[PATCH v3 3/3] vfio: selftests: Test BAR write faults after clear_refs

[Mina Almasry]

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").

Use vfio_pci_find_mem_bar() to locate a memory-backed BAR of at least
2 MiB that is safe to read and write, and zap existing BAR mappings via
PCI_COMMAND_MEMORY before each sub-test to 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 an unpopulated BAR VMA after clear_refs,
   exercising vmf_insert_pfn_pmd()/vmf_insert_pfn_pud() with
   FAULT_FLAG_WRITE set.

Skip gracefully when the device has no known memory-backed BAR >= 2 MiB
or when /proc/self/clear_refs soft-dirty tracking (CONFIG_MEM_SOFT_DIRTY)
is unavailable.

Suggested-by: Alex Williamson <alex@xxxxxxxxxxx>
Cc: David Matlack <dmatlack@xxxxxxxxxx>
Cc: Matt Evans <matt@xxxxxxxxxx>
Signed-off-by: Mina Almasry <almasrymina@xxxxxxxxxx>
---
 .../selftests/vfio/vfio_pci_device_test.c     | 65 +++++++++++++++++++
 1 file changed, 65 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..323a316f59e7 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 +105,68 @@ TEST_F(vfio_pci_device_test, validate_bars)
 	}
 }
 
+static void zap_bar_mappings(struct vfio_pci_device *device)
+{
+	vfio_pci_cmd_clear(device, PCI_COMMAND_MEMORY);
+	vfio_pci_cmd_set(device, PCI_COMMAND_MEMORY);
+}
+
+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)
+{
+	struct vfio_pci_mem_bar mem_bar;
+	int ret;
+	u32 val;
+
+	if (!vfio_pci_find_mem_bar(self->device, SZ_2M, &mem_bar))
+		SKIP(return, "No memory-backed BAR >= 2M on %s\n", device_bdf);
+
+	zap_bar_mappings(self->device);
+
+	ret = clear_soft_dirty_refs();
+	if (ret == -ENOENT || ret == -EINVAL)
+		SKIP(return, "soft-dirty clear_refs unsupported (%d)\n", ret);
+	ASSERT_EQ(0, ret);
+
+	/*
+	 * clear_soft_dirty_refs() stripped write permissions from
+	 * vma->vm_page_prot on the unpopulated BAR mapping. Fault it read-only
+	 * first, then write to exercise in-place write-upgrade
+	 * (wp_huge_pmd/wp_huge_pud).
+	 */
+	val = READ_ONCE(*(u32 *)mem_bar.vaddr);
+	WRITE_ONCE(*(u32 *)mem_bar.vaddr, val);
+
+	/*
+	 * Zap the BAR PTEs/PMDs, clear soft-dirty again, and fault with an
+	 * immediate store to exercise initial write insertion
+	 * (vmf_insert_pfn_pmd/pud with write=true).
+	 */
+	zap_bar_mappings(self->device);
+	ASSERT_EQ(0, clear_soft_dirty_refs());
+
+	WRITE_ONCE(*(u32 *)mem_bar.vaddr, val);
+	(void)READ_ONCE(*(u32 *)mem_bar.vaddr);
+}
+
 FIXTURE(vfio_pci_irq_test) {
 	struct iommu *iommu;
 	struct vfio_pci_device *device;
-- 
2.56.0.385.gac671c819a-goog