Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 316 insertions, 0 deletions

diff --git a/fs/9p/fid.c b/fs/9p/fid.c
new file mode 100644
index 000000000..76242d450
--- /dev/null
+++ b/fs/9p/fid.c
@@ -0,0 +1,316 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * V9FS FID Management
+ *
+ *  Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2005, 2006 by Eric Van Hensbergen <ericvh@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+static inline void __add_fid(struct dentry *dentry, struct p9_fid *fid)
+{
+	struct v9fs_dentry *v9fs_dentry = to_v9fs_dentry(dentry);
+
+	hlist_add_head(&fid->dlist, &v9fs_dentry->head);
+}
+
+
+/**
+ * v9fs_fid_add - add a fid to a dentry
+ * @dentry: dentry that the fid is being added to
+ * @pfid: fid to add, NULLed out
+ *
+ */
+void v9fs_fid_add(struct dentry *dentry, struct p9_fid **pfid)
+{
+	struct p9_fid *fid = *pfid;
+
+	spin_lock(&dentry->d_lock);
+	__add_fid(dentry, fid);
+	spin_unlock(&dentry->d_lock);
+
+	*pfid = NULL;
+}
+
+static bool v9fs_is_writeable(int mode)
+{
+	if (mode & (P9_OWRITE|P9_ORDWR))
+		return true;
+	else
+		return false;
+}
+
+/**
+ * v9fs_fid_find_inode - search for an open fid off of the inode list
+ * @inode: return a fid pointing to a specific inode
+ * @want_writeable: only consider fids which are writeable
+ * @uid: return a fid belonging to the specified user
+ * @any: ignore uid as a selection criteria
+ *
+ */
+struct p9_fid *v9fs_fid_find_inode(struct inode *inode, bool want_writeable,
+	kuid_t uid, bool any)
+{
+	struct hlist_head *h;
+	struct p9_fid *fid, *ret = NULL;
+
+	p9_debug(P9_DEBUG_VFS, " inode: %p\n", inode);
+
+	spin_lock(&inode->i_lock);
+	h = (struct hlist_head *)&inode->i_private;
+	hlist_for_each_entry(fid, h, ilist) {
+		if (any || uid_eq(fid->uid, uid)) {
+			if (want_writeable && !v9fs_is_writeable(fid->mode)) {
+				p9_debug(P9_DEBUG_VFS, " mode: %x not writeable?\n",
+							fid->mode);
+				continue;
+			}
+			p9_fid_get(fid);
+			ret = fid;
+			break;
+		}
+	}
+	spin_unlock(&inode->i_lock);
+	return ret;
+}
+
+/**
+ * v9fs_open_fid_add - add an open fid to an inode
+ * @inode: inode that the fid is being added to
+ * @pfid: fid to add, NULLed out
+ *
+ */
+
+void v9fs_open_fid_add(struct inode *inode, struct p9_fid **pfid)
+{
+	struct p9_fid *fid = *pfid;
+
+	spin_lock(&inode->i_lock);
+	hlist_add_head(&fid->ilist, (struct hlist_head *)&inode->i_private);
+	spin_unlock(&inode->i_lock);
+
+	*pfid = NULL;
+}
+
+
+/**
+ * v9fs_fid_find - retrieve a fid that belongs to the specified uid
+ * @dentry: dentry to look for fid in
+ * @uid: return fid that belongs to the specified user
+ * @any: if non-zero, return any fid associated with the dentry
+ *
+ */
+
+static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
+{
+	struct v9fs_dentry *v9fs_dentry = to_v9fs_dentry(dentry);
+	struct p9_fid *fid, *ret;
+
+	p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p) uid %d any %d\n",
+		 dentry, dentry, from_kuid(&init_user_ns, uid),
+		 any);
+	ret = NULL;
+	/* we'll recheck under lock if there's anything to look in */
+	if (!hlist_empty(&v9fs_dentry->head)) {
+		spin_lock(&dentry->d_lock);
+		hlist_for_each_entry(fid, &v9fs_dentry->head, dlist) {
+			if (any || uid_eq(fid->uid, uid)) {
+				ret = fid;
+				p9_fid_get(ret);
+				break;
+			}
+		}
+		spin_unlock(&dentry->d_lock);
+	}
+	if (!ret && dentry->d_inode)
+		ret = v9fs_fid_find_inode(dentry->d_inode, false, uid, any);
+
+	return ret;
+}
+
+/*
+ * We need to hold v9ses->rename_sem as long as we hold references
+ * to returned path array. Array element contain pointers to
+ * dentry names.
+ */
+static int build_path_from_dentry(struct v9fs_session_info *v9ses,
+				  struct dentry *dentry, const unsigned char ***names)
+{
+	int n = 0, i;
+	const unsigned char **wnames;
+	struct dentry *ds;
+
+	for (ds = dentry; !IS_ROOT(ds); ds = ds->d_parent)
+		n++;
+
+	wnames = kmalloc_array(n, sizeof(char *), GFP_KERNEL);
+	if (!wnames)
+		goto err_out;
+
+	for (ds = dentry, i = (n-1); i >= 0; i--, ds = ds->d_parent)
+		wnames[i] = ds->d_name.name;
+
+	*names = wnames;
+	return n;
+err_out:
+	return -ENOMEM;
+}
+
+static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
+					       kuid_t uid, int any)
+{
+	struct dentry *ds;
+	const unsigned char **wnames, *uname;
+	int i, n, l, access;
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid, *root_fid, *old_fid;
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	access = v9ses->flags & V9FS_ACCESS_MASK;
+	fid = v9fs_fid_find(dentry, uid, any);
+	if (fid)
+		return fid;
+	/*
+	 * we don't have a matching fid. To do a TWALK we need
+	 * parent fid. We need to prevent rename when we want to
+	 * look at the parent.
+	 */
+	down_read(&v9ses->rename_sem);
+	ds = dentry->d_parent;
+	fid = v9fs_fid_find(ds, uid, any);
+	if (fid) {
+		/* Found the parent fid do a lookup with that */
+		old_fid = fid;
+
+		fid = p9_client_walk(old_fid, 1, &dentry->d_name.name, 1);
+		p9_fid_put(old_fid);
+		goto fid_out;
+	}
+	up_read(&v9ses->rename_sem);
+
+	/* start from the root and try to do a lookup */
+	root_fid = v9fs_fid_find(dentry->d_sb->s_root, uid, any);
+	if (!root_fid) {
+		/* the user is not attached to the fs yet */
+		if (access == V9FS_ACCESS_SINGLE)
+			return ERR_PTR(-EPERM);
+
+		if (v9fs_proto_dotu(v9ses) || v9fs_proto_dotl(v9ses))
+			uname = NULL;
+		else
+			uname = v9ses->uname;
+
+		fid = p9_client_attach(v9ses->clnt, NULL, uname, uid,
+				       v9ses->aname);
+		if (IS_ERR(fid))
+			return fid;
+
+		root_fid = p9_fid_get(fid);
+		v9fs_fid_add(dentry->d_sb->s_root, &fid);
+	}
+	/* If we are root ourself just return that */
+	if (dentry->d_sb->s_root == dentry)
+		return root_fid;
+
+	/*
+	 * Do a multipath walk with attached root.
+	 * When walking parent we need to make sure we
+	 * don't have a parallel rename happening
+	 */
+	down_read(&v9ses->rename_sem);
+	n  = build_path_from_dentry(v9ses, dentry, &wnames);
+	if (n < 0) {
+		fid = ERR_PTR(n);
+		goto err_out;
+	}
+	fid = root_fid;
+	old_fid = root_fid;
+	i = 0;
+	while (i < n) {
+		l = min(n - i, P9_MAXWELEM);
+		/*
+		 * We need to hold rename lock when doing a multipath
+		 * walk to ensure none of the path components change
+		 */
+		fid = p9_client_walk(old_fid, l, &wnames[i],
+				     old_fid == root_fid /* clone */);
+		/* non-cloning walk will return the same fid */
+		if (fid != old_fid) {
+			p9_fid_put(old_fid);
+			old_fid = fid;
+		}
+		if (IS_ERR(fid)) {
+			kfree(wnames);
+			goto err_out;
+		}
+		i += l;
+	}
+	kfree(wnames);
+fid_out:
+	if (!IS_ERR(fid)) {
+		spin_lock(&dentry->d_lock);
+		if (d_unhashed(dentry)) {
+			spin_unlock(&dentry->d_lock);
+			p9_fid_put(fid);
+			fid = ERR_PTR(-ENOENT);
+		} else {
+			__add_fid(dentry, fid);
+			p9_fid_get(fid);
+			spin_unlock(&dentry->d_lock);
+		}
+	}
+err_out:
+	up_read(&v9ses->rename_sem);
+	return fid;
+}
+
+/**
+ * v9fs_fid_lookup - lookup for a fid, try to walk if not found
+ * @dentry: dentry to look for fid in
+ *
+ * Look for a fid in the specified dentry for the current user.
+ * If no fid is found, try to create one walking from a fid from the parent
+ * dentry (if it has one), or the root dentry. If the user haven't accessed
+ * the fs yet, attach now and walk from the root.
+ */
+
+struct p9_fid *v9fs_fid_lookup(struct dentry *dentry)
+{
+	kuid_t uid;
+	int  any, access;
+	struct v9fs_session_info *v9ses;
+
+	v9ses = v9fs_dentry2v9ses(dentry);
+	access = v9ses->flags & V9FS_ACCESS_MASK;
+	switch (access) {
+	case V9FS_ACCESS_SINGLE:
+	case V9FS_ACCESS_USER:
+	case V9FS_ACCESS_CLIENT:
+		uid = current_fsuid();
+		any = 0;
+		break;
+
+	case V9FS_ACCESS_ANY:
+		uid = v9ses->uid;
+		any = 1;
+		break;
+
+	default:
+		uid = INVALID_UID;
+		any = 0;
+		break;
+	}
+	return v9fs_fid_lookup_with_uid(dentry, uid, any);
+}
+