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, 172 insertions, 0 deletions

diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h
new file mode 100644
index 000000000..ba1ea5ed4
--- /dev/null
+++ b/include/uapi/misc/fastrpc.h
@@ -0,0 +1,172 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef __QCOM_FASTRPC_H__
+#define __QCOM_FASTRPC_H__
+
+#include <linux/types.h>
+
+#define FASTRPC_IOCTL_ALLOC_DMA_BUFF	_IOWR('R', 1, struct fastrpc_alloc_dma_buf)
+#define FASTRPC_IOCTL_FREE_DMA_BUFF	_IOWR('R', 2, __u32)
+#define FASTRPC_IOCTL_INVOKE		_IOWR('R', 3, struct fastrpc_invoke)
+#define FASTRPC_IOCTL_INIT_ATTACH	_IO('R', 4)
+#define FASTRPC_IOCTL_INIT_CREATE	_IOWR('R', 5, struct fastrpc_init_create)
+#define FASTRPC_IOCTL_MMAP		_IOWR('R', 6, struct fastrpc_req_mmap)
+#define FASTRPC_IOCTL_MUNMAP		_IOWR('R', 7, struct fastrpc_req_munmap)
+#define FASTRPC_IOCTL_INIT_ATTACH_SNS	_IO('R', 8)
+#define FASTRPC_IOCTL_INIT_CREATE_STATIC _IOWR('R', 9, struct fastrpc_init_create_static)
+#define FASTRPC_IOCTL_MEM_MAP		_IOWR('R', 10, struct fastrpc_mem_map)
+#define FASTRPC_IOCTL_MEM_UNMAP		_IOWR('R', 11, struct fastrpc_mem_unmap)
+#define FASTRPC_IOCTL_SET_OPTION	_IOWR('R', 12, struct fastrpc_ioctl_set_option)
+#define FASTRPC_IOCTL_GET_DSP_INFO	_IOWR('R', 13, struct fastrpc_ioctl_capability)
+
+/**
+ * enum fastrpc_map_flags - control flags for mapping memory on DSP user process
+ * @FASTRPC_MAP_STATIC: Map memory pages with RW- permission and CACHE WRITEBACK.
+ * The driver is responsible for cache maintenance when passed
+ * the buffer to FastRPC calls. Same virtual address will be
+ * assigned for subsequent FastRPC calls.
+ * @FASTRPC_MAP_RESERVED: Reserved
+ * @FASTRPC_MAP_FD: Map memory pages with RW- permission and CACHE WRITEBACK.
+ * Mapping tagged with a file descriptor. User is responsible for
+ * CPU and DSP cache maintenance for the buffer. Get virtual address
+ * of buffer on DSP using HAP_mmap_get() and HAP_mmap_put() APIs.
+ * @FASTRPC_MAP_FD_DELAYED: Mapping delayed until user call HAP_mmap() and HAP_munmap()
+ * functions on DSP. It is useful to map a buffer with cache modes
+ * other than default modes. User is responsible for CPU and DSP
+ * cache maintenance for the buffer.
+ * @FASTRPC_MAP_FD_NOMAP: This flag is used to skip CPU mapping,
+ * otherwise behaves similar to FASTRPC_MAP_FD_DELAYED flag.
+ * @FASTRPC_MAP_MAX: max count for flags
+ *
+ */
+enum fastrpc_map_flags {
+	FASTRPC_MAP_STATIC = 0,
+	FASTRPC_MAP_RESERVED,
+	FASTRPC_MAP_FD = 2,
+	FASTRPC_MAP_FD_DELAYED,
+	FASTRPC_MAP_FD_NOMAP = 16,
+	FASTRPC_MAP_MAX,
+};
+
+enum fastrpc_proc_attr {
+	/* Macro for Debug attr */
+	FASTRPC_MODE_DEBUG		= (1 << 0),
+	/* Macro for Ptrace */
+	FASTRPC_MODE_PTRACE		= (1 << 1),
+	/* Macro for CRC Check */
+	FASTRPC_MODE_CRC		= (1 << 2),
+	/* Macro for Unsigned PD */
+	FASTRPC_MODE_UNSIGNED_MODULE	= (1 << 3),
+	/* Macro for Adaptive QoS */
+	FASTRPC_MODE_ADAPTIVE_QOS	= (1 << 4),
+	/* Macro for System Process */
+	FASTRPC_MODE_SYSTEM_PROCESS	= (1 << 5),
+	/* Macro for Prvileged Process */
+	FASTRPC_MODE_PRIVILEGED		= (1 << 6),
+};
+
+/* Fastrpc attribute for memory protection of buffers */
+#define FASTRPC_ATTR_SECUREMAP	(1)
+
+/**
+ * FASTRPC_POLL_MODE - Enable/disable poll mode for FastRPC invocations
+ *
+ * Poll mode is an optimization that allows the CPU to poll shared memory
+ * for completion instead of waiting for an interrupt-based response.
+ * This reduces latency for fast-completing operations.
+ *
+ * Restrictions:
+ * - Only supported for USER_PD (User Protection Domain)
+ * - Only applies to dynamic modules (handle > 20)
+ * - Static modules always use interrupt-based completion
+ *
+ * Values:
+ * - 0: Disable poll mode (use interrupt-based completion)
+ * - 1: Enable poll mode (poll shared memory for completion)
+ */
+#define FASTRPC_POLL_MODE	(1)
+
+/* Values for FASTRPC_POLL_MODE request */
+#define FASTRPC_POLL_MODE_DISABLE	0
+#define FASTRPC_POLL_MODE_ENABLE	1
+
+struct fastrpc_invoke_args {
+	__u64 ptr;
+	__u64 length;
+	__s32 fd;
+	__u32 attr;
+};
+
+struct fastrpc_invoke {
+	__u32 handle;
+	__u32 sc;
+	__u64 args;
+};
+
+struct fastrpc_init_create {
+	__u32 filelen;	/* elf file length */
+	__s32 filefd;	/* fd for the file */
+	__u32 attrs;
+	__u32 siglen;
+	__u64 file;	/* pointer to elf file */
+};
+
+struct fastrpc_init_create_static {
+	__u32 namelen;	/* length of pd process name */
+	__u32 memlen;
+	__u64 name;	/* pd process name */
+};
+
+struct fastrpc_alloc_dma_buf {
+	__s32 fd;	/* fd */
+	__u32 flags;	/* flags to map with */
+	__u64 size;	/* size */
+};
+
+struct fastrpc_req_mmap {
+	__s32 fd;
+	__u32 flags;	/* flags for dsp to map with */
+	__u64 vaddrin;	/* optional virtual address */
+	__u64 size;	/* size */
+	__u64 vaddrout;	/* dsp virtual address */
+};
+
+struct fastrpc_mem_map {
+	__s32 version;
+	__s32 fd;		/* fd */
+	__s32 offset;		/* buffer offset */
+	__u32 flags;		/* flags defined in enum fastrpc_map_flags */
+	__u64 vaddrin;		/* buffer virtual address */
+	__u64 length;		/* buffer length */
+	__u64 vaddrout;		/* [out] remote virtual address */
+	__s32 attrs;		/* buffer attributes used for SMMU mapping */
+	__s32 reserved[4];
+};
+
+struct fastrpc_req_munmap {
+	__u64 vaddrout;	/* address to unmap */
+	__u64 size;	/* size */
+};
+
+struct fastrpc_mem_unmap {
+	__s32 vesion;
+	__s32 fd;		/* fd */
+	__u64 vaddr;		/* remote process (dsp) virtual address */
+	__u64 length;		/* buffer size */
+	__s32 reserved[5];
+};
+
+struct fastrpc_ioctl_set_option {
+	__u32 request_id;	/* Request type (e.g., FASTRPC_POLL_MODE) */
+	__u32 value;	/* Request-specific value */
+	__s32 reserved[6];
+};
+
+struct fastrpc_ioctl_capability {
+	__u32 unused; /* deprecated, ignored by the kernel */
+	__u32 attribute_id;
+	__u32 capability;   /* dsp capability */
+	__u32 reserved[4];
+};
+
+#endif /* __QCOM_FASTRPC_H__ */