diff options
Diffstat (limited to 'fs/xfs')
-rw-r--r-- | fs/xfs/xfs_acl.c | 4 | ||||
-rw-r--r-- | fs/xfs/xfs_buf.c | 5 | ||||
-rw-r--r-- | fs/xfs/xfs_buf.h | 41 | ||||
-rw-r--r-- | fs/xfs/xfs_dfrag.c | 34 | ||||
-rw-r--r-- | fs/xfs/xfs_discard.c | 6 | ||||
-rw-r--r-- | fs/xfs/xfs_file.c | 381 | ||||
-rw-r--r-- | fs/xfs/xfs_ialloc.c | 19 | ||||
-rw-r--r-- | fs/xfs/xfs_ioctl.c | 10 | ||||
-rw-r--r-- | fs/xfs/xfs_mount.c | 43 | ||||
-rw-r--r-- | fs/xfs/xfs_mount.h | 5 | ||||
-rw-r--r-- | fs/xfs/xfs_quotaops.c | 12 | ||||
-rw-r--r-- | fs/xfs/xfs_rtalloc.c | 2 | ||||
-rw-r--r-- | fs/xfs/xfs_super.c | 103 | ||||
-rw-r--r-- | fs/xfs/xfs_super.h | 2 | ||||
-rw-r--r-- | fs/xfs/xfs_sync.c | 2 | ||||
-rw-r--r-- | fs/xfs/xfs_trace.h | 1 | ||||
-rw-r--r-- | fs/xfs/xfs_trans_dquot.c | 8 |
17 files changed, 533 insertions, 145 deletions
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index ac702a6eab9b..1d32f1d52763 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -337,7 +337,7 @@ xfs_xattr_acl_get(struct dentry *dentry, const char *name, if (acl == NULL) return -ENODATA; - error = posix_acl_to_xattr(acl, value, size); + error = posix_acl_to_xattr(&init_user_ns, acl, value, size); posix_acl_release(acl); return error; @@ -361,7 +361,7 @@ xfs_xattr_acl_set(struct dentry *dentry, const char *name, if (!value) goto set_acl; - acl = posix_acl_from_xattr(value, size); + acl = posix_acl_from_xattr(&init_user_ns, value, size); if (!acl) { /* * acl_set_file(3) may request that we set default ACLs with diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index d7a9dd735e1e..933b7930b863 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -96,6 +96,7 @@ xfs_buf_lru_add( atomic_inc(&bp->b_hold); list_add_tail(&bp->b_lru, &btp->bt_lru); btp->bt_lru_nr++; + bp->b_lru_flags &= ~_XBF_LRU_DISPOSE; } spin_unlock(&btp->bt_lru_lock); } @@ -154,7 +155,8 @@ xfs_buf_stale( struct xfs_buftarg *btp = bp->b_target; spin_lock(&btp->bt_lru_lock); - if (!list_empty(&bp->b_lru)) { + if (!list_empty(&bp->b_lru) && + !(bp->b_lru_flags & _XBF_LRU_DISPOSE)) { list_del_init(&bp->b_lru); btp->bt_lru_nr--; atomic_dec(&bp->b_hold); @@ -1501,6 +1503,7 @@ xfs_buftarg_shrink( */ list_move(&bp->b_lru, &dispose); btp->bt_lru_nr--; + bp->b_lru_flags |= _XBF_LRU_DISPOSE; } spin_unlock(&btp->bt_lru_lock); diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index d03b73b9604e..7c0b6a0a1557 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -38,27 +38,28 @@ typedef enum { XBRW_ZERO = 3, /* Zero target memory */ } xfs_buf_rw_t; -#define XBF_READ (1 << 0) /* buffer intended for reading from device */ -#define XBF_WRITE (1 << 1) /* buffer intended for writing to device */ -#define XBF_READ_AHEAD (1 << 2) /* asynchronous read-ahead */ -#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */ -#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */ -#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */ +#define XBF_READ (1 << 0) /* buffer intended for reading from device */ +#define XBF_WRITE (1 << 1) /* buffer intended for writing to device */ +#define XBF_READ_AHEAD (1 << 2) /* asynchronous read-ahead */ +#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */ +#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */ +#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */ /* I/O hints for the BIO layer */ -#define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */ -#define XBF_FUA (1 << 11)/* force cache write through mode */ -#define XBF_FLUSH (1 << 12)/* flush the disk cache before a write */ +#define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */ +#define XBF_FUA (1 << 11)/* force cache write through mode */ +#define XBF_FLUSH (1 << 12)/* flush the disk cache before a write */ /* flags used only as arguments to access routines */ -#define XBF_TRYLOCK (1 << 16)/* lock requested, but do not wait */ -#define XBF_UNMAPPED (1 << 17)/* do not map the buffer */ +#define XBF_TRYLOCK (1 << 16)/* lock requested, but do not wait */ +#define XBF_UNMAPPED (1 << 17)/* do not map the buffer */ /* flags used only internally */ -#define _XBF_PAGES (1 << 20)/* backed by refcounted pages */ -#define _XBF_KMEM (1 << 21)/* backed by heap memory */ -#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */ -#define _XBF_COMPOUND (1 << 23)/* compound buffer */ +#define _XBF_PAGES (1 << 20)/* backed by refcounted pages */ +#define _XBF_KMEM (1 << 21)/* backed by heap memory */ +#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */ +#define _XBF_COMPOUND (1 << 23)/* compound buffer */ +#define _XBF_LRU_DISPOSE (1 << 24)/* buffer being discarded */ typedef unsigned int xfs_buf_flags_t; @@ -72,12 +73,13 @@ typedef unsigned int xfs_buf_flags_t; { XBF_SYNCIO, "SYNCIO" }, \ { XBF_FUA, "FUA" }, \ { XBF_FLUSH, "FLUSH" }, \ - { XBF_TRYLOCK, "TRYLOCK" }, /* should never be set */\ + { XBF_TRYLOCK, "TRYLOCK" }, /* should never be set */\ { XBF_UNMAPPED, "UNMAPPED" }, /* ditto */\ { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" }, \ - { _XBF_COMPOUND, "COMPOUND" } + { _XBF_COMPOUND, "COMPOUND" }, \ + { _XBF_LRU_DISPOSE, "LRU_DISPOSE" } typedef struct xfs_buftarg { dev_t bt_dev; @@ -124,7 +126,12 @@ typedef struct xfs_buf { xfs_buf_flags_t b_flags; /* status flags */ struct semaphore b_sema; /* semaphore for lockables */ + /* + * concurrent access to b_lru and b_lru_flags are protected by + * bt_lru_lock and not by b_sema + */ struct list_head b_lru; /* lru list */ + xfs_buf_flags_t b_lru_flags; /* internal lru status flags */ wait_queue_head_t b_waiters; /* unpin waiters */ struct list_head b_list; struct xfs_perag *b_pag; /* contains rbtree root */ diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c index e00de08dc8ac..b9b8646e62db 100644 --- a/fs/xfs/xfs_dfrag.c +++ b/fs/xfs/xfs_dfrag.c @@ -48,44 +48,44 @@ xfs_swapext( xfs_swapext_t *sxp) { xfs_inode_t *ip, *tip; - struct file *file, *tmp_file; + struct fd f, tmp; int error = 0; /* Pull information for the target fd */ - file = fget((int)sxp->sx_fdtarget); - if (!file) { + f = fdget((int)sxp->sx_fdtarget); + if (!f.file) { error = XFS_ERROR(EINVAL); goto out; } - if (!(file->f_mode & FMODE_WRITE) || - !(file->f_mode & FMODE_READ) || - (file->f_flags & O_APPEND)) { + if (!(f.file->f_mode & FMODE_WRITE) || + !(f.file->f_mode & FMODE_READ) || + (f.file->f_flags & O_APPEND)) { error = XFS_ERROR(EBADF); goto out_put_file; } - tmp_file = fget((int)sxp->sx_fdtmp); - if (!tmp_file) { + tmp = fdget((int)sxp->sx_fdtmp); + if (!tmp.file) { error = XFS_ERROR(EINVAL); goto out_put_file; } - if (!(tmp_file->f_mode & FMODE_WRITE) || - !(tmp_file->f_mode & FMODE_READ) || - (tmp_file->f_flags & O_APPEND)) { + if (!(tmp.file->f_mode & FMODE_WRITE) || + !(tmp.file->f_mode & FMODE_READ) || + (tmp.file->f_flags & O_APPEND)) { error = XFS_ERROR(EBADF); goto out_put_tmp_file; } - if (IS_SWAPFILE(file->f_path.dentry->d_inode) || - IS_SWAPFILE(tmp_file->f_path.dentry->d_inode)) { + if (IS_SWAPFILE(f.file->f_path.dentry->d_inode) || + IS_SWAPFILE(tmp.file->f_path.dentry->d_inode)) { error = XFS_ERROR(EINVAL); goto out_put_tmp_file; } - ip = XFS_I(file->f_path.dentry->d_inode); - tip = XFS_I(tmp_file->f_path.dentry->d_inode); + ip = XFS_I(f.file->f_path.dentry->d_inode); + tip = XFS_I(tmp.file->f_path.dentry->d_inode); if (ip->i_mount != tip->i_mount) { error = XFS_ERROR(EINVAL); @@ -105,9 +105,9 @@ xfs_swapext( error = xfs_swap_extents(ip, tip, sxp); out_put_tmp_file: - fput(tmp_file); + fdput(tmp); out_put_file: - fput(file); + fdput(f); out: return error; } diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index f9c3fe304a17..69cf4fcde03e 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -179,12 +179,14 @@ xfs_ioc_trim( * used by the fstrim application. In the end it really doesn't * matter as trimming blocks is an advisory interface. */ + if (range.start >= XFS_FSB_TO_B(mp, mp->m_sb.sb_dblocks) || + range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp))) + return -XFS_ERROR(EINVAL); + start = BTOBB(range.start); end = start + BTOBBT(range.len) - 1; minlen = BTOBB(max_t(u64, granularity, range.minlen)); - if (XFS_BB_TO_FSB(mp, start) >= mp->m_sb.sb_dblocks) - return -XFS_ERROR(EINVAL); if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1) end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)- 1; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 56afcdb2377d..aa473fa640a2 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; @@ -939,7 +940,6 @@ xfs_file_mmap( struct vm_area_struct *vma) { vma->vm_ops = &xfs_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; file_accessed(filp); return 0; @@ -959,17 +959,232 @@ 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 +1200,74 @@ 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 +1282,15 @@ 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 +1306,77 @@ 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 +1400,9 @@ 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; } @@ -1134,4 +1442,5 @@ const struct file_operations xfs_dir_file_operations = { static const struct vm_operations_struct xfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = xfs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c index 21e37b55f7e5..445bf1aef31c 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); @@ -962,23 +962,22 @@ xfs_dialloc( if (!pag->pagi_freecount && !okalloc) goto nextag; + /* + * Then read in the AGI buffer and recheck with the AGI buffer + * lock held. + */ error = xfs_ialloc_read_agi(mp, tp, agno, &agbp); if (error) goto out_error; - /* - * Once the AGI has been read in we have to recheck - * pagi_freecount with the AGI buffer lock held. - */ if (pag->pagi_freecount) { xfs_perag_put(pag); goto out_alloc; } - if (!okalloc) { - xfs_trans_brelse(tp, agbp); - goto nextag; - } + if (!okalloc) + goto nextag_relse_buffer; + error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced); if (error) { @@ -1007,6 +1006,8 @@ xfs_dialloc( return 0; } +nextag_relse_buffer: + xfs_trans_brelse(tp, agbp); nextag: xfs_perag_put(pag); if (++agno == mp->m_sb.sb_agcount) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 0e0232c3b6d9..8305f2ac6773 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -70,16 +70,16 @@ xfs_find_handle( int hsize; xfs_handle_t handle; struct inode *inode; - struct file *file = NULL; + struct fd f; struct path path; int error; struct xfs_inode *ip; if (cmd == XFS_IOC_FD_TO_HANDLE) { - file = fget(hreq->fd); - if (!file) + f = fdget(hreq->fd); + if (!f.file) return -EBADF; - inode = file->f_path.dentry->d_inode; + inode = f.file->f_path.dentry->d_inode; } else { error = user_lpath((const char __user *)hreq->path, &path); if (error) @@ -134,7 +134,7 @@ xfs_find_handle( out_put: if (cmd == XFS_IOC_FD_TO_HANDLE) - fput(file); + fdput(f); else path_put(&path); return error; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 29c2f83d4147..b2bd3a0e6376 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 05a05a7b6119..deee09e534dc 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_quotaops.c b/fs/xfs/xfs_quotaops.c index fed504fc2999..71926d630527 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -97,8 +97,7 @@ xfs_fs_set_xstate( STATIC int xfs_fs_get_dqblk( struct super_block *sb, - int type, - qid_t id, + struct kqid qid, struct fs_disk_quota *fdq) { struct xfs_mount *mp = XFS_M(sb); @@ -108,14 +107,14 @@ xfs_fs_get_dqblk( if (!XFS_IS_QUOTA_ON(mp)) return -ESRCH; - return -xfs_qm_scall_getquota(mp, id, xfs_quota_type(type), fdq); + return -xfs_qm_scall_getquota(mp, from_kqid(&init_user_ns, qid), + xfs_quota_type(qid.type), fdq); } STATIC int xfs_fs_set_dqblk( struct super_block *sb, - int type, - qid_t id, + struct kqid qid, struct fs_disk_quota *fdq) { struct xfs_mount *mp = XFS_M(sb); @@ -127,7 +126,8 @@ xfs_fs_set_dqblk( if (!XFS_IS_QUOTA_ON(mp)) return -ESRCH; - return -xfs_qm_scall_setqlim(mp, id, xfs_quota_type(type), fdq); + return -xfs_qm_scall_setqlim(mp, from_kqid(&init_user_ns, qid), + xfs_quota_type(qid.type), fdq); } const struct quotactl_ops xfs_quotactl_operations = { diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 92d4331cd4f1..ca28a4ba4b54 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -857,7 +857,7 @@ xfs_rtbuf_get( xfs_buf_t *bp; /* block buffer, result */ xfs_inode_t *ip; /* bitmap or summary inode */ xfs_bmbt_irec_t map; - int nmap; + int nmap = 1; int error; /* error value */ ip = issum ? mp->m_rsumip : mp->m_rbmip; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index bdaf4cb9f4a2..26a09bd7f975 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, @@ -919,6 +1006,7 @@ xfs_fs_put_super( struct xfs_mount *mp = XFS_M(sb); xfs_filestream_unmount(mp); + cancel_delayed_work_sync(&mp->m_sync_work); xfs_unmountfs(mp); xfs_syncd_stop(mp); xfs_freesb(mp); @@ -953,7 +1041,7 @@ xfs_fs_sync_fs( * We schedule xfssyncd now (now that the disk is * active) instead of later (when it might not be). */ - flush_delayed_work_sync(&mp->m_sync_work); + flush_delayed_work(&mp->m_sync_work); } return 0; @@ -1055,6 +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 @@ -1505,6 +1599,11 @@ xfs_init_zones(void) STATIC void xfs_destroy_zones(void) { + /* + * Make sure all delayed rcu free are flushed before we + * destroy caches. + */ + rcu_barrier(); kmem_zone_destroy(xfs_ili_zone); kmem_zone_destroy(xfs_inode_zone); kmem_zone_destroy(xfs_efi_zone); diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index 09b0c26b2245..9de4a920ba05 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_sync.c b/fs/xfs/xfs_sync.c index 96548176db80..9500caf15acf 100644 --- a/fs/xfs/xfs_sync.c +++ b/fs/xfs/xfs_sync.c @@ -475,7 +475,7 @@ xfs_flush_inodes( struct xfs_mount *mp = ip->i_mount; queue_work(xfs_syncd_wq, &mp->m_flush_work); - flush_work_sync(&mp->m_flush_work); + flush_work(&mp->m_flush_work); } STATIC void diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index e5795dd6013a..7d36ccf57f93 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), diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index bcb60542fcf1..0c7fa54f309e 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -578,9 +578,11 @@ xfs_quota_warn( /* no warnings for project quotas - we just return ENOSPC later */ if (dqp->dq_flags & XFS_DQ_PROJ) return; - quota_send_warning((dqp->dq_flags & XFS_DQ_USER) ? USRQUOTA : GRPQUOTA, - be32_to_cpu(dqp->q_core.d_id), mp->m_super->s_dev, - type); + quota_send_warning(make_kqid(&init_user_ns, + (dqp->dq_flags & XFS_DQ_USER) ? + USRQUOTA : GRPQUOTA, + be32_to_cpu(dqp->q_core.d_id)), + mp->m_super->s_dev, type); } /* |