attrib.c

linux 内核源代码

/**
 * attrib.c - NTFS attribute operations.  Part of the Linux-NTFS project.
 *
 * Copyright (c) 2001-2007 Anton Altaparmakov
 * Copyright (c) 2002 Richard Russon
 *
 * 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
 * by the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program/include file is distributed in the hope that it will be
 * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program (in the main directory of the Linux-NTFS
 * distribution in the file COPYING); if not, write to the Free Software
 * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */

#include <linux/buffer_head.h>
#include <linux/sched.h>
#include <linux/swap.h>
#include <linux/writeback.h>

#include "attrib.h"
#include "debug.h"
#include "layout.h"
#include "lcnalloc.h"
#include "malloc.h"
#include "mft.h"
#include "ntfs.h"
#include "types.h"

/**
 * ntfs_map_runlist_nolock - map (a part of) a runlist of an ntfs inode
 * @ni:		ntfs inode for which to map (part of) a runlist
 * @vcn:	map runlist part containing this vcn
 * @ctx:	active attribute search context if present or NULL if not
 *
 * Map the part of a runlist containing the @vcn of the ntfs inode @ni.
 *
 * If @ctx is specified, it is an active search context of @ni and its base mft
 * record.  This is needed when ntfs_map_runlist_nolock() encounters unmapped
 * runlist fragments and allows their mapping.  If you do not have the mft
 * record mapped, you can specify @ctx as NULL and ntfs_map_runlist_nolock()
 * will perform the necessary mapping and unmapping.
 *
 * Note, ntfs_map_runlist_nolock() saves the state of @ctx on entry and
 * restores it before returning.  Thus, @ctx will be left pointing to the same
 * attribute on return as on entry.  However, the actual pointers in @ctx may
 * point to different memory locations on return, so you must remember to reset
 * any cached pointers from the @ctx, i.e. after the call to
 * ntfs_map_runlist_nolock(), you will probably want to do:
 *	m = ctx->mrec;
 *	a = ctx->attr;
 * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
 * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
 *
 * Return 0 on success and -errno on error.  There is one special error code
 * which is not an error as such.  This is -ENOENT.  It means that @vcn is out
 * of bounds of the runlist.
 *
 * Note the runlist can be NULL after this function returns if @vcn is zero and
 * 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
 *	    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
 *	    why the mapping of the old inode failed.
 *
 * Locking: - The runlist described by @ni must be locked for writing on entry
 *	      and is locked on return.  Note the runlist will be modified.
 *	    - If @ctx is NULL, the base mft record of @ni must not be mapped on
 *	      entry and it will be left unmapped on return.
 *	    - If @ctx is not NULL, the base mft record must be mapped on entry
 *	      and it will be left mapped on return.
 */
int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, ntfs_attr_search_ctx *ctx)
{
	VCN end_vcn;
	unsigned long flags;
	ntfs_inode *base_ni;
	MFT_RECORD *m;
	ATTR_RECORD *a;
	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 = { NULL, };

	ntfs_debug("Mapping runlist part containing vcn 0x%llx.",
			(unsigned long long)vcn);
	if (!NInoAttr(ni))
		base_ni = ni;
	else
		base_ni = ni->ext.base_ntfs_ino;
	if (!ctx) {
		ctx_is_temporary = ctx_needs_reset = true;
		m = map_mft_record(base_ni);
		if (IS_ERR(m))
			return PTR_ERR(m);
		ctx = ntfs_attr_get_search_ctx(base_ni, m);
		if (unlikely(!ctx)) {
			err = -ENOMEM;
			goto err_out;
		}
	} else {
		VCN allocated_size_vcn;

		BUG_ON(IS_ERR(ctx->mrec));
		a = ctx->attr;
		BUG_ON(!a->non_resident);
		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->vol->cluster_size_bits;
		read_unlock_irqrestore(&ni->size_lock, flags);
		if (!a->data.non_resident.lowest_vcn && end_vcn <= 0)
			end_vcn = allocated_size_vcn - 1;
		/*
		 * If we already have the attribute extent containing @vcn in
		 * @ctx, no need to look it up again.  We slightly cheat in
		 * that if vcn exceeds the allocated size, we will refuse to
		 * map the runlist below, so there is definitely no need to get
		 * the right attribute extent.
		 */
		if (vcn >= allocated_size_vcn || (a->type == ni->type &&
				a->name_length == ni->name_len &&
				!memcmp((u8*)a + le16_to_cpu(a->name_offset),
				ni->name, ni->name_len) &&
				sle64_to_cpu(a->data.non_resident.lowest_vcn)
				<= vcn && end_vcn >= vcn))
			ctx_needs_reset = false;
		else {
			/* Save the old search context. */
			old_ctx = *ctx;
			/*
			 * If the currently mapped (extent) inode is not the
			 * base inode we will unmap it when we reinitialize the
			 * search context which means we need to get a
			 * reference to the page containing the mapped mft
			 * record so we do not accidentally drop changes to the
			 * mft record when it has not been marked dirty yet.
			 */
			if (old_ctx.base_ntfs_ino && old_ctx.ntfs_ino !=
					old_ctx.base_ntfs_ino) {
				put_this_page = old_ctx.ntfs_ino->page;
				page_cache_get(put_this_page);
			}
			/*
			 * Reinitialize the search context so we can lookup the
			 * needed attribute extent.
			 */
			ntfs_attr_reinit_search_ctx(ctx);
			ctx_needs_reset = true;
		}
	}
	if (ctx_needs_reset) {
		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;
		}
		BUG_ON(!ctx->attr->non_resident);
	}
	a = ctx->attr;
	/*
	 * Only decompress the mapping pairs if @vcn is inside it.  Otherwise
	 * we get into problems when we try to map an out of bounds vcn because
	 * we then try to map the already mapped runlist fragment and
	 * ntfs_mapping_pairs_decompress() fails.
	 */
	end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn) + 1;
	if (unlikely(vcn && vcn >= end_vcn)) {
		err = -ENOENT;
		goto err_out;
	}
	rl = ntfs_mapping_pairs_decompress(ni->vol, a, ni->runlist.rl);
	if (IS_ERR(rl))
		err = PTR_ERR(rl);
	else
		ni->runlist.rl = rl;
err_out:
	if (ctx_is_temporary) {
		if (likely(ctx))
			ntfs_attr_put_search_ctx(ctx);
		unmap_mft_record(base_ni);
	} else if (ctx_needs_reset) {
		/*
		 * If there is no attribute list, restoring the search context
		 * is acomplished simply by copying the saved context back over
		 * the caller supplied context.  If there is an attribute list,
		 * things are more complicated as we need to deal with mapping
		 * of mft records and resulting potential changes in pointers.
		 */
		if (NInoAttrList(base_ni)) {
			/*
			 * If the currently mapped (extent) inode is not the
			 * one we had before, we need to unmap it and map the
			 * old one.
			 */
			if (ctx->ntfs_ino != old_ctx.ntfs_ino) {
				/*
				 * If the currently mapped inode is not the
				 * base inode, unmap it.
				 */
				if (ctx->base_ntfs_ino && ctx->ntfs_ino !=
						ctx->base_ntfs_ino) {
					unmap_extent_mft_record(ctx->ntfs_ino);
					ctx->mrec = ctx->base_mrec;
					BUG_ON(!ctx->mrec);
				}
				/*
				 * If the old mapped inode is not the base
				 * inode, map it.
				 */
				if (old_ctx.base_ntfs_ino &&
						old_ctx.ntfs_ino !=
						old_ctx.base_ntfs_ino) {
retry_map:
					ctx->mrec = map_mft_record(
							old_ctx.ntfs_ino);
					/*
					 * Something bad has happened.  If out
					 * of memory retry till it succeeds.
					 * Any other errors are fatal and we
					 * return the error code in ctx->mrec.
					 * Let the caller deal with it...  We
					 * just need to fudge things so the
					 * caller can reinit and/or put the
					 * search context safely.
					 */
					if (IS_ERR(ctx->mrec)) {
						if (PTR_ERR(ctx->mrec) ==
								-ENOMEM) {
							schedule();
							goto retry_map;
						} else
							old_ctx.ntfs_ino =
								old_ctx.
								base_ntfs_ino;
					}
				}
			}
			/* Update the changed pointers in the saved context. */
			if (ctx->mrec != old_ctx.mrec) {
				if (!IS_ERR(ctx->mrec))
					old_ctx.attr = (ATTR_RECORD*)(
							(u8*)ctx->mrec +
							((u8*)old_ctx.attr -
							(u8*)old_ctx.mrec));
				old_ctx.mrec = ctx->mrec;
			}
		}
		/* Restore the search context to the saved one. */
		*ctx = old_ctx;
		/*
		 * We drop the reference on the page we took earlier.  In the
		 * case that IS_ERR(ctx->mrec) is true this means we might lose
		 * some changes to the mft record that had been made between
		 * the last time it was marked dirty/written out and now.  This
		 * at this stage is not a problem as the mapping error is fatal
		 * enough that the mft record cannot be written out anyway and
		 * the caller is very likely to shutdown the whole inode
		 * immediately and mark the volume dirty for chkdsk to pick up
		 * the pieces anyway.
		 */
		if (put_this_page)
			page_cache_release(put_this_page);
	}
	return err;
}

/**
 * ntfs_map_runlist - map (a part of) a runlist of an ntfs inode
 * @ni:		ntfs inode for which to map (part of) a runlist
 * @vcn:	map runlist part containing this vcn
 *
 * Map the part of a runlist containing the @vcn of the ntfs inode @ni.
 *
 * Return 0 on success and -errno on error.  There is one special error code
 * which is not an error as such.  This is -ENOENT.  It means that @vcn is out
 * of bounds of the runlist.
 *
 * Locking: - The runlist must be unlocked on entry and is unlocked on return.
 *	    - This function takes the runlist lock for writing and may modify
 *	      the runlist.
 */
int ntfs_map_runlist(ntfs_inode *ni, VCN vcn)
{
	int err = 0;

	down_write(&ni->runlist.lock);
	/* Make sure someone else didn't do the work while we were sleeping. */
	if (likely(ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn) <=
			LCN_RL_NOT_MAPPED))
		err = ntfs_map_runlist_nolock(ni, vcn, NULL);
	up_write(&ni->runlist.lock);
	return err;
}

/**
 * ntfs_attr_vcn_to_lcn_nolock - convert a vcn into a lcn given an ntfs inode
 * @ni:			ntfs inode of the attribute whose runlist to search
 * @vcn:		vcn to convert
 * @write_locked:	true if the runlist is locked for writing
 *
 * Find the virtual cluster number @vcn in the runlist of the ntfs attribute
 * described by the ntfs inode @ni and return the corresponding logical cluster
 * number (lcn).
 *
 * If the @vcn is not mapped yet, the attempt is made to map the attribute
 * extent containing the @vcn and the vcn to lcn conversion is retried.
 *
 * If @write_locked is true the caller has locked the runlist for writing and
 * if false for reading.
 *
 * Since lcns must be >= 0, we use negative return codes with special meaning:
 *
 * Return code	Meaning / Description
 * ==========================================
 *  LCN_HOLE	Hole / not allocated on disk.
 *  LCN_ENOENT	There is no such vcn in the runlist, i.e. @vcn is out of bounds.
 *  LCN_ENOMEM	Not enough memory to map runlist.
 *  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,
 *	      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)
{
	LCN lcn;
	unsigned long flags;
	bool is_retry = false;

	ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, %s_locked.",
			ni->mft_no, (unsigned long long)vcn,
			write_locked ? "write" : "read");
	BUG_ON(!ni);
	BUG_ON(!NInoNonResident(ni));
	BUG_ON(vcn < 0);
	if (!ni->runlist.rl) {
		read_lock_irqsave(&ni->size_lock, flags);
		if (!ni->allocated_size) {
			read_unlock_irqrestore(&ni->size_lock, flags);
			return LCN_ENOENT;
		}
		read_unlock_irqrestore(&ni->size_lock, flags);
	}
retry_remap:
	/* Convert vcn to lcn.  If that fails map the runlist and retry once. */
	lcn = ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn);
	if (likely(lcn >= LCN_HOLE)) {
		ntfs_debug("Done, lcn 0x%llx.", (long long)lcn);
		return lcn;
	}
	if (lcn != LCN_RL_NOT_MAPPED) {
		if (lcn != LCN_ENOENT)
			lcn = LCN_EIO;
	} else if (!is_retry) {
		int err;

		if (!write_locked) {