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, 423 insertions, 0 deletions

diff --git a/fs/eventfd.c b/fs/eventfd.c
new file mode 100644
index 000000000..9d33a0275
--- /dev/null
+++ b/fs/eventfd.c
@@ -0,0 +1,423 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  fs/eventfd.c
+ *
+ *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
+ *
+ */
+
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/sched/signal.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/anon_inodes.h>
+#include <linux/syscalls.h>
+#include <linux/export.h>
+#include <linux/kref.h>
+#include <linux/eventfd.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/idr.h>
+#include <linux/uio.h>
+
+static DEFINE_IDA(eventfd_ida);
+
+struct eventfd_ctx {
+	struct kref kref;
+	wait_queue_head_t wqh;
+	/*
+	 * Every time that a write(2) is performed on an eventfd, the
+	 * value of the __u64 being written is added to "count" and a
+	 * wakeup is performed on "wqh". If EFD_SEMAPHORE flag was not
+	 * specified, a read(2) will return the "count" value to userspace,
+	 * and will reset "count" to zero. The kernel side eventfd_signal()
+	 * also, adds to the "count" counter and issue a wakeup.
+	 */
+	__u64 count;
+	unsigned int flags;
+	int id;
+};
+
+/**
+ * eventfd_signal_mask - Increment the event counter
+ * @ctx: [in] Pointer to the eventfd context.
+ * @mask: [in] poll mask
+ *
+ * This function is supposed to be called by the kernel in paths that do not
+ * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
+ * value, and we signal this as overflow condition by returning a EPOLLERR
+ * to poll(2).
+ */
+void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
+{
+	unsigned long flags;
+
+	/*
+	 * Deadlock or stack overflow issues can happen if we recurse here
+	 * through waitqueue wakeup handlers. If the caller users potentially
+	 * nested waitqueues with custom wakeup handlers, then it should
+	 * check eventfd_signal_allowed() before calling this function. If
+	 * it returns false, the eventfd_signal() call should be deferred to a
+	 * safe context.
+	 */
+	if (WARN_ON_ONCE(current->in_eventfd))
+		return;
+
+	spin_lock_irqsave(&ctx->wqh.lock, flags);
+	current->in_eventfd = 1;
+	if (ctx->count < ULLONG_MAX)
+		ctx->count++;
+	if (waitqueue_active(&ctx->wqh))
+		wake_up_locked_poll(&ctx->wqh, EPOLLIN | mask);
+	current->in_eventfd = 0;
+	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
+}
+EXPORT_SYMBOL_GPL(eventfd_signal_mask);
+
+static void eventfd_free_ctx(struct eventfd_ctx *ctx)
+{
+	if (ctx->id >= 0)
+		ida_free(&eventfd_ida, ctx->id);
+	kfree(ctx);
+}
+
+static void eventfd_free(struct kref *kref)
+{
+	struct eventfd_ctx *ctx = container_of(kref, struct eventfd_ctx, kref);
+
+	eventfd_free_ctx(ctx);
+}
+
+/**
+ * eventfd_ctx_put - Releases a reference to the internal eventfd context.
+ * @ctx: [in] Pointer to eventfd context.
+ *
+ * The eventfd context reference must have been previously acquired either
+ * with eventfd_ctx_fdget() or eventfd_ctx_fileget().
+ */
+void eventfd_ctx_put(struct eventfd_ctx *ctx)
+{
+	kref_put(&ctx->kref, eventfd_free);
+}
+EXPORT_SYMBOL_GPL(eventfd_ctx_put);
+
+static int eventfd_release(struct inode *inode, struct file *file)
+{
+	struct eventfd_ctx *ctx = file->private_data;
+
+	wake_up_poll(&ctx->wqh, EPOLLHUP);
+	eventfd_ctx_put(ctx);
+	return 0;
+}
+
+static __poll_t eventfd_poll(struct file *file, poll_table *wait)
+{
+	struct eventfd_ctx *ctx = file->private_data;
+	__poll_t events = 0;
+	u64 count;
+
+	poll_wait(file, &ctx->wqh, wait);
+
+	/*
+	 * All writes to ctx->count occur within ctx->wqh.lock.  This read
+	 * can be done outside ctx->wqh.lock because we know that poll_wait
+	 * takes that lock (through add_wait_queue) if our caller will sleep.
+	 *
+	 * The read _can_ therefore seep into add_wait_queue's critical
+	 * section, but cannot move above it!  add_wait_queue's spin_lock acts
+	 * as an acquire barrier and ensures that the read be ordered properly
+	 * against the writes.  The following CAN happen and is safe:
+	 *
+	 *     poll                               write
+	 *     -----------------                  ------------
+	 *     lock ctx->wqh.lock (in poll_wait)
+	 *     count = ctx->count
+	 *     __add_wait_queue
+	 *     unlock ctx->wqh.lock
+	 *                                        lock ctx->qwh.lock
+	 *                                        ctx->count += n
+	 *                                        if (waitqueue_active)
+	 *                                          wake_up_locked_poll
+	 *                                        unlock ctx->qwh.lock
+	 *     eventfd_poll returns 0
+	 *
+	 * but the following, which would miss a wakeup, cannot happen:
+	 *
+	 *     poll                               write
+	 *     -----------------                  ------------
+	 *     count = ctx->count (INVALID!)
+	 *                                        lock ctx->qwh.lock
+	 *                                        ctx->count += n
+	 *                                        **waitqueue_active is false**
+	 *                                        **no wake_up_locked_poll!**
+	 *                                        unlock ctx->qwh.lock
+	 *     lock ctx->wqh.lock (in poll_wait)
+	 *     __add_wait_queue
+	 *     unlock ctx->wqh.lock
+	 *     eventfd_poll returns 0
+	 */
+	count = READ_ONCE(ctx->count);
+
+	if (count > 0)
+		events |= EPOLLIN;
+	if (count == ULLONG_MAX)
+		events |= EPOLLERR;
+	if (ULLONG_MAX - 1 > count)
+		events |= EPOLLOUT;
+
+	return events;
+}
+
+void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
+{
+	lockdep_assert_held(&ctx->wqh.lock);
+
+	*cnt = ((ctx->flags & EFD_SEMAPHORE) && ctx->count) ? 1 : ctx->count;
+	ctx->count -= *cnt;
+}
+EXPORT_SYMBOL_GPL(eventfd_ctx_do_read);
+
+/**
+ * eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue.
+ * @ctx: [in] Pointer to eventfd context.
+ * @wait: [in] Wait queue to be removed.
+ * @cnt: [out] Pointer to the 64-bit counter value.
+ *
+ * Returns %0 if successful, or the following error codes:
+ *
+ * -EAGAIN      : The operation would have blocked.
+ *
+ * This is used to atomically remove a wait queue entry from the eventfd wait
+ * queue head, and read/reset the counter value.
+ */
+int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
+				  __u64 *cnt)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctx->wqh.lock, flags);
+	eventfd_ctx_do_read(ctx, cnt);
+	__remove_wait_queue(&ctx->wqh, wait);
+	if (*cnt != 0 && waitqueue_active(&ctx->wqh))
+		wake_up_locked_poll(&ctx->wqh, EPOLLOUT);
+	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
+
+	return *cnt != 0 ? 0 : -EAGAIN;
+}
+EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue);
+
+static ssize_t eventfd_read(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct eventfd_ctx *ctx = file->private_data;
+	__u64 ucnt = 0;
+
+	if (iov_iter_count(to) < sizeof(ucnt))
+		return -EINVAL;
+	spin_lock_irq(&ctx->wqh.lock);
+	if (!ctx->count) {
+		if ((file->f_flags & O_NONBLOCK) ||
+		    (iocb->ki_flags & IOCB_NOWAIT)) {
+			spin_unlock_irq(&ctx->wqh.lock);
+			return -EAGAIN;
+		}
+
+		if (wait_event_interruptible_locked_irq(ctx->wqh, ctx->count)) {
+			spin_unlock_irq(&ctx->wqh.lock);
+			return -ERESTARTSYS;
+		}
+	}
+	eventfd_ctx_do_read(ctx, &ucnt);
+	current->in_eventfd = 1;
+	if (waitqueue_active(&ctx->wqh))
+		wake_up_locked_poll(&ctx->wqh, EPOLLOUT);
+	current->in_eventfd = 0;
+	spin_unlock_irq(&ctx->wqh.lock);
+	if (unlikely(copy_to_iter(&ucnt, sizeof(ucnt), to) != sizeof(ucnt)))
+		return -EFAULT;
+
+	return sizeof(ucnt);
+}
+
+static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count,
+			     loff_t *ppos)
+{
+	struct eventfd_ctx *ctx = file->private_data;
+	ssize_t res;
+	__u64 ucnt;
+
+	if (count != sizeof(ucnt))
+		return -EINVAL;
+	if (copy_from_user(&ucnt, buf, sizeof(ucnt)))
+		return -EFAULT;
+	if (ucnt == ULLONG_MAX)
+		return -EINVAL;
+	spin_lock_irq(&ctx->wqh.lock);
+	res = -EAGAIN;
+	if (ULLONG_MAX - ctx->count > ucnt)
+		res = sizeof(ucnt);
+	else if (!(file->f_flags & O_NONBLOCK)) {
+		res = wait_event_interruptible_locked_irq(ctx->wqh,
+				ULLONG_MAX - ctx->count > ucnt);
+		if (!res)
+			res = sizeof(ucnt);
+	}
+	if (likely(res > 0)) {
+		ctx->count += ucnt;
+		current->in_eventfd = 1;
+		if (waitqueue_active(&ctx->wqh))
+			wake_up_locked_poll(&ctx->wqh, EPOLLIN);
+		current->in_eventfd = 0;
+	}
+	spin_unlock_irq(&ctx->wqh.lock);
+
+	return res;
+}
+
+#ifdef CONFIG_PROC_FS
+static void eventfd_show_fdinfo(struct seq_file *m, struct file *f)
+{
+	struct eventfd_ctx *ctx = f->private_data;
+	__u64 cnt;
+
+	spin_lock_irq(&ctx->wqh.lock);
+	cnt = ctx->count;
+	spin_unlock_irq(&ctx->wqh.lock);
+
+	seq_printf(m,
+		   "eventfd-count: %16llx\n"
+		   "eventfd-id: %d\n"
+		   "eventfd-semaphore: %d\n",
+		   cnt,
+		   ctx->id,
+		   !!(ctx->flags & EFD_SEMAPHORE));
+}
+#endif
+
+static const struct file_operations eventfd_fops = {
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= eventfd_show_fdinfo,
+#endif
+	.release	= eventfd_release,
+	.poll		= eventfd_poll,
+	.read_iter	= eventfd_read,
+	.write		= eventfd_write,
+	.llseek		= noop_llseek,
+};
+
+/**
+ * eventfd_fget - Acquire a reference of an eventfd file descriptor.
+ * @fd: [in] Eventfd file descriptor.
+ *
+ * Returns a pointer to the eventfd file structure in case of success, or the
+ * following error pointer:
+ *
+ * -EBADF    : Invalid @fd file descriptor.
+ * -EINVAL   : The @fd file descriptor is not an eventfd file.
+ */
+struct file *eventfd_fget(int fd)
+{
+	struct file *file;
+
+	file = fget(fd);
+	if (!file)
+		return ERR_PTR(-EBADF);
+	if (file->f_op != &eventfd_fops) {
+		fput(file);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return file;
+}
+EXPORT_SYMBOL_GPL(eventfd_fget);
+
+/**
+ * eventfd_ctx_fdget - Acquires a reference to the internal eventfd context.
+ * @fd: [in] Eventfd file descriptor.
+ *
+ * Returns a pointer to the internal eventfd context, otherwise the error
+ * pointers returned by the following functions:
+ *
+ * eventfd_fget
+ */
+struct eventfd_ctx *eventfd_ctx_fdget(int fd)
+{
+	CLASS(fd, f)(fd);
+	if (fd_empty(f))
+		return ERR_PTR(-EBADF);
+	return eventfd_ctx_fileget(fd_file(f));
+}
+EXPORT_SYMBOL_GPL(eventfd_ctx_fdget);
+
+/**
+ * eventfd_ctx_fileget - Acquires a reference to the internal eventfd context.
+ * @file: [in] Eventfd file pointer.
+ *
+ * Returns a pointer to the internal eventfd context, otherwise the error
+ * pointer:
+ *
+ * -EINVAL   : The @fd file descriptor is not an eventfd file.
+ */
+struct eventfd_ctx *eventfd_ctx_fileget(struct file *file)
+{
+	struct eventfd_ctx *ctx;
+
+	if (file->f_op != &eventfd_fops)
+		return ERR_PTR(-EINVAL);
+
+	ctx = file->private_data;
+	kref_get(&ctx->kref);
+	return ctx;
+}
+EXPORT_SYMBOL_GPL(eventfd_ctx_fileget);
+
+static int do_eventfd(unsigned int count, int flags)
+{
+	struct eventfd_ctx *ctx __free(kfree) = NULL;
+
+	/* Check the EFD_* constants for consistency.  */
+	BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC);
+	BUILD_BUG_ON(EFD_NONBLOCK != O_NONBLOCK);
+	BUILD_BUG_ON(EFD_SEMAPHORE != (1 << 0));
+
+	if (flags & ~EFD_FLAGS_SET)
+		return -EINVAL;
+
+	ctx = kmalloc_obj(*ctx);
+	if (!ctx)
+		return -ENOMEM;
+
+	kref_init(&ctx->kref);
+	init_waitqueue_head(&ctx->wqh);
+	ctx->count = count;
+	ctx->flags = flags;
+
+	flags &= EFD_SHARED_FCNTL_FLAGS;
+	flags |= O_RDWR;
+
+	FD_PREPARE(fdf, flags,
+		   anon_inode_getfile_fmode("[eventfd]", &eventfd_fops, ctx,
+					    flags, FMODE_NOWAIT));
+	if (fdf.err)
+		return fdf.err;
+
+	ctx->id = ida_alloc(&eventfd_ida, GFP_KERNEL);
+	retain_and_null_ptr(ctx);
+	return fd_publish(fdf);
+}
+
+SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags)
+{
+	return do_eventfd(count, flags);
+}
+
+SYSCALL_DEFINE1(eventfd, unsigned int, count)
+{
+	return do_eventfd(count, 0);
+}
+