aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/vfs_inode.c41
-rw-r--r--fs/binfmt_elf_fdpic.c13
-rw-r--r--fs/cifs/cifs_dfs_ref.c3
-rw-r--r--fs/configfs/symlink.c4
-rw-r--r--fs/ecryptfs/inode.c24
-rw-r--r--fs/exofs/inode.c17
-rw-r--r--fs/exofs/pnfs.h10
-rw-r--r--fs/fcntl.c102
-rw-r--r--fs/gfs2/file.c38
-rw-r--r--fs/gfs2/meta_io.c2
-rw-r--r--fs/gfs2/ops_inode.c6
-rw-r--r--fs/gfs2/xattr.c21
-rw-r--r--fs/hppfs/hppfs.c18
-rw-r--r--fs/namei.c23
-rw-r--r--fs/namespace.c14
-rw-r--r--fs/nfs/dir.c1
-rw-r--r--fs/nfsd/vfs.c5
-rw-r--r--fs/notify/inotify/inotify_fsnotify.c2
-rw-r--r--fs/notify/inotify/inotify_user.c4
-rw-r--r--fs/proc/array.c89
-rw-r--r--fs/proc/base.c1
-rw-r--r--fs/proc/task_mmu.c3
-rw-r--r--fs/quota/dquot.c3
-rw-r--r--fs/ramfs/file-nommu.c26
-rw-r--r--fs/reiserfs/inode.c19
-rw-r--r--fs/reiserfs/ioctl.c3
-rw-r--r--fs/reiserfs/xattr.c18
-rw-r--r--fs/reiserfs/xattr_acl.c2
-rw-r--r--fs/ubifs/gc.c96
-rw-r--r--fs/xfs/linux-2.6/xfs_acl.c3
-rw-r--r--fs/xfs/linux-2.6/xfs_super.c14
-rw-r--r--fs/xfs/linux-2.6/xfs_sync.c183
-rw-r--r--fs/xfs/linux-2.6/xfs_sync.h2
-rw-r--r--fs/xfs/linux-2.6/xfs_trace.h1145
-rw-r--r--fs/xfs/quota/xfs_qm_syscalls.c2
-rw-r--r--fs/xfs/xfs_alloc.c44
-rw-r--r--fs/xfs/xfs_dfrag.c106
-rw-r--r--fs/xfs/xfs_iget.c1
-rw-r--r--fs/xfs/xfs_inode.c17
-rw-r--r--fs/xfs/xfs_rtalloc.c2
-rw-r--r--fs/xfs/xfs_vnodeops.c93
41 files changed, 1104 insertions, 1116 deletions
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 18f74ec4dce..9d03d1ebca6 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -1001,44 +1001,6 @@ done:
}
/**
- * v9fs_vfs_readlink - read a symlink's location
- * @dentry: dentry for symlink
- * @buffer: buffer to load symlink location into
- * @buflen: length of buffer
- *
- */
-
-static int v9fs_vfs_readlink(struct dentry *dentry, char __user * buffer,
- int buflen)
-{
- int retval;
- int ret;
- char *link = __getname();
-
- if (unlikely(!link))
- return -ENOMEM;
-
- if (buflen > PATH_MAX)
- buflen = PATH_MAX;
-
- P9_DPRINTK(P9_DEBUG_VFS, " dentry: %s (%p)\n", dentry->d_name.name,
- dentry);
-
- retval = v9fs_readlink(dentry, link, buflen);
-
- if (retval > 0) {
- if ((ret = copy_to_user(buffer, link, retval)) != 0) {
- P9_DPRINTK(P9_DEBUG_ERROR,
- "problem copying to user: %d\n", ret);
- retval = ret;
- }
- }
-
- __putname(link);
- return retval;
-}
-
-/**
* v9fs_vfs_follow_link - follow a symlink path
* @dentry: dentry for symlink
* @nd: nameidata
@@ -1230,7 +1192,6 @@ static const struct inode_operations v9fs_dir_inode_operations_ext = {
.rmdir = v9fs_vfs_rmdir,
.mknod = v9fs_vfs_mknod,
.rename = v9fs_vfs_rename,
- .readlink = v9fs_vfs_readlink,
.getattr = v9fs_vfs_getattr,
.setattr = v9fs_vfs_setattr,
};
@@ -1253,7 +1214,7 @@ static const struct inode_operations v9fs_file_inode_operations = {
};
static const struct inode_operations v9fs_symlink_inode_operations = {
- .readlink = v9fs_vfs_readlink,
+ .readlink = generic_readlink,
.follow_link = v9fs_vfs_follow_link,
.put_link = v9fs_vfs_put_link,
.getattr = v9fs_vfs_getattr,
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 7dc85997e96..c57d9ce5ff7 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -171,6 +171,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
#ifdef ELF_FDPIC_PLAT_INIT
unsigned long dynaddr;
#endif
+#ifndef CONFIG_MMU
+ unsigned long stack_prot;
+#endif
struct file *interpreter = NULL; /* to shut gcc up */
char *interpreter_name = NULL;
int executable_stack;
@@ -316,6 +319,8 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
* defunct, deceased, etc. after this point we have to exit via
* error_kill */
set_personality(PER_LINUX_FDPIC);
+ if (elf_read_implies_exec(&exec_params.hdr, executable_stack))
+ current->personality |= READ_IMPLIES_EXEC;
set_binfmt(&elf_fdpic_format);
current->mm->start_code = 0;
@@ -377,9 +382,13 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
if (stack_size < PAGE_SIZE * 2)
stack_size = PAGE_SIZE * 2;
+ stack_prot = PROT_READ | PROT_WRITE;
+ if (executable_stack == EXSTACK_ENABLE_X ||
+ (executable_stack == EXSTACK_DEFAULT && VM_STACK_FLAGS & VM_EXEC))
+ stack_prot |= PROT_EXEC;
+
down_write(&current->mm->mmap_sem);
- current->mm->start_brk = do_mmap(NULL, 0, stack_size,
- PROT_READ | PROT_WRITE | PROT_EXEC,
+ current->mm->start_brk = do_mmap(NULL, 0, stack_size, stack_prot,
MAP_PRIVATE | MAP_ANONYMOUS |
MAP_UNINITIALIZED | MAP_GROWSDOWN,
0);
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index fea9e898c4b..b44ce0a0711 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -269,7 +269,7 @@ static int add_mount_helper(struct vfsmount *newmnt, struct nameidata *nd,
int err;
mntget(newmnt);
- err = do_add_mount(newmnt, &nd->path, nd->path.mnt->mnt_flags, mntlist);
+ err = do_add_mount(newmnt, &nd->path, nd->path.mnt->mnt_flags | MNT_SHRINKABLE, mntlist);
switch (err) {
case 0:
path_put(&nd->path);
@@ -371,7 +371,6 @@ cifs_dfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
if (IS_ERR(mnt))
goto out_err;
- nd->path.mnt->mnt_flags |= MNT_SHRINKABLE;
rc = add_mount_helper(mnt, nd, &cifs_dfs_automount_list);
out:
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index c8afa6b1d91..32a5f46b115 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -121,8 +121,10 @@ static int get_target(const char *symname, struct path *path,
ret = -ENOENT;
path_put(path);
}
- } else
+ } else {
ret = -EPERM;
+ path_put(path);
+ }
}
return ret;
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 429ca0b3ba0..7f854503293 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -715,31 +715,31 @@ static void *ecryptfs_follow_link(struct dentry *dentry, struct nameidata *nd)
/* Released in ecryptfs_put_link(); only release here on error */
buf = kmalloc(len, GFP_KERNEL);
if (!buf) {
- rc = -ENOMEM;
+ buf = ERR_PTR(-ENOMEM);
goto out;
}
old_fs = get_fs();
set_fs(get_ds());
rc = dentry->d_inode->i_op->readlink(dentry, (char __user *)buf, len);
set_fs(old_fs);
- if (rc < 0)
- goto out_free;
- else
+ if (rc < 0) {
+ kfree(buf);
+ buf = ERR_PTR(rc);
+ } else
buf[rc] = '\0';
- rc = 0;
- nd_set_link(nd, buf);
- goto out;
-out_free:
- kfree(buf);
out:
- return ERR_PTR(rc);
+ nd_set_link(nd, buf);
+ return NULL;
}
static void
ecryptfs_put_link(struct dentry *dentry, struct nameidata *nd, void *ptr)
{
- /* Free the char* */
- kfree(nd_get_link(nd));
+ char *buf = nd_get_link(nd);
+ if (!IS_ERR(buf)) {
+ /* Free the char* */
+ kfree(buf);
+ }
}
/**
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 698a8636d39..2afbcebeda7 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -738,13 +738,28 @@ static int exofs_write_begin_export(struct file *file,
fsdata);
}
+static int exofs_write_end(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
+{
+ struct inode *inode = mapping->host;
+ /* According to comment in simple_write_end i_mutex is held */
+ loff_t i_size = inode->i_size;
+ int ret;
+
+ ret = simple_write_end(file, mapping,pos, len, copied, page, fsdata);
+ if (i_size != inode->i_size)
+ mark_inode_dirty(inode);
+ return ret;
+}
+
const struct address_space_operations exofs_aops = {
.readpage = exofs_readpage,
.readpages = exofs_readpages,
.writepage = exofs_writepage,
.writepages = exofs_writepages,
.write_begin = exofs_write_begin_export,
- .write_end = simple_write_end,
+ .write_end = exofs_write_end,
};
/******************************************************************************
diff --git a/fs/exofs/pnfs.h b/fs/exofs/pnfs.h
index 423033addd1..c52e9888b8a 100644
--- a/fs/exofs/pnfs.h
+++ b/fs/exofs/pnfs.h
@@ -15,13 +15,7 @@
#ifndef __EXOFS_PNFS_H__
#define __EXOFS_PNFS_H__
-#if defined(CONFIG_PNFS)
-
-
-/* FIXME: move this file to: linux/exportfs/pnfs_osd_xdr.h */
-#include "../nfs/objlayout/pnfs_osd_xdr.h"
-
-#else /* defined(CONFIG_PNFS) */
+#if ! defined(__PNFS_OSD_XDR_H__)
enum pnfs_iomode {
IOMODE_READ = 1,
@@ -46,6 +40,6 @@ struct pnfs_osd_data_map {
u32 odm_raid_algorithm;
};
-#endif /* else defined(CONFIG_PNFS) */
+#endif /* ! defined(__PNFS_OSD_XDR_H__) */
#endif /* __EXOFS_PNFS_H__ */
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 2cf93ec40a6..97e01dc0d95 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -618,60 +618,90 @@ static DEFINE_RWLOCK(fasync_lock);
static struct kmem_cache *fasync_cache __read_mostly;
/*
- * fasync_helper() is used by almost all character device drivers
- * to set up the fasync queue. It returns negative on error, 0 if it did
- * no changes and positive if it added/deleted the entry.
+ * Remove a fasync entry. If successfully removed, return
+ * positive and clear the FASYNC flag. If no entry exists,
+ * do nothing and return 0.
+ *
+ * NOTE! It is very important that the FASYNC flag always
+ * match the state "is the filp on a fasync list".
+ *
+ * We always take the 'filp->f_lock', in since fasync_lock
+ * needs to be irq-safe.
*/
-int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp)
+static int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
{
struct fasync_struct *fa, **fp;
- struct fasync_struct *new = NULL;
int result = 0;
- if (on) {
- new = kmem_cache_alloc(fasync_cache, GFP_KERNEL);
- if (!new)
- return -ENOMEM;
+ spin_lock(&filp->f_lock);
+ write_lock_irq(&fasync_lock);
+ for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
+ if (fa->fa_file != filp)
+ continue;
+ *fp = fa->fa_next;
+ kmem_cache_free(fasync_cache, fa);
+ filp->f_flags &= ~FASYNC;
+ result = 1;
+ break;
}
+ write_unlock_irq(&fasync_lock);
+ spin_unlock(&filp->f_lock);
+ return result;
+}
+
+/*
+ * Add a fasync entry. Return negative on error, positive if
+ * added, and zero if did nothing but change an existing one.
+ *
+ * NOTE! It is very important that the FASYNC flag always
+ * match the state "is the filp on a fasync list".
+ */
+static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp)
+{
+ struct fasync_struct *new, *fa, **fp;
+ int result = 0;
+
+ new = kmem_cache_alloc(fasync_cache, GFP_KERNEL);
+ if (!new)
+ return -ENOMEM;
- /*
- * We need to take f_lock first since it's not an IRQ-safe
- * lock.
- */
spin_lock(&filp->f_lock);
write_lock_irq(&fasync_lock);
for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
- if (fa->fa_file == filp) {
- if(on) {
- fa->fa_fd = fd;
- kmem_cache_free(fasync_cache, new);
- } else {
- *fp = fa->fa_next;
- kmem_cache_free(fasync_cache, fa);
- result = 1;
- }
- goto out;
- }
+ if (fa->fa_file != filp)
+ continue;
+ fa->fa_fd = fd;
+ kmem_cache_free(fasync_cache, new);
+ goto out;
}
- if (on) {
- new->magic = FASYNC_MAGIC;
- new->fa_file = filp;
- new->fa_fd = fd;
- new->fa_next = *fapp;
- *fapp = new;
- result = 1;
- }
+ new->magic = FASYNC_MAGIC;
+ new->fa_file = filp;
+ new->fa_fd = fd;
+ new->fa_next = *fapp;
+ *fapp = new;
+ result = 1;
+ filp->f_flags |= FASYNC;
+
out:
- if (on)
- filp->f_flags |= FASYNC;
- else
- filp->f_flags &= ~FASYNC;
write_unlock_irq(&fasync_lock);
spin_unlock(&filp->f_lock);
return result;
}
+/*
+ * fasync_helper() is used by almost all character device drivers
+ * to set up the fasync queue, and for regular files by the file
+ * lease code. It returns negative on error, 0 if it did no changes
+ * and positive if it added/deleted the entry.
+ */
+int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp)
+{
+ if (!on)
+ return fasync_remove_entry(filp, fapp);
+ return fasync_add_entry(fd, filp, fapp);
+}
+
EXPORT_SYMBOL(fasync_helper);
void __kill_fasync(struct fasync_struct *fa, int sig, int band)
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 4eb308aa323..a6abbae8a27 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -569,6 +569,40 @@ static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync)
return ret;
}
+/**
+ * gfs2_file_aio_write - Perform a write to a file
+ * @iocb: The io context
+ * @iov: The data to write
+ * @nr_segs: Number of @iov segments
+ * @pos: The file position
+ *
+ * We have to do a lock/unlock here to refresh the inode size for
+ * O_APPEND writes, otherwise we can land up writing at the wrong
+ * offset. There is still a race, but provided the app is using its
+ * own file locking, this will make O_APPEND work as expected.
+ *
+ */
+
+static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ struct file *file = iocb->ki_filp;
+
+ if (file->f_flags & O_APPEND) {
+ struct dentry *dentry = file->f_dentry;
+ struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
+ struct gfs2_holder gh;
+ int ret;
+
+ ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+ if (ret)
+ return ret;
+ gfs2_glock_dq_uninit(&gh);
+ }
+
+ return generic_file_aio_write(iocb, iov, nr_segs, pos);
+}
+
#ifdef CONFIG_GFS2_FS_LOCKING_DLM
/**
@@ -711,7 +745,7 @@ const struct file_operations gfs2_file_fops = {
.read = do_sync_read,
.aio_read = generic_file_aio_read,
.write = do_sync_write,
- .aio_write = generic_file_aio_write,
+ .aio_write = gfs2_file_aio_write,
.unlocked_ioctl = gfs2_ioctl,
.mmap = gfs2_mmap,
.open = gfs2_open,
@@ -741,7 +775,7 @@ const struct file_operations gfs2_file_fops_nolock = {
.read = do_sync_read,
.aio_read = generic_file_aio_read,
.write = do_sync_write,
- .aio_write = generic_file_aio_write,
+ .aio_write = gfs2_file_aio_write,
.unlocked_ioctl = gfs2_ioctl,
.mmap = gfs2_mmap,
.open = gfs2_open,
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index cb8d7a93d5e..6f68a5f18eb 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -121,7 +121,7 @@ struct inode *gfs2_aspace_get(struct gfs2_sbd *sdp)
if (aspace) {
mapping_set_gfp_mask(aspace->i_mapping, GFP_NOFS);
aspace->i_mapping->a_ops = &aspace_aops;
- aspace->i_size = ~0ULL;
+ aspace->i_size = MAX_LFS_FILESIZE;
ip = GFS2_I(aspace);
clear_bit(GIF_USER, &ip->i_flags);
insert_inode_hash(aspace);
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 247436c10de..78f73ca1ef3 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -748,7 +748,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
struct gfs2_rgrpd *nrgd;
unsigned int num_gh;
int dir_rename = 0;
- int alloc_required;
+ int alloc_required = 0;
unsigned int x;
int error;
@@ -867,7 +867,9 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
goto out_gunlock;
}
- alloc_required = error = gfs2_diradd_alloc_required(ndir, &ndentry->d_name);
+ if (nip == NULL)
+ alloc_required = gfs2_diradd_alloc_required(ndir, &ndentry->d_name);
+ error = alloc_required;
if (error < 0)
goto out_gunlock;
error = 0;
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 8a04108e0c2..c2ebdf2c01d 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -1296,6 +1296,7 @@ fail:
int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
{
+ struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_ea_location el;
struct buffer_head *dibh;
int error;
@@ -1305,16 +1306,17 @@ int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
return error;
if (GFS2_EA_IS_STUFFED(el.el_ea)) {
- error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), RES_DINODE + RES_EATTR, 0);
- if (error)
- return error;
-
- gfs2_trans_add_bh(ip->i_gl, el.el_bh, 1);
- memcpy(GFS2_EA2DATA(el.el_ea), data,
- GFS2_EA_DATA_LEN(el.el_ea));
- } else
+ error = gfs2_trans_begin(sdp, RES_DINODE + RES_EATTR, 0);
+ if (error == 0) {
+ gfs2_trans_add_bh(ip->i_gl, el.el_bh, 1);
+ memcpy(GFS2_EA2DATA(el.el_ea), data,
+ GFS2_EA_DATA_LEN(el.el_ea));
+ }
+ } else {
error = ea_acl_chmod_unstuffed(ip, el.el_ea, data);
+ }
+ brelse(el.el_bh);
if (error)
return error;
@@ -1327,8 +1329,7 @@ int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
brelse(dibh);
}
- gfs2_trans_end(GFS2_SB(&ip->i_inode));
-
+ gfs2_trans_end(sdp);
return error;
}
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index a5089a6dd67..7239efc690d 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -646,22 +646,27 @@ static const struct super_operations hppfs_sbops = {
static int hppfs_readlink(struct dentry *dentry, char __user *buffer,
int buflen)
{
- struct dentry *proc_dentry;
-
- proc_dentry = HPPFS_I(dentry->d_inode)->proc_dentry;
+ struct dentry *proc_dentry = HPPFS_I(dentry->d_inode)->proc_dentry;
return proc_dentry->d_inode->i_op->readlink(proc_dentry, buffer,
buflen);
}
static void *hppfs_follow_link(struct dentry *dentry, struct nameidata *nd)
{
- struct dentry *proc_dentry;
-
- proc_dentry = HPPFS_I(dentry->d_inode)->proc_dentry;
+ struct dentry *proc_dentry = HPPFS_I(dentry->d_inode)->proc_dentry;
return proc_dentry->d_inode->i_op->follow_link(proc_dentry, nd);
}
+static void hppfs_put_link(struct dentry *dentry, struct nameidata *nd,
+ void *cookie)
+{
+ struct dentry *proc_dentry = HPPFS_I(dentry->d_inode)->proc_dentry;
+
+ if (proc_dentry->d_inode->i_op->put_link)
+ proc_dentry->d_inode->i_op->put_link(proc_dentry, nd, cookie);
+}
+
static const struct inode_operations hppfs_dir_iops = {
.lookup = hppfs_lookup,
};
@@ -669,6 +674,7 @@ static const struct inode_operations hppfs_dir_iops = {
static const struct inode_operations hppfs_link_iops = {
.readlink = hppfs_readlink,
.follow_link = hppfs_follow_link,
+ .put_link = hppfs_put_link,
};
static struct inode *get_inode(struct super_block *sb, struct dentry *dentry)
diff --git a/fs/namei.c b/fs/namei.c
index b55440baf7a..94a5e60779f 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -561,6 +561,7 @@ static __always_inline int __do_follow_link(struct path *path, struct nameidata
dget(dentry);
}
mntget(path->mnt);
+ nd->last_type = LAST_BIND;
cookie = dentry->d_inode->i_op->follow_link(dentry, nd);
error = PTR_ERR(cookie);
if (!IS_ERR(cookie)) {
@@ -1603,11 +1604,12 @@ struct file *do_filp_open(int dfd, const char *pathname,
struct file *filp;
struct nameidata nd;
int error;
- struct path path, save;
+ struct path path;
struct dentry *dir;
int count = 0;
int will_truncate;
int flag = open_to_namei_flags(open_flag);
+ int force_reval = 0;
/*
* O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only
@@ -1619,7 +1621,7 @@ struct file *do_filp_open(int dfd, const char *pathname,
open_flag |= O_DSYNC;
if (!acc_mode)
- acc_mode = MAY_OPEN | ACC_MODE(flag);
+ acc_mode = MAY_OPEN | ACC_MODE(open_flag);
/* O_TRUNC implies we need access checks for write permissions */
if (flag & O_TRUNC)
@@ -1659,9 +1661,12 @@ struct file *do_filp_open(int dfd, const char *pathname,
/*
* Create - we need to know the parent.
*/
+reval:
error = path_init(dfd, pathname, LOOKUP_PARENT, &nd);
if (error)
return ERR_PTR(error);
+ if (force_reval)
+ nd.flags |= LOOKUP_REVAL;
error = path_walk(pathname, &nd);
if (error) {
if (nd.root.mnt)
@@ -1853,17 +1858,7 @@ do_link:
error = security_inode_follow_link(path.dentry, &nd);
if (error)
goto exit_dput;
- save = nd.path;
- path_get(&save);
error = __do_follow_link(&path, &nd);
- if (error == -ESTALE) {
- /* nd.path had been dropped */
- nd.path = save;
- path_get(&nd.path);
- nd.flags |= LOOKUP_REVAL;
- error = __do_follow_link(&path, &nd);
- }
- path_put(&save);
path_put(&path);
if (error) {
/* Does someone understand code flow here? Or it is only
@@ -1873,6 +1868,10 @@ do_link:
release_open_intent(&nd);
if (nd.root.mnt)
path_put(&nd.root);
+ if (error == -ESTALE && !force_reval) {
+ force_reval = 1;
+ goto reval;
+ }
return ERR_PTR(error);
}
nd.flags &= ~LOOKUP_PARENT;
diff --git a/fs/namespace.c b/fs/namespace.c
index 7d70d63ceb2..c768f733c8d 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -965,10 +965,12 @@ EXPORT_SYMBOL(may_umount_tree);
int may_umount(struct vfsmount *mnt)
{
int ret = 1;
+ down_read(&namespace_sem);
spin_lock(&vfsmount_lock);
if (propagate_mount_busy(mnt, 2))
ret = 0;
spin_unlock(&vfsmount_lock);
+ up_read(&namespace_sem);
return ret;
}
@@ -1352,12 +1354,12 @@ static int attach_recursive_mnt(struct vfsmount *source_mnt,
if (err)
goto out_cleanup_ids;
+ spin_lock(&vfsmount_lock);
+
if (IS_MNT_SHARED(dest_mnt)) {
for (p = source_mnt; p; p = next_mnt(p, source_mnt))
set_mnt_shared(p);
}
-
- spin_lock(&vfsmount_lock);
if (parent_path) {
detach_mnt(source_mnt, parent_path);
attach_mnt(source_mnt, path);
@@ -1534,8 +1536,12 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
err = change_mount_flags(path->mnt, flags);
else
err = do_remount_sb(sb, flags, data, 0);
- if (!err)
+ if (!err) {
+ spin_lock(&vfsmount_lock);
+ mnt_flags |= path->mnt->mnt_flags & MNT_PNODE_MASK;
path->mnt->mnt_flags = mnt_flags;
+ spin_unlock(&vfsmount_lock);
+ }
up_write(&sb->s_umount);
if (!err) {
security_sb_post_remount(path->mnt, flags, data);
@@ -1665,6 +1671,8 @@ int do_add_mount(struct vfsmount *newmnt, struct path *path,
{
int err;
+ mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD);
+
down_write(&namespace_sem);
/* Something was mounted here while we slept */
while (d_mountpoint(path->dentry) &&
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 2c5ace4f00a..3c7f03b669f 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1615,6 +1615,7 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
goto out;
new_dentry = dentry;
+ rehash = NULL;
new_inode = NULL;
}
}
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 7c2e337d05a..c194793b642 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -780,12 +780,9 @@ static inline int nfsd_dosync(struct file *filp, struct dentry *dp,
int (*fsync) (struct file *, struct dentry *, int);
int err;
- err = filemap_fdatawrite(inode->i_mapping);
+ err = filemap_write_and_wait(inode->i_mapping);
if (err == 0 && fop && (fsync = fop->fsync))
err = fsync(filp, dp, 0);
- if (err == 0)
- err = filemap_fdatawait(inode->i_mapping);
-
return err;
}
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index c9ee67b442e..1afb0a10229 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -121,7 +121,7 @@ static int idr_callback(int id, void *p, void *data)
if (warned)
return 0;
- warned = false;
+ warned = true;
entry = p;
ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 8271cf05c95..a94e8bd8eb1 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -552,7 +552,7 @@ retry:
spin_lock(&group->inotify_data.idr_lock);
ret = idr_get_new_above(&group->inotify_data.idr, &tmp_ientry->fsn_entry,
- group->inotify_data.last_wd,
+ group->inotify_data.last_wd+1,
&tmp_ientry->wd);
spin_unlock(&group->inotify_data.idr_lock);
if (ret) {
@@ -632,7 +632,7 @@ static struct fsnotify_group *inotify_new_group(struct user_struct *user, unsign
spin_lock_init(&group->inotify_data.idr_lock);
idr_init(&group->inotify_data.idr);
- group->inotify_data.last_wd = 1;
+ group->inotify_data.last_wd = 0;
group->inotify_data.user = user;
group->inotify_data.fa = NULL;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index f560325c444..13b5d070817 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -327,94 +327,6 @@ static inline void task_context_switch_counts(struct seq_file *m,
p->nivcsw);
}
-#ifdef CONFIG_MMU
-
-struct stack_stats {
- struct vm_area_struct *vma;
- unsigned long startpage;
- unsigned long usage;
-};
-
-static int stack_usage_pte_range(pmd_t *pmd, unsigned long addr,
- unsigned long end, struct mm_walk *walk)
-{
- struct stack_stats *ss = walk->private;
- struct vm_area_struct *vma = ss->vma;
- pte_t *pte, ptent;
- spinlock_t *ptl;
- int ret = 0;
-
- pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
- for (; addr != end; pte++, addr += PAGE_SIZE) {
- ptent = *pte;
-
-#ifdef CONFIG_STACK_GROWSUP
- if (pte_present(ptent) || is_swap_pte(ptent))
- ss->usage = addr - ss->startpage + PAGE_SIZE;
-#else
- if (pte_present(ptent) || is_swap_pte(ptent)) {
- ss->usage = ss->startpage - addr + PAGE_SIZE;
- pte++;
- ret = 1;
- break;
- }
-#endif
- }
- pte_unmap_unlock(pte - 1, ptl);
- cond_resched();
- return ret;
-}
-
-static inline unsigned long get_stack_usage_in_bytes(struct vm_area_struct *vma,
- struct task_struct *task)
-{
- struct stack_stats ss;
- struct mm_walk stack_walk = {
- .pmd_entry = stack_usage_pte_range,
- .mm = vma->vm_mm,
- .private = &ss,
- };
-
- if (!vma->vm_mm || is_vm_hugetlb_page(vma))
- return 0;
-
- ss.vma = vma;
- ss.startpage = task->stack_start & PAGE_MASK;
- ss.usage = 0;
-
-#ifdef CONFIG_STACK_GROWSUP
- walk_page_range(KSTK_ESP(task) & PAGE_MASK, vma->vm_end,
- &stack_walk);
-#else
- walk_page_range(vma->vm_start, (KSTK_ESP(task) & PAGE_MASK) + PAGE_SIZE,
- &stack_walk);
-#endif
- return ss.usage;
-}
-
-static inline void task_show_stack_usage(struct seq_file *m,
- struct task_struct *task)
-{
- struct vm_area_struct *vma;
- struct mm_struct *mm = get_task_mm(task);
-
- if (mm) {
- down_read(&mm->mmap_sem);
- vma = find_vma(mm, task->stack_start);
- if (vma)
- seq_printf(m, "Stack usage:\t%lu kB\n",
- get_stack_usage_in_bytes(vma, task) >> 10);
-
- up_read(&mm->mmap_sem);
- mmput(mm);
- }
-}
-#else
-static void task_show_stack_usage(struct seq_file *m, struct task_struct *task)
-{
-}
-#endif /* CONFIG_MMU */
-
static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
{
seq_printf(m, "Cpus_allowed:\t");
@@ -445,7 +357,6 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
task_show_regs(m, task);
#endif
task_context_switch_counts(m, task);
- task_show_stack_usage(m, task);
return 0;
}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 18d5cc62d8e..e42bbd843ed 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1419,7 +1419,6 @@ static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
goto out;
error = PROC_I(inode)->op.proc_get_link(inode, &nd->path);
- nd->last_type = LAST_BIND;
out:
return ERR_PTR(error);
}
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 47c03f4336b..f277c4a111c 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -361,12 +361,11 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
if (!pte_present(ptent))
continue;
- mss->resident += PAGE_SIZE;
-
page = vm_normal_page(vma, addr, ptent);
if (!page)
continue;
+ mss->resident += PAGE_SIZE;
/* Accumulate the size in pages that have been accessed. */
if (pte_young(ptent) || PageReferenced(page))
mss->referenced += PAGE_SIZE;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index dea86abdf2e..3fc62b097be 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1377,6 +1377,9 @@ static void inode_sub_rsv_space(struct inode *inode, qsize_t number)
static qsize_t inode_get_rsv_space(struct inode *inode)
{
qsize_t ret;
+
+ if (!inode->i_sb->dq_op->get_reserved_space)
+ return 0;
spin_lock(&inode->i_lock);
ret = *inode_reserved_space(inode);
spin_unlock(&inode->i_lock);
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 2efc57173fd..1739a4aba25 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -123,30 +123,6 @@ add_error:
/*****************************************************************************/
/*
- * check that file shrinkage doesn't leave any VMAs dangling in midair
- */
-static int ramfs_nommu_check_mappings(struct inode *inode,
- size_t newsize, size_t size)
-{
- struct vm_area_struct *vma;
- struct prio_tree_iter iter;
-
- /* search for VMAs that fall within the dead zone */
- vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
- newsize >> PAGE_SHIFT,
- (size + PAGE_SIZE - 1) >> PAGE_SHIFT
- ) {
- /* found one - only interested if it's shared out of the page
- * cache */
- if (vma->vm_flags & VM_SHARED)
- return -ETXTBSY; /* not quite true, but near enough */
- }
-
- return 0;
-}
-
-/*****************************************************************************/
-/*
*
*/
static int ramfs_nommu_resize(struct inode *inode, loff_t newsize, loff_t size)
@@ -164,7 +140,7 @@ static int ramfs_nommu_resize(struct inode *inode, loff_t newsize, loff_t size)
/* check that a decrease in size doesn't cut off any shared mappings */
if (newsize < size) {
- ret = ramfs_nommu_check_mappings(inode, newsize, size);
+ ret = nommu_shrink_inode_mappings(inode, size, newsize);
if (ret < 0)
return ret;
}
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 1150ebb2536..9087b10209e 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -3062,13 +3062,14 @@ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb,
int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = dentry->d_inode;
- int error;
unsigned int ia_valid;
+ int depth;
+ int error;
/* must be turned off for recursive notify_change calls */
ia_valid = attr->ia_valid &= ~(ATTR_KILL_SUID|ATTR_KILL_SGID);
- reiserfs_write_lock(inode->i_sb);
+ depth = reiserfs_write_lock_once(inode->i_sb);
if (attr->ia_valid & ATTR_SIZE) {
/* version 2 items will be caught by the s_maxbytes check
** done for us in vmtruncate
@@ -3149,8 +3150,17 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
journal_end(&th, inode->i_sb, jbegin_count);
}
}
- if (!error)
+ if (!error) {
+ /*
+ * Relax the lock here, as it might truncate the
+ * inode pages and wait for inode pages locks.
+ * To release such page lock, the owner needs the
+ * reiserfs lock
+ */
+ reiserfs_write_unlock_once(inode->i_sb, depth);
error = inode_setattr(inode, attr);
+ depth = reiserfs_write_lock_once(inode->i_sb);
+ }
}
if (!error && reiserfs_posixacl(inode->i_sb)) {
@@ -3159,7 +3169,8 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
}
out:
- reiserfs_write_unlock(inode->i_sb);
+ reiserfs_write_unlock_once(inode->i_sb, depth);
+
return error;
}
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index ace77451ceb..f53505de071 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -104,9 +104,10 @@ setflags_out:
err = put_user(inode->i_generation, (int __user *)arg);
break;
case REISERFS_IOC_SETVERSION:
- if (!is_owner_or_cap(inode))
+ if (!is_owner_or_cap(inode)) {
err = -EPERM;
break;
+ }
err = mnt_want_write(filp->f_path.mnt);
if (err)
break;
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index c3b004ee627..81f09fab8ae 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -452,7 +452,9 @@ static int lookup_and_delete_xattr(struct inode *inode, const char *name)
}
if (dentry->d_inode) {
+ reiserfs_write_lock(inode->i_sb);
err = xattr_unlink(xadir->d_inode, dentry);
+ reiserfs_write_unlock(inode->i_sb);
update_ctime(inode);
}
@@ -486,17 +488,21 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
if (get_inode_sd_version(inode) == STAT_DATA_V1)
return -EOPNOTSUPP;
- if (!buffer)
- return lookup_and_delete_xattr(inode, name);
-
reiserfs_write_unlock(inode->i_sb);
+
+ if (!buffer) {
+ err = lookup_and_delete_xattr(inode, name);
+ reiserfs_write_lock(inode->i_sb);
+ return err;
+ }
+
dentry = xattr_lookup(inode, name, flags);
if (IS_ERR(dentry)) {
reiserfs_write_lock(inode->i_sb);
return PTR_ERR(dentry);
}
- down_read(&REISERFS_I(inode)->i_xattr_sem);
+ down_write(&REISERFS_I(inode)->i_xattr_sem);
reiserfs_write_lock(inode->i_sb);
@@ -554,8 +560,12 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
.ia_size = buffer_size,
.ia_valid = ATTR_SIZE | ATTR_CTIME,
};
+
+ reiserfs_write_unlock(inode->i_sb);
mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_XATTR);
down_write(&dentry->d_inode->i_alloc_sem);
+ reiserfs_write_lock(inode->i_sb);
+
err = reiserfs_setattr(dentry, &newattrs);
up_write(&dentry->d_inode->i_alloc_sem);
mutex_unlock(&dentry->d_inode->i_mutex);
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index cc32e6ada67..dd20a7883f0 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -455,7 +455,9 @@ int reiserfs_acl_chmod(struct inode *inode)
return 0;
}
+ reiserfs_write_unlock(inode->i_sb);
acl = reiserfs_get_acl(inode, ACL_TYPE_ACCESS);
+ reiserfs_write_lock(inode->i_sb);
if (!acl)
return 0;
if (IS_ERR(acl))
diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c
index 618c2701d3a..e5a3d8e96bb 100644
--- a/fs/ubifs/gc.c
+++ b/fs/ubifs/gc.c
@@ -54,6 +54,7 @@
*/
#include <linux/pagemap.h>
+#include <linux/list_sort.h>
#include "ubifs.h"
/*
@@ -108,101 +109,6 @@ static int switch_gc_head(struct ubifs_info *c)
}
/**
- * list_sort - sort a list.
- * @priv: private data, passed to @cmp
- * @head: the list to sort
- * @cmp: the elements comparison function
- *
- * This function has been implemented by Mark J Roberts <mjr@znex.org>. It
- * implements "merge sort" which has O(nlog(n)) complexity. The list is sorted
- * in ascending order.
- *
- * The comparison function @cmp is supposed to return a negative value if @a is
- * than @b, and a positive value if @a is greater than @b. If @a and @b are
- * equivalent, then it does not matter what this function returns.
- */
-static void list_sort(void *priv, struct list_head *head,
- int (*cmp)(void *priv, struct list_head *a,
- struct list_head *b))
-{
- struct list_head *p, *q, *e, *list, *tail, *oldhead;
- int insize, nmerges, psize, qsize, i;
-
- if (list_empty(head))
- return;
-
- list = head->next;
- list_del(head);
- insize = 1;
- for (;;) {
- p = oldhead = list;
- list = tail = NULL;
- nmerges = 0;
-
- while (p) {
- nmerges++;
- q = p;
- psize = 0;
- for (i = 0; i < insize; i++) {
- psize++;
- q = q->next == oldhead ? NULL : q->next;
- if (!q)
- break;
- }
-
- qsize = insize;
- while (psize > 0 || (qsize > 0 && q)) {
- if (!psize) {
- e = q;
- q = q->next;
- qsize--;
- if (q == oldhead)
- q = NULL;
- } else if (!qsize || !q) {
- e = p;
- p = p->next;
- psize--;
- if (p == oldhead)
- p = NULL;
- } else if (cmp(priv, p, q) <= 0) {
- e = p;
- p = p->next;
- psize--;
- if (p == oldhead)
- p = NULL;
- } else {
- e = q;
- q = q->next;
- qsize--;
- if (q == oldhead)
- q = NULL;
- }
- if (tail)
- tail->next = e;
- else
- list = e;
- e->prev = tail;
- tail = e;
- }
- p = q;
- }
-
- tail->next = list;
- list->prev = tail;
-
- if (nmerges <= 1)
- break;
-
- insize *= 2;
- }
-
- head->next = list;
- head->prev = list->prev;
- list->prev->next = head;
- list->prev = head;
-}
-
-/**
* data_nodes_cmp - compare 2 data nodes.
* @priv: UBIFS file-system description object
* @a: first data node
diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c
index 2512125dfa7..883ca5ab8af 100644
--- a/fs/xfs/linux-2.6/xfs_acl.c
+++ b/fs/xfs/linux-2.6/xfs_acl.c
@@ -251,8 +251,9 @@ xfs_set_mode(struct inode *inode, mode_t mode)
if (mode != inode->i_mode) {
struct iattr iattr;
- iattr.ia_valid = ATTR_MODE;
+ iattr.ia_valid = ATTR_MODE | ATTR_CTIME;
iattr.ia_mode = mode;
+ iattr.ia_ctime = current_fs_time(inode->i_sb);
error = -xfs_setattr(XFS_I(inode), &iattr, XFS_ATTR_NOACL);
}
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 09783cc444a..77414db10dc 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -954,16 +954,14 @@ xfs_fs_destroy_inode(
ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIM));
/*
- * If we have nothing to flush with this inode then complete the
- * teardown now, otherwise delay the flush operation.
+ * We always use background reclaim here because even if the
+ * inode is clean, it still may be under IO and hence we have
+ * to take the flush lock. The background reclaim path handles
+ * this more efficiently than we can here, so simply let background
+ * reclaim tear down all inodes.
*/
- if (!xfs_inode_clean(ip)) {
- xfs_inode_set_reclaim_tag(ip);
- return;
- }
-
out_reclaim:
- xfs_ireclaim(ip);
+ xfs_inode_set_reclaim_tag(ip);
}
/*
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 6fed97a8cd3..1f5e4bb5e97 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -65,7 +65,6 @@ xfs_inode_ag_lookup(
* as the tree is sparse and a gang lookup walks to find
* the number of objects requested.
*/
- read_lock(&pag->pag_ici_lock);
if (tag == XFS_ICI_NO_TAG) {
nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
(void **)&ip, *first_index, 1);
@@ -74,7 +73,7 @@ xfs_inode_ag_lookup(
(void **)&ip, *first_index, 1, tag);
}
if (!nr_found)
- goto unlock;
+ return NULL;
/*
* Update the index for the next lookup. Catch overflows
@@ -84,13 +83,8 @@ xfs_inode_ag_lookup(
*/
*first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
if (*first_index < XFS_INO_TO_AGINO(mp, ip->i_ino))
- goto unlock;
-
+ return NULL;
return ip;
-
-unlock:
- read_unlock(&pag->pag_ici_lock);
- return NULL;
}
STATIC int
@@ -100,7 +94,8 @@ xfs_inode_ag_walk(
int (*execute)(struct xfs_inode *ip,
struct xfs_perag *pag, int flags),
int flags,
- int tag)
+ int tag,
+ int exclusive)
{
struct xfs_perag *pag = &mp->m_perag[ag];
uint32_t first_index;
@@ -114,10 +109,20 @@ restart:
int error = 0;
xfs_inode_t *ip;
+ if (exclusive)
+ write_lock(&pag->pag_ici_lock);
+ else
+ read_lock(&pag->pag_ici_lock);
ip = xfs_inode_ag_lookup(mp, pag, &first_index, tag);
- if (!ip)
+ if (!ip) {
+ if (exclusive)
+ write_unlock(&pag->pag_ici_lock);
+ else
+ read_unlock(&pag->pag_ici_lock);
break;
+ }
+ /* execute releases pag->pag_ici_lock */
error = execute(ip, pag, flags);
if (error == EAGAIN) {
skipped++;
@@ -125,9 +130,8 @@ restart:
}
if (error)
last_error = error;
- /*
- * bail out if the filesystem is corrupted.
- */
+
+ /* bail out if the filesystem is corrupted. */
if (error == EFSCORRUPTED)
break;
@@ -148,7 +152,8 @@ xfs_inode_ag_iterator(
int (*execute)(struct xfs_inode *ip,
struct xfs_perag *pag, int flags),
int flags,
- int tag)
+ int tag,
+ int exclusive)
{
int error = 0;
int last_error = 0;
@@ -157,7 +162,8 @@ xfs_inode_ag_iterator(
for (ag = 0; ag < mp->m_sb.sb_agcount; ag++) {
if (!mp->m_perag[ag].pag_ici_init)
continue;
- error = xfs_inode_ag_walk(mp, ag, execute, flags, tag);
+ error = xfs_inode_ag_walk(mp, ag, execute, flags, tag,
+ exclusive);
if (error) {
last_error = error;
if (error == EFSCORRUPTED)
@@ -174,30 +180,31 @@ xfs_sync_inode_valid(
struct xfs_perag *pag)
{
struct inode *inode = VFS_I(ip);
+ int error = EFSCORRUPTED;
/* nothing to sync during shutdown */
- if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
- read_unlock(&pag->pag_ici_lock);
- return EFSCORRUPTED;
- }
+ if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+ goto out_unlock;
- /*
- * If we can't get a reference on the inode, it must be in reclaim.
- * Leave it for the reclaim code to flush. Also avoid inodes that
- * haven't been fully initialised.
- */
- if (!igrab(inode)) {
- read_unlock(&pag->pag_ici_lock);
- return ENOENT;
- }
- read_unlock(&pag->pag_ici_lock);
+ /* avoid new or reclaimable inodes. Leave for reclaim code to flush */
+ error = ENOENT;
+ if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
+ goto out_unlock;
- if (is_bad_inode(inode) || xfs_iflags_test(ip, XFS_INEW)) {
+ /* If we can't grab the inode, it must on it's way to reclaim. */
+ if (!igrab(inode))
+ goto out_unlock;
+
+ if (is_bad_inode(inode)) {
IRELE(ip);
- return ENOENT;
+ goto out_unlock;
}
- return 0;
+ /* inode is valid */
+ error = 0;
+out_unlock:
+ read_unlock(&pag->pag_ici_lock);
+ return error;
}
STATIC int
@@ -282,7 +289,7 @@ xfs_sync_data(
ASSERT((flags & ~(SYNC_TRYLOCK|SYNC_WAIT)) == 0);
error = xfs_inode_ag_iterator(mp, xfs_sync_inode_data, flags,
- XFS_ICI_NO_TAG);
+ XFS_ICI_NO_TAG, 0);
if (error)
return XFS_ERROR(error);
@@ -304,7 +311,7 @@ xfs_sync_attr(
ASSERT((flags & ~SYNC_WAIT) == 0);
return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags,
- XFS_ICI_NO_TAG);
+ XFS_ICI_NO_TAG, 0);
}
STATIC int
@@ -664,60 +671,6 @@ xfs_syncd_stop(
kthread_stop(mp->m_sync_task);
}
-STATIC int
-xfs_reclaim_inode(
- xfs_inode_t *ip,
- int sync_mode)
-{
- xfs_perag_t *pag = xfs_get_perag(ip->i_mount, ip->i_ino);
-
- /* The hash lock here protects a thread in xfs_iget_core from
- * racing with us on linking the inode back with a vnode.
- * Once we have the XFS_IRECLAIM flag set it will not touch
- * us.
- */
- write_lock(&pag->pag_ici_lock);
- spin_lock(&ip->i_flags_lock);
- if (__xfs_iflags_test(ip, XFS_IRECLAIM) ||
- !__xfs_iflags_test(ip, XFS_IRECLAIMABLE)) {
- spin_unlock(&ip->i_flags_lock);
- write_unlock(&pag->pag_ici_lock);
- return -EAGAIN;
- }
- __xfs_iflags_set(ip, XFS_IRECLAIM);
- spin_unlock(&ip->i_flags_lock);
- write_unlock(&pag->pag_ici_lock);
- xfs_put_perag(ip->i_mount, pag);
-
- /*
- * If the inode is still dirty, then flush it out. If the inode
- * is not in the AIL, then it will be OK to flush it delwri as
- * long as xfs_iflush() does not keep any references to the inode.
- * We leave that decision up to xfs_iflush() since it has the
- * knowledge of whether it's OK to simply do a delwri flush of
- * the inode or whether we need to wait until the inode is
- * pulled from the AIL.
- * We get the flush lock regardless, though, just to make sure
- * we don't free it while it is being flushed.
- */
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_iflock(ip);
-
- /*
- * In the case of a forced shutdown we rely on xfs_iflush() to
- * wait for the inode to be unpinned before returning an error.
- */
- if (!is_bad_inode(VFS_I(ip)) && xfs_iflush(ip, sync_mode) == 0) {
- /* synchronize with xfs_iflush_done */
- xfs_iflock(ip);
- xfs_ifunlock(ip);
- }
-
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- xfs_ireclaim(ip);
- return 0;
-}
-
void
__xfs_inode_set_reclaim_tag(
struct xfs_perag *pag,
@@ -760,19 +713,55 @@ __xfs_inode_clear_reclaim_tag(
}
STATIC int
-xfs_reclaim_inode_now(
+xfs_reclaim_inode(
struct xfs_inode *ip,
struct xfs_perag *pag,
- int flags)
+ int sync_mode)
{
- /* ignore if already under reclaim */
- if (xfs_iflags_test(ip, XFS_IRECLAIM)) {
- read_unlock(&pag->pag_ici_lock);
+ /*
+ * The radix tree lock here protects a thread in xfs_iget from racing
+ * with us starting reclaim on the inode. Once we have the
+ * XFS_IRECLAIM flag set it will not touch us.
+ */
+ spin_lock(&ip->i_flags_lock);
+ ASSERT_ALWAYS(__xfs_iflags_test(ip, XFS_IRECLAIMABLE));
+ if (__xfs_iflags_test(ip, XFS_IRECLAIM)) {
+ /* ignore as it is already under reclaim */
+ spin_unlock(&ip->i_flags_lock);
+ write_unlock(&pag->pag_ici_lock);
return 0;
}
- read_unlock(&pag->pag_ici_lock);
+ __xfs_iflags_set(ip, XFS_IRECLAIM);
+ spin_unlock(&ip->i_flags_lock);
+ write_unlock(&pag->pag_ici_lock);
- return xfs_reclaim_inode(ip, flags);
+ /*
+ * If the inode is still dirty, then flush it out. If the inode
+ * is not in the AIL, then it will be OK to flush it delwri as
+ * long as xfs_iflush() does not keep any references to the inode.
+ * We leave that decision up to xfs_iflush() since it has the
+ * knowledge of whether it's OK to simply do a delwri flush of
+ * the inode or whether we need to wait until the inode is
+ * pulled from the AIL.
+ * We get the flush lock regardless, though, just to make sure
+ * we don't free it while it is being flushed.
+ */
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_iflock(ip);
+
+ /*
+ * In the case of a forced shutdown we rely on xfs_iflush() to
+ * wait for the inode to be unpinned before returning an error.
+ */
+ if (!is_bad_inode(VFS_I(ip)) && xfs_iflush(ip, sync_mode) == 0) {
+ /* synchronize with xfs_iflush_done */
+ xfs_iflock(ip);
+ xfs_ifunlock(ip);
+ }
+
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ xfs_ireclaim(ip);
+ return 0;
}
int
@@ -780,6 +769,6 @@ xfs_reclaim_inodes(
xfs_mount_t *mp,
int mode)
{
- return xfs_inode_ag_iterator(mp, xfs_reclaim_inode_now, mode,
- XFS_ICI_RECLAIM_TAG);
+ return xfs_inode_ag_iterator(mp, xfs_reclaim_inode, mode,
+ XFS_ICI_RECLAIM_TAG, 1);
}
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index a500b4d9183..ea932b43335 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -54,6 +54,6 @@ void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp, struct xfs_perag *pag,
int xfs_sync_inode_valid(struct xfs_inode *ip, struct xfs_perag *pag);
int xfs_inode_ag_iterator(struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag, int flags),
- int flags, int tag);
+ int flags, int tag, int write_lock);
#endif
diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h
index c40834bdee5..c22a608321a 100644
--- a/fs/xfs/linux-2.6/xfs_trace.h
+++ b/fs/xfs/linux-2.6/xfs_trace.h
@@ -33,51 +33,55 @@ struct xfs_dquot;
struct xlog_ticket;
struct log;
+DECLARE_EVENT_CLASS(xfs_attr_list_class,
+ TP_PROTO(struct xfs_attr_list_context *ctx),
+ TP_ARGS(ctx),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(u32, hashval)
+ __field(u32, blkno)
+ __field(u32, offset)
+ __field(void *, alist)
+ __field(int, bufsize)
+ __field(int, count)
+ __field(int, firstu)
+ __field(int, dupcnt)
+ __field(int, flags)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(ctx->dp)->i_sb->s_dev;
+ __entry->ino = ctx->dp->i_ino;
+ __entry->hashval = ctx->cursor->hashval;
+ __entry->blkno = ctx->cursor->blkno;
+ __entry->offset = ctx->cursor->offset;
+ __entry->alist = ctx->alist;
+ __entry->bufsize = ctx->bufsize;
+ __entry->count = ctx->count;
+ __entry->firstu = ctx->firstu;
+ __entry->flags = ctx->flags;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx cursor h/b/o 0x%x/0x%x/%u dupcnt %u "
+ "alist 0x%p size %u count %u firstu %u flags %d %s",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->hashval,
+ __entry->blkno,
+ __entry->offset,
+ __entry->dupcnt,
+ __entry->alist,
+ __entry->bufsize,
+ __entry->count,
+ __entry->firstu,
+ __entry->flags,
+ __print_flags(__entry->flags, "|", XFS_ATTR_FLAGS)
+ )
+)
+
#define DEFINE_ATTR_LIST_EVENT(name) \
-TRACE_EVENT(name, \
+DEFINE_EVENT(xfs_attr_list_class, name, \
TP_PROTO(struct xfs_attr_list_context *ctx), \
- TP_ARGS(ctx), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(xfs_ino_t, ino) \
- __field(u32, hashval) \
- __field(u32, blkno) \
- __field(u32, offset) \
- __field(void *, alist) \
- __field(int, bufsize) \
- __field(int, count) \
- __field(int, firstu) \
- __field(int, dupcnt) \
- __field(int, flags) \
- ), \
- TP_fast_assign( \
- __entry->dev = VFS_I(ctx->dp)->i_sb->s_dev; \
- __entry->ino = ctx->dp->i_ino; \
- __entry->hashval = ctx->cursor->hashval; \
- __entry->blkno = ctx->cursor->blkno; \
- __entry->offset = ctx->cursor->offset; \
- __entry->alist = ctx->alist; \
- __entry->bufsize = ctx->bufsize; \
- __entry->count = ctx->count; \
- __entry->firstu = ctx->firstu; \
- __entry->flags = ctx->flags; \
- ), \
- TP_printk("dev %d:%d ino 0x%llx cursor h/b/o 0x%x/0x%x/%u dupcnt %u " \
- "alist 0x%p size %u count %u firstu %u flags %d %s", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- __entry->ino, \
- __entry->hashval, \
- __entry->blkno, \
- __entry->offset, \
- __entry->dupcnt, \
- __entry->alist, \
- __entry->bufsize, \
- __entry->count, \
- __entry->firstu, \
- __entry->flags, \
- __print_flags(__entry->flags, "|", XFS_ATTR_FLAGS) \
- ) \
-)
+ TP_ARGS(ctx))
DEFINE_ATTR_LIST_EVENT(xfs_attr_list_sf);
DEFINE_ATTR_LIST_EVENT(xfs_attr_list_sf_all);
DEFINE_ATTR_LIST_EVENT(xfs_attr_list_leaf);
@@ -178,91 +182,99 @@ TRACE_EVENT(xfs_iext_insert,
(char *)__entry->caller_ip)
);
+DECLARE_EVENT_CLASS(xfs_bmap_class,
+ TP_PROTO(struct xfs_inode *ip, xfs_extnum_t idx, int state,
+ unsigned long caller_ip),
+ TP_ARGS(ip, idx, state, caller_ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_extnum_t, idx)
+ __field(xfs_fileoff_t, startoff)
+ __field(xfs_fsblock_t, startblock)
+ __field(xfs_filblks_t, blockcount)
+ __field(xfs_exntst_t, state)
+ __field(int, bmap_state)
+ __field(unsigned long, caller_ip)
+ ),
+ TP_fast_assign(
+ struct xfs_ifork *ifp = (state & BMAP_ATTRFORK) ?
+ ip->i_afp : &ip->i_df;
+ struct xfs_bmbt_irec r;
+
+ xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &r);
+ __entry->dev = VFS_I(ip)->i_sb->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->idx = idx;
+ __entry->startoff = r.br_startoff;
+ __entry->startblock = r.br_startblock;
+ __entry->blockcount = r.br_blockcount;
+ __entry->state = r.br_state;
+ __entry->bmap_state = state;
+ __entry->caller_ip = caller_ip;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx state %s idx %ld "
+ "offset %lld block %s count %lld flag %d caller %pf",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS),
+ (long)__entry->idx,
+ __entry->startoff,
+ xfs_fmtfsblock(__entry->startblock),
+ __entry->blockcount,
+ __entry->state,
+ (char *)__entry->caller_ip)
+)
+
#define DEFINE_BMAP_EVENT(name) \
-TRACE_EVENT(name, \
+DEFINE_EVENT(xfs_bmap_class, name, \
TP_PROTO(struct xfs_inode *ip, xfs_extnum_t idx, int state, \
unsigned long caller_ip), \
- TP_ARGS(ip, idx, state, caller_ip), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(xfs_ino_t, ino) \
- __field(xfs_extnum_t, idx) \
- __field(xfs_fileoff_t, startoff) \
- __field(xfs_fsblock_t, startblock) \
- __field(xfs_filblks_t, blockcount) \
- __field(xfs_exntst_t, state) \
- __field(int, bmap_state) \
- __field(unsigned long, caller_ip) \
- ), \
- TP_fast_assign( \
- struct xfs_ifork *ifp = (state & BMAP_ATTRFORK) ? \
- ip->i_afp : &ip->i_df; \
- struct xfs_bmbt_irec r; \
- \
- xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &r); \
- __entry->dev = VFS_I(ip)->i_sb->s_dev; \
- __entry->ino = ip->i_ino; \
- __entry->idx = idx; \
- __entry->startoff = r.br_startoff; \
- __entry->startblock = r.br_startblock; \
- __entry->blockcount = r.br_blockcount; \
- __entry->state = r.br_state; \
- __entry->bmap_state = state; \
- __entry->caller_ip = caller_ip; \
- ), \
- TP_printk("dev %d:%d ino 0x%llx state %s idx %ld " \
- "offset %lld block %s count %lld flag %d caller %pf", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- __entry->ino, \
- __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS), \
- (long)__entry->idx, \
- __entry->startoff, \
- xfs_fmtfsblock(__entry->startblock), \
- __entry->blockcount, \
- __entry->state, \
- (char *)__entry->caller_ip) \
-)
-
+ TP_ARGS(ip, idx, state, caller_ip))
DEFINE_BMAP_EVENT(xfs_iext_remove);
DEFINE_BMAP_EVENT(xfs_bmap_pre_update);
DEFINE_BMAP_EVENT(xfs_bmap_post_update);
DEFINE_BMAP_EVENT(xfs_extlist);
-#define DEFINE_BUF_EVENT(tname) \
-TRACE_EVENT(tname, \
- TP_PROTO(struct xfs_buf *bp, unsigned long caller_ip), \
- TP_ARGS(bp, caller_ip), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(xfs_daddr_t, bno) \
- __field(size_t, buffer_length) \
- __field(int, hold) \
- __field(int, pincount) \
- __field(unsigned, lockval) \
- __field(unsigned, flags) \
- __field(unsigned long, caller_ip) \
- ), \
- TP_fast_assign( \
- __entry->dev = bp->b_target->bt_dev; \
- __entry->bno = bp->b_bn; \
- __entry->buffer_length = bp->b_buffer_length; \
- __entry->hold = atomic_read(&bp->b_hold); \
- __entry->pincount = atomic_read(&bp->b_pin_count); \
- __entry->lockval = xfs_buf_lock_value(bp); \
- __entry->flags = bp->b_flags; \
- __entry->caller_ip = caller_ip; \
- ), \
- TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d " \
- "lock %d flags %s caller %pf", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- (unsigned long long)__entry->bno, \
- __entry->buffer_length, \
- __entry->hold, \
- __entry->pincount, \
- __entry->lockval, \
- __print_flags(__entry->flags, "|", XFS_BUF_FLAGS), \
- (void *)__entry->caller_ip) \
+DECLARE_EVENT_CLASS(xfs_buf_class,
+ TP_PROTO(struct xfs_buf *bp, unsigned long caller_ip),
+ TP_ARGS(bp, caller_ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_daddr_t, bno)
+ __field(size_t, buffer_length)
+ __field(int, hold)
+ __field(int, pincount)
+ __field(unsigned, lockval)
+ __field(unsigned, flags)
+ __field(unsigned long, caller_ip)
+ ),
+ TP_fast_assign(
+ __entry->dev = bp->b_target->bt_dev;
+ __entry->bno = bp->b_bn;
+ __entry->buffer_length = bp->b_buffer_length;
+ __entry->hold = atomic_read(&bp->b_hold);
+ __entry->pincount = atomic_read(&bp->b_pin_count);
+ __entry->lockval = xfs_buf_lock_value(bp);
+ __entry->flags = bp->b_flags;
+ __entry->caller_ip = caller_ip;
+ ),
+ TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d "
+ "lock %d flags %s caller %pf",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->bno,
+ __entry->buffer_length,
+ __entry->hold,
+ __entry->pincount,
+ __entry->lockval,
+ __print_flags(__entry->flags, "|", XFS_BUF_FLAGS),
+ (void *)__entry->caller_ip)
)
+
+#define DEFINE_BUF_EVENT(name) \
+DEFINE_EVENT(xfs_buf_class, name, \
+ TP_PROTO(struct xfs_buf *bp, unsigned long caller_ip), \
+ TP_ARGS(bp, caller_ip))
DEFINE_BUF_EVENT(xfs_buf_init);
DEFINE_BUF_EVENT(xfs_buf_free);
DEFINE_BUF_EVENT(xfs_buf_hold);
@@ -299,41 +311,45 @@ DEFINE_BUF_EVENT(xfs_reset_dqcounts);
DEFINE_BUF_EVENT(xfs_inode_item_push);
/* pass flags explicitly */
-#define DEFINE_BUF_FLAGS_EVENT(tname) \
-TRACE_EVENT(tname, \
- TP_PROTO(struct xfs_buf *bp, unsigned flags, unsigned long caller_ip), \
- TP_ARGS(bp, flags, caller_ip), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(xfs_daddr_t, bno) \
- __field(size_t, buffer_length) \
- __field(int, hold) \
- __field(int, pincount) \
- __field(unsigned, lockval) \
- __field(unsigned, flags) \
- __field(unsigned long, caller_ip) \
- ), \
- TP_fast_assign( \
- __entry->dev = bp->b_target->bt_dev; \
- __entry->bno = bp->b_bn; \
- __entry->buffer_length = bp->b_buffer_length; \
- __entry->flags = flags; \
- __entry->hold = atomic_read(&bp->b_hold); \
- __entry->pincount = atomic_read(&bp->b_pin_count); \
- __entry->lockval = xfs_buf_lock_value(bp); \
- __entry->caller_ip = caller_ip; \
- ), \
- TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d " \
- "lock %d flags %s caller %pf", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- (unsigned long long)__entry->bno, \
- __entry->buffer_length, \
- __entry->hold, \
- __entry->pincount, \
- __entry->lockval, \
- __print_flags(__entry->flags, "|", XFS_BUF_FLAGS), \
- (void *)__entry->caller_ip) \
+DECLARE_EVENT_CLASS(xfs_buf_flags_class,
+ TP_PROTO(struct xfs_buf *bp, unsigned flags, unsigned long caller_ip),
+ TP_ARGS(bp, flags, caller_ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_daddr_t, bno)
+ __field(size_t, buffer_length)
+ __field(int, hold)
+ __field(int, pincount)
+ __field(unsigned, lockval)
+ __field(unsigned, flags)
+ __field(unsigned long, caller_ip)
+ ),
+ TP_fast_assign(
+ __entry->dev = bp->b_target->bt_dev;
+ __entry->bno = bp->b_bn;
+ __entry->buffer_length = bp->b_buffer_length;
+ __entry->flags = flags;
+ __entry->hold = atomic_read(&bp->b_hold);
+ __entry->pincount = atomic_read(&bp->b_pin_count);
+ __entry->lockval = xfs_buf_lock_value(bp);
+ __entry->caller_ip = caller_ip;
+ ),
+ TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d "
+ "lock %d flags %s caller %pf",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->bno,
+ __entry->buffer_length,
+ __entry->hold,
+ __entry->pincount,
+ __entry->lockval,
+ __print_flags(__entry->flags, "|", XFS_BUF_FLAGS),
+ (void *)__entry->caller_ip)
)
+
+#define DEFINE_BUF_FLAGS_EVENT(name) \
+DEFINE_EVENT(xfs_buf_flags_class, name, \
+ TP_PROTO(struct xfs_buf *bp, unsigned flags, unsigned long caller_ip), \
+ TP_ARGS(bp, flags, caller_ip))
DEFINE_BUF_FLAGS_EVENT(xfs_buf_find);
DEFINE_BUF_FLAGS_EVENT(xfs_buf_get);
DEFINE_BUF_FLAGS_EVENT(xfs_buf_read);
@@ -376,55 +392,58 @@ TRACE_EVENT(xfs_buf_ioerror,
(void *)__entry->caller_ip)
);
-#define DEFINE_BUF_ITEM_EVENT(tname) \
-TRACE_EVENT(tname, \
- TP_PROTO(struct xfs_buf_log_item *bip), \
- TP_ARGS(bip), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(xfs_daddr_t, buf_bno) \
- __field(size_t, buf_len) \
- __field(int, buf_hold) \
- __field(int, buf_pincount) \
- __field(int, buf_lockval) \
- __field(unsigned, buf_flags) \
- __field(unsigned, bli_recur) \
- __field(int, bli_refcount) \
- __field(unsigned, bli_flags) \
- __field(void *, li_desc) \
- __field(unsigned, li_flags) \
- ), \
- TP_fast_assign( \
- __entry->dev = bip->bli_buf->b_target->bt_dev; \
- __entry->bli_flags = bip->bli_flags; \
- __entry->bli_recur = bip->bli_recur; \
- __entry->bli_refcount = atomic_read(&bip->bli_refcount); \
- __entry->buf_bno = bip->bli_buf->b_bn; \
- __entry->buf_len = bip->bli_buf->b_buffer_length; \
- __entry->buf_flags = bip->bli_buf->b_flags; \
- __entry->buf_hold = atomic_read(&bip->bli_buf->b_hold); \
- __entry->buf_pincount = \
- atomic_read(&bip->bli_buf->b_pin_count); \
- __entry->buf_lockval = xfs_buf_lock_value(bip->bli_buf); \
- __entry->li_desc = bip->bli_item.li_desc; \
- __entry->li_flags = bip->bli_item.li_flags; \
- ), \
- TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d " \
- "lock %d flags %s recur %d refcount %d bliflags %s " \
- "lidesc 0x%p liflags %s", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- (unsigned long long)__entry->buf_bno, \
- __entry->buf_len, \
- __entry->buf_hold, \
- __entry->buf_pincount, \
- __entry->buf_lockval, \
- __print_flags(__entry->buf_flags, "|", XFS_BUF_FLAGS), \
- __entry->bli_recur, \
- __entry->bli_refcount, \
- __print_flags(__entry->bli_flags, "|", XFS_BLI_FLAGS), \
- __entry->li_desc, \
- __print_flags(__entry->li_flags, "|", XFS_LI_FLAGS)) \
+DECLARE_EVENT_CLASS(xfs_buf_item_class,
+ TP_PROTO(struct xfs_buf_log_item *bip),
+ TP_ARGS(bip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_daddr_t, buf_bno)
+ __field(size_t, buf_len)
+ __field(int, buf_hold)
+ __field(int, buf_pincount)
+ __field(int, buf_lockval)
+ __field(unsigned, buf_flags)
+ __field(unsigned, bli_recur)
+ __field(int, bli_refcount)
+ __field(unsigned, bli_flags)
+ __field(void *, li_desc)
+ __field(unsigned, li_flags)
+ ),
+ TP_fast_assign(
+ __entry->dev = bip->bli_buf->b_target->bt_dev;
+ __entry->bli_flags = bip->bli_flags;
+ __entry->bli_recur = bip->bli_recur;
+ __entry->bli_refcount = atomic_read(&bip->bli_refcount);
+ __entry->buf_bno = bip->bli_buf->b_bn;
+ __entry->buf_len = bip->bli_buf->b_buffer_length;
+ __entry->buf_flags = bip->bli_buf->b_flags;
+ __entry->buf_hold = atomic_read(&bip->bli_buf->b_hold);
+ __entry->buf_pincount = atomic_read(&bip->bli_buf->b_pin_count);
+ __entry->buf_lockval = xfs_buf_lock_value(bip->bli_buf);
+ __entry->li_desc = bip->bli_item.li_desc;
+ __entry->li_flags = bip->bli_item.li_flags;
+ ),
+ TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d "
+ "lock %d flags %s recur %d refcount %d bliflags %s "
+ "lidesc 0x%p liflags %s",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->buf_bno,
+ __entry->buf_len,
+ __entry->buf_hold,
+ __entry->buf_pincount,
+ __entry->buf_lockval,
+ __print_flags(__entry->buf_flags, "|", XFS_BUF_FLAGS),
+ __entry->bli_recur,
+ __entry->bli_refcount,
+ __print_flags(__entry->bli_flags, "|", XFS_BLI_FLAGS),
+ __entry->li_desc,
+ __print_flags(__entry->li_flags, "|", XFS_LI_FLAGS))
)
+
+#define DEFINE_BUF_ITEM_EVENT(name) \
+DEFINE_EVENT(xfs_buf_item_class, name, \
+ TP_PROTO(struct xfs_buf_log_item *bip), \
+ TP_ARGS(bip))
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_stale);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format);
@@ -450,78 +469,90 @@ DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold);
DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold_release);
DEFINE_BUF_ITEM_EVENT(xfs_trans_binval);
+DECLARE_EVENT_CLASS(xfs_lock_class,
+ TP_PROTO(struct xfs_inode *ip, unsigned lock_flags,
+ unsigned long caller_ip),
+ TP_ARGS(ip, lock_flags, caller_ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(int, lock_flags)
+ __field(unsigned long, caller_ip)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(ip)->i_sb->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->lock_flags = lock_flags;
+ __entry->caller_ip = caller_ip;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx flags %s caller %pf",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __print_flags(__entry->lock_flags, "|", XFS_LOCK_FLAGS),
+ (void *)__entry->caller_ip)
+)
+
#define DEFINE_LOCK_EVENT(name) \
-TRACE_EVENT(name, \
+DEFINE_EVENT(xfs_lock_class, name, \
TP_PROTO(struct xfs_inode *ip, unsigned lock_flags, \
unsigned long caller_ip), \
- TP_ARGS(ip, lock_flags, caller_ip), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(xfs_ino_t, ino) \
- __field(int, lock_flags) \
- __field(unsigned long, caller_ip) \
- ), \
- TP_fast_assign( \
- __entry->dev = VFS_I(ip)->i_sb->s_dev; \
- __entry->ino = ip->i_ino; \
- __entry->lock_flags = lock_flags; \
- __entry->caller_ip = caller_ip; \
- ), \
- TP_printk("dev %d:%d ino 0x%llx flags %s caller %pf", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- __entry->ino, \
- __print_flags(__entry->lock_flags, "|", XFS_LOCK_FLAGS), \
- (void *)__entry->caller_ip) \
-)
-
+ TP_ARGS(ip, lock_flags, caller_ip))
DEFINE_LOCK_EVENT(xfs_ilock);
DEFINE_LOCK_EVENT(xfs_ilock_nowait);
DEFINE_LOCK_EVENT(xfs_ilock_demote);
DEFINE_LOCK_EVENT(xfs_iunlock);
+DECLARE_EVENT_CLASS(xfs_iget_class,
+ TP_PROTO(struct xfs_inode *ip),
+ TP_ARGS(ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(ip)->i_sb->s_dev;
+ __entry->ino = ip->i_ino;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino)
+)
+
#define DEFINE_IGET_EVENT(name) \
-TRACE_EVENT(name, \
+DEFINE_EVENT(xfs_iget_class, name, \
TP_PROTO(struct xfs_inode *ip), \
- TP_ARGS(ip), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(xfs_ino_t, ino) \
- ), \
- TP_fast_assign( \
- __entry->dev = VFS_I(ip)->i_sb->s_dev; \
- __entry->ino = ip->i_ino; \
- ), \
- TP_printk("dev %d:%d ino 0x%llx", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- __entry->ino) \
-)
+ TP_ARGS(ip))
DEFINE_IGET_EVENT(xfs_iget_skip);
DEFINE_IGET_EVENT(xfs_iget_reclaim);
DEFINE_IGET_EVENT(xfs_iget_found);
DEFINE_IGET_EVENT(xfs_iget_alloc);
+DECLARE_EVENT_CLASS(xfs_inode_class,
+ TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip),
+ TP_ARGS(ip, caller_ip),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(int, count)
+ __field(unsigned long, caller_ip)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(ip)->i_sb->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->count = atomic_read(&VFS_I(ip)->i_count);
+ __entry->caller_ip = caller_ip;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx count %d caller %pf",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->count,
+ (char *)__entry->caller_ip)
+)
+
#define DEFINE_INODE_EVENT(name) \
-TRACE_EVENT(name, \
+DEFINE_EVENT(xfs_inode_class, name, \
TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip), \
- TP_ARGS(ip, caller_ip), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(xfs_ino_t, ino) \
- __field(int, count) \
- __field(unsigned long, caller_ip) \
- ), \
- TP_fast_assign( \
- __entry->dev = VFS_I(ip)->i_sb->s_dev; \
- __entry->ino = ip->i_ino; \
- __entry->count = atomic_read(&VFS_I(ip)->i_count); \
- __entry->caller_ip = caller_ip; \
- ), \
- TP_printk("dev %d:%d ino 0x%llx count %d caller %pf", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- __entry->ino, \
- __entry->count, \
- (char *)__entry->caller_ip) \
-)
+ TP_ARGS(ip, caller_ip))
DEFINE_INODE_EVENT(xfs_ihold);
DEFINE_INODE_EVENT(xfs_irele);
/* the old xfs_itrace_entry tracer - to be replaced by s.th. in the VFS */
@@ -529,55 +560,59 @@ DEFINE_INODE_EVENT(xfs_inode);
#define xfs_itrace_entry(ip) \
trace_xfs_inode(ip, _THIS_IP_)
-#define DEFINE_DQUOT_EVENT(tname) \
-TRACE_EVENT(tname, \
- TP_PROTO(struct xfs_dquot *dqp), \
- TP_ARGS(dqp), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(__be32, id) \
- __field(unsigned, flags) \
- __field(unsigned, nrefs) \
- __field(unsigned long long, res_bcount) \
- __field(unsigned long long, bcount) \
- __field(unsigned long long, icount) \
- __field(unsigned long long, blk_hardlimit) \
- __field(unsigned long long, blk_softlimit) \
- __field(unsigned long long, ino_hardlimit) \
- __field(unsigned long long, ino_softlimit) \
- ), \
- TP_fast_assign( \
- __entry->dev = dqp->q_mount->m_super->s_dev; \
- __entry->id = dqp->q_core.d_id; \
- __entry->flags = dqp->dq_flags; \
- __entry->nrefs = dqp->q_nrefs; \
- __entry->res_bcount = dqp->q_res_bcount; \
- __entry->bcount = be64_to_cpu(dqp->q_core.d_bcount); \
- __entry->icount = be64_to_cpu(dqp->q_core.d_icount); \
- __entry->blk_hardlimit = \
- be64_to_cpu(dqp->q_core.d_blk_hardlimit); \
- __entry->blk_softlimit = \
- be64_to_cpu(dqp->q_core.d_blk_softlimit); \
- __entry->ino_hardlimit = \
- be64_to_cpu(dqp->q_core.d_ino_hardlimit); \
- __entry->ino_softlimit = \
- be64_to_cpu(dqp->q_core.d_ino_softlimit); \
+DECLARE_EVENT_CLASS(xfs_dquot_class,
+ TP_PROTO(struct xfs_dquot *dqp),
+ TP_ARGS(dqp),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(__be32, id)
+ __field(unsigned, flags)
+ __field(unsigned, nrefs)
+ __field(unsigned long long, res_bcount)
+ __field(unsigned long long, bcount)
+ __field(unsigned long long, icount)
+ __field(unsigned long long, blk_hardlimit)
+ __field(unsigned long long, blk_softlimit)
+ __field(unsigned long long, ino_hardlimit)
+ __field(unsigned long long, ino_softlimit)
), \
- TP_printk("dev %d:%d id 0x%x flags %s nrefs %u res_bc 0x%llx " \
- "bcnt 0x%llx [hard 0x%llx | soft 0x%llx] " \
- "icnt 0x%llx [hard 0x%llx | soft 0x%llx]", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- be32_to_cpu(__entry->id), \
- __print_flags(__entry->flags, "|", XFS_DQ_FLAGS), \
- __entry->nrefs, \
- __entry->res_bcount, \
- __entry->bcount, \
- __entry->blk_hardlimit, \
- __entry->blk_softlimit, \
- __entry->icount, \
- __entry->ino_hardlimit, \
- __entry->ino_softlimit) \
+ TP_fast_assign(
+ __entry->dev = dqp->q_mount->m_super->s_dev;
+ __entry->id = dqp->q_core.d_id;
+ __entry->flags = dqp->dq_flags;
+ __entry->nrefs = dqp->q_nrefs;
+ __entry->res_bcount = dqp->q_res_bcount;
+ __entry->bcount = be64_to_cpu(dqp->q_core.d_bcount);
+ __entry->icount = be64_to_cpu(dqp->q_core.d_icount);
+ __entry->blk_hardlimit =
+ be64_to_cpu(dqp->q_core.d_blk_hardlimit);
+ __entry->blk_softlimit =
+ be64_to_cpu(dqp->q_core.d_blk_softlimit);
+ __entry->ino_hardlimit =
+ be64_to_cpu(dqp->q_core.d_ino_hardlimit);
+ __entry->ino_softlimit =
+ be64_to_cpu(dqp->q_core.d_ino_softlimit);
+ ),
+ TP_printk("dev %d:%d id 0x%x flags %s nrefs %u res_bc 0x%llx "
+ "bcnt 0x%llx [hard 0x%llx | soft 0x%llx] "
+ "icnt 0x%llx [hard 0x%llx | soft 0x%llx]",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ be32_to_cpu(__entry->id),
+ __print_flags(__entry->flags, "|", XFS_DQ_FLAGS),
+ __entry->nrefs,
+ __entry->res_bcount,
+ __entry->bcount,
+ __entry->blk_hardlimit,
+ __entry->blk_softlimit,
+ __entry->icount,
+ __entry->ino_hardlimit,
+ __entry->ino_softlimit)
)
+
+#define DEFINE_DQUOT_EVENT(name) \
+DEFINE_EVENT(xfs_dquot_class, name, \
+ TP_PROTO(struct xfs_dquot *dqp), \
+ TP_ARGS(dqp))
DEFINE_DQUOT_EVENT(xfs_dqadjust);
DEFINE_DQUOT_EVENT(xfs_dqshake_dirty);
DEFINE_DQUOT_EVENT(xfs_dqshake_unlink);
@@ -610,72 +645,75 @@ DEFINE_DQUOT_EVENT(xfs_dqflush_done);
DEFINE_IGET_EVENT(xfs_dquot_dqalloc);
DEFINE_IGET_EVENT(xfs_dquot_dqdetach);
+DECLARE_EVENT_CLASS(xfs_loggrant_class,
+ TP_PROTO(struct log *log, struct xlog_ticket *tic),
+ TP_ARGS(log, tic),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(unsigned, trans_type)
+ __field(char, ocnt)
+ __field(char, cnt)
+ __field(int, curr_res)
+ __field(int, unit_res)
+ __field(unsigned int, flags)
+ __field(void *, reserve_headq)
+ __field(void *, write_headq)
+ __field(int, grant_reserve_cycle)
+ __field(int, grant_reserve_bytes)
+ __field(int, grant_write_cycle)
+ __field(int, grant_write_bytes)
+ __field(int, curr_cycle)
+ __field(int, curr_block)
+ __field(xfs_lsn_t, tail_lsn)
+ ),
+ TP_fast_assign(
+ __entry->dev = log->l_mp->m_super->s_dev;
+ __entry->trans_type = tic->t_trans_type;
+ __entry->ocnt = tic->t_ocnt;
+ __entry->cnt = tic->t_cnt;
+ __entry->curr_res = tic->t_curr_res;
+ __entry->unit_res = tic->t_unit_res;
+ __entry->flags = tic->t_flags;
+ __entry->reserve_headq = log->l_reserve_headq;
+ __entry->write_headq = log->l_write_headq;
+ __entry->grant_reserve_cycle = log->l_grant_reserve_cycle;
+ __entry->grant_reserve_bytes = log->l_grant_reserve_bytes;
+ __entry->grant_write_cycle = log->l_grant_write_cycle;
+ __entry->grant_write_bytes = log->l_grant_write_bytes;
+ __entry->curr_cycle = log->l_curr_cycle;
+ __entry->curr_block = log->l_curr_block;
+ __entry->tail_lsn = log->l_tail_lsn;
+ ),
+ TP_printk("dev %d:%d type %s t_ocnt %u t_cnt %u t_curr_res %u "
+ "t_unit_res %u t_flags %s reserve_headq 0x%p "
+ "write_headq 0x%p grant_reserve_cycle %d "
+ "grant_reserve_bytes %d grant_write_cycle %d "
+ "grant_write_bytes %d curr_cycle %d curr_block %d "
+ "tail_cycle %d tail_block %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __print_symbolic(__entry->trans_type, XFS_TRANS_TYPES),
+ __entry->ocnt,
+ __entry->cnt,
+ __entry->curr_res,
+ __entry->unit_res,
+ __print_flags(__entry->flags, "|", XLOG_TIC_FLAGS),
+ __entry->reserve_headq,
+ __entry->write_headq,
+ __entry->grant_reserve_cycle,
+ __entry->grant_reserve_bytes,
+ __entry->grant_write_cycle,
+ __entry->grant_write_bytes,
+ __entry->curr_cycle,
+ __entry->curr_block,
+ CYCLE_LSN(__entry->tail_lsn),
+ BLOCK_LSN(__entry->tail_lsn)
+ )
+)
-#define DEFINE_LOGGRANT_EVENT(tname) \
-TRACE_EVENT(tname, \
+#define DEFINE_LOGGRANT_EVENT(name) \
+DEFINE_EVENT(xfs_loggrant_class, name, \
TP_PROTO(struct log *log, struct xlog_ticket *tic), \
- TP_ARGS(log, tic), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(unsigned, trans_type) \
- __field(char, ocnt) \
- __field(char, cnt) \
- __field(int, curr_res) \
- __field(int, unit_res) \
- __field(unsigned int, flags) \
- __field(void *, reserve_headq) \
- __field(void *, write_headq) \
- __field(int, grant_reserve_cycle) \
- __field(int, grant_reserve_bytes) \
- __field(int, grant_write_cycle) \
- __field(int, grant_write_bytes) \
- __field(int, curr_cycle) \
- __field(int, curr_block) \
- __field(xfs_lsn_t, tail_lsn) \
- ), \
- TP_fast_assign( \
- __entry->dev = log->l_mp->m_super->s_dev; \
- __entry->trans_type = tic->t_trans_type; \
- __entry->ocnt = tic->t_ocnt; \
- __entry->cnt = tic->t_cnt; \
- __entry->curr_res = tic->t_curr_res; \
- __entry->unit_res = tic->t_unit_res; \
- __entry->flags = tic->t_flags; \
- __entry->reserve_headq = log->l_reserve_headq; \
- __entry->write_headq = log->l_write_headq; \
- __entry->grant_reserve_cycle = log->l_grant_reserve_cycle; \
- __entry->grant_reserve_bytes = log->l_grant_reserve_bytes; \
- __entry->grant_write_cycle = log->l_grant_write_cycle; \
- __entry->grant_write_bytes = log->l_grant_write_bytes; \
- __entry->curr_cycle = log->l_curr_cycle; \
- __entry->curr_block = log->l_curr_block; \
- __entry->tail_lsn = log->l_tail_lsn; \
- ), \
- TP_printk("dev %d:%d type %s t_ocnt %u t_cnt %u t_curr_res %u " \
- "t_unit_res %u t_flags %s reserve_headq 0x%p " \
- "write_headq 0x%p grant_reserve_cycle %d " \
- "grant_reserve_bytes %d grant_write_cycle %d " \
- "grant_write_bytes %d curr_cycle %d curr_block %d " \
- "tail_cycle %d tail_block %d", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- __print_symbolic(__entry->trans_type, XFS_TRANS_TYPES), \
- __entry->ocnt, \
- __entry->cnt, \
- __entry->curr_res, \
- __entry->unit_res, \
- __print_flags(__entry->flags, "|", XLOG_TIC_FLAGS), \
- __entry->reserve_headq, \
- __entry->write_headq, \
- __entry->grant_reserve_cycle, \
- __entry->grant_reserve_bytes, \
- __entry->grant_write_cycle, \
- __entry->grant_write_bytes, \
- __entry->curr_cycle, \
- __entry->curr_block, \
- CYCLE_LSN(__entry->tail_lsn), \
- BLOCK_LSN(__entry->tail_lsn) \
- ) \
-)
+ TP_ARGS(log, tic))
DEFINE_LOGGRANT_EVENT(xfs_log_done_nonperm);
DEFINE_LOGGRANT_EVENT(xfs_log_done_perm);
DEFINE_LOGGRANT_EVENT(xfs_log_reserve);
@@ -815,7 +853,7 @@ TRACE_EVENT(name, \
), \
TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx " \
"offset 0x%llx count %zd flags %s " \
- "startoff 0x%llx startblock 0x%llx blockcount 0x%llx", \
+ "startoff 0x%llx startblock %s blockcount 0x%llx", \
MAJOR(__entry->dev), MINOR(__entry->dev), \
__entry->ino, \
__entry->size, \
@@ -824,7 +862,7 @@ TRACE_EVENT(name, \
__entry->count, \
__print_flags(__entry->flags, "|", BMAPI_FLAGS), \
__entry->startoff, \
- __entry->startblock, \
+ xfs_fmtfsblock(__entry->startblock), \
__entry->blockcount) \
)
DEFINE_IOMAP_EVENT(xfs_iomap_enter);
@@ -897,28 +935,32 @@ TRACE_EVENT(xfs_itruncate_start,
__entry->toss_finish)
);
+DECLARE_EVENT_CLASS(xfs_itrunc_class,
+ TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size),
+ TP_ARGS(ip, new_size),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(xfs_fsize_t, size)
+ __field(xfs_fsize_t, new_size)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(ip)->i_sb->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->size = ip->i_d.di_size;
+ __entry->new_size = new_size;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->size,
+ __entry->new_size)
+)
+
#define DEFINE_ITRUNC_EVENT(name) \
-TRACE_EVENT(name, \
+DEFINE_EVENT(xfs_itrunc_class, name, \
TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size), \
- TP_ARGS(ip, new_size), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(xfs_ino_t, ino) \
- __field(xfs_fsize_t, size) \
- __field(xfs_fsize_t, new_size) \
- ), \
- TP_fast_assign( \
- __entry->dev = VFS_I(ip)->i_sb->s_dev; \
- __entry->ino = ip->i_ino; \
- __entry->size = ip->i_d.di_size; \
- __entry->new_size = new_size; \
- ), \
- TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- __entry->ino, \
- __entry->size, \
- __entry->new_size) \
-)
+ TP_ARGS(ip, new_size))
DEFINE_ITRUNC_EVENT(xfs_itruncate_finish_start);
DEFINE_ITRUNC_EVENT(xfs_itruncate_finish_end);
@@ -1037,28 +1079,28 @@ TRACE_EVENT(xfs_alloc_unbusy,
TRACE_EVENT(xfs_alloc_busysearch,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
- xfs_extlen_t len, int found),
- TP_ARGS(mp, agno, agbno, len, found),
+ xfs_extlen_t len, xfs_lsn_t lsn),
+ TP_ARGS(mp, agno, agbno, len, lsn),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
__field(xfs_agblock_t, agbno)
__field(xfs_extlen_t, len)
- __field(int, found)
+ __field(xfs_lsn_t, lsn)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
__entry->agbno = agbno;
__entry->len = len;
- __entry->found = found;
+ __entry->lsn = lsn;
),
- TP_printk("dev %d:%d agno %u agbno %u len %u %s",
+ TP_printk("dev %d:%d agno %u agbno %u len %u force lsn 0x%llx",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->agno,
__entry->agbno,
__entry->len,
- __print_symbolic(__entry->found, XFS_BUSY_STATES))
+ __entry->lsn)
);
TRACE_EVENT(xfs_agf,
@@ -1152,77 +1194,80 @@ TRACE_EVENT(xfs_free_extent,
);
-#define DEFINE_ALLOC_EVENT(name) \
-TRACE_EVENT(name, \
- TP_PROTO(struct xfs_alloc_arg *args), \
- TP_ARGS(args), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(xfs_agnumber_t, agno) \
- __field(xfs_agblock_t, agbno) \
- __field(xfs_extlen_t, minlen) \
- __field(xfs_extlen_t, maxlen) \
- __field(xfs_extlen_t, mod) \
- __field(xfs_extlen_t, prod) \
- __field(xfs_extlen_t, minleft) \
- __field(xfs_extlen_t, total) \
- __field(xfs_extlen_t, alignment) \
- __field(xfs_extlen_t, minalignslop) \
- __field(xfs_extlen_t, len) \
- __field(short, type) \
- __field(short, otype) \
- __field(char, wasdel) \
- __field(char, wasfromfl) \
- __field(char, isfl) \
- __field(char, userdata) \
- __field(xfs_fsblock_t, firstblock) \
- ), \
- TP_fast_assign( \
- __entry->dev = args->mp->m_super->s_dev; \
- __entry->agno = args->agno; \
- __entry->agbno = args->agbno; \
- __entry->minlen = args->minlen; \
- __entry->maxlen = args->maxlen; \
- __entry->mod = args->mod; \
- __entry->prod = args->prod; \
- __entry->minleft = args->minleft; \
- __entry->total = args->total; \
- __entry->alignment = args->alignment; \
- __entry->minalignslop = args->minalignslop; \
- __entry->len = args->len; \
- __entry->type = args->type; \
- __entry->otype = args->otype; \
- __entry->wasdel = args->wasdel; \
- __entry->wasfromfl = args->wasfromfl; \
- __entry->isfl = args->isfl; \
- __entry->userdata = args->userdata; \
- __entry->firstblock = args->firstblock; \
- ), \
- TP_printk("dev %d:%d agno %u agbno %u minlen %u maxlen %u mod %u " \
- "prod %u minleft %u total %u alignment %u minalignslop %u " \
- "len %u type %s otype %s wasdel %d wasfromfl %d isfl %d " \
- "userdata %d firstblock 0x%llx", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- __entry->agno, \
- __entry->agbno, \
- __entry->minlen, \
- __entry->maxlen, \
- __entry->mod, \
- __entry->prod, \
- __entry->minleft, \
- __entry->total, \
- __entry->alignment, \
- __entry->minalignslop, \
- __entry->len, \
- __print_symbolic(__entry->type, XFS_ALLOC_TYPES), \
- __print_symbolic(__entry->otype, XFS_ALLOC_TYPES), \
- __entry->wasdel, \
- __entry->wasfromfl, \
- __entry->isfl, \
- __entry->userdata, \
- __entry->firstblock) \
+DECLARE_EVENT_CLASS(xfs_alloc_class,
+ TP_PROTO(struct xfs_alloc_arg *args),
+ TP_ARGS(args),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_agnumber_t, agno)
+ __field(xfs_agblock_t, agbno)
+ __field(xfs_extlen_t, minlen)
+ __field(xfs_extlen_t, maxlen)
+ __field(xfs_extlen_t, mod)
+ __field(xfs_extlen_t, prod)
+ __field(xfs_extlen_t, minleft)
+ __field(xfs_extlen_t, total)
+ __field(xfs_extlen_t, alignment)
+ __field(xfs_extlen_t, minalignslop)
+ __field(xfs_extlen_t, len)
+ __field(short, type)
+ __field(short, otype)
+ __field(char, wasdel)
+ __field(char, wasfromfl)
+ __field(char, isfl)
+ __field(char, userdata)
+ __field(xfs_fsblock_t, firstblock)
+ ),
+ TP_fast_assign(
+ __entry->dev = args->mp->m_super->s_dev;
+ __entry->agno = args->agno;
+ __entry->agbno = args->agbno;
+ __entry->minlen = args->minlen;
+ __entry->maxlen = args->maxlen;
+ __entry->mod = args->mod;
+ __entry->prod = args->prod;
+ __entry->minleft = args->minleft;
+ __entry->total = args->total;
+ __entry->alignment = args->alignment;
+ __entry->minalignslop = args->minalignslop;
+ __entry->len = args->len;
+ __entry->type = args->type;
+ __entry->otype = args->otype;
+ __entry->wasdel = args->wasdel;
+ __entry->wasfromfl = args->wasfromfl;
+ __entry->isfl = args->isfl;
+ __entry->userdata = args->userdata;
+ __entry->firstblock = args->firstblock;
+ ),
+ TP_printk("dev %d:%d agno %u agbno %u minlen %u maxlen %u mod %u "
+ "prod %u minleft %u total %u alignment %u minalignslop %u "
+ "len %u type %s otype %s wasdel %d wasfromfl %d isfl %d "
+ "userdata %d firstblock 0x%llx",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->agno,
+ __entry->agbno,
+ __entry->minlen,
+ __entry->maxlen,
+ __entry->mod,
+ __entry->prod,
+ __entry->minleft,
+ __entry->total,
+ __entry->alignment,
+ __entry->minalignslop,
+ __entry->len,
+ __print_symbolic(__entry->type, XFS_ALLOC_TYPES),
+ __print_symbolic(__entry->otype, XFS_ALLOC_TYPES),
+ __entry->wasdel,
+ __entry->wasfromfl,
+ __entry->isfl,
+ __entry->userdata,
+ __entry->firstblock)
)
+#define DEFINE_ALLOC_EVENT(name) \
+DEFINE_EVENT(xfs_alloc_class, name, \
+ TP_PROTO(struct xfs_alloc_arg *args), \
+ TP_ARGS(args))
DEFINE_ALLOC_EVENT(xfs_alloc_exact_done);
DEFINE_ALLOC_EVENT(xfs_alloc_exact_error);
DEFINE_ALLOC_EVENT(xfs_alloc_near_nominleft);
@@ -1245,92 +1290,100 @@ DEFINE_ALLOC_EVENT(xfs_alloc_vextent_noagbp);
DEFINE_ALLOC_EVENT(xfs_alloc_vextent_loopfailed);
DEFINE_ALLOC_EVENT(xfs_alloc_vextent_allfailed);
-#define DEFINE_DIR2_TRACE(tname) \
-TRACE_EVENT(tname, \
+DECLARE_EVENT_CLASS(xfs_dir2_class,
+ TP_PROTO(struct xfs_da_args *args),
+ TP_ARGS(args),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __dynamic_array(char, name, args->namelen)
+ __field(int, namelen)
+ __field(xfs_dahash_t, hashval)
+ __field(xfs_ino_t, inumber)
+ __field(int, op_flags)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(args->dp)->i_sb->s_dev;
+ __entry->ino = args->dp->i_ino;
+ if (args->namelen)
+ memcpy(__get_str(name), args->name, args->namelen);
+ __entry->namelen = args->namelen;
+ __entry->hashval = args->hashval;
+ __entry->inumber = args->inumber;
+ __entry->op_flags = args->op_flags;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx name %.*s namelen %d hashval 0x%x "
+ "inumber 0x%llx op_flags %s",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->namelen,
+ __entry->namelen ? __get_str(name) : NULL,
+ __entry->namelen,
+ __entry->hashval,
+ __entry->inumber,
+ __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS))
+)
+
+#define DEFINE_DIR2_EVENT(name) \
+DEFINE_EVENT(xfs_dir2_class, name, \
TP_PROTO(struct xfs_da_args *args), \
- TP_ARGS(args), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(xfs_ino_t, ino) \
- __dynamic_array(char, name, args->namelen) \
- __field(int, namelen) \
- __field(xfs_dahash_t, hashval) \
- __field(xfs_ino_t, inumber) \
- __field(int, op_flags) \
- ), \
- TP_fast_assign( \
- __entry->dev = VFS_I(args->dp)->i_sb->s_dev; \
- __entry->ino = args->dp->i_ino; \
- if (args->namelen) \
- memcpy(__get_str(name), args->name, args->namelen); \
- __entry->namelen = args->namelen; \
- __entry->hashval = args->hashval; \
- __entry->inumber = args->inumber; \
- __entry->op_flags = args->op_flags; \
- ), \
- TP_printk("dev %d:%d ino 0x%llx name %.*s namelen %d hashval 0x%x " \
- "inumber 0x%llx op_flags %s", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- __entry->ino, \
- __entry->namelen, \
- __entry->namelen ? __get_str(name) : NULL, \
- __entry->namelen, \
- __entry->hashval, \
- __entry->inumber, \
- __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS)) \
+ TP_ARGS(args))
+DEFINE_DIR2_EVENT(xfs_dir2_sf_addname);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_create);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_lookup);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_replace);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_removename);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_toino4);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_toino8);
+DEFINE_DIR2_EVENT(xfs_dir2_sf_to_block);
+DEFINE_DIR2_EVENT(xfs_dir2_block_addname);
+DEFINE_DIR2_EVENT(xfs_dir2_block_lookup);
+DEFINE_DIR2_EVENT(xfs_dir2_block_replace);
+DEFINE_DIR2_EVENT(xfs_dir2_block_removename);
+DEFINE_DIR2_EVENT(xfs_dir2_block_to_sf);
+DEFINE_DIR2_EVENT(xfs_dir2_block_to_leaf);
+DEFINE_DIR2_EVENT(xfs_dir2_leaf_addname);
+DEFINE_DIR2_EVENT(xfs_dir2_leaf_lookup);
+DEFINE_DIR2_EVENT(xfs_dir2_leaf_replace);
+DEFINE_DIR2_EVENT(xfs_dir2_leaf_removename);
+DEFINE_DIR2_EVENT(xfs_dir2_leaf_to_block);
+DEFINE_DIR2_EVENT(xfs_dir2_leaf_to_node);
+DEFINE_DIR2_EVENT(xfs_dir2_node_addname);
+DEFINE_DIR2_EVENT(xfs_dir2_node_lookup);
+DEFINE_DIR2_EVENT(xfs_dir2_node_replace);
+DEFINE_DIR2_EVENT(xfs_dir2_node_removename);
+DEFINE_DIR2_EVENT(xfs_dir2_node_to_leaf);
+
+DECLARE_EVENT_CLASS(xfs_dir2_space_class,
+ TP_PROTO(struct xfs_da_args *args, int idx),
+ TP_ARGS(args, idx),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(int, op_flags)
+ __field(int, idx)
+ ),
+ TP_fast_assign(
+ __entry->dev = VFS_I(args->dp)->i_sb->s_dev;
+ __entry->ino = args->dp->i_ino;
+ __entry->op_flags = args->op_flags;
+ __entry->idx = idx;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx op_flags %s index %d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS),
+ __entry->idx)
)
-DEFINE_DIR2_TRACE(xfs_dir2_sf_addname);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_create);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_lookup);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_replace);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_removename);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_toino4);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_toino8);
-DEFINE_DIR2_TRACE(xfs_dir2_sf_to_block);
-DEFINE_DIR2_TRACE(xfs_dir2_block_addname);
-DEFINE_DIR2_TRACE(xfs_dir2_block_lookup);
-DEFINE_DIR2_TRACE(xfs_dir2_block_replace);
-DEFINE_DIR2_TRACE(xfs_dir2_block_removename);
-DEFINE_DIR2_TRACE(xfs_dir2_block_to_sf);
-DEFINE_DIR2_TRACE(xfs_dir2_block_to_leaf);
-DEFINE_DIR2_TRACE(xfs_dir2_leaf_addname);
-DEFINE_DIR2_TRACE(xfs_dir2_leaf_lookup);
-DEFINE_DIR2_TRACE(xfs_dir2_leaf_replace);
-DEFINE_DIR2_TRACE(xfs_dir2_leaf_removename);
-DEFINE_DIR2_TRACE(xfs_dir2_leaf_to_block);
-DEFINE_DIR2_TRACE(xfs_dir2_leaf_to_node);
-DEFINE_DIR2_TRACE(xfs_dir2_node_addname);
-DEFINE_DIR2_TRACE(xfs_dir2_node_lookup);
-DEFINE_DIR2_TRACE(xfs_dir2_node_replace);
-DEFINE_DIR2_TRACE(xfs_dir2_node_removename);
-DEFINE_DIR2_TRACE(xfs_dir2_node_to_leaf);
-#define DEFINE_DIR2_SPACE_TRACE(tname) \
-TRACE_EVENT(tname, \
+#define DEFINE_DIR2_SPACE_EVENT(name) \
+DEFINE_EVENT(xfs_dir2_space_class, name, \
TP_PROTO(struct xfs_da_args *args, int idx), \
- TP_ARGS(args, idx), \
- TP_STRUCT__entry( \
- __field(dev_t, dev) \
- __field(xfs_ino_t, ino) \
- __field(int, op_flags) \
- __field(int, idx) \
- ), \
- TP_fast_assign( \
- __entry->dev = VFS_I(args->dp)->i_sb->s_dev; \
- __entry->ino = args->dp->i_ino; \
- __entry->op_flags = args->op_flags; \
- __entry->idx = idx; \
- ), \
- TP_printk("dev %d:%d ino 0x%llx op_flags %s index %d", \
- MAJOR(__entry->dev), MINOR(__entry->dev), \
- __entry->ino, \
- __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS), \
- __entry->idx) \
-)
-DEFINE_DIR2_SPACE_TRACE(xfs_dir2_leafn_add);
-DEFINE_DIR2_SPACE_TRACE(xfs_dir2_leafn_remove);
-DEFINE_DIR2_SPACE_TRACE(xfs_dir2_grow_inode);
-DEFINE_DIR2_SPACE_TRACE(xfs_dir2_shrink_inode);
+ TP_ARGS(args, idx))
+DEFINE_DIR2_SPACE_EVENT(xfs_dir2_leafn_add);
+DEFINE_DIR2_SPACE_EVENT(xfs_dir2_leafn_remove);
+DEFINE_DIR2_SPACE_EVENT(xfs_dir2_grow_inode);
+DEFINE_DIR2_SPACE_EVENT(xfs_dir2_shrink_inode);
TRACE_EVENT(xfs_dir2_leafn_moveents,
TP_PROTO(struct xfs_da_args *args, int src_idx, int dst_idx, int count),
diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c
index 71af76fe8a2..873e07e2907 100644
--- a/fs/xfs/quota/xfs_qm_syscalls.c
+++ b/fs/xfs/quota/xfs_qm_syscalls.c
@@ -891,7 +891,7 @@ xfs_qm_dqrele_all_inodes(
uint flags)
{
ASSERT(mp->m_quotainfo);
- xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, XFS_ICI_NO_TAG);
+ xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, XFS_ICI_NO_TAG, 0);
}
/*------------------------------------------------------------------------*/
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index a1c65fc6d9c..275b1f4f943 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -2563,43 +2563,41 @@ xfs_alloc_search_busy(xfs_trans_t *tp,
xfs_mount_t *mp;
xfs_perag_busy_t *bsy;
xfs_agblock_t uend, bend;
- xfs_lsn_t lsn;
+ xfs_lsn_t lsn = 0;
int cnt;
mp = tp->t_mountp;
spin_lock(&mp->m_perag[agno].pagb_lock);
- cnt = mp->m_perag[agno].pagb_count;
uend = bno + len - 1;
- /* search pagb_list for this slot, skipping open slots */
- for (bsy = mp->m_perag[agno].pagb_list; cnt; bsy++) {
+ /*
+ * search pagb_list for this slot, skipping open slots. We have to
+ * search the entire array as there may be multiple overlaps and
+ * we have to get the most recent LSN for the log force to push out
+ * all the transactions that span the range.
+ */
+ for (cnt = 0; cnt < mp->m_perag[agno].pagb_count; cnt++) {
+ bsy = &mp->m_perag[agno].pagb_list[cnt];
+ if (!bsy->busy_tp)
+ continue;
- /*
- * (start1,length1) within (start2, length2)
- */
- if (bsy->busy_tp != NULL) {
- bend = bsy->busy_start + bsy->busy_length - 1;
- if ((bno > bend) || (uend < bsy->busy_start)) {
- cnt--;
- } else {
- break;
- }
- }
- }
+ bend = bsy->busy_start + bsy->busy_length - 1;
+ if (bno > bend || uend < bsy->busy_start)
+ continue;
- trace_xfs_alloc_busysearch(mp, agno, bno, len, !!cnt);
+ /* (start1,length1) within (start2, length2) */
+ if (XFS_LSN_CMP(bsy->busy_tp->t_commit_lsn, lsn) > 0)
+ lsn = bsy->busy_tp->t_commit_lsn;
+ }
+ spin_unlock(&mp->m_perag[agno].pagb_lock);
+ trace_xfs_alloc_busysearch(tp->t_mountp, agno, bno, len, lsn);
/*
* If a block was found, force the log through the LSN of the
* transaction that freed the block
*/
- if (cnt) {
- lsn = bsy->busy_tp->t_commit_lsn;
- spin_unlock(&mp->m_perag[agno].pagb_lock);
+ if (lsn)
xfs_log_force(mp, lsn, XFS_LOG_FORCE|XFS_LOG_SYNC);
- } else {
- spin_unlock(&mp->m_perag[agno].pagb_lock);
- }
}
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index d1483a4f71b..84ca1cf16a1 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -114,10 +114,82 @@ xfs_swapext(
return error;
}
+/*
+ * We need to check that the format of the data fork in the temporary inode is
+ * valid for the target inode before doing the swap. This is not a problem with
+ * attr1 because of the fixed fork offset, but attr2 has a dynamically sized
+ * data fork depending on the space the attribute fork is taking so we can get
+ * invalid formats on the target inode.
+ *
+ * E.g. target has space for 7 extents in extent format, temp inode only has
+ * space for 6. If we defragment down to 7 extents, then the tmp format is a
+ * btree, but when swapped it needs to be in extent format. Hence we can't just
+ * blindly swap data forks on attr2 filesystems.
+ *
+ * Note that we check the swap in both directions so that we don't end up with
+ * a corrupt temporary inode, either.
+ *
+ * Note that fixing the way xfs_fsr sets up the attribute fork in the source
+ * inode will prevent this situation from occurring, so all we do here is
+ * reject and log the attempt. basically we are putting the responsibility on
+ * userspace to get this right.
+ */
+static int
+xfs_swap_extents_check_format(
+ xfs_inode_t *ip, /* target inode */
+ xfs_inode_t *tip) /* tmp inode */
+{
+
+ /* Should never get a local format */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
+ tip->i_d.di_format == XFS_DINODE_FMT_LOCAL)
+ return EINVAL;
+
+ /*
+ * if the target inode has less extents that then temporary inode then
+ * why did userspace call us?
+ */
+ if (ip->i_d.di_nextents < tip->i_d.di_nextents)
+ return EINVAL;
+
+ /*
+ * if the target inode is in extent form and the temp inode is in btree
+ * form then we will end up with the target inode in the wrong format
+ * as we already know there are less extents in the temp inode.
+ */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+ tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
+ return EINVAL;
+
+ /* Check temp in extent form to max in target */
+ if (tip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+ XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) > ip->i_df.if_ext_max)
+ return EINVAL;
+
+ /* Check target in extent form to max in temp */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+ XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) > tip->i_df.if_ext_max)
+ return EINVAL;
+
+ /* Check root block of temp in btree form to max in target */
+ if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
+ XFS_IFORK_BOFF(ip) &&
+ tip->i_df.if_broot_bytes > XFS_IFORK_BOFF(ip))
+ return EINVAL;
+
+ /* Check root block of target in btree form to max in temp */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
+ XFS_IFORK_BOFF(tip) &&
+ ip->i_df.if_broot_bytes > XFS_IFORK_BOFF(tip))
+ return EINVAL;
+
+ return 0;
+}
+
int
xfs_swap_extents(
- xfs_inode_t *ip,
- xfs_inode_t *tip,
+ xfs_inode_t *ip, /* target inode */
+ xfs_inode_t *tip, /* tmp inode */
xfs_swapext_t *sxp)
{
xfs_mount_t *mp;
@@ -161,13 +233,6 @@ xfs_swap_extents(
goto out_unlock;
}
- /* Should never get a local format */
- if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
- tip->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
- error = XFS_ERROR(EINVAL);
- goto out_unlock;
- }
-
if (VN_CACHED(VFS_I(tip)) != 0) {
error = xfs_flushinval_pages(tip, 0, -1,
FI_REMAPF_LOCKED);
@@ -189,13 +254,12 @@ xfs_swap_extents(
goto out_unlock;
}
- /*
- * If the target has extended attributes, the tmp file
- * must also in order to ensure the correct data fork
- * format.
- */
- if ( XFS_IFORK_Q(ip) != XFS_IFORK_Q(tip) ) {
- error = XFS_ERROR(EINVAL);
+ /* check inode formats now that data is flushed */
+ error = xfs_swap_extents_check_format(ip, tip);
+ if (error) {
+ xfs_fs_cmn_err(CE_NOTE, mp,
+ "%s: inode 0x%llx format is incompatible for exchanging.",
+ __FILE__, ip->i_ino);
goto out_unlock;
}
@@ -276,6 +340,16 @@ xfs_swap_extents(
*tifp = *tempifp; /* struct copy */
/*
+ * Fix the in-memory data fork values that are dependent on the fork
+ * offset in the inode. We can't assume they remain the same as attr2
+ * has dynamic fork offsets.
+ */
+ ifp->if_ext_max = XFS_IFORK_SIZE(ip, XFS_DATA_FORK) /
+ (uint)sizeof(xfs_bmbt_rec_t);
+ tifp->if_ext_max = XFS_IFORK_SIZE(tip, XFS_DATA_FORK) /
+ (uint)sizeof(xfs_bmbt_rec_t);
+
+ /*
* Fix the on-disk inode values
*/
tmp = (__uint64_t)ip->i_d.di_nblocks;
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index fa402a6bbbc..155e798f30a 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -73,7 +73,6 @@ xfs_inode_alloc(
ASSERT(atomic_read(&ip->i_pincount) == 0);
ASSERT(!spin_is_locked(&ip->i_flags_lock));
ASSERT(completion_done(&ip->i_flush));
- ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ce278b3ae7f..ef77fd88c8e 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2841,8 +2841,8 @@ xfs_iflush(
mp = ip->i_mount;
/*
- * If the inode isn't dirty, then just release the inode
- * flush lock and do nothing.
+ * If the inode isn't dirty, then just release the inode flush lock and
+ * do nothing.
*/
if (xfs_inode_clean(ip)) {
xfs_ifunlock(ip);
@@ -2868,6 +2868,19 @@ xfs_iflush(
xfs_iunpin_wait(ip);
/*
+ * For stale inodes we cannot rely on the backing buffer remaining
+ * stale in cache for the remaining life of the stale inode and so
+ * xfs_itobp() below may give us a buffer that no longer contains
+ * inodes below. We have to check this after ensuring the inode is
+ * unpinned so that it is safe to reclaim the stale inode after the
+ * flush call.
+ */
+ if (xfs_iflags_test(ip, XFS_ISTALE)) {
+ xfs_ifunlock(ip);
+ return 0;
+ }
+
+ /*
* This may have been unpinned because the filesystem is shutting
* down forcibly. If that's the case we must not write this inode
* to disk, because the log record didn't make it to disk!
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 9e15a118536..6be05f756d5 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1517,6 +1517,8 @@ xfs_rtfree_range(
*/
error = xfs_rtfind_forw(mp, tp, end, mp->m_sb.sb_rextents - 1,
&postblock);
+ if (error)
+ return error;
/*
* If there are blocks not being freed at the front of the
* old extent, add summary data for them to be allocated.
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 6558ffd8d14..6f268756bf3 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -70,7 +70,6 @@ xfs_setattr(
uint commit_flags=0;
uid_t uid=0, iuid=0;
gid_t gid=0, igid=0;
- int timeflags = 0;
struct xfs_dquot *udqp, *gdqp, *olddquot1, *olddquot2;
int need_iolock = 1;
@@ -135,16 +134,13 @@ xfs_setattr(
if (flags & XFS_ATTR_NOLOCK)
need_iolock = 0;
if (!(mask & ATTR_SIZE)) {
- if ((mask != (ATTR_CTIME|ATTR_ATIME|ATTR_MTIME)) ||
- (mp->m_flags & XFS_MOUNT_WSYNC)) {
- tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
- commit_flags = 0;
- if ((code = xfs_trans_reserve(tp, 0,
- XFS_ICHANGE_LOG_RES(mp), 0,
- 0, 0))) {
- lock_flags = 0;
- goto error_return;
- }
+ tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
+ commit_flags = 0;
+ code = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp),
+ 0, 0, 0);
+ if (code) {
+ lock_flags = 0;
+ goto error_return;
}
} else {
if (DM_EVENT_ENABLED(ip, DM_EVENT_TRUNCATE) &&
@@ -295,15 +291,23 @@ xfs_setattr(
* or we are explicitly asked to change it. This handles
* the semantic difference between truncate() and ftruncate()
* as implemented in the VFS.
+ *
+ * The regular truncate() case without ATTR_CTIME and ATTR_MTIME
+ * is a special case where we need to update the times despite
+ * not having these flags set. For all other operations the
+ * VFS set these flags explicitly if it wants a timestamp
+ * update.
*/
- if (iattr->ia_size != ip->i_size || (mask & ATTR_CTIME))
- timeflags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+ if (iattr->ia_size != ip->i_size &&
+ (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
+ iattr->ia_ctime = iattr->ia_mtime =
+ current_fs_time(inode->i_sb);
+ mask |= ATTR_CTIME | ATTR_MTIME;
+ }
if (iattr->ia_size > ip->i_size) {
ip->i_d.di_size = iattr->ia_size;
ip->i_size = iattr->ia_size;
- if (!(flags & XFS_ATTR_DMI))
- xfs_ichgtime(ip, XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
} else if (iattr->ia_size <= ip->i_size ||
(iattr->ia_size == 0 && ip->i_d.di_nextents)) {
@@ -374,9 +378,6 @@ xfs_setattr(
ip->i_d.di_gid = gid;
inode->i_gid = gid;
}
-
- xfs_trans_log_inode (tp, ip, XFS_ILOG_CORE);
- timeflags |= XFS_ICHGTIME_CHG;
}
/*
@@ -393,51 +394,37 @@ xfs_setattr(
inode->i_mode &= S_IFMT;
inode->i_mode |= mode & ~S_IFMT;
-
- xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- timeflags |= XFS_ICHGTIME_CHG;
}
/*
* Change file access or modified times.
*/
- if (mask & (ATTR_ATIME|ATTR_MTIME)) {
- if (mask & ATTR_ATIME) {
- inode->i_atime = iattr->ia_atime;
- ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
- ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
- ip->i_update_core = 1;
- }
- if (mask & ATTR_MTIME) {
- inode->i_mtime = iattr->ia_mtime;
- ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
- ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
- timeflags &= ~XFS_ICHGTIME_MOD;
- timeflags |= XFS_ICHGTIME_CHG;
- }
- if (tp && (mask & (ATTR_MTIME_SET|ATTR_ATIME_SET)))
- xfs_trans_log_inode (tp, ip, XFS_ILOG_CORE);
+ if (mask & ATTR_ATIME) {
+ inode->i_atime = iattr->ia_atime;
+ ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
+ ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
+ ip->i_update_core = 1;
}
-
- /*
- * Change file inode change time only if ATTR_CTIME set
- * AND we have been called by a DMI function.
- */
-
- if ((flags & XFS_ATTR_DMI) && (mask & ATTR_CTIME)) {
+ if (mask & ATTR_CTIME) {
inode->i_ctime = iattr->ia_ctime;
ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
ip->i_update_core = 1;
- timeflags &= ~XFS_ICHGTIME_CHG;
+ }
+ if (mask & ATTR_MTIME) {
+ inode->i_mtime = iattr->ia_mtime;
+ ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
+ ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
+ ip->i_update_core = 1;
}
/*
- * Send out timestamp changes that need to be set to the
- * current time. Not done when called by a DMI function.
+ * And finally, log the inode core if any attribute in it
+ * has been changed.
*/
- if (timeflags && !(flags & XFS_ATTR_DMI))
- xfs_ichgtime(ip, timeflags);
+ if (mask & (ATTR_UID|ATTR_GID|ATTR_MODE|
+ ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
@@ -452,12 +439,10 @@ xfs_setattr(
* mix so this probably isn't worth the trouble to optimize.
*/
code = 0;
- if (tp) {
- if (mp->m_flags & XFS_MOUNT_WSYNC)
- xfs_trans_set_sync(tp);
+ if (mp->m_flags & XFS_MOUNT_WSYNC)
+ xfs_trans_set_sync(tp);
- code = xfs_trans_commit(tp, commit_flags);
- }
+ code = xfs_trans_commit(tp, commit_flags);
xfs_iunlock(ip, lock_flags);