similar to: [PATCH] VNIF: Using smart polling instead of event notification.

This is netback multithread support patchset version 4. Main Changes from v3: 1. Patchset is against xen/next tree. 2. Merge group and idx into netif->mapping. 3. Use vmalloc to allocate netbk structures. Main Changes from v2: 1. Merge "group" and "idx" into "netif->mapping", therefore page_ext is not used now. 2. Put netbk_add_netif() and netbk_remove_netif()

Hi, We are running into a situation where rsp_prod index in the shared ring is not getting updated for the netfront tx ring by the netback. We see that rsp_cons is the same value as rsp_prod, with req_prod 236 slots away(tx ring is full). From looking at the netfront driver code, it looks as if xennet_tx_buf_gc processing only happens if rsp_prod is more than rsp_cons. Our

Hi, We are running into a situation where rsp_prod index in the shared ring is not getting updated for the netfront tx ring by the netback. We see that rsp_cons is the same value as rsp_prod, with req_prod 236 slots away(tx ring is full). From looking at the netfront driver code, it looks as if xennet_tx_buf_gc processing only happens if rsp_prod is more than rsp_cons. Our

When counting required slots for skb, netback directly uses DIV_ROUND_UP to get slots required by header data. This is wrong when offset in the page of header data is not zero, and is also inconsistent with following calculation for required slot in netbk_gop_skb. In netbk_gop_skb, required slots are calculated based on offset and len in page of header data. It is possible that required slots

Hi all I''m hacking on a netback trying to identify whether TLB flushes causes heavy performance penalty on Tx path. The hack is quite nasty (you would not want to know, trust me). Basically what is doesn''t is, 1) alter network protocol to pass along mfns instead of grant references, 2) when the backend sees a new mfn, map it RO and cache it in its own address space. With this

Hi all, my name is Hirofumi Tsujimura. We are porting and testing a PV-on-HVM in the IPF. This is a first time to send mail. I probably found the problem when I tested the VNIF. My operation for the test is following. 1. create a domain VTx and attach the VNIF in it. 2. create a domain U. 3. send a packet to the domain VTx from the domain U with ping command. Then, the domain VTx

Instead of mixing printk and pr_<level> forms, just use pr_<level> Miscellaneous changes around these conversions: Add a missing newline to avoid message interleaving, coalesce formats, reflow modified lines to 80 columns. Signed-off-by: Joe Perches <joe at perches.com> --- drivers/net/xen-netback/netback.c | 7 +++---- drivers/net/xen-netfront.c | 28

Instead of mixing printk and pr_<level> forms, just use pr_<level> Miscellaneous changes around these conversions: Add a missing newline to avoid message interleaving, coalesce formats, reflow modified lines to 80 columns. Signed-off-by: Joe Perches <joe at perches.com> --- drivers/net/xen-netback/netback.c | 7 +++---- drivers/net/xen-netfront.c | 28

Instead of mixing printk and pr_<level> forms, just use pr_<level> Miscellaneous changes around these conversions: Add a missing newline to avoid message interleaving, coalesce formats, reflow modified lines to 80 columns. Signed-off-by: Joe Perches <joe at perches.com> --- drivers/net/xen-netback/netback.c | 7 +++---- drivers/net/xen-netfront.c | 28

In blkback driver, after I/O requests are submitted to Dom-0 block I/O subsystem, blkback goes to ''sleep'' effectively without letting blkfront know about it (req_event isn''t set appropriately). Hence blkfront doesn''t notify blkback when it submits a new I/O thus delaying the ''dispatch'' of the new I/O to Dom-0 block I/O subsystem. The new I/O is

This is really trying to cleanup some virt code, as suggested by Peter, who said > You could of course go fix that instead of mutilating things into > sort-of functional state. This work is needed for virtio, so it's probably easiest to merge it through my tree - is this fine by everyone? Arnd, if you agree, could you ack this please? Note to arch maintainers: please don't

This is really trying to cleanup some virt code, as suggested by Peter, who said > You could of course go fix that instead of mutilating things into > sort-of functional state. This work is needed for virtio, so it's probably easiest to merge it through my tree - is this fine by everyone? Arnd, if you agree, could you ack this please? Note to arch maintainers: please don't

Hi Ian, Today i fired up an old VM with a bittorrent client, trying to download some torrents. I seem to be hitting the unlikely case of "xennet: skb rides the rocket: xx slots" and this results in some dropped packets in domU, I don''t see any warnings in dom0. I have added some extra info, but i don''t have enough knowledge if this could/should be prevented from

include/xen/interface/io/ring.h uses full memory barriers to communicate with the other side. For guests compiled with CONFIG_SMP, smp_wmb and smp_mb would be sufficient, so mb() and wmb() here are only needed if a non-SMP guest runs on an SMP host. Switch to virt_xxx barriers which serve this exact purpose. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> ---

include/xen/interface/io/ring.h uses full memory barriers to communicate with the other side. For guests compiled with CONFIG_SMP, smp_wmb and smp_mb would be sufficient, so mb() and wmb() here are only needed if a non-SMP guest runs on an SMP host. Switch to __smp_XXX barriers which serve this exact purpose. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> ---

hi I've some problems with netback 1.what's mmap_pages for, which come from balloon operation ？ mmap_pages = alloc_empty_pages_and_pagevec(MAX_PENDING_REQS) 2.what's the meaning of "refcnt" defined in netif_t (netif->refcnt) 3.irq enable and disable such as disable_irq(netif->irq); why netback use such enable & disable operations while netfront dont use for its

Hi All, I am sure this has been answered somewhere in the list in the past, but I can''t find it. I was wondering if the linux guest netfront driver has GRO support in it. tcpdump shows packets coming in with 1500 bytes, although the eth0 in dom0 and the vif corresponding to the linux guest in dom0 is showing that they receive large packet: In dom0: eth0 Link encap:Ethernet HWaddr

Another checksum offload problem was reported on xen-users, when using a domU as a firewall: http://lists.xensource.com/archives/html/xen-users/2006-04/msg01150.html It also fails without VLANs. The path from dom0->domU with ip_summed==CHECKSUM_HW/proto_csum_blank==1 is broken. - skb_checksum_setup() assumes that a checksum will definitely be calculated in dev_queue_xmit(), but the

When counting required slots for skb, netback directly uses DIV_ROUND_UP to get slots required by header data. This is wrong when offset in the page of header data is not zero, and is also inconsistent with following calculation for required slot in netbk_gop_skb. In netbk_gop_skb, required slots are calculated based on offset and len in page of header data. It is possible that required slots

Not tested in any way. The original code for offload setting seems broken as it resets the features on every netback reconnect. This will set GSO_ROBUST at device creation time (earlier than connect time). RX checksum offload is forced on - so advertise as it is. Signed-off-by: Micha? Miros?aw <mirq-linux at rere.qmqm.pl> --- [I don't know Xen code enough to say this is correct. There