LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Mel Gorman <mel@csn.ul.ie>
To: Andi Kleen <andi@firstfloor.org>
Cc: linux-kernel@vger.kernel.org, pj@sgi.com, linux-mm@kvack.org,
	nickpiggin@yahoo.com.au
Subject: Re: [PATCH] [12/18] Add support to allocate hugetlb pages that are larger than MAX_ORDER
Date: Tue, 18 Mar 2008 16:27:14 +0000	[thread overview]
Message-ID: <20080318162714.GL23866@csn.ul.ie> (raw)
In-Reply-To: <20080317015826.110AA1B41E0@basil.firstfloor.org>

On (17/03/08 02:58), Andi Kleen didst pronounce:
> This is needed on x86-64 to handle GB pages in hugetlbfs, because it is
> not practical to enlarge MAX_ORDER to 1GB. 
> 
> Instead the 1GB pages are only allocated at boot using the bootmem
> allocator using the hugepages=... option.
> 
> These 1G bootmem pages are never freed. In theory it would be possible
> to implement that with some complications, but since it would be a one-way
> street (> MAX_ORDER pages cannot be allocated later) I decided not to currently.
> 
> The > MAX_ORDER code is not ifdef'ed per architecture. It is not very big
> and the ifdef uglyness seemed not be worth it.
> 
> Known problems: /proc/meminfo and "free" do not display the memory 
> allocated for gb pages in "Total". This is a little confusing for the
> user.
> 
> Signed-off-by: Andi Kleen <ak@suse.de>
> 
> ---
>  mm/hugetlb.c |   64 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 62 insertions(+), 2 deletions(-)
> 
> Index: linux/mm/hugetlb.c
> ===================================================================
> --- linux.orig/mm/hugetlb.c
> +++ linux/mm/hugetlb.c
> @@ -14,6 +14,7 @@
>  #include <linux/mempolicy.h>
>  #include <linux/cpuset.h>
>  #include <linux/mutex.h>
> +#include <linux/bootmem.h>
>  
>  #include <asm/page.h>
>  #include <asm/pgtable.h>
> @@ -153,7 +154,7 @@ static void free_huge_page(struct page *
>  	INIT_LIST_HEAD(&page->lru);
>  
>  	spin_lock(&hugetlb_lock);
> -	if (h->surplus_huge_pages_node[nid]) {
> +	if (h->surplus_huge_pages_node[nid] && h->order <= MAX_ORDER) {
>  		update_and_free_page(h, page);
>  		h->surplus_huge_pages--;
>  		h->surplus_huge_pages_node[nid]--;
> @@ -215,6 +216,9 @@ static struct page *alloc_fresh_huge_pag
>  {
>  	struct page *page;
>  
> +	if (h->order > MAX_ORDER)
> +		return NULL;
> +

Should this print out a KERN_INFO message to the effect that pages of
that size must be reserved at boot-time?

>  	page = alloc_pages_node(nid,
>  		htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|__GFP_NOWARN,
>  			huge_page_order(h));
> @@ -271,6 +275,9 @@ static struct page *alloc_buddy_huge_pag
>  	struct page *page;
>  	unsigned int nid;
>  
> +	if (h->order > MAX_ORDER)
> +		return NULL;
> +
>  	/*
>  	 * Assume we will successfully allocate the surplus page to
>  	 * prevent racing processes from causing the surplus to exceed
> @@ -422,6 +429,10 @@ return_unused_surplus_pages(struct hstat
>  	/* Uncommit the reservation */
>  	h->resv_huge_pages -= unused_resv_pages;
>  
> +	/* Cannot return gigantic pages currently */
> +	if (h->order > MAX_ORDER)
> +		return;
> +
>  	nr_pages = min(unused_resv_pages, h->surplus_huge_pages);
>  
>  	while (nr_pages) {
> @@ -499,6 +510,44 @@ static struct page *alloc_huge_page(stru
>  	return page;
>  }
>  
> +static __initdata LIST_HEAD(huge_boot_pages);
> +
> +struct huge_bm_page {
> +	struct list_head list;
> +	struct hstate *hstate;
> +};
> +
> +static int __init alloc_bm_huge_page(struct hstate *h)
> +{
> +	struct huge_bm_page *m;
> +	m = __alloc_bootmem_node_nopanic(NODE_DATA(h->hugetlb_next_nid),
> +					huge_page_size(h), huge_page_size(h),
> +					0);
> +	if (!m)
> +		return 0;
> +	BUG_ON((unsigned long)virt_to_phys(m) & (huge_page_size(h) - 1));
> +	/* Put them into a private list first because mem_map is not up yet */
> +	list_add(&m->list, &huge_boot_pages);
> +	m->hstate = h;
> +	huge_next_node(h);
> +	return 1;
> +}
> +
> +/* Put bootmem huge pages into the standard lists after mem_map is up */
> +static int __init huge_init_bm(void)
> +{
> +	struct huge_bm_page *m;
> +	list_for_each_entry (m, &huge_boot_pages, list) {
> +		struct page *page = virt_to_page(m);
> +		struct hstate *h = m->hstate;
> +		__ClearPageReserved(page);
> +		prep_compound_page(page, h->order);
> +		huge_new_page(h, page);
> +	}
> +	return 0;
> +}
> +__initcall(huge_init_bm);
> +
>  static int __init hugetlb_init_hstate(struct hstate *h)
>  {
>  	unsigned long i;
> @@ -509,7 +558,10 @@ static int __init hugetlb_init_hstate(st
>  	h->hugetlb_next_nid = first_node(node_online_map);
>  
>  	for (i = 0; i < max_huge_pages[h - hstates]; ++i) {
> -		if (!alloc_fresh_huge_page(h))
> +		if (h->order > MAX_ORDER) {
> +			if (!alloc_bm_huge_page(h))
> +				break;
> +		} else if (!alloc_fresh_huge_page(h))
>  			break;
>  	}
>  	max_huge_pages[h - hstates] = h->free_huge_pages = h->nr_huge_pages = i;
> @@ -581,6 +633,9 @@ static void do_try_to_free_low(struct hs
>  {
>  	int i;
>  
> +	if (h->order > MAX_ORDER)
> +		return;
> +
>  	for (i = 0; i < MAX_NUMNODES; ++i) {
>  		struct page *page, *next;
>  		struct list_head *freel = &h->hugepage_freelists[i];
> @@ -618,6 +673,11 @@ set_max_huge_pages(struct hstate *h, uns
>  
>  	*err = 0;
>  
> +	if (h->order > MAX_ORDER) {
> +		*err = -EINVAL;
> +		return max_huge_pages[h - hstates];
> +	}
> +

Ah, scratch the comment on an earlier patch where I said I cannot see
where err ever gets updated in set_max_huge_pages().

>  	/*
>  	 * Increase the pool size
>  	 * First take pages out of surplus state.  Then make up the
> 

-- 
Mel Gorman
Part-time Phd Student                          Linux Technology Center
University of Limerick                         IBM Dublin Software Lab

  reply	other threads:[~2008-03-19 20:59 UTC|newest]

Thread overview: 76+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-03-17  1:58 [PATCH] [0/18] GB pages hugetlb support Andi Kleen
2008-03-17  1:58 ` [PATCH] [1/18] Convert hugeltlb.c over to pass global state around in a structure Andi Kleen
2008-03-17 20:15   ` Adam Litke
2008-03-18 12:05   ` Mel Gorman
2008-03-17  1:58 ` [PATCH] [2/18] Add basic support for more than one hstate in hugetlbfs Andi Kleen
2008-03-17 20:22   ` Adam Litke
2008-03-17 20:44     ` Andi Kleen
2008-03-18 12:23   ` Mel Gorman
2008-03-23 10:38   ` KOSAKI Motohiro
2008-03-23 11:28     ` Andi Kleen
2008-03-23 11:30       ` KOSAKI Motohiro
2008-03-17  1:58 ` [PATCH] [3/18] Convert /proc output code over to report multiple hstates Andi Kleen
2008-03-18 12:28   ` Mel Gorman
2008-03-17  1:58 ` [PATCH] [4/18] Add basic support for more than one hstate in hugetlbfs Andi Kleen
2008-03-17  8:09   ` Paul Jackson
2008-03-17  8:15     ` Andi Kleen
2008-03-17 20:28   ` Adam Litke
2008-03-18 14:11   ` Mel Gorman
2008-03-17  1:58 ` [PATCH] [5/18] Expand the hugetlbfs sysctls to handle arrays for all hstates Andi Kleen
2008-03-18 14:34   ` Mel Gorman
2008-03-18 16:49     ` Andi Kleen
2008-03-18 17:01       ` Mel Gorman
2008-03-17  1:58 ` [PATCH] [6/18] Add support to have individual hstates for each hugetlbfs mount Andi Kleen
2008-03-18 14:10   ` Adam Litke
2008-03-18 15:02   ` Mel Gorman
2008-03-17  1:58 ` [PATCH] [7/18] Abstract out the NUMA node round robin code into a separate function Andi Kleen
2008-03-18 15:42   ` Mel Gorman
2008-03-18 15:47     ` Andi Kleen
2008-03-18 16:04       ` Mel Gorman
2008-03-17  1:58 ` [PATCH] [8/18] Add a __alloc_bootmem_node_nopanic Andi Kleen
2008-03-18 15:54   ` Mel Gorman
2008-03-17  1:58 ` [PATCH] [9/18] Export prep_compound_page to the hugetlb allocator Andi Kleen
2008-03-17  1:58 ` [PATCH] [10/18] Factor out new huge page preparation code into separate function Andi Kleen
2008-03-17 20:31   ` Adam Litke
2008-03-18 16:02   ` Mel Gorman
2008-03-17  1:58 ` [PATCH] [11/18] Fix alignment bug in bootmem allocator Andi Kleen
2008-03-17  2:19   ` Yinghai Lu
2008-03-17  7:02     ` Andi Kleen
2008-03-17  7:17       ` Yinghai Lu
2008-03-17  7:31         ` Yinghai Lu
2008-03-17  7:41           ` Andi Kleen
2008-03-17  7:53             ` Yinghai Lu
2008-03-17  8:10               ` Yinghai Lu
2008-03-17  8:17                 ` Andi Kleen
2008-03-17  8:56               ` Andi Kleen
2008-03-17 18:52                 ` Yinghai Lu
2008-03-17 21:27                   ` Yinghai Lu
2008-03-18  2:06                     ` Yinghai Lu
2008-03-18 16:18   ` Mel Gorman
2008-03-17  1:58 ` [PATCH] [12/18] Add support to allocate hugetlb pages that are larger than MAX_ORDER Andi Kleen
2008-03-18 16:27   ` Mel Gorman [this message]
2008-04-09 16:05   ` Andrew Hastings
2008-04-09 17:56     ` Andi Kleen
2008-03-17  1:58 ` [PATCH] [13/18] Add support to allocate hugepages of different size with hugepages= Andi Kleen
2008-03-18 16:32   ` Mel Gorman
2008-03-18 16:45     ` Andi Kleen
2008-03-18 16:46       ` Mel Gorman
2008-03-17  1:58 ` [PATCH] [14/18] Clean up hugetlb boot time printk Andi Kleen
2008-03-18 16:37   ` Mel Gorman
2008-03-17  1:58 ` [PATCH] [15/18] Add support to x86-64 to allocate and lookup GB pages in hugetlb Andi Kleen
2008-03-17  1:58 ` [PATCH] [16/18] Add huge pud support to hugetlbfs Andi Kleen
2008-03-17  1:58 ` [PATCH] [17/18] Add huge pud support to mm/memory.c Andi Kleen
2008-03-17  1:58 ` [PATCH] [18/18] Implement hugepagesz= option for x86-64 Andi Kleen
2008-03-17  9:29   ` Paul Jackson
2008-03-17  9:59     ` Andi Kleen
2008-03-17 10:02       ` Paul Jackson
2008-03-17  3:11 ` [PATCH] [0/18] GB pages hugetlb support Paul Jackson
2008-03-17  7:00   ` Andi Kleen
2008-03-17  7:00     ` Paul Jackson
2008-03-17  7:29       ` Andi Kleen
2008-03-17  5:35 ` Paul Jackson
2008-03-17  6:58   ` Andi Kleen
2008-03-17  9:26 ` Paul Jackson
2008-03-17 15:05 ` Adam Litke
2008-03-17 15:33   ` Andi Kleen
2008-03-17 15:59     ` Adam Litke

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20080318162714.GL23866@csn.ul.ie \
    --to=mel@csn.ul.ie \
    --cc=andi@firstfloor.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=nickpiggin@yahoo.com.au \
    --cc=pj@sgi.com \
    --subject='Re: [PATCH] [12/18] Add support to allocate hugetlb pages that are larger than MAX_ORDER' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).