X-Git-Url: https://git.karo-electronics.de/?a=blobdiff_plain;f=mm%2Fbootmem.c;h=4bc6ae2fbaa362ae55d59c778bfe7ee5cf1fe5b9;hb=9682290484370ce68ba23cd2ec2838e301934199;hp=2ccea700968f7ecaaa265023e79e52d540a82871;hpb=4f02f8220562591322c118d07a32bebf705318b7;p=mv-sheeva.git

diff --git a/mm/bootmem.c b/mm/bootmem.c
index 2ccea700968..4bc6ae2fbaa 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -36,6 +36,8 @@ static LIST_HEAD(bdata_list);
 unsigned long saved_max_pfn;
 #endif
 
+bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata;
+
 /* return the number of _pages_ that will be allocated for the boot bitmap */
 unsigned long __init bootmem_bootmap_pages(unsigned long pages)
 {
@@ -85,12 +87,12 @@ static unsigned long __init get_mapsize(bootmem_data_t *bdata)
 /*
  * Called once to set up the allocator itself.
  */
-static unsigned long __init init_bootmem_core(pg_data_t *pgdat,
+static unsigned long __init init_bootmem_core(bootmem_data_t *bdata,
 	unsigned long mapstart, unsigned long start, unsigned long end)
 {
-	bootmem_data_t *bdata = pgdat->bdata;
 	unsigned long mapsize;
 
+	mminit_validate_memmodel_limits(&start, &end);
 	bdata->node_bootmem_map = phys_to_virt(PFN_PHYS(mapstart));
 	bdata->node_boot_start = PFN_PHYS(start);
 	bdata->node_low_pfn = end;
@@ -111,44 +113,74 @@ static unsigned long __init init_bootmem_core(pg_data_t *pgdat,
  * might be used for boot-time allocations - or it might get added
  * to the free page pool later on.
  */
-static int __init reserve_bootmem_core(bootmem_data_t *bdata,
+static int __init can_reserve_bootmem_core(bootmem_data_t *bdata,
 			unsigned long addr, unsigned long size, int flags)
 {
 	unsigned long sidx, eidx;
 	unsigned long i;
-	int ret;
+
+	BUG_ON(!size);
+
+	/* out of range, don't hold other */
+	if (addr + size < bdata->node_boot_start ||
+		PFN_DOWN(addr) > bdata->node_low_pfn)
+		return 0;
 
 	/*
-	 * round up, partially reserved pages are considered
-	 * fully reserved.
+	 * Round up to index to the range.
 	 */
+	if (addr > bdata->node_boot_start)
+		sidx= PFN_DOWN(addr - bdata->node_boot_start);
+	else
+		sidx = 0;
+
+	eidx = PFN_UP(addr + size - bdata->node_boot_start);
+	if (eidx > bdata->node_low_pfn - PFN_DOWN(bdata->node_boot_start))
+		eidx = bdata->node_low_pfn - PFN_DOWN(bdata->node_boot_start);
+
+	for (i = sidx; i < eidx; i++) {
+		if (test_bit(i, bdata->node_bootmem_map)) {
+			if (flags & BOOTMEM_EXCLUSIVE)
+				return -EBUSY;
+		}
+	}
+
+	return 0;
+
+}
+
+static void __init reserve_bootmem_core(bootmem_data_t *bdata,
+			unsigned long addr, unsigned long size, int flags)
+{
+	unsigned long sidx, eidx;
+	unsigned long i;
+
 	BUG_ON(!size);
-	BUG_ON(PFN_DOWN(addr) >= bdata->node_low_pfn);
-	BUG_ON(PFN_UP(addr + size) > bdata->node_low_pfn);
-	BUG_ON(addr < bdata->node_boot_start);
 
-	sidx = PFN_DOWN(addr - bdata->node_boot_start);
+	/* out of range */
+	if (addr + size < bdata->node_boot_start ||
+		PFN_DOWN(addr) > bdata->node_low_pfn)
+		return;
+
+	/*
+	 * Round up to index to the range.
+	 */
+	if (addr > bdata->node_boot_start)
+		sidx= PFN_DOWN(addr - bdata->node_boot_start);
+	else
+		sidx = 0;
+
 	eidx = PFN_UP(addr + size - bdata->node_boot_start);
+	if (eidx > bdata->node_low_pfn - PFN_DOWN(bdata->node_boot_start))
+		eidx = bdata->node_low_pfn - PFN_DOWN(bdata->node_boot_start);
 
-	for (i = sidx; i < eidx; i++)
+	for (i = sidx; i < eidx; i++) {
 		if (test_and_set_bit(i, bdata->node_bootmem_map)) {
 #ifdef CONFIG_DEBUG_BOOTMEM
 			printk("hm, page %08lx reserved twice.\n", i*PAGE_SIZE);
 #endif
-			if (flags & BOOTMEM_EXCLUSIVE) {
-				ret = -EBUSY;
-				goto err;
-			}
 		}
-
-	return 0;
-
-err:
-	/* unreserve memory we accidentally reserved */
-	for (i--; i >= sidx; i--)
-		clear_bit(i, bdata->node_bootmem_map);
-
-	return ret;
+	}
 }
 
 static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
@@ -202,84 +234,99 @@ static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
  *
  * NOTE:  This function is _not_ reentrant.
  */
-void * __init
-__alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
-	      unsigned long align, unsigned long goal, unsigned long limit)
+static void * __init
+alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
+		unsigned long align, unsigned long goal, unsigned long limit)
 {
-	unsigned long offset, remaining_size, areasize, preferred;
+	unsigned long areasize, preferred;
 	unsigned long i, start = 0, incr, eidx, end_pfn;
 	void *ret;
+	unsigned long node_boot_start;
+	void *node_bootmem_map;
 
 	if (!size) {
-		printk("__alloc_bootmem_core(): zero-sized request\n");
+		printk("alloc_bootmem_core(): zero-sized request\n");
 		BUG();
 	}
 	BUG_ON(align & (align-1));
 
-	if (limit && bdata->node_boot_start >= limit)
-		return NULL;
-
 	/* on nodes without memory - bootmem_map is NULL */
 	if (!bdata->node_bootmem_map)
 		return NULL;
 
+	/* bdata->node_boot_start is supposed to be (12+6)bits alignment on x86_64 ? */
+	node_boot_start = bdata->node_boot_start;
+	node_bootmem_map = bdata->node_bootmem_map;
+	if (align) {
+		node_boot_start = ALIGN(bdata->node_boot_start, align);
+		if (node_boot_start > bdata->node_boot_start)
+			node_bootmem_map = (unsigned long *)bdata->node_bootmem_map +
+			    PFN_DOWN(node_boot_start - bdata->node_boot_start)/BITS_PER_LONG;
+	}
+
+	if (limit && node_boot_start >= limit)
+		return NULL;
+
 	end_pfn = bdata->node_low_pfn;
 	limit = PFN_DOWN(limit);
 	if (limit && end_pfn > limit)
 		end_pfn = limit;
 
-	eidx = end_pfn - PFN_DOWN(bdata->node_boot_start);
-	offset = 0;
-	if (align && (bdata->node_boot_start & (align - 1UL)) != 0)
-		offset = align - (bdata->node_boot_start & (align - 1UL));
-	offset = PFN_DOWN(offset);
+	eidx = end_pfn - PFN_DOWN(node_boot_start);
 
 	/*
 	 * We try to allocate bootmem pages above 'goal'
 	 * first, then we try to allocate lower pages.
 	 */
-	if (goal && goal >= bdata->node_boot_start && PFN_DOWN(goal) < end_pfn) {
-		preferred = goal - bdata->node_boot_start;
+	preferred = 0;
+	if (goal && PFN_DOWN(goal) < end_pfn) {
+		if (goal > node_boot_start)
+			preferred = goal - node_boot_start;
 
-		if (bdata->last_success >= preferred)
+		if (bdata->last_success > node_boot_start &&
+			bdata->last_success - node_boot_start >= preferred)
 			if (!limit || (limit && limit > bdata->last_success))
-				preferred = bdata->last_success;
-	} else
-		preferred = 0;
+				preferred = bdata->last_success - node_boot_start;
+	}
 
-	preferred = PFN_DOWN(ALIGN(preferred, align)) + offset;
+	preferred = PFN_DOWN(ALIGN(preferred, align));
 	areasize = (size + PAGE_SIZE-1) / PAGE_SIZE;
 	incr = align >> PAGE_SHIFT ? : 1;
 
 restart_scan:
-	for (i = preferred; i < eidx; i += incr) {
+	for (i = preferred; i < eidx;) {
 		unsigned long j;
-		i = find_next_zero_bit(bdata->node_bootmem_map, eidx, i);
+
+		i = find_next_zero_bit(node_bootmem_map, eidx, i);
 		i = ALIGN(i, incr);
 		if (i >= eidx)
 			break;
-		if (test_bit(i, bdata->node_bootmem_map))
+		if (test_bit(i, node_bootmem_map)) {
+			i += incr;
 			continue;
+		}
 		for (j = i + 1; j < i + areasize; ++j) {
 			if (j >= eidx)
 				goto fail_block;
-			if (test_bit(j, bdata->node_bootmem_map))
+			if (test_bit(j, node_bootmem_map))
 				goto fail_block;
 		}
 		start = i;
 		goto found;
 	fail_block:
 		i = ALIGN(j, incr);
+		if (i == j)
+			i += incr;
 	}
 
-	if (preferred > offset) {
-		preferred = offset;
+	if (preferred > 0) {
+		preferred = 0;
 		goto restart_scan;
 	}
 	return NULL;
 
 found:
-	bdata->last_success = PFN_PHYS(start);
+	bdata->last_success = PFN_PHYS(start) + node_boot_start;
 	BUG_ON(start >= eidx);
 
 	/*
@@ -289,6 +336,7 @@ found:
 	 */
 	if (align < PAGE_SIZE &&
 	    bdata->last_offset && bdata->last_pos+1 == start) {
+		unsigned long offset, remaining_size;
 		offset = ALIGN(bdata->last_offset, align);
 		BUG_ON(offset > PAGE_SIZE);
 		remaining_size = PAGE_SIZE - offset;
@@ -297,14 +345,12 @@ found:
 			/* last_pos unchanged */
 			bdata->last_offset = offset + size;
 			ret = phys_to_virt(bdata->last_pos * PAGE_SIZE +
-					   offset +
-					   bdata->node_boot_start);
+					   offset + node_boot_start);
 		} else {
 			remaining_size = size - remaining_size;
 			areasize = (remaining_size + PAGE_SIZE-1) / PAGE_SIZE;
 			ret = phys_to_virt(bdata->last_pos * PAGE_SIZE +
-					   offset +
-					   bdata->node_boot_start);
+					   offset + node_boot_start);
 			bdata->last_pos = start + areasize - 1;
 			bdata->last_offset = remaining_size;
 		}
@@ -312,25 +358,24 @@ found:
 	} else {
 		bdata->last_pos = start + areasize - 1;
 		bdata->last_offset = size & ~PAGE_MASK;
-		ret = phys_to_virt(start * PAGE_SIZE + bdata->node_boot_start);
+		ret = phys_to_virt(start * PAGE_SIZE + node_boot_start);
 	}
 
 	/*
 	 * Reserve the area now:
 	 */
 	for (i = start; i < start + areasize; i++)
-		if (unlikely(test_and_set_bit(i, bdata->node_bootmem_map)))
+		if (unlikely(test_and_set_bit(i, node_bootmem_map)))
 			BUG();
 	memset(ret, 0, size);
 	return ret;
 }
 
-static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
+static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 {
 	struct page *page;
 	unsigned long pfn;
-	bootmem_data_t *bdata = pgdat->bdata;
-	unsigned long i, count, total = 0;
+	unsigned long i, count;
 	unsigned long idx;
 	unsigned long *map; 
 	int gofast = 0;
@@ -342,10 +387,13 @@ static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
 	pfn = PFN_DOWN(bdata->node_boot_start);
 	idx = bdata->node_low_pfn - pfn;
 	map = bdata->node_bootmem_map;
-	/* Check physaddr is O(LOG2(BITS_PER_LONG)) page aligned */
-	if (bdata->node_boot_start == 0 ||
-	    ffs(bdata->node_boot_start) - PAGE_SHIFT > ffs(BITS_PER_LONG))
+	/*
+	 * Check if we are aligned to BITS_PER_LONG pages.  If so, we might
+	 * be able to free page orders of that size at once.
+	 */
+	if (!(pfn & (BITS_PER_LONG-1)))
 		gofast = 1;
+
 	for (i = 0; i < idx; ) {
 		unsigned long v = ~map[i / BITS_PER_LONG];
 
@@ -373,35 +421,38 @@ static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
 		}
 		pfn += BITS_PER_LONG;
 	}
-	total += count;
 
 	/*
 	 * Now free the allocator bitmap itself, it's not
 	 * needed anymore:
 	 */
 	page = virt_to_page(bdata->node_bootmem_map);
-	count = 0;
 	idx = (get_mapsize(bdata) + PAGE_SIZE-1) >> PAGE_SHIFT;
-	for (i = 0; i < idx; i++, page++) {
+	for (i = 0; i < idx; i++, page++)
 		__free_pages_bootmem(page, 0);
-		count++;
-	}
-	total += count;
+	count += i;
 	bdata->node_bootmem_map = NULL;
 
-	return total;
+	return count;
 }
 
 unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
 				unsigned long startpfn, unsigned long endpfn)
 {
-	return init_bootmem_core(pgdat, freepfn, startpfn, endpfn);
+	return init_bootmem_core(pgdat->bdata, freepfn, startpfn, endpfn);
 }
 
-void __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
+int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 				 unsigned long size, int flags)
 {
+	int ret;
+
+	ret = can_reserve_bootmem_core(pgdat->bdata, physaddr, size, flags);
+	if (ret < 0)
+		return -ENOMEM;
 	reserve_bootmem_core(pgdat->bdata, physaddr, size, flags);
+
+	return 0;
 }
 
 void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
@@ -412,21 +463,33 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 
 unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
 {
-	return free_all_bootmem_core(pgdat);
+	register_page_bootmem_info_node(pgdat);
+	return free_all_bootmem_core(pgdat->bdata);
 }
 
 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), start, 0, pages);
+	return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
 }
 
 #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
 int __init reserve_bootmem(unsigned long addr, unsigned long size,
 			    int flags)
 {
-	return reserve_bootmem_core(NODE_DATA(0)->bdata, addr, size, flags);
+	bootmem_data_t *bdata;
+	int ret;
+
+	list_for_each_entry(bdata, &bdata_list, list) {
+		ret = can_reserve_bootmem_core(bdata, addr, size, flags);
+		if (ret < 0)
+			return ret;
+	}
+	list_for_each_entry(bdata, &bdata_list, list)
+		reserve_bootmem_core(bdata, addr, size, flags);
+
+	return 0;
 }
 #endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */
 
@@ -439,7 +502,7 @@ void __init free_bootmem(unsigned long addr, unsigned long size)
 
 unsigned long __init free_all_bootmem(void)
 {
-	return free_all_bootmem_core(NODE_DATA(0));
+	return free_all_bootmem_core(NODE_DATA(0)->bdata);
 }
 
 void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
@@ -449,7 +512,7 @@ void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
 	void *ptr;
 
 	list_for_each_entry(bdata, &bdata_list, list) {
-		ptr = __alloc_bootmem_core(bdata, size, align, goal, 0);
+		ptr = alloc_bootmem_core(bdata, size, align, goal, 0);
 		if (ptr)
 			return ptr;
 	}
@@ -477,13 +540,44 @@ void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 {
 	void *ptr;
 
-	ptr = __alloc_bootmem_core(pgdat->bdata, size, align, goal, 0);
+	ptr = alloc_bootmem_core(pgdat->bdata, size, align, goal, 0);
 	if (ptr)
 		return ptr;
 
 	return __alloc_bootmem(size, align, goal);
 }
 
+#ifdef CONFIG_SPARSEMEM
+void * __init alloc_bootmem_section(unsigned long size,
+				    unsigned long section_nr)
+{
+	void *ptr;
+	unsigned long limit, goal, start_nr, end_nr, pfn;
+	struct pglist_data *pgdat;
+
+	pfn = section_nr_to_pfn(section_nr);
+	goal = PFN_PHYS(pfn);
+	limit = PFN_PHYS(section_nr_to_pfn(section_nr + 1)) - 1;
+	pgdat = NODE_DATA(early_pfn_to_nid(pfn));
+	ptr = alloc_bootmem_core(pgdat->bdata, size, SMP_CACHE_BYTES, goal,
+				limit);
+
+	if (!ptr)
+		return NULL;
+
+	start_nr = pfn_to_section_nr(PFN_DOWN(__pa(ptr)));
+	end_nr = pfn_to_section_nr(PFN_DOWN(__pa(ptr) + size));
+	if (start_nr != section_nr || end_nr != section_nr) {
+		printk(KERN_WARNING "alloc_bootmem failed on section %ld.\n",
+		       section_nr);
+		free_bootmem_core(pgdat->bdata, __pa(ptr), size);
+		ptr = NULL;
+	}
+
+	return ptr;
+}
+#endif
+
 #ifndef ARCH_LOW_ADDRESS_LIMIT
 #define ARCH_LOW_ADDRESS_LIMIT	0xffffffffUL
 #endif
@@ -495,8 +589,8 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
 	void *ptr;
 
 	list_for_each_entry(bdata, &bdata_list, list) {
-		ptr = __alloc_bootmem_core(bdata, size, align, goal,
-						ARCH_LOW_ADDRESS_LIMIT);
+		ptr = alloc_bootmem_core(bdata, size, align, goal,
+					ARCH_LOW_ADDRESS_LIMIT);
 		if (ptr)
 			return ptr;
 	}
@@ -512,6 +606,6 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
 void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 				       unsigned long align, unsigned long goal)
 {
-	return __alloc_bootmem_core(pgdat->bdata, size, align, goal,
-				    ARCH_LOW_ADDRESS_LIMIT);
+	return alloc_bootmem_core(pgdat->bdata, size, align, goal,
+				ARCH_LOW_ADDRESS_LIMIT);
 }