giving up

The vGPU folks would like to trap the first access to a BAR by setting
vm_ops on the VMAs produced by mmap-ing a VFIO device.  The fault handler
then can use remap_pfn_range to place some non-reserved pages in the VMA.

This kind of VM_PFNMAP mapping is not handled by KVM, but follow_pfn
and fixup_user_fault together help supporting it.  The patch also supports
VM_MIXEDMAP vmas where the pfns are not reserved and thus subject to
reference counting.

Cc: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Tested-by: Neo Jia <cjia@nvidia.com>
Reported-by: Kirti Wankhede <kwankhede@nvidia.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

2 files changed, 43 insertions, 3 deletions

diff --git a/mm/gup.c b/mm/gup.c
index c057784c8444..e3ac22f90fa4 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -720,6 +720,7 @@ retry:
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(fixup_user_fault);
 
 static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 						struct mm_struct *mm,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5aae59e00bef..154b9ab459b0 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1446,9 +1446,45 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
 			       unsigned long addr, bool *async,
 			       bool write_fault, kvm_pfn_t *p_pfn)
 {
-	*p_pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) +
-		vma->vm_pgoff;
-	BUG_ON(!kvm_is_reserved_pfn(*p_pfn));
+	unsigned long pfn;
+	int r;
+
+	r = follow_pfn(vma, addr, &pfn);
+	if (r) {
+		/*
+		 * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does
+		 * not call the fault handler, so do it here.
+		 */
+		bool unlocked = false;
+		r = fixup_user_fault(current, current->mm, addr,
+				     (write_fault ? FAULT_FLAG_WRITE : 0),
+				     &unlocked);
+		if (unlocked)
+			return -EAGAIN;
+		if (r)
+			return r;
+
+		r = follow_pfn(vma, addr, &pfn);
+		if (r)
+			return r;
+
+	}
+
+
+	/*
+	 * Get a reference here because callers of *hva_to_pfn* and
+	 * *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the
+	 * returned pfn.  This is only needed if the VMA has VM_MIXEDMAP
+	 * set, but the kvm_get_pfn/kvm_release_pfn_clean pair will
+	 * simply do nothing for reserved pfns.
+	 *
+	 * Whoever called remap_pfn_range is also going to call e.g.
+	 * unmap_mapping_range before the underlying pages are freed,
+	 * causing a call to our MMU notifier.
+	 */ 
+	kvm_get_pfn(pfn);
+
+	*p_pfn = pfn;
 	return 0;
 }
 
@@ -1493,12 +1529,15 @@ static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
 		goto exit;
 	}
 
+retry:
 	vma = find_vma_intersection(current->mm, addr, addr + 1);
 
 	if (vma == NULL)
 		pfn = KVM_PFN_ERR_FAULT;
 	else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) {
 		r = hva_to_pfn_remapped(vma, addr, async, write_fault, &pfn);
+		if (r == -EAGAIN)
+			goto retry;
 		if (r < 0)
 			pfn = KVM_PFN_ERR_FAULT;
 	} else {