diff options
Diffstat (limited to 'fs/ntfs/inode.c')
| -rw-r--r-- | fs/ntfs/inode.c | 391 |
1 files changed, 221 insertions, 170 deletions
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index b24f4c4b2c5..f47af5e6e23 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -1,7 +1,7 @@ /** * inode.c - NTFS kernel inode handling. Part of the Linux-NTFS project. * - * Copyright (c) 2001-2005 Anton Altaparmakov + * Copyright (c) 2001-2007 Anton Altaparmakov * * 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 @@ -19,17 +19,23 @@ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ -#include <linux/pagemap.h> #include <linux/buffer_head.h> -#include <linux/smp_lock.h> -#include <linux/quotaops.h> +#include <linux/fs.h> +#include <linux/mm.h> #include <linux/mount.h> +#include <linux/mutex.h> +#include <linux/pagemap.h> +#include <linux/quotaops.h> +#include <linux/slab.h> +#include <linux/log2.h> +#include <linux/aio.h> #include "aops.h" +#include "attrib.h" +#include "bitmap.h" #include "dir.h" #include "debug.h" #include "inode.h" -#include "attrib.h" #include "lcnalloc.h" #include "malloc.h" #include "mft.h" @@ -49,7 +55,7 @@ * * Return 1 if the attributes match and 0 if not. * - * NOTE: This function runs with the inode_lock spin lock held so it is not + * NOTE: This function runs with the inode_hash_lock spin lock held so it is not * allowed to sleep. */ int ntfs_test_inode(struct inode *vi, ntfs_attr *na) @@ -89,11 +95,11 @@ int ntfs_test_inode(struct inode *vi, ntfs_attr *na) * If initializing the normal file/directory inode, set @na->type to AT_UNUSED. * In that case, @na->name and @na->name_len should be set to NULL and 0, * respectively. Although that is not strictly necessary as - * ntfs_read_inode_locked() will fill them in later. + * ntfs_read_locked_inode() will fill them in later. * * Return 0 on success and -errno on error. * - * NOTE: This function runs with the inode_lock spin lock held so it is not + * NOTE: This function runs with the inode->i_lock spin lock held so it is not * allowed to sleep. (Hence the GFP_ATOMIC allocation.) */ static int ntfs_init_locked_inode(struct inode *vi, ntfs_attr *na) @@ -131,11 +137,11 @@ static int ntfs_init_locked_inode(struct inode *vi, ntfs_attr *na) BUG_ON(!na->name); i = na->name_len * sizeof(ntfschar); - ni->name = (ntfschar*)kmalloc(i + sizeof(ntfschar), GFP_ATOMIC); + ni->name = kmalloc(i + sizeof(ntfschar), GFP_ATOMIC); if (!ni->name) return -ENOMEM; memcpy(ni->name, na->name, i); - ni->name[i] = 0; + ni->name[na->name_len] = 0; } return 0; } @@ -165,8 +171,8 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *ntfs_iget(struct super_block *sb, unsigned long mft_no) { struct inode *vi; - ntfs_attr na; int err; + ntfs_attr na; na.mft_no = mft_no; na.type = AT_UNUSED; @@ -223,8 +229,8 @@ struct inode *ntfs_attr_iget(struct inode *base_vi, ATTR_TYPE type, ntfschar *name, u32 name_len) { struct inode *vi; - ntfs_attr na; int err; + ntfs_attr na; /* Make sure no one calls ntfs_attr_iget() for indices. */ BUG_ON(type == AT_INDEX_ALLOCATION); @@ -281,8 +287,8 @@ struct inode *ntfs_index_iget(struct inode *base_vi, ntfschar *name, u32 name_len) { struct inode *vi; - ntfs_attr na; int err; + ntfs_attr na; na.mft_no = base_vi->i_ino; na.type = AT_INDEX_ALLOCATION; @@ -318,7 +324,7 @@ struct inode *ntfs_alloc_big_inode(struct super_block *sb) ntfs_inode *ni; ntfs_debug("Entering."); - ni = kmem_cache_alloc(ntfs_big_inode_cache, SLAB_NOFS); + ni = kmem_cache_alloc(ntfs_big_inode_cache, GFP_NOFS); if (likely(ni != NULL)) { ni->state = 0; return VFS_I(ni); @@ -327,6 +333,12 @@ struct inode *ntfs_alloc_big_inode(struct super_block *sb) return NULL; } +static void ntfs_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + kmem_cache_free(ntfs_big_inode_cache, NTFS_I(inode)); +} + void ntfs_destroy_big_inode(struct inode *inode) { ntfs_inode *ni = NTFS_I(inode); @@ -335,7 +347,7 @@ void ntfs_destroy_big_inode(struct inode *inode) BUG_ON(ni->page); if (!atomic_dec_and_test(&ni->count)) BUG(); - kmem_cache_free(ntfs_big_inode_cache, NTFS_I(inode)); + call_rcu(&inode->i_rcu, ntfs_i_callback); } static inline ntfs_inode *ntfs_alloc_extent_inode(void) @@ -343,7 +355,7 @@ static inline ntfs_inode *ntfs_alloc_extent_inode(void) ntfs_inode *ni; ntfs_debug("Entering."); - ni = kmem_cache_alloc(ntfs_inode_cache, SLAB_NOFS); + ni = kmem_cache_alloc(ntfs_inode_cache, GFP_NOFS); if (likely(ni != NULL)) { ni->state = 0; return ni; @@ -361,6 +373,12 @@ static void ntfs_destroy_extent_inode(ntfs_inode *ni) kmem_cache_free(ntfs_inode_cache, ni); } +/* + * The attribute runlist lock has separate locking rules from the + * normal runlist lock, so split the two lock-classes: + */ +static struct lock_class_key attr_list_rl_lock_class; + /** * __ntfs_init_inode - initialize ntfs specific part of an inode * @sb: super block of mounted volume @@ -382,23 +400,31 @@ void __ntfs_init_inode(struct super_block *sb, ntfs_inode *ni) atomic_set(&ni->count, 1); ni->vol = NTFS_SB(sb); ntfs_init_runlist(&ni->runlist); - init_MUTEX(&ni->mrec_lock); + mutex_init(&ni->mrec_lock); ni->page = NULL; ni->page_ofs = 0; ni->attr_list_size = 0; ni->attr_list = NULL; ntfs_init_runlist(&ni->attr_list_rl); - ni->itype.index.bmp_ino = NULL; + lockdep_set_class(&ni->attr_list_rl.lock, + &attr_list_rl_lock_class); ni->itype.index.block_size = 0; ni->itype.index.vcn_size = 0; ni->itype.index.collation_rule = 0; ni->itype.index.block_size_bits = 0; ni->itype.index.vcn_size_bits = 0; - init_MUTEX(&ni->extent_lock); + mutex_init(&ni->extent_lock); ni->nr_extents = 0; ni->ext.base_ntfs_ino = NULL; } +/* + * Extent inodes get MFT-mapped in a nested way, while the base inode + * is still mapped. Teach this nesting to the lock validator by creating + * a separate class for nested inode's mrec_lock's: + */ +static struct lock_class_key extent_inode_mrec_lock_key; + inline ntfs_inode *ntfs_new_extent_inode(struct super_block *sb, unsigned long mft_no) { @@ -407,6 +433,7 @@ inline ntfs_inode *ntfs_new_extent_inode(struct super_block *sb, ntfs_debug("Entering."); if (likely(ni != NULL)) { __ntfs_init_inode(sb, ni); + lockdep_set_class(&ni->mrec_lock, &extent_inode_mrec_lock_key); ni->mft_no = mft_no; ni->type = AT_UNUSED; ni->name = NULL; @@ -510,7 +537,7 @@ err_corrupt_attr: * the ntfs inode. * * Q: What locks are held when the function is called? - * A: i_state has I_LOCK set, hence the inode is locked, also + * A: i_state has I_NEW set, hence the inode is locked, also * i_count is set to 1, so it is not going to go away * i_flags is set to 0 and we have no business touching it. Only an ioctl() * is allowed to write to them. We should of course be honouring them but @@ -524,6 +551,7 @@ static int ntfs_read_locked_inode(struct inode *vi) { ntfs_volume *vol = NTFS_SB(vi->i_sb); ntfs_inode *ni; + struct inode *bvi; MFT_RECORD *m; ATTR_RECORD *a; STANDARD_INFORMATION *si; @@ -534,8 +562,6 @@ static int ntfs_read_locked_inode(struct inode *vi) /* Setup the generic vfs inode parts now. */ - /* This is the optimal IO size (for stat), not the fs block size. */ - vi->i_blksize = PAGE_CACHE_SIZE; /* * This is for checking whether an inode has changed w.r.t. a file so * that the file can be updated if necessary (compare with f_version). @@ -586,7 +612,7 @@ static int ntfs_read_locked_inode(struct inode *vi) * might be tricky due to vfs interactions. Need to think about this * some more when implementing the unlink command. */ - vi->i_nlink = le16_to_cpu(m->link_count); + set_nlink(vi, le16_to_cpu(m->link_count)); /* * FIXME: Reparse points can have the directory bit set even though * they would be S_IFLNK. Need to deal with this further below when we @@ -596,7 +622,7 @@ static int ntfs_read_locked_inode(struct inode *vi) */ /* Everyone gets all permissions. */ vi->i_mode |= S_IRWXUGO; - /* If read-only, noone gets write permissions. */ + /* If read-only, no one gets write permissions. */ if (IS_RDONLY(vi)) vi->i_mode &= ~S_IWUGO; if (m->flags & MFT_RECORD_IS_DIRECTORY) { @@ -608,7 +634,7 @@ static int ntfs_read_locked_inode(struct inode *vi) vi->i_mode &= ~vol->dmask; /* Things break without this kludge! */ if (vi->i_nlink > 1) - vi->i_nlink = 1; + set_nlink(vi, 1); } else { vi->i_mode |= S_IFREG; /* Apply the file permissions mask set in the mount options. */ @@ -677,13 +703,28 @@ static int ntfs_read_locked_inode(struct inode *vi) ntfs_debug("Attribute list found in inode 0x%lx.", vi->i_ino); NInoSetAttrList(ni); a = ctx->attr; - if (a->flags & ATTR_IS_ENCRYPTED || - a->flags & ATTR_COMPRESSION_MASK || - a->flags & ATTR_IS_SPARSE) { + if (a->flags & ATTR_COMPRESSION_MASK) { ntfs_error(vi->i_sb, "Attribute list attribute is " - "compressed/encrypted/sparse."); + "compressed."); goto unm_err_out; } + if (a->flags & ATTR_IS_ENCRYPTED || + a->flags & ATTR_IS_SPARSE) { + if (a->non_resident) { + ntfs_error(vi->i_sb, "Non-resident attribute " + "list attribute is encrypted/" + "sparse."); + goto unm_err_out; + } + ntfs_warning(vi->i_sb, "Resident attribute list " + "attribute in inode 0x%lx is marked " + "encrypted/sparse which is not true. " + "However, Windows allows this and " + "chkdsk does not detect or correct it " + "so we will just ignore the invalid " + "flags and pretend they are not set.", + vi->i_ino); + } /* Now allocate memory for the attribute list. */ ni->attr_list_size = (u32)ntfs_attr_size(a); ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size); @@ -745,7 +786,6 @@ skip_attr_list_load: */ if (S_ISDIR(vi->i_mode)) { loff_t bvi_size; - struct inode *bvi; ntfs_inode *bni; INDEX_ROOT *ir; u8 *ir_end, *index_end; @@ -950,13 +990,12 @@ skip_attr_list_load: err = PTR_ERR(bvi); goto unm_err_out; } - ni->itype.index.bmp_ino = bvi; bni = NTFS_I(bvi); if (NInoCompressed(bni) || NInoEncrypted(bni) || NInoSparse(bni)) { ntfs_error(vi->i_sb, "$BITMAP attribute is compressed " "and/or encrypted and/or sparse."); - goto unm_err_out; + goto iput_unm_err_out; } /* Consistency check bitmap size vs. index allocation size. */ bvi_size = i_size_read(bvi); @@ -965,8 +1004,10 @@ skip_attr_list_load: ntfs_error(vi->i_sb, "Index bitmap too small (0x%llx) " "for index allocation (0x%llx).", bvi_size << 3, vi->i_size); - goto unm_err_out; + goto iput_unm_err_out; } + /* No longer need the bitmap attribute inode. */ + iput(bvi); skip_large_dir_stuff: /* Setup the operations for this inode. */ vi->i_op = &ntfs_dir_inode_ops; @@ -1049,10 +1090,10 @@ skip_large_dir_stuff: if (a->non_resident) { NInoSetNonResident(ni); if (NInoCompressed(ni) || NInoSparse(ni)) { - if (a->data.non_resident.compression_unit != - 4) { + if (NInoCompressed(ni) && a->data.non_resident. + compression_unit != 4) { ntfs_error(vi->i_sb, "Found " - "nonstandard " + "non-standard " "compression unit (%u " "instead of 4). " "Cannot handle this.", @@ -1061,16 +1102,26 @@ skip_large_dir_stuff: err = -EOPNOTSUPP; goto unm_err_out; } - ni->itype.compressed.block_clusters = 1U << - a->data.non_resident. - compression_unit; - ni->itype.compressed.block_size = 1U << ( - a->data.non_resident. - compression_unit + - vol->cluster_size_bits); - ni->itype.compressed.block_size_bits = ffs( - ni->itype.compressed. - block_size) - 1; + if (a->data.non_resident.compression_unit) { + ni->itype.compressed.block_size = 1U << + (a->data.non_resident. + compression_unit + + vol->cluster_size_bits); + ni->itype.compressed.block_size_bits = + ffs(ni->itype. + compressed. + block_size) - 1; + ni->itype.compressed.block_clusters = + 1U << a->data. + non_resident. + compression_unit; + } else { + ni->itype.compressed.block_size = 0; + ni->itype.compressed.block_size_bits = + 0; + ni->itype.compressed.block_clusters = + 0; + } ni->itype.compressed.size = sle64_to_cpu( a->data.non_resident. compressed_size); @@ -1131,7 +1182,8 @@ no_data_attr_special_case: vi->i_blocks = ni->allocated_size >> 9; ntfs_debug("Done."); return 0; - +iput_unm_err_out: + iput(bvi); unm_err_out: if (!err) err = -EIO; @@ -1162,7 +1214,7 @@ err_out: * necessary fields in @vi as well as initializing the ntfs inode. * * Q: What locks are held when the function is called? - * A: i_state has I_LOCK set, hence the inode is locked, also + * A: i_state has I_NEW set, hence the inode is locked, also * i_count is set to 1, so it is not going to go away * * Return 0 on success and -errno on error. In the error case, the inode will @@ -1187,11 +1239,10 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi) base_ni = NTFS_I(base_vi); /* Just mirror the values from the base inode. */ - vi->i_blksize = base_vi->i_blksize; vi->i_version = base_vi->i_version; vi->i_uid = base_vi->i_uid; vi->i_gid = base_vi->i_gid; - vi->i_nlink = base_vi->i_nlink; + set_nlink(vi, base_vi->i_nlink); vi->i_mtime = base_vi->i_mtime; vi->i_ctime = base_vi->i_ctime; vi->i_atime = base_vi->i_atime; @@ -1323,8 +1374,9 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi) goto unm_err_out; } if (NInoCompressed(ni) || NInoSparse(ni)) { - if (a->data.non_resident.compression_unit != 4) { - ntfs_error(vi->i_sb, "Found nonstandard " + if (NInoCompressed(ni) && a->data.non_resident. + compression_unit != 4) { + ntfs_error(vi->i_sb, "Found non-standard " "compression unit (%u instead " "of 4). Cannot handle this.", a->data.non_resident. @@ -1332,13 +1384,22 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi) err = -EOPNOTSUPP; goto unm_err_out; } - ni->itype.compressed.block_clusters = 1U << - a->data.non_resident.compression_unit; - ni->itype.compressed.block_size = 1U << ( - a->data.non_resident.compression_unit + - vol->cluster_size_bits); - ni->itype.compressed.block_size_bits = ffs( - ni->itype.compressed.block_size) - 1; + if (a->data.non_resident.compression_unit) { + ni->itype.compressed.block_size = 1U << + (a->data.non_resident. + compression_unit + + vol->cluster_size_bits); + ni->itype.compressed.block_size_bits = + ffs(ni->itype.compressed. + block_size) - 1; + ni->itype.compressed.block_clusters = 1U << + a->data.non_resident. + compression_unit; + } else { + ni->itype.compressed.block_size = 0; + ni->itype.compressed.block_size_bits = 0; + ni->itype.compressed.block_clusters = 0; + } ni->itype.compressed.size = sle64_to_cpu( a->data.non_resident.compressed_size); } @@ -1353,9 +1414,6 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi) ni->allocated_size = sle64_to_cpu( a->data.non_resident.allocated_size); } - /* Setup the operations for this attribute inode. */ - vi->i_op = NULL; - vi->i_fop = NULL; if (NInoMstProtected(ni)) vi->i_mapping->a_ops = &ntfs_mst_aops; else @@ -1391,7 +1449,6 @@ err_out: "Run chkdsk.", err, vi->i_ino, ni->type, ni->name_len, base_vi->i_ino); make_bad_inode(vi); - make_bad_inode(base_vi); if (err != -ENOMEM) NVolSetErrors(vol); return err; @@ -1424,7 +1481,7 @@ err_out: * normal directory inodes. * * Q: What locks are held when the function is called? - * A: i_state has I_LOCK set, hence the inode is locked, also + * A: i_state has I_NEW set, hence the inode is locked, also * i_count is set to 1, so it is not going to go away * * Return 0 on success and -errno on error. In the error case, the inode will @@ -1448,11 +1505,10 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi) ni = NTFS_I(vi); base_ni = NTFS_I(base_vi); /* Just mirror the values from the base inode. */ - vi->i_blksize = base_vi->i_blksize; vi->i_version = base_vi->i_version; vi->i_uid = base_vi->i_uid; vi->i_gid = base_vi->i_gid; - vi->i_nlink = base_vi->i_nlink; + set_nlink(vi, base_vi->i_nlink); vi->i_mtime = base_vi->i_mtime; vi->i_ctime = base_vi->i_ctime; vi->i_atime = base_vi->i_atime; @@ -1522,7 +1578,7 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi) ntfs_debug("Index collation rule is 0x%x.", le32_to_cpu(ir->collation_rule)); ni->itype.index.block_size = le32_to_cpu(ir->index_block_size); - if (ni->itype.index.block_size & (ni->itype.index.block_size - 1)) { + if (!is_power_of_2(ni->itype.index.block_size)) { ntfs_error(vi->i_sb, "Index block size (%u) is not a power of " "two.", ni->itype.index.block_size); goto unm_err_out; @@ -1576,6 +1632,7 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi) "$INDEX_ALLOCATION attribute."); goto unm_err_out; } + a = ctx->attr; if (!a->non_resident) { ntfs_error(vi->i_sb, "$INDEX_ALLOCATION attribute is " "resident."); @@ -1644,11 +1701,9 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi) vi->i_size); goto iput_unm_err_out; } - ni->itype.index.bmp_ino = bvi; + iput(bvi); skip_large_index_stuff: /* Setup the operations for this index inode. */ - vi->i_op = NULL; - vi->i_fop = NULL; vi->i_mapping->a_ops = &ntfs_mst_aops; vi->i_blocks = ni->allocated_size >> 9; /* @@ -1661,7 +1716,6 @@ skip_large_index_stuff: ntfs_debug("Done."); return 0; - iput_unm_err_out: iput(bvi); unm_err_out: @@ -1681,6 +1735,15 @@ err_out: return err; } +/* + * The MFT inode has special locking, so teach the lock validator + * about this by splitting off the locking rules of the MFT from + * the locking rules of other inodes. The MFT inode can never be + * accessed from the VFS side (or even internally), only by the + * map_mft functions. + */ +static struct lock_class_key mft_ni_runlist_lock_key, mft_ni_mrec_lock_key; + /** * ntfs_read_inode_mount - special read_inode for mount time use only * @vi: inode to read @@ -1809,19 +1872,33 @@ int ntfs_read_inode_mount(struct inode *vi) } else /* if (!err) */ { ATTR_LIST_ENTRY *al_entry, *next_al_entry; u8 *al_end; + static const char *es = " Not allowed. $MFT is corrupt. " + "You should run chkdsk."; ntfs_debug("Attribute list attribute found in $MFT."); NInoSetAttrList(ni); a = ctx->attr; - if (a->flags & ATTR_IS_ENCRYPTED || - a->flags & ATTR_COMPRESSION_MASK || - a->flags & ATTR_IS_SPARSE) { + if (a->flags & ATTR_COMPRESSION_MASK) { ntfs_error(sb, "Attribute list attribute is " - "compressed/encrypted/sparse. Not " - "allowed. $MFT is corrupt. You should " - "run chkdsk."); + "compressed.%s", es); goto put_err_out; } + if (a->flags & ATTR_IS_ENCRYPTED || + a->flags & ATTR_IS_SPARSE) { + if (a->non_resident) { + ntfs_error(sb, "Non-resident attribute list " + "attribute is encrypted/" + "sparse.%s", es); + goto put_err_out; + } + ntfs_warning(sb, "Resident attribute list attribute " + "in $MFT system file is marked " + "encrypted/sparse which is not true. " + "However, Windows allows this and " + "chkdsk does not detect or correct it " + "so we will just ignore the invalid " + "flags and pretend they are not set."); + } /* Now allocate memory for the attribute list. */ ni->attr_list_size = (u32)ntfs_attr_size(a); ni->attr_list = ntfs_malloc_nofs(ni->attr_list_size); @@ -1904,8 +1981,7 @@ int ntfs_read_inode_mount(struct inode *vi) goto em_put_err_out; next_al_entry = (ATTR_LIST_ENTRY*)((u8*)al_entry + le16_to_cpu(al_entry->length)); - if (le32_to_cpu(al_entry->type) > - const_le32_to_cpu(AT_DATA)) + if (le32_to_cpu(al_entry->type) > le32_to_cpu(AT_DATA)) goto em_put_err_out; if (AT_DATA != al_entry->type) continue; @@ -2047,7 +2123,8 @@ int ntfs_read_inode_mount(struct inode *vi) * ntfs_read_inode() will have set up the default ones. */ /* Set uid and gid to root. */ - vi->i_uid = vi->i_gid = 0; + vi->i_uid = GLOBAL_ROOT_UID; + vi->i_gid = GLOBAL_ROOT_GID; /* Regular file. No access for anyone. */ vi->i_mode = S_IFREG; /* No VFS initiated operations allowed for $MFT. */ @@ -2093,6 +2170,14 @@ int ntfs_read_inode_mount(struct inode *vi) ntfs_attr_put_search_ctx(ctx); ntfs_debug("Done."); ntfs_free(m); + + /* + * Split the locking rules of the MFT inode from the + * locking rules of other inodes: + */ + lockdep_set_class(&ni->runlist.lock, &mft_ni_runlist_lock_key); + lockdep_set_class(&ni->mrec_lock, &mft_ni_mrec_lock_key); + return 0; em_put_err_out: @@ -2107,37 +2192,6 @@ err_out: return -1; } -/** - * ntfs_put_inode - handler for when the inode reference count is decremented - * @vi: vfs inode - * - * The VFS calls ntfs_put_inode() every time the inode reference count (i_count) - * is about to be decremented (but before the decrement itself. - * - * If the inode @vi is a directory with two references, one of which is being - * dropped, we need to put the attribute inode for the directory index bitmap, - * if it is present, otherwise the directory inode would remain pinned for - * ever. - */ -void ntfs_put_inode(struct inode *vi) -{ - if (S_ISDIR(vi->i_mode) && atomic_read(&vi->i_count) == 2) { - ntfs_inode *ni = NTFS_I(vi); - if (NInoIndexAllocPresent(ni)) { - struct inode *bvi = NULL; - down(&vi->i_sem); - if (atomic_read(&vi->i_count) == 2) { - bvi = ni->itype.index.bmp_ino; - if (bvi) - ni->itype.index.bmp_ino = NULL; - } - up(&vi->i_sem); - if (bvi) - iput(bvi); - } - } -} - static void __ntfs_clear_inode(ntfs_inode *ni) { /* Free all alocated memory. */ @@ -2190,7 +2244,7 @@ void ntfs_clear_extent_inode(ntfs_inode *ni) } /** - * ntfs_clear_big_inode - clean up the ntfs specific part of an inode + * ntfs_evict_big_inode - clean up the ntfs specific part of an inode * @vi: vfs inode pending annihilation * * When the VFS is going to remove an inode from memory, ntfs_clear_big_inode() @@ -2199,25 +2253,16 @@ void ntfs_clear_extent_inode(ntfs_inode *ni) * * If the MFT record is dirty, we commit it before doing anything else. */ -void ntfs_clear_big_inode(struct inode *vi) +void ntfs_evict_big_inode(struct inode *vi) { ntfs_inode *ni = NTFS_I(vi); - /* - * If the inode @vi is an index inode we need to put the attribute - * inode for the index bitmap, if it is present, otherwise the index - * inode would disappear and the attribute inode for the index bitmap - * would no longer be referenced from anywhere and thus it would remain - * pinned for ever. - */ - if (NInoAttr(ni) && (ni->type == AT_INDEX_ALLOCATION) && - NInoIndexAllocPresent(ni) && ni->itype.index.bmp_ino) { - iput(ni->itype.index.bmp_ino); - ni->itype.index.bmp_ino = NULL; - } + truncate_inode_pages_final(&vi->i_data); + clear_inode(vi); + #ifdef NTFS_RW if (NInoDirty(ni)) { - BOOL was_bad = (is_bad_inode(vi)); + bool was_bad = (is_bad_inode(vi)); /* Committing the inode also commits all extent inodes. */ ntfs_commit_inode(vi); @@ -2255,20 +2300,20 @@ void ntfs_clear_big_inode(struct inode *vi) /** * ntfs_show_options - show mount options in /proc/mounts * @sf: seq_file in which to write our mount options - * @mnt: vfs mount whose mount options to display + * @root: root of the mounted tree whose mount options to display * * Called by the VFS once for each mounted ntfs volume when someone reads * /proc/mounts in order to display the NTFS specific mount options of each - * mount. The mount options of the vfs mount @mnt are written to the seq file + * mount. The mount options of fs specified by @root are written to the seq file * @sf and success is returned. */ -int ntfs_show_options(struct seq_file *sf, struct vfsmount *mnt) +int ntfs_show_options(struct seq_file *sf, struct dentry *root) { - ntfs_volume *vol = NTFS_SB(mnt->mnt_sb); + ntfs_volume *vol = NTFS_SB(root->d_sb); int i; - seq_printf(sf, ",uid=%i", vol->uid); - seq_printf(sf, ",gid=%i", vol->gid); + seq_printf(sf, ",uid=%i", from_kuid_munged(&init_user_ns, vol->uid)); + seq_printf(sf, ",gid=%i", from_kgid_munged(&init_user_ns, vol->gid)); if (vol->fmask == vol->dmask) seq_printf(sf, ",umask=0%o", vol->fmask); else { @@ -2311,12 +2356,7 @@ static const char *es = " Leaving inconsistent metadata. Unmount and run " * * Returns 0 on success or -errno on error. * - * Called with ->i_sem held. In all but one case ->i_alloc_sem is held for - * writing. The only case in the kernel where ->i_alloc_sem is not held is - * mm/filemap.c::generic_file_buffered_write() where vmtruncate() is called - * with the current i_size as the offset. The analogous place in NTFS is in - * fs/ntfs/file.c::ntfs_file_buffered_write() where we call vmtruncate() again - * without holding ->i_alloc_sem. + * Called with ->i_mutex held. */ int ntfs_truncate(struct inode *vi) { @@ -2460,8 +2500,6 @@ retry_truncate: /* Resize the attribute record to best fit the new attribute size. */ if (new_size < vol->mft_record_size && !ntfs_resident_attr_value_resize(m, a, new_size)) { - unsigned long flags; - /* The resize succeeded! */ flush_dcache_mft_record_page(ctx->ntfs_ino); mark_mft_record_dirty(ctx->ntfs_ino); @@ -2485,7 +2523,7 @@ retry_truncate: * specifies that the behaviour is unspecified thus we do not * have to do anything. This means that in our implementation * in the rare case that the file is mmap()ped and a write - * occured into the mmap()ped region just beyond the file size + * occurred into the mmap()ped region just beyond the file size * and writepage has not yet been called to write out the page * (which would clear the area beyond the file size) and we now * extend the file size to incorporate this dirty region @@ -2767,7 +2805,25 @@ unm_done: up_write(&ni->runlist.lock); done: /* Update the mtime and ctime on the base inode. */ - inode_update_time(VFS_I(base_ni), 1); + /* normally ->truncate shouldn't update ctime or mtime, + * but ntfs did before so it got a copy & paste version + * of file_update_time. one day someone should fix this + * for real. + */ + if (!IS_NOCMTIME(VFS_I(base_ni)) && !IS_RDONLY(VFS_I(base_ni))) { + struct timespec now = current_fs_time(VFS_I(base_ni)->i_sb); + int sync_it = 0; + + if (!timespec_equal(&VFS_I(base_ni)->i_mtime, &now) || + !timespec_equal(&VFS_I(base_ni)->i_ctime, &now)) + sync_it = 1; + VFS_I(base_ni)->i_mtime = now; + VFS_I(base_ni)->i_ctime = now; + + if (sync_it) + mark_inode_dirty_sync(VFS_I(base_ni)); + } + if (likely(!err)) { NInoClearTruncateFailed(ni); ntfs_debug("Done."); @@ -2776,11 +2832,8 @@ done: old_bad_out: old_size = -1; bad_out: - if (err != -ENOMEM && err != -EOPNOTSUPP) { - make_bad_inode(vi); - make_bad_inode(VFS_I(base_ni)); + if (err != -ENOMEM && err != -EOPNOTSUPP) NVolSetErrors(vol); - } if (err != -EOPNOTSUPP) NInoSetTruncateFailed(ni); else if (old_size >= 0) @@ -2795,11 +2848,8 @@ out: ntfs_debug("Failed. Returning error code %i.", err); return err; conv_err_out: - if (err != -ENOMEM && err != -EOPNOTSUPP) { - make_bad_inode(vi); - make_bad_inode(VFS_I(base_ni)); + if (err != -ENOMEM && err != -EOPNOTSUPP) NVolSetErrors(vol); - } if (err != -EOPNOTSUPP) NInoSetTruncateFailed(ni); else @@ -2815,9 +2865,11 @@ conv_err_out: * * See ntfs_truncate() description above for details. */ +#ifdef NTFS_RW void ntfs_truncate_vfs(struct inode *vi) { ntfs_truncate(vi); } +#endif /** * ntfs_setattr - called from notify_change() when an attribute is being changed @@ -2831,11 +2883,7 @@ void ntfs_truncate_vfs(struct inode *vi) { * We also abort all changes of user, group, and mode as we do not implement * the NTFS ACLs yet. * - * Called with ->i_sem held. For the ATTR_SIZE (i.e. ->truncate) case, also - * called with ->i_alloc_sem held for writing. - * - * Basically this is a copy of generic notify_change() and inode_setattr() - * functionality, except we intercept and abort changes in i_size. + * Called with ->i_mutex held. */ int ntfs_setattr(struct dentry *dentry, struct iattr *attr) { @@ -2867,8 +2915,10 @@ int ntfs_setattr(struct dentry *dentry, struct iattr *attr) NInoCompressed(ni) ? "compressed" : "encrypted"); err = -EOPNOTSUPP; - } else - err = vmtruncate(vi, attr->ia_size); + } else { + truncate_setsize(vi, attr->ia_size); + ntfs_truncate_vfs(vi); + } if (err || ia_valid == ATTR_SIZE) goto out; } else { @@ -2911,7 +2961,7 @@ out: * * Return 0 on success and -errno on error. */ -int ntfs_write_inode(struct inode *vi, int sync) +int __ntfs_write_inode(struct inode *vi, int sync) { sle64 nt; ntfs_inode *ni = NTFS_I(vi); @@ -2919,7 +2969,7 @@ int ntfs_write_inode(struct inode *vi, int sync) MFT_RECORD *m; STANDARD_INFORMATION *si; int err = 0; - BOOL modified = FALSE; + bool modified = false; ntfs_debug("Entering for %sinode 0x%lx.", NInoAttr(ni) ? "attr " : "", vi->i_ino); @@ -2961,7 +3011,7 @@ int ntfs_write_inode(struct inode *vi, int sync) sle64_to_cpu(si->last_data_change_time), (long long)sle64_to_cpu(nt)); si->last_data_change_time = nt; - modified = TRUE; + modified = true; } nt = utc2ntfs(vi->i_ctime); if (si->last_mft_change_time != nt) { @@ -2970,7 +3020,7 @@ int ntfs_write_inode(struct inode *vi, int sync) sle64_to_cpu(si->last_mft_change_time), (long long)sle64_to_cpu(nt)); si->last_mft_change_time = nt; - modified = TRUE; + modified = true; } nt = utc2ntfs(vi->i_atime); if (si->last_access_time != nt) { @@ -2979,7 +3029,7 @@ int ntfs_write_inode(struct inode *vi, int sync) (long long)sle64_to_cpu(si->last_access_time), (long long)sle64_to_cpu(nt)); si->last_access_time = nt; - modified = TRUE; + modified = true; } /* * If we just modified the standard information attribute we need to @@ -2997,15 +3047,18 @@ int ntfs_write_inode(struct inode *vi, int sync) * record will be cleaned and written out to disk below, i.e. before * this function returns. */ - if (modified && !NInoTestSetDirty(ctx->ntfs_ino)) - mark_ntfs_record_dirty(ctx->ntfs_ino->page, - ctx->ntfs_ino->page_ofs); + if (modified) { + flush_dcache_mft_record_page(ctx->ntfs_ino); + if (!NInoTestSetDirty(ctx->ntfs_ino)) + mark_ntfs_record_dirty(ctx->ntfs_ino->page, + ctx->ntfs_ino->page_ofs); + } ntfs_attr_put_search_ctx(ctx); /* Now the access times are updated, write the base mft record. */ if (NInoDirty(ni)) err = write_mft_record(ni, m, sync); /* Write all attached extent mft records. */ - down(&ni->extent_lock); + mutex_lock(&ni->extent_lock); if (ni->nr_extents > 0) { ntfs_inode **extent_nis = ni->ext.extent_ntfs_inos; int i; @@ -3032,7 +3085,7 @@ int ntfs_write_inode(struct inode *vi, int sync) } } } - up(&ni->extent_lock); + mutex_unlock(&ni->extent_lock); unmap_mft_record(ni); if (unlikely(err)) goto err_out; @@ -3047,9 +3100,7 @@ err_out: "retries later."); mark_inode_dirty(vi); } else { - ntfs_error(vi->i_sb, "Failed (error code %i): Marking inode " - "as bad. You should run chkdsk.", -err); - make_bad_inode(vi); + ntfs_error(vi->i_sb, "Failed (error %i): Run chkdsk.", -err); NVolSetErrors(ni->vol); } return err; |