Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Muchun Song <songmuchun@bytedance.com>
To:     akpm@linux-foundation.org, corbet@lwn.net, david@redhat.com,
        mike.kravetz@oracle.com, osalvador@suse.de, paulmck@kernel.org
Cc:     linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-mm@kvack.org, duanxiongchun@bytedance.com, smuchun@gmail.com,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v5 1/2] mm: memory_hotplug: enumerate all supported section flags
Date:   Mon, 20 Jun 2022 19:06:15 +0800
Message-Id: <20220620110616.12056-2-songmuchun@bytedance.com>
In-Reply-To: <20220620110616.12056-1-songmuchun@bytedance.com>
References: <20220620110616.12056-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

We are almost running out of section flags, only one bit is available in
the worst case (powerpc with 256k pages).  However, there are still some
free bits (in ->section_mem_map) on other architectures (e.g. x86_64 has
10 bits available, arm64 has 8 bits available with worst case of 64K
pages).  We have hard coded those numbers in code, it is inconvenient to
use those bits on other architectures except powerpc.  So transfer those
section flags to enumeration to make it easy to add new section flags in
the future. Also, move SECTION_TAINT_ZONE_DEVICE into the scope of
CONFIG_ZONE_DEVICE to save a bit on non-zone-device case.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/mmzone.h | 41 ++++++++++++++++++++++++++++++++---------
 mm/memory_hotplug.c    |  6 ++++++
 mm/sparse.c            |  2 +-
 3 files changed, 39 insertions(+), 10 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index aab70355d64f..2b5757752333 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1418,16 +1418,32 @@ extern size_t mem_section_usage_size(void);
  *      (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the
  *      worst combination is powerpc with 256k pages,
  *      which results in PFN_SECTION_SHIFT equal 6.
- * To sum it up, at least 6 bits are available.
+ * To sum it up, at least 6 bits are available on all architectures.
+ * However, we can exceed 6 bits on some other architectures except
+ * powerpc (e.g. 15 bits are available on x86_64, 13 bits are available
+ * with the worst case of 64K pages on arm64) if we make sure the
+ * exceeded bit is not applicable to powerpc.
  */
-#define SECTION_MARKED_PRESENT		(1UL<<0)
-#define SECTION_HAS_MEM_MAP		(1UL<<1)
-#define SECTION_IS_ONLINE		(1UL<<2)
-#define SECTION_IS_EARLY		(1UL<<3)
-#define SECTION_TAINT_ZONE_DEVICE	(1UL<<4)
-#define SECTION_MAP_LAST_BIT		(1UL<<5)
-#define SECTION_MAP_MASK		(~(SECTION_MAP_LAST_BIT-1))
-#define SECTION_NID_SHIFT		6
+enum {
+	SECTION_MARKED_PRESENT_BIT,
+	SECTION_HAS_MEM_MAP_BIT,
+	SECTION_IS_ONLINE_BIT,
+	SECTION_IS_EARLY_BIT,
+#ifdef CONFIG_ZONE_DEVICE
+	SECTION_TAINT_ZONE_DEVICE_BIT,
+#endif
+	SECTION_MAP_LAST_BIT,
+};
+
+#define SECTION_MARKED_PRESENT		BIT(SECTION_MARKED_PRESENT_BIT)
+#define SECTION_HAS_MEM_MAP		BIT(SECTION_HAS_MEM_MAP_BIT)
+#define SECTION_IS_ONLINE		BIT(SECTION_IS_ONLINE_BIT)
+#define SECTION_IS_EARLY		BIT(SECTION_IS_EARLY_BIT)
+#ifdef CONFIG_ZONE_DEVICE
+#define SECTION_TAINT_ZONE_DEVICE	BIT(SECTION_TAINT_ZONE_DEVICE_BIT)
+#endif
+#define SECTION_MAP_MASK		(~(BIT(SECTION_MAP_LAST_BIT) - 1))
+#define SECTION_NID_SHIFT		SECTION_MAP_LAST_BIT
 
 static inline struct page *__section_mem_map_addr(struct mem_section *section)
 {
@@ -1466,12 +1482,19 @@ static inline int online_section(struct mem_section *section)
 	return (section && (section->section_mem_map & SECTION_IS_ONLINE));
 }
 
+#ifdef CONFIG_ZONE_DEVICE
 static inline int online_device_section(struct mem_section *section)
 {
 	unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE;
 
 	return section && ((section->section_mem_map & flags) == flags);
 }
+#else
+static inline int online_device_section(struct mem_section *section)
+{
+	return 0;
+}
+#endif
 
 static inline int online_section_nr(unsigned long nr)
 {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1f1a730c4499..6662b86e9e64 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -670,12 +670,18 @@ static void __meminit resize_pgdat_range(struct pglist_data *pgdat, unsigned lon
 
 }
 
+#ifdef CONFIG_ZONE_DEVICE
 static void section_taint_zone_device(unsigned long pfn)
 {
 	struct mem_section *ms = __pfn_to_section(pfn);
 
 	ms->section_mem_map |= SECTION_TAINT_ZONE_DEVICE;
 }
+#else
+static inline void section_taint_zone_device(unsigned long pfn)
+{
+}
+#endif
 
 /*
  * Associate the pfn range with the given zone, initializing the memmaps
diff --git a/mm/sparse.c b/mm/sparse.c
index cb3bfae64036..e5a8a3a0edd7 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -281,7 +281,7 @@ static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long p
 {
 	unsigned long coded_mem_map =
 		(unsigned long)(mem_map - (section_nr_to_pfn(pnum)));
-	BUILD_BUG_ON(SECTION_MAP_LAST_BIT > (1UL<<PFN_SECTION_SHIFT));
+	BUILD_BUG_ON(SECTION_MAP_LAST_BIT > PFN_SECTION_SHIFT);
 	BUG_ON(coded_mem_map & ~SECTION_MAP_MASK);
 	return coded_mem_map;
 }
-- 
2.11.0