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, 453 insertions, 0 deletions

diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
new file mode 100644
index 000000000..50a000310
--- /dev/null
+++ b/fs/cachefiles/interface.c
@@ -0,0 +1,453 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* FS-Cache interface to CacheFiles
+ *
+ * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/slab.h>
+#include <linux/mount.h>
+#include <linux/xattr.h>
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/falloc.h>
+#include <trace/events/fscache.h>
+#include "internal.h"
+
+static atomic_t cachefiles_object_debug_id;
+
+/*
+ * Allocate a cache object record.
+ */
+static
+struct cachefiles_object *cachefiles_alloc_object(struct fscache_cookie *cookie)
+{
+	struct fscache_volume *vcookie = cookie->volume;
+	struct cachefiles_volume *volume = vcookie->cache_priv;
+	struct cachefiles_object *object;
+
+	_enter("{%s},%x,", vcookie->key, cookie->debug_id);
+
+	object = kmem_cache_zalloc(cachefiles_object_jar, GFP_KERNEL);
+	if (!object)
+		return NULL;
+
+	refcount_set(&object->ref, 1);
+
+	spin_lock_init(&object->lock);
+	INIT_LIST_HEAD(&object->cache_link);
+	object->volume = volume;
+	object->debug_id = atomic_inc_return(&cachefiles_object_debug_id);
+	object->cookie = fscache_get_cookie(cookie, fscache_cookie_get_attach_object);
+
+	fscache_count_object(vcookie->cache);
+	trace_cachefiles_ref(object->debug_id, cookie->debug_id, 1,
+			     cachefiles_obj_new);
+	return object;
+}
+
+/*
+ * Note that an object has been seen.
+ */
+void cachefiles_see_object(struct cachefiles_object *object,
+			   enum cachefiles_obj_ref_trace why)
+{
+	trace_cachefiles_ref(object->debug_id, object->cookie->debug_id,
+			     refcount_read(&object->ref), why);
+}
+
+/*
+ * Increment the usage count on an object;
+ */
+struct cachefiles_object *cachefiles_grab_object(struct cachefiles_object *object,
+						 enum cachefiles_obj_ref_trace why)
+{
+	int r;
+
+	__refcount_inc(&object->ref, &r);
+	trace_cachefiles_ref(object->debug_id, object->cookie->debug_id, r, why);
+	return object;
+}
+
+/*
+ * dispose of a reference to an object
+ */
+void cachefiles_put_object(struct cachefiles_object *object,
+			   enum cachefiles_obj_ref_trace why)
+{
+	unsigned int object_debug_id = object->debug_id;
+	unsigned int cookie_debug_id = object->cookie->debug_id;
+	struct fscache_cache *cache;
+	bool done;
+	int r;
+
+	done = __refcount_dec_and_test(&object->ref, &r);
+	trace_cachefiles_ref(object_debug_id, cookie_debug_id, r, why);
+	if (done) {
+		_debug("- kill object OBJ%x", object_debug_id);
+
+		ASSERTCMP(object->file, ==, NULL);
+
+		kfree(object->d_name);
+		cache = object->volume->cache->cache;
+		fscache_put_cookie(object->cookie, fscache_cookie_put_object);
+		object->cookie = NULL;
+		kmem_cache_free(cachefiles_object_jar, object);
+		fscache_uncount_object(cache);
+	}
+
+	_leave("");
+}
+
+/*
+ * Adjust the size of a cache file if necessary to match the DIO size.  We keep
+ * the EOF marker a multiple of DIO blocks so that we don't fall back to doing
+ * non-DIO for a partial block straddling the EOF, but we also have to be
+ * careful of someone expanding the file and accidentally accreting the
+ * padding.
+ */
+static int cachefiles_adjust_size(struct cachefiles_object *object)
+{
+	struct iattr newattrs;
+	struct file *file = object->file;
+	uint64_t ni_size;
+	loff_t oi_size;
+	int ret;
+
+	ni_size = object->cookie->object_size;
+	ni_size = round_up(ni_size, CACHEFILES_DIO_BLOCK_SIZE);
+
+	_enter("{OBJ%x},[%llu]",
+	       object->debug_id, (unsigned long long) ni_size);
+
+	if (!file)
+		return -ENOBUFS;
+
+	oi_size = i_size_read(file_inode(file));
+	if (oi_size == ni_size)
+		return 0;
+
+	inode_lock(file_inode(file));
+
+	/* if there's an extension to a partial page at the end of the backing
+	 * file, we need to discard the partial page so that we pick up new
+	 * data after it */
+	if (oi_size & ~PAGE_MASK && ni_size > oi_size) {
+		_debug("discard tail %llx", oi_size);
+		newattrs.ia_valid = ATTR_SIZE;
+		newattrs.ia_size = oi_size & PAGE_MASK;
+		ret = cachefiles_inject_remove_error();
+		if (ret == 0)
+			ret = notify_change(&nop_mnt_idmap, file->f_path.dentry,
+					    &newattrs, NULL);
+		if (ret < 0)
+			goto truncate_failed;
+	}
+
+	newattrs.ia_valid = ATTR_SIZE;
+	newattrs.ia_size = ni_size;
+	ret = cachefiles_inject_write_error();
+	if (ret == 0)
+		ret = notify_change(&nop_mnt_idmap, file->f_path.dentry,
+				    &newattrs, NULL);
+
+truncate_failed:
+	inode_unlock(file_inode(file));
+
+	if (ret < 0)
+		trace_cachefiles_io_error(NULL, file_inode(file), ret,
+					  cachefiles_trace_notify_change_error);
+	if (ret == -EIO) {
+		cachefiles_io_error_obj(object, "Size set failed");
+		ret = -ENOBUFS;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Attempt to look up the nominated node in this cache
+ */
+static bool cachefiles_lookup_cookie(struct fscache_cookie *cookie)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache = cookie->volume->cache->cache_priv;
+	const struct cred *saved_cred;
+	bool success;
+
+	object = cachefiles_alloc_object(cookie);
+	if (!object)
+		goto fail;
+
+	_enter("{OBJ%x}", object->debug_id);
+
+	if (!cachefiles_cook_key(object))
+		goto fail_put;
+
+	cookie->cache_priv = object;
+
+	cachefiles_begin_secure(cache, &saved_cred);
+
+	success = cachefiles_look_up_object(object);
+	if (!success)
+		goto fail_withdraw;
+
+	cachefiles_see_object(object, cachefiles_obj_see_lookup_cookie);
+
+	spin_lock(&cache->object_list_lock);
+	list_add(&object->cache_link, &cache->object_list);
+	spin_unlock(&cache->object_list_lock);
+	cachefiles_adjust_size(object);
+
+	cachefiles_end_secure(cache, saved_cred);
+	_leave(" = t");
+	return true;
+
+fail_withdraw:
+	cachefiles_end_secure(cache, saved_cred);
+	cachefiles_see_object(object, cachefiles_obj_see_lookup_failed);
+	fscache_caching_failed(cookie);
+	_debug("failed c=%08x o=%08x", cookie->debug_id, object->debug_id);
+	/* The caller holds an access count on the cookie, so we need them to
+	 * drop it before we can withdraw the object.
+	 */
+	return false;
+
+fail_put:
+	cachefiles_put_object(object, cachefiles_obj_put_alloc_fail);
+fail:
+	return false;
+}
+
+/*
+ * Shorten the backing object to discard any dirty data and free up
+ * any unused granules.
+ */
+static bool cachefiles_shorten_object(struct cachefiles_object *object,
+				      struct file *file, loff_t new_size)
+{
+	struct cachefiles_cache *cache = object->volume->cache;
+	struct inode *inode = file_inode(file);
+	loff_t i_size, dio_size;
+	int ret;
+
+	dio_size = round_up(new_size, CACHEFILES_DIO_BLOCK_SIZE);
+	i_size = i_size_read(inode);
+
+	trace_cachefiles_trunc(object, inode, i_size, dio_size,
+			       cachefiles_trunc_shrink);
+	ret = cachefiles_inject_remove_error();
+	if (ret == 0)
+		ret = vfs_truncate(&file->f_path, dio_size);
+	if (ret < 0) {
+		trace_cachefiles_io_error(object, file_inode(file), ret,
+					  cachefiles_trace_trunc_error);
+		cachefiles_io_error_obj(object, "Trunc-to-size failed %d", ret);
+		cachefiles_remove_object_xattr(cache, object, file->f_path.dentry);
+		return false;
+	}
+
+	if (new_size < dio_size) {
+		trace_cachefiles_trunc(object, inode, dio_size, new_size,
+				       cachefiles_trunc_dio_adjust);
+		ret = cachefiles_inject_write_error();
+		if (ret == 0)
+			ret = vfs_fallocate(file, FALLOC_FL_ZERO_RANGE,
+					    new_size, dio_size - new_size);
+		if (ret < 0) {
+			trace_cachefiles_io_error(object, file_inode(file), ret,
+						  cachefiles_trace_fallocate_error);
+			cachefiles_io_error_obj(object, "Trunc-to-dio-size failed %d", ret);
+			cachefiles_remove_object_xattr(cache, object, file->f_path.dentry);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+/*
+ * Resize the backing object.
+ */
+static void cachefiles_resize_cookie(struct netfs_cache_resources *cres,
+				     loff_t new_size)
+{
+	struct cachefiles_object *object = cachefiles_cres_object(cres);
+	struct cachefiles_cache *cache = object->volume->cache;
+	struct fscache_cookie *cookie = object->cookie;
+	const struct cred *saved_cred;
+	struct file *file = cachefiles_cres_file(cres);
+	loff_t old_size = cookie->object_size;
+
+	_enter("%llu->%llu", old_size, new_size);
+
+	if (new_size < old_size) {
+		cachefiles_begin_secure(cache, &saved_cred);
+		cachefiles_shorten_object(object, file, new_size);
+		cachefiles_end_secure(cache, saved_cred);
+		object->cookie->object_size = new_size;
+		return;
+	}
+
+	/* The file is being expanded.  We don't need to do anything
+	 * particularly.  cookie->initial_size doesn't change and so the point
+	 * at which we have to download before doesn't change.
+	 */
+	cookie->object_size = new_size;
+}
+
+/*
+ * Commit changes to the object as we drop it.
+ */
+static void cachefiles_commit_object(struct cachefiles_object *object,
+				     struct cachefiles_cache *cache)
+{
+	bool update = false;
+
+	if (test_and_clear_bit(FSCACHE_COOKIE_LOCAL_WRITE, &object->cookie->flags))
+		update = true;
+	if (test_and_clear_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &object->cookie->flags))
+		update = true;
+	if (update)
+		cachefiles_set_object_xattr(object);
+
+	if (test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags))
+		cachefiles_commit_tmpfile(cache, object);
+}
+
+/*
+ * Finalise and object and close the VFS structs that we have.
+ */
+static void cachefiles_clean_up_object(struct cachefiles_object *object,
+				       struct cachefiles_cache *cache)
+{
+	struct file *file;
+
+	if (test_bit(FSCACHE_COOKIE_RETIRED, &object->cookie->flags)) {
+		if (!test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags)) {
+			cachefiles_see_object(object, cachefiles_obj_see_clean_delete);
+			_debug("- inval object OBJ%x", object->debug_id);
+			cachefiles_delete_object(object, FSCACHE_OBJECT_WAS_RETIRED);
+		} else {
+			cachefiles_see_object(object, cachefiles_obj_see_clean_drop_tmp);
+			_debug("- inval object OBJ%x tmpfile", object->debug_id);
+		}
+	} else {
+		cachefiles_see_object(object, cachefiles_obj_see_clean_commit);
+		cachefiles_commit_object(object, cache);
+	}
+
+	cachefiles_unmark_inode_in_use(object, object->file);
+
+	spin_lock(&object->lock);
+	file = object->file;
+	object->file = NULL;
+	spin_unlock(&object->lock);
+
+	if (file)
+		fput(file);
+}
+
+/*
+ * Withdraw caching for a cookie.
+ */
+static void cachefiles_withdraw_cookie(struct fscache_cookie *cookie)
+{
+	struct cachefiles_object *object = cookie->cache_priv;
+	struct cachefiles_cache *cache = object->volume->cache;
+	const struct cred *saved_cred;
+
+	_enter("o=%x", object->debug_id);
+	cachefiles_see_object(object, cachefiles_obj_see_withdraw_cookie);
+
+	if (!list_empty(&object->cache_link)) {
+		spin_lock(&cache->object_list_lock);
+		cachefiles_see_object(object, cachefiles_obj_see_withdrawal);
+		list_del_init(&object->cache_link);
+		spin_unlock(&cache->object_list_lock);
+	}
+
+	if (object->file) {
+		cachefiles_begin_secure(cache, &saved_cred);
+		cachefiles_clean_up_object(object, cache);
+		cachefiles_end_secure(cache, saved_cred);
+	}
+
+	cookie->cache_priv = NULL;
+	cachefiles_put_object(object, cachefiles_obj_put_detach);
+}
+
+/*
+ * Invalidate the storage associated with a cookie.
+ */
+static bool cachefiles_invalidate_cookie(struct fscache_cookie *cookie)
+{
+	struct cachefiles_object *object = cookie->cache_priv;
+	struct file *new_file, *old_file;
+	bool old_tmpfile;
+
+	_enter("o=%x,[%llu]", object->debug_id, object->cookie->object_size);
+
+	old_tmpfile = test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags);
+
+	if (!object->file) {
+		fscache_resume_after_invalidation(cookie);
+		_leave(" = t [light]");
+		return true;
+	}
+
+	new_file = cachefiles_create_tmpfile(object);
+	if (IS_ERR(new_file))
+		goto failed;
+
+	/* Substitute the VFS target */
+	_debug("sub");
+	spin_lock(&object->lock);
+
+	old_file = object->file;
+	object->file = new_file;
+	object->content_info = CACHEFILES_CONTENT_NO_DATA;
+	set_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags);
+	set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &object->cookie->flags);
+
+	spin_unlock(&object->lock);
+	_debug("subbed");
+
+	/* Allow I/O to take place again */
+	fscache_resume_after_invalidation(cookie);
+
+	if (old_file) {
+		if (!old_tmpfile) {
+			struct cachefiles_volume *volume = object->volume;
+			struct dentry *fan = volume->fanout[(u8)cookie->key_hash];
+			struct dentry *obj;
+
+			obj = start_removing_dentry(fan, old_file->f_path.dentry);
+			if (!IS_ERR(obj))
+				cachefiles_bury_object(volume->cache, object,
+						       fan, obj,
+						       FSCACHE_OBJECT_INVALIDATED);
+		}
+		fput(old_file);
+	}
+
+	_leave(" = t");
+	return true;
+
+failed:
+	_leave(" = f");
+	return false;
+}
+
+const struct fscache_cache_ops cachefiles_cache_ops = {
+	.name			= "cachefiles",
+	.acquire_volume		= cachefiles_acquire_volume,
+	.free_volume		= cachefiles_free_volume,
+	.lookup_cookie		= cachefiles_lookup_cookie,
+	.withdraw_cookie	= cachefiles_withdraw_cookie,
+	.invalidate_cookie	= cachefiles_invalidate_cookie,
+	.begin_operation	= cachefiles_begin_operation,
+	.resize_cookie		= cachefiles_resize_cookie,
+	.prepare_to_write	= cachefiles_prepare_to_write,
+};