/* * fs/ext4/extents_status.c * * Written by Yongqiang Yang * Modified by * Allison Henderson * Hugh Dickins * Zheng Liu * * Ext4 extents status tree core functions. */ #include #include #include #include "ext4.h" #include /* * According to previous discussion in Ext4 Developer Workshop, we * will introduce a new structure called io tree to track all extent * status in order to solve some problems that we have met * (e.g. Reservation space warning), and provide extent-level locking. * Delay extent tree is the first step to achieve this goal. It is * original built by Yongqiang Yang. At that time it is called delay * extent tree, whose goal is only track delayed extents in memory to * simplify the implementation of fiemap and bigalloc, and introduce * lseek SEEK_DATA/SEEK_HOLE support. That is why it is still called * delay extent tree at the first commit. But for better understand * what it does, it has been rename to extent status tree. * * Step1: * Currently the first step has been done. All delayed extents are * tracked in the tree. It maintains the delayed extent when a delayed * allocation is issued, and the delayed extent is written out or * invalidated. Therefore the implementation of fiemap and bigalloc * are simplified, and SEEK_DATA/SEEK_HOLE are introduced. * * The following comment describes the implemenmtation of extent * status tree and future works. * * Step2: * In this step all extent status are tracked by extent status tree. * Thus, we can first try to lookup a block mapping in this tree before * finding it in extent tree. Hence, single extent cache can be removed * because extent status tree can do a better job. Extents in status * tree are loaded on-demand. Therefore, the extent status tree may not * contain all of the extents in a file. Meanwhile we define a shrinker * to reclaim memory from extent status tree because fragmented extent * tree will make status tree cost too much memory. written/unwritten/- * hole extents in the tree will be reclaimed by this shrinker when we * are under high memory pressure. Delayed extents will not be * reclimed because fiemap, bigalloc, and seek_data/hole need it. */ /* * Extent status tree implementation for ext4. * * * ========================================================================== * Extent status tree tracks all extent status. * * 1. Why we need to implement extent status tree? * * Without extent status tree, ext4 identifies a delayed extent by looking * up page cache, this has several deficiencies - complicated, buggy, * and inefficient code. * * FIEMAP, SEEK_HOLE/DATA, bigalloc, and writeout all need to know if a * block or a range of blocks are belonged to a delayed extent. * * Let us have a look at how they do without extent status tree. * -- FIEMAP * FIEMAP looks up page cache to identify delayed allocations from holes. * * -- SEEK_HOLE/DATA * SEEK_HOLE/DATA has the same problem as FIEMAP. * * -- bigalloc * bigalloc looks up page cache to figure out if a block is * already under delayed allocation or not to determine whether * quota reserving is needed for the cluster. * * -- writeout * Writeout looks up whole page cache to see if a buffer is * mapped, If there are not very many delayed buffers, then it is * time comsuming. * * With extent status tree implementation, FIEMAP, SEEK_HOLE/DATA, * bigalloc and writeout can figure out if a block or a range of * blocks is under delayed allocation(belonged to a delayed extent) or * not by searching the extent tree. * * * ========================================================================== * 2. Ext4 extent status tree impelmentation * * -- extent * A extent is a range of blocks which are contiguous logically and * physically. Unlike extent in extent tree, this extent in ext4 is * a in-memory struct, there is no corresponding on-disk data. There * is no limit on length of extent, so an extent can contain as many * blocks as they are contiguous logically and physically. * * -- extent status tree * Every inode has an extent status tree and all allocation blocks * are added to the tree with different status. The extent in the * tree are ordered by logical block no. * * -- operations on a extent status tree * There are three important operations on a delayed extent tree: find * next extent, adding a extent(a range of blocks) and removing a extent. * * -- race on a extent status tree * Extent status tree is protected by inode->i_es_lock. * * -- memory consumption * Fragmented extent tree will make extent status tree cost too much * memory. Hence, we will reclaim written/unwritten/hole extents from * the tree under a heavy memory pressure. * * * ========================================================================== * 3. Performance analysis * * -- overhead * 1. There is a cache extent for write access, so if writes are * not very random, adding space operaions are in O(1) time. * * -- gain * 2. Code is much simpler, more readable, more maintainable and * more efficient. * * * ========================================================================== * 4. TODO list * * -- Refactor delayed space reservation * * -- Extent-level locking */ static struct kmem_cache *ext4_es_cachep; static int __es_insert_extent(struct inode *inode, struct extent_status *newes); static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end); static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan); static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei); int __init ext4_init_es(void) { ext4_es_cachep = kmem_cache_create("ext4_extent_status", sizeof(struct extent_status), 0, (SLAB_RECLAIM_ACCOUNT), NULL); if (ext4_es_cachep == NULL) return -ENOMEM; return 0; } void ext4_exit_es(void) { if (ext4_es_cachep) kmem_cache_destroy(ext4_es_cachep); } void ext4_es_init_tree(struct ext4_es_tree *tree) { tree->root = RB_ROOT; tree->cache_es = NULL; } #ifdef ES_DEBUG__ static void ext4_es_print_tree(struct inode *inode) { struct ext4_es_tree *tree; struct rb_node *node; printk(KERN_DEBUG "status extents for inode %lu:", inode->i_ino); tree = &EXT4_I(inode)->i_es_tree; node = rb_first(&tree->root); while (node) { struct extent_status *es; es = rb_entry(node, struct extent_status, rb_node); printk(KERN_DEBUG " [%u/%u) %llu %x", es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); node = rb_next(node); } printk(KERN_DEBUG "\n"); } #else #define ext4_es_print_tree(inode) #endif static inline ext4_lblk_t ext4_es_end(struct extent_status *es) { BUG_ON(es->es_lblk + es->es_len < es->es_lblk); return es->es_lblk + es->es_len - 1; } /* * search through the tree for an delayed extent with a given offset. If * it can't be found, try to find next extent. */ static struct extent_status *__es_tree_search(struct rb_root *root, ext4_lblk_t lblk) { struct rb_node *node = root->rb_node; struct extent_status *es = NULL; while (node) { es = rb_entry(node, struct extent_status, rb_node); if (lblk < es->es_lblk) node = node->rb_left; else if (lblk > ext4_es_end(es)) node = node->rb_right; else return es; } if (es && lblk < es->es_lblk) return es; if (es && lblk > ext4_es_end(es)) { node = rb_next(&es->rb_node); return node ? rb_entry(node, struct extent_status, rb_node) : NULL; } return NULL; } /* * ext4_es_find_delayed_extent_range: find the 1st delayed extent covering * @es->lblk if it exists, otherwise, the next extent after @es->lblk. * * @inode: the inode which owns delayed extents * @lblk: the offset where we start to search * @end: the offset where we stop to search * @es: delayed extent that we found */ void ext4_es_find_delayed_extent_range(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es) { struct ext4_es_tree *tree = NULL; struct extent_status *es1 = NULL; struct rb_node *node; BUG_ON(es == NULL); BUG_ON(end < lblk); trace_ext4_es_find_delayed_extent_range_enter(inode, lblk); read_lock(&EXT4_I(inode)->i_es_lock); tree = &EXT4_I(inode)->i_es_tree; /* find extent in cache firstly */ es->es_lblk = es->es_len = es->es_pblk = 0; if (tree->cache_es) { es1 = tree->cache_es; if (in_range(lblk, es1->es_lblk, es1->es_len)) { es_debug("%u cached by [%u/%u) %llu %x\n", lblk, es1->es_lblk, es1->es_len, ext4_es_pblock(es1), ext4_es_status(es1)); goto out; } } es1 = __es_tree_search(&tree->root, lblk); out: if (es1 && !ext4_es_is_delayed(es1)) { while ((node = rb_next(&es1->rb_node)) != NULL) { es1 = rb_entry(node, struct extent_status, rb_node); if (es1->es_lblk > end) { es1 = NULL; break; } if (ext4_es_is_delayed(es1)) break; } } if (es1 && ext4_es_is_delayed(es1)) { tree->cache_es = es1; es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; } read_unlock(&EXT4_I(inode)->i_es_lock); trace_ext4_es_find_delayed_extent_range_exit(inode, es); } static void ext4_es_list_add(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (!list_empty(&ei->i_es_list)) return; spin_lock(&sbi->s_es_lock); if (list_empty(&ei->i_es_list)) { list_add_tail(&ei->i_es_list, &sbi->s_es_list); sbi->s_es_nr_inode++; } spin_unlock(&sbi->s_es_lock); } static void ext4_es_list_del(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); spin_lock(&sbi->s_es_lock); if (!list_empty(&ei->i_es_list)) { list_del_init(&ei->i_es_list); sbi->s_es_nr_inode--; WARN_ON_ONCE(sbi->s_es_nr_inode < 0); } spin_unlock(&sbi->s_es_lock); } static struct extent_status * ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk) { struct extent_status *es; es = kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC); if (es == NULL) return NULL; es->es_lblk = lblk; es->es_len = len; es->es_pblk = pblk; /* * We don't count delayed extent because we never try to reclaim them */ if (!ext4_es_is_delayed(es)) { if (!EXT4_I(inode)->i_es_shk_nr++) ext4_es_list_add(inode); percpu_counter_inc(&EXT4_SB(inode->i_sb)-> s_es_stats.es_stats_shk_cnt); } EXT4_I(inode)->i_es_all_nr++; percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt); return es; } static void ext4_es_free_extent(struct inode *inode, struct extent_status *es) { EXT4_I(inode)->i_es_all_nr--; percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt); /* Decrease the shrink counter when this es is not delayed */ if (!ext4_es_is_delayed(es)) { BUG_ON(EXT4_I(inode)->i_es_shk_nr == 0); if (!--EXT4_I(inode)->i_es_shk_nr) ext4_es_list_del(inode); percpu_counter_dec(&EXT4_SB(inode->i_sb)-> s_es_stats.es_stats_shk_cnt); } kmem_cache_free(ext4_es_cachep, es); } /* * Check whether or not two extents can be merged * Condition: * - logical block number is contiguous * - physical block number is contiguous * - status is equal */ static int ext4_es_can_be_merged(struct extent_status *es1, struct extent_status *es2) { if (ext4_es_type(es1) != ext4_es_type(es2)) return 0; if (((__u64) es1->es_len) + es2->es_len > EXT_MAX_BLOCKS) { pr_warn("ES assertion failed when merging extents. " "The sum of lengths of es1 (%d) and es2 (%d) " "is bigger than allowed file size (%d)\n", es1->es_len, es2->es_len, EXT_MAX_BLOCKS); WARN_ON(1); return 0; } if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk) return 0; if ((ext4_es_is_written(es1) || ext4_es_is_unwritten(es1)) && (ext4_es_pblock(es1) + es1->es_len == ext4_es_pblock(es2))) return 1; if (ext4_es_is_hole(es1)) return 1; /* we need to check delayed extent is without unwritten status */ if (ext4_es_is_delayed(es1) && !ext4_es_is_unwritten(es1)) return 1; return 0; } static struct extent_status * ext4_es_try_to_merge_left(struct inode *inode, struct extent_status *es) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es1; struct rb_node *node; node = rb_prev(&es->rb_node); if (!node) return es; es1 = rb_entry(node, struct extent_status, rb_node); if (ext4_es_can_be_merged(es1, es)) { es1->es_len += es->es_len; if (ext4_es_is_referenced(es)) ext4_es_set_referenced(es1); rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); es = es1; } return es; } static struct extent_status * ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es1; struct rb_node *node; node = rb_next(&es->rb_node); if (!node) return es; es1 = rb_entry(node, struct extent_status, rb_node); if (ext4_es_can_be_merged(es, es1)) { es->es_len += es1->es_len; if (ext4_es_is_referenced(es1)) ext4_es_set_referenced(es); rb_erase(node, &tree->root); ext4_es_free_extent(inode, es1); } return es; } #ifdef ES_AGGRESSIVE_TEST #include "ext4_extents.h" /* Needed when ES_AGGRESSIVE_TEST is defined */ static void ext4_es_insert_extent_ext_check(struct inode *inode, struct extent_status *es) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t ee_block; ext4_fsblk_t ee_start; unsigned short ee_len; int depth, ee_status, es_status; path = ext4_find_extent(inode, es->es_lblk, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return; depth = ext_depth(inode); ex = path[depth].p_ext; if (ex) { ee_block = le32_to_cpu(ex->ee_block); ee_start = ext4_ext_pblock(ex); ee_len = ext4_ext_get_actual_len(ex); ee_status = ext4_ext_is_unwritten(ex) ? 1 : 0; es_status = ext4_es_is_unwritten(es) ? 1 : 0; /* * Make sure ex and es are not overlap when we try to insert * a delayed/hole extent. */ if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) { if (in_range(es->es_lblk, ee_block, ee_len)) { pr_warn("ES insert assertion failed for " "inode: %lu we can find an extent " "at block [%d/%d/%llu/%c], but we " "want to add a delayed/hole extent " "[%d/%d/%llu/%x]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); } goto out; } /* * We don't check ee_block == es->es_lblk, etc. because es * might be a part of whole extent, vice versa. */ if (es->es_lblk < ee_block || ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) { pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), es_status ? 'u' : 'w'); goto out; } if (ee_status ^ es_status) { pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), es_status ? 'u' : 'w'); } } else { /* * We can't find an extent on disk. So we need to make sure * that we don't want to add an written/unwritten extent. */ if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) { pr_warn("ES insert assertion failed for inode: %lu " "can't find an extent at block %d but we want " "to add a written/unwritten extent " "[%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); } } out: ext4_ext_drop_refs(path); kfree(path); } static void ext4_es_insert_extent_ind_check(struct inode *inode, struct extent_status *es) { struct ext4_map_blocks map; int retval; /* * Here we call ext4_ind_map_blocks to lookup a block mapping because * 'Indirect' structure is defined in indirect.c. So we couldn't * access direct/indirect tree from outside. It is too dirty to define * this function in indirect.c file. */ map.m_lblk = es->es_lblk; map.m_len = es->es_len; retval = ext4_ind_map_blocks(NULL, inode, &map, 0); if (retval > 0) { if (ext4_es_is_delayed(es) || ext4_es_is_hole(es)) { /* * We want to add a delayed/hole extent but this * block has been allocated. */ pr_warn("ES insert assertion failed for inode: %lu " "We can find blocks but we want to add a " "delayed/hole extent [%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); return; } else if (ext4_es_is_written(es)) { if (retval != es->es_len) { pr_warn("ES insert assertion failed for " "inode: %lu retval %d != es_len %d\n", inode->i_ino, retval, es->es_len); return; } if (map.m_pblk != ext4_es_pblock(es)) { pr_warn("ES insert assertion failed for " "inode: %lu m_pblk %llu != " "es_pblk %llu\n", inode->i_ino, map.m_pblk, ext4_es_pblock(es)); return; } } else { /* * We don't need to check unwritten extent because * indirect-based file doesn't have it. */ BUG_ON(1); } } else if (retval == 0) { if (ext4_es_is_written(es)) { pr_warn("ES insert assertion failed for inode: %lu " "We can't find the block but we want to add " "a written extent [%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); return; } } } static inline void ext4_es_insert_extent_check(struct inode *inode, struct extent_status *es) { /* * We don't need to worry about the race condition because * caller takes i_data_sem locking. */ BUG_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ext4_es_insert_extent_ext_check(inode, es); else ext4_es_insert_extent_ind_check(inode, es); } #else static inline void ext4_es_insert_extent_check(struct inode *inode, struct extent_status *es) { } #endif static int __es_insert_extent(struct inode *inode, struct extent_status *newes) { struct ext4_es_tree *tree = &EXT4
/*
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 *
 * Copyright (C) 2000  Ani Joshi <ajoshi@unixbox.com>
 * Copyright (C) 2000, 2001, 06	 Ralf Baechle <ralf@linux-mips.org>
 * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
 */

#include <linux/types.h>
#include <linux/dma-mapping.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/scatterlist.h>
#include <linux/string.h>
#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/dma-contiguous.h>

#include <asm/cache.h>
#include <asm/cpu-type.h>
#include <asm/io.h>

#include <dma-coherence.h>

#ifdef CONFIG_DMA_MAYBE_COHERENT
int coherentio = 0;	/* User defined DMA coherency from command line. */
EXPORT_SYMBOL_GPL(coherentio);
int hw_coherentio = 0;	/* Actual hardware supported DMA coherency setting. */

static int __init setcoherentio(char *str)
{
	coherentio = 1;
	pr_info("Hardware DMA cache coherency (command line)\n");
	return 0;
}
early_param("coherentio", setcoherentio);

static int __init setnocoherentio(char *str)
{
	coherentio = 0;
	pr_info("Software DMA cache coherency (command line)\n");
	return 0;
}
early_param("nocoherentio", setnocoherentio);
#endif

static inline struct page *dma_addr_to_page(struct device *dev,
	dma_addr_t dma_addr)
{
	return pfn_to_page(
		plat_dma_addr_to_phys(dev, dma_addr) >> PAGE_SHIFT);
}

/*
 * The affected CPUs below in 'cpu_needs_post_dma_flush()' can
 * speculatively fill random cachelines with stale data at any time,
 * requiring an extra flush post-DMA.
 *
 * Warning on the terminology - Linux calls an uncached area coherent;
 * MIPS terminology calls memory areas with hardware maintained coherency
 * coherent.
 *
 * Note that the R14000 and R16000 should also be checked for in this
 * condition.  However this function is only called on non-I/O-coherent
 * systems and only the R10000 and R12000 are used in such systems, the
 * SGI IP28 Indigo² rsp. SGI IP32 aka O2.
 */
static inline int cpu_needs_post_dma_flush(struct device *dev)
{
	return !plat_device_is_coherent(dev) &&
	       (boot_cpu_type() == CPU_R10000 ||
		boot_cpu_type() == CPU_R12000 ||
		boot_cpu_type() == CPU_BMIPS5000);
}

static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
{
	gfp_t dma_flag;

	/* ignore region specifiers */
	gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);

#ifdef CONFIG_ISA
	if (dev == NULL)
		dma_flag = __GFP_DMA;
	else
#endif
#if define