mm: make __free_pages_bootmem() only available at boot time

In order to simpilify management of totalram_pages and
zone->managed_pages, make __free_pages_bootmem() only available at boot
time.  With this change applied, __free_pages_bootmem() will only be
used by bootmem.c and nobootmem.c at boot time, so mark it as __init.
Other callers of __free_pages_bootmem() have been converted to use
free_reserved_page(), which handles totalram_pages and
zone->managed_pages in a safer way.

This patch also fix a bug in free_pagetable() for x86_64, which should
increase zone->managed_pages instead of zone->present_pages when freeing
reserved pages.

And now we have managed_pages_count_lock to protect totalram_pages and
zone->managed_pages, so remove the redundant ppb_lock lock in
put_page_bootmem().  This greatly simplifies the locking rules.

Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: Tang Chen <tangchen@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Minchan Kim <minchan@kernel.org>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: <sworddragon2@aol.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Tejun Heo <tj@kernel.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b7bdf7b..ec312a9 100644 (file)
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -712,36 +712,22 @@ EXPORT_SYMBOL_GPL(arch_add_memory);
 
 static void __meminit free_pagetable(struct page *page, int order)
 {
-       struct zone *zone;
-       bool bootmem = false;
        unsigned long magic;
        unsigned int nr_pages = 1 << order;
 
        /* bootmem page has reserved flag */
        if (PageReserved(page)) {
                __ClearPageReserved(page);
-               bootmem = true;
 
                magic = (unsigned long)page->lru.next;
                if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
                        while (nr_pages--)
                                put_page_bootmem(page++);
                } else
-                       __free_pages_bootmem(page, order);
+                       while (nr_pages--)
+                               free_reserved_page(page++);
        } else
                free_pages((unsigned long)page_address(page), order);
-
-       /*
-        * SECTION_INFO pages and MIX_SECTION_INFO pages
-        * are all allocated by bootmem.
-        */
-       if (bootmem) {
-               zone = page_zone(page);
-               zone_span_writelock(zone);
-               zone->present_pages += nr_pages;
-               zone_span_writeunlock(zone);
-               totalram_pages += nr_pages;
-       }
 }
 
 static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 6096cb9..814ecb2 100644 (file)
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -101,12 +101,9 @@ void get_page_bootmem(unsigned long info,  struct page *page,
        atomic_inc(&page->_count);
 }
 
-/* reference to __meminit __free_pages_bootmem is valid
- * so use __ref to tell modpost not to generate a warning */
-void __ref put_page_bootmem(struct page *page)
+void put_page_bootmem(struct page *page)
 {
        unsigned long type;
-       static DEFINE_MUTEX(ppb_lock);
 
        type = (unsigned long) page->lru.next;
        BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
@@ -116,17 +113,8 @@ void __ref put_page_bootmem(struct page *page)
                ClearPagePrivate(page);
                set_page_private(page, 0);
                INIT_LIST_HEAD(&page->lru);
-
-               /*
-                * Please refer to comment for __free_pages_bootmem()
-                * for why we serialize here.
-                */
-               mutex_lock(&ppb_lock);
-               __free_pages_bootmem(page, 0);
-               mutex_unlock(&ppb_lock);
-               totalram_pages++;
+               free_reserved_page(page);
        }
-
 }
 
 #ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 93f292a..2437a7e 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -745,14 +745,7 @@ static void __free_pages_ok(struct page *page, unsigned int order)
        local_irq_restore(flags);
 }
 
-/*
- * Read access to zone->managed_pages is safe because it's unsigned long,
- * but we still need to serialize writers. Currently all callers of
- * __free_pages_bootmem() except put_page_bootmem() should only be used
- * at boot time. So for shorter boot time, we shift the burden to
- * put_page_bootmem() to serialize writers.
- */
-void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
+void __init __free_pages_bootmem(struct page *page, unsigned int order)
 {
        unsigned int nr_pages = 1 << order;
        unsigned int loop;