1 files changed, 385 insertions, 153 deletions

diff --git a/mm/slob.c b/mm/slob.c
index 71976c5d40d..b4899079d8b 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -3,57 +3,159 @@
  *
  * Matt Mackall <mpm@selenic.com> 12/30/03
  *
+ * NUMA support by Paul Mundt, 2007.
+ *
  * How SLOB works:
  *
  * The core of SLOB is a traditional K&R style heap allocator, with
  * support for returning aligned objects. The granularity of this
- * allocator is 8 bytes on x86, though it's perhaps possible to reduce
- * this to 4 if it's deemed worth the effort. The slob heap is a
- * singly-linked list of pages from __get_free_page, grown on demand
- * and allocation from the heap is currently first-fit.
+ * allocator is as little as 2 bytes, however typically most architectures
+ * will require 4 bytes on 32-bit and 8 bytes on 64-bit.
+ *
+ * The slob heap is a linked list of pages from alloc_pages(), and
+ * within each page, there is a singly-linked list of free blocks (slob_t).
+ * The heap is grown on demand and allocation from the heap is currently
+ * first-fit.
  *
  * Above this is an implementation of kmalloc/kfree. Blocks returned
- * from kmalloc are 8-byte aligned and prepended with a 8-byte header.
+ * from kmalloc are prepended with a 4-byte header with the kmalloc size.
  * If kmalloc is asked for objects of PAGE_SIZE or larger, it calls
- * __get_free_pages directly so that it can return page-aligned blocks
- * and keeps a linked list of such pages and their orders. These
- * objects are detected in kfree() by their page alignment.
+ * alloc_pages() directly, allocating compound pages so the page order
+ * does not have to be separately tracked, and also stores the exact
+ * allocation size in page->private so that it can be used to accurately
+ * provide ksize(). These objects are detected in kfree() because slob_page()
+ * is false for them.
  *
  * SLAB is emulated on top of SLOB by simply calling constructors and
- * destructors for every SLAB allocation. Objects are returned with
- * the 8-byte alignment unless the SLAB_HWCACHE_ALIGN flag is
- * set, in which case the low-level allocator will fragment blocks to
- * create the proper alignment. Again, objects of page-size or greater
- * are allocated by calling __get_free_pages. As SLAB objects know
- * their size, no separate size bookkeeping is necessary and there is
- * essentially no allocation space overhead.
+ * destructors for every SLAB allocation. Objects are returned with the
+ * 4-byte alignment unless the SLAB_HWCACHE_ALIGN flag is set, in which
+ * case the low-level allocator will fragment blocks to create the proper
+ * alignment. Again, objects of page-size or greater are allocated by
+ * calling alloc_pages(). As SLAB objects know their size, no separate
+ * size bookkeeping is necessary and there is essentially no allocation
+ * space overhead, and compound pages aren't needed for multi-page
+ * allocations.
+ *
+ * NUMA support in SLOB is fairly simplistic, pushing most of the real
+ * logic down to the page allocator, and simply doing the node accounting
+ * on the upper levels. In the event that a node id is explicitly
+ * provided, alloc_pages_node() with the specified node id is used
+ * instead. The common case (or when the node id isn't explicitly provided)
+ * will default to the current node, as per numa_node_id().
+ *
+ * Node aware pages are still inserted in to the global freelist, and
+ * these are scanned for by matching against the node id encoded in the
+ * page flags. As a result, block allocations that can be satisfied from
+ * the freelist will only be done so on pages residing on the same node,
+ * in order to prevent random node placement.
  */
 
+#include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/cache.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/timer.h>
 #include <linux/rcupdate.h>
+#include <linux/list.h>
+#include <asm/atomic.h>
+
+/*
+ * slob_block has a field 'units', which indicates size of block if +ve,
+ * or offset of next block if -ve (in SLOB_UNITs).
+ *
+ * Free blocks of size 1 unit simply contain the offset of the next block.
+ * Those with larger size contain their size in the first SLOB_UNIT of
+ * memory, and the offset of the next free block in the second SLOB_UNIT.
+ */
+#if PAGE_SIZE <= (32767 * 2)
+typedef s16 slobidx_t;
+#else
+typedef s32 slobidx_t;
+#endif
 
 struct slob_block {
-	int units;
-	struct slob_block *next;
+	slobidx_t units;
 };
 typedef struct slob_block slob_t;
 
+/*
+ * We use struct page fields to manage some slob allocation aspects,
+ * however to avoid the horrible mess in include/linux/mm_types.h, we'll
+ * just define our own struct page type variant here.
+ */
+struct slob_page {
+	union {
+		struct {
+			unsigned long flags;	/* mandatory */
+			atomic_t _count;	/* mandatory */
+			slobidx_t units;	/* free units left in page */
+			unsigned long pad[2];
+			slob_t *free;		/* first free slob_t in page */
+			struct list_head list;	/* linked list of free pages */
+		};
+		struct page page;
+	};
+};
+static inline void struct_slob_page_wrong_size(void)
+{ BUILD_BUG_ON(sizeof(struct slob_page) != sizeof(struct page)); }
+
+/*
+ * free_slob_page: call before a slob_page is returned to the page allocator.
+ */
+static inline void free_slob_page(struct slob_page *sp)
+{
+	reset_page_mapcount(&sp->page);
+	sp->page.mapping = NULL;
+}
+
+/*
+ * All (partially) free slob pages go on this list.
+ */
+static LIST_HEAD(free_slob_pages);
+
+/*
+ * slob_page: True for all slob pages (false for bigblock pages)
+ */
+static inline int slob_page(struct slob_page *sp)
+{
+	return test_bit(PG_active, &sp->flags);
+}
+
+static inline void set_slob_page(struct slob_page *sp)
+{
+	__set_bit(PG_active, &sp->flags);
+}
+
+static inline void clear_slob_page(struct slob_page *sp)
+{
+	__clear_bit(PG_active, &sp->flags);
+}
+
+/*
+ * slob_page_free: true for pages on free_slob_pages list.
+ */
+static inline int slob_page_free(struct slob_page *sp)
+{
+	return test_bit(PG_private, &sp->flags);
+}
+
+static inline void set_slob_page_free(struct slob_page *sp)
+{
+	list_add(&sp->list, &free_slob_pages);
+	__set_bit(PG_private, &sp->flags);
+}
+
+static inline void clear_slob_page_free(struct slob_page *sp)
+{
+	list_del(&sp->list);
+	__clear_bit(PG_private, &sp->flags);
+}
+
 #define SLOB_UNIT sizeof(slob_t)
 #define SLOB_UNITS(size) (((size) + SLOB_UNIT - 1)/SLOB_UNIT)
 #define SLOB_ALIGN L1_CACHE_BYTES
 
-struct bigblock {
-	int order;
-	void *pages;
-	struct bigblock *next;
-};
-typedef struct bigblock bigblock_t;
-
 /*
  * struct slob_rcu is inserted at the tail of allocated slob blocks, which
  * were created with a SLAB_DESTROY_BY_RCU slab. slob_rcu is used to free
@@ -64,133 +166,285 @@ struct slob_rcu {
 	int size;
 };
 
-static slob_t arena = { .next = &arena, .units = 1 };
-static slob_t *slobfree = &arena;
-static bigblock_t *bigblocks;
+/*
+ * slob_lock protects all slob allocator structures.
+ */
 static DEFINE_SPINLOCK(slob_lock);
-static DEFINE_SPINLOCK(block_lock);
 
-static void slob_free(void *b, int size);
-static void slob_timer_cbk(void);
+/*
+ * Encode the given size and next info into a free slob block s.
+ */
+static void set_slob(slob_t *s, slobidx_t size, slob_t *next)
+{
+	slob_t *base = (slob_t *)((unsigned long)s & PAGE_MASK);
+	slobidx_t offset = next - base;
 
+	if (size > 1) {
+		s[0].units = size;
+		s[1].units = offset;
+	} else
+		s[0].units = -offset;
+}
 
-static void *slob_alloc(size_t size, gfp_t gfp, int align)
+/*
+ * Return the size of a slob block.
+ */
+static slobidx_t slob_units(slob_t *s)
+{
+	if (s->units > 0)
+		return s->units;
+	return 1;
+}
+
+/*
+ * Return the next free slob block pointer after this one.
+ */
+static slob_t *slob_next(slob_t *s)
+{
+	slob_t *base = (slob_t *)((unsigned long)s & PAGE_MASK);
+	slobidx_t next;
+
+	if (s[0].units < 0)
+		next = -s[0].units;
+	else
+		next = s[1].units;
+	return base+next;
+}
+
+/*
+ * Returns true if s is the last free block in its page.
+ */
+static int slob_last(slob_t *s)
+{
+	return !((unsigned long)slob_next(s) & ~PAGE_MASK);
+}
+
+static void *slob_new_page(gfp_t gfp, int order, int node)
+{
+	void *page;
+
+#ifdef CONFIG_NUMA
+	if (node != -1)
+		page = alloc_pages_node(node, gfp, order);
+	else
+#endif
+		page = alloc_pages(gfp, order);
+
+	if (!page)
+		return NULL;
+
+	return page_address(page);
+}
+
+/*
+ * Allocate a slob block within a given slob_page sp.
+ */
+static void *slob_page_alloc(struct slob_page *sp, size_t size, int align)
 {
 	slob_t *prev, *cur, *aligned = 0;
 	int delta = 0, units = SLOB_UNITS(size);
-	unsigned long flags;
 
-	spin_lock_irqsave(&slob_lock, flags);
-	prev = slobfree;
-	for (cur = prev->next; ; prev = cur, cur = cur->next) {
+	for (prev = NULL, cur = sp->free; ; prev = cur, cur = slob_next(cur)) {
+		slobidx_t avail = slob_units(cur);
+
 		if (align) {
 			aligned = (slob_t *)ALIGN((unsigned long)cur, align);
 			delta = aligned - cur;
 		}
-		if (cur->units >= units + delta) { /* room enough? */
+		if (avail >= units + delta) { /* room enough? */
+			slob_t *next;
+
 			if (delta) { /* need to fragment head to align? */
-				aligned->units = cur->units - delta;
-				aligned->next = cur->next;
-				cur->next = aligned;
-				cur->units = delta;
+				next = slob_next(cur);
+				set_slob(aligned, avail - delta, next);
+				set_slob(cur, delta, aligned);
 				prev = cur;
 				cur = aligned;
+				avail = slob_units(cur);
 			}
 
-			if (cur->units == units) /* exact fit? */
-				prev->next = cur->next; /* unlink */
-			else { /* fragment */
-				prev->next = cur + units;
-				prev->next->units = cur->units - units;
-				prev->next->next = cur->next;
-				cur->units = units;
+			next = slob_next(cur);
+			if (avail == units) { /* exact fit? unlink. */
+				if (prev)
+					set_slob(prev, slob_units(prev), next);
+				else
+					sp->free = next;
+			} else { /* fragment */
+				if (prev)
+					set_slob(prev, slob_units(prev), cur + units);
+				else
+					sp->free = cur + units;
+				set_slob(cur + units, avail - units, next);
 			}
 
-			slobfree = prev;
-			spin_unlock_irqrestore(&slob_lock, flags);
+			sp->units -= units;
+			if (!sp->units)
+				clear_slob_page_free(sp);
 			return cur;
 		}
-		if (cur == slobfree) {
-			spin_unlock_irqrestore(&slob_lock, flags);
-
-			if (size == PAGE_SIZE) /* trying to shrink arena? */
-				return 0;
+		if (slob_last(cur))
+			return NULL;
+	}
+}
 
-			cur = (slob_t *)__get_free_page(gfp);
-			if (!cur)
-				return 0;
+/*
+ * slob_alloc: entry point into the slob allocator.
+ */
+static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
+{
+	struct slob_page *sp;
+	slob_t *b = NULL;
+	unsigned long flags;
 
-			slob_free(cur, PAGE_SIZE);
-			spin_lock_irqsave(&slob_lock, flags);
-			cur = slobfree;
+	spin_lock_irqsave(&slob_lock, flags);
+	/* Iterate through each partially free page, try to find room */
+	list_for_each_entry(sp, &free_slob_pages, list) {
+#ifdef CONFIG_NUMA
+		/*
+		 * If there's a node specification, search for a partial
+		 * page with a matching node id in the freelist.
+		 */
+		if (node != -1 && page_to_nid(&sp->page) != node)
+			continue;
+#endif
+
+		if (sp->units >= SLOB_UNITS(size)) {
+			b = slob_page_alloc(sp, size, align);
+			if (b)
+				break;
 		}
 	}
+	spin_unlock_irqrestore(&slob_lock, flags);
+
+	/* Not enough space: must allocate a new page */
+	if (!b) {
+		b = slob_new_page(gfp, 0, node);
+		if (!b)
+			return 0;
+		sp = (struct slob_page *)virt_to_page(b);
+		set_slob_page(sp);
+
+		spin_lock_irqsave(&slob_lock, flags);
+		sp->units = SLOB_UNITS(PAGE_SIZE);
+		sp->free = b;
+		INIT_LIST_HEAD(&sp->list);
+		set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE));
+		set_slob_page_free(sp);
+		b = slob_page_alloc(sp, size, align);
+		BUG_ON(!b);
+		spin_unlock_irqrestore(&slob_lock, flags);
+	}
+	return b;
 }
 
+/*
+ * slob_free: entry point into the slob allocator.
+ */
 static void slob_free(void *block, int size)
 {
-	slob_t *cur, *b = (slob_t *)block;
+	struct slob_page *sp;
+	slob_t *prev, *next, *b = (slob_t *)block;
+	slobidx_t units;
 	unsigned long flags;
 
 	if (!block)
 		return;
+	BUG_ON(!size);
 
-	if (size)
-		b->units = SLOB_UNITS(size);
+	sp = (struct slob_page *)virt_to_page(block);
+	units = SLOB_UNITS(size);
 
-	/* Find reinsertion point */
 	spin_lock_irqsave(&slob_lock, flags);
-	for (cur = slobfree; !(b > cur && b < cur->next); cur = cur->next)
-		if (cur >= cur->next && (b > cur || b < cur->next))
-			break;
 
-	if (b + b->units == cur->next) {
-		b->units += cur->next->units;
-		b->next = cur->next->next;
-	} else
-		b->next = cur->next;
+	if (sp->units + units == SLOB_UNITS(PAGE_SIZE)) {
+		/* Go directly to page allocator. Do not pass slob allocator */
+		if (slob_page_free(sp))
+			clear_slob_page_free(sp);
+		clear_slob_page(sp);
+		free_slob_page(sp);
+		free_page((unsigned long)b);
+		goto out;
+	}
 
-	if (cur + cur->units == b) {
-		cur->units += b->units;
-		cur->next = b->next;
-	} else
-		cur->next = b;
+	if (!slob_page_free(sp)) {
+		/* This slob page is about to become partially free. Easy! */
+		sp->units = units;
+		sp->free = b;
+		set_slob(b, units,
+			(void *)((unsigned long)(b +
+					SLOB_UNITS(PAGE_SIZE)) & PAGE_MASK));
+		set_slob_page_free(sp);
+		goto out;
+	}
 
-	slobfree = cur;
+	/*
+	 * Otherwise the page is already partially free, so find reinsertion
+	 * point.
+	 */
+	sp->units += units;
 
+	if (b < sp->free) {
+		set_slob(b, units, sp->free);
+		sp->free = b;
+	} else {
+		prev = sp->free;
+		next = slob_next(prev);
+		while (b > next) {
+			prev = next;
+			next = slob_next(prev);
+		}
+
+		if (!slob_last(prev) && b + units == next) {
+			units += slob_units(next);
+			set_slob(b, units, slob_next(next));
+		} else
+			set_slob(b, units, next);
+
+		if (prev + slob_units(prev) == b) {
+			units = slob_units(b) + slob_units(prev);
+			set_slob(prev, units, slob_next(b));
+		} else
+			set_slob(prev, slob_units(prev), b);
+	}
+out:
 	spin_unlock_irqrestore(&slob_lock, flags);
 }
 
-void *__kmalloc(size_t size, gfp_t gfp)
-{
-	slob_t *m;
-	bigblock_t *bb;
-	unsigned long flags;
+/*
+ * End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend.
+ */
 
-	if (size < PAGE_SIZE - SLOB_UNIT) {
-		m = slob_alloc(size + SLOB_UNIT, gfp, 0);
-		return m ? (void *)(m + 1) : 0;
-	}
+#ifndef ARCH_KMALLOC_MINALIGN
+#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long)
+#endif
 
-	bb = slob_alloc(sizeof(bigblock_t), gfp, 0);
-	if (!bb)
-		return 0;
+#ifndef ARCH_SLAB_MINALIGN
+#define ARCH_SLAB_MINALIGN __alignof__(unsigned long)
+#endif
 
-	bb->order = get_order(size);
-	bb->pages = (void *)__get_free_pages(gfp, bb->order);
+void *__kmalloc_node(size_t size, gfp_t gfp, int node)
+{
+	int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+
+	if (size < PAGE_SIZE - align) {
+		unsigned int *m;
+		m = slob_alloc(size + align, gfp, align, node);
+		if (m)
+			*m = size;
+		return (void *)m + align;
+	} else {
+		void *ret;
 
-	if (bb->pages) {
-		spin_lock_irqsave(&block_lock, flags);
-		bb->next = bigblocks;
-		bigblocks = bb;
-		spin_unlock_irqrestore(&block_lock, flags);
-		return bb->pages;
+		ret = slob_new_page(gfp | __GFP_COMP, get_order(size), node);
+		if (ret) {
+			struct page *page;
+			page = virt_to_page(ret);
+			page->private = size;
+		}
+		return ret;
 	}
-
-	slob_free(bb, sizeof(bigblock_t));
-	return 0;
 }
-EXPORT_SYMBOL(__kmalloc);
+EXPORT_SYMBOL(__kmalloc_node);
 
 /**
  * krealloc - reallocate memory. The contents will remain unchanged.
@@ -227,52 +481,34 @@ EXPORT_SYMBOL(krealloc);
 
 void kfree(const void *block)
 {
-	bigblock_t *bb, **last = &bigblocks;
-	unsigned long flags;
+	struct slob_page *sp;
 
 	if (!block)
 		return;
 
-	if (!((unsigned long)block & (PAGE_SIZE-1))) {
-		/* might be on the big block list */
-		spin_lock_irqsave(&block_lock, flags);
-		for (bb = bigblocks; bb; last = &bb->next, bb = bb->next) {
-			if (bb->pages == block) {
-				*last = bb->next;
-				spin_unlock_irqrestore(&block_lock, flags);
-				free_pages((unsigned long)block, bb->order);
-				slob_free(bb, sizeof(bigblock_t));
-				return;
-			}
-		}
-		spin_unlock_irqrestore(&block_lock, flags);
-	}
-
-	slob_free((slob_t *)block - 1, 0);
-	return;
+	sp = (struct slob_page *)virt_to_page(block);
+	if (slob_page(sp)) {
+		int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+		unsigned int *m = (unsigned int *)(block - align);
+		slob_free(m, *m + align);
+	} else
+		put_page(&sp->page);
 }
-
 EXPORT_SYMBOL(kfree);
 
+/* can't use ksize for kmem_cache_alloc memory, only kmalloc */
 size_t ksize(const void *block)
 {
-	bigblock_t *bb;
-	unsigned long flags;
+	struct slob_page *sp;
 
 	if (!block)
 		return 0;
 
-	if (!((unsigned long)block & (PAGE_SIZE-1))) {
-		spin_lock_irqsave(&block_lock, flags);
-		for (bb = bigblocks; bb; bb = bb->next)
-			if (bb->pages == block) {
-				spin_unlock_irqrestore(&slob_lock, flags);
-				return PAGE_SIZE << bb->order;
-			}
-		spin_unlock_irqrestore(&block_lock, flags);
-	}
-
-	return ((slob_t *)block - 1)->units * SLOB_UNIT;
+	sp = (struct slob_page *)virt_to_page(block);
+	if (slob_page(sp))
+		return ((slob_t *)block - 1)->units + SLOB_UNIT;
+	else
+		return sp->page.private;
 }
 
 struct kmem_cache {
@@ -289,7 +525,7 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 {
 	struct kmem_cache *c;
 
-	c = slob_alloc(sizeof(struct kmem_cache), flags, 0);
+	c = slob_alloc(sizeof(struct kmem_cache), flags, 0, -1);
 
 	if (c) {
 		c->name = name;
@@ -302,6 +538,8 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 		c->ctor = ctor;
 		/* ignore alignment unless it's forced */
 		c->align = (flags & SLAB_HWCACHE_ALIGN) ? SLOB_ALIGN : 0;
+		if (c->align < ARCH_SLAB_MINALIGN)
+			c->align = ARCH_SLAB_MINALIGN;
 		if (c->align < align)
 			c->align = align;
 	} else if (flags & SLAB_PANIC)
@@ -317,21 +555,21 @@ void kmem_cache_destroy(struct kmem_cache *c)
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
-void *kmem_cache_alloc(struct kmem_cache *c, gfp_t flags)
+void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 {
 	void *b;
 
 	if (c->size < PAGE_SIZE)
-		b = slob_alloc(c->size, flags, c->align);
+		b = slob_alloc(c->size, flags, c->align, node);
 	else
-		b = (void *)__get_free_pages(flags, get_order(c->size));
+		b = slob_new_page(flags, get_order(c->size), node);
 
 	if (c->ctor)
 		c->ctor(b, c, 0);
 
 	return b;
 }
-EXPORT_SYMBOL(kmem_cache_alloc);
+EXPORT_SYMBOL(kmem_cache_alloc_node);
 
 void *kmem_cache_zalloc(struct kmem_cache *c, gfp_t flags)
 {
@@ -385,9 +623,6 @@ const char *kmem_cache_name(struct kmem_cache *c)
 }
 EXPORT_SYMBOL(kmem_cache_name);
 
-static struct timer_list slob_timer = TIMER_INITIALIZER(
-	(void (*)(unsigned long))slob_timer_cbk, 0, 0);
-
 int kmem_cache_shrink(struct kmem_cache *d)
 {
 	return 0;
@@ -399,17 +634,14 @@ int kmem_ptr_validate(struct kmem_cache *a, const void *b)
 	return 0;
 }
 
-void __init kmem_cache_init(void)
+static unsigned int slob_ready __read_mostly;
+
+int slab_is_available(void)
 {
-	slob_timer_cbk();
+	return slob_ready;
 }
 
-static void slob_timer_cbk(void)
+void __init kmem_cache_init(void)
 {
-	void *p = slob_alloc(PAGE_SIZE, 0, PAGE_SIZE-1);
-
-	if (p)
-		free_page((unsigned long)p);
-
-	mod_timer(&slob_timer, jiffies + HZ);
+	slob_ready = 1;
 }