summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/ABI/testing/debugfs-vfio26
-rw-r--r--drivers/vfio/debugfs.c1
-rw-r--r--drivers/vfio/pci/mlx5/cmd.h15
-rw-r--r--drivers/vfio/pci/vfio_pci.c30
-rw-r--r--drivers/vfio/pci/vfio_pci_core.c101
-rw-r--r--drivers/vfio/vfio_main.c8
-rw-r--r--include/linux/vfio_pci_core.h18
-rw-r--r--tools/testing/selftests/vfio/Makefile2
-rw-r--r--tools/testing/selftests/vfio/lib/libvfio.mk2
9 files changed, 152 insertions, 51 deletions
diff --git a/Documentation/ABI/testing/debugfs-vfio b/Documentation/ABI/testing/debugfs-vfio
index 70ec2d454686..ed2f29c3a9b4 100644
--- a/Documentation/ABI/testing/debugfs-vfio
+++ b/Documentation/ABI/testing/debugfs-vfio
@@ -29,3 +29,29 @@ Date: Oct 2025
KernelVersion: 6.18
Contact: Cédric Le Goater <clg@redhat.com>
Description: Read the migration features of the vfio device.
+
+What: /sys/kernel/debug/vfio/<device>/pci
+Date: June 2026
+KernelVersion: 7.2
+Contact: Alex Williamson <alex.williamson@nvidia.com>
+Description: This debugfs file directory is used for debugging
+ VFIO PCI devices.
+
+What: /sys/kernel/debug/vfio/<device>/pci/nointxmask
+Date: June 2026
+KernelVersion: 7.2
+Contact: Alex Williamson <alex.williamson@nvidia.com>
+Description: Read the nointxmask policy latched for this device. This
+ policy governs whether the device may use PCI 2.3 style
+ INTx masking when supported, reporting a value of "N", or
+ requires APIC level INTx masking, reporting a value of "Y".
+
+What: /sys/kernel/debug/vfio/<device>/pci/disable_idle_d3
+Date: June 2026
+KernelVersion: 7.2
+Contact: Alex Williamson <alex.williamson@nvidia.com>
+Description: Read the disable_idle_d3 policy latched for this device. This
+ policy governs whether the device PM runtime usage count is
+ kept elevated while the device is bound to the driver and
+ unused, reporting a value of "Y", or decremented to allow the
+ device to enter a low power state, reporting a value of "N".
diff --git a/drivers/vfio/debugfs.c b/drivers/vfio/debugfs.c
index 8b0ca7a09064..8a2f1b0cce3f 100644
--- a/drivers/vfio/debugfs.c
+++ b/drivers/vfio/debugfs.c
@@ -97,6 +97,7 @@ void vfio_device_debugfs_init(struct vfio_device *vdev)
void vfio_device_debugfs_exit(struct vfio_device *vdev)
{
debugfs_remove_recursive(vdev->debug_root);
+ vdev->debug_root = NULL;
}
void vfio_debugfs_create_root(void)
diff --git a/drivers/vfio/pci/mlx5/cmd.h b/drivers/vfio/pci/mlx5/cmd.h
index deed0f132f39..c86d8b243a52 100644
--- a/drivers/vfio/pci/mlx5/cmd.h
+++ b/drivers/vfio/pci/mlx5/cmd.h
@@ -158,26 +158,29 @@ struct mlx5_vhca_qp {
struct mlx5_vhca_page_tracker {
u32 id;
u32 pdn;
- u8 is_err:1;
- u8 object_changed:1;
+ /* Flags modified at runtime - dedicated storage unit */
+ u8 is_err;
+ u8 object_changed;
+ int status;
struct mlx5_uars_page *uar;
struct mlx5_vhca_cq cq;
struct mlx5_vhca_qp *host_qp;
struct mlx5_vhca_qp *fw_qp;
struct mlx5_nb nb;
- int status;
};
struct mlx5vf_pci_core_device {
struct vfio_pci_core_device core_device;
int vf_id;
u16 vhca_id;
+ /* Flags only modified on setup/release - bitfield ok */
u8 migrate_cap:1;
- u8 deferred_reset:1;
- u8 mdev_detach:1;
- u8 log_active:1;
u8 chunk_mode:1;
u8 mig_state_cap:1;
+ /* Flags modified at runtime - dedicated storage unit */
+ u8 mdev_detach;
+ u8 log_active;
+ u8 deferred_reset;
struct completion tracker_comp;
/* protect migration state */
struct mutex state_mutex;
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 0c771064c0b8..830369ff878d 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -125,9 +125,30 @@ static int vfio_pci_open_device(struct vfio_device *core_vdev)
return 0;
}
+static int vfio_pci_init_dev(struct vfio_device *core_vdev)
+{
+ struct vfio_pci_core_device *vdev =
+ container_of(core_vdev, struct vfio_pci_core_device, vdev);
+
+ /*
+ * These behaviors originated in vfio-pci and moved into
+ * vfio-pci-core when the driver was split; vfio-pci remains the
+ * only driver that toggles them. Latch our module parameters per
+ * device at init time so that later parameter changes do not
+ * affect already-initialized devices.
+ */
+ vdev->nointxmask = nointxmask;
+ vdev->disable_idle_d3 = disable_idle_d3;
+#ifdef CONFIG_VFIO_PCI_VGA
+ vdev->disable_vga = disable_vga;
+#endif
+
+ return vfio_pci_core_init_dev(core_vdev);
+}
+
static const struct vfio_device_ops vfio_pci_ops = {
.name = "vfio-pci",
- .init = vfio_pci_core_init_dev,
+ .init = vfio_pci_init_dev,
.release = vfio_pci_core_release_dev,
.open_device = vfio_pci_open_device,
.close_device = vfio_pci_core_close_device,
@@ -256,13 +277,6 @@ static void __init vfio_pci_fill_ids(void)
static int __init vfio_pci_init(void)
{
int ret;
- bool is_disable_vga = true;
-
-#ifdef CONFIG_VFIO_PCI_VGA
- is_disable_vga = disable_vga;
-#endif
-
- vfio_pci_core_set_params(nointxmask, is_disable_vga, disable_idle_d3);
/* Register and scan for devices */
ret = pci_register_driver(&vfio_pci_driver);
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index a28f1e99362c..3f11a9624b9c 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -11,6 +11,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/aperture.h>
+#include <linux/debugfs.h>
#include <linux/device.h>
#include <linux/eventfd.h>
#include <linux/file.h>
@@ -29,6 +30,7 @@
#include <linux/sched/mm.h>
#include <linux/iommufd.h>
#include <linux/pci-p2pdma.h>
+#include <linux/seq_file.h>
#if IS_ENABLED(CONFIG_EEH)
#include <asm/eeh.h>
#endif
@@ -38,10 +40,6 @@
#define DRIVER_AUTHOR "Alex Williamson <alex.williamson@redhat.com>"
#define DRIVER_DESC "core driver for VFIO based PCI devices"
-static bool nointxmask;
-static bool disable_vga;
-static bool disable_idle_d3;
-
static void vfio_pci_eventfd_rcu_free(struct rcu_head *rcu)
{
struct vfio_pci_eventfd *eventfd =
@@ -92,15 +90,69 @@ struct vfio_pci_vf_token {
int users;
};
-static inline bool vfio_vga_disabled(void)
+static inline bool vfio_vga_disabled(struct vfio_pci_core_device *vdev)
{
#ifdef CONFIG_VFIO_PCI_VGA
- return disable_vga;
+ return vdev->disable_vga;
#else
return true;
#endif
}
+#ifdef CONFIG_VFIO_DEBUGFS
+static struct vfio_pci_core_device *
+vfio_pci_core_debugfs_private(struct seq_file *seq)
+{
+ struct device *dev = seq->private;
+ struct vfio_device *core_vdev = container_of(dev, struct vfio_device,
+ device);
+
+ return container_of(core_vdev, struct vfio_pci_core_device, vdev);
+}
+
+static int vfio_pci_core_debugfs_nointxmask(struct seq_file *seq, void *data)
+{
+ struct vfio_pci_core_device *vdev = vfio_pci_core_debugfs_private(seq);
+
+ seq_puts(seq, vdev->nointxmask ? "Y\n" : "N\n");
+ return 0;
+}
+
+static int vfio_pci_core_debugfs_disable_idle_d3(struct seq_file *seq,
+ void *data)
+{
+ struct vfio_pci_core_device *vdev = vfio_pci_core_debugfs_private(seq);
+
+ seq_puts(seq, vdev->disable_idle_d3 ? "Y\n" : "N\n");
+ return 0;
+}
+
+/*
+ * disable_idle_d3 and nointxmask are writable module parameters latched
+ * per device at init, so a device's effective value can differ from the
+ * current parameter setting. Expose the per-device (read-only) values
+ * here for visibility; read-only parameters can't drift and are omitted.
+ */
+static void vfio_pci_core_debugfs_init(struct vfio_pci_core_device *vdev)
+{
+ struct device *dev = &vdev->vdev.device;
+ struct dentry *pci_dir;
+
+ if (IS_ERR_OR_NULL(vdev->vdev.debug_root))
+ return;
+
+ pci_dir = debugfs_create_dir("pci", vdev->vdev.debug_root);
+ debugfs_create_devm_seqfile(dev, "nointxmask", pci_dir,
+ vfio_pci_core_debugfs_nointxmask);
+ debugfs_create_devm_seqfile(dev, "disable_idle_d3", pci_dir,
+ vfio_pci_core_debugfs_disable_idle_d3);
+}
+#else
+static inline void vfio_pci_core_debugfs_init(struct vfio_pci_core_device *vdev)
+{
+}
+#endif /* CONFIG_VFIO_DEBUGFS */
+
/*
* Our VGA arbiter participation is limited since we don't know anything
* about the device itself. However, if the device is the only VGA device
@@ -111,11 +163,12 @@ static inline bool vfio_vga_disabled(void)
*/
static unsigned int vfio_pci_set_decode(struct pci_dev *pdev, bool single_vga)
{
+ struct vfio_pci_core_device *vdev = dev_get_drvdata(&pdev->dev);
struct pci_dev *tmp = NULL;
unsigned char max_busnr;
unsigned int decodes;
- if (single_vga || !vfio_vga_disabled() || pci_is_root_bus(pdev->bus))
+ if (single_vga || !vfio_vga_disabled(vdev) || pci_is_root_bus(pdev->bus))
return VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM |
VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM;
@@ -538,7 +591,7 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev)
u16 cmd;
u8 msix_pos;
- if (!disable_idle_d3) {
+ if (!vdev->disable_idle_d3) {
ret = pm_runtime_resume_and_get(&pdev->dev);
if (ret < 0)
return ret;
@@ -562,7 +615,7 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev)
if (!vdev->pci_saved_state)
pci_dbg(pdev, "%s: Couldn't store saved state\n", __func__);
- if (likely(!nointxmask)) {
+ if (likely(!vdev->nointxmask)) {
if (vfio_pci_nointx(pdev)) {
pci_info(pdev, "Masking broken INTx support\n");
vdev->nointx = true;
@@ -602,7 +655,7 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev)
vdev->has_dyn_msix = false;
}
- if (!vfio_vga_disabled() && vfio_pci_is_vga(pdev))
+ if (!vfio_vga_disabled(vdev) && vfio_pci_is_vga(pdev))
vdev->has_vga = true;
vfio_pci_core_map_bars(vdev);
@@ -617,7 +670,7 @@ out_free_state:
out_disable_device:
pci_disable_device(pdev);
out_power:
- if (!disable_idle_d3)
+ if (!vdev->disable_idle_d3)
pm_runtime_put(&pdev->dev);
return ret;
}
@@ -753,7 +806,7 @@ out:
vfio_pci_dev_set_try_reset(vdev->vdev.dev_set);
/* Put the pm-runtime usage counter acquired during enable */
- if (!disable_idle_d3)
+ if (!vdev->disable_idle_d3)
pm_runtime_put(&pdev->dev);
}
EXPORT_SYMBOL_GPL(vfio_pci_core_disable);
@@ -2239,19 +2292,23 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev)
dev->driver->pm = &vfio_pci_core_pm_ops;
pm_runtime_allow(dev);
- if (!disable_idle_d3)
+ if (!vdev->disable_idle_d3)
pm_runtime_put(dev);
ret = vfio_register_group_dev(&vdev->vdev);
if (ret)
goto out_power;
+
+ vfio_pci_core_debugfs_init(vdev);
+
return 0;
out_power:
- if (!disable_idle_d3)
+ if (!vdev->disable_idle_d3)
pm_runtime_get_noresume(dev);
pm_runtime_forbid(dev);
+ vfio_pci_vga_uninit(vdev);
out_vf:
vfio_pci_vf_uninit(vdev);
return ret;
@@ -2267,7 +2324,7 @@ void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev)
vfio_pci_vf_uninit(vdev);
vfio_pci_vga_uninit(vdev);
- if (!disable_idle_d3)
+ if (!vdev->disable_idle_d3)
pm_runtime_get_noresume(&vdev->pdev->dev);
pm_runtime_forbid(&vdev->pdev->dev);
@@ -2599,7 +2656,7 @@ static void vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set)
* state. Increment the usage count for all the devices in the dev_set
* before reset and decrement the same after reset.
*/
- if (!disable_idle_d3 && vfio_pci_dev_set_pm_runtime_get(dev_set))
+ if (vfio_pci_dev_set_pm_runtime_get(dev_set))
return;
if (!pci_reset_bus(pdev))
@@ -2609,20 +2666,10 @@ static void vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set)
if (reset_done)
cur->needs_reset = false;
- if (!disable_idle_d3)
- pm_runtime_put(&cur->pdev->dev);
+ pm_runtime_put(&cur->pdev->dev);
}
}
-void vfio_pci_core_set_params(bool is_nointxmask, bool is_disable_vga,
- bool is_disable_idle_d3)
-{
- nointxmask = is_nointxmask;
- disable_vga = is_disable_vga;
- disable_idle_d3 = is_disable_idle_d3;
-}
-EXPORT_SYMBOL_GPL(vfio_pci_core_set_params);
-
static void vfio_pci_core_cleanup(void)
{
vfio_pci_uninit_perm_bits();
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 5e0422014523..ed538aebb0b8 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -407,6 +407,13 @@ void vfio_unregister_group_dev(struct vfio_device *device)
vfio_device_group_unregister(device);
/*
+ * Remove debugfs before device_del(), which releases devres. Some
+ * debugfs entries are created with debugfs_create_devm_seqfile() and
+ * therefore rely on devres-managed inode private data.
+ */
+ vfio_device_debugfs_exit(device);
+
+ /*
* Balances vfio_device_add() in register path, also prevents
* new device opened by userspace in the cdev path.
*/
@@ -435,7 +442,6 @@ void vfio_unregister_group_dev(struct vfio_device *device)
}
}
- vfio_device_debugfs_exit(device);
/* Balances vfio_device_set_group in register path */
vfio_device_remove_group(device);
}
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 5fc6ce4dd786..9a1674c152aa 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -101,6 +101,9 @@ struct vfio_pci_core_device {
const struct vfio_pci_device_ops *pci_ops;
void __iomem *barmap[PCI_STD_NUM_BARS];
bool bar_mmap_supported[PCI_STD_NUM_BARS];
+ /* Flags modified at runtime - dedicated storage unit */
+ bool virq_disabled;
+ bool bardirty;
u8 *pci_config_map;
u8 *vconfig;
struct perm_bits *msi_perm;
@@ -115,18 +118,21 @@ struct vfio_pci_core_device {
u16 msix_size;
u32 msix_offset;
u32 rbar[7];
+ /* Flags only modified on setup/release - bitfield ok */
bool has_dyn_msix:1;
bool pci_2_3:1;
- bool virq_disabled:1;
bool reset_works:1;
bool extended_caps:1;
- bool bardirty:1;
bool has_vga:1;
- bool needs_reset:1;
bool nointx:1;
bool needs_pm_restore:1;
- bool pm_intx_masked:1;
- bool pm_runtime_engaged:1;
+ bool disable_idle_d3:1;
+ bool nointxmask:1;
+ bool disable_vga:1;
+ /* Flags modified at runtime - dedicated storage unit */
+ bool needs_reset;
+ bool pm_intx_masked;
+ bool pm_runtime_engaged;
bool sriov_active;
struct pci_saved_state *pci_saved_state;
struct pci_saved_state *pm_save;
@@ -157,8 +163,6 @@ int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev,
unsigned int type, unsigned int subtype,
const struct vfio_pci_regops *ops,
size_t size, u32 flags, void *data);
-void vfio_pci_core_set_params(bool nointxmask, bool is_disable_vga,
- bool is_disable_idle_d3);
void vfio_pci_core_close_device(struct vfio_device *core_vdev);
int vfio_pci_core_init_dev(struct vfio_device *core_vdev);
void vfio_pci_core_release_dev(struct vfio_device *core_vdev);
diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile
index e6e8cb52ab03..2c32c48db509 100644
--- a/tools/testing/selftests/vfio/Makefile
+++ b/tools/testing/selftests/vfio/Makefile
@@ -29,8 +29,6 @@ CFLAGS += $(EXTRA_CFLAGS)
LDFLAGS += -pthread
-LDLIBS += -luuid
-
$(TEST_GEN_PROGS): $(OUTPUT)/%: $(OUTPUT)/%.o $(LIBVFIO_O)
$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $< $(LIBVFIO_O) $(LDLIBS) -o $@
diff --git a/tools/testing/selftests/vfio/lib/libvfio.mk b/tools/testing/selftests/vfio/lib/libvfio.mk
index 2b8d73b7d329..67942b085068 100644
--- a/tools/testing/selftests/vfio/lib/libvfio.mk
+++ b/tools/testing/selftests/vfio/lib/libvfio.mk
@@ -26,6 +26,8 @@ $(LIBVFIO_O_DIRS):
CFLAGS += -I$(LIBVFIO_SRCDIR)/include
+LDLIBS += -luuid
+
$(LIBVFIO_O): $(LIBVFIO_OUTPUT)/%.o : $(LIBVFIO_SRCDIR)/%.c | $(LIBVFIO_O_DIRS)
$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
generated by cgit v1.2.3 (git 2.39.1) at 2026-07-07 03:13:05 +0000