From 93de2a6a4b91b72607136dd656edf03fb399d27f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 23 Sep 2026 09:37:21 -0700 Subject: KVM: SEV: Do cache maintenance on the source VM during intra-host migration Manually perform cache maintenance on the source VM during intra-host migration to ensure no stale data is left in CPU caches after the VM is destroyed. Because the source VM is "converted" to a non-SEV VM, KVM's memory reclaim flows won't trigger cache maintenance, e.g. when all guest memory is reclaimed in response to detaching from the mmu_notifier. Note, relying on the destination VM to do cache maintenance isn't an option as KVM doesn't require identical guest memory configurations, i.e. the source VM may have access to memory that the destination VM does not. Enforcing equivalent memory configurations is infeasible, as it would require a *deep* comparison of memslots, e.g. to verify that not only are the memslot identical, but what the memslots point at is also identical. Fixes: b56639318bb2 ("KVM: SEV: Add support for SEV intra host migration") Cc: stable@vger.kernel.org Reported-by: Stefan Teodorescu Signed-off-by: Sean Christopherson Message-ID: <20260923163721.1584779-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- drivers/misc/open-dice.c | 232 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 232 insertions(+) create mode 100644 drivers/misc/open-dice.c (limited to 'drivers/misc/open-dice.c') diff --git a/drivers/misc/open-dice.c b/drivers/misc/open-dice.c new file mode 100644 index 000000000..b3cf59954 --- /dev/null +++ b/drivers/misc/open-dice.c @@ -0,0 +1,232 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 - Google LLC + * Author: David Brazdil + * Author: Song Guo + * + * Driver for Open Profile for DICE. + * + * This driver takes ownership of a reserved memory region containing data + * generated by the Open Profile for DICE measured boot protocol. The memory + * contents are not interpreted by the kernel but can be mapped into a userspace + * process via a misc device. Userspace can also request a wipe of the memory. + * + * Userspace can access the data with (w/o error handling): + * + * fd = open("/dev/open-dice0", O_RDWR); + * read(fd, &size, sizeof(unsigned long)); + * data = mmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); + * write(fd, NULL, 0); // wipe + * close(fd); + */ + +#include +#include +#include +#include +#include +#include +#include + +#define DRIVER_NAME "open-dice" + +struct open_dice_drvdata { + struct mutex lock; + char name[16]; + phys_addr_t mem_base; + resource_size_t mem_size; + struct miscdevice misc; +}; + +static inline struct open_dice_drvdata *to_open_dice_drvdata(struct file *filp) +{ + return container_of(filp->private_data, struct open_dice_drvdata, misc); +} + +static int open_dice_wipe(struct open_dice_drvdata *drvdata) +{ + void *kaddr; + + mutex_lock(&drvdata->lock); + kaddr = devm_memremap(drvdata->misc.this_device, drvdata->mem_base, + drvdata->mem_size, MEMREMAP_WC); + if (IS_ERR(kaddr)) { + mutex_unlock(&drvdata->lock); + return PTR_ERR(kaddr); + } + + memset(kaddr, 0, drvdata->mem_size); + devm_memunmap(drvdata->misc.this_device, kaddr); + mutex_unlock(&drvdata->lock); + return 0; +} + +/* + * Copies the size of the reserved memory region to the user-provided buffer. + */ +static ssize_t open_dice_read(struct file *filp, char __user *ptr, size_t len, + loff_t *off) +{ + unsigned long val = to_open_dice_drvdata(filp)->mem_size; + + return simple_read_from_buffer(ptr, len, off, &val, sizeof(val)); +} + +/* + * Triggers a wipe of the reserved memory region. The user-provided pointer + * is never dereferenced. + */ +static ssize_t open_dice_write(struct file *filp, const char __user *ptr, + size_t len, loff_t *off) +{ + if (open_dice_wipe(to_open_dice_drvdata(filp))) + return -EIO; + + /* Consume the input buffer. */ + return len; +} + +/* + * Creates a mapping of the reserved memory region in user address space. + */ +static int open_dice_mmap_prepare(struct vm_area_desc *desc) +{ + struct file *filp = desc->file; + struct open_dice_drvdata *drvdata = to_open_dice_drvdata(filp); + + if (vma_desc_test(desc, VMA_MAYSHARE_BIT)) { + /* Do not allow userspace to modify the underlying data. */ + if (vma_desc_test(desc, VMA_WRITE_BIT)) + return -EPERM; + /* Ensure userspace cannot acquire VM_WRITE later. */ + vma_desc_clear_flags(desc, VMA_MAYWRITE_BIT); + } + + /* Create write-combine mapping so all clients observe a wipe. */ + desc->page_prot = pgprot_writecombine(desc->page_prot); + vma_desc_set_flags(desc, VMA_DONTCOPY_BIT, VMA_DONTDUMP_BIT); + mmap_action_simple_ioremap(desc, drvdata->mem_base, + drvdata->mem_size); + return 0; +} + +static const struct file_operations open_dice_fops = { + .owner = THIS_MODULE, + .read = open_dice_read, + .write = open_dice_write, + .mmap_prepare = open_dice_mmap_prepare, +}; + +static int __init open_dice_probe(struct platform_device *pdev) +{ + static unsigned int dev_idx; + struct device *dev = &pdev->dev; + struct open_dice_drvdata *drvdata; + phys_addr_t mem_base; + resource_size_t mem_size; + int ret; + + if (dev->of_node) { + struct reserved_mem *rmem = of_reserved_mem_lookup(dev->of_node); + + if (!rmem) { + dev_err(dev, "failed to lookup reserved memory\n"); + return -EINVAL; + } + mem_base = rmem->base; + mem_size = rmem->size; + } else if (is_acpi_node(dev->fwnode)) { + struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + + if (!res) { + dev_err(dev, "failed to get MMIO resource\n"); + return -EINVAL; + } + mem_base = res->start; + mem_size = resource_size(res); + } else { + dev_err(dev, "device not supported (no DT or ACPI node)\n"); + return -EINVAL; + } + + if (!mem_size || (mem_size > ULONG_MAX)) { + dev_err(dev, "invalid memory region size\n"); + return -EINVAL; + } + + if (!PAGE_ALIGNED(mem_base) || !PAGE_ALIGNED(mem_size)) { + dev_err(dev, "memory region must be page-aligned\n"); + return -EINVAL; + } + + drvdata = devm_kmalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + *drvdata = (struct open_dice_drvdata){ + .mem_base = mem_base, + .mem_size = mem_size, + .misc = (struct miscdevice){ + .parent = dev, + .name = drvdata->name, + .minor = MISC_DYNAMIC_MINOR, + .fops = &open_dice_fops, + .mode = 0600, + }, + }; + mutex_init(&drvdata->lock); + + /* Index overflow check not needed, misc_register() will fail. */ + snprintf(drvdata->name, sizeof(drvdata->name), DRIVER_NAME"%u", dev_idx++); + + ret = misc_register(&drvdata->misc); + if (ret) { + dev_err(dev, "failed to register misc device '%s': %d\n", + drvdata->name, ret); + return ret; + } + + platform_set_drvdata(pdev, drvdata); + return 0; +} + +static void open_dice_remove(struct platform_device *pdev) +{ + struct open_dice_drvdata *drvdata = platform_get_drvdata(pdev); + + misc_deregister(&drvdata->misc); +} + +static const struct of_device_id open_dice_of_match[] = { + { .compatible = "google,open-dice" }, + { } +}; + +static struct platform_driver open_dice_driver = { + .remove = open_dice_remove, + .driver = { + .name = DRIVER_NAME, + .of_match_table = open_dice_of_match, + }, +}; + +static int __init open_dice_init(void) +{ + int ret = platform_driver_probe(&open_dice_driver, open_dice_probe); + + /* DICE regions are optional. Succeed even with zero instances. */ + return (ret == -ENODEV) ? 0 : ret; +} + +static void __exit open_dice_exit(void) +{ + platform_driver_unregister(&open_dice_driver); +} + +module_init(open_dice_init); +module_exit(open_dice_exit); + +MODULE_DESCRIPTION("Driver for Open Profile for DICE."); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("David Brazdil "); +MODULE_AUTHOR("Song Guo "); -- cgit v1.3.1