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, 290 insertions, 0 deletions

diff --git a/security/keys/big_key.c b/security/keys/big_key.c
new file mode 100644
index 000000000..268f702df
--- /dev/null
+++ b/security/keys/big_key.c
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Large capacity key type
+ *
+ * Copyright (C) 2017-2020 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#define pr_fmt(fmt) "big_key: "fmt
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/file.h>
+#include <linux/shmem_fs.h>
+#include <linux/err.h>
+#include <linux/random.h>
+#include <keys/user-type.h>
+#include <keys/big_key-type.h>
+#include <crypto/chacha20poly1305.h>
+
+/*
+ * Layout of key payload words.
+ */
+struct big_key_payload {
+	u8 *data;
+	struct path path;
+	size_t length;
+};
+#define to_big_key_payload(payload)			\
+	(struct big_key_payload *)((payload).data)
+
+/*
+ * If the data is under this limit, there's no point creating a shm file to
+ * hold it as the permanently resident metadata for the shmem fs will be at
+ * least as large as the data.
+ */
+#define BIG_KEY_FILE_THRESHOLD (sizeof(struct inode) + sizeof(struct dentry))
+
+/*
+ * big_key defined keys take an arbitrary string as the description and an
+ * arbitrary blob of data as the payload
+ */
+struct key_type key_type_big_key = {
+	.name			= "big_key",
+	.preparse		= big_key_preparse,
+	.free_preparse		= big_key_free_preparse,
+	.instantiate		= generic_key_instantiate,
+	.revoke			= big_key_revoke,
+	.destroy		= big_key_destroy,
+	.describe		= big_key_describe,
+	.read			= big_key_read,
+	.update			= big_key_update,
+};
+
+/*
+ * Preparse a big key
+ */
+int big_key_preparse(struct key_preparsed_payload *prep)
+{
+	struct big_key_payload *payload = to_big_key_payload(prep->payload);
+	struct file *file;
+	u8 *buf, *enckey;
+	ssize_t written;
+	size_t datalen = prep->datalen;
+	size_t enclen = datalen + CHACHA20POLY1305_AUTHTAG_SIZE;
+	int ret;
+
+	BUILD_BUG_ON(sizeof(*payload) != sizeof(prep->payload.data));
+
+	if (datalen == 0 || datalen > 1024 * 1024 || !prep->data)
+		return -EINVAL;
+
+	/* Set an arbitrary quota */
+	prep->quotalen = 16;
+
+	payload->length = datalen;
+
+	if (datalen > BIG_KEY_FILE_THRESHOLD) {
+		/* Create a shmem file to store the data in.  This will permit the data
+		 * to be swapped out if needed.
+		 *
+		 * File content is stored encrypted with randomly generated key.
+		 * Since the key is random for each file, we can set the nonce
+		 * to zero, provided we never define a ->update() call.
+		 */
+		loff_t pos = 0;
+
+		buf = kvmalloc(enclen, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+
+		/* generate random key */
+		enckey = kmalloc(CHACHA20POLY1305_KEY_SIZE, GFP_KERNEL);
+		if (!enckey) {
+			ret = -ENOMEM;
+			goto error;
+		}
+		ret = get_random_bytes_wait(enckey, CHACHA20POLY1305_KEY_SIZE);
+		if (unlikely(ret))
+			goto err_enckey;
+
+		/* encrypt data */
+		chacha20poly1305_encrypt(buf, prep->data, datalen, NULL, 0,
+					 0, enckey);
+
+		/* save aligned data to file */
+		file = shmem_kernel_file_setup("", enclen, EMPTY_VMA_FLAGS);
+		if (IS_ERR(file)) {
+			ret = PTR_ERR(file);
+			goto err_enckey;
+		}
+
+		written = kernel_write(file, buf, enclen, &pos);
+		if (written != enclen) {
+			ret = written;
+			if (written >= 0)
+				ret = -EIO;
+			goto err_fput;
+		}
+
+		/* Pin the mount and dentry to the key so that we can open it again
+		 * later
+		 */
+		payload->data = enckey;
+		payload->path = file->f_path;
+		path_get(&payload->path);
+		fput(file);
+		kvfree_sensitive(buf, enclen);
+	} else {
+		/* Just store the data in a buffer */
+		void *data = kmalloc(datalen, GFP_KERNEL);
+
+		if (!data)
+			return -ENOMEM;
+
+		payload->data = data;
+		memcpy(data, prep->data, prep->datalen);
+	}
+	return 0;
+
+err_fput:
+	fput(file);
+err_enckey:
+	kfree_sensitive(enckey);
+error:
+	kvfree_sensitive(buf, enclen);
+	return ret;
+}
+
+/*
+ * Clear preparsement.
+ */
+void big_key_free_preparse(struct key_preparsed_payload *prep)
+{
+	struct big_key_payload *payload = to_big_key_payload(prep->payload);
+
+	if (prep->datalen > BIG_KEY_FILE_THRESHOLD)
+		path_put(&payload->path);
+	kfree_sensitive(payload->data);
+}
+
+/*
+ * dispose of the links from a revoked keyring
+ * - called with the key sem write-locked
+ */
+void big_key_revoke(struct key *key)
+{
+	struct big_key_payload *payload = to_big_key_payload(key->payload);
+
+	/* clear the quota */
+	key_payload_reserve(key, 0);
+	if (key_is_positive(key) && payload->length > BIG_KEY_FILE_THRESHOLD)
+		vfs_truncate(&payload->path, 0);
+}
+
+/*
+ * dispose of the data dangling from the corpse of a big_key key
+ */
+void big_key_destroy(struct key *key)
+{
+	struct big_key_payload *payload = to_big_key_payload(key->payload);
+
+	if (payload->length > BIG_KEY_FILE_THRESHOLD) {
+		path_put(&payload->path);
+		payload->path.mnt = NULL;
+		payload->path.dentry = NULL;
+	}
+	kfree_sensitive(payload->data);
+	payload->data = NULL;
+}
+
+/*
+ * Update a big key
+ */
+int big_key_update(struct key *key, struct key_preparsed_payload *prep)
+{
+	int ret;
+
+	ret = key_payload_reserve(key, prep->datalen);
+	if (ret < 0)
+		return ret;
+
+	if (key_is_positive(key))
+		big_key_destroy(key);
+
+	return generic_key_instantiate(key, prep);
+}
+
+/*
+ * describe the big_key key
+ */
+void big_key_describe(const struct key *key, struct seq_file *m)
+{
+	struct big_key_payload *payload = to_big_key_payload(key->payload);
+
+	seq_puts(m, key->description);
+
+	if (key_is_positive(key))
+		seq_printf(m, ": %zu [%s]",
+			   payload->length,
+			   payload->length > BIG_KEY_FILE_THRESHOLD ? "file" : "buff");
+}
+
+/*
+ * read the key data
+ * - the key's semaphore is read-locked
+ */
+long big_key_read(const struct key *key, char *buffer, size_t buflen)
+{
+	struct big_key_payload *payload = to_big_key_payload(key->payload);
+	size_t datalen = payload->length;
+	long ret;
+
+	if (!buffer || buflen < datalen)
+		return datalen;
+
+	if (datalen > BIG_KEY_FILE_THRESHOLD) {
+		struct file *file;
+		u8 *buf, *enckey = payload->data;
+		size_t enclen = datalen + CHACHA20POLY1305_AUTHTAG_SIZE;
+		loff_t pos = 0;
+
+		buf = kvmalloc(enclen, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+
+		file = dentry_open(&payload->path, O_RDONLY, current_cred());
+		if (IS_ERR(file)) {
+			ret = PTR_ERR(file);
+			goto error;
+		}
+
+		/* read file to kernel and decrypt */
+		ret = kernel_read(file, buf, enclen, &pos);
+		if (ret != enclen) {
+			if (ret >= 0)
+				ret = -EIO;
+			goto err_fput;
+		}
+
+		ret = chacha20poly1305_decrypt(buf, buf, enclen, NULL, 0, 0,
+					       enckey) ? 0 : -EBADMSG;
+		if (unlikely(ret))
+			goto err_fput;
+
+		ret = datalen;
+
+		/* copy out decrypted data */
+		memcpy(buffer, buf, datalen);
+
+err_fput:
+		fput(file);
+error:
+		kvfree_sensitive(buf, enclen);
+	} else {
+		ret = datalen;
+		memcpy(buffer, payload->data, datalen);
+	}
+
+	return ret;
+}
+
+/*
+ * Register key type
+ */
+static int __init big_key_init(void)
+{
+	return register_key_type(&key_type_big_key);
+}
+
+late_initcall(big_key_init);