x86: Make 64 bit use early_res instead of bootmem before slab

Finally we can use early_res to replace bootmem for x86_64 now.

Still can use CONFIG_NO_BOOTMEM to enable it or not.

-v2: fix 32bit compiling about MAX_DMA32_PFN
-v3: folded bug fix from LKML message below
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <4B747239.4070907@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

arch/x86/Kconfig

@@ -568,6 +568,19 @@ config PARAVIRT_DEBUG
 	  Enable to debug paravirt_ops internals.  Specifically, BUG if
 	  a paravirt_op is missing when it is called.
 
+config NO_BOOTMEM
+	default y
+	bool "Disable Bootmem code"
+	depends on X86_64
+	---help---
+	  Use early_res directly instead of bootmem before slab is ready.
+		- allocator (buddy) [generic]
+		- early allocator (bootmem) [generic]
+		- very early allocator (reserve_early*()) [x86]
+		- very very early allocator (early brk model) [x86]
+	  So reduce one layer between early allocator to final allocator
+
+
 config MEMTEST
 	bool "Memtest"
 	---help---

arch/x86/include/asm/e820.h

@@ -117,6 +117,12 @@ extern void free_early(u64 start, u64 end);
 extern void early_res_to_bootmem(u64 start, u64 end);
 extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
 
+void reserve_early_without_check(u64 start, u64 end, char *name);
+u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
+			 u64 size, u64 align);
+#include <linux/range.h>
+int get_free_all_memory_range(struct range **rangep, int nodeid);
+
 extern unsigned long e820_end_of_ram_pfn(void);
 extern unsigned long e820_end_of_low_ram_pfn(void);
 extern int e820_find_active_region(const struct e820entry *ei,

arch/x86/kernel/e820.c

@@ -977,6 +977,25 @@ void __init reserve_early(u64 start, u64 end, char *name)
 	__reserve_early(start, end, name, 0);
 }
 
+void __init reserve_early_without_check(u64 start, u64 end, char *name)
+{
+	struct early_res *r;
+
+	if (start >= end)
+		return;
+
+	__check_and_double_early_res(end);
+
+	r = &early_res[early_res_count];
+
+	r->start = start;
+	r->end = end;
+	r->overlap_ok = 0;
+	if (name)
+		strncpy(r->name, name, sizeof(r->name) - 1);
+	early_res_count++;
+}
+
 void __init free_early(u64 start, u64 end)
 {
 	struct early_res *r;
@@ -991,6 +1010,94 @@ void __init free_early(u64 start, u64 end)
 	drop_range(i);
 }
 
+#ifdef CONFIG_NO_BOOTMEM
+static void __init subtract_early_res(struct range *range, int az)
+{
+	int i, count;
+	u64 final_start, final_end;
+	int idx = 0;
+
+	count  = 0;
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
+		count++;
+
+	/* need to skip first one ?*/
+	if (early_res != early_res_x)
+		idx = 1;
+
+#if 1
+	printk(KERN_INFO "Subtract (%d early reservations)\n", count);
+#endif
+	for (i = idx; i < count; i++) {
+		struct early_res *r = &early_res[i];
+#if 0
+		printk(KERN_INFO "  #%d [%010llx - %010llx] %15s", i,
+			r->start, r->end, r->name);
+#endif
+		final_start = PFN_DOWN(r->start);
+		final_end = PFN_UP(r->end);
+		if (final_start >= final_end) {
+#if 0
+			printk(KERN_CONT "\n");
+#endif
+			continue;
+		}
+#if 0
+		printk(KERN_CONT " subtract pfn [%010llx - %010llx]\n",
+			final_start, final_end);
+#endif
+		subtract_range(range, az, final_start, final_end);
+	}
+
+}
+
+int __init get_free_all_memory_range(struct range **rangep, int nodeid)
+{
+	int i, count;
+	u64 start = 0, end;
+	u64 size;
+	u64 mem;
+	struct range *range;
+	int nr_range;
+
+	count  = 0;
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
+		count++;
+
+	count *= 2;
+
+	size = sizeof(struct range) * count;
+#ifdef MAX_DMA32_PFN
+	if (max_pfn_mapped > MAX_DMA32_PFN)
+		start = MAX_DMA32_PFN << PAGE_SHIFT;
+#endif
+	end = max_pfn_mapped << PAGE_SHIFT;
+	mem = find_e820_area(start, end, size, sizeof(struct range));
+	if (mem == -1ULL)
+		panic("can not find more space for range free");
+
+	range = __va(mem);
+	/* use early_node_map[] and early_res to get range array at first */
+	memset(range, 0, size);
+	nr_range = 0;
+
+	/* need to go over early_node_map to find out good range for node */
+	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
+	subtract_early_res(range, count);
+	nr_range = clean_sort_range(range, count);
+
+	/* need to clear it ? */
+	if (nodeid == MAX_NUMNODES) {
+		memset(&early_res[0], 0,
+			 sizeof(struct early_res) * max_early_res);
+		early_res = NULL;
+		max_early_res = 0;
+	}
+
+	*rangep = range;
+	return nr_range;
+}
+#else
 void __init early_res_to_bootmem(u64 start, u64 end)
 {
 	int i, count;
@@ -1028,6 +1135,7 @@ void __init early_res_to_bootmem(u64 start, u64 end)
 	max_early_res = 0;
 	early_res_count = 0;
 }
+#endif
 
 /* Check for already reserved areas */
 static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
@@ -1083,31 +1191,56 @@ static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
 
 /*
  * Find a free area with specified alignment in a specific range.
+ * only with the area.between start to end is active range from early_node_map
+ * so they are good as RAM
  */
-u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
+u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
+			 u64 size, u64 align)
 {
-	int i;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
 	u64 addr, last;
-		u64 ei_last;
 
-		if (ei->type != E820_RAM)
-			continue;
-		addr = round_up(ei->addr, align);
-		ei_last = ei->addr + ei->size;
+	addr = round_up(ei_start, align);
 	if (addr < start)
 		addr = round_up(start, align);
 	if (addr >= ei_last)
-			continue;
+		goto out;
 	while (bad_addr(&addr, size, align) && addr+size <= ei_last)
 		;
 	last = addr + size;
 	if (last > ei_last)
-			continue;
+		goto out;
 	if (last > end)
+		goto out;
+
+	return addr;
+
+out:
+	return -1ULL;
+}
+
+/*
+ * Find a free area with specified alignment in a specific range.
+ */
+u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
+{
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+		u64 addr;
+		u64 ei_start, ei_last;
+
+		if (ei->type != E820_RAM)
+			continue;
+
+		ei_last = ei->addr + ei->size;
+		ei_start = ei->addr;
+		addr = find_early_area(ei_start, ei_last, start, end,
+					 size, align);
+
+		if (addr == -1ULL)
 			continue;
+
 		return addr;
 	}
 	return -1ULL;

arch/x86/kernel/setup.c

@@ -967,7 +967,9 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	initmem_init(0, max_pfn, acpi, k8);
+#ifndef CONFIG_NO_BOOTMEM
 	early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
+#endif
 
 	dma32_reserve_bootmem();
 

arch/x86/mm/init_64.c

@@ -572,6 +572,7 @@ kernel_physical_mapping_init(unsigned long start,
 void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 				int acpi, int k8)
 {
+#ifndef CONFIG_NO_BOOTMEM
 	unsigned long bootmap_size, bootmap;
 
 	bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT;
@@ -585,6 +586,9 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
 					 0, end_pfn);
 	e820_register_active_regions(0, start_pfn, end_pfn);
 	free_bootmem_with_active_regions(0, end_pfn);
+#else
+	e820_register_active_regions(0, start_pfn, end_pfn);
+#endif
 }
 #endif
 

arch/x86/mm/numa_64.c

@@ -198,11 +198,13 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 void __init
 setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 {
-	unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size;
+	unsigned long start_pfn, last_pfn, nodedata_phys;
 	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
-	unsigned long bootmap_start, nodedata_phys;
-	void *bootmap;
 	int nid;
+#ifndef CONFIG_NO_BOOTMEM
+	unsigned long bootmap_start, bootmap_pages, bootmap_size;
+	void *bootmap;
+#endif
 
 	if (!end)
 		return;
@@ -216,7 +218,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 
 	start = roundup(start, ZONE_ALIGN);
 
-	printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
+	printk(KERN_INFO "Initmem setup node %d %016lx-%016lx\n", nodeid,
 	       start, end);
 
 	start_pfn = start >> PAGE_SHIFT;
@@ -235,10 +237,13 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 		printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nodeid, nid);
 
 	memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
-	NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
+	NODE_DATA(nodeid)->node_id = nodeid;
 	NODE_DATA(nodeid)->node_start_pfn = start_pfn;
 	NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn;
 
+#ifndef CONFIG_NO_BOOTMEM
+	NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
+
 	/*
 	 * Find a place for the bootmem map
 	 * nodedata_phys could be on other nodes by alloc_bootmem,
@@ -275,6 +280,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
 		printk(KERN_INFO "    bootmap(%d) on node %d\n", nodeid, nid);
 
 	free_bootmem_with_active_regions(nodeid, end);
+#endif
 
 	node_set_online(nodeid);
 }
@@ -733,6 +739,10 @@ unsigned long __init numa_free_all_bootmem(void)
 	for_each_online_node(i)
 		pages += free_all_bootmem_node(NODE_DATA(i));
 
+#ifdef CONFIG_NO_BOOTMEM
+	pages += free_all_memory_core_early(MAX_NUMNODES);
+#endif
+
 	return pages;
 }
 

include/linux/bootmem.h

@@ -23,6 +23,7 @@ extern unsigned long max_pfn;
 extern unsigned long saved_max_pfn;
 #endif
 
+#ifndef CONFIG_NO_BOOTMEM
 /*
  * node_bootmem_map is a map pointer - the bits represent all physical 
  * memory pages (including holes) on the node.
@@ -37,6 +38,7 @@ typedef struct bootmem_data {
 } bootmem_data_t;
 
 extern bootmem_data_t bootmem_node_data[];
+#endif
 
 extern unsigned long bootmem_bootmap_pages(unsigned long);
 
@@ -46,6 +48,7 @@ extern unsigned long init_bootmem_node(pg_data_t *pgdat,
 				       unsigned long endpfn);
 extern unsigned long init_bootmem(unsigned long addr, unsigned long memend);
 
+unsigned long free_all_memory_core_early(int nodeid);
 extern unsigned long free_all_bootmem_node(pg_data_t *pgdat);
 extern unsigned long free_all_bootmem(void);
 
@@ -84,6 +87,10 @@ extern void *__alloc_bootmem_node(pg_data_t *pgdat,
 				  unsigned long size,
 				  unsigned long align,
 				  unsigned long goal);
+void *__alloc_bootmem_node_high(pg_data_t *pgdat,
+				  unsigned long size,
+				  unsigned long align,
+				  unsigned long goal);
 extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 				  unsigned long size,
 				  unsigned long align,

include/linux/mm.h

@@ -12,6 +12,7 @@
 #include <linux/prio_tree.h>
 #include <linux/debug_locks.h>
 #include <linux/mm_types.h>
+#include <linux/range.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -1049,6 +1050,10 @@ extern void get_pfn_range_for_nid(unsigned int nid,
 extern unsigned long find_min_pfn_with_active_regions(void);
 extern void free_bootmem_with_active_regions(int nid,
 						unsigned long max_low_pfn);
+int add_from_early_node_map(struct range *range, int az,
+				   int nr_range, int nid);
+void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
+				 u64 goal, u64 limit);
 typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
 extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
 extern void sparse_memory_present_with_active_regions(int nid);

include/linux/mmzone.h

@@ -620,7 +620,9 @@ typedef struct pglist_data {
 	struct page_cgroup *node_page_cgroup;
 #endif
 #endif
+#ifndef CONFIG_NO_BOOTMEM
 	struct bootmem_data *bdata;
+#endif
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/*
 	 * Must be held any time you expect node_start_pfn, node_present_pages

mm/page_alloc.c

@@ -3435,6 +3435,59 @@ void __init free_bootmem_with_active_regions(int nid,
 	}
 }
 
+int __init add_from_early_node_map(struct range *range, int az,
+				   int nr_range, int nid)
+{
+	int i;
+	u64 start, end;
+
+	/* need to go over early_node_map to find out good range for node */
+	for_each_active_range_index_in_nid(i, nid) {
+		start = early_node_map[i].start_pfn;
+		end = early_node_map[i].end_pfn;
+		nr_range = add_range(range, az, nr_range, start, end);
+	}
+	return nr_range;
+}
+
+void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit)
+{
+	int i;
+	void *ptr;
+
+	/* need to go over early_node_map to find out good range for node */
+	for_each_active_range_index_in_nid(i, nid) {
+		u64 addr;
+		u64 ei_start, ei_last;
+
+		ei_last = early_node_map[i].end_pfn;
+		ei_last <<= PAGE_SHIFT;
+		ei_start = early_node_map[i].start_pfn;
+		ei_start <<= PAGE_SHIFT;
+		addr = find_early_area(ei_start, ei_last,
+					 goal, limit, size, align);
+
+		if (addr == -1ULL)
+			continue;
+
+#if 0
+		printk(KERN_DEBUG "alloc (nid=%d %llx - %llx) (%llx - %llx) %llx %llx => %llx\n",
+				nid,
+				ei_start, ei_last, goal, limit, size,
+				align, addr);
+#endif
+
+		ptr = phys_to_virt(addr);
+		memset(ptr, 0, size);
+		reserve_early_without_check(addr, addr + size, "BOOTMEM");
+		return ptr;
+	}
+
+	return NULL;
+}
+
+
 void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
 {
 	int i;
@@ -4467,7 +4520,11 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
 }
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-struct pglist_data __refdata contig_page_data = { .bdata = &bootmem_node_data[0] };
+struct pglist_data __refdata contig_page_data = {
+#ifndef CONFIG_NO_BOOTMEM
+ .bdata = &bootmem_node_data[0]
+#endif
+ };
 EXPORT_SYMBOL(contig_page_data);
 #endif
 

mm/percpu.c

@@ -1929,7 +1929,10 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
 			}
 			/* copy and return the unused part */
 			memcpy(ptr, __per_cpu_load, ai->static_size);
+#ifndef CONFIG_NO_BOOTMEM
+			/* fix partial free ! */
 			free_fn(ptr + size_sum, ai->unit_size - size_sum);
+#endif
 		}
 	}
 

mm/sparse-vmemmap.c

@@ -40,7 +40,7 @@ static void * __init_refok __earlyonly_bootmem_alloc(int node,
 				unsigned long align,
 				unsigned long goal)
 {
-	return __alloc_bootmem_node(NODE_DATA(node), size, align, goal);
+	return __alloc_bootmem_node_high(NODE_DATA(node), size, align, goal);
 }