Skip to contentSkip to conversation

mm: replace memmap_context by memplug_context

PATCH In review Laurent Dufour 2 participants 5 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        | 10 +++++-----
 5 files changed, 18 insertions(+), 13 deletions(-)
arch/ia64/mm/init.c +3 -3
index a6dd80a2c939..ee50506d86f4 100644
@@ -518,7 +518,7 @@ 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;
 }
 
@@ -527,8 +527,8 @@ 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 3285dae06c03..34119f393a80 100644
@@ -2208,7 +2208,7 @@ 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 85804ba62215..a90aba3d6afb 100644
@@ -822,10 +822,15 @@ 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 3eb0b311b4a1..6a4b3a01e1b6 100644
@@ -725,7 +725,7 @@ 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 +5 -5
index 67a9943aa595..373ca5780758 100644
@@ -5875,7 +5875,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
  * 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 pfn, end_pfn = start_pfn + size;
@@ -5907,7 +5907,7 @@ 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) {
 			if (!early_pfn_valid(pfn))
 				continue;
 			if (!early_pfn_in_nid(pfn, nid))
@@ -5920,7 +5920,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 
 		page = pfn_to_page(pfn);
 		__init_single_page(page, pfn, zone, nid);
-		if (context == MEMMAP_HOTPLUG)
+		if (context == MEMINIT_HOTPLUG)
 			__SetPageReserved(page);
 
 		/*
@@ -6002,7 +6002,7 @@ void __ref memmap_init_zone_device(struct zone *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 section_activate()
 		 */
 		if (!(pfn & (pageblock_nr_pages - 1))) {
@@ -6028,7 +6028,7 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 void __meminit __weak memmap_init(unsigned long size, int nid,
 				  unsigned long zone, unsigned long start_pfn)
 {
-	memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY, NULL);
+	memmap_init_zone(size, nid, zone, start_pfn, MEMINIT_EARLY, NULL);
 }
 
 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  | 85 ++++++++++++++++++++++++++++----------------
 include/linux/node.h | 11 +++---
 mm/memory_hotplug.c  |  3 +-
 3 files changed, 64 insertions(+), 35 deletions(-)
drivers/base/node.c +55 -30
index 296546ffed6c..9c6e6a7b9354 100644
@@ -758,14 +758,36 @@ 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 */
-static int register_mem_sect_under_node(struct memory_block *mem_blk,
-					 void *arg)
+static int register_mem_block_under_node_early(struct memory_block *mem_blk,
+					       void *arg)
 {
 	unsigned long memory_block_pfns = memory_block_size_bytes() / PAGE_SIZE;
 	unsigned long start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
 	unsigned long end_pfn = start_pfn + memory_block_pfns - 1;
-	int ret, nid = *(int *)arg;
+	int nid = *(int *)arg;
 	unsigned long pfn;
 
 	for (pfn = start_pfn; pfn <= end_pfn; pfn++) {
@@ -782,38 +804,33 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk,
 		}
 
 		/*
-		 * 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.
@@ -829,11 +846,19 @@ 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)
 {
+	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_blocks(PFN_PHYS(start_pfn),
 				  PFN_PHYS(end_pfn - start_pfn), (void *)&nid,
-				  register_mem_sect_under_node);
+				  func);
 }
 
 #ifdef CONFIG_HUGETLBFS
include/linux/node.h +7 -4
index 4866f32a02d8..014ba3ab2efd 100644
@@ -99,11 +99,13 @@ 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;
 }
@@ -128,7 +130,8 @@ 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 6a4b3a01e1b6..308beca3ffeb 100644
@@ -1082,7 +1082,8 @@ int __ref add_memory_resource(int nid, struct resource *res)
 	}
 
 	/* 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
maintainer
#2 lore raw
In reply to Laurent Dufour
Quoted 6 lines · Laurent Dufour

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

c1d0da83358a ("mm: replace memmap_context by meminit_context")

What happened to the full changelog from the original commit, and all of the cc: and signed-off-by from it?

Please include that in the patch, you don't want to see all of that stripped off, right?

thanks,

greg k-h

#3 lore raw

Le 29/09/2020 à 16:29, Greg KH a écrit :

Quoted 5 lines · Laurent Dufour
Quoted 4 lines

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

c1d0da83358a ("mm: replace memmap_context by meminit_context")

Quoted 8 lines
Quoted 2 lines

What happened to the full changelog from the original commit, and all of the cc: and signed-off-by from it?

Please include that in the patch, you don't want to see all of that stripped off, right?

Sorry, I was thinking some magic script was pulling the original commit description based on the git commit id ;)

I'll send the patches again.
Is there a specific tag to use when mentioning the original commit id?

Thanks,
Laurent.

maintainer
#4 lore raw
Quoted 12 lines · Laurent Dufour

Le 29/09/2020 à 16:29, Greg KH a écrit :

Quoted 11 lines · Laurent Dufour
Quoted 6 lines

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

c1d0da83358a ("mm: replace memmap_context by meminit_context")

What happened to the full changelog from the original commit, and all of the cc: and signed-off-by from it?

Quoted 8 lines
Quoted 2 lines

Please include that in the patch, you don't want to see all of that stripped off, right?

Sorry, I was thinking some magic script was pulling the original commit description based on the git commit id ;)

I'll send the patches again.
Is there a specific tag to use when mentioning the original commit id?

You can copy the format we use when committing the patch to a stable tree if you want to be nice.

thanks,

greg k-h