diff options
Diffstat (limited to 'fs')
-rw-r--r-- | fs/xfs/xfs_file.c | 379 | ||||
-rw-r--r-- | fs/xfs/xfs_ialloc.c | 2 | ||||
-rw-r--r-- | fs/xfs/xfs_mount.c | 43 | ||||
-rw-r--r-- | fs/xfs/xfs_mount.h | 5 | ||||
-rw-r--r-- | fs/xfs/xfs_super.c | 95 | ||||
-rw-r--r-- | fs/xfs/xfs_super.h | 2 | ||||
-rw-r--r-- | fs/xfs/xfs_trace.h | 1 |
7 files changed, 447 insertions, 80 deletions
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 56afcdb2377..1eaeb8be3aa 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -36,6 +36,7 @@ #include <linux/dcache.h> #include <linux/falloc.h> +#include <linux/pagevec.h> static const struct vm_operations_struct xfs_file_vm_ops; @@ -959,17 +960,232 @@ xfs_vm_page_mkwrite( return block_page_mkwrite(vma, vmf, xfs_get_blocks); } +/* + * This type is designed to indicate the type of offset we would like + * to search from page cache for either xfs_seek_data() or xfs_seek_hole(). + */ +enum { + HOLE_OFF = 0, + DATA_OFF, +}; + +/* + * Lookup the desired type of offset from the given page. + * + * On success, return true and the offset argument will point to the + * start of the region that was found. Otherwise this function will + * return false and keep the offset argument unchanged. + */ +STATIC bool +xfs_lookup_buffer_offset( + struct page *page, + loff_t *offset, + unsigned int type) +{ + loff_t lastoff = page_offset(page); + bool found = false; + struct buffer_head *bh, *head; + + bh = head = page_buffers(page); + do { + /* + * Unwritten extents that have data in the page + * cache covering them can be identified by the + * BH_Unwritten state flag. Pages with multiple + * buffers might have a mix of holes, data and + * unwritten extents - any buffer with valid + * data in it should have BH_Uptodate flag set + * on it. + */ + if (buffer_unwritten(bh) || + buffer_uptodate(bh)) { + if (type == DATA_OFF) + found = true; + } else { + if (type == HOLE_OFF) + found = true; + } + + if (found) { + *offset = lastoff; + break; + } + lastoff += bh->b_size; + } while ((bh = bh->b_this_page) != head); + + return found; +} + +/* + * This routine is called to find out and return a data or hole offset + * from the page cache for unwritten extents according to the desired + * type for xfs_seek_data() or xfs_seek_hole(). + * + * The argument offset is used to tell where we start to search from the + * page cache. Map is used to figure out the end points of the range to + * lookup pages. + * + * Return true if the desired type of offset was found, and the argument + * offset is filled with that address. Otherwise, return false and keep + * offset unchanged. + */ +STATIC bool +xfs_find_get_desired_pgoff( + struct inode *inode, + struct xfs_bmbt_irec *map, + unsigned int type, + loff_t *offset) +{ + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + struct pagevec pvec; + pgoff_t index; + pgoff_t end; + loff_t endoff; + loff_t startoff = *offset; + loff_t lastoff = startoff; + bool found = false; + + pagevec_init(&pvec, 0); + + index = startoff >> PAGE_CACHE_SHIFT; + endoff = XFS_FSB_TO_B(mp, map->br_startoff + map->br_blockcount); + end = endoff >> PAGE_CACHE_SHIFT; + do { + int want; + unsigned nr_pages; + unsigned int i; + + want = min_t(pgoff_t, end - index, PAGEVEC_SIZE); + nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, + want); + /* + * No page mapped into given range. If we are searching holes + * and if this is the first time we got into the loop, it means + * that the given offset is landed in a hole, return it. + * + * If we have already stepped through some block buffers to find + * holes but they all contains data. In this case, the last + * offset is already updated and pointed to the end of the last + * mapped page, if it does not reach the endpoint to search, + * that means there should be a hole between them. + */ + if (nr_pages == 0) { + /* Data search found nothing */ + if (type == DATA_OFF) + break; + + ASSERT(type == HOLE_OFF); + if (lastoff == startoff || lastoff < endoff) { + found = true; + *offset = lastoff; + } + break; + } + + /* + * At lease we found one page. If this is the first time we + * step into the loop, and if the first page index offset is + * greater than the given search offset, a hole was found. + */ + if (type == HOLE_OFF && lastoff == startoff && + lastoff < page_offset(pvec.pages[0])) { + found = true; + break; + } + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + loff_t b_offset; + + /* + * At this point, the page may be truncated or + * invalidated (changing page->mapping to NULL), + * or even swizzled back from swapper_space to tmpfs + * file mapping. However, page->index will not change + * because we have a reference on the page. + * + * Searching done if the page index is out of range. + * If the current offset is not reaches the end of + * the specified search range, there should be a hole + * between them. + */ + if (page->index > end) { + if (type == HOLE_OFF && lastoff < endoff) { + *offset = lastoff; + found = true; + } + goto out; + } + + lock_page(page); + /* + * Page truncated or invalidated(page->mapping == NULL). + * We can freely skip it and proceed to check the next + * page. + */ + if (unlikely(page->mapping != inode->i_mapping)) { + unlock_page(page); + continue; + } + + if (!page_has_buffers(page)) { + unlock_page(page); + continue; + } + + found = xfs_lookup_buffer_offset(page, &b_offset, type); + if (found) { + /* + * The found offset may be less than the start + * point to search if this is the first time to + * come here. + */ + *offset = max_t(loff_t, startoff, b_offset); + unlock_page(page); + goto out; + } + + /* + * We either searching data but nothing was found, or + * searching hole but found a data buffer. In either + * case, probably the next page contains the desired + * things, update the last offset to it so. + */ + lastoff = page_offset(page) + PAGE_SIZE; + unlock_page(page); + } + + /* + * The number of returned pages less than our desired, search + * done. In this case, nothing was found for searching data, + * but we found a hole behind the last offset. + */ + if (nr_pages < want) { + if (type == HOLE_OFF) { + *offset = lastoff; + found = true; + } + break; + } + + index = pvec.pages[i - 1]->index + 1; + pagevec_release(&pvec); + } while (index <= end); + +out: + pagevec_release(&pvec); + return found; +} + STATIC loff_t xfs_seek_data( struct file *file, - loff_t start, - u32 type) + loff_t start) { struct inode *inode = file->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; - struct xfs_bmbt_irec map[2]; - int nmap = 2; loff_t uninitialized_var(offset); xfs_fsize_t isize; xfs_fileoff_t fsbno; @@ -985,36 +1201,74 @@ xfs_seek_data( goto out_unlock; } - fsbno = XFS_B_TO_FSBT(mp, start); - /* * Try to read extents from the first block indicated * by fsbno to the end block of the file. */ + fsbno = XFS_B_TO_FSBT(mp, start); end = XFS_B_TO_FSB(mp, isize); + for (;;) { + struct xfs_bmbt_irec map[2]; + int nmap = 2; + unsigned int i; - error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap, - XFS_BMAPI_ENTIRE); - if (error) - goto out_unlock; + error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap, + XFS_BMAPI_ENTIRE); + if (error) + goto out_unlock; - /* - * Treat unwritten extent as data extent since it might - * contains dirty data in page cache. - */ - if (map[0].br_startblock != HOLESTARTBLOCK) { - offset = max_t(loff_t, start, - XFS_FSB_TO_B(mp, map[0].br_startoff)); - } else { + /* No extents at given offset, must be beyond EOF */ + if (nmap == 0) { + error = ENXIO; + goto out_unlock; + } + + for (i = 0; i < nmap; i++) { + offset = max_t(loff_t, start, + XFS_FSB_TO_B(mp, map[i].br_startoff)); + + /* Landed in a data extent */ + if (map[i].br_startblock == DELAYSTARTBLOCK || + (map[i].br_state == XFS_EXT_NORM && + !isnullstartblock(map[i].br_startblock))) + goto out; + + /* + * Landed in an unwritten extent, try to search data + * from page cache. + */ + if (map[i].br_state == XFS_EXT_UNWRITTEN) { + if (xfs_find_get_desired_pgoff(inode, &map[i], + DATA_OFF, &offset)) + goto out; + } + } + + /* + * map[0] is hole or its an unwritten extent but + * without data in page cache. Probably means that + * we are reading after EOF if nothing in map[1]. + */ if (nmap == 1) { error = ENXIO; goto out_unlock; } - offset = max_t(loff_t, start, - XFS_FSB_TO_B(mp, map[1].br_startoff)); + ASSERT(i > 1); + + /* + * Nothing was found, proceed to the next round of search + * if reading offset not beyond or hit EOF. + */ + fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount; + start = XFS_FSB_TO_B(mp, fsbno); + if (start >= isize) { + error = ENXIO; + goto out_unlock; + } } +out: if (offset != file->f_pos) file->f_pos = offset; @@ -1029,16 +1283,15 @@ out_unlock: STATIC loff_t xfs_seek_hole( struct file *file, - loff_t start, - u32 type) + loff_t start) { struct inode *inode = file->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; loff_t uninitialized_var(offset); - loff_t holeoff; xfs_fsize_t isize; xfs_fileoff_t fsbno; + xfs_filblks_t end; uint lock; int error; @@ -1054,21 +1307,77 @@ xfs_seek_hole( } fsbno = XFS_B_TO_FSBT(mp, start); - error = xfs_bmap_first_unused(NULL, ip, 1, &fsbno, XFS_DATA_FORK); - if (error) - goto out_unlock; + end = XFS_B_TO_FSB(mp, isize); + + for (;;) { + struct xfs_bmbt_irec map[2]; + int nmap = 2; + unsigned int i; + + error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap, + XFS_BMAPI_ENTIRE); + if (error) + goto out_unlock; + + /* No extents at given offset, must be beyond EOF */ + if (nmap == 0) { + error = ENXIO; + goto out_unlock; + } + + for (i = 0; i < nmap; i++) { + offset = max_t(loff_t, start, + XFS_FSB_TO_B(mp, map[i].br_startoff)); + + /* Landed in a hole */ + if (map[i].br_startblock == HOLESTARTBLOCK) + goto out; + + /* + * Landed in an unwritten extent, try to search hole + * from page cache. + */ + if (map[i].br_state == XFS_EXT_UNWRITTEN) { + if (xfs_find_get_desired_pgoff(inode, &map[i], + HOLE_OFF, &offset)) + goto out; + } + } + + /* + * map[0] contains data or its unwritten but contains + * data in page cache, probably means that we are + * reading after EOF. We should fix offset to point + * to the end of the file(i.e., there is an implicit + * hole at the end of any file). + */ + if (nmap == 1) { + offset = isize; + break; + } + + ASSERT(i > 1); - holeoff = XFS_FSB_TO_B(mp, fsbno); - if (holeoff <= start) - offset = start; - else { /* - * xfs_bmap_first_unused() could return a value bigger than - * isize if there are no more holes past the supplied offset. + * Both mappings contains data, proceed to the next round of + * search if the current reading offset not beyond or hit EOF. */ - offset = min_t(loff_t, holeoff, isize); + fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount; + start = XFS_FSB_TO_B(mp, fsbno); + if (start >= isize) { + offset = isize; + break; + } } +out: + /* + * At this point, we must have found a hole. However, the returned + * offset may be bigger than the file size as it may be aligned to + * page boundary for unwritten extents, we need to deal with this + * situation in particular. + */ + offset = min_t(loff_t, offset, isize); if (offset != file->f_pos) file->f_pos = offset; @@ -1092,9 +1401,9 @@ xfs_file_llseek( case SEEK_SET: return generic_file_llseek(file, offset, origin); case SEEK_DATA: - return xfs_seek_data(file, offset, origin); + return xfs_seek_data(file, offset); case SEEK_HOLE: - return xfs_seek_hole(file, offset, origin); + return xfs_seek_hole(file, offset); default: return -EINVAL; } diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c index 5aceb3f8ecd..445bf1aef31 100644 --- a/fs/xfs/xfs_ialloc.c +++ b/fs/xfs/xfs_ialloc.c @@ -431,7 +431,7 @@ xfs_ialloc_next_ag( spin_lock(&mp->m_agirotor_lock); agno = mp->m_agirotor; - if (++mp->m_agirotor == mp->m_maxagi) + if (++mp->m_agirotor >= mp->m_maxagi) mp->m_agirotor = 0; spin_unlock(&mp->m_agirotor_lock); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 29c2f83d414..b2bd3a0e637 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -440,7 +440,7 @@ xfs_initialize_perag( xfs_agnumber_t agcount, xfs_agnumber_t *maxagi) { - xfs_agnumber_t index, max_metadata; + xfs_agnumber_t index; xfs_agnumber_t first_initialised = 0; xfs_perag_t *pag; xfs_agino_t agino; @@ -500,43 +500,10 @@ xfs_initialize_perag( else mp->m_flags &= ~XFS_MOUNT_32BITINODES; - if (mp->m_flags & XFS_MOUNT_32BITINODES) { - /* - * Calculate how much should be reserved for inodes to meet - * the max inode percentage. - */ - if (mp->m_maxicount) { - __uint64_t icount; - - icount = sbp->sb_dblocks * sbp->sb_imax_pct; - do_div(icount, 100); - icount += sbp->sb_agblocks - 1; - do_div(icount, sbp->sb_agblocks); - max_metadata = icount; - } else { - max_metadata = agcount; - } - - for (index = 0; index < agcount; index++) { - ino = XFS_AGINO_TO_INO(mp, index, agino); - if (ino > XFS_MAXINUMBER_32) { - index++; - break; - } - - pag = xfs_perag_get(mp, index); - pag->pagi_inodeok = 1; - if (index < max_metadata) - pag->pagf_metadata = 1; - xfs_perag_put(pag); - } - } else { - for (index = 0; index < agcount; index++) { - pag = xfs_perag_get(mp, index); - pag->pagi_inodeok = 1; - xfs_perag_put(pag); - } - } + if (mp->m_flags & XFS_MOUNT_32BITINODES) + index = xfs_set_inode32(mp); + else + index = xfs_set_inode64(mp); if (maxagi) *maxagi = index; diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 05a05a7b611..deee09e534d 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -54,12 +54,7 @@ typedef struct xfs_trans_reservations { #include "xfs_sync.h" struct xlog; -struct xfs_mount_args; struct xfs_inode; -struct xfs_bmbt_irec; -struct xfs_bmap_free; -struct xfs_extdelta; -struct xfs_swapext; struct xfs_mru_cache; struct xfs_nameops; struct xfs_ail; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index e0fd2734189..26a09bd7f97 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -88,6 +88,8 @@ mempool_t *xfs_ioend_pool; * unwritten extent conversion */ #define MNTOPT_NOBARRIER "nobarrier" /* .. disable */ #define MNTOPT_64BITINODE "inode64" /* inodes can be allocated anywhere */ +#define MNTOPT_32BITINODE "inode32" /* inode allocation limited to + * XFS_MAXINUMBER_32 */ #define MNTOPT_IKEEP "ikeep" /* do not free empty inode clusters */ #define MNTOPT_NOIKEEP "noikeep" /* free empty inode clusters */ #define MNTOPT_LARGEIO "largeio" /* report large I/O sizes in stat() */ @@ -120,12 +122,18 @@ mempool_t *xfs_ioend_pool; * in the future, too. */ enum { - Opt_barrier, Opt_nobarrier, Opt_err + Opt_barrier, + Opt_nobarrier, + Opt_inode64, + Opt_inode32, + Opt_err }; static const match_table_t tokens = { {Opt_barrier, "barrier"}, {Opt_nobarrier, "nobarrier"}, + {Opt_inode64, "inode64"}, + {Opt_inode32, "inode32"}, {Opt_err, NULL} }; @@ -197,7 +205,9 @@ xfs_parseargs( */ mp->m_flags |= XFS_MOUNT_BARRIER; mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE; +#if !XFS_BIG_INUMS mp->m_flags |= XFS_MOUNT_SMALL_INUMS; +#endif /* * These can be overridden by the mount option parsing. @@ -294,6 +304,8 @@ xfs_parseargs( return EINVAL; } dswidth = simple_strtoul(value, &eov, 10); + } else if (!strcmp(this_char, MNTOPT_32BITINODE)) { + mp->m_flags |= XFS_MOUNT_SMALL_INUMS; } else if (!strcmp(this_char, MNTOPT_64BITINODE)) { mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS; #if !XFS_BIG_INUMS @@ -492,6 +504,7 @@ xfs_showargs( { XFS_MOUNT_FILESTREAMS, "," MNTOPT_FILESTREAM }, { XFS_MOUNT_GRPID, "," MNTOPT_GRPID }, { XFS_MOUNT_DISCARD, "," MNTOPT_DISCARD }, + { XFS_MOUNT_SMALL_INUMS, "," MNTOPT_32BITINODE }, { 0, NULL } }; static struct proc_xfs_info xfs_info_unset[] = { @@ -591,6 +604,80 @@ xfs_max_file_offset( return (((__uint64_t)pagefactor) << bitshift) - 1; } +xfs_agnumber_t +xfs_set_inode32(struct xfs_mount *mp) +{ + xfs_agnumber_t index = 0; + xfs_agnumber_t maxagi = 0; + xfs_sb_t *sbp = &mp->m_sb; + xfs_agnumber_t max_metadata; + xfs_agino_t agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks -1, 0); + xfs_ino_t ino = XFS_AGINO_TO_INO(mp, sbp->sb_agcount -1, agino); + xfs_perag_t *pag; + + /* Calculate how much should be reserved for inodes to meet + * the max inode percentage. + */ + if (mp->m_maxicount) { + __uint64_t icount; + + icount = sbp->sb_dblocks * sbp->sb_imax_pct; + do_div(icount, 100); + icount += sbp->sb_agblocks - 1; + do_div(icount, sbp->sb_agblocks); + max_metadata = icount; + } else { + max_metadata = sbp->sb_agcount; + } + + for (index = 0; index < sbp->sb_agcount; index++) { + ino = XFS_AGINO_TO_INO(mp, index, agino); + + if (ino > XFS_MAXINUMBER_32) { + pag = xfs_perag_get(mp, index); + pag->pagi_inodeok = 0; + pag->pagf_metadata = 0; + xfs_perag_put(pag); + continue; + } + + pag = xfs_perag_get(mp, index); + pag->pagi_inodeok = 1; + maxagi++; + if (index < max_metadata) + pag->pagf_metadata = 1; + xfs_perag_put(pag); + } + mp->m_flags |= (XFS_MOUNT_32BITINODES | + XFS_MOUNT_SMALL_INUMS); + + return maxagi; +} + +xfs_agnumber_t +xfs_set_inode64(struct xfs_mount *mp) +{ + xfs_agnumber_t index = 0; + + for (index = 0; index < mp->m_sb.sb_agcount; index++) { + struct xfs_perag *pag; + + pag = xfs_perag_get(mp, index); + pag->pagi_inodeok = 1; + pag->pagf_metadata = 0; + xfs_perag_put(pag); + } + + /* There is no need for lock protection on m_flags, + * the rw_semaphore of the VFS superblock is locked + * during mount/umount/remount operations, so this is + * enough to avoid concurency on the m_flags field + */ + mp->m_flags &= ~(XFS_MOUNT_32BITINODES | + XFS_MOUNT_SMALL_INUMS); + return index; +} + STATIC int xfs_blkdev_get( xfs_mount_t *mp, @@ -1056,6 +1143,12 @@ xfs_fs_remount( case Opt_nobarrier: mp->m_flags &= ~XFS_MOUNT_BARRIER; break; + case Opt_inode64: + mp->m_maxagi = xfs_set_inode64(mp); + break; + case Opt_inode32: + mp->m_maxagi = xfs_set_inode32(mp); + break; default: /* * Logically we would return an error here to prevent diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index 09b0c26b224..9de4a920ba0 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -75,6 +75,8 @@ struct block_device; extern __uint64_t xfs_max_file_offset(unsigned int); extern void xfs_blkdev_issue_flush(struct xfs_buftarg *); +extern xfs_agnumber_t xfs_set_inode32(struct xfs_mount *); +extern xfs_agnumber_t xfs_set_inode64(struct xfs_mount *); extern const struct export_operations xfs_export_operations; extern const struct xattr_handler *xfs_xattr_handlers[]; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index e5795dd6013..7d36ccf57f9 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -37,6 +37,7 @@ struct xlog_recover; struct xlog_recover_item; struct xfs_buf_log_format; struct xfs_inode_log_format; +struct xfs_bmbt_irec; DECLARE_EVENT_CLASS(xfs_attr_list_class, TP_PROTO(struct xfs_attr_list_context *ctx), |