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

Pull virtio updates from Michael Tsirkin:
 "A small number of improvements all over the place:

   - vdpa/octeon support for multiple interrupts

   - virtio-pci support for error recovery

   - vp_vdpa support for notification with data

   - vhost/net fix to set num_buffers for spec compliance

   - virtio-mem now works with kdump on s390

  And small cleanups all over the place"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (23 commits)
  virtio_blk: Add support for transport error recovery
  virtio_pci: Add support for PCIe Function Level Reset
  vhost/net: Set num_buffers for virtio 1.0
  vdpa/octeon_ep: read vendor-specific PCI capability
  virtio-pci: define type and header for PCI vendor data
  vdpa/octeon_ep: handle device config change events
  vdpa/octeon_ep: enable support for multiple interrupts per device
  vdpa: solidrun: Replace deprecated PCI functions
  s390/kdump: virtio-mem kdump support (CONFIG_PROC_VMCORE_DEVICE_RAM)
  virtio-mem: support CONFIG_PROC_VMCORE_DEVICE_RAM
  virtio-mem: remember usable region size
  virtio-mem: mark device ready before registering callbacks in kdump mode
  fs/proc/vmcore: introduce PROC_VMCORE_DEVICE_RAM to detect device RAM ranges in 2nd kernel
  fs/proc/vmcore: factor out freeing a list of vmcore ranges
  fs/proc/vmcore: factor out allocating a vmcore range and adding it to a list
  fs/proc/vmcore: move vmcore definitions out of kcore.h
  fs/proc/vmcore: prefix all pr_* with "vmcore:"
  fs/proc/vmcore: disallow vmcore modifications while the vmcore is open
  fs/proc/vmcore: replace vmcoredd_mutex by vmcore_mutex
  fs/proc/vmcore: convert vmcore_cb_lock into vmcore_mutex
  ...

11 files changed, 403 insertions, 105 deletions

diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index bbaa26b523b8..bfbe391c20fe 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -1579,8 +1579,7 @@ static void virtblk_remove(struct virtio_device *vdev)
 	put_disk(vblk->disk);
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int virtblk_freeze(struct virtio_device *vdev)
+static int virtblk_freeze_priv(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
 	struct request_queue *q = vblk->disk->queue;
@@ -1602,7 +1601,7 @@ static int virtblk_freeze(struct virtio_device *vdev)
 	return 0;
 }
 
-static int virtblk_restore(struct virtio_device *vdev)
+static int virtblk_restore_priv(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
 	int ret;
@@ -1616,8 +1615,29 @@ static int virtblk_restore(struct virtio_device *vdev)
 
 	return 0;
 }
+
+#ifdef CONFIG_PM_SLEEP
+static int virtblk_freeze(struct virtio_device *vdev)
+{
+	return virtblk_freeze_priv(vdev);
+}
+
+static int virtblk_restore(struct virtio_device *vdev)
+{
+	return virtblk_restore_priv(vdev);
+}
 #endif
 
+static int virtblk_reset_prepare(struct virtio_device *vdev)
+{
+	return virtblk_freeze_priv(vdev);
+}
+
+static int virtblk_reset_done(struct virtio_device *vdev)
+{
+	return virtblk_restore_priv(vdev);
+}
+
 static const struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID },
 	{ 0 },
@@ -1653,6 +1673,8 @@ static struct virtio_driver virtio_blk = {
 	.freeze				= virtblk_freeze,
 	.restore			= virtblk_restore,
 #endif
+	.reset_prepare			= virtblk_reset_prepare,
+	.reset_done			= virtblk_reset_done,
 };
 
 static int __init virtio_blk_init(void)
diff --git a/drivers/vdpa/octeon_ep/octep_vdpa.h b/drivers/vdpa/octeon_ep/octep_vdpa.h
index 046710ec4d42..53b020b019f7 100644
--- a/drivers/vdpa/octeon_ep/octep_vdpa.h
+++ b/drivers/vdpa/octeon_ep/octep_vdpa.h
@@ -8,6 +8,7 @@
 #include <linux/pci_regs.h>
 #include <linux/vdpa.h>
 #include <linux/virtio_pci_modern.h>
+#include <uapi/linux/virtio_crypto.h>
 #include <uapi/linux/virtio_net.h>
 #include <uapi/linux/virtio_blk.h>
 #include <uapi/linux/virtio_config.h>
@@ -29,12 +30,12 @@
 #define OCTEP_EPF_RINFO(x) (0x000209f0 | ((x) << 25))
 #define OCTEP_VF_MBOX_DATA(x) (0x00010210 | ((x) << 17))
 #define OCTEP_PF_MBOX_DATA(x) (0x00022000 | ((x) << 4))
-
-#define OCTEP_EPF_RINFO_RPVF(val) (((val) >> 32) & 0xF)
-#define OCTEP_EPF_RINFO_NVFS(val) (((val) >> 48) & 0x7F)
+#define OCTEP_VF_IN_CTRL(x)        (0x00010000 | ((x) << 17))
+#define OCTEP_VF_IN_CTRL_RPVF(val) (((val) >> 48) & 0xF)
 
 #define OCTEP_FW_READY_SIGNATURE0  0xFEEDFEED
 #define OCTEP_FW_READY_SIGNATURE1  0x3355ffaa
+#define OCTEP_MAX_CB_INTR          8
 
 enum octep_vdpa_dev_status {
 	OCTEP_VDPA_DEV_STATUS_INVALID,
@@ -48,9 +49,26 @@ enum octep_vdpa_dev_status {
 struct octep_vring_info {
 	struct vdpa_callback cb;
 	void __iomem *notify_addr;
-	u32 __iomem *cb_notify_addr;
+	void __iomem *cb_notify_addr;
 	phys_addr_t notify_pa;
-	char msix_name[256];
+};
+
+enum octep_pci_vndr_cfg_type {
+	OCTEP_PCI_VNDR_CFG_TYPE_VIRTIO_ID,
+	OCTEP_PCI_VNDR_CFG_TYPE_MAX,
+};
+
+struct octep_pci_vndr_data {
+	struct virtio_pci_vndr_data hdr;
+	u8 id;
+	u8 bar;
+	union {
+		u64 data;
+		struct {
+			u32 offset;
+			u32 length;
+		};
+	};
 };
 
 struct octep_hw {
@@ -68,7 +86,9 @@ struct octep_hw {
 	u64 features;
 	u16 nr_vring;
 	u32 config_size;
-	int irq;
+	int nb_irqs;
+	int *irqs;
+	u8 dev_id;
 };
 
 u8 octep_hw_get_status(struct octep_hw *oct_hw);
diff --git a/drivers/vdpa/octeon_ep/octep_vdpa_hw.c b/drivers/vdpa/octeon_ep/octep_vdpa_hw.c
index 1d4767b33315..74240101c505 100644
--- a/drivers/vdpa/octeon_ep/octep_vdpa_hw.c
+++ b/drivers/vdpa/octeon_ep/octep_vdpa_hw.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2024 Marvell. */
 
 #include <linux/iopoll.h>
+#include <linux/build_bug.h>
 
 #include "octep_vdpa.h"
 
@@ -358,7 +359,14 @@ u16 octep_get_vq_size(struct octep_hw *oct_hw)
 
 static u32 octep_get_config_size(struct octep_hw *oct_hw)
 {
-	return sizeof(struct virtio_net_config);
+	switch (oct_hw->dev_id) {
+	case VIRTIO_ID_NET:
+		return sizeof(struct virtio_net_config);
+	case VIRTIO_ID_CRYPTO:
+		return sizeof(struct virtio_crypto_config);
+	default:
+		return 0;
+	}
 }
 
 static void __iomem *octep_get_cap_addr(struct octep_hw *oct_hw, struct virtio_pci_cap *cap)
@@ -416,8 +424,25 @@ static int octep_pci_signature_verify(struct octep_hw *oct_hw)
 	return 0;
 }
 
+static void octep_vndr_data_process(struct octep_hw *oct_hw,
+				    struct octep_pci_vndr_data *vndr_data)
+{
+	BUILD_BUG_ON(sizeof(struct octep_pci_vndr_data) % 4 != 0);
+
+	switch (vndr_data->id) {
+	case OCTEP_PCI_VNDR_CFG_TYPE_VIRTIO_ID:
+		oct_hw->dev_id = (u8)vndr_data->data;
+		break;
+	default:
+		dev_err(&oct_hw->pdev->dev, "Invalid vendor data id %u\n",
+			vndr_data->id);
+		break;
+	}
+}
+
 int octep_hw_caps_read(struct octep_hw *oct_hw, struct pci_dev *pdev)
 {
+	struct octep_pci_vndr_data vndr_data;
 	struct octep_mbox __iomem *mbox;
 	struct device *dev = &pdev->dev;
 	struct virtio_pci_cap cap;
@@ -466,6 +491,15 @@ int octep_hw_caps_read(struct octep_hw *oct_hw, struct pci_dev *pdev)
 		case VIRTIO_PCI_CAP_ISR_CFG:
 			oct_hw->isr = octep_get_cap_addr(oct_hw, &cap);
 			break;
+		case VIRTIO_PCI_CAP_VENDOR_CFG:
+			octep_pci_caps_read(oct_hw, &vndr_data, sizeof(vndr_data), pos);
+			if (vndr_data.hdr.vendor_id != PCI_VENDOR_ID_CAVIUM) {
+				dev_err(dev, "Invalid vendor data\n");
+				return -EINVAL;
+			}
+
+			octep_vndr_data_process(oct_hw, &vndr_data);
+			break;
 		}
 
 		pos = cap.cap_next;
@@ -495,8 +529,6 @@ int octep_hw_caps_read(struct octep_hw *oct_hw, struct pci_dev *pdev)
 	if (!oct_hw->vqs)
 		return -ENOMEM;
 
-	oct_hw->irq = -1;
-
 	dev_info(&pdev->dev, "Device features : %llx\n", oct_hw->features);
 	dev_info(&pdev->dev, "Maximum queues : %u\n", oct_hw->nr_vring);
 
diff --git a/drivers/vdpa/octeon_ep/octep_vdpa_main.c b/drivers/vdpa/octeon_ep/octep_vdpa_main.c
index cd55b1aac151..f3d4dda4e04c 100644
--- a/drivers/vdpa/octeon_ep/octep_vdpa_main.c
+++ b/drivers/vdpa/octeon_ep/octep_vdpa_main.c
@@ -49,58 +49,89 @@ static irqreturn_t octep_vdpa_intr_handler(int irq, void *data)
 	struct octep_hw *oct_hw = data;
 	int i;
 
-	for (i = 0; i < oct_hw->nr_vring; i++) {
-		if (oct_hw->vqs[i].cb.callback && ioread32(oct_hw->vqs[i].cb_notify_addr)) {
-			/* Acknowledge the per queue notification to the device */
-			iowrite32(0, oct_hw->vqs[i].cb_notify_addr);
-			oct_hw->vqs[i].cb.callback(oct_hw->vqs[i].cb.private);
+	/* Each device has multiple interrupts (nb_irqs) shared among rings
+	 * (nr_vring). Device interrupts are mapped to the rings in a
+	 * round-robin fashion.
+	 *
+	 * For example, if nb_irqs = 8 and nr_vring = 64:
+	 * 0 -> 0, 8, 16, 24, 32, 40, 48, 56;
+	 * 1 -> 1, 9, 17, 25, 33, 41, 49, 57;
+	 * ...
+	 * 7 -> 7, 15, 23, 31, 39, 47, 55, 63;
+	 */
+
+	for (i = irq - oct_hw->irqs[0]; i < oct_hw->nr_vring; i += oct_hw->nb_irqs) {
+		if (ioread8(oct_hw->vqs[i].cb_notify_addr)) {
+			/* Acknowledge the per ring notification to the device */
+			iowrite8(0, oct_hw->vqs[i].cb_notify_addr);
+
+			if (likely(oct_hw->vqs[i].cb.callback))
+				oct_hw->vqs[i].cb.callback(oct_hw->vqs[i].cb.private);
+			break;
 		}
 	}
 
+	/* Check for config interrupt. Config uses the first interrupt */
+	if (unlikely(irq == oct_hw->irqs[0] && ioread8(oct_hw->isr))) {
+		iowrite8(0, oct_hw->isr);
+
+		if (oct_hw->config_cb.callback)
+			oct_hw->config_cb.callback(oct_hw->config_cb.private);
+	}
+
 	return IRQ_HANDLED;
 }
 
 static void octep_free_irqs(struct octep_hw *oct_hw)
 {
 	struct pci_dev *pdev = oct_hw->pdev;
+	int irq;
 
-	if (oct_hw->irq != -1) {
-		devm_free_irq(&pdev->dev, oct_hw->irq, oct_hw);
-		oct_hw->irq = -1;
+	if (!oct_hw->irqs)
+		return;
+
+	for (irq = 0; irq < oct_hw->nb_irqs; irq++) {
+		if (!oct_hw->irqs[irq])
+			break;
+
+		devm_free_irq(&pdev->dev, oct_hw->irqs[irq], oct_hw);
 	}
+
 	pci_free_irq_vectors(pdev);
+	devm_kfree(&pdev->dev, oct_hw->irqs);
+	oct_hw->irqs = NULL;
 }
 
 static int octep_request_irqs(struct octep_hw *oct_hw)
 {
 	struct pci_dev *pdev = oct_hw->pdev;
-	int ret, irq;
+	int ret, irq, idx;
 
-	/* Currently HW device provisions one IRQ per VF, hence
-	 * allocate one IRQ for all virtqueues call interface.
-	 */
-	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSIX);
+	oct_hw->irqs = devm_kcalloc(&pdev->dev, oct_hw->nb_irqs, sizeof(int), GFP_KERNEL);
+	if (!oct_hw->irqs)
+		return -ENOMEM;
+
+	ret = pci_alloc_irq_vectors(pdev, 1, oct_hw->nb_irqs, PCI_IRQ_MSIX);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to alloc msix vector");
 		return ret;
 	}
 
-	snprintf(oct_hw->vqs->msix_name, sizeof(oct_hw->vqs->msix_name),
-		 OCTEP_VDPA_DRIVER_NAME "-vf-%d", pci_iov_vf_id(pdev));
-
-	irq = pci_irq_vector(pdev, 0);
-	ret = devm_request_irq(&pdev->dev, irq, octep_vdpa_intr_handler, 0,
-			       oct_hw->vqs->msix_name, oct_hw);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to register interrupt handler\n");
-		goto free_irq_vec;
+	for (idx = 0; idx < oct_hw->nb_irqs; idx++) {
+		irq = pci_irq_vector(pdev, idx);
+		ret = devm_request_irq(&pdev->dev, irq, octep_vdpa_intr_handler, 0,
+				       dev_name(&pdev->dev), oct_hw);
+		if (ret) {
+			dev_err(&pdev->dev, "Failed to register interrupt handler\n");
+			goto free_irqs;
+		}
+		oct_hw->irqs[idx] = irq;
 	}
-	oct_hw->irq = irq;
 
 	return 0;
 
-free_irq_vec:
-	pci_free_irq_vectors(pdev);
+free_irqs:
+	octep_free_irqs(oct_hw);
 	return ret;
 }
 
@@ -271,7 +302,9 @@ static u32 octep_vdpa_get_generation(struct vdpa_device *vdpa_dev)
 
 static u32 octep_vdpa_get_device_id(struct vdpa_device *vdpa_dev)
 {
-	return VIRTIO_ID_NET;
+	struct octep_hw *oct_hw = vdpa_to_octep_hw(vdpa_dev);
+
+	return oct_hw->dev_id;
 }
 
 static u32 octep_vdpa_get_vendor_id(struct vdpa_device *vdpa_dev)
@@ -559,6 +592,7 @@ static void octep_vdpa_setup_task(struct work_struct *work)
 	struct device *dev = &pdev->dev;
 	struct octep_hw *oct_hw;
 	unsigned long timeout;
+	u64 val;
 	int ret;
 
 	oct_hw = &mgmt_dev->oct_hw;
@@ -590,6 +624,13 @@ static void octep_vdpa_setup_task(struct work_struct *work)
 	if (ret)
 		return;
 
+	val = readq(oct_hw->base[OCTEP_HW_MBOX_BAR] + OCTEP_VF_IN_CTRL(0));
+	oct_hw->nb_irqs = OCTEP_VF_IN_CTRL_RPVF(val);
+	if (!oct_hw->nb_irqs || oct_hw->nb_irqs > OCTEP_MAX_CB_INTR) {
+		dev_err(dev, "Invalid number of interrupts %d\n", oct_hw->nb_irqs);
+		goto unmap_region;
+	}
+
 	ret = octep_hw_caps_read(oct_hw, pdev);
 	if (ret < 0)
 		goto unmap_region;
@@ -768,12 +809,6 @@ static int octep_vdpa_pf_setup(struct octep_pf *octpf)
 		return -EINVAL;
 	}
 
-	if (OCTEP_EPF_RINFO_RPVF(val) != BIT_ULL(0)) {
-		val &= ~GENMASK_ULL(35, 32);
-		val |= BIT_ULL(32);
-		writeq(val, addr + OCTEP_EPF_RINFO(0));
-	}
-
 	len = pci_resource_len(pdev, OCTEP_HW_CAPS_BAR);
 
 	octpf->vf_stride = len / totalvfs;
diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c
index c8b74980dbd1..55ec51c17ab3 100644
--- a/drivers/vdpa/solidrun/snet_main.c
+++ b/drivers/vdpa/solidrun/snet_main.c
@@ -556,36 +556,38 @@ static const struct vdpa_config_ops snet_config_ops = {
 static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet)
 {
 	char *name;
-	int ret, i, mask = 0;
+	unsigned short i;
+	bool bars_found = false;
+
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "psnet[%s]-bars", pci_name(pdev));
+	if (!name)
+		return -ENOMEM;
+
 	/* We don't know which BAR will be used to communicate..
 	 * We will map every bar with len > 0.
 	 *
 	 * Later, we will discover the BAR and unmap all other BARs.
 	 */
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		if (pci_resource_len(pdev, i))
-			mask |= (1 << i);
-	}
+		void __iomem *io;
 
-	/* No BAR can be used.. */
-	if (!mask) {
-		SNET_ERR(pdev, "Failed to find a PCI BAR\n");
-		return -ENODEV;
-	}
+		if (pci_resource_len(pdev, i) == 0)
+			continue;
 
-	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "psnet[%s]-bars", pci_name(pdev));
-	if (!name)
-		return -ENOMEM;
+		io = pcim_iomap_region(pdev, i, name);
+		if (IS_ERR(io)) {
+			SNET_ERR(pdev, "Failed to request and map PCI BARs\n");
+			return PTR_ERR(io);
+		}
 
-	ret = pcim_iomap_regions(pdev, mask, name);
-	if (ret) {
-		SNET_ERR(pdev, "Failed to request and map PCI BARs\n");
-		return ret;
+		psnet->bars[i] = io;
+		bars_found = true;
 	}
 
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		if (mask & (1 << i))
-			psnet->bars[i] = pcim_iomap_table(pdev)[i];
+	/* No BAR can be used.. */
+	if (!bars_found) {
+		SNET_ERR(pdev, "Failed to find a PCI BAR\n");
+		return -ENODEV;
 	}
 
 	return 0;
@@ -594,20 +596,20 @@ static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet)
 static int snet_open_vf_bar(struct pci_dev *pdev, struct snet *snet)
 {
 	char *name;
-	int ret;
+	void __iomem *io;
 
 	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "snet[%s]-bars", pci_name(pdev));
 	if (!name)
 		return -ENOMEM;
 
 	/* Request and map BAR */
-	ret = pcim_iomap_regions(pdev, BIT(snet->psnet->cfg.vf_bar), name);
-	if (ret) {
+	io = pcim_iomap_region(pdev, snet->psnet->cfg.vf_bar, name);
+	if (IS_ERR(io)) {
 		SNET_ERR(pdev, "Failed to request and map PCI BAR for a VF\n");
-		return ret;
+		return PTR_ERR(io);
 	}
 
-	snet->bar = pcim_iomap_table(pdev)[snet->psnet->cfg.vf_bar];
+	snet->bar = io;
 
 	return 0;
 }
@@ -656,15 +658,12 @@ static int psnet_detect_bar(struct psnet *psnet, u32 off)
 
 static void psnet_unmap_unused_bars(struct pci_dev *pdev, struct psnet *psnet)
 {
-	int i, mask = 0;
+	unsigned short i;
 
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		if (psnet->bars[i] && i != psnet->barno)
-			mask |= (1 << i);
+			pcim_iounmap_region(pdev, i);
 	}
-
-	if (mask)
-		pcim_iounmap_regions(pdev, mask);
 }
 
 /* Read SNET config from PCI BAR */
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c
index 16380764275e..8787407f75b0 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -367,6 +367,14 @@ static void vp_vdpa_kick_vq(struct vdpa_device *vdpa, u16 qid)
 	vp_iowrite16(qid, vp_vdpa->vring[qid].notify);
 }
 
+static void vp_vdpa_kick_vq_with_data(struct vdpa_device *vdpa, u32 data)
+{
+	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
+	u16 qid = data & 0xFFFF;
+
+	vp_iowrite32(data, vp_vdpa->vring[qid].notify);
+}
+
 static u32 vp_vdpa_get_generation(struct vdpa_device *vdpa)
 {
 	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
@@ -472,6 +480,7 @@ static const struct vdpa_config_ops vp_vdpa_ops = {
 	.get_vq_size	= vp_vdpa_get_vq_size,
 	.set_vq_address	= vp_vdpa_set_vq_address,
 	.kick_vq	= vp_vdpa_kick_vq,
+	.kick_vq_with_data      = vp_vdpa_kick_vq_with_data,
 	.get_generation	= vp_vdpa_get_generation,
 	.get_device_id	= vp_vdpa_get_device_id,
 	.get_vendor_id	= vp_vdpa_get_vendor_id,
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 9ad37c012189..b9b9e9d40951 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1107,6 +1107,7 @@ static void handle_rx(struct vhost_net *net)
 	size_t vhost_hlen, sock_hlen;
 	size_t vhost_len, sock_len;
 	bool busyloop_intr = false;
+	bool set_num_buffers;
 	struct socket *sock;
 	struct iov_iter fixup;
 	__virtio16 num_buffers;
@@ -1129,6 +1130,8 @@ static void handle_rx(struct vhost_net *net)
 	vq_log = unlikely(vhost_has_feature(vq, VHOST_F_LOG_ALL)) ?
 		vq->log : NULL;
 	mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);
+	set_num_buffers = mergeable ||
+			  vhost_has_feature(vq, VIRTIO_F_VERSION_1);
 
 	do {
 		sock_len = vhost_net_rx_peek_head_len(net, sock->sk,
@@ -1205,7 +1208,7 @@ static void handle_rx(struct vhost_net *net)
 		/* TODO: Should check and handle checksum. */
 
 		num_buffers = cpu_to_vhost16(vq, headcount);
-		if (likely(mergeable) &&
+		if (likely(set_num_buffers) &&
 		    copy_to_iter(&num_buffers, sizeof num_buffers,
 				 &fixup) != sizeof num_buffers) {
 			vq_err(vq, "Failed num_buffers write");
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index b10ed9f5b543..ba37665188b5 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -546,29 +546,7 @@ void unregister_virtio_device(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(unregister_virtio_device);
 
-#ifdef CONFIG_PM_SLEEP
-int virtio_device_freeze(struct virtio_device *dev)
-{
-	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
-	int ret;
-
-	virtio_config_core_disable(dev);
-
-	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
-
-	if (drv && drv->freeze) {
-		ret = drv->freeze(dev);
-		if (ret) {
-			virtio_config_core_enable(dev);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(virtio_device_freeze);
-
-int virtio_device_restore(struct virtio_device *dev)
+static int virtio_device_restore_priv(struct virtio_device *dev, bool restore)
 {
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 	int ret;
@@ -599,8 +577,14 @@ int virtio_device_restore(struct virtio_device *dev)
 	if (ret)
 		goto err;
 
-	if (drv->restore) {
-		ret = drv->restore(dev);
+	if (restore) {
+		if (drv->restore) {
+			ret = drv->restore(dev);
+			if (ret)
+				goto err;
+		}
+	} else {
+		ret = drv->reset_done(dev);
 		if (ret)
 			goto err;
 	}
@@ -617,9 +601,69 @@ err:
 	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return ret;
 }
+
+#ifdef CONFIG_PM_SLEEP
+int virtio_device_freeze(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+	int ret;
+
+	virtio_config_core_disable(dev);
+
+	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
+
+	if (drv && drv->freeze) {
+		ret = drv->freeze(dev);
+		if (ret) {
+			virtio_config_core_enable(dev);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_device_freeze);
+
+int virtio_device_restore(struct virtio_device *dev)
+{
+	return virtio_device_restore_priv(dev, true);
+}
 EXPORT_SYMBOL_GPL(virtio_device_restore);
 #endif
 
+int virtio_device_reset_prepare(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+	int ret;
+
+	if (!drv || !drv->reset_prepare)
+		return -EOPNOTSUPP;
+
+	virtio_config_core_disable(dev);
+
+	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
+
+	ret = drv->reset_prepare(dev);
+	if (ret) {
+		virtio_config_core_enable(dev);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_device_reset_prepare);
+
+int virtio_device_reset_done(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	if (!drv || !drv->reset_done)
+		return -EOPNOTSUPP;
+
+	return virtio_device_restore_priv(dev, false);
+}
+EXPORT_SYMBOL_GPL(virtio_device_reset_done);
+
 static int virtio_init(void)
 {
 	if (bus_register(&virtio_bus) != 0)
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index b36d2803674e..89da052f4f68 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -251,7 +251,7 @@ static unsigned int fill_balloon(struct virtio_balloon *vb, size_t num)
 
 	for (num_pfns = 0; num_pfns < num;
 	     num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
-		struct page *page = balloon_page_alloc();
+		page = balloon_page_alloc();
 
 		if (!page) {
 			dev_info_ratelimited(&vb->vdev->dev,
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index b0b871441578..8a294b9cbcf6 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -133,6 +133,8 @@ struct virtio_mem {
 	uint64_t addr;
 	/* Maximum region size in bytes. */
 	uint64_t region_size;
+	/* Usable region size in bytes. */
+	uint64_t usable_region_size;
 
 	/* The parent resource for all memory added via this device. */
 	struct resource *parent_resource;
@@ -2368,7 +2370,7 @@ static int virtio_mem_cleanup_pending_mb(struct virtio_mem *vm)
 static void virtio_mem_refresh_config(struct virtio_mem *vm)
 {
 	const struct range pluggable_range = mhp_get_pluggable_range(true);
-	uint64_t new_plugged_size, usable_region_size, end_addr;
+	uint64_t new_plugged_size, end_addr;
 
 	/* the plugged_size is just a reflection of what _we_ did previously */
 	virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size,
@@ -2378,8 +2380,8 @@ static void virtio_mem_refresh_config(struct virtio_mem *vm)
 
 	/* calculate the last usable memory block id */
 	virtio_cread_le(vm->vdev, struct virtio_mem_config,
-			usable_region_size, &usable_region_size);
-	end_addr = min(vm->addr + usable_region_size - 1,
+			usable_region_size, &vm->usable_region_size);
+	end_addr = min(vm->addr + vm->usable_region_size - 1,
 		       pluggable_range.end);
 
 	if (vm->in_sbm) {
@@ -2648,6 +2650,7 @@ static int virtio_mem_init_hotplug(struct virtio_mem *vm)
 	if (rc)
 		goto out_unreg_pm;
 
+	virtio_device_ready(vm->vdev);
 	return 0;
 out_unreg_pm:
 	unregister_pm_notifier(&vm->pm_notifier);
@@ -2725,13 +2728,103 @@ static bool virtio_mem_vmcore_pfn_is_ram(struct vmcore_cb *cb,
 	mutex_unlock(&vm->hotplug_mutex);
 	return is_ram;
 }
+
+#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM
+static int virtio_mem_vmcore_add_device_ram(struct virtio_mem *vm,
+		struct list_head *list, uint64_t start, uint64_t end)
+{
+	int rc;
+
+	rc = vmcore_alloc_add_range(list, start, end - start);
+	if (rc)
+		dev_err(&vm->vdev->dev,
+			 "Error adding device RAM range: %d\n", rc);
+	return rc;
+}
+
+static int virtio_mem_vmcore_get_device_ram(struct vmcore_cb *cb,
+		struct list_head *list)
+{
+	struct virtio_mem *vm = container_of(cb, struct virtio_mem,
+					     vmcore_cb);
+	const uint64_t device_start = vm->addr;
+	const uint64_t device_end = vm->addr + vm->usable_region_size;
+	uint64_t chunk_size, cur_start, cur_end, plugged_range_start = 0;
+	LIST_HEAD(tmp_list);
+	int rc;
+
+	if (!vm->plugged_size)
+		return 0;
+
+	/* Process memory sections, unless the device block size is bigger. */
+	chunk_size = max_t(uint64_t, PFN_PHYS(PAGES_PER_SECTION),
+			   vm->device_block_size);
+
+	mutex_lock(&vm->hotplug_mutex);
+
+	/*
+	 * We process larger chunks and indicate the complete chunk if any
+	 * block in there is plugged. This reduces the number of pfn_is_ram()
+	 * callbacks and mimic what is effectively being done when the old
+	 * kernel would add complete memory sections/blocks to the elfcore hdr.
+	 */
+	cur_start = device_start;
+	for (cur_start = device_start; cur_start < device_end; cur_start = cur_end) {
+		cur_end = ALIGN_DOWN(cur_start + chunk_size, chunk_size);
+		cur_end = min_t(uint64_t, cur_end, device_end);
+
+		rc = virtio_mem_send_state_request(vm, cur_start,
+						   cur_end - cur_start);
+
+		if (rc < 0) {
+			dev_err(&vm->vdev->dev,
+				"Error querying block states: %d\n", rc);
+			goto out;
+		} else if (rc != VIRTIO_MEM_STATE_UNPLUGGED) {
+			/* Merge ranges with plugged memory. */
+			if (!plugged_range_start)
+				plugged_range_start = cur_start;
+			continue;
+		}
+
+		/* Flush any plugged range. */
+		if (plugged_range_start) {
+			rc = virtio_mem_vmcore_add_device_ram(vm, &tmp_list,
+							      plugged_range_start,
+							      cur_start);
+			if (rc)
+				goto out;
+			plugged_range_start = 0;
+		}
+	}
+
+	/* Flush any plugged range. */
+	if (plugged_range_start)
+		rc = virtio_mem_vmcore_add_device_ram(vm, &tmp_list,
+						      plugged_range_start,
+						      cur_start);
+out:
+	mutex_unlock(&vm->hotplug_mutex);
+	if (rc < 0) {
+		vmcore_free_ranges(&tmp_list);
+		return rc;
+	}
+	list_splice_tail(&tmp_list, list);
+	return 0;
+}
+#endif /* CONFIG_PROC_VMCORE_DEVICE_RAM */
 #endif /* CONFIG_PROC_VMCORE */
 
 static int virtio_mem_init_kdump(struct virtio_mem *vm)
 {
+	/* We must be prepared to receive a callback immediately. */
+	virtio_device_ready(vm->vdev);
 #ifdef CONFIG_PROC_VMCORE
 	dev_info(&vm->vdev->dev, "memory hot(un)plug disabled in kdump kernel\n");
 	vm->vmcore_cb.pfn_is_ram = virtio_mem_vmcore_pfn_is_ram;
+#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM
+	vm->vmcore_cb.get_device_ram = virtio_mem_vmcore_get_device_ram;
+#endif /* CONFIG_PROC_VMCORE_DEVICE_RAM */
 	register_vmcore_cb(&vm->vmcore_cb);
 	return 0;
 #else /* CONFIG_PROC_VMCORE */
@@ -2760,6 +2853,8 @@ static int virtio_mem_init(struct virtio_mem *vm)
 	virtio_cread_le(vm->vdev, struct virtio_mem_config, addr, &vm->addr);
 	virtio_cread_le(vm->vdev, struct virtio_mem_config, region_size,
 			&vm->region_size);
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, usable_region_size,
+			&vm->usable_region_size);
 
 	/* Determine the nid for the device based on the lowest address. */
 	if (vm->nid == NUMA_NO_NODE)
@@ -2870,8 +2965,6 @@ static int virtio_mem_probe(struct virtio_device *vdev)
 	if (rc)
 		goto out_del_vq;
 
-	virtio_device_ready(vdev);
-
 	/* trigger a config update to start processing the requested_size */
 	if (!vm->in_kdump) {
 		atomic_set(&vm->config_changed, 1);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 88074451dd61..d6d79af44569 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -794,6 +794,46 @@ static int virtio_pci_sriov_configure(struct pci_dev *pci_dev, int num_vfs)
 	return num_vfs;
 }
 
+static void virtio_pci_reset_prepare(struct pci_dev *pci_dev)
+{
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	int ret = 0;
+
+	ret = virtio_device_reset_prepare(&vp_dev->vdev);
+	if (ret) {
+		if (ret != -EOPNOTSUPP)
+			dev_warn(&pci_dev->dev, "Reset prepare failure: %d",
+				 ret);
+		return;
+	}
+
+	if (pci_is_enabled(pci_dev))
+		pci_disable_device(pci_dev);
+}
+
+static void virtio_pci_reset_done(struct pci_dev *pci_dev)
+{
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	int ret;
+
+	if (pci_is_enabled(pci_dev))
+		return;
+
+	ret = pci_enable_device(pci_dev);
+	if (!ret) {
+		pci_set_master(pci_dev);
+		ret = virtio_device_reset_done(&vp_dev->vdev);
+	}
+
+	if (ret && ret != -EOPNOTSUPP)
+		dev_warn(&pci_dev->dev, "Reset done failure: %d", ret);
+}
+
+static const struct pci_error_handlers virtio_pci_err_handler = {
+	.reset_prepare  = virtio_pci_reset_prepare,
+	.reset_done     = virtio_pci_reset_done,
+};
+
 static struct pci_driver virtio_pci_driver = {
 	.name		= "virtio-pci",
 	.id_table	= virtio_pci_id_table,
@@ -803,6 +843,7 @@ static struct pci_driver virtio_pci_driver = {
 	.driver.pm	= &virtio_pci_pm_ops,
 #endif
 	.sriov_configure = virtio_pci_sriov_configure,
+	.err_handler	= &virtio_pci_err_handler,
 };
 
 struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev)