1 files changed, 251 insertions, 21 deletions

diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c
index 7de61f7f4314..ab2d808eea43 100644
--- a/fs/bcachefs/fs-io.c
+++ b/fs/bcachefs/fs-io.c
@@ -602,7 +602,7 @@ int bch2_migrate_page(struct address_space *mapping, struct page *newpage,
 	EBUG_ON(!PageLocked(page));
 	EBUG_ON(!PageLocked(newpage));
 
-	ret = migrate_page_move_mapping(mapping, newpage, page, 0);
+	ret = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);
 	if (ret != MIGRATEPAGE_SUCCESS)
 		return ret;
 
@@ -627,10 +627,10 @@ int bch2_migrate_page(struct address_space *mapping, struct page *newpage,
 
 static void bch2_readpages_end_io(struct bio *bio)
 {
-	struct bvec_iter_all iter;
 	struct bio_vec *bv;
+	unsigned i;
 
-	bio_for_each_segment_all(bv, bio, iter) {
+	bio_for_each_segment_all(bv, bio, i) {
 		struct page *page = bv->bv_page;
 
 		if (!bio->bi_status) {
@@ -782,8 +782,11 @@ static void readpage_bio_extend(struct readpages_iter *iter,
 			if (!get_more)
 				break;
 
-			page = xa_load(&iter->mapping->i_pages, page_offset);
-			if (page && !xa_is_value(page))
+			rcu_read_lock();
+			page = radix_tree_lookup(&iter->mapping->i_pages, page_offset);
+			rcu_read_unlock();
+
+			if (page && !radix_tree_exceptional_entry(page))
 				break;
 
 			page = __page_cache_alloc(readahead_gfp_mask(iter->mapping));
@@ -1034,33 +1037,32 @@ static void bch2_writepage_io_done(struct closure *cl)
 					struct bch_writepage_io, cl);
 	struct bch_fs *c = io->op.c;
 	struct bio *bio = &io->op.wbio.bio;
-	struct bvec_iter_all iter;
 	struct bio_vec *bvec;
-	unsigned i;
+	unsigned i, j;
 
 	if (io->op.error) {
-		bio_for_each_segment_all(bvec, bio, iter) {
+		bio_for_each_segment_all(bvec, bio, i) {
 			struct bch_page_state *s;
 
 			SetPageError(bvec->bv_page);
-			mapping_set_error(bvec->bv_page->mapping, -EIO);
+			mapping_set_error(io->inode->v.i_mapping, -EIO);
 
 			s = __bch2_page_state(bvec->bv_page);
 			spin_lock(&s->lock);
-			for (i = 0; i < PAGE_SECTORS; i++)
-				s->s[i].nr_replicas = 0;
+			for (j = 0; j < PAGE_SECTORS; j++)
+				s->s[j].nr_replicas = 0;
 			spin_unlock(&s->lock);
 		}
 	}
 
 	if (io->op.flags & BCH_WRITE_WROTE_DATA_INLINE) {
-		bio_for_each_segment_all(bvec, bio, iter) {
+		bio_for_each_segment_all(bvec, bio, i) {
 			struct bch_page_state *s;
 
 			s = __bch2_page_state(bvec->bv_page);
 			spin_lock(&s->lock);
-			for (i = 0; i < PAGE_SECTORS; i++)
-				s->s[i].nr_replicas = 0;
+			for (j = 0; j < PAGE_SECTORS; j++)
+				s->s[j].nr_replicas = 0;
 			spin_unlock(&s->lock);
 		}
 	}
@@ -1084,7 +1086,7 @@ static void bch2_writepage_io_done(struct closure *cl)
 	 */
 	i_sectors_acct(c, io->inode, NULL, io->op.i_sectors_delta);
 
-	bio_for_each_segment_all(bvec, bio, iter) {
+	bio_for_each_segment_all(bvec, bio, i) {
 		struct bch_page_state *s = __bch2_page_state(bvec->bv_page);
 
 		if (atomic_dec_and_test(&s->write_count))
@@ -1238,7 +1240,7 @@ do_io:
 
 		if (w->io &&
 		    (w->io->op.res.nr_replicas != nr_replicas_this_write ||
-		     bio_full(&w->io->op.wbio.bio, PAGE_SIZE) ||
+		     bio_full(&w->io->op.wbio.bio) ||
 		     w->io->op.wbio.bio.bi_iter.bi_size + (sectors << 9) >=
 		     (BIO_MAX_PAGES * PAGE_SIZE) ||
 		     bio_end_sector(&w->io->op.wbio.bio) != sector))
@@ -1804,9 +1806,8 @@ static long bch2_dio_write_loop(struct dio_write *dio)
 	struct address_space *mapping = req->ki_filp->f_mapping;
 	struct bch_inode_info *inode = file_bch_inode(req->ki_filp);
 	struct bio *bio = &dio->op.wbio.bio;
-	struct bvec_iter_all iter;
 	struct bio_vec *bv;
-	unsigned unaligned;
+	unsigned i, unaligned;
 	u64 new_i_size;
 	bool sync = dio->sync;
 	long ret;
@@ -1848,7 +1849,7 @@ static long bch2_dio_write_loop(struct dio_write *dio)
 			 * bio_iov_iter_get_pages was only able to get <
 			 * blocksize worth of pages:
 			 */
-			bio_for_each_segment_all(bv, bio, iter)
+			bio_for_each_segment_all(bv, bio, i)
 				put_page(bv->bv_page);
 			ret = -EFAULT;
 			goto err;
@@ -1896,7 +1897,7 @@ loop:
 			i_size_write(&inode->v, new_i_size);
 		spin_unlock(&inode->v.i_lock);
 
-		bio_for_each_segment_all(bv, bio, iter)
+		bio_for_each_segment_all(bv, bio, i)
 			put_page(bv->bv_page);
 		if (!dio->iter.count || dio->op.error)
 			break;
@@ -2833,6 +2834,235 @@ static void mark_range_unallocated(struct bch_inode_info *inode,
 	} while (index <= end_index);
 }
 
+static int generic_access_check_limits(struct file *file, loff_t pos,
+				       loff_t *count)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t max_size = inode->i_sb->s_maxbytes;
+
+	if (!(file->f_flags & O_LARGEFILE))
+		max_size = MAX_NON_LFS;
+
+	if (unlikely(pos >= max_size))
+		return -EFBIG;
+	*count = min(*count, max_size - pos);
+	return 0;
+}
+
+static int generic_write_check_limits(struct file *file, loff_t pos,
+				      loff_t *count)
+{
+	loff_t limit = rlimit(RLIMIT_FSIZE);
+
+	if (limit != RLIM_INFINITY) {
+		if (pos >= limit) {
+			send_sig(SIGXFSZ, current, 0);
+			return -EFBIG;
+		}
+		*count = min(*count, limit - pos);
+	}
+
+	return generic_access_check_limits(file, pos, count);
+}
+
+static int generic_remap_checks(struct file *file_in, loff_t pos_in,
+			 struct file *file_out, loff_t pos_out,
+			 loff_t *req_count, unsigned int remap_flags)
+{
+	struct inode *inode_in = file_in->f_mapping->host;
+	struct inode *inode_out = file_out->f_mapping->host;
+	uint64_t count = *req_count;
+	uint64_t bcount;
+	loff_t size_in, size_out;
+	loff_t bs = inode_out->i_sb->s_blocksize;
+	int ret;
+
+	/* The start of both ranges must be aligned to an fs block. */
+	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
+		return -EINVAL;
+
+	/* Ensure offsets don't wrap. */
+	if (pos_in + count < pos_in || pos_out + count < pos_out)
+		return -EINVAL;
+
+	size_in = i_size_read(inode_in);
+	size_out = i_size_read(inode_out);
+
+	/* Dedupe requires both ranges to be within EOF. */
+	if ((remap_flags & REMAP_FILE_DEDUP) &&
+	    (pos_in >= size_in || pos_in + count > size_in ||
+	     pos_out >= size_out || pos_out + count > size_out))
+		return -EINVAL;
+
+	/* Ensure the infile range is within the infile. */
+	if (pos_in >= size_in)
+		return -EINVAL;
+	count = min(count, size_in - (uint64_t)pos_in);
+
+	ret = generic_access_check_limits(file_in, pos_in, &count);
+	if (ret)
+		return ret;
+
+	ret = generic_write_check_limits(file_out, pos_out, &count);
+	if (ret)
+		return ret;
+
+	/*
+	 * If the user wanted us to link to the infile's EOF, round up to the
+	 * next block boundary for this check.
+	 *
+	 * Otherwise, make sure the count is also block-aligned, having
+	 * already confirmed the starting offsets' block alignment.
+	 */
+	if (pos_in + count == size_in) {
+		bcount = ALIGN(size_in, bs) - pos_in;
+	} else {
+		if (!IS_ALIGNED(count, bs))
+			count = ALIGN_DOWN(count, bs);
+		bcount = count;
+	}
+
+	/* Don't allow overlapped cloning within the same file. */
+	if (inode_in == inode_out &&
+	    pos_out + bcount > pos_in &&
+	    pos_out < pos_in + bcount)
+		return -EINVAL;
+
+	/*
+	 * We shortened the request but the caller can't deal with that, so
+	 * bounce the request back to userspace.
+	 */
+	if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN))
+		return -EINVAL;
+
+	*req_count = count;
+	return 0;
+}
+
+static int generic_remap_check_len(struct inode *inode_in,
+				   struct inode *inode_out,
+				   loff_t pos_out,
+				   loff_t *len,
+				   unsigned int remap_flags)
+{
+	u64 blkmask = i_blocksize(inode_in) - 1;
+	loff_t new_len = *len;
+
+	if ((*len & blkmask) == 0)
+		return 0;
+
+	if ((remap_flags & REMAP_FILE_DEDUP) ||
+	    pos_out + *len < i_size_read(inode_out))
+		new_len &= ~blkmask;
+
+	if (new_len == *len)
+		return 0;
+
+	if (remap_flags & REMAP_FILE_CAN_SHORTEN) {
+		*len = new_len;
+		return 0;
+	}
+
+	return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
+}
+
+static int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+				  struct file *file_out, loff_t pos_out,
+				  loff_t *len, unsigned int remap_flags)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	bool same_inode = (inode_in == inode_out);
+	int ret;
+
+	/* Don't touch certain kinds of inodes */
+	if (IS_IMMUTABLE(inode_out))
+		return -EPERM;
+
+	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
+		return -ETXTBSY;
+
+	/* Don't reflink dirs, pipes, sockets... */
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
+	/* Zero length dedupe exits immediately; reflink goes to EOF. */
+	if (*len == 0) {
+		loff_t isize = i_size_read(inode_in);
+
+		if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize)
+			return 0;
+		if (pos_in > isize)
+			return -EINVAL;
+		*len = isize - pos_in;
+		if (*len == 0)
+			return 0;
+	}
+
+	/* Check that we don't violate system file offset limits. */
+	ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len,
+			remap_flags);
+	if (ret)
+		return ret;
+
+	/* Wait for the completion of any pending IOs on both files */
+	inode_dio_wait(inode_in);
+	if (!same_inode)
+		inode_dio_wait(inode_out);
+
+	ret = filemap_write_and_wait_range(inode_in->i_mapping,
+			pos_in, pos_in + *len - 1);
+	if (ret)
+		return ret;
+
+	ret = filemap_write_and_wait_range(inode_out->i_mapping,
+			pos_out, pos_out + *len - 1);
+	if (ret)
+		return ret;
+
+	/*
+	 * Check that the extents are the same.
+	 */
+	if (remap_flags & REMAP_FILE_DEDUP) {
+		bool		is_same = false;
+
+		ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
+				inode_out, pos_out, *len, &is_same);
+		if (ret)
+			return ret;
+		if (!is_same)
+			return -EBADE;
+	}
+
+	ret = generic_remap_check_len(inode_in, inode_out, pos_out, len,
+			remap_flags);
+	if (ret)
+		return ret;
+
+	/* If can't alter the file contents, we're done. */
+	if (!(remap_flags & REMAP_FILE_DEDUP)) {
+		/* Update the timestamps, since we can alter file contents. */
+		if (!(file_out->f_mode & FMODE_NOCMTIME)) {
+			ret = file_update_time(file_out);
+			if (ret)
+				return ret;
+		}
+
+		/*
+		 * Clear the security bits if the process is not being run by
+		 * root.  This keeps people from modifying setuid and setgid
+		 * binaries.
+		 */
+		ret = file_remove_privs(file_out);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 loff_t bch2_remap_file_range(struct file *file_src, loff_t pos_src,
 			     struct file *file_dst, loff_t pos_dst,
 			     loff_t len, unsigned remap_flags)
@@ -3025,7 +3255,7 @@ static loff_t page_hole_offset(struct address_space *mapping, loff_t offset)
 	loff_t ret = -1;
 
 	page = find_lock_entry(mapping, index);
-	if (!page || xa_is_value(page))
+	if (!page || radix_tree_exception(page))
 		return offset;
 
 	pg_offset = __page_hole_offset(page, offset & (PAGE_SIZE - 1));