- 06 12月, 2012 3 次提交
-
-
由 Michael S. Tsirkin 提交于
For short packets zerocopy mode adds overhead of managing heads which isn't necessary: we could simly update used ring directly same as with zerocopy disabled. Things seem to run a bit faster if we detect and bypass head management when zcopy isn't used. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-
由 Michael S. Tsirkin 提交于
When memory map changes, we need to flush outstanding DMAs as they might in theory reference old memory addresses. To do this simply stop initiating new DMAs and wait for ubufs ref count to drop to 0. Afterwards reset the count back to 1. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-
由 Michael S. Tsirkin 提交于
vring changes already do a flush internally where appropriate, so we do not need a second flush. It's currently not very expensive but a follow-up patch makes flush more heavy-weight, so remove the extra flush here to avoid regressing performance if call or kick fds are changed on data path. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-
- 04 12月, 2012 1 次提交
-
-
由 Michael S. Tsirkin 提交于
These packet counters are used to drive the zercopy selection heuristic so nothing too bad happens if they are off a bit - and they are also reset once in a while. But it's cleaner to clear them when backend is set so that we start in a known state. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 29 11月, 2012 1 次提交
-
-
由 Michael S. Tsirkin 提交于
If a single descriptor crosses a region, the second chunk length should be decremented by size translated so far, instead it includes the full descriptor length. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Acked-by: NJason Wang <jasowang@redhat.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 20 11月, 2012 1 次提交
-
-
由 Sachin Kamat 提交于
linux/vhost.h was included twice. Signed-off-by: NSachin Kamat <sachin.kamat@linaro.org> Acked-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 03 11月, 2012 6 次提交
-
-
由 Michael S. Tsirkin 提交于
It seems that to avoid deadlocks it is enough to poll vq before we are going to use the last buffer. This is faster than c70aa540. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Michael S. Tsirkin 提交于
Even when vhost-net is in zero-copy transmit mode, net core might still decide to copy the skb later which is somewhat slower than a copy in user context: data copy overhead is added to the cost of page pin/unpin. The result is that enabling tx zero copy option leads to higher CPU utilization for guest to guest and guest to host traffic. To fix this, suppress zero copy tx after a given number of packets triggered late data copy. Re-enable periodically to detect workload changes. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Michael S. Tsirkin 提交于
Zerocopy handling code is vhost-net specific. Move it from vhost.c/vhost.h out to net.c Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Michael S. Tsirkin 提交于
This will be used to disable zerocopy when error rate is high. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Michael S. Tsirkin 提交于
Better document macros for DMA tracking. Add an explicit one for DMA in progress instead of relying on user supplying len != 1. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
由 Michael S. Tsirkin 提交于
Even if skb is marked for zero copy, net core might still decide to copy it later which is somewhat slower than a copy in user context: besides copying the data we need to pin/unpin the pages. Add a parameter reporting such cases through zero copy callback: if this happens a lot, device can take this into account and switch to copying in user context. This patch updates all users but ignores the passed value for now: it will be used by follow-up patches. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 25 10月, 2012 1 次提交
-
-
由 Michael S. Tsirkin 提交于
We copy head count to a 16 bit field, this works by chance on LE but on BE guest gets 0. Fix it up. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Tested-by: NAlexander Graf <agraf@suse.de> Cc: stable@vger.kernel.org Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 03 10月, 2012 1 次提交
-
-
由 Nicholas Bellinger 提交于
This patch converts tcm_vhost to use target_submit_cmd_map_sgls() for I/O submission and mapping of pre-allocated SGL memory from incoming virtio-scsi SGL memory -> se_cmd descriptors. This includes removing the original open-coded fabric uses of target core callers to support transport_generic_map_mem_to_cmd() between target_setup_cmd_from_cdb() and transport_handle_cdb_direct() logic. It also includes adding a handful of new tcm_vhost_cmnd member + assignments in vhost_scsi_allocate_cmd() used from cmwq process context I/O submission within tcm_vhost_submission_work() (v2: Use renamed target_submit_cmd_map_sgls) Reported-by: NChristoph Hellwig <hch@lst.de> Cc: Christoph Hellwig <hch@lst.de> Acked-by: NMichael S. Tsirkin <mst@redhat.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Stefan Hajnoczi <stefanha@gmail.com> Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>
-
- 27 9月, 2012 1 次提交
-
-
由 Al Viro 提交于
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
-
- 18 9月, 2012 2 次提交
-
-
由 Roland Dreier 提交于
Every fabric driver has to supply a se_tfo->set_fabric_sense_len() method, just so iSCSI can return an offset of 2. However, every fabric driver is already allocating a sense buffer and passing it into the target core, either via transport_init_se_cmd() or target_submit_cmd(). So instead of having iSCSI pass the start of its sense buffer into the core and then later tell the core to skip the first 2 bytes, it seems easier for iSCSI just to do the offset of 2 when it passes the sense buffer into the core. Then we can drop the se_tfo->set_fabric_sense_len() everywhere, and just add a couple of lines of code to iSCSI to set the sense data length to the beginning of the buffer right before it sends it over the network. (nab: Remove .set_fabric_sense_len usage from tcm_qla2xxx_npiv_ops + change transport_get_sense_buffer to follow v3.6-rc6 code w/o ->set_fabric_sense_len usage) Signed-off-by: NRoland Dreier <roland@purestorage.com> Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>
-
由 Roland Dreier 提交于
There are no callers of se_tfo->get_fabric_sense_len(), so we should stop having every fabric driver implement it. Signed-off-by: NRoland Dreier <roland@purestorage.com> Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>
-
- 21 8月, 2012 1 次提交
-
-
由 Michael S. Tsirkin 提交于
Here TRANSPORT_IQN_LEN is 224, which is a multiple of 4. Since vhost_tpgt is 2 bytes and abi_version is 4, the total size would be 230. But gcc needs struct size be aligned to first field size, which is 4 bytes, so it pads the structure by extra 2 bytes to the total of 232. This padding is very undesirable in an ABI: - it can not be initialized easily - it can not be checked easily - it can leak information between kernel and userspace Simplest solution is probably just to make the padding explicit. (v2: Add check for zero'ed backend->reserved field for VHOST_SCSI_SET_ENDPOINT and VHOST_SCSI_CLEAR_ENDPOINT ops as requested by MST) Reported-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>
-
- 17 8月, 2012 3 次提交
-
-
由 Nicholas Bellinger 提交于
This patch changes the vhost_scsi_target->vhost_wwpn[] type used by VHOST_SCSI_* ioctls to 'char *' as requested by Blue Swirl in order to match the latest QEMU vhost-scsi RFC-v3 userspace code. Queuing this up into target-pending/master for a -rc3 PULL. Reported-by: NBlue Swirl <blauwirbel@gmail.com> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>
-
由 Nicholas Bellinger 提交于
This patch contains the post RFC-v5 (post-merge) changes, this includes: - Add locking comment - Move vhost_scsi_complete_cmd ahead of TFO callbacks in order to drop forward declarations - Drop extra '!= NULL' usage in vhost_scsi_complete_cmd_work() - Change vhost_scsi_*_handle_kick() to use pr_debug - Fix possible race in vhost_scsi_set_endpoint() for vs->vs_tpg checking + assignment. - Convert tv_tpg->tpg_vhost_count + ->tv_tpg_port_count from atomic_t -> int, and make sure reference is protected by ->tv_tpg_mutex. - Drop unnecessary vhost_scsi->vhost_ref_cnt - Add 'err:' label for exception path in vhost_scsi_clear_endpoint() - Add enum for VQ numbers, add usage in vhost_scsi_open() - Add vhost_scsi_flush() + vhost_scsi_flush_vq() following drivers/vhost/net.c - Add smp_wmb() + vhost_scsi_flush() call during vhost_scsi_set_features() - Drop unnecessary copy_from_user() usage with GET_ABI_VERSION ioctl - Add missing vhost_scsi_compat_ioctl() caller for vhost_scsi_fops - Fix function parameter definition first line to follow existing vhost code style - Change 'vHost' usage -> 'vhost' in handful of locations - Change -EPERM -> -EBUSY usage for two failures in tcm_vhost_drop_nexus() - Add comment for tcm_vhost_workqueue in tcm_vhost_init() - Make GET_ABI_VERSION return 'int' + add comment in tcm_vhost.h Reported-by: NMichael S. Tsirkin <mst@redhat.com> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Zhi Yong Wu <wuzhy@cn.ibm.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>
-
由 Fengguang Wu 提交于
Fix up a new coccinelle warnings reported by Fengguang Wu + Intel 0-DAY kernel build testing backend: drivers/vhost/tcm_vhost.c:537:23-29: ERROR: allocation function on line 533 returns NULL not ERR_PTR on failure vim +537 drivers/vhost/tcm_vhost.c 534 if (!sg) 535 return -ENOMEM; 536 pr_debug("%s sg %p sgl_count %u is_err %ld\n", __func__, > 537 sg, sgl_count, IS_ERR(sg)); 538 sg_init_table(sg, sgl_count); 539 540 tv_cmd->tvc_sgl = sg; Signed-off-by: NFengguang Wu <fengguang.wu@intel.com> Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>
-
- 30 7月, 2012 1 次提交
-
-
由 Nicholas Bellinger 提交于
This patch adds the initial code for tcm_vhost, a Vhost level TCM fabric driver for virtio SCSI initiators into KVM guest. This code is currently up and running on v3.5-rc2 host+guest from target-pending/for-next-merge. Using tcm_vhost requires Zhi's -> Stefan -> nab's qemu vhost-scsi tree here: http://git.kernel.org/?p=virt/kvm/nab/qemu-kvm.git;a=shortlog;h=refs/heads/vhost-scsi -- Changelog v4 -> v5: Expose ABI version via VHOST_SCSI_GET_ABI_VERSION + use Rev 0 as starting point for v3.6-rc code (Stefan + ALiguori + nab) Convert vhost_scsi_handle_vq() to vq_err() (nab + MST) Minor style fixes from checkpatch (nab) Changelog v3 -> v4: Rename vhost_vring_target -> vhost_scsi_target (mst + nab) Use TRANSPORT_IQN_LEN in vhost_scsi_target->vhost_wwpn[] def (nab) Move back to drivers/vhost/, and just use drivers/vhost/Kconfig.tcm (mst) Move TCM_VHOST related ioctl defines from include/linux/vhost.h -> drivers/vhost/tcm_vhost.h as requested by MST (nab) Move Kbuild.tcm include from drivers/staging -> drivers/vhost/, and just use 'if STAGING' around 'source drivers/vhost/Kbuild.tcm' Changelog v2 -> v3: Unlock on error in tcm_vhost_drop_nexus() (DanC) Fix strlen() doesn't count the terminator (DanC) Call kfree() on an error path (DanC) Convert tcm_vhost_write_pending to use target_execute_cmd (hch + nab) Fix another strlen() off by one in tcm_vhost_make_tport (DanC) Add option under drivers/staging/Kconfig, and move to drivers/vhost/tcm/ as requested by MST (nab) Changelog v1 -> v2: Fix tv_cmd completion -> release SGL memory leak (nab) Fix sparse warnings for static variable usage ((Fengguang Wu) Fix sparse warnings for min() typing + printk format specs (Fengguang Wu) Convert to cmwq submission for I/O dispatch (nab + hch) Changelog v0 -> v1: Merge into single source + header file, and move to drivers/vhost/ Acked-by: NMichael S. Tsirkin <mst@redhat.com> Cc: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com> Cc: Anthony Liguori <aliguori@us.ibm.com> Cc: Zhi Yong Wu <wuzhy@cn.ibm.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Hannes Reinecke <hare@suse.de> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>
-
- 22 7月, 2012 2 次提交
-
-
由 Stefan Hajnoczi 提交于
The vhost work queue allows processing to be done in vhost worker thread context, which uses the owner process mm. Access to the vring and guest memory is typically only possible from vhost worker context so it is useful to allow work to be queued directly by users. Currently vhost_net only uses the poll wrappers which do not expose the work queue functions. However, for tcm_vhost (vhost_scsi) it will be necessary to queue custom work. Signed-off-by: NStefan Hajnoczi <stefanha@linux.vnet.ibm.com> Cc: Zhi Yong Wu <wuzhy@cn.ibm.com> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org> Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-
由 Stefan Hajnoczi 提交于
In order for other vhost devices to use the VHOST_FEATURES bits the vhost-net specific bits need to be moved to their own VHOST_NET_FEATURES constant. (Asias: Update drivers/vhost/test.c to use VHOST_NET_FEATURES) Signed-off-by: NStefan Hajnoczi <stefanha@linux.vnet.ibm.com> Cc: Zhi Yong Wu <wuzhy@cn.ibm.com> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Asias He <asias@redhat.com> Signed-off-by: NNicholas A. Bellinger <nab@risingtidesystems.com> Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-
- 27 6月, 2012 1 次提交
-
-
由 Jens Freimann 提交于
On some architectures address spaces are set up in a way that this is not necessary to work properly but on some others (like s390) it is. Make sure we operate on the user address space to allow copy_xxx_user() from the vhost_worker() thread by setting it explicitly before calling use_mm() and revert it after unuse_mm(). Signed-off-by: NJens Freimann <jfrei@linux.vnet.ibm.com> Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com> Acked-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 12 5月, 2012 1 次提交
-
-
由 Basil Gor 提交于
Take vlan header length into account, when vlan id is stored as vlan_tci. Otherwise tagged packets coming from macvtap will be truncated. Signed-off-by: NBasil Gor <basil.gor@gmail.com> Acked-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 02 5月, 2012 4 次提交
-
-
由 Jason Wang 提交于
We add used and signal guest in worker thread but did not poll the virtqueue during the zero copy callback. This may lead the missing of adding and signalling during zerocopy. Solve this by polling the virtqueue and let it wakeup the worker during callback. Signed-off-by: NJason Wang <jasowang@redhat.com> Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-
由 Jason Wang 提交于
When a packet were fully copied in zerocopy, we don't wait for the DMA done to mark the done flag, so after the packet were passed to lower device, we need to add used and signal guest immediately. Signed-off-by: NJason Wang <jasowang@redhat.com> Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-
由 Jason Wang 提交于
Currently, we restart tx polling unconditionally when sendmsg() fails. This would cause unnecessary wakeups of vhost wokers and waste cpu utlization when evil userspace(guest driver) is able to hit EFAULT or EINVAL. The polling is only needed when the socket send buffer were exceeded or not enough memory. So fix this by restarting polling only when sendmsg() returns EAGAIN/ENOBUFS. Signed-off-by: NJason Wang <jasowang@redhat.com> Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-
由 Jason Wang 提交于
When we want to disable vhost_net backend while there's a tx work, a possible NULL pointer defernece may happen we we try to deference the vq->bufs after vhost_net_set_backend() assign a NULL to it. As suggested by Michael, fix this by checking the vq->bufs instead of vhost_sock_zcopy(). Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-
- 14 4月, 2012 1 次提交
-
-
由 Michael S. Tsirkin 提交于
The skb struct ubuf_info callback gets passed struct ubuf_info itself, not the arg value as the field name and the function signature seem to imply. Rename the arg field to ctx to match usage, add documentation and change the callback argument type to make usage clear and to have compiler check correctness. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 12 4月, 2012 1 次提交
-
-
由 Zhi Yong Wu 提交于
commit ea5d4046 broke build for the vhost test module used by tools/virtio. Fix it up. Signed-off-by: NZhi Yong Wu <wuzhy@linux.vnet.ibm.com> Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-
- 20 3月, 2012 1 次提交
-
-
由 Cong Wang 提交于
Signed-off-by: NCong Wang <amwang@redhat.com>
-
- 28 2月, 2012 2 次提交
-
-
由 Michael S. Tsirkin 提交于
We shouldn't hold any locks on release path. Pass a flag to vhost_dev_cleanup to use the lockdep info correctly. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Tested-by: NSasha Levin <levinsasha928@gmail.com>
-
由 Nadav Har'El 提交于
This is a tiny, but important, patch to vhost. Vhost's worker thread only called schedule() when it had no work to do, and it wanted to go to sleep. But if there's always work to do, e.g., the guest is running a network-intensive program like netperf with small message sizes, schedule() was *never* called. This had several negative implications (on non-preemptive kernels): 1. Passing time was not properly accounted to the "vhost" process (ps and top would wrongly show it using zero CPU time). 2. Sometimes error messages about RCU timeouts would be printed, if the core running the vhost thread didn't schedule() for a very long time. 3. Worst of all, a vhost thread would "hog" the core. If several vhost threads need to share the same core, typically one would get most of the CPU time (and its associated guest most of the performance), while the others hardly get any work done. The trivial solution is to add if (need_resched()) schedule(); After doing every piece of work. This will not do the heavy schedule() all the time, just when the timer interrupt decided a reschedule is warranted (so need_resched returns true). Thanks to Abel Gordon for this patch. Signed-off-by: NNadav Har'El <nyh@il.ibm.com> Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-
- 14 1月, 2012 1 次提交
-
-
由 stephen hemminger 提交于
By adding some module aliases, programs (or users) won't have to explicitly call modprobe. Vhost-net will always be available if built into the kernel. It does require assigning a permanent minor number for depmod to work. Also: - use C99 style initialization. - add missing entry in documentation for loop-control Signed-off-by: NStephen Hemminger <shemminger@vyatta.com> Acked-By: NKay Sievers <kay.sievers@vrfy.org> Signed-off-by: NDavid S. Miller <davem@davemloft.net>
-
- 27 7月, 2011 1 次提交
-
-
由 Arun Sharma 提交于
This allows us to move duplicated code in <asm/atomic.h> (atomic_inc_not_zero() for now) to <linux/atomic.h> Signed-off-by: NArun Sharma <asharma@fb.com> Reviewed-by: NEric Dumazet <eric.dumazet@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: NMike Frysinger <vapier@gentoo.org> Signed-off-by: NAndrew Morton <akpm@linux-foundation.org> Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
-
- 21 7月, 2011 2 次提交
-
-
由 Shirley Ma 提交于
The meth for calculating the # of outstanding buffers gives incorrect results when vq->upend_idx wraps around zero. Fix that. Signed-off-by: NShirley Ma <xma@us.ibm.com> Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-
由 Michael S. Tsirkin 提交于
On backend change, we flushed out outstanding skbs but forgot to update the used ring, so that done entries were left in the ubuf_info ring. As a result we lose heads or complete incorrect ones, crashing the guest or leaking memory. Fix by updating the used ring. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-
- 19 7月, 2011 1 次提交
-
-
由 Michael S. Tsirkin 提交于
As we now only update used ring after enabling the backend, we can write flags with __put_user: as that's done on data path, it matters. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
-