similar to: Bug in SeaBIOS virtio-ring handling bug with vhost-scsi-pci

This helper returns 1 if a call to add_buf will not fail with -ENOSPC. This will help callers that do while(1) { alloc() if (add_buf()) { free(); break; } } This will result in one less alloc/free exercise. Signed-off-by: Amit Shah <amit.shah at redhat.com> --- v2: return true/false instead of 1/0 drivers/virtio/virtio_ring.c | 8 ++++++++ include/linux/virtio.h |

This helper returns 1 if a call to add_buf will not fail with -ENOSPC. This will help callers that do while(1) { alloc() if (add_buf()) { free(); break; } } This will result in one less alloc/free exercise. Signed-off-by: Amit Shah <amit.shah at redhat.com> --- v2: return true/false instead of 1/0 drivers/virtio/virtio_ring.c | 8 ++++++++ include/linux/virtio.h |

This patch series implements a PCI driver for virtio. This allows virtio devices (like block and network) to be used in QEMU/KVM. I'll post a very early KVM userspace backend in kvm-devel for those that are interested. This series depends on the two virtio fixes I've posted and Rusty's config_ops refactoring. I've tested with these patches on Rusty's experimental virtio

This patch series implements a PCI driver for virtio. This allows virtio devices (like block and network) to be used in QEMU/KVM. I'll post a very early KVM userspace backend in kvm-devel for those that are interested. This series depends on the two virtio fixes I've posted and Rusty's config_ops refactoring. I've tested with these patches on Rusty's experimental virtio

From 09d2dcb6b517e7e4cbbdfc960e3171105085ec9e Mon Sep 17 00:00:00 2001 From: Anthony Liguori <aliguori@us.ibm.com> Date: Wed, 7 Nov 2007 20:46:30 -0600 Subject: [PATCH] virtio: Export vring functions for modules to use This is needed for the virtio PCI device to be compiled as a module. Signed-off-by: Anthony Liguori <aliguori@us.ibm.com> Signed-off-by: Rusty Russell

From 09d2dcb6b517e7e4cbbdfc960e3171105085ec9e Mon Sep 17 00:00:00 2001 From: Anthony Liguori <aliguori@us.ibm.com> Date: Wed, 7 Nov 2007 20:46:30 -0600 Subject: [PATCH] virtio: Export vring functions for modules to use This is needed for the virtio PCI device to be compiled as a module. Signed-off-by: Anthony Liguori <aliguori@us.ibm.com> Signed-off-by: Rusty Russell

This helper returns 1 if a call to add_buf will not fail with -ENOSPC. This will help callers that do while(1) { alloc() if (add_buf()) { free(); break; } } This will result in one less alloc/free exercise. Signed-off-by: Amit Shah <amit.shah at redhat.com> --- drivers/virtio/virtio_ring.c | 8 ++++++++ include/linux/virtio.h | 5 +++++ 2 files changed, 13

This helper returns 1 if a call to add_buf will not fail with -ENOSPC. This will help callers that do while(1) { alloc() if (add_buf()) { free(); break; } } This will result in one less alloc/free exercise. Signed-off-by: Amit Shah <amit.shah at redhat.com> --- drivers/virtio/virtio_ring.c | 8 ++++++++ include/linux/virtio.h | 5 +++++ 2 files changed, 13

Convert the virtio-scsi driver to use pr_err() instead of printk(). Signed-off-by: Wanlong Gao <gaowanlong at cn.fujitsu.com> --- drivers/scsi/virtio_scsi.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 612e320..f679b8c 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@

Convert the virtio-scsi driver to use pr_err() instead of printk(). Signed-off-by: Wanlong Gao <gaowanlong at cn.fujitsu.com> --- drivers/scsi/virtio_scsi.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 612e320..f679b8c 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@

This patch implements the hotplug support for virtio-scsi. When there is a device attached/detached, the virtio-scsi driver will be signaled via event virtual queue and it will add/remove the scsi device in question automatically. v2: handle no_event event Signed-off-by: Cong Meng <mc at linux.vnet.ibm.com> Signed-off-by: Sen Wang <senwang at linux.vnet.ibm.com> ---

This patch implements the hotplug support for virtio-scsi. When there is a device attached/detached, the virtio-scsi driver will be signaled via event virtual queue and it will add/remove the scsi device in question automatically. v2: handle no_event event Signed-off-by: Cong Meng <mc at linux.vnet.ibm.com> Signed-off-by: Sen Wang <senwang at linux.vnet.ibm.com> ---

This patch implements the hotplug support for virtio-scsi. When there is a device attached/detached, the virtio-scsi driver will be signaled via event virtual queue and it will add/remove the scsi device in question automatically. v2: handle no_event event v3: add handle event dropped, and typo fix Signed-off-by: Sen Wang <senwang at linux.vnet.ibm.com> Signed-off-by: Cong Meng <mc at

This patch implements the hotplug support for virtio-scsi. When there is a device attached/detached, the virtio-scsi driver will be signaled via event virtual queue and it will add/remove the scsi device in question automatically. v2: handle no_event event v3: add handle event dropped, and typo fix Signed-off-by: Sen Wang <senwang at linux.vnet.ibm.com> Signed-off-by: Cong Meng <mc at

virtqueue ops were introduced in the hope that we'll have multiple implementations besides virtio_ring, but none have surfaced so far, and given that existing virtio ring is deployed in production we are likely stuck with it now, so this layer just adds complexity and overhead. Further, the need to pass vq twice to each call (as in dev->vq->vq_ops->kick(dev->vq) ) adds potential

virtqueue ops were introduced in the hope that we'll have multiple implementations besides virtio_ring, but none have surfaced so far, and given that existing virtio ring is deployed in production we are likely stuck with it now, so this layer just adds complexity and overhead. Further, the need to pass vq twice to each call (as in dev->vq->vq_ops->kick(dev->vq) ) adds potential

We force notification when the ring is full, even if the host has indicated it doesn't want to know. This seemed like a good idea at the time: if we fill the transmit ring, we should tell the host immediately. Unfortunately this logic also applies to the receiving ring, which is refilled constantly. We should introduce real notification thesholds to replace this logic. Meanwhile, removing

We force notification when the ring is full, even if the host has indicated it doesn't want to know. This seemed like a good idea at the time: if we fill the transmit ring, we should tell the host immediately. Unfortunately this logic also applies to the receiving ring, which is refilled constantly. We should introduce real notification thesholds to replace this logic. Meanwhile, removing

On 2018/11/8 ??9:38, Tiwei Bie wrote: >>> + >>> + if (vq->vq.num_free < descs_used) { >>> + pr_debug("Can't add buf len %i - avail = %i\n", >>> + descs_used, vq->vq.num_free); >>> + /* FIXME: for historical reasons, we force a notify here if >>> + * there are outgoing parts to the buffer. Presumably the

On 2018/11/8 ??9:38, Tiwei Bie wrote: >>> + >>> + if (vq->vq.num_free < descs_used) { >>> + pr_debug("Can't add buf len %i - avail = %i\n", >>> + descs_used, vq->vq.num_free); >>> + /* FIXME: for historical reasons, we force a notify here if >>> + * there are outgoing parts to the buffer. Presumably the