Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Zi Yan <zi.yan@sent.com>
To:     linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc:     Dave Hansen <dave.hansen@linux.intel.com>,
        Michal Hocko <mhocko@kernel.org>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Vlastimil Babka <vbabka@suse.cz>,
        Mel Gorman <mgorman@techsingularity.net>,
        John Hubbard <jhubbard@nvidia.com>,
        Mark Hairgrove <mhairgrove@nvidia.com>,
        Nitin Gupta <nigupta@nvidia.com>,
        David Nellans <dnellans@nvidia.com>, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH 06/31] mm: Make MAX_ORDER configurable in Kconfig for buddy allocator.
Date:   Fri, 15 Feb 2019 14:08:31 -0800
Message-Id: <20190215220856.29749-7-zi.yan@sent.com>
In-Reply-To: <20190215220856.29749-1-zi.yan@sent.com>
References: <20190215220856.29749-1-zi.yan@sent.com>
Reply-To: ziy@nvidia.com
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Zi Yan <ziy@nvidia.com>

To test 1GB THP implemented in the following patches, this patch enables
changing MAX_ORDER of the buddy allocator.

It should be dropped later when we solely rely on mem_defrag to generate
1GB THPs.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 arch/x86/Kconfig                 | 15 +++++++++++++++
 arch/x86/include/asm/sparsemem.h |  4 ++--
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 68261430fe6e..f766ff5651d5 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1665,6 +1665,21 @@ config X86_PMEM_LEGACY
 
 	  Say Y if unsure.
 
+config FORCE_MAX_ZONEORDER
+	int "Maximum zone order"
+	range 11 20
+	default "11"
+	help
+	  The kernel memory allocator divides physically contiguous memory
+	  blocks into "zones", where each zone is a power of two number of
+	  pages.  This option selects the largest power of two that the kernel
+	  keeps in the memory allocator.  If you need to allocate very large
+	  blocks of physically contiguous memory, then you may need to
+	  increase this value.
+
+	  This config option is actually maximum order plus one. For example,
+	  a value of 11 means that the largest free memory block is 2^10 pages.
+
 config HIGHPTE
 	bool "Allocate 3rd-level pagetables from highmem"
 	depends on HIGHMEM
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 199218719a86..2df61d5ccc2d 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -21,12 +21,12 @@
 #  define MAX_PHYSADDR_BITS	36
 #  define MAX_PHYSMEM_BITS	36
 # else
-#  define SECTION_SIZE_BITS	26
+#  define SECTION_SIZE_BITS	31
 #  define MAX_PHYSADDR_BITS	32
 #  define MAX_PHYSMEM_BITS	32
 # endif
 #else /* CONFIG_X86_32 */
-# define SECTION_SIZE_BITS	27 /* matt - 128 is convenient right now */
+# define SECTION_SIZE_BITS	31 /* matt - 128 is convenient right now */
 # define MAX_PHYSADDR_BITS	(pgtable_l5_enabled() ? 52 : 44)
 # define MAX_PHYSMEM_BITS	(pgtable_l5_enabled() ? 52 : 46)
 #endif
-- 
2.20.1