file.c

linux 内核源代码

				if (PageUptodate(page)) {
					if (!buffer_uptodate(bh))
						set_buffer_uptodate(bh);
				} else if (!buffer_uptodate(bh)) {
					zero_user_page(page, bh_offset(bh),
							blocksize, KM_USER0);
					set_buffer_uptodate(bh);
				}
				continue;
			}
		}
		/*
		 * Out of bounds buffer is invalid if it was not really out of
		 * bounds.
		 */
		BUG_ON(lcn != LCN_HOLE);
		/*
		 * We need the runlist locked for writing, so if it is locked
		 * for reading relock it now and retry in case it changed
		 * whilst we dropped the lock.
		 */
		BUG_ON(!rl);
		if (!rl_write_locked) {
			up_read(&ni->runlist.lock);
			down_write(&ni->runlist.lock);
			rl_write_locked = true;
			goto retry_remap;
		}
		/* Find the previous last allocated cluster. */
		BUG_ON(rl->lcn != LCN_HOLE);
		lcn = -1;
		rl2 = rl;
		while (--rl2 >= ni->runlist.rl) {
			if (rl2->lcn >= 0) {
				lcn = rl2->lcn + rl2->length;
				break;
			}
		}
		rl2 = ntfs_cluster_alloc(vol, bh_cpos, 1, lcn, DATA_ZONE,
				false);
		if (IS_ERR(rl2)) {
			err = PTR_ERR(rl2);
			ntfs_debug("Failed to allocate cluster, error code %i.",
					err);
			break;
		}
		lcn = rl2->lcn;
		rl = ntfs_runlists_merge(ni->runlist.rl, rl2);
		if (IS_ERR(rl)) {
			err = PTR_ERR(rl);
			if (err != -ENOMEM)
				err = -EIO;
			if (ntfs_cluster_free_from_rl(vol, rl2)) {
				ntfs_error(vol->sb, "Failed to release "
						"allocated cluster in error "
						"code path.  Run chkdsk to "
						"recover the lost cluster.");
				NVolSetErrors(vol);
			}
			ntfs_free(rl2);
			break;
		}
		ni->runlist.rl = rl;
		status.runlist_merged = 1;
		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;
		else
			base_ni = ni->ext.base_ntfs_ino;
		m = map_mft_record(base_ni);
		if (IS_ERR(m)) {
			err = PTR_ERR(m);
			break;
		}
		ctx = ntfs_attr_get_search_ctx(base_ni, m);
		if (unlikely(!ctx)) {
			err = -ENOMEM;
			unmap_mft_record(base_ni);
			break;
		}
		status.mft_attr_mapped = 1;
		err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
				CASE_SENSITIVE, bh_cpos, NULL, 0, ctx);
		if (unlikely(err)) {
			if (err == -ENOENT)
				err = -EIO;
			break;
		}
		m = ctx->mrec;
		a = ctx->attr;
		/*
		 * Find the runlist element with which the attribute extent
		 * starts.  Note, we cannot use the _attr_ version because we
		 * have mapped the mft record.  That is ok because we know the
		 * runlist fragment must be mapped already to have ever gotten
		 * here, so we can just use the _rl_ version.
		 */
		vcn = sle64_to_cpu(a->data.non_resident.lowest_vcn);
		rl2 = ntfs_rl_find_vcn_nolock(rl, vcn);
		BUG_ON(!rl2);
		BUG_ON(!rl2->length);
		BUG_ON(rl2->lcn < LCN_HOLE);
		highest_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
		/*
		 * If @highest_vcn is zero, calculate the real highest_vcn
		 * (which can really be zero).
		 */
		if (!highest_vcn)
			highest_vcn = (sle64_to_cpu(
					a->data.non_resident.allocated_size) >>
					vol->cluster_size_bits) - 1;
		/*
		 * Determine the size of the mapping pairs array for the new
		 * extent, i.e. the old extent with the hole filled.
		 */
		mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, vcn,
				highest_vcn);
		if (unlikely(mp_size <= 0)) {
			if (!(err = mp_size))
				err = -EIO;
			ntfs_debug("Failed to get size for mapping pairs "
					"array, error code %i.", err);
			break;
		}
		/*
		 * Resize the attribute record to fit the new mapping pairs
		 * array.
		 */
		attr_rec_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 using the current attribute
			// and fill it with as much of the mapping pairs
			// array as possible.  Then loop over each attribute
			// extent rewriting the mapping pairs arrays as we go
			// along and if when we reach the end we have not
			// enough space, try to resize the last attribute
			// extent and if even that fails, add a new attribute
			// extent.
			// We could also try to resize at each step in the hope
			// that we will not need to rewrite every single extent.
			// Note, we may need to decompress some extents to fill
			// the runlist as we are walking the extents...
			ntfs_error(vol->sb, "Not enough space in the mft "
					"record for the extended attribute "
					"record.  This case is not "
					"implemented yet.");
			err = -EOPNOTSUPP;
			break ;
		}
		status.mp_rebuilt = 1;
		/*
		 * Generate the mapping pairs array directly into the attribute
		 * record.
		 */
		err = ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
				a->data.non_resident.mapping_pairs_offset),
				mp_size, rl2, vcn, highest_vcn, NULL);
		if (unlikely(err)) {
			ntfs_error(vol->sb, "Cannot fill hole in 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;
			break;
		}
		/* Update the highest_vcn but only if it was not set. */
		if (unlikely(!a->data.non_resident.highest_vcn))
			a->data.non_resident.highest_vcn =
					cpu_to_sle64(highest_vcn);
		/*
		 * If the attribute is sparse/compressed, update the compressed
		 * size in the ntfs_inode structure and the attribute record.
		 */
		if (likely(NInoSparse(ni) || NInoCompressed(ni))) {
			/*
			 * If we are not in the first attribute extent, switch
			 * to it, but first ensure the changes will make it to
			 * disk later.
			 */
			if (a->data.non_resident.lowest_vcn) {
				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)) {
					status.attr_switched = 1;
					break;
				}
				/* @m is not used any more so do not set it. */
				a = ctx->attr;
			}
			write_lock_irqsave(&ni->size_lock, flags);
			ni->itype.compressed.size += vol->cluster_size;
			a->data.non_resident.compressed_size =
					cpu_to_sle64(ni->itype.compressed.size);
			write_unlock_irqrestore(&ni->size_lock, flags);
		}
		/* Ensure the changes make it to disk. */
		flush_dcache_mft_record_page(ctx->ntfs_ino);
		mark_mft_record_dirty(ctx->ntfs_ino);
		ntfs_attr_put_search_ctx(ctx);
		unmap_mft_record(base_ni);
		/* Successfully filled the hole. */
		status.runlist_merged = 0;
		status.mft_attr_mapped = 0;
		status.mp_rebuilt = 0;
		/* Setup the map cache and use that to deal with the buffer. */
		was_hole = true;
		vcn = bh_cpos;
		vcn_len = 1;
		lcn_block = lcn << (vol->cluster_size_bits - blocksize_bits);
		cdelta = 0;
		/*
		 * If the number of remaining clusters in the @pages is smaller
		 * or equal to the number of cached clusters, unlock the
		 * runlist as the map cache will be used from now on.
		 */
		if (likely(vcn + vcn_len >= cend)) {
			up_write(&ni->runlist.lock);
			rl_write_locked = false;
			rl = NULL;
		}
		goto map_buffer_cached;
	} while (bh_pos += blocksize, (bh = bh->b_this_page) != head);
	/* If there are no errors, do the next page. */
	if (likely(!err && ++u < nr_pages))
		goto do_next_page;
	/* If there are no errors, release the runlist lock if we took it. */
	if (likely(!err)) {
		if (unlikely(rl_write_locked)) {
			up_write(&ni->runlist.lock);
			rl_write_locked = false;
		} else if (unlikely(rl))
			up_read(&ni->runlist.lock);
		rl = NULL;
	}
	/* If we issued read requests, let them complete. */
	read_lock_irqsave(&ni->size_lock, flags);
	initialized_size = ni->initialized_size;
	read_unlock_irqrestore(&ni->size_lock, flags);
	while (wait_bh > wait) {
		bh = *--wait_bh;
		wait_on_buffer(bh);
		if (likely(buffer_uptodate(bh))) {
			page = bh->b_page;
			bh_pos = ((s64)page->index << PAGE_CACHE_SHIFT) +
					bh_offset(bh);
			/*
			 * If the buffer overflows the initialized size, need
			 * to zero the overflowing region.
			 */
			if (unlikely(bh_pos + blocksize > initialized_size)) {
				int ofs = 0;

				if (likely(bh_pos < initialized_size))
					ofs = initialized_size - bh_pos;
				zero_user_page(page, bh_offset(bh) + ofs,
						blocksize - ofs, KM_USER0);
			}
		} else /* if (unlikely(!buffer_uptodate(bh))) */
			err = -EIO;
	}
	if (likely(!err)) {
		/* Clear buffer_new on all buffers. */
		u = 0;
		do {
			bh = head = page_buffers(pages[u]);
			do {
				if (buffer_new(bh))
					clear_buffer_new(bh);
			} while ((bh = bh->b_this_page) != head);
		} while (++u < nr_pages);
		ntfs_debug("Done.");
		return err;
	}
	if (status.attr_switched) {
		/* Get back to the attribute extent we modified. */
		ntfs_attr_reinit_search_ctx(ctx);
		if (ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
				CASE_SENSITIVE, bh_cpos, NULL, 0, ctx)) {
			ntfs_error(vol->sb, "Failed to find required "
					"attribute extent of attribute in "
					"error code path.  Run chkdsk to "
					"recover.");
			write_lock_irqsave(&ni->size_lock, flags);
			ni->itype.compressed.size += vol->cluster_size;
			write_unlock_irqrestore(&ni->size_lock, flags);
			flush_dcache_mft_record_page(ctx->ntfs_ino);
			mark_mft_record_dirty(ctx->ntfs_ino);
			/*
			 * The only thing that is now wrong is the compressed
			 * size of the base attribute extent which chkdsk
			 * should be able to fix.
			 */
			NVolSetErrors(vol);
		} else {
			m = ctx->mrec;
			a = ctx->attr;
			status.attr_switched = 0;
		}
	}
	/*
	 * If the runlist has been modified, need to restore it by punching a
	 * hole into it and we then need to deallocate the on-disk cluster as
	 * well.  Note, we only modify the runlist if we are able to generate a
	 * new mapping pairs array, i.e. only when the mapped attribute extent
	 * is not switched.
	 */
	if (status.runlist_merged && !status.attr_switched) {
		BUG_ON(!rl_write_locked);
		/* Make the file cluster we allocated sparse in the runlist. */
		if (ntfs_rl_punch_nolock(vol, &ni->runlist, bh_cpos, 1)) {
			ntfs_error(vol->sb, "Failed to punch hole into "
					"attribute runlist in error code "
					"path.  Run chkdsk to recover the "
					"lost cluster.");
			NVolSetErrors(vol);
		} else /* if (success) */ {
			status.runlist_merged = 0;
			/*
			 * Deallocate the on-disk cluster we allocated but only
			 * if we succeeded in punching its vcn out of the
			 * runlist.
			 */
			down_write(&vol->lcnbmp_lock);
			if (ntfs_bitmap_clear_bit(vol->lcnbmp_ino, lcn)) {
				ntfs_error(vol->sb, "Failed to release "
						"allocated cluster in error "
						"code path.  Run chkdsk to "
						"recover the lost cluster.");
				NVolSetErrors(vol);
			}
			up_write(&vol->lcnbmp_lock);
		}
	}
	/*
	 * Resize the attribute record to its old size and rebuild the mapping
	 * pairs array.  Note, we only can do this if the runlist has been
	 * restored to its old state which also implies that the mapped
	 * attribute extent is not switched.
	 */
	if (status.mp_rebuilt && !status.runlist_merged) {
		if (ntfs_attr_record_resize(m, a, attr_rec_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_rec_len -
					le16_to_cpu(a->data.non_resident.
					mapping_pairs_offset), ni->runlist.rl,
					vcn, highest_vcn, 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);
		}
	}
	/* Release the mft record and the attribute. */
	if (status.mft_attr_mapped) {
		ntfs_attr_put_search_ctx(ctx);
		unmap_mft_record(base_ni);
	}
	/* Release the runlist lock. */
	if (rl_write_locked)
		up_write(&ni->runlist.lock);
	else if (rl)
		up_read(&ni->runlist.lock);
	/*
	 * Zero out any newly allocated blocks to avoid exposing stale data.
	 * If BH_New is set, we know that the block was newly allocated above
	 * and that it has not been fully zeroed and marked dirty yet.
	 */
	nr_pages = u;
	u = 0;
	end = bh_cpos << vol->cluster_size_bits;
	do {
		page = pages[u];
		bh = head = page_buffers(page);
		do {
			if (u == nr_pages &&
					((s64)page->index << PAGE_CACHE_SHIFT) +
					bh_offset(bh) >= end)
				break;
			if (!buffer_new(bh))
				continue;
			clear_buffer_new(bh);
			if (!buffer_uptodate(bh)) {
				if (PageUptodate(page))
					set_buffer_uptodate(bh);
				else {
					zero_user_page(page, bh_offset(bh),
							blocksize, KM_USER0);
					set_buffer_uptodate(bh);
				}
			}
			mark_buffer_dirty(bh);
		} while ((bh = bh->b_this_page) != head);
	} while (++u <= nr_pages);
	ntfs_error(vol->sb, "Failed.  Returning error code %i.", err);
	return err;
}

/*
 * 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
 * out to (ofs + bytes) and return the number of bytes which were copied.
 */
static inline size_t ntfs_copy_from_user(struct page **pages,
		unsigned nr_pages, unsigned ofs, const char __user *buf,
		size_t bytes)
{
	struct page **last_page = pages + nr_pages;
	char *addr;
	size_t total = 0;
	unsigned len;
	int left;

	do {