[3.11.y.z extended stable] Patch "mm: page_alloc: fix CMA area initialisation when pageblock > MAX_ORDER" has been added to staging queue

[Luis Henriques]

This is a note to let you know that I have just added a patch titled

    mm: page_alloc: fix CMA area initialisation when pageblock > MAX_ORDER

to the linux-3.11.y-queue branch of the 3.11.y.z extended stable tree 
which can be found at:

 http://kernel.ubuntu.com/git?p=ubuntu/linux.git;a=shortlog;h=refs/heads/linux-3.11.y-queue

If you, or anyone else, feels it should not be added to this tree, please 
reply to this email.

For more information about the 3.11.y.z tree, see
https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable

Thanks.
-Luis

------

>From 27910d2c2732f94eb416f510227d29d47decd93e Mon Sep 17 00:00:00 2001
From: Michal Nazarewicz <mina86 at mina86.com>
Date: Wed, 2 Jul 2014 15:22:35 -0700
Subject: mm: page_alloc: fix CMA area initialisation when pageblock >
 MAX_ORDER
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit dc78327c0ea7da5186d8cbc1647bd6088c5c9fa5 upstream.

With a kernel configured with ARM64_64K_PAGES && !TRANSPARENT_HUGEPAGE,
the following is triggered at early boot:

  SMP: Total of 8 processors activated.
  devtmpfs: initialized
  Unable to handle kernel NULL pointer dereference at virtual address 00000008
  pgd = fffffe0000050000
  [00000008] *pgd=00000043fba00003, *pmd=00000043fba00003, *pte=00e0000078010407
  Internal error: Oops: 96000006 [#1] SMP
  Modules linked in:
  CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.15.0-rc864k+ #44
  task: fffffe03bc040000 ti: fffffe03bc080000 task.ti: fffffe03bc080000
  PC is at __list_add+0x10/0xd4
  LR is at free_one_page+0x270/0x638
  ...
  Call trace:
    __list_add+0x10/0xd4
    free_one_page+0x26c/0x638
    __free_pages_ok.part.52+0x84/0xbc
    __free_pages+0x74/0xbc
    init_cma_reserved_pageblock+0xe8/0x104
    cma_init_reserved_areas+0x190/0x1e4
    do_one_initcall+0xc4/0x154
    kernel_init_freeable+0x204/0x2a8
    kernel_init+0xc/0xd4

This happens because init_cma_reserved_pageblock() calls
__free_one_page() with pageblock_order as page order but it is bigger
than MAX_ORDER.  This in turn causes accesses past zone->free_list[].

Fix the problem by changing init_cma_reserved_pageblock() such that it
splits pageblock into individual MAX_ORDER pages if pageblock is bigger
than a MAX_ORDER page.

In cases where !CONFIG_HUGETLB_PAGE_SIZE_VARIABLE, which is all
architectures expect for ia64, powerpc and tile at the moment, the
“pageblock_order > MAX_ORDER” condition will be optimised out since both
sides of the operator are constants.  In cases where pageblock size is
variable, the performance degradation should not be significant anyway
since init_cma_reserved_pageblock() is called only at boot time at most
MAX_CMA_AREAS times which by default is eight.

Signed-off-by: Michal Nazarewicz <mina86 at mina86.com>
Reported-by: Mark Salter <msalter at redhat.com>
Tested-by: Mark Salter <msalter at redhat.com>
Tested-by: Christopher Covington <cov at codeaurora.org>
Cc: Mel Gorman <mgorman at suse.de>
Cc: David Rientjes <rientjes at google.com>
Cc: Marek Szyprowski <m.szyprowski at samsung.com>
Cc: Catalin Marinas <catalin.marinas at arm.com>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques at canonical.com>
---
 mm/page_alloc.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6a2b267a521f..1b5e9fb49ed4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -780,9 +780,21 @@ void __init init_cma_reserved_pageblock(struct page *page)
 		set_page_count(p, 0);
 	} while (++p, --i);

-	set_page_refcounted(page);
 	set_pageblock_migratetype(page, MIGRATE_CMA);
-	__free_pages(page, pageblock_order);
+
+	if (pageblock_order >= MAX_ORDER) {
+		i = pageblock_nr_pages;
+		p = page;
+		do {
+			set_page_refcounted(p);
+			__free_pages(p, MAX_ORDER - 1);
+			p += MAX_ORDER_NR_PAGES;
+		} while (i -= MAX_ORDER_NR_PAGES);
+	} else {
+		set_page_refcounted(page);
+		__free_pages(page, pageblock_order);
+	}
+
 	adjust_managed_page_count(page, pageblock_nr_pages);
 }
 #endif
--
1.9.1