summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/autofs4/autofs_i.h1
-rw-r--r--fs/autofs4/inode.c1
-rw-r--r--fs/autofs4/waitq.c40
-rw-r--r--fs/block_dev.c13
-rw-r--r--fs/btrfs/disk-io.c5
-rw-r--r--fs/ceph/dir.c76
-rw-r--r--fs/ceph/export.c6
-rw-r--r--fs/ceph/inode.c3
-rw-r--r--fs/ceph/mds_client.c4
-rw-r--r--fs/ceph/super.c16
-rw-r--r--fs/ceph/super.h1
-rw-r--r--fs/ceph/xattr.c22
-rw-r--r--fs/coda/cnode.c38
-rw-r--r--fs/coda/coda_fs_i.h4
-rw-r--r--fs/coda/dir.c29
-rw-r--r--fs/coda/inode.c10
-rw-r--r--fs/dcache.c26
-rw-r--r--fs/direct-io.c57
-rw-r--r--fs/eventpoll.c234
-rw-r--r--fs/fuse/dev.c57
-rw-r--r--fs/fuse/dir.c58
-rw-r--r--fs/fuse/file.c58
-rw-r--r--fs/fuse/fuse_i.h10
-rw-r--r--fs/hfsplus/super.c11
-rw-r--r--fs/hugetlbfs/inode.c3
-rw-r--r--fs/nfs/internal.h2
-rw-r--r--fs/nfs/write.c4
-rw-r--r--fs/pipe.c2
-rw-r--r--fs/proc/array.c7
-rw-r--r--fs/proc/base.c2
-rw-r--r--fs/ubifs/debug.c90
-rw-r--r--fs/ubifs/debug.h44
-rw-r--r--fs/ubifs/journal.c7
-rw-r--r--fs/ubifs/replay.c8
-rw-r--r--fs/ubifs/tnc.c55
-rw-r--r--fs/ubifs/tnc_misc.c10
36 files changed, 696 insertions, 318 deletions
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 5869d4e974a9..d8d8e7ba6a1e 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -116,6 +116,7 @@ struct autofs_sb_info {
int needs_reghost;
struct super_block *sb;
struct mutex wq_mutex;
+ struct mutex pipe_mutex;
spinlock_t fs_lock;
struct autofs_wait_queue *queues; /* Wait queue pointer */
spinlock_t lookup_lock;
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index 2ba44c79d548..e16980b00b8d 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -225,6 +225,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
sbi->min_proto = 0;
sbi->max_proto = 0;
mutex_init(&sbi->wq_mutex);
+ mutex_init(&sbi->pipe_mutex);
spin_lock_init(&sbi->fs_lock);
sbi->queues = NULL;
spin_lock_init(&sbi->lookup_lock);
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index e1fbdeef85db..da8876d38a7b 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -56,26 +56,27 @@ void autofs4_catatonic_mode(struct autofs_sb_info *sbi)
mutex_unlock(&sbi->wq_mutex);
}
-static int autofs4_write(struct file *file, const void *addr, int bytes)
+static int autofs4_write(struct autofs_sb_info *sbi,
+ struct file *file, const void *addr, int bytes)
{
unsigned long sigpipe, flags;
mm_segment_t fs;
const char *data = (const char *)addr;
ssize_t wr = 0;
- /** WARNING: this is not safe for writing more than PIPE_BUF bytes! **/
-
sigpipe = sigismember(&current->pending.signal, SIGPIPE);
/* Save pointer to user space and point back to kernel space */
fs = get_fs();
set_fs(KERNEL_DS);
+ mutex_lock(&sbi->pipe_mutex);
while (bytes &&
(wr = file->f_op->write(file,data,bytes,&file->f_pos)) > 0) {
data += wr;
bytes -= wr;
}
+ mutex_unlock(&sbi->pipe_mutex);
set_fs(fs);
@@ -110,6 +111,13 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
pkt.hdr.proto_version = sbi->version;
pkt.hdr.type = type;
+ mutex_lock(&sbi->wq_mutex);
+
+ /* Check if we have become catatonic */
+ if (sbi->catatonic) {
+ mutex_unlock(&sbi->wq_mutex);
+ return;
+ }
switch (type) {
/* Kernel protocol v4 missing and expire packets */
case autofs_ptype_missing:
@@ -163,22 +171,18 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
}
default:
printk("autofs4_notify_daemon: bad type %d!\n", type);
+ mutex_unlock(&sbi->wq_mutex);
return;
}
- /* Check if we have become catatonic */
- mutex_lock(&sbi->wq_mutex);
- if (!sbi->catatonic) {
- pipe = sbi->pipe;
- get_file(pipe);
- }
+ pipe = sbi->pipe;
+ get_file(pipe);
+
mutex_unlock(&sbi->wq_mutex);
- if (pipe) {
- if (autofs4_write(pipe, &pkt, pktsz))
- autofs4_catatonic_mode(sbi);
- fput(pipe);
- }
+ if (autofs4_write(sbi, pipe, &pkt, pktsz))
+ autofs4_catatonic_mode(sbi);
+ fput(pipe);
}
static int autofs4_getpath(struct autofs_sb_info *sbi,
@@ -257,6 +261,9 @@ static int validate_request(struct autofs_wait_queue **wait,
struct autofs_wait_queue *wq;
struct autofs_info *ino;
+ if (sbi->catatonic)
+ return -ENOENT;
+
/* Wait in progress, continue; */
wq = autofs4_find_wait(sbi, qstr);
if (wq) {
@@ -289,6 +296,9 @@ static int validate_request(struct autofs_wait_queue **wait,
if (mutex_lock_interruptible(&sbi->wq_mutex))
return -EINTR;
+ if (sbi->catatonic)
+ return -ENOENT;
+
wq = autofs4_find_wait(sbi, qstr);
if (wq) {
*wait = wq;
@@ -389,7 +399,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
ret = validate_request(&wq, sbi, &qstr, dentry, notify);
if (ret <= 0) {
- if (ret == 0)
+ if (ret != -EINTR)
mutex_unlock(&sbi->wq_mutex);
kfree(qstr.name);
return ret;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 69a5b6fbee2b..0e575d1304b4 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -25,7 +25,6 @@
#include <linux/uio.h>
#include <linux/namei.h>
#include <linux/log2.h>
-#include <linux/kmemleak.h>
#include <linux/cleancache.h>
#include <asm/uaccess.h>
#include "internal.h"
@@ -521,7 +520,7 @@ static struct super_block *blockdev_superblock __read_mostly;
void __init bdev_cache_init(void)
{
int err;
- struct vfsmount *bd_mnt;
+ static struct vfsmount *bd_mnt;
bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
@@ -533,12 +532,7 @@ void __init bdev_cache_init(void)
bd_mnt = kern_mount(&bd_type);
if (IS_ERR(bd_mnt))
panic("Cannot create bdev pseudo-fs");
- /*
- * This vfsmount structure is only used to obtain the
- * blockdev_superblock, so tell kmemleak not to report it.
- */
- kmemleak_not_leak(bd_mnt);
- blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */
+ blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */
}
/*
@@ -1145,6 +1139,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
mutex_lock_nested(&bdev->bd_mutex, for_part);
if (!bdev->bd_openers) {
bdev->bd_disk = disk;
+ bdev->bd_queue = disk->queue;
bdev->bd_contains = bdev;
if (!partno) {
struct backing_dev_info *bdi;
@@ -1165,6 +1160,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
disk_put_part(bdev->bd_part);
bdev->bd_part = NULL;
bdev->bd_disk = NULL;
+ bdev->bd_queue = NULL;
mutex_unlock(&bdev->bd_mutex);
disk_unblock_events(disk);
put_disk(disk);
@@ -1238,6 +1234,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
disk_put_part(bdev->bd_part);
bdev->bd_disk = NULL;
bdev->bd_part = NULL;
+ bdev->bd_queue = NULL;
bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info);
if (bdev != bdev->bd_contains)
__blkdev_put(bdev->bd_contains, mode, 1);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f99a099a7747..d8525662ca7a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -872,7 +872,8 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
#ifdef CONFIG_MIGRATION
static int btree_migratepage(struct address_space *mapping,
- struct page *newpage, struct page *page)
+ struct page *newpage, struct page *page,
+ enum migrate_mode mode)
{
/*
* we can't safely write a btree page from here,
@@ -887,7 +888,7 @@ static int btree_migratepage(struct address_space *mapping,
if (page_has_private(page) &&
!try_to_release_page(page, GFP_KERNEL))
return -EAGAIN;
- return migrate_page(mapping, newpage, page);
+ return migrate_page(mapping, newpage, page, mode);
}
#endif
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 74fd74719dc2..618246bc2196 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -973,7 +973,7 @@ static int dentry_lease_is_valid(struct dentry *dentry)
spin_lock(&dentry->d_lock);
di = ceph_dentry(dentry);
- if (di && di->lease_session) {
+ if (di->lease_session) {
s = di->lease_session;
spin_lock(&s->s_cap_lock);
gen = s->s_cap_gen;
@@ -1072,13 +1072,11 @@ static void ceph_d_release(struct dentry *dentry)
struct ceph_dentry_info *di = ceph_dentry(dentry);
dout("d_release %p\n", dentry);
- if (di) {
- ceph_dentry_lru_del(dentry);
- if (di->lease_session)
- ceph_put_mds_session(di->lease_session);
- kmem_cache_free(ceph_dentry_cachep, di);
- dentry->d_fsdata = NULL;
- }
+ ceph_dentry_lru_del(dentry);
+ if (di->lease_session)
+ ceph_put_mds_session(di->lease_session);
+ kmem_cache_free(ceph_dentry_cachep, di);
+ dentry->d_fsdata = NULL;
}
static int ceph_snapdir_d_revalidate(struct dentry *dentry,
@@ -1096,17 +1094,36 @@ static int ceph_snapdir_d_revalidate(struct dentry *dentry,
*/
void ceph_dir_set_complete(struct inode *inode)
{
- /* not yet implemented */
+ struct dentry *dentry = d_find_any_alias(inode);
+
+ if (dentry && ceph_dentry(dentry) &&
+ ceph_test_mount_opt(ceph_sb_to_client(dentry->d_sb), DCACHE)) {
+ dout(" marking %p (%p) complete\n", inode, dentry);
+ set_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags);
+ }
+ dput(dentry);
}
void ceph_dir_clear_complete(struct inode *inode)
{
- /* not yet implemented */
+ struct dentry *dentry = d_find_any_alias(inode);
+
+ if (dentry && ceph_dentry(dentry)) {
+ dout(" marking %p (%p) complete\n", inode, dentry);
+ set_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags);
+ }
+ dput(dentry);
}
bool ceph_dir_test_complete(struct inode *inode)
{
- /* not yet implemented */
+ struct dentry *dentry = d_find_any_alias(inode);
+
+ if (dentry && ceph_dentry(dentry)) {
+ dout(" marking %p (%p) NOT complete\n", inode, dentry);
+ clear_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags);
+ }
+ dput(dentry);
return false;
}
@@ -1220,6 +1237,7 @@ static int ceph_dir_fsync(struct file *file, loff_t start, loff_t end,
do {
ceph_mdsc_get_request(req);
spin_unlock(&ci->i_unsafe_lock);
+
dout("dir_fsync %p wait on tid %llu (until %llu)\n",
inode, req->r_tid, last_tid);
if (req->r_timeout) {
@@ -1232,9 +1250,9 @@ static int ceph_dir_fsync(struct file *file, loff_t start, loff_t end,
} else {
wait_for_completion(&req->r_safe_completion);
}
- spin_lock(&ci->i_unsafe_lock);
ceph_mdsc_put_request(req);
+ spin_lock(&ci->i_unsafe_lock);
if (ret || list_empty(head))
break;
req = list_entry(head->next,
@@ -1259,13 +1277,11 @@ void ceph_dentry_lru_add(struct dentry *dn)
dout("dentry_lru_add %p %p '%.*s'\n", di, dn,
dn->d_name.len, dn->d_name.name);
- if (di) {
- mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
- spin_lock(&mdsc->dentry_lru_lock);
- list_add_tail(&di->lru, &mdsc->dentry_lru);
- mdsc->num_dentry++;
- spin_unlock(&mdsc->dentry_lru_lock);
- }
+ mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
+ spin_lock(&mdsc->dentry_lru_lock);
+ list_add_tail(&di->lru, &mdsc->dentry_lru);
+ mdsc->num_dentry++;
+ spin_unlock(&mdsc->dentry_lru_lock);
}
void ceph_dentry_lru_touch(struct dentry *dn)
@@ -1275,12 +1291,10 @@ void ceph_dentry_lru_touch(struct dentry *dn)
dout("dentry_lru_touch %p %p '%.*s' (offset %lld)\n", di, dn,
dn->d_name.len, dn->d_name.name, di->offset);
- if (di) {
- mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
- spin_lock(&mdsc->dentry_lru_lock);
- list_move_tail(&di->lru, &mdsc->dentry_lru);
- spin_unlock(&mdsc->dentry_lru_lock);
- }
+ mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
+ spin_lock(&mdsc->dentry_lru_lock);
+ list_move_tail(&di->lru, &mdsc->dentry_lru);
+ spin_unlock(&mdsc->dentry_lru_lock);
}
void ceph_dentry_lru_del(struct dentry *dn)
@@ -1290,13 +1304,11 @@ void ceph_dentry_lru_del(struct dentry *dn)
dout("dentry_lru_del %p %p '%.*s'\n", di, dn,
dn->d_name.len, dn->d_name.name);
- if (di) {
- mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
- spin_lock(&mdsc->dentry_lru_lock);
- list_del_init(&di->lru);
- mdsc->num_dentry--;
- spin_unlock(&mdsc->dentry_lru_lock);
- }
+ mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
+ spin_lock(&mdsc->dentry_lru_lock);
+ list_del_init(&di->lru);
+ mdsc->num_dentry--;
+ spin_unlock(&mdsc->dentry_lru_lock);
}
/*
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 9fbcdecaaccd..fbb2a643ef10 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -56,9 +56,7 @@ static int ceph_encode_fh(struct dentry *dentry, u32 *rawfh, int *max_len,
return -EINVAL;
spin_lock(&dentry->d_lock);
- parent = dget(dentry->d_parent);
- spin_unlock(&dentry->d_lock);
-
+ parent = dentry->d_parent;
if (*max_len >= connected_handle_length) {
dout("encode_fh %p connectable\n", dentry);
cfh->ino = ceph_ino(dentry->d_inode);
@@ -81,7 +79,7 @@ static int ceph_encode_fh(struct dentry *dentry, u32 *rawfh, int *max_len,
*max_len = handle_length;
type = 255;
}
- dput(parent);
+ spin_unlock(&dentry->d_lock);
return type;
}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 25283e7a37f8..2c489378b4cd 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -850,11 +850,12 @@ static void ceph_set_dentry_offset(struct dentry *dn)
{
struct dentry *dir = dn->d_parent;
struct inode *inode = dir->d_inode;
- struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_inode_info *ci;
struct ceph_dentry_info *di;
BUG_ON(!inode);
+ ci = ceph_inode(inode);
di = ceph_dentry(dn);
spin_lock(&ci->i_ceph_lock);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 6203d805eb45..23ab6a3f1825 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2772,7 +2772,7 @@ static void handle_lease(struct ceph_mds_client *mdsc,
di = ceph_dentry(dentry);
switch (h->action) {
case CEPH_MDS_LEASE_REVOKE:
- if (di && di->lease_session == session) {
+ if (di->lease_session == session) {
if (ceph_seq_cmp(di->lease_seq, seq) > 0)
h->seq = cpu_to_le32(di->lease_seq);
__ceph_mdsc_drop_dentry_lease(dentry);
@@ -2781,7 +2781,7 @@ static void handle_lease(struct ceph_mds_client *mdsc,
break;
case CEPH_MDS_LEASE_RENEW:
- if (di && di->lease_session == session &&
+ if (di->lease_session == session &&
di->lease_gen == session->s_cap_gen &&
di->lease_renew_from &&
di->lease_renew_after == 0) {
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 48f61a12af66..00de2c9568cd 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -131,6 +131,8 @@ enum {
Opt_rbytes,
Opt_norbytes,
Opt_noasyncreaddir,
+ Opt_dcache,
+ Opt_nodcache,
Opt_ino32,
};
@@ -152,6 +154,8 @@ static match_table_t fsopt_tokens = {
{Opt_rbytes, "rbytes"},
{Opt_norbytes, "norbytes"},
{Opt_noasyncreaddir, "noasyncreaddir"},
+ {Opt_dcache, "dcache"},
+ {Opt_nodcache, "nodcache"},
{Opt_ino32, "ino32"},
{-1, NULL}
};
@@ -231,6 +235,12 @@ static int parse_fsopt_token(char *c, void *private)
case Opt_noasyncreaddir:
fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR;
break;
+ case Opt_dcache:
+ fsopt->flags |= CEPH_MOUNT_OPT_DCACHE;
+ break;
+ case Opt_nodcache:
+ fsopt->flags &= ~CEPH_MOUNT_OPT_DCACHE;
+ break;
case Opt_ino32:
fsopt->flags |= CEPH_MOUNT_OPT_INO32;
break;
@@ -377,6 +387,10 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
seq_puts(m, ",norbytes");
if (fsopt->flags & CEPH_MOUNT_OPT_NOASYNCREADDIR)
seq_puts(m, ",noasyncreaddir");
+ if (fsopt->flags & CEPH_MOUNT_OPT_DCACHE)
+ seq_puts(m, ",dcache");
+ else
+ seq_puts(m, ",nodcache");
if (fsopt->wsize)
seq_printf(m, ",wsize=%d", fsopt->wsize);
@@ -647,10 +661,10 @@ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc,
root = ERR_PTR(-ENOMEM);
goto out;
}
- ceph_init_dentry(root);
} else {
root = d_obtain_alias(inode);
}
+ ceph_init_dentry(root);
dout("open_root_inode success, root dentry is %p\n", root);
} else {
root = ERR_PTR(err);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index cb3652b37271..1421f3d875a2 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -28,6 +28,7 @@
#define CEPH_MOUNT_OPT_RBYTES (1<<5) /* dir st_bytes = rbytes */
#define CEPH_MOUNT_OPT_NOASYNCREADDIR (1<<7) /* no dcache readdir */
#define CEPH_MOUNT_OPT_INO32 (1<<8) /* 32 bit inos */
+#define CEPH_MOUNT_OPT_DCACHE (1<<9) /* use dcache for readdir etc */
#define CEPH_MOUNT_OPT_DEFAULT (CEPH_MOUNT_OPT_RBYTES)
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index a5e36e4488a7..857214ae8c08 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -818,6 +818,7 @@ int ceph_removexattr(struct dentry *dentry, const char *name)
struct ceph_vxattr_cb *vxattrs = ceph_inode_vxattrs(inode);
int issued;
int err;
+ int required_blob_size;
int dirty;
if (ceph_snap(inode) != CEPH_NOSNAP)
@@ -833,14 +834,34 @@ int ceph_removexattr(struct dentry *dentry, const char *name)
return -EOPNOTSUPP;
}
+ err = -ENOMEM;
spin_lock(&ci->i_ceph_lock);
__build_xattrs(inode);
+retry:
issued = __ceph_caps_issued(ci, NULL);
dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued));
if (!(issued & CEPH_CAP_XATTR_EXCL))
goto do_sync;
+ required_blob_size = __get_required_blob_size(ci, 0, 0);
+
+ if (!ci->i_xattrs.prealloc_blob ||
+ required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) {
+ struct ceph_buffer *blob;
+
+ spin_unlock(&ci->i_ceph_lock);
+ dout(" preaallocating new blob size=%d\n", required_blob_size);
+ blob = ceph_buffer_new(required_blob_size, GFP_NOFS);
+ if (!blob)
+ goto out;
+ spin_lock(&ci->i_ceph_lock);
+ if (ci->i_xattrs.prealloc_blob)
+ ceph_buffer_put(ci->i_xattrs.prealloc_blob);
+ ci->i_xattrs.prealloc_blob = blob;
+ goto retry;
+ }
+
err = __remove_xattr_by_name(ceph_inode(inode), name);
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
ci->i_xattrs.dirty = true;
@@ -853,6 +874,7 @@ int ceph_removexattr(struct dentry *dentry, const char *name)
do_sync:
spin_unlock(&ci->i_ceph_lock);
err = ceph_send_removexattr(dentry, name);
+out:
return err;
}
diff --git a/fs/coda/cnode.c b/fs/coda/cnode.c
index 6475877b0763..911cf30d057d 100644
--- a/fs/coda/cnode.c
+++ b/fs/coda/cnode.c
@@ -88,24 +88,21 @@ struct inode * coda_iget(struct super_block * sb, struct CodaFid * fid,
- link the two up if this is needed
- fill in the attributes
*/
-int coda_cnode_make(struct inode **inode, struct CodaFid *fid, struct super_block *sb)
+struct inode *coda_cnode_make(struct CodaFid *fid, struct super_block *sb)
{
struct coda_vattr attr;
+ struct inode *inode;
int error;
/* We get inode numbers from Venus -- see venus source */
error = venus_getattr(sb, fid, &attr);
- if ( error ) {
- *inode = NULL;
- return error;
- }
+ if (error)
+ return ERR_PTR(error);
- *inode = coda_iget(sb, fid, &attr);
- if ( IS_ERR(*inode) ) {
+ inode = coda_iget(sb, fid, &attr);
+ if (IS_ERR(inode))
printk("coda_cnode_make: coda_iget failed\n");
- return PTR_ERR(*inode);
- }
- return 0;
+ return inode;
}
@@ -156,19 +153,16 @@ struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb)
}
/* the CONTROL inode is made without asking attributes from Venus */
-int coda_cnode_makectl(struct inode **inode, struct super_block *sb)
+struct inode *coda_cnode_makectl(struct super_block *sb)
{
- int error = -ENOMEM;
-
- *inode = new_inode(sb);
- if (*inode) {
- (*inode)->i_ino = CTL_INO;
- (*inode)->i_op = &coda_ioctl_inode_operations;
- (*inode)->i_fop = &coda_ioctl_operations;
- (*inode)->i_mode = 0444;
- error = 0;
+ struct inode *inode = new_inode(sb);
+ if (inode) {
+ inode->i_ino = CTL_INO;
+ inode->i_op = &coda_ioctl_inode_operations;
+ inode->i_fop = &coda_ioctl_operations;
+ inode->i_mode = 0444;
+ return inode;
}
-
- return error;
+ return ERR_PTR(-ENOMEM);
}
diff --git a/fs/coda/coda_fs_i.h b/fs/coda/coda_fs_i.h
index e35071b1de0e..b24fdfd8a3f0 100644
--- a/fs/coda/coda_fs_i.h
+++ b/fs/coda/coda_fs_i.h
@@ -49,9 +49,9 @@ struct coda_file_info {
#define C_DYING 0x4 /* from venus (which died) */
#define C_PURGE 0x8
-int coda_cnode_make(struct inode **, struct CodaFid *, struct super_block *);
+struct inode *coda_cnode_make(struct CodaFid *, struct super_block *);
struct inode *coda_iget(struct super_block *sb, struct CodaFid *fid, struct coda_vattr *attr);
-int coda_cnode_makectl(struct inode **inode, struct super_block *sb);
+struct inode *coda_cnode_makectl(struct super_block *sb);
struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb);
void coda_replace_fid(struct inode *, struct CodaFid *, struct CodaFid *);
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 83d2fd8ec24b..177515829062 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -96,12 +96,11 @@ const struct file_operations coda_dir_operations = {
/* access routines: lookup, readlink, permission */
static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, struct nameidata *nd)
{
- struct inode *inode = NULL;
- struct CodaFid resfid = { { 0, } };
- int type = 0;
- int error = 0;
+ struct super_block *sb = dir->i_sb;
const char *name = entry->d_name.name;
size_t length = entry->d_name.len;
+ struct inode *inode;
+ int type = 0;
if (length > CODA_MAXNAMLEN) {
printk(KERN_ERR "name too long: lookup, %s (%*s)\n",
@@ -111,23 +110,21 @@ static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, struc
/* control object, create inode on the fly */
if (coda_isroot(dir) && coda_iscontrol(name, length)) {
- error = coda_cnode_makectl(&inode, dir->i_sb);
+ inode = coda_cnode_makectl(sb);
type = CODA_NOCACHE;
- goto exit;
+ } else {
+ struct CodaFid fid = { { 0, } };
+ int error = venus_lookup(sb, coda_i2f(dir), name, length,
+ &type, &fid);
+ inode = !error ? coda_cnode_make(&fid, sb) : ERR_PTR(error);
}
- error = venus_lookup(dir->i_sb, coda_i2f(dir), name, length,
- &type, &resfid);
- if (!error)
- error = coda_cnode_make(&inode, &resfid, dir->i_sb);
-
- if (error && error != -ENOENT)
- return ERR_PTR(error);
-
-exit:
- if (inode && (type & CODA_NOCACHE))
+ if (!IS_ERR(inode) && (type & CODA_NOCACHE))
coda_flag_inode(inode, C_VATTR | C_PURGE);
+ if (inode == ERR_PTR(-ENOENT))
+ inode = NULL;
+
return d_splice_alias(inode, entry);
}
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 1c08a8cd673a..5e2e1b3f068d 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -204,10 +204,12 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
printk("coda_read_super: rootfid is %s\n", coda_f2s(&fid));
/* make root inode */
- error = coda_cnode_make(&root, &fid, sb);
- if ( error || !root ) {
- printk("Failure of coda_cnode_make for root: error %d\n", error);
- goto error;
+ root = coda_cnode_make(&fid, sb);
+ if (IS_ERR(root)) {
+ error = PTR_ERR(root);
+ printk("Failure of coda_cnode_make for root: error %d\n", error);
+ root = NULL;
+ goto error;
}
printk("coda_read_super: rootinode is %ld dev %s\n",
diff --git a/fs/dcache.c b/fs/dcache.c
index 3c6d3113a255..16a53cc2cc02 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -243,6 +243,7 @@ static void dentry_lru_add(struct dentry *dentry)
static void __dentry_lru_del(struct dentry *dentry)
{
list_del_init(&dentry->d_lru);
+ dentry->d_flags &= ~DCACHE_SHRINK_LIST;
dentry->d_sb->s_nr_dentry_unused--;
dentry_stat.nr_unused--;
}
@@ -806,6 +807,7 @@ relock:
spin_unlock(&dentry->d_lock);
} else {
list_move_tail(&dentry->d_lru, &tmp);
+ dentry->d_flags |= DCACHE_SHRINK_LIST;
spin_unlock(&dentry->d_lock);
if (!--count)
break;
@@ -1097,14 +1099,19 @@ resume:
/*
* move only zero ref count dentries to the dispose list.
+ *
+ * Those which are presently on the shrink list, being processed
+ * by shrink_dentry_list(), shouldn't be moved. Otherwise the
+ * loop in shrink_dcache_parent() might not make any progress
+ * and loop forever.
*/
- if (!dentry->d_count) {
+ if (dentry->d_count) {
+ dentry_lru_del(dentry);
+ } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
dentry_lru_move_list(dentry, dispose);
+ dentry->d_flags |= DCACHE_SHRINK_LIST;
found++;
- } else {
- dentry_lru_del(dentry);
}
-
/*
* We can return to the caller if we have found some (this
* ensures forward progress). We'll be coming back to find
@@ -1468,7 +1475,14 @@ static struct dentry * __d_find_any_alias(struct inode *inode)
return alias;
}
-static struct dentry * d_find_any_alias(struct inode *inode)
+/**
+ * d_find_any_alias - find any alias for a given inode
+ * @inode: inode to find an alias for
+ *
+ * If any aliases exist for the given inode, take and return a
+ * reference for one of them. If no aliases exist, return %NULL.
+ */
+struct dentry *d_find_any_alias(struct inode *inode)
{
struct dentry *de;
@@ -1477,7 +1491,7 @@ static struct dentry * d_find_any_alias(struct inode *inode)
spin_unlock(&inode->i_lock);
return de;
}
-
+EXPORT_SYMBOL(d_find_any_alias);
/**
* d_obtain_alias - find or allocate a dentry for a given inode
diff --git a/fs/direct-io.c b/fs/direct-io.c
index d740ab67ff6e..4a588dbd11bf 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -36,6 +36,7 @@
#include <linux/rwsem.h>
#include <linux/uio.h>
#include <linux/atomic.h>
+#include <linux/prefetch.h>
/*
* How many user pages to map in one call to get_user_pages(). This determines
@@ -580,9 +581,8 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
{
int ret;
sector_t fs_startblk; /* Into file, in filesystem-sized blocks */
+ sector_t fs_endblk; /* Into file, in filesystem-sized blocks */
unsigned long fs_count; /* Number of filesystem-sized blocks */
- unsigned long dio_count;/* Number of dio_block-sized blocks */
- unsigned long blkmask;
int create;
/*
@@ -593,11 +593,9 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
if (ret == 0) {
BUG_ON(sdio->block_in_file >= sdio->final_block_in_request);
fs_startblk = sdio->block_in_file >> sdio->blkfactor;
- dio_count = sdio->final_block_in_request - sdio->block_in_file;
- fs_count = dio_count >> sdio->blkfactor;
- blkmask = (1 << sdio->blkfactor) - 1;
- if (dio_count & blkmask)
- fs_count++;
+ fs_endblk = (sdio->final_block_in_request - 1) >>
+ sdio->blkfactor;
+ fs_count = fs_endblk - fs_startblk + 1;
map_bh->b_state = 0;
map_bh->b_size = fs_count << dio->inode->i_blkbits;
@@ -1090,8 +1088,8 @@ static inline int drop_refcount(struct dio *dio)
* individual fields and will generate much worse code. This is important
* for the whole file.
*/
-ssize_t
-__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
+static inline ssize_t
+do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, const struct iovec *iov, loff_t offset,
unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
dio_submit_t submit_io, int flags)
@@ -1100,7 +1098,6 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
size_t size;
unsigned long addr;
unsigned blkbits = inode->i_blkbits;
- unsigned bdev_blkbits = 0;
unsigned blocksize_mask = (1 << blkbits) - 1;
ssize_t retval = -EINVAL;
loff_t end = offset;
@@ -1113,12 +1110,14 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
if (rw & WRITE)
rw = WRITE_ODIRECT;
- if (bdev)
- bdev_blkbits = blksize_bits(bdev_logical_block_size(bdev));
+ /*
+ * Avoid references to bdev if not absolutely needed to give
+ * the early prefetch in the caller enough time.
+ */
if (offset & blocksize_mask) {
if (bdev)
- blkbits = bdev_blkbits;
+ blkbits = blksize_bits(bdev_logical_block_size(bdev));
blocksize_mask = (1 << blkbits) - 1;
if (offset & blocksize_mask)
goto out;
@@ -1129,11 +1128,13 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
addr = (unsigned long)iov[seg].iov_base;
size = iov[seg].iov_len;
end += size;
- if ((addr & blocksize_mask) || (size & blocksize_mask)) {
+ if (unlikely((addr & blocksize_mask) ||
+ (size & blocksize_mask))) {
if (bdev)
- blkbits = bdev_blkbits;
+ blkbits = blksize_bits(
+ bdev_logical_block_size(bdev));
blocksize_mask = (1 << blkbits) - 1;
- if ((addr & blocksize_mask) || (size & blocksize_mask))
+ if ((addr & blocksize_mask) || (size & blocksize_mask))
goto out;
}
}
@@ -1316,6 +1317,30 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
out:
return retval;
}
+
+ssize_t
+__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
+ struct block_device *bdev, const struct iovec *iov, loff_t offset,
+ unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
+ dio_submit_t submit_io, int flags)
+{
+ /*
+ * The block device state is needed in the end to finally
+ * submit everything. Since it's likely to be cache cold
+ * prefetch it here as first thing to hide some of the
+ * latency.
+ *
+ * Attempt to prefetch the pieces we likely need later.
+ */
+ prefetch(&bdev->bd_disk->part_tbl);
+ prefetch(bdev->bd_queue);
+ prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES);
+
+ return do_blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
+ nr_segs, get_block, end_io,
+ submit_io, flags);
+}
+
EXPORT_SYMBOL(__blockdev_direct_IO);
static __init int dio_init(void)
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 828e750af23a..aabdfc38cf24 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -197,6 +197,12 @@ struct eventpoll {
/* The user that created the eventpoll descriptor */
struct user_struct *user;
+
+ struct file *file;
+
+ /* used to optimize loop detection check */
+ int visited;
+ struct list_head visited_list_link;
};
/* Wait structure used by the poll hooks */
@@ -255,6 +261,15 @@ static struct kmem_cache *epi_cache __read_mostly;
/* Slab cache used to allocate "struct eppoll_entry" */
static struct kmem_cache *pwq_cache __read_mostly;
+/* Visited nodes during ep_loop_check(), so we can unset them when we finish */
+static LIST_HEAD(visited_list);
+
+/*
+ * List of files with newly added links, where we may need to limit the number
+ * of emanating paths. Protected by the epmutex.
+ */
+static LIST_HEAD(tfile_check_list);
+
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
@@ -276,6 +291,12 @@ ctl_table epoll_table[] = {
};
#endif /* CONFIG_SYSCTL */
+static const struct file_operations eventpoll_fops;
+
+static inline int is_file_epoll(struct file *f)
+{
+ return f->f_op == &eventpoll_fops;
+}
/* Setup the structure that is used as key for the RB tree */
static inline void ep_set_ffd(struct epoll_filefd *ffd,
@@ -711,12 +732,6 @@ static const struct file_operations eventpoll_fops = {
.llseek = noop_llseek,
};
-/* Fast test to see if the file is an eventpoll file */
-static inline int is_file_epoll(struct file *f)
-{
- return f->f_op == &eventpoll_fops;
-}
-
/*
* This is called from eventpoll_release() to unlink files from the eventpoll
* interface. We need to have this facility to cleanup correctly files that are
@@ -926,6 +941,99 @@ static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
rb_insert_color(&epi->rbn, &ep->rbr);
}
+
+
+#define PATH_ARR_SIZE 5
+/*
+ * These are the number paths of length 1 to 5, that we are allowing to emanate
+ * from a single file of interest. For example, we allow 1000 paths of length
+ * 1, to emanate from each file of interest. This essentially represents the
+ * potential wakeup paths, which need to be limited in order to avoid massive
+ * uncontrolled wakeup storms. The common use case should be a single ep which
+ * is connected to n file sources. In this case each file source has 1 path
+ * of length 1. Thus, the numbers below should be more than sufficient. These
+ * path limits are enforced during an EPOLL_CTL_ADD operation, since a modify
+ * and delete can't add additional paths. Protected by the epmutex.
+ */
+static const int path_limits[PATH_ARR_SIZE] = { 1000, 500, 100, 50, 10 };
+static int path_count[PATH_ARR_SIZE];
+
+static int path_count_inc(int nests)
+{
+ if (++path_count[nests] > path_limits[nests])
+ return -1;
+ return 0;
+}
+
+static void path_count_init(void)
+{
+ int i;
+
+ for (i = 0; i < PATH_ARR_SIZE; i++)
+ path_count[i] = 0;
+}
+
+static int reverse_path_check_proc(void *priv, void *cookie, int call_nests)
+{
+ int error = 0;
+ struct file *file = priv;
+ struct file *child_file;
+ struct epitem *epi;
+
+ list_for_each_entry(epi, &file->f_ep_links, fllink) {
+ child_file = epi->ep->file;
+ if (is_file_epoll(child_file)) {
+ if (list_empty(&child_file->f_ep_links)) {
+ if (path_count_inc(call_nests)) {
+ error = -1;
+ break;
+ }
+ } else {
+ error = ep_call_nested(&poll_loop_ncalls,
+ EP_MAX_NESTS,
+ reverse_path_check_proc,
+ child_file, child_file,
+ current);
+ }
+ if (error != 0)
+ break;
+ } else {
+ printk(KERN_ERR "reverse_path_check_proc: "
+ "file is not an ep!\n");
+ }
+ }
+ return error;
+}
+
+/**
+ * reverse_path_check - The tfile_check_list is list of file *, which have
+ * links that are proposed to be newly added. We need to
+ * make sure that those added links don't add too many
+ * paths such that we will spend all our time waking up
+ * eventpoll objects.
+ *
+ * Returns: Returns zero if the proposed links don't create too many paths,
+ * -1 otherwise.
+ */
+static int reverse_path_check(void)
+{
+ int length = 0;
+ int error = 0;
+ struct file *current_file;
+
+ /* let's call this for all tfiles */
+ list_for_each_entry(current_file, &tfile_check_list, f_tfile_llink) {
+ length++;
+ path_count_init();
+ error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
+ reverse_path_check_proc, current_file,
+ current_file, current);
+ if (error)
+ break;
+ }
+ return error;
+}
+
/*
* Must be called with "mtx" held.
*/
@@ -987,6 +1095,11 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
*/
ep_rbtree_insert(ep, epi);
+ /* now check if we've created too many backpaths */
+ error = -EINVAL;
+ if (reverse_path_check())
+ goto error_remove_epi;
+
/* We have to drop the new item inside our item list to keep track of it */
spin_lock_irqsave(&ep->lock, flags);
@@ -1011,6 +1124,14 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
return 0;
+error_remove_epi:
+ spin_lock(&tfile->f_lock);
+ if (ep_is_linked(&epi->fllink))
+ list_del_init(&epi->fllink);
+ spin_unlock(&tfile->f_lock);
+
+ rb_erase(&epi->rbn, &ep->rbr);
+
error_unregister:
ep_unregister_pollwait(ep, epi);
@@ -1275,18 +1396,36 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
int error = 0;
struct file *file = priv;
struct eventpoll *ep = file->private_data;
+ struct eventpoll *ep_tovisit;
struct rb_node *rbp;
struct epitem *epi;
mutex_lock_nested(&ep->mtx, call_nests + 1);
+ ep->visited = 1;
+ list_add(&ep->visited_list_link, &visited_list);
for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
epi = rb_entry(rbp, struct epitem, rbn);
if (unlikely(is_file_epoll(epi->ffd.file))) {
+ ep_tovisit = epi->ffd.file->private_data;
+ if (ep_tovisit->visited)
+ continue;
error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
- ep_loop_check_proc, epi->ffd.file,
- epi->ffd.file->private_data, current);
+ ep_loop_check_proc, epi->ffd.file,
+ ep_tovisit, current);
if (error != 0)
break;
+ } else {
+ /*
+ * If we've reached a file that is not associated with
+ * an ep, then we need to check if the newly added
+ * links are going to add too many wakeup paths. We do
+ * this by adding it to the tfile_check_list, if it's
+ * not already there, and calling reverse_path_check()
+ * during ep_insert().
+ */
+ if (list_empty(&epi->ffd.file->f_tfile_llink))
+ list_add(&epi->ffd.file->f_tfile_llink,
+ &tfile_check_list);
}
}
mutex_unlock(&ep->mtx);
@@ -1307,8 +1446,31 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
*/
static int ep_loop_check(struct eventpoll *ep, struct file *file)
{
- return ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
+ int ret;
+ struct eventpoll *ep_cur, *ep_next;
+
+ ret = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS,
ep_loop_check_proc, file, ep, current);
+ /* clear visited list */
+ list_for_each_entry_safe(ep_cur, ep_next, &visited_list,
+ visited_list_link) {
+ ep_cur->visited = 0;
+ list_del(&ep_cur->visited_list_link);
+ }
+ return ret;
+}
+
+static void clear_tfile_check_list(void)
+{
+ struct file *file;
+
+ /* first clear the tfile_check_list */
+ while (!list_empty(&tfile_check_list)) {
+ file = list_first_entry(&tfile_check_list, struct file,
+ f_tfile_llink);
+ list_del_init(&file->f_tfile_llink);
+ }
+ INIT_LIST_HEAD(&tfile_check_list);
}
/*
@@ -1316,8 +1478,9 @@ static int ep_loop_check(struct eventpoll *ep, struct file *file)
*/
SYSCALL_DEFINE1(epoll_create1, int, flags)
{
- int error;
+ int error, fd;
struct eventpoll *ep = NULL;
+ struct file *file;
/* Check the EPOLL_* constant for consistency. */
BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);
@@ -1334,11 +1497,25 @@ SYSCALL_DEFINE1(epoll_create1, int, flags)
* Creates all the items needed to setup an eventpoll file. That is,
* a file structure and a free file descriptor.
*/
- error = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep,
+ fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC));
+ if (fd < 0) {
+ error = fd;
+ goto out_free_ep;
+ }
+ file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep,
O_RDWR | (flags & O_CLOEXEC));
- if (error < 0)
- ep_free(ep);
-
+ if (IS_ERR(file)) {
+ error = PTR_ERR(file);
+ goto out_free_fd;
+ }
+ fd_install(fd, file);
+ ep->file = file;
+ return fd;
+
+out_free_fd:
+ put_unused_fd(fd);
+out_free_ep:
+ ep_free(ep);
return error;
}
@@ -1404,21 +1581,27 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
/*
* When we insert an epoll file descriptor, inside another epoll file
* descriptor, there is the change of creating closed loops, which are
- * better be handled here, than in more critical paths.
+ * better be handled here, than in more critical paths. While we are
+ * checking for loops we also determine the list of files reachable
+ * and hang them on the tfile_check_list, so we can check that we
+ * haven't created too many possible wakeup paths.
*
- * We hold epmutex across the loop check and the insert in this case, in
- * order to prevent two separate inserts from racing and each doing the
- * insert "at the same time" such that ep_loop_check passes on both
- * before either one does the insert, thereby creating a cycle.
+ * We need to hold the epmutex across both ep_insert and ep_remove
+ * b/c we want to make sure we are looking at a coherent view of
+ * epoll network.
*/
- if (unlikely(is_file_epoll(tfile) && op == EPOLL_CTL_ADD)) {
+ if (op == EPOLL_CTL_ADD || op == EPOLL_CTL_DEL) {
mutex_lock(&epmutex);
did_lock_epmutex = 1;
- error = -ELOOP;
- if (ep_loop_check(ep, tfile) != 0)
- goto error_tgt_fput;
}
-
+ if (op == EPOLL_CTL_ADD) {
+ if (is_file_epoll(tfile)) {
+ error = -ELOOP;
+ if (ep_loop_check(ep, tfile) != 0)
+ goto error_tgt_fput;
+ } else
+ list_add(&tfile->f_tfile_llink, &tfile_check_list);
+ }
mutex_lock_nested(&ep->mtx, 0);
@@ -1437,6 +1620,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
error = ep_insert(ep, &epds, tfile, fd);
} else
error = -EEXIST;
+ clear_tfile_check_list();
break;
case EPOLL_CTL_DEL:
if (epi)
@@ -1455,7 +1639,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
mutex_unlock(&ep->mtx);
error_tgt_fput:
- if (unlikely(did_lock_epmutex))
+ if (did_lock_epmutex)
mutex_unlock(&epmutex);
fput(tfile);
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 2aaf3eaaf13d..5f3368ab0fa9 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1378,7 +1378,59 @@ static int fuse_notify_inval_entry(struct fuse_conn *fc, unsigned int size,
down_read(&fc->killsb);
err = -ENOENT;
if (fc->sb)
- err = fuse_reverse_inval_entry(fc->sb, outarg.parent, &name);
+ err = fuse_reverse_inval_entry(fc->sb, outarg.parent, 0, &name);
+ up_read(&fc->killsb);
+ kfree(buf);
+ return err;
+
+err:
+ kfree(buf);
+ fuse_copy_finish(cs);
+ return err;
+}
+
+static int fuse_notify_delete(struct fuse_conn *fc, unsigned int size,
+ struct fuse_copy_state *cs)
+{
+ struct fuse_notify_delete_out outarg;
+ int err = -ENOMEM;
+ char *buf;
+ struct qstr name;
+
+ buf = kzalloc(FUSE_NAME_MAX + 1, GFP_KERNEL);
+ if (!buf)
+ goto err;
+
+ err = -EINVAL;
+ if (size < sizeof(outarg))
+ goto err;
+
+ err = fuse_copy_one(cs, &outarg, sizeof(outarg));
+ if (err)
+ goto err;
+
+ err = -ENAMETOOLONG;
+ if (outarg.namelen > FUSE_NAME_MAX)
+ goto err;
+
+ err = -EINVAL;
+ if (size != sizeof(outarg) + outarg.namelen + 1)
+ goto err;
+
+ name.name = buf;
+ name.len = outarg.namelen;
+ err = fuse_copy_one(cs, buf, outarg.namelen + 1);
+ if (err)
+ goto err;
+ fuse_copy_finish(cs);
+ buf[outarg.namelen] = 0;
+ name.hash = full_name_hash(name.name, name.len);
+
+ down_read(&fc->killsb);
+ err = -ENOENT;
+ if (fc->sb)
+ err = fuse_reverse_inval_entry(fc->sb, outarg.parent,
+ outarg.child, &name);
up_read(&fc->killsb);
kfree(buf);
return err;
@@ -1597,6 +1649,9 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
case FUSE_NOTIFY_RETRIEVE:
return fuse_notify_retrieve(fc, size, cs);
+ case FUSE_NOTIFY_DELETE:
+ return fuse_notify_delete(fc, size, cs);
+
default:
fuse_copy_finish(cs);
return -EINVAL;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 5ddd6ea8f839..206632887bb4 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -868,7 +868,7 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat,
}
int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
- struct qstr *name)
+ u64 child_nodeid, struct qstr *name)
{
int err = -ENOTDIR;
struct inode *parent;
@@ -895,8 +895,36 @@ int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
fuse_invalidate_attr(parent);
fuse_invalidate_entry(entry);
+
+ if (child_nodeid != 0 && entry->d_inode) {
+ mutex_lock(&entry->d_inode->i_mutex);
+ if (get_node_id(entry->d_inode) != child_nodeid) {
+ err = -ENOENT;
+ goto badentry;
+ }
+ if (d_mountpoint(entry)) {
+ err = -EBUSY;
+ goto badentry;
+ }
+ if (S_ISDIR(entry->d_inode->i_mode)) {
+ shrink_dcache_parent(entry);
+ if (!simple_empty(entry)) {
+ err = -ENOTEMPTY;
+ goto badentry;
+ }
+ entry->d_inode->i_flags |= S_DEAD;
+ }
+ dont_mount(entry);
+ clear_nlink(entry->d_inode);
+ err = 0;
+ badentry:
+ mutex_unlock(&entry->d_inode->i_mutex);
+ if (!err)
+ d_delete(entry);
+ } else {
+ err = 0;
+ }
dput(entry);
- err = 0;
unlock:
mutex_unlock(&parent->i_mutex);
@@ -1182,6 +1210,30 @@ static int fuse_dir_fsync(struct file *file, loff_t start, loff_t end,
return fuse_fsync_common(file, start, end, datasync, 1);
}
+static long fuse_dir_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ struct fuse_conn *fc = get_fuse_conn(file->f_mapping->host);
+
+ /* FUSE_IOCTL_DIR only supported for API version >= 7.18 */
+ if (fc->minor < 18)
+ return -ENOTTY;
+
+ return fuse_ioctl_common(file, cmd, arg, FUSE_IOCTL_DIR);
+}
+
+static long fuse_dir_compat_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ struct fuse_conn *fc = get_fuse_conn(file->f_mapping->host);
+
+ if (fc->minor < 18)
+ return -ENOTTY;
+
+ return fuse_ioctl_common(file, cmd, arg,
+ FUSE_IOCTL_COMPAT | FUSE_IOCTL_DIR);
+}
+
static bool update_mtime(unsigned ivalid)
{
/* Always update if mtime is explicitly set */
@@ -1596,6 +1648,8 @@ static const struct file_operations fuse_dir_operations = {
.open = fuse_dir_open,
.release = fuse_dir_release,
.fsync = fuse_dir_fsync,
+ .unlocked_ioctl = fuse_dir_ioctl,
+ .compat_ioctl = fuse_dir_compat_ioctl,
};
static const struct inode_operations fuse_common_inode_operations = {
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 0c84100acd44..4a199fd93fbd 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1555,48 +1555,16 @@ static loff_t fuse_file_llseek(struct file *file, loff_t offset, int origin)
loff_t retval;
struct inode *inode = file->f_path.dentry->d_inode;
- mutex_lock(&inode->i_mutex);
- if (origin != SEEK_CUR && origin != SEEK_SET) {
- retval = fuse_update_attributes(inode, NULL, file, NULL);
- if (retval)
- goto exit;
- }
+ /* No i_mutex protection necessary for SEEK_CUR and SEEK_SET */
+ if (origin == SEEK_CUR || origin == SEEK_SET)
+ return generic_file_llseek(file, offset, origin);
- switch (origin) {
- case SEEK_END:
- offset += i_size_read(inode);
- break;
- case SEEK_CUR:
- if (offset == 0) {
- retval = file->f_pos;
- goto exit;
- }
- offset += file->f_pos;
- break;
- case SEEK_DATA:
- if (offset >= i_size_read(inode)) {
- retval = -ENXIO;
- goto exit;
- }
- break;
- case SEEK_HOLE:
- if (offset >= i_size_read(inode)) {
- retval = -ENXIO;
- goto exit;
- }
- offset = i_size_read(inode);
- break;
- }
- retval = -EINVAL;
- if (offset >= 0 && offset <= inode->i_sb->s_maxbytes) {
- if (offset != file->f_pos) {
- file->f_pos = offset;
- file->f_version = 0;
- }
- retval = offset;
- }
-exit:
+ mutex_lock(&inode->i_mutex);
+ retval = fuse_update_attributes(inode, NULL, file, NULL);
+ if (!retval)
+ retval = generic_file_llseek(file, offset, origin);
mutex_unlock(&inode->i_mutex);
+
return retval;
}
@@ -1808,7 +1776,7 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
BUILD_BUG_ON(sizeof(struct fuse_ioctl_iovec) * FUSE_IOCTL_MAX_IOV > PAGE_SIZE);
err = -ENOMEM;
- pages = kzalloc(sizeof(pages[0]) * FUSE_MAX_PAGES_PER_REQ, GFP_KERNEL);
+ pages = kcalloc(FUSE_MAX_PAGES_PER_REQ, sizeof(pages[0]), GFP_KERNEL);
iov_page = (struct iovec *) __get_free_page(GFP_KERNEL);
if (!pages || !iov_page)
goto out;
@@ -1958,8 +1926,8 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
}
EXPORT_SYMBOL_GPL(fuse_do_ioctl);
-static long fuse_file_ioctl_common(struct file *file, unsigned int cmd,
- unsigned long arg, unsigned int flags)
+long fuse_ioctl_common(struct file *file, unsigned int cmd,
+ unsigned long arg, unsigned int flags)
{
struct inode *inode = file->f_dentry->d_inode;
struct fuse_conn *fc = get_fuse_conn(inode);
@@ -1976,13 +1944,13 @@ static long fuse_file_ioctl_common(struct file *file, unsigned int cmd,
static long fuse_file_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
- return fuse_file_ioctl_common(file, cmd, arg, 0);
+ return fuse_ioctl_common(file, cmd, arg, 0);
}
static long fuse_file_compat_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
- return fuse_file_ioctl_common(file, cmd, arg, FUSE_IOCTL_COMPAT);
+ return fuse_ioctl_common(file, cmd, arg, FUSE_IOCTL_COMPAT);
}
/*
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 1964da0257d9..572cefc78012 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -755,9 +755,15 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
/**
* File-system tells the kernel to invalidate parent attributes and
* the dentry matching parent/name.
+ *
+ * If the child_nodeid is non-zero and:
+ * - matches the inode number for the dentry matching parent/name,
+ * - is not a mount point
+ * - is a file or oan empty directory
+ * then the dentry is unhashed (d_delete()).
*/
int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
- struct qstr *name);
+ u64 child_nodeid, struct qstr *name);
int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
bool isdir);
@@ -765,6 +771,8 @@ ssize_t fuse_direct_io(struct file *file, const char __user *buf,
size_t count, loff_t *ppos, int write);
long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
unsigned int flags);
+long fuse_ioctl_common(struct file *file, unsigned int cmd,
+ unsigned long arg, unsigned int flags);
unsigned fuse_file_poll(struct file *file, poll_table *wait);
int fuse_dev_release(struct inode *inode, struct file *file);
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index edf0a801446b..427682ca9e48 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -499,9 +499,16 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
if (!sbi->hidden_dir) {
mutex_lock(&sbi->vh_mutex);
sbi->hidden_dir = hfsplus_new_inode(sb, S_IFDIR);
- hfsplus_create_cat(sbi->hidden_dir->i_ino, root, &str,
- sbi->hidden_dir);
+ if (!sbi->hidden_dir) {
+ mutex_unlock(&sbi->vh_mutex);
+ err = -ENOMEM;
+ goto out_put_root;
+ }
+ err = hfsplus_create_cat(sbi->hidden_dir->i_ino, root,
+ &str, sbi->hidden_dir);
mutex_unlock(&sbi->vh_mutex);
+ if (err)
+ goto out_put_hidden_dir;
hfsplus_mark_inode_dirty(sbi->hidden_dir,
HFSPLUS_I_CAT_DIRTY);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index e425ad9d0490..1e85a7ac0217 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -583,7 +583,8 @@ static int hugetlbfs_set_page_dirty(struct page *page)
}
static int hugetlbfs_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page)
+ struct page *newpage, struct page *page,
+ enum migrate_mode mode)
{
int rc;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 5ee92538b063..8102db9b926c 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -332,7 +332,7 @@ void nfs_commit_release_pages(struct nfs_write_data *data);
#ifdef CONFIG_MIGRATION
extern int nfs_migrate_page(struct address_space *,
- struct page *, struct page *);
+ struct page *, struct page *, enum migrate_mode);
#else
#define nfs_migrate_page NULL
#endif
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 0c3885255f97..834f0fe96f89 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1688,7 +1688,7 @@ out_error:
#ifdef CONFIG_MIGRATION
int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
- struct page *page)
+ struct page *page, enum migrate_mode mode)
{
/*
* If PagePrivate is set, then the page is currently associated with
@@ -1703,7 +1703,7 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
nfs_fscache_release_page(page, GFP_KERNEL);
- return migrate_page(mapping, newpage, page);
+ return migrate_page(mapping, newpage, page, mode);
}
#endif
diff --git a/fs/pipe.c b/fs/pipe.c
index f0e485d54e64..a932ced92a16 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1137,7 +1137,7 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
if (nr_pages < pipe->nrbufs)
return -EBUSY;
- bufs = kcalloc(nr_pages, sizeof(struct pipe_buffer), GFP_KERNEL);
+ bufs = kcalloc(nr_pages, sizeof(*bufs), GFP_KERNEL | __GFP_NOWARN);
if (unlikely(!bufs))
return -ENOMEM;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 8c344f037bd0..9252ee3b71e3 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -464,7 +464,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
seq_printf(m, "%d (%s) %c %d %d %d %d %d %u %lu \
%lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \
-%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld\n",
+%lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld %lu %lu %lu\n",
pid_nr_ns(pid, ns),
tcomm,
state,
@@ -511,7 +511,10 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
task->policy,
(unsigned long long)delayacct_blkio_ticks(task),
cputime_to_clock_t(gtime),
- cputime_to_clock_t(cgtime));
+ cputime_to_clock_t(cgtime),
+ (mm && permitted) ? mm->start_data : 0,
+ (mm && permitted) ? mm->end_data : 0,
+ (mm && permitted) ? mm->start_brk : 0);
if (mm)
mmput(mm);
return 0;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 8173dfd89cb2..5485a5388ecb 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -654,6 +654,8 @@ static int proc_pid_permission(struct inode *inode, int mask)
bool has_perms;
task = get_proc_task(inode);
+ if (!task)
+ return -ESRCH;
has_perms = has_pid_permissions(pid, task, 1);
put_task_struct(task);
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index b09ba2dd8b62..f922cbacdb96 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -38,9 +38,6 @@
DEFINE_SPINLOCK(dbg_lock);
-static char dbg_key_buf0[128];
-static char dbg_key_buf1[128];
-
static const char *get_key_fmt(int fmt)
{
switch (fmt) {
@@ -103,8 +100,8 @@ static const char *get_dent_type(int type)
}
}
-static void sprintf_key(const struct ubifs_info *c, const union ubifs_key *key,
- char *buffer)
+const char *dbg_snprintf_key(const struct ubifs_info *c,
+ const union ubifs_key *key, char *buffer, int len)
{
char *p = buffer;
int type = key_type(c, key);
@@ -112,45 +109,34 @@ static void sprintf_key(const struct ubifs_info *c, const union ubifs_key *key,
if (c->key_fmt == UBIFS_SIMPLE_KEY_FMT) {
switch (type) {
case UBIFS_INO_KEY:
- sprintf(p, "(%lu, %s)", (unsigned long)key_inum(c, key),
- get_key_type(type));
+ len -= snprintf(p, len, "(%lu, %s)",
+ (unsigned long)key_inum(c, key),
+ get_key_type(type));
break;
case UBIFS_DENT_KEY:
case UBIFS_XENT_KEY:
- sprintf(p, "(%lu, %s, %#08x)",
- (unsigned long)key_inum(c, key),
- get_key_type(type), key_hash(c, key));
+ len -= snprintf(p, len, "(%lu, %s, %#08x)",
+ (unsigned long)key_inum(c, key),
+ get_key_type(type), key_hash(c, key));
break;
case UBIFS_DATA_KEY:
- sprintf(p, "(%lu, %s, %u)",
- (unsigned long)key_inum(c, key),
- get_key_type(type), key_block(c, key));
+ len -= snprintf(p, len, "(%lu, %s, %u)",
+ (unsigned long)key_inum(c, key),
+ get_key_type(type), key_block(c, key));
break;
case UBIFS_TRUN_KEY:
- sprintf(p, "(%lu, %s)",
- (unsigned long)key_inum(c, key),
- get_key_type(type));
+ len -= snprintf(p, len, "(%lu, %s)",
+ (unsigned long)key_inum(c, key),
+ get_key_type(type));
break;
default:
- sprintf(p, "(bad key type: %#08x, %#08x)",
- key->u32[0], key->u32[1]);
+ len -= snprintf(p, len, "(bad key type: %#08x, %#08x)",
+ key->u32[0], key->u32[1]);
}
} else
- sprintf(p, "bad key format %d", c->key_fmt);
-}
-
-const char *dbg_key_str0(const struct ubifs_info *c, const union ubifs_key *key)
-{
- /* dbg_lock must be held */
- sprintf_key(c, key, dbg_key_buf0);
- return dbg_key_buf0;
-}
-
-const char *dbg_key_str1(const struct ubifs_info *c, const union ubifs_key *key)
-{
- /* dbg_lock must be held */
- sprintf_key(c, key, dbg_key_buf1);
- return dbg_key_buf1;
+ len -= snprintf(p, len, "bad key format %d", c->key_fmt);
+ ubifs_assert(len > 0);
+ return p;
}
const char *dbg_ntype(int type)
@@ -319,6 +305,7 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
int i, n;
union ubifs_key key;
const struct ubifs_ch *ch = node;
+ char key_buf[DBG_KEY_BUF_LEN];
if (dbg_is_tst_rcvry(c))
return;
@@ -474,7 +461,8 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
const struct ubifs_ino_node *ino = node;
key_read(c, &ino->key, &key);
- printk(KERN_DEBUG "\tkey %s\n", DBGKEY(&key));
+ printk(KERN_DEBUG "\tkey %s\n",
+ dbg_snprintf_key(c, &key, key_buf, DBG_KEY_BUF_LEN));
printk(KERN_DEBUG "\tcreat_sqnum %llu\n",
(unsigned long long)le64_to_cpu(ino->creat_sqnum));
printk(KERN_DEBUG "\tsize %llu\n",
@@ -517,7 +505,8 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
int nlen = le16_to_cpu(dent->nlen);
key_read(c, &dent->key, &key);
- printk(KERN_DEBUG "\tkey %s\n", DBGKEY(&key));
+ printk(KERN_DEBUG "\tkey %s\n",
+ dbg_snprintf_key(c, &key, key_buf, DBG_KEY_BUF_LEN));
printk(KERN_DEBUG "\tinum %llu\n",
(unsigned long long)le64_to_cpu(dent->inum));
printk(KERN_DEBUG "\ttype %d\n", (int)dent->type);
@@ -541,7 +530,8 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
int dlen = le32_to_cpu(ch->len) - UBIFS_DATA_NODE_SZ;
key_read(c, &dn->key, &key);
- printk(KERN_DEBUG "\tkey %s\n", DBGKEY(&key));
+ printk(KERN_DEBUG "\tkey %s\n",
+ dbg_snprintf_key(c, &key, key_buf, DBG_KEY_BUF_LEN));
printk(KERN_DEBUG "\tsize %u\n",
le32_to_cpu(dn->size));
printk(KERN_DEBUG "\tcompr_typ %d\n",
@@ -582,7 +572,9 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node)
key_read(c, &br->key, &key);
printk(KERN_DEBUG "\t%d: LEB %d:%d len %d key %s\n",
i, le32_to_cpu(br->lnum), le32_to_cpu(br->offs),
- le32_to_cpu(br->len), DBGKEY(&key));
+ le32_to_cpu(br->len),
+ dbg_snprintf_key(c, &key, key_buf,
+ DBG_KEY_BUF_LEN));
}
break;
}
@@ -934,6 +926,7 @@ void dbg_dump_znode(const struct ubifs_info *c,
{
int n;
const struct ubifs_zbranch *zbr;
+ char key_buf[DBG_KEY_BUF_LEN];
spin_lock(&dbg_lock);
if (znode->parent)
@@ -958,12 +951,16 @@ void dbg_dump_znode(const struct ubifs_info *c,
printk(KERN_DEBUG "\t%d: znode %p LEB %d:%d len %d key "
"%s\n", n, zbr->znode, zbr->lnum,
zbr->offs, zbr->len,
- DBGKEY(&zbr->key));
+ dbg_snprintf_key(c, &zbr->key,
+ key_buf,
+ DBG_KEY_BUF_LEN));
else
printk(KERN_DEBUG "\t%d: LNC %p LEB %d:%d len %d key "
"%s\n", n, zbr->znode, zbr->lnum,
zbr->offs, zbr->len,
- DBGKEY(&zbr->key));
+ dbg_snprintf_key(c, &zbr->key,
+ key_buf,
+ DBG_KEY_BUF_LEN));
}
spin_unlock(&dbg_lock);
}
@@ -1260,6 +1257,7 @@ static int dbg_check_key_order(struct ubifs_info *c, struct ubifs_zbranch *zbr1,
int err, nlen1, nlen2, cmp;
struct ubifs_dent_node *dent1, *dent2;
union ubifs_key key;
+ char key_buf[DBG_KEY_BUF_LEN];
ubifs_assert(!keys_cmp(c, &zbr1->key, &zbr2->key));
dent1 = kmalloc(UBIFS_MAX_DENT_NODE_SZ, GFP_NOFS);
@@ -1290,9 +1288,11 @@ static int dbg_check_key_order(struct ubifs_info *c, struct ubifs_zbranch *zbr1,
key_read(c, &dent1->key, &key);
if (keys_cmp(c, &zbr1->key, &key)) {
dbg_err("1st entry at %d:%d has key %s", zbr1->lnum,
- zbr1->offs, DBGKEY(&key));
+ zbr1->offs, dbg_snprintf_key(c, &key, key_buf,
+ DBG_KEY_BUF_LEN));
dbg_err("but it should have key %s according to tnc",
- DBGKEY(&zbr1->key));
+ dbg_snprintf_key(c, &zbr1->key, key_buf,
+ DBG_KEY_BUF_LEN));
dbg_dump_node(c, dent1);
goto out_free;
}
@@ -1300,9 +1300,11 @@ static int dbg_check_key_order(struct ubifs_info *c, struct ubifs_zbranch *zbr1,
key_read(c, &dent2->key, &key);
if (keys_cmp(c, &zbr2->key, &key)) {
dbg_err("2nd entry at %d:%d has key %s", zbr1->lnum,
- zbr1->offs, DBGKEY(&key));
+ zbr1->offs, dbg_snprintf_key(c, &key, key_buf,
+ DBG_KEY_BUF_LEN));
dbg_err("but it should have key %s according to tnc",
- DBGKEY(&zbr2->key));
+ dbg_snprintf_key(c, &zbr2->key, key_buf,
+ DBG_KEY_BUF_LEN));
dbg_dump_node(c, dent2);
goto out_free;
}
@@ -1319,7 +1321,7 @@ static int dbg_check_key_order(struct ubifs_info *c, struct ubifs_zbranch *zbr1,
dbg_err("2 xent/dent nodes with the same name");
else
dbg_err("bad order of colliding key %s",
- DBGKEY(&key));
+ dbg_snprintf_key(c, &key, key_buf, DBG_KEY_BUF_LEN));
ubifs_msg("first node at %d:%d\n", zbr1->lnum, zbr1->offs);
dbg_dump_node(c, dent1);
diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h
index 8d9c46810189..307ab1d23f75 100644
--- a/fs/ubifs/debug.h
+++ b/fs/ubifs/debug.h
@@ -169,40 +169,39 @@ struct ubifs_global_debug_info {
spin_unlock(&dbg_lock); \
} while (0)
-const char *dbg_key_str0(const struct ubifs_info *c,
- const union ubifs_key *key);
-const char *dbg_key_str1(const struct ubifs_info *c,
- const union ubifs_key *key);
-
-/*
- * DBGKEY macros require @dbg_lock to be held, which it is in the dbg message
- * macros.
- */
-#define DBGKEY(key) dbg_key_str0(c, (key))
-#define DBGKEY1(key) dbg_key_str1(c, (key))
-
-extern spinlock_t dbg_lock;
-
-#define ubifs_dbg_msg(type, fmt, ...) do { \
- spin_lock(&dbg_lock); \
- pr_debug("UBIFS DBG " type ": " fmt "\n", ##__VA_ARGS__); \
- spin_unlock(&dbg_lock); \
+#define ubifs_dbg_msg(type, fmt, ...) \
+ pr_debug("UBIFS DBG " type ": " fmt "\n", ##__VA_ARGS__)
+
+#define DBG_KEY_BUF_LEN 32
+#define ubifs_dbg_msg_key(type, key, fmt, ...) do { \
+ char __tmp_key_buf[DBG_KEY_BUF_LEN]; \
+ pr_debug("UBIFS DBG " type ": " fmt "%s\n", ##__VA_ARGS__, \
+ dbg_snprintf_key(c, key, __tmp_key_buf, DBG_KEY_BUF_LEN)); \
} while (0)
/* Just a debugging messages not related to any specific UBIFS subsystem */
-#define dbg_msg(fmt, ...) ubifs_dbg_msg("msg", fmt, ##__VA_ARGS__)
+#define dbg_msg(fmt, ...) \
+ printk(KERN_DEBUG "UBIFS DBG (pid %d): %s: " fmt "\n", current->pid, \
+ __func__, ##__VA_ARGS__)
+
/* General messages */
#define dbg_gen(fmt, ...) ubifs_dbg_msg("gen", fmt, ##__VA_ARGS__)
/* Additional journal messages */
#define dbg_jnl(fmt, ...) ubifs_dbg_msg("jnl", fmt, ##__VA_ARGS__)
+#define dbg_jnlk(key, fmt, ...) \
+ ubifs_dbg_msg_key("jnl", key, fmt, ##__VA_ARGS__)
/* Additional TNC messages */
#define dbg_tnc(fmt, ...) ubifs_dbg_msg("tnc", fmt, ##__VA_ARGS__)
+#define dbg_tnck(key, fmt, ...) \
+ ubifs_dbg_msg_key("tnc", key, fmt, ##__VA_ARGS__)
/* Additional lprops messages */
#define dbg_lp(fmt, ...) ubifs_dbg_msg("lp", fmt, ##__VA_ARGS__)
/* Additional LEB find messages */
#define dbg_find(fmt, ...) ubifs_dbg_msg("find", fmt, ##__VA_ARGS__)
/* Additional mount messages */
#define dbg_mnt(fmt, ...) ubifs_dbg_msg("mnt", fmt, ##__VA_ARGS__)
+#define dbg_mntk(key, fmt, ...) \
+ ubifs_dbg_msg_key("mnt", key, fmt, ##__VA_ARGS__)
/* Additional I/O messages */
#define dbg_io(fmt, ...) ubifs_dbg_msg("io", fmt, ##__VA_ARGS__)
/* Additional commit messages */
@@ -218,6 +217,7 @@ extern spinlock_t dbg_lock;
/* Additional recovery messages */
#define dbg_rcvry(fmt, ...) ubifs_dbg_msg("rcvry", fmt, ##__VA_ARGS__)
+extern spinlock_t dbg_lock;
extern struct ubifs_global_debug_info ubifs_dbg;
static inline int dbg_is_chk_gen(const struct ubifs_info *c)
@@ -258,6 +258,8 @@ const char *dbg_cstate(int cmt_state);
const char *dbg_jhead(int jhead);
const char *dbg_get_key_dump(const struct ubifs_info *c,
const union ubifs_key *key);
+const char *dbg_snprintf_key(const struct ubifs_info *c,
+ const union ubifs_key *key, char *buffer, int len);
void dbg_dump_inode(struct ubifs_info *c, const struct inode *inode);
void dbg_dump_node(const struct ubifs_info *c, const void *node);
void dbg_dump_lpt_node(const struct ubifs_info *c, void *node, int lnum,
@@ -368,6 +370,10 @@ static inline const char *dbg_jhead(int jhead) { return ""; }
static inline const char *
dbg_get_key_dump(const struct ubifs_info *c,
const union ubifs_key *key) { return ""; }
+static inline const char *
+dbg_snprintf_key(const struct ubifs_info *c,
+ const union ubifs_key *key, char *buffer,
+ int len) { return ""; }
static inline void dbg_dump_inode(struct ubifs_info *c,
const struct inode *inode) { return; }
static inline void dbg_dump_node(const struct ubifs_info *c,
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index cef0460f4c54..2f438ab2e7a2 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -697,9 +697,8 @@ int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode,
int dlen = COMPRESSED_DATA_NODE_BUF_SZ, allocated = 1;
struct ubifs_inode *ui = ubifs_inode(inode);
- dbg_jnl("ino %lu, blk %u, len %d, key %s",
- (unsigned long)key_inum(c, key), key_block(c, key), len,
- DBGKEY(key));
+ dbg_jnlk(key, "ino %lu, blk %u, len %d, key ",
+ (unsigned long)key_inum(c, key), key_block(c, key), len);
ubifs_assert(len <= UBIFS_BLOCK_SIZE);
data = kmalloc(dlen, GFP_NOFS | __GFP_NOWARN);
@@ -1177,7 +1176,7 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode,
dn = (void *)trun + UBIFS_TRUN_NODE_SZ;
blk = new_size >> UBIFS_BLOCK_SHIFT;
data_key_init(c, &key, inum, blk);
- dbg_jnl("last block key %s", DBGKEY(&key));
+ dbg_jnlk(&key, "last block key ");
err = ubifs_tnc_lookup(c, &key, dn);
if (err == -ENOENT)
dlen = 0; /* Not found (so it is a hole) */
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index ccabaf1164b3..b007637f0406 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -221,8 +221,8 @@ static int apply_replay_entry(struct ubifs_info *c, struct replay_entry *r)
{
int err;
- dbg_mnt("LEB %d:%d len %d deletion %d sqnum %llu %s", r->lnum,
- r->offs, r->len, r->deletion, r->sqnum, DBGKEY(&r->key));
+ dbg_mntk(&r->key, "LEB %d:%d len %d deletion %d sqnum %llu key ",
+ r->lnum, r->offs, r->len, r->deletion, r->sqnum);
/* Set c->replay_sqnum to help deal with dangling branches. */
c->replay_sqnum = r->sqnum;
@@ -361,7 +361,7 @@ static int insert_node(struct ubifs_info *c, int lnum, int offs, int len,
{
struct replay_entry *r;
- dbg_mnt("add LEB %d:%d, key %s", lnum, offs, DBGKEY(key));
+ dbg_mntk(key, "add LEB %d:%d, key ", lnum, offs);
if (key_inum(c, key) >= c->highest_inum)
c->highest_inum = key_inum(c, key);
@@ -409,7 +409,7 @@ static int insert_dent(struct ubifs_info *c, int lnum, int offs, int len,
struct replay_entry *r;
char *nbuf;
- dbg_mnt("add LEB %d:%d, key %s", lnum, offs, DBGKEY(key));
+ dbg_mntk(key, "add LEB %d:%d, key ", lnum, offs);
if (key_inum(c, key) >= c->highest_inum)
c->highest_inum = key_inum(c, key);
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index e14ee53159db..16ad84d8402f 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -505,7 +505,7 @@ static int fallible_read_node(struct ubifs_info *c, const union ubifs_key *key,
{
int ret;
- dbg_tnc("LEB %d:%d, key %s", zbr->lnum, zbr->offs, DBGKEY(key));
+ dbg_tnck(key, "LEB %d:%d, key ", zbr->lnum, zbr->offs);
ret = try_read_node(c, node, key_type(c, key), zbr->len, zbr->lnum,
zbr->offs);
@@ -519,8 +519,8 @@ static int fallible_read_node(struct ubifs_info *c, const union ubifs_key *key,
ret = 0;
}
if (ret == 0 && c->replaying)
- dbg_mnt("dangling branch LEB %d:%d len %d, key %s",
- zbr->lnum, zbr->offs, zbr->len, DBGKEY(key));
+ dbg_mntk(key, "dangling branch LEB %d:%d len %d, key ",
+ zbr->lnum, zbr->offs, zbr->len);
return ret;
}
@@ -995,9 +995,9 @@ static int fallible_resolve_collision(struct ubifs_info *c,
if (adding || !o_znode)
return 0;
- dbg_mnt("dangling match LEB %d:%d len %d %s",
+ dbg_mntk(key, "dangling match LEB %d:%d len %d key ",
o_znode->zbranch[o_n].lnum, o_znode->zbranch[o_n].offs,
- o_znode->zbranch[o_n].len, DBGKEY(key));
+ o_znode->zbranch[o_n].len);
*zn = o_znode;
*n = o_n;
return 1;
@@ -1179,7 +1179,7 @@ int ubifs_lookup_level0(struct ubifs_info *c, const union ubifs_key *key,
struct ubifs_znode *znode;
unsigned long time = get_seconds();
- dbg_tnc("search key %s", DBGKEY(key));
+ dbg_tnck(key, "search key ");
ubifs_assert(key_type(c, key) < UBIFS_INVALID_KEY);
znode = c->zroot.znode;
@@ -1315,7 +1315,7 @@ static int lookup_level0_dirty(struct ubifs_info *c, const union ubifs_key *key,
struct ubifs_znode *znode;
unsigned long time = get_seconds();
- dbg_tnc("search and dirty key %s", DBGKEY(key));
+ dbg_tnck(key, "search and dirty key ");
znode = c->zroot.znode;
if (unlikely(!znode)) {
@@ -1722,8 +1722,8 @@ static int validate_data_node(struct ubifs_info *c, void *buf,
if (!keys_eq(c, &zbr->key, &key1)) {
ubifs_err("bad key in node at LEB %d:%d",
zbr->lnum, zbr->offs);
- dbg_tnc("looked for key %s found node's key %s",
- DBGKEY(&zbr->key), DBGKEY1(&key1));
+ dbg_tnck(&zbr->key, "looked for key ");
+ dbg_tnck(&key1, "found node's key ");
goto out_err;
}
@@ -1776,7 +1776,7 @@ int ubifs_tnc_bulk_read(struct ubifs_info *c, struct bu_info *bu)
ubifs_err("failed to read from LEB %d:%d, error %d",
lnum, offs, err);
dbg_dump_stack();
- dbg_tnc("key %s", DBGKEY(&bu->key));
+ dbg_tnck(&bu->key, "key ");
return err;
}
@@ -1811,7 +1811,7 @@ static int do_lookup_nm(struct ubifs_info *c, const union ubifs_key *key,
int found, n, err;
struct ubifs_znode *znode;
- dbg_tnc("name '%.*s' key %s", nm->len, nm->name, DBGKEY(key));
+ dbg_tnck(key, "name '%.*s' key ", nm->len, nm->name);
mutex_lock(&c->tnc_mutex);
found = ubifs_lookup_level0(c, key, &znode, &n);
if (!found) {
@@ -1985,8 +1985,7 @@ again:
zp = znode->parent;
if (znode->child_cnt < c->fanout) {
ubifs_assert(n != c->fanout);
- dbg_tnc("inserted at %d level %d, key %s", n, znode->level,
- DBGKEY(key));
+ dbg_tnck(key, "inserted at %d level %d, key ", n, znode->level);
insert_zbranch(znode, zbr, n);
@@ -2001,7 +2000,7 @@ again:
* Unfortunately, @znode does not have more empty slots and we have to
* split it.
*/
- dbg_tnc("splitting level %d, key %s", znode->level, DBGKEY(key));
+ dbg_tnck(key, "splitting level %d, key ", znode->level);
if (znode->alt)
/*
@@ -2095,7 +2094,7 @@ do_split:
}
/* Insert new key and branch */
- dbg_tnc("inserting at %d level %d, key %s", n, zn->level, DBGKEY(key));
+ dbg_tnck(key, "inserting at %d level %d, key ", n, zn->level);
insert_zbranch(zi, zbr, n);
@@ -2171,7 +2170,7 @@ int ubifs_tnc_add(struct ubifs_info *c, const union ubifs_key *key, int lnum,
struct ubifs_znode *znode;
mutex_lock(&c->tnc_mutex);
- dbg_tnc("%d:%d, len %d, key %s", lnum, offs, len, DBGKEY(key));
+ dbg_tnck(key, "%d:%d, len %d, key ", lnum, offs, len);
found = lookup_level0_dirty(c, key, &znode, &n);
if (!found) {
struct ubifs_zbranch zbr;
@@ -2220,8 +2219,8 @@ int ubifs_tnc_replace(struct ubifs_info *c, const union ubifs_key *key,
struct ubifs_znode *znode;
mutex_lock(&c->tnc_mutex);
- dbg_tnc("old LEB %d:%d, new LEB %d:%d, len %d, key %s", old_lnum,
- old_offs, lnum, offs, len, DBGKEY(key));
+ dbg_tnck(key, "old LEB %d:%d, new LEB %d:%d, len %d, key ", old_lnum,
+ old_offs, lnum, offs, len);
found = lookup_level0_dirty(c, key, &znode, &n);
if (found < 0) {
err = found;
@@ -2303,8 +2302,8 @@ int ubifs_tnc_add_nm(struct ubifs_info *c, const union ubifs_key *key,
struct ubifs_znode *znode;
mutex_lock(&c->tnc_mutex);
- dbg_tnc("LEB %d:%d, name '%.*s', key %s", lnum, offs, nm->len, nm->name,
- DBGKEY(key));
+ dbg_tnck(key, "LEB %d:%d, name '%.*s', key ",
+ lnum, offs, nm->len, nm->name);
found = lookup_level0_dirty(c, key, &znode, &n);
if (found < 0) {
err = found;
@@ -2397,7 +2396,7 @@ static int tnc_delete(struct ubifs_info *c, struct ubifs_znode *znode, int n)
/* Delete without merge for now */
ubifs_assert(znode->level == 0);
ubifs_assert(n >= 0 && n < c->fanout);
- dbg_tnc("deleting %s", DBGKEY(&znode->zbranch[n].key));
+ dbg_tnck(&znode->zbranch[n].key, "deleting key ");
zbr = &znode->zbranch[n];
lnc_free(zbr);
@@ -2507,7 +2506,7 @@ int ubifs_tnc_remove(struct ubifs_info *c, const union ubifs_key *key)
struct ubifs_znode *znode;
mutex_lock(&c->tnc_mutex);
- dbg_tnc("key %s", DBGKEY(key));
+ dbg_tnck(key, "key ");
found = lookup_level0_dirty(c, key, &znode, &n);
if (found < 0) {
err = found;
@@ -2538,7 +2537,7 @@ int ubifs_tnc_remove_nm(struct ubifs_info *c, const union ubifs_key *key,
struct ubifs_znode *znode;
mutex_lock(&c->tnc_mutex);
- dbg_tnc("%.*s, key %s", nm->len, nm->name, DBGKEY(key));
+ dbg_tnck(key, "%.*s, key ", nm->len, nm->name);
err = lookup_level0_dirty(c, key, &znode, &n);
if (err < 0)
goto out_unlock;
@@ -2653,7 +2652,7 @@ int ubifs_tnc_remove_range(struct ubifs_info *c, union ubifs_key *from_key,
dbg_dump_znode(c, znode);
goto out_unlock;
}
- dbg_tnc("removing %s", DBGKEY(key));
+ dbg_tnck(key, "removing key ");
}
if (k) {
for (i = n + 1 + k; i < znode->child_cnt; i++)
@@ -2773,7 +2772,7 @@ struct ubifs_dent_node *ubifs_tnc_next_ent(struct ubifs_info *c,
struct ubifs_zbranch *zbr;
union ubifs_key *dkey;
- dbg_tnc("%s %s", nm->name ? (char *)nm->name : "(lowest)", DBGKEY(key));
+ dbg_tnck(key, "%s ", nm->name ? (char *)nm->name : "(lowest)");
ubifs_assert(is_hash_key(c, key));
mutex_lock(&c->tnc_mutex);
@@ -3332,9 +3331,9 @@ int dbg_check_inode_size(struct ubifs_info *c, const struct inode *inode,
out_dump:
block = key_block(c, key);
- ubifs_err("inode %lu has size %lld, but there are data at offset %lld "
- "(data key %s)", (unsigned long)inode->i_ino, size,
- ((loff_t)block) << UBIFS_BLOCK_SHIFT, DBGKEY(key));
+ ubifs_err("inode %lu has size %lld, but there are data at offset %lld",
+ (unsigned long)inode->i_ino, size,
+ ((loff_t)block) << UBIFS_BLOCK_SHIFT);
mutex_unlock(&c->tnc_mutex);
dbg_dump_inode(c, inode);
dbg_dump_stack();
diff --git a/fs/ubifs/tnc_misc.c b/fs/ubifs/tnc_misc.c
index b48db999903e..dc28fe6ec07a 100644
--- a/fs/ubifs/tnc_misc.c
+++ b/fs/ubifs/tnc_misc.c
@@ -328,8 +328,8 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len,
case UBIFS_XENT_KEY:
break;
default:
- dbg_msg("bad key type at slot %d: %s", i,
- DBGKEY(&zbr->key));
+ dbg_msg("bad key type at slot %d: %d",
+ i, key_type(c, &zbr->key));
err = 3;
goto out_dump;
}
@@ -475,7 +475,7 @@ int ubifs_tnc_read_node(struct ubifs_info *c, struct ubifs_zbranch *zbr,
zbr->offs);
if (err) {
- dbg_tnc("key %s", DBGKEY(key));
+ dbg_tnck(key, "key ");
return err;
}
@@ -484,8 +484,8 @@ int ubifs_tnc_read_node(struct ubifs_info *c, struct ubifs_zbranch *zbr,
if (!keys_eq(c, key, &key1)) {
ubifs_err("bad key in node at LEB %d:%d",
zbr->lnum, zbr->offs);
- dbg_tnc("looked for key %s found node's key %s",
- DBGKEY(key), DBGKEY1(&key1));
+ dbg_tnck(key, "looked for key ");
+ dbg_tnck(&key1, "but found node's key ");
dbg_dump_node(c, node);
return -EINVAL;
}