diff options
| author | Alex Williamson <alex.williamson@nvidia.com> | 2026-06-15 13:12:34 -0600 |
|---|---|---|
| committer | Alex Williamson <alex@shazbot.org> | 2026-06-29 14:26:31 -0600 |
| commit | 586a989d8b0db75d6f97c80a4f588d46e1df6881 (patch) | |
| tree | 2a0439cccff5e8cdea5ff7e66bdb5b49e0031480 | |
| parent | dc7fe87de492ea7f33a72b78d26650b75bf37f4f (diff) | |
| download | linux-next-586a989d8b0db75d6f97c80a4f588d46e1df6881.tar.gz linux-next-586a989d8b0db75d6f97c80a4f588d46e1df6881.zip | |
vfio/pci: Expose latched module parameter policy in debugfs
The nointxmask and disable_idle_d3 module parameters remain writable,
but vfio-pci now latches their values into each device at init. Once a
device is registered, changing the module parameter only affects future
devices, leaving no direct way to confirm the effective policy for an
existing device.
Add a pci debugfs directory under the VFIO device debugfs root and
report the per-device nointxmask and disable_idle_d3 values. These are
read-only debugfs views and use the same Y/N bool output convention as
the module parameters.
Read-only vfio-pci parameters, such as disable_vga, are not exposed here
because they cannot drift from the latched device value, therefore the
existing module parameter exposure via sysfs is sufficient.
Note that while only vfio-pci currently provides these options, the
implementation is in vfio-pci-core and therefore properly reflects the
device policy in the core, regardless of driver.
Assisted-by: OpenAI Codex:gpt-5
Cc: Guixin Liu <kanie@linux.alibaba.com>
Signed-off-by: Alex Williamson <alex.williamson@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20260615191241.688297-7-alex.williamson@nvidia.com
Signed-off-by: Alex Williamson <alex@shazbot.org>
| -rw-r--r-- | Documentation/ABI/testing/debugfs-vfio | 26 | ||||
| -rw-r--r-- | drivers/vfio/pci/vfio_pci_core.c | 59 |
2 files changed, 85 insertions, 0 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/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index db36d903dcd4..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 @@ -97,6 +99,60 @@ static inline bool vfio_vga_disabled(struct vfio_pci_core_device *vdev) #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 @@ -2242,6 +2298,9 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev) ret = vfio_register_group_dev(&vdev->vdev); if (ret) goto out_power; + + vfio_pci_core_debugfs_init(vdev); + return 0; out_power: |
