diff options
Diffstat (limited to 'include/uapi')
| -rw-r--r-- | include/uapi/asm-generic/param.h | 6 | ||||
| -rw-r--r-- | include/uapi/asm-generic/unistd.h | 8 | ||||
| -rw-r--r-- | include/uapi/linux/bits.h | 4 | ||||
| -rw-r--r-- | include/uapi/linux/btrfs.h | 3 | ||||
| -rw-r--r-- | include/uapi/linux/coredump.h | 104 | ||||
| -rw-r--r-- | include/uapi/linux/ethtool_netlink.h | 4 | ||||
| -rw-r--r-- | include/uapi/linux/ethtool_netlink_generated.h | 4 | ||||
| -rw-r--r-- | include/uapi/linux/falloc.h | 17 | ||||
| -rw-r--r-- | include/uapi/linux/fcntl.h | 18 | ||||
| -rw-r--r-- | include/uapi/linux/fs.h | 88 | ||||
| -rw-r--r-- | include/uapi/linux/kvm.h | 26 | ||||
| -rw-r--r-- | include/uapi/linux/mptcp_pm.h | 6 | ||||
| -rw-r--r-- | include/uapi/linux/netfilter/nf_tables.h | 10 | ||||
| -rw-r--r-- | include/uapi/linux/netfilter/nfnetlink.h | 2 | ||||
| -rw-r--r-- | include/uapi/linux/nsfs.h | 11 | ||||
| -rw-r--r-- | include/uapi/linux/pidfd.h | 15 | ||||
| -rw-r--r-- | include/uapi/linux/ublk_cmd.h | 32 | ||||
| -rw-r--r-- | include/uapi/linux/vm_sockets.h | 4 |
18 files changed, 316 insertions, 46 deletions
diff --git a/include/uapi/asm-generic/param.h b/include/uapi/asm-generic/param.h index baad02ea7f93..3ed505dfea13 100644 --- a/include/uapi/asm-generic/param.h +++ b/include/uapi/asm-generic/param.h @@ -2,8 +2,12 @@ #ifndef _UAPI__ASM_GENERIC_PARAM_H #define _UAPI__ASM_GENERIC_PARAM_H +#ifndef __USER_HZ +#define __USER_HZ 100 +#endif + #ifndef HZ -#define HZ 100 +#define HZ __USER_HZ #endif #ifndef EXEC_PAGESIZE diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 2892a45023af..04e0077fb4c9 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -852,8 +852,14 @@ __SYSCALL(__NR_removexattrat, sys_removexattrat) #define __NR_open_tree_attr 467 __SYSCALL(__NR_open_tree_attr, sys_open_tree_attr) +/* fs/inode.c */ +#define __NR_file_getattr 468 +__SYSCALL(__NR_file_getattr, sys_file_getattr) +#define __NR_file_setattr 469 +__SYSCALL(__NR_file_setattr, sys_file_setattr) + #undef __NR_syscalls -#define __NR_syscalls 468 +#define __NR_syscalls 470 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/bits.h b/include/uapi/linux/bits.h index 682b406e1067..a04afef9efca 100644 --- a/include/uapi/linux/bits.h +++ b/include/uapi/linux/bits.h @@ -4,9 +4,9 @@ #ifndef _UAPI_LINUX_BITS_H #define _UAPI_LINUX_BITS_H -#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h)))) +#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h)))) -#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h)))) +#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) #define __GENMASK_U128(h, l) \ ((_BIT128((h)) << 1) - (_BIT128(l))) diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index dd02160015b2..8e710bbb688e 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -616,8 +616,11 @@ struct btrfs_ioctl_clone_range_args { #define BTRFS_DEFRAG_RANGE_COMPRESS 1 #define BTRFS_DEFRAG_RANGE_START_IO 2 #define BTRFS_DEFRAG_RANGE_COMPRESS_LEVEL 4 +/* Request no compression on the range (uncompress if necessary). */ +#define BTRFS_DEFRAG_RANGE_NOCOMPRESS 8 #define BTRFS_DEFRAG_RANGE_FLAGS_SUPP (BTRFS_DEFRAG_RANGE_COMPRESS | \ BTRFS_DEFRAG_RANGE_COMPRESS_LEVEL | \ + BTRFS_DEFRAG_RANGE_NOCOMPRESS | \ BTRFS_DEFRAG_RANGE_START_IO) struct btrfs_ioctl_defrag_range_args { diff --git a/include/uapi/linux/coredump.h b/include/uapi/linux/coredump.h new file mode 100644 index 000000000000..dc3789b78af0 --- /dev/null +++ b/include/uapi/linux/coredump.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_LINUX_COREDUMP_H +#define _UAPI_LINUX_COREDUMP_H + +#include <linux/types.h> + +/** + * coredump_{req,ack} flags + * @COREDUMP_KERNEL: kernel writes coredump + * @COREDUMP_USERSPACE: userspace writes coredump + * @COREDUMP_REJECT: don't generate coredump + * @COREDUMP_WAIT: wait for coredump server + */ +enum { + COREDUMP_KERNEL = (1ULL << 0), + COREDUMP_USERSPACE = (1ULL << 1), + COREDUMP_REJECT = (1ULL << 2), + COREDUMP_WAIT = (1ULL << 3), +}; + +/** + * struct coredump_req - message kernel sends to userspace + * @size: size of struct coredump_req + * @size_ack: known size of struct coredump_ack on this kernel + * @mask: supported features + * + * When a coredump happens the kernel will connect to the coredump + * socket and send a coredump request to the coredump server. The @size + * member is set to the size of struct coredump_req and provides a hint + * to userspace how much data can be read. Userspace may use MSG_PEEK to + * peek the size of struct coredump_req and then choose to consume it in + * one go. Userspace may also simply read a COREDUMP_ACK_SIZE_VER0 + * request. If the size the kernel sends is larger userspace simply + * discards any remaining data. + * + * The coredump_req->mask member is set to the currently know features. + * Userspace may only set coredump_ack->mask to the bits raised by the + * kernel in coredump_req->mask. + * + * The coredump_req->size_ack member is set by the kernel to the size of + * struct coredump_ack the kernel knows. Userspace may only send up to + * coredump_req->size_ack bytes to the kernel and must set + * coredump_ack->size accordingly. + */ +struct coredump_req { + __u32 size; + __u32 size_ack; + __u64 mask; +}; + +enum { + COREDUMP_REQ_SIZE_VER0 = 16U, /* size of first published struct */ +}; + +/** + * struct coredump_ack - message userspace sends to kernel + * @size: size of the struct + * @spare: unused + * @mask: features kernel is supposed to use + * + * The @size member must be set to the size of struct coredump_ack. It + * may never exceed what the kernel returned in coredump_req->size_ack + * but it may of course be smaller (>= COREDUMP_ACK_SIZE_VER0 and <= + * coredump_req->size_ack). + * + * The @mask member must be set to the features the coredump server + * wants the kernel to use. Only bits the kernel returned in + * coredump_req->mask may be set. + */ +struct coredump_ack { + __u32 size; + __u32 spare; + __u64 mask; +}; + +enum { + COREDUMP_ACK_SIZE_VER0 = 16U, /* size of first published struct */ +}; + +/** + * enum coredump_mark - Markers for the coredump socket + * + * The kernel will place a single byte on the coredump socket. The + * markers notify userspace whether the coredump ack succeeded or + * failed. + * + * @COREDUMP_MARK_MINSIZE: the provided coredump_ack size was too small + * @COREDUMP_MARK_MAXSIZE: the provided coredump_ack size was too big + * @COREDUMP_MARK_UNSUPPORTED: the provided coredump_ack mask was invalid + * @COREDUMP_MARK_CONFLICTING: the provided coredump_ack mask has conflicting options + * @COREDUMP_MARK_REQACK: the coredump request and ack was successful + * @__COREDUMP_MARK_MAX: the maximum coredump mark value + */ +enum coredump_mark { + COREDUMP_MARK_REQACK = 0U, + COREDUMP_MARK_MINSIZE = 1U, + COREDUMP_MARK_MAXSIZE = 2U, + COREDUMP_MARK_UNSUPPORTED = 3U, + COREDUMP_MARK_CONFLICTING = 4U, + __COREDUMP_MARK_MAX = (1U << 31), +}; + +#endif /* _UAPI_LINUX_COREDUMP_H */ diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 9ff72cfb2e98..09a75bdb6560 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -208,10 +208,6 @@ enum { ETHTOOL_A_STATS_PHY_MAX = (__ETHTOOL_A_STATS_PHY_CNT - 1) }; -/* generic netlink info */ -#define ETHTOOL_GENL_NAME "ethtool" -#define ETHTOOL_GENL_VERSION 1 - #define ETHTOOL_MCGRP_MONITOR_NAME "monitor" #endif /* _UAPI_LINUX_ETHTOOL_NETLINK_H_ */ diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h index 9a02f579de22..aa8ab5227c1e 100644 --- a/include/uapi/linux/ethtool_netlink_generated.h +++ b/include/uapi/linux/ethtool_netlink_generated.h @@ -6,8 +6,8 @@ #ifndef _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H #define _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H -#define ETHTOOL_FAMILY_NAME "ethtool" -#define ETHTOOL_FAMILY_VERSION 1 +#define ETHTOOL_GENL_NAME "ethtool" +#define ETHTOOL_GENL_VERSION 1 enum { ETHTOOL_UDP_TUNNEL_TYPE_VXLAN, diff --git a/include/uapi/linux/falloc.h b/include/uapi/linux/falloc.h index 5810371ed72b..1f9ca757d02d 100644 --- a/include/uapi/linux/falloc.h +++ b/include/uapi/linux/falloc.h @@ -78,4 +78,21 @@ */ #define FALLOC_FL_UNSHARE_RANGE 0x40 +/* + * FALLOC_FL_WRITE_ZEROES zeroes a specified file range in such a way that + * subsequent writes to that range do not require further changes to the file + * mapping metadata. This flag is beneficial for subsequent pure overwriting + * within this range, as it can save on block allocation and, consequently, + * significant metadata changes. Therefore, filesystems that always require + * out-of-place writes should not support this flag. + * + * Different filesystems may implement different limitations on the + * granularity of the zeroing operation. Most will preferably be accelerated + * by submitting write zeroes command if the backing storage supports, which + * may not physically write zeros to the media. + * + * This flag cannot be specified in conjunction with the FALLOC_FL_KEEP_SIZE. + */ +#define FALLOC_FL_WRITE_ZEROES 0x80 + #endif /* _UAPI_FALLOC_H_ */ diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index a15ac2fa4b20..f291ab4f94eb 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -90,10 +90,28 @@ #define DN_ATTRIB 0x00000020 /* File changed attibutes */ #define DN_MULTISHOT 0x80000000 /* Don't remove notifier */ +/* Reserved kernel ranges [-100], [-10000, -40000]. */ #define AT_FDCWD -100 /* Special value for dirfd used to indicate openat should use the current working directory. */ +/* + * The concept of process and threads in userland and the kernel is a confusing + * one - within the kernel every thread is a 'task' with its own individual PID, + * however from userland's point of view threads are grouped by a single PID, + * which is that of the 'thread group leader', typically the first thread + * spawned. + * + * To cut the Gideon knot, for internal kernel usage, we refer to + * PIDFD_SELF_THREAD to refer to the current thread (or task from a kernel + * perspective), and PIDFD_SELF_THREAD_GROUP to refer to the current thread + * group leader... + */ +#define PIDFD_SELF_THREAD -10000 /* Current thread. */ +#define PIDFD_SELF_THREAD_GROUP -10001 /* Current thread group leader. */ + +#define FD_PIDFS_ROOT -10002 /* Root of the pidfs filesystem */ +#define FD_INVALID -10009 /* Invalid file descriptor: -10000 - EBADF = -10009 */ /* Generic flags for the *at(2) family of syscalls. */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 0098b0ce8ccb..0bd678a4a10e 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -60,6 +60,17 @@ #define RENAME_EXCHANGE (1 << 1) /* Exchange source and dest */ #define RENAME_WHITEOUT (1 << 2) /* Whiteout source */ +/* + * The root inode of procfs is guaranteed to always have the same inode number. + * For programs that make heavy use of procfs, verifying that the root is a + * real procfs root and using openat2(RESOLVE_{NO_{XDEV,MAGICLINKS},BENEATH}) + * will allow you to make sure you are never tricked into operating on the + * wrong procfs file. + */ +enum procfs_ino { + PROCFS_ROOT_INO = 1, +}; + struct file_clone_range { __s64 src_fd; __u64 src_offset; @@ -91,6 +102,63 @@ struct fs_sysfs_path { __u8 name[128]; }; +/* Protection info capability flags */ +#define LBMD_PI_CAP_INTEGRITY (1 << 0) +#define LBMD_PI_CAP_REFTAG (1 << 1) + +/* Checksum types for Protection Information */ +#define LBMD_PI_CSUM_NONE 0 +#define LBMD_PI_CSUM_IP 1 +#define LBMD_PI_CSUM_CRC16_T10DIF 2 +#define LBMD_PI_CSUM_CRC64_NVME 4 + +/* sizeof first published struct */ +#define LBMD_SIZE_VER0 16 + +/* + * Logical block metadata capability descriptor + * If the device does not support metadata, all the fields will be zero. + * Applications must check lbmd_flags to determine whether metadata is + * supported or not. + */ +struct logical_block_metadata_cap { + /* Bitmask of logical block metadata capability flags */ + __u32 lbmd_flags; + /* + * The amount of data described by each unit of logical block + * metadata + */ + __u16 lbmd_interval; + /* + * Size in bytes of the logical block metadata associated with each + * interval + */ + __u8 lbmd_size; + /* + * Size in bytes of the opaque block tag associated with each + * interval + */ + __u8 lbmd_opaque_size; + /* + * Offset in bytes of the opaque block tag within the logical block + * metadata + */ + __u8 lbmd_opaque_offset; + /* Size in bytes of the T10 PI tuple associated with each interval */ + __u8 lbmd_pi_size; + /* Offset in bytes of T10 PI tuple within the logical block metadata */ + __u8 lbmd_pi_offset; + /* T10 PI guard tag type */ + __u8 lbmd_guard_tag_type; + /* Size in bytes of the T10 PI application tag */ + __u8 lbmd_app_tag_size; + /* Size in bytes of the T10 PI reference tag */ + __u8 lbmd_ref_tag_size; + /* Size in bytes of the T10 PI storage tag */ + __u8 lbmd_storage_tag_size; + __u8 pad; +}; + /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */ #define FILE_DEDUPE_RANGE_SAME 0 #define FILE_DEDUPE_RANGE_DIFFERS 1 @@ -149,6 +217,24 @@ struct fsxattr { }; /* + * Variable size structure for file_[sg]et_attr(). + * + * Note. This is alternative to the structure 'struct file_kattr'/'struct fsxattr'. + * As this structure is passed to/from userspace with its size, this can + * be versioned based on the size. + */ +struct file_attr { + __u64 fa_xflags; /* xflags field value (get/set) */ + __u32 fa_extsize; /* extsize field value (get/set)*/ + __u32 fa_nextents; /* nextents field value (get) */ + __u32 fa_projid; /* project identifier (get/set) */ + __u32 fa_cowextsize; /* CoW extsize field value (get/set) */ +}; + +#define FILE_ATTR_SIZE_VER0 24 +#define FILE_ATTR_SIZE_LATEST FILE_ATTR_SIZE_VER0 + +/* * Flags for the fsx_xflags field */ #define FS_XFLAG_REALTIME 0x00000001 /* data in realtime volume */ @@ -247,6 +333,8 @@ struct fsxattr { * also /sys/kernel/debug/ for filesystems with debugfs exports */ #define FS_IOC_GETFSSYSFSPATH _IOR(0x15, 1, struct fs_sysfs_path) +/* Get logical block metadata capability details */ +#define FS_IOC_GETLBMD_CAP _IOWR(0x15, 2, struct logical_block_metadata_cap) /* * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d00b85cb168c..7a4c35ff03fe 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -178,6 +178,7 @@ struct kvm_xen_exit { #define KVM_EXIT_NOTIFY 37 #define KVM_EXIT_LOONGARCH_IOCSR 38 #define KVM_EXIT_MEMORY_FAULT 39 +#define KVM_EXIT_TDX 40 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -447,6 +448,31 @@ struct kvm_run { __u64 gpa; __u64 size; } memory_fault; + /* KVM_EXIT_TDX */ + struct { + __u64 flags; + __u64 nr; + union { + struct { + __u64 ret; + __u64 data[5]; + } unknown; + struct { + __u64 ret; + __u64 gpa; + __u64 size; + } get_quote; + struct { + __u64 ret; + __u64 leaf; + __u64 r11, r12, r13, r14; + } get_tdvmcall_info; + struct { + __u64 ret; + __u64 vector; + } setup_event_notify; + }; + } tdx; /* Fix the size of the union. */ char padding[256]; }; diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h index 84fa8a21dfd0..6ac84b2f636c 100644 --- a/include/uapi/linux/mptcp_pm.h +++ b/include/uapi/linux/mptcp_pm.h @@ -27,14 +27,14 @@ * token, rem_id. * @MPTCP_EVENT_SUB_ESTABLISHED: A new subflow has been established. 'error' * should not be set. Attributes: token, family, loc_id, rem_id, saddr4 | - * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error]. + * saddr6, daddr4 | daddr6, sport, dport, backup, if-idx [, error]. * @MPTCP_EVENT_SUB_CLOSED: A subflow has been closed. An error (copy of * sk_err) could be set if an error has been detected for this subflow. * Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | - * daddr6, sport, dport, backup, if_idx [, error]. + * daddr6, sport, dport, backup, if-idx [, error]. * @MPTCP_EVENT_SUB_PRIORITY: The priority of a subflow has changed. 'error' * should not be set. Attributes: token, family, loc_id, rem_id, saddr4 | - * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error]. + * saddr6, daddr4 | daddr6, sport, dport, backup, if-idx [, error]. * @MPTCP_EVENT_LISTENER_CREATED: A new PM listener is created. Attributes: * family, sport, saddr4 | saddr6. * @MPTCP_EVENT_LISTENER_CLOSED: A PM listener is closed. Attributes: family, diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 518ba144544c..2beb30be2c5f 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -142,8 +142,6 @@ enum nf_tables_msg_types { NFT_MSG_DESTROYOBJ, NFT_MSG_DESTROYFLOWTABLE, NFT_MSG_GETSETELEM_RESET, - NFT_MSG_NEWDEV, - NFT_MSG_DELDEV, NFT_MSG_MAX, }; @@ -1786,18 +1784,10 @@ enum nft_synproxy_attributes { * enum nft_device_attributes - nf_tables device netlink attributes * * @NFTA_DEVICE_NAME: name of this device (NLA_STRING) - * @NFTA_DEVICE_TABLE: table containing the flowtable or chain hooking into the device (NLA_STRING) - * @NFTA_DEVICE_FLOWTABLE: flowtable hooking into the device (NLA_STRING) - * @NFTA_DEVICE_CHAIN: chain hooking into the device (NLA_STRING) - * @NFTA_DEVICE_SPEC: hook spec matching the device (NLA_STRING) */ enum nft_devices_attributes { NFTA_DEVICE_UNSPEC, NFTA_DEVICE_NAME, - NFTA_DEVICE_TABLE, - NFTA_DEVICE_FLOWTABLE, - NFTA_DEVICE_CHAIN, - NFTA_DEVICE_SPEC, __NFTA_DEVICE_MAX }; #define NFTA_DEVICE_MAX (__NFTA_DEVICE_MAX - 1) diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h index 50d807af2649..6cd58cd2a6f0 100644 --- a/include/uapi/linux/netfilter/nfnetlink.h +++ b/include/uapi/linux/netfilter/nfnetlink.h @@ -25,8 +25,6 @@ enum nfnetlink_groups { #define NFNLGRP_ACCT_QUOTA NFNLGRP_ACCT_QUOTA NFNLGRP_NFTRACE, #define NFNLGRP_NFTRACE NFNLGRP_NFTRACE - NFNLGRP_NFT_DEV, -#define NFNLGRP_NFT_DEV NFNLGRP_NFT_DEV __NFNLGRP_MAX, }; #define NFNLGRP_MAX (__NFNLGRP_MAX - 1) diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index 34127653fd00..97d8d80d139f 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -42,4 +42,15 @@ struct mnt_ns_info { /* Get previous namespace. */ #define NS_MNT_GET_PREV _IOR(NSIO, 12, struct mnt_ns_info) +enum init_ns_ino { + IPC_NS_INIT_INO = 0xEFFFFFFFU, + UTS_NS_INIT_INO = 0xEFFFFFFEU, + USER_NS_INIT_INO = 0xEFFFFFFDU, + PID_NS_INIT_INO = 0xEFFFFFFCU, + CGROUP_NS_INIT_INO = 0xEFFFFFFBU, + TIME_NS_INIT_INO = 0xEFFFFFFAU, + NET_NS_INIT_INO = 0xEFFFFFF9U, + MNT_NS_INIT_INO = 0xEFFFFFF8U, +}; + #endif /* __LINUX_NSFS_H */ diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index c27a4e238e4b..957db425d459 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -43,21 +43,6 @@ #define PIDFD_COREDUMP_ROOT (1U << 3) /* coredump was done as root. */ /* - * The concept of process and threads in userland and the kernel is a confusing - * one - within the kernel every thread is a 'task' with its own individual PID, - * however from userland's point of view threads are grouped by a single PID, - * which is that of the 'thread group leader', typically the first thread - * spawned. - * - * To cut the Gideon knot, for internal kernel usage, we refer to - * PIDFD_SELF_THREAD to refer to the current thread (or task from a kernel - * perspective), and PIDFD_SELF_THREAD_GROUP to refer to the current thread - * group leader... - */ -#define PIDFD_SELF_THREAD -10000 /* Current thread. */ -#define PIDFD_SELF_THREAD_GROUP -20000 /* Current thread group leader. */ - -/* * ...and for userland we make life simpler - PIDFD_SELF refers to the current * thread, PIDFD_SELF_PROCESS refers to the process thread group leader. * diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 77d9d6af46da..c9751bdfd937 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -135,8 +135,28 @@ #define UBLKSRV_IO_BUF_TOTAL_SIZE (1ULL << UBLKSRV_IO_BUF_TOTAL_BITS) /* - * zero copy requires 4k block size, and can remap ublk driver's io - * request into ublksrv's vm space + * ublk server can register data buffers for incoming I/O requests with a sparse + * io_uring buffer table. The request buffer can then be used as the data buffer + * for io_uring operations via the fixed buffer index. + * Note that the ublk server can never directly access the request data memory. + * + * To use this feature, the ublk server must first register a sparse buffer + * table on an io_uring instance. + * When an incoming ublk request is received, the ublk server submits a + * UBLK_U_IO_REGISTER_IO_BUF command to that io_uring instance. The + * ublksrv_io_cmd's q_id and tag specify the request whose buffer to register + * and addr is the index in the io_uring's buffer table to install the buffer. + * SQEs can now be submitted to the io_uring to read/write the request's buffer + * by enabling fixed buffers (e.g. using IORING_OP_{READ,WRITE}_FIXED or + * IORING_URING_CMD_FIXED) and passing the registered buffer index in buf_index. + * Once the last io_uring operation using the request's buffer has completed, + * the ublk server submits a UBLK_U_IO_UNREGISTER_IO_BUF command with q_id, tag, + * and addr again specifying the request buffer to unregister. + * The ublk request is completed when its buffer is unregistered from all + * io_uring instances and the ublk server issues UBLK_U_IO_COMMIT_AND_FETCH_REQ. + * + * Not available for UBLK_F_UNPRIVILEGED_DEV, as a ublk server can leak + * uninitialized kernel memory by not reading into the full request buffer. */ #define UBLK_F_SUPPORT_ZERO_COPY (1ULL << 0) @@ -450,10 +470,10 @@ static inline struct ublk_auto_buf_reg ublk_sqe_addr_to_auto_buf_reg( __u64 sqe_addr) { struct ublk_auto_buf_reg reg = { - .index = sqe_addr & 0xffff, - .flags = (sqe_addr >> 16) & 0xff, - .reserved0 = (sqe_addr >> 24) & 0xff, - .reserved1 = sqe_addr >> 32, + .index = (__u16)sqe_addr, + .flags = (__u8)(sqe_addr >> 16), + .reserved0 = (__u8)(sqe_addr >> 24), + .reserved1 = (__u32)(sqe_addr >> 32), }; return reg; diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h index ed07181d4eff..e05280e41522 100644 --- a/include/uapi/linux/vm_sockets.h +++ b/include/uapi/linux/vm_sockets.h @@ -17,6 +17,10 @@ #ifndef _UAPI_VM_SOCKETS_H #define _UAPI_VM_SOCKETS_H +#ifndef __KERNEL__ +#include <sys/socket.h> /* for struct sockaddr and sa_family_t */ +#endif + #include <linux/socket.h> #include <linux/types.h> |