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, 506 insertions, 0 deletions

diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c
new file mode 100644
index 000000000..f7ab66e70
--- /dev/null
+++ b/fs/ocfs2/cluster/netdebug.c
@@ -0,0 +1,506 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * netdebug.c
+ *
+ * debug functionality for o2net
+ *
+ * Copyright (C) 2005, 2008 Oracle.  All rights reserved.
+ */
+
+#ifdef CONFIG_DEBUG_FS
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/idr.h>
+#include <linux/kref.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+
+#include <linux/uaccess.h>
+
+#include "tcp.h"
+#include "nodemanager.h"
+#define MLOG_MASK_PREFIX ML_TCP
+#include "masklog.h"
+
+#include "tcp_internal.h"
+
+#define O2NET_DEBUG_DIR		"o2net"
+#define SC_DEBUG_NAME		"sock_containers"
+#define NST_DEBUG_NAME		"send_tracking"
+#define STATS_DEBUG_NAME	"stats"
+#define NODES_DEBUG_NAME	"connected_nodes"
+
+#define SHOW_SOCK_CONTAINERS	0
+#define SHOW_SOCK_STATS		1
+
+static struct dentry *o2net_dentry;
+
+static DEFINE_SPINLOCK(o2net_debug_lock);
+
+static LIST_HEAD(sock_containers);
+static LIST_HEAD(send_tracking);
+
+void o2net_debug_add_nst(struct o2net_send_tracking *nst)
+{
+	spin_lock_bh(&o2net_debug_lock);
+	list_add(&nst->st_net_debug_item, &send_tracking);
+	spin_unlock_bh(&o2net_debug_lock);
+}
+
+void o2net_debug_del_nst(struct o2net_send_tracking *nst)
+{
+	spin_lock_bh(&o2net_debug_lock);
+	if (!list_empty(&nst->st_net_debug_item))
+		list_del_init(&nst->st_net_debug_item);
+	spin_unlock_bh(&o2net_debug_lock);
+}
+
+static struct o2net_send_tracking
+			*next_nst(struct o2net_send_tracking *nst_start)
+{
+	struct o2net_send_tracking *nst, *ret = NULL;
+
+	assert_spin_locked(&o2net_debug_lock);
+
+	list_for_each_entry(nst, &nst_start->st_net_debug_item,
+			    st_net_debug_item) {
+		/* discover the head of the list */
+		if (&nst->st_net_debug_item == &send_tracking)
+			break;
+
+		/* use st_task to detect real nsts in the list */
+		if (nst->st_task != NULL) {
+			ret = nst;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static void *nst_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct o2net_send_tracking *nst, *dummy_nst = seq->private;
+
+	spin_lock_bh(&o2net_debug_lock);
+	nst = next_nst(dummy_nst);
+	spin_unlock_bh(&o2net_debug_lock);
+
+	return nst;
+}
+
+static void *nst_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct o2net_send_tracking *nst, *dummy_nst = seq->private;
+
+	spin_lock_bh(&o2net_debug_lock);
+	nst = next_nst(dummy_nst);
+	list_del_init(&dummy_nst->st_net_debug_item);
+	if (nst)
+		list_add(&dummy_nst->st_net_debug_item,
+			 &nst->st_net_debug_item);
+	spin_unlock_bh(&o2net_debug_lock);
+
+	return nst; /* unused, just needs to be null when done */
+}
+
+static int nst_seq_show(struct seq_file *seq, void *v)
+{
+	struct o2net_send_tracking *nst, *dummy_nst = seq->private;
+	ktime_t now;
+	s64 sock, send, status;
+
+	spin_lock_bh(&o2net_debug_lock);
+	nst = next_nst(dummy_nst);
+	if (!nst)
+		goto out;
+
+	now = ktime_get();
+	sock = ktime_to_us(ktime_sub(now, nst->st_sock_time));
+	send = ktime_to_us(ktime_sub(now, nst->st_send_time));
+	status = ktime_to_us(ktime_sub(now, nst->st_status_time));
+
+	/* get_task_comm isn't exported.  oh well. */
+	seq_printf(seq, "%p:\n"
+		   "  pid:          %lu\n"
+		   "  tgid:         %lu\n"
+		   "  process name: %s\n"
+		   "  node:         %u\n"
+		   "  sc:           %p\n"
+		   "  message id:   %d\n"
+		   "  message type: %u\n"
+		   "  message key:  0x%08x\n"
+		   "  sock acquiry: %lld usecs ago\n"
+		   "  send start:   %lld usecs ago\n"
+		   "  wait start:   %lld usecs ago\n",
+		   nst, (unsigned long)task_pid_nr(nst->st_task),
+		   (unsigned long)nst->st_task->tgid,
+		   nst->st_task->comm, nst->st_node,
+		   nst->st_sc, nst->st_id, nst->st_msg_type,
+		   nst->st_msg_key,
+		   (long long)sock,
+		   (long long)send,
+		   (long long)status);
+
+out:
+	spin_unlock_bh(&o2net_debug_lock);
+
+	return 0;
+}
+
+static void nst_seq_stop(struct seq_file *seq, void *v)
+{
+}
+
+static const struct seq_operations nst_seq_ops = {
+	.start = nst_seq_start,
+	.next = nst_seq_next,
+	.stop = nst_seq_stop,
+	.show = nst_seq_show,
+};
+
+static int nst_fop_open(struct inode *inode, struct file *file)
+{
+	struct o2net_send_tracking *dummy_nst;
+
+	dummy_nst = __seq_open_private(file, &nst_seq_ops, sizeof(*dummy_nst));
+	if (!dummy_nst)
+		return -ENOMEM;
+	o2net_debug_add_nst(dummy_nst);
+
+	return 0;
+}
+
+static int nst_fop_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct o2net_send_tracking *dummy_nst = seq->private;
+
+	o2net_debug_del_nst(dummy_nst);
+	return seq_release_private(inode, file);
+}
+
+static const struct file_operations nst_seq_fops = {
+	.open = nst_fop_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = nst_fop_release,
+};
+
+void o2net_debug_add_sc(struct o2net_sock_container *sc)
+{
+	spin_lock_bh(&o2net_debug_lock);
+	list_add(&sc->sc_net_debug_item, &sock_containers);
+	spin_unlock_bh(&o2net_debug_lock);
+}
+
+void o2net_debug_del_sc(struct o2net_sock_container *sc)
+{
+	spin_lock_bh(&o2net_debug_lock);
+	list_del_init(&sc->sc_net_debug_item);
+	spin_unlock_bh(&o2net_debug_lock);
+}
+
+struct o2net_sock_debug {
+	int dbg_ctxt;
+	struct o2net_sock_container *dbg_sock;
+};
+
+static struct o2net_sock_container
+			*next_sc(struct o2net_sock_container *sc_start)
+{
+	struct o2net_sock_container *sc, *ret = NULL;
+
+	assert_spin_locked(&o2net_debug_lock);
+
+	list_for_each_entry(sc, &sc_start->sc_net_debug_item,
+			    sc_net_debug_item) {
+		/* discover the head of the list miscast as a sc */
+		if (&sc->sc_net_debug_item == &sock_containers)
+			break;
+
+		/* use sc_page to detect real scs in the list */
+		if (sc->sc_page != NULL) {
+			ret = sc;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static void *sc_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct o2net_sock_debug *sd = seq->private;
+	struct o2net_sock_container *sc, *dummy_sc = sd->dbg_sock;
+
+	spin_lock_bh(&o2net_debug_lock);
+	sc = next_sc(dummy_sc);
+	spin_unlock_bh(&o2net_debug_lock);
+
+	return sc;
+}
+
+static void *sc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct o2net_sock_debug *sd = seq->private;
+	struct o2net_sock_container *sc, *dummy_sc = sd->dbg_sock;
+
+	spin_lock_bh(&o2net_debug_lock);
+	sc = next_sc(dummy_sc);
+	list_del_init(&dummy_sc->sc_net_debug_item);
+	if (sc)
+		list_add(&dummy_sc->sc_net_debug_item, &sc->sc_net_debug_item);
+	spin_unlock_bh(&o2net_debug_lock);
+
+	return sc; /* unused, just needs to be null when done */
+}
+
+#ifdef CONFIG_OCFS2_FS_STATS
+# define sc_send_count(_s)		((_s)->sc_send_count)
+# define sc_recv_count(_s)		((_s)->sc_recv_count)
+# define sc_tv_acquiry_total_ns(_s)	(ktime_to_ns((_s)->sc_tv_acquiry_total))
+# define sc_tv_send_total_ns(_s)	(ktime_to_ns((_s)->sc_tv_send_total))
+# define sc_tv_status_total_ns(_s)	(ktime_to_ns((_s)->sc_tv_status_total))
+# define sc_tv_process_total_ns(_s)	(ktime_to_ns((_s)->sc_tv_process_total))
+#else
+# define sc_send_count(_s)		(0U)
+# define sc_recv_count(_s)		(0U)
+# define sc_tv_acquiry_total_ns(_s)	(0LL)
+# define sc_tv_send_total_ns(_s)	(0LL)
+# define sc_tv_status_total_ns(_s)	(0LL)
+# define sc_tv_process_total_ns(_s)	(0LL)
+#endif
+
+/* So that debugfs.ocfs2 can determine which format is being used */
+#define O2NET_STATS_STR_VERSION		1
+static void sc_show_sock_stats(struct seq_file *seq,
+			       struct o2net_sock_container *sc)
+{
+	if (!sc)
+		return;
+
+	seq_printf(seq, "%d,%u,%lu,%lld,%lld,%lld,%lu,%lld\n", O2NET_STATS_STR_VERSION,
+		   sc->sc_node->nd_num, (unsigned long)sc_send_count(sc),
+		   (long long)sc_tv_acquiry_total_ns(sc),
+		   (long long)sc_tv_send_total_ns(sc),
+		   (long long)sc_tv_status_total_ns(sc),
+		   (unsigned long)sc_recv_count(sc),
+		   (long long)sc_tv_process_total_ns(sc));
+}
+
+static void sc_show_sock_container(struct seq_file *seq,
+				   struct o2net_sock_container *sc)
+{
+	struct inet_sock *inet = NULL;
+	__be32 saddr = 0, daddr = 0;
+	__be16 sport = 0, dport = 0;
+
+	if (!sc)
+		return;
+
+	if (sc->sc_sock) {
+		inet = inet_sk(sc->sc_sock->sk);
+		/* the stack's structs aren't sparse endian clean */
+		saddr = (__force __be32)inet->inet_saddr;
+		daddr = (__force __be32)inet->inet_daddr;
+		sport = (__force __be16)inet->inet_sport;
+		dport = (__force __be16)inet->inet_dport;
+	}
+
+	/* XXX sigh, inet-> doesn't have sparse annotation so any
+	 * use of it here generates a warning with -Wbitwise */
+	seq_printf(seq, "%p:\n"
+		   "  krefs:           %d\n"
+		   "  sock:            %pI4:%u -> "
+				      "%pI4:%u\n"
+		   "  remote node:     %s\n"
+		   "  page off:        %zu\n"
+		   "  handshake ok:    %u\n"
+		   "  timer:           %lld usecs\n"
+		   "  data ready:      %lld usecs\n"
+		   "  advance start:   %lld usecs\n"
+		   "  advance stop:    %lld usecs\n"
+		   "  func start:      %lld usecs\n"
+		   "  func stop:       %lld usecs\n"
+		   "  func key:        0x%08x\n"
+		   "  func type:       %u\n",
+		   sc,
+		   kref_read(&sc->sc_kref),
+		   &saddr, inet ? ntohs(sport) : 0,
+		   &daddr, inet ? ntohs(dport) : 0,
+		   sc->sc_node->nd_name,
+		   sc->sc_page_off,
+		   sc->sc_handshake_ok,
+		   (long long)ktime_to_us(sc->sc_tv_timer),
+		   (long long)ktime_to_us(sc->sc_tv_data_ready),
+		   (long long)ktime_to_us(sc->sc_tv_advance_start),
+		   (long long)ktime_to_us(sc->sc_tv_advance_stop),
+		   (long long)ktime_to_us(sc->sc_tv_func_start),
+		   (long long)ktime_to_us(sc->sc_tv_func_stop),
+		   sc->sc_msg_key,
+		   sc->sc_msg_type);
+}
+
+static int sc_seq_show(struct seq_file *seq, void *v)
+{
+	struct o2net_sock_debug *sd = seq->private;
+	struct o2net_sock_container *sc, *dummy_sc = sd->dbg_sock;
+
+	spin_lock_bh(&o2net_debug_lock);
+	sc = next_sc(dummy_sc);
+
+	if (sc) {
+		if (sd->dbg_ctxt == SHOW_SOCK_CONTAINERS)
+			sc_show_sock_container(seq, sc);
+		else
+			sc_show_sock_stats(seq, sc);
+	}
+
+	spin_unlock_bh(&o2net_debug_lock);
+
+	return 0;
+}
+
+static void sc_seq_stop(struct seq_file *seq, void *v)
+{
+}
+
+static const struct seq_operations sc_seq_ops = {
+	.start = sc_seq_start,
+	.next = sc_seq_next,
+	.stop = sc_seq_stop,
+	.show = sc_seq_show,
+};
+
+static int sc_common_open(struct file *file, int ctxt)
+{
+	struct o2net_sock_debug *sd;
+	struct o2net_sock_container *dummy_sc;
+
+	dummy_sc = kzalloc_obj(*dummy_sc);
+	if (!dummy_sc)
+		return -ENOMEM;
+
+	sd = __seq_open_private(file, &sc_seq_ops, sizeof(*sd));
+	if (!sd) {
+		kfree(dummy_sc);
+		return -ENOMEM;
+	}
+
+	sd->dbg_ctxt = ctxt;
+	sd->dbg_sock = dummy_sc;
+
+	o2net_debug_add_sc(dummy_sc);
+
+	return 0;
+}
+
+static int sc_fop_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct o2net_sock_debug *sd = seq->private;
+	struct o2net_sock_container *dummy_sc = sd->dbg_sock;
+
+	o2net_debug_del_sc(dummy_sc);
+	kfree(dummy_sc);
+	return seq_release_private(inode, file);
+}
+
+static int stats_fop_open(struct inode *inode, struct file *file)
+{
+	return sc_common_open(file, SHOW_SOCK_STATS);
+}
+
+static const struct file_operations stats_seq_fops = {
+	.open = stats_fop_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = sc_fop_release,
+};
+
+static int sc_fop_open(struct inode *inode, struct file *file)
+{
+	return sc_common_open(file, SHOW_SOCK_CONTAINERS);
+}
+
+static const struct file_operations sc_seq_fops = {
+	.open = sc_fop_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = sc_fop_release,
+};
+
+static int o2net_fill_bitmap(char *buf, int len)
+{
+	unsigned long map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	int i = -1, out = 0;
+
+	o2net_fill_node_map(map, O2NM_MAX_NODES);
+
+	while ((i = find_next_bit(map, O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES)
+		out += scnprintf(buf + out, PAGE_SIZE - out, "%d ", i);
+	out += scnprintf(buf + out, PAGE_SIZE - out, "\n");
+
+	return out;
+}
+
+static int nodes_fop_open(struct inode *inode, struct file *file)
+{
+	char *buf;
+
+	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	i_size_write(inode, o2net_fill_bitmap(buf, PAGE_SIZE));
+
+	file->private_data = buf;
+
+	return 0;
+}
+
+static int o2net_debug_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static ssize_t o2net_debug_read(struct file *file, char __user *buf,
+				size_t nbytes, loff_t *ppos)
+{
+	return simple_read_from_buffer(buf, nbytes, ppos, file->private_data,
+				       i_size_read(file->f_mapping->host));
+}
+
+static const struct file_operations nodes_fops = {
+	.open		= nodes_fop_open,
+	.release	= o2net_debug_release,
+	.read		= o2net_debug_read,
+	.llseek		= generic_file_llseek,
+};
+
+void o2net_debugfs_exit(void)
+{
+	debugfs_remove_recursive(o2net_dentry);
+}
+
+void o2net_debugfs_init(void)
+{
+	umode_t mode = S_IFREG|S_IRUSR;
+
+	o2net_dentry = debugfs_create_dir(O2NET_DEBUG_DIR, NULL);
+
+	debugfs_create_file(NST_DEBUG_NAME, mode, o2net_dentry, NULL,
+			    &nst_seq_fops);
+	debugfs_create_file(SC_DEBUG_NAME, mode, o2net_dentry, NULL,
+			    &sc_seq_fops);
+	debugfs_create_file(STATS_DEBUG_NAME, mode, o2net_dentry, NULL,
+			    &stats_seq_fops);
+	debugfs_create_file(NODES_DEBUG_NAME, mode, o2net_dentry, NULL,
+			    &nodes_fops);
+}
+
+#endif	/* CONFIG_DEBUG_FS */