[PATCH v2 2/2] vfio: selftests: Test BAR write faults after clear_refs

From: Mina Almasry

Date: Sun Nov 01 2026 - 01:22:28 EST


Add a regression test in vfio_pci_device_test to verify that huge_fault
on writable MAP_SHARED VFIO PCI BAR mappings handles write faults after
soft-dirty tracking clears VM_SOFTDIRTY and downgrades vma->vm_page_prot
to read-only via /proc/self/clear_refs ("4").

Specifically, for each mappable read/write BAR (already aligned up to
SZ_1G by vfio_pci_bar_map() with MADV_HUGEPAGE), verify both:

1. Read-then-write fault sequence after clear_refs, exercising in-place
huge PMD/PUD write-protection upgrade via wp_huge_pmd()/wp_huge_pud().
2. Direct initial write fault on a freshly mapped unpopulated BAR VMA
after clear_refs, exercising vmf_insert_pfn_pmd()/vmf_insert_pfn_pud()
with FAULT_FLAG_WRITE set.

Skip gracefully when /proc/self/clear_refs is absent or soft-dirty
tracking (CONFIG_MEM_SOFT_DIRTY) is disabled, or when the device exposes
no mappable read/write BARs.

Cc: David Matlack <dmatlack@xxxxxxxxxx>
Signed-off-by: Mina Almasry <almasrymina@xxxxxxxxxx>
---
.../selftests/vfio/vfio_pci_device_test.c | 83 +++++++++++++++++++
1 file changed, 83 insertions(+)

diff --git a/tools/testing/selftests/vfio/vfio_pci_device_test.c b/tools/testing/selftests/vfio/vfio_pci_device_test.c
index 93c11fd5e081..75ccc557efb9 100644
--- a/tools/testing/selftests/vfio/vfio_pci_device_test.c
+++ b/tools/testing/selftests/vfio/vfio_pci_device_test.c
@@ -1,10 +1,13 @@
// SPDX-License-Identifier: GPL-2.0-only
+#include <errno.h>
#include <fcntl.h>
#include <stdlib.h>
+#include <unistd.h>

#include <sys/ioctl.h>
#include <sys/mman.h>

+#include <linux/compiler.h>
#include <linux/limits.h>
#include <linux/pci_regs.h>
#include <linux/sizes.h>
@@ -102,6 +105,86 @@ TEST_F(vfio_pci_device_test, validate_bars)
}
}

+static int clear_soft_dirty_refs(void)
+{
+ ssize_t ret;
+ int fd;
+
+ fd = open("/proc/self/clear_refs", O_WRONLY);
+ if (fd < 0)
+ return -errno;
+
+ ret = write(fd, "4\n", 2);
+ if (ret < 0)
+ ret = -errno;
+ else
+ VFIO_ASSERT_EQ(ret, 2);
+
+ VFIO_ASSERT_EQ(close(fd), 0);
+ return ret < 0 ? ret : 0;
+}
+
+TEST_F(vfio_pci_device_test, bar_write_fault_after_clear_refs)
+{
+ const u32 rw_mmap_flags = VFIO_REGION_INFO_FLAG_MMAP |
+ VFIO_REGION_INFO_FLAG_READ |
+ VFIO_REGION_INFO_FLAG_WRITE;
+ struct vfio_pci_bar *bar;
+ bool tested = false;
+ int ret, i;
+ u32 val;
+
+ ret = clear_soft_dirty_refs();
+ if (ret == -ENOENT || ret == -EINVAL)
+ SKIP(return, "soft-dirty clear_refs unsupported (%d)\n", ret);
+ ASSERT_EQ(0, ret);
+
+ vfio_pci_cmd_set(self->device, PCI_COMMAND_MEMORY);
+
+ for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+ void *vaddr;
+
+ bar = &self->device->bars[i];
+ if ((bar->info.flags & rw_mmap_flags) != rw_mmap_flags)
+ continue;
+
+ ASSERT_NE(NULL, bar->vaddr);
+
+ /*
+ * clear_soft_dirty_refs() stripped write permissions from
+ * vma->vm_page_prot on the unpopulated BAR mapping created by
+ * vfio_pci_device_init(). Fault it read-only first, then write
+ * to exercise in-place write-upgrade (wp_huge_pmd/wp_huge_pud).
+ */
+ val = READ_ONCE(*(u32 *)bar->vaddr);
+ WRITE_ONCE(*(u32 *)bar->vaddr, val);
+
+ /*
+ * Replace the VMA with a fresh unpopulated mapping at the same
+ * hugepage-aligned address, clear soft-dirty again, and fault
+ * with an immediate store to exercise initial write insertion
+ * (vmf_insert_pfn_pmd/pud with write=true).
+ */
+ vaddr = mmap(bar->vaddr, bar->info.size, PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_FIXED, self->device->fd,
+ bar->info.offset);
+ ASSERT_EQ(bar->vaddr, vaddr);
+ madvise(bar->vaddr, bar->info.size, MADV_HUGEPAGE);
+
+ ASSERT_EQ(0, clear_soft_dirty_refs());
+
+ WRITE_ONCE(*(u32 *)bar->vaddr, val);
+ (void)READ_ONCE(*(u32 *)bar->vaddr);
+
+ tested = true;
+ }
+
+ vfio_pci_cmd_clear(self->device, PCI_COMMAND_MEMORY);
+
+ if (!tested)
+ SKIP(return, "No mappable read/write BAR on %s\n", device_bdf);
+}
+
FIXTURE(vfio_pci_irq_test) {
struct iommu *iommu;
struct vfio_pci_device *device;
--
2.56.0.385.gac671c819a-goog