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>

5 files changed, 326 insertions, 0 deletions

diff --git a/include/uapi/fwctl/bnxt.h b/include/uapi/fwctl/bnxt.h
new file mode 100644
index 000000000..398c1ad0c
--- /dev/null
+++ b/include/uapi/fwctl/bnxt.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2026, Broadcom Inc
+ */
+
+#ifndef _UAPI_FWCTL_BNXT_H_
+#define _UAPI_FWCTL_BNXT_H_
+
+#include <linux/types.h>
+
+enum fwctl_bnxt_commands {
+	FWCTL_BNXT_INLINE_COMMANDS = 0,
+	FWCTL_BNXT_QUERY_COMMANDS,
+	FWCTL_BNXT_SEND_COMMANDS,
+	FWCTL_BNXT_DMA_COMMANDS,
+};
+
+/**
+ * struct fwctl_info_bnxt - ioctl(FWCTL_INFO) out_device_data
+ * @uctx_caps: The command capabilities driver accepts.
+ *
+ * Return basic information about the FW interface available.
+ */
+struct fwctl_info_bnxt {
+	__u32 uctx_caps;
+};
+
+#define FWCTL_BNXT_MAX_DMABUF	0x10000   /* 64 KiB */
+
+#endif
diff --git a/include/uapi/fwctl/cxl.h b/include/uapi/fwctl/cxl.h
new file mode 100644
index 000000000..43f522f0c
--- /dev/null
+++ b/include/uapi/fwctl/cxl.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2024-2025 Intel Corporation
+ *
+ * These are definitions for the mailbox command interface of CXL subsystem.
+ */
+#ifndef _UAPI_FWCTL_CXL_H_
+#define _UAPI_FWCTL_CXL_H_
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <cxl/features.h>
+
+/**
+ * struct fwctl_rpc_cxl - ioctl(FWCTL_RPC) input for CXL
+ * @opcode: CXL mailbox command opcode
+ * @flags: Flags for the command (input).
+ * @op_size: Size of input payload.
+ * @reserved1: Reserved. Must be 0s.
+ * @get_sup_feats_in: Get Supported Features input
+ * @get_feat_in: Get Feature input
+ * @set_feat_in: Set Feature input
+ */
+struct fwctl_rpc_cxl {
+	__struct_group(fwctl_rpc_cxl_hdr, hdr, /* no attrs */,
+		__u32 opcode;
+		__u32 flags;
+		__u32 op_size;
+		__u32 reserved1;
+	);
+	union {
+		struct cxl_mbox_get_sup_feats_in get_sup_feats_in;
+		struct cxl_mbox_get_feat_in get_feat_in;
+		struct cxl_mbox_set_feat_in set_feat_in;
+	};
+};
+
+/**
+ * struct fwctl_rpc_cxl_out - ioctl(FWCTL_RPC) output for CXL
+ * @size: Size of the output payload
+ * @retval: Return value from device
+ * @get_sup_feats_out: Get Supported Features output
+ * @payload: raw byte stream of payload
+ */
+struct fwctl_rpc_cxl_out {
+	__struct_group(fwctl_rpc_cxl_out_hdr, hdr, /* no attrs */,
+		__u32 size;
+		__u32 retval;
+	);
+	union {
+		struct cxl_mbox_get_sup_feats_out get_sup_feats_out;
+		__DECLARE_FLEX_ARRAY(__u8, payload);
+	};
+};
+
+#endif
diff --git a/include/uapi/fwctl/fwctl.h b/include/uapi/fwctl/fwctl.h
new file mode 100644
index 000000000..2d6d4049c
--- /dev/null
+++ b/include/uapi/fwctl/fwctl.h
@@ -0,0 +1,142 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES.
+ */
+#ifndef _UAPI_FWCTL_H
+#define _UAPI_FWCTL_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define FWCTL_TYPE 0x9A
+
+/**
+ * DOC: General ioctl format
+ *
+ * The ioctl interface follows a general format to allow for extensibility. Each
+ * ioctl is passed a structure pointer as the argument providing the size of
+ * the structure in the first u32. The kernel checks that any structure space
+ * beyond what it understands is 0. This allows userspace to use the backward
+ * compatible portion while consistently using the newer, larger, structures.
+ *
+ * ioctls use a standard meaning for common errnos:
+ *
+ *  - ENOTTY: The IOCTL number itself is not supported at all
+ *  - E2BIG: The IOCTL number is supported, but the provided structure has
+ *    non-zero in a part the kernel does not understand.
+ *  - EOPNOTSUPP: The IOCTL number is supported, and the structure is
+ *    understood, however a known field has a value the kernel does not
+ *    understand or support.
+ *  - EINVAL: Everything about the IOCTL was understood, but a field is not
+ *    correct.
+ *  - ENOMEM: Out of memory.
+ *  - ENODEV: The underlying device has been hot-unplugged and the FD is
+ *            orphaned.
+ *
+ * As well as additional errnos, within specific ioctls.
+ */
+enum {
+	FWCTL_CMD_BASE = 0,
+	FWCTL_CMD_INFO = 0,
+	FWCTL_CMD_RPC = 1,
+};
+
+enum fwctl_device_type {
+	FWCTL_DEVICE_TYPE_ERROR = 0,
+	FWCTL_DEVICE_TYPE_MLX5 = 1,
+	FWCTL_DEVICE_TYPE_CXL = 2,
+	FWCTL_DEVICE_TYPE_BNXT = 3,
+	FWCTL_DEVICE_TYPE_PDS = 4,
+};
+
+/**
+ * struct fwctl_info - ioctl(FWCTL_INFO)
+ * @size: sizeof(struct fwctl_info)
+ * @flags: Must be 0
+ * @out_device_type: Returns the type of the device from enum fwctl_device_type
+ * @device_data_len: On input the length of the out_device_data memory. On
+ *	output the size of the kernel's device_data which may be larger or
+ *	smaller than the input. Maybe 0 on input.
+ * @out_device_data: Pointer to a memory of device_data_len bytes. Kernel will
+ *	fill the entire memory, zeroing as required.
+ *
+ * Returns basic information about this fwctl instance, particularly what driver
+ * is being used to define the device_data format.
+ */
+struct fwctl_info {
+	__u32 size;
+	__u32 flags;
+	__u32 out_device_type;
+	__u32 device_data_len;
+	__aligned_u64 out_device_data;
+};
+#define FWCTL_INFO _IO(FWCTL_TYPE, FWCTL_CMD_INFO)
+
+/**
+ * enum fwctl_rpc_scope - Scope of access for the RPC
+ *
+ * Refer to fwctl.rst for a more detailed discussion of these scopes.
+ */
+enum fwctl_rpc_scope {
+	/**
+	 * @FWCTL_RPC_CONFIGURATION: Device configuration access scope
+	 *
+	 * Read/write access to device configuration. When configuration
+	 * is written to the device it remains in a fully supported state.
+	 */
+	FWCTL_RPC_CONFIGURATION = 0,
+	/**
+	 * @FWCTL_RPC_DEBUG_READ_ONLY: Read only access to debug information
+	 *
+	 * Readable debug information. Debug information is compatible with
+	 * kernel lockdown, and does not disclose any sensitive information. For
+	 * instance exposing any encryption secrets from this information is
+	 * forbidden.
+	 */
+	FWCTL_RPC_DEBUG_READ_ONLY = 1,
+	/**
+	 * @FWCTL_RPC_DEBUG_WRITE: Writable access to lockdown compatible debug information
+	 *
+	 * Allows write access to data in the device which may leave a fully
+	 * supported state. This is intended to permit intensive and possibly
+	 * invasive debugging. This scope will taint the kernel.
+	 */
+	FWCTL_RPC_DEBUG_WRITE = 2,
+	/**
+	 * @FWCTL_RPC_DEBUG_WRITE_FULL: Write access to all debug information
+	 *
+	 * Allows read/write access to everything. Requires CAP_SYS_RAW_IO, so
+	 * it is not required to follow lockdown principals. If in doubt
+	 * debugging should be placed in this scope. This scope will taint the
+	 * kernel.
+	 */
+	FWCTL_RPC_DEBUG_WRITE_FULL = 3,
+};
+
+/**
+ * struct fwctl_rpc - ioctl(FWCTL_RPC)
+ * @size: sizeof(struct fwctl_rpc)
+ * @scope: One of enum fwctl_rpc_scope, required scope for the RPC
+ * @in_len: Length of the in memory
+ * @out_len: Length of the out memory
+ * @in: Request message in device specific format
+ * @out: Response message in device specific format
+ *
+ * Deliver a Remote Procedure Call to the device FW and return the response. The
+ * call's parameters and return are marshaled into linear buffers of memory. Any
+ * errno indicates that delivery of the RPC to the device failed. Return status
+ * originating in the device during a successful delivery must be encoded into
+ * out.
+ *
+ * The format of the buffers matches the out_device_type from FWCTL_INFO.
+ */
+struct fwctl_rpc {
+	__u32 size;
+	__u32 scope;
+	__u32 in_len;
+	__u32 out_len;
+	__aligned_u64 in;
+	__aligned_u64 out;
+};
+#define FWCTL_RPC _IO(FWCTL_TYPE, FWCTL_CMD_RPC)
+
+#endif
diff --git a/include/uapi/fwctl/mlx5.h b/include/uapi/fwctl/mlx5.h
new file mode 100644
index 000000000..625819180
--- /dev/null
+++ b/include/uapi/fwctl/mlx5.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES
+ *
+ * These are definitions for the command interface for mlx5 HW. mlx5 FW has a
+ * User Context mechanism which allows the FW to understand a security scope.
+ * FWCTL binds each FD to a FW user context and then places the User Context ID
+ * (UID) in each command header. The created User Context has a capability set
+ * that is appropriate for FWCTL's security model.
+ *
+ * Command formation should use a copy of the structs in mlx5_ifc.h following
+ * the Programmers Reference Manual. A open release is available here:
+ *
+ *  https://network.nvidia.com/files/doc-2020/ethernet-adapters-programming-manual.pdf
+ *
+ * The device_type for this file is FWCTL_DEVICE_TYPE_MLX5.
+ */
+#ifndef _UAPI_FWCTL_MLX5_H
+#define _UAPI_FWCTL_MLX5_H
+
+#include <linux/types.h>
+
+/**
+ * struct fwctl_info_mlx5 - ioctl(FWCTL_INFO) out_device_data
+ * @uid: The FW UID this FD is bound to. Each command header will force
+ *	this value.
+ * @uctx_caps: The FW capabilities that are enabled for the uid.
+ *
+ * Return basic information about the FW interface available.
+ */
+struct fwctl_info_mlx5 {
+	__u32 uid;
+	__u32 uctx_caps;
+};
+
+#endif
diff --git a/include/uapi/fwctl/pds.h b/include/uapi/fwctl/pds.h
new file mode 100644
index 000000000..66be32411
--- /dev/null
+++ b/include/uapi/fwctl/pds.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright(c) Advanced Micro Devices, Inc */
+
+/*
+ * fwctl interface info for pds_fwctl
+ */
+
+#ifndef _UAPI_FWCTL_PDS_H_
+#define _UAPI_FWCTL_PDS_H_
+
+#include <linux/types.h>
+
+/**
+ * struct fwctl_info_pds
+ * @uctx_caps:  bitmap of firmware capabilities
+ *
+ * Return basic information about the FW interface available.
+ */
+struct fwctl_info_pds {
+	__u32 uctx_caps;
+};
+
+/**
+ * enum pds_fwctl_capabilities
+ * @PDS_FWCTL_QUERY_CAP: firmware can be queried for information
+ * @PDS_FWCTL_SEND_CAP:  firmware can be sent commands
+ */
+enum pds_fwctl_capabilities {
+	PDS_FWCTL_QUERY_CAP = 0,
+	PDS_FWCTL_SEND_CAP,
+};
+
+/**
+ * struct fwctl_rpc_pds
+ * @in.op:       requested operation code
+ * @in.ep:       firmware endpoint to operate on
+ * @in.rsvd:     reserved
+ * @in.len:      length of payload data
+ * @in.payload:  address of payload buffer
+ * @in:          rpc in parameters
+ * @out.retval:  operation result value
+ * @out.rsvd:    reserved
+ * @out.len:     length of result data buffer
+ * @out.payload: address of payload data buffer
+ * @out:         rpc out parameters
+ */
+struct fwctl_rpc_pds {
+	struct {
+		__u32 op;
+		__u32 ep;
+		__u32 rsvd;
+		__u32 len;
+		__aligned_u64 payload;
+	} in;
+	struct {
+		__u32 retval;
+		__u32 rsvd[2];
+		__u32 len;
+		__aligned_u64 payload;
+	} out;
+};
+#endif /* _UAPI_FWCTL_PDS_H_ */