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, 561 insertions, 0 deletions

diff --git a/drivers/mtd/ubi/fastmap-wl.c b/drivers/mtd/ubi/fastmap-wl.c
new file mode 100644
index 000000000..e24bb6b18
--- /dev/null
+++ b/drivers/mtd/ubi/fastmap-wl.c
@@ -0,0 +1,561 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2012 Linutronix GmbH
+ * Copyright (c) 2014 sigma star gmbh
+ * Author: Richard Weinberger <richard@nod.at>
+ */
+
+/**
+ * update_fastmap_work_fn - calls ubi_update_fastmap from a work queue
+ * @wrk: the work description object
+ */
+static void update_fastmap_work_fn(struct work_struct *wrk)
+{
+	struct ubi_device *ubi = container_of(wrk, struct ubi_device, fm_work);
+
+	ubi_update_fastmap(ubi);
+	spin_lock(&ubi->wl_lock);
+	ubi->fm_work_scheduled = 0;
+	spin_unlock(&ubi->wl_lock);
+}
+
+/**
+ * find_anchor_wl_entry - find wear-leveling entry to used as anchor PEB.
+ * @root: the RB-tree where to look for
+ */
+static struct ubi_wl_entry *find_anchor_wl_entry(struct rb_root *root)
+{
+	struct rb_node *p;
+	struct ubi_wl_entry *e, *victim = NULL;
+	int max_ec = UBI_MAX_ERASECOUNTER;
+
+	ubi_rb_for_each_entry(p, e, root, u.rb) {
+		if (e->pnum < UBI_FM_MAX_START && e->ec < max_ec) {
+			victim = e;
+			max_ec = e->ec;
+		}
+	}
+
+	return victim;
+}
+
+static inline void return_unused_peb(struct ubi_device *ubi,
+				     struct ubi_wl_entry *e)
+{
+	wl_tree_add(e, &ubi->free);
+	ubi->free_count++;
+}
+
+/**
+ * return_unused_pool_pebs - returns unused PEB to the free tree.
+ * @ubi: UBI device description object
+ * @pool: fastmap pool description object
+ */
+static void return_unused_pool_pebs(struct ubi_device *ubi,
+				    struct ubi_fm_pool *pool)
+{
+	int i;
+	struct ubi_wl_entry *e;
+
+	for (i = pool->used; i < pool->size; i++) {
+		e = ubi->lookuptbl[pool->pebs[i]];
+		return_unused_peb(ubi, e);
+	}
+}
+
+/**
+ * ubi_wl_get_fm_peb - find a physical erase block with a given maximal number.
+ * @ubi: UBI device description object
+ * @anchor: This PEB will be used as anchor PEB by fastmap
+ *
+ * The function returns a physical erase block with a given maximal number
+ * and removes it from the wl subsystem.
+ * Must be called with wl_lock held!
+ */
+struct ubi_wl_entry *ubi_wl_get_fm_peb(struct ubi_device *ubi, int anchor)
+{
+	struct ubi_wl_entry *e = NULL;
+
+	if (!ubi->free.rb_node)
+		goto out;
+
+	if (anchor)
+		e = find_anchor_wl_entry(&ubi->free);
+	else
+		e = find_mean_wl_entry(ubi, &ubi->free);
+
+	if (!e)
+		goto out;
+
+	self_check_in_wl_tree(ubi, e, &ubi->free);
+
+	/* remove it from the free list,
+	 * the wl subsystem does no longer know this erase block */
+	rb_erase(&e->u.rb, &ubi->free);
+	ubi->free_count--;
+out:
+	return e;
+}
+
+/*
+ * wait_free_pebs_for_pool - wait until there enough free pebs
+ * @ubi: UBI device description object
+ *
+ * Wait and execute do_work until there are enough free pebs, fill pool
+ * as much as we can. This will reduce pool refilling times, which can
+ * reduce the fastmap updating frequency.
+ */
+static void wait_free_pebs_for_pool(struct ubi_device *ubi)
+{
+	struct ubi_fm_pool *wl_pool = &ubi->fm_wl_pool;
+	struct ubi_fm_pool *pool = &ubi->fm_pool;
+	int free, expect_free, executed;
+	/*
+	 * There are at least following free pebs which reserved by UBI:
+	 * 1. WL_RESERVED_PEBS[1]
+	 * 2. EBA_RESERVED_PEBS[1]
+	 * 3. fm pebs - 1: Twice fastmap size deducted by fastmap and fm_anchor
+	 * 4. beb_rsvd_pebs: This value should be get under lock ubi->wl_lock
+	 */
+	int reserved = WL_RESERVED_PEBS + EBA_RESERVED_PEBS +
+		       ubi->fm_size / ubi->leb_size - 1 + ubi->fm_pool_rsv_cnt;
+
+	do {
+		spin_lock(&ubi->wl_lock);
+		free = ubi->free_count;
+		free += pool->size - pool->used + wl_pool->size - wl_pool->used;
+		expect_free = reserved + ubi->beb_rsvd_pebs;
+		spin_unlock(&ubi->wl_lock);
+
+		/*
+		 * Break out if there are no works or work is executed failure,
+		 * given the fact that erase_worker will schedule itself when
+		 * -EBUSY is returned from mtd layer caused by system shutdown.
+		 */
+		if (do_work(ubi, &executed) || !executed)
+			break;
+	} while (free < expect_free);
+}
+
+/*
+ * left_free_count - returns the number of free pebs to fill fm pools
+ * @ubi: UBI device description object
+ *
+ * This helper function returns the number of free pebs (deducted
+ * by fastmap pebs) to fill fm_pool and fm_wl_pool.
+ */
+static int left_free_count(struct ubi_device *ubi)
+{
+	int fm_used = 0;	// fastmap non anchor pebs.
+
+	if (!ubi->free.rb_node)
+		return 0;
+
+	if (!ubi->ro_mode && !ubi->fm_disabled)
+		fm_used = ubi->fm_size / ubi->leb_size - 1;
+
+	return ubi->free_count - fm_used;
+}
+
+/*
+ * can_fill_pools - whether free PEBs will be left after filling pools
+ * @ubi: UBI device description object
+ * @free: current number of free PEBs
+ *
+ * Return %1 if there are still left free PEBs after filling pools,
+ * otherwise %0 is returned.
+ */
+static int can_fill_pools(struct ubi_device *ubi, int free)
+{
+	struct ubi_fm_pool *wl_pool = &ubi->fm_wl_pool;
+	struct ubi_fm_pool *pool = &ubi->fm_pool;
+	int pool_need = pool->max_size - pool->size +
+			wl_pool->max_size - wl_pool->size;
+
+	if (free - pool_need < 1)
+		return 0;
+
+	return 1;
+}
+
+/**
+ * ubi_refill_pools_and_lock - refills all fastmap PEB pools and takes fm locks.
+ * @ubi: UBI device description object
+ */
+void ubi_refill_pools_and_lock(struct ubi_device *ubi)
+{
+	struct ubi_fm_pool *wl_pool = &ubi->fm_wl_pool;
+	struct ubi_fm_pool *pool = &ubi->fm_pool;
+	struct ubi_wl_entry *e;
+	int enough;
+
+	if (!ubi->ro_mode && !ubi->fm_disabled)
+		wait_free_pebs_for_pool(ubi);
+
+	down_write(&ubi->fm_protect);
+	down_write(&ubi->work_sem);
+	down_write(&ubi->fm_eba_sem);
+
+	spin_lock(&ubi->wl_lock);
+
+	return_unused_pool_pebs(ubi, wl_pool);
+	return_unused_pool_pebs(ubi, pool);
+
+	wl_pool->size = 0;
+	pool->size = 0;
+
+	if (ubi->fm_anchor) {
+		wl_tree_add(ubi->fm_anchor, &ubi->free);
+		ubi->free_count++;
+		ubi->fm_anchor = NULL;
+	}
+
+	if (!ubi->fm_disabled)
+		/*
+		 * All available PEBs are in ubi->free, now is the time to get
+		 * the best anchor PEBs.
+		 */
+		ubi->fm_anchor = ubi_wl_get_fm_peb(ubi, 1);
+
+	for (;;) {
+		enough = 0;
+		if (pool->size < pool->max_size) {
+			if (left_free_count(ubi) <= 0)
+				break;
+
+			e = wl_get_wle(ubi);
+			if (!e)
+				break;
+
+			pool->pebs[pool->size] = e->pnum;
+			pool->size++;
+		} else
+			enough++;
+
+		if (wl_pool->size < wl_pool->max_size) {
+			int left_free = left_free_count(ubi);
+
+			if (left_free <= 0)
+				break;
+
+			e = find_wl_entry(ubi, &ubi->free, ubi->wl_free_max_diff,
+					  !can_fill_pools(ubi, left_free));
+			self_check_in_wl_tree(ubi, e, &ubi->free);
+			rb_erase(&e->u.rb, &ubi->free);
+			ubi->free_count--;
+
+			wl_pool->pebs[wl_pool->size] = e->pnum;
+			wl_pool->size++;
+		} else
+			enough++;
+
+		if (enough == 2)
+			break;
+	}
+
+	wl_pool->used = 0;
+	pool->used = 0;
+
+	spin_unlock(&ubi->wl_lock);
+}
+
+/**
+ * produce_free_peb - produce a free physical eraseblock.
+ * @ubi: UBI device description object
+ *
+ * This function tries to make a free PEB by means of synchronous execution of
+ * pending works. This may be needed if, for example the background thread is
+ * disabled. Returns zero in case of success and a negative error code in case
+ * of failure.
+ */
+static int produce_free_peb(struct ubi_device *ubi)
+{
+	int err;
+
+	while (!ubi->free.rb_node && ubi->works_count) {
+		dbg_wl("do one work synchronously");
+		err = do_work(ubi, NULL);
+
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
+ * ubi_wl_get_peb - get a physical eraseblock.
+ * @ubi: UBI device description object
+ *
+ * This function returns a physical eraseblock in case of success and a
+ * negative error code in case of failure.
+ * Returns with ubi->fm_eba_sem held in read mode!
+ */
+int ubi_wl_get_peb(struct ubi_device *ubi)
+{
+	int ret, attempts = 0;
+	struct ubi_fm_pool *pool = &ubi->fm_pool;
+	struct ubi_fm_pool *wl_pool = &ubi->fm_wl_pool;
+
+again:
+	down_read(&ubi->fm_eba_sem);
+	spin_lock(&ubi->wl_lock);
+
+	/* We check here also for the WL pool because at this point we can
+	 * refill the WL pool synchronous. */
+	if (pool->used == pool->size || wl_pool->used == wl_pool->size) {
+		spin_unlock(&ubi->wl_lock);
+		up_read(&ubi->fm_eba_sem);
+		ret = ubi_update_fastmap(ubi);
+		if (ret) {
+			ubi_msg(ubi, "Unable to write a new fastmap: %i", ret);
+			down_read(&ubi->fm_eba_sem);
+			return -ENOSPC;
+		}
+		down_read(&ubi->fm_eba_sem);
+		spin_lock(&ubi->wl_lock);
+	}
+
+	if (pool->used == pool->size) {
+		spin_unlock(&ubi->wl_lock);
+		attempts++;
+		if (attempts == 10) {
+			ubi_err(ubi, "Unable to get a free PEB from user WL pool");
+			ret = -ENOSPC;
+			goto out;
+		}
+		up_read(&ubi->fm_eba_sem);
+		ret = produce_free_peb(ubi);
+		if (ret < 0) {
+			down_read(&ubi->fm_eba_sem);
+			goto out;
+		}
+		goto again;
+	}
+
+	ubi_assert(pool->used < pool->size);
+	ret = pool->pebs[pool->used++];
+	prot_queue_add(ubi, ubi->lookuptbl[ret]);
+	spin_unlock(&ubi->wl_lock);
+out:
+	return ret;
+}
+
+/**
+ * next_peb_for_wl - returns next PEB to be used internally by the
+ * WL sub-system.
+ *
+ * @ubi: UBI device description object
+ * @need_fill: whether to fill wear-leveling pool when no PEBs are found
+ */
+static struct ubi_wl_entry *next_peb_for_wl(struct ubi_device *ubi,
+					    bool need_fill)
+{
+	struct ubi_fm_pool *pool = &ubi->fm_wl_pool;
+	int pnum;
+
+	if (pool->used == pool->size) {
+		if (need_fill && !ubi->fm_work_scheduled) {
+			/*
+			 * We cannot update the fastmap here because this
+			 * function is called in atomic context.
+			 * Let's fail here and refill/update it as soon as
+			 * possible.
+			 */
+			ubi->fm_work_scheduled = 1;
+			schedule_work(&ubi->fm_work);
+		}
+		return NULL;
+	}
+
+	pnum = pool->pebs[pool->used];
+	return ubi->lookuptbl[pnum];
+}
+
+/**
+ * need_wear_leveling - checks whether to trigger a wear leveling work.
+ * UBI fetches free PEB from wl_pool, we check free PEBs from both 'wl_pool'
+ * and 'ubi->free', because free PEB in 'ubi->free' tree maybe moved into
+ * 'wl_pool' by ubi_refill_pools().
+ *
+ * @ubi: UBI device description object
+ */
+static bool need_wear_leveling(struct ubi_device *ubi)
+{
+	int ec;
+	struct ubi_wl_entry *e;
+
+	if (!ubi->used.rb_node)
+		return false;
+
+	e = next_peb_for_wl(ubi, false);
+	if (!e) {
+		if (!ubi->free.rb_node)
+			return false;
+		e = find_wl_entry(ubi, &ubi->free, ubi->wl_free_max_diff, 0);
+		ec = e->ec;
+	} else {
+		ec = e->ec;
+		if (ubi->free.rb_node) {
+			e = find_wl_entry(ubi, &ubi->free, ubi->wl_free_max_diff, 0);
+			ec = max(ec, e->ec);
+		}
+	}
+	e = rb_entry(rb_first(&ubi->used), struct ubi_wl_entry, u.rb);
+
+	return ec - e->ec >= ubi->wl_threshold;
+}
+
+/* get_peb_for_wl - returns a PEB to be used internally by the WL sub-system.
+ *
+ * @ubi: UBI device description object
+ */
+static struct ubi_wl_entry *get_peb_for_wl(struct ubi_device *ubi)
+{
+	struct ubi_fm_pool *pool = &ubi->fm_wl_pool;
+	int pnum;
+
+	ubi_assert(rwsem_is_locked(&ubi->fm_eba_sem));
+
+	if (pool->used == pool->size) {
+		/* We cannot update the fastmap here because this
+		 * function is called in atomic context.
+		 * Let's fail here and refill/update it as soon as possible. */
+		if (!ubi->fm_work_scheduled) {
+			ubi->fm_work_scheduled = 1;
+			schedule_work(&ubi->fm_work);
+		}
+		return NULL;
+	}
+
+	pnum = pool->pebs[pool->used++];
+	return ubi->lookuptbl[pnum];
+}
+
+/**
+ * ubi_ensure_anchor_pebs - schedule wear-leveling to produce an anchor PEB.
+ * @ubi: UBI device description object
+ */
+int ubi_ensure_anchor_pebs(struct ubi_device *ubi)
+{
+	struct ubi_work *wrk;
+	struct ubi_wl_entry *anchor;
+
+	spin_lock(&ubi->wl_lock);
+
+	/* Do we already have an anchor? */
+	if (ubi->fm_anchor) {
+		spin_unlock(&ubi->wl_lock);
+		return 0;
+	}
+
+	/* See if we can find an anchor PEB on the list of free PEBs */
+	anchor = ubi_wl_get_fm_peb(ubi, 1);
+	if (anchor) {
+		ubi->fm_anchor = anchor;
+		spin_unlock(&ubi->wl_lock);
+		return 0;
+	}
+
+	ubi->fm_do_produce_anchor = 1;
+	/* No luck, trigger wear leveling to produce a new anchor PEB. */
+	if (ubi->wl_scheduled) {
+		spin_unlock(&ubi->wl_lock);
+		return 0;
+	}
+	ubi->wl_scheduled = 1;
+	spin_unlock(&ubi->wl_lock);
+
+	wrk = kmalloc_obj(struct ubi_work, GFP_NOFS);
+	if (!wrk) {
+		spin_lock(&ubi->wl_lock);
+		ubi->wl_scheduled = 0;
+		spin_unlock(&ubi->wl_lock);
+		return -ENOMEM;
+	}
+
+	wrk->func = &wear_leveling_worker;
+	__schedule_ubi_work(ubi, wrk);
+	return 0;
+}
+
+/**
+ * ubi_wl_put_fm_peb - returns a PEB used in a fastmap to the wear-leveling
+ * sub-system.
+ * see: ubi_wl_put_peb()
+ *
+ * @ubi: UBI device description object
+ * @fm_e: physical eraseblock to return
+ * @lnum: the last used logical eraseblock number for the PEB
+ * @torture: if this physical eraseblock has to be tortured
+ */
+int ubi_wl_put_fm_peb(struct ubi_device *ubi, struct ubi_wl_entry *fm_e,
+		      int lnum, int torture)
+{
+	struct ubi_wl_entry *e;
+	int vol_id, pnum = fm_e->pnum;
+
+	dbg_wl("PEB %d", pnum);
+
+	ubi_assert(pnum >= 0);
+	ubi_assert(pnum < ubi->peb_count);
+
+	spin_lock(&ubi->wl_lock);
+	e = ubi->lookuptbl[pnum];
+
+	/* This can happen if we recovered from a fastmap the very
+	 * first time and writing now a new one. In this case the wl system
+	 * has never seen any PEB used by the original fastmap.
+	 */
+	if (!e) {
+		e = fm_e;
+		ubi_assert(e->ec >= 0);
+		ubi->lookuptbl[pnum] = e;
+	}
+
+	spin_unlock(&ubi->wl_lock);
+
+	vol_id = lnum ? UBI_FM_DATA_VOLUME_ID : UBI_FM_SB_VOLUME_ID;
+	return schedule_erase(ubi, e, vol_id, lnum, torture, true);
+}
+
+/**
+ * ubi_is_erase_work - checks whether a work is erase work.
+ * @wrk: The work object to be checked
+ */
+int ubi_is_erase_work(struct ubi_work *wrk)
+{
+	return wrk->func == erase_worker;
+}
+
+static void ubi_fastmap_close(struct ubi_device *ubi)
+{
+	return_unused_pool_pebs(ubi, &ubi->fm_pool);
+	return_unused_pool_pebs(ubi, &ubi->fm_wl_pool);
+
+	if (ubi->fm_anchor) {
+		return_unused_peb(ubi, ubi->fm_anchor);
+		ubi->fm_anchor = NULL;
+	}
+
+	ubi_free_fastmap(ubi);
+}
+
+/**
+ * may_reserve_for_fm - tests whether a PEB shall be reserved for fastmap.
+ * See find_mean_wl_entry()
+ *
+ * @ubi: UBI device description object
+ * @e: physical eraseblock to return
+ * @root: RB tree to test against.
+ */
+static struct ubi_wl_entry *may_reserve_for_fm(struct ubi_device *ubi,
+					   struct ubi_wl_entry *e,
+					   struct rb_root *root) {
+	if (e && !ubi->fm_disabled && !ubi->fm && !ubi->fm_anchor &&
+	    e->pnum < UBI_FM_MAX_START)
+		e = rb_entry(rb_next(root->rb_node),
+			     struct ubi_wl_entry, u.rb);
+
+	return e;
+}