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, 287 insertions, 0 deletions

diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
new file mode 100644
index 000000000..3d294365e
--- /dev/null
+++ b/drivers/md/dm-target.c
@@ -0,0 +1,287 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2001 Sistina Software (UK) Limited
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm-core.h"
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kmod.h>
+#include <linux/bio.h>
+#include <linux/dax.h>
+
+#define DM_MSG_PREFIX "target"
+
+static LIST_HEAD(_targets);
+static DECLARE_RWSEM(_lock);
+
+static inline struct target_type *__find_target_type(const char *name)
+{
+	struct target_type *tt;
+
+	list_for_each_entry(tt, &_targets, list)
+		if (!strcmp(name, tt->name))
+			return tt;
+
+	return NULL;
+}
+
+static struct target_type *get_target_type(const char *name)
+{
+	struct target_type *tt;
+
+	down_read(&_lock);
+
+	tt = __find_target_type(name);
+	if (tt && !try_module_get(tt->module))
+		tt = NULL;
+
+	up_read(&_lock);
+	return tt;
+}
+
+static void load_module(const char *name)
+{
+	request_module("dm-%s", name);
+}
+
+struct target_type *dm_get_target_type(const char *name)
+{
+	struct target_type *tt = get_target_type(name);
+
+	if (!tt) {
+		load_module(name);
+		tt = get_target_type(name);
+	}
+
+	return tt;
+}
+
+void dm_put_target_type(struct target_type *tt)
+{
+	down_read(&_lock);
+	module_put(tt->module);
+	up_read(&_lock);
+}
+
+int dm_target_iterate(void (*iter_func)(struct target_type *tt,
+					void *param), void *param)
+{
+	struct target_type *tt;
+
+	down_read(&_lock);
+	list_for_each_entry(tt, &_targets, list)
+		iter_func(tt, param);
+	up_read(&_lock);
+
+	return 0;
+}
+
+int dm_register_target(struct target_type *tt)
+{
+	int rv = 0;
+
+	down_write(&_lock);
+	if (__find_target_type(tt->name)) {
+		DMERR("%s: '%s' target already registered",
+		      __func__, tt->name);
+		rv = -EBUSY;
+	} else {
+		list_add(&tt->list, &_targets);
+	}
+	up_write(&_lock);
+
+	return rv;
+}
+EXPORT_SYMBOL(dm_register_target);
+
+void dm_unregister_target(struct target_type *tt)
+{
+	down_write(&_lock);
+	if (!__find_target_type(tt->name)) {
+		DMCRIT("Unregistering unrecognised target: %s", tt->name);
+		BUG();
+	}
+
+	list_del(&tt->list);
+
+	up_write(&_lock);
+}
+EXPORT_SYMBOL(dm_unregister_target);
+
+/*
+ * io-err: always fails an io, useful for bringing
+ * up LVs that have holes in them.
+ */
+struct io_err_c {
+	struct dm_dev *dev;
+	sector_t start;
+};
+
+static int io_err_get_args(struct dm_target *tt, unsigned int argc, char **args)
+{
+	unsigned long long start;
+	struct io_err_c *ioec;
+	char dummy;
+	int ret;
+
+	ioec = kmalloc_obj(*ioec);
+	if (!ioec) {
+		tt->error = "Cannot allocate io_err context";
+		return -ENOMEM;
+	}
+
+	ret = -EINVAL;
+	if (sscanf(args[1], "%llu%c", &start, &dummy) != 1 ||
+	    start != (sector_t)start) {
+		tt->error = "Invalid device sector";
+		goto bad;
+	}
+	ioec->start = start;
+
+	ret = dm_get_device(tt, args[0], dm_table_get_mode(tt->table), &ioec->dev);
+	if (ret) {
+		tt->error = "Device lookup failed";
+		goto bad;
+	}
+
+	tt->private = ioec;
+
+	return 0;
+
+bad:
+	kfree(ioec);
+
+	return ret;
+}
+
+static int io_err_ctr(struct dm_target *tt, unsigned int argc, char **args)
+{
+	/*
+	 * If we have arguments, assume it is the path to the backing
+	 * block device and its mapping start sector (same as dm-linear).
+	 * In this case, get the device so that we can get its limits.
+	 */
+	if (argc == 2) {
+		int ret = io_err_get_args(tt, argc, args);
+
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * Return error for discards instead of -EOPNOTSUPP
+	 */
+	tt->num_discard_bios = 1;
+	tt->discards_supported = true;
+
+	return 0;
+}
+
+static void io_err_dtr(struct dm_target *tt)
+{
+	struct io_err_c *ioec = tt->private;
+
+	if (ioec) {
+		dm_put_device(tt, ioec->dev);
+		kfree(ioec);
+	}
+}
+
+static int io_err_map(struct dm_target *tt, struct bio *bio)
+{
+	return DM_MAPIO_KILL;
+}
+
+static int io_err_clone_and_map_rq(struct dm_target *ti, struct request *rq,
+				   union map_info *map_context,
+				   struct request **clone)
+{
+	return DM_MAPIO_KILL;
+}
+
+static void io_err_release_clone_rq(struct request *clone,
+				    union map_info *map_context)
+{
+}
+
+#ifdef CONFIG_BLK_DEV_ZONED
+static sector_t io_err_map_sector(struct dm_target *ti, sector_t bi_sector)
+{
+	struct io_err_c *ioec = ti->private;
+
+	return ioec->start + dm_target_offset(ti, bi_sector);
+}
+
+static int io_err_report_zones(struct dm_target *ti,
+		struct dm_report_zones_args *args, unsigned int nr_zones)
+{
+	struct io_err_c *ioec = ti->private;
+
+	/*
+	 * This should never be called when we do not have a backing device
+	 * as that mean the target is not a zoned one.
+	 */
+	if (WARN_ON_ONCE(!ioec))
+		return -EIO;
+
+	return dm_report_zones(ioec->dev->bdev, ioec->start,
+			       io_err_map_sector(ti, args->next_sector),
+			       args, nr_zones);
+}
+#else
+#define io_err_report_zones NULL
+#endif
+
+static int io_err_iterate_devices(struct dm_target *ti,
+				  iterate_devices_callout_fn fn, void *data)
+{
+	struct io_err_c *ioec = ti->private;
+
+	if (!ioec)
+		return 0;
+
+	return fn(ti, ioec->dev, ioec->start, ti->len, data);
+}
+
+static void io_err_io_hints(struct dm_target *ti, struct queue_limits *limits)
+{
+	limits->max_hw_discard_sectors = UINT_MAX;
+	limits->discard_granularity = 512;
+}
+
+static long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
+		long nr_pages, enum dax_access_mode mode, void **kaddr,
+		unsigned long *pfn)
+{
+	return -EIO;
+}
+
+static struct target_type error_target = {
+	.name = "error",
+	.version = {1, 7, 0},
+	.features = DM_TARGET_WILDCARD | DM_TARGET_ZONED_HM |
+		DM_TARGET_PASSES_INTEGRITY,
+	.ctr  = io_err_ctr,
+	.dtr  = io_err_dtr,
+	.map  = io_err_map,
+	.clone_and_map_rq = io_err_clone_and_map_rq,
+	.release_clone_rq = io_err_release_clone_rq,
+	.iterate_devices = io_err_iterate_devices,
+	.io_hints = io_err_io_hints,
+	.direct_access = io_err_dax_direct_access,
+	.report_zones = io_err_report_zones,
+};
+
+int __init dm_target_init(void)
+{
+	return dm_register_target(&error_target);
+}
+
+void dm_target_exit(void)
+{
+	dm_unregister_target(&error_target);
+}