From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, Olaf Hering <olaf@aepfle.de>,
Hugh Dickins <hughd@google.com>,
Boris Ostrovsky <boris.ostrovsky@oracle.com>,
Juergen Gross <jgross@suse.com>
Subject: [PATCH 4.4 57/60] xen/gntdev: Use VM_MIXEDMAP instead of VM_IO to avoid NUMA balancing
Date: Wed, 4 Jan 2017 21:47:42 +0100 [thread overview]
Message-ID: <20170104200708.416507353@linuxfoundation.org> (raw)
In-Reply-To: <20170104200705.627445996@linuxfoundation.org>
4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
commit 30faaafdfa0c754c91bac60f216c9f34a2bfdf7e upstream.
Commit 9c17d96500f7 ("xen/gntdev: Grant maps should not be subject to
NUMA balancing") set VM_IO flag to prevent grant maps from being
subjected to NUMA balancing.
It was discovered recently that this flag causes get_user_pages() to
always fail with -EFAULT.
check_vma_flags
__get_user_pages
__get_user_pages_locked
__get_user_pages_unlocked
get_user_pages_fast
iov_iter_get_pages
dio_refill_pages
do_direct_IO
do_blockdev_direct_IO
do_blockdev_direct_IO
ext4_direct_IO_read
generic_file_read_iter
aio_run_iocb
(which can happen if guest's vdisk has direct-io-safe option).
To avoid this let's use VM_MIXEDMAP flag instead --- it prevents
NUMA balancing just as VM_IO does and has no effect on
check_vma_flags().
Reported-by: Olaf Hering <olaf@aepfle.de>
Suggested-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Acked-by: Hugh Dickins <hughd@google.com>
Tested-by: Olaf Hering <olaf@aepfle.de>
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/xen/gntdev.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -804,7 +804,7 @@ static int gntdev_mmap(struct file *flip
vma->vm_ops = &gntdev_vmops;
- vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_IO;
+ vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_MIXEDMAP;
if (use_ptemod)
vma->vm_flags |= VM_DONTCOPY;
next prev parent reply other threads:[~2017-01-04 21:19 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20170104205105epcas5p4dfb9f8f2e2771bc19858b096e326c051@epcas5p4.samsung.com>
2017-01-04 20:46 ` [PATCH 4.4 00/60] 4.4.40-stable review Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 01/60] btrfs: limit async_work allocation and worker func duration Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 02/60] Btrfs: fix tree search logic when replaying directory entry deletes Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 03/60] btrfs: store and load values of stripes_min/stripes_max in balance status item Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 04/60] Btrfs: fix qgroup rescan worker initialization Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 05/60] USB: serial: option: add support for Telit LE922A PIDs 0x1040, 0x1041 Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 06/60] USB: serial: option: add dlink dwm-158 Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 07/60] USB: serial: kl5kusb105: fix open error path Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 08/60] USB: cdc-acm: add device id for GW Instek AFG-125 Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 09/60] usb: hub: Fix auto-remount of safely removed or ejected USB-3 devices Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 10/60] usb: gadget: f_uac2: fix error handling at afunc_bind Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 11/60] usb: gadget: composite: correctly initialize ep->maxpacket Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 12/60] USB: UHCI: report non-PME wakeup signalling for Intel hardware Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 13/60] ALSA: usb-audio: Add QuickCam Communicate Deluxe/S7500 to volume_control_quirks Greg Kroah-Hartman
2017-01-04 20:46 ` [PATCH 4.4 14/60] ALSA: hiface: Fix M2Tech hiFace driver sampling rate change Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 15/60] ALSA: hda/ca0132 - Add quirk for Alienware 15 R2 2016 Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 16/60] ALSA: hda - ignore the assoc and seq when comparing pin configurations Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 17/60] ALSA: hda - fix headset-mic problem on a Dell laptop Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 18/60] ALSA: hda - Gate the mic jack on HP Z1 Gen3 AiO Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 19/60] ALSA: hda: when comparing pin configurations, ignore assoc in addition to seq Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 20/60] clk: ti: omap36xx: Work around sprz319 advisory 2.1 Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 21/60] Btrfs: fix memory leak in reading btree blocks Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 22/60] Btrfs: bail out if block group has different mixed flag Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 23/60] Btrfs: return gracefully from balance if fs tree is corrupted Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 24/60] Btrfs: dont leak reloc root nodes on error Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 25/60] Btrfs: fix memory leak in do_walk_down Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 26/60] Btrfs: dont BUG() during drop snapshot Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 27/60] btrfs: make file clone aware of fatal signals Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 28/60] block_dev: dont test bdev->bd_contains when it is not stable Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 29/60] mm: Add a user_ns owner to mm_struct and fix ptrace permission checks Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 30/60] ptrace: Capture the ptracers creds not PT_PTRACE_CAP Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 32/60] ext4: fix mballoc breakage with 64k block size Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 33/60] ext4: fix stack memory corruption " Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 34/60] ext4: use more strict checks for inodes_per_block on mount Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 35/60] ext4: fix in-superblock mount options processing Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 36/60] ext4: add sanity checking to count_overhead() Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 37/60] ext4: reject inodes with negative size Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 38/60] ext4: return -ENOMEM instead of success Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 39/60] ext4: do not perform data journaling when data is encrypted Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 40/60] f2fs: set ->owner for debugfs status files file_operations Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 41/60] loop: return proper error from loop_queue_rq() Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 42/60] mm/vmscan.c: set correct defer count for shrinker Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 43/60] fs: exec: apply CLOEXEC before changing dumpable task flags Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 44/60] exec: Ensure mm->user_ns contains the execed files Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 45/60] usb: gadget: composite: always set ep->mult to a sensible value Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 46/60] blk-mq: Do not invoke .queue_rq() for a stopped queue Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 47/60] dm flakey: return -EINVAL on interval bounds error in flakey_ctr() Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 48/60] dm crypt: mark key as invalid until properly loaded Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 49/60] dm space map metadata: fix struct sm_metadata leak on failed create Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 50/60] ASoC: intel: Fix crash at suspend/resume without card registration Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 51/60] CIFS: Fix a possible memory corruption during reconnect Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 52/60] CIFS: Fix missing nls unload in smb2_reconnect() Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 53/60] CIFS: Fix a possible memory corruption in push locks Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 54/60] kernel/watchdog: use nmi registers snapshot in hardlockup handler Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 55/60] kernel/debug/debug_core.c: more properly delay for secondary CPUs Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 56/60] tpm xen: Remove bogus tpm_chip_unregister Greg Kroah-Hartman
2017-01-04 20:47 ` Greg Kroah-Hartman [this message]
2017-01-04 20:47 ` [PATCH 4.4 58/60] arm/xen: Use alloc_percpu rather than __alloc_percpu Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 59/60] xfs: set AGI buffer type in xlog_recover_clear_agi_bucket Greg Kroah-Hartman
2017-01-04 20:47 ` [PATCH 4.4 60/60] driver core: fix race between creating/querying glue dir and its cleanup Greg Kroah-Hartman
2017-01-05 0:42 ` [PATCH 4.4 00/60] 4.4.40-stable review Shuah Khan
2017-01-05 5:25 ` Guenter Roeck
2017-01-05 15:33 ` Guillaume Nault
2017-01-05 20:35 ` Greg Kroah-Hartman
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=20170104200708.416507353@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=boris.ostrovsky@oracle.com \
--cc=hughd@google.com \
--cc=jgross@suse.com \
--cc=linux-kernel@vger.kernel.org \
--cc=olaf@aepfle.de \
--cc=stable@vger.kernel.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.