diff options
Diffstat (limited to 'drivers/virtio')
| -rw-r--r-- | drivers/virtio/Kconfig | 2 | ||||
| -rw-r--r-- | drivers/virtio/virtio.c | 42 | ||||
| -rw-r--r-- | drivers/virtio/virtio_balloon.c | 8 | ||||
| -rw-r--r-- | drivers/virtio/virtio_input.c | 3 | ||||
| -rw-r--r-- | drivers/virtio/virtio_mmio.c | 27 | ||||
| -rw-r--r-- | drivers/virtio/virtio_pci_common.c | 423 | ||||
| -rw-r--r-- | drivers/virtio/virtio_pci_common.h | 51 | ||||
| -rw-r--r-- | drivers/virtio/virtio_pci_legacy.c | 9 | ||||
| -rw-r--r-- | drivers/virtio/virtio_pci_modern.c | 25 | ||||
| -rw-r--r-- | drivers/virtio/virtio_ring.c | 6 |
10 files changed, 264 insertions, 332 deletions
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 77590320d44c..623f72334fa5 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -75,7 +75,7 @@ config VIRTIO_MMIO_CMDLINE_DEVICES Allow virtio-mmio devices instantiation via the kernel command line or module parameters. Be aware that using incorrect parameters (base address in particular) can crash your system - you have been warned. - See Documentation/kernel-parameters.txt for details. + See Documentation/admin-guide/kernel-parameters.rst for details. If unsure, say 'N'. diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 7062bb0975a5..400d70b69379 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -100,11 +100,6 @@ static int virtio_uevent(struct device *_dv, struct kobj_uevent_env *env) dev->id.device, dev->id.vendor); } -static void add_status(struct virtio_device *dev, unsigned status) -{ - dev->config->set_status(dev, dev->config->get_status(dev) | status); -} - void virtio_check_driver_offered_feature(const struct virtio_device *vdev, unsigned int fbit) { @@ -145,14 +140,15 @@ void virtio_config_changed(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(virtio_config_changed); -static void virtio_config_disable(struct virtio_device *dev) +void virtio_config_disable(struct virtio_device *dev) { spin_lock_irq(&dev->config_lock); dev->config_enabled = false; spin_unlock_irq(&dev->config_lock); } +EXPORT_SYMBOL_GPL(virtio_config_disable); -static void virtio_config_enable(struct virtio_device *dev) +void virtio_config_enable(struct virtio_device *dev) { spin_lock_irq(&dev->config_lock); dev->config_enabled = true; @@ -161,8 +157,15 @@ static void virtio_config_enable(struct virtio_device *dev) dev->config_change_pending = false; spin_unlock_irq(&dev->config_lock); } +EXPORT_SYMBOL_GPL(virtio_config_enable); + +void virtio_add_status(struct virtio_device *dev, unsigned int status) +{ + dev->config->set_status(dev, dev->config->get_status(dev) | status); +} +EXPORT_SYMBOL_GPL(virtio_add_status); -static int virtio_finalize_features(struct virtio_device *dev) +int virtio_finalize_features(struct virtio_device *dev) { int ret = dev->config->finalize_features(dev); unsigned status; @@ -173,7 +176,7 @@ static int virtio_finalize_features(struct virtio_device *dev) if (!virtio_has_feature(dev, VIRTIO_F_VERSION_1)) return 0; - add_status(dev, VIRTIO_CONFIG_S_FEATURES_OK); + virtio_add_status(dev, VIRTIO_CONFIG_S_FEATURES_OK); status = dev->config->get_status(dev); if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) { dev_err(&dev->dev, "virtio: device refuses features: %x\n", @@ -182,6 +185,7 @@ static int virtio_finalize_features(struct virtio_device *dev) } return 0; } +EXPORT_SYMBOL_GPL(virtio_finalize_features); static int virtio_dev_probe(struct device *_d) { @@ -193,7 +197,7 @@ static int virtio_dev_probe(struct device *_d) u64 driver_features_legacy; /* We have a driver! */ - add_status(dev, VIRTIO_CONFIG_S_DRIVER); + virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER); /* Figure out what features the device supports. */ device_features = dev->config->get_features(dev); @@ -247,7 +251,7 @@ static int virtio_dev_probe(struct device *_d) return 0; err: - add_status(dev, VIRTIO_CONFIG_S_FAILED); + virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED); return err; } @@ -265,7 +269,7 @@ static int virtio_dev_remove(struct device *_d) WARN_ON_ONCE(dev->config->get_status(dev)); /* Acknowledge the device's existence again. */ - add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE); + virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE); return 0; } @@ -316,7 +320,7 @@ int register_virtio_device(struct virtio_device *dev) dev->config->reset(dev); /* Acknowledge that we've seen the device. */ - add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE); + virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE); INIT_LIST_HEAD(&dev->vqs); @@ -325,7 +329,7 @@ int register_virtio_device(struct virtio_device *dev) err = device_register(&dev->dev); out: if (err) - add_status(dev, VIRTIO_CONFIG_S_FAILED); + virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED); return err; } EXPORT_SYMBOL_GPL(register_virtio_device); @@ -365,18 +369,18 @@ int virtio_device_restore(struct virtio_device *dev) dev->config->reset(dev); /* Acknowledge that we've seen the device. */ - add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE); + virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE); /* Maybe driver failed before freeze. * Restore the failed status, for debugging. */ if (dev->failed) - add_status(dev, VIRTIO_CONFIG_S_FAILED); + virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED); if (!drv) return 0; /* We have a driver! */ - add_status(dev, VIRTIO_CONFIG_S_DRIVER); + virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER); ret = virtio_finalize_features(dev); if (ret) @@ -389,14 +393,14 @@ int virtio_device_restore(struct virtio_device *dev) } /* Finally, tell the device we're all set */ - add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK); + virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK); virtio_config_enable(dev); return 0; err: - add_status(dev, VIRTIO_CONFIG_S_FAILED); + virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED); return ret; } EXPORT_SYMBOL_GPL(virtio_device_restore); diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 181793f07852..4e1191508228 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -31,6 +31,7 @@ #include <linux/wait.h> #include <linux/mm.h> #include <linux/mount.h> +#include <linux/magic.h> /* * Balloon device works in 4K page units. So each page is pointed to by @@ -413,7 +414,8 @@ static int init_vqs(struct virtio_balloon *vb) * optionally stat. */ nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2; - err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names); + err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names, + NULL); if (err) return err; @@ -615,8 +617,12 @@ static void virtballoon_remove(struct virtio_device *vdev) cancel_work_sync(&vb->update_balloon_stats_work); remove_common(vb); +#ifdef CONFIG_BALLOON_COMPACTION if (vb->vb_dev_info.inode) iput(vb->vb_dev_info.inode); + + kern_unmount(balloon_mnt); +#endif kfree(vb); } diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c index 350a2a5a49db..79f1293cda93 100644 --- a/drivers/virtio/virtio_input.c +++ b/drivers/virtio/virtio_input.c @@ -173,7 +173,8 @@ static int virtinput_init_vqs(struct virtio_input *vi) static const char * const names[] = { "events", "status" }; int err; - err = vi->vdev->config->find_vqs(vi->vdev, 2, vqs, cbs, names); + err = vi->vdev->config->find_vqs(vi->vdev, 2, vqs, cbs, names, + NULL); if (err) return err; vi->evt = vqs[0]; diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 48bfea91dbca..78343b8f9034 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -59,6 +59,7 @@ #define pr_fmt(fmt) "virtio-mmio: " fmt #include <linux/acpi.h> +#include <linux/dma-mapping.h> #include <linux/highmem.h> #include <linux/interrupt.h> #include <linux/io.h> @@ -69,7 +70,7 @@ #include <linux/spinlock.h> #include <linux/virtio.h> #include <linux/virtio_config.h> -#include <linux/virtio_mmio.h> +#include <uapi/linux/virtio_mmio.h> #include <linux/virtio_ring.h> @@ -445,7 +446,8 @@ error_available: static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[]) + const char * const names[], + struct irq_affinity *desc) { struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); unsigned int irq = platform_get_irq(vm_dev->pdev, 0); @@ -489,6 +491,7 @@ static const struct virtio_config_ops virtio_mmio_config_ops = { }; +static void virtio_mmio_release_dev_empty(struct device *_d) {} /* Platform device */ @@ -497,6 +500,7 @@ static int virtio_mmio_probe(struct platform_device *pdev) struct virtio_mmio_device *vm_dev; struct resource *mem; unsigned long magic; + int rc; mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!mem) @@ -511,6 +515,7 @@ static int virtio_mmio_probe(struct platform_device *pdev) return -ENOMEM; vm_dev->vdev.dev.parent = &pdev->dev; + vm_dev->vdev.dev.release = virtio_mmio_release_dev_empty; vm_dev->vdev.config = &virtio_mmio_config_ops; vm_dev->pdev = pdev; INIT_LIST_HEAD(&vm_dev->virtqueues); @@ -545,9 +550,25 @@ static int virtio_mmio_probe(struct platform_device *pdev) } vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID); - if (vm_dev->version == 1) + if (vm_dev->version == 1) { writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE); + rc = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); + /* + * In the legacy case, ensure our coherently-allocated virtio + * ring will be at an address expressable as a 32-bit PFN. + */ + if (!rc) + dma_set_coherent_mask(&pdev->dev, + DMA_BIT_MASK(32 + PAGE_SHIFT)); + } else { + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + } + if (rc) + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (rc) + dev_warn(&pdev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n"); + platform_set_drvdata(pdev, vm_dev); return register_virtio_device(&vm_dev->vdev); diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index d9a905827967..df548a6fb844 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -33,11 +33,9 @@ void vp_synchronize_vectors(struct virtio_device *vdev) struct virtio_pci_device *vp_dev = to_vp_device(vdev); int i; - if (vp_dev->intx_enabled) - synchronize_irq(vp_dev->pci_dev->irq); - - for (i = 0; i < vp_dev->msix_vectors; ++i) - synchronize_irq(vp_dev->msix_entries[i].vector); + synchronize_irq(pci_irq_vector(vp_dev->pci_dev, 0)); + for (i = 1; i < vp_dev->msix_vectors; i++) + synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i)); } /* the notify function used when creating a virt queue */ @@ -62,16 +60,13 @@ static irqreturn_t vp_config_changed(int irq, void *opaque) static irqreturn_t vp_vring_interrupt(int irq, void *opaque) { struct virtio_pci_device *vp_dev = opaque; - struct virtio_pci_vq_info *info; irqreturn_t ret = IRQ_NONE; - unsigned long flags; + struct virtqueue *vq; - spin_lock_irqsave(&vp_dev->lock, flags); - list_for_each_entry(info, &vp_dev->virtqueues, node) { - if (vring_interrupt(irq, info->vq) == IRQ_HANDLED) + list_for_each_entry(vq, &vp_dev->vdev.vqs, list) { + if (vq->callback && vring_interrupt(irq, vq) == IRQ_HANDLED) ret = IRQ_HANDLED; } - spin_unlock_irqrestore(&vp_dev->lock, flags); return ret; } @@ -102,296 +97,232 @@ static irqreturn_t vp_interrupt(int irq, void *opaque) return vp_vring_interrupt(irq, opaque); } -static void vp_free_vectors(struct virtio_device *vdev) +static void vp_remove_vqs(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - int i; + struct virtqueue *vq, *n; - if (vp_dev->intx_enabled) { - free_irq(vp_dev->pci_dev->irq, vp_dev); - vp_dev->intx_enabled = 0; + list_for_each_entry_safe(vq, n, &vdev->vqs, list) { + if (vp_dev->msix_vector_map) { + int v = vp_dev->msix_vector_map[vq->index]; + + if (v != VIRTIO_MSI_NO_VECTOR) + free_irq(pci_irq_vector(vp_dev->pci_dev, v), + vq); + } + vp_dev->del_vq(vq); } +} - for (i = 0; i < vp_dev->msix_used_vectors; ++i) - free_irq(vp_dev->msix_entries[i].vector, vp_dev); +/* the config->del_vqs() implementation */ +void vp_del_vqs(struct virtio_device *vdev) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + int i; - for (i = 0; i < vp_dev->msix_vectors; i++) - if (vp_dev->msix_affinity_masks[i]) + if (WARN_ON_ONCE(list_empty_careful(&vdev->vqs))) + return; + + vp_remove_vqs(vdev); + + if (vp_dev->pci_dev->msix_enabled) { + for (i = 0; i < vp_dev->msix_vectors; i++) free_cpumask_var(vp_dev->msix_affinity_masks[i]); - if (vp_dev->msix_enabled) { /* Disable the vector used for configuration */ vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR); - pci_disable_msix(vp_dev->pci_dev); - vp_dev->msix_enabled = 0; + kfree(vp_dev->msix_affinity_masks); + kfree(vp_dev->msix_names); + kfree(vp_dev->msix_vector_map); } - vp_dev->msix_vectors = 0; - vp_dev->msix_used_vectors = 0; - kfree(vp_dev->msix_names); - vp_dev->msix_names = NULL; - kfree(vp_dev->msix_entries); - vp_dev->msix_entries = NULL; - kfree(vp_dev->msix_affinity_masks); - vp_dev->msix_affinity_masks = NULL; + free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev); + pci_free_irq_vectors(vp_dev->pci_dev); } -static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors, - bool per_vq_vectors) +static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs, + struct virtqueue *vqs[], vq_callback_t *callbacks[], + const char * const names[], struct irq_affinity *desc) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); const char *name = dev_name(&vp_dev->vdev.dev); - unsigned i, v; - int err = -ENOMEM; + int i, err = -ENOMEM, allocated_vectors, nvectors; + unsigned flags = PCI_IRQ_MSIX; + bool shared = false; + u16 msix_vec; - vp_dev->msix_vectors = nvectors; + if (desc) { + flags |= PCI_IRQ_AFFINITY; + desc->pre_vectors++; /* virtio config vector */ + } - vp_dev->msix_entries = kmalloc(nvectors * sizeof *vp_dev->msix_entries, - GFP_KERNEL); - if (!vp_dev->msix_entries) - goto error; - vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names, - GFP_KERNEL); + nvectors = 1; + for (i = 0; i < nvqs; i++) + if (callbacks[i]) + nvectors++; + + /* Try one vector per queue first. */ + err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors, + nvectors, flags, desc); + if (err < 0) { + /* Fallback to one vector for config, one shared for queues. */ + shared = true; + err = pci_alloc_irq_vectors(vp_dev->pci_dev, 2, 2, + PCI_IRQ_MSIX); + if (err < 0) + return err; + } + if (err < 0) + return err; + + vp_dev->msix_vectors = nvectors; + vp_dev->msix_names = kmalloc_array(nvectors, + sizeof(*vp_dev->msix_names), GFP_KERNEL); if (!vp_dev->msix_names) - goto error; - vp_dev->msix_affinity_masks - = kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks, - GFP_KERNEL); - if (!vp_dev->msix_affinity_masks) - goto error; - for (i = 0; i < nvectors; ++i) - if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i], - GFP_KERNEL)) - goto error; + goto out_free_irq_vectors; - for (i = 0; i < nvectors; ++i) - vp_dev->msix_entries[i].entry = i; + vp_dev->msix_affinity_masks = kcalloc(nvectors, + sizeof(*vp_dev->msix_affinity_masks), GFP_KERNEL); + if (!vp_dev->msix_affinity_masks) + goto out_free_msix_names; - err = pci_enable_msix_exact(vp_dev->pci_dev, - vp_dev->msix_entries, nvectors); - if (err) - goto error; - vp_dev->msix_enabled = 1; + for (i = 0; i < nvectors; ++i) { + if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i], + GFP_KERNEL)) + goto out_free_msix_affinity_masks; + } /* Set the vector used for configuration */ - v = vp_dev->msix_used_vectors; - snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names, + snprintf(vp_dev->msix_names[0], sizeof(*vp_dev->msix_names), "%s-config", name); - err = request_irq(vp_dev->msix_entries[v].vector, - vp_config_changed, 0, vp_dev->msix_names[v], - vp_dev); + err = request_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_config_changed, + 0, vp_dev->msix_names[0], vp_dev); if (err) - goto error; - ++vp_dev->msix_used_vectors; + goto out_free_msix_affinity_masks; - v = vp_dev->config_vector(vp_dev, v); /* Verify we had enough resources to assign the vector */ - if (v == VIRTIO_MSI_NO_VECTOR) { + if (vp_dev->config_vector(vp_dev, 0) == VIRTIO_MSI_NO_VECTOR) { err = -EBUSY; - goto error; - } - - if (!per_vq_vectors) { - /* Shared vector for all VQs */ - v = vp_dev->msix_used_vectors; - snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names, - "%s-virtqueues", name); - err = request_irq(vp_dev->msix_entries[v].vector, - vp_vring_interrupt, 0, vp_dev->msix_names[v], - vp_dev); - if (err) - goto error; - ++vp_dev->msix_used_vectors; + goto out_free_config_irq; } - return 0; -error: - vp_free_vectors(vdev); - return err; -} -static int vp_request_intx(struct virtio_device *vdev) -{ - int err; - struct virtio_pci_device *vp_dev = to_vp_device(vdev); + vp_dev->msix_vector_map = kmalloc_array(nvqs, + sizeof(*vp_dev->msix_vector_map), GFP_KERNEL); + if (!vp_dev->msix_vector_map) + goto out_disable_config_irq; - err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, - IRQF_SHARED, dev_name(&vdev->dev), vp_dev); - if (!err) - vp_dev->intx_enabled = 1; - return err; -} + allocated_vectors = 1; /* vector 0 is the config interrupt */ + for (i = 0; i < nvqs; ++i) { + if (!names[i]) { + vqs[i] = NULL; + continue; + } -static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index, - void (*callback)(struct virtqueue *vq), - const char *name, - u16 msix_vec) -{ - struct virtio_pci_device *vp_dev = to_vp_device(vdev); - struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL); - struct virtqueue *vq; - unsigned long flags; + if (callbacks[i]) + msix_vec = allocated_vectors; + else + msix_vec = VIRTIO_MSI_NO_VECTOR; - /* fill out our structure that represents an active queue */ - if (!info) - return ERR_PTR(-ENOMEM); + vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i], + msix_vec); + if (IS_ERR(vqs[i])) { + err = PTR_ERR(vqs[i]); + goto out_remove_vqs; + } - vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, msix_vec); - if (IS_ERR(vq)) - goto out_info; + if (msix_vec == VIRTIO_MSI_NO_VECTOR) { + vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR; + continue; + } - info->vq = vq; - if (callback) { - spin_lock_irqsave(&vp_dev->lock, flags); - list_add(&info->node, &vp_dev->virtqueues); - spin_unlock_irqrestore(&vp_dev->lock, flags); - } else { - INIT_LIST_HEAD(&info->node); + snprintf(vp_dev->msix_names[i + 1], + sizeof(*vp_dev->msix_names), "%s-%s", + dev_name(&vp_dev->vdev.dev), names[i]); + err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec), + vring_interrupt, IRQF_SHARED, + vp_dev->msix_names[i + 1], vqs[i]); + if (err) { + /* don't free this irq on error */ + vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR; + goto out_remove_vqs; + } + vp_dev->msix_vector_map[i] = msix_vec; + + /* + * Use a different vector for each queue if they are available, + * else share the same vector for all VQs. + */ + if (!shared) + allocated_vectors++; } - vp_dev->vqs[index] = info; - return vq; - -out_info: - kfree(info); - return vq; -} - -static void vp_del_vq(struct virtqueue *vq) -{ - struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); - struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index]; - unsigned long flags; - - spin_lock_irqsave(&vp_dev->lock, flags); - list_del(&info->node); - spin_unlock_irqrestore(&vp_dev->lock, flags); - - vp_dev->del_vq(info); - kfree(info); -} - -/* the config->del_vqs() implementation */ -void vp_del_vqs(struct virtio_device *vdev) -{ - struct virtio_pci_device *vp_dev = to_vp_device(vdev); - struct virtqueue *vq, *n; - struct virtio_pci_vq_info *info; + return 0; - list_for_each_entry_safe(vq, n, &vdev->vqs, list) { - info = vp_dev->vqs[vq->index]; - if (vp_dev->per_vq_vectors && - info->msix_vector != VIRTIO_MSI_NO_VECTOR) - free_irq(vp_dev->msix_entries[info->msix_vector].vector, - vq); - vp_del_vq(vq); +out_remove_vqs: + vp_remove_vqs(vdev); + kfree(vp_dev->msix_vector_map); +out_disable_config_irq: + vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR); +out_free_config_irq: + free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev); +out_free_msix_affinity_masks: + for (i = 0; i < nvectors; i++) { + if (vp_dev->msix_affinity_masks[i]) + free_cpumask_var(vp_dev->msix_affinity_masks[i]); } - vp_dev->per_vq_vectors = false; - - vp_free_vectors(vdev); - kfree(vp_dev->vqs); - vp_dev->vqs = NULL; + kfree(vp_dev->msix_affinity_masks); +out_free_msix_names: + kfree(vp_dev->msix_names); +out_free_irq_vectors: + pci_free_irq_vectors(vp_dev->pci_dev); + return err; } -static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], - vq_callback_t *callbacks[], - const char * const names[], - bool use_msix, - bool per_vq_vectors) +static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned nvqs, + struct virtqueue *vqs[], vq_callback_t *callbacks[], + const char * const names[]) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - u16 msix_vec; - int i, err, nvectors, allocated_vectors; + int i, err; - vp_dev->vqs = kmalloc(nvqs * sizeof *vp_dev->vqs, GFP_KERNEL); - if (!vp_dev->vqs) - return -ENOMEM; - - if (!use_msix) { - /* Old style: one normal interrupt for change and all vqs. */ - err = vp_request_intx(vdev); - if (err) - goto error_find; - } else { - if (per_vq_vectors) { - /* Best option: one for change interrupt, one per vq. */ - nvectors = 1; - for (i = 0; i < nvqs; ++i) - if (callbacks[i]) - ++nvectors; - } else { - /* Second best: one for change, shared for all vqs. */ - nvectors = 2; - } - - err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors); - if (err) - goto error_find; - } + err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED, + dev_name(&vdev->dev), vp_dev); + if (err) + return err; - vp_dev->per_vq_vectors = per_vq_vectors; - allocated_vectors = vp_dev->msix_used_vectors; for (i = 0; i < nvqs; ++i) { if (!names[i]) { vqs[i] = NULL; continue; - } else if (!callbacks[i] || !vp_dev->msix_enabled) - msix_vec = VIRTIO_MSI_NO_VECTOR; - else if (vp_dev->per_vq_vectors) - msix_vec = allocated_vectors++; - else - msix_vec = VP_MSIX_VQ_VECTOR; - vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i], msix_vec); + } + vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i], + VIRTIO_MSI_NO_VECTOR); if (IS_ERR(vqs[i])) { err = PTR_ERR(vqs[i]); - goto error_find; - } - - if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR) - continue; - - /* allocate per-vq irq if available and necessary */ - snprintf(vp_dev->msix_names[msix_vec], - sizeof *vp_dev->msix_names, - "%s-%s", - dev_name(&vp_dev->vdev.dev), names[i]); - err = request_irq(vp_dev->msix_entries[msix_vec].vector, - vring_interrupt, 0, - vp_dev->msix_names[msix_vec], - vqs[i]); - if (err) { - vp_del_vq(vqs[i]); - goto error_find; + goto out_remove_vqs; } } + return 0; -error_find: - vp_del_vqs(vdev); +out_remove_vqs: + vp_remove_vqs(vdev); + free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev); return err; } /* the config->find_vqs() implementation */ int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], - vq_callback_t *callbacks[], - const char * const names[]) + struct virtqueue *vqs[], vq_callback_t *callbacks[], + const char * const names[], struct irq_affinity *desc) { int err; - /* Try MSI-X with one vector per queue. */ - err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, true, true); + err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, desc); if (!err) return 0; - /* Fallback: MSI-X with one vector for config, one shared for queues. */ - err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, - true, false); - if (!err) - return 0; - /* Finally fall back to regular interrupts. */ - return vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, - false, false); + return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names); } const char *vp_bus_name(struct virtio_device *vdev) @@ -410,16 +341,15 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu) { struct virtio_device *vdev = vq->vdev; struct virtio_pci_device *vp_dev = to_vp_device(vdev); - struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index]; - struct cpumask *mask; - unsigned int irq; if (!vq->callback) return -EINVAL; - if (vp_dev->msix_enabled) { - mask = vp_dev->msix_affinity_masks[info->msix_vector]; - irq = vp_dev->msix_entries[info->msix_vector].vector; + if (vp_dev->pci_dev->msix_enabled) { + int vec = vp_dev->msix_vector_map[vq->index]; + struct cpumask *mask = vp_dev->msix_affinity_masks[vec]; + unsigned int irq = pci_irq_vector(vp_dev->pci_dev, vec); + if (cpu == -1) irq_set_affinity_hint(irq, NULL); else { @@ -431,6 +361,17 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu) return 0; } +const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + unsigned int *map = vp_dev->msix_vector_map; + + if (!map || map[index] == VIRTIO_MSI_NO_VECTOR) + return NULL; + + return pci_irq_get_affinity(vp_dev->pci_dev, map[index]); +} + #ifdef CONFIG_PM_SLEEP static int virtio_pci_freeze(struct device *dev) { @@ -499,8 +440,6 @@ static int virtio_pci_probe(struct pci_dev *pci_dev, vp_dev->vdev.dev.parent = &pci_dev->dev; vp_dev->vdev.dev.release = virtio_pci_release_dev; vp_dev->pci_dev = pci_dev; - INIT_LIST_HEAD(&vp_dev->virtqueues); - spin_lock_init(&vp_dev->lock); /* enable the device */ rc = pci_enable_device(pci_dev); diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index 28263200ed42..ac8c9d788964 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -31,17 +31,6 @@ #include <linux/highmem.h> #include <linux/spinlock.h> -struct virtio_pci_vq_info { - /* the actual virtqueue */ - struct virtqueue *vq; - - /* the list node for the virtqueues list */ - struct list_head node; - - /* MSI-X vector (or none) */ - unsigned msix_vector; -}; - /* Our device structure */ struct virtio_pci_device { struct virtio_device vdev; @@ -75,48 +64,25 @@ struct virtio_pci_device { /* the IO mapping for the PCI config space */ void __iomem *ioaddr; - /* a list of queues so we can dispatch IRQs */ - spinlock_t lock; - struct list_head virtqueues; - - /* array of all queues for house-keeping */ - struct virtio_pci_vq_info **vqs; - - /* MSI-X support */ - int msix_enabled; - int intx_enabled; - struct msix_entry *msix_entries; cpumask_var_t *msix_affinity_masks; /* Name strings for interrupts. This size should be enough, * and I'm too lazy to allocate each name separately. */ char (*msix_names)[256]; - /* Number of available vectors */ - unsigned msix_vectors; - /* Vectors allocated, excluding per-vq vectors if any */ - unsigned msix_used_vectors; - - /* Whether we have vector per vq */ - bool per_vq_vectors; + /* Total Number of MSI-X vectors (including per-VQ ones). */ + int msix_vectors; + /* Map of per-VQ MSI-X vectors, may be NULL */ + unsigned *msix_vector_map; struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev, - struct virtio_pci_vq_info *info, unsigned idx, void (*callback)(struct virtqueue *vq), const char *name, u16 msix_vec); - void (*del_vq)(struct virtio_pci_vq_info *info); + void (*del_vq)(struct virtqueue *vq); u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector); }; -/* Constants for MSI-X */ -/* Use first vector for configuration changes, second and the rest for - * virtqueues Thus, we need at least 2 vectors for MSI. */ -enum { - VP_MSIX_CONFIG_VECTOR = 0, - VP_MSIX_VQ_VECTOR = 1, -}; - /* Convert a generic virtio device to our structure */ static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev) { @@ -131,9 +97,8 @@ bool vp_notify(struct virtqueue *vq); void vp_del_vqs(struct virtio_device *vdev); /* the config->find_vqs() implementation */ int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], - vq_callback_t *callbacks[], - const char * const names[]); + struct virtqueue *vqs[], vq_callback_t *callbacks[], + const char * const names[], struct irq_affinity *desc); const char *vp_bus_name(struct virtio_device *vdev); /* Setup the affinity for a virtqueue: @@ -143,6 +108,8 @@ const char *vp_bus_name(struct virtio_device *vdev); */ int vp_set_vq_affinity(struct virtqueue *vq, int cpu); +const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index); + #if IS_ENABLED(CONFIG_VIRTIO_PCI_LEGACY) int virtio_pci_legacy_probe(struct virtio_pci_device *); void virtio_pci_legacy_remove(struct virtio_pci_device *); diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c index 6d9e5173d5fa..f7362c5fe18a 100644 --- a/drivers/virtio/virtio_pci_legacy.c +++ b/drivers/virtio/virtio_pci_legacy.c @@ -112,7 +112,6 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) } static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, - struct virtio_pci_vq_info *info, unsigned index, void (*callback)(struct virtqueue *vq), const char *name, @@ -130,8 +129,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN)) return ERR_PTR(-ENOENT); - info->msix_vector = msix_vec; - /* create the vring */ vq = vring_create_virtqueue(index, num, VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev, @@ -162,14 +159,13 @@ out_deactivate: return ERR_PTR(err); } -static void del_vq(struct virtio_pci_vq_info *info) +static void del_vq(struct virtqueue *vq) { - struct virtqueue *vq = info->vq; struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL); - if (vp_dev->msix_enabled) { + if (vp_dev->pci_dev->msix_enabled) { iowrite16(VIRTIO_MSI_NO_VECTOR, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); /* Flush the write out to device */ @@ -194,6 +190,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = { .finalize_features = vp_finalize_features, .bus_name = vp_bus_name, .set_vq_affinity = vp_set_vq_affinity, + .get_vq_affinity = vp_get_vq_affinity, }; /* the PCI probing function */ diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index e76bd91a29da..7bc3004b840e 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -33,12 +33,12 @@ static inline u8 vp_ioread8(u8 __iomem *addr) { return ioread8(addr); } -static inline u16 vp_ioread16 (u16 __iomem *addr) +static inline u16 vp_ioread16 (__le16 __iomem *addr) { return ioread16(addr); } -static inline u32 vp_ioread32(u32 __iomem *addr) +static inline u32 vp_ioread32(__le32 __iomem *addr) { return ioread32(addr); } @@ -48,12 +48,12 @@ static inline void vp_iowrite8(u8 value, u8 __iomem *addr) iowrite8(value, addr); } -static inline void vp_iowrite16(u16 value, u16 __iomem *addr) +static inline void vp_iowrite16(u16 value, __le16 __iomem *addr) { iowrite16(value, addr); } -static inline void vp_iowrite32(u32 value, u32 __iomem *addr) +static inline void vp_iowrite32(u32 value, __le32 __iomem *addr) { iowrite32(value, addr); } @@ -293,7 +293,6 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) } static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, - struct virtio_pci_vq_info *info, unsigned index, void (*callback)(struct virtqueue *vq), const char *name, @@ -323,8 +322,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, /* get offset of notification word for this vq */ off = vp_ioread16(&cfg->queue_notify_off); - info->msix_vector = msix_vec; - /* create the vring */ vq = vring_create_virtqueue(index, num, SMP_CACHE_BYTES, &vp_dev->vdev, @@ -387,13 +384,12 @@ err_map_notify: } static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], - vq_callback_t *callbacks[], - const char * const names[]) + struct virtqueue *vqs[], vq_callback_t *callbacks[], + const char * const names[], struct irq_affinity *desc) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); struct virtqueue *vq; - int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names); + int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, desc); if (rc) return rc; @@ -409,14 +405,13 @@ static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs, return 0; } -static void del_vq(struct virtio_pci_vq_info *info) +static void del_vq(struct virtqueue *vq) { - struct virtqueue *vq = info->vq; struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); vp_iowrite16(vq->index, &vp_dev->common->queue_select); - if (vp_dev->msix_enabled) { + if (vp_dev->pci_dev->msix_enabled) { vp_iowrite16(VIRTIO_MSI_NO_VECTOR, &vp_dev->common->queue_msix_vector); /* Flush the write out to device */ @@ -442,6 +437,7 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = { .finalize_features = vp_finalize_features, .bus_name = vp_bus_name, .set_vq_affinity = vp_set_vq_affinity, + .get_vq_affinity = vp_get_vq_affinity, }; static const struct virtio_config_ops virtio_pci_config_ops = { @@ -457,6 +453,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = { .finalize_features = vp_finalize_features, .bus_name = vp_bus_name, .set_vq_affinity = vp_set_vq_affinity, + .get_vq_affinity = vp_get_vq_affinity, }; /** diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 489bfc61cf30..409aeaa49246 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -420,7 +420,7 @@ unmap_release: if (i == err_idx) break; vring_unmap_one(vq, &desc[i]); - i = vq->vring.desc[i].next; + i = virtio16_to_cpu(_vq->vdev, vq->vring.desc[i].next); } vq->vq.num_free += total_sg; @@ -601,7 +601,7 @@ EXPORT_SYMBOL_GPL(virtqueue_kick); static void detach_buf(struct vring_virtqueue *vq, unsigned int head) { unsigned int i, j; - u16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT); + __virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT); /* Clear data ptr. */ vq->desc_state[head].data = NULL; @@ -649,7 +649,7 @@ static inline bool more_used(const struct vring_virtqueue *vq) * @vq: the struct virtqueue we're talking about. * @len: the length written into the buffer * - * If the driver wrote data into the buffer, @len will be set to the + * If the device wrote data into the buffer, @len will be set to the * amount written. This means you don't need to clear the buffer * beforehand to ensure there's no data leakage in the case of short * writes. |