Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759438AbXKHA72 (ORCPT ); Wed, 7 Nov 2007 19:59:28 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752204AbXKHA7U (ORCPT ); Wed, 7 Nov 2007 19:59:20 -0500 Received: from mga02.intel.com ([134.134.136.20]:50157 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751419AbXKHA7S (ORCPT ); Wed, 7 Nov 2007 19:59:18 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.21,387,1188802800"; d="scan'208";a="265457899" Subject: Patch]Add strict_goal parameter to __alloc_bootmem_core From: Zou Nan hai To: LKML Cc: Linus Torvalds , Greg KH , Dave Jones , Martin Ebourne , Suresh Siddha , Andi Kleen , Andrew Morton , Christoph Lameter , Mel Gorman , Andy Whitcroft Content-Type: text/plain Organization: Message-Id: <1194483110.3046.1469.camel@linux-znh> Mime-Version: 1.0 X-Mailer: Ximian Evolution 1.2.2 (1.2.2-4) Date: 08 Nov 2007 08:51:50 +0800 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4690 Lines: 133 Resend the patch for more people to review. If __alloc_bootmem_core was given a goal, it will first try to allocate memory above that goal. If failed, it will try from the low pages. Sometimes we don't want this behavior, we want the goal to be strict. This patch introduce a strict_goal parameter to __alloc_bootmem_core, If strict_goal is set, __alloc_bootmem_core will return NULL to indicate it can't allocate memory above that goal. Note we do not scan from last_success if strict_goal is set, it will scan from the beginning of the goal instead We skip this optimization to keep the code simple because strict_goal is not supposed to be used in hot path. Signed-off-by: Zou Nan hai Signed-off-by: Suresh Siddha diff -Nraup a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c --- a/arch/x86/mm/numa_64.c 2007-10-24 11:50:57.000000000 +0800 +++ b/arch/x86/mm/numa_64.c 2007-11-07 13:06:50.000000000 +0800 @@ -247,7 +247,7 @@ void __init setup_node_zones(int nodeid) __alloc_bootmem_core(NODE_DATA(nodeid)->bdata, memmapsize, SMP_CACHE_BYTES, round_down(limit - memmapsize, PAGE_SIZE), - limit); + limit, 1); #endif } diff -Nraup a/include/linux/bootmem.h b/include/linux/bootmem.h --- a/include/linux/bootmem.h 2007-11-07 13:06:35.000000000 +0800 +++ b/include/linux/bootmem.h 2007-11-07 13:06:04.000000000 +0800 @@ -58,7 +58,8 @@ extern void *__alloc_bootmem_core(struct unsigned long size, unsigned long align, unsigned long goal, - unsigned long limit); + unsigned long limit, + int strict_goal); #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE extern void reserve_bootmem(unsigned long addr, unsigned long size); diff -Nraup a/mm/bootmem.c b/mm/bootmem.c --- a/mm/bootmem.c 2007-11-07 13:06:35.000000000 +0800 +++ b/mm/bootmem.c 2007-11-07 13:06:18.000000000 +0800 @@ -179,7 +179,7 @@ static void __init free_bootmem_core(boo */ void * __init __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size, - unsigned long align, unsigned long goal, unsigned long limit) + unsigned long align, unsigned long goal, unsigned long limit, int strict_goal) { unsigned long offset, remaining_size, areasize, preferred; unsigned long i, start = 0, incr, eidx, end_pfn; @@ -212,15 +212,20 @@ __alloc_bootmem_core(struct bootmem_data /* * 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; + * if the goal is not strict. + */ + + preferred = 0; + if (goal) { + if (goal >= bdata->node_boot_start && PFN_DOWN(goal) < end_pfn) { + preferred = goal - bdata->node_boot_start; if (bdata->last_success >= preferred) - if (!limit || (limit && limit > bdata->last_success)) + if (!strict_goal && (!limit || (limit && limit > bdata->last_success))) preferred = bdata->last_success; - } else - preferred = 0; + } else if (strict_goal) + return NULL; + } preferred = PFN_DOWN(ALIGN(preferred, align)) + offset; areasize = (size + PAGE_SIZE-1) / PAGE_SIZE; @@ -247,7 +252,7 @@ restart_scan: i = ALIGN(j, incr); } - if (preferred > offset) { + if (preferred > offset && !strict_goal) { preferred = offset; goto restart_scan; } @@ -421,7 +426,7 @@ void * __init __alloc_bootmem_nopanic(un 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, 0); if (ptr) return ptr; } @@ -449,7 +454,7 @@ void * __init __alloc_bootmem_node(pg_da { void *ptr; - ptr = __alloc_bootmem_core(pgdat->bdata, size, align, goal, 0); + ptr = __alloc_bootmem_core(pgdat->bdata, size, align, goal, 0, 0); if (ptr) return ptr; @@ -468,7 +473,7 @@ void * __init __alloc_bootmem_low(unsign list_for_each_entry(bdata, &bdata_list, list) { ptr = __alloc_bootmem_core(bdata, size, align, goal, - ARCH_LOW_ADDRESS_LIMIT); + ARCH_LOW_ADDRESS_LIMIT, 0); if (ptr) return ptr; } @@ -485,5 +490,5 @@ void * __init __alloc_bootmem_low_node(p unsigned long align, unsigned long goal) { return __alloc_bootmem_core(pgdat->bdata, size, align, goal, - ARCH_LOW_ADDRESS_LIMIT); + ARCH_LOW_ADDRESS_LIMIT, 0); } - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/