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, 297 insertions, 0 deletions

diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
new file mode 100644
index 000000000..f797cc99f
--- /dev/null
+++ b/fs/lockd/clntlock.c
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/fs/lockd/clntlock.c
+ *
+ * Lock handling for the client side NLM implementation
+ *
+ * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+#include <linux/nfs_fs.h>
+#include <linux/sunrpc/addr.h>
+#include <linux/sunrpc/svc.h>
+#include <linux/sunrpc/svc_xprt.h>
+#include <linux/kthread.h>
+
+#include "lockd.h"
+#include "trace.h"
+
+#define NLMDBG_FACILITY		NLMDBG_CLIENT
+
+/*
+ * Local function prototypes
+ */
+static int			reclaimer(void *ptr);
+
+/*
+ * The following functions handle blocking and granting from the
+ * client perspective.
+ */
+
+static LIST_HEAD(nlm_blocked);
+static DEFINE_SPINLOCK(nlm_blocked_lock);
+
+/**
+ * nlmclnt_init - Set up per-NFS mount point lockd data structures
+ * @nlm_init: pointer to arguments structure
+ *
+ * Returns pointer to an appropriate nlm_host struct,
+ * or an ERR_PTR value.
+ */
+struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init)
+{
+	struct nlm_host *host;
+	u32 nlm_version = (nlm_init->nfs_version == 2) ? 1 : 4;
+	int status;
+
+	status = lockd_up(nlm_init->net, nlm_init->cred);
+	if (status < 0)
+		return ERR_PTR(status);
+
+	host = nlmclnt_lookup_host(nlm_init->address, nlm_init->addrlen,
+				   nlm_init->protocol, nlm_version,
+				   nlm_init->hostname, nlm_init->noresvport,
+				   nlm_init->net, nlm_init->cred);
+	if (host == NULL)
+		goto out_nohost;
+	if (host->h_rpcclnt == NULL && nlm_bind_host(host) == NULL)
+		goto out_nobind;
+
+	host->h_nlmclnt_ops = nlm_init->nlmclnt_ops;
+	return host;
+out_nobind:
+	nlmclnt_release_host(host);
+out_nohost:
+	lockd_down(nlm_init->net);
+	return ERR_PTR(-ENOLCK);
+}
+EXPORT_SYMBOL_GPL(nlmclnt_init);
+
+/**
+ * nlmclnt_done - Release resources allocated by nlmclnt_init()
+ * @host: nlm_host structure reserved by nlmclnt_init()
+ *
+ */
+void nlmclnt_done(struct nlm_host *host)
+{
+	struct net *net = host->net;
+
+	nlmclnt_release_host(host);
+	lockd_down(net);
+}
+EXPORT_SYMBOL_GPL(nlmclnt_done);
+
+void nlmclnt_prepare_block(struct nlm_wait *block, struct nlm_host *host, struct file_lock *fl)
+{
+	block->b_host = host;
+	block->b_lock = fl;
+	init_waitqueue_head(&block->b_wait);
+	block->b_status = nlm_lck_blocked;
+}
+
+struct rpc_clnt *nlmclnt_rpc_clnt(struct nlm_host *host)
+{
+	return host->h_rpcclnt;
+}
+EXPORT_SYMBOL_GPL(nlmclnt_rpc_clnt);
+
+/*
+ * Queue up a lock for blocking so that the GRANTED request can see it
+ */
+void nlmclnt_queue_block(struct nlm_wait *block)
+{
+	spin_lock(&nlm_blocked_lock);
+	list_add(&block->b_list, &nlm_blocked);
+	spin_unlock(&nlm_blocked_lock);
+}
+
+/*
+ * Dequeue the block and return its final status
+ */
+__be32 nlmclnt_dequeue_block(struct nlm_wait *block)
+{
+	__be32 status;
+
+	spin_lock(&nlm_blocked_lock);
+	list_del(&block->b_list);
+	status = block->b_status;
+	spin_unlock(&nlm_blocked_lock);
+	return status;
+}
+
+/*
+ * Block on a lock
+ */
+int nlmclnt_wait(struct nlm_wait *block, struct nlm_rqst *req, long timeout)
+{
+	long ret;
+
+	/* A borken server might ask us to block even if we didn't
+	 * request it. Just say no!
+	 */
+	if (block == NULL)
+		return -EAGAIN;
+
+	/* Go to sleep waiting for GRANT callback. Some servers seem
+	 * to lose callbacks, however, so we're going to poll from
+	 * time to time just to make sure.
+	 *
+	 * For now, the retry frequency is pretty high; normally 
+	 * a 1 minute timeout would do. See the comment before
+	 * nlmclnt_lock for an explanation.
+	 */
+	ret = wait_event_interruptible_timeout(block->b_wait,
+			block->b_status != nlm_lck_blocked,
+			timeout);
+	if (ret < 0)
+		return -ERESTARTSYS;
+	/* Reset the lock status after a server reboot so we resend */
+	if (block->b_status == nlm_lck_denied_grace_period)
+		block->b_status = nlm_lck_blocked;
+	return 0;
+}
+
+/*
+ * The server lockd has called us back to tell us the lock was granted
+ */
+__be32 nlmclnt_grant(const struct sockaddr *addr, const struct lockd_lock *lock)
+{
+	const struct file_lock *fl = &lock->fl;
+	const struct nfs_fh *fh = &lock->fh;
+	struct nlm_wait	*block;
+	__be32 res = nlm_lck_denied;
+
+	/*
+	 * Look up blocked request based on arguments. 
+	 * Warning: must not use cookie to match it!
+	 */
+	spin_lock(&nlm_blocked_lock);
+	list_for_each_entry(block, &nlm_blocked, b_list) {
+		struct file_lock *fl_blocked = block->b_lock;
+
+		if (fl_blocked->fl_start != fl->fl_start)
+			continue;
+		if (fl_blocked->fl_end != fl->fl_end)
+			continue;
+		/*
+		 * Careful! The NLM server will return the 32-bit "pid" that
+		 * we put on the wire: in this case the lockowner "pid".
+		 */
+		if (fl_blocked->fl_u.nfs_fl.owner->pid != lock->svid)
+			continue;
+		if (!rpc_cmp_addr(nlm_addr(block->b_host), addr))
+			continue;
+		if (nfs_compare_fh(NFS_FH(file_inode(fl_blocked->c.flc_file)), fh) != 0)
+			continue;
+		/* Alright, we found a lock. Set the return status
+		 * and wake up the caller
+		 */
+		block->b_status = nlm_granted;
+		wake_up(&block->b_wait);
+		res = nlm_granted;
+	}
+	spin_unlock(&nlm_blocked_lock);
+	trace_nlmclnt_grant(lock, addr, svc_addr_len(addr), res);
+	return res;
+}
+
+/*
+ * The following procedures deal with the recovery of locks after a
+ * server crash.
+ */
+
+/*
+ * Reclaim all locks on server host. We do this by spawning a separate
+ * reclaimer thread.
+ */
+void
+nlmclnt_recovery(struct nlm_host *host)
+{
+	struct task_struct *task;
+
+	if (!host->h_reclaiming++) {
+		nlm_get_host(host);
+		task = kthread_run(reclaimer, host, "%s-reclaim", host->h_name);
+		if (IS_ERR(task))
+			printk(KERN_ERR "lockd: unable to spawn reclaimer "
+				"thread. Locks for %s won't be reclaimed! "
+				"(%ld)\n", host->h_name, PTR_ERR(task));
+	}
+}
+
+static int
+reclaimer(void *ptr)
+{
+	struct nlm_host	  *host = (struct nlm_host *) ptr;
+	struct nlm_wait	  *block;
+	struct nlm_rqst   *req;
+	struct file_lock *fl, *next;
+	u32 nsmstate;
+	struct net *net = host->net;
+
+	req = kmalloc_obj(*req);
+	if (!req)
+		return 0;
+
+	allow_signal(SIGKILL);
+
+	down_write(&host->h_rwsem);
+	lockd_up(net, NULL);	/* note: this cannot fail as lockd is already running */
+
+	dprintk("lockd: reclaiming locks for host %s\n", host->h_name);
+
+restart:
+	nsmstate = host->h_nsmstate;
+
+	/* Force a portmap getport - the peer's lockd will
+	 * most likely end up on a different port.
+	 */
+	host->h_nextrebind = jiffies;
+	nlm_rebind_host(host);
+
+	/* First, reclaim all locks that have been granted. */
+	list_splice_init(&host->h_granted, &host->h_reclaim);
+	list_for_each_entry_safe(fl, next, &host->h_reclaim, fl_u.nfs_fl.list) {
+		list_del_init(&fl->fl_u.nfs_fl.list);
+
+		/*
+		 * sending this thread a SIGKILL will result in any unreclaimed
+		 * locks being removed from the h_granted list. This means that
+		 * the kernel will not attempt to reclaim them again if a new
+		 * reclaimer thread is spawned for this host.
+		 */
+		if (signalled())
+			continue;
+		if (nlmclnt_reclaim(host, fl, req) != 0)
+			continue;
+		list_add_tail(&fl->fl_u.nfs_fl.list, &host->h_granted);
+		if (host->h_nsmstate != nsmstate) {
+			/* Argh! The server rebooted again! */
+			goto restart;
+		}
+	}
+
+	host->h_reclaiming = 0;
+	up_write(&host->h_rwsem);
+	dprintk("NLM: done reclaiming locks for host %s\n", host->h_name);
+
+	/* Now, wake up all processes that sleep on a blocked lock */
+	spin_lock(&nlm_blocked_lock);
+	list_for_each_entry(block, &nlm_blocked, b_list) {
+		if (block->b_host == host) {
+			block->b_status = nlm_lck_denied_grace_period;
+			wake_up(&block->b_wait);
+		}
+	}
+	spin_unlock(&nlm_blocked_lock);
+
+	/* Release host handle after use */
+	nlmclnt_release_host(host);
+	lockd_down(net);
+	kfree(req);
+	return 0;
+}