percpu: move common parts out of pcpu_[de]populate_chunk()

percpu-vm and percpu-km implement separate versions of
pcpu_[de]populate_chunk() and some part which is or should be common
are currently in the specific implementations.  Make the following
changes.

* Allocate area clearing is moved from the pcpu_populate_chunk()
  implementations to pcpu_alloc().  This makes percpu-km's version
  noop.

* Quick exit tests in pcpu_[de]populate_chunk() of percpu-vm are moved
  to their respective callers so that they are applied to percpu-km
  too.  This doesn't make any meaningful difference as both functions
  are noop for percpu-km; however, this is more consistent and will
  help implementing atomic allocation support.

Signed-off-by: Tejun Heo <tj@kernel.org>

3 files changed, 31 insertions, 40 deletions

diff --git a/mm/percpu-km.c b/mm/percpu-km.c
index 89633fefc6a2..9a9096f08867 100644
--- a/mm/percpu-km.c
+++ b/mm/percpu-km.c
@@ -35,11 +35,6 @@
 
 static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
 {
-        unsigned int cpu;
-
-        for_each_possible_cpu(cpu)
-                memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
-
         return 0;
 }
 
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index d9e0b615492e..edf709793318 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -265,7 +265,7 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
  * @size: size of the area to populate in bytes
  *
  * For each cpu, populate and map pages [@page_start,@page_end) into
- * @chunk.  The area is cleared on return.
+ * @chunk.
  *
  * CONTEXT:
  * pcpu_alloc_mutex, does GFP_KERNEL allocation.
@@ -276,18 +276,8 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
         int page_end = PFN_UP(off + size);
         int free_end = page_start, unmap_end = page_start;
         struct page **pages;
-        unsigned int cpu;
         int rs, re, rc;
 
-        /* quick path, check whether all pages are already there */
-        rs = page_start;
-        pcpu_next_pop(chunk, &rs, &re, page_end);
-        if (rs == page_start && re == page_end)
-                goto clear;
-
-        /* need to allocate and map pages, this chunk can't be immutable */
-        WARN_ON(chunk->immutable);
-
         pages = pcpu_get_pages(chunk);
         if (!pages)
                 return -ENOMEM;
@@ -308,10 +298,6 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
         }
         pcpu_post_map_flush(chunk, page_start, page_end);
 
-        bitmap_set(chunk->populated, page_start, page_end - page_start);
-clear:
-        for_each_possible_cpu(cpu)
-                memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
         return 0;
 
 err_unmap:
@@ -345,15 +331,6 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size)
         struct page **pages;
         int rs, re;
 
-        /* quick path, check whether it's empty already */
-        rs = page_start;
-        pcpu_next_unpop(chunk, &rs, &re, page_end);
-        if (rs == page_start && re == page_end)
-                return;
-
-        /* immutable chunks can't be depopulated */
-        WARN_ON(chunk->immutable);
-
         /*
          * If control reaches here, there must have been at least one
          * successful population attempt so the temp pages array must
@@ -372,8 +349,6 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size)
 
         pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)
                 pcpu_free_pages(chunk, pages, rs, re);
-
-        bitmap_clear(chunk->populated, page_start, page_end - page_start);
 }
 
 static struct pcpu_chunk *pcpu_create_chunk(void)
diff --git a/mm/percpu.c b/mm/percpu.c
index da997f9800bd..6087384f6ef0 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -709,7 +709,8 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved)
         static int warn_limit = 10;
         struct pcpu_chunk *chunk;
         const char *err;
-        int slot, off, new_alloc;
+        int slot, off, new_alloc, cpu;
+        int page_start, page_end, rs, re;
         unsigned long flags;
         void __percpu *ptr;
 
@@ -802,17 +803,32 @@ restart:
 area_found:
         spin_unlock_irqrestore(&pcpu_lock, flags);
 
-        /* populate, map and clear the area */
-        if (pcpu_populate_chunk(chunk, off, size)) {
-                spin_lock_irqsave(&pcpu_lock, flags);
-                pcpu_free_area(chunk, off);
-                err = "failed to populate";
-                goto fail_unlock;
+        /* populate if not all pages are already there */
+        page_start = PFN_DOWN(off);
+        page_end = PFN_UP(off + size);
+
+        rs = page_start;
+        pcpu_next_pop(chunk, &rs, &re, page_end);
+
+        if (rs != page_start || re != page_end) {
+                WARN_ON(chunk->immutable);
+
+                if (pcpu_populate_chunk(chunk, off, size)) {
+                        spin_lock_irqsave(&pcpu_lock, flags);
+                        pcpu_free_area(chunk, off);
+                        err = "failed to populate";
+                        goto fail_unlock;
+                }
+
+                bitmap_set(chunk->populated, page_start, page_end - page_start);
         }
 
         mutex_unlock(&pcpu_alloc_mutex);
 
-        /* return address relative to base address */
+        /* clear the areas and return address relative to base address */
+        for_each_possible_cpu(cpu)
+                memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
+
         ptr = __addr_to_pcpu_ptr(chunk->base_addr + off);
         kmemleak_alloc_percpu(ptr, size);
         return ptr;
@@ -903,7 +919,12 @@ static void pcpu_reclaim(struct work_struct *work)
         spin_unlock_irq(&pcpu_lock);
 
         list_for_each_entry_safe(chunk, next, &todo, list) {
-                pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size);
+                int rs = 0, re;
+
+                pcpu_next_unpop(chunk, &rs, &re, PFN_UP(pcpu_unit_size));
+                if (rs || re != PFN_UP(pcpu_unit_size))
+                        pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size);
+
                 pcpu_destroy_chunk(chunk);
         }