[PATCH] bootmem speedup from the IA64 tree

From: Christoph Hellwig <hch@lst.de>

This patch is from the IA64 tree, with some minor cleanups by me.
David described it as:

  This is a performance speed up and some minor indendation fixups.

  The problem is that the bootmem code is (a) hugely slow and (b) has
  execution that grow quadratically with the size of the bootmap bitmap.
  This causes noticable slowdowns, especially on machines with (relatively)
  large holes in the physical memory map.  Issue (b) is addressed by
  maintaining the "last_success" cache, so that we start the next search
  from the place where we last found some memory (this part of the patch
  could stand additional reviewing/testing).  Issue (a) is addressed by
  using find_next_zero_bit() instead of the slow bit-by-bit testing.

include/linux/bootmem.h

@@ -32,6 +32,8 @@ typedef struct bootmem_data {
 	void *node_bootmem_map;
 	unsigned long last_offset;
 	unsigned long last_pos;
+	unsigned long last_success;	/* Previous allocation point.  To speed
+					 * up searching */
 } bootmem_data_t;
 
 extern unsigned long __init bootmem_bootmap_pages (unsigned long);

mm/bootmem.c

@@ -115,6 +115,9 @@ static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
 	if (end > bdata->node_low_pfn)
 		BUG();
 
+	if (addr < bdata->last_success)
+		bdata->last_success = addr;
+
 	/*
 	 * Round up the beginning of the address.
 	 */
@@ -135,26 +138,23 @@ static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
  * is not a problem.
  *
  * On low memory boxes we get it right in 100% of the cases.
- */
-
-/*
+ *
  * alignment has to be a power of 2 value.
+ *
+ * NOTE:  This function is _not_ reenetrant.
  */
-static void * __init __alloc_bootmem_core (bootmem_data_t *bdata, 
-	unsigned long size, unsigned long align, unsigned long goal)
+static void * __init
+__alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
+		unsigned long align, unsigned long goal)
 {
-	unsigned long i, start = 0;
+	unsigned long offset, remaining_size, areasize, preferred;
+	unsigned long i, start = 0, incr, eidx;
 	void *ret;
-	unsigned long offset, remaining_size;
-	unsigned long areasize, preferred, incr;
-	unsigned long eidx = bdata->node_low_pfn - (bdata->node_boot_start >>
-							PAGE_SHIFT);
-
-	if (!size) BUG();
 
-	if (align & (align-1))
-		BUG();
+	BUG_ON(!size);
+	BUG_ON(align & (align-1));
 
+	eidx = bdata->node_low_pfn - (bdata->node_boot_start >> PAGE_SHIFT);
 	offset = 0;
 	if (align &&
 	    (bdata->node_boot_start & (align - 1UL)) != 0)
@@ -168,6 +168,9 @@ static void * __init __alloc_bootmem_core (bootmem_data_t *bdata,
 	if (goal && (goal >= bdata->node_boot_start) && 
 	    ((goal >> PAGE_SHIFT) < bdata->node_low_pfn)) {
 		preferred = goal - bdata->node_boot_start;
+
+		if (bdata->last_success >= preferred)
+			preferred = bdata->last_success;
 	} else
 		preferred = 0;
 
@@ -179,6 +182,8 @@ static void * __init __alloc_bootmem_core (bootmem_data_t *bdata,
 restart_scan:
 	for (i = preferred; i < eidx; i += incr) {
 		unsigned long j;
+		i = find_next_zero_bit(bdata->node_bootmem_map, eidx, i);
+		i = (i + incr - 1) & -incr;
 		if (test_bit(i, bdata->node_bootmem_map))
 			continue;
 		for (j = i + 1; j < i + areasize; ++j) {
@@ -189,31 +194,33 @@ static void * __init __alloc_bootmem_core (bootmem_data_t *bdata,
 		}
 		start = i;
 		goto found;
-	fail_block:;
+	fail_block:
+		;
 	}
+
 	if (preferred) {
 		preferred = offset;
 		goto restart_scan;
 	}
 	return NULL;
+
 found:
-	if (start >= eidx)
-		BUG();
+	bdata->last_success = start << PAGE_SHIFT;
+	BUG_ON(start >= eidx);
 
 	/*
 	 * Is the next page of the previous allocation-end the start
 	 * of this allocation's buffer? If yes then we can 'merge'
 	 * the previous partial page with this allocation.
 	 */
-	if (align < PAGE_SIZE
-	    && bdata->last_offset && bdata->last_pos+1 == start) {
+	if (align < PAGE_SIZE &&
+	    bdata->last_offset && bdata->last_pos+1 == start) {
 		offset = (bdata->last_offset+align-1) & ~(align-1);
-		if (offset > PAGE_SIZE)
-			BUG();
+		BUG_ON(offset > PAGE_SIZE);
 		remaining_size = PAGE_SIZE-offset;
 		if (size < remaining_size) {
 			areasize = 0;
-			// last_pos unchanged
+			/* last_pos unchanged */
 			bdata->last_offset = offset+size;
 			ret = phys_to_virt(bdata->last_pos*PAGE_SIZE + offset +
 						bdata->node_boot_start);
@@ -231,11 +238,12 @@ static void * __init __alloc_bootmem_core (bootmem_data_t *bdata,
 		bdata->last_offset = size & ~PAGE_MASK;
 		ret = phys_to_virt(start * PAGE_SIZE + bdata->node_boot_start);
 	}
+
 	/*
 	 * Reserve the area now:
 	 */
 	for (i = start; i < start+areasize; i++)
-		if (test_and_set_bit(i, bdata->node_bootmem_map))
+		if (unlikely(test_and_set_bit(i, bdata->node_bootmem_map)))
 			BUG();
 	memset(ret, 0, size);
 	return ret;
@@ -268,7 +276,7 @@ static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
 			}
 		} else {
 			i+=BITS_PER_LONG;
-			page+=BITS_PER_LONG; 
+			page += BITS_PER_LONG;
 		}
 	}
 	total += count;