Merge branch 'for-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

Pull percpu updates from Tejun Heo:

 - Nick improved generic implementations of percpu operations which
   modify the variable and return so that they calculate the physical
   address only once.

 - percpu_ref percpu <-> atomic mode switching improvements. The
   patchset was originally posted about a year ago but fell through the
   crack.

 - misc non-critical fixes.

* 'for-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu:
  mm/percpu.c: fix potential memory leakage for pcpu_embed_first_chunk()
  mm/percpu.c: correct max_distance calculation for pcpu_embed_first_chunk()
  percpu: eliminate two sparse warnings
  percpu: improve generic percpu modify-return implementation
  percpu-refcount: init ->confirm_switch member properly
  percpu_ref: allow operation mode switching operations to be called concurrently
  percpu_ref: restructure operation mode switching
  percpu_ref: unify staggered atomic switching wait behavior
  percpu_ref: reorganize __percpu_ref_switch_to_atomic() and relocate percpu_ref_switch_to_atomic()
  percpu_ref: remove unnecessary RCU grace period for staggered atomic switching confirmation

1 files changed, 20 insertions, 18 deletions

diff --git a/mm/percpu.c b/mm/percpu.c
index 9903830..2557143 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1961,8 +1961,9 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 	void *base = (void *)ULONG_MAX;
 	void **areas = NULL;
 	struct pcpu_alloc_info *ai;
-	size_t size_sum, areas_size, max_distance;
-	int group, i, rc;
+	size_t size_sum, areas_size;
+	unsigned long max_distance;
+	int group, i, highest_group, rc;
 
 	ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size,
 				   cpu_distance_fn);
@@ -1978,7 +1979,8 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 		goto out_free;
 	}
 
-	/* allocate, copy and determine base address */
+	/* allocate, copy and determine base address & max_distance */
+	highest_group = 0;
 	for (group = 0; group < ai->nr_groups; group++) {
 		struct pcpu_group_info *gi = &ai->groups[group];
 		unsigned int cpu = NR_CPUS;
@@ -1999,6 +2001,21 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 		areas[group] = ptr;
 
 		base = min(ptr, base);
+		if (ptr > areas[highest_group])
+			highest_group = group;
+	}
+	max_distance = areas[highest_group] - base;
+	max_distance += ai->unit_size * ai->groups[highest_group].nr_units;
+
+	/* warn if maximum distance is further than 75% of vmalloc space */
+	if (max_distance > VMALLOC_TOTAL * 3 / 4) {
+		pr_warn("max_distance=0x%lx too large for vmalloc space 0x%lx\n",
+				max_distance, VMALLOC_TOTAL);
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+		/* and fail if we have fallback */
+		rc = -EINVAL;
+		goto out_free_areas;
+#endif
 	}
 
 	/*
@@ -2023,23 +2040,8 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 	}
 
 	/* base address is now known, determine group base offsets */
-	max_distance = 0;
 	for (group = 0; group < ai->nr_groups; group++) {
 		ai->groups[group].base_offset = areas[group] - base;
-		max_distance = max_t(size_t, max_distance,
-				     ai->groups[group].base_offset);
-	}
-	max_distance += ai->unit_size;
-
-	/* warn if maximum distance is further than 75% of vmalloc space */
-	if (max_distance > VMALLOC_TOTAL * 3 / 4) {
-		pr_warn("max_distance=0x%zx too large for vmalloc space 0x%lx\n",
-			max_distance, VMALLOC_TOTAL);
-#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
-		/* and fail if we have fallback */
-		rc = -EINVAL;
-		goto out_free;
-#endif
 	}
 
 	pr_info("Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",