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
...

arch/s390/Kconfig

···
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE	if PCI
 	select NEED_PER_CPU_EMBED_FIRST_CHUNK
+	select NEED_PROC_VMCORE_DEVICE_RAM if PROC_VMCORE
 	select NEED_SG_DMA_LENGTH	if PCI
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3

arch/s390/kernel/crash_dump.c

···
 	return cnt;
 }
 
+static void fill_ptload(Elf64_Phdr *phdr, unsigned long paddr,
+		unsigned long vaddr, unsigned long size)
+{
+	phdr->p_type = PT_LOAD;
+	phdr->p_vaddr = vaddr;
+	phdr->p_offset = paddr;
+	phdr->p_paddr = paddr;
+	phdr->p_filesz = size;
+	phdr->p_memsz = size;
+	phdr->p_flags = PF_R | PF_W | PF_X;
+	phdr->p_align = PAGE_SIZE;
+}
+
 /*
  * Initialize ELF loads (new kernel)
  */
···
 	if (os_info_has_vm)
 		old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE);
 	for_each_physmem_range(idx, &oldmem_type, &start, &end) {
-		phdr->p_type = PT_LOAD;
-		phdr->p_vaddr = old_identity_base + start;
-		phdr->p_offset = start;
-		phdr->p_paddr = start;
-		phdr->p_filesz = end - start;
-		phdr->p_memsz = end - start;
-		phdr->p_flags = PF_R | PF_W | PF_X;
-		phdr->p_align = PAGE_SIZE;
+		fill_ptload(phdr, start, old_identity_base + start,
+			    end - start);
 		phdr++;
 	}
 }
···
 {
 	return os_info_old_value(OS_INFO_KASLR_OFFSET);
 }
+
+#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM
+/*
+ * Fill PT_LOAD for a physical memory range owned by a device and detected by
+ * its device driver.
+ */
+void elfcorehdr_fill_device_ram_ptload_elf64(Elf64_Phdr *phdr,
+		unsigned long long paddr, unsigned long long size)
+{
+	unsigned long old_identity_base = 0;
+
+	if (os_info_has_vm())
+		old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE);
+	fill_ptload(phdr, paddr, old_identity_base + paddr, size);
+}
+#endif
 
 /*
  * Prepare PT_LOAD type program header for kernel image region

drivers/block/virtio_blk.c

···
 	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;
···
 	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;
···
 
 	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 },
···
 	.freeze				= virtblk_freeze,
 	.restore			= virtblk_restore,
 #endif
+	.reset_prepare			= virtblk_reset_prepare,
+	.reset_done			= virtblk_reset_done,
 };
 
 static int __init virtio_blk_init(void)

drivers/vdpa/octeon_ep/octep_vdpa.h

···
 #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>
···
 #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,
···
 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 {
···
 	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);

drivers/vdpa/octeon_ep/octep_vdpa_hw.c

···
 /* Copyright (C) 2024 Marvell. */
 
 #include <linux/iopoll.h>
+#include <linux/build_bug.h>
 
 #include "octep_vdpa.h"
 
···
 
 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)
···
 	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;
···
 		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;
···
 	oct_hw->vqs = devm_kcalloc(&pdev->dev, oct_hw->nr_vring, sizeof(*oct_hw->vqs), GFP_KERNEL);
 	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);

drivers/vdpa/octeon_ep/octep_vdpa_main.c

···
 	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;
 }
 
···
 
 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)
···
 	struct device *dev = &pdev->dev;
 	struct octep_hw *oct_hw;
 	unsigned long timeout;
+	u64 val;
 	int ret;
 
 	oct_hw = &mgmt_dev->oct_hw;
···
 	ret = octep_iomap_region(pdev, oct_hw->base, OCTEP_HW_CAPS_BAR);
 	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)
···
 	if (val == 0) {
 		dev_err(&pdev->dev, "Invalid device configuration\n");
 		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);

drivers/vdpa/solidrun/snet_main.c

···
 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;
+
+		if (pci_resource_len(pdev, i) == 0)
+			continue;
+
+		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);
+		}
+
+		psnet->bars[i] = io;
+		bars_found = true;
 	}
 
 	/* No BAR can be used.. */
-	if (!mask) {
+	if (!bars_found) {
 		SNET_ERR(pdev, "Failed to find a PCI BAR\n");
 		return -ENODEV;
-	}
-
-	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "psnet[%s]-bars", pci_name(pdev));
-	if (!name)
-		return -ENOMEM;
-
-	ret = pcim_iomap_regions(pdev, mask, name);
-	if (ret) {
-		SNET_ERR(pdev, "Failed to request and map PCI BARs\n");
-		return ret;
-	}
-
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		if (mask & (1 << i))
-			psnet->bars[i] = pcim_iomap_table(pdev)[i];
 	}
 
 	return 0;
···
 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;
 }
···
 
 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 */

drivers/vdpa/virtio_pci/vp_vdpa.c

···
 	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);
···
 	.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,

drivers/vhost/net.c

···
 	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;
···
 	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,
···
 		/* 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");

drivers/virtio/virtio.c

···
 }
 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;
···
 	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;
 	}
···
 	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)
 {

drivers/virtio/virtio_balloon.c

···
 
 	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,

drivers/virtio/virtio_mem.c

···
 	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;
···
 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,
···
 
 	/* 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) {
···
 	if (rc)
 		goto out_unreg_pm;
 
+	virtio_device_ready(vm->vdev);
 	return 0;
 out_unreg_pm:
 	unregister_pm_notifier(&vm->pm_notifier);
···
 	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 */
···
 	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)
···
 	rc = virtio_mem_init(vm);
 	if (rc)
 		goto out_del_vq;
-
-	virtio_device_ready(vdev);
 
 	/* trigger a config update to start processing the requested_size */
 	if (!vm->in_kdump) {

drivers/virtio/virtio_pci_common.c

···
 	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,
···
 	.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)

fs/proc/Kconfig

···
 	  as ELF notes to /proc/vmcore. You can still disable device
 	  dump using the kernel command line option 'novmcoredd'.
 
+config NEED_PROC_VMCORE_DEVICE_RAM
+	bool
+
+config PROC_VMCORE_DEVICE_RAM
+	def_bool y
+	depends on PROC_VMCORE && NEED_PROC_VMCORE_DEVICE_RAM
+	depends on VIRTIO_MEM
+	help
+	  If the elfcore hdr is allocated and prepared by the dump kernel
+	  ("2nd kernel") instead of the crashed kernel, RAM provided by memory
+	  devices such as virtio-mem will not be included in the dump
+	  image, because only the device driver can properly detect them.
+
+	  With this config enabled, these RAM ranges will be queried from the
+	  device drivers once the device gets probed, so they can be included
+	  in the crash dump.
+
+	  Relevant architectures should select NEED_PROC_VMCORE_DEVICE_RAM.
+
 config PROC_SYSCTL
 	bool "Sysctl support (/proc/sys)" if EXPERT
 	depends on PROC_FS

fs/proc/vmcore.c

···
  *
  */
 
+#define pr_fmt(fmt) "vmcore: " fmt
+
 #include <linux/mm.h>
 #include <linux/kcore.h>
 #include <linux/user.h>
···
 static struct proc_dir_entry *proc_vmcore;
 
 #ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+struct vmcoredd_node {
+	struct list_head list;	/* List of dumps */
+	void *buf;		/* Buffer containing device's dump */
+	unsigned int size;	/* Size of the buffer */
+};
+
 /* Device Dump list and mutex to synchronize access to list */
 static LIST_HEAD(vmcoredd_list);
-static DEFINE_MUTEX(vmcoredd_mutex);
 
 static bool vmcoredd_disabled;
 core_param(novmcoredd, vmcoredd_disabled, bool, 0);
···
 /* Device Dump Size */
 static size_t vmcoredd_orig_sz;
 
-static DEFINE_SPINLOCK(vmcore_cb_lock);
+static DEFINE_MUTEX(vmcore_mutex);
+
 DEFINE_STATIC_SRCU(vmcore_cb_srcu);
 /* List of registered vmcore callbacks. */
 static LIST_HEAD(vmcore_cb_list);
 /* Whether the vmcore has been opened once. */
 static bool vmcore_opened;
+/* Whether the vmcore is currently open. */
+static unsigned int vmcore_open;
+
+static void vmcore_process_device_ram(struct vmcore_cb *cb);
 
 void register_vmcore_cb(struct vmcore_cb *cb)
 {
 	INIT_LIST_HEAD(&cb->next);
-	spin_lock(&vmcore_cb_lock);
+	mutex_lock(&vmcore_mutex);
 	list_add_tail(&cb->next, &vmcore_cb_list);
 	/*
 	 * Registering a vmcore callback after the vmcore was opened is
···
 	 */
 	if (vmcore_opened)
 		pr_warn_once("Unexpected vmcore callback registration\n");
-	spin_unlock(&vmcore_cb_lock);
+	if (!vmcore_open && cb->get_device_ram)
+		vmcore_process_device_ram(cb);
+	mutex_unlock(&vmcore_mutex);
 }
 EXPORT_SYMBOL_GPL(register_vmcore_cb);
 
 void unregister_vmcore_cb(struct vmcore_cb *cb)
 {
-	spin_lock(&vmcore_cb_lock);
+	mutex_lock(&vmcore_mutex);
 	list_del_rcu(&cb->next);
 	/*
 	 * Unregistering a vmcore callback after the vmcore was opened is
···
 	 */
 	if (vmcore_opened)
 		pr_warn_once("Unexpected vmcore callback unregistration\n");
-	spin_unlock(&vmcore_cb_lock);
+	mutex_unlock(&vmcore_mutex);
 
 	synchronize_srcu(&vmcore_cb_srcu);
 }
···
 
 static int open_vmcore(struct inode *inode, struct file *file)
 {
-	spin_lock(&vmcore_cb_lock);
+	mutex_lock(&vmcore_mutex);
 	vmcore_opened = true;
-	spin_unlock(&vmcore_cb_lock);
+	if (vmcore_open + 1 == 0) {
+		mutex_unlock(&vmcore_mutex);
+		return -EBUSY;
+	}
+	vmcore_open++;
+	mutex_unlock(&vmcore_mutex);
+
+	return 0;
+}
+
+static int release_vmcore(struct inode *inode, struct file *file)
+{
+	mutex_lock(&vmcore_mutex);
+	vmcore_open--;
+	mutex_unlock(&vmcore_mutex);
 
 	return 0;
 }
···
 {
 	struct vmcoredd_node *dump;
 	u64 offset = 0;
-	int ret = 0;
 	size_t tsz;
 	char *buf;
 
-	mutex_lock(&vmcoredd_mutex);
 	list_for_each_entry(dump, &vmcoredd_list, list) {
 		if (start < offset + dump->size) {
 			tsz = min(offset + (u64)dump->size - start, (u64)size);
 			buf = dump->buf + start - offset;
-			if (copy_to_iter(buf, tsz, iter) < tsz) {
-				ret = -EFAULT;
-				goto out_unlock;
-			}
+			if (copy_to_iter(buf, tsz, iter) < tsz)
+				return -EFAULT;
 
 			size -= tsz;
 			start += tsz;
 
 			/* Leave now if buffer filled already */
 			if (!size)
-				goto out_unlock;
+				return 0;
 		}
 		offset += dump->size;
 	}
 
-out_unlock:
-	mutex_unlock(&vmcoredd_mutex);
-	return ret;
+	return 0;
 }
 
 #ifdef CONFIG_MMU
···
 {
 	struct vmcoredd_node *dump;
 	u64 offset = 0;
-	int ret = 0;
 	size_t tsz;
 	char *buf;
 
-	mutex_lock(&vmcoredd_mutex);
 	list_for_each_entry(dump, &vmcoredd_list, list) {
 		if (start < offset + dump->size) {
 			tsz = min(offset + (u64)dump->size - start, (u64)size);
 			buf = dump->buf + start - offset;
 			if (remap_vmalloc_range_partial(vma, dst, buf, 0,
-							tsz)) {
-				ret = -EFAULT;
-				goto out_unlock;
-			}
+							tsz))
+				return -EFAULT;
 
 			size -= tsz;
 			start += tsz;
···
 
 			/* Leave now if buffer filled already */
 			if (!size)
-				goto out_unlock;
+				return 0;
 		}
 		offset += dump->size;
 	}
 
-out_unlock:
-	mutex_unlock(&vmcoredd_mutex);
-	return ret;
+	return 0;
 }
 #endif /* CONFIG_MMU */
 #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
···
  */
 static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos)
 {
+	struct vmcore_range *m = NULL;
 	ssize_t acc = 0, tmp;
 	size_t tsz;
 	u64 start;
-	struct vmcore *m = NULL;
 
 	if (!iov_iter_count(iter) || *fpos >= vmcore_size)
 		return 0;
···
 {
 	size_t size = vma->vm_end - vma->vm_start;
 	u64 start, end, len, tsz;
-	struct vmcore *m;
+	struct vmcore_range *m;
 
 	start = (u64)vma->vm_pgoff << PAGE_SHIFT;
 	end = start + size;
···
 
 static const struct proc_ops vmcore_proc_ops = {
 	.proc_open	= open_vmcore,
+	.proc_release	= release_vmcore,
 	.proc_read_iter	= read_vmcore,
 	.proc_lseek	= default_llseek,
 	.proc_mmap	= mmap_vmcore,
 };
 
-static struct vmcore* __init get_new_element(void)
-{
-	return kzalloc(sizeof(struct vmcore), GFP_KERNEL);
-}
-
 static u64 get_vmcore_size(size_t elfsz, size_t elfnotesegsz,
 			   struct list_head *vc_list)
 {
+	struct vmcore_range *m;
 	u64 size;
-	struct vmcore *m;
 
 	size = elfsz + elfnotesegsz;
 	list_for_each_entry(m, vc_list, list) {
···
 	Elf64_Ehdr *ehdr_ptr;
 	Elf64_Phdr *phdr_ptr;
 	loff_t vmcore_off;
-	struct vmcore *new;
 
 	ehdr_ptr = (Elf64_Ehdr *)elfptr;
 	phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */
···
 		end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE);
 		size = end - start;
 
-		/* Add this contiguous chunk of memory to vmcore list.*/
-		new = get_new_element();
-		if (!new)
+		if (vmcore_alloc_add_range(vc_list, start, size))
 			return -ENOMEM;
-		new->paddr = start;
-		new->size = size;
-		list_add_tail(&new->list, vc_list);
 
 		/* Update the program header offset. */
 		phdr_ptr->p_offset = vmcore_off + (paddr - start);
···
 	Elf32_Ehdr *ehdr_ptr;
 	Elf32_Phdr *phdr_ptr;
 	loff_t vmcore_off;
-	struct vmcore *new;
 
 	ehdr_ptr = (Elf32_Ehdr *)elfptr;
 	phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); /* PT_NOTE hdr */
···
 		end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE);
 		size = end - start;
 
-		/* Add this contiguous chunk of memory to vmcore list.*/
-		new = get_new_element();
-		if (!new)
+		if (vmcore_alloc_add_range(vc_list, start, size))
 			return -ENOMEM;
-		new->paddr = start;
-		new->size = size;
-		list_add_tail(&new->list, vc_list);
 
 		/* Update the program header offset */
 		phdr_ptr->p_offset = vmcore_off + (paddr - start);
···
 static void set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz,
 				    struct list_head *vc_list)
 {
+	struct vmcore_range *m;
 	loff_t vmcore_off;
-	struct vmcore *m;
 
 	/* Skip ELF header, program headers and ELF note segment. */
 	vmcore_off = elfsz + elfnotes_sz;
···
 	dump->buf = buf;
 	dump->size = data_size;
 
-	/* Add the dump to driver sysfs list */
-	mutex_lock(&vmcoredd_mutex);
-	list_add_tail(&dump->list, &vmcoredd_list);
-	mutex_unlock(&vmcoredd_mutex);
+	/* Add the dump to driver sysfs list and update the elfcore hdr */
+	mutex_lock(&vmcore_mutex);
+	if (vmcore_opened)
+		pr_warn_once("Unexpected adding of device dump\n");
+	if (vmcore_open) {
+		ret = -EBUSY;
+		goto out_err;
+	}
 
+	list_add_tail(&dump->list, &vmcoredd_list);
 	vmcoredd_update_size(data_size);
+	mutex_unlock(&vmcore_mutex);
 	return 0;
 
 out_err:
···
 EXPORT_SYMBOL(vmcore_add_device_dump);
 #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
 
+#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM
+static int vmcore_realloc_elfcore_buffer_elf64(size_t new_size)
+{
+	char *elfcorebuf_new;
+
+	if (WARN_ON_ONCE(new_size < elfcorebuf_sz))
+		return -EINVAL;
+	if (get_order(elfcorebuf_sz_orig) == get_order(new_size)) {
+		elfcorebuf_sz_orig = new_size;
+		return 0;
+	}
+
+	elfcorebuf_new = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+						  get_order(new_size));
+	if (!elfcorebuf_new)
+		return -ENOMEM;
+	memcpy(elfcorebuf_new, elfcorebuf, elfcorebuf_sz);
+	free_pages((unsigned long)elfcorebuf, get_order(elfcorebuf_sz_orig));
+	elfcorebuf = elfcorebuf_new;
+	elfcorebuf_sz_orig = new_size;
+	return 0;
+}
+
+static void vmcore_reset_offsets_elf64(void)
+{
+	Elf64_Phdr *phdr_start = (Elf64_Phdr *)(elfcorebuf + sizeof(Elf64_Ehdr));
+	loff_t vmcore_off = elfcorebuf_sz + elfnotes_sz;
+	Elf64_Ehdr *ehdr = (Elf64_Ehdr *)elfcorebuf;
+	Elf64_Phdr *phdr;
+	int i;
+
+	for (i = 0, phdr = phdr_start; i < ehdr->e_phnum; i++, phdr++) {
+		u64 start, end;
+
+		/*
+		 * After merge_note_headers_elf64() we should only have a single
+		 * PT_NOTE entry that starts immediately after elfcorebuf_sz.
+		 */
+		if (phdr->p_type == PT_NOTE) {
+			phdr->p_offset = elfcorebuf_sz;
+			continue;
+		}
+
+		start = rounddown(phdr->p_offset, PAGE_SIZE);
+		end = roundup(phdr->p_offset + phdr->p_memsz, PAGE_SIZE);
+		phdr->p_offset = vmcore_off + (phdr->p_offset - start);
+		vmcore_off = vmcore_off + end - start;
+	}
+	set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list);
+}
+
+static int vmcore_add_device_ram_elf64(struct list_head *list, size_t count)
+{
+	Elf64_Phdr *phdr_start = (Elf64_Phdr *)(elfcorebuf + sizeof(Elf64_Ehdr));
+	Elf64_Ehdr *ehdr = (Elf64_Ehdr *)elfcorebuf;
+	struct vmcore_range *cur;
+	Elf64_Phdr *phdr;
+	size_t new_size;
+	int rc;
+
+	if ((Elf32_Half)(ehdr->e_phnum + count) != ehdr->e_phnum + count) {
+		pr_err("too many device ram ranges\n");
+		return -ENOSPC;
+	}
+
+	/* elfcorebuf_sz must always cover full pages. */
+	new_size = sizeof(Elf64_Ehdr) +
+		   (ehdr->e_phnum + count) * sizeof(Elf64_Phdr);
+	new_size = roundup(new_size, PAGE_SIZE);
+
+	/*
+	 * Make sure we have sufficient space to include the new PT_LOAD
+	 * entries.
+	 */
+	rc = vmcore_realloc_elfcore_buffer_elf64(new_size);
+	if (rc) {
+		pr_err("resizing elfcore failed\n");
+		return rc;
+	}
+
+	/* Modify our used elfcore buffer size to cover the new entries. */
+	elfcorebuf_sz = new_size;
+
+	/* Fill the added PT_LOAD entries. */
+	phdr = phdr_start + ehdr->e_phnum;
+	list_for_each_entry(cur, list, list) {
+		WARN_ON_ONCE(!IS_ALIGNED(cur->paddr | cur->size, PAGE_SIZE));
+		elfcorehdr_fill_device_ram_ptload_elf64(phdr, cur->paddr, cur->size);
+
+		/* p_offset will be adjusted later. */
+		phdr++;
+		ehdr->e_phnum++;
+	}
+	list_splice_tail(list, &vmcore_list);
+
+	/* We changed elfcorebuf_sz and added new entries; reset all offsets. */
+	vmcore_reset_offsets_elf64();
+
+	/* Finally, recalculate the total vmcore size. */
+	vmcore_size = get_vmcore_size(elfcorebuf_sz, elfnotes_sz,
+				      &vmcore_list);
+	proc_vmcore->size = vmcore_size;
+	return 0;
+}
+
+static void vmcore_process_device_ram(struct vmcore_cb *cb)
+{
+	unsigned char *e_ident = (unsigned char *)elfcorebuf;
+	struct vmcore_range *first, *m;
+	LIST_HEAD(list);
+	int count;
+
+	/* We only support Elf64 dumps for now. */
+	if (WARN_ON_ONCE(e_ident[EI_CLASS] != ELFCLASS64)) {
+		pr_err("device ram ranges only support Elf64\n");
+		return;
+	}
+
+	if (cb->get_device_ram(cb, &list)) {
+		pr_err("obtaining device ram ranges failed\n");
+		return;
+	}
+	count = list_count_nodes(&list);
+	if (!count)
+		return;
+
+	/*
+	 * For some reason these ranges are already know? Might happen
+	 * with unusual register->unregister->register sequences; we'll simply
+	 * sanity check using the first range.
+	 */
+	first = list_first_entry(&list, struct vmcore_range, list);
+	list_for_each_entry(m, &vmcore_list, list) {
+		unsigned long long m_end = m->paddr + m->size;
+		unsigned long long first_end = first->paddr + first->size;
+
+		if (first->paddr < m_end && m->paddr < first_end)
+			goto out_free;
+	}
+
+	/* If adding the mem nodes succeeds, they must not be freed. */
+	if (!vmcore_add_device_ram_elf64(&list, count))
+		return;
+out_free:
+	vmcore_free_ranges(&list);
+}
+#else /* !CONFIG_PROC_VMCORE_DEVICE_RAM */
+static void vmcore_process_device_ram(struct vmcore_cb *cb)
+{
+}
+#endif /* CONFIG_PROC_VMCORE_DEVICE_RAM */
+
 /* Free all dumps in vmcore device dump list */
 static void vmcore_free_device_dumps(void)
 {
 #ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
-	mutex_lock(&vmcoredd_mutex);
+	mutex_lock(&vmcore_mutex);
 	while (!list_empty(&vmcoredd_list)) {
 		struct vmcoredd_node *dump;
 
···
 		vfree(dump->buf);
 		vfree(dump);
 	}
-	mutex_unlock(&vmcoredd_mutex);
+	mutex_unlock(&vmcore_mutex);
 #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
 }
 
···
 	rc = parse_crash_elf_headers();
 	if (rc) {
 		elfcorehdr_free(elfcorehdr_addr);
-		pr_warn("Kdump: vmcore not initialized\n");
+		pr_warn("not initialized\n");
 		return rc;
 	}
 	elfcorehdr_free(elfcorehdr_addr);
···
 		proc_vmcore = NULL;
 	}
 
-	/* clear the vmcore list. */
-	while (!list_empty(&vmcore_list)) {
-		struct vmcore *m;
-
-		m = list_first_entry(&vmcore_list, struct vmcore, list);
-		list_del(&m->list);
-		kfree(m);
-	}
+	vmcore_free_ranges(&vmcore_list);
 	free_elfcorebuf();
 
 	/* clear vmcore device dump list */

include/linux/crash_dump.h

···
 extern void elfcorehdr_free(unsigned long long addr);
 extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos);
 extern ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos);
+void elfcorehdr_fill_device_ram_ptload_elf64(Elf64_Phdr *phdr,
+		unsigned long long paddr, unsigned long long size);
 extern int remap_oldmem_pfn_range(struct vm_area_struct *vma,
 				  unsigned long from, unsigned long pfn,
 				  unsigned long size, pgprot_t prot);
···
  *              indicated in the vmcore instead. For example, a ballooned page
  *              contains no data and reading from such a page will cause high
  *              load in the hypervisor.
+ * @get_device_ram: query RAM ranges that can only be detected by device
+ *   drivers, such as the virtio-mem driver, so they can be included in
+ *   the crash dump on architectures that allocate the elfcore hdr in the dump
+ *   ("2nd") kernel. Indicated RAM ranges may contain holes to reduce the
+ *   total number of ranges; such holes can be detected using the pfn_is_ram
+ *   callback just like for other RAM.
  * @next: List head to manage registered callbacks internally; initialized by
  *        register_vmcore_cb().
  *
···
  */
 struct vmcore_cb {
 	bool (*pfn_is_ram)(struct vmcore_cb *cb, unsigned long pfn);
+	int (*get_device_ram)(struct vmcore_cb *cb, struct list_head *list);
 	struct list_head next;
 };
 extern void register_vmcore_cb(struct vmcore_cb *cb);
 extern void unregister_vmcore_cb(struct vmcore_cb *cb);
+
+struct vmcore_range {
+	struct list_head list;
+	unsigned long long paddr;
+	unsigned long long size;
+	loff_t offset;
+};
+
+/* Allocate a vmcore range and add it to the list. */
+static inline int vmcore_alloc_add_range(struct list_head *list,
+		unsigned long long paddr, unsigned long long size)
+{
+	struct vmcore_range *m = kzalloc(sizeof(*m), GFP_KERNEL);
+
+	if (!m)
+		return -ENOMEM;
+	m->paddr = paddr;
+	m->size = size;
+	list_add_tail(&m->list, list);
+	return 0;
+}
+
+/* Free a list of vmcore ranges. */
+static inline void vmcore_free_ranges(struct list_head *list)
+{
+	struct vmcore_range *m, *tmp;
+
+	list_for_each_entry_safe(m, tmp, list, list) {
+		list_del(&m->list);
+		kfree(m);
+	}
+}
 
 #else /* !CONFIG_CRASH_DUMP */
 static inline bool is_kdump_kernel(void) { return false; }

include/linux/kcore.h

···
 	int type;
 };
 
-struct vmcore {
-	struct list_head list;
-	unsigned long long paddr;
-	unsigned long long size;
-	loff_t offset;
-};
-
-struct vmcoredd_node {
-	struct list_head list;	/* List of dumps */
-	void *buf;		/* Buffer containing device's dump */
-	unsigned int size;	/* Size of the buffer */
-};
-
 #ifdef CONFIG_PROC_KCORE
 void __init kclist_add(struct kcore_list *, void *, size_t, int type);
 

include/linux/virtio.h

···
 int virtio_device_restore(struct virtio_device *dev);
 #endif
 void virtio_reset_device(struct virtio_device *dev);
+int virtio_device_reset_prepare(struct virtio_device *dev);
+int virtio_device_reset_done(struct virtio_device *dev);
 
 size_t virtio_max_dma_size(const struct virtio_device *vdev);
 
···
  *    changes; may be called in interrupt context.
  * @freeze: optional function to call during suspend/hibernation.
  * @restore: optional function to call on resume.
+ * @reset_prepare: optional function to call when a transport specific reset
+ *    occurs.
+ * @reset_done: optional function to call after transport specific reset
+ *    operation has finished.
  */
 struct virtio_driver {
 	struct device_driver driver;
···
 	void (*config_changed)(struct virtio_device *dev);
 	int (*freeze)(struct virtio_device *dev);
 	int (*restore)(struct virtio_device *dev);
+	int (*reset_prepare)(struct virtio_device *dev);
+	int (*reset_done)(struct virtio_device *dev);
 };
 
 #define drv_to_virtio(__drv)	container_of_const(__drv, struct virtio_driver, driver)

include/uapi/linux/vduse.h

···
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
 #ifndef _UAPI_VDUSE_H_
 #define _UAPI_VDUSE_H_
 

include/uapi/linux/virtio_pci.h

···
 #define VIRTIO_PCI_CAP_PCI_CFG		5
 /* Additional shared memory capability */
 #define VIRTIO_PCI_CAP_SHARED_MEMORY_CFG 8
+/* PCI vendor data configuration */
+#define VIRTIO_PCI_CAP_VENDOR_CFG	9
 
 /* This is the PCI capability header: */
 struct virtio_pci_cap {
···
 	__u8 padding[2];	/* Pad to full dword. */
 	__le32 offset;		/* Offset within bar. */
 	__le32 length;		/* Length of the structure, in bytes. */
+};
+
+/* This is the PCI vendor data capability header: */
+struct virtio_pci_vndr_data {
+	__u8 cap_vndr;		/* Generic PCI field: PCI_CAP_ID_VNDR */
+	__u8 cap_next;		/* Generic PCI field: next ptr. */
+	__u8 cap_len;		/* Generic PCI field: capability length */
+	__u8 cfg_type;		/* Identifies the structure. */
+	__u16 vendor_id;	/* Identifies the vendor-specific format. */
+	/* For Vendor Definition */
+	/* Pads structure to a multiple of 4 bytes */
+	/* Reads must not have side effects */
 };
 
 struct virtio_pci_cap64 {