From: Manish Honap <[email protected]>
Exercise the vfio-cxl contract on a bound CXL Type-2 device: the two VFIO
regions and the geometry capability, the HDM memory mmap (including a 2 MB
huge fault), the dword-aligned trapped decoder block, and the
lock-on-commit FSM. The decoder writes land in the per-open shadow and
each test reopens the device, so the FSM tests repeat cleanly.
Cover the HDM memory two ways: a host-CPU load/store of the mmap, and the
path a VMM actually uses, mmap plus a stage-2 IOAS map for the device's
ATS access. The mmap flag is required for the IOAS path, so assert it is
advertised rather than skipping when it is absent.
Signed-off-by: Manish Honap <[email protected]>
---
MAINTAINERS | 1 +
tools/testing/selftests/vfio/Makefile | 1 +
.../selftests/vfio/lib/vfio_pci_device.c | 57 +-
.../selftests/vfio/vfio_cxl_type2_test.c | 799 ++++++++++++++++++
4 files changed, 855 insertions(+), 3 deletions(-)
create mode 100644 tools/testing/selftests/vfio/vfio_cxl_type2_test.c
diff --git a/MAINTAINERS b/MAINTAINERS
index b9361a8d618e..192b1681b3bd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -28319,6 +28319,7 @@ L: [email protected]
S: Supported
F: Documentation/driver-api/vfio-pci-cxl.rst
F: drivers/vfio/pci/cxl/
+F: tools/testing/selftests/vfio/vfio_cxl_type2_test.c
VFIO DRIVER
M: Alex Williamson <[email protected]>
diff --git a/tools/testing/selftests/vfio/Makefile
b/tools/testing/selftests/vfio/Makefile
index 2c32c48db509..08f88e88cb4d 100644
--- a/tools/testing/selftests/vfio/Makefile
+++ b/tools/testing/selftests/vfio/Makefile
@@ -13,6 +13,7 @@ TEST_GEN_PROGS += vfio_pci_device_test
TEST_GEN_PROGS += vfio_pci_device_init_perf_test
TEST_GEN_PROGS += vfio_pci_driver_test
TEST_GEN_PROGS += vfio_pci_sriov_uapi_test
+TEST_GEN_PROGS += vfio_cxl_type2_test
TEST_FILES += scripts/cleanup.sh
TEST_FILES += scripts/lib.sh
diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c
b/tools/testing/selftests/vfio/lib/vfio_pci_device.c
index 94dc5fcecbeb..ab49b41653c4 100644
--- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c
+++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c
@@ -160,9 +160,31 @@ static void vfio_pci_region_get(struct vfio_pci_device
*device, int index,
ioctl_assert(device->fd, VFIO_DEVICE_GET_REGION_INFO, info);
}
+/* Return the sparse-mmap capability in @info, or NULL if the region has none. */
+static struct vfio_region_info_cap_sparse_mmap *
+vfio_pci_sparse_mmap_cap(struct vfio_region_info *info)
+{
+ struct vfio_info_cap_header *hdr;
+ u32 offset;
+
+ if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS))
+ return NULL;
+
+ for (offset = info->cap_offset; offset; offset = hdr->next) {
+ hdr = (void *)info + offset;
+ if (hdr->id == VFIO_REGION_INFO_CAP_SPARSE_MMAP)
+ return (struct vfio_region_info_cap_sparse_mmap *)hdr;
+ }
+
+ return NULL;
+}
+
static void vfio_pci_bar_map(struct vfio_pci_device *device, int index)
{
struct vfio_pci_bar *bar = &device->bars[index];
+ struct vfio_region_info_cap_sparse_mmap *sparse;
+ u8 infobuf[1024] = {};
+ struct vfio_region_info *info = (void *)infobuf;
size_t align, size;
int prot = 0;
void *vaddr;
@@ -190,9 +212,38 @@ static void vfio_pci_bar_map(struct vfio_pci_device
*device, int index)
align = min_t(size_t, size, SZ_1G);
vaddr = mmap_reserve(size, align, 0);
- bar->vaddr = mmap(vaddr, size, prot, MAP_SHARED | MAP_FIXED,
- device->fd, bar->info.offset);
- VFIO_ASSERT_NE(bar->vaddr, MAP_FAILED);
+
+ /*
+ * A BAR that is only partially mmappable, such as a CXL Type-2
component
+ * BAR with the HDM decoder block trapped, advertises the mmappable
+ * ranges through a sparse-mmap capability. Map each area within the
+ * reservation and leave the excluded ranges unmapped; mapping the whole
+ * BAR would be rejected.
+ */
+ info->argsz = sizeof(infobuf);
+ info->index = index;
+ ioctl_assert(device->fd, VFIO_DEVICE_GET_REGION_INFO, info);
+ sparse = vfio_pci_sparse_mmap_cap(info);
+ if (sparse) {
+ u32 i;
+
+ bar->vaddr = vaddr;
+ for (i = 0; i < sparse->nr_areas; i++) {
+ void *p;
+
+ if (!sparse->areas[i].size)
+ continue;
+ p = mmap(vaddr + sparse->areas[i].offset,
+ sparse->areas[i].size, prot,
+ MAP_SHARED | MAP_FIXED, device->fd,
+ bar->info.offset + sparse->areas[i].offset);
+ VFIO_ASSERT_NE(p, MAP_FAILED);
+ }
+ } else {
+ bar->vaddr = mmap(vaddr, size, prot, MAP_SHARED | MAP_FIXED,
+ device->fd, bar->info.offset);
+ VFIO_ASSERT_NE(bar->vaddr, MAP_FAILED);
+ }
madvise(bar->vaddr, size, MADV_HUGEPAGE);
}
diff --git a/tools/testing/selftests/vfio/vfio_cxl_type2_test.c
b/tools/testing/selftests/vfio/vfio_cxl_type2_test.c
new file mode 100644
index 000000000000..8c23ddd014ca
--- /dev/null
+++ b/tools/testing/selftests/vfio/vfio_cxl_type2_test.c
@@ -0,0 +1,799 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vfio_cxl_type2_test - corner-case tests for the vfio-cxl kernel contract.
+ *
+ * Exercises the user-visible surface the vfio-cxl module adds to a CXL Type-2
+ * device: the two VFIO regions (HDM memory and the trapped HDM decoder block),
+ * the component-register geometry capability, and the lock-on-commit decoder
+ * FSM the kernel runs on the trapped block.
+ *
+ * Unlike a plain vfio-pci device the guest programs its own endpoint decoder,
+ * so the trapped block enforces the commit handshake and freezes a locked
+ * decoder. These tests drive that FSM directly. Writes to the decoder block
+ * land in the per-open kernel shadow only, never on the physical decoder, and
+ * each test reopens the device (fresh shadow), so the FSM tests are safe to
+ * repeat and do not leak state between tests.
+ *
+ * Usage: ./vfio_cxl_type2_test <BDF> (or export VFIO_SELFTESTS_BDF=<BDF>).
+ * The device must be bound to vfio-pci with the vfio-cxl module available.
+ *
+ * Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES.
+ */
+
+#include <fcntl.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+
+#include <linux/pci_regs.h>
+#include <linux/sizes.h>
+#include <linux/vfio.h>
+
+#include <cxl/cxl_regs.h>
+
+#include <libvfio.h>
+
+#include "kselftest_harness.h"
+
+#define PCI_DVSEC_VENDOR_ID_CXL 0x1e98
+#define PCI_DVSEC_ID_CXL_DEVICE 0x0000
+
+/* CXL r3.1 8.1.9.1: Register Block Identifier for the component registers. */
+#define CXL_REGLOC_RBI_COMPONENT 1
+
+/*
+ * Register Locator DVSEC block-1 field masks. The uapi pci_regs.h names expand
+ * to __GENMASK(), which is not a macro in this userspace include path, so use
+ * explicit values.
+ */
+#define REG_LOCATOR_BIR_MASK 0x00000007
+#define REG_LOCATOR_BLOCK_ID_MASK 0x0000ff00
+#define REG_LOCATOR_BLOCK_OFF_LOW_MASK 0xffff0000
+
+/*
+ * vfio-pci's region-offset packing is kernel-internal (vfio_pci_core.h), not
+ * UAPI. Define it locally; the guards let a future kernel hoist it to UAPI.
+ */
+#ifndef VFIO_PCI_OFFSET_SHIFT
+#define VFIO_PCI_OFFSET_SHIFT 40
+#endif
+#ifndef VFIO_PCI_INDEX_TO_OFFSET
+#define VFIO_PCI_INDEX_TO_OFFSET(i) ((uint64_t)(i) << VFIO_PCI_OFFSET_SHIFT)
+#endif
+
+static const char *device_bdf;
+
+/* Locate a region-info capability by id inside a GET_REGION_INFO buffer. */
+static const struct vfio_info_cap_header *
+find_region_cap(const void *buf, size_t bufsz, uint16_t id)
+{
+ const struct vfio_region_info *ri = buf;
+ const struct vfio_info_cap_header *cap;
+ size_t off = ri->cap_offset;
+
+ while (off && off + sizeof(*cap) <= bufsz) {
+ cap = (const void *)((const char *)buf + off);
+ if (cap->id == id)
+ return cap;
+ off = cap->next;
+ }
+ return NULL;
+}
+
+/*
+ * Find a CXL region by scanning every region's VFIO_REGION_INFO_CAP_TYPE for
+ * the CXL type and the requested subtype. Returns the region index or -1.
+ * @buf is a caller scratch buffer left holding the matched region's info
+ * (with caps).
+ */
+static int find_cxl_region(int fd, uint32_t nregions, uint32_t subtype,
+ void *buf, size_t bufsz)
+{
+ uint32_t i;
+
+ for (i = 0; i < nregions; i++) {
+ struct vfio_region_info *ri = buf;
+ const struct vfio_region_info_cap_type *t;
+ const struct vfio_info_cap_header *hdr;
+
+ memset(buf, 0, bufsz);
+ ri->argsz = bufsz;
+ ri->index = i;
+ if (ioctl(fd, VFIO_DEVICE_GET_REGION_INFO, ri))
+ continue;
+ if (!(ri->flags & VFIO_REGION_INFO_FLAG_CAPS))
+ continue;
+
+ hdr = find_region_cap(buf, bufsz, VFIO_REGION_INFO_CAP_TYPE);
+ if (!hdr)
+ continue;
+ t = (const void *)hdr;
+ if (t->type == VFIO_REGION_TYPE_CXL && t->subtype == subtype)
+ return i;
+ }
+ return -1;
+}
+
+/* Walk the PCI extended capability list for the CXL Device DVSEC. */
+static uint16_t find_cxl_dvsec(struct vfio_pci_device *dev)
+{
+ uint16_t pos = PCI_CFG_SPACE_SIZE;
+ int iter = 0;
+
+ while (pos && iter++ < 64) {
+ uint32_t hdr = vfio_pci_config_readl(dev, pos);
+ uint16_t cap_id = hdr & 0xffff;
+ uint16_t next = (hdr >> 20) & 0xffc;
+ uint32_t h1, h2;
+
+ if (cap_id == PCI_EXT_CAP_ID_DVSEC) {
+ h1 = vfio_pci_config_readl(dev, pos + 4);
+ h2 = vfio_pci_config_readl(dev, pos + 8);
+ if ((h1 & 0xffff) == PCI_DVSEC_VENDOR_ID_CXL &&
+ (h2 & 0xffff) == PCI_DVSEC_ID_CXL_DEVICE)
+ return pos;
+ }
+ pos = next;
+ }
+ return 0;
+}
+
+FIXTURE(vfio_cxl) {
+ struct iommu *iommu;
+ struct vfio_pci_device *dev;
+
+ int mem_idx;
+ uint64_t mem_size;
+ uint32_t mem_flags;
+ int comp_idx;
+ uint64_t comp_size;
+ uint32_t comp_bar;
+ uint64_t comp_offset; /* HDM block offset within comp_bar */
+ uint64_t comp_off; /* mmap/rw base offset of the comp region */
+ uint16_t dvsec;
+};
+
+FIXTURE_SETUP(vfio_cxl)
+{
+ uint8_t infobuf[512] = {};
+ struct vfio_device_info *info = (void *)infobuf;
+ const struct vfio_region_info_cap_cxl_comp_regs *geo;
+ const struct vfio_info_cap_header *hdr;
+ uint8_t rbuf[1024];
+
+ self->iommu = iommu_init(default_iommu_mode);
+ self->dev = vfio_pci_device_init(device_bdf, self->iommu);
+
+ info->argsz = sizeof(infobuf);
+ ASSERT_EQ(0, ioctl(self->dev->fd, VFIO_DEVICE_GET_INFO, info));
+
+ if (!(info->flags & VFIO_DEVICE_FLAGS_CXL))
+ SKIP(return, "not a CXL Type-2 device");
+
+ self->mem_idx = find_cxl_region(self->dev->fd, info->num_regions,
+ VFIO_REGION_SUBTYPE_CXL_MEM,
+ rbuf, sizeof(rbuf));
+ ASSERT_GE(self->mem_idx, 0);
+ self->mem_size = ((struct vfio_region_info *)rbuf)->size;
+ self->mem_flags = ((struct vfio_region_info *)rbuf)->flags;
+
+ self->comp_idx = find_cxl_region(self->dev->fd, info->num_regions,
+ VFIO_REGION_SUBTYPE_CXL_COMP_REGS,
+ rbuf, sizeof(rbuf));
+ ASSERT_GE(self->comp_idx, 0);
+ self->comp_size = ((struct vfio_region_info *)rbuf)->size;
+
+ /* The geometry cap rides on the component-register region. */
+ hdr = find_region_cap(rbuf, sizeof(rbuf),
+ VFIO_REGION_INFO_CAP_CXL_COMP_REGS);
+ ASSERT_NE(NULL, hdr);
+ geo = (const void *)hdr;
+ self->comp_bar = geo->bar;
+ self->comp_offset = geo->offset;
+
+ self->comp_off = VFIO_PCI_INDEX_TO_OFFSET(self->comp_idx);
+ self->dvsec = find_cxl_dvsec(self->dev);
+}
+
+FIXTURE_TEARDOWN(vfio_cxl)
+{
+ vfio_pci_device_cleanup(self->dev);
+ iommu_cleanup(self->iommu);
+}
+
+/* GET_INFO advertises the flag and both CXL regions with a sane geometry cap.
*/
+TEST_F(vfio_cxl, device_is_cxl)
+{
+ ASSERT_NE(self->mem_idx, self->comp_idx);
+ ASSERT_GT(self->mem_size, 0);
+ ASSERT_GT(self->comp_size, 0);
+ ASSERT_LT(self->comp_bar, PCI_STD_NUM_BARS);
+ /* The HDM memory must advertise mmap; a VMM needs it for stage-2. */
+ ASSERT_NE(0, self->mem_flags & VFIO_REGION_INFO_FLAG_MMAP);
+}
+
+/*
+ * The component BAR carries the physical HDM decoder block, which vfio traps
+ * and excludes from mmap so the guest cannot reprogram it directly. Mapping
the
+ * whole BAR must fail; mapping the ranges around the excluded block, as the
+ * sparse-mmap capability advertises, must succeed.
+ */
+TEST_F(vfio_cxl, comp_bar_sparse_mmap)
+{
+ size_t page_size = getpagesize();
+ uint8_t rbuf[1024] = {};
+ struct vfio_region_info *ri = (void *)rbuf;
+ const struct vfio_region_info_cap_sparse_mmap *sm;
+ const struct vfio_info_cap_header *hdr;
+ uint64_t bar_off, decoder_page;
+ void *map;
+ uint32_t i;
+
+ /* Region info for the component BAR, with capabilities. */
+ ri->argsz = sizeof(rbuf);
+ ri->index = self->comp_bar;
+ ASSERT_EQ(0, ioctl(self->dev->fd, VFIO_DEVICE_GET_REGION_INFO, ri));
+ ASSERT_NE(0, ri->flags & VFIO_REGION_INFO_FLAG_MMAP);
+ bar_off = ri->offset;
+
+ /* The trapped decoder block splits the BAR, so it must be sparse. */
+ hdr = find_region_cap(rbuf, sizeof(rbuf),
+ VFIO_REGION_INFO_CAP_SPARSE_MMAP);
+ ASSERT_NE(NULL, hdr);
+ sm = (const void *)hdr;
+ ASSERT_GT(sm->nr_areas, 0);
+
+ /* Mapping the whole BAR must fail: it covers the excluded block. */
+ map = mmap(NULL, ri->size, PROT_READ | PROT_WRITE, MAP_SHARED,
+ self->dev->fd, bar_off);
+ ASSERT_EQ(MAP_FAILED, map);
+
+ /* Every advertised area is page aligned and must map. */
+ for (i = 0; i < sm->nr_areas; i++) {
+ uint64_t ao = sm->areas[i].offset;
+ uint64_t as = sm->areas[i].size;
+
+ if (!as)
+ continue;
+ ASSERT_EQ(0, ao & (page_size - 1));
+ ASSERT_EQ(0, as & (page_size - 1));
+
+ map = mmap(NULL, as, PROT_READ | PROT_WRITE, MAP_SHARED,
+ self->dev->fd, bar_off + ao);
+ ASSERT_NE(MAP_FAILED, map);
+ ASSERT_EQ(0, munmap(map, as));
+ }
+
+ /* The page holding the decoder block must never be mmappable. */
+ decoder_page = self->comp_offset & ~(uint64_t)(page_size - 1);
+ map = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+ self->dev->fd, bar_off + decoder_page);
+ ASSERT_EQ(MAP_FAILED, map);
+}
+
+/* mmap one page of the HDM memory, write a pattern, read it back. */
+TEST_F(vfio_cxl, hdm_mem_mmap_rw)
+{
+ uint64_t off = VFIO_PCI_INDEX_TO_OFFSET(self->mem_idx);
+ uint32_t pattern = 0xdeadbeefU, readback = 0;
+ void *map;
+
+ if (self->mem_size < SZ_4K)
+ SKIP(return, "HDM memory < 4K");
+
+ map = mmap(NULL, SZ_4K, PROT_READ | PROT_WRITE, MAP_SHARED,
+ self->dev->fd, off);
+ ASSERT_NE(MAP_FAILED, map);
+
+ memcpy(map, &pattern, sizeof(pattern));
+ memcpy(&readback, map, sizeof(readback));
+ ASSERT_EQ(pattern, readback);
+
+ ASSERT_EQ(0, munmap(map, SZ_4K));
+}
+
+/*
+ * A 2 MB-aligned window should map as a huge (PMD) fault. The kernel falls
back
+ * to base pages when it cannot, so only correctness (write/read) is asserted.
+ */
+TEST_F(vfio_cxl, hdm_mem_huge_mmap)
+{
+ uint64_t off = VFIO_PCI_INDEX_TO_OFFSET(self->mem_idx);
+ uint32_t pattern = 0x5a5a5a5aU, readback = 0;
+ void *map, *last;
+
+ if (self->mem_size < SZ_2M)
+ SKIP(return, "HDM memory < 2M");
+
+ map = mmap(NULL, SZ_2M, PROT_READ | PROT_WRITE, MAP_SHARED,
+ self->dev->fd, off);
+ ASSERT_NE(MAP_FAILED, map);
+
+ /* Touch the last dword so a 2 MB PMD fault covers the whole window. */
+ last = (char *)map + SZ_2M - sizeof(pattern);
+ memcpy(last, &pattern, sizeof(pattern));
+ memcpy(&readback, last, sizeof(readback));
+ ASSERT_EQ(pattern, readback);
+
+ ASSERT_EQ(0, munmap(map, SZ_2M));
+}
+
+/*
+ * A guest driver disables and re-enables PCI Memory-Space during init and
+ * reset. The committed HDM decoder stays valid across that toggle, so once
+ * Memory-Space is re-enabled the coherent HDM memory must be reachable again
+ * without a reset. This is the regression test for the hdm_valid access gate
+ * being cleared by a Memory-Space disable and never restored, which left a
+ * later valid mmap fault wrongly SIGBUS-ing.
+ *
+ * The region is exercised only through the mmap path (as a VMM does) and only
+ * while Memory-Space is enabled. An access with Memory-Space disabled aborts
+ * on the fabric as a fatal host error, so the test never attempts one: the
+ * toggle in between is pure config-space writes.
+ */
+TEST_F(vfio_cxl, hdm_mem_survives_mem_space_toggle)
+{
+ uint64_t off = VFIO_PCI_INDEX_TO_OFFSET(self->mem_idx);
+ uint32_t pattern = 0x12345678U, readback = 0;
+ uint16_t cmd;
+ void *map;
+
+ if (self->mem_size < SZ_4K)
+ SKIP(return, "HDM memory < 4K");
+
+ /* Seed a known pattern through the mmap path with Memory-Space on. */
+ cmd = vfio_pci_config_readw(self->dev, PCI_COMMAND);
+ vfio_pci_config_writew(self->dev, PCI_COMMAND,
+ cmd | PCI_COMMAND_MEMORY);
+ map = mmap(NULL, SZ_4K, PROT_READ | PROT_WRITE, MAP_SHARED,
+ self->dev->fd, off);
+ ASSERT_NE(MAP_FAILED, map);
+ memcpy(map, &pattern, sizeof(pattern));
+ ASSERT_EQ(0, munmap(map, SZ_4K));
+
+ /*
+ * Toggle Memory-Space off and back on with no HDM access in between,
+ * as a guest driver does during init/reset.
+ */
+ vfio_pci_config_writew(self->dev, PCI_COMMAND,
+ cmd & ~PCI_COMMAND_MEMORY);
+ vfio_pci_config_writew(self->dev, PCI_COMMAND,
+ cmd | PCI_COMMAND_MEMORY);
+
+ /*
+ * The committed decoder stayed valid across the toggle, so a fresh mmap
+ * fault succeeds and the seeded pattern reads back, without a reset.
+ * Before the fix the gate was cleared by the disable and never
restored,
+ * so the fault wrongly SIGBUS-ed.
+ */
+ map = mmap(NULL, SZ_4K, PROT_READ | PROT_WRITE, MAP_SHARED,
+ self->dev->fd, off);
+ ASSERT_NE(MAP_FAILED, map);
+ memcpy(&readback, map, sizeof(readback));
+ ASSERT_EQ(pattern, readback);
+ ASSERT_EQ(0, munmap(map, SZ_4K));
+
+ /* Restore PCI_COMMAND. */
+ vfio_pci_config_writew(self->dev, PCI_COMMAND, cmd);
+}
+
+/*
+ * Mirror how a VMM uses the region: mmap the HDM memory and map it into the
+ * IOAS (stage-2) so the device can reach it over ATS. The mmap flag is
required
+ * for that path, so its absence is a failure, not a skip. The host CPU does
not
+ * dereference the mapping; the guest reaches it through stage-2.
+ */
+TEST_F(vfio_cxl, hdm_mem_ioas_map)
+{
+ uint64_t off = VFIO_PCI_INDEX_TO_OFFSET(self->mem_idx);
+ struct iova_allocator *iova_alloc;
+ struct dma_region region;
+ void *map;
+
+ ASSERT_NE(0, self->mem_flags & VFIO_REGION_INFO_FLAG_MMAP);
+
+ /* iova_allocator_alloc() requires a power-of-2 size. */
+ if (self->mem_size < SZ_2M)
+ SKIP(return, "HDM memory < 2M");
+
+ map = mmap(NULL, SZ_2M, PROT_READ | PROT_WRITE, MAP_SHARED,
+ self->dev->fd, off);
+ ASSERT_NE(MAP_FAILED, map);
+
+ iova_alloc = iova_allocator_init(self->iommu);
+ region.vaddr = map;
+ region.size = SZ_2M;
+ region.iova = iova_allocator_alloc(iova_alloc, SZ_2M);
+
+ iommu_map(self->iommu, ®ion);
