public-mirrors/linux
1
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-09-18 22:14:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Tracing and eventfs fixes for v6.8:

Browse source 
- Fix the return code for ring_buffer_poll_wait()
   It was returing a -EINVAL instead of EPOLLERR.
 
 - Zero out the tracefs_inode so that all fields are initialized.
   The ti->private could have had stale data, but instead of
   just initializing it to NULL, clear out the entire structure
   when it is allocated.
 
 - Fix a crash in timerlat
   The hrtimer was initialized at read and not open, but is
   canceled at close. If the file was opened and never read
   the close will pass a NULL pointer to hrtime_cancel().
 
 - Rewrite of eventfs.
   Linus wrote a patch series to remove the dentry references in the
   eventfs_inode and to use ref counting and more of proper VFS
   interfaces to make it work.
 
 - Add warning to put_ei() if ei is not set to free. That means
   something is about to free it when it shouldn't.
 
 - Restructure the eventfs_inode to make it more compact, and remove
   the unused llist field.
 
 - Remove the fsnotify*() funtions for when the inodes were being created
   in the lookup code. It doesn't make sense to notify about creation
   just because something is being looked up.
 
 - The inode hard link count was not accurate. It was being updated
   when a file was looked up. The inodes of directories were updating
   their parent inode hard link count every time the inode was created.
   That means if memory reclaim cleaned a stale directory inode and
   the inode was lookup up again, it would increment the parent inode
   again as well. Al Viro said to just have all eventfs directories
   have a hard link count of 1. That tells user space not to trust it.
 -----BEGIN PGP SIGNATURE-----
 
 iIoEABYIADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCZb1l/RQccm9zdGVkdEBn
 b29kbWlzLm9yZwAKCRAp5XQQmuv6qk6jAQDmecDOnx+j/Rm5krbX/meVPYXFj2CU
 1wO7w1HBzopsBwEA5AjTKm9IGrl/eVG/+jViS165b+sJfwEcblHEFPWcIwo=
 =uUzb
 -----END PGP SIGNATURE-----

Merge tag 'trace-v6.8-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing and eventfs fixes from Steven Rostedt:

 - Fix the return code for ring_buffer_poll_wait()

   It was returing a -EINVAL instead of EPOLLERR.

 - Zero out the tracefs_inode so that all fields are initialized.

   The ti->private could have had stale data, but instead of just
   initializing it to NULL, clear out the entire structure when it is
   allocated.

 - Fix a crash in timerlat

   The hrtimer was initialized at read and not open, but is canceled at
   close. If the file was opened and never read the close will pass a
   NULL pointer to hrtime_cancel().

 - Rewrite of eventfs.

   Linus wrote a patch series to remove the dentry references in the
   eventfs_inode and to use ref counting and more of proper VFS
   interfaces to make it work.

 - Add warning to put_ei() if ei is not set to free. That means
   something is about to free it when it shouldn't.

 - Restructure the eventfs_inode to make it more compact, and remove the
   unused llist field.

 - Remove the fsnotify*() funtions for when the inodes were being
   created in the lookup code. It doesn't make sense to notify about
   creation just because something is being looked up.

 - The inode hard link count was not accurate.

   It was being updated when a file was looked up. The inodes of
   directories were updating their parent inode hard link count every
   time the inode was created. That means if memory reclaim cleaned a
   stale directory inode and the inode was lookup up again, it would
   increment the parent inode again as well. Al Viro said to just have
   all eventfs directories have a hard link count of 1. That tells user
   space not to trust it.

* tag 'trace-v6.8-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  eventfs: Keep all directory links at 1
  eventfs: Remove fsnotify*() functions from lookup()
  eventfs: Restructure eventfs_inode structure to be more condensed
  eventfs: Warn if an eventfs_inode is freed without is_freed being set
  tracing/timerlat: Move hrtimer_init to timerlat_fd open()
  eventfs: Get rid of dentry pointers without refcounts
  eventfs: Clean up dentry ops and add revalidate function
  eventfs: Remove unused d_parent pointer field
  tracefs: dentry lookup crapectomy
  tracefs: Avoid using the ei->dentry pointer unnecessarily
  eventfs: Initialize the tracefs inode properly
  tracefs: Zero out the tracefs_inode when allocating it
  ring-buffer: Clean ring_buffer_poll_wait() error return
This commit is contained in:
Linus Torvalds 2024-02-02 15:32:58 -08:00
commit 56897d5188
5 changed files with 195 additions and 526 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

568
fs/tracefs/event_inode.c
View file

@ -62,6 +62,46 @@ enum {
#define EVENTFS_MODE_MASK (EVENTFS_SAVE_MODE - 1) #define EVENTFS_MODE_MASK (EVENTFS_SAVE_MODE - 1)
/*
* eventfs_inode reference count management.
*
* NOTE! We count only references from dentries, in the
* form 'dentry->d_fsdata'. There are also references from
* directory inodes ('ti->private'), but the dentry reference
* count is always a superset of the inode reference count.
*/
static void release_ei(struct kref *ref)
{
struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref);
WARN_ON_ONCE(!ei->is_freed);
kfree(ei->entry_attrs);
kfree_const(ei->name);
kfree_rcu(ei, rcu);
}
static inline void put_ei(struct eventfs_inode *ei)
{
if (ei)
kref_put(&ei->kref, release_ei);
}
static inline void free_ei(struct eventfs_inode *ei)
{
if (ei) {
ei->is_freed = 1;
put_ei(ei);
}
}
static inline struct eventfs_inode *get_ei(struct eventfs_inode *ei)
{
if (ei)
kref_get(&ei->kref);
return ei;
}
static struct dentry *eventfs_root_lookup(struct inode *dir, static struct dentry *eventfs_root_lookup(struct inode *dir,
struct dentry *dentry, struct dentry *dentry,
unsigned int flags); unsigned int flags);
@ -156,33 +196,30 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
return ret; return ret;
} }
static void update_top_events_attr(struct eventfs_inode *ei, struct dentry *dentry) static void update_top_events_attr(struct eventfs_inode *ei, struct super_block *sb)
{ {
struct inode *inode; struct inode *root;
/* Only update if the "events" was on the top level */ /* Only update if the "events" was on the top level */
if (!ei || !(ei->attr.mode & EVENTFS_TOPLEVEL)) if (!ei || !(ei->attr.mode & EVENTFS_TOPLEVEL))
return; return;
/* Get the tracefs root inode. */ /* Get the tracefs root inode. */
inode = d_inode(dentry->d_sb->s_root); root = d_inode(sb->s_root);
ei->attr.uid = inode->i_uid; ei->attr.uid = root->i_uid;
ei->attr.gid = inode->i_gid; ei->attr.gid = root->i_gid;
} }
static void set_top_events_ownership(struct inode *inode) static void set_top_events_ownership(struct inode *inode)
{ {
struct tracefs_inode *ti = get_tracefs(inode); struct tracefs_inode *ti = get_tracefs(inode);
struct eventfs_inode *ei = ti->private; struct eventfs_inode *ei = ti->private;
struct dentry *dentry;
/* The top events directory doesn't get automatically updated */ /* The top events directory doesn't get automatically updated */
if (!ei || !ei->is_events || !(ei->attr.mode & EVENTFS_TOPLEVEL)) if (!ei || !ei->is_events || !(ei->attr.mode & EVENTFS_TOPLEVEL))
return; return;
dentry = ei->dentry; update_top_events_attr(ei, inode->i_sb);
update_top_events_attr(ei, dentry);
if (!(ei->attr.mode & EVENTFS_SAVE_UID)) if (!(ei->attr.mode & EVENTFS_SAVE_UID))
inode->i_uid = ei->attr.uid; inode->i_uid = ei->attr.uid;
@ -233,10 +270,11 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
{ {
struct eventfs_inode *ei; struct eventfs_inode *ei;
mutex_lock(&eventfs_mutex);
do { do {
/* The parent always has an ei, except for events itself */ // The parent is stable because we do not do renames
ei = dentry->d_parent->d_fsdata; dentry = dentry->d_parent;
// ... and directories always have d_fsdata
ei = dentry->d_fsdata;
/* /*
* If the ei is being freed, the ownership of the children * If the ei is being freed, the ownership of the children
@ -246,12 +284,10 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
ei = NULL; ei = NULL;
break; break;
} }
// Walk upwards until you find the events inode
dentry = ei->dentry;
} while (!ei->is_events); } while (!ei->is_events);
mutex_unlock(&eventfs_mutex);
update_top_events_attr(ei, dentry); update_top_events_attr(ei, dentry->d_sb);
return ei; return ei;
} }
@ -282,11 +318,10 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode,
} }
/** /**
* create_file - create a file in the tracefs filesystem * lookup_file - look up a file in the tracefs filesystem
* @name: the name of the file to create. * @dentry: the dentry to look up
* @mode: the permission that the file should have. * @mode: the permission that the file should have.
* @attr: saved attributes changed by user * @attr: saved attributes changed by user
* @parent: parent dentry for this file.
* @data: something that the caller will want to get to later on. * @data: something that the caller will want to get to later on.
* @fop: struct file_operations that should be used for this file. * @fop: struct file_operations that should be used for this file.
* *
@ -294,30 +329,25 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode,
* directory. The inode.i_private pointer will point to @data in the open() * directory. The inode.i_private pointer will point to @data in the open()
* call. * call.
*/ */
static struct dentry *create_file(const char *name, umode_t mode, static struct dentry *lookup_file(struct eventfs_inode *parent_ei,
struct dentry *dentry,
umode_t mode,
struct eventfs_attr *attr, struct eventfs_attr *attr,
struct dentry *parent, void *data, void *data,
const struct file_operations *fop) const struct file_operations *fop)
{ {
struct tracefs_inode *ti; struct tracefs_inode *ti;
struct dentry *dentry;
struct inode *inode; struct inode *inode;
if (!(mode & S_IFMT)) if (!(mode & S_IFMT))
mode |= S_IFREG; mode |= S_IFREG;
if (WARN_ON_ONCE(!S_ISREG(mode))) if (WARN_ON_ONCE(!S_ISREG(mode)))
return NULL; return ERR_PTR(-EIO);
WARN_ON_ONCE(!parent);
dentry = eventfs_start_creating(name, parent);
if (IS_ERR(dentry))
return dentry;
inode = tracefs_get_inode(dentry->d_sb); inode = tracefs_get_inode(dentry->d_sb);
if (unlikely(!inode)) if (unlikely(!inode))
return eventfs_failed_creating(dentry); return ERR_PTR(-ENOMEM);
/* If the user updated the directory's attributes, use them */ /* If the user updated the directory's attributes, use them */
update_inode_attr(dentry, inode, attr, mode); update_inode_attr(dentry, inode, attr, mode);
@ -331,32 +361,31 @@ static struct dentry *create_file(const char *name, umode_t mode,
ti = get_tracefs(inode); ti = get_tracefs(inode);
ti->flags |= TRACEFS_EVENT_INODE; ti->flags |= TRACEFS_EVENT_INODE;
d_instantiate(dentry, inode);
fsnotify_create(dentry->d_parent->d_inode, dentry); // Files have their parent's ei as their fsdata
return eventfs_end_creating(dentry); dentry->d_fsdata = get_ei(parent_ei);
d_add(dentry, inode);
return NULL;
}; };
/** /**
* create_dir - create a dir in the tracefs filesystem * lookup_dir_entry - look up a dir in the tracefs filesystem
* @dentry: the directory to look up
* @ei: the eventfs_inode that represents the directory to create * @ei: the eventfs_inode that represents the directory to create
* @parent: parent dentry for this file.
* *
* This function will create a dentry for a directory represented by * This function will look up a dentry for a directory represented by
* a eventfs_inode. * a eventfs_inode.
*/ */
static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent) static struct dentry *lookup_dir_entry(struct dentry *dentry,
struct eventfs_inode *pei, struct eventfs_inode *ei)
{ {
struct tracefs_inode *ti; struct tracefs_inode *ti;
struct dentry *dentry;
struct inode *inode; struct inode *inode;
dentry = eventfs_start_creating(ei->name, parent);
if (IS_ERR(dentry))
return dentry;
inode = tracefs_get_inode(dentry->d_sb); inode = tracefs_get_inode(dentry->d_sb);
if (unlikely(!inode)) if (unlikely(!inode))
return eventfs_failed_creating(dentry); return ERR_PTR(-ENOMEM);
/* If the user updated the directory's attributes, use them */ /* If the user updated the directory's attributes, use them */
update_inode_attr(dentry, inode, &ei->attr, update_inode_attr(dentry, inode, &ei->attr,
@ -370,64 +399,46 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent
ti = get_tracefs(inode); ti = get_tracefs(inode);
ti->flags |= TRACEFS_EVENT_INODE; ti->flags |= TRACEFS_EVENT_INODE;
/* Only directories have ti->private set to an ei, not files */
ti->private = ei;
inc_nlink(inode); dentry->d_fsdata = get_ei(ei);
d_instantiate(dentry, inode);
inc_nlink(dentry->d_parent->d_inode); d_add(dentry, inode);
fsnotify_mkdir(dentry->d_parent->d_inode, dentry); return NULL;
return eventfs_end_creating(dentry);
} }
static void free_ei(struct eventfs_inode *ei) static inline struct eventfs_inode *alloc_ei(const char *name)
{ {
kfree_const(ei->name); struct eventfs_inode *ei = kzalloc(sizeof(*ei), GFP_KERNEL);
kfree(ei->d_children);
kfree(ei->entry_attrs); if (!ei)
kfree(ei); return NULL;
ei->name = kstrdup_const(name, GFP_KERNEL);
if (!ei->name) {
kfree(ei);
return NULL;
}
kref_init(&ei->kref);
return ei;
} }
/** /**
* eventfs_set_ei_status_free - remove the dentry reference from an eventfs_inode * eventfs_d_release - dentry is going away
* @ti: the tracefs_inode of the dentry
* @dentry: dentry which has the reference to remove. * @dentry: dentry which has the reference to remove.
* *
* Remove the association between a dentry from an eventfs_inode. * Remove the association between a dentry from an eventfs_inode.
*/ */
void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry) void eventfs_d_release(struct dentry *dentry)
{ {
struct eventfs_inode *ei; put_ei(dentry->d_fsdata);
int i;
mutex_lock(&eventfs_mutex);
ei = dentry->d_fsdata;
if (!ei)
goto out;
/* This could belong to one of the files of the ei */
if (ei->dentry != dentry) {
for (i = 0; i < ei->nr_entries; i++) {
if (ei->d_children[i] == dentry)
break;
}
if (WARN_ON_ONCE(i == ei->nr_entries))
goto out;
ei->d_children[i] = NULL;
} else if (ei->is_freed) {
free_ei(ei);
} else {
ei->dentry = NULL;
}
dentry->d_fsdata = NULL;
out:
mutex_unlock(&eventfs_mutex);
} }
/** /**
* create_file_dentry - create a dentry for a file of an eventfs_inode * lookup_file_dentry - create a dentry for a file of an eventfs_inode
* @ei: the eventfs_inode that the file will be created under * @ei: the eventfs_inode that the file will be created under
* @idx: the index into the d_children[] of the @ei * @idx: the index into the entry_attrs[] of the @ei
* @parent: The parent dentry of the created file. * @parent: The parent dentry of the created file.
* @name: The name of the file to create * @name: The name of the file to create
* @mode: The mode of the file. * @mode: The mode of the file.
@ -438,163 +449,17 @@ void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry)
* address located at @e_dentry. * address located at @e_dentry.
*/ */
static struct dentry * static struct dentry *
create_file_dentry(struct eventfs_inode *ei, int idx, lookup_file_dentry(struct dentry *dentry,
struct dentry *parent, const char *name, umode_t mode, void *data, struct eventfs_inode *ei, int idx,
umode_t mode, void *data,
const struct file_operations *fops) const struct file_operations *fops)
{ {
struct eventfs_attr *attr = NULL; struct eventfs_attr *attr = NULL;
struct dentry **e_dentry = &ei->d_children[idx];
struct dentry *dentry;
WARN_ON_ONCE(!inode_is_locked(parent->d_inode));
mutex_lock(&eventfs_mutex);
if (ei->is_freed) {
mutex_unlock(&eventfs_mutex);
return NULL;
}
/* If the e_dentry already has a dentry, use it */
if (*e_dentry) {
dget(*e_dentry);
mutex_unlock(&eventfs_mutex);
return *e_dentry;
}
/* ei->entry_attrs are protected by SRCU */
if (ei->entry_attrs) if (ei->entry_attrs)
attr = &ei->entry_attrs[idx]; attr = &ei->entry_attrs[idx];
mutex_unlock(&eventfs_mutex); return lookup_file(ei, dentry, mode, attr, data, fops);
dentry = create_file(name, mode, attr, parent, data, fops);
mutex_lock(&eventfs_mutex);
if (IS_ERR_OR_NULL(dentry)) {
/*
* When the mutex was released, something else could have
* created the dentry for this e_dentry. In which case
* use that one.
*
* If ei->is_freed is set, the e_dentry is currently on its
* way to being freed, don't return it. If e_dentry is NULL
* it means it was already freed.
*/
if (ei->is_freed) {
dentry = NULL;
} else {
dentry = *e_dentry;
dget(dentry);
}
mutex_unlock(&eventfs_mutex);
return dentry;
}
if (!*e_dentry && !ei->is_freed) {
*e_dentry = dentry;
dentry->d_fsdata = ei;
} else {
/*
* Should never happen unless we get here due to being freed.
* Otherwise it means two dentries exist with the same name.
*/
WARN_ON_ONCE(!ei->is_freed);
dentry = NULL;
}
mutex_unlock(&eventfs_mutex);
return dentry;
}
/**
* eventfs_post_create_dir - post create dir routine
* @ei: eventfs_inode of recently created dir
*
* Map the meta-data of files within an eventfs dir to their parent dentry
*/
static void eventfs_post_create_dir(struct eventfs_inode *ei)
{
struct eventfs_inode *ei_child;
struct tracefs_inode *ti;
lockdep_assert_held(&eventfs_mutex);
/* srcu lock already held */
/* fill parent-child relation */
list_for_each_entry_srcu(ei_child, &ei->children, list,
srcu_read_lock_held(&eventfs_srcu)) {
ei_child->d_parent = ei->dentry;
}
ti = get_tracefs(ei->dentry->d_inode);
ti->private = ei;
}
/**
* create_dir_dentry - Create a directory dentry for the eventfs_inode
* @pei: The eventfs_inode parent of ei.
* @ei: The eventfs_inode to create the directory for
* @parent: The dentry of the parent of this directory
*
* This creates and attaches a directory dentry to the eventfs_inode @ei.
*/
static struct dentry *
create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei,
struct dentry *parent)
{
struct dentry *dentry = NULL;
WARN_ON_ONCE(!inode_is_locked(parent->d_inode));
mutex_lock(&eventfs_mutex);
if (pei->is_freed || ei->is_freed) {
mutex_unlock(&eventfs_mutex);
return NULL;
}
if (ei->dentry) {
/* If the eventfs_inode already has a dentry, use it */
dentry = ei->dentry;
dget(dentry);
mutex_unlock(&eventfs_mutex);
return dentry;
}
mutex_unlock(&eventfs_mutex);
dentry = create_dir(ei, parent);
mutex_lock(&eventfs_mutex);
if (IS_ERR_OR_NULL(dentry) && !ei->is_freed) {
/*
* When the mutex was released, something else could have
* created the dentry for this e_dentry. In which case
* use that one.
*
* If ei->is_freed is set, the e_dentry is currently on its
* way to being freed.
*/
dentry = ei->dentry;
if (dentry)
dget(dentry);
mutex_unlock(&eventfs_mutex);
return dentry;
}
if (!ei->dentry && !ei->is_freed) {
ei->dentry = dentry;
eventfs_post_create_dir(ei);
dentry->d_fsdata = ei;
} else {
/*
* Should never happen unless we get here due to being freed.
* Otherwise it means two dentries exist with the same name.
*/
WARN_ON_ONCE(!ei->is_freed);
dentry = NULL;
}
mutex_unlock(&eventfs_mutex);
return dentry;
} }
/** /**
@ -611,79 +476,50 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
struct dentry *dentry, struct dentry *dentry,
unsigned int flags) unsigned int flags)
{ {
const struct file_operations *fops;
const struct eventfs_entry *entry;
struct eventfs_inode *ei_child; struct eventfs_inode *ei_child;
struct tracefs_inode *ti; struct tracefs_inode *ti;
struct eventfs_inode *ei; struct eventfs_inode *ei;
struct dentry *ei_dentry = NULL;
struct dentry *ret = NULL;
struct dentry *d;
const char *name = dentry->d_name.name; const char *name = dentry->d_name.name;
umode_t mode; struct dentry *result = NULL;
void *data;
int idx;
int i;
int r;
ti = get_tracefs(dir); ti = get_tracefs(dir);
if (!(ti->flags & TRACEFS_EVENT_INODE)) if (!(ti->flags & TRACEFS_EVENT_INODE))
return NULL; return ERR_PTR(-EIO);
/* Grab srcu to prevent the ei from going away */
idx = srcu_read_lock(&eventfs_srcu);
/*
* Grab the eventfs_mutex to consistent value from ti->private.
* This s
*/
mutex_lock(&eventfs_mutex); mutex_lock(&eventfs_mutex);
ei = READ_ONCE(ti->private);
if (ei && !ei->is_freed)
ei_dentry = READ_ONCE(ei->dentry);
mutex_unlock(&eventfs_mutex);
if (!ei || !ei_dentry) ei = ti->private;
if (!ei || ei->is_freed)
goto out; goto out;
data = ei->data; list_for_each_entry(ei_child, &ei->children, list) {
list_for_each_entry_srcu(ei_child, &ei->children, list,
srcu_read_lock_held(&eventfs_srcu)) {
if (strcmp(ei_child->name, name) != 0) if (strcmp(ei_child->name, name) != 0)
continue; continue;
ret = simple_lookup(dir, dentry, flags); if (ei_child->is_freed)
if (IS_ERR(ret))
goto out; goto out;
d = create_dir_dentry(ei, ei_child, ei_dentry); result = lookup_dir_entry(dentry, ei, ei_child);
dput(d);
goto out; goto out;
} }
for (i = 0; i < ei->nr_entries; i++) { for (int i = 0; i < ei->nr_entries; i++) {
entry = &ei->entries[i]; void *data;
if (strcmp(name, entry->name) == 0) { umode_t mode;
void *cdata = data; const struct file_operations *fops;
mutex_lock(&eventfs_mutex); const struct eventfs_entry *entry = &ei->entries[i];
/* If ei->is_freed, then the event itself may be too */
if (!ei->is_freed) if (strcmp(name, entry->name) != 0)
r = entry->callback(name, &mode, &cdata, &fops); continue;
else
r = -1; data = ei->data;
mutex_unlock(&eventfs_mutex); if (entry->callback(name, &mode, &data, &fops) <= 0)
if (r <= 0) goto out;
continue;
ret = simple_lookup(dir, dentry, flags); result = lookup_file_dentry(dentry, ei, i, mode, data, fops);
if (IS_ERR(ret)) goto out;
goto out;
d = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops);
dput(d);
break;
}
} }
out: out:
srcu_read_unlock(&eventfs_srcu, idx); mutex_unlock(&eventfs_mutex);
return ret; return result;
} }
/* /*
@ -833,25 +669,10 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
if (!parent) if (!parent)
return ERR_PTR(-EINVAL); return ERR_PTR(-EINVAL);
ei = kzalloc(sizeof(*ei), GFP_KERNEL); ei = alloc_ei(name);
if (!ei) if (!ei)
return ERR_PTR(-ENOMEM); return ERR_PTR(-ENOMEM);
ei->name = kstrdup_const(name, GFP_KERNEL);
if (!ei->name) {
kfree(ei);
return ERR_PTR(-ENOMEM);
}
if (size) {
ei->d_children = kcalloc(size, sizeof(*ei->d_children), GFP_KERNEL);
if (!ei->d_children) {
kfree_const(ei->name);
kfree(ei);
return ERR_PTR(-ENOMEM);
}
}
ei->entries = entries; ei->entries = entries;
ei->nr_entries = size; ei->nr_entries = size;
ei->data = data; ei->data = data;
@ -859,10 +680,8 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
INIT_LIST_HEAD(&ei->list); INIT_LIST_HEAD(&ei->list);
mutex_lock(&eventfs_mutex); mutex_lock(&eventfs_mutex);
if (!parent->is_freed) { if (!parent->is_freed)
list_add_tail(&ei->list, &parent->children); list_add_tail(&ei->list, &parent->children);
ei->d_parent = parent->dentry;
}
mutex_unlock(&eventfs_mutex); mutex_unlock(&eventfs_mutex);
/* Was the parent freed? */ /* Was the parent freed? */
@ -902,28 +721,20 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
if (IS_ERR(dentry)) if (IS_ERR(dentry))
return ERR_CAST(dentry); return ERR_CAST(dentry);
ei = kzalloc(sizeof(*ei), GFP_KERNEL); ei = alloc_ei(name);
if (!ei) if (!ei)
goto fail_ei; goto fail;
inode = tracefs_get_inode(dentry->d_sb); inode = tracefs_get_inode(dentry->d_sb);
if (unlikely(!inode)) if (unlikely(!inode))
goto fail; goto fail;
if (size) { // Note: we have a ref to the dentry from tracefs_start_creating()
ei->d_children = kcalloc(size, sizeof(*ei->d_children), GFP_KERNEL); ei->events_dir = dentry;
if (!ei->d_children)
goto fail;
}
ei->dentry = dentry;
ei->entries = entries; ei->entries = entries;
ei->nr_entries = size; ei->nr_entries = size;
ei->is_events = 1; ei->is_events = 1;
ei->data = data; ei->data = data;
ei->name = kstrdup_const(name, GFP_KERNEL);
if (!ei->name)
goto fail;
/* Save the ownership of this directory */ /* Save the ownership of this directory */
uid = d_inode(dentry->d_parent)->i_uid; uid = d_inode(dentry->d_parent)->i_uid;
@ -954,11 +765,19 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
inode->i_op = &eventfs_root_dir_inode_operations; inode->i_op = &eventfs_root_dir_inode_operations;
inode->i_fop = &eventfs_file_operations; inode->i_fop = &eventfs_file_operations;
dentry->d_fsdata = ei; dentry->d_fsdata = get_ei(ei);
/* directory inodes start off with i_nlink == 2 (for "." entry) */ /*
inc_nlink(inode); * Keep all eventfs directories with i_nlink == 1.
* Due to the dynamic nature of the dentry creations and not
* wanting to add a pointer to the parent eventfs_inode in the
* eventfs_inode structure, keeping the i_nlink in sync with the
* number of directories would cause too much complexity for
* something not worth much. Keeping directory links at 1
* tells userspace not to trust the link number.
*/
d_instantiate(dentry, inode); d_instantiate(dentry, inode);
/* The dentry of the "events" parent does keep track though */
inc_nlink(dentry->d_parent->d_inode); inc_nlink(dentry->d_parent->d_inode);
fsnotify_mkdir(dentry->d_parent->d_inode, dentry); fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
tracefs_end_creating(dentry); tracefs_end_creating(dentry);
@ -966,72 +785,11 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
return ei; return ei;
fail: fail:
kfree(ei->d_children); free_ei(ei);
kfree(ei);
fail_ei:
tracefs_failed_creating(dentry); tracefs_failed_creating(dentry);
return ERR_PTR(-ENOMEM); return ERR_PTR(-ENOMEM);
} }
static LLIST_HEAD(free_list);
static void eventfs_workfn(struct work_struct *work)
{
struct eventfs_inode *ei, *tmp;
struct llist_node *llnode;
llnode = llist_del_all(&free_list);
llist_for_each_entry_safe(ei, tmp, llnode, llist) {
/* This dput() matches the dget() from unhook_dentry() */
for (int i = 0; i < ei->nr_entries; i++) {
if (ei->d_children[i])
dput(ei->d_children[i]);
}
/* This should only get here if it had a dentry */
if (!WARN_ON_ONCE(!ei->dentry))
dput(ei->dentry);
}
}
static DECLARE_WORK(eventfs_work, eventfs_workfn);
static void free_rcu_ei(struct rcu_head *head)
{
struct eventfs_inode *ei = container_of(head, struct eventfs_inode, rcu);
if (ei->dentry) {
/* Do not free the ei until all references of dentry are gone */
if (llist_add(&ei->llist, &free_list))
queue_work(system_unbound_wq, &eventfs_work);
return;
}
/* If the ei doesn't have a dentry, neither should its children */
for (int i = 0; i < ei->nr_entries; i++) {
WARN_ON_ONCE(ei->d_children[i]);
}
free_ei(ei);
}
static void unhook_dentry(struct dentry *dentry)
{
if (!dentry)
return;
/*
* Need to add a reference to the dentry that is expected by
* simple_recursive_removal(), which will include a dput().
*/
dget(dentry);
/*
* Also add a reference for the dput() in eventfs_workfn().
* That is required as that dput() will free the ei after
* the SRCU grace period is over.
*/
dget(dentry);
}
/** /**
* eventfs_remove_rec - remove eventfs dir or file from list * eventfs_remove_rec - remove eventfs dir or file from list
* @ei: eventfs_inode to be removed. * @ei: eventfs_inode to be removed.
@ -1044,8 +802,6 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
{ {
struct eventfs_inode *ei_child; struct eventfs_inode *ei_child;
if (!ei)
return;
/* /*
* Check recursion depth. It should never be greater than 3: * Check recursion depth. It should never be greater than 3:
* 0 - events/ * 0 - events/
@ -1057,28 +813,11 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
return; return;
/* search for nested folders or files */ /* search for nested folders or files */
list_for_each_entry_srcu(ei_child, &ei->children, list, list_for_each_entry(ei_child, &ei->children, list)
lockdep_is_held(&eventfs_mutex)) {
/* Children only have dentry if parent does */
WARN_ON_ONCE(ei_child->dentry && !ei->dentry);
eventfs_remove_rec(ei_child, level + 1); eventfs_remove_rec(ei_child, level + 1);
}
list_del(&ei->list);
ei->is_freed = 1; free_ei(ei);
for (int i = 0; i < ei->nr_entries; i++) {
if (ei->d_children[i]) {
/* Children only have dentry if parent does */
WARN_ON_ONCE(!ei->dentry);
unhook_dentry(ei->d_children[i]);
}
}
unhook_dentry(ei->dentry);
list_del_rcu(&ei->list);
call_srcu(&eventfs_srcu, &ei->rcu, free_rcu_ei);
} }
/** /**
@ -1089,22 +828,12 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
*/ */
void eventfs_remove_dir(struct eventfs_inode *ei) void eventfs_remove_dir(struct eventfs_inode *ei)
{ {
struct dentry *dentry;
if (!ei) if (!ei)
return; return;
mutex_lock(&eventfs_mutex); mutex_lock(&eventfs_mutex);
dentry = ei->dentry;
eventfs_remove_rec(ei, 0); eventfs_remove_rec(ei, 0);
mutex_unlock(&eventfs_mutex); mutex_unlock(&eventfs_mutex);
/*
* If any of the ei children has a dentry, then the ei itself
* must have a dentry.
*/
if (dentry)
simple_recursive_removal(dentry, NULL);
} }
/** /**
@ -1117,7 +846,11 @@ void eventfs_remove_events_dir(struct eventfs_inode *ei)
{ {
struct dentry *dentry; struct dentry *dentry;
dentry = ei->dentry; dentry = ei->events_dir;
if (!dentry)
return;
ei->events_dir = NULL;
eventfs_remove_dir(ei); eventfs_remove_dir(ei);
/* /*
@ -1127,5 +860,6 @@ void eventfs_remove_events_dir(struct eventfs_inode *ei)
* sticks around while the other ei->dentry are created * sticks around while the other ei->dentry are created
* and destroyed dynamically. * and destroyed dynamically.
*/ */
d_invalidate(dentry);
dput(dentry); dput(dentry);
} }

102
fs/tracefs/inode.c
View file

@ -38,8 +38,6 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb)
if (!ti) if (!ti)
return NULL; return NULL;
ti->flags = 0;
return &ti->vfs_inode; return &ti->vfs_inode;
} }
@ -379,21 +377,30 @@ static const struct super_operations tracefs_super_operations = {
.show_options = tracefs_show_options, .show_options = tracefs_show_options,
}; };
static void tracefs_dentry_iput(struct dentry *dentry, struct inode *inode) /*
* It would be cleaner if eventfs had its own dentry ops.
*
* Note that d_revalidate is called potentially under RCU,
* so it can't take the eventfs mutex etc. It's fine - if
* we open a file just as it's marked dead, things will
* still work just fine, and just see the old stale case.
*/
static void tracefs_d_release(struct dentry *dentry)
{ {
struct tracefs_inode *ti; if (dentry->d_fsdata)
eventfs_d_release(dentry);
}
if (!dentry || !inode) static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags)
return; {
struct eventfs_inode *ei = dentry->d_fsdata;
ti = get_tracefs(inode); return !(ei && ei->is_freed);
if (ti && ti->flags & TRACEFS_EVENT_INODE)
eventfs_set_ei_status_free(ti, dentry);
iput(inode);
} }
static const struct dentry_operations tracefs_dentry_operations = { static const struct dentry_operations tracefs_dentry_operations = {
.d_iput = tracefs_dentry_iput, .d_revalidate = tracefs_d_revalidate,
.d_release = tracefs_d_release,
}; };
static int trace_fill_super(struct super_block *sb, void *data, int silent) static int trace_fill_super(struct super_block *sb, void *data, int silent)
@ -497,75 +504,6 @@ struct dentry *tracefs_end_creating(struct dentry *dentry)
return dentry; return dentry;
} }
/**
* eventfs_start_creating - start the process of creating a dentry
* @name: Name of the file created for the dentry
* @parent: The parent dentry where this dentry will be created
*
* This is a simple helper function for the dynamically created eventfs
* files. When the directory of the eventfs files are accessed, their
* dentries are created on the fly. This function is used to start that
* process.
*/
struct dentry *eventfs_start_creating(const char *name, struct dentry *parent)
{
struct dentry *dentry;
int error;
/* Must always have a parent. */
if (WARN_ON_ONCE(!parent))
return ERR_PTR(-EINVAL);
error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
&tracefs_mount_count);
if (error)
return ERR_PTR(error);
if (unlikely(IS_DEADDIR(parent->d_inode)))
dentry = ERR_PTR(-ENOENT);
else
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))
simple_release_fs(&tracefs_mount, &tracefs_mount_count);
return dentry;
}
/**
* eventfs_failed_creating - clean up a failed eventfs dentry creation
* @dentry: The dentry to clean up
*
* If after calling eventfs_start_creating(), a failure is detected, the
* resources created by eventfs_start_creating() needs to be cleaned up. In
* that case, this function should be called to perform that clean up.
*/
struct dentry *eventfs_failed_creating(struct dentry *dentry)
{
dput(dentry);
simple_release_fs(&tracefs_mount, &tracefs_mount_count);
return NULL;
}
/**
* eventfs_end_creating - Finish the process of creating a eventfs dentry
* @dentry: The dentry that has successfully been created.
*
* This function is currently just a place holder to match
* eventfs_start_creating(). In case any synchronization needs to be added,
* this function will be used to implement that without having to modify
* the callers of eventfs_start_creating().
*/
struct dentry *eventfs_end_creating(struct dentry *dentry)
{
return dentry;
}
/* Find the inode that this will use for default */ /* Find the inode that this will use for default */
static struct inode *instance_inode(struct dentry *parent, struct inode *inode) static struct inode *instance_inode(struct dentry *parent, struct inode *inode)
{ {
@ -779,7 +717,11 @@ static void init_once(void *foo)
{ {
struct tracefs_inode *ti = (struct tracefs_inode *) foo; struct tracefs_inode *ti = (struct tracefs_inode *) foo;
/* inode_init_once() calls memset() on the vfs_inode portion */
inode_init_once(&ti->vfs_inode); inode_init_once(&ti->vfs_inode);
/* Zero out the rest */
memset_after(ti, 0, vfs_inode);
} }
static int __init tracefs_init(void) static int __init tracefs_init(void)

43
fs/tracefs/internal.h
View file

@ -11,9 +11,10 @@ enum {
}; };
struct tracefs_inode { struct tracefs_inode {
struct inode vfs_inode;
/* The below gets initialized with memset_after(ti, 0, vfs_inode) */
unsigned long flags; unsigned long flags;
void *private; void *private;
struct inode vfs_inode;
}; };
/* /*
@ -31,43 +32,37 @@ struct eventfs_attr {
/* /*
* struct eventfs_inode - hold the properties of the eventfs directories. * struct eventfs_inode - hold the properties of the eventfs directories.
* @list: link list into the parent directory * @list: link list into the parent directory
* @rcu: Union with @list for freeing
* @children: link list into the child eventfs_inode
* @entries: the array of entries representing the files in the directory * @entries: the array of entries representing the files in the directory
* @name: the name of the directory to create * @name: the name of the directory to create
* @children: link list into the child eventfs_inode * @events_dir: the dentry of the events directory
* @dentry: the dentry of the directory
* @d_parent: pointer to the parent's dentry
* @d_children: The array of dentries to represent the files when created
* @entry_attrs: Saved mode and ownership of the @d_children * @entry_attrs: Saved mode and ownership of the @d_children
* @attr: Saved mode and ownership of eventfs_inode itself
* @data: The private data to pass to the callbacks * @data: The private data to pass to the callbacks
* @attr: Saved mode and ownership of eventfs_inode itself
* @is_freed: Flag set if the eventfs is on its way to be freed * @is_freed: Flag set if the eventfs is on its way to be freed
* Note if is_freed is set, then dentry is corrupted. * Note if is_freed is set, then dentry is corrupted.
* @is_events: Flag set for only the top level "events" directory
* @nr_entries: The number of items in @entries * @nr_entries: The number of items in @entries
* @ino: The saved inode number
*/ */
struct eventfs_inode { struct eventfs_inode {
struct list_head list; union {
struct list_head list;
struct rcu_head rcu;
};
struct list_head children;
const struct eventfs_entry *entries; const struct eventfs_entry *entries;
const char *name; const char *name;
struct list_head children; struct dentry *events_dir;
struct dentry *dentry; /* Check is_freed to access */
struct dentry *d_parent;
struct dentry **d_children;
struct eventfs_attr *entry_attrs; struct eventfs_attr *entry_attrs;
struct eventfs_attr attr;
void *data; void *data;
struct eventfs_attr attr;
struct kref kref;
unsigned int is_freed:1; unsigned int is_freed:1;
unsigned int is_events:1; unsigned int is_events:1;
unsigned int nr_entries:30; unsigned int nr_entries:30;
unsigned int ino; unsigned int ino;
/*
* Union - used for deletion
* @llist: for calling dput() if needed after RCU
* @rcu: eventfs_inode to delete in RCU
*/
union {
struct llist_node llist;
struct rcu_head rcu;
};
}; };
static inline struct tracefs_inode *get_tracefs(const struct inode *inode) static inline struct tracefs_inode *get_tracefs(const struct inode *inode)
@ -79,9 +74,7 @@ struct dentry *tracefs_start_creating(const char *name, struct dentry *parent);
struct dentry *tracefs_end_creating(struct dentry *dentry); struct dentry *tracefs_end_creating(struct dentry *dentry);
struct dentry *tracefs_failed_creating(struct dentry *dentry); struct dentry *tracefs_failed_creating(struct dentry *dentry);
struct inode *tracefs_get_inode(struct super_block *sb); struct inode *tracefs_get_inode(struct super_block *sb);
struct dentry *eventfs_start_creating(const char *name, struct dentry *parent);
struct dentry *eventfs_failed_creating(struct dentry *dentry); void eventfs_d_release(struct dentry *dentry);
struct dentry *eventfs_end_creating(struct dentry *dentry);
void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry);
#endif /* _TRACEFS_INTERNAL_H */ #endif /* _TRACEFS_INTERNAL_H */

2
kernel/trace/ring_buffer.c
View file

@ -944,7 +944,7 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
full = 0; full = 0;
} else { } else {
if (!cpumask_test_cpu(cpu, buffer->cpumask)) if (!cpumask_test_cpu(cpu, buffer->cpumask))
return -EINVAL; return EPOLLERR;
cpu_buffer = buffer->buffers[cpu]; cpu_buffer = buffer->buffers[cpu];
work = &cpu_buffer->irq_work; work = &cpu_buffer->irq_work;

6
kernel/trace/trace_osnoise.c
View file

@ -2444,6 +2444,9 @@ static int timerlat_fd_open(struct inode *inode, struct file *file)
tlat = this_cpu_tmr_var(); tlat = this_cpu_tmr_var();
tlat->count = 0; tlat->count = 0;
hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
tlat->timer.function = timerlat_irq;
migrate_enable(); migrate_enable();
return 0; return 0;
}; };
@ -2526,9 +2529,6 @@ timerlat_fd_read(struct file *file, char __user *ubuf, size_t count,
tlat->tracing_thread = false; tlat->tracing_thread = false;
tlat->kthread = current; tlat->kthread = current;
hrtimer_init(&tlat->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
tlat->timer.function = timerlat_irq;
/* Annotate now to drift new period */ /* Annotate now to drift new period */
tlat->abs_period = hrtimer_cb_get_time(&tlat->timer); tlat->abs_period = hrtimer_cb_get_time(&tlat->timer);