linux-kernel - [PATCH v7 1/6] vfio: refactor vfio_pci_mmap_huge

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20251126052627.43335-2-ankita@nvidia.com>
Date: Wed, 26 Nov 2025 05:26:22 +0000
From: <ankita@...dia.com>
To: <ankita@...dia.com>, <jgg@...pe.ca>, <yishaih@...dia.com>,
	<skolothumtho@...dia.com>, <kevin.tian@...el.com>, <alex@...zbot.org>,
	<aniketa@...dia.com>, <vsethi@...dia.com>, <mochs@...dia.com>
CC: <Yunxiang.Li@....com>, <yi.l.liu@...el.com>,
	<zhangdongdong@...incomputing.com>, <avihaih@...dia.com>,
	<bhelgaas@...gle.com>, <peterx@...hat.com>, <pstanner@...hat.com>,
	<apopple@...dia.com>, <kvm@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
	<cjia@...dia.com>, <kwankhede@...dia.com>, <targupta@...dia.com>,
	<zhiw@...dia.com>, <danw@...dia.com>, <dnigam@...dia.com>, <kjaju@...dia.com>
Subject: [PATCH v7 1/6] vfio: refactor vfio_pci_mmap_huge_fault function

From: Ankit Agrawal <ankita@...dia.com>

Refactor vfio_pci_mmap_huge_fault to take out the implementation
to map the VMA to the PTE/PMD/PUD as a separate function.

Export the new function to be used by nvgrace-gpu module.

No functional change is intended.

Cc: Shameer Kolothum <skolothumtho@...dia.com>
Cc: Alex Williamson <alex@...zbot.org>
Cc: Jason Gunthorpe <jgg@...pe.ca>
Reviewed-by: Shameer Kolothum <skolothumtho@...dia.com>
Signed-off-by: Ankit Agrawal <ankita@...dia.com>
---
 drivers/vfio/pci/vfio_pci_core.c | 54 +++++++++++++++++---------------
 include/linux/vfio_pci_core.h    | 16 ++++++++++
 2 files changed, 45 insertions(+), 25 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 7dcf5439dedc..52e3a10d776b 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1640,48 +1640,52 @@ 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_huge_fault(struct vm_fault *vmf,
-					   unsigned int order)
+vm_fault_t vfio_pci_vmf_insert_pfn(struct vfio_pci_core_device *vdev,
+				   struct vm_fault *vmf,
+				   unsigned long pfn,
+				   unsigned int order)
 {
-	struct vm_area_struct *vma = vmf->vma;
-	struct vfio_pci_core_device *vdev = vma->vm_private_data;
-	unsigned long addr = vmf->address & ~((PAGE_SIZE << order) - 1);
-	unsigned long pgoff = (addr - vma->vm_start) >> PAGE_SHIFT;
-	unsigned long pfn = vma_to_pfn(vma) + pgoff;
-	vm_fault_t ret = VM_FAULT_SIGBUS;
-
-	if (order && (addr < vma->vm_start ||
-		      addr + (PAGE_SIZE << order) > vma->vm_end ||
-		      pfn & ((1 << order) - 1))) {
-		ret = VM_FAULT_FALLBACK;
-		goto out;
-	}
-
-	down_read(&vdev->memory_lock);
+	lockdep_assert_held_read(&vdev->memory_lock);
 
 	if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev))
-		goto out_unlock;
+		return VM_FAULT_SIGBUS;
 
 	switch (order) {
 	case 0:
-		ret = vmf_insert_pfn(vma, vmf->address, pfn);
-		break;
+		return vmf_insert_pfn(vmf->vma, vmf->address, pfn);
 #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
 	case PMD_ORDER:
-		ret = vmf_insert_pfn_pmd(vmf, pfn, false);
-		break;
+		return vmf_insert_pfn_pmd(vmf, pfn, false);
 #endif
 #ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP
 	case PUD_ORDER:
-		ret = vmf_insert_pfn_pud(vmf, pfn, false);
+		return vmf_insert_pfn_pud(vmf, pfn, false);
 		break;
 #endif
 	default:
+		return VM_FAULT_FALLBACK;
+	}
+}
+EXPORT_SYMBOL_GPL(vfio_pci_vmf_insert_pfn);
+
+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 addr = vmf->address & ~((PAGE_SIZE << order) - 1);
+	unsigned long pgoff = (addr - vma->vm_start) >> PAGE_SHIFT;
+	unsigned long pfn = vma_to_pfn(vma) + pgoff;
+	vm_fault_t ret;
+
+	if (unmappable_for_order(vma, addr, pfn, order)) {
 		ret = VM_FAULT_FALLBACK;
+		goto out;
 	}
 
-out_unlock:
-	up_read(&vdev->memory_lock);
+	scoped_guard(rwsem_read, &vdev->memory_lock)
+		ret = vfio_pci_vmf_insert_pfn(vdev, vmf, pfn, order);
+
 out:
 	dev_dbg_ratelimited(&vdev->pdev->dev,
 			   "%s(,order = %d) BAR %ld page offset 0x%lx: 0x%x\n",
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index f541044e42a2..1d457216ce4d 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -119,6 +119,9 @@ ssize_t vfio_pci_core_read(struct vfio_device *core_vdev, char __user *buf,
 		size_t count, loff_t *ppos);
 ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *buf,
 		size_t count, loff_t *ppos);
+vm_fault_t vfio_pci_vmf_insert_pfn(struct vfio_pci_core_device *vdev,
+				   struct vm_fault *vmf, unsigned long pfn,
+				   unsigned int order);
 int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma);
 void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count);
 int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf);
@@ -161,4 +164,17 @@ VFIO_IOREAD_DECLARATION(32)
 VFIO_IOREAD_DECLARATION(64)
 #endif
 
+static inline bool unmappable_for_order(struct vm_area_struct *vma,
+					unsigned long addr,
+					unsigned long pfn,
+					unsigned int order)
+{
+	if (order && (addr < vma->vm_start ||
+		      addr + (PAGE_SIZE << order) > vma->vm_end ||
+		      !IS_ALIGNED(pfn, 1 << order)))
+		return true;
+
+	return false;
+}
+
 #endif /* VFIO_PCI_CORE_H */
-- 
2.34.1