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, 227 insertions, 0 deletions

diff --git a/fs/btrfs/misc.h b/fs/btrfs/misc.h
new file mode 100644
index 000000000..802060943
--- /dev/null
+++ b/fs/btrfs/misc.h
@@ -0,0 +1,227 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_MISC_H
+#define BTRFS_MISC_H
+
+#include <linux/types.h>
+#include <linux/bitmap.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/math64.h>
+#include <linux/rbtree.h>
+#include <linux/bio.h>
+
+/*
+ * Convenience macros to define a pointer with the __free(kfree) and
+ * __free(kvfree) cleanup attributes and initialized to NULL.
+ */
+#define AUTO_KFREE(name)       *name __free(kfree) = NULL
+#define AUTO_KVFREE(name)      *name __free(kvfree) = NULL
+
+/*
+ * Enumerate bits using enum autoincrement. Define the @name as the n-th bit.
+ */
+#define ENUM_BIT(name)                                  \
+	__ ## name ## _BIT,                             \
+	name = (1U << __ ## name ## _BIT),              \
+	__ ## name ## _SEQ = __ ## name ## _BIT
+
+static inline phys_addr_t bio_iter_phys(const struct bio *bio,
+					const struct bvec_iter *iter)
+{
+	struct bio_vec bv = bio_iter_iovec(bio, *iter);
+
+	return bvec_phys(&bv);
+}
+
+/*
+ * Iterate bio using btrfs block size.
+ *
+ * This will handle large folio and highmem.
+ *
+ * @paddr:	Physical memory address of each iteration
+ * @bio:	The bio to iterate
+ * @iter:	The bvec_iter (pointer) to use.
+ * @blocksize:	The blocksize to iterate.
+ *
+ * This requires all folios in the bio to cover at least one block.
+ */
+#define btrfs_bio_for_each_block(paddr, bio, iter, blocksize)		\
+	for (; (iter)->bi_size &&					\
+	     (paddr = bio_iter_phys((bio), (iter)), 1);			\
+	     bio_advance_iter_single((bio), (iter), (blocksize)))
+
+/* Can only be called on a non-cloned bio. */
+static inline u32 bio_get_size(struct bio *bio)
+{
+	struct bio_vec *bvec;
+	u32 ret = 0;
+	int i;
+
+	bio_for_each_bvec_all(bvec, bio, i)
+		ret += bvec->bv_len;
+	return ret;
+}
+
+/* Initialize a bvec_iter to the size of the specified bio. */
+static inline struct bvec_iter init_bvec_iter_for_bio(struct bio *bio)
+{
+	const u32 bio_size = bio_get_size(bio);
+
+	return (struct bvec_iter) {
+		.bi_sector = 0,
+		.bi_size = bio_size,
+		.bi_idx = 0,
+		.bi_offset = 0,
+	};
+}
+
+#define btrfs_bio_for_each_block_all(paddr, bio, blocksize)		\
+	for (struct bvec_iter iter = init_bvec_iter_for_bio(bio);	\
+	     (iter).bi_size &&						\
+	     (paddr = bio_iter_phys((bio), &(iter)), 1);		\
+	     bio_advance_iter_single((bio), &(iter), (blocksize)))
+
+static inline void cond_wake_up(struct wait_queue_head *wq)
+{
+	/*
+	 * This implies a full smp_mb barrier, see comments for
+	 * waitqueue_active why.
+	 */
+	if (wq_has_sleeper(wq))
+		wake_up(wq);
+}
+
+static inline void cond_wake_up_nomb(struct wait_queue_head *wq)
+{
+	/*
+	 * Special case for conditional wakeup where the barrier required for
+	 * waitqueue_active is implied by some of the preceding code. Eg. one
+	 * of such atomic operations (atomic_dec_and_return, ...), or a
+	 * unlock/lock sequence, etc.
+	 */
+	if (waitqueue_active(wq))
+		wake_up(wq);
+}
+
+static inline u64 mult_perc(u64 num, u32 percent)
+{
+	return div_u64(num * percent, 100);
+}
+/* Copy of is_power_of_two that is 64bit safe */
+static inline bool is_power_of_two_u64(u64 n)
+{
+	return n != 0 && (n & (n - 1)) == 0;
+}
+
+static inline bool has_single_bit_set(u64 n)
+{
+	return is_power_of_two_u64(n);
+}
+
+/*
+ * Simple bytenr based rb_tree relate structures
+ *
+ * Any structure wants to use bytenr as single search index should have their
+ * structure start with these members.
+ */
+struct rb_simple_node {
+	struct rb_node rb_node;
+	u64 bytenr;
+};
+
+static inline struct rb_node *rb_simple_search(const struct rb_root *root, u64 bytenr)
+{
+	struct rb_node *node = root->rb_node;
+	struct rb_simple_node *entry;
+
+	while (node) {
+		entry = rb_entry(node, struct rb_simple_node, rb_node);
+
+		if (bytenr < entry->bytenr)
+			node = node->rb_left;
+		else if (bytenr > entry->bytenr)
+			node = node->rb_right;
+		else
+			return node;
+	}
+	return NULL;
+}
+
+/*
+ * Search @root from an entry that starts or comes after @bytenr.
+ *
+ * @root:	the root to search.
+ * @bytenr:	bytenr to search from.
+ *
+ * Return the rb_node that start at or after @bytenr.  If there is no entry at
+ * or after @bytner return NULL.
+ */
+static inline struct rb_node *rb_simple_search_first(const struct rb_root *root,
+						     u64 bytenr)
+{
+	struct rb_node *node = root->rb_node, *ret = NULL;
+	struct rb_simple_node *entry, *ret_entry = NULL;
+
+	while (node) {
+		entry = rb_entry(node, struct rb_simple_node, rb_node);
+
+		if (bytenr < entry->bytenr) {
+			if (!ret || entry->bytenr < ret_entry->bytenr) {
+				ret = node;
+				ret_entry = entry;
+			}
+
+			node = node->rb_left;
+		} else if (bytenr > entry->bytenr) {
+			node = node->rb_right;
+		} else {
+			return node;
+		}
+	}
+
+	return ret;
+}
+
+static int rb_simple_node_bytenr_cmp(struct rb_node *new, const struct rb_node *existing)
+{
+	struct rb_simple_node *new_entry = rb_entry(new, struct rb_simple_node, rb_node);
+	struct rb_simple_node *existing_entry = rb_entry(existing, struct rb_simple_node, rb_node);
+
+	if (new_entry->bytenr < existing_entry->bytenr)
+		return -1;
+	else if (new_entry->bytenr > existing_entry->bytenr)
+		return 1;
+
+	return 0;
+}
+
+static inline struct rb_node *rb_simple_insert(struct rb_root *root,
+					       struct rb_simple_node *simple_node)
+{
+	return rb_find_add(&simple_node->rb_node, root, rb_simple_node_bytenr_cmp);
+}
+
+static inline bool bitmap_test_range_all_set(const unsigned long *addr,
+					     unsigned long start,
+					     unsigned long nbits)
+{
+	unsigned long found_zero;
+
+	found_zero = find_next_zero_bit(addr, start + nbits, start);
+	return (found_zero == start + nbits);
+}
+
+static inline bool bitmap_test_range_all_zero(const unsigned long *addr,
+					      unsigned long start,
+					      unsigned long nbits)
+{
+	unsigned long found_set;
+
+	found_set = find_next_bit(addr, start + nbits, start);
+	return (found_set == start + nbits);
+}
+
+#endif