diff --git a/MAINTAINERS b/MAINTAINERS index 981f02d6833d..12dd77fb4e4e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18114,9 +18114,18 @@ F: drivers/virtio/ F: include/linux/vdpa.h F: include/linux/virtio*.h F: include/uapi/linux/virtio_*.h -F: mm/balloon_compaction.c F: tools/virtio/ +VIRTIO BALLOON +M: "Michael S. Tsirkin" +M: David Hildenbrand +L: virtualization@lists.linux-foundation.org +S: Maintained +F: drivers/virtio/virtio_balloon.c +F: include/uapi/linux/virtio_balloon.h +F: include/linux/balloon_compaction.h +F: mm/balloon_compaction.c + VIRTIO CRYPTO DRIVER M: Gonglei L: virtualization@lists.linux-foundation.org @@ -18182,6 +18191,13 @@ S: Maintained F: drivers/iommu/virtio-iommu.c F: include/uapi/linux/virtio_iommu.h +VIRTIO MEM DRIVER +M: David Hildenbrand +L: virtualization@lists.linux-foundation.org +S: Maintained +F: drivers/virtio/virtio_mem.c +F: include/uapi/linux/virtio_mem.h + VIRTUAL BOX GUEST DEVICE DRIVER M: Hans de Goede M: Arnd Bergmann diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 47b4969d9b93..5be5a977da1b 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -35,6 +35,7 @@ int pxm_to_node(int pxm) return NUMA_NO_NODE; return pxm_to_node_map[pxm]; } +EXPORT_SYMBOL(pxm_to_node); int node_to_pxm(int node) { diff --git a/drivers/crypto/virtio/virtio_crypto_algs.c b/drivers/crypto/virtio/virtio_crypto_algs.c index fd045e64972a..cb8a6ea2a4bc 100644 --- a/drivers/crypto/virtio/virtio_crypto_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_algs.c @@ -350,13 +350,18 @@ __virtio_crypto_skcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req, int err; unsigned long flags; struct scatterlist outhdr, iv_sg, status_sg, **sgs; - int i; u64 dst_len; unsigned int num_out = 0, num_in = 0; int sg_total; uint8_t *iv; + struct scatterlist *sg; src_nents = sg_nents_for_len(req->src, req->cryptlen); + if (src_nents < 0) { + pr_err("Invalid number of src SG.\n"); + return src_nents; + } + dst_nents = sg_nents(req->dst); pr_debug("virtio_crypto: Number of sgs (src_nents: %d, dst_nents: %d)\n", @@ -402,6 +407,7 @@ __virtio_crypto_skcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req, goto free; } + dst_len = min_t(unsigned int, req->cryptlen, dst_len); pr_debug("virtio_crypto: src_len: %u, dst_len: %llu\n", req->cryptlen, dst_len); @@ -442,12 +448,12 @@ __virtio_crypto_skcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req, vc_sym_req->iv = iv; /* Source data */ - for (i = 0; i < src_nents; i++) - sgs[num_out++] = &req->src[i]; + for (sg = req->src; src_nents; sg = sg_next(sg), src_nents--) + sgs[num_out++] = sg; /* Destination data */ - for (i = 0; i < dst_nents; i++) - sgs[num_out + num_in++] = &req->dst[i]; + for (sg = req->dst; sg; sg = sg_next(sg)) + sgs[num_out + num_in++] = sg; /* Status */ sg_init_one(&status_sg, &vc_req->status, sizeof(vc_req->status)); @@ -577,10 +583,11 @@ static void virtio_crypto_skcipher_finalize_req( scatterwalk_map_and_copy(req->iv, req->dst, req->cryptlen - AES_BLOCK_SIZE, AES_BLOCK_SIZE, 0); - crypto_finalize_skcipher_request(vc_sym_req->base.dataq->engine, - req, err); kzfree(vc_sym_req->iv); virtcrypto_clear_request(&vc_sym_req->base); + + crypto_finalize_skcipher_request(vc_sym_req->base.dataq->engine, + req, err); } static struct virtio_crypto_algo virtio_crypto_algs[] = { { diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig index 3bfe72c59864..8f201d019f5a 100644 --- a/drivers/misc/mic/Kconfig +++ b/drivers/misc/mic/Kconfig @@ -116,7 +116,7 @@ config MIC_COSM config VOP tristate "VOP Driver" - depends on VOP_BUS && VHOST_DPN + depends on VOP_BUS select VHOST_RING select VIRTIO help diff --git a/drivers/net/caif/Kconfig b/drivers/net/caif/Kconfig index 1538ad194cf4..1f2f2e8209c3 100644 --- a/drivers/net/caif/Kconfig +++ b/drivers/net/caif/Kconfig @@ -50,7 +50,7 @@ config CAIF_HSI config CAIF_VIRTIO tristate "CAIF virtio transport driver" - depends on CAIF && HAS_DMA && VHOST_DPN + depends on CAIF && HAS_DMA select VHOST_RING select VIRTIO select GENERIC_ALLOCATOR diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index e8140065c8a5..3e1ceb8e9f2b 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -10,7 +10,7 @@ if VDPA config VDPA_SIM tristate "vDPA device simulator" - depends on RUNTIME_TESTING_MENU && HAS_DMA && VHOST_DPN + depends on RUNTIME_TESTING_MENU && HAS_DMA select VHOST_RING default n help diff --git a/drivers/vdpa/ifcvf/ifcvf_base.c b/drivers/vdpa/ifcvf/ifcvf_base.c index e24371d644b5..94bf0328b68d 100644 --- a/drivers/vdpa/ifcvf/ifcvf_base.c +++ b/drivers/vdpa/ifcvf/ifcvf_base.c @@ -185,6 +185,9 @@ void ifcvf_set_status(struct ifcvf_hw *hw, u8 status) void ifcvf_reset(struct ifcvf_hw *hw) { + hw->config_cb.callback = NULL; + hw->config_cb.private = NULL; + ifcvf_set_status(hw, 0); /* flush set_status, make sure VF is stopped, reset */ ifcvf_get_status(hw); diff --git a/drivers/vdpa/ifcvf/ifcvf_base.h b/drivers/vdpa/ifcvf/ifcvf_base.h index e80307092351..f4554412e607 100644 --- a/drivers/vdpa/ifcvf/ifcvf_base.h +++ b/drivers/vdpa/ifcvf/ifcvf_base.h @@ -27,6 +27,7 @@ ((1ULL << VIRTIO_NET_F_MAC) | \ (1ULL << VIRTIO_F_ANY_LAYOUT) | \ (1ULL << VIRTIO_F_VERSION_1) | \ + (1ULL << VIRTIO_NET_F_STATUS) | \ (1ULL << VIRTIO_F_ORDER_PLATFORM) | \ (1ULL << VIRTIO_F_IOMMU_PLATFORM) | \ (1ULL << VIRTIO_NET_F_MRG_RXBUF)) @@ -81,6 +82,9 @@ struct ifcvf_hw { void __iomem *net_cfg; struct vring_info vring[IFCVF_MAX_QUEUE_PAIRS * 2]; void __iomem * const *base; + char config_msix_name[256]; + struct vdpa_callback config_cb; + }; struct ifcvf_adapter { diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index abf6a061cab6..f5a60c14b979 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -18,6 +18,16 @@ #define DRIVER_AUTHOR "Intel Corporation" #define IFCVF_DRIVER_NAME "ifcvf" +static irqreturn_t ifcvf_config_changed(int irq, void *arg) +{ + struct ifcvf_hw *vf = arg; + + if (vf->config_cb.callback) + return vf->config_cb.callback(vf->config_cb.private); + + return IRQ_HANDLED; +} + static irqreturn_t ifcvf_intr_handler(int irq, void *arg) { struct vring_info *vring = arg; @@ -28,6 +38,68 @@ static irqreturn_t ifcvf_intr_handler(int irq, void *arg) return IRQ_HANDLED; } +static void ifcvf_free_irq_vectors(void *data) +{ + pci_free_irq_vectors(data); +} + +static void ifcvf_free_irq(struct ifcvf_adapter *adapter, int queues) +{ + struct pci_dev *pdev = adapter->pdev; + struct ifcvf_hw *vf = &adapter->vf; + int i; + + + for (i = 0; i < queues; i++) + devm_free_irq(&pdev->dev, vf->vring[i].irq, &vf->vring[i]); + + ifcvf_free_irq_vectors(pdev); +} + +static int ifcvf_request_irq(struct ifcvf_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct ifcvf_hw *vf = &adapter->vf; + int vector, i, ret, irq; + + ret = pci_alloc_irq_vectors(pdev, IFCVF_MAX_INTR, + IFCVF_MAX_INTR, PCI_IRQ_MSIX); + if (ret < 0) { + IFCVF_ERR(pdev, "Failed to alloc IRQ vectors\n"); + return ret; + } + + snprintf(vf->config_msix_name, 256, "ifcvf[%s]-config\n", + pci_name(pdev)); + vector = 0; + irq = pci_irq_vector(pdev, vector); + ret = devm_request_irq(&pdev->dev, irq, + ifcvf_config_changed, 0, + vf->config_msix_name, vf); + + for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) { + snprintf(vf->vring[i].msix_name, 256, "ifcvf[%s]-%d\n", + pci_name(pdev), i); + vector = i + IFCVF_MSI_QUEUE_OFF; + irq = pci_irq_vector(pdev, vector); + ret = devm_request_irq(&pdev->dev, irq, + ifcvf_intr_handler, 0, + vf->vring[i].msix_name, + &vf->vring[i]); + if (ret) { + IFCVF_ERR(pdev, + "Failed to request irq for vq %d\n", i); + ifcvf_free_irq(adapter, i); + + return ret; + } + + vf->vring[i].irq = irq; + } + + return 0; +} + static int ifcvf_start_datapath(void *private) { struct ifcvf_hw *vf = ifcvf_private_to_vf(private); @@ -118,17 +190,37 @@ static void ifcvf_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status) { struct ifcvf_adapter *adapter; struct ifcvf_hw *vf; + u8 status_old; + int ret; vf = vdpa_to_vf(vdpa_dev); adapter = dev_get_drvdata(vdpa_dev->dev.parent); + status_old = ifcvf_get_status(vf); + + if (status_old == status) + return; + + if ((status_old & VIRTIO_CONFIG_S_DRIVER_OK) && + !(status & VIRTIO_CONFIG_S_DRIVER_OK)) { + ifcvf_stop_datapath(adapter); + ifcvf_free_irq(adapter, IFCVF_MAX_QUEUE_PAIRS * 2); + } if (status == 0) { - ifcvf_stop_datapath(adapter); ifcvf_reset_vring(adapter); return; } - if (status & VIRTIO_CONFIG_S_DRIVER_OK) { + if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && + !(status_old & VIRTIO_CONFIG_S_DRIVER_OK)) { + ret = ifcvf_request_irq(adapter); + if (ret) { + status = ifcvf_get_status(vf); + status |= VIRTIO_CONFIG_S_FAILED; + ifcvf_set_status(vf, status); + return; + } + if (ifcvf_start_datapath(adapter) < 0) IFCVF_ERR(adapter->pdev, "Failed to set ifcvf vdpa status %u\n", @@ -254,7 +346,10 @@ static void ifcvf_vdpa_set_config(struct vdpa_device *vdpa_dev, static void ifcvf_vdpa_set_config_cb(struct vdpa_device *vdpa_dev, struct vdpa_callback *cb) { - /* We don't support config interrupt */ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + vf->config_cb.callback = cb->callback; + vf->config_cb.private = cb->private; } /* @@ -284,38 +379,6 @@ static const struct vdpa_config_ops ifc_vdpa_ops = { .set_config_cb = ifcvf_vdpa_set_config_cb, }; -static int ifcvf_request_irq(struct ifcvf_adapter *adapter) -{ - struct pci_dev *pdev = adapter->pdev; - struct ifcvf_hw *vf = &adapter->vf; - int vector, i, ret, irq; - - - for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) { - snprintf(vf->vring[i].msix_name, 256, "ifcvf[%s]-%d\n", - pci_name(pdev), i); - vector = i + IFCVF_MSI_QUEUE_OFF; - irq = pci_irq_vector(pdev, vector); - ret = devm_request_irq(&pdev->dev, irq, - ifcvf_intr_handler, 0, - vf->vring[i].msix_name, - &vf->vring[i]); - if (ret) { - IFCVF_ERR(pdev, - "Failed to request irq for vq %d\n", i); - return ret; - } - vf->vring[i].irq = irq; - } - - return 0; -} - -static void ifcvf_free_irq_vectors(void *data) -{ - pci_free_irq_vectors(data); -} - static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct device *dev = &pdev->dev; @@ -349,13 +412,6 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) return ret; } - ret = pci_alloc_irq_vectors(pdev, IFCVF_MAX_INTR, - IFCVF_MAX_INTR, PCI_IRQ_MSIX); - if (ret < 0) { - IFCVF_ERR(pdev, "Failed to alloc irq vectors\n"); - return ret; - } - ret = devm_add_action_or_reset(dev, ifcvf_free_irq_vectors, pdev); if (ret) { IFCVF_ERR(pdev, @@ -379,12 +435,6 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) adapter->pdev = pdev; adapter->vdpa.dma_dev = &pdev->dev; - ret = ifcvf_request_irq(adapter); - if (ret) { - IFCVF_ERR(pdev, "Failed to request MSI-X irq\n"); - goto err; - } - ret = ifcvf_init_hw(vf, pdev); if (ret) { IFCVF_ERR(pdev, "Failed to init IFCVF hw\n"); diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 01c456f7c1f7..c7334cc65bb2 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -101,7 +101,7 @@ static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx) static void vdpasim_vq_reset(struct vdpasim_virtqueue *vq) { - vq->ready = 0; + vq->ready = false; vq->desc_addr = 0; vq->driver_addr = 0; vq->device_addr = 0; @@ -131,9 +131,10 @@ static void vdpasim_work(struct work_struct *work) vdpasim, work); struct vdpasim_virtqueue *txq = &vdpasim->vqs[1]; struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0]; - size_t read, write, total_write; - int err; + ssize_t read, write; + size_t total_write; int pkts = 0; + int err; spin_lock(&vdpasim->lock); diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig index c4f273793595..2c75d164b827 100644 --- a/drivers/vhost/Kconfig +++ b/drivers/vhost/Kconfig @@ -13,15 +13,6 @@ config VHOST_RING This option is selected by any driver which needs to access the host side of a virtio ring. -config VHOST_DPN - bool - depends on !ARM || AEABI - default y - help - Anything selecting VHOST or VHOST_RING must depend on VHOST_DPN. - This excludes the deprecated ARM ABI since that forces a 4 byte - alignment on all structs - incompatible with virtio spec requirements. - config VHOST tristate select VHOST_IOTLB @@ -37,7 +28,7 @@ if VHOST_MENU config VHOST_NET tristate "Host kernel accelerator for virtio net" - depends on NET && EVENTFD && (TUN || !TUN) && (TAP || !TAP) && VHOST_DPN + depends on NET && EVENTFD && (TUN || !TUN) && (TAP || !TAP) select VHOST ---help--- This kernel module can be loaded in host kernel to accelerate @@ -49,7 +40,7 @@ config VHOST_NET config VHOST_SCSI tristate "VHOST_SCSI TCM fabric driver" - depends on TARGET_CORE && EVENTFD && VHOST_DPN + depends on TARGET_CORE && EVENTFD select VHOST default n ---help--- @@ -58,7 +49,7 @@ config VHOST_SCSI config VHOST_VSOCK tristate "vhost virtio-vsock driver" - depends on VSOCKETS && EVENTFD && VHOST_DPN + depends on VSOCKETS && EVENTFD select VHOST select VIRTIO_VSOCKETS_COMMON default n @@ -72,7 +63,7 @@ config VHOST_VSOCK config VHOST_VDPA tristate "Vhost driver for vDPA-based backend" - depends on EVENTFD && VHOST_DPN + depends on EVENTFD select VHOST depends on VDPA help diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 516519dcc8ff..e992decfec53 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1327,7 +1327,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) } vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX, UIO_MAXIOV + VHOST_NET_BATCH, - VHOST_NET_PKT_WEIGHT, VHOST_NET_WEIGHT, + VHOST_NET_PKT_WEIGHT, VHOST_NET_WEIGHT, true, NULL); vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 8b104f76f324..6fb4d7ecfa19 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1628,7 +1628,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f) vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick; } vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV, - VHOST_SCSI_WEIGHT, 0, NULL); + VHOST_SCSI_WEIGHT, 0, true, NULL); vhost_scsi_init_inflight(vs, NULL); diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c index 9a3a09005e03..0466921f4772 100644 --- a/drivers/vhost/test.c +++ b/drivers/vhost/test.c @@ -120,7 +120,7 @@ static int vhost_test_open(struct inode *inode, struct file *f) vqs[VHOST_TEST_VQ] = &n->vqs[VHOST_TEST_VQ]; n->vqs[VHOST_TEST_VQ].handle_kick = handle_vq_kick; vhost_dev_init(dev, vqs, VHOST_TEST_VQ_MAX, UIO_MAXIOV, - VHOST_TEST_PKT_WEIGHT, VHOST_TEST_WEIGHT, NULL); + VHOST_TEST_PKT_WEIGHT, VHOST_TEST_WEIGHT, true, NULL); f->private_data = n; diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 40e2a5747c98..7580e34f76c1 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -15,12 +15,14 @@ #include #include #include +#include #include #include #include #include #include #include +#include #include "vhost.h" @@ -70,6 +72,7 @@ struct vhost_vdpa { int nvqs; int virtio_id; int minor; + struct eventfd_ctx *config_ctx; }; static DEFINE_IDA(vhost_vdpa_ida); @@ -101,6 +104,17 @@ static irqreturn_t vhost_vdpa_virtqueue_cb(void *private) return IRQ_HANDLED; } +static irqreturn_t vhost_vdpa_config_cb(void *private) +{ + struct vhost_vdpa *v = private; + struct eventfd_ctx *config_ctx = v->config_ctx; + + if (config_ctx) + eventfd_signal(config_ctx, 1); + + return IRQ_HANDLED; +} + static void vhost_vdpa_reset(struct vhost_vdpa *v) { struct vdpa_device *vdpa = v->vdpa; @@ -288,6 +302,36 @@ static long vhost_vdpa_get_vring_num(struct vhost_vdpa *v, u16 __user *argp) return 0; } +static void vhost_vdpa_config_put(struct vhost_vdpa *v) +{ + if (v->config_ctx) + eventfd_ctx_put(v->config_ctx); +} + +static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp) +{ + struct vdpa_callback cb; + int fd; + struct eventfd_ctx *ctx; + + cb.callback = vhost_vdpa_config_cb; + cb.private = v->vdpa; + if (copy_from_user(&fd, argp, sizeof(fd))) + return -EFAULT; + + ctx = fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(fd); + swap(ctx, v->config_ctx); + + if (!IS_ERR_OR_NULL(ctx)) + eventfd_ctx_put(ctx); + + if (IS_ERR(v->config_ctx)) + return PTR_ERR(v->config_ctx); + + v->vdpa->config->set_config_cb(v->vdpa, &cb); + + return 0; +} static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, void __user *argp) { @@ -395,6 +439,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, case VHOST_SET_LOG_FD: r = -ENOIOCTLCMD; break; + case VHOST_VDPA_SET_CONFIG_CALL: + r = vhost_vdpa_set_config_call(v, argp); + break; default: r = vhost_dev_ioctl(&v->vdev, cmd, argp); if (r == -ENOIOCTLCMD) @@ -694,7 +741,7 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep) vqs[i] = &v->vqs[i]; vqs[i]->handle_kick = handle_vq_kick; } - vhost_dev_init(dev, vqs, nvqs, 0, 0, 0, + vhost_dev_init(dev, vqs, nvqs, 0, 0, 0, false, vhost_vdpa_process_iotlb_msg); dev->iotlb = vhost_iotlb_alloc(0, 0); @@ -729,6 +776,7 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) vhost_dev_stop(&v->vdev); vhost_vdpa_iotlb_free(v); vhost_vdpa_free_domain(v); + vhost_vdpa_config_put(v); vhost_dev_cleanup(&v->vdev); kfree(v->vdev.vqs); mutex_unlock(&d->mutex); @@ -739,12 +787,74 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) return 0; } +#ifdef CONFIG_MMU +static vm_fault_t vhost_vdpa_fault(struct vm_fault *vmf) +{ + struct vhost_vdpa *v = vmf->vma->vm_file->private_data; + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + struct vdpa_notification_area notify; + struct vm_area_struct *vma = vmf->vma; + u16 index = vma->vm_pgoff; + + notify = ops->get_vq_notification(vdpa, index); + + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + if (remap_pfn_range(vma, vmf->address & PAGE_MASK, + notify.addr >> PAGE_SHIFT, PAGE_SIZE, + vma->vm_page_prot)) + return VM_FAULT_SIGBUS; + + return VM_FAULT_NOPAGE; +} + +static const struct vm_operations_struct vhost_vdpa_vm_ops = { + .fault = vhost_vdpa_fault, +}; + +static int vhost_vdpa_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct vhost_vdpa *v = vma->vm_file->private_data; + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + struct vdpa_notification_area notify; + int index = vma->vm_pgoff; + + if (vma->vm_end - vma->vm_start != PAGE_SIZE) + return -EINVAL; + if ((vma->vm_flags & VM_SHARED) == 0) + return -EINVAL; + if (vma->vm_flags & VM_READ) + return -EINVAL; + if (index > 65535) + return -EINVAL; + if (!ops->get_vq_notification) + return -ENOTSUPP; + + /* To be safe and easily modelled by userspace, We only + * support the doorbell which sits on the page boundary and + * does not share the page with other registers. + */ + notify = ops->get_vq_notification(vdpa, index); + if (notify.addr & (PAGE_SIZE - 1)) + return -EINVAL; + if (vma->vm_end - vma->vm_start != notify.size) + return -ENOTSUPP; + + vma->vm_ops = &vhost_vdpa_vm_ops; + return 0; +} +#endif /* CONFIG_MMU */ + static const struct file_operations vhost_vdpa_fops = { .owner = THIS_MODULE, .open = vhost_vdpa_open, .release = vhost_vdpa_release, .write_iter = vhost_vdpa_chr_write_iter, .unlocked_ioctl = vhost_vdpa_unlocked_ioctl, +#ifdef CONFIG_MMU + .mmap = vhost_vdpa_mmap, +#endif /* CONFIG_MMU */ .compat_ioctl = compat_ptr_ioctl, }; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 596132a96cd5..062595ee1f83 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -166,11 +166,16 @@ static int vhost_poll_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct vhost_poll *poll = container_of(wait, struct vhost_poll, wait); + struct vhost_work *work = &poll->work; if (!(key_to_poll(key) & poll->mask)) return 0; - vhost_poll_queue(poll); + if (!poll->dev->use_worker) + work->fn(work); + else + vhost_poll_queue(poll); + return 0; } @@ -454,6 +459,7 @@ static size_t vhost_get_desc_size(struct vhost_virtqueue *vq, void vhost_dev_init(struct vhost_dev *dev, struct vhost_virtqueue **vqs, int nvqs, int iov_limit, int weight, int byte_weight, + bool use_worker, int (*msg_handler)(struct vhost_dev *dev, struct vhost_iotlb_msg *msg)) { @@ -471,6 +477,7 @@ void vhost_dev_init(struct vhost_dev *dev, dev->iov_limit = iov_limit; dev->weight = weight; dev->byte_weight = byte_weight; + dev->use_worker = use_worker; dev->msg_handler = msg_handler; init_llist_head(&dev->work_list); init_waitqueue_head(&dev->wait); @@ -534,6 +541,36 @@ bool vhost_dev_has_owner(struct vhost_dev *dev) } EXPORT_SYMBOL_GPL(vhost_dev_has_owner); +static void vhost_attach_mm(struct vhost_dev *dev) +{ + /* No owner, become one */ + if (dev->use_worker) { + dev->mm = get_task_mm(current); + } else { + /* vDPA device does not use worker thead, so there's + * no need to hold the address space for mm. This help + * to avoid deadlock in the case of mmap() which may + * held the refcnt of the file and depends on release + * method to remove vma. + */ + dev->mm = current->mm; + mmgrab(dev->mm); + } +} + +static void vhost_detach_mm(struct vhost_dev *dev) +{ + if (!dev->mm) + return; + + if (dev->use_worker) + mmput(dev->mm); + else + mmdrop(dev->mm); + + dev->mm = NULL; +} + /* Caller should have device mutex */ long vhost_dev_set_owner(struct vhost_dev *dev) { @@ -546,34 +583,37 @@ long vhost_dev_set_owner(struct vhost_dev *dev) goto err_mm; } - /* No owner, become one */ - dev->mm = get_task_mm(current); + vhost_attach_mm(dev); + dev->kcov_handle = kcov_common_handle(); - worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid); - if (IS_ERR(worker)) { - err = PTR_ERR(worker); - goto err_worker; + if (dev->use_worker) { + worker = kthread_create(vhost_worker, dev, + "vhost-%d", current->pid); + if (IS_ERR(worker)) { + err = PTR_ERR(worker); + goto err_worker; + } + + dev->worker = worker; + wake_up_process(worker); /* avoid contributing to loadavg */ + + err = vhost_attach_cgroups(dev); + if (err) + goto err_cgroup; } - dev->worker = worker; - wake_up_process(worker); /* avoid contributing to loadavg */ - - err = vhost_attach_cgroups(dev); - if (err) - goto err_cgroup; - err = vhost_dev_alloc_iovecs(dev); if (err) goto err_cgroup; return 0; err_cgroup: - kthread_stop(worker); - dev->worker = NULL; + if (dev->worker) { + kthread_stop(dev->worker); + dev->worker = NULL; + } err_worker: - if (dev->mm) - mmput(dev->mm); - dev->mm = NULL; + vhost_detach_mm(dev); dev->kcov_handle = 0; err_mm: return err; @@ -670,9 +710,7 @@ void vhost_dev_cleanup(struct vhost_dev *dev) dev->worker = NULL; dev->kcov_handle = 0; } - if (dev->mm) - mmput(dev->mm); - dev->mm = NULL; + vhost_detach_mm(dev); } EXPORT_SYMBOL_GPL(vhost_dev_cleanup); @@ -882,7 +920,7 @@ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq, #define vhost_put_user(vq, x, ptr) \ ({ \ - int ret = -EFAULT; \ + int ret; \ if (!vq->iotlb) { \ ret = __put_user(x, ptr); \ } else { \ @@ -1244,9 +1282,9 @@ static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access) } static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, - struct vring_desc __user *desc, - struct vring_avail __user *avail, - struct vring_used __user *used) + vring_desc_t __user *desc, + vring_avail_t __user *avail, + vring_used_t __user *used) { return access_ok(desc, vhost_get_desc_size(vq, num)) && @@ -1574,7 +1612,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg r = -EFAULT; break; } - eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd); + eventfp = f.fd == VHOST_FILE_UNBIND ? NULL : eventfd_fget(f.fd); if (IS_ERR(eventfp)) { r = PTR_ERR(eventfp); break; @@ -1590,7 +1628,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg r = -EFAULT; break; } - ctx = f.fd == -1 ? NULL : eventfd_ctx_fdget(f.fd); + ctx = f.fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(f.fd); if (IS_ERR(ctx)) { r = PTR_ERR(ctx); break; @@ -1602,7 +1640,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg r = -EFAULT; break; } - ctx = f.fd == -1 ? NULL : eventfd_ctx_fdget(f.fd); + ctx = f.fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(f.fd); if (IS_ERR(ctx)) { r = PTR_ERR(ctx); break; @@ -1727,7 +1765,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp) r = get_user(fd, (int __user *)argp); if (r < 0) break; - ctx = fd == -1 ? NULL : eventfd_ctx_fdget(fd); + ctx = fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(fd); if (IS_ERR(ctx)) { r = PTR_ERR(ctx); break; @@ -2300,7 +2338,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads, unsigned count) { - struct vring_used_elem __user *used; + vring_used_elem_t __user *used; u16 old, new; int start; diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index f8403bd46b85..c8e96a095d3b 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -67,9 +67,9 @@ struct vhost_virtqueue { /* The actual ring of buffers. */ struct mutex mutex; unsigned int num; - struct vring_desc __user *desc; - struct vring_avail __user *avail; - struct vring_used __user *used; + vring_desc_t __user *desc; + vring_avail_t __user *avail; + vring_used_t __user *used; const struct vhost_iotlb_map *meta_iotlb[VHOST_NUM_ADDRS]; struct file *kick; struct eventfd_ctx *call_ctx; @@ -154,6 +154,7 @@ struct vhost_dev { int weight; int byte_weight; u64 kcov_handle; + bool use_worker; int (*msg_handler)(struct vhost_dev *dev, struct vhost_iotlb_msg *msg); }; @@ -161,6 +162,7 @@ struct vhost_dev { bool vhost_exceeds_weight(struct vhost_virtqueue *vq, int pkts, int total_len); void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs, int iov_limit, int weight, int byte_weight, + bool use_worker, int (*msg_handler)(struct vhost_dev *dev, struct vhost_iotlb_msg *msg)); long vhost_dev_set_owner(struct vhost_dev *dev); diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index ba8e0d6cfd97..e059a9a47cdf 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -620,9 +620,9 @@ static inline int xfer_to_user(const struct vringh *vrh, */ int vringh_init_user(struct vringh *vrh, u64 features, unsigned int num, bool weak_barriers, - struct vring_desc __user *desc, - struct vring_avail __user *avail, - struct vring_used __user *used) + vring_desc_t __user *desc, + vring_avail_t __user *avail, + vring_used_t __user *used) { /* Sane power of 2 please! */ if (!num || num > 0xffff || (num & (num - 1))) { diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index fb4e944c4d0d..a483cec31d5c 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -632,7 +632,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file) vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs), UIO_MAXIOV, VHOST_VSOCK_PKT_WEIGHT, - VHOST_VSOCK_WEIGHT, NULL); + VHOST_VSOCK_WEIGHT, true, NULL); file->private_data = vsock; spin_lock_init(&vsock->send_pkt_list_lock); diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 69a32dfc318a..4c1e14615001 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -78,6 +78,23 @@ config VIRTIO_BALLOON If unsure, say M. +config VIRTIO_MEM + tristate "Virtio mem driver" + default m + depends on X86_64 + depends on VIRTIO + depends on MEMORY_HOTPLUG_SPARSE + depends on MEMORY_HOTREMOVE + select CONTIG_ALLOC + help + This driver provides access to virtio-mem paravirtualized memory + devices, allowing to hotplug and hotunplug memory. + + This driver was only tested under x86-64, but should theoretically + work on all architectures that support memory hotplug and hotremove. + + If unsure, say M. + config VIRTIO_INPUT tristate "Virtio input driver" depends on VIRTIO diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile index 29a1386ecc03..4d993791f2d7 100644 --- a/drivers/virtio/Makefile +++ b/drivers/virtio/Makefile @@ -7,3 +7,4 @@ virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o obj-$(CONFIG_VIRTIO_VDPA) += virtio_vdpa.o +obj-$(CONFIG_VIRTIO_MEM) += virtio_mem.o diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 51086a5afdd4..1f157d2f4952 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -1107,11 +1107,18 @@ static int virtballoon_restore(struct virtio_device *vdev) static int virtballoon_validate(struct virtio_device *vdev) { - /* Tell the host whether we care about poisoned pages. */ + /* + * Inform the hypervisor that our pages are poisoned or + * initialized. If we cannot do that then we should disable + * page reporting as it could potentially change the contents + * of our free pages. + */ if (!want_init_on_free() && (IS_ENABLED(CONFIG_PAGE_POISONING_NO_SANITY) || !page_poisoning_enabled())) __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON); + else if (!virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) + __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_REPORTING); __virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM); return 0; diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c new file mode 100644 index 000000000000..50c689f25045 --- /dev/null +++ b/drivers/virtio/virtio_mem.c @@ -0,0 +1,1965 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Virtio-mem device driver. + * + * Copyright Red Hat, Inc. 2020 + * + * Author(s): David Hildenbrand + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +static bool unplug_online = true; +module_param(unplug_online, bool, 0644); +MODULE_PARM_DESC(unplug_online, "Try to unplug online memory"); + +enum virtio_mem_mb_state { + /* Unplugged, not added to Linux. Can be reused later. */ + VIRTIO_MEM_MB_STATE_UNUSED = 0, + /* (Partially) plugged, not added to Linux. Error on add_memory(). */ + VIRTIO_MEM_MB_STATE_PLUGGED, + /* Fully plugged, fully added to Linux, offline. */ + VIRTIO_MEM_MB_STATE_OFFLINE, + /* Partially plugged, fully added to Linux, offline. */ + VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL, + /* Fully plugged, fully added to Linux, online (!ZONE_MOVABLE). */ + VIRTIO_MEM_MB_STATE_ONLINE, + /* Partially plugged, fully added to Linux, online (!ZONE_MOVABLE). */ + VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL, + /* + * Fully plugged, fully added to Linux, online (ZONE_MOVABLE). + * We are not allowed to allocate (unplug) parts of this block that + * are not movable (similar to gigantic pages). We will never allow + * to online OFFLINE_PARTIAL to ZONE_MOVABLE (as they would contain + * unmovable parts). + */ + VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE, + VIRTIO_MEM_MB_STATE_COUNT +}; + +struct virtio_mem { + struct virtio_device *vdev; + + /* We might first have to unplug all memory when starting up. */ + bool unplug_all_required; + + /* Workqueue that processes the plug/unplug requests. */ + struct work_struct wq; + atomic_t config_changed; + + /* Virtqueue for guest->host requests. */ + struct virtqueue *vq; + + /* Wait for a host response to a guest request. */ + wait_queue_head_t host_resp; + + /* Space for one guest request and the host response. */ + struct virtio_mem_req req; + struct virtio_mem_resp resp; + + /* The current size of the device. */ + uint64_t plugged_size; + /* The requested size of the device. */ + uint64_t requested_size; + + /* The device block size (for communicating with the device). */ + uint64_t device_block_size; + /* The translated node id. NUMA_NO_NODE in case not specified. */ + int nid; + /* Physical start address of the memory region. */ + uint64_t addr; + /* Maximum region size in bytes. */ + uint64_t region_size; + + /* The subblock size. */ + uint64_t subblock_size; + /* The number of subblocks per memory block. */ + uint32_t nb_sb_per_mb; + + /* Id of the first memory block of this device. */ + unsigned long first_mb_id; + /* Id of the last memory block of this device. */ + unsigned long last_mb_id; + /* Id of the last usable memory block of this device. */ + unsigned long last_usable_mb_id; + /* Id of the next memory bock to prepare when needed. */ + unsigned long next_mb_id; + + /* The parent resource for all memory added via this device. */ + struct resource *parent_resource; + + /* Summary of all memory block states. */ + unsigned long nb_mb_state[VIRTIO_MEM_MB_STATE_COUNT]; +#define VIRTIO_MEM_NB_OFFLINE_THRESHOLD 10 + + /* + * One byte state per memory block. + * + * Allocated via vmalloc(). When preparing new blocks, resized + * (alloc+copy+free) when needed (crossing pages with the next mb). + * (when crossing pages). + * + * With 128MB memory blocks, we have states for 512GB of memory in one + * page. + */ + uint8_t *mb_state; + + /* + * $nb_sb_per_mb bit per memory block. Handled similar to mb_state. + * + * With 4MB subblocks, we manage 128GB of memory in one page. + */ + unsigned long *sb_bitmap; + + /* + * Mutex that protects the nb_mb_state, mb_state, and sb_bitmap. + * + * When this lock is held the pointers can't change, ONLINE and + * OFFLINE blocks can't change the state and no subblocks will get + * plugged/unplugged. + */ + struct mutex hotplug_mutex; + bool hotplug_active; + + /* An error occurred we cannot handle - stop processing requests. */ + bool broken; + + /* The driver is being removed. */ + spinlock_t removal_lock; + bool removing; + + /* Timer for retrying to plug/unplug memory. */ + struct hrtimer retry_timer; + unsigned int retry_timer_ms; +#define VIRTIO_MEM_RETRY_TIMER_MIN_MS 50000 +#define VIRTIO_MEM_RETRY_TIMER_MAX_MS 300000 + + /* Memory notifier (online/offline events). */ + struct notifier_block memory_notifier; + + /* Next device in the list of virtio-mem devices. */ + struct list_head next; +}; + +/* + * We have to share a single online_page callback among all virtio-mem + * devices. We use RCU to iterate the list in the callback. + */ +static DEFINE_MUTEX(virtio_mem_mutex); +static LIST_HEAD(virtio_mem_devices); + +static void virtio_mem_online_page_cb(struct page *page, unsigned int order); + +/* + * Register a virtio-mem device so it will be considered for the online_page + * callback. + */ +static int register_virtio_mem_device(struct virtio_mem *vm) +{ + int rc = 0; + + /* First device registers the callback. */ + mutex_lock(&virtio_mem_mutex); + if (list_empty(&virtio_mem_devices)) + rc = set_online_page_callback(&virtio_mem_online_page_cb); + if (!rc) + list_add_rcu(&vm->next, &virtio_mem_devices); + mutex_unlock(&virtio_mem_mutex); + + return rc; +} + +/* + * Unregister a virtio-mem device so it will no longer be considered for the + * online_page callback. + */ +static void unregister_virtio_mem_device(struct virtio_mem *vm) +{ + /* Last device unregisters the callback. */ + mutex_lock(&virtio_mem_mutex); + list_del_rcu(&vm->next); + if (list_empty(&virtio_mem_devices)) + restore_online_page_callback(&virtio_mem_online_page_cb); + mutex_unlock(&virtio_mem_mutex); + + synchronize_rcu(); +} + +/* + * Calculate the memory block id of a given address. + */ +static unsigned long virtio_mem_phys_to_mb_id(unsigned long addr) +{ + return addr / memory_block_size_bytes(); +} + +/* + * Calculate the physical start address of a given memory block id. + */ +static unsigned long virtio_mem_mb_id_to_phys(unsigned long mb_id) +{ + return mb_id * memory_block_size_bytes(); +} + +/* + * Calculate the subblock id of a given address. + */ +static unsigned long virtio_mem_phys_to_sb_id(struct virtio_mem *vm, + unsigned long addr) +{ + const unsigned long mb_id = virtio_mem_phys_to_mb_id(addr); + const unsigned long mb_addr = virtio_mem_mb_id_to_phys(mb_id); + + return (addr - mb_addr) / vm->subblock_size; +} + +/* + * Set the state of a memory block, taking care of the state counter. + */ +static void virtio_mem_mb_set_state(struct virtio_mem *vm, unsigned long mb_id, + enum virtio_mem_mb_state state) +{ + const unsigned long idx = mb_id - vm->first_mb_id; + enum virtio_mem_mb_state old_state; + + old_state = vm->mb_state[idx]; + vm->mb_state[idx] = state; + + BUG_ON(vm->nb_mb_state[old_state] == 0); + vm->nb_mb_state[old_state]--; + vm->nb_mb_state[state]++; +} + +/* + * Get the state of a memory block. + */ +static enum virtio_mem_mb_state virtio_mem_mb_get_state(struct virtio_mem *vm, + unsigned long mb_id) +{ + const unsigned long idx = mb_id - vm->first_mb_id; + + return vm->mb_state[idx]; +} + +/* + * Prepare the state array for the next memory block. + */ +static int virtio_mem_mb_state_prepare_next_mb(struct virtio_mem *vm) +{ + unsigned long old_bytes = vm->next_mb_id - vm->first_mb_id + 1; + unsigned long new_bytes = vm->next_mb_id - vm->first_mb_id + 2; + int old_pages = PFN_UP(old_bytes); + int new_pages = PFN_UP(new_bytes); + uint8_t *new_mb_state; + + if (vm->mb_state && old_pages == new_pages) + return 0; + + new_mb_state = vzalloc(new_pages * PAGE_SIZE); + if (!new_mb_state) + return -ENOMEM; + + mutex_lock(&vm->hotplug_mutex); + if (vm->mb_state) + memcpy(new_mb_state, vm->mb_state, old_pages * PAGE_SIZE); + vfree(vm->mb_state); + vm->mb_state = new_mb_state; + mutex_unlock(&vm->hotplug_mutex); + + return 0; +} + +#define virtio_mem_for_each_mb_state(_vm, _mb_id, _state) \ + for (_mb_id = _vm->first_mb_id; \ + _mb_id < _vm->next_mb_id && _vm->nb_mb_state[_state]; \ + _mb_id++) \ + if (virtio_mem_mb_get_state(_vm, _mb_id) == _state) + +#define virtio_mem_for_each_mb_state_rev(_vm, _mb_id, _state) \ + for (_mb_id = _vm->next_mb_id - 1; \ + _mb_id >= _vm->first_mb_id && _vm->nb_mb_state[_state]; \ + _mb_id--) \ + if (virtio_mem_mb_get_state(_vm, _mb_id) == _state) + +/* + * Mark all selected subblocks plugged. + * + * Will not modify the state of the memory block. + */ +static void virtio_mem_mb_set_sb_plugged(struct virtio_mem *vm, + unsigned long mb_id, int sb_id, + int count) +{ + const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id; + + __bitmap_set(vm->sb_bitmap, bit, count); +} + +/* + * Mark all selected subblocks unplugged. + * + * Will not modify the state of the memory block. + */ +static void virtio_mem_mb_set_sb_unplugged(struct virtio_mem *vm, + unsigned long mb_id, int sb_id, + int count) +{ + const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id; + + __bitmap_clear(vm->sb_bitmap, bit, count); +} + +/* + * Test if all selected subblocks are plugged. + */ +static bool virtio_mem_mb_test_sb_plugged(struct virtio_mem *vm, + unsigned long mb_id, int sb_id, + int count) +{ + const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id; + + if (count == 1) + return test_bit(bit, vm->sb_bitmap); + + /* TODO: Helper similar to bitmap_set() */ + return find_next_zero_bit(vm->sb_bitmap, bit + count, bit) >= + bit + count; +} + +/* + * Test if all selected subblocks are unplugged. + */ +static bool virtio_mem_mb_test_sb_unplugged(struct virtio_mem *vm, + unsigned long mb_id, int sb_id, + int count) +{ + const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id; + + /* TODO: Helper similar to bitmap_set() */ + return find_next_bit(vm->sb_bitmap, bit + count, bit) >= bit + count; +} + +/* + * Find the first unplugged subblock. Returns vm->nb_sb_per_mb in case there is + * none. + */ +static int virtio_mem_mb_first_unplugged_sb(struct virtio_mem *vm, + unsigned long mb_id) +{ + const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb; + + return find_next_zero_bit(vm->sb_bitmap, bit + vm->nb_sb_per_mb, bit) - + bit; +} + +/* + * Prepare the subblock bitmap for the next memory block. + */ +static int virtio_mem_sb_bitmap_prepare_next_mb(struct virtio_mem *vm) +{ + const unsigned long old_nb_mb = vm->next_mb_id - vm->first_mb_id; + const unsigned long old_nb_bits = old_nb_mb * vm->nb_sb_per_mb; + const unsigned long new_nb_bits = (old_nb_mb + 1) * vm->nb_sb_per_mb; + int old_pages = PFN_UP(BITS_TO_LONGS(old_nb_bits) * sizeof(long)); + int new_pages = PFN_UP(BITS_TO_LONGS(new_nb_bits) * sizeof(long)); + unsigned long *new_sb_bitmap, *old_sb_bitmap; + + if (vm->sb_bitmap && old_pages == new_pages) + return 0; + + new_sb_bitmap = vzalloc(new_pages * PAGE_SIZE); + if (!new_sb_bitmap) + return -ENOMEM; + + mutex_lock(&vm->hotplug_mutex); + if (new_sb_bitmap) + memcpy(new_sb_bitmap, vm->sb_bitmap, old_pages * PAGE_SIZE); + + old_sb_bitmap = vm->sb_bitmap; + vm->sb_bitmap = new_sb_bitmap; + mutex_unlock(&vm->hotplug_mutex); + + vfree(old_sb_bitmap); + return 0; +} + +/* + * Try to add a memory block to Linux. This will usually only fail + * if out of memory. + * + * Must not be called with the vm->hotplug_mutex held (possible deadlock with + * onlining code). + * + * Will not modify the state of the memory block. + */ +static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id) +{ + const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id); + int nid = vm->nid; + + if (nid == NUMA_NO_NODE) + nid = memory_add_physaddr_to_nid(addr); + + dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id); + return add_memory(nid, addr, memory_block_size_bytes()); +} + +/* + * Try to remove a memory block from Linux. Will only fail if the memory block + * is not offline. + * + * Must not be called with the vm->hotplug_mutex held (possible deadlock with + * onlining code). + * + * Will not modify the state of the memory block. + */ +static int virtio_mem_mb_remove(struct virtio_mem *vm, unsigned long mb_id) +{ + const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id); + int nid = vm->nid; + + if (nid == NUMA_NO_NODE) + nid = memory_add_physaddr_to_nid(addr); + + dev_dbg(&vm->vdev->dev, "removing memory block: %lu\n", mb_id); + return remove_memory(nid, addr, memory_block_size_bytes()); +} + +/* + * Try to offline and remove a memory block from Linux. + * + * Must not be called with the vm->hotplug_mutex held (possible deadlock with + * onlining code). + * + * Will not modify the state of the memory block. + */ +static int virtio_mem_mb_offline_and_remove(struct virtio_mem *vm, + unsigned long mb_id) +{ + const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id); + int nid = vm->nid; + + if (nid == NUMA_NO_NODE) + nid = memory_add_physaddr_to_nid(addr); + + dev_dbg(&vm->vdev->dev, "offlining and removing memory block: %lu\n", + mb_id); + return offline_and_remove_memory(nid, addr, memory_block_size_bytes()); +} + +/* + * Trigger the workqueue so the device can perform its magic. + */ +static void virtio_mem_retry(struct virtio_mem *vm) +{ + unsigned long flags; + + spin_lock_irqsave(&vm->removal_lock, flags); + if (!vm->removing) + queue_work(system_freezable_wq, &vm->wq); + spin_unlock_irqrestore(&vm->removal_lock, flags); +} + +static int virtio_mem_translate_node_id(struct virtio_mem *vm, uint16_t node_id) +{ + int node = NUMA_NO_NODE; + +#if defined(CONFIG_ACPI_NUMA) + if (virtio_has_feature(vm->vdev, VIRTIO_MEM_F_ACPI_PXM)) + node = pxm_to_node(node_id); +#endif + return node; +} + +/* + * Test if a virtio-mem device overlaps with the given range. Can be called + * from (notifier) callbacks lockless. + */ +static bool virtio_mem_overlaps_range(struct virtio_mem *vm, + unsigned long start, unsigned long size) +{ + unsigned long dev_start = virtio_mem_mb_id_to_phys(vm->first_mb_id); + unsigned long dev_end = virtio_mem_mb_id_to_phys(vm->last_mb_id) + + memory_block_size_bytes(); + + return start < dev_end && dev_start < start + size; +} + +/* + * Test if a virtio-mem device owns a memory block. Can be called from + * (notifier) callbacks lockless. + */ +static bool virtio_mem_owned_mb(struct virtio_mem *vm, unsigned long mb_id) +{ + return mb_id >= vm->first_mb_id && mb_id <= vm->last_mb_id; +} + +static int virtio_mem_notify_going_online(struct virtio_mem *vm, + unsigned long mb_id, + enum zone_type zone) +{ + switch (virtio_mem_mb_get_state(vm, mb_id)) { + case VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL: + /* + * We won't allow to online a partially plugged memory block + * to the MOVABLE zone - it would contain unmovable parts. + */ + if (zone == ZONE_MOVABLE) { + dev_warn_ratelimited(&vm->vdev->dev, + "memory block has holes, MOVABLE not supported\n"); + return NOTIFY_BAD; + } + return NOTIFY_OK; + case VIRTIO_MEM_MB_STATE_OFFLINE: + return NOTIFY_OK; + default: + break; + } + dev_warn_ratelimited(&vm->vdev->dev, + "memory block onlining denied\n"); + return NOTIFY_BAD; +} + +static void virtio_mem_notify_offline(struct virtio_mem *vm, + unsigned long mb_id) +{ + switch (virtio_mem_mb_get_state(vm, mb_id)) { + case VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL: + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL); + break; + case VIRTIO_MEM_MB_STATE_ONLINE: + case VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE: + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE); + break; + default: + BUG(); + break; + } + + /* + * Trigger the workqueue, maybe we can now unplug memory. Also, + * when we offline and remove a memory block, this will re-trigger + * us immediately - which is often nice because the removal of + * the memory block (e.g., memmap) might have freed up memory + * on other memory blocks we manage. + */ + virtio_mem_retry(vm); +} + +static void virtio_mem_notify_online(struct virtio_mem *vm, unsigned long mb_id, + enum zone_type zone) +{ + unsigned long nb_offline; + + switch (virtio_mem_mb_get_state(vm, mb_id)) { + case VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL: + BUG_ON(zone == ZONE_MOVABLE); + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL); + break; + case VIRTIO_MEM_MB_STATE_OFFLINE: + if (zone == ZONE_MOVABLE) + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE); + else + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_ONLINE); + break; + default: + BUG(); + break; + } + nb_offline = vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] + + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL]; + + /* see if we can add new blocks now that we onlined one block */ + if (nb_offline == VIRTIO_MEM_NB_OFFLINE_THRESHOLD - 1) + virtio_mem_retry(vm); +} + +static void virtio_mem_notify_going_offline(struct virtio_mem *vm, + unsigned long mb_id) +{ + const unsigned long nr_pages = PFN_DOWN(vm->subblock_size); + struct page *page; + unsigned long pfn; + int sb_id, i; + + for (sb_id = 0; sb_id < vm->nb_sb_per_mb; sb_id++) { + if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1)) + continue; + /* + * Drop our reference to the pages so the memory can get + * offlined and add the unplugged pages to the managed + * page counters (so offlining code can correctly subtract + * them again). + */ + pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) + + sb_id * vm->subblock_size); + adjust_managed_page_count(pfn_to_page(pfn), nr_pages); + for (i = 0; i < nr_pages; i++) { + page = pfn_to_page(pfn + i); + if (WARN_ON(!page_ref_dec_and_test(page))) + dump_page(page, "unplugged page referenced"); + } + } +} + +static void virtio_mem_notify_cancel_offline(struct virtio_mem *vm, + unsigned long mb_id) +{ + const unsigned long nr_pages = PFN_DOWN(vm->subblock_size); + unsigned long pfn; + int sb_id, i; + + for (sb_id = 0; sb_id < vm->nb_sb_per_mb; sb_id++) { + if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1)) + continue; + /* + * Get the reference we dropped when going offline and + * subtract the unplugged pages from the managed page + * counters. + */ + pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) + + sb_id * vm->subblock_size); + adjust_managed_page_count(pfn_to_page(pfn), -nr_pages); + for (i = 0; i < nr_pages; i++) + page_ref_inc(pfn_to_page(pfn + i)); + } +} + +/* + * This callback will either be called synchronously from add_memory() or + * asynchronously (e.g., triggered via user space). We have to be careful + * with locking when calling add_memory(). + */ +static int virtio_mem_memory_notifier_cb(struct notifier_block *nb, + unsigned long action, void *arg) +{ + struct virtio_mem *vm = container_of(nb, struct virtio_mem, + memory_notifier); + struct memory_notify *mhp = arg; + const unsigned long start = PFN_PHYS(mhp->start_pfn); + const unsigned long size = PFN_PHYS(mhp->nr_pages); + const unsigned long mb_id = virtio_mem_phys_to_mb_id(start); + enum zone_type zone; + int rc = NOTIFY_OK; + + if (!virtio_mem_overlaps_range(vm, start, size)) + return NOTIFY_DONE; + + /* + * Memory is onlined/offlined in memory block granularity. We cannot + * cross virtio-mem device boundaries and memory block boundaries. Bail + * out if this ever changes. + */ + if (WARN_ON_ONCE(size != memory_block_size_bytes() || + !IS_ALIGNED(start, memory_block_size_bytes()))) + return NOTIFY_BAD; + + /* + * Avoid circular locking lockdep warnings. We lock the mutex + * e.g., in MEM_GOING_ONLINE and unlock it in MEM_ONLINE. The + * blocking_notifier_call_chain() has it's own lock, which gets unlocked + * between both notifier calls and will bail out. False positive. + */ + lockdep_off(); + + switch (action) { + case MEM_GOING_OFFLINE: + mutex_lock(&vm->hotplug_mutex); + if (vm->removing) { + rc = notifier_from_errno(-EBUSY); + mutex_unlock(&vm->hotplug_mutex); + break; + } + vm->hotplug_active = true; + virtio_mem_notify_going_offline(vm, mb_id); + break; + case MEM_GOING_ONLINE: + mutex_lock(&vm->hotplug_mutex); + if (vm->removing) { + rc = notifier_from_errno(-EBUSY); + mutex_unlock(&vm->hotplug_mutex); + break; + } + vm->hotplug_active = true; + zone = page_zonenum(pfn_to_page(mhp->start_pfn)); + rc = virtio_mem_notify_going_online(vm, mb_id, zone); + break; + case MEM_OFFLINE: + virtio_mem_notify_offline(vm, mb_id); + vm->hotplug_active = false; + mutex_unlock(&vm->hotplug_mutex); + break; + case MEM_ONLINE: + zone = page_zonenum(pfn_to_page(mhp->start_pfn)); + virtio_mem_notify_online(vm, mb_id, zone); + vm->hotplug_active = false; + mutex_unlock(&vm->hotplug_mutex); + break; + case MEM_CANCEL_OFFLINE: + if (!vm->hotplug_active) + break; + virtio_mem_notify_cancel_offline(vm, mb_id); + vm->hotplug_active = false; + mutex_unlock(&vm->hotplug_mutex); + break; + case MEM_CANCEL_ONLINE: + if (!vm->hotplug_active) + break; + vm->hotplug_active = false; + mutex_unlock(&vm->hotplug_mutex); + break; + default: + break; + } + + lockdep_on(); + + return rc; +} + +/* + * Set a range of pages PG_offline. Remember pages that were never onlined + * (via generic_online_page()) using PageDirty(). + */ +static void virtio_mem_set_fake_offline(unsigned long pfn, + unsigned int nr_pages, bool onlined) +{ + for (; nr_pages--; pfn++) { + struct page *page = pfn_to_page(pfn); + + __SetPageOffline(page); + if (!onlined) { + SetPageDirty(page); + /* FIXME: remove after cleanups */ + ClearPageReserved(page); + } + } +} + +/* + * Clear PG_offline from a range of pages. If the pages were never onlined, + * (via generic_online_page()), clear PageDirty(). + */ +static void virtio_mem_clear_fake_offline(unsigned long pfn, + unsigned int nr_pages, bool onlined) +{ + for (; nr_pages--; pfn++) { + struct page *page = pfn_to_page(pfn); + + __ClearPageOffline(page); + if (!onlined) + ClearPageDirty(page); + } +} + +/* + * Release a range of fake-offline pages to the buddy, effectively + * fake-onlining them. + */ +static void virtio_mem_fake_online(unsigned long pfn, unsigned int nr_pages) +{ + const int order = MAX_ORDER - 1; + int i; + + /* + * We are always called with subblock granularity, which is at least + * aligned to MAX_ORDER - 1. + */ + for (i = 0; i < nr_pages; i += 1 << order) { + struct page *page = pfn_to_page(pfn + i); + + /* + * If the page is PageDirty(), it was kept fake-offline when + * onlining the memory block. Otherwise, it was allocated + * using alloc_contig_range(). All pages in a subblock are + * alike. + */ + if (PageDirty(page)) { + virtio_mem_clear_fake_offline(pfn + i, 1 << order, + false); + generic_online_page(page, order); + } else { + virtio_mem_clear_fake_offline(pfn + i, 1 << order, + true); + free_contig_range(pfn + i, 1 << order); + adjust_managed_page_count(page, 1 << order); + } + } +} + +static void virtio_mem_online_page_cb(struct page *page, unsigned int order) +{ + const unsigned long addr = page_to_phys(page); + const unsigned long mb_id = virtio_mem_phys_to_mb_id(addr); + struct virtio_mem *vm; + int sb_id; + + /* + * We exploit here that subblocks have at least MAX_ORDER - 1 + * size/alignment and that this callback is is called with such a + * size/alignment. So we cannot cross subblocks and therefore + * also not memory blocks. + */ + rcu_read_lock(); + list_for_each_entry_rcu(vm, &virtio_mem_devices, next) { + if (!virtio_mem_owned_mb(vm, mb_id)) + continue; + + sb_id = virtio_mem_phys_to_sb_id(vm, addr); + /* + * If plugged, online the pages, otherwise, set them fake + * offline (PageOffline). + */ + if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1)) + generic_online_page(page, order); + else + virtio_mem_set_fake_offline(PFN_DOWN(addr), 1 << order, + false); + rcu_read_unlock(); + return; + } + rcu_read_unlock(); + + /* not virtio-mem memory, but e.g., a DIMM. online it */ + generic_online_page(page, order); +} + +static uint64_t virtio_mem_send_request(struct virtio_mem *vm, + const struct virtio_mem_req *req) +{ + struct scatterlist *sgs[2], sg_req, sg_resp; + unsigned int len; + int rc; + + /* don't use the request residing on the stack (vaddr) */ + vm->req = *req; + + /* out: buffer for request */ + sg_init_one(&sg_req, &vm->req, sizeof(vm->req)); + sgs[0] = &sg_req; + + /* in: buffer for response */ + sg_init_one(&sg_resp, &vm->resp, sizeof(vm->resp)); + sgs[1] = &sg_resp; + + rc = virtqueue_add_sgs(vm->vq, sgs, 1, 1, vm, GFP_KERNEL); + if (rc < 0) + return rc; + + virtqueue_kick(vm->vq); + + /* wait for a response */ + wait_event(vm->host_resp, virtqueue_get_buf(vm->vq, &len)); + + return virtio16_to_cpu(vm->vdev, vm->resp.type); +} + +static int virtio_mem_send_plug_request(struct virtio_mem *vm, uint64_t addr, + uint64_t size) +{ + const uint64_t nb_vm_blocks = size / vm->device_block_size; + const struct virtio_mem_req req = { + .type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_PLUG), + .u.plug.addr = cpu_to_virtio64(vm->vdev, addr), + .u.plug.nb_blocks = cpu_to_virtio16(vm->vdev, nb_vm_blocks), + }; + + if (atomic_read(&vm->config_changed)) + return -EAGAIN; + + switch (virtio_mem_send_request(vm, &req)) { + case VIRTIO_MEM_RESP_ACK: + vm->plugged_size += size; + return 0; + case VIRTIO_MEM_RESP_NACK: + return -EAGAIN; + case VIRTIO_MEM_RESP_BUSY: + return -ETXTBSY; + case VIRTIO_MEM_RESP_ERROR: + return -EINVAL; + default: + return -ENOMEM; + } +} + +static int virtio_mem_send_unplug_request(struct virtio_mem *vm, uint64_t addr, + uint64_t size) +{ + const uint64_t nb_vm_blocks = size / vm->device_block_size; + const struct virtio_mem_req req = { + .type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_UNPLUG), + .u.unplug.addr = cpu_to_virtio64(vm->vdev, addr), + .u.unplug.nb_blocks = cpu_to_virtio16(vm->vdev, nb_vm_blocks), + }; + + if (atomic_read(&vm->config_changed)) + return -EAGAIN; + + switch (virtio_mem_send_request(vm, &req)) { + case VIRTIO_MEM_RESP_ACK: + vm->plugged_size -= size; + return 0; + case VIRTIO_MEM_RESP_BUSY: + return -ETXTBSY; + case VIRTIO_MEM_RESP_ERROR: + return -EINVAL; + default: + return -ENOMEM; + } +} + +static int virtio_mem_send_unplug_all_request(struct virtio_mem *vm) +{ + const struct virtio_mem_req req = { + .type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_UNPLUG_ALL), + }; + + switch (virtio_mem_send_request(vm, &req)) { + case VIRTIO_MEM_RESP_ACK: + vm->unplug_all_required = false; + vm->plugged_size = 0; + /* usable region might have shrunk */ + atomic_set(&vm->config_changed, 1); + return 0; + case VIRTIO_MEM_RESP_BUSY: + return -ETXTBSY; + default: + return -ENOMEM; + } +} + +/* + * Plug selected subblocks. Updates the plugged state, but not the state + * of the memory block. + */ +static int virtio_mem_mb_plug_sb(struct virtio_mem *vm, unsigned long mb_id, + int sb_id, int count) +{ + const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id) + + sb_id * vm->subblock_size; + const uint64_t size = count * vm->subblock_size; + int rc; + + dev_dbg(&vm->vdev->dev, "plugging memory block: %lu : %i - %i\n", mb_id, + sb_id, sb_id + count - 1); + + rc = virtio_mem_send_plug_request(vm, addr, size); + if (!rc) + virtio_mem_mb_set_sb_plugged(vm, mb_id, sb_id, count); + return rc; +} + +/* + * Unplug selected subblocks. Updates the plugged state, but not the state + * of the memory block. + */ +static int virtio_mem_mb_unplug_sb(struct virtio_mem *vm, unsigned long mb_id, + int sb_id, int count) +{ + const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id) + + sb_id * vm->subblock_size; + const uint64_t size = count * vm->subblock_size; + int rc; + + dev_dbg(&vm->vdev->dev, "unplugging memory block: %lu : %i - %i\n", + mb_id, sb_id, sb_id + count - 1); + + rc = virtio_mem_send_unplug_request(vm, addr, size); + if (!rc) + virtio_mem_mb_set_sb_unplugged(vm, mb_id, sb_id, count); + return rc; +} + +/* + * Unplug the desired number of plugged subblocks of a offline or not-added + * memory block. Will fail if any subblock cannot get unplugged (instead of + * skipping it). + * + * Will not modify the state of the memory block. + * + * Note: can fail after some subblocks were unplugged. + */ +static int virtio_mem_mb_unplug_any_sb(struct virtio_mem *vm, + unsigned long mb_id, uint64_t *nb_sb) +{ + int sb_id, count; + int rc; + + sb_id = vm->nb_sb_per_mb - 1; + while (*nb_sb) { + /* Find the next candidate subblock */ + while (sb_id >= 0 && + virtio_mem_mb_test_sb_unplugged(vm, mb_id, sb_id, 1)) + sb_id--; + if (sb_id < 0) + break; + /* Try to unplug multiple subblocks at a time */ + count = 1; + while (count < *nb_sb && sb_id > 0 && + virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id - 1, 1)) { + count++; + sb_id--; + } + + rc = virtio_mem_mb_unplug_sb(vm, mb_id, sb_id, count); + if (rc) + return rc; + *nb_sb -= count; + sb_id--; + } + + return 0; +} + +/* + * Unplug all plugged subblocks of an offline or not-added memory block. + * + * Will not modify the state of the memory block. + * + * Note: can fail after some subblocks were unplugged. + */ +static int virtio_mem_mb_unplug(struct virtio_mem *vm, unsigned long mb_id) +{ + uint64_t nb_sb = vm->nb_sb_per_mb; + + return virtio_mem_mb_unplug_any_sb(vm, mb_id, &nb_sb); +} + +/* + * Prepare tracking data for the next memory block. + */ +static int virtio_mem_prepare_next_mb(struct virtio_mem *vm, + unsigned long *mb_id) +{ + int rc; + + if (vm->next_mb_id > vm->last_usable_mb_id) + return -ENOSPC; + + /* Resize the state array if required. */ + rc = virtio_mem_mb_state_prepare_next_mb(vm); + if (rc) + return rc; + + /* Resize the subblock bitmap if required. */ + rc = virtio_mem_sb_bitmap_prepare_next_mb(vm); + if (rc) + return rc; + + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_UNUSED]++; + *mb_id = vm->next_mb_id++; + return 0; +} + +/* + * Don't add too many blocks that are not onlined yet to avoid running OOM. + */ +static bool virtio_mem_too_many_mb_offline(struct virtio_mem *vm) +{ + unsigned long nb_offline; + + nb_offline = vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] + + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL]; + return nb_offline >= VIRTIO_MEM_NB_OFFLINE_THRESHOLD; +} + +/* + * Try to plug the desired number of subblocks and add the memory block + * to Linux. + * + * Will modify the state of the memory block. + */ +static int virtio_mem_mb_plug_and_add(struct virtio_mem *vm, + unsigned long mb_id, + uint64_t *nb_sb) +{ + const int count = min_t(int, *nb_sb, vm->nb_sb_per_mb); + int rc, rc2; + + if (WARN_ON_ONCE(!count)) + return -EINVAL; + + /* + * Plug the requested number of subblocks before adding it to linux, + * so that onlining will directly online all plugged subblocks. + */ + rc = virtio_mem_mb_plug_sb(vm, mb_id, 0, count); + if (rc) + return rc; + + /* + * Mark the block properly offline before adding it to Linux, + * so the memory notifiers will find the block in the right state. + */ + if (count == vm->nb_sb_per_mb) + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE); + else + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL); + + /* Add the memory block to linux - if that fails, try to unplug. */ + rc = virtio_mem_mb_add(vm, mb_id); + if (rc) { + enum virtio_mem_mb_state new_state = VIRTIO_MEM_MB_STATE_UNUSED; + + dev_err(&vm->vdev->dev, + "adding memory block %lu failed with %d\n", mb_id, rc); + rc2 = virtio_mem_mb_unplug_sb(vm, mb_id, 0, count); + + /* + * TODO: Linux MM does not properly clean up yet in all cases + * where adding of memory failed - especially on -ENOMEM. + */ + if (rc2) + new_state = VIRTIO_MEM_MB_STATE_PLUGGED; + virtio_mem_mb_set_state(vm, mb_id, new_state); + return rc; + } + + *nb_sb -= count; + return 0; +} + +/* + * Try to plug the desired number of subblocks of a memory block that + * is already added to Linux. + * + * Will modify the state of the memory block. + * + * Note: Can fail after some subblocks were successfully plugged. + */ +static int virtio_mem_mb_plug_any_sb(struct virtio_mem *vm, unsigned long mb_id, + uint64_t *nb_sb, bool online) +{ + unsigned long pfn, nr_pages; + int sb_id, count; + int rc; + + if (WARN_ON_ONCE(!*nb_sb)) + return -EINVAL; + + while (*nb_sb) { + sb_id = virtio_mem_mb_first_unplugged_sb(vm, mb_id); + if (sb_id >= vm->nb_sb_per_mb) + break; + count = 1; + while (count < *nb_sb && + sb_id + count < vm->nb_sb_per_mb && + !virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id + count, + 1)) + count++; + + rc = virtio_mem_mb_plug_sb(vm, mb_id, sb_id, count); + if (rc) + return rc; + *nb_sb -= count; + if (!online) + continue; + + /* fake-online the pages if the memory block is online */ + pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) + + sb_id * vm->subblock_size); + nr_pages = PFN_DOWN(count * vm->subblock_size); + virtio_mem_fake_online(pfn, nr_pages); + } + + if (virtio_mem_mb_test_sb_plugged(vm, mb_id, 0, vm->nb_sb_per_mb)) { + if (online) + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_ONLINE); + else + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE); + } + + return rc; +} + +/* + * Try to plug the requested amount of memory. + */ +static int virtio_mem_plug_request(struct virtio_mem *vm, uint64_t diff) +{ + uint64_t nb_sb = diff / vm->subblock_size; + unsigned long mb_id; + int rc; + + if (!nb_sb) + return 0; + + /* Don't race with onlining/offlining */ + mutex_lock(&vm->hotplug_mutex); + + /* Try to plug subblocks of partially plugged online blocks. */ + virtio_mem_for_each_mb_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL) { + rc = virtio_mem_mb_plug_any_sb(vm, mb_id, &nb_sb, true); + if (rc || !nb_sb) + goto out_unlock; + cond_resched(); + } + + /* Try to plug subblocks of partially plugged offline blocks. */ + virtio_mem_for_each_mb_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) { + rc = virtio_mem_mb_plug_any_sb(vm, mb_id, &nb_sb, false); + if (rc || !nb_sb) + goto out_unlock; + cond_resched(); + } + + /* + * We won't be working on online/offline memory blocks from this point, + * so we can't race with memory onlining/offlining. Drop the mutex. + */ + mutex_unlock(&vm->hotplug_mutex); + + /* Try to plug and add unused blocks */ + virtio_mem_for_each_mb_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED) { + if (virtio_mem_too_many_mb_offline(vm)) + return -ENOSPC; + + rc = virtio_mem_mb_plug_and_add(vm, mb_id, &nb_sb); + if (rc || !nb_sb) + return rc; + cond_resched(); + } + + /* Try to prepare, plug and add new blocks */ + while (nb_sb) { + if (virtio_mem_too_many_mb_offline(vm)) + return -ENOSPC; + + rc = virtio_mem_prepare_next_mb(vm, &mb_id); + if (rc) + return rc; + rc = virtio_mem_mb_plug_and_add(vm, mb_id, &nb_sb); + if (rc) + return rc; + cond_resched(); + } + + return 0; +out_unlock: + mutex_unlock(&vm->hotplug_mutex); + return rc; +} + +/* + * Unplug the desired number of plugged subblocks of an offline memory block. + * Will fail if any subblock cannot get unplugged (instead of skipping it). + * + * Will modify the state of the memory block. Might temporarily drop the + * hotplug_mutex. + * + * Note: Can fail after some subblocks were successfully unplugged. + */ +static int virtio_mem_mb_unplug_any_sb_offline(struct virtio_mem *vm, + unsigned long mb_id, + uint64_t *nb_sb) +{ + int rc; + + rc = virtio_mem_mb_unplug_any_sb(vm, mb_id, nb_sb); + + /* some subblocks might have been unplugged even on failure */ + if (!virtio_mem_mb_test_sb_plugged(vm, mb_id, 0, vm->nb_sb_per_mb)) + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL); + if (rc) + return rc; + + if (virtio_mem_mb_test_sb_unplugged(vm, mb_id, 0, vm->nb_sb_per_mb)) { + /* + * Remove the block from Linux - this should never fail. + * Hinder the block from getting onlined by marking it + * unplugged. Temporarily drop the mutex, so + * any pending GOING_ONLINE requests can be serviced/rejected. + */ + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_UNUSED); + + mutex_unlock(&vm->hotplug_mutex); + rc = virtio_mem_mb_remove(vm, mb_id); + BUG_ON(rc); + mutex_lock(&vm->hotplug_mutex); + } + return 0; +} + +/* + * Unplug the given plugged subblocks of an online memory block. + * + * Will modify the state of the memory block. + */ +static int virtio_mem_mb_unplug_sb_online(struct virtio_mem *vm, + unsigned long mb_id, int sb_id, + int count) +{ + const unsigned long nr_pages = PFN_DOWN(vm->subblock_size) * count; + unsigned long start_pfn; + int rc; + + start_pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) + + sb_id * vm->subblock_size); + rc = alloc_contig_range(start_pfn, start_pfn + nr_pages, + MIGRATE_MOVABLE, GFP_KERNEL); + if (rc == -ENOMEM) + /* whoops, out of memory */ + return rc; + if (rc) + return -EBUSY; + + /* Mark it as fake-offline before unplugging it */ + virtio_mem_set_fake_offline(start_pfn, nr_pages, true); + adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages); + + /* Try to unplug the allocated memory */ + rc = virtio_mem_mb_unplug_sb(vm, mb_id, sb_id, count); + if (rc) { + /* Return the memory to the buddy. */ + virtio_mem_fake_online(start_pfn, nr_pages); + return rc; + } + + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL); + return 0; +} + +/* + * Unplug the desired number of plugged subblocks of an online memory block. + * Will skip subblock that are busy. + * + * Will modify the state of the memory block. Might temporarily drop the + * hotplug_mutex. + * + * Note: Can fail after some subblocks were successfully unplugged. Can + * return 0 even if subblocks were busy and could not get unplugged. + */ +static int virtio_mem_mb_unplug_any_sb_online(struct virtio_mem *vm, + unsigned long mb_id, + uint64_t *nb_sb) +{ + int rc, sb_id; + + /* If possible, try to unplug the complete block in one shot. */ + if (*nb_sb >= vm->nb_sb_per_mb && + virtio_mem_mb_test_sb_plugged(vm, mb_id, 0, vm->nb_sb_per_mb)) { + rc = virtio_mem_mb_unplug_sb_online(vm, mb_id, 0, + vm->nb_sb_per_mb); + if (!rc) { + *nb_sb -= vm->nb_sb_per_mb; + goto unplugged; + } else if (rc != -EBUSY) + return rc; + } + + /* Fallback to single subblocks. */ + for (sb_id = vm->nb_sb_per_mb - 1; sb_id >= 0 && *nb_sb; sb_id--) { + /* Find the next candidate subblock */ + while (sb_id >= 0 && + !virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1)) + sb_id--; + if (sb_id < 0) + break; + + rc = virtio_mem_mb_unplug_sb_online(vm, mb_id, sb_id, 1); + if (rc == -EBUSY) + continue; + else if (rc) + return rc; + *nb_sb -= 1; + } + +unplugged: + /* + * Once all subblocks of a memory block were unplugged, offline and + * remove it. This will usually not fail, as no memory is in use + * anymore - however some other notifiers might NACK the request. + */ + if (virtio_mem_mb_test_sb_unplugged(vm, mb_id, 0, vm->nb_sb_per_mb)) { + mutex_unlock(&vm->hotplug_mutex); + rc = virtio_mem_mb_offline_and_remove(vm, mb_id); + mutex_lock(&vm->hotplug_mutex); + if (!rc) + virtio_mem_mb_set_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_UNUSED); + } + + return 0; +} + +/* + * Try to unplug the requested amount of memory. + */ +static int virtio_mem_unplug_request(struct virtio_mem *vm, uint64_t diff) +{ + uint64_t nb_sb = diff / vm->subblock_size; + unsigned long mb_id; + int rc; + + if (!nb_sb) + return 0; + + /* + * We'll drop the mutex a couple of times when it is safe to do so. + * This might result in some blocks switching the state (online/offline) + * and we could miss them in this run - we will retry again later. + */ + mutex_lock(&vm->hotplug_mutex); + + /* Try to unplug subblocks of partially plugged offline blocks. */ + virtio_mem_for_each_mb_state_rev(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) { + rc = virtio_mem_mb_unplug_any_sb_offline(vm, mb_id, + &nb_sb); + if (rc || !nb_sb) + goto out_unlock; + cond_resched(); + } + + /* Try to unplug subblocks of plugged offline blocks. */ + virtio_mem_for_each_mb_state_rev(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE) { + rc = virtio_mem_mb_unplug_any_sb_offline(vm, mb_id, + &nb_sb); + if (rc || !nb_sb) + goto out_unlock; + cond_resched(); + } + + if (!unplug_online) { + mutex_unlock(&vm->hotplug_mutex); + return 0; + } + + /* Try to unplug subblocks of partially plugged online blocks. */ + virtio_mem_for_each_mb_state_rev(vm, mb_id, + VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL) { + rc = virtio_mem_mb_unplug_any_sb_online(vm, mb_id, + &nb_sb); + if (rc || !nb_sb) + goto out_unlock; + mutex_unlock(&vm->hotplug_mutex); + cond_resched(); + mutex_lock(&vm->hotplug_mutex); + } + + /* Try to unplug subblocks of plugged online blocks. */ + virtio_mem_for_each_mb_state_rev(vm, mb_id, + VIRTIO_MEM_MB_STATE_ONLINE) { + rc = virtio_mem_mb_unplug_any_sb_online(vm, mb_id, + &nb_sb); + if (rc || !nb_sb) + goto out_unlock; + mutex_unlock(&vm->hotplug_mutex); + cond_resched(); + mutex_lock(&vm->hotplug_mutex); + } + + mutex_unlock(&vm->hotplug_mutex); + return nb_sb ? -EBUSY : 0; +out_unlock: + mutex_unlock(&vm->hotplug_mutex); + return rc; +} + +/* + * Try to unplug all blocks that couldn't be unplugged before, for example, + * because the hypervisor was busy. + */ +static int virtio_mem_unplug_pending_mb(struct virtio_mem *vm) +{ + unsigned long mb_id; + int rc; + + virtio_mem_for_each_mb_state(vm, mb_id, VIRTIO_MEM_MB_STATE_PLUGGED) { + rc = virtio_mem_mb_unplug(vm, mb_id); + if (rc) + return rc; + virtio_mem_mb_set_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED); + } + + return 0; +} + +/* + * Update all parts of the config that could have changed. + */ +static void virtio_mem_refresh_config(struct virtio_mem *vm) +{ + const uint64_t phys_limit = 1UL << MAX_PHYSMEM_BITS; + uint64_t new_plugged_size, usable_region_size, end_addr; + + /* the plugged_size is just a reflection of what _we_ did previously */ + virtio_cread(vm->vdev, struct virtio_mem_config, plugged_size, + &new_plugged_size); + if (WARN_ON_ONCE(new_plugged_size != vm->plugged_size)) + vm->plugged_size = new_plugged_size; + + /* calculate the last usable memory block id */ + virtio_cread(vm->vdev, struct virtio_mem_config, + usable_region_size, &usable_region_size); + end_addr = vm->addr + usable_region_size; + end_addr = min(end_addr, phys_limit); + vm->last_usable_mb_id = virtio_mem_phys_to_mb_id(end_addr) - 1; + + /* see if there is a request to change the size */ + virtio_cread(vm->vdev, struct virtio_mem_config, requested_size, + &vm->requested_size); + + dev_info(&vm->vdev->dev, "plugged size: 0x%llx", vm->plugged_size); + dev_info(&vm->vdev->dev, "requested size: 0x%llx", vm->requested_size); +} + +/* + * Workqueue function for handling plug/unplug requests and config updates. + */ +static void virtio_mem_run_wq(struct work_struct *work) +{ + struct virtio_mem *vm = container_of(work, struct virtio_mem, wq); + uint64_t diff; + int rc; + + hrtimer_cancel(&vm->retry_timer); + + if (vm->broken) + return; + +retry: + rc = 0; + + /* Make sure we start with a clean state if there are leftovers. */ + if (unlikely(vm->unplug_all_required)) + rc = virtio_mem_send_unplug_all_request(vm); + + if (atomic_read(&vm->config_changed)) { + atomic_set(&vm->config_changed, 0); + virtio_mem_refresh_config(vm); + } + + /* Unplug any leftovers from previous runs */ + if (!rc) + rc = virtio_mem_unplug_pending_mb(vm); + + if (!rc && vm->requested_size != vm->plugged_size) { + if (vm->requested_size > vm->plugged_size) { + diff = vm->requested_size - vm->plugged_size; + rc = virtio_mem_plug_request(vm, diff); + } else { + diff = vm->plugged_size - vm->requested_size; + rc = virtio_mem_unplug_request(vm, diff); + } + } + + switch (rc) { + case 0: + vm->retry_timer_ms = VIRTIO_MEM_RETRY_TIMER_MIN_MS; + break; + case -ENOSPC: + /* + * We cannot add any more memory (alignment, physical limit) + * or we have too many offline memory blocks. + */ + break; + case -ETXTBSY: + /* + * The hypervisor cannot process our request right now + * (e.g., out of memory, migrating); + */ + case -EBUSY: + /* + * We cannot free up any memory to unplug it (all plugged memory + * is busy). + */ + case -ENOMEM: + /* Out of memory, try again later. */ + hrtimer_start(&vm->retry_timer, ms_to_ktime(vm->retry_timer_ms), + HRTIMER_MODE_REL); + break; + case -EAGAIN: + /* Retry immediately (e.g., the config changed). */ + goto retry; + default: + /* Unknown error, mark as broken */ + dev_err(&vm->vdev->dev, + "unknown error, marking device broken: %d\n", rc); + vm->broken = true; + } +} + +static enum hrtimer_restart virtio_mem_timer_expired(struct hrtimer *timer) +{ + struct virtio_mem *vm = container_of(timer, struct virtio_mem, + retry_timer); + + virtio_mem_retry(vm); + vm->retry_timer_ms = min_t(unsigned int, vm->retry_timer_ms * 2, + VIRTIO_MEM_RETRY_TIMER_MAX_MS); + return HRTIMER_NORESTART; +} + +static void virtio_mem_handle_response(struct virtqueue *vq) +{ + struct virtio_mem *vm = vq->vdev->priv; + + wake_up(&vm->host_resp); +} + +static int virtio_mem_init_vq(struct virtio_mem *vm) +{ + struct virtqueue *vq; + + vq = virtio_find_single_vq(vm->vdev, virtio_mem_handle_response, + "guest-request"); + if (IS_ERR(vq)) + return PTR_ERR(vq); + vm->vq = vq; + + return 0; +} + +static int virtio_mem_init(struct virtio_mem *vm) +{ + const uint64_t phys_limit = 1UL << MAX_PHYSMEM_BITS; + uint16_t node_id; + + if (!vm->vdev->config->get) { + dev_err(&vm->vdev->dev, "config access disabled\n"); + return -EINVAL; + } + + /* + * We don't want to (un)plug or reuse any memory when in kdump. The + * memory is still accessible (but not mapped). + */ + if (is_kdump_kernel()) { + dev_warn(&vm->vdev->dev, "disabled in kdump kernel\n"); + return -EBUSY; + } + + /* Fetch all properties that can't change. */ + virtio_cread(vm->vdev, struct virtio_mem_config, plugged_size, + &vm->plugged_size); + virtio_cread(vm->vdev, struct virtio_mem_config, block_size, + &vm->device_block_size); + virtio_cread(vm->vdev, struct virtio_mem_config, node_id, + &node_id); + vm->nid = virtio_mem_translate_node_id(vm, node_id); + virtio_cread(vm->vdev, struct virtio_mem_config, addr, &vm->addr); + virtio_cread(vm->vdev, struct virtio_mem_config, region_size, + &vm->region_size); + + /* + * We always hotplug memory in memory block granularity. This way, + * we have to wait for exactly one memory block to online. + */ + if (vm->device_block_size > memory_block_size_bytes()) { + dev_err(&vm->vdev->dev, + "The block size is not supported (too big).\n"); + return -EINVAL; + } + + /* bad device setup - warn only */ + if (!IS_ALIGNED(vm->addr, memory_block_size_bytes())) + dev_warn(&vm->vdev->dev, + "The alignment of the physical start address can make some memory unusable.\n"); + if (!IS_ALIGNED(vm->addr + vm->region_size, memory_block_size_bytes())) + dev_warn(&vm->vdev->dev, + "The alignment of the physical end address can make some memory unusable.\n"); + if (vm->addr + vm->region_size > phys_limit) + dev_warn(&vm->vdev->dev, + "Some memory is not addressable. This can make some memory unusable.\n"); + + /* + * Calculate the subblock size: + * - At least MAX_ORDER - 1 / pageblock_order. + * - At least the device block size. + * In the worst case, a single subblock per memory block. + */ + vm->subblock_size = PAGE_SIZE * 1ul << max_t(uint32_t, MAX_ORDER - 1, + pageblock_order); + vm->subblock_size = max_t(uint64_t, vm->device_block_size, + vm->subblock_size); + vm->nb_sb_per_mb = memory_block_size_bytes() / vm->subblock_size; + + /* Round up to the next full memory block */ + vm->first_mb_id = virtio_mem_phys_to_mb_id(vm->addr - 1 + + memory_block_size_bytes()); + vm->next_mb_id = vm->first_mb_id; + vm->last_mb_id = virtio_mem_phys_to_mb_id(vm->addr + + vm->region_size) - 1; + + dev_info(&vm->vdev->dev, "start address: 0x%llx", vm->addr); + dev_info(&vm->vdev->dev, "region size: 0x%llx", vm->region_size); + dev_info(&vm->vdev->dev, "device block size: 0x%llx", + (unsigned long long)vm->device_block_size); + dev_info(&vm->vdev->dev, "memory block size: 0x%lx", + memory_block_size_bytes()); + dev_info(&vm->vdev->dev, "subblock size: 0x%llx", + (unsigned long long)vm->subblock_size); + if (vm->nid != NUMA_NO_NODE) + dev_info(&vm->vdev->dev, "nid: %d", vm->nid); + + return 0; +} + +static int virtio_mem_create_resource(struct virtio_mem *vm) +{ + /* + * When force-unloading the driver and removing the device, we + * could have a garbage pointer. Duplicate the string. + */ + const char *name = kstrdup(dev_name(&vm->vdev->dev), GFP_KERNEL); + + if (!name) + return -ENOMEM; + + vm->parent_resource = __request_mem_region(vm->addr, vm->region_size, + name, IORESOURCE_SYSTEM_RAM); + if (!vm->parent_resource) { + kfree(name); + dev_warn(&vm->vdev->dev, "could not reserve device region\n"); + dev_info(&vm->vdev->dev, + "reloading the driver is not supported\n"); + return -EBUSY; + } + + /* The memory is not actually busy - make add_memory() work. */ + vm->parent_resource->flags &= ~IORESOURCE_BUSY; + return 0; +} + +static void virtio_mem_delete_resource(struct virtio_mem *vm) +{ + const char *name; + + if (!vm->parent_resource) + return; + + name = vm->parent_resource->name; + release_resource(vm->parent_resource); + kfree(vm->parent_resource); + kfree(name); + vm->parent_resource = NULL; +} + +static int virtio_mem_probe(struct virtio_device *vdev) +{ + struct virtio_mem *vm; + int rc; + + BUILD_BUG_ON(sizeof(struct virtio_mem_req) != 24); + BUILD_BUG_ON(sizeof(struct virtio_mem_resp) != 10); + + vdev->priv = vm = kzalloc(sizeof(*vm), GFP_KERNEL); + if (!vm) + return -ENOMEM; + + init_waitqueue_head(&vm->host_resp); + vm->vdev = vdev; + INIT_WORK(&vm->wq, virtio_mem_run_wq); + mutex_init(&vm->hotplug_mutex); + INIT_LIST_HEAD(&vm->next); + spin_lock_init(&vm->removal_lock); + hrtimer_init(&vm->retry_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + vm->retry_timer.function = virtio_mem_timer_expired; + vm->retry_timer_ms = VIRTIO_MEM_RETRY_TIMER_MIN_MS; + + /* register the virtqueue */ + rc = virtio_mem_init_vq(vm); + if (rc) + goto out_free_vm; + + /* initialize the device by querying the config */ + rc = virtio_mem_init(vm); + if (rc) + goto out_del_vq; + + /* create the parent resource for all memory */ + rc = virtio_mem_create_resource(vm); + if (rc) + goto out_del_vq; + + /* + * If we still have memory plugged, we have to unplug all memory first. + * Registering our parent resource makes sure that this memory isn't + * actually in use (e.g., trying to reload the driver). + */ + if (vm->plugged_size) { + vm->unplug_all_required = 1; + dev_info(&vm->vdev->dev, "unplugging all memory is required\n"); + } + + /* register callbacks */ + vm->memory_notifier.notifier_call = virtio_mem_memory_notifier_cb; + rc = register_memory_notifier(&vm->memory_notifier); + if (rc) + goto out_del_resource; + rc = register_virtio_mem_device(vm); + if (rc) + goto out_unreg_mem; + + virtio_device_ready(vdev); + + /* trigger a config update to start processing the requested_size */ + atomic_set(&vm->config_changed, 1); + queue_work(system_freezable_wq, &vm->wq); + + return 0; +out_unreg_mem: + unregister_memory_notifier(&vm->memory_notifier); +out_del_resource: + virtio_mem_delete_resource(vm); +out_del_vq: + vdev->config->del_vqs(vdev); +out_free_vm: + kfree(vm); + vdev->priv = NULL; + + return rc; +} + +static void virtio_mem_remove(struct virtio_device *vdev) +{ + struct virtio_mem *vm = vdev->priv; + unsigned long mb_id; + int rc; + + /* + * Make sure the workqueue won't be triggered anymore and no memory + * blocks can be onlined/offlined until we're finished here. + */ + mutex_lock(&vm->hotplug_mutex); + spin_lock_irq(&vm->removal_lock); + vm->removing = true; + spin_unlock_irq(&vm->removal_lock); + mutex_unlock(&vm->hotplug_mutex); + + /* wait until the workqueue stopped */ + cancel_work_sync(&vm->wq); + hrtimer_cancel(&vm->retry_timer); + + /* + * After we unregistered our callbacks, user space can online partially + * plugged offline blocks. Make sure to remove them. + */ + virtio_mem_for_each_mb_state(vm, mb_id, + VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) { + rc = virtio_mem_mb_remove(vm, mb_id); + BUG_ON(rc); + virtio_mem_mb_set_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED); + } + /* + * After we unregistered our callbacks, user space can no longer + * offline partially plugged online memory blocks. No need to worry + * about them. + */ + + /* unregister callbacks */ + unregister_virtio_mem_device(vm); + unregister_memory_notifier(&vm->memory_notifier); + + /* + * There is no way we could reliably remove all memory we have added to + * the system. And there is no way to stop the driver/device from going + * away. Warn at least. + */ + if (vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] || + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL] || + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE] || + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL] || + vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_MOVABLE]) + dev_warn(&vdev->dev, "device still has system memory added\n"); + else + virtio_mem_delete_resource(vm); + + /* remove all tracking data - no locking needed */ + vfree(vm->mb_state); + vfree(vm->sb_bitmap); + + /* reset the device and cleanup the queues */ + vdev->config->reset(vdev); + vdev->config->del_vqs(vdev); + + kfree(vm); + vdev->priv = NULL; +} + +static void virtio_mem_config_changed(struct virtio_device *vdev) +{ + struct virtio_mem *vm = vdev->priv; + + atomic_set(&vm->config_changed, 1); + virtio_mem_retry(vm); +} + +#ifdef CONFIG_PM_SLEEP +static int virtio_mem_freeze(struct virtio_device *vdev) +{ + /* + * When restarting the VM, all memory is usually unplugged. Don't + * allow to suspend/hibernate. + */ + dev_err(&vdev->dev, "save/restore not supported.\n"); + return -EPERM; +} + +static int virtio_mem_restore(struct virtio_device *vdev) +{ + return -EPERM; +} +#endif + +static unsigned int virtio_mem_features[] = { +#if defined(CONFIG_NUMA) && defined(CONFIG_ACPI_NUMA) + VIRTIO_MEM_F_ACPI_PXM, +#endif +}; + +static struct virtio_device_id virtio_mem_id_table[] = { + { VIRTIO_ID_MEM, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; + +static struct virtio_driver virtio_mem_driver = { + .feature_table = virtio_mem_features, + .feature_table_size = ARRAY_SIZE(virtio_mem_features), + .driver.name = KBUILD_MODNAME, + .driver.owner = THIS_MODULE, + .id_table = virtio_mem_id_table, + .probe = virtio_mem_probe, + .remove = virtio_mem_remove, + .config_changed = virtio_mem_config_changed, +#ifdef CONFIG_PM_SLEEP + .freeze = virtio_mem_freeze, + .restore = virtio_mem_restore, +#endif +}; + +module_virtio_driver(virtio_mem_driver); +MODULE_DEVICE_TABLE(virtio, virtio_mem_id_table); +MODULE_AUTHOR("David Hildenbrand "); +MODULE_DESCRIPTION("Virtio-mem driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 97d5725fd9a2..9d16aaffca9d 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -466,10 +466,8 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs, int irq = platform_get_irq(vm_dev->pdev, 0); int i, err, queue_idx = 0; - if (irq < 0) { - dev_err(&vdev->dev, "Cannot get IRQ resource\n"); + if (irq < 0) return irq; - } err = request_irq(irq, vm_interrupt, IRQF_SHARED, dev_name(&vdev->dev), vm_dev); diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 7abcc50838b8..db93cedd262f 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -16,6 +16,7 @@ #include #define VIRTIO_PCI_NO_LEGACY +#define VIRTIO_RING_NO_LEGACY #include "virtio_pci_common.h" /* diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index fee7fab5d706..375515803cd8 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -318,6 +318,7 @@ extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern int remove_memory(int nid, u64 start, u64 size); extern void __remove_memory(int nid, u64 start, u64 size); +extern int offline_and_remove_memory(int nid, u64 start, u64 size); #else static inline void try_offline_node(int nid) {} diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 222f6f7b2bb3..6be1aa559b1e 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -777,6 +777,16 @@ PAGE_TYPE_OPS(Buddy, buddy) * not onlined when onlining the section). * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. + * + * If a driver wants to allow to offline unmovable PageOffline() pages without + * putting them back to the buddy, it can do so via the memory notifier by + * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the + * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() + * pages (now with a reference count of zero) are treated like free pages, + * allowing the containing memory block to get offlined. A driver that + * relies on this feature is aware that re-onlining the memory block will + * require to re-set the pages PageOffline() and not giving them to the + * buddy via online_page_callback_t. */ PAGE_TYPE_OPS(Offline, offline) diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 5453af87a33e..239db794357c 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -17,6 +17,16 @@ struct vdpa_callback { void *private; }; +/** + * vDPA notification area + * @addr: base address of the notification area + * @size: size of the notification area + */ +struct vdpa_notification_area { + resource_size_t addr; + resource_size_t size; +}; + /** * vDPA device - representation of a vDPA device * @dev: underlying device @@ -73,6 +83,10 @@ struct vdpa_device { * @vdev: vdpa device * @idx: virtqueue index * Returns virtqueue state (last_avail_idx) + * @get_vq_notification: Get the notification area for a virtqueue + * @vdev: vdpa device + * @idx: virtqueue index + * Returns the notifcation area * @get_vq_align: Get the virtqueue align requirement * for the device * @vdev: vdpa device @@ -162,6 +176,8 @@ struct vdpa_config_ops { bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx); int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, u64 state); u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx); + struct vdpa_notification_area + (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 9e2763d7c159..59bd50f99291 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -105,9 +105,9 @@ struct vringh_kiov { /* Helpers for userspace vrings. */ int vringh_init_user(struct vringh *vrh, u64 features, unsigned int num, bool weak_barriers, - struct vring_desc __user *desc, - struct vring_avail __user *avail, - struct vring_used __user *used); + vring_desc_t __user *desc, + vring_avail_t __user *avail, + vring_used_t __user *used); static inline void vringh_iov_init(struct vringh_iov *iov, struct iovec *iovec, unsigned num) diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 9fe72e4b1373..0c2349612e77 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -15,6 +15,8 @@ #include #include +#define VHOST_FILE_UNBIND -1 + /* ioctls */ #define VHOST_VIRTIO 0xAF @@ -140,4 +142,6 @@ /* Get the max ring size. */ #define VHOST_VDPA_GET_VRING_NUM _IOR(VHOST_VIRTIO, 0x76, __u16) +/* Set event fd for config interrupt*/ +#define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int) #endif diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index ecc27a17401a..b052355ac7a3 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -44,6 +44,7 @@ #define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ #define VIRTIO_ID_CRYPTO 20 /* virtio crypto */ #define VIRTIO_ID_IOMMU 23 /* virtio IOMMU */ +#define VIRTIO_ID_MEM 24 /* virtio mem */ #define VIRTIO_ID_FS 26 /* virtio filesystem */ #define VIRTIO_ID_PMEM 27 /* virtio pmem */ #define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */ diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h new file mode 100644 index 000000000000..a9ffe041843c --- /dev/null +++ b/include/uapi/linux/virtio_mem.h @@ -0,0 +1,211 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* + * Virtio Mem Device + * + * Copyright Red Hat, Inc. 2020 + * + * Authors: + * David Hildenbrand + * + * This header is BSD licensed so anyone can use the definitions + * to implement compatible drivers/servers: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL IBM OR + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF + * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#ifndef _LINUX_VIRTIO_MEM_H +#define _LINUX_VIRTIO_MEM_H + +#include +#include +#include +#include + +/* + * Each virtio-mem device manages a dedicated region in physical address + * space. Each device can belong to a single NUMA node, multiple devices + * for a single NUMA node are possible. A virtio-mem device is like a + * "resizable DIMM" consisting of small memory blocks that can be plugged + * or unplugged. The device driver is responsible for (un)plugging memory + * blocks on demand. + * + * Virtio-mem devices can only operate on their assigned memory region in + * order to (un)plug memory. A device cannot (un)plug memory belonging to + * other devices. + * + * The "region_size" corresponds to the maximum amount of memory that can + * be provided by a device. The "size" corresponds to the amount of memory + * that is currently plugged. "requested_size" corresponds to a request + * from the device to the device driver to (un)plug blocks. The + * device driver should try to (un)plug blocks in order to reach the + * "requested_size". It is impossible to plug more memory than requested. + * + * The "usable_region_size" represents the memory region that can actually + * be used to (un)plug memory. It is always at least as big as the + * "requested_size" and will grow dynamically. It will only shrink when + * explicitly triggered (VIRTIO_MEM_REQ_UNPLUG). + * + * There are no guarantees what will happen if unplugged memory is + * read/written. Such memory should, in general, not be touched. E.g., + * even writing might succeed, but the values will simply be discarded at + * random points in time. + * + * It can happen that the device cannot process a request, because it is + * busy. The device driver has to retry later. + * + * Usually, during system resets all memory will get unplugged, so the + * device driver can start with a clean state. However, in specific + * scenarios (if the device is busy) it can happen that the device still + * has memory plugged. The device driver can request to unplug all memory + * (VIRTIO_MEM_REQ_UNPLUG) - which might take a while to succeed if the + * device is busy. + */ + +/* --- virtio-mem: feature bits --- */ + +/* node_id is an ACPI PXM and is valid */ +#define VIRTIO_MEM_F_ACPI_PXM 0 + + +/* --- virtio-mem: guest -> host requests --- */ + +/* request to plug memory blocks */ +#define VIRTIO_MEM_REQ_PLUG 0 +/* request to unplug memory blocks */ +#define VIRTIO_MEM_REQ_UNPLUG 1 +/* request to unplug all blocks and shrink the usable size */ +#define VIRTIO_MEM_REQ_UNPLUG_ALL 2 +/* request information about the plugged state of memory blocks */ +#define VIRTIO_MEM_REQ_STATE 3 + +struct virtio_mem_req_plug { + __virtio64 addr; + __virtio16 nb_blocks; + __virtio16 padding[3]; +}; + +struct virtio_mem_req_unplug { + __virtio64 addr; + __virtio16 nb_blocks; + __virtio16 padding[3]; +}; + +struct virtio_mem_req_state { + __virtio64 addr; + __virtio16 nb_blocks; + __virtio16 padding[3]; +}; + +struct virtio_mem_req { + __virtio16 type; + __virtio16 padding[3]; + + union { + struct virtio_mem_req_plug plug; + struct virtio_mem_req_unplug unplug; + struct virtio_mem_req_state state; + } u; +}; + + +/* --- virtio-mem: host -> guest response --- */ + +/* + * Request processed successfully, applicable for + * - VIRTIO_MEM_REQ_PLUG + * - VIRTIO_MEM_REQ_UNPLUG + * - VIRTIO_MEM_REQ_UNPLUG_ALL + * - VIRTIO_MEM_REQ_STATE + */ +#define VIRTIO_MEM_RESP_ACK 0 +/* + * Request denied - e.g. trying to plug more than requested, applicable for + * - VIRTIO_MEM_REQ_PLUG + */ +#define VIRTIO_MEM_RESP_NACK 1 +/* + * Request cannot be processed right now, try again later, applicable for + * - VIRTIO_MEM_REQ_PLUG + * - VIRTIO_MEM_REQ_UNPLUG + * - VIRTIO_MEM_REQ_UNPLUG_ALL + */ +#define VIRTIO_MEM_RESP_BUSY 2 +/* + * Error in request (e.g. addresses/alignment), applicable for + * - VIRTIO_MEM_REQ_PLUG + * - VIRTIO_MEM_REQ_UNPLUG + * - VIRTIO_MEM_REQ_STATE + */ +#define VIRTIO_MEM_RESP_ERROR 3 + + +/* State of memory blocks is "plugged" */ +#define VIRTIO_MEM_STATE_PLUGGED 0 +/* State of memory blocks is "unplugged" */ +#define VIRTIO_MEM_STATE_UNPLUGGED 1 +/* State of memory blocks is "mixed" */ +#define VIRTIO_MEM_STATE_MIXED 2 + +struct virtio_mem_resp_state { + __virtio16 state; +}; + +struct virtio_mem_resp { + __virtio16 type; + __virtio16 padding[3]; + + union { + struct virtio_mem_resp_state state; + } u; +}; + +/* --- virtio-mem: configuration --- */ + +struct virtio_mem_config { + /* Block size and alignment. Cannot change. */ + __u64 block_size; + /* Valid with VIRTIO_MEM_F_ACPI_PXM. Cannot change. */ + __u16 node_id; + __u8 padding[6]; + /* Start address of the memory region. Cannot change. */ + __u64 addr; + /* Region size (maximum). Cannot change. */ + __u64 region_size; + /* + * Currently usable region size. Can grow up to region_size. Can + * shrink due to VIRTIO_MEM_REQ_UNPLUG_ALL (in which case no config + * update will be sent). + */ + __u64 usable_region_size; + /* + * Currently used size. Changes due to plug/unplug requests, but no + * config updates will be sent. + */ + __u64 plugged_size; + /* Requested size. New plug requests cannot exceed it. Can change. */ + __u64 requested_size; +}; + +#endif /* _LINUX_VIRTIO_MEM_H */ diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h index 559f42e73315..476d3e5c0fe7 100644 --- a/include/uapi/linux/virtio_ring.h +++ b/include/uapi/linux/virtio_ring.h @@ -86,6 +86,13 @@ * at the end of the used ring. Guest should ignore the used->flags field. */ #define VIRTIO_RING_F_EVENT_IDX 29 +/* Alignment requirements for vring elements. + * When using pre-virtio 1.0 layout, these fall out naturally. + */ +#define VRING_AVAIL_ALIGN_SIZE 2 +#define VRING_USED_ALIGN_SIZE 4 +#define VRING_DESC_ALIGN_SIZE 16 + /* Virtio ring descriptors: 16 bytes. These can chain together via "next". */ struct vring_desc { /* Address (guest-physical). */ @@ -112,28 +119,47 @@ struct vring_used_elem { __virtio32 len; }; +typedef struct vring_used_elem __attribute__((aligned(VRING_USED_ALIGN_SIZE))) + vring_used_elem_t; + struct vring_used { __virtio16 flags; __virtio16 idx; - struct vring_used_elem ring[]; + vring_used_elem_t ring[]; }; +/* + * The ring element addresses are passed between components with different + * alignments assumptions. Thus, we might need to decrease the compiler-selected + * alignment, and so must use a typedef to make sure the aligned attribute + * actually takes hold: + * + * https://gcc.gnu.org/onlinedocs//gcc/Common-Type-Attributes.html#Common-Type-Attributes + * + * When used on a struct, or struct member, the aligned attribute can only + * increase the alignment; in order to decrease it, the packed attribute must + * be specified as well. When used as part of a typedef, the aligned attribute + * can both increase and decrease alignment, and specifying the packed + * attribute generates a warning. + */ +typedef struct vring_desc __attribute__((aligned(VRING_DESC_ALIGN_SIZE))) + vring_desc_t; +typedef struct vring_avail __attribute__((aligned(VRING_AVAIL_ALIGN_SIZE))) + vring_avail_t; +typedef struct vring_used __attribute__((aligned(VRING_USED_ALIGN_SIZE))) + vring_used_t; + struct vring { unsigned int num; - struct vring_desc *desc; + vring_desc_t *desc; - struct vring_avail *avail; + vring_avail_t *avail; - struct vring_used *used; + vring_used_t *used; }; -/* Alignment requirements for vring elements. - * When using pre-virtio 1.0 layout, these fall out naturally. - */ -#define VRING_AVAIL_ALIGN_SIZE 2 -#define VRING_USED_ALIGN_SIZE 4 -#define VRING_DESC_ALIGN_SIZE 16 +#ifndef VIRTIO_RING_NO_LEGACY /* The standard layout for the ring is a continuous chunk of memory which looks * like this. We assume num is a power of 2. @@ -181,6 +207,8 @@ static inline unsigned vring_size(unsigned int num, unsigned long align) + sizeof(__virtio16) * 3 + sizeof(struct vring_used_elem) * num; } +#endif /* VIRTIO_RING_NO_LEGACY */ + /* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */ /* Assuming a given event_idx value from the other side, if * we have just incremented index from old to new_idx, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c4d5c45820d0..9b34e03e730a 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1201,11 +1201,17 @@ struct zone *test_pages_in_a_zone(unsigned long start_pfn, /* * Scan pfn range [start,end) to find movable/migratable pages (LRU pages, - * non-lru movable pages and hugepages). We scan pfn because it's much - * easier than scanning over linked list. This function returns the pfn - * of the first found movable page if it's found, otherwise 0. + * non-lru movable pages and hugepages). Will skip over most unmovable + * pages (esp., pages that can be skipped when offlining), but bail out on + * definitely unmovable pages. + * + * Returns: + * 0 in case a movable page is found and movable_pfn was updated. + * -ENOENT in case no movable page was found. + * -EBUSY in case a definitely unmovable page was found. */ -static unsigned long scan_movable_pages(unsigned long start, unsigned long end) +static int scan_movable_pages(unsigned long start, unsigned long end, + unsigned long *movable_pfn) { unsigned long pfn; @@ -1217,18 +1223,30 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end) continue; page = pfn_to_page(pfn); if (PageLRU(page)) - return pfn; + goto found; if (__PageMovable(page)) - return pfn; + goto found; + + /* + * PageOffline() pages that are not marked __PageMovable() and + * have a reference count > 0 (after MEM_GOING_OFFLINE) are + * definitely unmovable. If their reference count would be 0, + * they could at least be skipped when offlining memory. + */ + if (PageOffline(page) && page_count(page)) + return -EBUSY; if (!PageHuge(page)) continue; head = compound_head(page); if (page_huge_active(head)) - return pfn; + goto found; skip = compound_nr(head) - (page - head); pfn += skip - 1; } + return -ENOENT; +found: + *movable_pfn = pfn; return 0; } @@ -1491,7 +1509,8 @@ static int __ref __offline_pages(unsigned long start_pfn, } do { - for (pfn = start_pfn; pfn;) { + pfn = start_pfn; + do { if (signal_pending(current)) { ret = -EINTR; reason = "signal backoff"; @@ -1501,14 +1520,19 @@ static int __ref __offline_pages(unsigned long start_pfn, cond_resched(); lru_add_drain_all(); - pfn = scan_movable_pages(pfn, end_pfn); - if (pfn) { + ret = scan_movable_pages(pfn, end_pfn, &pfn); + if (!ret) { /* * TODO: fatal migration failures should bail * out */ do_migrate_range(pfn, end_pfn); } + } while (!ret); + + if (ret != -ENOENT) { + reason = "unmovable page"; + goto failed_removal_isolated; } /* @@ -1774,4 +1798,41 @@ int remove_memory(int nid, u64 start, u64 size) return rc; } EXPORT_SYMBOL_GPL(remove_memory); + +/* + * Try to offline and remove a memory block. Might take a long time to + * finish in case memory is still in use. Primarily useful for memory devices + * that logically unplugged all memory (so it's no longer in use) and want to + * offline + remove the memory block. + */ +int offline_and_remove_memory(int nid, u64 start, u64 size) +{ + struct memory_block *mem; + int rc = -EINVAL; + + if (!IS_ALIGNED(start, memory_block_size_bytes()) || + size != memory_block_size_bytes()) + return rc; + + lock_device_hotplug(); + mem = find_memory_block(__pfn_to_section(PFN_DOWN(start))); + if (mem) + rc = device_offline(&mem->dev); + /* Ignore if the device is already offline. */ + if (rc > 0) + rc = 0; + + /* + * In case we succeeded to offline the memory block, remove it. + * This cannot fail as it cannot get onlined in the meantime. + */ + if (!rc) { + rc = try_remove_memory(nid, start, size); + WARN_ON_ONCE(rc); + } + unlock_device_hotplug(); + + return rc; +} +EXPORT_SYMBOL_GPL(offline_and_remove_memory); #endif /* CONFIG_MEMORY_HOTREMOVE */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 727751219003..48eb0f1410d4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8285,6 +8285,19 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page, if ((flags & MEMORY_OFFLINE) && PageHWPoison(page)) continue; + /* + * We treat all PageOffline() pages as movable when offlining + * to give drivers a chance to decrement their reference count + * in MEM_GOING_OFFLINE in order to indicate that these pages + * can be offlined as there are no direct references anymore. + * For actually unmovable PageOffline() where the driver does + * not support this, we will fail later when trying to actually + * move these pages that still have a reference count > 0. + * (false negatives in this function only) + */ + if ((flags & MEMORY_OFFLINE) && PageOffline(page)) + continue; + if (__PageMovable(page) || PageLRU(page)) continue; @@ -8516,6 +8529,7 @@ done: pfn_max_align_up(end), migratetype); return ret; } +EXPORT_SYMBOL(alloc_contig_range); static int __alloc_contig_pages(unsigned long start_pfn, unsigned long nr_pages, gfp_t gfp_mask) @@ -8631,6 +8645,7 @@ void free_contig_range(unsigned long pfn, unsigned int nr_pages) } WARN(count != 0, "%d pages are still in use!\n", count); } +EXPORT_SYMBOL(free_contig_range); /* * The zone indicated has a new number of managed_pages; batch sizes and percpu @@ -8703,6 +8718,17 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) offlined_pages++; continue; } + /* + * At this point all remaining PageOffline() pages have a + * reference count of 0 and can simply be skipped. + */ + if (PageOffline(page)) { + BUG_ON(page_count(page)); + BUG_ON(PageBuddy(page)); + pfn++; + offlined_pages++; + continue; + } BUG_ON(page_count(page)); BUG_ON(!PageBuddy(page)); diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 2c11a38d6e87..f6d07c5f0d34 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -151,6 +151,7 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * a bit mask) * MEMORY_OFFLINE - isolate to offline (!allocate) memory * e.g., skip over PageHWPoison() pages + * and PageOffline() pages. * REPORT_FAILURE - report details about the failure to * isolate the range * @@ -259,6 +260,14 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, else if ((flags & MEMORY_OFFLINE) && PageHWPoison(page)) /* A HWPoisoned page cannot be also PageBuddy */ pfn++; + else if ((flags & MEMORY_OFFLINE) && PageOffline(page) && + !page_count(page)) + /* + * The responsible driver agreed to skip PageOffline() + * pages when offlining memory by dropping its + * reference in MEM_GOING_OFFLINE. + */ + pfn++; else break; }