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, 339 insertions, 0 deletions

diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
new file mode 100644
index 000000000..c86ab6e55
--- /dev/null
+++ b/lib/cpu_rmap.c
@@ -0,0 +1,339 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * cpu_rmap.c: CPU affinity reverse-map support
+ * Copyright 2011 Solarflare Communications Inc.
+ */
+
+#include <linux/cpu_rmap.h>
+#include <linux/interrupt.h>
+#include <linux/export.h>
+
+/*
+ * These functions maintain a mapping from CPUs to some ordered set of
+ * objects with CPU affinities.  This can be seen as a reverse-map of
+ * CPU affinity.  However, we do not assume that the object affinities
+ * cover all CPUs in the system.  For those CPUs not directly covered
+ * by object affinities, we attempt to find a nearest object based on
+ * CPU topology.
+ */
+
+/**
+ * alloc_cpu_rmap - allocate CPU affinity reverse-map
+ * @size: Number of objects to be mapped
+ * @flags: Allocation flags e.g. %GFP_KERNEL
+ */
+struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
+{
+	struct cpu_rmap *rmap;
+	unsigned int cpu;
+	size_t obj_offset;
+
+	/* This is a silly number of objects, and we use u16 indices. */
+	if (size > 0xffff)
+		return NULL;
+
+	/* Offset of object pointer array from base structure */
+	obj_offset = ALIGN(offsetof(struct cpu_rmap, near[nr_cpu_ids]),
+			   sizeof(void *));
+
+	rmap = kzalloc(obj_offset + size * sizeof(rmap->obj[0]), flags);
+	if (!rmap)
+		return NULL;
+
+	kref_init(&rmap->refcount);
+	rmap->obj = (void **)((char *)rmap + obj_offset);
+
+	/* Initially assign CPUs to objects on a rota, since we have
+	 * no idea where the objects are.  Use infinite distance, so
+	 * any object with known distance is preferable.  Include the
+	 * CPUs that are not present/online, since we definitely want
+	 * any newly-hotplugged CPUs to have some object assigned.
+	 */
+	for_each_possible_cpu(cpu) {
+		rmap->near[cpu].index = cpu % size;
+		rmap->near[cpu].dist = CPU_RMAP_DIST_INF;
+	}
+
+	rmap->size = size;
+	return rmap;
+}
+EXPORT_SYMBOL(alloc_cpu_rmap);
+
+/**
+ * cpu_rmap_release - internal reclaiming helper called from kref_put
+ * @ref: kref to struct cpu_rmap
+ */
+static void cpu_rmap_release(struct kref *ref)
+{
+	struct cpu_rmap *rmap = container_of(ref, struct cpu_rmap, refcount);
+	kfree(rmap);
+}
+
+/**
+ * cpu_rmap_get - internal helper to get new ref on a cpu_rmap
+ * @rmap: reverse-map allocated with alloc_cpu_rmap()
+ */
+void cpu_rmap_get(struct cpu_rmap *rmap)
+{
+	kref_get(&rmap->refcount);
+}
+
+/**
+ * cpu_rmap_put - release ref on a cpu_rmap
+ * @rmap: reverse-map allocated with alloc_cpu_rmap()
+ */
+int cpu_rmap_put(struct cpu_rmap *rmap)
+{
+	return kref_put(&rmap->refcount, cpu_rmap_release);
+}
+EXPORT_SYMBOL(cpu_rmap_put);
+
+/* Reevaluate nearest object for given CPU, comparing with the given
+ * neighbours at the given distance.
+ */
+static bool cpu_rmap_copy_neigh(struct cpu_rmap *rmap, unsigned int cpu,
+				const struct cpumask *mask, u16 dist)
+{
+	int neigh;
+
+	for_each_cpu(neigh, mask) {
+		if (rmap->near[cpu].dist > dist &&
+		    rmap->near[neigh].dist <= dist) {
+			rmap->near[cpu].index = rmap->near[neigh].index;
+			rmap->near[cpu].dist = dist;
+			return true;
+		}
+	}
+	return false;
+}
+
+#ifdef DEBUG
+static void debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix)
+{
+	unsigned index;
+	unsigned int cpu;
+
+	pr_info("cpu_rmap %p, %s:\n", rmap, prefix);
+
+	for_each_possible_cpu(cpu) {
+		index = rmap->near[cpu].index;
+		pr_info("cpu %d -> obj %u (distance %u)\n",
+			cpu, index, rmap->near[cpu].dist);
+	}
+}
+#else
+static inline void
+debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix)
+{
+}
+#endif
+
+static int get_free_index(struct cpu_rmap *rmap)
+{
+	int i;
+
+	for (i = 0; i < rmap->size; i++)
+		if (!rmap->obj[i])
+			return i;
+
+	return -ENOSPC;
+}
+
+/**
+ * cpu_rmap_add - add object to a rmap
+ * @rmap: CPU rmap allocated with alloc_cpu_rmap()
+ * @obj: Object to add to rmap
+ *
+ * Return index of object or -ENOSPC if no free entry was found
+ */
+int cpu_rmap_add(struct cpu_rmap *rmap, void *obj)
+{
+	int index = get_free_index(rmap);
+
+	if (index < 0)
+		return index;
+
+	rmap->obj[index] = obj;
+	return index;
+}
+EXPORT_SYMBOL(cpu_rmap_add);
+
+/**
+ * cpu_rmap_update - update CPU rmap following a change of object affinity
+ * @rmap: CPU rmap to update
+ * @index: Index of object whose affinity changed
+ * @affinity: New CPU affinity of object
+ */
+int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,
+		    const struct cpumask *affinity)
+{
+	cpumask_var_t update_mask;
+	unsigned int cpu;
+
+	if (unlikely(!zalloc_cpumask_var(&update_mask, GFP_KERNEL)))
+		return -ENOMEM;
+
+	/* Invalidate distance for all CPUs for which this used to be
+	 * the nearest object.  Mark those CPUs for update.
+	 */
+	for_each_online_cpu(cpu) {
+		if (rmap->near[cpu].index == index) {
+			rmap->near[cpu].dist = CPU_RMAP_DIST_INF;
+			cpumask_set_cpu(cpu, update_mask);
+		}
+	}
+
+	debug_print_rmap(rmap, "after invalidating old distances");
+
+	/* Set distance to 0 for all CPUs in the new affinity mask.
+	 * Mark all CPUs within their NUMA nodes for update.
+	 */
+	for_each_cpu(cpu, affinity) {
+		rmap->near[cpu].index = index;
+		rmap->near[cpu].dist = 0;
+		cpumask_or(update_mask, update_mask,
+			   cpumask_of_node(cpu_to_node(cpu)));
+	}
+
+	debug_print_rmap(rmap, "after updating neighbours");
+
+	/* Update distances based on topology */
+	for_each_cpu(cpu, update_mask) {
+		if (cpu_rmap_copy_neigh(rmap, cpu,
+					topology_sibling_cpumask(cpu), 1))
+			continue;
+		if (cpu_rmap_copy_neigh(rmap, cpu,
+					topology_core_cpumask(cpu), 2))
+			continue;
+		if (cpu_rmap_copy_neigh(rmap, cpu,
+					cpumask_of_node(cpu_to_node(cpu)), 3))
+			continue;
+		/* We could continue into NUMA node distances, but for now
+		 * we give up.
+		 */
+	}
+
+	debug_print_rmap(rmap, "after copying neighbours");
+
+	free_cpumask_var(update_mask);
+	return 0;
+}
+EXPORT_SYMBOL(cpu_rmap_update);
+
+/* Glue between IRQ affinity notifiers and CPU rmaps */
+
+struct irq_glue {
+	struct irq_affinity_notify notify;
+	struct cpu_rmap *rmap;
+	u16 index;
+};
+
+/**
+ * free_irq_cpu_rmap - free a CPU affinity reverse-map used for IRQs
+ * @rmap: Reverse-map allocated with alloc_irq_cpu_map(), or %NULL
+ *
+ * Must be called in process context, before freeing the IRQs.
+ */
+void free_irq_cpu_rmap(struct cpu_rmap *rmap)
+{
+	struct irq_glue *glue;
+	u16 index;
+
+	if (!rmap)
+		return;
+
+	for (index = 0; index < rmap->size; index++) {
+		glue = rmap->obj[index];
+		if (glue)
+			irq_set_affinity_notifier(glue->notify.irq, NULL);
+	}
+
+	cpu_rmap_put(rmap);
+}
+EXPORT_SYMBOL(free_irq_cpu_rmap);
+
+/**
+ * irq_cpu_rmap_notify - callback for IRQ subsystem when IRQ affinity updated
+ * @notify: struct irq_affinity_notify passed by irq/manage.c
+ * @mask: cpu mask for new SMP affinity
+ *
+ * This is executed in workqueue context.
+ */
+static void
+irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
+{
+	struct irq_glue *glue =
+		container_of(notify, struct irq_glue, notify);
+	int rc;
+
+	rc = cpu_rmap_update(glue->rmap, glue->index, mask);
+	if (rc)
+		pr_warn("irq_cpu_rmap_notify: update failed: %d\n", rc);
+}
+
+/**
+ * irq_cpu_rmap_release - reclaiming callback for IRQ subsystem
+ * @ref: kref to struct irq_affinity_notify passed by irq/manage.c
+ */
+static void irq_cpu_rmap_release(struct kref *ref)
+{
+	struct irq_glue *glue =
+		container_of(ref, struct irq_glue, notify.kref);
+
+	glue->rmap->obj[glue->index] = NULL;
+	cpu_rmap_put(glue->rmap);
+	kfree(glue);
+}
+
+/**
+ * irq_cpu_rmap_remove - remove an IRQ from a CPU affinity reverse-map
+ * @rmap: The reverse-map
+ * @irq: The IRQ number
+ */
+int irq_cpu_rmap_remove(struct cpu_rmap *rmap, int irq)
+{
+	return irq_set_affinity_notifier(irq, NULL);
+}
+EXPORT_SYMBOL(irq_cpu_rmap_remove);
+
+/**
+ * irq_cpu_rmap_add - add an IRQ to a CPU affinity reverse-map
+ * @rmap: The reverse-map
+ * @irq: The IRQ number
+ *
+ * This adds an IRQ affinity notifier that will update the reverse-map
+ * automatically.
+ *
+ * Must be called in process context, after the IRQ is allocated but
+ * before it is bound with request_irq().
+ */
+int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq)
+{
+	struct irq_glue *glue = kzalloc_obj(*glue);
+	int rc;
+
+	if (!glue)
+		return -ENOMEM;
+	glue->notify.notify = irq_cpu_rmap_notify;
+	glue->notify.release = irq_cpu_rmap_release;
+	glue->rmap = rmap;
+	cpu_rmap_get(rmap);
+	rc = cpu_rmap_add(rmap, glue);
+	if (rc < 0)
+		goto err_add;
+
+	glue->index = rc;
+	rc = irq_set_affinity_notifier(irq, &glue->notify);
+	if (rc)
+		goto err_set;
+
+	return rc;
+
+err_set:
+	rmap->obj[glue->index] = NULL;
+err_add:
+	cpu_rmap_put(glue->rmap);
+	kfree(glue);
+	return rc;
+}
+EXPORT_SYMBOL(irq_cpu_rmap_add);