virtio: features, fixes

virtio-mem
 doorbell mapping for vdpa
 config interrupt support in ifc
 fixes all over the place
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAl7fZ6APHG1zdEByZWRo
 YXQuY29tAAoJECgfDbjSjVRpkDoIAMcBcQx5su1iuX7vT35xzUWZO478eAf1jOMZ
 7KxKUVBeztkcxVFUlRVRu9MR6wOzwHils+1HD6025775Smr5M6x3aJxR6xOORaBj
 RoU6OVGkpDvbzsxlhW+xhONz4O7/RkveKJPCwzGjqHrsFeh92lkfTqroz/EuNpw+
 LZsO0+DhdUf123HbwHQp5lxW8EjyrRabgeZZg/D9VLPhoCP88vCjRhBXU2GPuaUl
 /UNXsQafn4xUgrxPaoN5f4Phn/P46NNrbZ1jmlkw/z/3QhF/DhktGXGaZsIHDCN/
 vicUii0or5QLeBsZpMbKko/BIe2xWHxFjkMRhMOMZOfcBb6sMBI=
 =auUa
 -----END PGP SIGNATURE-----

Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:

 - virtio-mem: paravirtualized memory hotplug

 - support doorbell mapping for vdpa

 - config interrupt support in ifc

 - fixes all over the place

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (40 commits)
  vhost/test: fix up after API change
  virtio_mem: convert device block size into 64bit
  virtio-mem: drop unnecessary initialization
  ifcvf: implement config interrupt in IFCVF
  vhost: replace -1 with VHOST_FILE_UNBIND in ioctls
  vhost_vdpa: Support config interrupt in vdpa
  ifcvf: ignore continuous setting same status value
  virtio-mem: Don't rely on implicit compiler padding for requests
  virtio-mem: Try to unplug the complete online memory block first
  virtio-mem: Use -ETXTBSY as error code if the device is busy
  virtio-mem: Unplug subblocks right-to-left
  virtio-mem: Drop manual check for already present memory
  virtio-mem: Add parent resource for all added "System RAM"
  virtio-mem: Better retry handling
  virtio-mem: Offline and remove completely unplugged memory blocks
  mm/memory_hotplug: Introduce offline_and_remove_memory()
  virtio-mem: Allow to offline partially unplugged memory blocks
  mm: Allow to offline unmovable PageOffline() pages via MEM_GOING_OFFLINE
  virtio-mem: Paravirtualized memory hotunplug part 2
  virtio-mem: Paravirtualized memory hotunplug part 1
  ...

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" <mst@redhat.com>
+M:	David Hildenbrand <david@redhat.com>
+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 <arei.gonglei@huawei.com>
 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 <david@redhat.com>
+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 <hdegoede@redhat.com>
 M:	Arnd Bergmann <arnd@arndb.de>

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)
 {

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++)
+	for (sg = req->src; src_nents; sg = sg_next(sg), src_nents--)
-		sgs[num_out++] = &req->src[i];
+		sgs[num_out++] = sg;
 
 	/* Destination data */
-	for (i = 0; i < dst_nents; i++)
+	for (sg = req->dst; sg; sg = sg_next(sg))
-		sgs[num_out + num_in++] = &req->dst[i];
+		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[] = { {

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

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

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

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);

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 {

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");

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;
+	ssize_t read, write;
-	int err;
+	size_t total_write;
 	int pkts = 0;
+	int err;
 
 	spin_lock(&vdpasim->lock);
 

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

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);

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);
 

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;
 

drivers/vhost/vdpa.c

@@ -15,12 +15,14 @@
 #include <linux/module.h>
 #include <linux/cdev.h>
 #include <linux/device.h>
+#include <linux/mm.h>
 #include <linux/iommu.h>
 #include <linux/uuid.h>
 #include <linux/vdpa.h>
 #include <linux/nospec.h>
 #include <linux/vhost.h>
 #include <linux/virtio_net.h>
+#include <linux/kernel.h>
 
 #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,
 };
 

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 */
+	vhost_attach_mm(dev);
-	dev->mm = get_task_mm(current);
+
 	dev->kcov_handle = kcov_common_handle();
-	worker = kthread_create(vhost_worker, dev, "vhost-%d", current->pid);
+	if (dev->use_worker) {
-	if (IS_ERR(worker)) {
+		worker = kthread_create(vhost_worker, dev,
-		err = PTR_ERR(worker);
+					"vhost-%d", current->pid);
-		goto err_worker;
+		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);
+	if (dev->worker) {
-	dev->worker = NULL;
+		kthread_stop(dev->worker);
+		dev->worker = NULL;
+	}
 err_worker:
-	if (dev->mm)
+	vhost_detach_mm(dev);
-		mmput(dev->mm);
-	dev->mm = NULL;
 	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)
+	vhost_detach_mm(dev);
-		mmput(dev->mm);
-	dev->mm = NULL;
 }
 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,
+			 vring_desc_t __user *desc,
-			 struct vring_avail __user *avail,
+			 vring_avail_t __user *avail,
-			 struct vring_used __user *used)
+			 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;
 

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;
+	vring_desc_t __user *desc;
-	struct vring_avail __user *avail;
+	vring_avail_t __user *avail;
-	struct vring_used __user *used;
+	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);

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,
+		     vring_desc_t __user *desc,
-		     struct vring_avail __user *avail,
+		     vring_avail_t __user *avail,
-		     struct vring_used __user *used)
+		     vring_used_t __user *used)
 {
 	/* Sane power of 2 please! */
 	if (!num || num > 0xffff || (num & (num - 1))) {

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);

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

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

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;

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) {
+	if (irq < 0)
-		dev_err(&vdev->dev, "Cannot get IRQ resource\n");
 		return irq;
-	}
 
 	err = request_irq(irq, vm_interrupt, IRQF_SHARED,
 			dev_name(&vdev->dev), vm_dev);

drivers/virtio/virtio_pci_modern.c

@@ -16,6 +16,7 @@
 
 #include <linux/delay.h>
 #define VIRTIO_PCI_NO_LEGACY
+#define VIRTIO_RING_NO_LEGACY
 #include "virtio_pci_common.h"
 
 /*

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) {}

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)
 

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);

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,
+		     vring_desc_t __user *desc,
-		     struct vring_avail __user *avail,
+		     vring_avail_t __user *avail,
-		     struct vring_used __user *used);
+		     vring_used_t __user *used);
 
 static inline void vringh_iov_init(struct vringh_iov *iov,
 				   struct iovec *iovec, unsigned num)

include/uapi/linux/vhost.h

@@ -15,6 +15,8 @@
 #include <linux/types.h>
 #include <linux/ioctl.h>
 
+#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

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 */

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 <david@redhat.com>
+ *
+ * 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 <linux/types.h>
+#include <linux/virtio_types.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio_config.h>
+
+/*
+ * 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 */

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.
+#ifndef VIRTIO_RING_NO_LEGACY
- * 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
 
 /* 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,

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
+ * non-lru movable pages and hugepages). Will skip over most unmovable
- * easier than scanning over linked list. This function returns the pfn
+ * pages (esp., pages that can be skipped when offlining), but bail out on
- * of the first found movable page if it's found, otherwise 0.
+ * 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);
+			ret = scan_movable_pages(pfn, end_pfn, &pfn);
-			if (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 */

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));

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;
 	}