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, 204 insertions, 0 deletions

diff --git a/fs/verity/read_metadata.c b/fs/verity/read_metadata.c
new file mode 100644
index 000000000..b4c089243
--- /dev/null
+++ b/fs/verity/read_metadata.c
@@ -0,0 +1,204 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Ioctl to read verity metadata
+ *
+ * Copyright 2021 Google LLC
+ */
+
+#include "fsverity_private.h"
+
+#include <linux/backing-dev.h>
+#include <linux/export.h>
+#include <linux/highmem.h>
+#include <linux/sched/signal.h>
+#include <linux/uaccess.h>
+
+static int fsverity_read_merkle_tree(struct inode *inode,
+				     const struct fsverity_info *vi,
+				     void __user *buf, u64 offset, int length)
+{
+	const struct fsverity_operations *vops = inode->i_sb->s_vop;
+	u64 end_offset;
+	unsigned int offs_in_page;
+	pgoff_t index, last_index;
+	int retval = 0;
+	int err = 0;
+
+	end_offset = min(offset + length, vi->tree_params.tree_size);
+	if (offset >= end_offset)
+		return 0;
+	offs_in_page = offset_in_page(offset);
+	index = offset >> PAGE_SHIFT;
+	last_index = (end_offset - 1) >> PAGE_SHIFT;
+
+	/*
+	 * Kick off readahead for the range we are going to read to ensure a
+	 * single large sequential read instead of lots of small ones.
+	 */
+	if (inode->i_sb->s_vop->readahead_merkle_tree) {
+		filemap_invalidate_lock_shared(inode->i_mapping);
+		inode->i_sb->s_vop->readahead_merkle_tree(
+			inode, index, last_index - index + 1);
+		filemap_invalidate_unlock_shared(inode->i_mapping);
+	}
+
+	/*
+	 * Iterate through each Merkle tree page in the requested range and copy
+	 * the requested portion to userspace.  Note that the Merkle tree block
+	 * size isn't important here, as we are returning a byte stream; i.e.,
+	 * we can just work with pages even if the tree block size != PAGE_SIZE.
+	 */
+	for (; index <= last_index; index++) {
+		unsigned int bytes_to_copy = min_t(u64, end_offset - offset,
+						   PAGE_SIZE - offs_in_page);
+		struct page *page;
+		const void *virt;
+
+		page = vops->read_merkle_tree_page(inode, index);
+		if (IS_ERR(page)) {
+			err = PTR_ERR(page);
+			fsverity_err(inode,
+				     "Error %d reading Merkle tree page %lu",
+				     err, index);
+			break;
+		}
+
+		virt = kmap_local_page(page);
+		if (copy_to_user(buf, virt + offs_in_page, bytes_to_copy)) {
+			kunmap_local(virt);
+			put_page(page);
+			err = -EFAULT;
+			break;
+		}
+		kunmap_local(virt);
+		put_page(page);
+
+		retval += bytes_to_copy;
+		buf += bytes_to_copy;
+		offset += bytes_to_copy;
+
+		if (fatal_signal_pending(current))  {
+			err = -EINTR;
+			break;
+		}
+		cond_resched();
+		offs_in_page = 0;
+	}
+	return retval ? retval : err;
+}
+
+/* Copy the requested portion of the buffer to userspace. */
+static int fsverity_read_buffer(void __user *dst, u64 offset, int length,
+				const void *src, size_t src_length)
+{
+	if (offset >= src_length)
+		return 0;
+	src += offset;
+	src_length -= offset;
+
+	length = min_t(size_t, length, src_length);
+
+	if (copy_to_user(dst, src, length))
+		return -EFAULT;
+
+	return length;
+}
+
+static int fsverity_read_descriptor(struct inode *inode,
+				    void __user *buf, u64 offset, int length)
+{
+	struct fsverity_descriptor *desc;
+	size_t desc_size;
+	int res;
+
+	res = fsverity_get_descriptor(inode, &desc);
+	if (res)
+		return res;
+
+	/* don't include the builtin signature */
+	desc_size = offsetof(struct fsverity_descriptor, signature);
+	desc->sig_size = 0;
+
+	res = fsverity_read_buffer(buf, offset, length, desc, desc_size);
+
+	kfree(desc);
+	return res;
+}
+
+static int fsverity_read_signature(struct inode *inode,
+				   void __user *buf, u64 offset, int length)
+{
+	struct fsverity_descriptor *desc;
+	int res;
+
+	res = fsverity_get_descriptor(inode, &desc);
+	if (res)
+		return res;
+
+	if (desc->sig_size == 0) {
+		res = -ENODATA;
+		goto out;
+	}
+
+	/*
+	 * Include only the builtin signature.  fsverity_get_descriptor()
+	 * already verified that sig_size is in-bounds.
+	 */
+	res = fsverity_read_buffer(buf, offset, length, desc->signature,
+				   le32_to_cpu(desc->sig_size));
+out:
+	kfree(desc);
+	return res;
+}
+
+/**
+ * fsverity_ioctl_read_metadata() - read verity metadata from a file
+ * @filp: file to read the metadata from
+ * @uarg: user pointer to fsverity_read_metadata_arg
+ *
+ * Return: length read on success, 0 on EOF, -errno on failure
+ */
+int fsverity_ioctl_read_metadata(struct file *filp, const void __user *uarg)
+{
+	struct inode *inode = file_inode(filp);
+	const struct fsverity_info *vi;
+	struct fsverity_read_metadata_arg arg;
+	int length;
+	void __user *buf;
+
+	vi = fsverity_get_info(inode);
+	if (!vi)
+		return -ENODATA; /* not a verity file */
+	/*
+	 * Note that we don't have to explicitly check that the file is open for
+	 * reading, since verity files can only be opened for reading.
+	 */
+
+	if (copy_from_user(&arg, uarg, sizeof(arg)))
+		return -EFAULT;
+
+	if (arg.__reserved)
+		return -EINVAL;
+
+	/* offset + length must not overflow. */
+	if (arg.offset + arg.length < arg.offset)
+		return -EINVAL;
+
+	/* Ensure that the return value will fit in INT_MAX. */
+	length = min_t(u64, arg.length, INT_MAX);
+
+	buf = u64_to_user_ptr(arg.buf_ptr);
+
+	switch (arg.metadata_type) {
+	case FS_VERITY_METADATA_TYPE_MERKLE_TREE:
+		return fsverity_read_merkle_tree(inode, vi, buf, arg.offset,
+						 length);
+	case FS_VERITY_METADATA_TYPE_DESCRIPTOR:
+		return fsverity_read_descriptor(inode, buf, arg.offset, length);
+	case FS_VERITY_METADATA_TYPE_SIGNATURE:
+		return fsverity_read_signature(inode, buf, arg.offset, length);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL_GPL(fsverity_ioctl_read_metadata);