[PATCH] reiserfs: allow multiple block insertion into the tree

I've had these reiserfs patches in -mm for many months.  We've been
undecided because they trigger bugs in a couple of apps.  But those apps
are now fixed, so it's best to get these speedups in.


From: Oleg Drokin <green@namesys.com>

This patch allows insertion of more than one "indirect" block pointer into
the tree in reiserfs.  (with all the necessary balancing code changes).
The first user of that feature is hole-creation code that is now ~1000
times more cpu-efficient for the case of large holes.

fs/reiserfs/do_balan.c

@@ -319,8 +319,6 @@ static int balance_leaf (struct tree_balance * tb,
 		    int new_item_len;
 		    int version;
 
-		    RFALSE (!is_direct_le_ih (ih),
-			    "PAP-12075: only direct inserted item can be broken. %h", ih);
 		    ret_val = leaf_shift_left (tb, tb->lnum[0]-1, -1);
 
 		    /* Calculate item length to insert to S[0] */
@@ -343,7 +341,7 @@ static int balance_leaf (struct tree_balance * tb,
 		    version = ih_version (ih);
 
 		    /* Calculate key component, item length and body to insert into S[0] */
-                    set_le_ih_k_offset( ih, le_ih_k_offset( ih ) + tb->lbytes );
+                    set_le_ih_k_offset( ih, le_ih_k_offset( ih ) + (tb->lbytes << (is_indirect_le_ih(ih)?tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT:0)) );
 
 		    put_ih_item_len( ih, new_item_len );
 		    if ( tb->lbytes >  zeros_num ) {
@@ -452,23 +450,28 @@ static int balance_leaf (struct tree_balance * tb,
 				ih_item_len( B_N_PITEM_HEAD(tb->L[0],n+item_pos-ret_val)),
 				l_n,body, zeros_num > l_n ? l_n : zeros_num
 				);
-
-			    RFALSE( l_n && 
-				    is_indirect_le_ih(B_N_PITEM_HEAD
-						      (tb->L[0],
-						       n + item_pos - ret_val)),
-				    "PAP-12110: pasting more than 1 unformatted node pointer into indirect item");
-
 			    /* 0-th item in S0 can be only of DIRECT type when l_n != 0*/
 			    {
 				int version;
+				int temp_l = l_n;
 				
+				RFALSE (ih_item_len (B_N_PITEM_HEAD (tbS0, 0)),
+					"PAP-12106: item length must be 0");
+				RFALSE (comp_short_le_keys (B_N_PKEY (tbS0, 0),
+							    B_N_PKEY (tb->L[0],
+									    n + item_pos - ret_val)),
+					"PAP-12107: items must be of the same file");
+				if (is_indirect_le_ih(B_N_PITEM_HEAD (tb->L[0],
+								      n + item_pos - ret_val)))	{
+				    temp_l = l_n << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT);
+				}
+				/* update key of first item in S0 */
 				version = ih_version (B_N_PITEM_HEAD (tbS0, 0));
 				set_le_key_k_offset (version, B_N_PKEY (tbS0, 0), 
-						   le_key_k_offset (version, B_N_PKEY (tbS0, 0)) + l_n);
-			      version = ih_version (B_N_PITEM_HEAD(tb->CFL[0],tb->lkey[0]));
+						     le_key_k_offset (version, B_N_PKEY (tbS0, 0)) + temp_l);
+				/* update left delimiting key */
 				set_le_key_k_offset (version, B_N_PDELIM_KEY(tb->CFL[0],tb->lkey[0]),
-						   le_key_k_offset (version, B_N_PDELIM_KEY(tb->CFL[0],tb->lkey[0])) + l_n);
+						     le_key_k_offset (version, B_N_PDELIM_KEY(tb->CFL[0],tb->lkey[0])) + temp_l);
 			    }
 
 			    /* Calculate new body, position in item and insert_size[0] */
@@ -537,7 +540,7 @@ static int balance_leaf (struct tree_balance * tb,
 			    );
 		    /* if appended item is indirect item, put unformatted node into un list */
 		    if (is_indirect_le_ih (pasted))
-			set_ih_free_space (pasted, ((struct unfm_nodeinfo*)body)->unfm_freespace);
+			set_ih_free_space (pasted, 0);
 		    tb->insert_size[0] = 0;
 		    zeros_num = 0;
 		}
@@ -565,15 +568,11 @@ static int balance_leaf (struct tree_balance * tb,
 	    { /* new item or its part falls to R[0] */
 		if ( item_pos == n - tb->rnum[0] + 1 && tb->rbytes != -1 )
 		{ /* part of new item falls into R[0] */
-		    int old_key_comp, old_len, r_zeros_number;
+		    loff_t old_key_comp, old_len, r_zeros_number;
 		    const char * r_body;
 		    int version;
 		    loff_t offset;
 
-		    RFALSE( !is_direct_le_ih (ih),
-			    "PAP-12135: only direct item can be split. (%h)", 
-			    ih);
-
 		    leaf_shift_right(tb,tb->rnum[0]-1,-1);
 
 		    version = ih_version(ih);
@@ -582,7 +581,7 @@ static int balance_leaf (struct tree_balance * tb,
 		    old_len = ih_item_len(ih);
 
 		    /* Calculate key component and item length to insert into R[0] */
-                    offset = le_ih_k_offset( ih ) + (old_len - tb->rbytes );
+                    offset = le_ih_k_offset( ih ) + ((old_len - tb->rbytes )<<(is_indirect_le_ih(ih)?tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT:0));
                     set_le_ih_k_offset( ih, offset );
 		    put_ih_item_len( ih, tb->rbytes);
 		    /* Insert part of the item into R[0] */
@@ -590,13 +589,13 @@ static int balance_leaf (struct tree_balance * tb,
 		    bi.bi_bh = tb->R[0];
 		    bi.bi_parent = tb->FR[0];
 		    bi.bi_position = get_right_neighbor_position (tb, 0);
-		    if ( offset - old_key_comp > zeros_num ) {
+		    if ( (old_len - tb->rbytes) > zeros_num ) {
 			r_zeros_number = 0;
-			r_body = body + offset - old_key_comp - zeros_num;
+			r_body = body + (old_len - tb->rbytes) - zeros_num;
 		    }
 		    else {
 			r_body = body;
-			r_zeros_number = zeros_num - (offset - old_key_comp);
+			r_zeros_number = zeros_num - (old_len - tb->rbytes);
 			zeros_num -= r_zeros_number;
 		    }
 
@@ -707,12 +706,17 @@ static int balance_leaf (struct tree_balance * tb,
 			
 			{
 			  int version;
+			  unsigned long temp_rem = n_rem;
 			  
 			  version = ih_version (B_N_PITEM_HEAD (tb->R[0],0));
+			  if (is_indirect_le_key(version,B_N_PKEY(tb->R[0],0))){
+			      temp_rem = n_rem << (tb->tb_sb->s_blocksize_bits -
+					 UNFM_P_SHIFT);
+			  }
 			  set_le_key_k_offset (version, B_N_PKEY(tb->R[0],0), 
-					       le_key_k_offset (version, B_N_PKEY(tb->R[0],0)) + n_rem);
+					       le_key_k_offset (version, B_N_PKEY(tb->R[0],0)) + temp_rem);
 			  set_le_key_k_offset (version, B_N_PDELIM_KEY(tb->CFR[0],tb->rkey[0]), 
-					       le_key_k_offset (version, B_N_PDELIM_KEY(tb->CFR[0],tb->rkey[0])) + n_rem);
+					       le_key_k_offset (version, B_N_PDELIM_KEY(tb->CFR[0],tb->rkey[0])) + temp_rem);
 			}
 /*		  k_offset (B_N_PKEY(tb->R[0],0)) += n_rem;
 		  k_offset (B_N_PDELIM_KEY(tb->CFR[0],tb->rkey[0])) += n_rem;*/
@@ -736,13 +740,12 @@ static int balance_leaf (struct tree_balance * tb,
 			leaf_paste_in_buffer(&bi, 0, n_shift, tb->insert_size[0] - n_rem, r_body, r_zeros_number);
 
 			if (is_indirect_le_ih (B_N_PITEM_HEAD(tb->R[0],0))) {
-
+#if 0
 			    RFALSE( n_rem,
 				    "PAP-12160: paste more than one unformatted node pointer");
-
-			    set_ih_free_space (B_N_PITEM_HEAD(tb->R[0],0), ((struct unfm_nodeinfo*)body)->unfm_freespace);
+#endif
+			    set_ih_free_space (B_N_PITEM_HEAD(tb->R[0],0), 0);
 			}
-
 			tb->insert_size[0] = n_rem;
 			if ( ! n_rem )
 			    pos_in_item ++;
@@ -781,7 +784,7 @@ static int balance_leaf (struct tree_balance * tb,
 		    }
 
 		    if (is_indirect_le_ih (pasted))
-			set_ih_free_space (pasted, ((struct unfm_nodeinfo*)body)->unfm_freespace);
+			set_ih_free_space (pasted, 0);
 		    zeros_num = tb->insert_size[0] = 0;
 		}
 	    }
@@ -858,12 +861,6 @@ static int balance_leaf (struct tree_balance * tb,
 		    const char * r_body;
 		    int version;
 
-		    RFALSE( !is_direct_le_ih(ih),
-			/* The items which can be inserted are:
-			   Stat_data item, direct item, indirect item and directory item which consist of only two entries "." and "..".
-			   These items must not be broken except for a direct one. */
-			    "PAP-12205: non-direct item can not be broken when inserting");
-
 		    /* Move snum[i]-1 items from S[0] to S_new[i] */
 		    leaf_move_items (LEAF_FROM_S_TO_SNEW, tb, snum[i] - 1, -1, S_new[i]);
 		    /* Remember key component and item length */
@@ -873,7 +870,7 @@ static int balance_leaf (struct tree_balance * tb,
 
 		    /* Calculate key component and item length to insert into S_new[i] */
                     set_le_ih_k_offset( ih,
-                                le_ih_k_offset(ih) + (old_len - sbytes[i] ) );
+                                le_ih_k_offset(ih) + ((old_len - sbytes[i] )<<(is_indirect_le_ih(ih)?tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT:0)) );
 
 		    put_ih_item_len( ih, sbytes[i] );
 
@@ -883,13 +880,13 @@ static int balance_leaf (struct tree_balance * tb,
 		    bi.bi_parent = 0;
 		    bi.bi_position = 0;
 
-		    if ( le_ih_k_offset (ih) - old_key_comp > zeros_num ) {
+		    if ( (old_len - sbytes[i]) > zeros_num ) {
 			r_zeros_number = 0;
-			r_body = body + (le_ih_k_offset(ih) - old_key_comp) - zeros_num;
+			r_body = body + (old_len - sbytes[i]) - zeros_num;
 		    }
 		    else {
 			r_body = body;
-			r_zeros_number = zeros_num - (le_ih_k_offset (ih) - old_key_comp);
+			r_zeros_number = zeros_num - (old_len - sbytes[i]);
 			zeros_num -= r_zeros_number;
 		    }
 
@@ -1010,11 +1007,13 @@ static int balance_leaf (struct tree_balance * tb,
 
 			    tmp = B_N_PITEM_HEAD(S_new[i],0);
 			    if (is_indirect_le_ih (tmp)) {
-				if (n_rem)
-				    reiserfs_panic (tb->tb_sb, "PAP-12230: balance_leaf: invalid action with indirect item");
-				set_ih_free_space (tmp, ((struct unfm_nodeinfo*)body)->unfm_freespace);
+				set_ih_free_space (tmp, 0);
+				set_le_ih_k_offset( tmp, le_ih_k_offset(tmp) + 
+					            (n_rem << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT)));
+			    } else {
+				set_le_ih_k_offset( tmp, le_ih_k_offset(tmp) + 
+				                    n_rem );
 			    }
-                            set_le_ih_k_offset( tmp, le_ih_k_offset(tmp) + n_rem );
 			}
 
 			tb->insert_size[0] = n_rem;
@@ -1060,7 +1059,7 @@ static int balance_leaf (struct tree_balance * tb,
 
 		    /* if we paste to indirect item update ih_free_space */
 		    if (is_indirect_le_ih (pasted))
-			set_ih_free_space (pasted, ((struct unfm_nodeinfo*)body)->unfm_freespace);
+			set_ih_free_space (pasted, 0);
 		    zeros_num = tb->insert_size[0] = 0;
 		}
 	    }
@@ -1152,11 +1151,12 @@ static int balance_leaf (struct tree_balance * tb,
 		    leaf_paste_in_buffer (&bi, item_pos, pos_in_item, tb->insert_size[0], body, zeros_num);
 
 		    if (is_indirect_le_ih (pasted)) {
-
+#if 0
 			RFALSE( tb->insert_size[0] != UNFM_P_SIZE,
 				"PAP-12280: insert_size for indirect item must be %d, not %d",
 				UNFM_P_SIZE, tb->insert_size[0]);
-			set_ih_free_space (pasted, ((struct unfm_nodeinfo*)body)->unfm_freespace);
+#endif
+			set_ih_free_space (pasted, 0);
 		    }
 		    tb->insert_size[0] = 0;
 		}

fs/reiserfs/inode.c

@@ -766,7 +766,11 @@ int reiserfs_get_block (struct inode * inode, sector_t block,
 	       pointer to 'block'-th block use block, which is already
 	       allocated */
 	    struct cpu_key tmp_key;
-	    struct unfm_nodeinfo un = {0, 0};
+	    unp_t unf_single=0; // We use this in case we need to allocate only
+				// one block which is a fastpath
+	    unp_t *un;
+	    __u64 max_to_insert=MAX_ITEM_LEN(inode->i_sb->s_blocksize)/UNFM_P_SIZE;
+	    __u64 blocks_needed;
 
 	    RFALSE( pos_in_item != ih_item_len(ih) / UNFM_P_SIZE,
 		    "vs-804: invalid position for append");
@@ -776,23 +780,51 @@ int reiserfs_get_block (struct inode * inode, sector_t block,
 			  //pos_in_item * inode->i_sb->s_blocksize,
 			  TYPE_INDIRECT, 3);// key type is unimportant
 
-	    if (cpu_key_k_offset (&tmp_key) == cpu_key_k_offset (&key)) {
+	    blocks_needed = 1 + ((cpu_key_k_offset (&key) - cpu_key_k_offset (&tmp_key)) >> inode->i_sb->s_blocksize_bits);
+	    RFALSE( blocks_needed < 0, "green-805: invalid offset");
+
+	    if ( blocks_needed == 1 ) {
+		un = &unf_single;
+	    } else {
+		un=kmalloc( min(blocks_needed,max_to_insert)*UNFM_P_SIZE,
+			    GFP_ATOMIC); // We need to avoid scheduling.
+		if ( !un) {
+		    un = &unf_single;
+		    blocks_needed = 1;
+		    max_to_insert = 0;
+		} else
+		    memset(un, 0, UNFM_P_SIZE * min(blocks_needed,max_to_insert));
+	    }
+	    if ( blocks_needed <= max_to_insert) {
 		/* we are going to add target block to the file. Use allocated
 		   block for that */
-		un.unfm_nodenum = cpu_to_le32 (allocated_block_nr);
+		un[blocks_needed-1] = cpu_to_le32 (allocated_block_nr);
 		set_block_dev_mapped (bh_result, allocated_block_nr, inode);
 		set_buffer_new(bh_result);
 		done = 1;
 	    } else {
 		/* paste hole to the indirect item */
+		/* If kmalloc failed, max_to_insert becomes zero and it means we
+		   only have space for one block */
+		blocks_needed=max_to_insert?max_to_insert:1;
 	    }
-	    retval = reiserfs_paste_into_item (&th, &path, &tmp_key, (char *)&un, UNFM_P_SIZE);
+	    retval = reiserfs_paste_into_item (&th, &path, &tmp_key, (char *)un, UNFM_P_SIZE * blocks_needed);
+
+	    if (blocks_needed != 1)
+		kfree(un);
+
 	    if (retval) {
 		reiserfs_free_block (&th, allocated_block_nr);
 		goto failure;
 	    }
-	    if (un.unfm_nodenum)
+	    if (done) {
 		inode->i_blocks += inode->i_sb->s_blocksize / 512;
+	    } else {
+		/* We need to mark new file size in case this function will be
+		   interrupted/aborted later on. And we may do this only for
+		   holes. */
+		inode->i_size += inode->i_sb->s_blocksize * blocks_needed;
+	    }
 	    //mark_tail_converted (inode);
 	}
 

fs/reiserfs/tail_conversion.c

@@ -30,7 +30,7 @@ int direct2indirect (struct reiserfs_transaction_handle *th, struct inode * inod
                                 key of unfm pointer to be pasted */
     int	n_blk_size,
       n_retval;	  /* returned value for reiserfs_insert_item and clones */
-    struct unfm_nodeinfo unfm_ptr;  /* Handle on an unformatted node
+    unp_t unfm_ptr;  /* Handle on an unformatted node
 				       that will be inserted in the
 				       tree. */
 
@@ -59,8 +59,7 @@ int direct2indirect (struct reiserfs_transaction_handle *th, struct inode * inod
     
     p_le_ih = PATH_PITEM_HEAD (path);
 
-    unfm_ptr.unfm_nodenum = cpu_to_le32 (unbh->b_blocknr);
-    unfm_ptr.unfm_freespace = 0; // ???
+    unfm_ptr = cpu_to_le32 (unbh->b_blocknr);
     
     if ( is_statdata_le_ih (p_le_ih) )  {
 	/* Insert new indirect item. */