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, 386 insertions, 0 deletions

diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
new file mode 100644
index 000000000..6d0073c24
--- /dev/null
+++ b/fs/nfs/namespace.c
@@ -0,0 +1,386 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/fs/nfs/namespace.c
+ *
+ * Copyright (C) 2005 Trond Myklebust <Trond.Myklebust@netapp.com>
+ * - Modified by David Howells <dhowells@redhat.com>
+ *
+ * NFS namespace
+ */
+
+#include <linux/module.h>
+#include <linux/dcache.h>
+#include <linux/gfp.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/nfs_fs.h>
+#include <linux/string.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/vfs.h>
+#include <linux/sunrpc/gss_api.h>
+#include "internal.h"
+#include "nfs.h"
+
+#define NFSDBG_FACILITY		NFSDBG_VFS
+
+static void nfs_expire_automounts(struct work_struct *work);
+
+static LIST_HEAD(nfs_automount_list);
+static DECLARE_DELAYED_WORK(nfs_automount_task, nfs_expire_automounts);
+int nfs_mountpoint_expiry_timeout = 500 * HZ;
+
+/*
+ * nfs_path - reconstruct the path given an arbitrary dentry
+ * @base - used to return pointer to the end of devname part of path
+ * @dentry_in - pointer to dentry
+ * @buffer - result buffer
+ * @buflen_in - length of buffer
+ * @flags - options (see below)
+ *
+ * Helper function for constructing the server pathname
+ * by arbitrary hashed dentry.
+ *
+ * This is mainly for use in figuring out the path on the
+ * server side when automounting on top of an existing partition
+ * and in generating /proc/mounts and friends.
+ *
+ * Supported flags:
+ * NFS_PATH_CANONICAL: ensure there is exactly one slash after
+ *		       the original device (export) name
+ *		       (if unset, the original name is returned verbatim)
+ */
+char *nfs_path(char **p, struct dentry *dentry_in, char *buffer,
+	       ssize_t buflen_in, unsigned flags)
+{
+	char *end;
+	int namelen;
+	unsigned seq;
+	const char *base;
+	struct dentry *dentry;
+	ssize_t buflen;
+
+rename_retry:
+	buflen = buflen_in;
+	dentry = dentry_in;
+	end = buffer+buflen;
+	*--end = '\0';
+	buflen--;
+
+	seq = read_seqbegin(&rename_lock);
+	rcu_read_lock();
+	while (1) {
+		spin_lock(&dentry->d_lock);
+		if (IS_ROOT(dentry))
+			break;
+		namelen = dentry->d_name.len;
+		buflen -= namelen + 1;
+		if (buflen < 0)
+			goto Elong_unlock;
+		end -= namelen;
+		memcpy(end, dentry->d_name.name, namelen);
+		*--end = '/';
+		spin_unlock(&dentry->d_lock);
+		dentry = dentry->d_parent;
+	}
+	if (read_seqretry(&rename_lock, seq)) {
+		spin_unlock(&dentry->d_lock);
+		rcu_read_unlock();
+		goto rename_retry;
+	}
+	if ((flags & NFS_PATH_CANONICAL) && *end != '/') {
+		if (--buflen < 0) {
+			spin_unlock(&dentry->d_lock);
+			rcu_read_unlock();
+			goto Elong;
+		}
+		*--end = '/';
+	}
+	*p = end;
+	base = dentry->d_fsdata;
+	if (!base) {
+		spin_unlock(&dentry->d_lock);
+		rcu_read_unlock();
+		WARN_ON(1);
+		return end;
+	}
+	namelen = strlen(base);
+	if (*end == '/') {
+		/* Strip off excess slashes in base string */
+		while (namelen > 0 && base[namelen - 1] == '/')
+			namelen--;
+	}
+	buflen -= namelen;
+	if (buflen < 0) {
+		spin_unlock(&dentry->d_lock);
+		rcu_read_unlock();
+		goto Elong;
+	}
+	end -= namelen;
+	memcpy(end, base, namelen);
+	spin_unlock(&dentry->d_lock);
+	rcu_read_unlock();
+	return end;
+Elong_unlock:
+	spin_unlock(&dentry->d_lock);
+	rcu_read_unlock();
+	if (read_seqretry(&rename_lock, seq))
+		goto rename_retry;
+Elong:
+	return ERR_PTR(-ENAMETOOLONG);
+}
+EXPORT_SYMBOL_GPL(nfs_path);
+
+/*
+ * nfs_d_automount - Handle crossing a mountpoint on the server
+ * @path - The mountpoint
+ *
+ * When we encounter a mountpoint on the server, we want to set up
+ * a mountpoint on the client too, to prevent inode numbers from
+ * colliding, and to allow "df" to work properly.
+ * On NFSv4, we also want to allow for the fact that different
+ * filesystems may be migrated to different servers in a failover
+ * situation, and that different filesystems may want to use
+ * different security flavours.
+ */
+struct vfsmount *nfs_d_automount(struct path *path)
+{
+	struct nfs_fs_context *ctx;
+	struct fs_context *fc;
+	struct vfsmount *mnt = ERR_PTR(-ENOMEM);
+	struct nfs_server *server = NFS_SB(path->dentry->d_sb);
+	struct nfs_client *client = server->nfs_client;
+	unsigned long s_flags = path->dentry->d_sb->s_flags;
+	int timeout = READ_ONCE(nfs_mountpoint_expiry_timeout);
+	int ret;
+
+	if (IS_ROOT(path->dentry))
+		return ERR_PTR(-ESTALE);
+
+	/* Open a new filesystem context, transferring parameters from the
+	 * parent superblock, including the network namespace.
+	 */
+	fc = fs_context_for_submount(path->mnt->mnt_sb->s_type, path->dentry);
+	if (IS_ERR(fc))
+		return ERR_CAST(fc);
+
+	ctx = nfs_fc2context(fc);
+	ctx->clone_data.dentry	= path->dentry;
+	ctx->clone_data.sb	= path->dentry->d_sb;
+	ctx->clone_data.fattr	= nfs_alloc_fattr();
+	if (!ctx->clone_data.fattr)
+		goto out_fc;
+
+	if (fc->cred != server->cred) {
+		put_cred(fc->cred);
+		fc->cred = get_cred(server->cred);
+	}
+
+	if (fc->net_ns != client->cl_net) {
+		put_net(fc->net_ns);
+		fc->net_ns = get_net(client->cl_net);
+	}
+
+	/* Inherit the flags covered by NFS_SB_MASK */
+	fc->sb_flags_mask |= NFS_SB_MASK;
+	fc->sb_flags &= ~NFS_SB_MASK;
+	fc->sb_flags |= s_flags & NFS_SB_MASK;
+
+	/* for submounts we want the same server; referrals will reassign */
+	memcpy(&ctx->nfs_server._address, &client->cl_addr, client->cl_addrlen);
+	ctx->nfs_server.addrlen	= client->cl_addrlen;
+	ctx->nfs_server.port	= server->port;
+
+	ctx->version		= client->rpc_ops->version;
+	ctx->minorversion	= client->cl_minorversion;
+	ctx->nfs_mod		= client->cl_nfs_mod;
+	get_nfs_version(ctx->nfs_mod);
+
+	/* Inherit block sizes if they were specified as mount parameters */
+	if (server->automount_inherit & NFS_AUTOMOUNT_INHERIT_BSIZE)
+		ctx->bsize = server->bsize;
+
+	ret = client->rpc_ops->submount(fc, server);
+	if (ret < 0) {
+		mnt = ERR_PTR(ret);
+		goto out_fc;
+	}
+
+	up_write(&fc->root->d_sb->s_umount);
+	mnt = vfs_create_mount(fc);
+	if (IS_ERR(mnt))
+		goto out_fc;
+
+	if (timeout <= 0)
+		goto out_fc;
+
+	mnt_set_expiry(mnt, &nfs_automount_list);
+	schedule_delayed_work(&nfs_automount_task, timeout);
+
+out_fc:
+	put_fs_context(fc);
+	return mnt;
+}
+
+static int
+nfs_namespace_getattr(struct mnt_idmap *idmap,
+		      const struct path *path, struct kstat *stat,
+		      u32 request_mask, unsigned int query_flags)
+{
+	if (NFS_FH(d_inode(path->dentry))->size != 0)
+		return nfs_getattr(idmap, path, stat, request_mask,
+				   query_flags);
+	generic_fillattr(&nop_mnt_idmap, request_mask, d_inode(path->dentry),
+			 stat);
+	return 0;
+}
+
+static int
+nfs_namespace_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+		      struct iattr *attr)
+{
+	if (NFS_FH(d_inode(dentry))->size != 0)
+		return nfs_setattr(idmap, dentry, attr);
+	return -EACCES;
+}
+
+const struct inode_operations nfs_mountpoint_inode_operations = {
+	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
+	.fileattr_get	= nfs_fileattr_get,
+};
+
+const struct inode_operations nfs_referral_inode_operations = {
+	.getattr	= nfs_namespace_getattr,
+	.setattr	= nfs_namespace_setattr,
+	.fileattr_get	= nfs_fileattr_get,
+};
+
+static void nfs_expire_automounts(struct work_struct *work)
+{
+	struct list_head *list = &nfs_automount_list;
+	int timeout = READ_ONCE(nfs_mountpoint_expiry_timeout);
+
+	mark_mounts_for_expiry(list);
+	if (!list_empty(list) && timeout > 0)
+		schedule_delayed_work(&nfs_automount_task, timeout);
+}
+
+void nfs_release_automount_timer(void)
+{
+	if (list_empty(&nfs_automount_list))
+		cancel_delayed_work(&nfs_automount_task);
+}
+
+/**
+ * nfs_do_submount - set up mountpoint when crossing a filesystem boundary
+ * @fc: pointer to struct nfs_fs_context
+ *
+ */
+int nfs_do_submount(struct fs_context *fc)
+{
+	struct nfs_fs_context *ctx = nfs_fc2context(fc);
+	struct dentry *dentry = ctx->clone_data.dentry;
+	struct nfs_server *server;
+	char *buffer, *p;
+	int ret;
+
+	/* create a new volume representation */
+	server = ctx->nfs_mod->rpc_ops->clone_server(NFS_SB(ctx->clone_data.sb),
+						     ctx->mntfh,
+						     ctx->clone_data.fattr,
+						     ctx->selected_flavor);
+
+	if (IS_ERR(server))
+		return PTR_ERR(server);
+
+	ctx->server = server;
+
+	buffer = kmalloc(4096, GFP_USER);
+	if (!buffer)
+		return -ENOMEM;
+
+	ctx->internal		= true;
+
+	p = nfs_devname(dentry, buffer, 4096);
+	if (IS_ERR(p)) {
+		nfs_errorf(fc, "NFS: Couldn't determine submount pathname");
+		ret = PTR_ERR(p);
+	} else {
+		ret = vfs_parse_fs_qstr(fc, "source",
+					&QSTR_LEN(p, buffer + 4096 - p));
+		if (!ret)
+			ret = vfs_get_tree(fc);
+	}
+	kfree(buffer);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nfs_do_submount);
+
+int nfs_submount(struct fs_context *fc, struct nfs_server *server)
+{
+	struct nfs_fs_context *ctx = nfs_fc2context(fc);
+	struct dentry *dentry = ctx->clone_data.dentry;
+	struct dentry *parent = dget_parent(dentry);
+	int err;
+
+	/* Look it up again to get its attributes */
+	err = server->nfs_client->rpc_ops->lookup(d_inode(parent), dentry, &dentry->d_name,
+						  ctx->mntfh, ctx->clone_data.fattr);
+	dput(parent);
+	if (err != 0)
+		return err;
+
+	ctx->selected_flavor = server->client->cl_auth->au_flavor;
+	return nfs_do_submount(fc);
+}
+EXPORT_SYMBOL_GPL(nfs_submount);
+
+static int param_set_nfs_timeout(const char *val, const struct kernel_param *kp)
+{
+	long num;
+	int ret;
+
+	if (!val)
+		return -EINVAL;
+	ret = kstrtol(val, 0, &num);
+	if (ret)
+		return -EINVAL;
+	if (num > 0) {
+		if (num >= INT_MAX / HZ)
+			num = INT_MAX;
+		else
+			num *= HZ;
+		*((int *)kp->arg) = num;
+		if (!list_empty(&nfs_automount_list))
+			mod_delayed_work(system_percpu_wq, &nfs_automount_task, num);
+	} else {
+		*((int *)kp->arg) = -1*HZ;
+		cancel_delayed_work(&nfs_automount_task);
+	}
+	return 0;
+}
+
+static int param_get_nfs_timeout(char *buffer, const struct kernel_param *kp)
+{
+	long num = *((int *)kp->arg);
+
+	if (num > 0) {
+		if (num >= INT_MAX - (HZ - 1))
+			num = INT_MAX / HZ;
+		else
+			num = (num + (HZ - 1)) / HZ;
+	} else
+		num = -1;
+	return sysfs_emit(buffer, "%li\n", num);
+}
+
+static const struct kernel_param_ops param_ops_nfs_timeout = {
+	.set = param_set_nfs_timeout,
+	.get = param_get_nfs_timeout,
+};
+#define param_check_nfs_timeout(name, p) __param_check(name, p, int)
+
+module_param(nfs_mountpoint_expiry_timeout, nfs_timeout, 0644);
+MODULE_PARM_DESC(nfs_mountpoint_expiry_timeout,
+		"Set the NFS automounted mountpoint timeout value (seconds)."
+		"Values <= 0 turn expiration off.");