vfio/pci: implement huge_fault support

With the addition of pfnmap support in vmf_insert_pfn_{pmd,pud}() we can
take advantage of PMD and PUD faults to PCI BAR mmaps and create more
efficient mappings.  PCI BARs are always a power of two and will typically
get at least PMD alignment without userspace even trying.  Userspace
alignment for PUD mappings is also not too difficult.

Consolidate faults through a single handler with a new wrapper for
standard single page faults.  The pre-faulting behavior of commit
d71a989cf5 ("vfio/pci: Insert full vma on mmap'd MMIO fault") is removed
in this refactoring since huge_fault will cover the bulk of the faults and
results in more efficient page table usage.  We also want to avoid that
pre-faulted single page mappings preempt huge page mappings.

Link: https://lkml.kernel.org/r/20240826204353.2228736-20-peterx@redhat.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Gavin Shan <gshan@redhat.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Niklas Schnelle <schnelle@linux.ibm.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

drivers/vfio/pci/vfio_pci_core.c

@@ -20,6 +20,7 @@
 #include <linux/mutex.h>
 #include <linux/notifier.h>
 #include <linux/pci.h>
+#include <linux/pfn_t.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -1657,14 +1658,20 @@ static unsigned long vma_to_pfn(struct vm_area_struct *vma)
 	return (pci_resource_start(vdev->pdev, index) >> PAGE_SHIFT) + pgoff;
 }
 
-static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf)
+static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf,
+					   unsigned int order)
 {
 	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;
 
+	if (order && (vmf->address & ((PAGE_SIZE << order) - 1) ||
+		      vmf->address + (PAGE_SIZE << order) > vma->vm_end)) {
+		ret = VM_FAULT_FALLBACK;
+		goto out;
+	}
+
 	pfn = vma_to_pfn(vma);
 
 	down_read(&vdev->memory_lock);
@@ -1672,30 +1679,49 @@ static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf)
 	if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev))
 		goto out_unlock;
 
+	switch (order) {
+	case 0:
 		ret = vmf_insert_pfn(vma, vmf->address, pfn + pgoff);
-	if (ret & VM_FAULT_ERROR)
-		goto out_unlock;
-
-	/*
-	 * 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;
+#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
+	case PMD_ORDER:
+		ret = vmf_insert_pfn_pmd(vmf, __pfn_to_pfn_t(pfn + pgoff,
+							     PFN_DEV), false);
+		break;
+#endif
+#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP
+	case PUD_ORDER:
+		ret = vmf_insert_pfn_pud(vmf, __pfn_to_pfn_t(pfn + pgoff,
+							     PFN_DEV), false);
+		break;
+#endif
+	default:
+		ret = VM_FAULT_FALLBACK;
 	}
 
 out_unlock:
 	up_read(&vdev->memory_lock);
+out:
+	dev_dbg_ratelimited(&vdev->pdev->dev,
+			   "%s(,order = %d) BAR %ld page offset 0x%lx: 0x%x\n",
+			    __func__, order,
+			    vma->vm_pgoff >>
+				(VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT),
+			    pgoff, (unsigned int)ret);
 
 	return ret;
 }
 
+static vm_fault_t vfio_pci_mmap_page_fault(struct vm_fault *vmf)
+{
+	return vfio_pci_mmap_huge_fault(vmf, 0);
+}
+
 static const struct vm_operations_struct vfio_pci_mmap_ops = {
-	.fault = vfio_pci_mmap_fault,
+	.fault = vfio_pci_mmap_page_fault,
+#ifdef CONFIG_ARCH_SUPPORTS_HUGE_PFNMAP
+	.huge_fault = vfio_pci_mmap_huge_fault,
+#endif
 };
 
 int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma)