linux_dsm_epyc7002/fs/sysv/inode.c

371 lines
9.5 KiB
C
Raw Normal View History

/*
* linux/fs/sysv/inode.c
*
* minix/inode.c
* Copyright (C) 1991, 1992 Linus Torvalds
*
* xenix/inode.c
* Copyright (C) 1992 Doug Evans
*
* coh/inode.c
* Copyright (C) 1993 Pascal Haible, Bruno Haible
*
* sysv/inode.c
* Copyright (C) 1993 Paul B. Monday
*
* sysv/inode.c
* Copyright (C) 1993 Bruno Haible
* Copyright (C) 1997, 1998 Krzysztof G. Baranowski
*
* This file contains code for allocating/freeing inodes and for read/writing
* the superblock.
*/
#include <linux/highuid.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/buffer_head.h>
#include <linux/vfs.h>
#include <linux/writeback.h>
#include <linux/namei.h>
#include <asm/byteorder.h>
#include "sysv.h"
static int sysv_sync_fs(struct super_block *sb, int wait)
{
struct sysv_sb_info *sbi = SYSV_SB(sb);
unsigned long time = get_seconds(), old_time;
mutex_lock(&sbi->s_lock);
/*
* If we are going to write out the super block,
* then attach current time stamp.
* But if the filesystem was marked clean, keep it clean.
*/
old_time = fs32_to_cpu(sbi, *sbi->s_sb_time);
if (sbi->s_type == FSTYPE_SYSV4) {
if (*sbi->s_sb_state == cpu_to_fs32(sbi, 0x7c269d38 - old_time))
*sbi->s_sb_state = cpu_to_fs32(sbi, 0x7c269d38 - time);
*sbi->s_sb_time = cpu_to_fs32(sbi, time);
mark_buffer_dirty(sbi->s_bh2);
}
mutex_unlock(&sbi->s_lock);
return 0;
}
static int sysv_remount(struct super_block *sb, int *flags, char *data)
{
struct sysv_sb_info *sbi = SYSV_SB(sb);
fs: push sync_filesystem() down to the file system's remount_fs() Previously, the no-op "mount -o mount /dev/xxx" operation when the file system is already mounted read-write causes an implied, unconditional syncfs(). This seems pretty stupid, and it's certainly documented or guaraunteed to do this, nor is it particularly useful, except in the case where the file system was mounted rw and is getting remounted read-only. However, it's possible that there might be some file systems that are actually depending on this behavior. In most file systems, it's probably fine to only call sync_filesystem() when transitioning from read-write to read-only, and there are some file systems where this is not needed at all (for example, for a pseudo-filesystem or something like romfs). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: linux-fsdevel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Evgeniy Dushistov <dushistov@mail.ru> Cc: Jan Kara <jack@suse.cz> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Anders Larsen <al@alarsen.net> Cc: Phillip Lougher <phillip@squashfs.org.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz> Cc: Petr Vandrovec <petr@vandrovec.name> Cc: xfs@oss.sgi.com Cc: linux-btrfs@vger.kernel.org Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Cc: codalist@coda.cs.cmu.edu Cc: linux-ext4@vger.kernel.org Cc: linux-f2fs-devel@lists.sourceforge.net Cc: fuse-devel@lists.sourceforge.net Cc: cluster-devel@redhat.com Cc: linux-mtd@lists.infradead.org Cc: jfs-discussion@lists.sourceforge.net Cc: linux-nfs@vger.kernel.org Cc: linux-nilfs@vger.kernel.org Cc: linux-ntfs-dev@lists.sourceforge.net Cc: ocfs2-devel@oss.oracle.com Cc: reiserfs-devel@vger.kernel.org
2014-03-13 21:14:33 +07:00
sync_filesystem(sb);
if (sbi->s_forced_ro)
*flags |= MS_RDONLY;
return 0;
}
static void sysv_put_super(struct super_block *sb)
{
struct sysv_sb_info *sbi = SYSV_SB(sb);
if (!(sb->s_flags & MS_RDONLY)) {
/* XXX ext2 also updates the state here */
mark_buffer_dirty(sbi->s_bh1);
if (sbi->s_bh1 != sbi->s_bh2)
mark_buffer_dirty(sbi->s_bh2);
}
brelse(sbi->s_bh1);
if (sbi->s_bh1 != sbi->s_bh2)
brelse(sbi->s_bh2);
kfree(sbi);
}
static int sysv_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct sysv_sb_info *sbi = SYSV_SB(sb);
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
buf->f_type = sb->s_magic;
buf->f_bsize = sb->s_blocksize;
buf->f_blocks = sbi->s_ndatazones;
buf->f_bavail = buf->f_bfree = sysv_count_free_blocks(sb);
buf->f_files = sbi->s_ninodes;
buf->f_ffree = sysv_count_free_inodes(sb);
buf->f_namelen = SYSV_NAMELEN;
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
return 0;
}
/*
* NXI <-> N0XI for PDP, XIN <-> XIN0 for le32, NIX <-> 0NIX for be32
*/
static inline void read3byte(struct sysv_sb_info *sbi,
unsigned char * from, unsigned char * to)
{
if (sbi->s_bytesex == BYTESEX_PDP) {
to[0] = from[0];
to[1] = 0;
to[2] = from[1];
to[3] = from[2];
} else if (sbi->s_bytesex == BYTESEX_LE) {
to[0] = from[0];
to[1] = from[1];
to[2] = from[2];
to[3] = 0;
} else {
to[0] = 0;
to[1] = from[0];
to[2] = from[1];
to[3] = from[2];
}
}
static inline void write3byte(struct sysv_sb_info *sbi,
unsigned char * from, unsigned char * to)
{
if (sbi->s_bytesex == BYTESEX_PDP) {
to[0] = from[0];
to[1] = from[2];
to[2] = from[3];
} else if (sbi->s_bytesex == BYTESEX_LE) {
to[0] = from[0];
to[1] = from[1];
to[2] = from[2];
} else {
to[0] = from[1];
to[1] = from[2];
to[2] = from[3];
}
}
static const struct inode_operations sysv_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = page_follow_link_light,
.put_link = page_put_link,
.getattr = sysv_getattr,
};
void sysv_set_inode(struct inode *inode, dev_t rdev)
{
if (S_ISREG(inode->i_mode)) {
inode->i_op = &sysv_file_inode_operations;
inode->i_fop = &sysv_file_operations;
inode->i_mapping->a_ops = &sysv_aops;
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &sysv_dir_inode_operations;
inode->i_fop = &sysv_dir_operations;
inode->i_mapping->a_ops = &sysv_aops;
} else if (S_ISLNK(inode->i_mode)) {
if (inode->i_blocks) {
inode->i_op = &sysv_symlink_inode_operations;
inode->i_mapping->a_ops = &sysv_aops;
} else {
inode->i_op = &sysv_fast_symlink_inode_operations;
nd_terminate_link(SYSV_I(inode)->i_data, inode->i_size,
sizeof(SYSV_I(inode)->i_data) - 1);
}
} else
init_special_inode(inode, inode->i_mode, rdev);
}
struct inode *sysv_iget(struct super_block *sb, unsigned int ino)
{
struct sysv_sb_info * sbi = SYSV_SB(sb);
struct buffer_head * bh;
struct sysv_inode * raw_inode;
struct sysv_inode_info * si;
struct inode *inode;
unsigned int block;
if (!ino || ino > sbi->s_ninodes) {
printk("Bad inode number on dev %s: %d is out of range\n",
sb->s_id, ino);
return ERR_PTR(-EIO);
}
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
raw_inode = sysv_raw_inode(sb, ino, &bh);
if (!raw_inode) {
printk("Major problem: unable to read inode from dev %s\n",
inode->i_sb->s_id);
goto bad_inode;
}
/* SystemV FS: kludge permissions if ino==SYSV_ROOT_INO ?? */
inode->i_mode = fs16_to_cpu(sbi, raw_inode->i_mode);
i_uid_write(inode, (uid_t)fs16_to_cpu(sbi, raw_inode->i_uid));
i_gid_write(inode, (gid_t)fs16_to_cpu(sbi, raw_inode->i_gid));
set_nlink(inode, fs16_to_cpu(sbi, raw_inode->i_nlink));
inode->i_size = fs32_to_cpu(sbi, raw_inode->i_size);
inode->i_atime.tv_sec = fs32_to_cpu(sbi, raw_inode->i_atime);
inode->i_mtime.tv_sec = fs32_to_cpu(sbi, raw_inode->i_mtime);
inode->i_ctime.tv_sec = fs32_to_cpu(sbi, raw_inode->i_ctime);
inode->i_ctime.tv_nsec = 0;
inode->i_atime.tv_nsec = 0;
inode->i_mtime.tv_nsec = 0;
inode->i_blocks = 0;
si = SYSV_I(inode);
for (block = 0; block < 10+1+1+1; block++)
read3byte(sbi, &raw_inode->i_data[3*block],
(u8 *)&si->i_data[block]);
brelse(bh);
si->i_dir_start_lookup = 0;
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
sysv_set_inode(inode,
old_decode_dev(fs32_to_cpu(sbi, si->i_data[0])));
else
sysv_set_inode(inode, 0);
unlock_new_inode(inode);
return inode;
bad_inode:
iget_failed(inode);
return ERR_PTR(-EIO);
}
static int __sysv_write_inode(struct inode *inode, int wait)
{
struct super_block * sb = inode->i_sb;
struct sysv_sb_info * sbi = SYSV_SB(sb);
struct buffer_head * bh;
struct sysv_inode * raw_inode;
struct sysv_inode_info * si;
unsigned int ino, block;
int err = 0;
ino = inode->i_ino;
if (!ino || ino > sbi->s_ninodes) {
printk("Bad inode number on dev %s: %d is out of range\n",
inode->i_sb->s_id, ino);
return -EIO;
}
raw_inode = sysv_raw_inode(sb, ino, &bh);
if (!raw_inode) {
printk("unable to read i-node block\n");
return -EIO;
}
raw_inode->i_mode = cpu_to_fs16(sbi, inode->i_mode);
raw_inode->i_uid = cpu_to_fs16(sbi, fs_high2lowuid(i_uid_read(inode)));
raw_inode->i_gid = cpu_to_fs16(sbi, fs_high2lowgid(i_gid_read(inode)));
raw_inode->i_nlink = cpu_to_fs16(sbi, inode->i_nlink);
raw_inode->i_size = cpu_to_fs32(sbi, inode->i_size);
raw_inode->i_atime = cpu_to_fs32(sbi, inode->i_atime.tv_sec);
raw_inode->i_mtime = cpu_to_fs32(sbi, inode->i_mtime.tv_sec);
raw_inode->i_ctime = cpu_to_fs32(sbi, inode->i_ctime.tv_sec);
si = SYSV_I(inode);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
si->i_data[0] = cpu_to_fs32(sbi, old_encode_dev(inode->i_rdev));
for (block = 0; block < 10+1+1+1; block++)
write3byte(sbi, (u8 *)&si->i_data[block],
&raw_inode->i_data[3*block]);
mark_buffer_dirty(bh);
if (wait) {
sync_dirty_buffer(bh);
if (buffer_req(bh) && !buffer_uptodate(bh)) {
printk ("IO error syncing sysv inode [%s:%08x]\n",
sb->s_id, ino);
err = -EIO;
}
}
brelse(bh);
return 0;
}
int sysv_write_inode(struct inode *inode, struct writeback_control *wbc)
{
return __sysv_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL);
}
int sysv_sync_inode(struct inode *inode)
{
return __sysv_write_inode(inode, 1);
}
static void sysv_evict_inode(struct inode *inode)
{
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-04 04:47:49 +07:00
truncate_inode_pages_final(&inode->i_data);
if (!inode->i_nlink) {
inode->i_size = 0;
sysv_truncate(inode);
}
invalidate_inode_buffers(inode);
clear_inode(inode);
if (!inode->i_nlink)
sysv_free_inode(inode);
}
static struct kmem_cache *sysv_inode_cachep;
static struct inode *sysv_alloc_inode(struct super_block *sb)
{
struct sysv_inode_info *si;
si = kmem_cache_alloc(sysv_inode_cachep, GFP_KERNEL);
if (!si)
return NULL;
return &si->vfs_inode;
}
2011-01-07 13:49:49 +07:00
static void sysv_i_callback(struct rcu_head *head)
{
2011-01-07 13:49:49 +07:00
struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(sysv_inode_cachep, SYSV_I(inode));
}
2011-01-07 13:49:49 +07:00
static void sysv_destroy_inode(struct inode *inode)
{
call_rcu(&inode->i_rcu, sysv_i_callback);
}
static void init_once(void *p)
{
struct sysv_inode_info *si = (struct sysv_inode_info *)p;
inode_init_once(&si->vfs_inode);
}
const struct super_operations sysv_sops = {
.alloc_inode = sysv_alloc_inode,
.destroy_inode = sysv_destroy_inode,
.write_inode = sysv_write_inode,
.evict_inode = sysv_evict_inode,
.put_super = sysv_put_super,
.sync_fs = sysv_sync_fs,
.remount_fs = sysv_remount,
.statfs = sysv_statfs,
};
int __init sysv_init_icache(void)
{
sysv_inode_cachep = kmem_cache_create("sysv_inode_cache",
sizeof(struct sysv_inode_info), 0,
[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
SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD,
init_once);
if (!sysv_inode_cachep)
return -ENOMEM;
return 0;
}
void sysv_destroy_icache(void)
{
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(sysv_inode_cachep);
}