Re: [Devel] dm: ploop: arithemtic overflow in ploop

On 5/10/24 14:54, Alexey Kuznetsov wrote: Images of size > 2TB are corrupted! https://pmc.acronis.work/browse/TTASK-68430 Signed-off-by: Alexey Kuznetsov --- drivers/md/dm-ploop.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-ploop.h

Re: [Devel] [PATCH vz9] drm: Disable modeset by default

On 2/9/24 19:47, Konstantin Khorenko wrote: 1. VHS and HCI are server products => nice graphical console output is not that important. 2. QXL driver is buggy, we face issues with L1 VMs hungs during console writing using QXL driver. => let's disable framebuffer by default (like we

Re: [Devel] fuse: call proper fiemap_prep as it is required by new kernel api

On 10/13/23 20:35, Alexey Kuznetsov wrote: Otherwise we consider locations with dirty page cache as holes. Affects: #VSTOR-76073, #PSBM-151414, #PSBM-151424, #PSBM-151464 Signed-off-by: Alexey Kuznetsov --- fs/fuse/file.c | 4 1 file changed, 4 insertions(+) diff --git

[Devel] [PATCH 1/1] exec: fix memory allocation size in the alloc_exec_handle()

We have heap corruption here for sure. Signed-off-by: Denis V. Lunev --- lib/exec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/exec.c b/lib/exec.c index e22a950..769d09e 100644 --- a/lib/exec.c +++ b/lib/exec.c @@ -1285,7 +1285,7 @@ int vzctl2_wrap_exec_script(char

Re: [Devel] [PATCH vz9 v2] ploop: port and fix the standby mode feature.

vers/md/dm-ploop-map.c| 36 +++- drivers/md/dm-ploop-target.c | 12 +++- drivers/md/dm-ploop.h| 1 + include/linux/blkdev.h | 4 kernel/ve/ve.c | 9 + 6 files changed, 70 insertions(+), 2 deletions(-) Cc: Denis V. Lunev Cc:

Re: [Devel] [PATCH RH7] virtio_net: fix hang on vhost backend setting

On 17.05.2022 18:29, Pavel Tikhomirov wrote: We can see a hang for 40 sec in (vz7.185.3) in vhost_net_set_backend: crash> ps -m | grep UN [0 00:00:40.157] [UN] PID: 38937 TASK: 9b7f54ca8000 CPU: 2 COMMAND: "qemu-kvm" [] vhost_net_ubuf_put_and_wait+0x65/0xb0 [vhost_net] []

[Devel] [PATCH vz8 1/2] ve: remove /proc/fairsched(, 2) and /proc/vz/fairsched #PSBM-79882

These files are legacy and are not used anymore. Dropping. Signed-off-by: Denis V. Lunev --- kernel/ve/veowner.c | 25 - 1 file changed, 25 deletions(-) diff --git a/kernel/ve/veowner.c b/kernel/ve/veowner.c index da9fd60e5282..d7b3b94bd3e6 100644 --- a/kernel/ve

[Devel] [PATCH vz8 0/2] simple /proc fixes

Signed-off-by: Denis V. Lunev ___ Devel mailing list Devel@openvz.org https://lists.openvz.org/mailman/listinfo/devel

[Devel] [PATCH vz8 2/2] ve: drop /proc/bc directory #PSBM-127913

It is obsolete and unused. Signed-off-by: Denis V. Lunev --- kernel/ve/veowner.c | 6 -- 1 file changed, 6 deletions(-) diff --git a/kernel/ve/veowner.c b/kernel/ve/veowner.c index d7b3b94bd3e6..90af7bc720ff 100644 --- a/kernel/ve/veowner.c +++ b/kernel/ve/veowner.c @@ -18,18 +18,12

[Devel] [PATCH vz7, vz8 1/1] kvm: fix AMD IBRS/IBPB/STIBP/SSBD reporting #PSBM-120787

We should report these bits in 8008 EBX on AMD only, i.e. when AMD specific feature bits are enabled. Signed-off-by: Denis V. Lunev CC: Vasily Averin CC: Konstantin Khorenko --- arch/x86/kvm/cpuid.c | 8 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm

Re: [Devel] [PATCH rh7 v2] keys, user: Fix high order allocation in user_instantiate() #PSBM-107794

On 9/15/20 9:49 AM, Vasily Averin wrote: > On 9/14/20 2:16 PM, Andrey Ryabinin wrote: >> @@ -96,7 +97,8 @@ static void user_free_payload_rcu(struct rcu_head *head) >> struct user_key_payload *payload; >> >> payload = container_of(head, struct user_key_payload, rcu); >> -

Re: [Devel] [PATCH rh7] keys, user: Fix high order allocation in user_instantiate()

On 9/14/20 1:55 PM, Andrey Ryabinin wrote: > Adding user key might trigger 4-order allocation which is unreliable > in case of fragmented memory: > > [ cut here ] > WARNING: CPU: 3 PID: 134927 at mm/page_alloc.c:3533 > __alloc_pages_nodemask+0x1b1/0x600 > order 4 >= 3,

Re: [Devel] [PATCH RHEL7 COMMIT] ve/cgroup: At cgroup_mark(unmark)_ve_roots skip non-virtualized roots

On 8/6/20 8:32 AM, Vasily Averin wrote: > The commit is pushed to "branch-rh7-3.10.0-1127.18.2.vz7.163.x-ovz" and will > appear at https://src.openvz.org/scm/ovz/vzkernel.git > after rh7-3.10.0-1127.18.2.el7 > --> > commit 2c7e88541f87587f184eb3e23ba44e89428ed7a6 > Author: Valeriy Vdovin >

Re: [Devel] [PATCH rh7 v2] mm/memcg: fix cache growth above cache.limit_in_bytes

On 7/30/20 6:57 PM, Evgenii Shatokhin wrote: > On 30.07.2020 17:00, Denis V. Lunev wrote: >> On 7/30/20 4:58 PM, Andrey Ryabinin wrote: >>> Exceeding cache above cache.limit_in_bytes schedules high_work_func() >>> which tries to reclaim 32 pages. If cache generated f

Re: [Devel] [PATCH rh7 v2] mm/memcg: fix cache growth above cache.limit_in_bytes

On 7/30/20 4:58 PM, Andrey Ryabinin wrote: > Exceeding cache above cache.limit_in_bytes schedules high_work_func() > which tries to reclaim 32 pages. If cache generated fast enough or it allows > cgroup to steadily grow above cache.limit_in_bytes because we don't reclaim > enough. Try to reclaim

Re: [Devel] [PATCH RH7] net/mlx5: suppress high order allocation warning in mlx5_frag_buf_alloc_node()

On 7/28/20 10:54 AM, Vasily Averin wrote: > [ 16.850796] IPv6: ADDRCONF(NETDEV_CHANGE): enp24s0f0: link becomes ready > [ 16.997441] [ cut here ] > [ 16.997450] WARNING: CPU: 0 PID: 9668 at mm/page_alloc.c:3548 > __alloc_pages_nodemask+0x1b1/0x600 > [ 16.997453]

Re: [Devel] [PATCH RHEL7] Removed warning from kmalloc in function alloc_rootdomain

On 7/3/20 7:19 PM, Denis V. Lunev wrote: > On 7/3/20 7:12 PM, Valeriy Vdovin wrote: >> 'alloc_rootdomain' is used during cpu hotplug actions when cpu's are >> removed or added. So it's relatively rare occasion. The size of >> allocated structure 'struct root_domain' is ~22k

Re: [Devel] [PATCH RHEL7] Removed warning from kmalloc in function alloc_rootdomain

On 7/3/20 7:12 PM, Valeriy Vdovin wrote: > 'alloc_rootdomain' is used during cpu hotplug actions when cpu's are > removed or added. So it's relatively rare occasion. The size of > allocated structure 'struct root_domain' is ~22k, which is a warnable > order 3. Because this structure is related to

Re: [Devel] [PATCH rh7 v3 4/4] /proc//vz_latency: Show maximal allocation latency in the last second.

;time[0] + > + KSTAT_ALLOC_MAX_LAT_PERIOD)) { > + if (alloc_lat->maxlat[1] < lat) { > + alloc_lat->maxlat[1] = lat; > + alloc_lat->time[1] = time; > + } > + } else if (time_before(time, alloc_

Re: [Devel] [PATCH rh7 v3 3/4] /proc/vz/latency: distinguish atomic allocations in irq from in task atomics.

k, > unsigned int order, > int ind, cpu; > > time = jiffies_to_usecs(jiffies - time) * 1000; > - if (!(gfp_mask & __GFP_WAIT)) > - ind = KSTAT_ALLOCSTAT_ATOMIC; > - else > + if (!(gfp_mask & __GFP_WAIT)) { > + if (in_task()) > + ind = KSTAT_ALLOCSTAT_ATOMIC; > + else > + ind = KSTAT_ALLOCSTAT_IRQ; > + } else { > if (order > 0) > ind = KSTAT_ALLOCSTAT_LOW_MP; > else > ind = KSTAT_ALLOCSTAT_LOW; > + } > > local_irq_save(flags); > cpu = smp_processor_id(); Reviewed-by: Denis V. Lunev ___ Devel mailing list Devel@openvz.org https://lists.openvz.org/mailman/listinfo/devel

Re: [Devel] [PATCH rh7 v3 2/4] vz_latency: don't account allocations in interrupts to random tasks

time; > - current->alloc_lat[ind].count++; > + if (in_task()) { > + current->alloc_lat[ind].totlat += time; > + current->alloc_lat[ind].count++; > + } > > if (!page) > kstat_glob.alloc_fails[cpu][ind]++; Reviewed-by: Denis

Re: [Devel] [PATCH rh7 v3 1/4] linux/preempt_mask.h: Add in_task() macro.

oftirq() (softirq_count()) > #define in_interrupt() (irq_count()) > #define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) > +#define in_task()(!(preempt_count() & \ > +(NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFS

Re: [Devel] [PATCH rh7 v2 4/4] /proc//vz_latency: Show maximal allocation latency in the last second.

On 08/20/2018 03:03 PM, Andrey Ryabinin wrote: > Add to '/proc//vz_latency' column with maximal latency task have seen > in the last 2 minutes. > > E.g.: > > cat /proc/1/vz_latency > TypeTotal_latCalls Max (2min) > allocatomic:0

Re: [Devel] [PATCH vz7] net/sctp: Allocate SSN map on a per-page basis

we can allocate pages on demand right now, i.e. when it will be really necessary. Can be done in the next patch of the set. Den On 03/27/2018 08:55 PM, Oleg Babin wrote: > SCTP protocol allocates TCB on receiving INIT and COOKIE ECHO chunks > which specify input and output stream count. As the

Re: [Devel] [vz7.7 PATCH] x86/kvm/vmx: do not use vm-exit instruction length for fast MMIO when running nested

On 02/13/2018 12:49 PM, Roman Kagan wrote: > From: Vitaly Kuznetsov > > I was investigating an issue with seabios >= 1.10 which stopped working > for nested KVM on Hyper-V. The problem appears to be in > handle_ept_violation() function: when we do fast mmio we need to skip >

Re: [Devel] [PATCH vz7.39] scsi: virtio: Reduce BUG if total_sg > virtqueue size to WARN.

On 12/19/2017 05:26 PM, Denis V. Lunev wrote: > On 12/19/2017 04:02 PM, Roman Kagan wrote: >> From: "Richard W.M. Jones" <rjo...@redhat.com> >> >> If using indirect descriptors, you can make the total_sg as large as you >> want. If not, BUG is too

Re: [Devel] [PATCH vz7.39] scsi: virtio: Reduce BUG if total_sg > virtqueue size to WARN.

On 12/19/2017 04:02 PM, Roman Kagan wrote: > From: "Richard W.M. Jones" > > If using indirect descriptors, you can make the total_sg as large as you > want. If not, BUG is too serious because the function later returns > -ENOSPC. > > Signed-off-by: Richard W.M. Jones

Re: [Devel] [PATCH vz7.39] scsi: virtio: Reduce BUG if total_sg > virtqueue size to WARN.

On 12/19/2017 04:02 PM, Roman Kagan wrote: > From: "Richard W.M. Jones" > > If using indirect descriptors, you can make the total_sg as large as you > want. If not, BUG is too serious because the function later returns > -ENOSPC. > > Signed-off-by: Richard W.M. Jones

Re: [Devel] [PATCH 0/6] backporting async_pf injection functionality

On 09/25/2017 04:00 PM, Kirill Tkhai wrote: > > On 25.09.2017 15:57, Denis V. Lunev wrote: >> On 09/25/2017 03:47 PM, Kirill Tkhai wrote: >>> Hi, Denis, >>> >>> your patches in base64 format. Could you resend them as plain-text like we >>> u

Re: [Devel] [PATCH] KVM: VMX: Do not BUG() on out-of-bounds guest IRQ

On 09/25/2017 03:53 PM, Kirill Tkhai wrote: > On 21.09.2017 11:18, Denis Plotnikov wrote: >> From: Jan H. Schönherr >> >> The value of the guest_irq argument to vmx_update_pi_irte() is >> ultimately coming from a KVM_IRQFD API call. Do not BUG() in >> vmx_update_pi_irte() if

Re: [Devel] [PATCH 0/6] backporting async_pf injection functionality

On 09/25/2017 03:47 PM, Kirill Tkhai wrote: > Hi, Denis, > > your patches in base64 format. Could you resend them as plain-text like we > usually do? > > Here is body of the patch 1/6: > > "X-MS-Exchange-Processed-By-BccFoldering: 15.20.0056.000 > X-Microsoft-Exchange-Diagnostics: > >

Re: [Devel] [PATCH 0/6] backporting async_pf injection functionality

On 09/20/2017 05:41 PM, Roman Kagan wrote: > On Wed, Sep 20, 2017 at 05:30:59PM +0300, Denis Plotnikov wrote: >> the patch set is for >> 1. Replace Roman's patch avoiding async_pf injection while in the guest mode >> with >>the similar patch from the mainstream for kernel code consistency >>

Re: [Devel] [PATCH vz7.6 v2] kvm: x86: hyperv: avoid livelock in oneshot SynIC timers

On 07/24/2017 11:36 AM, Konstantin Khorenko wrote: > Once more: need this in vz7 update 5 or later? > update6, as written in the subject ;) > -- > Best regards, > > Konstantin Khorenko, > Virtuozzo Linux Kernel Team > > On 07/24/2017 10:33 AM, Roman Kagan wrote: >> If the SynIC timer message

Re: [Devel] [PATCH RHEL7 COMMIT] kvm/x86: skip async_pf when in guest mode

On 12/07/2016 07:11 PM, Vasily Averin wrote: > Den, > it's for our customers, > both for VZ7-rtm (vz7.15.2) and VZ7-u1 (vz7.18.7) kernels > Is it important for customers? > > thank you, > Vasily Averin no. we do not care. This functionality is not announced. We do not support nesting

Re: [Devel] [PATCH RHEL7 COMMIT] kvm/x86: skip async_pf when in guest mode

On 12/07/2016 06:27 PM, Konstantin Khorenko wrote: > Please consider to RK. > > Den, let us know if you don't think it's needed. > which branch you are speaking about? For RK in UP3? How we can be sure that all QA nodes will be updated in this case? They are running not released kernels. Den >

Re: [Devel] [vzlin-dev] [PATCH vz7] fuse: relax i_mutex coverage in fuse_fsync

On 12/01/2016 10:09 PM, Maxim Patlasov wrote: > On 12/01/2016 12:06 AM, Dmitry Monakhov wrote: > >> Maxim Patlasov writes: >> >>> Alexey, >>> >>> >>> You're right. And while composing the patch I well understood that it's >>> possible to rework fuse_sync_writes() using a

Re: [Devel] [PATCH vz7] fuse: relax i_mutex coverage in fuse_fsync

On 11/30/2016 04:02 AM, Maxim Patlasov wrote: > fuse_fsync_common() does need i_mutex for fuse_sync_writes() and > fuse_flush_mtime(). But when those operations are done, it's actually > doesn't matter whether to hold the lock over fuse_request_send(FUSE_FSYNC) > or not: we ensured that all

Re: [Devel] [PATCH vz7.19 0/2] KVM:x86: fixes for get_kvmclock_ns

On 11/16/2016 01:38 PM, Konstantin Khorenko wrote: > Looks like mainstream suggested another approach, so dropping these > patches. > > Please send new patches once they are accepted. > (or we have to apply unaccepted due to some reasons) > The entire serie has been resent on Friday. [PATCH

Re: [Devel] [PATCH 00/16] add tsc_scale and fix VM pause/resume

On 11/14/2016 12:20 PM, Denis V. Lunev wrote: > On 11/11/2016 09:47 AM, Roman Kagan wrote: >> From: Denis Plotnikov <dplotni...@virtuozzo.com> >> >> The set of patches: >> 1. adds tsc_scaling functionality for VMX >> 2. generalizes a number o

Re: [Devel] [PATCH 00/16] add tsc_scale and fix VM pause/resume

On 11/11/2016 09:47 AM, Roman Kagan wrote: > From: Denis Plotnikov > > The set of patches: > 1. adds tsc_scaling functionality for VMX > 2. generalizes a number of functions responsible for tsc writing and >reading > 3. fix VM pause/resume issue #PSBM-54338 by

Re: [Devel] [PATCH 00/16] add tsc_scale and fix VM pause/resume

On 11/11/2016 11:47 AM, Roman Kagan wrote: > From: Denis Plotnikov > > The set of patches: > 1. adds tsc_scaling functionality for VMX > 2. generalizes a number of functions responsible for tsc writing and >reading > 3. fix VM pause/resume issue #PSBM-54338 by

[Devel] Re: [PATCH 2/3] tcp: Like icmp use register_pernet_subsys

Acked-by: Denis V. Lunev d...@openvz.org On Fri, 2009-02-20 at 07:53 -0800, Eric W. Biederman wrote: To remove the possibility of packets flying around when network devices are being cleaned up use reisger_pernet_subsys instead of register_pernet_device. Signed-off-by: Eric W. Biederman

[Devel] Re: [PATCH 1/3] netns: Fix icmp shutdown.

Acked-by: Denis V. Lunev d...@openvz.org On Fri, 2009-02-20 at 07:52 -0800, Eric W. Biederman wrote: Recently I had a kernel panic in icmp_send during a network namespace cleanup. There were packets in the arp queue that failed to be sent and we attempted to generate an ICMP host unreachable

Re: [Devel] Why use FAKEGATEWAY{,NET} instead of default dev venet0?

On Tue, 2008-10-14 at 14:15 +0400, Peter Volkov wrote: В Втр, 14/10/2008 в 11:51 +0400, Denis V. Lunev пишет: On Fri, 2008-09-12 at 13:08 +0400, Peter Volkov wrote: venet0 is peer-to-peer device. Why openvz scripts set some $FAKEGATEWAYNET network on p2p device and then put nonexistent

Re: [Devel] Why use FAKEGATEWAY{,NET} instead of default dev venet0?

On Fri, 2008-09-12 at 13:08 +0400, Peter Volkov wrote: Hello. I have a question which puzzles me from the the very beginning I've started to use OPENVZ. venet0 is peer-to-peer device. Why openvz scripts set some $FAKEGATEWAYNET network on p2p device and then put nonexistent $FAKEGATEWAY as

[Devel] [PATCH net-next 0/14] ipv6: making IP/ICMP mibs per/namespace

This patch series makes IP6/ICMP6 mibs per/namespace using infrastructure accepted with UDP6 mib infrastructure. Regards, Den ___ Containers mailing list [EMAIL PROTECTED] https://lists.linux-foundation.org/mailman/listinfo/containers

[Devel] [PATCH net-next 1/9] netns: move /proc/net/dev_snmp6 to struct net

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/netns/mib.h |4 net/ipv6/proc.c | 20 +++- 2 files changed, 15 insertions(+), 9 deletions(-) diff --git a/include/net/netns/mib.h b/include/net/netns/mib.h index 4491476..ffcef5d 100644

[Devel] [PATCH net-next 7/9] netns: add stab functions for per/namespace mibs allocation

The content of init_ipv6_mibs/cleanup_ipv6_mibs will be moved to new calls one by one next. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv6/af_inet6.c | 18 -- 1 files changed, 16 insertions(+), 2 deletions(-) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c

[Devel] [PATCH net-next 6/9] netns: allow per device ipv6 snmp statistics in non-initial namespace

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv6/proc.c |3 --- 1 files changed, 0 insertions(+), 3 deletions(-) diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index c38c9e5..23e567f 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -231,9 +231,6 @@ int snmp6_register_dev

[Devel] [PATCH net-next 3/9] ipv6: consolidate ipv6 sock_stat code at the beginning of net/ipv6/proc.c

Simple, comsolidate sockstat6 staff in one place, at the beginning of the file. Right now sockstat6_seq_open/sockstat6_seq_fops looks like an intrusion in the middle of snmp6 code. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv6/proc.c | 26 +- 1 files

[Devel] [PATCH net-next 8/9] netns: make udpv6 mib per/namespace

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/netns/mib.h |1 + include/net/udp.h | 12 ++-- net/ipv4/udp.c |3 --- net/ipv6/af_inet6.c |9 - net/ipv6/proc.c |3 ++- 5 files changed, 13 insertions(+), 15 deletions

[Devel] [PATCH net-next 9/9] netns: make uplitev6 mib per/namespace

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/netns/mib.h |1 + include/net/udp.h | 11 --- net/ipv6/af_inet6.c | 14 -- net/ipv6/proc.c |3 ++- net/ipv6/udplite.c |2 -- 5 files changed, 15 insertions(+), 16 deletions

[Devel] [PATCH net-next 4/9] ipv6: separate seq_ops for global per/device ipv6 statistics

stored in the same field. This effectively requires to separate seq_ops of these files. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv6/proc.c | 48 1 files changed, 32 insertions(+), 16 deletions(-) diff --git a/net/ipv6/proc.c b

[Devel] [PATCH net-next 0/9] ipv6: making UDP mibs per/namespace

This patch series provides a basic infrastructure to make snmp6 statistics per/namespace and actually virtualize udp6/udplite6 mibs. This set follows approach used by Pavel Emelyanov in IPv4 code. IP6/icmp6 statistics is also ready and will follow. Regards, Den

[Devel] [PATCH net-next 5/9] netns: register global ipv6 mibs statistics in each namespace

Unused net variable will become used very soon. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv6/proc.c |6 -- 1 files changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 7601f56..c38c9e5 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6

[Devel] [PATCH net-next 2/9] netns: register /proc/net/dev_snmp6/* in each ns

Do the same for /proc/net/snmp6. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv6/proc.c | 40 1 files changed, 16 insertions(+), 24 deletions(-) diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 16ebf85..5764062 100644 --- a/net/ipv6

[Devel] Re: [PATCH net-next] [RFC] netns: enable cross-ve Unix sockets

On Wed, 2008-10-01 at 18:15 +0200, Daniel Lezcano wrote: Pavel Emelyanov wrote: Daniel Lezcano wrote: Pavel Emelyanov wrote: Yes per namespace, I agree. If the option is controlled by the parent and it is done by sysctl, you will have to make proc/sys per namespace like Pavel did

[Devel] [PATCH net-next] [RFC] netns: enable cross-ve Unix sockets

. if somebody really wants to isolate containers, he should start from filesystem separation. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/unix/af_unix.c |3 --- 1 files changed, 0 insertions(+), 3 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 39d2173

[Devel] Re: [PATCH net-next] [RFC] netns: enable cross-ve Unix sockets

On Wed, 2008-10-01 at 13:13 +0200, Daniel Lezcano wrote: Denis V. Lunev wrote: This patch opens a way to connect via Unix socket from one namespace to another if these sockets are opened via conventional filesystem interface. Such approach allows to share important services between

[Devel] Re: [PATCH net-next] [RFC] netns: enable cross-ve Unix sockets

On Wed, 2008-10-01 at 13:55 +0200, Daniel Lezcano wrote: Denis V. Lunev wrote: On Wed, 2008-10-01 at 13:13 +0200, Daniel Lezcano wrote: Denis V. Lunev wrote: This patch opens a way to connect via Unix socket from one namespace to another if these sockets are opened via conventional

[Devel] Re: [PATCH net-next] [RFC] netns: enable cross-ve Unix sockets

On Wed, 2008-10-01 at 14:31 +0200, Daniel Lezcano wrote: Pavel Emelyanov wrote: So there are 2 cases: * full isolation : restriction on VPS * partial isolation : no restriction but *perhaps* problem when migrating Looks like we need an option per namespace to reduce the isolation

[Devel] Re: [PATCH net-next] [RFC] netns: enable cross-ve Unix sockets

On Wed, 2008-10-01 at 15:46 +0200, Daniel Lezcano wrote: Denis V. Lunev wrote: On Wed, 2008-10-01 at 14:31 +0200, Daniel Lezcano wrote: Pavel Emelyanov wrote: So there are 2 cases: * full isolation : restriction on VPS * partial isolation : no restriction but *perhaps* problem when

[Devel] Re: [PATCH 2/2] netns: Add network namespace argument in rt6_fill_node() and ipv6_dev_get_saddr()

On Thu, 2008-08-14 at 16:04 -0400, Vlad Yasevich wrote: Hi Brian Brian Haley wrote: --- diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 483a01d..e0945d4 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -319,7 +319,8 @@ static void sctp_v6_get_saddr(struct sctp_sock

[Devel] Re: [PATCH 1/2] netns: fix NULL-dereference in dev_net()

On Thu, 2008-08-14 at 15:27 -0400, Brian Haley wrote: Change dev_net() to handle a NULL argument - return init_net instead. -Brian Signed-off-by: Brian Haley [EMAIL PROTECTED] --- the code is designed keeping in mind that there are no checks for net != NULL in any place. They are

Re: [Devel] 2.6.26 panic (skb-dev==NULL), NFS support

On Fri, 2008-08-01 at 10:12 +0400, Denis V. Lunev wrote: On Fri, 2008-08-01 at 02:26 +0200, Karel Tuma wrote: Hello list, I hope this is the right place to post. I've recently moved to 2.6.26 git (i hope that's the bleeding edge) OpenVZ to find out how usable it is. I'm running

Re: [Devel] 2.6.26 panic (skb-dev==NULL), NFS support

On Fri, 2008-08-01 at 02:26 +0200, Karel Tuma wrote: Hello list, I hope this is the right place to post. I've recently moved to 2.6.26 git (i hope that's the bleeding edge) OpenVZ to find out how usable it is. I'm running it on a box under fair IO load (100-300 BIO/s). The thing panics in

Re: [Devel] Re: C/R minisummit notes

On Wed, 2008-07-23 at 14:55 -0400, Oren Laadan wrote: Hi, I've placed a somewhat more detailed summary on the wiki: http://wiki.openvz.org/Containers/Mini-summit_2008_notes (also accessible from: http://wiki.openvz.org/Containers/Mini-summit_2008) To further discuss technical details,

[Devel] Re: [PATCH net-next 0/9] selective (per/namespace) flush of rt_cache

On Mon, 2008-07-07 at 03:29 -0700, Eric W. Biederman wrote: David Miller [EMAIL PROTECTED] writes: From: Denis V. Lunev [EMAIL PROTECTED] Date: Fri, 04 Jul 2008 17:16:00 +0400 This series of patches implements selective rt cache flushing to make sure that in one namespace we'll

[Devel] Re: [PATCH net-next 0/9] selective (per/namespace) flush of rt_cache

On Sat, 2008-07-05 at 20:55 -0700, David Miller wrote: From: Denis V. Lunev [EMAIL PROTECTED] Date: Fri, 04 Jul 2008 17:16:00 +0400 This series of patches implements selective rt cache flushing to make sure that in one namespace we'll not been able to affect the performance of other from

[Devel] [PATCH net-next 8/9] netns: place rt_genid into struct net

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/netns/ipv4.h |1 + net/ipv4/route.c | 76 ++ 2 files changed, 44 insertions(+), 33 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 356617f

[Devel] [PATCH net-next 2/9] net: add fib_rules_ops to flush_cache method

This is required to pass namespace context into rt_cache_flush called from -flush_cache. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/fib_rules.h |2 +- net/core/fib_rules.c|2 +- net/decnet/dn_rules.c |2 +- net/ipv4/fib_rules.c|4 ++-- 4 files

[Devel] [PATCH net-next 3/9] ipv4: remove static flush_delay variable

(as it was before) accessing this local variable is removed using flush_mutex. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv4/route.c | 11 --- 1 files changed, 8 insertions(+), 3 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index cedc366..790de32 100644

[Devel] [PATCH net-next 1/9] netns: add namespace parameter to rt_cache_flush

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/route.h |2 +- net/ipv4/arp.c |2 +- net/ipv4/devinet.c |8 +--- net/ipv4/fib_frontend.c | 17 + net/ipv4/fib_hash.c |6 +++--- net/ipv4/fib_rules.c|2 +- net/ipv4

[Devel] [PATCH net-next 7/9] ipv4: pass current value of rt_genid into rt_hash

Basically, there is no difference to atomic_read internally or pass it as a parameter as rt_hash is inline. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv4/route.c | 28 +--- 1 files changed, 17 insertions(+), 11 deletions(-) diff --git a/net/ipv4/route.c

[Devel] [PATCH net-next 6/9] netns: add struct net parameter to rt_cache_invalidate

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv4/route.c |6 +++--- 1 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f99d9db..9725223 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -778,7 +778,7 @@ static void

[Devel] [PATCH net-next 5/9] netns: make rt_secret_rebuild timer per namespace

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/netns/ipv4.h |2 ++ net/ipv4/route.c | 40 ++-- 2 files changed, 32 insertions(+), 10 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index a29adf1

[Devel] [PATCH net-next 0/9] selective (per/namespace) flush of rt_cache

Hello, Dave! This series of patches implements selective rt cache flushing to make sure that in one namespace we'll not been able to affect the performance of other from the user space. Regards, Den ___ Containers mailing list [EMAIL

[Devel] [PATCH net-next 4/9] netns: register net.ipv4.route.flush in each namespace

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/netns/ipv4.h |1 + net/ipv4/route.c | 79 -- 2 files changed, 70 insertions(+), 10 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 6ef90b5

[Devel] [PATCH net-next 9/9] netns: selective flush of rt_cache

dst cache is marked as expired on the per/namespace basis by previous path. Right now we have to implement selective cache shrinking. This procedure has been ported from older OpenVz codebase. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv4/route.c | 31

[Devel] [PATCH 0/8 net-2.6.26] [NETNS]: namespace refcounting cleanup

refcounting code to remove extra atomic from any possible fast paths. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] ___ Containers mailing list [EMAIL PROTECTED] https://lists.linux-foundation.org/mailman/listinfo/containers

[Devel] [PATCH 6/8 net-2.6.26] [NETNS]: Add netns refcnt debug for dst ops.

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv6/route.c |4 +++- 1 files changed, 3 insertions(+), 1 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6293cb9..210a079 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2622,7 +2622,7 @@ static int

[Devel] [PATCH 4/8 net-2.6.26] [NETNS]: Add netns refcnt debug into fib_info.

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv4/fib_semantics.c |3 ++- 1 files changed, 2 insertions(+), 1 deletions(-) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index a13c847..3b83c34 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c

[Devel] [PATCH 5/8 net-2.6.26] [NETNS]: Add netns refcnt debug for inet bind buckets.

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv4/inet_hashtables.c |3 ++- 1 files changed, 2 insertions(+), 1 deletions(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 32ca2f8..1612184 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4

[Devel] [PATCH 2/8 net-2.6.26] [NETNS]: Add netns refcnt debug for kernel sockets.

Protocol control sockets and netlink kernel sockets should not prevent the namespace stop request. They are initialized and disposed in a special way by sk_change_net/sk_release_kernel. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/sock.h |2 +- net/core/sock.c|1

[Devel] [PATCH 8/8 net-2.6.26] [NETNS]: Add netns refcnt debug for network devices.

dev_set_net is called for - just allocated devices - devices moving from one namespace to another release_net has proper check inside to distinguish these cases. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/linux/netdevice.h |3 ++- net/core/dev.c|2 ++ 2 files

[Devel] [PATCH 1/8 net-2.6.26] [NETNS]: Make netns refconting debug like a socket one.

Make release_net/hold_net noop for performance-hungry people. This is a debug staff and should be used in the debug mode only. Add check for net != NULL in hold/release calls. This will be required later on. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/net_namespace.h | 44

[Devel] [PATCH 7/8 net-2.6.26] [NETNS]: Add netns refcnt debug to fib rules.

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/fib_rules.h |1 + net/core/fib_rules.c|5 +++-- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 34349f9..a5c6ccc 100644 --- a/include/net/fib_rules.h

[Devel] [PATCH 3/8 net-2.6.26] [NETNS]: Add netns refcnt debug for timewait buckets.

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv4/inet_timewait_sock.c |3 ++- 1 files changed, 2 insertions(+), 1 deletions(-) diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index a741378..ce16e9a 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net

[Devel] Re: [PATCH 0/3 net-2.6.26] Compilation fixes.

On Wed, 2008-04-02 at 00:10 -0700, David Miller wrote: From: Denis V. Lunev [EMAIL PROTECTED] Date: Mon, 31 Mar 2008 19:46:01 +0400 Hello, Dave! Recently I have seen several issues post to the netdev@ blaming inclusion of the net_namespace.h from seq_file. This set fixes

[Devel] Re: [PATCH 0/3] IPv6 start/stop problems

On Tue, 2008-03-18 at 17:32 +0300, Denis V. Lunev wrote: Hello, Dave! We have faced a several problems with IPv6 start/stop on 2.6.18 RHEL5 kernel in OpenVz. The code in the 2.6.25 does not differ from 2.6.18 in respect to this. Hi, Dave! Have you changed you mind about this? Regards

[Devel] [PATCH 5/13 net-2.6.26] [SCTP]: Use inet_ctl_sock_create for control socket creation.

sk-sk_proc-(un)hash is noop right now, so the unification is correct. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/sctp/protocol.c |7 ++- 1 files changed, 2 insertions(+), 5 deletions(-) diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 5aea911..6a3be58 100644

[Devel] [PATCH 3/13 net-2.6.26] [DCCP]: dccp_v(4|6)_ctl_socket is leaked.

This seems a purism as module can't be unloaded, but though if cleanup method is present it should be correct and clean all staff created. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/dccp/ipv4.c |1 + net/dccp/ipv6.c |1 + 2 files changed, 2 insertions(+), 0 deletions

[Devel] [PATCH 6/13 net-2.6.26] [SCTP]: Replace socket with sock for SCTP control socket.

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/sctp/protocol.c | 12 +++- 1 files changed, 7 insertions(+), 5 deletions(-) diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 6a3be58..ac0833c 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -74,7 +74,7

[Devel] [PATCH 7/13 net-2.6.26] [INET]: Let inet_ctl_sock_create return sock rather than socket.

All upper protocol layers are already use sock internally. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/inet_common.h |2 +- net/dccp/ipv4.c |4 +--- net/dccp/ipv6.c |4 +--- net/ipv4/af_inet.c| 12 +++- net/ipv4/tcp_ipv4.c

[Devel] [PATCH 1/13 net-2.6.26] [TCP]: Replace socket with sock for reset sending.

Replace tcp_socket with tcp_sock. This is more effective (less derefferences on fast paths). Additionally, the approach is unified to one used in ICMP. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv4/tcp_ipv4.c | 10 ++ 1 files changed, 6 insertions(+), 4 deletions

[Devel] [PATCH 10/13 net-2.6.26] [INET]: uc_ttl assignment in inet_ctl_sock_create is redundant.

uc_ttl is initialized in inet(6)_create and never changed except setsockopt ioctl. Remove this assignment. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv4/af_inet.c |1 - 1 files changed, 0 insertions(+), 1 deletions(-) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index

[Devel] [PATCH 11/13 net-2.6.26] [IPV6]: Simplify IPv6 control sockets creation.

Do this by replacing sock_create_kern with inet_ctl_sock_create. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv6/icmp.c | 16 ++-- net/ipv6/mcast.c | 19 ++- net/ipv6/ndisc.c | 12 +--- 3 files changed, 17 insertions(+), 30 deletions

[Devel] [PATCH 8/13 net-2.6.26] [NETNS]: Inet control socket should not hold a namespace.

This is a generic requirement, so make inet_ctl_sock_create namespace aware and create a inet_ctl_sock_destroy wrapper around sk_release_kernel. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/inet_common.h |8 +++- net/dccp/ipv4.c |4 ++-- net/dccp/ipv6.c

[Devel] [PATCH 9/13 net-2.6.26] [ICMP]: Simplify ICMP control socket creation.

Replace sock_create_kern with inet_ctl_sock_create. Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- net/ipv4/icmp.c | 25 +++-- 1 files changed, 7 insertions(+), 18 deletions(-) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 803bc9f..efc7cbe 100644 --- a/net/ipv4

[Devel] [PATCH 12/13 net-2.6.26] [NETNS]: Create tcp control socket in the each namespace.

Signed-off-by: Denis V. Lunev [EMAIL PROTECTED] --- include/net/netns/ipv4.h |1 + net/ipv4/tcp_ipv4.c | 21 +++-- 2 files changed, 20 insertions(+), 2 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index af685f7..34ee348 100644

  1   2   3   4   5   >