diff options
Diffstat (limited to 'fs/ntfs/file.c')
| -rw-r--r-- | fs/ntfs/file.c | 392 |
1 files changed, 141 insertions, 251 deletions
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 72753389181..5c9e2c81cb1 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1,7 +1,7 @@ /* * file.c - NTFS kernel file operations. Part of the Linux-NTFS project. * - * Copyright (c) 2001-2005 Anton Altaparmakov + * Copyright (c) 2001-2011 Anton Altaparmakov and Tuxera Inc. * * This program/include file is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as published @@ -20,12 +20,14 @@ */ #include <linux/buffer_head.h> +#include <linux/gfp.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/sched.h> #include <linux/swap.h> #include <linux/uio.h> #include <linux/writeback.h> +#include <linux/aio.h> #include <asm/page.h> #include <asm/uaccess.h> @@ -61,7 +63,7 @@ static int ntfs_file_open(struct inode *vi, struct file *filp) { if (sizeof(unsigned long) < 8) { if (i_size_read(vi) > MAX_LFS_FILESIZE) - return -EFBIG; + return -EOVERFLOW; } return generic_file_open(vi, filp); } @@ -97,20 +99,16 @@ static int ntfs_file_open(struct inode *vi, struct file *filp) * the page at all. For a more detailed explanation see ntfs_truncate() in * fs/ntfs/inode.c. * - * @cached_page and @lru_pvec are just optimizations for dealing with multiple - * pages. - * * Return 0 on success and -errno on error. In the case that an error is * encountered it is possible that the initialized size will already have been * incremented some way towards @new_init_size but it is guaranteed that if * this is the case, the necessary zeroing will also have happened and that all * metadata is self-consistent. * - * Locking: i_sem on the vfs inode corrseponsind to the ntfs inode @ni must be + * Locking: i_mutex on the vfs inode corrseponsind to the ntfs inode @ni must be * held by the caller. */ -static int ntfs_attr_extend_initialized(ntfs_inode *ni, const s64 new_init_size, - struct page **cached_page, struct pagevec *lru_pvec) +static int ntfs_attr_extend_initialized(ntfs_inode *ni, const s64 new_init_size) { s64 old_init_size; loff_t old_i_size; @@ -231,14 +229,12 @@ do_non_resident_extend: * Read the page. If the page is not present, this will zero * the uninitialized regions for us. */ - page = read_cache_page(mapping, index, - (filler_t*)mapping->a_ops->readpage, NULL); + page = read_mapping_page(mapping, index, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); goto init_err_out; } - wait_on_page_locked(page); - if (unlikely(!PageUptodate(page) || PageError(page))) { + if (unlikely(PageError(page))) { page_cache_release(page); err = -EIO; goto init_err_out; @@ -248,7 +244,7 @@ do_non_resident_extend: * enough to make ntfs_writepage() work. */ write_lock_irqsave(&ni->size_lock, flags); - ni->initialized_size = (index + 1) << PAGE_CACHE_SHIFT; + ni->initialized_size = (s64)(index + 1) << PAGE_CACHE_SHIFT; if (ni->initialized_size > new_init_size) ni->initialized_size = new_init_size; write_unlock_irqrestore(&ni->size_lock, flags); @@ -363,7 +359,7 @@ static inline void ntfs_fault_in_pages_readable(const char __user *uaddr, volatile char c; /* Set @end to the first byte outside the last page we care about. */ - end = (const char __user*)PAGE_ALIGN((ptrdiff_t __user)uaddr + bytes); + end = (const char __user*)PAGE_ALIGN((unsigned long)uaddr + bytes); while (!__get_user(c, uaddr) && (uaddr += PAGE_SIZE, uaddr < end)) ; @@ -401,21 +397,16 @@ static inline void ntfs_fault_in_pages_readable_iovec(const struct iovec *iov, * @cached_page: allocated but as yet unused page * @lru_pvec: lru-buffering pagevec of caller * - * Obtain @nr_pages locked page cache pages from the mapping @maping and + * Obtain @nr_pages locked page cache pages from the mapping @mapping and * starting at index @index. * - * If a page is newly created, increment its refcount and add it to the - * caller's lru-buffering pagevec @lru_pvec. - * - * This is the same as mm/filemap.c::__grab_cache_page(), except that @nr_pages - * are obtained at once instead of just one page and that 0 is returned on - * success and -errno on error. + * If a page is newly created, add it to lru list * * Note, the page locks are obtained in ascending page index order. */ static inline int __ntfs_grab_cache_pages(struct address_space *mapping, pgoff_t index, const unsigned nr_pages, struct page **pages, - struct page **cached_page, struct pagevec *lru_pvec) + struct page **cached_page) { int err, nr; @@ -431,7 +422,7 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping, goto err_out; } } - err = add_to_page_cache(*cached_page, mapping, index, + err = add_to_page_cache_lru(*cached_page, mapping, index, GFP_KERNEL); if (unlikely(err)) { if (err == -EEXIST) @@ -439,9 +430,6 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping, goto err_out; } pages[nr] = *cached_page; - page_cache_get(*cached_page); - if (unlikely(!pagevec_add(lru_pvec, *cached_page))) - __pagevec_lru_add(lru_pvec); *cached_page = NULL; } index++; @@ -473,7 +461,7 @@ static inline int ntfs_submit_bh_for_read(struct buffer_head *bh) * @bytes: number of bytes to be written * * This is called for non-resident attributes from ntfs_file_buffered_write() - * with i_sem held on the inode (@pages[0]->mapping->host). There are + * with i_mutex held on the inode (@pages[0]->mapping->host). There are * @nr_pages pages in @pages which are locked but not kmap()ped. The source * data has not yet been copied into the @pages. * @@ -510,7 +498,7 @@ static int ntfs_prepare_pages_for_non_resident_write(struct page **pages, u32 attr_rec_len = 0; unsigned blocksize, u; int err, mp_size; - BOOL rl_write_locked, was_hole, is_retry; + bool rl_write_locked, was_hole, is_retry; unsigned char blocksize_bits; struct { u8 runlist_merged:1; @@ -529,11 +517,12 @@ static int ntfs_prepare_pages_for_non_resident_write(struct page **pages, "index 0x%lx, nr_pages 0x%x, pos 0x%llx, bytes 0x%zx.", vi->i_ino, ni->type, pages[0]->index, nr_pages, (long long)pos, bytes); - blocksize_bits = vi->i_blkbits; - blocksize = 1 << blocksize_bits; + blocksize = vol->sb->s_blocksize; + blocksize_bits = vol->sb->s_blocksize_bits; u = 0; do { - struct page *page = pages[u]; + page = pages[u]; + BUG_ON(!page); /* * create_empty_buffers() will create uptodate/dirty buffers if * the page is uptodate/dirty. @@ -544,13 +533,13 @@ static int ntfs_prepare_pages_for_non_resident_write(struct page **pages, return -ENOMEM; } } while (++u < nr_pages); - rl_write_locked = FALSE; + rl_write_locked = false; rl = NULL; err = 0; vcn = lcn = -1; vcn_len = 0; lcn_block = -1; - was_hole = FALSE; + was_hole = false; cpos = pos >> vol->cluster_size_bits; end = pos + bytes; cend = (end + vol->cluster_size - 1) >> vol->cluster_size_bits; @@ -608,11 +597,8 @@ do_next_page: ntfs_submit_bh_for_read(bh); *wait_bh++ = bh; } else { - u8 *kaddr = kmap_atomic(page, KM_USER0); - memset(kaddr + bh_offset(bh), 0, + zero_user(page, bh_offset(bh), blocksize); - kunmap_atomic(kaddr, KM_USER0); - flush_dcache_page(page); set_buffer_uptodate(bh); } } @@ -687,12 +673,8 @@ map_buffer_cached: ntfs_submit_bh_for_read(bh); *wait_bh++ = bh; } else { - u8 *kaddr = kmap_atomic(page, - KM_USER0); - memset(kaddr + bh_offset(bh), - 0, blocksize); - kunmap_atomic(kaddr, KM_USER0); - flush_dcache_page(page); + zero_user(page, bh_offset(bh), + blocksize); set_buffer_uptodate(bh); } } @@ -710,11 +692,8 @@ map_buffer_cached: */ if (bh_end <= pos || bh_pos >= end) { if (!buffer_uptodate(bh)) { - u8 *kaddr = kmap_atomic(page, KM_USER0); - memset(kaddr + bh_offset(bh), 0, + zero_user(page, bh_offset(bh), blocksize); - kunmap_atomic(kaddr, KM_USER0); - flush_dcache_page(page); set_buffer_uptodate(bh); } mark_buffer_dirty(bh); @@ -726,7 +705,7 @@ map_buffer_cached: u8 *kaddr; unsigned pofs; - kaddr = kmap_atomic(page, KM_USER0); + kaddr = kmap_atomic(page); if (bh_pos < pos) { pofs = bh_pos & ~PAGE_CACHE_MASK; memset(kaddr + pofs, 0, pos - bh_pos); @@ -735,7 +714,7 @@ map_buffer_cached: pofs = end & ~PAGE_CACHE_MASK; memset(kaddr + pofs, 0, bh_end - end); } - kunmap_atomic(kaddr, KM_USER0); + kunmap_atomic(kaddr); flush_dcache_page(page); } continue; @@ -753,15 +732,12 @@ map_buffer_cached: if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } else if (!buffer_uptodate(bh)) { - u8 *kaddr = kmap_atomic(page, KM_USER0); - memset(kaddr + bh_offset(bh), 0, blocksize); - kunmap_atomic(kaddr, KM_USER0); - flush_dcache_page(page); + zero_user(page, bh_offset(bh), blocksize); set_buffer_uptodate(bh); } continue; } - is_retry = FALSE; + is_retry = false; if (!rl) { down_read(&ni->runlist.lock); retry_remap: @@ -777,7 +753,7 @@ retry_remap: * Successful remap, setup the map cache and * use that to deal with the buffer. */ - was_hole = FALSE; + was_hole = false; vcn = bh_cpos; vcn_len = rl[1].vcn - vcn; lcn_block = lcn << (vol->cluster_size_bits - @@ -793,7 +769,7 @@ retry_remap: if (likely(vcn + vcn_len >= cend)) { if (rl_write_locked) { up_write(&ni->runlist.lock); - rl_write_locked = FALSE; + rl_write_locked = false; } else up_read(&ni->runlist.lock); rl = NULL; @@ -819,13 +795,13 @@ retry_remap: */ up_read(&ni->runlist.lock); down_write(&ni->runlist.lock); - rl_write_locked = TRUE; + rl_write_locked = true; goto retry_remap; } err = ntfs_map_runlist_nolock(ni, bh_cpos, NULL); if (likely(!err)) { - is_retry = TRUE; + is_retry = true; goto retry_remap; } /* @@ -880,11 +856,8 @@ rl_not_mapped_enoent: if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } else if (!buffer_uptodate(bh)) { - u8 *kaddr = kmap_atomic(page, KM_USER0); - memset(kaddr + bh_offset(bh), 0, - blocksize); - kunmap_atomic(kaddr, KM_USER0); - flush_dcache_page(page); + zero_user(page, bh_offset(bh), + blocksize); set_buffer_uptodate(bh); } continue; @@ -904,7 +877,7 @@ rl_not_mapped_enoent: if (!rl_write_locked) { up_read(&ni->runlist.lock); down_write(&ni->runlist.lock); - rl_write_locked = TRUE; + rl_write_locked = true; goto retry_remap; } /* Find the previous last allocated cluster. */ @@ -918,7 +891,7 @@ rl_not_mapped_enoent: } } rl2 = ntfs_cluster_alloc(vol, bh_cpos, 1, lcn, DATA_ZONE, - FALSE); + false); if (IS_ERR(rl2)) { err = PTR_ERR(rl2); ntfs_debug("Failed to allocate cluster, error code %i.", @@ -943,7 +916,8 @@ rl_not_mapped_enoent: } ni->runlist.rl = rl; status.runlist_merged = 1; - ntfs_debug("Allocated cluster, lcn 0x%llx.", lcn); + ntfs_debug("Allocated cluster, lcn 0x%llx.", + (unsigned long long)lcn); /* Map and lock the mft record and get the attribute record. */ if (!NInoAttr(ni)) base_ni = ni; @@ -1093,7 +1067,7 @@ rl_not_mapped_enoent: status.mft_attr_mapped = 0; status.mp_rebuilt = 0; /* Setup the map cache and use that to deal with the buffer. */ - was_hole = TRUE; + was_hole = true; vcn = bh_cpos; vcn_len = 1; lcn_block = lcn << (vol->cluster_size_bits - blocksize_bits); @@ -1105,7 +1079,7 @@ rl_not_mapped_enoent: */ if (likely(vcn + vcn_len >= cend)) { up_write(&ni->runlist.lock); - rl_write_locked = FALSE; + rl_write_locked = false; rl = NULL; } goto map_buffer_cached; @@ -1117,7 +1091,7 @@ rl_not_mapped_enoent: if (likely(!err)) { if (unlikely(rl_write_locked)) { up_write(&ni->runlist.lock); - rl_write_locked = FALSE; + rl_write_locked = false; } else if (unlikely(rl)) up_read(&ni->runlist.lock); rl = NULL; @@ -1138,16 +1112,12 @@ rl_not_mapped_enoent: * to zero the overflowing region. */ if (unlikely(bh_pos + blocksize > initialized_size)) { - u8 *kaddr; int ofs = 0; if (likely(bh_pos < initialized_size)) ofs = initialized_size - bh_pos; - kaddr = kmap_atomic(page, KM_USER0); - memset(kaddr + bh_offset(bh) + ofs, 0, - blocksize - ofs); - kunmap_atomic(kaddr, KM_USER0); - flush_dcache_page(page); + zero_user_segment(page, bh_offset(bh) + ofs, + blocksize); } } else /* if (unlikely(!buffer_uptodate(bh))) */ err = -EIO; @@ -1206,8 +1176,6 @@ rl_not_mapped_enoent: "attribute runlist in error code " "path. Run chkdsk to recover the " "lost cluster."); - make_bad_inode(vi); - make_bad_inode(VFS_I(base_ni)); NVolSetErrors(vol); } else /* if (success) */ { status.runlist_merged = 0; @@ -1238,8 +1206,6 @@ rl_not_mapped_enoent: ntfs_error(vol->sb, "Failed to restore attribute " "record in error code path. Run " "chkdsk to recover."); - make_bad_inode(vi); - make_bad_inode(VFS_I(base_ni)); NVolSetErrors(vol); } else /* if (success) */ { if (ntfs_mapping_pairs_build(vol, (u8*)a + @@ -1252,8 +1218,6 @@ rl_not_mapped_enoent: "mapping pairs array in error " "code path. Run chkdsk to " "recover."); - make_bad_inode(vi); - make_bad_inode(VFS_I(base_ni)); NVolSetErrors(vol); } flush_dcache_mft_record_page(ctx->ntfs_ino); @@ -1293,11 +1257,8 @@ rl_not_mapped_enoent: if (PageUptodate(page)) set_buffer_uptodate(bh); else { - u8 *kaddr = kmap_atomic(page, KM_USER0); - memset(kaddr + bh_offset(bh), 0, + zero_user(page, bh_offset(bh), blocksize); - kunmap_atomic(kaddr, KM_USER0); - flush_dcache_page(page); set_buffer_uptodate(bh); } } @@ -1310,7 +1271,7 @@ rl_not_mapped_enoent: /* * Copy as much as we can into the pages and return the number of bytes which - * were sucessfully copied. If a fault is encountered then clear the pages + * were successfully copied. If a fault is encountered then clear the pages * out to (ofs + bytes) and return the number of bytes which were copied. */ static inline size_t ntfs_copy_from_user(struct page **pages, @@ -1318,7 +1279,7 @@ static inline size_t ntfs_copy_from_user(struct page **pages, size_t bytes) { struct page **last_page = pages + nr_pages; - char *kaddr; + char *addr; size_t total = 0; unsigned len; int left; @@ -1327,13 +1288,13 @@ static inline size_t ntfs_copy_from_user(struct page **pages, len = PAGE_CACHE_SIZE - ofs; if (len > bytes) len = bytes; - kaddr = kmap_atomic(*pages, KM_USER0); - left = __copy_from_user_inatomic(kaddr + ofs, buf, len); - kunmap_atomic(kaddr, KM_USER0); + addr = kmap_atomic(*pages); + left = __copy_from_user_inatomic(addr + ofs, buf, len); + kunmap_atomic(addr); if (unlikely(left)) { /* Do it the slow way. */ - kaddr = kmap(*pages); - left = __copy_from_user(kaddr + ofs, buf, len); + addr = kmap(*pages); + left = __copy_from_user(addr + ofs, buf, len); kunmap(*pages); if (unlikely(left)) goto err_out; @@ -1357,14 +1318,12 @@ err_out: len = PAGE_CACHE_SIZE; if (len > bytes) len = bytes; - kaddr = kmap_atomic(*pages, KM_USER0); - memset(kaddr, 0, len); - kunmap_atomic(kaddr, KM_USER0); + zero_user(*pages, 0, len); } goto out; } -static size_t __ntfs_copy_from_user_iovec(char *vaddr, +static size_t __ntfs_copy_from_user_iovec_inatomic(char *vaddr, const struct iovec *iov, size_t iov_ofs, size_t bytes) { size_t total = 0; @@ -1382,10 +1341,6 @@ static size_t __ntfs_copy_from_user_iovec(char *vaddr, bytes -= len; vaddr += len; if (unlikely(left)) { - /* - * Zero the rest of the target like __copy_from_user(). - */ - memset(vaddr, 0, bytes); total -= left; break; } @@ -1426,51 +1381,56 @@ static inline void ntfs_set_next_iovec(const struct iovec **iovp, * pages (out to offset + bytes), to emulate ntfs_copy_from_user()'s * single-segment behaviour. * - * We call the same helper (__ntfs_copy_from_user_iovec()) both when atomic and - * when not atomic. This is ok because __ntfs_copy_from_user_iovec() calls + * We call the same helper (__ntfs_copy_from_user_iovec_inatomic()) both when + * atomic and when not atomic. This is ok because it calls * __copy_from_user_inatomic() and it is ok to call this when non-atomic. In * fact, the only difference between __copy_from_user_inatomic() and - * __copy_from_user() is that the latter calls might_sleep(). And on many - * architectures __copy_from_user_inatomic() is just defined to - * __copy_from_user() so it makes no difference at all on those architectures. + * __copy_from_user() is that the latter calls might_sleep() and the former + * should not zero the tail of the buffer on error. And on many architectures + * __copy_from_user_inatomic() is just defined to __copy_from_user() so it + * makes no difference at all on those architectures. */ static inline size_t ntfs_copy_from_user_iovec(struct page **pages, unsigned nr_pages, unsigned ofs, const struct iovec **iov, size_t *iov_ofs, size_t bytes) { struct page **last_page = pages + nr_pages; - char *kaddr; + char *addr; size_t copied, len, total = 0; do { len = PAGE_CACHE_SIZE - ofs; if (len > bytes) len = bytes; - kaddr = kmap_atomic(*pages, KM_USER0); - copied = __ntfs_copy_from_user_iovec(kaddr + ofs, + addr = kmap_atomic(*pages); + copied = __ntfs_copy_from_user_iovec_inatomic(addr + ofs, *iov, *iov_ofs, len); - kunmap_atomic(kaddr, KM_USER0); + kunmap_atomic(addr); if (unlikely(copied != len)) { /* Do it the slow way. */ - kaddr = kmap(*pages); - copied = __ntfs_copy_from_user_iovec(kaddr + ofs, - *iov, *iov_ofs, len); - kunmap(*pages); + addr = kmap(*pages); + copied = __ntfs_copy_from_user_iovec_inatomic(addr + + ofs, *iov, *iov_ofs, len); if (unlikely(copied != len)) goto err_out; + kunmap(*pages); } total += len; + ntfs_set_next_iovec(iov, iov_ofs, len); bytes -= len; if (!bytes) break; - ntfs_set_next_iovec(iov, iov_ofs, len); ofs = 0; } while (++pages < last_page); out: return total; err_out: - total += copied; + BUG_ON(copied > len); /* Zero the rest of the target like __copy_from_user(). */ + memset(addr + ofs + copied, 0, len - copied); + kunmap(*pages); + total += copied; + ntfs_set_next_iovec(iov, iov_ofs, copied); while (++pages < last_page) { bytes -= len; if (!bytes) @@ -1478,9 +1438,7 @@ err_out: len = PAGE_CACHE_SIZE; if (len > bytes) len = bytes; - kaddr = kmap_atomic(*pages, KM_USER0); - memset(kaddr, 0, len); - kunmap_atomic(kaddr, KM_USER0); + zero_user(*pages, 0, len); } goto out; } @@ -1489,14 +1447,15 @@ static inline void ntfs_flush_dcache_pages(struct page **pages, unsigned nr_pages) { BUG_ON(!nr_pages); + /* + * Warning: Do not do the decrement at the same time as the call to + * flush_dcache_page() because it is a NULL macro on i386 and hence the + * decrement never happens so the loop never terminates. + */ do { - /* - * Warning: Do not do the decrement at the same time as the - * call because flush_dcache_page() is a NULL macro on i386 - * and hence the decrement never happens. - */ + --nr_pages; flush_dcache_page(pages[nr_pages]); - } while (--nr_pages > 0); + } while (nr_pages > 0); } /** @@ -1525,25 +1484,25 @@ static inline int ntfs_commit_pages_after_non_resident_write( vi = pages[0]->mapping->host; ni = NTFS_I(vi); - blocksize = 1 << vi->i_blkbits; + blocksize = vi->i_sb->s_blocksize; end = pos + bytes; u = 0; do { s64 bh_pos; struct page *page; - BOOL partial; + bool partial; page = pages[u]; bh_pos = (s64)page->index << PAGE_CACHE_SHIFT; bh = head = page_buffers(page); - partial = FALSE; + partial = false; do { s64 bh_end; bh_end = bh_pos + blocksize; if (bh_end <= pos || bh_pos >= end) { if (!buffer_uptodate(bh)) - partial = TRUE; + partial = true; } else { set_buffer_uptodate(bh); mark_buffer_dirty(bh); @@ -1622,11 +1581,8 @@ err_out: unmap_mft_record(base_ni); ntfs_error(vi->i_sb, "Failed to update initialized_size/i_size (error " "code %i).", err); - if (err != -ENOMEM) { + if (err != -ENOMEM) NVolSetErrors(ni->vol); - make_bad_inode(VFS_I(base_ni)); - make_bad_inode(vi); - } return err; } @@ -1637,7 +1593,7 @@ err_out: * @pos: byte position in file at which the write begins * @bytes: number of bytes to be written * - * This is called from ntfs_file_buffered_write() with i_sem held on the inode + * This is called from ntfs_file_buffered_write() with i_mutex held on the inode * (@pages[0]->mapping->host). There are @nr_pages pages in @pages which are * locked but not kmap()ped. The source data has already been copied into the * @page. ntfs_prepare_pages_for_non_resident_write() has been called before @@ -1736,7 +1692,7 @@ static int ntfs_commit_pages_after_write(struct page **pages, BUG_ON(end > le32_to_cpu(a->length) - le16_to_cpu(a->data.resident.value_offset)); kattr = (u8*)a + le16_to_cpu(a->data.resident.value_offset); - kaddr = kmap_atomic(page, KM_USER0); + kaddr = kmap_atomic(page); /* Copy the received data from the page to the mft record. */ memcpy(kattr + pos, kaddr + pos, bytes); /* Update the attribute length if necessary. */ @@ -1758,7 +1714,7 @@ static int ntfs_commit_pages_after_write(struct page **pages, flush_dcache_page(page); SetPageUptodate(page); } - kunmap_atomic(kaddr, KM_USER0); + kunmap_atomic(kaddr); /* Update initialized_size/i_size if necessary. */ read_lock_irqsave(&ni->size_lock, flags); initialized_size = ni->initialized_size; @@ -1766,8 +1722,6 @@ static int ntfs_commit_pages_after_write(struct page **pages, read_unlock_irqrestore(&ni->size_lock, flags); BUG_ON(initialized_size != i_size); if (end > initialized_size) { - unsigned long flags; - write_lock_irqsave(&ni->size_lock, flags); ni->initialized_size = end; i_size_write(vi, end); @@ -1801,8 +1755,6 @@ err_out: ntfs_error(vi->i_sb, "Resident attribute commit write failed " "with error %i.", err); NVolSetErrors(ni->vol); - make_bad_inode(VFS_I(base_ni)); - make_bad_inode(vi); } if (ctx) ntfs_attr_put_search_ctx(ctx); @@ -1811,10 +1763,20 @@ err_out: return err; } +static void ntfs_write_failed(struct address_space *mapping, loff_t to) +{ + struct inode *inode = mapping->host; + + if (to > inode->i_size) { + truncate_pagecache(inode, inode->i_size); + ntfs_truncate_vfs(inode); + } +} + /** * ntfs_file_buffered_write - * - * Locking: The vfs is holding ->i_sem on the inode. + * Locking: The vfs is holding ->i_mutex on the inode. */ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, @@ -1836,7 +1798,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, ssize_t status, written; unsigned nr_pages; int err; - struct pagevec lru_pvec; ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, " "pos 0x%llx, count 0x%lx.", @@ -1882,9 +1843,8 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, * fails again. */ if (unlikely(NInoTruncateFailed(ni))) { - down_write(&vi->i_alloc_sem); + inode_dio_wait(vi); err = ntfs_truncate(vi); - up_write(&vi->i_alloc_sem); if (err || NInoTruncateFailed(ni)) { if (!err) err = -EIO; @@ -1948,7 +1908,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, } } } - pagevec_init(&lru_pvec, 0); written = 0; /* * If the write starts beyond the initialized size, extend it up to the @@ -1961,8 +1920,7 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, ll = ni->initialized_size; read_unlock_irqrestore(&ni->size_lock, flags); if (pos > ll) { - err = ntfs_attr_extend_initialized(ni, pos, &cached_page, - &lru_pvec); + err = ntfs_attr_extend_initialized(ni, pos); if (err < 0) { ntfs_error(vol->sb, "Cannot perform write to inode " "0x%lx, attribute type 0x%x, because " @@ -2005,7 +1963,7 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, */ down_read(&ni->runlist.lock); lcn = ntfs_attr_vcn_to_lcn_nolock(ni, pos >> - vol->cluster_size_bits, FALSE); + vol->cluster_size_bits, false); up_read(&ni->runlist.lock); if (unlikely(lcn < LCN_HOLE)) { status = -EIO; @@ -2048,7 +2006,7 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, ntfs_fault_in_pages_readable_iovec(iov, iov_ofs, bytes); /* Get and lock @do_pages starting at index @start_idx. */ status = __ntfs_grab_cache_pages(mapping, start_idx, do_pages, - pages, &cached_page, &lru_pvec); + pages, &cached_page); if (unlikely(status)) break; /* @@ -2075,8 +2033,9 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, * allocated space, which is not a disaster. */ i_size = i_size_read(vi); - if (pos + bytes > i_size) - vmtruncate(vi, i_size); + if (pos + bytes > i_size) { + ntfs_write_failed(mapping, pos + bytes); + } break; } } @@ -2101,7 +2060,6 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb, } do { unlock_page(pages[--do_pages]); - mark_page_accessed(pages[do_pages]); page_cache_release(pages[do_pages]); } while (do_pages); if (unlikely(status)) @@ -2113,15 +2071,6 @@ err_out: *ppos = pos; if (cached_page) page_cache_release(cached_page); - /* For now, when the user asks for O_SYNC, we actually give O_DSYNC. */ - if (likely(!status)) { - if (unlikely((file->f_flags & O_SYNC) || IS_SYNC(vi))) { - if (!mapping->a_ops->writepage || !is_sync_kiocb(iocb)) - status = generic_osync_inode(vi, mapping, - OSYNC_METADATA|OSYNC_DATA); - } - } - pagevec_lru_add(&lru_pvec); ntfs_debug("Done. Returning %s (written 0x%lx, status %li).", written ? "written" : "status", (unsigned long)written, (long)status); @@ -2138,30 +2087,11 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb, struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; loff_t pos; - unsigned long seg; size_t count; /* after file limit checks */ ssize_t written, err; - count = 0; - for (seg = 0; seg < nr_segs; seg++) { - const struct iovec *iv = &iov[seg]; - /* - * If any segment has a negative length, or the cumulative - * length ever wraps negative then return -EINVAL. - */ - count += iv->iov_len; - if (unlikely((ssize_t)(count|iv->iov_len) < 0)) - return -EINVAL; - if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len)) - continue; - if (!seg) - return -EFAULT; - nr_segs = seg; - count -= iv->iov_len; /* This segment is no good */ - break; - } + count = iov_length(iov, nr_segs); pos = *ppos; - vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); /* We can write back this queue in page reclaim. */ current->backing_dev_info = mapping->backing_dev_info; written = 0; @@ -2170,10 +2100,12 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb, goto out; if (!count) goto out; - err = remove_suid(file->f_dentry); + err = file_remove_suid(file); + if (err) + goto out; + err = file_update_time(file); if (err) goto out; - inode_update_time(inode, 1); written = ntfs_file_buffered_write(iocb, iov, nr_segs, pos, ppos, count); out: @@ -2184,51 +2116,21 @@ out: /** * ntfs_file_aio_write - */ -static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; BUG_ON(iocb->ki_pos != pos); - down(&inode->i_sem); - ret = ntfs_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); - up(&inode->i_sem); - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err = sync_page_range(inode, mapping, pos, ret); - if (err < 0) - ret = err; - } - return ret; -} - -/** - * ntfs_file_writev - - * - * Basically the same as generic_file_writev() except that it ends up calling - * ntfs_file_aio_write_nolock() instead of __generic_file_aio_write_nolock(). - */ -static ssize_t ntfs_file_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - struct kiocb kiocb; - ssize_t ret; - - down(&inode->i_sem); - init_sync_kiocb(&kiocb, file); - ret = ntfs_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); - up(&inode->i_sem); - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err = sync_page_range(inode, mapping, *ppos - ret, ret); + mutex_lock(&inode->i_mutex); + ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos); + mutex_unlock(&inode->i_mutex); + if (ret > 0) { + int err = generic_write_sync(file, iocb->ki_pos - ret, ret); if (err < 0) ret = err; } @@ -2236,21 +2138,8 @@ static ssize_t ntfs_file_writev(struct file *file, const struct iovec *iov, } /** - * ntfs_file_write - simple wrapper for ntfs_file_writev() - */ -static ssize_t ntfs_file_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; - - return ntfs_file_writev(file, &local_iov, 1, ppos); -} - -/** * ntfs_file_fsync - sync a file to disk * @filp: file to be synced - * @dentry: dentry describing the file to sync * @datasync: if non-zero only flush user data and not metadata * * Data integrity sync of a file to disk. Used for fsync, fdatasync, and msync @@ -2266,25 +2155,28 @@ static ssize_t ntfs_file_write(struct file *file, const char __user *buf, * Also, if @datasync is true, we do not wait on the inode to be written out * but we always wait on the page cache pages to be written out. * - * Note: In the past @filp could be NULL so we ignore it as we don't need it - * anyway. - * - * Locking: Caller must hold i_sem on the inode. + * Locking: Caller must hold i_mutex on the inode. * * TODO: We should probably also write all attribute/index inodes associated * with this inode but since we have no simple way of getting to them we ignore * this problem for now. */ -static int ntfs_file_fsync(struct file *filp, struct dentry *dentry, - int datasync) +static int ntfs_file_fsync(struct file *filp, loff_t start, loff_t end, + int datasync) { - struct inode *vi = dentry->d_inode; + struct inode *vi = filp->f_mapping->host; int err, ret = 0; ntfs_debug("Entering for inode 0x%lx.", vi->i_ino); + + err = filemap_write_and_wait_range(vi->i_mapping, start, end); + if (err) + return err; + mutex_lock(&vi->i_mutex); + BUG_ON(S_ISDIR(vi->i_mode)); if (!datasync || !NInoNonResident(NTFS_I(vi))) - ret = ntfs_write_inode(vi, 1); + ret = __ntfs_write_inode(vi, 1); write_inode_now(vi, !datasync); /* * NOTE: If we were to use mapping->private_list (see ext2 and @@ -2299,20 +2191,19 @@ static int ntfs_file_fsync(struct file *filp, struct dentry *dentry, else ntfs_warning(vi->i_sb, "Failed to f%ssync inode 0x%lx. Error " "%u.", datasync ? "data" : "", vi->i_ino, -ret); + mutex_unlock(&vi->i_mutex); return ret; } #endif /* NTFS_RW */ -struct file_operations ntfs_file_ops = { +const struct file_operations ntfs_file_ops = { .llseek = generic_file_llseek, /* Seek inside file. */ - .read = generic_file_read, /* Read from file. */ - .aio_read = generic_file_aio_read, /* Async read from file. */ - .readv = generic_file_readv, /* Read from file. */ + .read = new_sync_read, /* Read from file. */ + .read_iter = generic_file_read_iter, /* Async read from file. */ #ifdef NTFS_RW - .write = ntfs_file_write, /* Write to file. */ + .write = do_sync_write, /* Write to file. */ .aio_write = ntfs_file_aio_write, /* Async write to file. */ - .writev = ntfs_file_writev, /* Write to file. */ /*.release = ,*/ /* Last file is closed. See fs/ext2/file.c:: ext2_release_file() for @@ -2328,7 +2219,7 @@ struct file_operations ntfs_file_ops = { mounted filesystem. */ .mmap = generic_file_mmap, /* Mmap file. */ .open = ntfs_file_open, /* Open file. */ - .sendfile = generic_file_sendfile, /* Zero-copy data send with + .splice_read = generic_file_splice_read /* Zero-copy data send with the data source being on the ntfs partition. We do not need to care about the @@ -2340,13 +2231,12 @@ struct file_operations ntfs_file_ops = { the data source. */ }; -struct inode_operations ntfs_file_inode_ops = { +const struct inode_operations ntfs_file_inode_ops = { #ifdef NTFS_RW - .truncate = ntfs_truncate_vfs, .setattr = ntfs_setattr, #endif /* NTFS_RW */ }; -struct file_operations ntfs_empty_file_ops = {}; +const struct file_operations ntfs_empty_file_ops = {}; -struct inode_operations ntfs_empty_inode_ops = {}; +const struct inode_operations ntfs_empty_inode_ops = {}; |