Re: [Xen-devel] pvSCSI test

On 02/12/2015 05:43 PM, Kristian Hagsted Rasmussen wrote: On Monday, February 9, 2015 07:02, Juergen Gross wrote: To: Kristian Hagsted Rasmussen; Olaf Hering; xen-de...@lists.xensource.com Subject: Re: [Xen-devel] pvSCSI test snip No, that's okay. The connection between p-dev and the drive

Re: [Xen-devel] [PATCH for-4.6 0/5] xen: arm: Parse PCI DT nodes' ranges and interrupt-map

On 10/24/2014 04:58 AM, Ian Campbell wrote: This message has been archived. View the original item

[Xen-devel] [PATCH v3] modify the IO_TLB_SEGSIZE and IO_TLB_DEFAULT_SIZE configurable as flexible requirement about SW-IOMMU.

The maximum of SW-IOMMU is limited to 2^11*128 = 256K. And the maximum of IO_TLB_DEFAULT_SIZE is limited to (64UL<<20) 64M. While in different platform and different requirement this seems improper. So modifing the IO_TLB_SEGSIZE to io_tlb_segsize and IO_TLB_DEFAULT_SIZE to io_tlb_default_size whi

[Xen-devel] [libvirt test] 34580: tolerable FAIL - PUSHED

flight 34580 libvirt real [real] http://www.chiark.greenend.org.uk/~xensrcts/logs/34580/ Failures :-/ but no regressions. Regressions which are regarded as allowable (not blocking): test-amd64-i386-libvirt 9 guest-start fail REGR. vs. 34464 Tests which did not succeed, but a

[Xen-devel] [linux-linus test] 34568: regressions - FAIL

flight 34568 linux-linus real [real] http://www.chiark.greenend.org.uk/~xensrcts/logs/34568/ Regressions :-( Tests which did not succeed and are blocking, including tests which could not be run: test-amd64-i386-qemuu-rhel6hvm-intel 5 xen-boot fail REGR. vs. 34227 test-amd64-i386-qemut

Re: [Xen-devel] [PATCH 18/18] x86: add multiboot2 protocol support for EFI platforms

On Sat, Feb 14, 2015 at 08:23:45PM +0300, Andrei Borzenkov wrote: > В Wed, 11 Feb 2015 08:20:04 + > "Jan Beulich" пишет: > > > >>> On 10.02.15 at 22:27, wrote: > > > After some testing we have found at least one machine on which this thing > > > does not work. It is Dell PowerEdge R820 with l

Re: [Xen-devel] [PATCH V5] x86 spinlock: Fix memory corruption on completing completions

On 02/15, Raghavendra K T wrote: > > * Raghavendra K T [2015-02-15 11:25:44]: > > Resending the V5 with smp_mb__after_atomic() change without bumping up > revision Reviewed-by: Oleg Nesterov Of course, this needs the acks from maintainers. And I agree that SLOWPATH in .head makes xadd() in unl

[Xen-devel] [rumpuserxen test] 34575: regressions - FAIL

flight 34575 rumpuserxen real [real] http://www.chiark.greenend.org.uk/~xensrcts/logs/34575/ Regressions :-( Tests which did not succeed and are blocking, including tests which could not be run: build-i386-rumpuserxen6 xen-build fail REGR. vs. 33866 build-amd64-rumpuserx

Re: [Xen-devel] [PATCH V5] x86 spinlock: Fix memory corruption on completing completions

On 02/15/2015 09:47 PM, Oleg Nesterov wrote: Well, I regret I mentioned the lack of barrier after enter_slowpath ;) On 02/15, Raghavendra K T wrote: @@ -46,7 +46,8 @@ static __always_inline bool static_key_false(struct static_key *key); static inline void __ticket_enter_slowpath(arch_spinl

Re: [Xen-devel] [PATCH V5] x86 spinlock: Fix memory corruption on completing completions

* Raghavendra K T [2015-02-15 11:25:44]: Resending the V5 with smp_mb__after_atomic() change without bumping up revision ---8<--- >From 0b9ecde30e3bf5b5b24009fd2ac5fc7ac4b81158 Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Fri, 6 Feb 2015 16:44:11 +0530 Subject: [PATCH RESEND V5] x86 sp

Re: [Xen-devel] [PATCH V5] x86 spinlock: Fix memory corruption on completing completions

Well, I regret I mentioned the lack of barrier after enter_slowpath ;) On 02/15, Raghavendra K T wrote: > > @@ -46,7 +46,8 @@ static __always_inline bool static_key_false(struct > static_key *key); > > static inline void __ticket_enter_slowpath(arch_spinlock_t *lock) > { > - set_bit(0, (vol

Re: [Xen-devel] [PATCH V4] x86 spinlock: Fix memory corruption on completing completions

On 02/15, Raghavendra K T wrote: > > On 02/13/2015 09:02 PM, Oleg Nesterov wrote: > >>> @@ -772,7 +773,8 @@ __visible void kvm_lock_spinning(struct arch_spinlock >>> *lock, __ticket_t want) >>> * check again make sure it didn't become free while >>> * we weren't looking. >>> */ >>>

[Xen-devel] [linux-3.10 test] 34550: regressions - FAIL

flight 34550 linux-3.10 real [real] http://www.chiark.greenend.org.uk/~xensrcts/logs/34550/ Regressions :-( Tests which did not succeed and are blocking, including tests which could not be run: test-amd64-amd64-xl-qemut-winxpsp3 7 windows-install fail REGR. vs. 26303 Regressions which are

[Xen-devel] [linux-3.16 test] 34547: regressions - FAIL

flight 34547 linux-3.16 real [real] http://www.chiark.greenend.org.uk/~xensrcts/logs/34547/ Regressions :-( Tests which did not succeed and are blocking, including tests which could not be run: test-amd64-amd64-xl-credit2 15 guest-localmigrate/x10fail REGR. vs. 34167 test-amd64-i386-pair

Re: [Xen-devel] [PATCH OSSTEST 11/12] Changes on test step of debain hvm guest install

> -Original Message- > From: Ian Jackson [mailto:ian.jack...@eu.citrix.com] > Sent: Friday, February 13, 2015 8:03 PM > To: Hu, Robert > Cc: xen-devel@lists.xen.org; jfeh...@suse.com; wei.l...@citrix.com; > ian.campb...@citrix.com; Pang, LongtaoX > Subject: RE: [PATCH OSSTEST 11/12] Changes

[Xen-devel] [qemu-mainline test] 34543: regressions - FAIL

flight 34543 qemu-mainline real [real] http://www.chiark.greenend.org.uk/~xensrcts/logs/34543/ Regressions :-( Tests which did not succeed and are blocking, including tests which could not be run: test-amd64-i386-xl-qemuu-debianhvm-amd64 7 debian-hvm-install fail REGR. vs. 33480 test-amd64-amd

[Xen-devel] [PATCH 01/10] xen/blkfront: convert to blk-mq API

This patch convert xen-blkfront driver to use the block multiqueue API and force to use only one hardware queue at this time. Signed-off-by: Arianna Avanzini Signed-off-by: Bob Liu --- drivers/block/xen-blkfront.c | 118 --- 1 file changed, 100 insertions

[Xen-devel] [PATCH 03/10] xen/blkfront: reorg info->io_lock after using blk-mq API

Drop unnecessary holding of info->io_lock when calling into blk-mq apis. Signed-off-by: Bob Liu --- drivers/block/xen-blkfront.c | 38 -- 1 file changed, 16 insertions(+), 22 deletions(-) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.

[Xen-devel] [PATCH 10/10] xen/blkfront: use work queue to fast blkif interrupt return

Move the request complete logic out of blkif_interrupt() to a work queue, after that we can replace 'spin_lock_irq' with 'spin_lock' so that irq won't be disabled too long in blk_mq_queue_rq(). No more warning like this: INFO: rcu_sched detected stalls on CPUs/tasks: { 7} (detected by 0, t=15002 j

[Xen-devel] [PATCH 09/10] xen/blkback: get hardware queue number from blkfront

Backend advertise the max number it supported to "multi-queue-max-queues", and read the negotiate value from "multi-queue-num-queues". Signed-off-by: Bob Liu --- drivers/block/xen-blkback/blkback.c | 8 drivers/block/xen-blkback/xenbus.c | 36 ++-- 2 fi

[Xen-devel] [RFC PATCH 00/10] Multi-queue support for xen-block driver

This patchset convert the Xen PV block driver to the multi-queue block layer API by sharing and using multiple I/O rings between the frontend and backend. History: It's based on the result of Arianna's internship for GNOME's Outreach Program for Women, in which she was mentored by Konrad Rzeszutek

[Xen-devel] [PATCH 05/10] xen/blkback: separate ring information out of struct xen_blkif

This patch separate ring information from struct xen_blkif to an new struct xen_blkif_ring to make preparation for real multi hardware queues supporting. Signed-off-by: Arianna Avanzini Signed-off-by: Bob Liu --- drivers/block/xen-blkback/blkback.c | 362 ++-- dr

[Xen-devel] [PATCH 06/10] xen/blkfront: pseudo support for multi hardware queues

Prepare patch for multi hardware queues, the ring number was mandatory set to 1. Signed-off-by: Arianna Avanzini Signed-off-by: Bob Liu --- drivers/block/xen-blkfront.c | 408 +-- 1 file changed, 234 insertions(+), 174 deletions(-) diff --git a/drivers/b

[Xen-devel] [PATCH 02/10] xen/blkfront: drop legacy block layer support

As Christoph suggested, remove the legacy support similar to most drivers coverted (virtio, mtip, and nvme). Signed-off-by: Arianna Avanzini Signed-off-by: Bob Liu --- drivers/block/xen-blkfront.c | 167 +-- 1 file changed, 32 insertions(+), 135 deletions

[Xen-devel] [PATCH 07/10] xen/blkback: pseudo support for multi hardware queues

Prepare patch for multi hardware queues, the ring number was mandatory set to 1. Signed-off-by: Arianna Avanzini Signed-off-by: Bob Liu --- drivers/block/xen-blkback/common.h | 3 +- drivers/block/xen-blkback/xenbus.c | 368 +++-- 2 files changed, 233 insertion

[Xen-devel] [PATCH 04/10] xen/blkfront: separate ring information to an new struct

A ring is the representation of a hardware queue, this patch separate ring information from blkfront_info to an new struct blkfront_ring_info to make preparation for real multi hardware queues supporting. Signed-off-by: Arianna Avanzini Signed-off-by: Bob Liu --- drivers/block/xen-blkfront.c |

[Xen-devel] [PATCH 08/10] xen/blkfront: negotiate hardware queue number with backend

The max number of hardware queues for xen/blkfront is num_online_cpus() or set by module parameter, while the number xen/blkback supported is notified through xenstore("multi-queue-max-queues"). The negotiated number was the smaller one, and was written back to xen/blkback as "multi-queue-num-queue