linux_dsm_epyc7002/fs/fat/cache.c

345 lines
8.4 KiB
C
Raw Normal View History

/*
* linux/fs/fat/cache.c
*
* Written 1992,1993 by Werner Almesberger
*
* Mar 1999. AV. Changed cache, so that it uses the starting cluster instead
* of inode number.
* May 1999. AV. Fixed the bogosity with FAT32 (read "FAT28"). Fscking lusers.
*/
#include <linux/fs.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/buffer_head.h>
#include "fat.h"
/* this must be > 0. */
#define FAT_MAX_CACHE 8
struct fat_cache {
struct list_head cache_list;
int nr_contig; /* number of contiguous clusters */
int fcluster; /* cluster number in the file. */
int dcluster; /* cluster number on disk. */
};
struct fat_cache_id {
unsigned int id;
int nr_contig;
int fcluster;
int dcluster;
};
static inline int fat_max_cache(struct inode *inode)
{
return FAT_MAX_CACHE;
}
static struct kmem_cache *fat_cache_cachep;
static void init_once(void *foo)
{
struct fat_cache *cache = (struct fat_cache *)foo;
INIT_LIST_HEAD(&cache->cache_list);
}
int __init fat_cache_init(void)
{
fat_cache_cachep = kmem_cache_create("fat_cache",
sizeof(struct fat_cache),
[PATCH] cpuset memory spread: slab cache filesystems Mark file system inode and similar slab caches subject to SLAB_MEM_SPREAD memory spreading. If a slab cache is marked SLAB_MEM_SPREAD, then anytime that a task that's in a cpuset with the 'memory_spread_slab' option enabled goes to allocate from such a slab cache, the allocations are spread evenly over all the memory nodes (task->mems_allowed) allowed to that task, instead of favoring allocation on the node local to the current cpu. The following inode and similar caches are marked SLAB_MEM_SPREAD: file cache ==== ===== fs/adfs/super.c adfs_inode_cache fs/affs/super.c affs_inode_cache fs/befs/linuxvfs.c befs_inode_cache fs/bfs/inode.c bfs_inode_cache fs/block_dev.c bdev_cache fs/cifs/cifsfs.c cifs_inode_cache fs/coda/inode.c coda_inode_cache fs/dquot.c dquot fs/efs/super.c efs_inode_cache fs/ext2/super.c ext2_inode_cache fs/ext2/xattr.c (fs/mbcache.c) ext2_xattr fs/ext3/super.c ext3_inode_cache fs/ext3/xattr.c (fs/mbcache.c) ext3_xattr fs/fat/cache.c fat_cache fs/fat/inode.c fat_inode_cache fs/freevxfs/vxfs_super.c vxfs_inode fs/hpfs/super.c hpfs_inode_cache fs/isofs/inode.c isofs_inode_cache fs/jffs/inode-v23.c jffs_fm fs/jffs2/super.c jffs2_i fs/jfs/super.c jfs_ip fs/minix/inode.c minix_inode_cache fs/ncpfs/inode.c ncp_inode_cache fs/nfs/direct.c nfs_direct_cache fs/nfs/inode.c nfs_inode_cache fs/ntfs/super.c ntfs_big_inode_cache_name fs/ntfs/super.c ntfs_inode_cache fs/ocfs2/dlm/dlmfs.c dlmfs_inode_cache fs/ocfs2/super.c ocfs2_inode_cache fs/proc/inode.c proc_inode_cache fs/qnx4/inode.c qnx4_inode_cache fs/reiserfs/super.c reiser_inode_cache fs/romfs/inode.c romfs_inode_cache fs/smbfs/inode.c smb_inode_cache fs/sysv/inode.c sysv_inode_cache fs/udf/super.c udf_inode_cache fs/ufs/super.c ufs_inode_cache net/socket.c sock_inode_cache net/sunrpc/rpc_pipe.c rpc_inode_cache The choice of which slab caches to so mark was quite simple. I marked those already marked SLAB_RECLAIM_ACCOUNT, except for fs/xfs, dentry_cache, inode_cache, and buffer_head, which were marked in a previous patch. Even though SLAB_RECLAIM_ACCOUNT is for a different purpose, it marks the same potentially large file system i/o related slab caches as we need for memory spreading. Given that the rule now becomes "wherever you would have used a SLAB_RECLAIM_ACCOUNT slab cache flag before (usually the inode cache), use the SLAB_MEM_SPREAD flag too", this should be easy enough to maintain. Future file system writers will just copy one of the existing file system slab cache setups and tend to get it right without thinking. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 18:16:05 +07:00
0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD,
init_once);
if (fat_cache_cachep == NULL)
return -ENOMEM;
return 0;
}
void fat_cache_destroy(void)
{
kmem_cache_destroy(fat_cache_cachep);
}
static inline struct fat_cache *fat_cache_alloc(struct inode *inode)
{
return kmem_cache_alloc(fat_cache_cachep, GFP_NOFS);
}
static inline void fat_cache_free(struct fat_cache *cache)
{
BUG_ON(!list_empty(&cache->cache_list));
kmem_cache_free(fat_cache_cachep, cache);
}
static inline void fat_cache_update_lru(struct inode *inode,
struct fat_cache *cache)
{
if (MSDOS_I(inode)->cache_lru.next != &cache->cache_list)
list_move(&cache->cache_list, &MSDOS_I(inode)->cache_lru);
}
static int fat_cache_lookup(struct inode *inode, int fclus,
struct fat_cache_id *cid,
int *cached_fclus, int *cached_dclus)
{
static struct fat_cache nohit = { .fcluster = 0, };
struct fat_cache *hit = &nohit, *p;
int offset = -1;
spin_lock(&MSDOS_I(inode)->cache_lru_lock);
list_for_each_entry(p, &MSDOS_I(inode)->cache_lru, cache_list) {
/* Find the cache of "fclus" or nearest cache. */
if (p->fcluster <= fclus && hit->fcluster < p->fcluster) {
hit = p;
if ((hit->fcluster + hit->nr_contig) < fclus) {
offset = hit->nr_contig;
} else {
offset = fclus - hit->fcluster;
break;
}
}
}
if (hit != &nohit) {
fat_cache_update_lru(inode, hit);
cid->id = MSDOS_I(inode)->cache_valid_id;
cid->nr_contig = hit->nr_contig;
cid->fcluster = hit->fcluster;
cid->dcluster = hit->dcluster;
*cached_fclus = cid->fcluster + offset;
*cached_dclus = cid->dcluster + offset;
}
spin_unlock(&MSDOS_I(inode)->cache_lru_lock);
return offset;
}
static struct fat_cache *fat_cache_merge(struct inode *inode,
struct fat_cache_id *new)
{
struct fat_cache *p;
list_for_each_entry(p, &MSDOS_I(inode)->cache_lru, cache_list) {
/* Find the same part as "new" in cluster-chain. */
if (p->fcluster == new->fcluster) {
BUG_ON(p->dcluster != new->dcluster);
if (new->nr_contig > p->nr_contig)
p->nr_contig = new->nr_contig;
return p;
}
}
return NULL;
}
static void fat_cache_add(struct inode *inode, struct fat_cache_id *new)
{
struct fat_cache *cache, *tmp;
if (new->fcluster == -1) /* dummy cache */
return;
spin_lock(&MSDOS_I(inode)->cache_lru_lock);
if (new->id != FAT_CACHE_VALID &&
new->id != MSDOS_I(inode)->cache_valid_id)
goto out; /* this cache was invalidated */
cache = fat_cache_merge(inode, new);
if (cache == NULL) {
if (MSDOS_I(inode)->nr_caches < fat_max_cache(inode)) {
MSDOS_I(inode)->nr_caches++;
spin_unlock(&MSDOS_I(inode)->cache_lru_lock);
tmp = fat_cache_alloc(inode);
spin_lock(&MSDOS_I(inode)->cache_lru_lock);
cache = fat_cache_merge(inode, new);
if (cache != NULL) {
MSDOS_I(inode)->nr_caches--;
fat_cache_free(tmp);
goto out_update_lru;
}
cache = tmp;
} else {
struct list_head *p = MSDOS_I(inode)->cache_lru.prev;
cache = list_entry(p, struct fat_cache, cache_list);
}
cache->fcluster = new->fcluster;
cache->dcluster = new->dcluster;
cache->nr_contig = new->nr_contig;
}
out_update_lru:
fat_cache_update_lru(inode, cache);
out:
spin_unlock(&MSDOS_I(inode)->cache_lru_lock);
}
/*
* Cache invalidation occurs rarely, thus the LRU chain is not updated. It
* fixes itself after a while.
*/
static void __fat_cache_inval_inode(struct inode *inode)
{
struct msdos_inode_info *i = MSDOS_I(inode);
struct fat_cache *cache;
while (!list_empty(&i->cache_lru)) {
cache = list_entry(i->cache_lru.next, struct fat_cache, cache_list);
list_del_init(&cache->cache_list);
i->nr_caches--;
fat_cache_free(cache);
}
/* Update. The copy of caches before this id is discarded. */
i->cache_valid_id++;
if (i->cache_valid_id == FAT_CACHE_VALID)
i->cache_valid_id++;
}
void fat_cache_inval_inode(struct inode *inode)
{
spin_lock(&MSDOS_I(inode)->cache_lru_lock);
__fat_cache_inval_inode(inode);
spin_unlock(&MSDOS_I(inode)->cache_lru_lock);
}
static inline int cache_contiguous(struct fat_cache_id *cid, int dclus)
{
cid->nr_contig++;
return ((cid->dcluster + cid->nr_contig) == dclus);
}
static inline void cache_init(struct fat_cache_id *cid, int fclus, int dclus)
{
cid->id = FAT_CACHE_VALID;
cid->fcluster = fclus;
cid->dcluster = dclus;
cid->nr_contig = 0;
}
int fat_get_cluster(struct inode *inode, int cluster, int *fclus, int *dclus)
{
struct super_block *sb = inode->i_sb;
const int limit = sb->s_maxbytes >> MSDOS_SB(sb)->cluster_bits;
struct fat_entry fatent;
struct fat_cache_id cid;
int nr;
BUG_ON(MSDOS_I(inode)->i_start == 0);
*fclus = 0;
*dclus = MSDOS_I(inode)->i_start;
if (cluster == 0)
return 0;
if (fat_cache_lookup(inode, cluster, &cid, fclus, dclus) < 0) {
/*
* dummy, always not contiguous
* This is reinitialized by cache_init(), later.
*/
cache_init(&cid, -1, -1);
}
fatent_init(&fatent);
while (*fclus < cluster) {
/* prevent the infinite loop of cluster chain */
if (*fclus > limit) {
fat_fs_error_ratelimit(sb,
"%s: detected the cluster chain loop"
" (i_pos %lld)", __func__,
MSDOS_I(inode)->i_pos);
nr = -EIO;
goto out;
}
nr = fat_ent_read(inode, &fatent, *dclus);
if (nr < 0)
goto out;
else if (nr == FAT_ENT_FREE) {
fat_fs_error_ratelimit(sb, "%s: invalid cluster chain"
" (i_pos %lld)", __func__,
MSDOS_I(inode)->i_pos);
nr = -EIO;
goto out;
} else if (nr == FAT_ENT_EOF) {
fat_cache_add(inode, &cid);
goto out;
}
(*fclus)++;
*dclus = nr;
if (!cache_contiguous(&cid, *dclus))
cache_init(&cid, *fclus, *dclus);
}
nr = 0;
fat_cache_add(inode, &cid);
out:
fatent_brelse(&fatent);
return nr;
}
static int fat_bmap_cluster(struct inode *inode, int cluster)
{
struct super_block *sb = inode->i_sb;
int ret, fclus, dclus;
if (MSDOS_I(inode)->i_start == 0)
return 0;
ret = fat_get_cluster(inode, cluster, &fclus, &dclus);
if (ret < 0)
return ret;
else if (ret == FAT_ENT_EOF) {
fat_fs_error(sb, "%s: request beyond EOF (i_pos %lld)",
__func__, MSDOS_I(inode)->i_pos);
return -EIO;
}
return dclus;
}
int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
unsigned long *mapped_blocks, int create)
{
struct super_block *sb = inode->i_sb;
struct msdos_sb_info *sbi = MSDOS_SB(sb);
const unsigned long blocksize = sb->s_blocksize;
const unsigned char blocksize_bits = sb->s_blocksize_bits;
sector_t last_block;
int cluster, offset;
*phys = 0;
*mapped_blocks = 0;
if ((sbi->fat_bits != 32) && (inode->i_ino == MSDOS_ROOT_INO)) {
if (sector < (sbi->dir_entries >> sbi->dir_per_block_bits)) {
*phys = sector + sbi->dir_start;
*mapped_blocks = 1;
}
return 0;
}
last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits;
if (sector >= last_block) {
if (!create)
return 0;
/*
* ->mmu_private can access on only allocation path.
* (caller must hold ->i_mutex)
*/
last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1))
>> blocksize_bits;
if (sector >= last_block)
return 0;
}
cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
offset = sector & (sbi->sec_per_clus - 1);
cluster = fat_bmap_cluster(inode, cluster);
if (cluster < 0)
return cluster;
else if (cluster) {
*phys = fat_clus_to_blknr(sbi, cluster) + offset;
*mapped_blocks = sbi->sec_per_clus - offset;
if (*mapped_blocks > last_block - sector)
*mapped_blocks = last_block - sector;
}
return 0;
}