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, 468 insertions, 0 deletions

diff --git a/fs/proc/root.c b/fs/proc/root.c
new file mode 100644
index 000000000..99adddfeb
--- /dev/null
+++ b/fs/proc/root.c
@@ -0,0 +1,468 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/proc/root.c
+ *
+ *  Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ *  proc root directory handling functions
+ */
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/sched/stat.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/user_namespace.h>
+#include <linux/fs_context.h>
+#include <linux/mount.h>
+#include <linux/pid_namespace.h>
+#include <linux/fs_parser.h>
+#include <linux/cred.h>
+#include <linux/magic.h>
+#include <linux/slab.h>
+
+#include "internal.h"
+
+struct proc_fs_context {
+	struct pid_namespace	*pid_ns;
+	unsigned int		mask;
+	enum proc_hidepid	hidepid;
+	int			gid;
+	enum proc_pidonly	pidonly;
+};
+
+enum proc_param {
+	Opt_gid,
+	Opt_hidepid,
+	Opt_subset,
+	Opt_pidns,
+};
+
+static const struct fs_parameter_spec proc_fs_parameters[] = {
+	fsparam_u32("gid",		Opt_gid),
+	fsparam_string("hidepid",	Opt_hidepid),
+	fsparam_string("subset",	Opt_subset),
+	fsparam_file_or_string("pidns",	Opt_pidns),
+	{}
+};
+
+static inline int valid_hidepid(unsigned int value)
+{
+	return (value == HIDEPID_OFF ||
+		value == HIDEPID_NO_ACCESS ||
+		value == HIDEPID_INVISIBLE ||
+		value == HIDEPID_NOT_PTRACEABLE);
+}
+
+static int proc_parse_hidepid_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+	struct fs_parameter_spec hidepid_u32_spec = fsparam_u32("hidepid", Opt_hidepid);
+	struct fs_parse_result result;
+	int base = (unsigned long)hidepid_u32_spec.data;
+
+	if (param->type != fs_value_is_string)
+		return invalf(fc, "proc: unexpected type of hidepid value\n");
+
+	if (!kstrtouint(param->string, base, &result.uint_32)) {
+		if (!valid_hidepid(result.uint_32))
+			return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string);
+		ctx->hidepid = result.uint_32;
+		return 0;
+	}
+
+	if (!strcmp(param->string, "off"))
+		ctx->hidepid = HIDEPID_OFF;
+	else if (!strcmp(param->string, "noaccess"))
+		ctx->hidepid = HIDEPID_NO_ACCESS;
+	else if (!strcmp(param->string, "invisible"))
+		ctx->hidepid = HIDEPID_INVISIBLE;
+	else if (!strcmp(param->string, "ptraceable"))
+		ctx->hidepid = HIDEPID_NOT_PTRACEABLE;
+	else
+		return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string);
+
+	return 0;
+}
+
+static int proc_parse_subset_param(struct fs_context *fc, char *value)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+
+	while (value) {
+		char *ptr = strchr(value, ',');
+
+		if (ptr != NULL)
+			*ptr++ = '\0';
+
+		if (*value != '\0') {
+			if (!strcmp(value, "pid")) {
+				ctx->pidonly = PROC_PIDONLY_ON;
+			} else {
+				return invalf(fc, "proc: unsupported subset option - %s\n", value);
+			}
+		}
+		value = ptr;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_PID_NS
+static int proc_parse_pidns_param(struct fs_context *fc,
+				  struct fs_parameter *param,
+				  struct fs_parse_result *result)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+	struct pid_namespace *target, *active = task_active_pid_ns(current);
+	struct ns_common *ns;
+	struct file *ns_filp __free(fput) = NULL;
+
+	switch (param->type) {
+	case fs_value_is_file:
+		/* came through fsconfig, steal the file reference */
+		ns_filp = no_free_ptr(param->file);
+		break;
+	case fs_value_is_string:
+		ns_filp = filp_open(param->string, O_RDONLY, 0);
+		break;
+	default:
+		WARN_ON_ONCE(true);
+		break;
+	}
+	if (!ns_filp)
+		ns_filp = ERR_PTR(-EBADF);
+	if (IS_ERR(ns_filp)) {
+		errorfc(fc, "could not get file from pidns argument");
+		return PTR_ERR(ns_filp);
+	}
+
+	if (!proc_ns_file(ns_filp))
+		return invalfc(fc, "pidns argument is not an nsfs file");
+	ns = get_proc_ns(file_inode(ns_filp));
+	if (ns->ns_type != CLONE_NEWPID)
+		return invalfc(fc, "pidns argument is not a pidns file");
+	target = container_of(ns, struct pid_namespace, ns);
+
+	/*
+	 * pidns= is shorthand for joining the pidns to get a fsopen fd, so the
+	 * permission model should be the same as pidns_install().
+	 */
+	if (!ns_capable(target->user_ns, CAP_SYS_ADMIN)) {
+		errorfc(fc, "insufficient permissions to set pidns");
+		return -EPERM;
+	}
+	if (!pidns_is_ancestor(target, active))
+		return invalfc(fc, "cannot set pidns to non-descendant pidns");
+
+	put_pid_ns(ctx->pid_ns);
+	ctx->pid_ns = get_pid_ns(target);
+	put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(ctx->pid_ns->user_ns);
+	return 0;
+}
+#endif /* CONFIG_PID_NS */
+
+static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+	struct fs_parse_result result;
+	int opt, err;
+
+	opt = fs_parse(fc, proc_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_gid:
+		ctx->gid = result.uint_32;
+		break;
+
+	case Opt_hidepid:
+		err = proc_parse_hidepid_param(fc, param);
+		if (err)
+			return err;
+		break;
+
+	case Opt_subset:
+		err = proc_parse_subset_param(fc, param->string);
+		if (err)
+			return err;
+		break;
+
+	case Opt_pidns:
+#ifdef CONFIG_PID_NS
+		/*
+		 * We would have to RCU-protect every proc_pid_ns() or
+		 * proc_sb_info() access if we allowed this to be reconfigured
+		 * for an existing procfs instance. Luckily, procfs instances
+		 * are cheap to create, and mount-beneath would let you
+		 * atomically replace an instance even with overmounts.
+		 */
+		if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+			errorfc(fc, "cannot reconfigure pidns for existing procfs");
+			return -EBUSY;
+		}
+		err = proc_parse_pidns_param(fc, param, &result);
+		if (err)
+			return err;
+		break;
+#else
+		errorfc(fc, "pidns mount flag not supported on this system");
+		return -EOPNOTSUPP;
+#endif
+
+	default:
+		return -EINVAL;
+	}
+
+	ctx->mask |= 1 << opt;
+	return 0;
+}
+
+static int proc_apply_options(struct proc_fs_info *fs_info,
+			       struct fs_context *fc,
+			       struct user_namespace *user_ns)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+
+	if ((ctx->mask & (1 << Opt_subset)) &&
+	    fc->purpose == FS_CONTEXT_FOR_RECONFIGURE &&
+	    ctx->pidonly != fs_info->pidonly)
+		return invalf(fc, "proc: subset=pid cannot be changed\n");
+
+	if (ctx->mask & (1 << Opt_gid))
+		fs_info->pid_gid = make_kgid(user_ns, ctx->gid);
+	if (ctx->mask & (1 << Opt_hidepid))
+		fs_info->hide_pid = ctx->hidepid;
+	if (ctx->mask & (1 << Opt_subset))
+		fs_info->pidonly = ctx->pidonly;
+	if (ctx->mask & (1 << Opt_pidns) &&
+	    !WARN_ON_ONCE(fc->purpose == FS_CONTEXT_FOR_RECONFIGURE)) {
+		put_pid_ns(fs_info->pid_ns);
+		fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
+	}
+	return 0;
+}
+
+static int proc_fill_super(struct super_block *s, struct fs_context *fc)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+	struct inode *root_inode;
+	struct proc_fs_info *fs_info;
+	int ret;
+
+	fs_info = kzalloc_obj(*fs_info);
+	if (!fs_info)
+		return -ENOMEM;
+
+	fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
+	fs_info->mounter_cred = get_cred(fc->cred);
+	ret = proc_apply_options(fs_info, fc, current_user_ns());
+	if (ret)
+		return ret;
+
+	/* User space would break if executables or devices appear on proc */
+	s->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
+	s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
+	s->s_blocksize = 1024;
+	s->s_blocksize_bits = 10;
+	s->s_magic = PROC_SUPER_MAGIC;
+	s->s_op = &proc_sops;
+	s->s_time_gran = 1;
+	s->s_fs_info = fs_info;
+
+	if (fs_info->pidonly == PROC_PIDONLY_ON)
+		s->s_iflags |= SB_I_RESTRICTED_VARIANT;
+
+	/*
+	 * procfs isn't actually a stacking filesystem; however, there is
+	 * too much magic going on inside it to permit stacking things on
+	 * top of it
+	 */
+	s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
+
+	/* procfs dentries and inodes don't require IO to create */
+	s->s_shrink->seeks = 0;
+
+	pde_get(&proc_root);
+	root_inode = proc_get_inode(s, &proc_root);
+	if (!root_inode) {
+		pr_err("proc_fill_super: get root inode failed\n");
+		return -ENOMEM;
+	}
+
+	s->s_root = d_make_root(root_inode);
+	if (!s->s_root) {
+		pr_err("proc_fill_super: allocate dentry failed\n");
+		return -ENOMEM;
+	}
+
+	ret = proc_setup_self(s);
+	if (ret) {
+		return ret;
+	}
+	return proc_setup_thread_self(s);
+}
+
+static int proc_reconfigure(struct fs_context *fc)
+{
+	struct super_block *sb = fc->root->d_sb;
+	struct proc_fs_info *fs_info = proc_sb_info(sb);
+
+	sync_filesystem(sb);
+
+	return proc_apply_options(fs_info, fc, current_user_ns());
+}
+
+static int proc_get_tree(struct fs_context *fc)
+{
+	return get_tree_nodev(fc, proc_fill_super);
+}
+
+static void proc_fs_context_free(struct fs_context *fc)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+
+	put_pid_ns(ctx->pid_ns);
+	kfree(ctx);
+}
+
+static const struct fs_context_operations proc_fs_context_ops = {
+	.free		= proc_fs_context_free,
+	.parse_param	= proc_parse_param,
+	.get_tree	= proc_get_tree,
+	.reconfigure	= proc_reconfigure,
+};
+
+static int proc_init_fs_context(struct fs_context *fc)
+{
+	struct proc_fs_context *ctx;
+
+	ctx = kzalloc_obj(struct proc_fs_context);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->pid_ns = get_pid_ns(task_active_pid_ns(current));
+	put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(ctx->pid_ns->user_ns);
+	fc->fs_private = ctx;
+	fc->ops = &proc_fs_context_ops;
+	return 0;
+}
+
+static void proc_kill_sb(struct super_block *sb)
+{
+	struct proc_fs_info *fs_info = proc_sb_info(sb);
+
+	kill_anon_super(sb);
+	if (fs_info) {
+		put_pid_ns(fs_info->pid_ns);
+		put_cred(fs_info->mounter_cred);
+		kfree_rcu(fs_info, rcu);
+	}
+}
+
+static struct file_system_type proc_fs_type = {
+	.name			= "proc",
+	.init_fs_context	= proc_init_fs_context,
+	.parameters		= proc_fs_parameters,
+	.kill_sb		= proc_kill_sb,
+	.fs_flags		= FS_USERNS_MOUNT | FS_USERNS_MOUNT_RESTRICTED | FS_DISALLOW_NOTIFY_PERM,
+};
+
+void __init proc_root_init(void)
+{
+	proc_init_kmemcache();
+	set_proc_pid_nlink();
+	proc_self_init();
+	proc_thread_self_init();
+	proc_symlink("mounts", NULL, "self/mounts");
+
+	proc_net_init();
+	proc_mkdir("fs", NULL);
+	proc_mkdir("driver", NULL);
+	proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */
+#if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
+	/* just give it a mountpoint */
+	proc_create_mount_point("openprom");
+#endif
+	proc_tty_init();
+	proc_mkdir("bus", NULL);
+	proc_sys_init();
+
+	/*
+	 * Last things last. It is not like userspace processes eager
+	 * to open /proc files exist at this point but register last
+	 * anyway.
+	 */
+	register_filesystem(&proc_fs_type);
+}
+
+static int proc_root_getattr(struct mnt_idmap *idmap,
+			     const struct path *path, struct kstat *stat,
+			     u32 request_mask, unsigned int query_flags)
+{
+	generic_fillattr(&nop_mnt_idmap, request_mask, d_inode(path->dentry),
+			 stat);
+	stat->nlink = proc_root.nlink + nr_processes();
+	return 0;
+}
+
+static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
+{
+	if (!proc_pid_lookup(dentry, flags))
+		return NULL;
+
+	return proc_lookup(dir, dentry, flags);
+}
+
+static int proc_root_readdir(struct file *file, struct dir_context *ctx)
+{
+	if (ctx->pos < FIRST_PROCESS_ENTRY) {
+		int error = proc_readdir(file, ctx);
+		if (unlikely(error <= 0))
+			return error;
+		ctx->pos = FIRST_PROCESS_ENTRY;
+	}
+
+	return proc_pid_readdir(file, ctx);
+}
+
+/*
+ * The root /proc directory is special, as it has the
+ * <pid> directories. Thus we don't use the generic
+ * directory handling functions for that..
+ */
+static const struct file_operations proc_root_operations = {
+	.read		 = generic_read_dir,
+	.iterate_shared	 = proc_root_readdir,
+	.llseek		= generic_file_llseek,
+};
+
+/*
+ * proc root can do almost nothing..
+ */
+static const struct inode_operations proc_root_inode_operations = {
+	.lookup		= proc_root_lookup,
+	.getattr	= proc_root_getattr,
+};
+
+/*
+ * This is the root "inode" in the /proc tree..
+ */
+struct proc_dir_entry proc_root = {
+	.low_ino	= PROCFS_ROOT_INO,
+	.namelen	= 5,
+	.mode		= S_IFDIR | S_IRUGO | S_IXUGO,
+	.nlink		= 2,
+	.refcnt		= REFCOUNT_INIT(1),
+	.proc_iops	= &proc_root_inode_operations,
+	.proc_dir_ops	= &proc_root_operations,
+	.parent		= &proc_root,
+	.subdir		= RB_ROOT,
+	.name		= "/proc",
+};