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 07/31] mm: deallocate pages with order > MAX_ORDER.
Date:   Fri, 15 Feb 2019 14:08:32 -0800
Message-Id: <20190215220856.29749-8-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>

When MAX_ORDER is not set to allocate 1GB pages and 1GB THPs are created
from in-place promotion, we need this to properly free 1GB THPs.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 mm/page_alloc.c | 36 ++++++++++++++++++++++++++++++------
 1 file changed, 30 insertions(+), 6 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9ba2cdc320f2..cfa99bb54bd6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1287,6 +1287,24 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
 	}
 }
 
+static void destroy_compound_gigantic_page(struct page *page,
+					unsigned int order)
+{
+	int i;
+	int nr_pages = 1 << order;
+	struct page *p = page + 1;
+
+	atomic_set(compound_mapcount_ptr(page), 0);
+	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
+		clear_compound_head(p);
+		set_page_refcounted(p);
+	}
+
+	set_compound_order(page, 0);
+	__ClearPageHead(page);
+	set_page_refcounted(page);
+}
+
 static void __free_pages_ok(struct page *page, unsigned int order)
 {
 	unsigned long flags;
@@ -1296,11 +1314,16 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 	if (!free_pages_prepare(page, order, true))
 		return;
 
-	migratetype = get_pfnblock_migratetype(page, pfn);
-	local_irq_save(flags);
-	__count_vm_events(PGFREE, 1 << order);
-	free_one_page(page_zone(page), page, pfn, order, migratetype);
-	local_irq_restore(flags);
+	if (order > MAX_ORDER) {
+		destroy_compound_gigantic_page(page, order);
+		free_contig_range(page_to_pfn(page), 1 << order);
+	} else {
+		migratetype = get_pfnblock_migratetype(page, pfn);
+		local_irq_save(flags);
+		__count_vm_events(PGFREE, 1 << order);
+		free_one_page(page_zone(page), page, pfn, order, migratetype);
+		local_irq_restore(flags);
+	}
 }
 
 static void __init __free_pages_boot_core(struct page *page, unsigned int order)
@@ -8281,6 +8304,8 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	return ret;
 }
 
+#endif
+
 void free_contig_range(unsigned long pfn, unsigned nr_pages)
 {
 	unsigned int count = 0;
@@ -8293,7 +8318,6 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
 	}
 	WARN(count != 0, "%d pages are still in use!\n", count);
 }
-#endif
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
-- 
2.20.1