summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Makefile1
-rw-r--r--fs/affs/file.c19
-rw-r--r--fs/aio.c20
-rw-r--r--fs/cifs/cifsencrypt.c6
-rw-r--r--fs/cifs/connect.c13
-rw-r--r--fs/cifs/file.c1
-rw-r--r--fs/cifs/inode.c2
-rw-r--r--fs/cifs/smb2misc.c2
-rw-r--r--fs/cifs/smb2ops.c3
-rw-r--r--fs/cifs/smb2pdu.c17
-rw-r--r--fs/debugfs/inode.c3
-rw-r--r--fs/fs-writeback.c93
-rw-r--r--fs/hfsplus/brec.c20
-rw-r--r--fs/jffs2/xattr.c2
-rw-r--r--fs/locks.c5
-rw-r--r--fs/nfsd/blocklayout.c2
-rw-r--r--fs/nfsd/blocklayoutxdr.c6
-rw-r--r--fs/nfsd/nfs4layouts.c12
-rw-r--r--fs/nfsd/nfs4proc.c2
-rw-r--r--fs/nfsd/nfs4state.c4
-rw-r--r--fs/nfsd/nfs4xdr.c20
-rw-r--r--fs/nfsd/nfscache.c6
-rw-r--r--fs/ocfs2/file.c17
-rw-r--r--fs/sysfs/group.c11
-rw-r--r--fs/tracefs/Makefile4
-rw-r--r--fs/tracefs/inode.c650
26 files changed, 868 insertions, 73 deletions
diff --git a/fs/Makefile b/fs/Makefile
index a88ac4838c9e..cb92fd4c3172 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -118,6 +118,7 @@ obj-$(CONFIG_HOSTFS) += hostfs/
obj-$(CONFIG_HPPFS) += hppfs/
obj-$(CONFIG_CACHEFILES) += cachefiles/
obj-$(CONFIG_DEBUG_FS) += debugfs/
+obj-$(CONFIG_TRACING) += tracefs/
obj-$(CONFIG_OCFS2_FS) += ocfs2/
obj-$(CONFIG_BTRFS_FS) += btrfs/
obj-$(CONFIG_GFS2_FS) += gfs2/
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 33eaa67bb026..3aa7eb66547e 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -699,8 +699,10 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
boff = tmp % bsize;
if (boff) {
bh = affs_bread_ino(inode, bidx, 0);
- if (IS_ERR(bh))
- return PTR_ERR(bh);
+ if (IS_ERR(bh)) {
+ written = PTR_ERR(bh);
+ goto err_first_bh;
+ }
tmp = min(bsize - boff, to - from);
BUG_ON(boff + tmp > bsize || tmp > bsize);
memcpy(AFFS_DATA(bh) + boff, data + from, tmp);
@@ -712,14 +714,16 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
bidx++;
} else if (bidx) {
bh = affs_bread_ino(inode, bidx - 1, 0);
- if (IS_ERR(bh))
- return PTR_ERR(bh);
+ if (IS_ERR(bh)) {
+ written = PTR_ERR(bh);
+ goto err_first_bh;
+ }
}
while (from + bsize <= to) {
prev_bh = bh;
bh = affs_getemptyblk_ino(inode, bidx);
if (IS_ERR(bh))
- goto out;
+ goto err_bh;
memcpy(AFFS_DATA(bh), data + from, bsize);
if (buffer_new(bh)) {
AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
@@ -751,7 +755,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
prev_bh = bh;
bh = affs_bread_ino(inode, bidx, 1);
if (IS_ERR(bh))
- goto out;
+ goto err_bh;
tmp = min(bsize, to - from);
BUG_ON(tmp > bsize);
memcpy(AFFS_DATA(bh), data + from, tmp);
@@ -790,12 +794,13 @@ done:
if (tmp > inode->i_size)
inode->i_size = AFFS_I(inode)->mmu_private = tmp;
+err_first_bh:
unlock_page(page);
page_cache_release(page);
return written;
-out:
+err_bh:
bh = prev_bh;
if (!written)
written = PTR_ERR(bh);
diff --git a/fs/aio.c b/fs/aio.c
index 3b8467aeb5ee..1ab60010cf6c 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -310,11 +310,11 @@ static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma)
return 0;
}
-static void aio_ring_remap(struct file *file, struct vm_area_struct *vma)
+static int aio_ring_remap(struct file *file, struct vm_area_struct *vma)
{
struct mm_struct *mm = vma->vm_mm;
struct kioctx_table *table;
- int i;
+ int i, res = -EINVAL;
spin_lock(&mm->ioctx_lock);
rcu_read_lock();
@@ -324,13 +324,17 @@ static void aio_ring_remap(struct file *file, struct vm_area_struct *vma)
ctx = table->table[i];
if (ctx && ctx->aio_ring_file == file) {
- ctx->user_id = ctx->mmap_base = vma->vm_start;
+ if (!atomic_read(&ctx->dead)) {
+ ctx->user_id = ctx->mmap_base = vma->vm_start;
+ res = 0;
+ }
break;
}
}
rcu_read_unlock();
spin_unlock(&mm->ioctx_lock);
+ return res;
}
static const struct file_operations aio_ring_fops = {
@@ -760,6 +764,9 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
err_cleanup:
aio_nr_sub(ctx->max_reqs);
err_ctx:
+ atomic_set(&ctx->dead, 1);
+ if (ctx->mmap_size)
+ vm_munmap(ctx->mmap_base, ctx->mmap_size);
aio_free_ring(ctx);
err:
mutex_unlock(&ctx->ring_lock);
@@ -781,11 +788,12 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
{
struct kioctx_table *table;
- if (atomic_xchg(&ctx->dead, 1))
+ spin_lock(&mm->ioctx_lock);
+ if (atomic_xchg(&ctx->dead, 1)) {
+ spin_unlock(&mm->ioctx_lock);
return -EINVAL;
+ }
-
- spin_lock(&mm->ioctx_lock);
table = rcu_dereference_raw(mm->ioctx_table);
WARN_ON(ctx != table->table[ctx->id]);
table->table[ctx->id] = NULL;
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 4ac7445e6ec7..aa0dc2573374 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -1,6 +1,9 @@
/*
* fs/cifs/cifsencrypt.c
*
+ * Encryption and hashing operations relating to NTLM, NTLMv2. See MS-NLMP
+ * for more detailed information
+ *
* Copyright (C) International Business Machines Corp., 2005,2013
* Author(s): Steve French (sfrench@us.ibm.com)
*
@@ -515,7 +518,8 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
__func__);
return rc;
}
- } else if (ses->serverName) {
+ } else {
+ /* We use ses->serverName if no domain name available */
len = strlen(ses->serverName);
server = kmalloc(2 + (len * 2), GFP_KERNEL);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index d3aa999ab785..480cf9c81d50 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1599,6 +1599,8 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
pr_warn("CIFS: username too long\n");
goto cifs_parse_mount_err;
}
+
+ kfree(vol->username);
vol->username = kstrdup(string, GFP_KERNEL);
if (!vol->username)
goto cifs_parse_mount_err;
@@ -1700,6 +1702,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
goto cifs_parse_mount_err;
}
+ kfree(vol->domainname);
vol->domainname = kstrdup(string, GFP_KERNEL);
if (!vol->domainname) {
pr_warn("CIFS: no memory for domainname\n");
@@ -1731,6 +1734,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
}
if (strncasecmp(string, "default", 7) != 0) {
+ kfree(vol->iocharset);
vol->iocharset = kstrdup(string,
GFP_KERNEL);
if (!vol->iocharset) {
@@ -2913,8 +2917,7 @@ ip_rfc1001_connect(struct TCP_Server_Info *server)
* calling name ends in null (byte 16) from old smb
* convention.
*/
- if (server->workstation_RFC1001_name &&
- server->workstation_RFC1001_name[0] != 0)
+ if (server->workstation_RFC1001_name[0] != 0)
rfc1002mangle(ses_init_buf->trailer.
session_req.calling_name,
server->workstation_RFC1001_name,
@@ -3692,6 +3695,12 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses,
#endif /* CIFS_WEAK_PW_HASH */
rc = SMBNTencrypt(tcon->password, ses->server->cryptkey,
bcc_ptr, nls_codepage);
+ if (rc) {
+ cifs_dbg(FYI, "%s Can't generate NTLM rsp. Error: %d\n",
+ __func__, rc);
+ cifs_buf_release(smb_buffer);
+ return rc;
+ }
bcc_ptr += CIFS_AUTH_RESP_SIZE;
if (ses->capabilities & CAP_UNICODE) {
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index a94b3e673182..ca30c391a894 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1823,6 +1823,7 @@ refind_writable:
cifsFileInfo_put(inv_file);
spin_lock(&cifs_file_list_lock);
++refind;
+ inv_file = NULL;
goto refind_writable;
}
}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 2d4f37235ed0..3e126d7bb2ea 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -771,6 +771,8 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
cifs_buf_release(srchinf->ntwrk_buf_start);
}
kfree(srchinf);
+ if (rc)
+ goto cgii_exit;
} else
goto cgii_exit;
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 689f035915cf..22dfdf17d065 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -322,7 +322,7 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
/* return pointer to beginning of data area, ie offset from SMB start */
if ((*off != 0) && (*len != 0))
- return hdr->ProtocolId + *off;
+ return (char *)(&hdr->ProtocolId[0]) + *off;
else
return NULL;
}
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 96b5d40a2ece..eab05e1aa587 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -684,7 +684,8 @@ smb2_clone_range(const unsigned int xid,
/* No need to change MaxChunks since already set to 1 */
chunk_sizes_updated = true;
- }
+ } else
+ goto cchunk_out;
}
cchunk_out:
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 3417340bf89e..65cd7a84c8bc 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1218,7 +1218,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
struct smb2_ioctl_req *req;
struct smb2_ioctl_rsp *rsp;
struct TCP_Server_Info *server;
- struct cifs_ses *ses = tcon->ses;
+ struct cifs_ses *ses;
struct kvec iov[2];
int resp_buftype;
int num_iovecs;
@@ -1233,6 +1233,11 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
if (plen)
*plen = 0;
+ if (tcon)
+ ses = tcon->ses;
+ else
+ return -EIO;
+
if (ses && (ses->server))
server = ses->server;
else
@@ -1296,14 +1301,12 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
rsp = (struct smb2_ioctl_rsp *)iov[0].iov_base;
if ((rc != 0) && (rc != -EINVAL)) {
- if (tcon)
- cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
+ cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
goto ioctl_exit;
} else if (rc == -EINVAL) {
if ((opcode != FSCTL_SRV_COPYCHUNK_WRITE) &&
(opcode != FSCTL_SRV_COPYCHUNK)) {
- if (tcon)
- cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
+ cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
goto ioctl_exit;
}
}
@@ -1629,7 +1632,7 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, 0);
- if ((rc != 0) && tcon)
+ if (rc != 0)
cifs_stats_fail_inc(tcon, SMB2_FLUSH_HE);
free_rsp_buf(resp_buftype, iov[0].iov_base);
@@ -2114,7 +2117,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
struct kvec iov[2];
int rc = 0;
int len;
- int resp_buftype;
+ int resp_buftype = CIFS_NO_BUFFER;
unsigned char *bufptr;
struct TCP_Server_Info *server;
struct cifs_ses *ses = tcon->ses;
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 96400ab42d13..61e72d44cf94 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -254,6 +254,9 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
pr_debug("debugfs: creating file '%s'\n",name);
+ if (IS_ERR(parent))
+ return parent;
+
error = simple_pin_fs(&debug_fs_type, &debugfs_mount,
&debugfs_mount_count);
if (error)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e907052eeadb..32a8bbd7a9ad 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -53,6 +53,18 @@ struct wb_writeback_work {
struct completion *done; /* set if the caller waits */
};
+/*
+ * If an inode is constantly having its pages dirtied, but then the
+ * updates stop dirtytime_expire_interval seconds in the past, it's
+ * possible for the worst case time between when an inode has its
+ * timestamps updated and when they finally get written out to be two
+ * dirtytime_expire_intervals. We set the default to 12 hours (in
+ * seconds), which means most of the time inodes will have their
+ * timestamps written to disk after 12 hours, but in the worst case a
+ * few inodes might not their timestamps updated for 24 hours.
+ */
+unsigned int dirtytime_expire_interval = 12 * 60 * 60;
+
/**
* writeback_in_progress - determine whether there is writeback in progress
* @bdi: the device's backing_dev_info structure.
@@ -275,8 +287,8 @@ static int move_expired_inodes(struct list_head *delaying_queue,
if ((flags & EXPIRE_DIRTY_ATIME) == 0)
older_than_this = work->older_than_this;
- else if ((work->reason == WB_REASON_SYNC) == 0) {
- expire_time = jiffies - (HZ * 86400);
+ else if (!work->for_sync) {
+ expire_time = jiffies - (dirtytime_expire_interval * HZ);
older_than_this = &expire_time;
}
while (!list_empty(delaying_queue)) {
@@ -458,6 +470,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
*/
redirty_tail(inode, wb);
} else if (inode->i_state & I_DIRTY_TIME) {
+ inode->dirtied_when = jiffies;
list_move(&inode->i_wb_list, &wb->b_dirty_time);
} else {
/* The inode is clean. Remove from writeback lists. */
@@ -505,12 +518,17 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
spin_lock(&inode->i_lock);
dirty = inode->i_state & I_DIRTY;
- if (((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) &&
- (inode->i_state & I_DIRTY_TIME)) ||
- (inode->i_state & I_DIRTY_TIME_EXPIRED)) {
- dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
- trace_writeback_lazytime(inode);
- }
+ if (inode->i_state & I_DIRTY_TIME) {
+ if ((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) ||
+ unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) ||
+ unlikely(time_after(jiffies,
+ (inode->dirtied_time_when +
+ dirtytime_expire_interval * HZ)))) {
+ dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
+ trace_writeback_lazytime(inode);
+ }
+ } else
+ inode->i_state &= ~I_DIRTY_TIME_EXPIRED;
inode->i_state &= ~dirty;
/*
@@ -1131,6 +1149,56 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason)
rcu_read_unlock();
}
+/*
+ * Wake up bdi's periodically to make sure dirtytime inodes gets
+ * written back periodically. We deliberately do *not* check the
+ * b_dirtytime list in wb_has_dirty_io(), since this would cause the
+ * kernel to be constantly waking up once there are any dirtytime
+ * inodes on the system. So instead we define a separate delayed work
+ * function which gets called much more rarely. (By default, only
+ * once every 12 hours.)
+ *
+ * If there is any other write activity going on in the file system,
+ * this function won't be necessary. But if the only thing that has
+ * happened on the file system is a dirtytime inode caused by an atime
+ * update, we need this infrastructure below to make sure that inode
+ * eventually gets pushed out to disk.
+ */
+static void wakeup_dirtytime_writeback(struct work_struct *w);
+static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback);
+
+static void wakeup_dirtytime_writeback(struct work_struct *w)
+{
+ struct backing_dev_info *bdi;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
+ if (list_empty(&bdi->wb.b_dirty_time))
+ continue;
+ bdi_wakeup_thread(bdi);
+ }
+ rcu_read_unlock();
+ schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
+}
+
+static int __init start_dirtytime_writeback(void)
+{
+ schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
+ return 0;
+}
+__initcall(start_dirtytime_writeback);
+
+int dirtytime_interval_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ int ret;
+
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ if (ret == 0 && write)
+ mod_delayed_work(system_wq, &dirtytime_work, 0);
+ return ret;
+}
+
static noinline void block_dump___mark_inode_dirty(struct inode *inode)
{
if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
@@ -1269,8 +1337,13 @@ void __mark_inode_dirty(struct inode *inode, int flags)
}
inode->dirtied_when = jiffies;
- list_move(&inode->i_wb_list, dirtytime ?
- &bdi->wb.b_dirty_time : &bdi->wb.b_dirty);
+ if (dirtytime)
+ inode->dirtied_time_when = jiffies;
+ if (inode->i_state & (I_DIRTY_INODE | I_DIRTY_PAGES))
+ list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
+ else
+ list_move(&inode->i_wb_list,
+ &bdi->wb.b_dirty_time);
spin_unlock(&bdi->wb.list_lock);
trace_writeback_dirty_inode_enqueue(inode);
diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
index 6e560d56094b..754fdf8c6356 100644
--- a/fs/hfsplus/brec.c
+++ b/fs/hfsplus/brec.c
@@ -131,13 +131,16 @@ skip:
hfs_bnode_write(node, entry, data_off + key_len, entry_len);
hfs_bnode_dump(node);
- if (new_node) {
- /* update parent key if we inserted a key
- * at the start of the first node
- */
- if (!rec && new_node != node)
- hfs_brec_update_parent(fd);
+ /*
+ * update parent key if we inserted a key
+ * at the start of the node and it is not the new node
+ */
+ if (!rec && new_node != node) {
+ hfs_bnode_read_key(node, fd->search_key, data_off + size);
+ hfs_brec_update_parent(fd);
+ }
+ if (new_node) {
hfs_bnode_put(fd->bnode);
if (!new_node->parent) {
hfs_btree_inc_height(tree);
@@ -168,9 +171,6 @@ skip:
goto again;
}
- if (!rec)
- hfs_brec_update_parent(fd);
-
return 0;
}
@@ -370,6 +370,8 @@ again:
if (IS_ERR(parent))
return PTR_ERR(parent);
__hfs_brec_find(parent, fd, hfs_find_rec_by_key);
+ if (fd->record < 0)
+ return -ENOENT;
hfs_bnode_dump(parent);
rec = fd->record;
diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c
index d72817ac51f6..762c7a3cf43d 100644
--- a/fs/jffs2/xattr.c
+++ b/fs/jffs2/xattr.c
@@ -195,7 +195,7 @@ static int do_verify_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_dat
/* unchecked xdatum is chained with c->xattr_unchecked */
list_del_init(&xd->xindex);
- dbg_xattr("success on verfying xdatum (xid=%u, version=%u)\n",
+ dbg_xattr("success on verifying xdatum (xid=%u, version=%u)\n",
xd->xid, xd->version);
return 0;
diff --git a/fs/locks.c b/fs/locks.c
index 528fedfda15e..40bc384728c0 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1388,9 +1388,8 @@ any_leases_conflict(struct inode *inode, struct file_lock *breaker)
int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
{
int error = 0;
- struct file_lock *new_fl;
struct file_lock_context *ctx = inode->i_flctx;
- struct file_lock *fl;
+ struct file_lock *new_fl, *fl, *tmp;
unsigned long break_time;
int want_write = (mode & O_ACCMODE) != O_RDONLY;
LIST_HEAD(dispose);
@@ -1420,7 +1419,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
break_time++; /* so that 0 means no break time */
}
- list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
+ list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
if (!leases_conflict(fl, new_fl))
continue;
if (want_write) {
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index cdbc78c72542..03d647bf195d 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -137,7 +137,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
seg->offset = iomap.offset;
seg->length = iomap.length;
- dprintk("GET: %lld:%lld %d\n", bex->foff, bex->len, bex->es);
+ dprintk("GET: 0x%llx:0x%llx %d\n", bex->foff, bex->len, bex->es);
return 0;
out_error:
diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c
index 9da89fddab33..9aa2796da90d 100644
--- a/fs/nfsd/blocklayoutxdr.c
+++ b/fs/nfsd/blocklayoutxdr.c
@@ -122,19 +122,19 @@ nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp,
p = xdr_decode_hyper(p, &bex.foff);
if (bex.foff & (block_size - 1)) {
- dprintk("%s: unaligned offset %lld\n",
+ dprintk("%s: unaligned offset 0x%llx\n",
__func__, bex.foff);
goto fail;
}
p = xdr_decode_hyper(p, &bex.len);
if (bex.len & (block_size - 1)) {
- dprintk("%s: unaligned length %lld\n",
+ dprintk("%s: unaligned length 0x%llx\n",
__func__, bex.foff);
goto fail;
}
p = xdr_decode_hyper(p, &bex.soff);
if (bex.soff & (block_size - 1)) {
- dprintk("%s: unaligned disk offset %lld\n",
+ dprintk("%s: unaligned disk offset 0x%llx\n",
__func__, bex.soff);
goto fail;
}
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 1028a0629543..6904213a4363 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -118,7 +118,7 @@ void nfsd4_setup_layout_type(struct svc_export *exp)
{
struct super_block *sb = exp->ex_path.mnt->mnt_sb;
- if (exp->ex_flags & NFSEXP_NOPNFS)
+ if (!(exp->ex_flags & NFSEXP_PNFS))
return;
if (sb->s_export_op->get_uuid &&
@@ -440,15 +440,14 @@ nfsd4_return_file_layout(struct nfs4_layout *lp, struct nfsd4_layout_seg *seg,
list_move_tail(&lp->lo_perstate, reaplist);
return;
}
- end = seg->offset;
+ lo->offset = layout_end(seg);
} else {
/* retain the whole layout segment on a split. */
if (layout_end(seg) < end) {
dprintk("%s: split not supported\n", __func__);
return;
}
-
- lo->offset = layout_end(seg);
+ end = seg->offset;
}
layout_update_len(lo, end);
@@ -513,6 +512,9 @@ nfsd4_return_client_layouts(struct svc_rqst *rqstp,
spin_lock(&clp->cl_lock);
list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) {
+ if (ls->ls_layout_type != lrp->lr_layout_type)
+ continue;
+
if (lrp->lr_return_type == RETURN_FSID &&
!fh_fsid_match(&ls->ls_stid.sc_file->fi_fhandle,
&cstate->current_fh.fh_handle))
@@ -587,6 +589,8 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str));
+ trace_layout_recall_fail(&ls->ls_stid.sc_stateid);
+
printk(KERN_WARNING
"nfsd: client %s failed to respond to layout recall. "
" Fencing..\n", addr_str);
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index d30bea8d0277..92b9d97aff4f 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1237,8 +1237,8 @@ nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp);
gdp->gd_notify_types &= ops->notify_types;
- exp_put(exp);
out:
+ exp_put(exp);
return nfserr;
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d2f2c37dc2db..8ba1d888f1e6 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3221,7 +3221,7 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
} else
nfs4_free_openowner(&oo->oo_owner);
spin_unlock(&clp->cl_lock);
- return oo;
+ return ret;
}
static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) {
@@ -5062,7 +5062,7 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp,
} else
nfs4_free_lockowner(&lo->lo_owner);
spin_unlock(&clp->cl_lock);
- return lo;
+ return ret;
}
static void
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index df5e66caf100..5fb7e78169a6 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1562,7 +1562,11 @@ nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp,
p = xdr_decode_hyper(p, &lgp->lg_seg.offset);
p = xdr_decode_hyper(p, &lgp->lg_seg.length);
p = xdr_decode_hyper(p, &lgp->lg_minlength);
- nfsd4_decode_stateid(argp, &lgp->lg_sid);
+
+ status = nfsd4_decode_stateid(argp, &lgp->lg_sid);
+ if (status)
+ return status;
+
READ_BUF(4);
lgp->lg_maxcount = be32_to_cpup(p++);
@@ -1580,7 +1584,11 @@ nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp,
p = xdr_decode_hyper(p, &lcp->lc_seg.offset);
p = xdr_decode_hyper(p, &lcp->lc_seg.length);
lcp->lc_reclaim = be32_to_cpup(p++);
- nfsd4_decode_stateid(argp, &lcp->lc_sid);
+
+ status = nfsd4_decode_stateid(argp, &lcp->lc_sid);
+ if (status)
+ return status;
+
READ_BUF(4);
lcp->lc_newoffset = be32_to_cpup(p++);
if (lcp->lc_newoffset) {
@@ -1628,7 +1636,11 @@ nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp,
READ_BUF(16);
p = xdr_decode_hyper(p, &lrp->lr_seg.offset);
p = xdr_decode_hyper(p, &lrp->lr_seg.length);
- nfsd4_decode_stateid(argp, &lrp->lr_sid);
+
+ status = nfsd4_decode_stateid(argp, &lrp->lr_sid);
+ if (status)
+ return status;
+
READ_BUF(4);
lrp->lrf_body_len = be32_to_cpup(p++);
if (lrp->lrf_body_len > 0) {
@@ -4123,7 +4135,7 @@ nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr,
return nfserr_resource;
*p++ = cpu_to_be32(lrp->lrs_present);
if (lrp->lrs_present)
- nfsd4_encode_stateid(xdr, &lrp->lr_sid);
+ return nfsd4_encode_stateid(xdr, &lrp->lr_sid);
return nfs_ok;
}
#endif /* CONFIG_NFSD_PNFS */
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 83a9694ec485..46ec934f5dee 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -165,13 +165,17 @@ int nfsd_reply_cache_init(void)
{
unsigned int hashsize;
unsigned int i;
+ int status = 0;
max_drc_entries = nfsd_cache_size_limit();
atomic_set(&num_drc_entries, 0);
hashsize = nfsd_hashsize(max_drc_entries);
maskbits = ilog2(hashsize);
- register_shrinker(&nfsd_reply_cache_shrinker);
+ status = register_shrinker(&nfsd_reply_cache_shrinker);
+ if (status)
+ return status;
+
drc_slab = kmem_cache_create("nfsd_drc", sizeof(struct svc_cacherep),
0, 0, NULL);
if (!drc_slab)
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 266845de2100..91f03ce98108 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2392,7 +2392,6 @@ relock:
/*
* for completing the rest of the request.
*/
- *ppos += written;
count -= written;
written_buffered = generic_perform_write(file, from, *ppos);
/*
@@ -2407,7 +2406,6 @@ relock:
goto out_dio;
}
- iocb->ki_pos = *ppos + written_buffered;
/* We need to ensure that the page cache pages are written to
* disk and invalidated to preserve the expected O_DIRECT
* semantics.
@@ -2416,6 +2414,7 @@ relock:
ret = filemap_write_and_wait_range(file->f_mapping, *ppos,
endbyte);
if (ret == 0) {
+ iocb->ki_pos = *ppos + written_buffered;
written += written_buffered;
invalidate_mapping_pages(mapping,
*ppos >> PAGE_CACHE_SHIFT,
@@ -2438,10 +2437,14 @@ out_dio:
/* buffered aio wouldn't have proper lock coverage today */
BUG_ON(ret == -EIOCBQUEUED && !(file->f_flags & O_DIRECT));
+ if (unlikely(written <= 0))
+ goto no_sync;
+
if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) ||
((file->f_flags & O_DIRECT) && !direct_io)) {
- ret = filemap_fdatawrite_range(file->f_mapping, *ppos,
- *ppos + count - 1);
+ ret = filemap_fdatawrite_range(file->f_mapping,
+ iocb->ki_pos - written,
+ iocb->ki_pos - 1);
if (ret < 0)
written = ret;
@@ -2452,10 +2455,12 @@ out_dio:
}
if (!ret)
- ret = filemap_fdatawait_range(file->f_mapping, *ppos,
- *ppos + count - 1);
+ ret = filemap_fdatawait_range(file->f_mapping,
+ iocb->ki_pos - written,
+ iocb->ki_pos - 1);
}
+no_sync:
/*
* deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io
* function pointer which is called when o_direct io completes so that
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 2554d8835b48..b400c04371f0 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -41,7 +41,7 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj,
if (grp->attrs) {
for (i = 0, attr = grp->attrs; *attr && !error; i++, attr++) {
- umode_t mode = 0;
+ umode_t mode = (*attr)->mode;
/*
* In update mode, we're changing the permissions or
@@ -55,9 +55,14 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj,
if (!mode)
continue;
}
+
+ WARN(mode & ~(SYSFS_PREALLOC | 0664),
+ "Attribute %s: Invalid permissions 0%o\n",
+ (*attr)->name, mode);
+
+ mode &= SYSFS_PREALLOC | 0664;
error = sysfs_add_file_mode_ns(parent, *attr, false,
- (*attr)->mode | mode,
- NULL);
+ mode, NULL);
if (unlikely(error))
break;
}
diff --git a/fs/tracefs/Makefile b/fs/tracefs/Makefile
new file mode 100644
index 000000000000..82fa35b656c4
--- /dev/null
+++ b/fs/tracefs/Makefile
@@ -0,0 +1,4 @@
+tracefs-objs := inode.o
+
+obj-$(CONFIG_TRACING) += tracefs.o
+
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
new file mode 100644
index 000000000000..d92bdf3b079a
--- /dev/null
+++ b/fs/tracefs/inode.c
@@ -0,0 +1,650 @@
+/*
+ * inode.c - part of tracefs, a pseudo file system for activating tracing
+ *
+ * Based on debugfs by: Greg Kroah-Hartman <greg@kroah.com>
+ *
+ * Copyright (C) 2014 Red Hat Inc, author: Steven Rostedt <srostedt@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * tracefs is the file system that is used by the tracing infrastructure.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/kobject.h>
+#include <linux/namei.h>
+#include <linux/tracefs.h>
+#include <linux/fsnotify.h>
+#include <linux/seq_file.h>
+#include <linux/parser.h>
+#include <linux/magic.h>
+#include <linux/slab.h>
+
+#define TRACEFS_DEFAULT_MODE 0700
+
+static struct vfsmount *tracefs_mount;
+static int tracefs_mount_count;
+static bool tracefs_registered;
+
+static ssize_t default_read_file(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ return 0;
+}
+
+static ssize_t default_write_file(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ return count;
+}
+
+static const struct file_operations tracefs_file_operations = {
+ .read = default_read_file,
+ .write = default_write_file,
+ .open = simple_open,
+ .llseek = noop_llseek,
+};
+
+static struct tracefs_dir_ops {
+ int (*mkdir)(const char *name);
+ int (*rmdir)(const char *name);
+} tracefs_ops;
+
+static char *get_dname(struct dentry *dentry)
+{
+ const char *dname;
+ char *name;
+ int len = dentry->d_name.len;
+
+ dname = dentry->d_name.name;
+ name = kmalloc(len + 1, GFP_KERNEL);
+ if (!name)
+ return NULL;
+ memcpy(name, dname, len);
+ name[len] = 0;
+ return name;
+}
+
+static int tracefs_syscall_mkdir(struct inode *inode, struct dentry *dentry, umode_t mode)
+{
+ char *name;
+ int ret;
+
+ name = get_dname(dentry);
+ if (!name)
+ return -ENOMEM;
+
+ /*
+ * The mkdir call can call the generic functions that create
+ * the files within the tracefs system. It is up to the individual
+ * mkdir routine to handle races.
+ */
+ mutex_unlock(&inode->i_mutex);
+ ret = tracefs_ops.mkdir(name);
+ mutex_lock(&inode->i_mutex);
+
+ kfree(name);
+
+ return ret;
+}
+
+static int tracefs_syscall_rmdir(struct inode *inode, struct dentry *dentry)
+{
+ char *name;
+ int ret;
+
+ name = get_dname(dentry);
+ if (!name)
+ return -ENOMEM;
+
+ /*
+ * The rmdir call can call the generic functions that create
+ * the files within the tracefs system. It is up to the individual
+ * rmdir routine to handle races.
+ * This time we need to unlock not only the parent (inode) but
+ * also the directory that is being deleted.
+ */
+ mutex_unlock(&inode->i_mutex);
+ mutex_unlock(&dentry->d_inode->i_mutex);
+
+ ret = tracefs_ops.rmdir(name);
+
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
+ mutex_lock(&dentry->d_inode->i_mutex);
+
+ kfree(name);
+
+ return ret;
+}
+
+static const struct inode_operations tracefs_dir_inode_operations = {
+ .lookup = simple_lookup,
+ .mkdir = tracefs_syscall_mkdir,
+ .rmdir = tracefs_syscall_rmdir,
+};
+
+static struct inode *tracefs_get_inode(struct super_block *sb)
+{
+ struct inode *inode = new_inode(sb);
+ if (inode) {
+ inode->i_ino = get_next_ino();
+ inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ }
+ return inode;
+}
+
+struct tracefs_mount_opts {
+ kuid_t uid;
+ kgid_t gid;
+ umode_t mode;
+};
+
+enum {
+ Opt_uid,
+ Opt_gid,
+ Opt_mode,
+ Opt_err
+};
+
+static const match_table_t tokens = {
+ {Opt_uid, "uid=%u"},
+ {Opt_gid, "gid=%u"},
+ {Opt_mode, "mode=%o"},
+ {Opt_err, NULL}
+};
+
+struct tracefs_fs_info {
+ struct tracefs_mount_opts mount_opts;
+};
+
+static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
+{
+ substring_t args[MAX_OPT_ARGS];
+ int option;
+ int token;
+ kuid_t uid;
+ kgid_t gid;
+ char *p;
+
+ opts->mode = TRACEFS_DEFAULT_MODE;
+
+ while ((p = strsep(&data, ",")) != NULL) {
+ if (!*p)
+ continue;
+
+ token = match_token(p, tokens, args);
+ switch (token) {
+ case Opt_uid:
+ if (match_int(&args[0], &option))
+ return -EINVAL;
+ uid = make_kuid(current_user_ns(), option);
+ if (!uid_valid(uid))
+ return -EINVAL;
+ opts->uid = uid;
+ break;
+ case Opt_gid:
+ if (match_int(&args[0], &option))
+ return -EINVAL;
+ gid = make_kgid(current_user_ns(), option);
+ if (!gid_valid(gid))
+ return -EINVAL;
+ opts->gid = gid;
+ break;
+ case Opt_mode:
+ if (match_octal(&args[0], &option))
+ return -EINVAL;
+ opts->mode = option & S_IALLUGO;
+ break;
+ /*
+ * We might like to report bad mount options here;
+ * but traditionally tracefs has ignored all mount options
+ */
+ }
+ }
+
+ return 0;
+}
+
+static int tracefs_apply_options(struct super_block *sb)
+{
+ struct tracefs_fs_info *fsi = sb->s_fs_info;
+ struct inode *inode = sb->s_root->d_inode;
+ struct tracefs_mount_opts *opts = &fsi->mount_opts;
+
+ inode->i_mode &= ~S_IALLUGO;
+ inode->i_mode |= opts->mode;
+
+ inode->i_uid = opts->uid;
+ inode->i_gid = opts->gid;
+
+ return 0;
+}
+
+static int tracefs_remount(struct super_block *sb, int *flags, char *data)
+{
+ int err;
+ struct tracefs_fs_info *fsi = sb->s_fs_info;
+
+ sync_filesystem(sb);
+ err = tracefs_parse_options(data, &fsi->mount_opts);
+ if (err)
+ goto fail;
+
+ tracefs_apply_options(sb);
+
+fail:
+ return err;
+}
+
+static int tracefs_show_options(struct seq_file *m, struct dentry *root)
+{
+ struct tracefs_fs_info *fsi = root->d_sb->s_fs_info;
+ struct tracefs_mount_opts *opts = &fsi->mount_opts;
+
+ if (!uid_eq(opts->uid, GLOBAL_ROOT_UID))
+ seq_printf(m, ",uid=%u",
+ from_kuid_munged(&init_user_ns, opts->uid));
+ if (!gid_eq(opts->gid, GLOBAL_ROOT_GID))
+ seq_printf(m, ",gid=%u",
+ from_kgid_munged(&init_user_ns, opts->gid));
+ if (opts->mode != TRACEFS_DEFAULT_MODE)
+ seq_printf(m, ",mode=%o", opts->mode);
+
+ return 0;
+}
+
+static const struct super_operations tracefs_super_operations = {
+ .statfs = simple_statfs,
+ .remount_fs = tracefs_remount,
+ .show_options = tracefs_show_options,
+};
+
+static int trace_fill_super(struct super_block *sb, void *data, int silent)
+{
+ static struct tree_descr trace_files[] = {{""}};
+ struct tracefs_fs_info *fsi;
+ int err;
+
+ save_mount_options(sb, data);
+
+ fsi = kzalloc(sizeof(struct tracefs_fs_info), GFP_KERNEL);
+ sb->s_fs_info = fsi;
+ if (!fsi) {
+ err = -ENOMEM;
+ goto fail;
+ }
+
+ err = tracefs_parse_options(data, &fsi->mount_opts);
+ if (err)
+ goto fail;
+
+ err = simple_fill_super(sb, TRACEFS_MAGIC, trace_files);
+ if (err)
+ goto fail;
+
+ sb->s_op = &tracefs_super_operations;
+
+ tracefs_apply_options(sb);
+
+ return 0;
+
+fail:
+ kfree(fsi);
+ sb->s_fs_info = NULL;
+ return err;
+}
+
+static struct dentry *trace_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name,
+ void *data)
+{
+ return mount_single(fs_type, flags, data, trace_fill_super);
+}
+
+static struct file_system_type trace_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "tracefs",
+ .mount = trace_mount,
+ .kill_sb = kill_litter_super,
+};
+MODULE_ALIAS_FS("tracefs");
+
+static struct dentry *start_creating(const char *name, struct dentry *parent)
+{
+ struct dentry *dentry;
+ int error;
+
+ pr_debug("tracefs: creating file '%s'\n",name);
+
+ error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
+ &tracefs_mount_count);
+ if (error)
+ return ERR_PTR(error);
+
+ /* If the parent is not specified, we create it in the root.
+ * We need the root dentry to do this, which is in the super
+ * block. A pointer to that is in the struct vfsmount that we
+ * have around.
+ */
+ if (!parent)
+ parent = tracefs_mount->mnt_root;
+
+ mutex_lock(&parent->d_inode->i_mutex);
+ dentry = lookup_one_len(name, parent, strlen(name));
+ if (!IS_ERR(dentry) && dentry->d_inode) {
+ dput(dentry);
+ dentry = ERR_PTR(-EEXIST);
+ }
+ if (IS_ERR(dentry))
+ mutex_unlock(&parent->d_inode->i_mutex);
+ return dentry;
+}
+
+static struct dentry *failed_creating(struct dentry *dentry)
+{
+ mutex_unlock(&dentry->d_parent->d_inode->i_mutex);
+ dput(dentry);
+ simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+ return NULL;
+}
+
+static struct dentry *end_creating(struct dentry *dentry)
+{
+ mutex_unlock(&dentry->d_parent->d_inode->i_mutex);
+ return dentry;
+}
+
+/**
+ * tracefs_create_file - create a file in the tracefs filesystem
+ * @name: a pointer to a string containing the name of the file to create.
+ * @mode: the permission that the file should have.
+ * @parent: a pointer to the parent dentry for this file. This should be a
+ * directory dentry if set. If this parameter is NULL, then the
+ * file will be created in the root of the tracefs filesystem.
+ * @data: a pointer to something that the caller will want to get to later
+ * on. The inode.i_private pointer will point to this value on
+ * the open() call.
+ * @fops: a pointer to a struct file_operations that should be used for
+ * this file.
+ *
+ * This is the basic "create a file" function for tracefs. It allows for a
+ * wide range of flexibility in creating a file, or a directory (if you want
+ * to create a directory, the tracefs_create_dir() function is
+ * recommended to be used instead.)
+ *
+ * This function will return a pointer to a dentry if it succeeds. This
+ * pointer must be passed to the tracefs_remove() function when the file is
+ * to be removed (no automatic cleanup happens if your module is unloaded,
+ * you are responsible here.) If an error occurs, %NULL will be returned.
+ *
+ * If tracefs is not enabled in the kernel, the value -%ENODEV will be
+ * returned.
+ */
+struct dentry *tracefs_create_file(const char *name, umode_t mode,
+ struct dentry *parent, void *data,
+ const struct file_operations *fops)
+{
+ struct dentry *dentry;
+ struct inode *inode;
+
+ if (!(mode & S_IFMT))
+ mode |= S_IFREG;
+ BUG_ON(!S_ISREG(mode));
+ dentry = start_creating(name, parent);
+
+ if (IS_ERR(dentry))
+ return NULL;
+
+ inode = tracefs_get_inode(dentry->d_sb);
+ if (unlikely(!inode))
+ return failed_creating(dentry);
+
+ inode->i_mode = mode;
+ inode->i_fop = fops ? fops : &tracefs_file_operations;
+ inode->i_private = data;
+ d_instantiate(dentry, inode);
+ fsnotify_create(dentry->d_parent->d_inode, dentry);
+ return end_creating(dentry);
+}
+
+static struct dentry *__create_dir(const char *name, struct dentry *parent,
+ const struct inode_operations *ops)
+{
+ struct dentry *dentry = start_creating(name, parent);
+ struct inode *inode;
+
+ if (IS_ERR(dentry))
+ return NULL;
+
+ inode = tracefs_get_inode(dentry->d_sb);
+ if (unlikely(!inode))
+ return failed_creating(dentry);
+
+ inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
+ inode->i_op = ops;
+ inode->i_fop = &simple_dir_operations;
+
+ /* directory inodes start off with i_nlink == 2 (for "." entry) */
+ inc_nlink(inode);
+ d_instantiate(dentry, inode);
+ inc_nlink(dentry->d_parent->d_inode);
+ fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
+ return end_creating(dentry);
+}
+
+/**
+ * tracefs_create_dir - create a directory in the tracefs filesystem
+ * @name: a pointer to a string containing the name of the directory to
+ * create.
+ * @parent: a pointer to the parent dentry for this file. This should be a
+ * directory dentry if set. If this parameter is NULL, then the
+ * directory will be created in the root of the tracefs filesystem.
+ *
+ * This function creates a directory in tracefs with the given name.
+ *
+ * This function will return a pointer to a dentry if it succeeds. This
+ * pointer must be passed to the tracefs_remove() function when the file is
+ * to be removed. If an error occurs, %NULL will be returned.
+ *
+ * If tracing is not enabled in the kernel, the value -%ENODEV will be
+ * returned.
+ */
+struct dentry *tracefs_create_dir(const char *name, struct dentry *parent)
+{
+ return __create_dir(name, parent, &simple_dir_inode_operations);
+}
+
+/**
+ * tracefs_create_instance_dir - create the tracing instances directory
+ * @name: The name of the instances directory to create
+ * @parent: The parent directory that the instances directory will exist
+ * @mkdir: The function to call when a mkdir is performed.
+ * @rmdir: The function to call when a rmdir is performed.
+ *
+ * Only one instances directory is allowed.
+ *
+ * The instances directory is special as it allows for mkdir and rmdir to
+ * to be done by userspace. When a mkdir or rmdir is performed, the inode
+ * locks are released and the methhods passed in (@mkdir and @rmdir) are
+ * called without locks and with the name of the directory being created
+ * within the instances directory.
+ *
+ * Returns the dentry of the instances directory.
+ */
+struct dentry *tracefs_create_instance_dir(const char *name, struct dentry *parent,
+ int (*mkdir)(const char *name),
+ int (*rmdir)(const char *name))
+{
+ struct dentry *dentry;
+
+ /* Only allow one instance of the instances directory. */
+ if (WARN_ON(tracefs_ops.mkdir || tracefs_ops.rmdir))
+ return NULL;
+
+ dentry = __create_dir(name, parent, &tracefs_dir_inode_operations);
+ if (!dentry)
+ return NULL;
+
+ tracefs_ops.mkdir = mkdir;
+ tracefs_ops.rmdir = rmdir;
+
+ return dentry;
+}
+
+static inline int tracefs_positive(struct dentry *dentry)
+{
+ return dentry->d_inode && !d_unhashed(dentry);
+}
+
+static int __tracefs_remove(struct dentry *dentry, struct dentry *parent)
+{
+ int ret = 0;
+
+ if (tracefs_positive(dentry)) {
+ if (dentry->d_inode) {
+ dget(dentry);
+ switch (dentry->d_inode->i_mode & S_IFMT) {
+ case S_IFDIR:
+ ret = simple_rmdir(parent->d_inode, dentry);
+ break;
+ default:
+ simple_unlink(parent->d_inode, dentry);
+ break;
+ }
+ if (!ret)
+ d_delete(dentry);
+ dput(dentry);
+ }
+ }
+ return ret;
+}
+
+/**
+ * tracefs_remove - removes a file or directory from the tracefs filesystem
+ * @dentry: a pointer to a the dentry of the file or directory to be
+ * removed.
+ *
+ * This function removes a file or directory in tracefs that was previously
+ * created with a call to another tracefs function (like
+ * tracefs_create_file() or variants thereof.)
+ */
+void tracefs_remove(struct dentry *dentry)
+{
+ struct dentry *parent;
+ int ret;
+
+ if (IS_ERR_OR_NULL(dentry))
+ return;
+
+ parent = dentry->d_parent;
+ if (!parent || !parent->d_inode)
+ return;
+
+ mutex_lock(&parent->d_inode->i_mutex);
+ ret = __tracefs_remove(dentry, parent);
+ mutex_unlock(&parent->d_inode->i_mutex);
+ if (!ret)
+ simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+}
+
+/**
+ * tracefs_remove_recursive - recursively removes a directory
+ * @dentry: a pointer to a the dentry of the directory to be removed.
+ *
+ * This function recursively removes a directory tree in tracefs that
+ * was previously created with a call to another tracefs function
+ * (like tracefs_create_file() or variants thereof.)
+ */
+void tracefs_remove_recursive(struct dentry *dentry)
+{
+ struct dentry *child, *parent;
+
+ if (IS_ERR_OR_NULL(dentry))
+ return;
+
+ parent = dentry->d_parent;
+ if (!parent || !parent->d_inode)
+ return;
+
+ parent = dentry;
+ down:
+ mutex_lock(&parent->d_inode->i_mutex);
+ loop:
+ /*
+ * The parent->d_subdirs is protected by the d_lock. Outside that
+ * lock, the child can be unlinked and set to be freed which can
+ * use the d_u.d_child as the rcu head and corrupt this list.
+ */
+ spin_lock(&parent->d_lock);
+ list_for_each_entry(child, &parent->d_subdirs, d_child) {
+ if (!tracefs_positive(child))
+ continue;
+
+ /* perhaps simple_empty(child) makes more sense */
+ if (!list_empty(&child->d_subdirs)) {
+ spin_unlock(&parent->d_lock);
+ mutex_unlock(&parent->d_inode->i_mutex);
+ parent = child;
+ goto down;
+ }
+
+ spin_unlock(&parent->d_lock);
+
+ if (!__tracefs_remove(child, parent))
+ simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+
+ /*
+ * The parent->d_lock protects agaist child from unlinking
+ * from d_subdirs. When releasing the parent->d_lock we can
+ * no longer trust that the next pointer is valid.
+ * Restart the loop. We'll skip this one with the
+ * tracefs_positive() check.
+ */
+ goto loop;
+ }
+ spin_unlock(&parent->d_lock);
+
+ mutex_unlock(&parent->d_inode->i_mutex);
+ child = parent;
+ parent = parent->d_parent;
+ mutex_lock(&parent->d_inode->i_mutex);
+
+ if (child != dentry)
+ /* go up */
+ goto loop;
+
+ if (!__tracefs_remove(child, parent))
+ simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+ mutex_unlock(&parent->d_inode->i_mutex);
+}
+
+/**
+ * tracefs_initialized - Tells whether tracefs has been registered
+ */
+bool tracefs_initialized(void)
+{
+ return tracefs_registered;
+}
+
+static struct kobject *trace_kobj;
+
+static int __init tracefs_init(void)
+{
+ int retval;
+
+ trace_kobj = kobject_create_and_add("tracing", kernel_kobj);
+ if (!trace_kobj)
+ return -EINVAL;
+
+ retval = register_filesystem(&trace_fs_type);
+ if (!retval)
+ tracefs_registered = true;
+
+ return retval;
+}
+core_initcall(tracefs_init);
View Lorry Controller Status