LKML Archive on lore.kernel.org help / color / mirror / Atom feed
From: Greg KH <gregkh@suse.de> To: linux-kernel@vger.kernel.org, stable@kernel.org Cc: Justin Forbes <jmforbes@linuxtx.org>, Zwane Mwaikambo <zwane@arm.linux.org.uk>, "Theodore Ts'o" <tytso@mit.edu>, Randy Dunlap <rdunlap@xenotime.net>, Dave Jones <davej@redhat.com>, Chuck Wolber <chuckw@quantumlinux.com>, Chris Wedgwood <reviews@ml.cw.f00f.org>, Michael Krufky <mkrufky@linuxtv.org>, Chuck Ebbert <cebbert@redhat.com>, Domenico Andreoli <cavokz@gmail.com>, Willy Tarreau <w@1wt.eu>, Rodrigo Rubira Branco <rbranco@la.checkpoint.com>, Jake Edge <jake@lwn.net>, Eugene Teo <eteo@redhat.com>, torvalds@linux-foundation.org, akpm@linux-foundation.org, alan@lxorguk.ukuu.org.uk, Andy Whitcroft <apw@shadowen.org>, Jon Tollefson <kniht@linux.vnet.ibm.com>, Mel Gorman <mel@csn.ul.ie>, Nick Piggin <nickpiggin@yahoo.com.au>, Christoph Lameter <cl@linux-foundation.org> Subject: [patch 08/49] hugetlb: pull gigantic page initialisation out of the default path Date: Tue, 11 Nov 2008 16:23:07 -0800 [thread overview] Message-ID: <20081112002307.GI10989@kroah.com> (raw) In-Reply-To: <20081112002215.GA10989@kroah.com> [-- Attachment #1: hugetlb-pull-gigantic-page-initialisation-out-of-the-default-path.patch --] [-- Type: text/plain, Size: 4054 bytes --] 2.6.27-stable review patch. If anyone has any objections, please let us know. ------------------ From: Andy Whitcroft <apw@shadowen.org> commit 18229df5b613ed0732a766fc37850de2e7988e43 upstream As we can determine exactly when a gigantic page is in use we can optimise the common regular page cases by pulling out gigantic page initialisation into its own function. As gigantic pages are never released to buddy we do not need a destructor. This effectivly reverts the previous change to the main buddy allocator. It also adds a paranoid check to ensure we never release gigantic pages from hugetlbfs to the main buddy. Signed-off-by: Andy Whitcroft <apw@shadowen.org> Cc: Jon Tollefson <kniht@linux.vnet.ibm.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Christoph Lameter <cl@linux-foundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> --- mm/hugetlb.c | 12 +++++++++++- mm/internal.h | 1 + mm/page_alloc.c | 28 +++++++++++++++++++++------- 3 files changed, 33 insertions(+), 8 deletions(-) --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -455,6 +455,8 @@ static void update_and_free_page(struct { int i; + VM_BUG_ON(h->order >= MAX_ORDER); + h->nr_huge_pages--; h->nr_huge_pages_node[page_to_nid(page)]--; for (i = 0; i < pages_per_huge_page(h); i++) { @@ -969,6 +971,14 @@ found: return 1; } +static void prep_compound_huge_page(struct page *page, int order) +{ + if (unlikely(order > (MAX_ORDER - 1))) + prep_compound_gigantic_page(page, order); + else + prep_compound_page(page, order); +} + /* Put bootmem huge pages into the standard lists after mem_map is up */ static void __init gather_bootmem_prealloc(void) { @@ -979,7 +989,7 @@ static void __init gather_bootmem_preall struct hstate *h = m->hstate; __ClearPageReserved(page); WARN_ON(page_count(page) != 1); - prep_compound_page(page, h->order); + prep_compound_huge_page(page, h->order); prep_new_huge_page(h, page, page_to_nid(page)); } } --- a/mm/internal.h +++ b/mm/internal.h @@ -17,6 +17,7 @@ void free_pgtables(struct mmu_gather *tl unsigned long floor, unsigned long ceiling); extern void prep_compound_page(struct page *page, unsigned long order); +extern void prep_compound_gigantic_page(struct page *page, unsigned long order); static inline void set_page_count(struct page *page, int v) { --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -268,24 +268,39 @@ void prep_compound_page(struct page *pag { int i; int nr_pages = 1 << order; + + set_compound_page_dtor(page, free_compound_page); + set_compound_order(page, order); + __SetPageHead(page); + for (i = 1; i < nr_pages; i++) { + struct page *p = page + i; + + __SetPageTail(p); + p->first_page = page; + } +} + +#ifdef CONFIG_HUGETLBFS +void prep_compound_gigantic_page(struct page *page, unsigned long order) +{ + int i; + int nr_pages = 1 << order; struct page *p = page + 1; set_compound_page_dtor(page, free_compound_page); set_compound_order(page, order); __SetPageHead(page); - for (i = 1; i < nr_pages; i++, p++) { - if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0)) - p = pfn_to_page(page_to_pfn(page) + i); + for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { __SetPageTail(p); p->first_page = page; } } +#endif static void destroy_compound_page(struct page *page, unsigned long order) { int i; int nr_pages = 1 << order; - struct page *p = page + 1; if (unlikely(compound_order(page) != order)) bad_page(page); @@ -293,9 +308,8 @@ static void destroy_compound_page(struct if (unlikely(!PageHead(page))) bad_page(page); __ClearPageHead(page); - for (i = 1; i < nr_pages; i++, p++) { - if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0)) - p = pfn_to_page(page_to_pfn(page) + i); + for (i = 1; i < nr_pages; i++) { + struct page *p = page + i; if (unlikely(!PageTail(p) | (p->first_page != page))) --
next prev parent reply other threads:[~2008-11-12 0:29 UTC|newest] Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top [not found] <20081112001401.926965113@mini.kroah.org> 2008-11-12 0:22 ` [patch 00/49] 2.6.27.5 stable review Greg KH 2008-11-12 0:22 ` [patch 01/49] ext3: wait on all pending commits in ext3_sync_fs Greg KH 2008-11-12 0:22 ` [patch 02/49] x86: add DMI quirk for AMI BIOS which corrupts address 0xc000 during resume Greg KH 2008-11-12 0:22 ` [patch 03/49] x86: reserve low 64K on AMI and Phoenix BIOS boxen Greg KH 2008-11-12 0:22 ` [patch 04/49] x86: add X86_RESERVE_LOW_64K Greg KH 2008-11-12 0:23 ` [patch 05/49] x86: fix CONFIG_X86_RESERVE_LOW_64K=y Greg KH 2008-11-12 0:23 ` [patch 06/49] x86: fix macro with bad_bios_dmi_table Greg KH 2008-11-12 0:23 ` [patch 07/49] cgroups: fix invalid cgrp->dentry before cgroup has been completely removed Greg KH 2008-11-12 0:23 ` Greg KH [this message] 2008-11-12 0:23 ` [patch 09/49] hugetlbfs: handle pages higher order than MAX_ORDER Greg KH 2008-11-12 0:23 ` [patch 10/49] cciss: fix regression firmware not displayed in procfs Greg KH 2008-11-12 0:23 ` [patch 11/49] cciss: fix sysfs broken symlink regression Greg KH 2008-11-12 0:23 ` [patch 12/49] cciss: new hardware support Greg KH 2008-11-12 0:23 ` [patch 13/49] md: linear: Fix a division by zero bug for very small arrays Greg KH 2008-11-12 0:23 ` [patch 14/49] md: fix bug in raid10 recovery Greg KH 2008-11-12 0:23 ` [patch 15/49] JFFS2: fix race condition in jffs2_lzo_compress() Greg KH 2008-11-12 0:23 ` [patch 16/49] JFFS2: Fix lack of locking in thread_should_wake() Greg KH 2008-11-12 0:23 ` [patch 17/49] ARM: xsc3: fix xsc3_l2_inv_range Greg KH 2008-11-12 0:23 ` [patch 18/49] MTD: Fix cfi_send_gen_cmd handling of x16 devices in x8 mode (v4) Greg KH 2008-11-12 0:23 ` [patch 19/49] x86: dont use tsc_khz to calculate lpj if notsc is passed Greg KH 2008-11-12 0:23 ` [patch 20/49] net: unix: fix inflight counting bug in garbage collector Greg KH 2008-11-12 0:23 ` [patch 21/49] r8169: get ethtool settings through the generic mii helper Greg KH 2008-11-12 0:23 ` [patch 22/49] r8169: fix RxMissed register access Greg KH 2008-11-12 0:23 ` [patch 23/49] r8169: wake up the PHY of the 8168 Greg KH 2008-11-12 0:23 ` [patch 24/49] I/OAT: fix channel resources free for not allocated channels Greg KH 2008-11-12 0:23 ` [patch 25/49] I/OAT: fix dma_pin_iovec_pages() error handling Greg KH 2008-11-12 0:23 ` [patch 26/49] I/OAT: fix async_tx.callback checking Greg KH 2008-11-12 0:23 ` [patch 27/49] dca: fixup initialization dependency Greg KH 2008-11-12 0:23 ` [patch 28/49] iwlwifi: allow consecutive scans in unassociated state Greg KH 2008-11-12 0:23 ` [patch 29/49] iwlwifi: allow association on radar channel in power save Greg KH 2008-11-12 0:23 ` [patch 30/49] iwlwifi: remove HT flags from RXON when not in HT anymore Greg KH 2008-11-12 0:23 ` [patch 31/49] iwlwifi: dont fail if scan is issued too early Greg KH 2008-11-12 0:24 ` [patch 32/49] iwlwifi: use correct DMA_MASK Greg KH 2008-11-12 0:24 ` [patch 33/49] iwlwifi: fix suspend to RAM in iwlwifi Greg KH 2008-11-12 0:24 ` [patch 34/49] iwlwifi: generic init calibrations framework Greg KH 2008-11-12 0:24 ` [patch 35/49] zd1211rw: Add 2 device IDs Greg KH 2008-11-12 0:24 ` [patch 36/49] iwl3945: fix deadlock on suspend Greg KH 2008-11-12 0:24 ` [patch 37/49] iwl3945: do not send scan command if channel count zero Greg KH 2008-11-12 0:24 ` [patch 38/49] cpqarry: fix return value of cpqarray_init() Greg KH 2008-11-12 0:24 ` [patch 39/49] ACPI: dock: avoid check _STA method Greg KH 2008-11-12 0:24 ` [patch 40/49] ARM: 5300/1: fixup spitz reset during boot Greg KH 2008-11-12 0:24 ` [patch 41/49] KEYS: Make request key instantiate the per-user keyrings Greg KH 2008-11-12 0:24 ` [patch 42/49] libata: fix last_reset timestamp handling Greg KH 2008-11-12 0:24 ` [patch 43/49] ALSA: hda: make a STAC_DELL_EQ option Greg KH 2008-11-12 0:24 ` [patch 44/49] Fix __pfn_to_page(pfn) for CONFIG_DISCONTIGMEM=y Greg KH 2008-11-12 0:24 ` [patch 45/49] mmc: increase SD write timeout for crappy cards Greg KH 2008-11-12 0:24 ` [patch 46/49] hfsplus: fix Buffer overflow with a corrupted image (CVE-2008-4933) Greg KH 2008-11-12 0:24 ` [patch 47/49] hfsplus: check read_mapping_page() return value (CVE-2008-4934) Greg KH 2008-11-12 0:24 ` [patch 48/49] hfs: fix namelength memory corruption (CVE-2008-5025) Greg KH 2008-11-12 0:24 ` [patch 49/49] HID: fix incorrent length condition in hidraw_write() Greg KH 2008-11-12 0:44 ` [patch 00/49] 2.6.27.5 stable review Gabriel C 2008-11-12 1:07 ` Greg KH 2008-11-12 0:54 ` Willy Tarreau 2008-11-12 14:08 ` Frans Pop 2008-11-12 17:03 ` [stable] " Greg KH 2008-11-13 22:07 ` Greg KH
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=20081112002307.GI10989@kroah.com \ --to=gregkh@suse.de \ --cc=akpm@linux-foundation.org \ --cc=alan@lxorguk.ukuu.org.uk \ --cc=apw@shadowen.org \ --cc=cavokz@gmail.com \ --cc=cebbert@redhat.com \ --cc=chuckw@quantumlinux.com \ --cc=cl@linux-foundation.org \ --cc=davej@redhat.com \ --cc=eteo@redhat.com \ --cc=jake@lwn.net \ --cc=jmforbes@linuxtx.org \ --cc=kniht@linux.vnet.ibm.com \ --cc=linux-kernel@vger.kernel.org \ --cc=mel@csn.ul.ie \ --cc=mkrufky@linuxtv.org \ --cc=nickpiggin@yahoo.com.au \ --cc=rbranco@la.checkpoint.com \ --cc=rdunlap@xenotime.net \ --cc=reviews@ml.cw.f00f.org \ --cc=stable@kernel.org \ --cc=torvalds@linux-foundation.org \ --cc=tytso@mit.edu \ --cc=w@1wt.eu \ --cc=zwane@arm.linux.org.uk \ /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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
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).