| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20090908113734.869cdad7.kamezawa.hiroyu@jp.fujitsu.com>
Date: Tue, 8 Sep 2009 11:37:34 +0900
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
To: Hugh Dickins <hugh.dickins@...cali.co.uk>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Nick Piggin <npiggin@...e.de>, Rik van Riel <riel@...hat.com>,
linux-kernel@...r.kernel.org, linux-mm@...ck.org
Subject: Re: [PATCH 7/8] mm: reinstate ZERO_PAGE
On Mon, 7 Sep 2009 22:39:34 +0100 (BST)
Hugh Dickins <hugh.dickins@...cali.co.uk> wrote:
> KAMEZAWA Hiroyuki has observed customers of earlier kernels taking
> advantage of the ZERO_PAGE: which we stopped do_anonymous_page() from
> using in 2.6.24. And there were a couple of regression reports on LKML.
>
> Following suggestions from Linus, reinstate do_anonymous_page() use of
> the ZERO_PAGE; but this time avoid dirtying its struct page cacheline
> with (map)count updates - let vm_normal_page() regard it as abnormal.
>
> Use it only on arches which __HAVE_ARCH_PTE_SPECIAL (x86, s390, sh32,
> most powerpc): that's not essential, but minimizes additional branches
> (keeping them in the unlikely pte_special case); and incidentally
> excludes mips (some models of which needed eight colours of ZERO_PAGE
> to avoid costly exceptions).
>
> Don't be fanatical about avoiding ZERO_PAGE updates: get_user_pages()
> callers won't want to make exceptions for it, so increment its count
> there. Changes to mlock and migration? happily seems not needed.
>
> In most places it's quicker to check pfn than struct page address:
> prepare a __read_mostly zero_pfn for that. Does get_dump_page()
> still need its ZERO_PAGE check? probably not, but keep it anyway.
>
> Signed-off-by: Hugh Dickins <hugh.dickins@...cali.co.uk>
A nitpick but this was a concern you shown, IIUC.
== __get_user_pages()..
if (pages) {
pages[i] = page;
flush_anon_page(vma, page, start);
flush_dcache_page(page);
}
==
This part will call flush_dcache_page() even when ZERO_PAGE is found.
Don't we need to mask this ?
Thanks,
-Kame
> ---
> I have not studied the performance of this at all: I'd rather it go
> into mmotm where others may decide whether it's a good thing or not.
>
> mm/memory.c | 53 +++++++++++++++++++++++++++++++++++++++++---------
> 1 file changed, 44 insertions(+), 9 deletions(-)
>
> --- mm6/mm/memory.c 2009-09-07 13:16:53.000000000 +0100
> +++ mm7/mm/memory.c 2009-09-07 13:17:01.000000000 +0100
> @@ -107,6 +107,17 @@ static int __init disable_randmaps(char
> }
> __setup("norandmaps", disable_randmaps);
>
> +static unsigned long zero_pfn __read_mostly;
> +
> +/*
> + * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
> + */
> +static int __init init_zero_pfn(void)
> +{
> + zero_pfn = page_to_pfn(ZERO_PAGE(0));
> + return 0;
> +}
> +core_initcall(init_zero_pfn);
>
> /*
> * If a p?d_bad entry is found while walking page tables, report
> @@ -499,7 +510,9 @@ struct page *vm_normal_page(struct vm_ar
> if (HAVE_PTE_SPECIAL) {
> if (likely(!pte_special(pte)))
> goto check_pfn;
> - if (!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)))
> + if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
> + return NULL;
> + if (pfn != zero_pfn)
> print_bad_pte(vma, addr, pte, NULL);
> return NULL;
> }
> @@ -1144,9 +1157,14 @@ struct page *follow_page(struct vm_area_
> goto no_page;
> if ((flags & FOLL_WRITE) && !pte_write(pte))
> goto unlock;
> +
> page = vm_normal_page(vma, address, pte);
> - if (unlikely(!page))
> - goto bad_page;
> + if (unlikely(!page)) {
> + if ((flags & FOLL_DUMP) ||
> + pte_pfn(pte) != zero_pfn)
> + goto bad_page;
> + page = pte_page(pte);
> + }
>
> if (flags & FOLL_GET)
> get_page(page);
> @@ -2085,10 +2103,19 @@ gotten:
>
> if (unlikely(anon_vma_prepare(vma)))
> goto oom;
> - VM_BUG_ON(old_page == ZERO_PAGE(0));
> - new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
> - if (!new_page)
> - goto oom;
> +
> + if (pte_pfn(orig_pte) == zero_pfn) {
> + new_page = alloc_zeroed_user_highpage_movable(vma, address);
> + if (!new_page)
> + goto oom;
> + } else {
> + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
> + if (!new_page)
> + goto oom;
> + cow_user_page(new_page, old_page, address, vma);
> + }
> + __SetPageUptodate(new_page);
> +
> /*
> * Don't let another task, with possibly unlocked vma,
> * keep the mlocked page.
> @@ -2098,8 +2125,6 @@ gotten:
> clear_page_mlock(old_page);
> unlock_page(old_page);
> }
> - cow_user_page(new_page, old_page, address, vma);
> - __SetPageUptodate(new_page);
>
> if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
> goto oom_free_new;
> @@ -2594,6 +2619,15 @@ static int do_anonymous_page(struct mm_s
> spinlock_t *ptl;
> pte_t entry;
>
> + if (HAVE_PTE_SPECIAL && !(flags & FAULT_FLAG_WRITE)) {
> + entry = pte_mkspecial(pfn_pte(zero_pfn, vma->vm_page_prot));
> + ptl = pte_lockptr(mm, pmd);
> + spin_lock(ptl);
> + if (!pte_none(*page_table))
> + goto unlock;
> + goto setpte;
> + }
> +
> /* Allocate our own private page. */
> pte_unmap(page_table);
>
> @@ -2617,6 +2651,7 @@ static int do_anonymous_page(struct mm_s
>
> inc_mm_counter(mm, anon_rss);
> page_add_new_anon_rmap(page, vma, address);
> +setpte:
> set_pte_at(mm, address, page_table, entry);
>
> /* No need to invalidate - it was non-present before */
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists