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, 426 insertions, 0 deletions

diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
new file mode 100644
index 000000000..00cc385bc
--- /dev/null
+++ b/fs/proc/proc_net.c
@@ -0,0 +1,426 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  linux/fs/proc/net.c
+ *
+ *  Copyright (C) 2007
+ *
+ *  Author: Eric Biederman <ebiederm@xmission.com>
+ *
+ *  proc net directory handling functions
+ */
+#include <linux/errno.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/mount.h>
+#include <linux/nsproxy.h>
+#include <linux/uidgid.h>
+#include <net/net_namespace.h>
+#include <linux/seq_file.h>
+#include <linux/security.h>
+
+#include "internal.h"
+
+static inline struct net *PDE_NET(struct proc_dir_entry *pde)
+{
+	return pde->parent->data;
+}
+
+static struct net *get_proc_net(const struct inode *inode)
+{
+	return maybe_get_net(PDE_NET(PDE(inode)));
+}
+
+static int seq_open_net(struct inode *inode, struct file *file)
+{
+	unsigned int state_size = PDE(inode)->state_size;
+	struct seq_net_private *p;
+	struct net *net;
+
+	WARN_ON_ONCE(state_size < sizeof(*p));
+
+	if (file->f_mode & FMODE_WRITE && !PDE(inode)->write)
+		return -EACCES;
+
+	net = get_proc_net(inode);
+	if (!net)
+		return -ENXIO;
+
+	p = __seq_open_private(file, PDE(inode)->seq_ops, state_size);
+	if (!p) {
+		put_net(net);
+		return -ENOMEM;
+	}
+#ifdef CONFIG_NET_NS
+	p->net = net;
+	netns_tracker_alloc(net, &p->ns_tracker, GFP_KERNEL);
+#endif
+	return 0;
+}
+
+static void seq_file_net_put_net(struct seq_file *seq)
+{
+#ifdef CONFIG_NET_NS
+	struct seq_net_private *priv = seq->private;
+
+	put_net_track(priv->net, &priv->ns_tracker);
+#else
+	put_net(&init_net);
+#endif
+}
+
+static int seq_release_net(struct inode *ino, struct file *f)
+{
+	struct seq_file *seq = f->private_data;
+
+	seq_file_net_put_net(seq);
+	seq_release_private(ino, f);
+	return 0;
+}
+
+static const struct proc_ops proc_net_seq_ops = {
+	.proc_open	= seq_open_net,
+	.proc_read	= seq_read,
+	.proc_write	= proc_simple_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release_net,
+};
+
+int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux)
+{
+#ifdef CONFIG_NET_NS
+	struct seq_net_private *p = priv_data;
+
+	p->net = get_net_track(current->nsproxy->net_ns, &p->ns_tracker,
+			       GFP_KERNEL);
+#endif
+	return 0;
+}
+
+void bpf_iter_fini_seq_net(void *priv_data)
+{
+#ifdef CONFIG_NET_NS
+	struct seq_net_private *p = priv_data;
+
+	put_net_track(p->net, &p->ns_tracker);
+#endif
+}
+
+struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
+		struct proc_dir_entry *parent, const struct seq_operations *ops,
+		unsigned int state_size, void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	pde_force_lookup(p);
+	p->proc_ops = &proc_net_seq_ops;
+	p->seq_ops = ops;
+	p->state_size = state_size;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL_GPL(proc_create_net_data);
+
+/**
+ * proc_create_net_data_write - Create a writable net_ns-specific proc file
+ * @name: The name of the file.
+ * @mode: The file's access mode.
+ * @parent: The parent directory in which to create.
+ * @ops: The seq_file ops with which to read the file.
+ * @write: The write method with which to 'modify' the file.
+ * @state_size: The size of the per-file private state to allocate.
+ * @data: Data for retrieval by pde_data().
+ *
+ * Create a network namespaced proc file in the @parent directory with the
+ * specified @name and @mode that allows reading of a file that displays a
+ * series of elements and also provides for the file accepting writes that have
+ * some arbitrary effect.
+ *
+ * The functions in the @ops table are used to iterate over items to be
+ * presented and extract the readable content using the seq_file interface.
+ *
+ * The @write function is called with the data copied into a kernel space
+ * scratch buffer and has a NUL appended for convenience.  The buffer may be
+ * modified by the @write function.  @write should return 0 on success.
+ *
+ * The @data value is accessible from the @show and @write functions by calling
+ * pde_data() on the file inode.  The network namespace must be accessed by
+ * calling seq_file_net() on the seq_file struct.
+ */
+struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode,
+						  struct proc_dir_entry *parent,
+						  const struct seq_operations *ops,
+						  proc_write_t write,
+						  unsigned int state_size, void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	pde_force_lookup(p);
+	p->proc_ops = &proc_net_seq_ops;
+	p->seq_ops = ops;
+	p->state_size = state_size;
+	p->write = write;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL_GPL(proc_create_net_data_write);
+
+static int single_open_net(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *de = PDE(inode);
+	struct net *net;
+	int err;
+
+	net = get_proc_net(inode);
+	if (!net)
+		return -ENXIO;
+
+	err = single_open(file, de->single_show, net);
+	if (err)
+		put_net(net);
+	return err;
+}
+
+static int single_release_net(struct inode *ino, struct file *f)
+{
+	struct seq_file *seq = f->private_data;
+	put_net(seq->private);
+	return single_release(ino, f);
+}
+
+static const struct proc_ops proc_net_single_ops = {
+	.proc_open	= single_open_net,
+	.proc_read	= seq_read,
+	.proc_write	= proc_simple_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release_net,
+};
+
+struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
+		struct proc_dir_entry *parent,
+		int (*show)(struct seq_file *, void *), void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	pde_force_lookup(p);
+	p->proc_ops = &proc_net_single_ops;
+	p->single_show = show;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL_GPL(proc_create_net_single);
+
+/**
+ * proc_create_net_single_write - Create a writable net_ns-specific proc file
+ * @name: The name of the file.
+ * @mode: The file's access mode.
+ * @parent: The parent directory in which to create.
+ * @show: The seqfile show method with which to read the file.
+ * @write: The write method with which to 'modify' the file.
+ * @data: Data for retrieval by pde_data().
+ *
+ * Create a network-namespaced proc file in the @parent directory with the
+ * specified @name and @mode that allows reading of a file that displays a
+ * single element rather than a series and also provides for the file accepting
+ * writes that have some arbitrary effect.
+ *
+ * The @show function is called to extract the readable content via the
+ * seq_file interface.
+ *
+ * The @write function is called with the data copied into a kernel space
+ * scratch buffer and has a NUL appended for convenience.  The buffer may be
+ * modified by the @write function.  @write should return 0 on success.
+ *
+ * The @data value is accessible from the @show and @write functions by calling
+ * pde_data() on the file inode.  The network namespace must be accessed by
+ * calling seq_file_single_net() on the seq_file struct.
+ */
+struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode,
+						    struct proc_dir_entry *parent,
+						    int (*show)(struct seq_file *, void *),
+						    proc_write_t write,
+						    void *data)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_reg(name, mode, &parent, data);
+	if (!p)
+		return NULL;
+	pde_force_lookup(p);
+	p->proc_ops = &proc_net_single_ops;
+	p->single_show = show;
+	p->write = write;
+	return proc_register(parent, p);
+}
+EXPORT_SYMBOL_GPL(proc_create_net_single_write);
+
+static struct net *get_proc_task_net(struct inode *dir)
+{
+	struct task_struct *task;
+	struct nsproxy *ns;
+	struct net *net = NULL;
+	struct proc_fs_info *fs_info = proc_sb_info(dir->i_sb);
+
+	rcu_read_lock();
+	task = pid_task(proc_pid(dir), PIDTYPE_PID);
+	if (task != NULL) {
+		task_lock(task);
+		ns = task->nsproxy;
+		if (ns != NULL)
+			net = get_net(ns->net_ns);
+		task_unlock(task);
+	}
+	rcu_read_unlock();
+
+	if (net && (fs_info->pidonly == PROC_PIDONLY_ON) &&
+	    security_capable(fs_info->mounter_cred, net->user_ns, CAP_NET_ADMIN, CAP_OPT_NONE) < 0) {
+		put_net(net);
+		net = NULL;
+	}
+
+	return net;
+}
+
+static struct dentry *proc_tgid_net_lookup(struct inode *dir,
+		struct dentry *dentry, unsigned int flags)
+{
+	struct dentry *de;
+	struct net *net;
+
+	de = ERR_PTR(-ENOENT);
+	net = get_proc_task_net(dir);
+	if (net != NULL) {
+		de = proc_lookup_de(dir, dentry, net->proc_net);
+		put_net(net);
+	}
+	return de;
+}
+
+static int proc_tgid_net_getattr(struct mnt_idmap *idmap,
+				 const struct path *path, struct kstat *stat,
+				 u32 request_mask, unsigned int query_flags)
+{
+	struct inode *inode = d_inode(path->dentry);
+	struct net *net;
+
+	net = get_proc_task_net(inode);
+
+	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
+
+	if (net != NULL) {
+		stat->nlink = net->proc_net->nlink;
+		put_net(net);
+	}
+
+	return 0;
+}
+
+const struct inode_operations proc_net_inode_operations = {
+	.lookup		= proc_tgid_net_lookup,
+	.getattr	= proc_tgid_net_getattr,
+	.setattr        = proc_nochmod_setattr,
+};
+
+static int proc_tgid_net_readdir(struct file *file, struct dir_context *ctx)
+{
+	int ret;
+	struct net *net;
+
+	ret = -EINVAL;
+	net = get_proc_task_net(file_inode(file));
+	if (net != NULL) {
+		ret = proc_readdir_de(file, ctx, net->proc_net);
+		put_net(net);
+	}
+	return ret;
+}
+
+const struct file_operations proc_net_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= generic_read_dir,
+	.iterate_shared	= proc_tgid_net_readdir,
+};
+
+static __net_init int proc_net_ns_init(struct net *net)
+{
+	struct proc_dir_entry *netd, *net_statd;
+	kuid_t uid;
+	kgid_t gid;
+	int err;
+
+	/*
+	 * This PDE acts only as an anchor for /proc/${pid}/net hierarchy.
+	 * Corresponding inode (PDE(inode) == net->proc_net) is never
+	 * instantiated therefore blanket zeroing is fine.
+	 * net->proc_net_stat inode is instantiated normally.
+	 */
+	err = -ENOMEM;
+	netd = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL);
+	if (!netd)
+		goto out;
+
+	netd->subdir = RB_ROOT;
+	netd->data = net;
+	netd->nlink = 2;
+	netd->namelen = 3;
+	netd->parent = &proc_root;
+	netd->name = netd->inline_name;
+	memcpy(netd->name, "net", 4);
+
+	uid = make_kuid(net->user_ns, 0);
+	if (!uid_valid(uid))
+		uid = netd->uid;
+
+	gid = make_kgid(net->user_ns, 0);
+	if (!gid_valid(gid))
+		gid = netd->gid;
+
+	proc_set_user(netd, uid, gid);
+
+	/* Seed dentry revalidation for /proc/${pid}/net */
+	pde_force_lookup(netd);
+
+	err = -EEXIST;
+	net_statd = proc_net_mkdir(net, "stat", netd);
+	if (!net_statd)
+		goto free_net;
+
+	net->proc_net = netd;
+	net->proc_net_stat = net_statd;
+	return 0;
+
+free_net:
+	pde_free(netd);
+out:
+	return err;
+}
+
+static __net_exit void proc_net_ns_exit(struct net *net)
+{
+	remove_proc_entry("stat", net->proc_net);
+	pde_free(net->proc_net);
+}
+
+static struct pernet_operations __net_initdata proc_net_ns_ops = {
+	.init = proc_net_ns_init,
+	.exit = proc_net_ns_exit,
+};
+
+int __init proc_net_init(void)
+{
+	proc_symlink("net", NULL, "self/net");
+
+	return register_pernet_subsys(&proc_net_ns_ops);
+}