Skip to contentSkip to conversation

mm: replace memmap_context by memplug_context

PATCH New Laurent Dufour 1 participant 2 messages Sep 29, 2020

Subsystems (7)
lore
Share & tools
lore
#0 lore raw

PATCH 1/2 mm: replace memmap_context by memplug_context

Backport version to the 5.4-stable tree of the commit:

c1d0da83358a ("mm: replace memmap_context by meminit_context")

---
 arch/ia64/mm/init.c    |  6 +++---
 include/linux/mm.h     |  2 +-
 include/linux/mmzone.h | 11 ++++++++---
 mm/memory_hotplug.c    |  2 +-
 mm/page_alloc.c        | 11 ++++++-----
 5 files changed, 19 insertions(+), 13 deletions(-)
arch/ia64/mm/init.c +3 -3
index 79e5cc70f1fd..561e2573bd34 100644
@@ -499,7 +499,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg)
 	if (map_start < map_end)
 		memmap_init_zone((unsigned long)(map_end - map_start),
 				 args->nid, args->zone, page_to_pfn(map_start),
-				 MEMMAP_EARLY, NULL);
+				 MEMINIT_EARLY, NULL);
 	return 0;
 }
 
@@ -508,8 +508,8 @@ memmap_init (unsigned long size, int nid, unsigned long zone,
 	     unsigned long start_pfn)
 {
 	if (!vmem_map) {
-		memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY,
-				NULL);
+		memmap_init_zone(size, nid, zone, start_pfn,
+				 MEMINIT_EARLY, NULL);
 	} else {
 		struct page *start;
 		struct memmap_init_callback_data args;
include/linux/mm.h +1 -1
index 05bc5f25ab85..83828c118b6b 100644
@@ -2179,7 +2179,7 @@ static inline void zero_resv_unavail(void) {}
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
 extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
-		enum memmap_context, struct vmem_altmap *);
+		enum meminit_context, struct vmem_altmap *);
 extern void setup_per_zone_wmarks(void);
 extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
include/linux/mmzone.h +8 -3
index fdd93a39f1fa..fa02014eba8e 100644
@@ -759,10 +759,15 @@ bool zone_watermark_ok(struct zone *z, unsigned int order,
 		unsigned int alloc_flags);
 bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
 		unsigned long mark, int classzone_idx);
-enum memmap_context {
-	MEMMAP_EARLY,
-	MEMMAP_HOTPLUG,
+/*
+ * Memory initialization context, use to differentiate memory added by
+ * the platform statically or via memory hotplug interface.
+ */
+enum meminit_context {
+	MEMINIT_EARLY,
+	MEMINIT_HOTPLUG,
 };
+
 extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
 				     unsigned long size);
 
mm/memory_hotplug.c +1 -1
index aae7ff485671..c839c4ad4871 100644
@@ -733,7 +733,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 	 * are reserved so nobody should be touching them so we should be safe
 	 */
 	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn,
-			MEMMAP_HOTPLUG, altmap);
+			 MEMINIT_HOTPLUG, altmap);
 
 	set_zone_contiguous(zone);
 }
mm/page_alloc.c +6 -5
index 5717ee66c8b3..545800433dfb 100644
@@ -5480,7 +5480,7 @@ void __ref build_all_zonelists(pg_data_t *pgdat)
  * done. Non-atomic initialization, single-pass.
  */
 void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
-		unsigned long start_pfn, enum memmap_context context,
+		unsigned long start_pfn, enum meminit_context context,
 		struct vmem_altmap *altmap)
 {
 	unsigned long end_pfn = start_pfn + size;
@@ -5507,7 +5507,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		 * There can be holes in boot-time mem_map[]s handed to this
 		 * function.  They do not exist on hotplugged memory.
 		 */
-		if (context != MEMMAP_EARLY)
+		if (context != MEMINIT_EARLY)
 			goto not_early;
 
 		if (!early_pfn_valid(pfn))
@@ -5542,7 +5542,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 not_early:
 		page = pfn_to_page(pfn);
 		__init_single_page(page, pfn, zone, nid);
-		if (context == MEMMAP_HOTPLUG)
+		if (context == MEMINIT_HOTPLUG)
 			SetPageReserved(page);
 
 		/*
@@ -5557,7 +5557,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		 * check here not to call set_pageblock_migratetype() against
 		 * pfn out of zone.
 		 *
-		 * Please note that MEMMAP_HOTPLUG path doesn't clear memmap
+		 * Please note that MEMINIT_HOTPLUG path doesn't clear memmap
 		 * because this is done early in sparse_add_one_section
 		 */
 		if (!(pfn & (pageblock_nr_pages - 1))) {
@@ -5578,7 +5578,8 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 
 #ifndef __HAVE_ARCH_MEMMAP_INIT
 #define memmap_init(size, nid, zone, start_pfn) \
-	memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY, NULL)
+	memmap_init_zone((size), (nid), (zone), (start_pfn), \
+			 MEMINIT_EARLY, NULL)
 #endif
 
 static int zone_batchsize(struct zone *zone)
Signature · 1 line
2.28.0
#1 lore raw

PATCH 2/2 mm: don't rely on system state to detect hot-plug operations

Backport version to the 5.4-stable tree of the commit:

f85086f95fa3 ("mm: don't rely on system state to detect hot-plug operations")

---
 drivers/base/node.c  | 84 ++++++++++++++++++++++++++++----------------
 include/linux/node.h | 11 +++---
 mm/memory_hotplug.c  |  3 +-
 3 files changed, 63 insertions(+), 35 deletions(-)
drivers/base/node.c +54 -30
index f3565c2dbc52..503e2f90e58e 100644
@@ -403,10 +403,32 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
 	return pfn_to_nid(pfn);
 }
 
+static int do_register_memory_block_under_node(int nid,
+					       struct memory_block *mem_blk)
+{
+	int ret;
+
+	/*
+	 * If this memory block spans multiple nodes, we only indicate
+	 * the last processed node.
+	 */
+	mem_blk->nid = nid;
+
+	ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
+				       &mem_blk->dev.kobj,
+				       kobject_name(&mem_blk->dev.kobj));
+	if (ret)
+		return ret;
+
+	return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
+				&node_devices[nid]->dev.kobj,
+				kobject_name(&node_devices[nid]->dev.kobj));
+}
+
 /* register memory section under specified node if it spans that node */
-int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg)
+int register_mem_block_under_node_early(struct memory_block *mem_blk, void *arg)
 {
-	int ret, nid = *(int *)arg;
+	int nid = *(int *)arg;
 	unsigned long pfn, sect_start_pfn, sect_end_pfn;
 
 	sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
@@ -426,38 +448,33 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg)
 		}
 
 		/*
-		 * We need to check if page belongs to nid only for the boot
-		 * case, during hotplug we know that all pages in the memory
-		 * block belong to the same node.
-		 */
-		if (system_state == SYSTEM_BOOTING) {
-			page_nid = get_nid_for_pfn(pfn);
-			if (page_nid < 0)
-				continue;
-			if (page_nid != nid)
-				continue;
-		}
-
-		/*
-		 * If this memory block spans multiple nodes, we only indicate
-		 * the last processed node.
+		 * We need to check if page belongs to nid only at the boot
+		 * case because node's ranges can be interleaved.
 		 */
-		mem_blk->nid = nid;
-
-		ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
-					&mem_blk->dev.kobj,
-					kobject_name(&mem_blk->dev.kobj));
-		if (ret)
-			return ret;
+		page_nid = get_nid_for_pfn(pfn);
+		if (page_nid < 0)
+			continue;
+		if (page_nid != nid)
+			continue;
 
-		return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
-				&node_devices[nid]->dev.kobj,
-				kobject_name(&node_devices[nid]->dev.kobj));
+		return do_register_memory_block_under_node(nid, mem_blk);
 	}
 	/* mem section does not span the specified node */
 	return 0;
 }
 
+/*
+ * During hotplug we know that all pages in the memory block belong to the same
+ * node.
+ */
+static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk,
+						 void *arg)
+{
+	int nid = *(int *)arg;
+
+	return do_register_memory_block_under_node(nid, mem_blk);
+}
+
 /*
  * Unregister a memory block device under the node it spans. Memory blocks
  * with multiple nodes cannot be offlined and therefore also never be removed.
@@ -473,10 +490,17 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
 			  kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
 }
 
-int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn)
+int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
+		      enum meminit_context context)
 {
-	return walk_memory_range(start_pfn, end_pfn, (void *)&nid,
-					register_mem_sect_under_node);
+	walk_memory_blocks_func_t func;
+
+	if (context == MEMINIT_HOTPLUG)
+		func = register_mem_block_under_node_hotplug;
+	else
+		func = register_mem_block_under_node_early;
+
+	return walk_memory_range(start_pfn, end_pfn, (void *)&nid, func);
 }
 
 #ifdef CONFIG_HUGETLBFS
include/linux/node.h +7 -4
index 708939bae9aa..a79ec4492650 100644
@@ -32,11 +32,13 @@ extern struct node *node_devices[];
 typedef  void (*node_registration_func_t)(struct node *);
 
 #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
-extern int link_mem_sections(int nid, unsigned long start_pfn,
-			     unsigned long end_pfn);
+int link_mem_sections(int nid, unsigned long start_pfn,
+		      unsigned long end_pfn,
+		      enum meminit_context context);
 #else
 static inline int link_mem_sections(int nid, unsigned long start_pfn,
-				    unsigned long end_pfn)
+				    unsigned long end_pfn,
+				    enum meminit_context context)
 {
 	return 0;
 }
@@ -61,7 +63,8 @@ static inline int register_one_node(int nid)
 		if (error)
 			return error;
 		/* link memory sections under this node */
-		error = link_mem_sections(nid, start_pfn, end_pfn);
+		error = link_mem_sections(nid, start_pfn, end_pfn,
+					  MEMINIT_EARLY);
 	}
 
 	return error;
mm/memory_hotplug.c +2 -1
index c839c4ad4871..e60e28131f67 100644
@@ -1102,7 +1102,8 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online)
 	}
 
 	/* link memory sections under this node.*/
-	ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1));
+	ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
+				MEMINIT_HOTPLUG);
 	BUG_ON(ret);
 
 	/* create new memmap entry */
Signature · 1 line
2.28.0