From: Greg KH <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: torvalds@linux-foundation.org, akpm@linux-foundation.org,
alan@lxorguk.ukuu.org.uk, Tejun Heo <tj@kernel.org>,
Yanmin Zhang <yanmin.zhang@intel.com>,
ShuoX Liu <shuox.liu@intel.com>, "H. Peter Anvin" <hpa@zytor.com>
Subject: [ 04/54] percpu, x86: dont use PMD_SIZE as embedded atom_size on 32bit
Date: Fri, 18 May 2012 14:16:03 -0700 [thread overview]
Message-ID: <20120518211559.805734534@linuxfoundation.org> (raw)
In-Reply-To: <20120518212656.GA4992@kroah.com>
3.0-stable review patch. If anyone has any objections, please let me know.
------------------
From: Tejun Heo <tj@kernel.org>
commit d5e28005a1d2e67833852f4c9ea8ec206ea3ff85 upstream.
With the embed percpu first chunk allocator, x86 uses either PAGE_SIZE
or PMD_SIZE for atom_size. PMD_SIZE is used when CPU supports PSE so
that percpu areas are aligned to PMD mappings and possibly allow using
PMD mappings in vmalloc areas in the future. Using larger atom_size
doesn't waste actual memory; however, it does require larger vmalloc
space allocation later on for !first chunks.
With reasonably sized vmalloc area, PMD_SIZE shouldn't be a problem
but x86_32 at this point is anything but reasonable in terms of
address space and using larger atom_size reportedly leads to frequent
percpu allocation failures on certain setups.
As there is no reason to not use PMD_SIZE on x86_64 as vmalloc space
is aplenty and most x86_64 configurations support PSE, fix the issue
by always using PMD_SIZE on x86_64 and PAGE_SIZE on x86_32.
v2: drop cpu_has_pse test and make x86_64 always use PMD_SIZE and
x86_32 PAGE_SIZE as suggested by hpa.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Yanmin Zhang <yanmin.zhang@intel.com>
Reported-by: ShuoX Liu <shuox.liu@intel.com>
Acked-by: H. Peter Anvin <hpa@zytor.com>
LKML-Reference: <4F97BA98.6010001@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/x86/kernel/setup_percpu.c | 14 +++++++++++++-
1 file changed, 13 insertions(+), 1 deletion(-)
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -185,10 +185,22 @@ void __init setup_per_cpu_areas(void)
#endif
rc = -EINVAL;
if (pcpu_chosen_fc != PCPU_FC_PAGE) {
- const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE;
const size_t dyn_size = PERCPU_MODULE_RESERVE +
PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE;
+ size_t atom_size;
+ /*
+ * On 64bit, use PMD_SIZE for atom_size so that embedded
+ * percpu areas are aligned to PMD. This, in the future,
+ * can also allow using PMD mappings in vmalloc area. Use
+ * PAGE_SIZE on 32bit as vmalloc space is highly contended
+ * and large vmalloc area allocs can easily fail.
+ */
+#ifdef CONFIG_X86_64
+ atom_size = PMD_SIZE;
+#else
+ atom_size = PAGE_SIZE;
+#endif
rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
dyn_size, atom_size,
pcpu_cpu_distance,
next prev parent reply other threads:[~2012-05-18 21:16 UTC|newest]
Thread overview: 70+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-05-18 21:26 [ 00/54] 3.0.32-stable review Greg KH
2012-05-18 21:16 ` [ 01/54] smsc95xx: mark link down on startup and let PHY interrupt deal with carrier changes Greg KH
2012-05-18 21:16 ` [ 02/54] xen/pte: Fix crashes when trying to see non-existent PGD/PMD/PUD/PTEs Greg KH
2012-05-18 21:16 ` [ 03/54] xen/pci: dont use PCI BIOS service for configuration space accesses Greg KH
2012-05-18 21:16 ` Greg KH [this message]
2012-05-18 21:16 ` [ 05/54] asm-generic: Use __BITS_PER_LONG in statfs.h Greg KH
2012-05-18 21:16 ` [ 06/54] Fix __read_seqcount_begin() to use ACCESS_ONCE for sequence value read Greg KH
2012-05-18 21:16 ` [ 07/54] ARM: 7410/1: Add extra clobber registers for assembly in kernel_execve Greg KH
2012-05-18 21:16 ` [ 08/54] ARM: 7414/1: SMP: prevent use of the console when using idmap_pgd Greg KH
2012-05-18 21:16 ` [ 09/54] regulator: Fix the logic to ensure new voltage setting in valid range Greg KH
2012-05-18 21:16 ` [ 10/54] ARM: orion5x: Fix GPIO enable bits for MPP9 Greg KH
2012-05-18 21:16 ` [ 11/54] asix: Fix tx transfer padding for full-speed USB Greg KH
2012-05-18 21:16 ` [ 12/54] netem: fix possible skb leak Greg KH
2012-05-18 21:16 ` [ 13/54] net: In unregister_netdevice_notifier unregister the netdevices Greg KH
2012-05-21 17:35 ` Herton Ronaldo Krzesinski
2012-05-27 0:13 ` Greg KH
2012-05-27 0:18 ` David Miller
2012-05-27 0:22 ` Greg KH
2012-05-18 21:16 ` [ 14/54] net: l2tp: unlock socket lock before returning from l2tp_ip_sendmsg Greg KH
2012-05-18 21:16 ` [ 15/54] sky2: propogate rx hash when packet is copied Greg KH
2012-05-18 21:16 ` [ 16/54] sky2: fix receive length error in mixed non-VLAN/VLAN traffic Greg KH
2012-05-18 21:16 ` [ 17/54] tg3: Avoid panic from reserved statblk field access Greg KH
2012-05-18 21:16 ` [ 18/54] sungem: Fix WakeOnLan Greg KH
2012-05-18 21:16 ` [ 19/54] tcp: change tcp_adv_win_scale and tcp_rmem[2] Greg KH
2012-05-18 21:16 ` [ 20/54] sony-laptop: Enable keyboard backlight by default Greg KH
2012-05-18 21:16 ` [ 21/54] ALSA: echoaudio: Remove incorrect part of assertion Greg KH
2012-05-18 21:16 ` [ 22/54] ALSA: HDA: Lessen CPU usage when waiting for chip to respond Greg KH
2012-05-18 21:16 ` [ 23/54] usbnet: fix skb traversing races during unlink(v2) Greg KH
2012-05-18 21:16 ` [ 24/54] namespaces, pid_ns: fix leakage on fork() failure Greg KH
2012-05-18 21:16 ` [ 25/54] sparc64: Do not clobber %g2 in xcall_fetch_glob_regs() Greg KH
2012-05-18 21:16 ` [ 26/54] ARM: prevent VM_GROWSDOWN mmaps extending below FIRST_USER_ADDRESS Greg KH
2012-05-18 21:16 ` [ 27/54] media: rc: Postpone ISR registration Greg KH
2012-05-18 21:16 ` [ 28/54] cdc_ether: Ignore bogus union descriptor for RNDIS devices Greg KH
2012-05-18 21:16 ` [ 29/54] cdc_ether: add Novatel USB551L device IDs for FLAG_WWAN Greg KH
2012-05-18 21:16 ` [ 30/54] percpu: pcpu_embed_first_chunk() should free unused parts after all allocs are complete Greg KH
2012-05-18 21:16 ` [ 31/54] kmemleak: Fix the kmemleak tracking of the percpu areas with !SMP Greg KH
2012-05-19 13:27 ` Christoph Biedl
2012-05-19 14:46 ` Greg KH
2012-05-19 15:45 ` Christoph Biedl
2012-05-19 21:45 ` Catalin Marinas
2012-05-18 21:16 ` [ 32/54] hugetlb: prevent BUG_ON in hugetlb_fault() -> hugetlb_cow() Greg KH
2012-05-18 21:16 ` [ 33/54] mm: nobootmem: fix sign extend problem in __free_pages_memory() Greg KH
2012-05-18 21:16 ` [ 34/54] jffs2: Fix lock acquisition order bug in gc path Greg KH
2012-05-18 21:16 ` [ 35/54] arch/tile: apply commit 74fca9da0 to the compat signal handling as well Greg KH
2012-05-18 21:16 ` [ 36/54] crypto: mv_cesa requires on CRYPTO_HASH to build Greg KH
2012-05-18 21:16 ` [ 37/54] MD: Add del_timer_sync to mddev_suspend (fix nasty panic) Greg KH
2012-05-18 21:16 ` [ 38/54] tcp: do_tcp_sendpages() must try to push data out on oom conditions Greg KH
2012-05-18 21:16 ` [ 39/54] init: dont try mounting device as nfs root unless type fully matches Greg KH
2012-05-18 21:16 ` [ 40/54] ext4: avoid deadlock on sync-mounted FS w/o journal Greg KH
2012-05-18 21:16 ` [ 41/54] NFSv4: Revalidate uid/gid after open Greg KH
2012-05-18 21:16 ` [ 42/54] memcg: free spare array to avoid memory leak Greg KH
2012-05-18 21:16 ` [ 43/54] compat: Fix RT signal mask corruption via sigprocmask Greg KH
2012-05-18 21:16 ` [ 44/54] ext3: Fix error handling on inode bitmap corruption Greg KH
2012-05-18 21:16 ` [ 45/54] ext4: fix " Greg KH
2012-05-18 21:16 ` [ 46/54] ACPI / PM: Add Sony Vaio VPCCW29FX to nonvs blacklist Greg KH
2012-05-18 21:16 ` [ 47/54] SCSI: hpsa: Add IRQF_SHARED back in for the non-MSI(X) interrupt handler Greg KH
2012-05-18 21:16 ` [ 48/54] wake up s_wait_unfrozen when ->freeze_fs fails Greg KH
2012-05-18 21:16 ` [ 49/54] pch_gpio: Support new device LAPIS Semiconductor ML7831 IOH Greg KH
2012-05-18 21:16 ` [ 50/54] pch_gbe: fixed the issue which receives an unnecessary packet Greg KH
2012-05-18 21:16 ` [ 51/54] pch_gbe: support ML7831 IOH Greg KH
2012-05-18 21:16 ` [ 52/54] pch_gbe: Fixed the issue on which PC was frozen when link was downed Greg KH
2012-05-18 21:16 ` [ 53/54] pch_gbe: Do not abort probe on bad MAC Greg KH
2012-05-18 21:16 ` [ 54/54] pch_gbe: memory corruption calling pch_gbe_validate_option() Greg KH
2012-05-19 1:01 ` [ 00/54] 3.0.32-stable review Steven Rostedt
2012-05-19 4:20 ` Greg KH
2012-05-20 2:01 ` [PATCH] pidmap: Use GFP_ATOMIC to allocate page (was: Re: [ 00/54] 3.0.32-stable review) Steven Rostedt
2012-05-20 2:32 ` David Rientjes
2012-05-20 19:03 ` Linus Torvalds
2012-05-20 23:22 ` David Rientjes
2012-05-20 23:35 ` Linus Torvalds
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=20120518211559.805734534@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=akpm@linux-foundation.org \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=shuox.liu@intel.com \
--cc=stable@vger.kernel.org \
--cc=tj@kernel.org \
--cc=torvalds@linux-foundation.org \
--cc=yanmin.zhang@intel.com \
/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
Be 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).