KVM: SEV: Do cache maintenance on the source VM during intra-host migrationgrafted

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 <fane@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20260923163721.1584779-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 306 insertions, 0 deletions

diff --git a/drivers/mtd/devices/ms02-nv.c b/drivers/mtd/devices/ms02-nv.c
new file mode 100644
index 000000000..453b3e05f
--- /dev/null
+++ b/drivers/mtd/devices/ms02-nv.c
@@ -0,0 +1,306 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *	Copyright (c) 2001 Maciej W. Rozycki
+ */
+
+#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mtd/mtd.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <asm/addrspace.h>
+#include <asm/bootinfo.h>
+#include <asm/dec/ioasic_addrs.h>
+#include <asm/dec/kn02.h>
+#include <asm/dec/kn03.h>
+#include <asm/io.h>
+#include <asm/paccess.h>
+
+#include "ms02-nv.h"
+
+
+static char version[] __initdata =
+	"ms02-nv.c: v.1.0.0  13 Aug 2001  Maciej W. Rozycki.\n";
+
+MODULE_AUTHOR("Maciej W. Rozycki <macro@linux-mips.org>");
+MODULE_DESCRIPTION("DEC MS02-NV NVRAM module driver");
+MODULE_LICENSE("GPL");
+
+
+/*
+ * Addresses we probe for an MS02-NV at.  Modules may be located
+ * at any 8MiB boundary within a 0MiB up to 112MiB range or at any 32MiB
+ * boundary within a 0MiB up to 448MiB range.  We don't support a module
+ * at 0MiB, though.
+ */
+static ulong ms02nv_addrs[] __initdata = {
+	0x07000000, 0x06800000, 0x06000000, 0x05800000, 0x05000000,
+	0x04800000, 0x04000000, 0x03800000, 0x03000000, 0x02800000,
+	0x02000000, 0x01800000, 0x01000000, 0x00800000
+};
+
+static const char ms02nv_name[] = "DEC MS02-NV NVRAM";
+static const char ms02nv_res_diag_ram[] = "Diagnostic RAM";
+static const char ms02nv_res_user_ram[] = "General-purpose RAM";
+static const char ms02nv_res_csr[] = "Control and status register";
+
+static struct mtd_info *root_ms02nv_mtd;
+
+
+static int ms02nv_read(struct mtd_info *mtd, loff_t from,
+			size_t len, size_t *retlen, u_char *buf)
+{
+	struct ms02nv_private *mp = mtd->priv;
+
+	memcpy(buf, mp->uaddr + from, len);
+	*retlen = len;
+	return 0;
+}
+
+static int ms02nv_write(struct mtd_info *mtd, loff_t to,
+			size_t len, size_t *retlen, const u_char *buf)
+{
+	struct ms02nv_private *mp = mtd->priv;
+
+	memcpy(mp->uaddr + to, buf, len);
+	*retlen = len;
+	return 0;
+}
+
+
+static inline uint ms02nv_probe_one(ulong addr)
+{
+	ms02nv_uint *ms02nv_diagp;
+	ms02nv_uint *ms02nv_magicp;
+	uint ms02nv_diag;
+	uint ms02nv_magic;
+	size_t size;
+
+	int err;
+
+	/*
+	 * The firmware writes MS02NV_ID at MS02NV_MAGIC and also
+	 * a diagnostic status at MS02NV_DIAG.
+	 */
+	ms02nv_diagp = (ms02nv_uint *)(CKSEG1ADDR(addr + MS02NV_DIAG));
+	ms02nv_magicp = (ms02nv_uint *)(CKSEG1ADDR(addr + MS02NV_MAGIC));
+	err = get_dbe(ms02nv_magic, ms02nv_magicp);
+	if (err)
+		return 0;
+	if (ms02nv_magic != MS02NV_ID)
+		return 0;
+
+	ms02nv_diag = *ms02nv_diagp;
+	size = (ms02nv_diag & MS02NV_DIAG_SIZE_MASK) << MS02NV_DIAG_SIZE_SHIFT;
+	if (size > MS02NV_CSR)
+		size = MS02NV_CSR;
+
+	return size;
+}
+
+static int __init ms02nv_init_one(ulong addr)
+{
+	struct mtd_info *mtd;
+	struct ms02nv_private *mp;
+	struct resource *mod_res;
+	struct resource *diag_res;
+	struct resource *user_res;
+	struct resource *csr_res;
+	ulong fixaddr;
+	size_t size, fixsize;
+
+	static int version_printed;
+
+	int ret = -ENODEV;
+
+	/* The module decodes 8MiB of address space. */
+	mod_res = kzalloc_obj(*mod_res);
+	if (!mod_res)
+		return -ENOMEM;
+
+	mod_res->name = ms02nv_name;
+	mod_res->start = addr;
+	mod_res->end = addr + MS02NV_SLOT_SIZE - 1;
+	mod_res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	if (request_resource(&iomem_resource, mod_res) < 0)
+		goto err_out_mod_res;
+
+	size = ms02nv_probe_one(addr);
+	if (!size)
+		goto err_out_mod_res_rel;
+
+	if (!version_printed) {
+		printk(KERN_INFO "%s", version);
+		version_printed = 1;
+	}
+
+	ret = -ENOMEM;
+	mtd = kzalloc_obj(*mtd);
+	if (!mtd)
+		goto err_out_mod_res_rel;
+	mp = kzalloc_obj(*mp);
+	if (!mp)
+		goto err_out_mtd;
+
+	mtd->priv = mp;
+	mp->resource.module = mod_res;
+
+	/* Firmware's diagnostic NVRAM area. */
+	diag_res = kzalloc_obj(*diag_res);
+	if (!diag_res)
+		goto err_out_mp;
+
+	diag_res->name = ms02nv_res_diag_ram;
+	diag_res->start = addr;
+	diag_res->end = addr + MS02NV_RAM - 1;
+	diag_res->flags = IORESOURCE_BUSY;
+	request_resource(mod_res, diag_res);
+
+	mp->resource.diag_ram = diag_res;
+
+	/* User-available general-purpose NVRAM area. */
+	user_res = kzalloc_obj(*user_res);
+	if (!user_res)
+		goto err_out_diag_res;
+
+	user_res->name = ms02nv_res_user_ram;
+	user_res->start = addr + MS02NV_RAM;
+	user_res->end = addr + size - 1;
+	user_res->flags = IORESOURCE_BUSY;
+	request_resource(mod_res, user_res);
+
+	mp->resource.user_ram = user_res;
+
+	/* Control and status register. */
+	csr_res = kzalloc_obj(*csr_res);
+	if (!csr_res)
+		goto err_out_user_res;
+
+	csr_res->name = ms02nv_res_csr;
+	csr_res->start = addr + MS02NV_CSR;
+	csr_res->end = addr + MS02NV_CSR + 3;
+	csr_res->flags = IORESOURCE_BUSY;
+	request_resource(mod_res, csr_res);
+
+	mp->resource.csr = csr_res;
+
+	mp->addr = phys_to_virt(addr);
+	mp->size = size;
+
+	/*
+	 * Hide the firmware's diagnostic area.  It may get destroyed
+	 * upon a reboot.  Take paging into account for mapping support.
+	 */
+	fixaddr = (addr + MS02NV_RAM + PAGE_SIZE - 1) & ~(PAGE_SIZE - 1);
+	fixsize = (size - (fixaddr - addr)) & ~(PAGE_SIZE - 1);
+	mp->uaddr = phys_to_virt(fixaddr);
+
+	mtd->type = MTD_RAM;
+	mtd->flags = MTD_CAP_RAM;
+	mtd->size = fixsize;
+	mtd->name = ms02nv_name;
+	mtd->owner = THIS_MODULE;
+	mtd->_read = ms02nv_read;
+	mtd->_write = ms02nv_write;
+	mtd->writesize = 1;
+
+	ret = -EIO;
+	if (mtd_device_register(mtd, NULL, 0)) {
+		printk(KERN_ERR
+			"ms02-nv: Unable to register MTD device, aborting!\n");
+		goto err_out_csr_res;
+	}
+
+	printk(KERN_INFO "mtd%d: %s at 0x%08lx, size %zuMiB.\n",
+		mtd->index, ms02nv_name, addr, size >> 20);
+
+	mp->next = root_ms02nv_mtd;
+	root_ms02nv_mtd = mtd;
+
+	return 0;
+
+
+err_out_csr_res:
+	release_resource(csr_res);
+	kfree(csr_res);
+err_out_user_res:
+	release_resource(user_res);
+	kfree(user_res);
+err_out_diag_res:
+	release_resource(diag_res);
+	kfree(diag_res);
+err_out_mp:
+	kfree(mp);
+err_out_mtd:
+	kfree(mtd);
+err_out_mod_res_rel:
+	release_resource(mod_res);
+err_out_mod_res:
+	kfree(mod_res);
+	return ret;
+}
+
+static void __exit ms02nv_remove_one(void)
+{
+	struct mtd_info *mtd = root_ms02nv_mtd;
+	struct ms02nv_private *mp = mtd->priv;
+
+	root_ms02nv_mtd = mp->next;
+
+	mtd_device_unregister(mtd);
+
+	release_resource(mp->resource.csr);
+	kfree(mp->resource.csr);
+	release_resource(mp->resource.user_ram);
+	kfree(mp->resource.user_ram);
+	release_resource(mp->resource.diag_ram);
+	kfree(mp->resource.diag_ram);
+	release_resource(mp->resource.module);
+	kfree(mp->resource.module);
+	kfree(mp);
+	kfree(mtd);
+}
+
+
+static int __init ms02nv_init(void)
+{
+	volatile u32 *csr;
+	uint stride = 0;
+	int count = 0;
+	int i;
+
+	switch (mips_machtype) {
+	case MACH_DS5000_200:
+		csr = (volatile u32 *)CKSEG1ADDR(KN02_SLOT_BASE + KN02_CSR);
+		if (*csr & KN02_CSR_BNK32M)
+			stride = 2;
+		break;
+	case MACH_DS5000_2X0:
+	case MACH_DS5900:
+		csr = (volatile u32 *)CKSEG1ADDR(KN03_SLOT_BASE + IOASIC_MCR);
+		if (*csr & KN03_MCR_BNK32M)
+			stride = 2;
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(ms02nv_addrs); i++)
+		if (!ms02nv_init_one(ms02nv_addrs[i] << stride))
+			count++;
+
+	return (count > 0) ? 0 : -ENODEV;
+}
+
+static void __exit ms02nv_cleanup(void)
+{
+	while (root_ms02nv_mtd)
+		ms02nv_remove_one();
+}
+
+
+module_init(ms02nv_init);
+module_exit(ms02nv_cleanup);