Re: [PATCH v8 01/13] linux-headers: Update to v6.2-rc1

["Cédric Le Goater" <clg@redhat.com>]

On 1/16/23 15:11, Avihai Horon wrote:
> Update to commit 1b929c02afd3 ("Linux 6.2-rc1").
> 
> Signed-off-by: Avihai Horon <avihaih@nvidia.com>


Reviewed-by: Cédric Le Goater <clg@redhat.com>

Thanks,

C.


> ---
>   include/standard-headers/drm/drm_fourcc.h     |  63 +++-
>   include/standard-headers/linux/ethtool.h      |  81 ++++-
>   include/standard-headers/linux/fuse.h         |  20 +-
>   .../linux/input-event-codes.h                 |   4 +
>   include/standard-headers/linux/pci_regs.h     |   2 +
>   include/standard-headers/linux/virtio_blk.h   |  19 ++
>   include/standard-headers/linux/virtio_bt.h    |   8 +
>   include/standard-headers/linux/virtio_net.h   |   4 +
>   linux-headers/asm-arm64/kvm.h                 |   1 +
>   linux-headers/asm-generic/hugetlb_encode.h    |  26 +-
>   linux-headers/asm-generic/mman-common.h       |   2 +
>   linux-headers/asm-mips/mman.h                 |   2 +
>   linux-headers/asm-riscv/kvm.h                 |   7 +
>   linux-headers/asm-x86/kvm.h                   |  11 +-
>   linux-headers/linux/kvm.h                     |  32 +-
>   linux-headers/linux/psci.h                    |  14 +
>   linux-headers/linux/userfaultfd.h             |   4 +
>   linux-headers/linux/vfio.h                    | 278 +++++++++++++++++-
>   18 files changed, 522 insertions(+), 56 deletions(-)
> 
> diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h
> index 48b620cbef..69cab17b38 100644
> --- a/include/standard-headers/drm/drm_fourcc.h
> +++ b/include/standard-headers/drm/drm_fourcc.h
> @@ -98,18 +98,42 @@ extern "C" {
>   #define DRM_FORMAT_INVALID	0
>   
>   /* color index */
> +#define DRM_FORMAT_C1		fourcc_code('C', '1', ' ', ' ') /* [7:0] C0:C1:C2:C3:C4:C5:C6:C7 1:1:1:1:1:1:1:1 eight pixels/byte */
> +#define DRM_FORMAT_C2		fourcc_code('C', '2', ' ', ' ') /* [7:0] C0:C1:C2:C3 2:2:2:2 four pixels/byte */
> +#define DRM_FORMAT_C4		fourcc_code('C', '4', ' ', ' ') /* [7:0] C0:C1 4:4 two pixels/byte */
>   #define DRM_FORMAT_C8		fourcc_code('C', '8', ' ', ' ') /* [7:0] C */
>   
> -/* 8 bpp Red */
> +/* 1 bpp Darkness (inverse relationship between channel value and brightness) */
> +#define DRM_FORMAT_D1		fourcc_code('D', '1', ' ', ' ') /* [7:0] D0:D1:D2:D3:D4:D5:D6:D7 1:1:1:1:1:1:1:1 eight pixels/byte */
> +
> +/* 2 bpp Darkness (inverse relationship between channel value and brightness) */
> +#define DRM_FORMAT_D2		fourcc_code('D', '2', ' ', ' ') /* [7:0] D0:D1:D2:D3 2:2:2:2 four pixels/byte */
> +
> +/* 4 bpp Darkness (inverse relationship between channel value and brightness) */
> +#define DRM_FORMAT_D4		fourcc_code('D', '4', ' ', ' ') /* [7:0] D0:D1 4:4 two pixels/byte */
> +
> +/* 8 bpp Darkness (inverse relationship between channel value and brightness) */
> +#define DRM_FORMAT_D8		fourcc_code('D', '8', ' ', ' ') /* [7:0] D */
> +
> +/* 1 bpp Red (direct relationship between channel value and brightness) */
> +#define DRM_FORMAT_R1		fourcc_code('R', '1', ' ', ' ') /* [7:0] R0:R1:R2:R3:R4:R5:R6:R7 1:1:1:1:1:1:1:1 eight pixels/byte */
> +
> +/* 2 bpp Red (direct relationship between channel value and brightness) */
> +#define DRM_FORMAT_R2		fourcc_code('R', '2', ' ', ' ') /* [7:0] R0:R1:R2:R3 2:2:2:2 four pixels/byte */
> +
> +/* 4 bpp Red (direct relationship between channel value and brightness) */
> +#define DRM_FORMAT_R4		fourcc_code('R', '4', ' ', ' ') /* [7:0] R0:R1 4:4 two pixels/byte */
> +
> +/* 8 bpp Red (direct relationship between channel value and brightness) */
>   #define DRM_FORMAT_R8		fourcc_code('R', '8', ' ', ' ') /* [7:0] R */
>   
> -/* 10 bpp Red */
> +/* 10 bpp Red (direct relationship between channel value and brightness) */
>   #define DRM_FORMAT_R10		fourcc_code('R', '1', '0', ' ') /* [15:0] x:R 6:10 little endian */
>   
> -/* 12 bpp Red */
> +/* 12 bpp Red (direct relationship between channel value and brightness) */
>   #define DRM_FORMAT_R12		fourcc_code('R', '1', '2', ' ') /* [15:0] x:R 4:12 little endian */
>   
> -/* 16 bpp Red */
> +/* 16 bpp Red (direct relationship between channel value and brightness) */
>   #define DRM_FORMAT_R16		fourcc_code('R', '1', '6', ' ') /* [15:0] R little endian */
>   
>   /* 16 bpp RG */
> @@ -204,7 +228,9 @@ extern "C" {
>   #define DRM_FORMAT_VYUY		fourcc_code('V', 'Y', 'U', 'Y') /* [31:0] Y1:Cb0:Y0:Cr0 8:8:8:8 little endian */
>   
>   #define DRM_FORMAT_AYUV		fourcc_code('A', 'Y', 'U', 'V') /* [31:0] A:Y:Cb:Cr 8:8:8:8 little endian */
> +#define DRM_FORMAT_AVUY8888	fourcc_code('A', 'V', 'U', 'Y') /* [31:0] A:Cr:Cb:Y 8:8:8:8 little endian */
>   #define DRM_FORMAT_XYUV8888	fourcc_code('X', 'Y', 'U', 'V') /* [31:0] X:Y:Cb:Cr 8:8:8:8 little endian */
> +#define DRM_FORMAT_XVUY8888	fourcc_code('X', 'V', 'U', 'Y') /* [31:0] X:Cr:Cb:Y 8:8:8:8 little endian */
>   #define DRM_FORMAT_VUY888	fourcc_code('V', 'U', '2', '4') /* [23:0] Cr:Cb:Y 8:8:8 little endian */
>   #define DRM_FORMAT_VUY101010	fourcc_code('V', 'U', '3', '0') /* Y followed by U then V, 10:10:10. Non-linear modifier only */
>   
> @@ -717,6 +743,35 @@ extern "C" {
>    */
>   #define DRM_FORMAT_MOD_VIVANTE_SPLIT_SUPER_TILED fourcc_mod_code(VIVANTE, 4)
>   
> +/*
> + * Vivante TS (tile-status) buffer modifiers. They can be combined with all of
> + * the color buffer tiling modifiers defined above. When TS is present it's a
> + * separate buffer containing the clear/compression status of each tile. The
> + * modifiers are defined as VIVANTE_MOD_TS_c_s, where c is the color buffer
> + * tile size in bytes covered by one entry in the status buffer and s is the
> + * number of status bits per entry.
> + * We reserve the top 8 bits of the Vivante modifier space for tile status
> + * clear/compression modifiers, as future cores might add some more TS layout
> + * variations.
> + */
> +#define VIVANTE_MOD_TS_64_4               (1ULL << 48)
> +#define VIVANTE_MOD_TS_64_2               (2ULL << 48)
> +#define VIVANTE_MOD_TS_128_4              (3ULL << 48)
> +#define VIVANTE_MOD_TS_256_4              (4ULL << 48)
> +#define VIVANTE_MOD_TS_MASK               (0xfULL << 48)
> +
> +/*
> + * Vivante compression modifiers. Those depend on a TS modifier being present
> + * as the TS bits get reinterpreted as compression tags instead of simple
> + * clear markers when compression is enabled.
> + */
> +#define VIVANTE_MOD_COMP_DEC400           (1ULL << 52)
> +#define VIVANTE_MOD_COMP_MASK             (0xfULL << 52)
> +
> +/* Masking out the extension bits will yield the base modifier. */
> +#define VIVANTE_MOD_EXT_MASK              (VIVANTE_MOD_TS_MASK | \
> +                                           VIVANTE_MOD_COMP_MASK)
> +
>   /* NVIDIA frame buffer modifiers */
>   
>   /*
> diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h
> index 4537da20cc..87176ab075 100644
> --- a/include/standard-headers/linux/ethtool.h
> +++ b/include/standard-headers/linux/ethtool.h
> @@ -159,8 +159,10 @@ static inline uint32_t ethtool_cmd_speed(const struct ethtool_cmd *ep)
>    *	in its bus driver structure (e.g. pci_driver::name).  Must
>    *	not be an empty string.
>    * @version: Driver version string; may be an empty string
> - * @fw_version: Firmware version string; may be an empty string
> - * @erom_version: Expansion ROM version string; may be an empty string
> + * @fw_version: Firmware version string; driver defined; may be an
> + *	empty string
> + * @erom_version: Expansion ROM version string; driver defined; may be
> + *	an empty string
>    * @bus_info: Device bus address.  This should match the dev_name()
>    *	string for the underlying bus device, if there is one.  May be
>    *	an empty string.
> @@ -179,10 +181,6 @@ static inline uint32_t ethtool_cmd_speed(const struct ethtool_cmd *ep)
>    *
>    * Users can use the %ETHTOOL_GSSET_INFO command to get the number of
>    * strings in any string set (from Linux 2.6.34).
> - *
> - * Drivers should set at most @driver, @version, @fw_version and
> - * @bus_info in their get_drvinfo() implementation.  The ethtool
> - * core fills in the other fields using other driver operations.
>    */
>   struct ethtool_drvinfo {
>   	uint32_t	cmd;
> @@ -736,6 +734,51 @@ enum ethtool_module_power_mode {
>   	ETHTOOL_MODULE_POWER_MODE_HIGH,
>   };
>   
> +/**
> + * enum ethtool_podl_pse_admin_state - operational state of the PoDL PSE
> + *	functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState
> + * @ETHTOOL_PODL_PSE_ADMIN_STATE_UNKNOWN: state of PoDL PSE functions are
> + * 	unknown
> + * @ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED: PoDL PSE functions are disabled
> + * @ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED: PoDL PSE functions are enabled
> + */
> +enum ethtool_podl_pse_admin_state {
> +	ETHTOOL_PODL_PSE_ADMIN_STATE_UNKNOWN = 1,
> +	ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED,
> +	ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED,
> +};
> +
> +/**
> + * enum ethtool_podl_pse_pw_d_status - power detection status of the PoDL PSE.
> + *	IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus:
> + * @ETHTOOL_PODL_PSE_PW_D_STATUS_UNKNOWN: PoDL PSE
> + * @ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED: "The enumeration “disabled” is
> + *	asserted true when the PoDL PSE state diagram variable mr_pse_enable is
> + *	false"
> + * @ETHTOOL_PODL_PSE_PW_D_STATUS_SEARCHING: "The enumeration “searching” is
> + *	asserted true when either of the PSE state diagram variables
> + *	pi_detecting or pi_classifying is true."
> + * @ETHTOOL_PODL_PSE_PW_D_STATUS_DELIVERING: "The enumeration “deliveringPower”
> + *	is asserted true when the PoDL PSE state diagram variable pi_powered is
> + *	true."
> + * @ETHTOOL_PODL_PSE_PW_D_STATUS_SLEEP: "The enumeration “sleep” is asserted
> + *	true when the PoDL PSE state diagram variable pi_sleeping is true."
> + * @ETHTOOL_PODL_PSE_PW_D_STATUS_IDLE: "The enumeration “idle” is asserted true
> + *	when the logical combination of the PoDL PSE state diagram variables
> + *	pi_prebiased*!pi_sleeping is true."
> + * @ETHTOOL_PODL_PSE_PW_D_STATUS_ERROR: "The enumeration “error” is asserted
> + *	true when the PoDL PSE state diagram variable overload_held is true."
> + */
> +enum ethtool_podl_pse_pw_d_status {
> +	ETHTOOL_PODL_PSE_PW_D_STATUS_UNKNOWN = 1,
> +	ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED,
> +	ETHTOOL_PODL_PSE_PW_D_STATUS_SEARCHING,
> +	ETHTOOL_PODL_PSE_PW_D_STATUS_DELIVERING,
> +	ETHTOOL_PODL_PSE_PW_D_STATUS_SLEEP,
> +	ETHTOOL_PODL_PSE_PW_D_STATUS_IDLE,
> +	ETHTOOL_PODL_PSE_PW_D_STATUS_ERROR,
> +};
> +
>   /**
>    * struct ethtool_gstrings - string set for data tagging
>    * @cmd: Command number = %ETHTOOL_GSTRINGS
> @@ -1692,6 +1735,13 @@ enum ethtool_link_mode_bit_indices {
>   	ETHTOOL_LINK_MODE_100baseFX_Half_BIT		 = 90,
>   	ETHTOOL_LINK_MODE_100baseFX_Full_BIT		 = 91,
>   	ETHTOOL_LINK_MODE_10baseT1L_Full_BIT		 = 92,
> +	ETHTOOL_LINK_MODE_800000baseCR8_Full_BIT	 = 93,
> +	ETHTOOL_LINK_MODE_800000baseKR8_Full_BIT	 = 94,
> +	ETHTOOL_LINK_MODE_800000baseDR8_Full_BIT	 = 95,
> +	ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT	 = 96,
> +	ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT	 = 97,
> +	ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT	 = 98,
> +
>   	/* must be last entry */
>   	__ETHTOOL_LINK_MODE_MASK_NBITS
>   };
> @@ -1803,6 +1853,7 @@ enum ethtool_link_mode_bit_indices {
>   #define SPEED_100000		100000
>   #define SPEED_200000		200000
>   #define SPEED_400000		400000
> +#define SPEED_800000		800000
>   
>   #define SPEED_UNKNOWN		-1
>   
> @@ -1840,6 +1891,20 @@ static inline int ethtool_validate_duplex(uint8_t duplex)
>   #define MASTER_SLAVE_STATE_SLAVE		3
>   #define MASTER_SLAVE_STATE_ERR			4
>   
> +/* These are used to throttle the rate of data on the phy interface when the
> + * native speed of the interface is higher than the link speed. These should
> + * not be used for phy interfaces which natively support multiple speeds (e.g.
> + * MII or SGMII).
> + */
> +/* No rate matching performed. */
> +#define RATE_MATCH_NONE		0
> +/* The phy sends pause frames to throttle the MAC. */
> +#define RATE_MATCH_PAUSE	1
> +/* The phy asserts CRS to prevent the MAC from transmitting. */
> +#define RATE_MATCH_CRS		2
> +/* The MAC is programmed with a sufficiently-large IPG. */
> +#define RATE_MATCH_OPEN_LOOP	3
> +
>   /* Which connector port. */
>   #define PORT_TP			0x00
>   #define PORT_AUI		0x01
> @@ -2033,8 +2098,8 @@ enum ethtool_reset_flags {
>    *	reported consistently by PHYLIB.  Read-only.
>    * @master_slave_cfg: Master/slave port mode.
>    * @master_slave_state: Master/slave port state.
> + * @rate_matching: Rate adaptation performed by the PHY
>    * @reserved: Reserved for future use; see the note on reserved space.
> - * @reserved1: Reserved for future use; see the note on reserved space.
>    * @link_mode_masks: Variable length bitmaps.
>    *
>    * If autonegotiation is disabled, the speed and @duplex represent the
> @@ -2085,7 +2150,7 @@ struct ethtool_link_settings {
>   	uint8_t	transceiver;
>   	uint8_t	master_slave_cfg;
>   	uint8_t	master_slave_state;
> -	uint8_t	reserved1[1];
> +	uint8_t	rate_matching;
>   	uint32_t	reserved[7];
>   	uint32_t	link_mode_masks[];
>   	/* layout of link_mode_masks fields:
> diff --git a/include/standard-headers/linux/fuse.h b/include/standard-headers/linux/fuse.h
> index bda06258be..a1af78d989 100644
> --- a/include/standard-headers/linux/fuse.h
> +++ b/include/standard-headers/linux/fuse.h
> @@ -194,6 +194,13 @@
>    *  - add FUSE_SECURITY_CTX init flag
>    *  - add security context to create, mkdir, symlink, and mknod requests
>    *  - add FUSE_HAS_INODE_DAX, FUSE_ATTR_DAX
> + *
> + *  7.37
> + *  - add FUSE_TMPFILE
> + *
> + *  7.38
> + *  - add FUSE_EXPIRE_ONLY flag to fuse_notify_inval_entry
> + *  - add FOPEN_PARALLEL_DIRECT_WRITES
>    */
>   
>   #ifndef _LINUX_FUSE_H
> @@ -225,7 +232,7 @@
>   #define FUSE_KERNEL_VERSION 7
>   
>   /** Minor version number of this interface */
> -#define FUSE_KERNEL_MINOR_VERSION 36
> +#define FUSE_KERNEL_MINOR_VERSION 38
>   
>   /** The node ID of the root inode */
>   #define FUSE_ROOT_ID 1
> @@ -297,6 +304,7 @@ struct fuse_file_lock {
>    * FOPEN_CACHE_DIR: allow caching this directory
>    * FOPEN_STREAM: the file is stream-like (no file position at all)
>    * FOPEN_NOFLUSH: don't flush data cache on close (unless FUSE_WRITEBACK_CACHE)
> + * FOPEN_PARALLEL_DIRECT_WRITES: Allow concurrent direct writes on the same inode
>    */
>   #define FOPEN_DIRECT_IO		(1 << 0)
>   #define FOPEN_KEEP_CACHE	(1 << 1)
> @@ -304,6 +312,7 @@ struct fuse_file_lock {
>   #define FOPEN_CACHE_DIR		(1 << 3)
>   #define FOPEN_STREAM		(1 << 4)
>   #define FOPEN_NOFLUSH		(1 << 5)
> +#define FOPEN_PARALLEL_DIRECT_WRITES	(1 << 6)
>   
>   /**
>    * INIT request/reply flags
> @@ -484,6 +493,12 @@ struct fuse_file_lock {
>    */
>   #define FUSE_SETXATTR_ACL_KILL_SGID	(1 << 0)
>   
> +/**
> + * notify_inval_entry flags
> + * FUSE_EXPIRE_ONLY
> + */
> +#define FUSE_EXPIRE_ONLY		(1 << 0)
> +
>   enum fuse_opcode {
>   	FUSE_LOOKUP		= 1,
>   	FUSE_FORGET		= 2,  /* no reply */
> @@ -533,6 +548,7 @@ enum fuse_opcode {
>   	FUSE_SETUPMAPPING	= 48,
>   	FUSE_REMOVEMAPPING	= 49,
>   	FUSE_SYNCFS		= 50,
> +	FUSE_TMPFILE		= 51,
>   
>   	/* CUSE specific operations */
>   	CUSE_INIT		= 4096,
> @@ -911,7 +927,7 @@ struct fuse_notify_inval_inode_out {
>   struct fuse_notify_inval_entry_out {
>   	uint64_t	parent;
>   	uint32_t	namelen;
> -	uint32_t	padding;
> +	uint32_t	flags;
>   };
>   
>   struct fuse_notify_delete_out {
> diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h
> index 50790aee5a..f6bab08540 100644
> --- a/include/standard-headers/linux/input-event-codes.h
> +++ b/include/standard-headers/linux/input-event-codes.h
> @@ -614,6 +614,9 @@
>   #define KEY_KBD_LAYOUT_NEXT	0x248	/* AC Next Keyboard Layout Select */
>   #define KEY_EMOJI_PICKER	0x249	/* Show/hide emoji picker (HUTRR101) */
>   #define KEY_DICTATE		0x24a	/* Start or Stop Voice Dictation Session (HUTRR99) */
> +#define KEY_CAMERA_ACCESS_ENABLE	0x24b	/* Enables programmatic access to camera devices. (HUTRR72) */
> +#define KEY_CAMERA_ACCESS_DISABLE	0x24c	/* Disables programmatic access to camera devices. (HUTRR72) */
> +#define KEY_CAMERA_ACCESS_TOGGLE	0x24d	/* Toggles the current state of the camera access control. (HUTRR72) */
>   
>   #define KEY_BRIGHTNESS_MIN		0x250	/* Set Brightness to Minimum */
>   #define KEY_BRIGHTNESS_MAX		0x251	/* Set Brightness to Maximum */
> @@ -862,6 +865,7 @@
>   #define ABS_TOOL_WIDTH		0x1c
>   
>   #define ABS_VOLUME		0x20
> +#define ABS_PROFILE		0x21
>   
>   #define ABS_MISC		0x28
>   
> diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h
> index 57b8e2ffb1..85ab127881 100644
> --- a/include/standard-headers/linux/pci_regs.h
> +++ b/include/standard-headers/linux/pci_regs.h
> @@ -1058,6 +1058,7 @@
>   /* Precision Time Measurement */
>   #define PCI_PTM_CAP			0x04	    /* PTM Capability */
>   #define  PCI_PTM_CAP_REQ		0x00000001  /* Requester capable */
> +#define  PCI_PTM_CAP_RES		0x00000002  /* Responder capable */
>   #define  PCI_PTM_CAP_ROOT		0x00000004  /* Root capable */
>   #define  PCI_PTM_GRANULARITY_MASK	0x0000FF00  /* Clock granularity */
>   #define PCI_PTM_CTRL			0x08	    /* PTM Control */
> @@ -1119,6 +1120,7 @@
>   #define  PCI_DOE_STATUS_DATA_OBJECT_READY	0x80000000  /* Data Object Ready */
>   #define PCI_DOE_WRITE		0x10    /* DOE Write Data Mailbox Register */
>   #define PCI_DOE_READ		0x14    /* DOE Read Data Mailbox Register */
> +#define PCI_DOE_CAP_SIZEOF	0x18	/* Size of DOE register block */
>   
>   /* DOE Data Object - note not actually registers */
>   #define PCI_DOE_DATA_OBJECT_HEADER_1_VID		0x0000ffff
> diff --git a/include/standard-headers/linux/virtio_blk.h b/include/standard-headers/linux/virtio_blk.h
> index 2dcc90826a..e81715cd70 100644
> --- a/include/standard-headers/linux/virtio_blk.h
> +++ b/include/standard-headers/linux/virtio_blk.h
> @@ -40,6 +40,7 @@
>   #define VIRTIO_BLK_F_MQ		12	/* support more than one vq */
>   #define VIRTIO_BLK_F_DISCARD	13	/* DISCARD is supported */
>   #define VIRTIO_BLK_F_WRITE_ZEROES	14	/* WRITE ZEROES is supported */
> +#define VIRTIO_BLK_F_SECURE_ERASE	16 /* Secure Erase is supported */
>   
>   /* Legacy feature bits */
>   #ifndef VIRTIO_BLK_NO_LEGACY
> @@ -119,6 +120,21 @@ struct virtio_blk_config {
>   	uint8_t write_zeroes_may_unmap;
>   
>   	uint8_t unused1[3];
> +
> +	/* the next 3 entries are guarded by VIRTIO_BLK_F_SECURE_ERASE */
> +	/*
> +	 * The maximum secure erase sectors (in 512-byte sectors) for
> +	 * one segment.
> +	 */
> +	__virtio32 max_secure_erase_sectors;
> +	/*
> +	 * The maximum number of secure erase segments in a
> +	 * secure erase command.
> +	 */
> +	__virtio32 max_secure_erase_seg;
> +	/* Secure erase commands must be aligned to this number of sectors. */
> +	__virtio32 secure_erase_sector_alignment;
> +
>   } QEMU_PACKED;
>   
>   /*
> @@ -153,6 +169,9 @@ struct virtio_blk_config {
>   /* Write zeroes command */
>   #define VIRTIO_BLK_T_WRITE_ZEROES	13
>   
> +/* Secure erase command */
> +#define VIRTIO_BLK_T_SECURE_ERASE	14
> +
>   #ifndef VIRTIO_BLK_NO_LEGACY
>   /* Barrier before this op. */
>   #define VIRTIO_BLK_T_BARRIER	0x80000000
> diff --git a/include/standard-headers/linux/virtio_bt.h b/include/standard-headers/linux/virtio_bt.h
> index 245e1eff4b..a11ecc3f92 100644
> --- a/include/standard-headers/linux/virtio_bt.h
> +++ b/include/standard-headers/linux/virtio_bt.h
> @@ -9,6 +9,7 @@
>   #define VIRTIO_BT_F_VND_HCI	0	/* Indicates vendor command support */
>   #define VIRTIO_BT_F_MSFT_EXT	1	/* Indicates MSFT vendor support */
>   #define VIRTIO_BT_F_AOSP_EXT	2	/* Indicates AOSP vendor support */
> +#define VIRTIO_BT_F_CONFIG_V2	3	/* Use second version configuration */
>   
>   enum virtio_bt_config_type {
>   	VIRTIO_BT_CONFIG_TYPE_PRIMARY	= 0,
> @@ -28,4 +29,11 @@ struct virtio_bt_config {
>   	uint16_t msft_opcode;
>   } QEMU_PACKED;
>   
> +struct virtio_bt_config_v2 {
> +	uint8_t  type;
> +	uint8_t  alignment;
> +	uint16_t vendor;
> +	uint16_t msft_opcode;
> +};
> +
>   #endif /* _LINUX_VIRTIO_BT_H */
> diff --git a/include/standard-headers/linux/virtio_net.h b/include/standard-headers/linux/virtio_net.h
> index 42c68caf71..c0e797067a 100644
> --- a/include/standard-headers/linux/virtio_net.h
> +++ b/include/standard-headers/linux/virtio_net.h
> @@ -57,6 +57,9 @@
>   					 * Steering */
>   #define VIRTIO_NET_F_CTRL_MAC_ADDR 23	/* Set MAC address */
>   #define VIRTIO_NET_F_NOTF_COAL	53	/* Device supports notifications coalescing */
> +#define VIRTIO_NET_F_GUEST_USO4	54	/* Guest can handle USOv4 in. */
> +#define VIRTIO_NET_F_GUEST_USO6	55	/* Guest can handle USOv6 in. */
> +#define VIRTIO_NET_F_HOST_USO	56	/* Host can handle USO in. */
>   #define VIRTIO_NET_F_HASH_REPORT  57	/* Supports hash report */
>   #define VIRTIO_NET_F_RSS	  60	/* Supports RSS RX steering */
>   #define VIRTIO_NET_F_RSC_EXT	  61	/* extended coalescing info */
> @@ -130,6 +133,7 @@ struct virtio_net_hdr_v1 {
>   #define VIRTIO_NET_HDR_GSO_TCPV4	1	/* GSO frame, IPv4 TCP (TSO) */
>   #define VIRTIO_NET_HDR_GSO_UDP		3	/* GSO frame, IPv4 UDP (UFO) */
>   #define VIRTIO_NET_HDR_GSO_TCPV6	4	/* GSO frame, IPv6 TCP */
> +#define VIRTIO_NET_HDR_GSO_UDP_L4	5	/* GSO frame, IPv4& IPv6 UDP (USO) */
>   #define VIRTIO_NET_HDR_GSO_ECN		0x80	/* TCP has ECN set */
>   	uint8_t gso_type;
>   	__virtio16 hdr_len;	/* Ethernet + IP + tcp/udp hdrs */
> diff --git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h
> index 4bf2d7246e..a7cfefb3a8 100644
> --- a/linux-headers/asm-arm64/kvm.h
> +++ b/linux-headers/asm-arm64/kvm.h
> @@ -43,6 +43,7 @@
>   #define __KVM_HAVE_VCPU_EVENTS
>   
>   #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
> +#define KVM_DIRTY_LOG_PAGE_OFFSET 64
>   
>   #define KVM_REG_SIZE(id)						\
>   	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
> diff --git a/linux-headers/asm-generic/hugetlb_encode.h b/linux-headers/asm-generic/hugetlb_encode.h
> index 4f3d5aaa11..de687009bf 100644
> --- a/linux-headers/asm-generic/hugetlb_encode.h
> +++ b/linux-headers/asm-generic/hugetlb_encode.h
> @@ -20,18 +20,18 @@
>   #define HUGETLB_FLAG_ENCODE_SHIFT	26
>   #define HUGETLB_FLAG_ENCODE_MASK	0x3f
>   
> -#define HUGETLB_FLAG_ENCODE_16KB	(14 << HUGETLB_FLAG_ENCODE_SHIFT)
> -#define HUGETLB_FLAG_ENCODE_64KB	(16 << HUGETLB_FLAG_ENCODE_SHIFT)
> -#define HUGETLB_FLAG_ENCODE_512KB	(19 << HUGETLB_FLAG_ENCODE_SHIFT)
> -#define HUGETLB_FLAG_ENCODE_1MB		(20 << HUGETLB_FLAG_ENCODE_SHIFT)
> -#define HUGETLB_FLAG_ENCODE_2MB		(21 << HUGETLB_FLAG_ENCODE_SHIFT)
> -#define HUGETLB_FLAG_ENCODE_8MB		(23 << HUGETLB_FLAG_ENCODE_SHIFT)
> -#define HUGETLB_FLAG_ENCODE_16MB	(24 << HUGETLB_FLAG_ENCODE_SHIFT)
> -#define HUGETLB_FLAG_ENCODE_32MB	(25 << HUGETLB_FLAG_ENCODE_SHIFT)
> -#define HUGETLB_FLAG_ENCODE_256MB	(28 << HUGETLB_FLAG_ENCODE_SHIFT)
> -#define HUGETLB_FLAG_ENCODE_512MB	(29 << HUGETLB_FLAG_ENCODE_SHIFT)
> -#define HUGETLB_FLAG_ENCODE_1GB		(30 << HUGETLB_FLAG_ENCODE_SHIFT)
> -#define HUGETLB_FLAG_ENCODE_2GB		(31 << HUGETLB_FLAG_ENCODE_SHIFT)
> -#define HUGETLB_FLAG_ENCODE_16GB	(34 << HUGETLB_FLAG_ENCODE_SHIFT)
> +#define HUGETLB_FLAG_ENCODE_16KB	(14U << HUGETLB_FLAG_ENCODE_SHIFT)
> +#define HUGETLB_FLAG_ENCODE_64KB	(16U << HUGETLB_FLAG_ENCODE_SHIFT)
> +#define HUGETLB_FLAG_ENCODE_512KB	(19U << HUGETLB_FLAG_ENCODE_SHIFT)
> +#define HUGETLB_FLAG_ENCODE_1MB		(20U << HUGETLB_FLAG_ENCODE_SHIFT)
> +#define HUGETLB_FLAG_ENCODE_2MB		(21U << HUGETLB_FLAG_ENCODE_SHIFT)
> +#define HUGETLB_FLAG_ENCODE_8MB		(23U << HUGETLB_FLAG_ENCODE_SHIFT)
> +#define HUGETLB_FLAG_ENCODE_16MB	(24U << HUGETLB_FLAG_ENCODE_SHIFT)
> +#define HUGETLB_FLAG_ENCODE_32MB	(25U << HUGETLB_FLAG_ENCODE_SHIFT)
> +#define HUGETLB_FLAG_ENCODE_256MB	(28U << HUGETLB_FLAG_ENCODE_SHIFT)
> +#define HUGETLB_FLAG_ENCODE_512MB	(29U << HUGETLB_FLAG_ENCODE_SHIFT)
> +#define HUGETLB_FLAG_ENCODE_1GB		(30U << HUGETLB_FLAG_ENCODE_SHIFT)
> +#define HUGETLB_FLAG_ENCODE_2GB		(31U << HUGETLB_FLAG_ENCODE_SHIFT)
> +#define HUGETLB_FLAG_ENCODE_16GB	(34U << HUGETLB_FLAG_ENCODE_SHIFT)
>   
>   #endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */
> diff --git a/linux-headers/asm-generic/mman-common.h b/linux-headers/asm-generic/mman-common.h
> index 6c1aa92a92..6ce1f1ceb4 100644
> --- a/linux-headers/asm-generic/mman-common.h
> +++ b/linux-headers/asm-generic/mman-common.h
> @@ -77,6 +77,8 @@
>   
>   #define MADV_DONTNEED_LOCKED	24	/* like DONTNEED, but drop locked pages too */
>   
> +#define MADV_COLLAPSE	25		/* Synchronous hugepage collapse */
> +
>   /* compatibility flags */
>   #define MAP_FILE	0
>   
> diff --git a/linux-headers/asm-mips/mman.h b/linux-headers/asm-mips/mman.h
> index 1be428663c..c6e1fc77c9 100644
> --- a/linux-headers/asm-mips/mman.h
> +++ b/linux-headers/asm-mips/mman.h
> @@ -103,6 +103,8 @@
>   
>   #define MADV_DONTNEED_LOCKED	24	/* like DONTNEED, but drop locked pages too */
>   
> +#define MADV_COLLAPSE	25		/* Synchronous hugepage collapse */
> +
>   /* compatibility flags */
>   #define MAP_FILE	0
>   
> diff --git a/linux-headers/asm-riscv/kvm.h b/linux-headers/asm-riscv/kvm.h
> index 7351417afd..92af6f3f05 100644
> --- a/linux-headers/asm-riscv/kvm.h
> +++ b/linux-headers/asm-riscv/kvm.h
> @@ -48,6 +48,10 @@ struct kvm_sregs {
>   /* CONFIG registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
>   struct kvm_riscv_config {
>   	unsigned long isa;
> +	unsigned long zicbom_block_size;
> +	unsigned long mvendorid;
> +	unsigned long marchid;
> +	unsigned long mimpid;
>   };
>   
>   /* CORE registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
> @@ -98,6 +102,9 @@ enum KVM_RISCV_ISA_EXT_ID {
>   	KVM_RISCV_ISA_EXT_M,
>   	KVM_RISCV_ISA_EXT_SVPBMT,
>   	KVM_RISCV_ISA_EXT_SSTC,
> +	KVM_RISCV_ISA_EXT_SVINVAL,
> +	KVM_RISCV_ISA_EXT_ZIHINTPAUSE,
> +	KVM_RISCV_ISA_EXT_ZICBOM,
>   	KVM_RISCV_ISA_EXT_MAX,
>   };
>   
> diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h
> index 46de10a809..2747d2ce14 100644
> --- a/linux-headers/asm-x86/kvm.h
> +++ b/linux-headers/asm-x86/kvm.h
> @@ -53,14 +53,6 @@
>   /* Architectural interrupt line count. */
>   #define KVM_NR_INTERRUPTS 256
>   
> -struct kvm_memory_alias {
> -	__u32 slot;  /* this has a different namespace than memory slots */
> -	__u32 flags;
> -	__u64 guest_phys_addr;
> -	__u64 memory_size;
> -	__u64 target_phys_addr;
> -};
> -
>   /* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */
>   struct kvm_pic_state {
>   	__u8 last_irr;	/* edge detection */
> @@ -214,6 +206,8 @@ struct kvm_msr_list {
>   struct kvm_msr_filter_range {
>   #define KVM_MSR_FILTER_READ  (1 << 0)
>   #define KVM_MSR_FILTER_WRITE (1 << 1)
> +#define KVM_MSR_FILTER_RANGE_VALID_MASK (KVM_MSR_FILTER_READ | \
> +					 KVM_MSR_FILTER_WRITE)
>   	__u32 flags;
>   	__u32 nmsrs; /* number of msrs in bitmap */
>   	__u32 base;  /* MSR index the bitmap starts at */
> @@ -224,6 +218,7 @@ struct kvm_msr_filter_range {
>   struct kvm_msr_filter {
>   #define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
>   #define KVM_MSR_FILTER_DEFAULT_DENY  (1 << 0)
> +#define KVM_MSR_FILTER_VALID_MASK (KVM_MSR_FILTER_DEFAULT_DENY)
>   	__u32 flags;
>   	struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
>   };
> diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
> index ebdafa576d..30b2795d10 100644
> --- a/linux-headers/linux/kvm.h
> +++ b/linux-headers/linux/kvm.h
> @@ -86,14 +86,6 @@ struct kvm_debug_guest {
>   /* *** End of deprecated interfaces *** */
>   
>   
> -/* for KVM_CREATE_MEMORY_REGION */
> -struct kvm_memory_region {
> -	__u32 slot;
> -	__u32 flags;
> -	__u64 guest_phys_addr;
> -	__u64 memory_size; /* bytes */
> -};
> -
>   /* for KVM_SET_USER_MEMORY_REGION */
>   struct kvm_userspace_memory_region {
>   	__u32 slot;
> @@ -104,9 +96,9 @@ struct kvm_userspace_memory_region {
>   };
>   
>   /*
> - * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace,
> - * other bits are reserved for kvm internal use which are defined in
> - * include/linux/kvm_host.h.
> + * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
> + * userspace, other bits are reserved for kvm internal use which are defined
> + * in include/linux/kvm_host.h.
>    */
>   #define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
>   #define KVM_MEM_READONLY	(1UL << 1)
> @@ -483,6 +475,9 @@ struct kvm_run {
>   #define KVM_MSR_EXIT_REASON_INVAL	(1 << 0)
>   #define KVM_MSR_EXIT_REASON_UNKNOWN	(1 << 1)
>   #define KVM_MSR_EXIT_REASON_FILTER	(1 << 2)
> +#define KVM_MSR_EXIT_REASON_VALID_MASK	(KVM_MSR_EXIT_REASON_INVAL   |	\
> +					 KVM_MSR_EXIT_REASON_UNKNOWN |	\
> +					 KVM_MSR_EXIT_REASON_FILTER)
>   			__u32 reason; /* kernel -> user */
>   			__u32 index; /* kernel -> user */
>   			__u64 data; /* kernel <-> user */
> @@ -1175,6 +1170,9 @@ struct kvm_ppc_resize_hpt {
>   #define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220
>   #define KVM_CAP_S390_ZPCI_OP 221
>   #define KVM_CAP_S390_CPU_TOPOLOGY 222
> +#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223
> +#define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224
> +#define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225
>   
>   #ifdef KVM_CAP_IRQ_ROUTING
>   
> @@ -1264,6 +1262,7 @@ struct kvm_x86_mce {
>   #define KVM_XEN_HVM_CONFIG_RUNSTATE		(1 << 3)
>   #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
>   #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
> +#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
>   
>   struct kvm_xen_hvm_config {
>   	__u32 flags;
> @@ -1434,18 +1433,12 @@ struct kvm_vfio_spapr_tce {
>   	__s32	tablefd;
>   };
>   
> -/*
> - * ioctls for VM fds
> - */
> -#define KVM_SET_MEMORY_REGION     _IOW(KVMIO,  0x40, struct kvm_memory_region)
>   /*
>    * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns
>    * a vcpu fd.
>    */
>   #define KVM_CREATE_VCPU           _IO(KVMIO,   0x41)
>   #define KVM_GET_DIRTY_LOG         _IOW(KVMIO,  0x42, struct kvm_dirty_log)
> -/* KVM_SET_MEMORY_ALIAS is obsolete: */
> -#define KVM_SET_MEMORY_ALIAS      _IOW(KVMIO,  0x43, struct kvm_memory_alias)
>   #define KVM_SET_NR_MMU_PAGES      _IO(KVMIO,   0x44)
>   #define KVM_GET_NR_MMU_PAGES      _IO(KVMIO,   0x45)
>   #define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \
> @@ -1737,6 +1730,8 @@ enum pv_cmd_id {
>   	KVM_PV_UNSHARE_ALL,
>   	KVM_PV_INFO,
>   	KVM_PV_DUMP,
> +	KVM_PV_ASYNC_CLEANUP_PREPARE,
> +	KVM_PV_ASYNC_CLEANUP_PERFORM,
>   };
>   
>   struct kvm_pv_cmd {
> @@ -1767,6 +1762,7 @@ struct kvm_xen_hvm_attr {
>   	union {
>   		__u8 long_mode;
>   		__u8 vector;
> +		__u8 runstate_update_flag;
>   		struct {
>   			__u64 gfn;
>   		} shared_info;
> @@ -1807,6 +1803,8 @@ struct kvm_xen_hvm_attr {
>   /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
>   #define KVM_XEN_ATTR_TYPE_EVTCHN		0x3
>   #define KVM_XEN_ATTR_TYPE_XEN_VERSION		0x4
> +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */
> +#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG	0x5
>   
>   /* Per-vCPU Xen attributes */
>   #define KVM_XEN_VCPU_GET_ATTR	_IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
> diff --git a/linux-headers/linux/psci.h b/linux-headers/linux/psci.h
> index 213b2a0f70..e60dfd8907 100644
> --- a/linux-headers/linux/psci.h
> +++ b/linux-headers/linux/psci.h
> @@ -48,12 +48,26 @@
>   #define PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU	PSCI_0_2_FN64(7)
>   
>   #define PSCI_1_0_FN_PSCI_FEATURES		PSCI_0_2_FN(10)
> +#define PSCI_1_0_FN_CPU_FREEZE			PSCI_0_2_FN(11)
> +#define PSCI_1_0_FN_CPU_DEFAULT_SUSPEND		PSCI_0_2_FN(12)
> +#define PSCI_1_0_FN_NODE_HW_STATE		PSCI_0_2_FN(13)
>   #define PSCI_1_0_FN_SYSTEM_SUSPEND		PSCI_0_2_FN(14)
>   #define PSCI_1_0_FN_SET_SUSPEND_MODE		PSCI_0_2_FN(15)
> +#define PSCI_1_0_FN_STAT_RESIDENCY		PSCI_0_2_FN(16)
> +#define PSCI_1_0_FN_STAT_COUNT			PSCI_0_2_FN(17)
> +
>   #define PSCI_1_1_FN_SYSTEM_RESET2		PSCI_0_2_FN(18)
> +#define PSCI_1_1_FN_MEM_PROTECT			PSCI_0_2_FN(19)
> +#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE	PSCI_0_2_FN(19)
>   
> +#define PSCI_1_0_FN64_CPU_DEFAULT_SUSPEND	PSCI_0_2_FN64(12)
> +#define PSCI_1_0_FN64_NODE_HW_STATE		PSCI_0_2_FN64(13)
>   #define PSCI_1_0_FN64_SYSTEM_SUSPEND		PSCI_0_2_FN64(14)
> +#define PSCI_1_0_FN64_STAT_RESIDENCY		PSCI_0_2_FN64(16)
> +#define PSCI_1_0_FN64_STAT_COUNT		PSCI_0_2_FN64(17)
> +
>   #define PSCI_1_1_FN64_SYSTEM_RESET2		PSCI_0_2_FN64(18)
> +#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE	PSCI_0_2_FN64(19)
>   
>   /* PSCI v0.2 power state encoding for CPU_SUSPEND function */
>   #define PSCI_0_2_POWER_STATE_ID_MASK		0xffff
> diff --git a/linux-headers/linux/userfaultfd.h b/linux-headers/linux/userfaultfd.h
> index a3a377cd44..ba5d0df52f 100644
> --- a/linux-headers/linux/userfaultfd.h
> +++ b/linux-headers/linux/userfaultfd.h
> @@ -12,6 +12,10 @@
>   
>   #include <linux/types.h>
>   
> +/* ioctls for /dev/userfaultfd */
> +#define USERFAULTFD_IOC 0xAA
> +#define USERFAULTFD_IOC_NEW _IO(USERFAULTFD_IOC, 0x00)
> +
>   /*
>    * If the UFFDIO_API is upgraded someday, the UFFDIO_UNREGISTER and
>    * UFFDIO_WAKE ioctls should be defined as _IOW and not as _IOR.  In
> diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
> index ede44b5572..c59692ce0b 100644
> --- a/linux-headers/linux/vfio.h
> +++ b/linux-headers/linux/vfio.h
> @@ -819,12 +819,20 @@ struct vfio_device_feature {
>    * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P means that RUNNING_P2P
>    * is supported in addition to the STOP_COPY states.
>    *
> + * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY means that
> + * PRE_COPY is supported in addition to the STOP_COPY states.
> + *
> + * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P | VFIO_MIGRATION_PRE_COPY
> + * means that RUNNING_P2P, PRE_COPY and PRE_COPY_P2P are supported
> + * in addition to the STOP_COPY states.
> + *
>    * Other combinations of flags have behavior to be defined in the future.
>    */
>   struct vfio_device_feature_migration {
>   	__aligned_u64 flags;
>   #define VFIO_MIGRATION_STOP_COPY	(1 << 0)
>   #define VFIO_MIGRATION_P2P		(1 << 1)
> +#define VFIO_MIGRATION_PRE_COPY		(1 << 2)
>   };
>   #define VFIO_DEVICE_FEATURE_MIGRATION 1
>   
> @@ -875,8 +883,13 @@ struct vfio_device_feature_mig_state {
>    *  RESUMING - The device is stopped and is loading a new internal state
>    *  ERROR - The device has failed and must be reset
>    *
> - * And 1 optional state to support VFIO_MIGRATION_P2P:
> + * And optional states to support VFIO_MIGRATION_P2P:
>    *  RUNNING_P2P - RUNNING, except the device cannot do peer to peer DMA
> + * And VFIO_MIGRATION_PRE_COPY:
> + *  PRE_COPY - The device is running normally but tracking internal state
> + *             changes
> + * And VFIO_MIGRATION_P2P | VFIO_MIGRATION_PRE_COPY:
> + *  PRE_COPY_P2P - PRE_COPY, except the device cannot do peer to peer DMA
>    *
>    * The FSM takes actions on the arcs between FSM states. The driver implements
>    * the following behavior for the FSM arcs:
> @@ -908,20 +921,48 @@ struct vfio_device_feature_mig_state {
>    *
>    *   To abort a RESUMING session the device must be reset.
>    *
> + * PRE_COPY -> RUNNING
>    * RUNNING_P2P -> RUNNING
>    *   While in RUNNING the device is fully operational, the device may generate
>    *   interrupts, DMA, respond to MMIO, all vfio device regions are functional,
>    *   and the device may advance its internal state.
>    *
> + *   The PRE_COPY arc will terminate a data transfer session.
> + *
> + * PRE_COPY_P2P -> RUNNING_P2P
>    * RUNNING -> RUNNING_P2P
>    * STOP -> RUNNING_P2P
>    *   While in RUNNING_P2P the device is partially running in the P2P quiescent
>    *   state defined below.
>    *
> + *   The PRE_COPY_P2P arc will terminate a data transfer session.
> + *
> + * RUNNING -> PRE_COPY
> + * RUNNING_P2P -> PRE_COPY_P2P
>    * STOP -> STOP_COPY
> - *   This arc begin the process of saving the device state and will return a
> - *   new data_fd.
> + *   PRE_COPY, PRE_COPY_P2P and STOP_COPY form the "saving group" of states
> + *   which share a data transfer session. Moving between these states alters
> + *   what is streamed in session, but does not terminate or otherwise affect
> + *   the associated fd.
> + *
> + *   These arcs begin the process of saving the device state and will return a
> + *   new data_fd. The migration driver may perform actions such as enabling
> + *   dirty logging of device state when entering PRE_COPY or PER_COPY_P2P.
> + *
> + *   Each arc does not change the device operation, the device remains
> + *   RUNNING, P2P quiesced or in STOP. The STOP_COPY state is described below
> + *   in PRE_COPY_P2P -> STOP_COPY.
> + *
> + * PRE_COPY -> PRE_COPY_P2P
> + *   Entering PRE_COPY_P2P continues all the behaviors of PRE_COPY above.
> + *   However, while in the PRE_COPY_P2P state, the device is partially running
> + *   in the P2P quiescent state defined below, like RUNNING_P2P.
> + *
> + * PRE_COPY_P2P -> PRE_COPY
> + *   This arc allows returning the device to a full RUNNING behavior while
> + *   continuing all the behaviors of PRE_COPY.
>    *
> + * PRE_COPY_P2P -> STOP_COPY
>    *   While in the STOP_COPY state the device has the same behavior as STOP
>    *   with the addition that the data transfers session continues to stream the
>    *   migration state. End of stream on the FD indicates the entire device
> @@ -939,6 +980,13 @@ struct vfio_device_feature_mig_state {
>    *   device state for this arc if required to prepare the device to receive the
>    *   migration data.
>    *
> + * STOP_COPY -> PRE_COPY
> + * STOP_COPY -> PRE_COPY_P2P
> + *   These arcs are not permitted and return error if requested. Future
> + *   revisions of this API may define behaviors for these arcs, in this case
> + *   support will be discoverable by a new flag in
> + *   VFIO_DEVICE_FEATURE_MIGRATION.
> + *
>    * any -> ERROR
>    *   ERROR cannot be specified as a device state, however any transition request
>    *   can be failed with an errno return and may then move the device_state into
> @@ -950,7 +998,7 @@ struct vfio_device_feature_mig_state {
>    * The optional peer to peer (P2P) quiescent state is intended to be a quiescent
>    * state for the device for the purposes of managing multiple devices within a
>    * user context where peer-to-peer DMA between devices may be active. The
> - * RUNNING_P2P states must prevent the device from initiating
> + * RUNNING_P2P and PRE_COPY_P2P states must prevent the device from initiating
>    * any new P2P DMA transactions. If the device can identify P2P transactions
>    * then it can stop only P2P DMA, otherwise it must stop all DMA. The migration
>    * driver must complete any such outstanding operations prior to completing the
> @@ -963,6 +1011,8 @@ struct vfio_device_feature_mig_state {
>    * above FSM arcs. As there are multiple paths through the FSM arcs the path
>    * should be selected based on the following rules:
>    *   - Select the shortest path.
> + *   - The path cannot have saving group states as interior arcs, only
> + *     starting/end states.
>    * Refer to vfio_mig_get_next_state() for the result of the algorithm.
>    *
>    * The automatic transit through the FSM arcs that make up the combination
> @@ -976,6 +1026,9 @@ struct vfio_device_feature_mig_state {
>    * support them. The user can discover if these states are supported by using
>    * VFIO_DEVICE_FEATURE_MIGRATION. By using combination transitions the user can
>    * avoid knowing about these optional states if the kernel driver supports them.
> + *
> + * Arcs touching PRE_COPY and PRE_COPY_P2P are removed if support for PRE_COPY
> + * is not present.
>    */
>   enum vfio_device_mig_state {
>   	VFIO_DEVICE_STATE_ERROR = 0,
> @@ -984,8 +1037,225 @@ enum vfio_device_mig_state {
>   	VFIO_DEVICE_STATE_STOP_COPY = 3,
>   	VFIO_DEVICE_STATE_RESUMING = 4,
>   	VFIO_DEVICE_STATE_RUNNING_P2P = 5,
> +	VFIO_DEVICE_STATE_PRE_COPY = 6,
> +	VFIO_DEVICE_STATE_PRE_COPY_P2P = 7,
> +};
> +
> +/**
> + * VFIO_MIG_GET_PRECOPY_INFO - _IO(VFIO_TYPE, VFIO_BASE + 21)
> + *
> + * This ioctl is used on the migration data FD in the precopy phase of the
> + * migration data transfer. It returns an estimate of the current data sizes
> + * remaining to be transferred. It allows the user to judge when it is
> + * appropriate to leave PRE_COPY for STOP_COPY.
> + *
> + * This ioctl is valid only in PRE_COPY states and kernel driver should
> + * return -EINVAL from any other migration state.
> + *
> + * The vfio_precopy_info data structure returned by this ioctl provides
> + * estimates of data available from the device during the PRE_COPY states.
> + * This estimate is split into two categories, initial_bytes and
> + * dirty_bytes.
> + *
> + * The initial_bytes field indicates the amount of initial precopy
> + * data available from the device. This field should have a non-zero initial
> + * value and decrease as migration data is read from the device.
> + * It is recommended to leave PRE_COPY for STOP_COPY only after this field
> + * reaches zero. Leaving PRE_COPY earlier might make things slower.
> + *
> + * The dirty_bytes field tracks device state changes relative to data
> + * previously retrieved.  This field starts at zero and may increase as
> + * the internal device state is modified or decrease as that modified
> + * state is read from the device.
> + *
> + * Userspace may use the combination of these fields to estimate the
> + * potential data size available during the PRE_COPY phases, as well as
> + * trends relative to the rate the device is dirtying its internal
> + * state, but these fields are not required to have any bearing relative
> + * to the data size available during the STOP_COPY phase.
> + *
> + * Drivers have a lot of flexibility in when and what they transfer during the
> + * PRE_COPY phase, and how they report this from VFIO_MIG_GET_PRECOPY_INFO.
> + *
> + * During pre-copy the migration data FD has a temporary "end of stream" that is
> + * reached when both initial_bytes and dirty_byte are zero. For instance, this
> + * may indicate that the device is idle and not currently dirtying any internal
> + * state. When read() is done on this temporary end of stream the kernel driver
> + * should return ENOMSG from read(). Userspace can wait for more data (which may
> + * never come) by using poll.
> + *
> + * Once in STOP_COPY the migration data FD has a permanent end of stream
> + * signaled in the usual way by read() always returning 0 and poll always
> + * returning readable. ENOMSG may not be returned in STOP_COPY.
> + * Support for this ioctl is mandatory if a driver claims to support
> + * VFIO_MIGRATION_PRE_COPY.
> + *
> + * Return: 0 on success, -1 and errno set on failure.
> + */
> +struct vfio_precopy_info {
> +	__u32 argsz;
> +	__u32 flags;
> +	__aligned_u64 initial_bytes;
> +	__aligned_u64 dirty_bytes;
> +};
> +
> +#define VFIO_MIG_GET_PRECOPY_INFO _IO(VFIO_TYPE, VFIO_BASE + 21)
> +
> +/*
> + * Upon VFIO_DEVICE_FEATURE_SET, allow the device to be moved into a low power
> + * state with the platform-based power management.  Device use of lower power
> + * states depends on factors managed by the runtime power management core,
> + * including system level support and coordinating support among dependent
> + * devices.  Enabling device low power entry does not guarantee lower power
> + * usage by the device, nor is a mechanism provided through this feature to
> + * know the current power state of the device.  If any device access happens
> + * (either from the host or through the vfio uAPI) when the device is in the
> + * low power state, then the host will move the device out of the low power
> + * state as necessary prior to the access.  Once the access is completed, the
> + * device may re-enter the low power state.  For single shot low power support
> + * with wake-up notification, see
> + * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP below.  Access to mmap'd
> + * device regions is disabled on LOW_POWER_ENTRY and may only be resumed after
> + * calling LOW_POWER_EXIT.
> + */
> +#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY 3
> +
> +/*
> + * This device feature has the same behavior as
> + * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY with the exception that the user
> + * provides an eventfd for wake-up notification.  When the device moves out of
> + * the low power state for the wake-up, the host will not allow the device to
> + * re-enter a low power state without a subsequent user call to one of the low
> + * power entry device feature IOCTLs.  Access to mmap'd device regions is
> + * disabled on LOW_POWER_ENTRY_WITH_WAKEUP and may only be resumed after the
> + * low power exit.  The low power exit can happen either through LOW_POWER_EXIT
> + * or through any other access (where the wake-up notification has been
> + * generated).  The access to mmap'd device regions will not trigger low power
> + * exit.
> + *
> + * The notification through the provided eventfd will be generated only when
> + * the device has entered and is resumed from a low power state after
> + * calling this device feature IOCTL.  A device that has not entered low power
> + * state, as managed through the runtime power management core, will not
> + * generate a notification through the provided eventfd on access.  Calling the
> + * LOW_POWER_EXIT feature is optional in the case where notification has been
> + * signaled on the provided eventfd that a resume from low power has occurred.
> + */
> +struct vfio_device_low_power_entry_with_wakeup {
> +	__s32 wakeup_eventfd;
> +	__u32 reserved;
> +};
> +
> +#define VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP 4
> +
> +/*
> + * Upon VFIO_DEVICE_FEATURE_SET, disallow use of device low power states as
> + * previously enabled via VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY or
> + * VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP device features.
> + * This device feature IOCTL may itself generate a wakeup eventfd notification
> + * in the latter case if the device had previously entered a low power state.
> + */
> +#define VFIO_DEVICE_FEATURE_LOW_POWER_EXIT 5
> +
> +/*
> + * Upon VFIO_DEVICE_FEATURE_SET start/stop device DMA logging.
> + * VFIO_DEVICE_FEATURE_PROBE can be used to detect if the device supports
> + * DMA logging.
> + *
> + * DMA logging allows a device to internally record what DMAs the device is
> + * initiating and report them back to userspace. It is part of the VFIO
> + * migration infrastructure that allows implementing dirty page tracking
> + * during the pre copy phase of live migration. Only DMA WRITEs are logged,
> + * and this API is not connected to VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE.
> + *
> + * When DMA logging is started a range of IOVAs to monitor is provided and the
> + * device can optimize its logging to cover only the IOVA range given. Each
> + * DMA that the device initiates inside the range will be logged by the device
> + * for later retrieval.
> + *
> + * page_size is an input that hints what tracking granularity the device
> + * should try to achieve. If the device cannot do the hinted page size then
> + * it's the driver choice which page size to pick based on its support.
> + * On output the device will return the page size it selected.
> + *
> + * ranges is a pointer to an array of
> + * struct vfio_device_feature_dma_logging_range.
> + *
> + * The core kernel code guarantees to support by minimum num_ranges that fit
> + * into a single kernel page. User space can try higher values but should give
> + * up if the above can't be achieved as of some driver limitations.
> + *
> + * A single call to start device DMA logging can be issued and a matching stop
> + * should follow at the end. Another start is not allowed in the meantime.
> + */
> +struct vfio_device_feature_dma_logging_control {
> +	__aligned_u64 page_size;
> +	__u32 num_ranges;
> +	__u32 __reserved;
> +	__aligned_u64 ranges;
>   };
>   
> +struct vfio_device_feature_dma_logging_range {
> +	__aligned_u64 iova;
> +	__aligned_u64 length;
> +};
> +
> +#define VFIO_DEVICE_FEATURE_DMA_LOGGING_START 6
> +
> +/*
> + * Upon VFIO_DEVICE_FEATURE_SET stop device DMA logging that was started
> + * by VFIO_DEVICE_FEATURE_DMA_LOGGING_START
> + */
> +#define VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP 7
> +
> +/*
> + * Upon VFIO_DEVICE_FEATURE_GET read back and clear the device DMA log
> + *
> + * Query the device's DMA log for written pages within the given IOVA range.
> + * During querying the log is cleared for the IOVA range.
> + *
> + * bitmap is a pointer to an array of u64s that will hold the output bitmap
> + * with 1 bit reporting a page_size unit of IOVA. The mapping of IOVA to bits
> + * is given by:
> + *  bitmap[(addr - iova)/page_size] & (1ULL << (addr % 64))
> + *
> + * The input page_size can be any power of two value and does not have to
> + * match the value given to VFIO_DEVICE_FEATURE_DMA_LOGGING_START. The driver
> + * will format its internal logging to match the reporting page size, possibly
> + * by replicating bits if the internal page size is lower than requested.
> + *
> + * The LOGGING_REPORT will only set bits in the bitmap and never clear or
> + * perform any initialization of the user provided bitmap.
> + *
> + * If any error is returned userspace should assume that the dirty log is
> + * corrupted. Error recovery is to consider all memory dirty and try to
> + * restart the dirty tracking, or to abort/restart the whole migration.
> + *
> + * If DMA logging is not enabled, an error will be returned.
> + *
> + */
> +struct vfio_device_feature_dma_logging_report {
> +	__aligned_u64 iova;
> +	__aligned_u64 length;
> +	__aligned_u64 page_size;
> +	__aligned_u64 bitmap;
> +};
> +
> +#define VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT 8
> +
> +/*
> + * Upon VFIO_DEVICE_FEATURE_GET read back the estimated data length that will
> + * be required to complete stop copy.
> + *
> + * Note: Can be called on each device state.
> + */
> +
> +struct vfio_device_feature_mig_data_size {
> +	__aligned_u64 stop_copy_length;
> +};
> +
> +#define VFIO_DEVICE_FEATURE_MIG_DATA_SIZE 9
> +
>   /* -------- API for Type1 VFIO IOMMU -------- */
>   
>   /**