sparsemem: Put mem map for one node together.

Add vmemmap_alloc_block_buf for mem map only.

It will fallback to the old way if it cannot get a block that big.

Before this patch, when a node have 128g ram installed, memmap are
split into two parts or more.
[    0.000000]  [ffffea0000000000-ffffea003fffffff] PMD -> [ffff880100600000-ffff88013e9fffff] on node 1
[    0.000000]  [ffffea0040000000-ffffea006fffffff] PMD -> [ffff88013ec00000-ffff88016ebfffff] on node 1
[    0.000000]  [ffffea0070000000-ffffea007fffffff] PMD -> [ffff882000600000-ffff8820105fffff] on node 0
[    0.000000]  [ffffea0080000000-ffffea00bfffffff] PMD -> [ffff882010800000-ffff8820507fffff] on node 0
[    0.000000]  [ffffea00c0000000-ffffea00dfffffff] PMD -> [ffff882050a00000-ffff8820709fffff] on node 0
[    0.000000]  [ffffea00e0000000-ffffea00ffffffff] PMD -> [ffff884000600000-ffff8840205fffff] on node 2
[    0.000000]  [ffffea0100000000-ffffea013fffffff] PMD -> [ffff884020800000-ffff8840607fffff] on node 2
[    0.000000]  [ffffea0140000000-ffffea014fffffff] PMD -> [ffff884060a00000-ffff8840709fffff] on node 2
[    0.000000]  [ffffea0150000000-ffffea017fffffff] PMD -> [ffff886000600000-ffff8860305fffff] on node 3
[    0.000000]  [ffffea0180000000-ffffea01bfffffff] PMD -> [ffff886030800000-ffff8860707fffff] on node 3
[    0.000000]  [ffffea01c0000000-ffffea01ffffffff] PMD -> [ffff888000600000-ffff8880405fffff] on node 4
[    0.000000]  [ffffea0200000000-ffffea022fffffff] PMD -> [ffff888040800000-ffff8880707fffff] on node 4
[    0.000000]  [ffffea0230000000-ffffea023fffffff] PMD -> [ffff88a000600000-ffff88a0105fffff] on node 5
[    0.000000]  [ffffea0240000000-ffffea027fffffff] PMD -> [ffff88a010800000-ffff88a0507fffff] on node 5
[    0.000000]  [ffffea0280000000-ffffea029fffffff] PMD -> [ffff88a050a00000-ffff88a0709fffff] on node 5
[    0.000000]  [ffffea02a0000000-ffffea02bfffffff] PMD -> [ffff88c000600000-ffff88c0205fffff] on node 6
[    0.000000]  [ffffea02c0000000-ffffea02ffffffff] PMD -> [ffff88c020800000-ffff88c0607fffff] on node 6
[    0.000000]  [ffffea0300000000-ffffea030fffffff] PMD -> [ffff88c060a00000-ffff88c0709fffff] on node 6
[    0.000000]  [ffffea0310000000-ffffea033fffffff] PMD -> [ffff88e000600000-ffff88e0305fffff] on node 7
[    0.000000]  [ffffea0340000000-ffffea037fffffff] PMD -> [ffff88e030800000-ffff88e0707fffff] on node 7

after patch will get
[    0.000000]  [ffffea0000000000-ffffea006fffffff] PMD -> [ffff880100200000-ffff88016e5fffff] on node 0
[    0.000000]  [ffffea0070000000-ffffea00dfffffff] PMD -> [ffff882000200000-ffff8820701fffff] on node 1
[    0.000000]  [ffffea00e0000000-ffffea014fffffff] PMD -> [ffff884000200000-ffff8840701fffff] on node 2
[    0.000000]  [ffffea0150000000-ffffea01bfffffff] PMD -> [ffff886000200000-ffff8860701fffff] on node 3
[    0.000000]  [ffffea01c0000000-ffffea022fffffff] PMD -> [ffff888000200000-ffff8880701fffff] on node 4
[    0.000000]  [ffffea0230000000-ffffea029fffffff] PMD -> [ffff88a000200000-ffff88a0701fffff] on node 5
[    0.000000]  [ffffea02a0000000-ffffea030fffffff] PMD -> [ffff88c000200000-ffff88c0701fffff] on node 6
[    0.000000]  [ffffea0310000000-ffffea037fffffff] PMD -> [ffff88e000200000-ffff88e0701fffff] on node 7

-v2: change buf to vmemmap_buf instead according to Ingo
     also add CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER according to Ingo
-v3: according to Andrew, use sizeof(name) instead of hard coded 15

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <1265793639-15071-19-git-send-email-yinghai@kernel.org>
Cc: Christoph Lameter <cl@linux-foundation.org>
Acked-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

arch/x86/mm/init_64.c

@@ -977,7 +977,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 			if (pmd_none(*pmd)) {
 				pte_t entry;
 
-				p = vmemmap_alloc_block(PMD_SIZE, node);
+				p = vmemmap_alloc_block_buf(PMD_SIZE, node);
 				if (!p)
 					return -ENOMEM;
 

include/linux/mm.h

@@ -1326,12 +1326,19 @@ extern int randomize_va_space;
 const char * arch_vma_name(struct vm_area_struct *vma);
 void print_vma_addr(char *prefix, unsigned long rip);
 
+void sparse_mem_maps_populate_node(struct page **map_map,
+				   unsigned long pnum_begin,
+				   unsigned long pnum_end,
+				   unsigned long map_count,
+				   int nodeid);
+
 struct page *sparse_mem_map_populate(unsigned long pnum, int nid);
 pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
 pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node);
 pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
 pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
 void *vmemmap_alloc_block(unsigned long size, int node);
+void *vmemmap_alloc_block_buf(unsigned long size, int node);
 void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
 int vmemmap_populate_basepages(struct page *start_page,
 						unsigned long pages, int node);

mm/Kconfig

@@ -115,6 +115,10 @@ config SPARSEMEM_EXTREME
 config SPARSEMEM_VMEMMAP_ENABLE
 	bool
 
+config SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+	def_bool y
+	depends on SPARSEMEM && X86_64
+
 config SPARSEMEM_VMEMMAP
 	bool "Sparse Memory virtual memmap"
 	depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE

mm/sparse-vmemmap.c

@@ -43,6 +43,8 @@ static void * __init_refok __earlyonly_bootmem_alloc(int node,
 	return __alloc_bootmem_node_high(NODE_DATA(node), size, align, goal);
 }
 
+static void *vmemmap_buf;
+static void *vmemmap_buf_end;
 
 void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 {
@@ -64,6 +66,24 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 				__pa(MAX_DMA_ADDRESS));
 }
 
+/* need to make sure size is all the same during early stage */
+void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node)
+{
+	void *ptr;
+
+	if (!vmemmap_buf)
+		return vmemmap_alloc_block(size, node);
+
+	/* take the from buf */
+	ptr = (void *)ALIGN((unsigned long)vmemmap_buf, size);
+	if (ptr + size > vmemmap_buf_end)
+		return vmemmap_alloc_block(size, node);
+
+	vmemmap_buf = ptr + size;
+
+	return ptr;
+}
+
 void __meminit vmemmap_verify(pte_t *pte, int node,
 				unsigned long start, unsigned long end)
 {
@@ -80,7 +100,7 @@ pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node)
 	pte_t *pte = pte_offset_kernel(pmd, addr);
 	if (pte_none(*pte)) {
 		pte_t entry;
-		void *p = vmemmap_alloc_block(PAGE_SIZE, node);
+		void *p = vmemmap_alloc_block_buf(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
 		entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
@@ -163,3 +183,55 @@ struct page * __meminit sparse_mem_map_populate(unsigned long pnum, int nid)
 
 	return map;
 }
+
+void __init sparse_mem_maps_populate_node(struct page **map_map,
+					  unsigned long pnum_begin,
+					  unsigned long pnum_end,
+					  unsigned long map_count, int nodeid)
+{
+	unsigned long pnum;
+	unsigned long size = sizeof(struct page) * PAGES_PER_SECTION;
+	void *vmemmap_buf_start;
+
+	size = ALIGN(size, PMD_SIZE);
+	vmemmap_buf_start = __earlyonly_bootmem_alloc(nodeid, size * map_count,
+			 PMD_SIZE, __pa(MAX_DMA_ADDRESS));
+
+	if (vmemmap_buf_start) {
+		vmemmap_buf = vmemmap_buf_start;
+		vmemmap_buf_end = vmemmap_buf_start + size * map_count;
+	}
+
+	for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+		struct mem_section *ms;
+
+		if (!present_section_nr(pnum))
+			continue;
+
+		map_map[pnum] = sparse_mem_map_populate(pnum, nodeid);
+		if (map_map[pnum])
+			continue;
+		ms = __nr_to_section(pnum);
+		printk(KERN_ERR "%s: sparsemem memory map backing failed "
+			"some memory will not be available.\n", __func__);
+		ms->section_mem_map = 0;
+	}
+
+	if (vmemmap_buf_start) {
+		/* need to free left buf */
+#ifdef CONFIG_NO_BOOTMEM
+		free_early(__pa(vmemmap_buf_start), __pa(vmemmap_buf_end));
+		if (vmemmap_buf_start < vmemmap_buf) {
+			char name[15];
+
+			snprintf(name, sizeof(name), "MEMMAP %d", nodeid);
+			reserve_early_without_check(__pa(vmemmap_buf_start),
+						    __pa(vmemmap_buf), name);
+		}
+#else
+		free_bootmem(__pa(vmemmap_buf), vmemmap_buf_end - vmemmap_buf);
+#endif
+		vmemmap_buf = NULL;
+		vmemmap_buf_end = NULL;
+	}
+}

mm/sparse.c

@@ -390,8 +390,65 @@ struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid)
 		       PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION));
 	return map;
 }
+void __init sparse_mem_maps_populate_node(struct page **map_map,
+					  unsigned long pnum_begin,
+					  unsigned long pnum_end,
+					  unsigned long map_count, int nodeid)
+{
+	void *map;
+	unsigned long pnum;
+	unsigned long size = sizeof(struct page) * PAGES_PER_SECTION;
+
+	map = alloc_remap(nodeid, size * map_count);
+	if (map) {
+		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+			if (!present_section_nr(pnum))
+				continue;
+			map_map[pnum] = map;
+			map += size;
+		}
+		return;
+	}
+
+	size = PAGE_ALIGN(size);
+	map = alloc_bootmem_pages_node(NODE_DATA(nodeid), size * map_count);
+	if (map) {
+		for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+			if (!present_section_nr(pnum))
+				continue;
+			map_map[pnum] = map;
+			map += size;
+		}
+		return;
+	}
+
+	/* fallback */
+	for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+		struct mem_section *ms;
+
+		if (!present_section_nr(pnum))
+			continue;
+		map_map[pnum] = sparse_mem_map_populate(pnum, nodeid);
+		if (map_map[pnum])
+			continue;
+		ms = __nr_to_section(pnum);
+		printk(KERN_ERR "%s: sparsemem memory map backing failed "
+			"some memory will not be available.\n", __func__);
+		ms->section_mem_map = 0;
+	}
+}
 #endif /* !CONFIG_SPARSEMEM_VMEMMAP */
 
+static void __init sparse_early_mem_maps_alloc_node(struct page **map_map,
+				 unsigned long pnum_begin,
+				 unsigned long pnum_end,
+				 unsigned long map_count, int nodeid)
+{
+	sparse_mem_maps_populate_node(map_map, pnum_begin, pnum_end,
+					 map_count, nodeid);
+}
+
+#ifndef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
 static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 {
 	struct page *map;
@@ -407,6 +464,7 @@ static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 	ms->section_mem_map = 0;
 	return NULL;
 }
+#endif
 
 void __attribute__((weak)) __meminit vmemmap_populate_print_last(void)
 {
@@ -420,12 +478,14 @@ void __init sparse_init(void)
 {
 	unsigned long pnum;
 	struct page *map;
+	struct page **map_map;
 	unsigned long *usemap;
 	unsigned long **usemap_map;
-	int size;
+	int size, size2;
 	int nodeid_begin = 0;
 	unsigned long pnum_begin = 0;
 	unsigned long usemap_count;
+	unsigned long map_count;
 
 	/*
 	 * map is using big page (aka 2M in x86 64 bit)
@@ -478,6 +538,48 @@ void __init sparse_init(void)
 	sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, NR_MEM_SECTIONS,
 					 usemap_count, nodeid_begin);
 
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+	size2 = sizeof(struct page *) * NR_MEM_SECTIONS;
+	map_map = alloc_bootmem(size2);
+	if (!map_map)
+		panic("can not allocate map_map\n");
+
+	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
+		struct mem_section *ms;
+
+		if (!present_section_nr(pnum))
+			continue;
+		ms = __nr_to_section(pnum);
+		nodeid_begin = sparse_early_nid(ms);
+		pnum_begin = pnum;
+		break;
+	}
+	map_count = 1;
+	for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) {
+		struct mem_section *ms;
+		int nodeid;
+
+		if (!present_section_nr(pnum))
+			continue;
+		ms = __nr_to_section(pnum);
+		nodeid = sparse_early_nid(ms);
+		if (nodeid == nodeid_begin) {
+			map_count++;
+			continue;
+		}
+		/* ok, we need to take cake of from pnum_begin to pnum - 1*/
+		sparse_early_mem_maps_alloc_node(map_map, pnum_begin, pnum,
+						 map_count, nodeid_begin);
+		/* new start, update count etc*/
+		nodeid_begin = nodeid;
+		pnum_begin = pnum;
+		map_count = 1;
+	}
+	/* ok, last chunk */
+	sparse_early_mem_maps_alloc_node(map_map, pnum_begin, NR_MEM_SECTIONS,
+					 map_count, nodeid_begin);
+#endif
+
 	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
 		if (!present_section_nr(pnum))
 			continue;
@@ -486,7 +588,11 @@ void __init sparse_init(void)
 		if (!usemap)
 			continue;
 
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+		map = map_map[pnum];
+#else
 		map = sparse_early_mem_map_alloc(pnum);
+#endif
 		if (!map)
 			continue;
 
@@ -496,6 +602,9 @@ void __init sparse_init(void)
 
 	vmemmap_populate_print_last();
 
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+	free_bootmem(__pa(map_map), size2);
+#endif
 	free_bootmem(__pa(usemap_map), size);
 }