/**
* attrib.c - NTFS attribute operations. Part of the Linux-NTFS project.
*
- * Copyright (c) 2001-2005 Anton Altaparmakov
+ * Copyright (c) 2001-2007 Anton Altaparmakov
* Copyright (c) 2002 Richard Russon
*
* This program/include file is free software; you can redistribute it and/or
*/
#include <linux/buffer_head.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
#include <linux/swap.h>
+#include <linux/writeback.h>
#include "attrib.h"
#include "debug.h"
* the attribute has zero allocated size, i.e. there simply is no runlist.
*
* WARNING: If @ctx is supplied, regardless of whether success or failure is
- * returned, you need to check IS_ERR(@ctx->mrec) and if TRUE the @ctx
+ * returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx
* is no longer valid, i.e. you need to either call
* ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
* In that case PTR_ERR(@ctx->mrec) will give you the error code for
runlist_element *rl;
struct page *put_this_page = NULL;
int err = 0;
- BOOL ctx_is_temporary, ctx_needs_reset;
- ntfs_attr_search_ctx old_ctx;
+ bool ctx_is_temporary, ctx_needs_reset;
+ ntfs_attr_search_ctx old_ctx = { NULL, };
ntfs_debug("Mapping runlist part containing vcn 0x%llx.",
(unsigned long long)vcn);
else
base_ni = ni->ext.base_ntfs_ino;
if (!ctx) {
- ctx_is_temporary = ctx_needs_reset = TRUE;
+ ctx_is_temporary = ctx_needs_reset = true;
m = map_mft_record(base_ni);
if (IS_ERR(m))
return PTR_ERR(m);
BUG_ON(IS_ERR(ctx->mrec));
a = ctx->attr;
BUG_ON(!a->non_resident);
- ctx_is_temporary = FALSE;
+ ctx_is_temporary = false;
end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
read_lock_irqsave(&ni->size_lock, flags);
allocated_size_vcn = ni->allocated_size >>
ni->name, ni->name_len) &&
sle64_to_cpu(a->data.non_resident.lowest_vcn)
<= vcn && end_vcn >= vcn))
- ctx_needs_reset = FALSE;
+ ctx_needs_reset = false;
else {
/* Save the old search context. */
old_ctx = *ctx;
* needed attribute extent.
*/
ntfs_attr_reinit_search_ctx(ctx);
- ctx_needs_reset = TRUE;
+ ctx_needs_reset = true;
}
}
if (ctx_needs_reset) {
* ntfs_mapping_pairs_decompress() fails.
*/
end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn) + 1;
- if (!a->data.non_resident.lowest_vcn && end_vcn == 1)
- end_vcn = sle64_to_cpu(a->data.non_resident.allocated_size) >>
- ni->vol->cluster_size_bits;
- if (unlikely(vcn >= end_vcn)) {
+ if (unlikely(vcn && vcn >= end_vcn)) {
err = -ENOENT;
goto err_out;
}
* LCN_EIO Critical error (runlist/file is corrupt, i/o error, etc).
*
* Locking: - The runlist must be locked on entry and is left locked on return.
- * - If @write_locked is FALSE, i.e. the runlist is locked for reading,
+ * - If @write_locked is 'false', i.e. the runlist is locked for reading,
* the lock may be dropped inside the function so you cannot rely on
* the runlist still being the same when this function returns.
*/
LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn,
- const BOOL write_locked)
+ const bool write_locked)
{
LCN lcn;
unsigned long flags;
- BOOL is_retry = FALSE;
+ bool is_retry = false;
ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, %s_locked.",
ni->mft_no, (unsigned long long)vcn,
down_read(&ni->runlist.lock);
}
if (likely(!err)) {
- is_retry = TRUE;
+ is_retry = true;
goto retry_remap;
}
if (err == -ENOENT)
* -EIO - Critical error (runlist/file is corrupt, i/o error, etc).
*
* WARNING: If @ctx is supplied, regardless of whether success or failure is
- * returned, you need to check IS_ERR(@ctx->mrec) and if TRUE the @ctx
+ * returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx
* is no longer valid, i.e. you need to either call
* ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
* In that case PTR_ERR(@ctx->mrec) will give you the error code for
unsigned long flags;
runlist_element *rl;
int err = 0;
- BOOL is_retry = FALSE;
+ bool is_retry = false;
ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, with%s ctx.",
ni->mft_no, (unsigned long long)vcn, ctx ? "" : "out");
*/
err = ntfs_map_runlist_nolock(ni, vcn, ctx);
if (likely(!err)) {
- is_retry = TRUE;
+ is_retry = true;
goto retry_remap;
}
}
* On actual error, ntfs_attr_find() returns -EIO. In this case @ctx->attr is
* undefined and in particular do not rely on it not changing.
*
- * If @ctx->is_first is TRUE, the search begins with @ctx->attr itself. If it
- * is FALSE, the search begins after @ctx->attr.
+ * If @ctx->is_first is 'true', the search begins with @ctx->attr itself. If it
+ * is 'false', the search begins after @ctx->attr.
*
* If @ic is IGNORE_CASE, the @name comparisson is not case sensitive and
* @ctx->ntfs_ino must be set to the ntfs inode to which the mft record
/*
* Iterate over attributes in mft record starting at @ctx->attr, or the
- * attribute following that, if @ctx->is_first is TRUE.
+ * attribute following that, if @ctx->is_first is 'true'.
*/
if (ctx->is_first) {
a = ctx->attr;
- ctx->is_first = FALSE;
+ ctx->is_first = false;
} else
a = (ATTR_RECORD*)((u8*)ctx->attr +
le32_to_cpu(ctx->attr->length));
ctx->al_entry = (ATTR_LIST_ENTRY*)al_start;
/*
* Iterate over entries in attribute list starting at @ctx->al_entry,
- * or the entry following that, if @ctx->is_first is TRUE.
+ * or the entry following that, if @ctx->is_first is 'true'.
*/
if (ctx->is_first) {
al_entry = ctx->al_entry;
- ctx->is_first = FALSE;
+ ctx->is_first = false;
} else
al_entry = (ATTR_LIST_ENTRY*)((u8*)ctx->al_entry +
le16_to_cpu(ctx->al_entry->length));
le32_to_cpu(ctx->mrec->bytes_allocated))
break;
if (a->type == AT_END)
- continue;
+ break;
if (!a->length)
break;
if (al_entry->instance != a->instance)
ctx->mrec = ctx->base_mrec;
ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
le16_to_cpu(ctx->mrec->attrs_offset));
- ctx->is_first = TRUE;
+ ctx->is_first = true;
ctx->ntfs_ino = base_ni;
ctx->base_ntfs_ino = NULL;
ctx->base_mrec = NULL;
/* Sanity checks are performed elsewhere. */
.attr = (ATTR_RECORD*)((u8*)mrec +
le16_to_cpu(mrec->attrs_offset)),
- .is_first = TRUE,
+ .is_first = true,
.ntfs_ino = ni,
};
}
{
if (likely(!ctx->base_ntfs_ino)) {
/* No attribute list. */
- ctx->is_first = TRUE;
+ ctx->is_first = true;
/* Sanity checks are performed elsewhere. */
ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
le16_to_cpu(ctx->mrec->attrs_offset));
{
ntfs_attr_search_ctx *ctx;
- ctx = kmem_cache_alloc(ntfs_attr_ctx_cache, SLAB_NOFS);
+ ctx = kmem_cache_alloc(ntfs_attr_ctx_cache, GFP_NOFS);
if (ctx)
ntfs_attr_init_search_ctx(ctx, ni, mrec);
return ctx;
*/
int ntfs_attr_can_be_resident(const ntfs_volume *vol, const ATTR_TYPE type)
{
- if (type == AT_INDEX_ALLOCATION || type == AT_EA)
+ if (type == AT_INDEX_ALLOCATION)
return -EPERM;
return 0;
}
/**
* ntfs_attr_make_non_resident - convert a resident to a non-resident attribute
* @ni: ntfs inode describing the attribute to convert
+ * @data_size: size of the resident data to copy to the non-resident attribute
*
* Convert the resident ntfs attribute described by the ntfs inode @ni to a
* non-resident one.
*
+ * @data_size must be equal to the attribute value size. This is needed since
+ * we need to know the size before we can map the mft record and our callers
+ * always know it. The reason we cannot simply read the size from the vfs
+ * inode i_size is that this is not necessarily uptodate. This happens when
+ * ntfs_attr_make_non_resident() is called in the ->truncate call path(s).
+ *
* Return 0 on success and -errno on error. The following error return codes
* are defined:
* -EPERM - The attribute is not allowed to be non-resident.
* NOTE to self: No changes in the attribute list are required to move from
* a resident to a non-resident attribute.
*
- * Locking: - The caller must hold i_sem on the inode.
+ * Locking: - The caller must hold i_mutex on the inode.
*/
-int ntfs_attr_make_non_resident(ntfs_inode *ni)
+int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size)
{
s64 new_size;
struct inode *vi = VFS_I(ni);
* The size needs to be aligned to a cluster boundary for allocation
* purposes.
*/
- new_size = (i_size_read(vi) + vol->cluster_size - 1) &
+ new_size = (data_size + vol->cluster_size - 1) &
~(vol->cluster_size - 1);
if (new_size > 0) {
- runlist_element *rl2;
-
/*
* Will need the page later and since the page lock nests
* outside all ntfs locks, we need to get the page now.
return -ENOMEM;
/* Start by allocating clusters to hold the attribute value. */
rl = ntfs_cluster_alloc(vol, 0, new_size >>
- vol->cluster_size_bits, -1, DATA_ZONE);
+ vol->cluster_size_bits, -1, DATA_ZONE, true);
if (IS_ERR(rl)) {
err = PTR_ERR(rl);
ntfs_debug("Failed to allocate cluster%s, error code "
err);
goto page_err_out;
}
- /* Change the runlist terminator to LCN_ENOENT. */
- rl2 = rl;
- while (rl2->length)
- rl2++;
- BUG_ON(rl2->lcn != LCN_RL_NOT_MAPPED);
- rl2->lcn = LCN_ENOENT;
} else {
rl = NULL;
page = NULL;
* attribute value.
*/
attr_size = le32_to_cpu(a->data.resident.value_length);
- BUG_ON(attr_size != i_size_read(vi));
+ BUG_ON(attr_size != data_size);
if (page && !PageUptodate(page)) {
kaddr = kmap_atomic(page, KM_USER0);
memcpy(kaddr, (u8*)a +
a->data.non_resident.initialized_size =
cpu_to_sle64(attr_size);
if (NInoSparse(ni) || NInoCompressed(ni)) {
- a->data.non_resident.compression_unit = 4;
+ a->data.non_resident.compression_unit = 0;
+ if (NInoCompressed(ni) || vol->major_ver < 3)
+ a->data.non_resident.compression_unit = 4;
a->data.non_resident.compressed_size =
a->data.non_resident.allocated_size;
} else
ni->allocated_size = new_size;
if (NInoSparse(ni) || NInoCompressed(ni)) {
ni->itype.compressed.size = ni->allocated_size;
- 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;
- }
+ 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;
+ }
+ vi->i_blocks = ni->itype.compressed.size >> 9;
+ } else
+ vi->i_blocks = ni->allocated_size >> 9;
write_unlock_irqrestore(&ni->size_lock, flags);
/*
* This needs to be last since the address space operations ->readpage
* and ->writepage can run concurrently with us as they are not
- * serialized on i_sem. Note, we are not allowed to fail once we flip
+ * serialized on i_mutex. Note, we are not allowed to fail once we flip
* this switch, which is another reason to do this last.
*/
NInoSetNonResident(ni);
}
/**
+ * ntfs_attr_extend_allocation - extend the allocated space of an attribute
+ * @ni: ntfs inode of the attribute whose allocation to extend
+ * @new_alloc_size: new size in bytes to which to extend the allocation to
+ * @new_data_size: new size in bytes to which to extend the data to
+ * @data_start: beginning of region which is required to be non-sparse
+ *
+ * Extend the allocated space of an attribute described by the ntfs inode @ni
+ * to @new_alloc_size bytes. If @data_start is -1, the whole extension may be
+ * implemented as a hole in the file (as long as both the volume and the ntfs
+ * inode @ni have sparse support enabled). If @data_start is >= 0, then the
+ * region between the old allocated size and @data_start - 1 may be made sparse
+ * but the regions between @data_start and @new_alloc_size must be backed by
+ * actual clusters.
+ *
+ * If @new_data_size is -1, it is ignored. If it is >= 0, then the data size
+ * of the attribute is extended to @new_data_size. Note that the i_size of the
+ * vfs inode is not updated. Only the data size in the base attribute record
+ * is updated. The caller has to update i_size separately if this is required.
+ * WARNING: It is a BUG() for @new_data_size to be smaller than the old data
+ * size as well as for @new_data_size to be greater than @new_alloc_size.
+ *
+ * For resident attributes this involves resizing the attribute record and if
+ * necessary moving it and/or other attributes into extent mft records and/or
+ * converting the attribute to a non-resident attribute which in turn involves
+ * extending the allocation of a non-resident attribute as described below.
+ *
+ * For non-resident attributes this involves allocating clusters in the data
+ * zone on the volume (except for regions that are being made sparse) and
+ * extending the run list to describe the allocated clusters as well as
+ * updating the mapping pairs array of the attribute. This in turn involves
+ * resizing the attribute record and if necessary moving it and/or other
+ * attributes into extent mft records and/or splitting the attribute record
+ * into multiple extent attribute records.
+ *
+ * Also, the attribute list attribute is updated if present and in some of the
+ * above cases (the ones where extent mft records/attributes come into play),
+ * an attribute list attribute is created if not already present.
+ *
+ * Return the new allocated size on success and -errno on error. In the case
+ * that an error is encountered but a partial extension at least up to
+ * @data_start (if present) is possible, the allocation is partially extended
+ * and this is returned. This means the caller must check the returned size to
+ * determine if the extension was partial. If @data_start is -1 then partial
+ * allocations are not performed.
+ *
+ * WARNING: Do not call ntfs_attr_extend_allocation() for $MFT/$DATA.
+ *
+ * Locking: This function takes the runlist lock of @ni for writing as well as
+ * locking the mft record of the base ntfs inode. These locks are maintained
+ * throughout execution of the function. These locks are required so that the
+ * attribute can be resized safely and so that it can for example be converted
+ * from resident to non-resident safely.
+ *
+ * TODO: At present attribute list attribute handling is not implemented.
+ *
+ * TODO: At present it is not safe to call this function for anything other
+ * than the $DATA attribute(s) of an uncompressed and unencrypted file.
+ */
+s64 ntfs_attr_extend_allocation(ntfs_inode *ni, s64 new_alloc_size,
+ const s64 new_data_size, const s64 data_start)
+{
+ VCN vcn;
+ s64 ll, allocated_size, start = data_start;
+ struct inode *vi = VFS_I(ni);
+ ntfs_volume *vol = ni->vol;
+ ntfs_inode *base_ni;
+ MFT_RECORD *m;
+ ATTR_RECORD *a;
+ ntfs_attr_search_ctx *ctx;
+ runlist_element *rl, *rl2;
+ unsigned long flags;
+ int err, mp_size;
+ u32 attr_len = 0; /* Silence stupid gcc warning. */
+ bool mp_rebuilt;
+
+#ifdef DEBUG
+ read_lock_irqsave(&ni->size_lock, flags);
+ allocated_size = ni->allocated_size;
+ read_unlock_irqrestore(&ni->size_lock, flags);
+ ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, "
+ "old_allocated_size 0x%llx, "
+ "new_allocated_size 0x%llx, new_data_size 0x%llx, "
+ "data_start 0x%llx.", vi->i_ino,
+ (unsigned)le32_to_cpu(ni->type),
+ (unsigned long long)allocated_size,
+ (unsigned long long)new_alloc_size,
+ (unsigned long long)new_data_size,
+ (unsigned long long)start);
+#endif
+retry_extend:
+ /*
+ * For non-resident attributes, @start and @new_size need to be aligned
+ * to cluster boundaries for allocation purposes.
+ */
+ if (NInoNonResident(ni)) {
+ if (start > 0)
+ start &= ~(s64)vol->cluster_size_mask;
+ new_alloc_size = (new_alloc_size + vol->cluster_size - 1) &
+ ~(s64)vol->cluster_size_mask;
+ }
+ BUG_ON(new_data_size >= 0 && new_data_size > new_alloc_size);
+ /* Check if new size is allowed in $AttrDef. */
+ err = ntfs_attr_size_bounds_check(vol, ni->type, new_alloc_size);
+ if (unlikely(err)) {
+ /* Only emit errors when the write will fail completely. */
+ read_lock_irqsave(&ni->size_lock, flags);
+ allocated_size = ni->allocated_size;
+ read_unlock_irqrestore(&ni->size_lock, flags);
+ if (start < 0 || start >= allocated_size) {
+ if (err == -ERANGE) {
+ ntfs_error(vol->sb, "Cannot extend allocation "
+ "of inode 0x%lx, attribute "
+ "type 0x%x, because the new "
+ "allocation would exceed the "
+ "maximum allowed size for "
+ "this attribute type.",
+ vi->i_ino, (unsigned)
+ le32_to_cpu(ni->type));
+ } else {
+ ntfs_error(vol->sb, "Cannot extend allocation "
+ "of inode 0x%lx, attribute "
+ "type 0x%x, because this "
+ "attribute type is not "
+ "defined on the NTFS volume. "
+ "Possible corruption! You "
+ "should run chkdsk!",
+ vi->i_ino, (unsigned)
+ le32_to_cpu(ni->type));
+ }
+ }
+ /* Translate error code to be POSIX conformant for write(2). */
+ if (err == -ERANGE)
+ err = -EFBIG;
+ else
+ err = -EIO;
+ return err;
+ }
+ if (!NInoAttr(ni))
+ base_ni = ni;
+ else
+ base_ni = ni->ext.base_ntfs_ino;
+ /*
+ * We will be modifying both the runlist (if non-resident) and the mft
+ * record so lock them both down.
+ */
+ down_write(&ni->runlist.lock);
+ m = map_mft_record(base_ni);
+ if (IS_ERR(m)) {
+ err = PTR_ERR(m);
+ m = NULL;
+ ctx = NULL;
+ goto err_out;
+ }
+ ctx = ntfs_attr_get_search_ctx(base_ni, m);
+ if (unlikely(!ctx)) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+ read_lock_irqsave(&ni->size_lock, flags);
+ allocated_size = ni->allocated_size;
+ read_unlock_irqrestore(&ni->size_lock, flags);
+ /*
+ * If non-resident, seek to the last extent. If resident, there is
+ * only one extent, so seek to that.
+ */
+ vcn = NInoNonResident(ni) ? allocated_size >> vol->cluster_size_bits :
+ 0;
+ /*
+ * Abort if someone did the work whilst we waited for the locks. If we
+ * just converted the attribute from resident to non-resident it is
+ * likely that exactly this has happened already. We cannot quite
+ * abort if we need to update the data size.
+ */
+ if (unlikely(new_alloc_size <= allocated_size)) {
+ ntfs_debug("Allocated size already exceeds requested size.");
+ new_alloc_size = allocated_size;
+ if (new_data_size < 0)
+ goto done;
+ /*
+ * We want the first attribute extent so that we can update the
+ * data size.
+ */
+ vcn = 0;
+ }
+ err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
+ CASE_SENSITIVE, vcn, NULL, 0, ctx);
+ if (unlikely(err)) {
+ if (err == -ENOENT)
+ err = -EIO;
+ goto err_out;
+ }
+ m = ctx->mrec;
+ a = ctx->attr;
+ /* Use goto to reduce indentation. */
+ if (a->non_resident)
+ goto do_non_resident_extend;
+ BUG_ON(NInoNonResident(ni));
+ /* The total length of the attribute value. */
+ attr_len = le32_to_cpu(a->data.resident.value_length);
+ /*
+ * Extend the attribute record to be able to store the new attribute
+ * size. ntfs_attr_record_resize() will not do anything if the size is
+ * not changing.
+ */
+ if (new_alloc_size < vol->mft_record_size &&
+ !ntfs_attr_record_resize(m, a,
+ le16_to_cpu(a->data.resident.value_offset) +
+ new_alloc_size)) {
+ /* The resize succeeded! */
+ write_lock_irqsave(&ni->size_lock, flags);
+ ni->allocated_size = le32_to_cpu(a->length) -
+ le16_to_cpu(a->data.resident.value_offset);
+ write_unlock_irqrestore(&ni->size_lock, flags);
+ if (new_data_size >= 0) {
+ BUG_ON(new_data_size < attr_len);
+ a->data.resident.value_length =
+ cpu_to_le32((u32)new_data_size);
+ }
+ goto flush_done;
+ }
+ /*
+ * We have to drop all the locks so we can call
+ * ntfs_attr_make_non_resident(). This could be optimised by try-
+ * locking the first page cache page and only if that fails dropping
+ * the locks, locking the page, and redoing all the locking and
+ * lookups. While this would be a huge optimisation, it is not worth
+ * it as this is definitely a slow code path.
+ */
+ ntfs_attr_put_search_ctx(ctx);
+ unmap_mft_record(base_ni);
+ up_write(&ni->runlist.lock);
+ /*
+ * Not enough space in the mft record, try to make the attribute
+ * non-resident and if successful restart the extension process.
+ */
+ err = ntfs_attr_make_non_resident(ni, attr_len);
+ if (likely(!err))
+ goto retry_extend;
+ /*
+ * Could not make non-resident. If this is due to this not being
+ * permitted for this attribute type or there not being enough space,
+ * try to make other attributes non-resident. Otherwise fail.
+ */
+ if (unlikely(err != -EPERM && err != -ENOSPC)) {
+ /* Only emit errors when the write will fail completely. */
+ read_lock_irqsave(&ni->size_lock, flags);
+ allocated_size = ni->allocated_size;
+ read_unlock_irqrestore(&ni->size_lock, flags);
+ if (start < 0 || start >= allocated_size)
+ ntfs_error(vol->sb, "Cannot extend allocation of "
+ "inode 0x%lx, attribute type 0x%x, "
+ "because the conversion from resident "
+ "to non-resident attribute failed "
+ "with error code %i.", vi->i_ino,
+ (unsigned)le32_to_cpu(ni->type), err);
+ if (err != -ENOMEM)
+ err = -EIO;
+ goto conv_err_out;
+ }
+ /* TODO: Not implemented from here, abort. */
+ read_lock_irqsave(&ni->size_lock, flags);
+ allocated_size = ni->allocated_size;
+ read_unlock_irqrestore(&ni->size_lock, flags);
+ if (start < 0 || start >= allocated_size) {
+ if (err == -ENOSPC)
+ ntfs_error(vol->sb, "Not enough space in the mft "
+ "record/on disk for the non-resident "
+ "attribute value. This case is not "
+ "implemented yet.");
+ else /* if (err == -EPERM) */
+ ntfs_error(vol->sb, "This attribute type may not be "
+ "non-resident. This case is not "
+ "implemented yet.");
+ }
+ err = -EOPNOTSUPP;
+ goto conv_err_out;
+#if 0
+ // TODO: Attempt to make other attributes non-resident.
+ if (!err)
+ goto do_resident_extend;
+ /*
+ * Both the attribute list attribute and the standard information
+ * attribute must remain in the base inode. Thus, if this is one of
+ * these attributes, we have to try to move other attributes out into
+ * extent mft records instead.
+ */
+ if (ni->type == AT_ATTRIBUTE_LIST ||
+ ni->type == AT_STANDARD_INFORMATION) {
+ // TODO: Attempt to move other attributes into extent mft
+ // records.
+ err = -EOPNOTSUPP;
+ if (!err)
+ goto do_resident_extend;
+ goto err_out;
+ }
+ // TODO: Attempt to move this attribute to an extent mft record, but
+ // only if it is not already the only attribute in an mft record in
+ // which case there would be nothing to gain.
+ err = -EOPNOTSUPP;
+ if (!err)
+ goto do_resident_extend;
+ /* There is nothing we can do to make enough space. )-: */
+ goto err_out;
+#endif
+do_non_resident_extend:
+ BUG_ON(!NInoNonResident(ni));
+ if (new_alloc_size == allocated_size) {
+ BUG_ON(vcn);
+ goto alloc_done;
+ }
+ /*
+ * If the data starts after the end of the old allocation, this is a
+ * $DATA attribute and sparse attributes are enabled on the volume and
+ * for this inode, then create a sparse region between the old
+ * allocated size and the start of the data. Otherwise simply proceed
+ * with filling the whole space between the old allocated size and the
+ * new allocated size with clusters.
+ */
+ if ((start >= 0 && start <= allocated_size) || ni->type != AT_DATA ||
+ !NVolSparseEnabled(vol) || NInoSparseDisabled(ni))
+ goto skip_sparse;
+ // TODO: This is not implemented yet. We just fill in with real
+ // clusters for now...
+ ntfs_debug("Inserting holes is not-implemented yet. Falling back to "
+ "allocating real clusters instead.");
+skip_sparse:
+ rl = ni->runlist.rl;
+ if (likely(rl)) {
+ /* Seek to the end of the runlist. */
+ while (rl->length)
+ rl++;
+ }
+ /* If this attribute extent is not mapped, map it now. */
+ if (unlikely(!rl || rl->lcn == LCN_RL_NOT_MAPPED ||
+ (rl->lcn == LCN_ENOENT && rl > ni->runlist.rl &&
+ (rl-1)->lcn == LCN_RL_NOT_MAPPED))) {
+ if (!rl && !allocated_size)
+ goto first_alloc;
+ rl = ntfs_mapping_pairs_decompress(vol, a, ni->runlist.rl);
+ if (IS_ERR(rl)) {
+ err = PTR_ERR(rl);
+ if (start < 0 || start >= allocated_size)
+ ntfs_error(vol->sb, "Cannot extend allocation "
+ "of inode 0x%lx, attribute "
+ "type 0x%x, because the "
+ "mapping of a runlist "
+ "fragment failed with error "
+ "code %i.", vi->i_ino,
+ (unsigned)le32_to_cpu(ni->type),
+ err);
+ if (err != -ENOMEM)
+ err = -EIO;
+ goto err_out;
+ }
+ ni->runlist.rl = rl;
+ /* Seek to the end of the runlist. */
+ while (rl->length)
+ rl++;
+ }
+ /*
+ * We now know the runlist of the last extent is mapped and @rl is at
+ * the end of the runlist. We want to begin allocating clusters
+ * starting at the last allocated cluster to reduce fragmentation. If
+ * there are no valid LCNs in the attribute we let the cluster
+ * allocator choose the starting cluster.
+ */
+ /* If the last LCN is a hole or simillar seek back to last real LCN. */
+ while (rl->lcn < 0 && rl > ni->runlist.rl)
+ rl--;
+first_alloc:
+ // FIXME: Need to implement partial allocations so at least part of the
+ // write can be performed when start >= 0. (Needed for POSIX write(2)
+ // conformance.)
+ rl2 = ntfs_cluster_alloc(vol, allocated_size >> vol->cluster_size_bits,
+ (new_alloc_size - allocated_size) >>
+ vol->cluster_size_bits, (rl && (rl->lcn >= 0)) ?
+ rl->lcn + rl->length : -1, DATA_ZONE, true);
+ if (IS_ERR(rl2)) {
+ err = PTR_ERR(rl2);
+ if (start < 0 || start >= allocated_size)
+ ntfs_error(vol->sb, "Cannot extend allocation of "
+ "inode 0x%lx, attribute type 0x%x, "
+ "because the allocation of clusters "
+ "failed with error code %i.", vi->i_ino,
+ (unsigned)le32_to_cpu(ni->type), err);
+ if (err != -ENOMEM && err != -ENOSPC)
+ err = -EIO;
+ goto err_out;
+ }
+ rl = ntfs_runlists_merge(ni->runlist.rl, rl2);
+ if (IS_ERR(rl)) {
+ err = PTR_ERR(rl);
+ if (start < 0 || start >= allocated_size)
+ ntfs_error(vol->sb, "Cannot extend allocation of "
+ "inode 0x%lx, attribute type 0x%x, "
+ "because the runlist merge failed "
+ "with error code %i.", vi->i_ino,
+ (unsigned)le32_to_cpu(ni->type), err);
+ if (err != -ENOMEM)
+ err = -EIO;
+ if (ntfs_cluster_free_from_rl(vol, rl2)) {
+ ntfs_error(vol->sb, "Failed to release allocated "
+ "cluster(s) in error code path. Run "
+ "chkdsk to recover the lost "
+ "cluster(s).");
+ NVolSetErrors(vol);
+ }
+ ntfs_free(rl2);
+ goto err_out;
+ }
+ ni->runlist.rl = rl;
+ ntfs_debug("Allocated 0x%llx clusters.", (long long)(new_alloc_size -
+ allocated_size) >> vol->cluster_size_bits);
+ /* Find the runlist element with which the attribute extent starts. */
+ ll = sle64_to_cpu(a->data.non_resident.lowest_vcn);
+ rl2 = ntfs_rl_find_vcn_nolock(rl, ll);
+ BUG_ON(!rl2);
+ BUG_ON(!rl2->length);
+ BUG_ON(rl2->lcn < LCN_HOLE);
+ mp_rebuilt = false;
+ /* Get the size for the new mapping pairs array for this extent. */
+ mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1);
+ if (unlikely(mp_size <= 0)) {
+ err = mp_size;
+ if (start < 0 || start >= allocated_size)
+ ntfs_error(vol->sb, "Cannot extend allocation of "
+ "inode 0x%lx, attribute type 0x%x, "
+ "because determining the size for the "
+ "mapping pairs failed with error code "
+ "%i.", vi->i_ino,
+ (unsigned)le32_to_cpu(ni->type), err);
+ err = -EIO;
+ goto undo_alloc;
+ }
+ /* Extend the attribute record to fit the bigger mapping pairs array. */
+ attr_len = le32_to_cpu(a->length);
+ err = ntfs_attr_record_resize(m, a, mp_size +
+ le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
+ if (unlikely(err)) {
+ BUG_ON(err != -ENOSPC);
+ // TODO: Deal with this by moving this extent to a new mft
+ // record or by starting a new extent in a new mft record,
+ // possibly by extending this extent partially and filling it
+ // and creating a new extent for the remainder, or by making
+ // other attributes non-resident and/or by moving other
+ // attributes out of this mft record.
+ if (start < 0 || start >= allocated_size)
+ ntfs_error(vol->sb, "Not enough space in the mft "
+ "record for the extended attribute "
+ "record. This case is not "
+ "implemented yet.");
+ err = -EOPNOTSUPP;
+ goto undo_alloc;
+ }
+ mp_rebuilt = true;
+ /* Generate the mapping pairs array directly into the attr record. */
+ err = ntfs_mapping_pairs_build(vol, (u8*)a +
+ le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
+ mp_size, rl2, ll, -1, NULL);
+ if (unlikely(err)) {
+ if (start < 0 || start >= allocated_size)
+ ntfs_error(vol->sb, "Cannot extend allocation of "
+ "inode 0x%lx, attribute type 0x%x, "
+ "because building the mapping pairs "
+ "failed with error code %i.", vi->i_ino,
+ (unsigned)le32_to_cpu(ni->type), err);
+ err = -EIO;
+ goto undo_alloc;
+ }
+ /* Update the highest_vcn. */
+ a->data.non_resident.highest_vcn = cpu_to_sle64((new_alloc_size >>
+ vol->cluster_size_bits) - 1);
+ /*
+ * We now have extended the allocated size of the attribute. Reflect
+ * this in the ntfs_inode structure and the attribute record.
+ */
+ if (a->data.non_resident.lowest_vcn) {
+ /*
+ * We are not in the first attribute extent, switch to it, but
+ * first ensure the changes will make it to disk later.
+ */
+ flush_dcache_mft_record_page(ctx->ntfs_ino);
+ mark_mft_record_dirty(ctx->ntfs_ino);
+ ntfs_attr_reinit_search_ctx(ctx);
+ err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
+ CASE_SENSITIVE, 0, NULL, 0, ctx);
+ if (unlikely(err))
+ goto restore_undo_alloc;
+ /* @m is not used any more so no need to set it. */
+ a = ctx->attr;
+ }
+ write_lock_irqsave(&ni->size_lock, flags);
+ ni->allocated_size = new_alloc_size;
+ a->data.non_resident.allocated_size = cpu_to_sle64(new_alloc_size);
+ /*
+ * FIXME: This would fail if @ni is a directory, $MFT, or an index,
+ * since those can have sparse/compressed set. For example can be
+ * set compressed even though it is not compressed itself and in that
+ * case the bit means that files are to be created compressed in the
+ * directory... At present this is ok as this code is only called for
+ * regular files, and only for their $DATA attribute(s).
+ * FIXME: The calculation is wrong if we created a hole above. For now
+ * it does not matter as we never create holes.
+ */
+ if (NInoSparse(ni) || NInoCompressed(ni)) {
+ ni->itype.compressed.size += new_alloc_size - allocated_size;
+ a->data.non_resident.compressed_size =
+ cpu_to_sle64(ni->itype.compressed.size);
+ vi->i_blocks = ni->itype.compressed.size >> 9;
+ } else
+ vi->i_blocks = new_alloc_size >> 9;
+ write_unlock_irqrestore(&ni->size_lock, flags);
+alloc_done:
+ if (new_data_size >= 0) {
+ BUG_ON(new_data_size <
+ sle64_to_cpu(a->data.non_resident.data_size));
+ a->data.non_resident.data_size = cpu_to_sle64(new_data_size);
+ }
+flush_done:
+ /* Ensure the changes make it to disk. */
+ flush_dcache_mft_record_page(ctx->ntfs_ino);
+ mark_mft_record_dirty(ctx->ntfs_ino);
+done:
+ ntfs_attr_put_search_ctx(ctx);
+ unmap_mft_record(base_ni);
+ up_write(&ni->runlist.lock);
+ ntfs_debug("Done, new_allocated_size 0x%llx.",
+ (unsigned long long)new_alloc_size);
+ return new_alloc_size;
+restore_undo_alloc:
+ if (start < 0 || start >= allocated_size)
+ ntfs_error(vol->sb, "Cannot complete extension of allocation "
+ "of inode 0x%lx, attribute type 0x%x, because "
+ "lookup of first attribute extent failed with "
+ "error code %i.", vi->i_ino,
+ (unsigned)le32_to_cpu(ni->type), err);
+ if (err == -ENOENT)
+ err = -EIO;
+ ntfs_attr_reinit_search_ctx(ctx);
+ if (ntfs_attr_lookup(ni->type, ni->name, ni->name_len, CASE_SENSITIVE,
+ allocated_size >> vol->cluster_size_bits, NULL, 0,
+ ctx)) {
+ ntfs_error(vol->sb, "Failed to find last attribute extent of "
+ "attribute in error code path. Run chkdsk to "
+ "recover.");
+ write_lock_irqsave(&ni->size_lock, flags);
+ ni->allocated_size = new_alloc_size;
+ /*
+ * FIXME: This would fail if @ni is a directory... See above.
+ * FIXME: The calculation is wrong if we created a hole above.
+ * For now it does not matter as we never create holes.
+ */
+ if (NInoSparse(ni) || NInoCompressed(ni)) {
+ ni->itype.compressed.size += new_alloc_size -
+ allocated_size;
+ vi->i_blocks = ni->itype.compressed.size >> 9;
+ } else
+ vi->i_blocks = new_alloc_size >> 9;
+ write_unlock_irqrestore(&ni->size_lock, flags);
+ ntfs_attr_put_search_ctx(ctx);
+ unmap_mft_record(base_ni);
+ up_write(&ni->runlist.lock);
+ /*
+ * The only thing that is now wrong is the allocated size of the
+ * base attribute extent which chkdsk should be able to fix.
+ */
+ NVolSetErrors(vol);
+ return err;
+ }
+ ctx->attr->data.non_resident.highest_vcn = cpu_to_sle64(
+ (allocated_size >> vol->cluster_size_bits) - 1);
+undo_alloc:
+ ll = allocated_size >> vol->cluster_size_bits;
+ if (ntfs_cluster_free(ni, ll, -1, ctx) < 0) {
+ ntfs_error(vol->sb, "Failed to release allocated cluster(s) "
+ "in error code path. Run chkdsk to recover "
+ "the lost cluster(s).");
+ NVolSetErrors(vol);
+ }
+ m = ctx->mrec;
+ a = ctx->attr;
+ /*
+ * If the runlist truncation fails and/or the search context is no
+ * longer valid, we cannot resize the attribute record or build the
+ * mapping pairs array thus we mark the inode bad so that no access to
+ * the freed clusters can happen.
+ */
+ if (ntfs_rl_truncate_nolock(vol, &ni->runlist, ll) || IS_ERR(m)) {
+ ntfs_error(vol->sb, "Failed to %s in error code path. Run "
+ "chkdsk to recover.", IS_ERR(m) ?
+ "restore attribute search context" :
+ "truncate attribute runlist");
+ NVolSetErrors(vol);
+ } else if (mp_rebuilt) {
+ if (ntfs_attr_record_resize(m, a, attr_len)) {
+ ntfs_error(vol->sb, "Failed to restore attribute "
+ "record in error code path. Run "
+ "chkdsk to recover.");
+ NVolSetErrors(vol);
+ } else /* if (success) */ {
+ if (ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
+ a->data.non_resident.
+ mapping_pairs_offset), attr_len -
+ le16_to_cpu(a->data.non_resident.
+ mapping_pairs_offset), rl2, ll, -1,
+ NULL)) {
+ ntfs_error(vol->sb, "Failed to restore "
+ "mapping pairs array in error "
+ "code path. Run chkdsk to "
+ "recover.");
+ NVolSetErrors(vol);
+ }
+ flush_dcache_mft_record_page(ctx->ntfs_ino);
+ mark_mft_record_dirty(ctx->ntfs_ino);
+ }
+ }
+err_out:
+ if (ctx)
+ ntfs_attr_put_search_ctx(ctx);
+ if (m)
+ unmap_mft_record(base_ni);
+ up_write(&ni->runlist.lock);
+conv_err_out:
+ ntfs_debug("Failed. Returning error code %i.", err);
+ return err;
+}
+
+/**
* ntfs_attr_set - fill (a part of) an attribute with a byte
* @ni: ntfs inode describing the attribute to fill
* @ofs: offset inside the attribute at which to start to fill
struct page *page;
u8 *kaddr;
pgoff_t idx, end;
- unsigned int start_ofs, end_ofs, size;
+ unsigned start_ofs, end_ofs, size;
ntfs_debug("Entering for ofs 0x%llx, cnt 0x%llx, val 0x%hx.",
(long long)ofs, (long long)cnt, val);
end >>= PAGE_CACHE_SHIFT;
/* If there is a first partial page, need to do it the slow way. */
if (start_ofs) {
- page = read_cache_page(mapping, idx,
- (filler_t*)mapping->a_ops->readpage, NULL);
+ page = read_mapping_page(mapping, idx, NULL);
if (IS_ERR(page)) {
ntfs_error(vol->sb, "Failed to read first partial "
- "page (sync error, index 0x%lx).", idx);
- return PTR_ERR(page);
- }
- wait_on_page_locked(page);
- if (unlikely(!PageUptodate(page))) {
- ntfs_error(vol->sb, "Failed to read first partial page "
- "(async error, index 0x%lx).", idx);
- page_cache_release(page);
+ "page (error, index 0x%lx).", idx);
return PTR_ERR(page);
}
/*
kunmap_atomic(kaddr, KM_USER0);
set_page_dirty(page);
page_cache_release(page);
+ balance_dirty_pages_ratelimited(mapping);
+ cond_resched();
if (idx == end)
goto done;
idx++;
/* Finally unlock and release the page. */
unlock_page(page);
page_cache_release(page);
+ balance_dirty_pages_ratelimited(mapping);
+ cond_resched();
}
/* If there is a last partial page, need to do it the slow way. */
if (end_ofs) {
- page = read_cache_page(mapping, idx,
- (filler_t*)mapping->a_ops->readpage, NULL);
+ page = read_mapping_page(mapping, idx, NULL);
if (IS_ERR(page)) {
ntfs_error(vol->sb, "Failed to read last partial page "
- "(sync error, index 0x%lx).", idx);
- return PTR_ERR(page);
- }
- wait_on_page_locked(page);
- if (unlikely(!PageUptodate(page))) {
- ntfs_error(vol->sb, "Failed to read last partial page "
- "(async error, index 0x%lx).", idx);
- page_cache_release(page);
+ "(error, index 0x%lx).", idx);
return PTR_ERR(page);
}
kaddr = kmap_atomic(page, KM_USER0);
kunmap_atomic(kaddr, KM_USER0);
set_page_dirty(page);
page_cache_release(page);
+ balance_dirty_pages_ratelimited(mapping);
+ cond_resched();
}
done:
ntfs_debug("Done.");