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, 474 insertions, 0 deletions

diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c
new file mode 100644
index 000000000..3a197252a
--- /dev/null
+++ b/fs/nfs/sysfs.c
@@ -0,0 +1,474 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 Hammerspace Inc
+ */
+
+#include <linux/module.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/netdevice.h>
+#include <linux/string.h>
+#include <linux/nfs_fs.h>
+#include <net/net_namespace.h>
+#include <linux/rcupdate.h>
+#include <linux/lockd/bind.h>
+
+#include "internal.h"
+#include "nfs4_fs.h"
+#include "netns.h"
+#include "sysfs.h"
+
+static struct kset *nfs_kset;
+
+static void nfs_kset_release(struct kobject *kobj)
+{
+	struct kset *kset = container_of(kobj, struct kset, kobj);
+	kfree(kset);
+}
+
+static const struct kobj_ns_type_operations *nfs_netns_object_child_ns_type(
+		const struct kobject *kobj)
+{
+	return &net_ns_type_operations;
+}
+
+static struct kobj_type nfs_kset_type = {
+	.release = nfs_kset_release,
+	.sysfs_ops = &kobj_sysfs_ops,
+	.child_ns_type = nfs_netns_object_child_ns_type,
+};
+
+int nfs_sysfs_init(void)
+{
+	int ret;
+
+	nfs_kset = kzalloc_obj(*nfs_kset);
+	if (!nfs_kset)
+		return -ENOMEM;
+
+	ret = kobject_set_name(&nfs_kset->kobj, "nfs");
+	if (ret) {
+		kfree(nfs_kset);
+		return ret;
+	}
+
+	nfs_kset->kobj.parent = fs_kobj;
+	nfs_kset->kobj.ktype = &nfs_kset_type;
+	nfs_kset->kobj.kset = NULL;
+
+	ret = kset_register(nfs_kset);
+	if (ret) {
+		kfree(nfs_kset);
+		return ret;
+	}
+
+	return 0;
+}
+
+void nfs_sysfs_exit(void)
+{
+	kset_unregister(nfs_kset);
+}
+
+static ssize_t nfs_netns_identifier_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	struct nfs_netns_client *c = container_of(kobj,
+			struct nfs_netns_client,
+			kobject);
+	ssize_t ret;
+
+	rcu_read_lock();
+	ret = sysfs_emit(buf, "%s\n", rcu_dereference(c->identifier));
+	rcu_read_unlock();
+	return ret;
+}
+
+/* Strip trailing '\n' */
+static size_t nfs_string_strip(const char *c, size_t len)
+{
+	while (len > 0 && c[len-1] == '\n')
+		--len;
+	return len;
+}
+
+static ssize_t nfs_netns_identifier_store(struct kobject *kobj,
+		struct kobj_attribute *attr,
+		const char *buf, size_t count)
+{
+	struct nfs_netns_client *c = container_of(kobj,
+			struct nfs_netns_client,
+			kobject);
+	const char *old;
+	char *p;
+	size_t len;
+
+	len = nfs_string_strip(buf, min_t(size_t, count, CONTAINER_ID_MAXLEN));
+	if (!len)
+		return 0;
+	p = kmemdup_nul(buf, len, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+	old = rcu_dereference_protected(xchg(&c->identifier, (char __rcu *)p), 1);
+	if (old) {
+		synchronize_rcu();
+		kfree(old);
+	}
+	return count;
+}
+
+static void nfs_netns_client_release(struct kobject *kobj)
+{
+	struct nfs_netns_client *c = container_of(kobj,
+			struct nfs_netns_client,
+			kobject);
+
+	kfree(rcu_dereference_raw(c->identifier));
+}
+
+static const struct ns_common *nfs_netns_client_namespace(const struct kobject *kobj)
+{
+	return to_ns_common(container_of(kobj, struct nfs_netns_client,
+					 kobject)->net);
+}
+
+static struct kobj_attribute nfs_netns_client_id = __ATTR(identifier,
+		0644, nfs_netns_identifier_show, nfs_netns_identifier_store);
+
+static struct attribute *nfs_netns_client_attrs[] = {
+	&nfs_netns_client_id.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(nfs_netns_client);
+
+static struct kobj_type nfs_netns_client_type = {
+	.release = nfs_netns_client_release,
+	.default_groups = nfs_netns_client_groups,
+	.sysfs_ops = &kobj_sysfs_ops,
+	.namespace = nfs_netns_client_namespace,
+};
+
+static void nfs_netns_object_release(struct kobject *kobj)
+{
+	struct nfs_netns_client *c = container_of(kobj,
+			struct nfs_netns_client,
+			nfs_net_kobj);
+	kfree(c);
+}
+
+static const struct ns_common *nfs_netns_namespace(const struct kobject *kobj)
+{
+	return to_ns_common(container_of(kobj, struct nfs_netns_client,
+					 nfs_net_kobj)->net);
+}
+
+static struct kobj_type nfs_netns_object_type = {
+	.release = nfs_netns_object_release,
+	.sysfs_ops = &kobj_sysfs_ops,
+	.namespace =  nfs_netns_namespace,
+};
+
+static struct nfs_netns_client *nfs_netns_client_alloc(struct kobject *parent,
+		struct net *net)
+{
+	struct nfs_netns_client *p;
+
+	p = kzalloc_obj(*p);
+	if (p) {
+		p->net = net;
+		p->kobject.kset = nfs_kset;
+		p->nfs_net_kobj.kset = nfs_kset;
+
+		if (kobject_init_and_add(&p->nfs_net_kobj, &nfs_netns_object_type,
+					parent, "net") != 0) {
+			kobject_put(&p->nfs_net_kobj);
+			return NULL;
+		}
+
+		if (kobject_init_and_add(&p->kobject, &nfs_netns_client_type,
+					&p->nfs_net_kobj, "nfs_client") == 0)
+			return p;
+
+		kobject_put(&p->kobject);
+		kobject_put(&p->nfs_net_kobj);
+	}
+	return NULL;
+}
+
+void nfs_netns_sysfs_setup(struct nfs_net *netns, struct net *net)
+{
+	struct nfs_netns_client *clp;
+
+	clp = nfs_netns_client_alloc(&nfs_kset->kobj, net);
+	if (clp) {
+		netns->nfs_client = clp;
+		kobject_uevent(&clp->kobject, KOBJ_ADD);
+	}
+}
+
+void nfs_netns_sysfs_destroy(struct nfs_net *netns)
+{
+	struct nfs_netns_client *clp = netns->nfs_client;
+
+	if (clp) {
+		kobject_uevent(&clp->kobject, KOBJ_REMOVE);
+		kobject_del(&clp->kobject);
+		kobject_put(&clp->kobject);
+		kobject_del(&clp->nfs_net_kobj);
+		kobject_put(&clp->nfs_net_kobj);
+		netns->nfs_client = NULL;
+	}
+}
+
+static bool shutdown_match_client(const struct rpc_task *task, const void *data)
+{
+	return true;
+}
+
+static void shutdown_client(struct rpc_clnt *clnt)
+{
+	clnt->cl_shutdown = 1;
+	rpc_cancel_tasks(clnt, -EIO, shutdown_match_client, NULL);
+}
+
+/*
+ * Shut down the nfs_client only once all the superblocks
+ * have been shut down.
+ */
+static void shutdown_nfs_client(struct nfs_client *clp)
+{
+	struct nfs_server *server;
+	rcu_read_lock();
+	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+		if (!(server->flags & NFS_MOUNT_SHUTDOWN)) {
+			rcu_read_unlock();
+			return;
+		}
+	}
+	rcu_read_unlock();
+	nfs_mark_client_ready(clp, -EIO);
+	shutdown_client(clp->cl_rpcclient);
+}
+
+static ssize_t
+shutdown_show(struct kobject *kobj, struct kobj_attribute *attr,
+				char *buf)
+{
+	struct nfs_server *server = container_of(kobj, struct nfs_server, kobj);
+	bool shutdown = server->flags & NFS_MOUNT_SHUTDOWN;
+	return sysfs_emit(buf, "%d\n", shutdown);
+}
+
+static ssize_t
+shutdown_store(struct kobject *kobj, struct kobj_attribute *attr,
+				const char *buf, size_t count)
+{
+	struct nfs_server *server;
+	int ret, val;
+
+	server = container_of(kobj, struct nfs_server, kobj);
+
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val != 1)
+		return -EINVAL;
+
+	/* already shut down? */
+	if (server->flags & NFS_MOUNT_SHUTDOWN)
+		goto out;
+
+	server->flags |= NFS_MOUNT_SHUTDOWN;
+	shutdown_client(server->client);
+
+	if (!IS_ERR(server->client_acl))
+		shutdown_client(server->client_acl);
+
+	if (server->nlm_host)
+		nlmclnt_shutdown_rpc_clnt(server->nlm_host);
+out:
+	shutdown_nfs_client(server->nfs_client);
+	return count;
+}
+
+static struct kobj_attribute nfs_sysfs_attr_shutdown = __ATTR_RW(shutdown);
+
+#if IS_ENABLED(CONFIG_NFS_V4)
+static ssize_t
+implid_domain_show(struct kobject *kobj, struct kobj_attribute *attr,
+				char *buf)
+{
+	struct nfs_server *server = container_of(kobj, struct nfs_server, kobj);
+	struct nfs41_impl_id *impl_id = server->nfs_client->cl_implid;
+
+	if (!impl_id || strlen(impl_id->domain) == 0)
+		return 0; //sysfs_emit(buf, "");
+	return sysfs_emit(buf, "%s\n", impl_id->domain);
+}
+
+static struct kobj_attribute nfs_sysfs_attr_implid_domain = __ATTR_RO(implid_domain);
+
+
+static ssize_t
+implid_name_show(struct kobject *kobj, struct kobj_attribute *attr,
+				char *buf)
+{
+	struct nfs_server *server = container_of(kobj, struct nfs_server, kobj);
+	struct nfs41_impl_id *impl_id = server->nfs_client->cl_implid;
+
+	if (!impl_id || strlen(impl_id->name) == 0)
+		return 0; //sysfs_emit(buf, "");
+	return sysfs_emit(buf, "%s\n", impl_id->name);
+}
+
+static struct kobj_attribute nfs_sysfs_attr_implid_name = __ATTR_RO(implid_name);
+
+#endif /* IS_ENABLED(CONFIG_NFS_V4) */
+
+#define RPC_CLIENT_NAME_SIZE 64
+
+void nfs_sysfs_link_rpc_client(struct nfs_server *server,
+			struct rpc_clnt *clnt, const char *uniq)
+{
+	char name[RPC_CLIENT_NAME_SIZE];
+	int ret;
+
+	strscpy(name, clnt->cl_program->name, sizeof(name));
+	strncat(name, uniq ? uniq : "", sizeof(name) - strlen(name) - 1);
+	strncat(name, "_client", sizeof(name) - strlen(name) - 1);
+
+	ret = sysfs_create_link_nowarn(&server->kobj,
+						&clnt->cl_sysfs->kobject, name);
+	if (ret < 0)
+		pr_warn("NFS: can't create link to %s in sysfs (%d)\n",
+			name, ret);
+}
+EXPORT_SYMBOL_GPL(nfs_sysfs_link_rpc_client);
+
+static void nfs_sysfs_sb_release(struct kobject *kobj)
+{
+	/* no-op: why? see lib/kobject.c kobject_cleanup() */
+}
+
+static const struct ns_common *nfs_netns_server_namespace(const struct kobject *kobj)
+{
+	return to_ns_common(container_of(kobj, struct nfs_server,
+					 kobj)->nfs_client->cl_net);
+}
+
+static struct kobj_type nfs_sb_ktype = {
+	.release = nfs_sysfs_sb_release,
+	.sysfs_ops = &kobj_sysfs_ops,
+	.namespace = nfs_netns_server_namespace,
+	.child_ns_type = nfs_netns_object_child_ns_type,
+};
+
+#if IS_ENABLED(CONFIG_NFS_V4)
+static void nfs_sysfs_add_nfsv41_server(struct nfs_server *server)
+{
+	int ret;
+
+	if (!server->nfs_client->cl_implid)
+		return;
+
+	ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_implid_domain.attr,
+					   nfs_netns_server_namespace(&server->kobj));
+	if (ret < 0)
+		pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n",
+			server->s_sysfs_id, ret);
+
+	ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_implid_name.attr,
+				   nfs_netns_server_namespace(&server->kobj));
+	if (ret < 0)
+		pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n",
+			server->s_sysfs_id, ret);
+}
+#else /* CONFIG_NFS_V4 */
+static inline void nfs_sysfs_add_nfsv41_server(struct nfs_server *server)
+{
+}
+#endif /* CONFIG_NFS_V4 */
+
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+
+static ssize_t
+localio_show(struct kobject *kobj, struct kobj_attribute *attr,
+				char *buf)
+{
+	struct nfs_server *server = container_of(kobj, struct nfs_server, kobj);
+	bool localio = nfs_server_is_local(server->nfs_client);
+	return sysfs_emit(buf, "%d\n", localio);
+}
+
+static struct kobj_attribute nfs_sysfs_attr_localio = __ATTR_RO(localio);
+
+static void nfs_sysfs_add_nfs_localio_server(struct nfs_server *server)
+{
+	int ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_localio.attr,
+				       nfs_netns_server_namespace(&server->kobj));
+	if (ret < 0)
+		pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n",
+			server->s_sysfs_id, ret);
+}
+#else
+static inline void nfs_sysfs_add_nfs_localio_server(struct nfs_server *server)
+{
+}
+#endif /* IS_ENABLED(CONFIG_NFS_LOCALIO) */
+
+void nfs_sysfs_add_server(struct nfs_server *server)
+{
+	int ret;
+
+	ret = kobject_init_and_add(&server->kobj, &nfs_sb_ktype,
+				&nfs_kset->kobj, "server-%d", server->s_sysfs_id);
+	if (ret < 0) {
+		pr_warn("NFS: nfs sysfs add server-%d failed (%d)\n",
+					server->s_sysfs_id, ret);
+		return;
+	}
+	ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_shutdown.attr,
+				nfs_netns_server_namespace(&server->kobj));
+	if (ret < 0)
+		pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n",
+			server->s_sysfs_id, ret);
+
+	nfs_sysfs_add_nfsv41_server(server);
+	nfs_sysfs_add_nfs_localio_server(server);
+}
+EXPORT_SYMBOL_GPL(nfs_sysfs_add_server);
+
+void nfs_sysfs_move_server_to_sb(struct super_block *s)
+{
+	struct nfs_server *server = s->s_fs_info;
+	int ret;
+
+	ret = kobject_rename(&server->kobj, s->s_id);
+	if (ret < 0)
+		pr_warn("NFS: rename sysfs %s failed (%d)\n",
+					server->kobj.name, ret);
+}
+
+void nfs_sysfs_move_sb_to_server(struct nfs_server *server)
+{
+	const char *s;
+	int ret = -ENOMEM;
+
+	s = kasprintf(GFP_KERNEL, "server-%d", server->s_sysfs_id);
+	if (s) {
+		ret = kobject_rename(&server->kobj, s);
+		kfree(s);
+	}
+	if (ret < 0)
+		pr_warn("NFS: rename sysfs %s failed (%d)\n",
+					server->kobj.name, ret);
+}
+
+/* unlink, not dec-ref */
+void nfs_sysfs_remove_server(struct nfs_server *server)
+{
+	kobject_del(&server->kobj);
+}