mirror of
				git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
				synced 2025-09-04 20:19:47 +08:00 
			
		
		
		
	 f784a3f196
			
		
	
	
		f784a3f196
		
	
	
	
	
		
			
			In free_area_init_core(), zone->managed_pages is set to an approximate value for lowmem, and will be adjusted when the bootmem allocator frees pages into the buddy system. But free_area_init_core() is also called by hotadd_new_pgdat() when hot-adding memory. As a result, zone->managed_pages of the newly added node's pgdat is set to an approximate value in the very beginning. Even if the memory on that node has node been onlined, /sys/device/system/node/nodeXXX/meminfo has wrong value: hot-add node2 (memory not onlined) cat /sys/device/system/node/node2/meminfo Node 2 MemTotal: 33554432 kB Node 2 MemFree: 0 kB Node 2 MemUsed: 33554432 kB Node 2 Active: 0 kB This patch fixes this problem by reset node managed pages to 0 after hot-adding a new node. 1. Move reset_managed_pages_done from reset_node_managed_pages() to reset_all_zones_managed_pages() 2. Make reset_node_managed_pages() non-static 3. Call reset_node_managed_pages() in hotadd_new_pgdat() after pgdat is initialized Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: <stable@vger.kernel.org> [3.16+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
		
			
				
	
	
		
			862 lines
		
	
	
		
			21 KiB
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			862 lines
		
	
	
		
			21 KiB
		
	
	
	
		
			C
		
	
	
	
	
	
| /*
 | |
|  *  bootmem - A boot-time physical memory allocator and configurator
 | |
|  *
 | |
|  *  Copyright (C) 1999 Ingo Molnar
 | |
|  *                1999 Kanoj Sarcar, SGI
 | |
|  *                2008 Johannes Weiner
 | |
|  *
 | |
|  * Access to this subsystem has to be serialized externally (which is true
 | |
|  * for the boot process anyway).
 | |
|  */
 | |
| #include <linux/init.h>
 | |
| #include <linux/pfn.h>
 | |
| #include <linux/slab.h>
 | |
| #include <linux/bootmem.h>
 | |
| #include <linux/export.h>
 | |
| #include <linux/kmemleak.h>
 | |
| #include <linux/range.h>
 | |
| #include <linux/memblock.h>
 | |
| #include <linux/bug.h>
 | |
| #include <linux/io.h>
 | |
| 
 | |
| #include <asm/processor.h>
 | |
| 
 | |
| #include "internal.h"
 | |
| 
 | |
| #ifndef CONFIG_NEED_MULTIPLE_NODES
 | |
| struct pglist_data __refdata contig_page_data = {
 | |
| 	.bdata = &bootmem_node_data[0]
 | |
| };
 | |
| EXPORT_SYMBOL(contig_page_data);
 | |
| #endif
 | |
| 
 | |
| unsigned long max_low_pfn;
 | |
| unsigned long min_low_pfn;
 | |
| unsigned long max_pfn;
 | |
| 
 | |
| bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata;
 | |
| 
 | |
| static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list);
 | |
| 
 | |
| static int bootmem_debug;
 | |
| 
 | |
| static int __init bootmem_debug_setup(char *buf)
 | |
| {
 | |
| 	bootmem_debug = 1;
 | |
| 	return 0;
 | |
| }
 | |
| early_param("bootmem_debug", bootmem_debug_setup);
 | |
| 
 | |
| #define bdebug(fmt, args...) ({				\
 | |
| 	if (unlikely(bootmem_debug))			\
 | |
| 		printk(KERN_INFO			\
 | |
| 			"bootmem::%s " fmt,		\
 | |
| 			__func__, ## args);		\
 | |
| })
 | |
| 
 | |
| static unsigned long __init bootmap_bytes(unsigned long pages)
 | |
| {
 | |
| 	unsigned long bytes = DIV_ROUND_UP(pages, 8);
 | |
| 
 | |
| 	return ALIGN(bytes, sizeof(long));
 | |
| }
 | |
| 
 | |
| /**
 | |
|  * bootmem_bootmap_pages - calculate bitmap size in pages
 | |
|  * @pages: number of pages the bitmap has to represent
 | |
|  */
 | |
| unsigned long __init bootmem_bootmap_pages(unsigned long pages)
 | |
| {
 | |
| 	unsigned long bytes = bootmap_bytes(pages);
 | |
| 
 | |
| 	return PAGE_ALIGN(bytes) >> PAGE_SHIFT;
 | |
| }
 | |
| 
 | |
| /*
 | |
|  * link bdata in order
 | |
|  */
 | |
| static void __init link_bootmem(bootmem_data_t *bdata)
 | |
| {
 | |
| 	bootmem_data_t *ent;
 | |
| 
 | |
| 	list_for_each_entry(ent, &bdata_list, list) {
 | |
| 		if (bdata->node_min_pfn < ent->node_min_pfn) {
 | |
| 			list_add_tail(&bdata->list, &ent->list);
 | |
| 			return;
 | |
| 		}
 | |
| 	}
 | |
| 
 | |
| 	list_add_tail(&bdata->list, &bdata_list);
 | |
| }
 | |
| 
 | |
| /*
 | |
|  * Called once to set up the allocator itself.
 | |
|  */
 | |
| static unsigned long __init init_bootmem_core(bootmem_data_t *bdata,
 | |
| 	unsigned long mapstart, unsigned long start, unsigned long end)
 | |
| {
 | |
| 	unsigned long mapsize;
 | |
| 
 | |
| 	mminit_validate_memmodel_limits(&start, &end);
 | |
| 	bdata->node_bootmem_map = phys_to_virt(PFN_PHYS(mapstart));
 | |
| 	bdata->node_min_pfn = start;
 | |
| 	bdata->node_low_pfn = end;
 | |
| 	link_bootmem(bdata);
 | |
| 
 | |
| 	/*
 | |
| 	 * Initially all pages are reserved - setup_arch() has to
 | |
| 	 * register free RAM areas explicitly.
 | |
| 	 */
 | |
| 	mapsize = bootmap_bytes(end - start);
 | |
| 	memset(bdata->node_bootmem_map, 0xff, mapsize);
 | |
| 
 | |
| 	bdebug("nid=%td start=%lx map=%lx end=%lx mapsize=%lx\n",
 | |
| 		bdata - bootmem_node_data, start, mapstart, end, mapsize);
 | |
| 
 | |
| 	return mapsize;
 | |
| }
 | |
| 
 | |
| /**
 | |
|  * init_bootmem_node - register a node as boot memory
 | |
|  * @pgdat: node to register
 | |
|  * @freepfn: pfn where the bitmap for this node is to be placed
 | |
|  * @startpfn: first pfn on the node
 | |
|  * @endpfn: first pfn after the node
 | |
|  *
 | |
|  * Returns the number of bytes needed to hold the bitmap for this node.
 | |
|  */
 | |
| unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
 | |
| 				unsigned long startpfn, unsigned long endpfn)
 | |
| {
 | |
| 	return init_bootmem_core(pgdat->bdata, freepfn, startpfn, endpfn);
 | |
| }
 | |
| 
 | |
| /**
 | |
|  * init_bootmem - register boot memory
 | |
|  * @start: pfn where the bitmap is to be placed
 | |
|  * @pages: number of available physical pages
 | |
|  *
 | |
|  * Returns the number of bytes needed to hold the bitmap.
 | |
|  */
 | |
| unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
 | |
| {
 | |
| 	max_low_pfn = pages;
 | |
| 	min_low_pfn = start;
 | |
| 	return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
 | |
| }
 | |
| 
 | |
| /*
 | |
|  * free_bootmem_late - free bootmem pages directly to page allocator
 | |
|  * @addr: starting physical address of the range
 | |
|  * @size: size of the range in bytes
 | |
|  *
 | |
|  * This is only useful when the bootmem allocator has already been torn
 | |
|  * down, but we are still initializing the system.  Pages are given directly
 | |
|  * to the page allocator, no bootmem metadata is updated because it is gone.
 | |
|  */
 | |
| void __init free_bootmem_late(unsigned long physaddr, unsigned long size)
 | |
| {
 | |
| 	unsigned long cursor, end;
 | |
| 
 | |
| 	kmemleak_free_part(__va(physaddr), size);
 | |
| 
 | |
| 	cursor = PFN_UP(physaddr);
 | |
| 	end = PFN_DOWN(physaddr + size);
 | |
| 
 | |
| 	for (; cursor < end; cursor++) {
 | |
| 		__free_pages_bootmem(pfn_to_page(cursor), 0);
 | |
| 		totalram_pages++;
 | |
| 	}
 | |
| }
 | |
| 
 | |
| static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 | |
| {
 | |
| 	struct page *page;
 | |
| 	unsigned long *map, start, end, pages, count = 0;
 | |
| 
 | |
| 	if (!bdata->node_bootmem_map)
 | |
| 		return 0;
 | |
| 
 | |
| 	map = bdata->node_bootmem_map;
 | |
| 	start = bdata->node_min_pfn;
 | |
| 	end = bdata->node_low_pfn;
 | |
| 
 | |
| 	bdebug("nid=%td start=%lx end=%lx\n",
 | |
| 		bdata - bootmem_node_data, start, end);
 | |
| 
 | |
| 	while (start < end) {
 | |
| 		unsigned long idx, vec;
 | |
| 		unsigned shift;
 | |
| 
 | |
| 		idx = start - bdata->node_min_pfn;
 | |
| 		shift = idx & (BITS_PER_LONG - 1);
 | |
| 		/*
 | |
| 		 * vec holds at most BITS_PER_LONG map bits,
 | |
| 		 * bit 0 corresponds to start.
 | |
| 		 */
 | |
| 		vec = ~map[idx / BITS_PER_LONG];
 | |
| 
 | |
| 		if (shift) {
 | |
| 			vec >>= shift;
 | |
| 			if (end - start >= BITS_PER_LONG)
 | |
| 				vec |= ~map[idx / BITS_PER_LONG + 1] <<
 | |
| 					(BITS_PER_LONG - shift);
 | |
| 		}
 | |
| 		/*
 | |
| 		 * If we have a properly aligned and fully unreserved
 | |
| 		 * BITS_PER_LONG block of pages in front of us, free
 | |
| 		 * it in one go.
 | |
| 		 */
 | |
| 		if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) {
 | |
| 			int order = ilog2(BITS_PER_LONG);
 | |
| 
 | |
| 			__free_pages_bootmem(pfn_to_page(start), order);
 | |
| 			count += BITS_PER_LONG;
 | |
| 			start += BITS_PER_LONG;
 | |
| 		} else {
 | |
| 			unsigned long cur = start;
 | |
| 
 | |
| 			start = ALIGN(start + 1, BITS_PER_LONG);
 | |
| 			while (vec && cur != start) {
 | |
| 				if (vec & 1) {
 | |
| 					page = pfn_to_page(cur);
 | |
| 					__free_pages_bootmem(page, 0);
 | |
| 					count++;
 | |
| 				}
 | |
| 				vec >>= 1;
 | |
| 				++cur;
 | |
| 			}
 | |
| 		}
 | |
| 	}
 | |
| 
 | |
| 	page = virt_to_page(bdata->node_bootmem_map);
 | |
| 	pages = bdata->node_low_pfn - bdata->node_min_pfn;
 | |
| 	pages = bootmem_bootmap_pages(pages);
 | |
| 	count += pages;
 | |
| 	while (pages--)
 | |
| 		__free_pages_bootmem(page++, 0);
 | |
| 
 | |
| 	bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count);
 | |
| 
 | |
| 	return count;
 | |
| }
 | |
| 
 | |
| static int reset_managed_pages_done __initdata;
 | |
| 
 | |
| void reset_node_managed_pages(pg_data_t *pgdat)
 | |
| {
 | |
| 	struct zone *z;
 | |
| 
 | |
| 	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
 | |
| 		z->managed_pages = 0;
 | |
| }
 | |
| 
 | |
| void __init reset_all_zones_managed_pages(void)
 | |
| {
 | |
| 	struct pglist_data *pgdat;
 | |
| 
 | |
| 	if (reset_managed_pages_done)
 | |
| 		return;
 | |
| 
 | |
| 	for_each_online_pgdat(pgdat)
 | |
| 		reset_node_managed_pages(pgdat);
 | |
| 
 | |
| 	reset_managed_pages_done = 1;
 | |
| }
 | |
| 
 | |
| /**
 | |
|  * free_all_bootmem - release free pages to the buddy allocator
 | |
|  *
 | |
|  * Returns the number of pages actually released.
 | |
|  */
 | |
| unsigned long __init free_all_bootmem(void)
 | |
| {
 | |
| 	unsigned long total_pages = 0;
 | |
| 	bootmem_data_t *bdata;
 | |
| 
 | |
| 	reset_all_zones_managed_pages();
 | |
| 
 | |
| 	list_for_each_entry(bdata, &bdata_list, list)
 | |
| 		total_pages += free_all_bootmem_core(bdata);
 | |
| 
 | |
| 	totalram_pages += total_pages;
 | |
| 
 | |
| 	return total_pages;
 | |
| }
 | |
| 
 | |
| static void __init __free(bootmem_data_t *bdata,
 | |
| 			unsigned long sidx, unsigned long eidx)
 | |
| {
 | |
| 	unsigned long idx;
 | |
| 
 | |
| 	bdebug("nid=%td start=%lx end=%lx\n", bdata - bootmem_node_data,
 | |
| 		sidx + bdata->node_min_pfn,
 | |
| 		eidx + bdata->node_min_pfn);
 | |
| 
 | |
| 	if (bdata->hint_idx > sidx)
 | |
| 		bdata->hint_idx = sidx;
 | |
| 
 | |
| 	for (idx = sidx; idx < eidx; idx++)
 | |
| 		if (!test_and_clear_bit(idx, bdata->node_bootmem_map))
 | |
| 			BUG();
 | |
| }
 | |
| 
 | |
| static int __init __reserve(bootmem_data_t *bdata, unsigned long sidx,
 | |
| 			unsigned long eidx, int flags)
 | |
| {
 | |
| 	unsigned long idx;
 | |
| 	int exclusive = flags & BOOTMEM_EXCLUSIVE;
 | |
| 
 | |
| 	bdebug("nid=%td start=%lx end=%lx flags=%x\n",
 | |
| 		bdata - bootmem_node_data,
 | |
| 		sidx + bdata->node_min_pfn,
 | |
| 		eidx + bdata->node_min_pfn,
 | |
| 		flags);
 | |
| 
 | |
| 	for (idx = sidx; idx < eidx; idx++)
 | |
| 		if (test_and_set_bit(idx, bdata->node_bootmem_map)) {
 | |
| 			if (exclusive) {
 | |
| 				__free(bdata, sidx, idx);
 | |
| 				return -EBUSY;
 | |
| 			}
 | |
| 			bdebug("silent double reserve of PFN %lx\n",
 | |
| 				idx + bdata->node_min_pfn);
 | |
| 		}
 | |
| 	return 0;
 | |
| }
 | |
| 
 | |
| static int __init mark_bootmem_node(bootmem_data_t *bdata,
 | |
| 				unsigned long start, unsigned long end,
 | |
| 				int reserve, int flags)
 | |
| {
 | |
| 	unsigned long sidx, eidx;
 | |
| 
 | |
| 	bdebug("nid=%td start=%lx end=%lx reserve=%d flags=%x\n",
 | |
| 		bdata - bootmem_node_data, start, end, reserve, flags);
 | |
| 
 | |
| 	BUG_ON(start < bdata->node_min_pfn);
 | |
| 	BUG_ON(end > bdata->node_low_pfn);
 | |
| 
 | |
| 	sidx = start - bdata->node_min_pfn;
 | |
| 	eidx = end - bdata->node_min_pfn;
 | |
| 
 | |
| 	if (reserve)
 | |
| 		return __reserve(bdata, sidx, eidx, flags);
 | |
| 	else
 | |
| 		__free(bdata, sidx, eidx);
 | |
| 	return 0;
 | |
| }
 | |
| 
 | |
| static int __init mark_bootmem(unsigned long start, unsigned long end,
 | |
| 				int reserve, int flags)
 | |
| {
 | |
| 	unsigned long pos;
 | |
| 	bootmem_data_t *bdata;
 | |
| 
 | |
| 	pos = start;
 | |
| 	list_for_each_entry(bdata, &bdata_list, list) {
 | |
| 		int err;
 | |
| 		unsigned long max;
 | |
| 
 | |
| 		if (pos < bdata->node_min_pfn ||
 | |
| 		    pos >= bdata->node_low_pfn) {
 | |
| 			BUG_ON(pos != start);
 | |
| 			continue;
 | |
| 		}
 | |
| 
 | |
| 		max = min(bdata->node_low_pfn, end);
 | |
| 
 | |
| 		err = mark_bootmem_node(bdata, pos, max, reserve, flags);
 | |
| 		if (reserve && err) {
 | |
| 			mark_bootmem(start, pos, 0, 0);
 | |
| 			return err;
 | |
| 		}
 | |
| 
 | |
| 		if (max == end)
 | |
| 			return 0;
 | |
| 		pos = bdata->node_low_pfn;
 | |
| 	}
 | |
| 	BUG();
 | |
| }
 | |
| 
 | |
| /**
 | |
|  * free_bootmem_node - mark a page range as usable
 | |
|  * @pgdat: node the range resides on
 | |
|  * @physaddr: starting address of the range
 | |
|  * @size: size of the range in bytes
 | |
|  *
 | |
|  * Partial pages will be considered reserved and left as they are.
 | |
|  *
 | |
|  * The range must reside completely on the specified node.
 | |
|  */
 | |
| void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 | |
| 			      unsigned long size)
 | |
| {
 | |
| 	unsigned long start, end;
 | |
| 
 | |
| 	kmemleak_free_part(__va(physaddr), size);
 | |
| 
 | |
| 	start = PFN_UP(physaddr);
 | |
| 	end = PFN_DOWN(physaddr + size);
 | |
| 
 | |
| 	mark_bootmem_node(pgdat->bdata, start, end, 0, 0);
 | |
| }
 | |
| 
 | |
| /**
 | |
|  * free_bootmem - mark a page range as usable
 | |
|  * @addr: starting physical address of the range
 | |
|  * @size: size of the range in bytes
 | |
|  *
 | |
|  * Partial pages will be considered reserved and left as they are.
 | |
|  *
 | |
|  * The range must be contiguous but may span node boundaries.
 | |
|  */
 | |
| void __init free_bootmem(unsigned long physaddr, unsigned long size)
 | |
| {
 | |
| 	unsigned long start, end;
 | |
| 
 | |
| 	kmemleak_free_part(__va(physaddr), size);
 | |
| 
 | |
| 	start = PFN_UP(physaddr);
 | |
| 	end = PFN_DOWN(physaddr + size);
 | |
| 
 | |
| 	mark_bootmem(start, end, 0, 0);
 | |
| }
 | |
| 
 | |
| /**
 | |
|  * reserve_bootmem_node - mark a page range as reserved
 | |
|  * @pgdat: node the range resides on
 | |
|  * @physaddr: starting address of the range
 | |
|  * @size: size of the range in bytes
 | |
|  * @flags: reservation flags (see linux/bootmem.h)
 | |
|  *
 | |
|  * Partial pages will be reserved.
 | |
|  *
 | |
|  * The range must reside completely on the specified node.
 | |
|  */
 | |
| int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 | |
| 				 unsigned long size, int flags)
 | |
| {
 | |
| 	unsigned long start, end;
 | |
| 
 | |
| 	start = PFN_DOWN(physaddr);
 | |
| 	end = PFN_UP(physaddr + size);
 | |
| 
 | |
| 	return mark_bootmem_node(pgdat->bdata, start, end, 1, flags);
 | |
| }
 | |
| 
 | |
| /**
 | |
|  * reserve_bootmem - mark a page range as reserved
 | |
|  * @addr: starting address of the range
 | |
|  * @size: size of the range in bytes
 | |
|  * @flags: reservation flags (see linux/bootmem.h)
 | |
|  *
 | |
|  * Partial pages will be reserved.
 | |
|  *
 | |
|  * The range must be contiguous but may span node boundaries.
 | |
|  */
 | |
| int __init reserve_bootmem(unsigned long addr, unsigned long size,
 | |
| 			    int flags)
 | |
| {
 | |
| 	unsigned long start, end;
 | |
| 
 | |
| 	start = PFN_DOWN(addr);
 | |
| 	end = PFN_UP(addr + size);
 | |
| 
 | |
| 	return mark_bootmem(start, end, 1, flags);
 | |
| }
 | |
| 
 | |
| static unsigned long __init align_idx(struct bootmem_data *bdata,
 | |
| 				      unsigned long idx, unsigned long step)
 | |
| {
 | |
| 	unsigned long base = bdata->node_min_pfn;
 | |
| 
 | |
| 	/*
 | |
| 	 * Align the index with respect to the node start so that the
 | |
| 	 * combination of both satisfies the requested alignment.
 | |
| 	 */
 | |
| 
 | |
| 	return ALIGN(base + idx, step) - base;
 | |
| }
 | |
| 
 | |
| static unsigned long __init align_off(struct bootmem_data *bdata,
 | |
| 				      unsigned long off, unsigned long align)
 | |
| {
 | |
| 	unsigned long base = PFN_PHYS(bdata->node_min_pfn);
 | |
| 
 | |
| 	/* Same as align_idx for byte offsets */
 | |
| 
 | |
| 	return ALIGN(base + off, align) - base;
 | |
| }
 | |
| 
 | |
| static void * __init alloc_bootmem_bdata(struct bootmem_data *bdata,
 | |
| 					unsigned long size, unsigned long align,
 | |
| 					unsigned long goal, unsigned long limit)
 | |
| {
 | |
| 	unsigned long fallback = 0;
 | |
| 	unsigned long min, max, start, sidx, midx, step;
 | |
| 
 | |
| 	bdebug("nid=%td size=%lx [%lu pages] align=%lx goal=%lx limit=%lx\n",
 | |
| 		bdata - bootmem_node_data, size, PAGE_ALIGN(size) >> PAGE_SHIFT,
 | |
| 		align, goal, limit);
 | |
| 
 | |
| 	BUG_ON(!size);
 | |
| 	BUG_ON(align & (align - 1));
 | |
| 	BUG_ON(limit && goal + size > limit);
 | |
| 
 | |
| 	if (!bdata->node_bootmem_map)
 | |
| 		return NULL;
 | |
| 
 | |
| 	min = bdata->node_min_pfn;
 | |
| 	max = bdata->node_low_pfn;
 | |
| 
 | |
| 	goal >>= PAGE_SHIFT;
 | |
| 	limit >>= PAGE_SHIFT;
 | |
| 
 | |
| 	if (limit && max > limit)
 | |
| 		max = limit;
 | |
| 	if (max <= min)
 | |
| 		return NULL;
 | |
| 
 | |
| 	step = max(align >> PAGE_SHIFT, 1UL);
 | |
| 
 | |
| 	if (goal && min < goal && goal < max)
 | |
| 		start = ALIGN(goal, step);
 | |
| 	else
 | |
| 		start = ALIGN(min, step);
 | |
| 
 | |
| 	sidx = start - bdata->node_min_pfn;
 | |
| 	midx = max - bdata->node_min_pfn;
 | |
| 
 | |
| 	if (bdata->hint_idx > sidx) {
 | |
| 		/*
 | |
| 		 * Handle the valid case of sidx being zero and still
 | |
| 		 * catch the fallback below.
 | |
| 		 */
 | |
| 		fallback = sidx + 1;
 | |
| 		sidx = align_idx(bdata, bdata->hint_idx, step);
 | |
| 	}
 | |
| 
 | |
| 	while (1) {
 | |
| 		int merge;
 | |
| 		void *region;
 | |
| 		unsigned long eidx, i, start_off, end_off;
 | |
| find_block:
 | |
| 		sidx = find_next_zero_bit(bdata->node_bootmem_map, midx, sidx);
 | |
| 		sidx = align_idx(bdata, sidx, step);
 | |
| 		eidx = sidx + PFN_UP(size);
 | |
| 
 | |
| 		if (sidx >= midx || eidx > midx)
 | |
| 			break;
 | |
| 
 | |
| 		for (i = sidx; i < eidx; i++)
 | |
| 			if (test_bit(i, bdata->node_bootmem_map)) {
 | |
| 				sidx = align_idx(bdata, i, step);
 | |
| 				if (sidx == i)
 | |
| 					sidx += step;
 | |
| 				goto find_block;
 | |
| 			}
 | |
| 
 | |
| 		if (bdata->last_end_off & (PAGE_SIZE - 1) &&
 | |
| 				PFN_DOWN(bdata->last_end_off) + 1 == sidx)
 | |
| 			start_off = align_off(bdata, bdata->last_end_off, align);
 | |
| 		else
 | |
| 			start_off = PFN_PHYS(sidx);
 | |
| 
 | |
| 		merge = PFN_DOWN(start_off) < sidx;
 | |
| 		end_off = start_off + size;
 | |
| 
 | |
| 		bdata->last_end_off = end_off;
 | |
| 		bdata->hint_idx = PFN_UP(end_off);
 | |
| 
 | |
| 		/*
 | |
| 		 * Reserve the area now:
 | |
| 		 */
 | |
| 		if (__reserve(bdata, PFN_DOWN(start_off) + merge,
 | |
| 				PFN_UP(end_off), BOOTMEM_EXCLUSIVE))
 | |
| 			BUG();
 | |
| 
 | |
| 		region = phys_to_virt(PFN_PHYS(bdata->node_min_pfn) +
 | |
| 				start_off);
 | |
| 		memset(region, 0, size);
 | |
| 		/*
 | |
| 		 * The min_count is set to 0 so that bootmem allocated blocks
 | |
| 		 * are never reported as leaks.
 | |
| 		 */
 | |
| 		kmemleak_alloc(region, size, 0, 0);
 | |
| 		return region;
 | |
| 	}
 | |
| 
 | |
| 	if (fallback) {
 | |
| 		sidx = align_idx(bdata, fallback - 1, step);
 | |
| 		fallback = 0;
 | |
| 		goto find_block;
 | |
| 	}
 | |
| 
 | |
| 	return NULL;
 | |
| }
 | |
| 
 | |
| static void * __init alloc_bootmem_core(unsigned long size,
 | |
| 					unsigned long align,
 | |
| 					unsigned long goal,
 | |
| 					unsigned long limit)
 | |
| {
 | |
| 	bootmem_data_t *bdata;
 | |
| 	void *region;
 | |
| 
 | |
| 	if (WARN_ON_ONCE(slab_is_available()))
 | |
| 		return kzalloc(size, GFP_NOWAIT);
 | |
| 
 | |
| 	list_for_each_entry(bdata, &bdata_list, list) {
 | |
| 		if (goal && bdata->node_low_pfn <= PFN_DOWN(goal))
 | |
| 			continue;
 | |
| 		if (limit && bdata->node_min_pfn >= PFN_DOWN(limit))
 | |
| 			break;
 | |
| 
 | |
| 		region = alloc_bootmem_bdata(bdata, size, align, goal, limit);
 | |
| 		if (region)
 | |
| 			return region;
 | |
| 	}
 | |
| 
 | |
| 	return NULL;
 | |
| }
 | |
| 
 | |
| static void * __init ___alloc_bootmem_nopanic(unsigned long size,
 | |
| 					      unsigned long align,
 | |
| 					      unsigned long goal,
 | |
| 					      unsigned long limit)
 | |
| {
 | |
| 	void *ptr;
 | |
| 
 | |
| restart:
 | |
| 	ptr = alloc_bootmem_core(size, align, goal, limit);
 | |
| 	if (ptr)
 | |
| 		return ptr;
 | |
| 	if (goal) {
 | |
| 		goal = 0;
 | |
| 		goto restart;
 | |
| 	}
 | |
| 
 | |
| 	return NULL;
 | |
| }
 | |
| 
 | |
| /**
 | |
|  * __alloc_bootmem_nopanic - allocate boot memory without panicking
 | |
|  * @size: size of the request in bytes
 | |
|  * @align: alignment of the region
 | |
|  * @goal: preferred starting address of the region
 | |
|  *
 | |
|  * The goal is dropped if it can not be satisfied and the allocation will
 | |
|  * fall back to memory below @goal.
 | |
|  *
 | |
|  * Allocation may happen on any node in the system.
 | |
|  *
 | |
|  * Returns NULL on failure.
 | |
|  */
 | |
| void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
 | |
| 					unsigned long goal)
 | |
| {
 | |
| 	unsigned long limit = 0;
 | |
| 
 | |
| 	return ___alloc_bootmem_nopanic(size, align, goal, limit);
 | |
| }
 | |
| 
 | |
| static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
 | |
| 					unsigned long goal, unsigned long limit)
 | |
| {
 | |
| 	void *mem = ___alloc_bootmem_nopanic(size, align, goal, limit);
 | |
| 
 | |
| 	if (mem)
 | |
| 		return mem;
 | |
| 	/*
 | |
| 	 * Whoops, we cannot satisfy the allocation request.
 | |
| 	 */
 | |
| 	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
 | |
| 	panic("Out of memory");
 | |
| 	return NULL;
 | |
| }
 | |
| 
 | |
| /**
 | |
|  * __alloc_bootmem - allocate boot memory
 | |
|  * @size: size of the request in bytes
 | |
|  * @align: alignment of the region
 | |
|  * @goal: preferred starting address of the region
 | |
|  *
 | |
|  * The goal is dropped if it can not be satisfied and the allocation will
 | |
|  * fall back to memory below @goal.
 | |
|  *
 | |
|  * Allocation may happen on any node in the system.
 | |
|  *
 | |
|  * The function panics if the request can not be satisfied.
 | |
|  */
 | |
| void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 | |
| 			      unsigned long goal)
 | |
| {
 | |
| 	unsigned long limit = 0;
 | |
| 
 | |
| 	return ___alloc_bootmem(size, align, goal, limit);
 | |
| }
 | |
| 
 | |
| void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 | |
| 				unsigned long size, unsigned long align,
 | |
| 				unsigned long goal, unsigned long limit)
 | |
| {
 | |
| 	void *ptr;
 | |
| 
 | |
| 	if (WARN_ON_ONCE(slab_is_available()))
 | |
| 		return kzalloc(size, GFP_NOWAIT);
 | |
| again:
 | |
| 
 | |
| 	/* do not panic in alloc_bootmem_bdata() */
 | |
| 	if (limit && goal + size > limit)
 | |
| 		limit = 0;
 | |
| 
 | |
| 	ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit);
 | |
| 	if (ptr)
 | |
| 		return ptr;
 | |
| 
 | |
| 	ptr = alloc_bootmem_core(size, align, goal, limit);
 | |
| 	if (ptr)
 | |
| 		return ptr;
 | |
| 
 | |
| 	if (goal) {
 | |
| 		goal = 0;
 | |
| 		goto again;
 | |
| 	}
 | |
| 
 | |
| 	return NULL;
 | |
| }
 | |
| 
 | |
| void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
 | |
| 				   unsigned long align, unsigned long goal)
 | |
| {
 | |
| 	if (WARN_ON_ONCE(slab_is_available()))
 | |
| 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 | |
| 
 | |
| 	return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
 | |
| }
 | |
| 
 | |
| void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 | |
| 				    unsigned long align, unsigned long goal,
 | |
| 				    unsigned long limit)
 | |
| {
 | |
| 	void *ptr;
 | |
| 
 | |
| 	ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
 | |
| 	if (ptr)
 | |
| 		return ptr;
 | |
| 
 | |
| 	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
 | |
| 	panic("Out of memory");
 | |
| 	return NULL;
 | |
| }
 | |
| 
 | |
| /**
 | |
|  * __alloc_bootmem_node - allocate boot memory from a specific node
 | |
|  * @pgdat: node to allocate from
 | |
|  * @size: size of the request in bytes
 | |
|  * @align: alignment of the region
 | |
|  * @goal: preferred starting address of the region
 | |
|  *
 | |
|  * The goal is dropped if it can not be satisfied and the allocation will
 | |
|  * fall back to memory below @goal.
 | |
|  *
 | |
|  * Allocation may fall back to any node in the system if the specified node
 | |
|  * can not hold the requested memory.
 | |
|  *
 | |
|  * The function panics if the request can not be satisfied.
 | |
|  */
 | |
| void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 | |
| 				   unsigned long align, unsigned long goal)
 | |
| {
 | |
| 	if (WARN_ON_ONCE(slab_is_available()))
 | |
| 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 | |
| 
 | |
| 	return  ___alloc_bootmem_node(pgdat, size, align, goal, 0);
 | |
| }
 | |
| 
 | |
| void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
 | |
| 				   unsigned long align, unsigned long goal)
 | |
| {
 | |
| #ifdef MAX_DMA32_PFN
 | |
| 	unsigned long end_pfn;
 | |
| 
 | |
| 	if (WARN_ON_ONCE(slab_is_available()))
 | |
| 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 | |
| 
 | |
| 	/* update goal according ...MAX_DMA32_PFN */
 | |
| 	end_pfn = pgdat_end_pfn(pgdat);
 | |
| 
 | |
| 	if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) &&
 | |
| 	    (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) {
 | |
| 		void *ptr;
 | |
| 		unsigned long new_goal;
 | |
| 
 | |
| 		new_goal = MAX_DMA32_PFN << PAGE_SHIFT;
 | |
| 		ptr = alloc_bootmem_bdata(pgdat->bdata, size, align,
 | |
| 						 new_goal, 0);
 | |
| 		if (ptr)
 | |
| 			return ptr;
 | |
| 	}
 | |
| #endif
 | |
| 
 | |
| 	return __alloc_bootmem_node(pgdat, size, align, goal);
 | |
| 
 | |
| }
 | |
| 
 | |
| #ifndef ARCH_LOW_ADDRESS_LIMIT
 | |
| #define ARCH_LOW_ADDRESS_LIMIT	0xffffffffUL
 | |
| #endif
 | |
| 
 | |
| /**
 | |
|  * __alloc_bootmem_low - allocate low boot memory
 | |
|  * @size: size of the request in bytes
 | |
|  * @align: alignment of the region
 | |
|  * @goal: preferred starting address of the region
 | |
|  *
 | |
|  * The goal is dropped if it can not be satisfied and the allocation will
 | |
|  * fall back to memory below @goal.
 | |
|  *
 | |
|  * Allocation may happen on any node in the system.
 | |
|  *
 | |
|  * The function panics if the request can not be satisfied.
 | |
|  */
 | |
| void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
 | |
| 				  unsigned long goal)
 | |
| {
 | |
| 	return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT);
 | |
| }
 | |
| 
 | |
| void * __init __alloc_bootmem_low_nopanic(unsigned long size,
 | |
| 					  unsigned long align,
 | |
| 					  unsigned long goal)
 | |
| {
 | |
| 	return ___alloc_bootmem_nopanic(size, align, goal,
 | |
| 					ARCH_LOW_ADDRESS_LIMIT);
 | |
| }
 | |
| 
 | |
| /**
 | |
|  * __alloc_bootmem_low_node - allocate low boot memory from a specific node
 | |
|  * @pgdat: node to allocate from
 | |
|  * @size: size of the request in bytes
 | |
|  * @align: alignment of the region
 | |
|  * @goal: preferred starting address of the region
 | |
|  *
 | |
|  * The goal is dropped if it can not be satisfied and the allocation will
 | |
|  * fall back to memory below @goal.
 | |
|  *
 | |
|  * Allocation may fall back to any node in the system if the specified node
 | |
|  * can not hold the requested memory.
 | |
|  *
 | |
|  * The function panics if the request can not be satisfied.
 | |
|  */
 | |
| void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 | |
| 				       unsigned long align, unsigned long goal)
 | |
| {
 | |
| 	if (WARN_ON_ONCE(slab_is_available()))
 | |
| 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 | |
| 
 | |
| 	return ___alloc_bootmem_node(pgdat, size, align,
 | |
| 				     goal, ARCH_LOW_ADDRESS_LIMIT);
 | |
| }
 |