diff options
Diffstat (limited to 'fs/xfs/xfs_inode_item.c')
| -rw-r--r-- | fs/xfs/xfs_inode_item.c | 862 |
1 files changed, 306 insertions, 556 deletions
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index fd4f398bd6f..a640137b357 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -17,21 +17,20 @@ */ #include "xfs.h" #include "xfs_fs.h" -#include "xfs_types.h" -#include "xfs_bit.h" -#include "xfs_log.h" -#include "xfs_inum.h" -#include "xfs_trans.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" #include "xfs_sb.h" #include "xfs_ag.h" #include "xfs_mount.h" -#include "xfs_trans_priv.h" -#include "xfs_bmap_btree.h" -#include "xfs_dinode.h" #include "xfs_inode.h" +#include "xfs_trans.h" #include "xfs_inode_item.h" #include "xfs_error.h" #include "xfs_trace.h" +#include "xfs_trans_priv.h" +#include "xfs_dinode.h" +#include "xfs_log.h" kmem_zone_t *xfs_ili_zone; /* inode log item zone */ @@ -41,477 +40,335 @@ static inline struct xfs_inode_log_item *INODE_ITEM(struct xfs_log_item *lip) return container_of(lip, struct xfs_inode_log_item, ili_item); } - -/* - * This returns the number of iovecs needed to log the given inode item. - * - * We need one iovec for the inode log format structure, one for the - * inode core, and possibly one for the inode data/extents/b-tree root - * and one for the inode attribute data/extents/b-tree root. - */ -STATIC uint -xfs_inode_item_size( - struct xfs_log_item *lip) +STATIC void +xfs_inode_item_data_fork_size( + struct xfs_inode_log_item *iip, + int *nvecs, + int *nbytes) { - struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - uint nvecs = 2; - - /* - * Only log the data/extents/b-tree root if there is something - * left to log. - */ - iip->ili_format.ilf_fields |= XFS_ILOG_CORE; switch (ip->i_d.di_format) { case XFS_DINODE_FMT_EXTENTS: - iip->ili_format.ilf_fields &= - ~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT | - XFS_ILOG_DEV | XFS_ILOG_UUID); - if ((iip->ili_format.ilf_fields & XFS_ILOG_DEXT) && - (ip->i_d.di_nextents > 0) && - (ip->i_df.if_bytes > 0)) { - ASSERT(ip->i_df.if_u1.if_extents != NULL); - nvecs++; - } else { - iip->ili_format.ilf_fields &= ~XFS_ILOG_DEXT; + if ((iip->ili_fields & XFS_ILOG_DEXT) && + ip->i_d.di_nextents > 0 && + ip->i_df.if_bytes > 0) { + /* worst case, doesn't subtract delalloc extents */ + *nbytes += XFS_IFORK_DSIZE(ip); + *nvecs += 1; } break; - case XFS_DINODE_FMT_BTREE: - ASSERT(ip->i_df.if_ext_max == - XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t)); - iip->ili_format.ilf_fields &= - ~(XFS_ILOG_DDATA | XFS_ILOG_DEXT | - XFS_ILOG_DEV | XFS_ILOG_UUID); - if ((iip->ili_format.ilf_fields & XFS_ILOG_DBROOT) && - (ip->i_df.if_broot_bytes > 0)) { - ASSERT(ip->i_df.if_broot != NULL); - nvecs++; - } else { - ASSERT(!(iip->ili_format.ilf_fields & - XFS_ILOG_DBROOT)); -#ifdef XFS_TRANS_DEBUG - if (iip->ili_root_size > 0) { - ASSERT(iip->ili_root_size == - ip->i_df.if_broot_bytes); - ASSERT(memcmp(iip->ili_orig_root, - ip->i_df.if_broot, - iip->ili_root_size) == 0); - } else { - ASSERT(ip->i_df.if_broot_bytes == 0); - } -#endif - iip->ili_format.ilf_fields &= ~XFS_ILOG_DBROOT; + if ((iip->ili_fields & XFS_ILOG_DBROOT) && + ip->i_df.if_broot_bytes > 0) { + *nbytes += ip->i_df.if_broot_bytes; + *nvecs += 1; } break; - case XFS_DINODE_FMT_LOCAL: - iip->ili_format.ilf_fields &= - ~(XFS_ILOG_DEXT | XFS_ILOG_DBROOT | - XFS_ILOG_DEV | XFS_ILOG_UUID); - if ((iip->ili_format.ilf_fields & XFS_ILOG_DDATA) && - (ip->i_df.if_bytes > 0)) { - ASSERT(ip->i_df.if_u1.if_data != NULL); - ASSERT(ip->i_d.di_size > 0); - nvecs++; - } else { - iip->ili_format.ilf_fields &= ~XFS_ILOG_DDATA; + if ((iip->ili_fields & XFS_ILOG_DDATA) && + ip->i_df.if_bytes > 0) { + *nbytes += roundup(ip->i_df.if_bytes, 4); + *nvecs += 1; } break; case XFS_DINODE_FMT_DEV: - iip->ili_format.ilf_fields &= - ~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT | - XFS_ILOG_DEXT | XFS_ILOG_UUID); - break; - case XFS_DINODE_FMT_UUID: - iip->ili_format.ilf_fields &= - ~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT | - XFS_ILOG_DEXT | XFS_ILOG_DEV); break; - default: ASSERT(0); break; } +} - /* - * If there are no attributes associated with this file, - * then there cannot be anything more to log. - * Clear all attribute-related log flags. - */ - if (!XFS_IFORK_Q(ip)) { - iip->ili_format.ilf_fields &= - ~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT | XFS_ILOG_AEXT); - return nvecs; - } +STATIC void +xfs_inode_item_attr_fork_size( + struct xfs_inode_log_item *iip, + int *nvecs, + int *nbytes) +{ + struct xfs_inode *ip = iip->ili_inode; - /* - * Log any necessary attribute data. - */ switch (ip->i_d.di_aformat) { case XFS_DINODE_FMT_EXTENTS: - iip->ili_format.ilf_fields &= - ~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT); - if ((iip->ili_format.ilf_fields & XFS_ILOG_AEXT) && - (ip->i_d.di_anextents > 0) && - (ip->i_afp->if_bytes > 0)) { - ASSERT(ip->i_afp->if_u1.if_extents != NULL); - nvecs++; - } else { - iip->ili_format.ilf_fields &= ~XFS_ILOG_AEXT; + if ((iip->ili_fields & XFS_ILOG_AEXT) && + ip->i_d.di_anextents > 0 && + ip->i_afp->if_bytes > 0) { + /* worst case, doesn't subtract unused space */ + *nbytes += XFS_IFORK_ASIZE(ip); + *nvecs += 1; } break; - case XFS_DINODE_FMT_BTREE: - iip->ili_format.ilf_fields &= - ~(XFS_ILOG_ADATA | XFS_ILOG_AEXT); - if ((iip->ili_format.ilf_fields & XFS_ILOG_ABROOT) && - (ip->i_afp->if_broot_bytes > 0)) { - ASSERT(ip->i_afp->if_broot != NULL); - nvecs++; - } else { - iip->ili_format.ilf_fields &= ~XFS_ILOG_ABROOT; + if ((iip->ili_fields & XFS_ILOG_ABROOT) && + ip->i_afp->if_broot_bytes > 0) { + *nbytes += ip->i_afp->if_broot_bytes; + *nvecs += 1; } break; - case XFS_DINODE_FMT_LOCAL: - iip->ili_format.ilf_fields &= - ~(XFS_ILOG_AEXT | XFS_ILOG_ABROOT); - if ((iip->ili_format.ilf_fields & XFS_ILOG_ADATA) && - (ip->i_afp->if_bytes > 0)) { - ASSERT(ip->i_afp->if_u1.if_data != NULL); - nvecs++; - } else { - iip->ili_format.ilf_fields &= ~XFS_ILOG_ADATA; + if ((iip->ili_fields & XFS_ILOG_ADATA) && + ip->i_afp->if_bytes > 0) { + *nbytes += roundup(ip->i_afp->if_bytes, 4); + *nvecs += 1; } break; - default: ASSERT(0); break; } - - return nvecs; } /* - * This is called to fill in the vector of log iovecs for the - * given inode log item. It fills the first item with an inode - * log format structure, the second with the on-disk inode structure, - * and a possible third and/or fourth with the inode data/extents/b-tree - * root and inode attributes data/extents/b-tree root. + * This returns the number of iovecs needed to log the given inode item. + * + * We need one iovec for the inode log format structure, one for the + * inode core, and possibly one for the inode data/extents/b-tree root + * and one for the inode attribute data/extents/b-tree root. */ STATIC void -xfs_inode_item_format( +xfs_inode_item_size( struct xfs_log_item *lip, - struct xfs_log_iovec *vecp) + int *nvecs, + int *nbytes) { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - uint nvecs; - size_t data_bytes; - xfs_bmbt_rec_t *ext_buffer; - xfs_mount_t *mp; - vecp->i_addr = &iip->ili_format; - vecp->i_len = sizeof(xfs_inode_log_format_t); - vecp->i_type = XLOG_REG_TYPE_IFORMAT; - vecp++; - nvecs = 1; + *nvecs += 2; + *nbytes += sizeof(struct xfs_inode_log_format) + + xfs_icdinode_size(ip->i_d.di_version); - /* - * Clear i_update_core if the timestamps (or any other - * non-transactional modification) need flushing/logging - * and we're about to log them with the rest of the core. - * - * This is the same logic as xfs_iflush() but this code can't - * run at the same time as xfs_iflush because we're in commit - * processing here and so we have the inode lock held in - * exclusive mode. Although it doesn't really matter - * for the timestamps if both routines were to grab the - * timestamps or not. That would be ok. - * - * We clear i_update_core before copying out the data. - * This is for coordination with our timestamp updates - * that don't hold the inode lock. They will always - * update the timestamps BEFORE setting i_update_core, - * so if we clear i_update_core after they set it we - * are guaranteed to see their updates to the timestamps - * either here. Likewise, if they set it after we clear it - * here, we'll see it either on the next commit of this - * inode or the next time the inode gets flushed via - * xfs_iflush(). This depends on strongly ordered memory - * semantics, but we have that. We use the SYNCHRONIZE - * macro to make sure that the compiler does not reorder - * the i_update_core access below the data copy below. - */ - if (ip->i_update_core) { - ip->i_update_core = 0; - SYNCHRONIZE(); - } - - /* - * Make sure to get the latest timestamps from the Linux inode. - */ - xfs_synchronize_times(ip); - - vecp->i_addr = &ip->i_d; - vecp->i_len = sizeof(struct xfs_icdinode); - vecp->i_type = XLOG_REG_TYPE_ICORE; - vecp++; - nvecs++; - iip->ili_format.ilf_fields |= XFS_ILOG_CORE; + xfs_inode_item_data_fork_size(iip, nvecs, nbytes); + if (XFS_IFORK_Q(ip)) + xfs_inode_item_attr_fork_size(iip, nvecs, nbytes); +} - /* - * If this is really an old format inode, then we need to - * log it as such. This means that we have to copy the link - * count from the new field to the old. We don't have to worry - * about the new fields, because nothing trusts them as long as - * the old inode version number is there. If the superblock already - * has a new version number, then we don't bother converting back. - */ - mp = ip->i_mount; - ASSERT(ip->i_d.di_version == 1 || xfs_sb_version_hasnlink(&mp->m_sb)); - if (ip->i_d.di_version == 1) { - if (!xfs_sb_version_hasnlink(&mp->m_sb)) { - /* - * Convert it back. - */ - ASSERT(ip->i_d.di_nlink <= XFS_MAXLINK_1); - ip->i_d.di_onlink = ip->i_d.di_nlink; - } else { - /* - * The superblock version has already been bumped, - * so just make the conversion to the new inode - * format permanent. - */ - ip->i_d.di_version = 2; - ip->i_d.di_onlink = 0; - memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad)); - } - } +STATIC void +xfs_inode_item_format_data_fork( + struct xfs_inode_log_item *iip, + struct xfs_inode_log_format *ilf, + struct xfs_log_vec *lv, + struct xfs_log_iovec **vecp) +{ + struct xfs_inode *ip = iip->ili_inode; + size_t data_bytes; switch (ip->i_d.di_format) { case XFS_DINODE_FMT_EXTENTS: - ASSERT(!(iip->ili_format.ilf_fields & - (XFS_ILOG_DDATA | XFS_ILOG_DBROOT | - XFS_ILOG_DEV | XFS_ILOG_UUID))); - if (iip->ili_format.ilf_fields & XFS_ILOG_DEXT) { - ASSERT(ip->i_df.if_bytes > 0); + iip->ili_fields &= + ~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT | + XFS_ILOG_DEV | XFS_ILOG_UUID); + + if ((iip->ili_fields & XFS_ILOG_DEXT) && + ip->i_d.di_nextents > 0 && + ip->i_df.if_bytes > 0) { + struct xfs_bmbt_rec *p; + ASSERT(ip->i_df.if_u1.if_extents != NULL); - ASSERT(ip->i_d.di_nextents > 0); - ASSERT(iip->ili_extents_buf == NULL); - ASSERT((ip->i_df.if_bytes / - (uint)sizeof(xfs_bmbt_rec_t)) > 0); -#ifdef XFS_NATIVE_HOST - if (ip->i_d.di_nextents == ip->i_df.if_bytes / - (uint)sizeof(xfs_bmbt_rec_t)) { - /* - * There are no delayed allocation - * extents, so just point to the - * real extents array. - */ - vecp->i_addr = ip->i_df.if_u1.if_extents; - vecp->i_len = ip->i_df.if_bytes; - vecp->i_type = XLOG_REG_TYPE_IEXT; - } else -#endif - { - /* - * There are delayed allocation extents - * in the inode, or we need to convert - * the extents to on disk format. - * Use xfs_iextents_copy() - * to copy only the real extents into - * a separate buffer. We'll free the - * buffer in the unlock routine. - */ - ext_buffer = kmem_alloc(ip->i_df.if_bytes, - KM_SLEEP); - iip->ili_extents_buf = ext_buffer; - vecp->i_addr = ext_buffer; - vecp->i_len = xfs_iextents_copy(ip, ext_buffer, - XFS_DATA_FORK); - vecp->i_type = XLOG_REG_TYPE_IEXT; - } - ASSERT(vecp->i_len <= ip->i_df.if_bytes); - iip->ili_format.ilf_dsize = vecp->i_len; - vecp++; - nvecs++; + ASSERT(ip->i_df.if_bytes / sizeof(xfs_bmbt_rec_t) > 0); + + p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IEXT); + data_bytes = xfs_iextents_copy(ip, p, XFS_DATA_FORK); + xlog_finish_iovec(lv, *vecp, data_bytes); + + ASSERT(data_bytes <= ip->i_df.if_bytes); + + ilf->ilf_dsize = data_bytes; + ilf->ilf_size++; + } else { + iip->ili_fields &= ~XFS_ILOG_DEXT; } break; - case XFS_DINODE_FMT_BTREE: - ASSERT(!(iip->ili_format.ilf_fields & - (XFS_ILOG_DDATA | XFS_ILOG_DEXT | - XFS_ILOG_DEV | XFS_ILOG_UUID))); - if (iip->ili_format.ilf_fields & XFS_ILOG_DBROOT) { - ASSERT(ip->i_df.if_broot_bytes > 0); + iip->ili_fields &= + ~(XFS_ILOG_DDATA | XFS_ILOG_DEXT | + XFS_ILOG_DEV | XFS_ILOG_UUID); + + if ((iip->ili_fields & XFS_ILOG_DBROOT) && + ip->i_df.if_broot_bytes > 0) { ASSERT(ip->i_df.if_broot != NULL); - vecp->i_addr = ip->i_df.if_broot; - vecp->i_len = ip->i_df.if_broot_bytes; - vecp->i_type = XLOG_REG_TYPE_IBROOT; - vecp++; - nvecs++; - iip->ili_format.ilf_dsize = ip->i_df.if_broot_bytes; + xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IBROOT, + ip->i_df.if_broot, + ip->i_df.if_broot_bytes); + ilf->ilf_dsize = ip->i_df.if_broot_bytes; + ilf->ilf_size++; + } else { + ASSERT(!(iip->ili_fields & + XFS_ILOG_DBROOT)); + iip->ili_fields &= ~XFS_ILOG_DBROOT; } break; - case XFS_DINODE_FMT_LOCAL: - ASSERT(!(iip->ili_format.ilf_fields & - (XFS_ILOG_DBROOT | XFS_ILOG_DEXT | - XFS_ILOG_DEV | XFS_ILOG_UUID))); - if (iip->ili_format.ilf_fields & XFS_ILOG_DDATA) { - ASSERT(ip->i_df.if_bytes > 0); - ASSERT(ip->i_df.if_u1.if_data != NULL); - ASSERT(ip->i_d.di_size > 0); - - vecp->i_addr = ip->i_df.if_u1.if_data; + iip->ili_fields &= + ~(XFS_ILOG_DEXT | XFS_ILOG_DBROOT | + XFS_ILOG_DEV | XFS_ILOG_UUID); + if ((iip->ili_fields & XFS_ILOG_DDATA) && + ip->i_df.if_bytes > 0) { /* * Round i_bytes up to a word boundary. * The underlying memory is guaranteed to * to be there by xfs_idata_realloc(). */ data_bytes = roundup(ip->i_df.if_bytes, 4); - ASSERT((ip->i_df.if_real_bytes == 0) || - (ip->i_df.if_real_bytes == data_bytes)); - vecp->i_len = (int)data_bytes; - vecp->i_type = XLOG_REG_TYPE_ILOCAL; - vecp++; - nvecs++; - iip->ili_format.ilf_dsize = (unsigned)data_bytes; + ASSERT(ip->i_df.if_real_bytes == 0 || + ip->i_df.if_real_bytes == data_bytes); + ASSERT(ip->i_df.if_u1.if_data != NULL); + ASSERT(ip->i_d.di_size > 0); + xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL, + ip->i_df.if_u1.if_data, data_bytes); + ilf->ilf_dsize = (unsigned)data_bytes; + ilf->ilf_size++; + } else { + iip->ili_fields &= ~XFS_ILOG_DDATA; } break; - case XFS_DINODE_FMT_DEV: - ASSERT(!(iip->ili_format.ilf_fields & - (XFS_ILOG_DBROOT | XFS_ILOG_DEXT | - XFS_ILOG_DDATA | XFS_ILOG_UUID))); - if (iip->ili_format.ilf_fields & XFS_ILOG_DEV) { - iip->ili_format.ilf_u.ilfu_rdev = - ip->i_df.if_u2.if_rdev; - } + iip->ili_fields &= + ~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT | + XFS_ILOG_DEXT | XFS_ILOG_UUID); + if (iip->ili_fields & XFS_ILOG_DEV) + ilf->ilf_u.ilfu_rdev = ip->i_df.if_u2.if_rdev; break; - case XFS_DINODE_FMT_UUID: - ASSERT(!(iip->ili_format.ilf_fields & - (XFS_ILOG_DBROOT | XFS_ILOG_DEXT | - XFS_ILOG_DDATA | XFS_ILOG_DEV))); - if (iip->ili_format.ilf_fields & XFS_ILOG_UUID) { - iip->ili_format.ilf_u.ilfu_uuid = - ip->i_df.if_u2.if_uuid; - } + iip->ili_fields &= + ~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT | + XFS_ILOG_DEXT | XFS_ILOG_DEV); + if (iip->ili_fields & XFS_ILOG_UUID) + ilf->ilf_u.ilfu_uuid = ip->i_df.if_u2.if_uuid; break; - default: ASSERT(0); break; } +} - /* - * If there are no attributes associated with the file, - * then we're done. - * Assert that no attribute-related log flags are set. - */ - if (!XFS_IFORK_Q(ip)) { - ASSERT(nvecs == lip->li_desc->lid_size); - iip->ili_format.ilf_size = nvecs; - ASSERT(!(iip->ili_format.ilf_fields & - (XFS_ILOG_ADATA | XFS_ILOG_ABROOT | XFS_ILOG_AEXT))); - return; - } +STATIC void +xfs_inode_item_format_attr_fork( + struct xfs_inode_log_item *iip, + struct xfs_inode_log_format *ilf, + struct xfs_log_vec *lv, + struct xfs_log_iovec **vecp) +{ + struct xfs_inode *ip = iip->ili_inode; + size_t data_bytes; switch (ip->i_d.di_aformat) { case XFS_DINODE_FMT_EXTENTS: - ASSERT(!(iip->ili_format.ilf_fields & - (XFS_ILOG_ADATA | XFS_ILOG_ABROOT))); - if (iip->ili_format.ilf_fields & XFS_ILOG_AEXT) { -#ifdef DEBUG - int nrecs = ip->i_afp->if_bytes / - (uint)sizeof(xfs_bmbt_rec_t); - ASSERT(nrecs > 0); - ASSERT(nrecs == ip->i_d.di_anextents); - ASSERT(ip->i_afp->if_bytes > 0); + iip->ili_fields &= + ~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT); + + if ((iip->ili_fields & XFS_ILOG_AEXT) && + ip->i_d.di_anextents > 0 && + ip->i_afp->if_bytes > 0) { + struct xfs_bmbt_rec *p; + + ASSERT(ip->i_afp->if_bytes / sizeof(xfs_bmbt_rec_t) == + ip->i_d.di_anextents); ASSERT(ip->i_afp->if_u1.if_extents != NULL); - ASSERT(ip->i_d.di_anextents > 0); -#endif -#ifdef XFS_NATIVE_HOST - /* - * There are not delayed allocation extents - * for attributes, so just point at the array. - */ - vecp->i_addr = ip->i_afp->if_u1.if_extents; - vecp->i_len = ip->i_afp->if_bytes; -#else - ASSERT(iip->ili_aextents_buf == NULL); - /* - * Need to endian flip before logging - */ - ext_buffer = kmem_alloc(ip->i_afp->if_bytes, - KM_SLEEP); - iip->ili_aextents_buf = ext_buffer; - vecp->i_addr = ext_buffer; - vecp->i_len = xfs_iextents_copy(ip, ext_buffer, - XFS_ATTR_FORK); -#endif - vecp->i_type = XLOG_REG_TYPE_IATTR_EXT; - iip->ili_format.ilf_asize = vecp->i_len; - vecp++; - nvecs++; + + p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_EXT); + data_bytes = xfs_iextents_copy(ip, p, XFS_ATTR_FORK); + xlog_finish_iovec(lv, *vecp, data_bytes); + + ilf->ilf_asize = data_bytes; + ilf->ilf_size++; + } else { + iip->ili_fields &= ~XFS_ILOG_AEXT; } break; - case XFS_DINODE_FMT_BTREE: - ASSERT(!(iip->ili_format.ilf_fields & - (XFS_ILOG_ADATA | XFS_ILOG_AEXT))); - if (iip->ili_format.ilf_fields & XFS_ILOG_ABROOT) { - ASSERT(ip->i_afp->if_broot_bytes > 0); + iip->ili_fields &= + ~(XFS_ILOG_ADATA | XFS_ILOG_AEXT); + + if ((iip->ili_fields & XFS_ILOG_ABROOT) && + ip->i_afp->if_broot_bytes > 0) { ASSERT(ip->i_afp->if_broot != NULL); - vecp->i_addr = ip->i_afp->if_broot; - vecp->i_len = ip->i_afp->if_broot_bytes; - vecp->i_type = XLOG_REG_TYPE_IATTR_BROOT; - vecp++; - nvecs++; - iip->ili_format.ilf_asize = ip->i_afp->if_broot_bytes; + + xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_BROOT, + ip->i_afp->if_broot, + ip->i_afp->if_broot_bytes); + ilf->ilf_asize = ip->i_afp->if_broot_bytes; + ilf->ilf_size++; + } else { + iip->ili_fields &= ~XFS_ILOG_ABROOT; } break; - case XFS_DINODE_FMT_LOCAL: - ASSERT(!(iip->ili_format.ilf_fields & - (XFS_ILOG_ABROOT | XFS_ILOG_AEXT))); - if (iip->ili_format.ilf_fields & XFS_ILOG_ADATA) { - ASSERT(ip->i_afp->if_bytes > 0); - ASSERT(ip->i_afp->if_u1.if_data != NULL); + iip->ili_fields &= + ~(XFS_ILOG_AEXT | XFS_ILOG_ABROOT); - vecp->i_addr = ip->i_afp->if_u1.if_data; + if ((iip->ili_fields & XFS_ILOG_ADATA) && + ip->i_afp->if_bytes > 0) { /* * Round i_bytes up to a word boundary. * The underlying memory is guaranteed to * to be there by xfs_idata_realloc(). */ data_bytes = roundup(ip->i_afp->if_bytes, 4); - ASSERT((ip->i_afp->if_real_bytes == 0) || - (ip->i_afp->if_real_bytes == data_bytes)); - vecp->i_len = (int)data_bytes; - vecp->i_type = XLOG_REG_TYPE_IATTR_LOCAL; - vecp++; - nvecs++; - iip->ili_format.ilf_asize = (unsigned)data_bytes; + ASSERT(ip->i_afp->if_real_bytes == 0 || + ip->i_afp->if_real_bytes == data_bytes); + ASSERT(ip->i_afp->if_u1.if_data != NULL); + xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL, + ip->i_afp->if_u1.if_data, + data_bytes); + ilf->ilf_asize = (unsigned)data_bytes; + ilf->ilf_size++; + } else { + iip->ili_fields &= ~XFS_ILOG_ADATA; } break; - default: ASSERT(0); break; } - - ASSERT(nvecs == lip->li_desc->lid_size); - iip->ili_format.ilf_size = nvecs; } +/* + * This is called to fill in the vector of log iovecs for the given inode + * log item. It fills the first item with an inode log format structure, + * the second with the on-disk inode structure, and a possible third and/or + * fourth with the inode data/extents/b-tree root and inode attributes + * data/extents/b-tree root. + */ +STATIC void +xfs_inode_item_format( + struct xfs_log_item *lip, + struct xfs_log_vec *lv) +{ + struct xfs_inode_log_item *iip = INODE_ITEM(lip); + struct xfs_inode *ip = iip->ili_inode; + struct xfs_inode_log_format *ilf; + struct xfs_log_iovec *vecp = NULL; + + ASSERT(ip->i_d.di_version > 1); + + ilf = xlog_prepare_iovec(lv, &vecp, XLOG_REG_TYPE_IFORMAT); + ilf->ilf_type = XFS_LI_INODE; + ilf->ilf_ino = ip->i_ino; + ilf->ilf_blkno = ip->i_imap.im_blkno; + ilf->ilf_len = ip->i_imap.im_len; + ilf->ilf_boffset = ip->i_imap.im_boffset; + ilf->ilf_fields = XFS_ILOG_CORE; + ilf->ilf_size = 2; /* format + core */ + xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format)); + + xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ICORE, + &ip->i_d, + xfs_icdinode_size(ip->i_d.di_version)); + + xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp); + if (XFS_IFORK_Q(ip)) { + xfs_inode_item_format_attr_fork(iip, ilf, lv, &vecp); + } else { + iip->ili_fields &= + ~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT | XFS_ILOG_AEXT); + } + + /* update the format with the exact fields we actually logged */ + ilf->ilf_fields |= (iip->ili_fields & ~XFS_ILOG_TIMESTAMP); +} /* * This is called to pin the inode associated with the inode log @@ -546,28 +403,19 @@ xfs_inode_item_unpin( trace_xfs_inode_unpin(ip, _RET_IP_); ASSERT(atomic_read(&ip->i_pincount) > 0); if (atomic_dec_and_test(&ip->i_pincount)) - wake_up(&ip->i_ipin_wait); + wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT); } -/* - * This is called to attempt to lock the inode associated with this - * inode log item, in preparation for the push routine which does the actual - * iflush. Don't sleep on the inode lock or the flush lock. - * - * If the flush lock is already held, indicating that the inode has - * been or is in the process of being flushed, then (ideally) we'd like to - * see if the inode's buffer is still incore, and if so give it a nudge. - * We delay doing so until the pushbuf routine, though, to avoid holding - * the AIL lock across a call to the blackhole which is the buffer cache. - * Also we don't want to sleep in any device strategy routines, which can happen - * if we do the subsequent bawrite in here. - */ STATIC uint -xfs_inode_item_trylock( - struct xfs_log_item *lip) +xfs_inode_item_push( + struct xfs_log_item *lip, + struct list_head *buffer_list) { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; + struct xfs_buf *bp = NULL; + uint rval = XFS_ITEM_SUCCESS; + int error; if (xfs_ipincount(ip) > 0) return XFS_ITEM_PINNED; @@ -575,34 +423,49 @@ xfs_inode_item_trylock( if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) return XFS_ITEM_LOCKED; - if (!xfs_iflock_nowait(ip)) { - /* - * inode has already been flushed to the backing buffer, - * leave it locked in shared mode, pushbuf routine will - * unlock it. - */ - return XFS_ITEM_PUSHBUF; + /* + * Re-check the pincount now that we stabilized the value by + * taking the ilock. + */ + if (xfs_ipincount(ip) > 0) { + rval = XFS_ITEM_PINNED; + goto out_unlock; } - /* Stale items should force out the iclog */ + /* + * Stale inode items should force out the iclog. + */ if (ip->i_flags & XFS_ISTALE) { - xfs_ifunlock(ip); - /* - * we hold the AIL lock - notify the unlock routine of this - * so it doesn't try to get the lock again. - */ - xfs_iunlock(ip, XFS_ILOCK_SHARED|XFS_IUNLOCK_NONOTIFY); - return XFS_ITEM_PINNED; + rval = XFS_ITEM_PINNED; + goto out_unlock; + } + + /* + * Someone else is already flushing the inode. Nothing we can do + * here but wait for the flush to finish and remove the item from + * the AIL. + */ + if (!xfs_iflock_nowait(ip)) { + rval = XFS_ITEM_FLUSHING; + goto out_unlock; } -#ifdef DEBUG - if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { - ASSERT(iip->ili_format.ilf_fields != 0); - ASSERT(iip->ili_logged == 0); - ASSERT(lip->li_flags & XFS_LI_IN_AIL); + ASSERT(iip->ili_fields != 0 || XFS_FORCED_SHUTDOWN(ip->i_mount)); + ASSERT(iip->ili_logged == 0 || XFS_FORCED_SHUTDOWN(ip->i_mount)); + + spin_unlock(&lip->li_ailp->xa_lock); + + error = xfs_iflush(ip, &bp); + if (!error) { + if (!xfs_buf_delwri_queue(bp, buffer_list)) + rval = XFS_ITEM_FLUSHING; + xfs_buf_relse(bp); } -#endif - return XFS_ITEM_SUCCESS; + + spin_lock(&lip->li_ailp->xa_lock); +out_unlock: + xfs_iunlock(ip, XFS_ILOCK_SHARED); + return rval; } /* @@ -619,41 +482,13 @@ xfs_inode_item_unlock( struct xfs_inode *ip = iip->ili_inode; unsigned short lock_flags; - ASSERT(iip->ili_inode->i_itemp != NULL); - ASSERT(xfs_isilocked(iip->ili_inode, XFS_ILOCK_EXCL)); - - /* - * Clear the transaction pointer in the inode. - */ - ip->i_transp = NULL; - - /* - * If the inode needed a separate buffer with which to log - * its extents, then free it now. - */ - if (iip->ili_extents_buf != NULL) { - ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS); - ASSERT(ip->i_d.di_nextents > 0); - ASSERT(iip->ili_format.ilf_fields & XFS_ILOG_DEXT); - ASSERT(ip->i_df.if_bytes > 0); - kmem_free(iip->ili_extents_buf); - iip->ili_extents_buf = NULL; - } - if (iip->ili_aextents_buf != NULL) { - ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS); - ASSERT(ip->i_d.di_anextents > 0); - ASSERT(iip->ili_format.ilf_fields & XFS_ILOG_AEXT); - ASSERT(ip->i_afp->if_bytes > 0); - kmem_free(iip->ili_aextents_buf); - iip->ili_aextents_buf = NULL; - } + ASSERT(ip->i_itemp != NULL); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); lock_flags = iip->ili_lock_flags; iip->ili_lock_flags = 0; - if (lock_flags) { - xfs_iunlock(iip->ili_inode, lock_flags); - IRELE(iip->ili_inode); - } + if (lock_flags) + xfs_iunlock(ip, lock_flags); } /* @@ -668,15 +503,15 @@ xfs_inode_item_unlock( * where the cluster buffer may be unpinned before the inode is inserted into * the AIL during transaction committed processing. If the buffer is unpinned * before the inode item has been committed and inserted, then it is possible - * for the buffer to be written and IO completions before the inode is inserted + * for the buffer to be written and IO completes before the inode is inserted * into the AIL. In that case, we'd be inserting a clean, stale inode into the * AIL which will never get removed. It will, however, get reclaimed which * triggers an assert in xfs_inode_free() complaining about freein an inode * still in the AIL. * - * To avoid this, return a lower LSN than the one passed in so that the - * transaction committed code will not move the inode forward in the AIL but - * will still unpin it properly. + * To avoid this, just unpin the inode directly and return a LSN of -1 so the + * transaction committed code knows that it does not need to do any further + * processing on the item. */ STATIC xfs_lsn_t xfs_inode_item_committed( @@ -686,86 +521,11 @@ xfs_inode_item_committed( struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - if (xfs_iflags_test(ip, XFS_ISTALE)) - return lsn - 1; - return lsn; -} - -/* - * This gets called by xfs_trans_push_ail(), when IOP_TRYLOCK - * failed to get the inode flush lock but did get the inode locked SHARED. - * Here we're trying to see if the inode buffer is incore, and if so whether it's - * marked delayed write. If that's the case, we'll promote it and that will - * allow the caller to write the buffer by triggering the xfsbufd to run. - */ -STATIC void -xfs_inode_item_pushbuf( - struct xfs_log_item *lip) -{ - struct xfs_inode_log_item *iip = INODE_ITEM(lip); - struct xfs_inode *ip = iip->ili_inode; - struct xfs_buf *bp; - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED)); - - /* - * If a flush is not in progress anymore, chances are that the - * inode was taken off the AIL. So, just get out. - */ - if (completion_done(&ip->i_flush) || - !(lip->li_flags & XFS_LI_IN_AIL)) { - xfs_iunlock(ip, XFS_ILOCK_SHARED); - return; + if (xfs_iflags_test(ip, XFS_ISTALE)) { + xfs_inode_item_unpin(lip, 0); + return -1; } - - bp = xfs_incore(ip->i_mount->m_ddev_targp, iip->ili_format.ilf_blkno, - iip->ili_format.ilf_len, XBF_TRYLOCK); - - xfs_iunlock(ip, XFS_ILOCK_SHARED); - if (!bp) - return; - if (XFS_BUF_ISDELAYWRITE(bp)) - xfs_buf_delwri_promote(bp); - xfs_buf_relse(bp); -} - -/* - * This is called to asynchronously write the inode associated with this - * inode log item out to disk. The inode will already have been locked by - * a successful call to xfs_inode_item_trylock(). - */ -STATIC void -xfs_inode_item_push( - struct xfs_log_item *lip) -{ - struct xfs_inode_log_item *iip = INODE_ITEM(lip); - struct xfs_inode *ip = iip->ili_inode; - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED)); - ASSERT(!completion_done(&ip->i_flush)); - - /* - * Since we were able to lock the inode's flush lock and - * we found it on the AIL, the inode must be dirty. This - * is because the inode is removed from the AIL while still - * holding the flush lock in xfs_iflush_done(). Thus, if - * we found it in the AIL and were able to obtain the flush - * lock without sleeping, then there must not have been - * anyone in the process of flushing the inode. - */ - ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || - iip->ili_format.ilf_fields != 0); - - /* - * Push the inode to it's backing buffer. This will not remove the - * inode from the AIL - a further push will be required to trigger a - * buffer push. However, this allows all the dirty inodes to be pushed - * to the buffer before it is pushed to disk. THe buffer IO completion - * will pull th einode from the AIL, mark it clean and unlock the flush - * lock. - */ - (void) xfs_iflush(ip, 0); - xfs_iunlock(ip, XFS_ILOCK_SHARED); + return lsn; } /* @@ -783,16 +543,14 @@ xfs_inode_item_committing( /* * This is the ops vector shared by all buf log items. */ -static struct xfs_item_ops xfs_inode_item_ops = { +static const struct xfs_item_ops xfs_inode_item_ops = { .iop_size = xfs_inode_item_size, .iop_format = xfs_inode_item_format, .iop_pin = xfs_inode_item_pin, .iop_unpin = xfs_inode_item_unpin, - .iop_trylock = xfs_inode_item_trylock, .iop_unlock = xfs_inode_item_unlock, .iop_committed = xfs_inode_item_committed, .iop_push = xfs_inode_item_push, - .iop_pushbuf = xfs_inode_item_pushbuf, .iop_committing = xfs_inode_item_committing }; @@ -813,11 +571,6 @@ xfs_inode_item_init( iip->ili_inode = ip; xfs_log_item_init(mp, &iip->ili_item, XFS_LI_INODE, &xfs_inode_item_ops); - iip->ili_format.ilf_type = XFS_LI_INODE; - iip->ili_format.ilf_ino = ip->i_ino; - iip->ili_format.ilf_blkno = ip->i_imap.im_blkno; - iip->ili_format.ilf_len = ip->i_imap.im_len; - iip->ili_format.ilf_boffset = ip->i_imap.im_boffset; } /* @@ -827,11 +580,6 @@ void xfs_inode_item_destroy( xfs_inode_t *ip) { -#ifdef XFS_TRANS_DEBUG - if (ip->i_itemp->ili_root_size != 0) { - kmem_free(ip->i_itemp->ili_orig_root); - } -#endif kmem_zone_free(xfs_ili_zone, ip->i_itemp); } @@ -864,7 +612,7 @@ xfs_iflush_done( * Scan the buffer IO completions for other inodes being completed and * attach them to the current inode log item. */ - blip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *); + blip = bp->b_fspriv; prev = NULL; while (blip != NULL) { if (lip->li_cb != xfs_iflush_done) { @@ -876,7 +624,7 @@ xfs_iflush_done( /* remove from list */ next = blip->li_bio_list; if (!prev) { - XFS_BUF_SET_FSPRIVATE(bp, next); + bp->b_fspriv = next; } else { prev->li_bio_list = next; } @@ -923,7 +671,8 @@ xfs_iflush_done( ASSERT(i <= need_ail); } /* xfs_trans_ail_delete_bulk() drops the AIL lock. */ - xfs_trans_ail_delete_bulk(ailp, log_items, i); + xfs_trans_ail_delete_bulk(ailp, log_items, i, + SHUTDOWN_CORRUPT_INCORE); } @@ -944,27 +693,28 @@ xfs_iflush_done( } /* - * This is the inode flushing abort routine. It is called - * from xfs_iflush when the filesystem is shutting down to clean - * up the inode state. - * It is responsible for removing the inode item - * from the AIL if it has not been re-logged, and unlocking the inode's - * flush lock. + * This is the inode flushing abort routine. It is called from xfs_iflush when + * the filesystem is shutting down to clean up the inode state. It is + * responsible for removing the inode item from the AIL if it has not been + * re-logged, and unlocking the inode's flush lock. */ void xfs_iflush_abort( - xfs_inode_t *ip) + xfs_inode_t *ip, + bool stale) { xfs_inode_log_item_t *iip = ip->i_itemp; - iip = ip->i_itemp; if (iip) { struct xfs_ail *ailp = iip->ili_item.li_ailp; if (iip->ili_item.li_flags & XFS_LI_IN_AIL) { spin_lock(&ailp->xa_lock); if (iip->ili_item.li_flags & XFS_LI_IN_AIL) { /* xfs_trans_ail_delete() drops the AIL lock. */ - xfs_trans_ail_delete(ailp, (xfs_log_item_t *)iip); + xfs_trans_ail_delete(ailp, &iip->ili_item, + stale ? + SHUTDOWN_LOG_IO_ERROR : + SHUTDOWN_CORRUPT_INCORE); } else spin_unlock(&ailp->xa_lock); } @@ -978,7 +728,7 @@ xfs_iflush_abort( * Clear the inode logging fields so no more flushes are * attempted. */ - iip->ili_format.ilf_fields = 0; + iip->ili_fields = 0; } /* * Release the inode's flush lock since we're done with it. @@ -991,7 +741,7 @@ xfs_istale_done( struct xfs_buf *bp, struct xfs_log_item *lip) { - xfs_iflush_abort(INODE_ITEM(lip)->ili_inode); + xfs_iflush_abort(INODE_ITEM(lip)->ili_inode, true); } /* |