From d2ccde1c8e90d38cee87a1b0309ad2827f3fd30d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 11 Dec 2023 02:45:28 +0000
Subject: [PATCH] add boot partition size
---
kernel/include/uapi/linux/vfio.h | 519 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 517 insertions(+), 2 deletions(-)
diff --git a/kernel/include/uapi/linux/vfio.h b/kernel/include/uapi/linux/vfio.h
index 1aa7b82..2f313a2 100644
--- a/kernel/include/uapi/linux/vfio.h
+++ b/kernel/include/uapi/linux/vfio.h
@@ -200,8 +200,12 @@
#define VFIO_DEVICE_FLAGS_PLATFORM (1 << 2) /* vfio-platform device */
#define VFIO_DEVICE_FLAGS_AMBA (1 << 3) /* vfio-amba device */
#define VFIO_DEVICE_FLAGS_CCW (1 << 4) /* vfio-ccw device */
+#define VFIO_DEVICE_FLAGS_AP (1 << 5) /* vfio-ap device */
+#define VFIO_DEVICE_FLAGS_FSL_MC (1 << 6) /* vfio-fsl-mc device */
+#define VFIO_DEVICE_FLAGS_CAPS (1 << 7) /* Info supports caps */
__u32 num_regions; /* Max region index + 1 */
__u32 num_irqs; /* Max IRQ index + 1 */
+ __u32 cap_offset; /* Offset within info struct of first cap */
};
#define VFIO_DEVICE_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 7)
@@ -215,6 +219,16 @@
#define VFIO_DEVICE_API_PLATFORM_STRING "vfio-platform"
#define VFIO_DEVICE_API_AMBA_STRING "vfio-amba"
#define VFIO_DEVICE_API_CCW_STRING "vfio-ccw"
+#define VFIO_DEVICE_API_AP_STRING "vfio-ap"
+
+/*
+ * The following capabilities are unique to s390 zPCI devices. Their contents
+ * are further-defined in vfio_zdev.h
+ */
+#define VFIO_DEVICE_INFO_CAP_ZPCI_BASE 1
+#define VFIO_DEVICE_INFO_CAP_ZPCI_GROUP 2
+#define VFIO_DEVICE_INFO_CAP_ZPCI_UTIL 3
+#define VFIO_DEVICE_INFO_CAP_ZPCI_PFIP 4
/**
* VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8,
@@ -293,13 +307,319 @@
__u32 subtype; /* type specific */
};
+/*
+ * List of region types, global per bus driver.
+ * If you introduce a new type, please add it here.
+ */
+
+/* PCI region type containing a PCI vendor part */
#define VFIO_REGION_TYPE_PCI_VENDOR_TYPE (1 << 31)
#define VFIO_REGION_TYPE_PCI_VENDOR_MASK (0xffff)
+#define VFIO_REGION_TYPE_GFX (1)
+#define VFIO_REGION_TYPE_CCW (2)
+#define VFIO_REGION_TYPE_MIGRATION (3)
-/* 8086 Vendor sub-types */
+/* sub-types for VFIO_REGION_TYPE_PCI_* */
+
+/* 8086 vendor PCI sub-types */
#define VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION (1)
#define VFIO_REGION_SUBTYPE_INTEL_IGD_HOST_CFG (2)
#define VFIO_REGION_SUBTYPE_INTEL_IGD_LPC_CFG (3)
+
+/* 10de vendor PCI sub-types */
+/*
+ * NVIDIA GPU NVlink2 RAM is coherent RAM mapped onto the host address space.
+ */
+#define VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM (1)
+
+/* 1014 vendor PCI sub-types */
+/*
+ * IBM NPU NVlink2 ATSD (Address Translation Shootdown) register of NPU
+ * to do TLB invalidation on a GPU.
+ */
+#define VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD (1)
+
+/* sub-types for VFIO_REGION_TYPE_GFX */
+#define VFIO_REGION_SUBTYPE_GFX_EDID (1)
+
+/**
+ * struct vfio_region_gfx_edid - EDID region layout.
+ *
+ * Set display link state and EDID blob.
+ *
+ * The EDID blob has monitor information such as brand, name, serial
+ * number, physical size, supported video modes and more.
+ *
+ * This special region allows userspace (typically qemu) set a virtual
+ * EDID for the virtual monitor, which allows a flexible display
+ * configuration.
+ *
+ * For the edid blob spec look here:
+ * https://en.wikipedia.org/wiki/Extended_Display_Identification_Data
+ *
+ * On linux systems you can find the EDID blob in sysfs:
+ * /sys/class/drm/${card}/${connector}/edid
+ *
+ * You can use the edid-decode ulility (comes with xorg-x11-utils) to
+ * decode the EDID blob.
+ *
+ * @edid_offset: location of the edid blob, relative to the
+ * start of the region (readonly).
+ * @edid_max_size: max size of the edid blob (readonly).
+ * @edid_size: actual edid size (read/write).
+ * @link_state: display link state (read/write).
+ * VFIO_DEVICE_GFX_LINK_STATE_UP: Monitor is turned on.
+ * VFIO_DEVICE_GFX_LINK_STATE_DOWN: Monitor is turned off.
+ * @max_xres: max display width (0 == no limitation, readonly).
+ * @max_yres: max display height (0 == no limitation, readonly).
+ *
+ * EDID update protocol:
+ * (1) set link-state to down.
+ * (2) update edid blob and size.
+ * (3) set link-state to up.
+ */
+struct vfio_region_gfx_edid {
+ __u32 edid_offset;
+ __u32 edid_max_size;
+ __u32 edid_size;
+ __u32 max_xres;
+ __u32 max_yres;
+ __u32 link_state;
+#define VFIO_DEVICE_GFX_LINK_STATE_UP 1
+#define VFIO_DEVICE_GFX_LINK_STATE_DOWN 2
+};
+
+/* sub-types for VFIO_REGION_TYPE_CCW */
+#define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD (1)
+#define VFIO_REGION_SUBTYPE_CCW_SCHIB (2)
+#define VFIO_REGION_SUBTYPE_CCW_CRW (3)
+
+/* sub-types for VFIO_REGION_TYPE_MIGRATION */
+#define VFIO_REGION_SUBTYPE_MIGRATION (1)
+
+/*
+ * The structure vfio_device_migration_info is placed at the 0th offset of
+ * the VFIO_REGION_SUBTYPE_MIGRATION region to get and set VFIO device related
+ * migration information. Field accesses from this structure are only supported
+ * at their native width and alignment. Otherwise, the result is undefined and
+ * vendor drivers should return an error.
+ *
+ * device_state: (read/write)
+ * - The user application writes to this field to inform the vendor driver
+ * about the device state to be transitioned to.
+ * - The vendor driver should take the necessary actions to change the
+ * device state. After successful transition to a given state, the
+ * vendor driver should return success on write(device_state, state)
+ * system call. If the device state transition fails, the vendor driver
+ * should return an appropriate -errno for the fault condition.
+ * - On the user application side, if the device state transition fails,
+ * that is, if write(device_state, state) returns an error, read
+ * device_state again to determine the current state of the device from
+ * the vendor driver.
+ * - The vendor driver should return previous state of the device unless
+ * the vendor driver has encountered an internal error, in which case
+ * the vendor driver may report the device_state VFIO_DEVICE_STATE_ERROR.
+ * - The user application must use the device reset ioctl to recover the
+ * device from VFIO_DEVICE_STATE_ERROR state. If the device is
+ * indicated to be in a valid device state by reading device_state, the
+ * user application may attempt to transition the device to any valid
+ * state reachable from the current state or terminate itself.
+ *
+ * device_state consists of 3 bits:
+ * - If bit 0 is set, it indicates the _RUNNING state. If bit 0 is clear,
+ * it indicates the _STOP state. When the device state is changed to
+ * _STOP, driver should stop the device before write() returns.
+ * - If bit 1 is set, it indicates the _SAVING state, which means that the
+ * driver should start gathering device state information that will be
+ * provided to the VFIO user application to save the device's state.
+ * - If bit 2 is set, it indicates the _RESUMING state, which means that
+ * the driver should prepare to resume the device. Data provided through
+ * the migration region should be used to resume the device.
+ * Bits 3 - 31 are reserved for future use. To preserve them, the user
+ * application should perform a read-modify-write operation on this
+ * field when modifying the specified bits.
+ *
+ * +------- _RESUMING
+ * |+------ _SAVING
+ * ||+----- _RUNNING
+ * |||
+ * 000b => Device Stopped, not saving or resuming
+ * 001b => Device running, which is the default state
+ * 010b => Stop the device & save the device state, stop-and-copy state
+ * 011b => Device running and save the device state, pre-copy state
+ * 100b => Device stopped and the device state is resuming
+ * 101b => Invalid state
+ * 110b => Error state
+ * 111b => Invalid state
+ *
+ * State transitions:
+ *
+ * _RESUMING _RUNNING Pre-copy Stop-and-copy _STOP
+ * (100b) (001b) (011b) (010b) (000b)
+ * 0. Running or default state
+ * |
+ *
+ * 1. Normal Shutdown (optional)
+ * |------------------------------------->|
+ *
+ * 2. Save the state or suspend
+ * |------------------------->|---------->|
+ *
+ * 3. Save the state during live migration
+ * |----------->|------------>|---------->|
+ *
+ * 4. Resuming
+ * |<---------|
+ *
+ * 5. Resumed
+ * |--------->|
+ *
+ * 0. Default state of VFIO device is _RUNNING when the user application starts.
+ * 1. During normal shutdown of the user application, the user application may
+ * optionally change the VFIO device state from _RUNNING to _STOP. This
+ * transition is optional. The vendor driver must support this transition but
+ * must not require it.
+ * 2. When the user application saves state or suspends the application, the
+ * device state transitions from _RUNNING to stop-and-copy and then to _STOP.
+ * On state transition from _RUNNING to stop-and-copy, driver must stop the
+ * device, save the device state and send it to the application through the
+ * migration region. The sequence to be followed for such transition is given
+ * below.
+ * 3. In live migration of user application, the state transitions from _RUNNING
+ * to pre-copy, to stop-and-copy, and to _STOP.
+ * On state transition from _RUNNING to pre-copy, the driver should start
+ * gathering the device state while the application is still running and send
+ * the device state data to application through the migration region.
+ * On state transition from pre-copy to stop-and-copy, the driver must stop
+ * the device, save the device state and send it to the user application
+ * through the migration region.
+ * Vendor drivers must support the pre-copy state even for implementations
+ * where no data is provided to the user before the stop-and-copy state. The
+ * user must not be required to consume all migration data before the device
+ * transitions to a new state, including the stop-and-copy state.
+ * The sequence to be followed for above two transitions is given below.
+ * 4. To start the resuming phase, the device state should be transitioned from
+ * the _RUNNING to the _RESUMING state.
+ * In the _RESUMING state, the driver should use the device state data
+ * received through the migration region to resume the device.
+ * 5. After providing saved device data to the driver, the application should
+ * change the state from _RESUMING to _RUNNING.
+ *
+ * reserved:
+ * Reads on this field return zero and writes are ignored.
+ *
+ * pending_bytes: (read only)
+ * The number of pending bytes still to be migrated from the vendor driver.
+ *
+ * data_offset: (read only)
+ * The user application should read data_offset field from the migration
+ * region. The user application should read the device data from this
+ * offset within the migration region during the _SAVING state or write
+ * the device data during the _RESUMING state. See below for details of
+ * sequence to be followed.
+ *
+ * data_size: (read/write)
+ * The user application should read data_size to get the size in bytes of
+ * the data copied in the migration region during the _SAVING state and
+ * write the size in bytes of the data copied in the migration region
+ * during the _RESUMING state.
+ *
+ * The format of the migration region is as follows:
+ * ------------------------------------------------------------------
+ * |vfio_device_migration_info| data section |
+ * | | /////////////////////////////// |
+ * ------------------------------------------------------------------
+ * ^ ^
+ * offset 0-trapped part data_offset
+ *
+ * The structure vfio_device_migration_info is always followed by the data
+ * section in the region, so data_offset will always be nonzero. The offset
+ * from where the data is copied is decided by the kernel driver. The data
+ * section can be trapped, mmapped, or partitioned, depending on how the kernel
+ * driver defines the data section. The data section partition can be defined
+ * as mapped by the sparse mmap capability. If mmapped, data_offset must be
+ * page aligned, whereas initial section which contains the
+ * vfio_device_migration_info structure, might not end at the offset, which is
+ * page aligned. The user is not required to access through mmap regardless
+ * of the capabilities of the region mmap.
+ * The vendor driver should determine whether and how to partition the data
+ * section. The vendor driver should return data_offset accordingly.
+ *
+ * The sequence to be followed while in pre-copy state and stop-and-copy state
+ * is as follows:
+ * a. Read pending_bytes, indicating the start of a new iteration to get device
+ * data. Repeated read on pending_bytes at this stage should have no side
+ * effects.
+ * If pending_bytes == 0, the user application should not iterate to get data
+ * for that device.
+ * If pending_bytes > 0, perform the following steps.
+ * b. Read data_offset, indicating that the vendor driver should make data
+ * available through the data section. The vendor driver should return this
+ * read operation only after data is available from (region + data_offset)
+ * to (region + data_offset + data_size).
+ * c. Read data_size, which is the amount of data in bytes available through
+ * the migration region.
+ * Read on data_offset and data_size should return the offset and size of
+ * the current buffer if the user application reads data_offset and
+ * data_size more than once here.
+ * d. Read data_size bytes of data from (region + data_offset) from the
+ * migration region.
+ * e. Process the data.
+ * f. Read pending_bytes, which indicates that the data from the previous
+ * iteration has been read. If pending_bytes > 0, go to step b.
+ *
+ * The user application can transition from the _SAVING|_RUNNING
+ * (pre-copy state) to the _SAVING (stop-and-copy) state regardless of the
+ * number of pending bytes. The user application should iterate in _SAVING
+ * (stop-and-copy) until pending_bytes is 0.
+ *
+ * The sequence to be followed while _RESUMING device state is as follows:
+ * While data for this device is available, repeat the following steps:
+ * a. Read data_offset from where the user application should write data.
+ * b. Write migration data starting at the migration region + data_offset for
+ * the length determined by data_size from the migration source.
+ * c. Write data_size, which indicates to the vendor driver that data is
+ * written in the migration region. Vendor driver must return this write
+ * operations on consuming data. Vendor driver should apply the
+ * user-provided migration region data to the device resume state.
+ *
+ * If an error occurs during the above sequences, the vendor driver can return
+ * an error code for next read() or write() operation, which will terminate the
+ * loop. The user application should then take the next necessary action, for
+ * example, failing migration or terminating the user application.
+ *
+ * For the user application, data is opaque. The user application should write
+ * data in the same order as the data is received and the data should be of
+ * same transaction size at the source.
+ */
+
+struct vfio_device_migration_info {
+ __u32 device_state; /* VFIO device state */
+#define VFIO_DEVICE_STATE_STOP (0)
+#define VFIO_DEVICE_STATE_RUNNING (1 << 0)
+#define VFIO_DEVICE_STATE_SAVING (1 << 1)
+#define VFIO_DEVICE_STATE_RESUMING (1 << 2)
+#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_RUNNING | \
+ VFIO_DEVICE_STATE_SAVING | \
+ VFIO_DEVICE_STATE_RESUMING)
+
+#define VFIO_DEVICE_STATE_VALID(state) \
+ (state & VFIO_DEVICE_STATE_RESUMING ? \
+ (state & VFIO_DEVICE_STATE_MASK) == VFIO_DEVICE_STATE_RESUMING : 1)
+
+#define VFIO_DEVICE_STATE_IS_ERROR(state) \
+ ((state & VFIO_DEVICE_STATE_MASK) == (VFIO_DEVICE_STATE_SAVING | \
+ VFIO_DEVICE_STATE_RESUMING))
+
+#define VFIO_DEVICE_STATE_SET_ERROR(state) \
+ ((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_SATE_SAVING | \
+ VFIO_DEVICE_STATE_RESUMING)
+
+ __u32 reserved;
+ __u64 pending_bytes;
+ __u64 data_offset;
+ __u64 data_size;
+};
/*
* The MSIX mappable capability informs that MSIX data of a BAR can be mmapped
@@ -310,6 +630,33 @@
* VFIO_DEVICE_SET_IRQS interface must still be used for MSIX configuration.
*/
#define VFIO_REGION_INFO_CAP_MSIX_MAPPABLE 3
+
+/*
+ * Capability with compressed real address (aka SSA - small system address)
+ * where GPU RAM is mapped on a system bus. Used by a GPU for DMA routing
+ * and by the userspace to associate a NVLink bridge with a GPU.
+ */
+#define VFIO_REGION_INFO_CAP_NVLINK2_SSATGT 4
+
+struct vfio_region_info_cap_nvlink2_ssatgt {
+ struct vfio_info_cap_header header;
+ __u64 tgt;
+};
+
+/*
+ * Capability with an NVLink link speed. The value is read by
+ * the NVlink2 bridge driver from the bridge's "ibm,nvlink-speed"
+ * property in the device tree. The value is fixed in the hardware
+ * and failing to provide the correct value results in the link
+ * not working with no indication from the driver why.
+ */
+#define VFIO_REGION_INFO_CAP_NVLINK2_LNKSPD 5
+
+struct vfio_region_info_cap_nvlink2_lnkspd {
+ struct vfio_info_cap_header header;
+ __u32 link_speed;
+ __u32 __pad;
+};
/**
* VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9,
@@ -472,6 +819,7 @@
enum {
VFIO_CCW_IO_IRQ_INDEX,
+ VFIO_CCW_CRW_IRQ_INDEX,
VFIO_CCW_NUM_IRQS
};
@@ -602,6 +950,43 @@
#define VFIO_DEVICE_IOEVENTFD _IO(VFIO_TYPE, VFIO_BASE + 16)
+/**
+ * VFIO_DEVICE_FEATURE - _IORW(VFIO_TYPE, VFIO_BASE + 17,
+ * struct vfio_device_feature)
+ *
+ * Get, set, or probe feature data of the device. The feature is selected
+ * using the FEATURE_MASK portion of the flags field. Support for a feature
+ * can be probed by setting both the FEATURE_MASK and PROBE bits. A probe
+ * may optionally include the GET and/or SET bits to determine read vs write
+ * access of the feature respectively. Probing a feature will return success
+ * if the feature is supported and all of the optionally indicated GET/SET
+ * methods are supported. The format of the data portion of the structure is
+ * specific to the given feature. The data portion is not required for
+ * probing. GET and SET are mutually exclusive, except for use with PROBE.
+ *
+ * Return 0 on success, -errno on failure.
+ */
+struct vfio_device_feature {
+ __u32 argsz;
+ __u32 flags;
+#define VFIO_DEVICE_FEATURE_MASK (0xffff) /* 16-bit feature index */
+#define VFIO_DEVICE_FEATURE_GET (1 << 16) /* Get feature into data[] */
+#define VFIO_DEVICE_FEATURE_SET (1 << 17) /* Set feature from data[] */
+#define VFIO_DEVICE_FEATURE_PROBE (1 << 18) /* Probe feature support */
+ __u8 data[];
+};
+
+#define VFIO_DEVICE_FEATURE _IO(VFIO_TYPE, VFIO_BASE + 17)
+
+/*
+ * Provide support for setting a PCI VF Token, which is used as a shared
+ * secret between PF and VF drivers. This feature may only be set on a
+ * PCI SR-IOV PF when SR-IOV is enabled on the PF and there are no existing
+ * open VFs. Data provided when setting this feature is a 16-byte array
+ * (__u8 b[16]), representing a UUID.
+ */
+#define VFIO_DEVICE_FEATURE_PCI_VF_TOKEN (0)
+
/* -------- API for Type1 VFIO IOMMU -------- */
/**
@@ -616,7 +1001,69 @@
__u32 argsz;
__u32 flags;
#define VFIO_IOMMU_INFO_PGSIZES (1 << 0) /* supported page sizes info */
- __u64 iova_pgsizes; /* Bitmap of supported page sizes */
+#define VFIO_IOMMU_INFO_CAPS (1 << 1) /* Info supports caps */
+ __u64 iova_pgsizes; /* Bitmap of supported page sizes */
+ __u32 cap_offset; /* Offset within info struct of first cap */
+};
+
+/*
+ * The IOVA capability allows to report the valid IOVA range(s)
+ * excluding any non-relaxable reserved regions exposed by
+ * devices attached to the container. Any DMA map attempt
+ * outside the valid iova range will return error.
+ *
+ * The structures below define version 1 of this capability.
+ */
+#define VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE 1
+
+struct vfio_iova_range {
+ __u64 start;
+ __u64 end;
+};
+
+struct vfio_iommu_type1_info_cap_iova_range {
+ struct vfio_info_cap_header header;
+ __u32 nr_iovas;
+ __u32 reserved;
+ struct vfio_iova_range iova_ranges[];
+};
+
+/*
+ * The migration capability allows to report supported features for migration.
+ *
+ * The structures below define version 1 of this capability.
+ *
+ * The existence of this capability indicates that IOMMU kernel driver supports
+ * dirty page logging.
+ *
+ * pgsize_bitmap: Kernel driver returns bitmap of supported page sizes for dirty
+ * page logging.
+ * max_dirty_bitmap_size: Kernel driver returns maximum supported dirty bitmap
+ * size in bytes that can be used by user applications when getting the dirty
+ * bitmap.
+ */
+#define VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION 2
+
+struct vfio_iommu_type1_info_cap_migration {
+ struct vfio_info_cap_header header;
+ __u32 flags;
+ __u64 pgsize_bitmap;
+ __u64 max_dirty_bitmap_size; /* in bytes */
+};
+
+/*
+ * The DMA available capability allows to report the current number of
+ * simultaneously outstanding DMA mappings that are allowed.
+ *
+ * The structure below defines version 1 of this capability.
+ *
+ * avail: specifies the current number of outstanding DMA mappings allowed.
+ */
+#define VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL 3
+
+struct vfio_iommu_type1_info_dma_avail {
+ struct vfio_info_cap_header header;
+ __u32 avail;
};
#define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
@@ -639,6 +1086,12 @@
#define VFIO_IOMMU_MAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 13)
+struct vfio_bitmap {
+ __u64 pgsize; /* page size for bitmap in bytes */
+ __u64 size; /* in bytes */
+ __u64 __user *data; /* one bit per page */
+};
+
/**
* VFIO_IOMMU_UNMAP_DMA - _IOWR(VFIO_TYPE, VFIO_BASE + 14,
* struct vfio_dma_unmap)
@@ -648,12 +1101,23 @@
* field. No guarantee is made to the user that arbitrary unmaps of iova
* or size different from those used in the original mapping call will
* succeed.
+ * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get the dirty bitmap
+ * before unmapping IO virtual addresses. When this flag is set, the user must
+ * provide a struct vfio_bitmap in data[]. User must provide zero-allocated
+ * memory via vfio_bitmap.data and its size in the vfio_bitmap.size field.
+ * A bit in the bitmap represents one page, of user provided page size in
+ * vfio_bitmap.pgsize field, consecutively starting from iova offset. Bit set
+ * indicates that the page at that offset from iova is dirty. A Bitmap of the
+ * pages in the range of unmapped size is returned in the user-provided
+ * vfio_bitmap.data.
*/
struct vfio_iommu_type1_dma_unmap {
__u32 argsz;
__u32 flags;
+#define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0)
__u64 iova; /* IO virtual address */
__u64 size; /* Size of mapping (bytes) */
+ __u8 data[];
};
#define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14)
@@ -665,6 +1129,57 @@
#define VFIO_IOMMU_ENABLE _IO(VFIO_TYPE, VFIO_BASE + 15)
#define VFIO_IOMMU_DISABLE _IO(VFIO_TYPE, VFIO_BASE + 16)
+/**
+ * VFIO_IOMMU_DIRTY_PAGES - _IOWR(VFIO_TYPE, VFIO_BASE + 17,
+ * struct vfio_iommu_type1_dirty_bitmap)
+ * IOCTL is used for dirty pages logging.
+ * Caller should set flag depending on which operation to perform, details as
+ * below:
+ *
+ * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_START flag set, instructs
+ * the IOMMU driver to log pages that are dirtied or potentially dirtied by
+ * the device; designed to be used when a migration is in progress. Dirty pages
+ * are logged until logging is disabled by user application by calling the IOCTL
+ * with VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP flag.
+ *
+ * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP flag set, instructs
+ * the IOMMU driver to stop logging dirtied pages.
+ *
+ * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP flag set
+ * returns the dirty pages bitmap for IOMMU container for a given IOVA range.
+ * The user must specify the IOVA range and the pgsize through the structure
+ * vfio_iommu_type1_dirty_bitmap_get in the data[] portion. This interface
+ * supports getting a bitmap of the smallest supported pgsize only and can be
+ * modified in future to get a bitmap of any specified supported pgsize. The
+ * user must provide a zeroed memory area for the bitmap memory and specify its
+ * size in bitmap.size. One bit is used to represent one page consecutively
+ * starting from iova offset. The user should provide page size in bitmap.pgsize
+ * field. A bit set in the bitmap indicates that the page at that offset from
+ * iova is dirty. The caller must set argsz to a value including the size of
+ * structure vfio_iommu_type1_dirty_bitmap_get, but excluding the size of the
+ * actual bitmap. If dirty pages logging is not enabled, an error will be
+ * returned.
+ *
+ * Only one of the flags _START, _STOP and _GET may be specified at a time.
+ *
+ */
+struct vfio_iommu_type1_dirty_bitmap {
+ __u32 argsz;
+ __u32 flags;
+#define VFIO_IOMMU_DIRTY_PAGES_FLAG_START (1 << 0)
+#define VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP (1 << 1)
+#define VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP (1 << 2)
+ __u8 data[];
+};
+
+struct vfio_iommu_type1_dirty_bitmap_get {
+ __u64 iova; /* IO virtual address */
+ __u64 size; /* Size of iova range */
+ struct vfio_bitmap bitmap;
+};
+
+#define VFIO_IOMMU_DIRTY_PAGES _IO(VFIO_TYPE, VFIO_BASE + 17)
+
/* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
/*
--
Gitblit v1.6.2