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, 203 insertions, 0 deletions

diff --git a/lib/objpool.c b/lib/objpool.c
new file mode 100644
index 000000000..d98fadf1d
--- /dev/null
+++ b/lib/objpool.c
@@ -0,0 +1,203 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/objpool.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/atomic.h>
+#include <linux/irqflags.h>
+#include <linux/cpumask.h>
+#include <linux/log2.h>
+
+/*
+ * objpool: ring-array based lockless MPMC/FIFO queues
+ *
+ * Copyright: wuqiang.matt@bytedance.com,mhiramat@kernel.org
+ */
+
+/* initialize percpu objpool_slot */
+static int
+objpool_init_percpu_slot(struct objpool_head *pool,
+			 struct objpool_slot *slot,
+			 int nodes, void *context,
+			 objpool_init_obj_cb objinit)
+{
+	void *obj = (void *)&slot->entries[pool->capacity];
+	int i;
+
+	/* initialize elements of percpu objpool_slot */
+	slot->mask = pool->capacity - 1;
+
+	for (i = 0; i < nodes; i++) {
+		if (objinit) {
+			int rc = objinit(obj, context);
+			if (rc)
+				return rc;
+		}
+		slot->entries[slot->tail & slot->mask] = obj;
+		obj = obj + pool->obj_size;
+		slot->tail++;
+		slot->last = slot->tail;
+		pool->nr_objs++;
+	}
+
+	return 0;
+}
+
+/* allocate and initialize percpu slots */
+static int
+objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs,
+			  void *context, objpool_init_obj_cb objinit)
+{
+	int i, cpu_count = 0;
+
+	for (i = 0; i < nr_cpu_ids; i++) {
+
+		struct objpool_slot *slot;
+		int nodes, size, rc;
+
+		/* skip the cpu node which could never be present */
+		if (!cpu_possible(i))
+			continue;
+
+		/* compute how many objects to be allocated with this slot */
+		nodes = nr_objs / pool->nr_possible_cpus;
+		if (cpu_count < (nr_objs % pool->nr_possible_cpus))
+			nodes++;
+		cpu_count++;
+
+		size = struct_size(slot, entries, pool->capacity) +
+			pool->obj_size * nodes;
+
+		/*
+		 * here we allocate percpu-slot & objs together in a single
+		 * allocation to make it more compact, taking advantage of
+		 * warm caches and TLB hits. in default vmalloc is used to
+		 * reduce the pressure of kernel slab system. as we know,
+		 * mimimal size of vmalloc is one page since vmalloc would
+		 * always align the requested size to page size.
+		 * but if vmalloc fails or it is not available (e.g. GFP_ATOMIC)
+		 * allocate percpu slot with kmalloc.
+		 */
+		slot = NULL;
+
+		if ((pool->gfp & (GFP_ATOMIC | GFP_KERNEL)) != GFP_ATOMIC)
+			slot = __vmalloc_node(size, sizeof(void *), pool->gfp,
+				cpu_to_node(i), __builtin_return_address(0));
+
+		if (!slot) {
+			slot = kmalloc_node(size, pool->gfp, cpu_to_node(i));
+			if (!slot)
+				return -ENOMEM;
+		}
+		memset(slot, 0, size);
+		pool->cpu_slots[i] = slot;
+
+		/* initialize the objpool_slot of cpu node i */
+		rc = objpool_init_percpu_slot(pool, slot, nodes, context, objinit);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+/* cleanup all percpu slots of the object pool */
+static void objpool_fini_percpu_slots(struct objpool_head *pool)
+{
+	int i;
+
+	if (!pool->cpu_slots)
+		return;
+
+	for (i = 0; i < nr_cpu_ids; i++)
+		kvfree(pool->cpu_slots[i]);
+	kfree(pool->cpu_slots);
+}
+
+/* initialize object pool and pre-allocate objects */
+int objpool_init(struct objpool_head *pool, int nr_objs, int object_size,
+		gfp_t gfp, void *context, objpool_init_obj_cb objinit,
+		objpool_fini_cb release)
+{
+	int rc, capacity, slot_size;
+
+	/* check input parameters */
+	if (nr_objs <= 0 || nr_objs > OBJPOOL_NR_OBJECT_MAX ||
+	    object_size <= 0 || object_size > OBJPOOL_OBJECT_SIZE_MAX)
+		return -EINVAL;
+
+	/* align up to unsigned long size */
+	object_size = ALIGN(object_size, sizeof(long));
+
+	/* calculate capacity of percpu objpool_slot */
+	capacity = roundup_pow_of_two(nr_objs);
+	if (!capacity)
+		return -EINVAL;
+
+	/* initialize objpool pool */
+	memset(pool, 0, sizeof(struct objpool_head));
+	pool->nr_possible_cpus = num_possible_cpus();
+	pool->obj_size = object_size;
+	pool->capacity = capacity;
+	pool->gfp = gfp & ~__GFP_ZERO;
+	pool->context = context;
+	pool->release = release;
+	slot_size = nr_cpu_ids * sizeof(struct objpool_slot *);
+	pool->cpu_slots = kzalloc(slot_size, pool->gfp);
+	if (!pool->cpu_slots)
+		return -ENOMEM;
+
+	/* initialize per-cpu slots */
+	rc = objpool_init_percpu_slots(pool, nr_objs, context, objinit);
+	if (rc)
+		objpool_fini_percpu_slots(pool);
+	else
+		refcount_set(&pool->ref, pool->nr_objs + 1);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(objpool_init);
+
+/* release whole objpool forcely */
+void objpool_free(struct objpool_head *pool)
+{
+	if (!pool->cpu_slots)
+		return;
+
+	/* release percpu slots */
+	objpool_fini_percpu_slots(pool);
+
+	/* call user's cleanup callback if provided */
+	if (pool->release)
+		pool->release(pool, pool->context);
+}
+EXPORT_SYMBOL_GPL(objpool_free);
+
+/* drop the allocated object, rather reclaim it to objpool */
+int objpool_drop(void *obj, struct objpool_head *pool)
+{
+	if (!obj || !pool)
+		return -EINVAL;
+
+	if (refcount_dec_and_test(&pool->ref)) {
+		objpool_free(pool);
+		return 0;
+	}
+
+	return -EAGAIN;
+}
+EXPORT_SYMBOL_GPL(objpool_drop);
+
+/* drop unused objects and defref objpool for releasing */
+void objpool_fini(struct objpool_head *pool)
+{
+	int count = 1; /* extra ref for objpool itself */
+
+	/* drop all remained objects from objpool */
+	while (objpool_pop(pool))
+		count++;
+
+	if (refcount_sub_and_test(count, &pool->ref))
+		objpool_free(pool);
+}
+EXPORT_SYMBOL_GPL(objpool_fini);