vfio/pci: Insert full vma on mmap'd MMIO fault

In order to improve performance of typical scenarios we can try to insert
the entire vma on fault.  This accelerates typical cases, such as when
the MMIO region is DMA mapped by QEMU.  The vfio_iommu_type1 driver will
fault in the entire DMA mapped range through fixup_user_fault().

In synthetic testing, this improves the time required to walk a PCI BAR
mapping from userspace by roughly 1/3rd.

This is likely an interim solution until vmf_insert_pfn_{pmd,pud}() gain
support for pfnmaps.
Suggested-by: Yan Zhao <yan.y.zhao@intel.com>
Link: https://lore.kernel.org/all/Zl6XdUkt%2FzMMGOLF@yzhao56-desk.sh.intel.com/Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Link: https://lore.kernel.org/r/20240607035213.2054226-1-alex.williamson@redhat.comSigned-off-by: Alex Williamson <alex.williamson@redhat.com>

drivers/vfio/pci/vfio_pci_core.c

@@ -1662,6 +1662,7 @@ static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf)
 	struct vm_area_struct *vma = vmf->vma;
 	struct vfio_pci_core_device *vdev = vma->vm_private_data;
 	unsigned long pfn, pgoff = vmf->pgoff - vma->vm_pgoff;
+	unsigned long addr = vma->vm_start;
 	vm_fault_t ret = VM_FAULT_SIGBUS;
 
 	pfn = vma_to_pfn(vma);
@@ -1669,11 +1670,25 @@ static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf)
 	down_read(&vdev->memory_lock);
 
 	if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev))
-		goto out_disabled;
+		goto out_unlock;
 
 	ret = vmf_insert_pfn(vma, vmf->address, pfn + pgoff);
+	if (ret & VM_FAULT_ERROR)
+		goto out_unlock;
 
-out_disabled:
+	/*
+	 * Pre-fault the remainder of the vma, abort further insertions and
+	 * supress error if fault is encountered during pre-fault.
+	 */
+	for (; addr < vma->vm_end; addr += PAGE_SIZE, pfn++) {
+		if (addr == vmf->address)
+			continue;
+
+		if (vmf_insert_pfn(vma, addr, pfn) & VM_FAULT_ERROR)
+			break;
+	}
+
+out_unlock:
 	up_read(&vdev->memory_lock);
 
 	return ret;