ARN |
> __GFP_RETRY_MAYFAIL);
> - if (!vs) {
> - vs = vzalloc(sizeof(*vs));
> - if (!vs)
> - goto err_vs;
> - }
> + vs = kvzalloc(sizeof(*vs), GFP_KERNEL);
> + if (!vs)
> + goto err_vs;
>
> vqs = kmalloc_array(VHOST_SCSI_MAX_VQ, sizeof(*vqs), GFP_KERNEL);
> if (!vqs)
Acked-by: Pankaj Gupta
t; return r;
> BUG_ON(r != 1);
> base = kmap_atomic(page);
> set_bit(bit, base);
> kunmap_atomic(base);
> - set_page_dirty_lock(page);
> - put_page(page);
> + unpin_user_pages_dirty_lock(&page, 1, true);
> return 0;
> }
Acked-by: Pankaj Gupta
Hi Jason,
>
> On 2017年03月23日 13:34, Jason Wang wrote:
> >
> >
> >>
> >>> +{
> >>> +if (rvq->rh != rvq->rt)
> >>> +goto out;
> >>> +
> >>> +rvq->rh = rvq->rt = 0;
> >>> +rvq->rt = skb_array_consume_batched_bh(rvq->rx_array, rvq->rxq,
> >>> +VHOST_RX_BATC
>
> On Mon, Mar 27, 2017 at 02:39:47PM +0200, Jesper Dangaard Brouer wrote:
> > On Mon, 27 Mar 2017 10:55:14 +0200
> > Jesper Dangaard Brouer wrote:
> >
> > > A possible solution, would be use the local_bh_{disable,enable} instead
> > > of the {preempt_disable,enable} calls. But it is slower,
Hello,
It looks like a race with softirq and normal process context.
Just thinking if we really want allocations from 'softirqs' to be done using
per cpu list? Or we can have some check in 'free_hot_cold_page' for softirqs
to check if we are on a path of returning from hard interrupt don't al
>
>
>
> On 04/26/2016 02:24 PM, Pankaj Gupta wrote:
> > Hi Jason,
> >
> > Overall patches look good. Just one doubt I have is below:
> >> We use spinlock to synchronize the work list now which may cause
> >> unnecessary contentions. So th
Hi Jason,
Overall patches look good. Just one doubt I have is below:
>
> We use spinlock to synchronize the work list now which may cause
> unnecessary contentions. So this patch switch to use llist to remove
> this contention. Pktgen tests shows about 5% improvement:
>
> Before:
> ~130 pps
>
> The following series adds the ability for a hypervisor to set an MTU on the
> guest during feature negotiation phase. This is useful for VM orchestration
> when, for instance, tunneling is involved and the MTU of the various systems
> should be homogenous.
>
> The first patch adds the featur
>
> This patch adds a simple queue selection function to macvlan
> layer. In most cases, this will just use the standard fallback
> fuction, but when rx-queue has been recoreded we'll try to use
> that value.
>
> Signed-off-by: Vladislav Yasevich
> ---
> drivers/net/macvlan.c | 20 +++
> On Wed, Jun 24, 2015 at 10:31:09PM -0300, Julio Faracco wrote:
> > 2015-06-24 3:10 GMT-03:00 Michael S. Tsirkin :
> > >
> > > On Tue, Jun 23, 2015 at 10:44:29PM -0300, Julio Faracco wrote:
> > > > virtio_net paravirtualized driver does not have a tx_timeout() function
> > > > to
> > > > guarante
cify dependent commit's summary.
Signed-off-by: Pankaj Gupta
---
drivers/net/macvtap.c | 10 ++
include/linux/if_macvlan.h | 2 +-
2 files changed, 3 insertions(+), 9 deletions(-)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 483afb1..6a64197f 100644
--- a/drivers
Macvtap should be compatible with tuntap for maximum number
of queues. '1059590254fa9dce9cafc4f07d1103dbec415e76' removes
the limitation and increases number of queues in tuntap.
Now, Its safe to increase number of queues in Macvtap as well.
Signed-off-by: Pankaj Gupta
---
inc
12 matches
Mail list logo
