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, 407 insertions, 0 deletions

diff --git a/fs/proc/fd.c b/fs/proc/fd.c
new file mode 100644
index 000000000..0f9a1556f
--- /dev/null
+++ b/fs/proc/fd.c
@@ -0,0 +1,407 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/sched/signal.h>
+#include <linux/errno.h>
+#include <linux/dcache.h>
+#include <linux/path.h>
+#include <linux/fdtable.h>
+#include <linux/namei.h>
+#include <linux/pid.h>
+#include <linux/ptrace.h>
+#include <linux/bitmap.h>
+#include <linux/security.h>
+#include <linux/file.h>
+#include <linux/seq_file.h>
+#include <linux/fs.h>
+#include <linux/filelock.h>
+
+#include <linux/proc_fs.h>
+
+#include "../mount.h"
+#include "internal.h"
+#include "fd.h"
+
+static int seq_show(struct seq_file *m, void *v)
+{
+	struct files_struct *files = NULL;
+	int f_flags = 0, ret = -ENOENT;
+	struct file *file = NULL;
+	struct task_struct *task;
+
+	task = get_proc_task(m->private);
+	if (!task)
+		return -ENOENT;
+
+	task_lock(task);
+	files = task->files;
+	if (files) {
+		unsigned int fd = proc_fd(m->private);
+
+		spin_lock(&files->file_lock);
+		file = files_lookup_fd_locked(files, fd);
+		if (file) {
+			f_flags = file->f_flags;
+			if (close_on_exec(fd, files))
+				f_flags |= O_CLOEXEC;
+
+			get_file(file);
+			ret = 0;
+		}
+		spin_unlock(&files->file_lock);
+	}
+	task_unlock(task);
+	put_task_struct(task);
+
+	if (ret)
+		return ret;
+
+	seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\nino:\t%llu\n",
+		   (long long)file->f_pos, f_flags,
+		   real_mount(file->f_path.mnt)->mnt_id,
+		   file_inode(file)->i_ino);
+
+	/* show_fd_locks() never dereferences files, so a stale value is safe */
+	show_fd_locks(m, file, files);
+	if (seq_has_overflowed(m))
+		goto out;
+
+	if (file->f_op->show_fdinfo)
+		file->f_op->show_fdinfo(m, file);
+
+out:
+	fput(file);
+	return 0;
+}
+
+static int seq_fdinfo_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, seq_show, inode);
+}
+
+/*
+ * Shared /proc/pid/fdinfo and /proc/pid/fdinfo/fd permission helper to ensure
+ * that the current task has PTRACE_MODE_READ in addition to the normal
+ * POSIX-like checks.
+ */
+static int proc_fdinfo_permission(struct mnt_idmap *idmap, struct inode *inode,
+				  int mask)
+{
+	bool allowed = false;
+	struct task_struct *task = get_proc_task(inode);
+
+	if (!task)
+		return -ESRCH;
+
+	allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
+	put_task_struct(task);
+
+	if (!allowed)
+		return -EACCES;
+
+	return generic_permission(idmap, inode, mask);
+}
+
+static const struct inode_operations proc_fdinfo_file_inode_operations = {
+	.permission	= proc_fdinfo_permission,
+	.setattr	= proc_nochmod_setattr,
+};
+
+static const struct file_operations proc_fdinfo_file_operations = {
+	.open		= seq_fdinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode)
+{
+	struct file *file;
+
+	file = fget_task(task, fd);
+	if (file) {
+		*mode = file->f_mode;
+		fput(file);
+	}
+	return !!file;
+}
+
+static void tid_fd_update_inode(struct task_struct *task, struct inode *inode,
+				fmode_t f_mode)
+{
+	task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
+
+	if (S_ISLNK(inode->i_mode)) {
+		unsigned i_mode = S_IFLNK;
+		if (f_mode & FMODE_READ)
+			i_mode |= S_IRUSR | S_IXUSR;
+		if (f_mode & FMODE_WRITE)
+			i_mode |= S_IWUSR | S_IXUSR;
+		inode->i_mode = i_mode;
+	}
+	security_task_to_inode(task, inode);
+}
+
+static int tid_fd_revalidate(struct inode *dir, const struct qstr *name,
+			     struct dentry *dentry, unsigned int flags)
+{
+	struct task_struct *task;
+	struct inode *inode;
+	unsigned int fd;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	inode = d_inode(dentry);
+	task = get_proc_task(inode);
+	fd = proc_fd(inode);
+
+	if (task) {
+		fmode_t f_mode;
+		if (tid_fd_mode(task, fd, &f_mode)) {
+			tid_fd_update_inode(task, inode, f_mode);
+			put_task_struct(task);
+			return 1;
+		}
+		put_task_struct(task);
+	}
+	return 0;
+}
+
+static const struct dentry_operations tid_fd_dentry_operations = {
+	.d_revalidate	= tid_fd_revalidate,
+	.d_delete	= pid_delete_dentry,
+};
+
+static int proc_fd_link(struct dentry *dentry, struct path *path,
+			struct task_struct *task)
+{
+	int ret = -ENOENT;
+	unsigned int fd = proc_fd(d_inode(dentry));
+	struct file *fd_file;
+
+	fd_file = fget_task(task, fd);
+	if (fd_file) {
+		*path = fd_file->f_path;
+		path_get(&fd_file->f_path);
+		ret = 0;
+		fput(fd_file);
+	}
+
+	return ret;
+}
+
+struct fd_data {
+	fmode_t mode;
+	unsigned fd;
+};
+
+static struct dentry *proc_fd_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
+{
+	const struct fd_data *data = ptr;
+	struct proc_inode *ei;
+	struct inode *inode;
+
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK);
+	if (!inode)
+		return ERR_PTR(-ENOENT);
+
+	ei = PROC_I(inode);
+	ei->fd = data->fd;
+
+	inode->i_op = &proc_pid_link_inode_operations;
+	inode->i_size = 64;
+
+	ei->op.proc_get_link = proc_fd_link;
+	tid_fd_update_inode(task, inode, data->mode);
+
+	return proc_splice_unmountable(inode, dentry,
+				       &tid_fd_dentry_operations);
+}
+
+static struct dentry *proc_lookupfd_common(struct inode *dir,
+					   struct dentry *dentry,
+					   instantiate_t instantiate)
+{
+	struct task_struct *task = get_proc_task(dir);
+	struct fd_data data = {.fd = name_to_int(&dentry->d_name)};
+	struct dentry *result = ERR_PTR(-ENOENT);
+
+	if (!task)
+		goto out_no_task;
+	if (data.fd == ~0U)
+		goto out;
+	if (!tid_fd_mode(task, data.fd, &data.mode))
+		goto out;
+
+	result = instantiate(dentry, task, &data);
+out:
+	put_task_struct(task);
+out_no_task:
+	return result;
+}
+
+static int proc_readfd_common(struct file *file, struct dir_context *ctx,
+			      instantiate_t instantiate)
+{
+	struct task_struct *p = get_proc_task(file_inode(file));
+	unsigned int fd;
+
+	if (!p)
+		return -ENOENT;
+
+	if (!dir_emit_dots(file, ctx))
+		goto out;
+
+	for (fd = ctx->pos - 2;; fd++) {
+		struct file *f;
+		struct fd_data data;
+		char name[10 + 1];
+		unsigned int len;
+
+		f = fget_task_next(p, &fd);
+		ctx->pos = fd + 2LL;
+		if (!f)
+			break;
+		data.mode = f->f_mode;
+		fput(f);
+		data.fd = fd;
+
+		len = snprintf(name, sizeof(name), "%u", fd);
+		if (!proc_fill_cache(file, ctx,
+				     name, len, instantiate, p,
+				     &data))
+			break;
+		cond_resched();
+	}
+out:
+	put_task_struct(p);
+	return 0;
+}
+
+static int proc_readfd_count(struct inode *inode, loff_t *count)
+{
+	struct task_struct *p = get_proc_task(inode);
+	struct fdtable *fdt;
+
+	if (!p)
+		return -ENOENT;
+
+	task_lock(p);
+	if (p->files) {
+		rcu_read_lock();
+
+		fdt = files_fdtable(p->files);
+		*count = bitmap_weight(fdt->open_fds, fdt->max_fds);
+
+		rcu_read_unlock();
+	}
+	task_unlock(p);
+
+	put_task_struct(p);
+
+	return 0;
+}
+
+static int proc_fd_iterate(struct file *file, struct dir_context *ctx)
+{
+	return proc_readfd_common(file, ctx, proc_fd_instantiate);
+}
+
+const struct file_operations proc_fd_operations = {
+	.read		= generic_read_dir,
+	.iterate_shared	= proc_fd_iterate,
+	.llseek		= generic_file_llseek,
+};
+
+static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
+				    unsigned int flags)
+{
+	return proc_lookupfd_common(dir, dentry, proc_fd_instantiate);
+}
+
+/*
+ * /proc/pid/fd needs a special permission handler so that a process can still
+ * access /proc/self/fd after it has executed a setuid().
+ */
+int proc_fd_permission(struct mnt_idmap *idmap,
+		       struct inode *inode, int mask)
+{
+	struct task_struct *p;
+	int rv;
+
+	rv = generic_permission(&nop_mnt_idmap, inode, mask);
+	if (rv == 0)
+		return rv;
+
+	rcu_read_lock();
+	p = pid_task(proc_pid(inode), PIDTYPE_PID);
+	if (p && same_thread_group(p, current))
+		rv = 0;
+	rcu_read_unlock();
+
+	return rv;
+}
+
+static int proc_fd_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);
+
+	generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
+	return proc_readfd_count(inode, &stat->size);
+}
+
+const struct inode_operations proc_fd_inode_operations = {
+	.lookup		= proc_lookupfd,
+	.permission	= proc_fd_permission,
+	.getattr	= proc_fd_getattr,
+	.setattr	= proc_nochmod_setattr,
+};
+
+static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
+{
+	const struct fd_data *data = ptr;
+	struct proc_inode *ei;
+	struct inode *inode;
+
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFREG | S_IRUGO);
+	if (!inode)
+		return ERR_PTR(-ENOENT);
+
+	ei = PROC_I(inode);
+	ei->fd = data->fd;
+
+	inode->i_op = &proc_fdinfo_file_inode_operations;
+
+	inode->i_fop = &proc_fdinfo_file_operations;
+	tid_fd_update_inode(task, inode, 0);
+
+	return proc_splice_unmountable(inode, dentry,
+				       &tid_fd_dentry_operations);
+}
+
+static struct dentry *
+proc_lookupfdinfo(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
+	return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
+}
+
+static int proc_fdinfo_iterate(struct file *file, struct dir_context *ctx)
+{
+	return proc_readfd_common(file, ctx,
+				  proc_fdinfo_instantiate);
+}
+
+const struct inode_operations proc_fdinfo_inode_operations = {
+	.lookup		= proc_lookupfdinfo,
+	.permission	= proc_fdinfo_permission,
+	.setattr	= proc_nochmod_setattr,
+};
+
+const struct file_operations proc_fdinfo_operations = {
+	.read		= generic_read_dir,
+	.iterate_shared	= proc_fdinfo_iterate,
+	.llseek		= generic_file_llseek,
+};