// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. * All Rights Reserved. */ #ifndef __XFS_INODE_H__ #define __XFS_INODE_H__ #include "xfs_inode_buf.h" #include "xfs_inode_fork.h" #include "xfs_inode_util.h" /* * Kernel only inode definitions */ struct xfs_dinode; struct xfs_inode; struct xfs_buf; struct xfs_bmbt_irec; struct xfs_inode_log_item; struct xfs_mount; struct xfs_trans; struct xfs_dquot; typedef struct xfs_inode { /* Inode linking and identification information. */ struct xfs_mount *i_mount; /* fs mount struct ptr */ struct xfs_dquot *i_udquot; /* user dquot */ struct xfs_dquot *i_gdquot; /* group dquot */ struct xfs_dquot *i_pdquot; /* project dquot */ /* Inode location stuff */ xfs_ino_t i_ino; /* inode number (agno/agino)*/ struct xfs_imap i_imap; /* location for xfs_imap() */ /* Extent information. */ struct xfs_ifork *i_cowfp; /* copy on write extents */ struct xfs_ifork i_df; /* data fork */ struct xfs_ifork i_af; /* attribute fork */ /* Transaction and locking information. */ struct xfs_inode_log_item *i_itemp; /* logging information */ struct rw_semaphore i_lock; /* inode lock */ atomic_t i_pincount; /* inode pin count */ struct llist_node i_gclist; /* deferred inactivation list */ /* * Bitsets of inode metadata that have been checked and/or are sick. * Callers must hold i_flags_lock before accessing this field. */ uint16_t i_checked; uint16_t i_sick; spinlock_t i_flags_lock; /* inode i_flags lock */ /* Miscellaneous state. */ unsigned long i_flags; /* see defined flags below */ uint64_t i_delayed_blks; /* count of delay alloc blks */ xfs_fsize_t i_disk_size; /* number of bytes in file */ xfs_rfsblock_t i_nblocks; /* # of direct & btree blocks */ prid_t i_projid; /* owner's project id */ xfs_extlen_t i_extsize; /* basic/minimum extent size */ /* cowextsize is only used for v3 inodes, flushiter for v1/2 */ union { xfs_extlen_t i_cowextsize; /* basic cow extent size */ uint16_t i_flushiter; /* incremented on flush */ }; uint8_t i_forkoff; /* attr fork offset >> 3 */ uint16_t i_diflags; /* XFS_DIFLAG_... */ uint64_t i_diflags2; /* XFS_DIFLAG2_... */ struct timespec64 i_crtime; /* time created */ /* * Unlinked list pointers. These point to the next and previous inodes * in the AGI unlinked bucket list, respectively. These fields can * only be updated with the AGI locked. * * i_next_unlinked caches di_next_unlinked. */ xfs_agino_t i_next_unlinked; /* * If the inode is not on an unlinked list, this field is zero. If the * inode is the first element in an unlinked list, this field is * NULLAGINO. Otherwise, i_prev_unlinked points to the previous inode * in the unlinked list. */ xfs_agino_t i_prev_unlinked; /* VFS inode */ struct inode i_vnode; /* embedded VFS inode */ /* pending io completions */ spinlock_t i_ioend_lock; struct work_struct i_ioend_work; struct list_head i_ioend_list; } xfs_inode_t; static inline bool xfs_inode_on_unlinked_list(const struct xfs_inode *ip) { return ip->i_prev_unlinked != 0; } static inline bool xfs_inode_has_attr_fork(struct xfs_inode *ip) { return ip->i_forkoff > 0; } static inline struct xfs_ifork * xfs_ifork_ptr( struct xfs_inode *ip, int whichfork) { switch (whichfork) { case XFS_DATA_FORK: return &ip->i_df; case XFS_ATTR_FORK: if (!xfs_inode_has_attr_fork(ip)) return NULL; return &ip->i_af; case XFS_COW_FORK: return ip->i_cowfp; default: ASSERT(0); return NULL; } } static inline unsigned int xfs_inode_fork_boff(struct xfs_inode *ip) { return ip->i_forkoff << 3; } static inline unsigned int xfs_inode_data_fork_size(struct xfs_inode *ip) { if (xfs_inode_has_attr_fork(ip)) return xfs_inode_fork_boff(ip); return XFS_LITINO(ip->i_mount); } static inline unsigned int xfs_inode_attr_fork_size(struct xfs_inode *ip) { if (xfs_inode_has_attr_fork(ip)) return XFS_LITINO(ip->i_mount) - xfs_inode_fork_boff(ip); return 0; } static inline unsigned int xfs_inode_fork_size( struct xfs_inode *ip, int whichfork) { switch (whichfork) { case XFS_DATA_FORK: return xfs_inode_data_fork_size(ip); case XFS_ATTR_FORK: return xfs_inode_attr_fork_size(ip); default: return 0; } } /* Convert from vfs inode to xfs inode */ static inline struct xfs_inode *XFS_I(struct inode *inode) { return container_of(inode, struct xfs_inode, i_vnode); } /* convert from xfs inode to vfs inode */ static inline struct inode *VFS_I(struct xfs_inode *ip) { return &ip->i_vnode; } /* convert from const xfs inode to const vfs inode */ static inline const struct inode *VFS_IC(const struct xfs_inode *ip) { return &ip->i_vnode; } /* * For regular files we only update the on-disk filesize when actually * writing data back to disk. Until then only the copy in the VFS inode * is uptodate. */ static inline xfs_fsize_t XFS_ISIZE(struct xfs_inode *ip) { if (S_ISREG(VFS_I(ip)->i_mode)) return i_size_read(VFS_I(ip)); return ip->i_disk_size; } /* * If this I/O goes past the on-disk inode size update it unless it would * be past the current in-core inode size. */ static inline xfs_fsize_t xfs_new_eof(struct xfs_inode *ip, xfs_fsize_t new_size) { xfs_fsize_t i_size = i_size_read(VFS_I(ip)); if (new_size > i_size || new_size < 0) new_size = i_size; return new_size > ip->i_disk_size ? new_size : 0; } /* * i_flags helper functions */ static inline void __xfs_iflags_set(xfs_inode_t *ip, unsigned long flags) { ip->i_flags |= flags; } static inline void xfs_iflags_set(xfs_inode_t *ip, unsigned long flags) { spin_lock(&ip->i_flags_lock); __xfs_iflags_set(ip, flags); spin_unlock(&ip->i_flags_lock); } static inline void xfs_iflags_clear(xfs_inode_t *ip, unsigned long flags) { spin_lock(&ip->i_flags_lock); ip->i_flags &= ~flags; spin_unlock(&ip->i_flags_lock); } static inline int __xfs_iflags_test(xfs_inode_t *ip, unsigned long flags) { return (ip->i_flags & flags); } static inline int xfs_iflags_test(xfs_inode_t *ip, unsigned long flags) { int ret; spin_lock(&ip->i_flags_lock); ret = __xfs_iflags_test(ip, flags); spin_unlock(&ip->i_flags_lock); return ret; } static inline int xfs_iflags_test_and_clear(xfs_inode_t *ip, unsigned long flags) { int ret; spin_lock(&ip->i_flags_lock); ret = ip->i_flags & flags; if (ret) ip->i_flags &= ~flags; spin_unlock(&ip->i_flags_lock); return ret; } static inline int xfs_iflags_test_and_set(xfs_inode_t *ip, unsigned long flags) { int ret; spin_lock(&ip->i_flags_lock); ret = ip->i_flags & flags; if (!ret) ip->i_flags |= flags; spin_unlock(&ip->i_flags_lock); return ret; } static inline bool xfs_is_reflink_inode(struct xfs_inode *ip) { return ip->i_diflags2 & XFS_DIFLAG2_REFLINK; } static inline bool xfs_is_metadata_inode(const struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; return ip->i_ino == mp->m_sb.sb_rbmino || ip->i_ino == mp->m_sb.sb_rsumino || xfs_is_quota_inode(&mp->m_sb, ip->i_ino); } bool xfs_is_always_cow_inode(struct xfs_inode *ip); static inline bool xfs_is_cow_inode(struct xfs_inode *ip) { return xfs_is_reflink_inode(ip) || xfs_is_always_cow_inode(ip); } static inline bool xfs_inode_has_filedata(const struct xfs_inode *ip) { return ip->i_df.if_nextents > 0 || ip->i_delayed_blks > 0; } /* * Check if an inode has any data in the COW fork. This might be often false * even for inodes with the reflink flag when there is no pending COW operation. */ static inline bool xfs_inode_has_cow_data(struct xfs_inode *ip) { return ip->i_cowfp && ip->i_cowfp->if_bytes; } static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip) { return ip->i_diflags2 & XFS_DIFLAG2_BIGTIME; } static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip) { return ip->i_diflags2 & XFS_DIFLAG2_NREXT64; } /* * Decide if this file is a realtime file whose data allocation unit is larger * than a single filesystem block. */ static inline bool xfs_inode_has_bigrtalloc(struct xfs_inode *ip) { return XFS_IS_REALTIME_INODE(ip) && ip->i_mount->m_sb.sb_rextsize > 1; } /* * Return the buftarg used for data allocations on a given inode. */ #define xfs_inode_buftarg(ip) \ (XFS_IS_REALTIME_INODE(ip) ? \ (ip)->i_mount->m_rtdev_targp : (ip)->i_mount->m_ddev_targp) static inline bool xfs_inode_can_atomicwrite( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; struct xfs_buftarg *target = xfs_inode_buftarg(ip); if (mp->m_sb.sb_blocksize < target->bt_bdev_awu_min) return false; if (mp->m_sb.sb_blocksize > target->bt_bdev_awu_max) return false; return true; } /* * In-core inode flags. */ #define XFS_IRECLAIM (1 << 0) /* started reclaiming this inode */ #define XFS_ISTALE (1 << 1) /* inode has been staled */ #define XFS_IRECLAIMABLE (1 << 2) /* inode can be reclaimed */ #define XFS_INEW (1 << 3) /* inode has just been allocated */ #define XFS_IPRESERVE_DM_FIELDS (1 << 4) /* has legacy DMAPI fields set */ #define XFS_ITRUNCATED (1 << 5) /* truncated down so flush-on-close */ #define XFS_EOFBLOCKS_RELEASED (1 << 6) /* eofblocks were freed in ->release */ #define XFS_IFLUSHING (1 << 7) /* inode is being flushed */ #define __XFS_IPINNED_BIT 8 /* wakeup key for zero pin count */ #define XFS_IPINNED (1 << __XFS_IPINNED_BIT) #define XFS_IEOFBLOCKS (1 << 9) /* has the preallocblocks tag set */ #define XFS_NEED_INACTIVE (1 << 10) /* see XFS_INACTIVATING below */ /* * If this unlinked inode is in the middle of recovery, don't let drop_inode * truncate and free the inode. This can happen if we iget the inode during * log recovery to replay a bmap operation on the inode. */ #define XFS_IRECOVERY (1 << 11) #define XFS_ICOWBLOCKS (1 << 12)/* has the cowblocks tag set */ /* * If we need to update on-disk metadata before this IRECLAIMABLE inode can be * freed, then NEED_INACTIVE will be set. Once we start the updates, the * INACTIVATING bit will be set to keep iget away from this inode. After the * inactivation completes, both flags will be cleared and the inode is a * plain old IRECLAIMABLE inode. */ #define XFS_INACTIVATING (1 << 13) /* Quotacheck is running but inode has not been added to quota counts. */ #define XFS_IQUOTAUNCHECKED (1 << 14) /* * Remap in progress. Callers that wish to update file data while * holding a shared IOLOCK or MMAPLOCK must drop the lock and retake * the lock in exclusive mode. Relocking the file will block until * IREMAPPING is cleared. */ #define XFS_IREMAPPING (1U << 15) /* All inode state flags related to inode reclaim. */ #define XFS_ALL_IRECLAIM_FLAGS (XFS_IRECLAIMABLE | \ XFS_IRECLAIM | \ XFS_NEED_INACTIVE | \ XFS_INACTIVATING) /* * Per-lifetime flags need to be reset when re-using a reclaimable inode during * inode lookup. This prevents unintended behaviour on the new inode from * ocurring. */ #define XFS_IRECLAIM_RESET_FLAGS \ (XFS_IRECLAIMABLE | XFS_IRECLAIM | \ XFS_EOFBLOCKS_RELEASED | XFS_ITRUNCATED | XFS_NEED_INACTIVE | \ XFS_INACTIVATING | XFS_IQUOTAUNCHECKED) /* * Flags for inode locking. * Bit ranges: 1<<1 - 1<<16-1 -- iolock/ilock modes (bitfield) * 1<<16 - 1<<32-1 -- lockdep annotation (integers) */ #define XFS_IOLOCK_EXCL (1u << 0) #define XFS_IOLOCK_SHARED (1u << 1) #define XFS_ILOCK_EXCL (1u << 2) #define XFS_ILOCK_SHARED (1u << 3) #define XFS_MMAPLOCK_EXCL (1u << 4) #define XFS_MMAPLOCK_SHARED (1u << 5) #define XFS_LOCK_MASK (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED \ | XFS_ILOCK_EXCL | XFS_ILOCK_SHARED \ | XFS_MMAPLOCK_EXCL | XFS_MMAPLOCK_SHARED) #define XFS_LOCK_FLAGS \ { XFS_IOLOCK_EXCL, "IOLOCK_EXCL" }, \ { XFS_IOLOCK_SHARED, "IOLOCK_SHARED" }, \ { XFS_ILOCK_EXCL, "ILOCK_EXCL" }, \ { XFS_ILOCK_SHARED, "ILOCK_SHARED" }, \ { XFS_MMAPLOCK_EXCL, "MMAPLOCK_EXCL" }, \ { XFS_MMAPLOCK_SHARED, "MMAPLOCK_SHARED" } /* * Flags for lockdep annotations. * * XFS_LOCK_PARENT - for directory operations that require locking a * parent directory inode and a child entry inode. IOLOCK requires nesting, * MMAPLOCK does not support this class, ILOCK requires a single subclass * to differentiate parent from child. * * XFS_LOCK_RTBITMAP/XFS_LOCK_RTSUM - the realtime device bitmap and summary * inodes do not participate in the normal lock order, and thus have their * own subclasses. * * XFS_LOCK_INUMORDER - for locking several inodes at the some time * with xfs_lock_inodes(). This flag is used as the starting subclass * and each subsequent lock acquired will increment the subclass by one. * However, MAX_LOCKDEP_SUBCLASSES == 8, which means we are greatly * limited to the subclasses we can represent via nesting. We need at least * 5 inodes nest depth for the ILOCK through rename, and we also have to support * XFS_ILOCK_PARENT, which gives 6 subclasses. Then we have XFS_ILOCK_RTBITMAP * and XFS_ILOCK_RTSUM, which are another 2 unique subclasses, so that's all * 8 subclasses supported by lockdep. * * This also means we have to number the sub-classes in the lowest bits of * the mask we keep, and we have to ensure we never exceed 3 bits of lockdep * mask and we can't use bit-masking to build the subclasses. What a mess. * * Bit layout: * * Bit Lock Region * 16-19 XFS_IOLOCK_SHIFT dependencies * 20-23 XFS_MMAPLOCK_SHIFT dependencies * 24-31 XFS_ILOCK_SHIFT dependencies * * IOLOCK values * * 0-3 subclass value * 4-7 unused * * MMAPLOCK values * * 0-3 subclass value * 4-7 unused * * ILOCK values * 0-4 subclass values * 5 PARENT subclass (not nestable) * 6 RTBITMAP subclass (not nestable) * 7 RTSUM subclass (not nestable) * */ #define XFS_IOLOCK_SHIFT 16 #define XFS_IOLOCK_MAX_SUBCLASS 3 #define XFS_IOLOCK_DEP_MASK 0x000f0000u #define XFS_MMAPLOCK_SHIFT 20 #define XFS_MMAPLOCK_NUMORDER 0 #define XFS_MMAPLOCK_MAX_SUBCLASS 3 #define XFS_MMAPLOCK_DEP_MASK 0x00f00000u #define XFS_ILOCK_SHIFT 24 #define XFS_ILOCK_PARENT_VAL 5u #define XFS_ILOCK_MAX_SUBCLASS (XFS_ILOCK_PARENT_VAL - 1) #define XFS_ILOCK_RTBITMAP_VAL 6u #define XFS_ILOCK_RTSUM_VAL 7u #define XFS_ILOCK_DEP_MASK 0xff000000u #define XFS_ILOCK_PARENT (XFS_ILOCK_PARENT_VAL << XFS_ILOCK_SHIFT) #define XFS_ILOCK_RTBITMAP (XFS_ILOCK_RTBITMAP_VAL << XFS_ILOCK_SHIFT) #define XFS_ILOCK_RTSUM (XFS_ILOCK_RTSUM_VAL << XFS_ILOCK_SHIFT) #define XFS_LOCK_SUBCLASS_MASK (XFS_IOLOCK_DEP_MASK | \ XFS_MMAPLOCK_DEP_MASK | \ XFS_ILOCK_DEP_MASK) #define XFS_IOLOCK_DEP(flags) (((flags) & XFS_IOLOCK_DEP_MASK) \ >> XFS_IOLOCK_SHIFT) #define XFS_MMAPLOCK_DEP(flags) (((flags) & XFS_MMAPLOCK_DEP_MASK) \ >> XFS_MMAPLOCK_SHIFT) #define XFS_ILOCK_DEP(flags) (((flags) & XFS_ILOCK_DEP_MASK) \ >> XFS_ILOCK_SHIFT) /* * Layouts are broken in the BREAK_WRITE case to ensure that * layout-holders do not collide with local writes. Additionally, * layouts are broken in the BREAK_UNMAP case to make sure the * layout-holder has a consistent view of the file's extent map. While * BREAK_WRITE breaks can be satisfied by recalling FL_LAYOUT leases, * BREAK_UNMAP breaks additionally require waiting for busy dax-pages to * go idle. */ enum layout_break_reason { BREAK_WRITE, BREAK_UNMAP, }; /* * For multiple groups support: if S_ISGID bit is set in the parent * directory, group of new file is set to that of the parent, and * new subdirectory gets S_ISGID bit from parent. */ #define XFS_INHERIT_GID(pip) \ (xfs_has_grpid((pip)->i_mount) || (VFS_I(pip)->i_mode & S_ISGID)) int xfs_inactive(struct xfs_inode *ip); int xfs_lookup(struct xfs_inode *dp, const struct xfs_name *name, struct xfs_inode **ipp, struct xfs_name *ci_name); int xfs_create(const struct xfs_icreate_args *iargs, struct xfs_name *name, struct xfs_inode **ipp); int xfs_create_tmpfile(const struct xfs_icreate_args *iargs, struct xfs_inode **ipp); int xfs_remove(struct xfs_inode *dp, struct xfs_name *name, struct xfs_inode *ip); int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip, struct xfs_name *target_name); int xfs_rename(struct mnt_idmap *idmap, struct xfs_inode *src_dp, struct xfs_name *src_name, struct xfs_inode *src_ip, struct xfs_inode *target_dp, struct xfs_name *target_name, struct xfs_inode *target_ip, unsigned int flags); void xfs_ilock(xfs_inode_t *, uint); int xfs_ilock_nowait(xfs_inode_t *, uint); void xfs_iunlock(xfs_inode_t *, uint); void xfs_ilock_demote(xfs_inode_t *, uint); void xfs_assert_ilocked(struct xfs_inode *, uint); uint xfs_ilock_data_map_shared(struct xfs_inode *); uint xfs_ilock_attr_map_shared(struct xfs_inode *); int xfs_ifree(struct xfs_trans *, struct xfs_inode *); int xfs_itruncate_extents_flags(struct xfs_trans **, struct xfs_inode *, int, xfs_fsize_t, int); void xfs_iext_realloc(xfs_inode_t *, int, int); int xfs_log_force_inode(struct xfs_inode *ip); void xfs_iunpin_wait(xfs_inode_t *); #define xfs_ipincount(ip) ((unsigned int) atomic_read(&ip->i_pincount)) int xfs_iflush_cluster(struct xfs_buf *); void xfs_lock_two_inodes(struct xfs_inode *ip0, uint ip0_mode, struct xfs_inode *ip1, uint ip1_mode); int xfs_icreate(struct xfs_trans *tp, xfs_ino_t ino, const struct xfs_icreate_args *args, struct xfs_inode **ipp); static inline int xfs_itruncate_extents( struct xfs_trans **tpp, struct xfs_inode *ip, int whichfork, xfs_fsize_t new_size) { return xfs_itruncate_extents_flags(tpp, ip, whichfork, new_size, 0); } int xfs_break_dax_layouts(struct inode *inode, bool *retry); int xfs_break_layouts(struct inode *inode, uint *iolock, enum layout_break_reason reason); static inline void xfs_update_stable_writes(struct xfs_inode *ip) { if (bdev_stable_writes(xfs_inode_buftarg(ip)->bt_bdev)) mapping_set_stable_writes(VFS_I(ip)->i_mapping); else mapping_clear_stable_writes(VFS_I(ip)->i_mapping); } /* * When setting up a newly allocated inode, we need to call * xfs_finish_inode_setup() once the inode is fully instantiated at * the VFS level to prevent the rest of the world seeing the inode * before we've completed instantiation. Otherwise we can do it * the moment the inode lookup is complete. */ static inline void xfs_finish_inode_setup(struct xfs_inode *ip) { xfs_iflags_clear(ip, XFS_INEW); barrier(); unlock_new_inode(VFS_I(ip)); } static inline void xfs_setup_existing_inode(struct xfs_inode *ip) { xfs_setup_inode(ip); xfs_setup_iops(ip); xfs_finish_inode_setup(ip); } void xfs_irele(struct xfs_inode *ip); extern struct kmem_cache *xfs_inode_cache; /* The default CoW extent size hint. */ #define XFS_DEFAULT_COWEXTSZ_HINT 32 bool xfs_inode_needs_inactive(struct xfs_inode *ip); struct xfs_inode *xfs_iunlink_lookup(struct xfs_perag *pag, xfs_agino_t agino); int xfs_iunlink_reload_next(struct xfs_trans *tp, struct xfs_buf *agibp, xfs_agino_t prev_agino, xfs_agino_t next_agino); void xfs_end_io(struct work_struct *work); int xfs_ilock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2); void xfs_iunlock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2); void xfs_iunlock2_remapping(struct xfs_inode *ip1, struct xfs_inode *ip2); void xfs_lock_inodes(struct xfs_inode **ips, int inodes, uint lock_mode); void xfs_sort_inodes(struct xfs_inode **i_tab, unsigned int num_inodes); static inline bool xfs_inode_unlinked_incomplete( struct xfs_inode *ip) { return VFS_I(ip)->i_nlink == 0 && !xfs_inode_on_unlinked_list(ip); } int xfs_inode_reload_unlinked_bucket(struct xfs_trans *tp, struct xfs_inode *ip); int xfs_inode_reload_unlinked(struct xfs_inode *ip); bool xfs_ifork_zapped(const struct xfs_inode *ip, int whichfork); void xfs_inode_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip, xfs_filblks_t *dblocks, xfs_filblks_t *rblocks); unsigned int xfs_inode_alloc_unitsize(struct xfs_inode *ip); int xfs_icreate_dqalloc(const struct xfs_icreate_args *args, struct xfs_dquot **udqpp, struct xfs_dquot **gdqpp, struct xfs_dquot **pdqpp); #endif /* __XFS_INODE_H__ */