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, 102 insertions, 0 deletions

diff --git a/include/crypto/chacha.h b/include/crypto/chacha.h
new file mode 100644
index 000000000..1cc301a48
--- /dev/null
+++ b/include/crypto/chacha.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common values and helper functions for the ChaCha and XChaCha stream ciphers.
+ *
+ * XChaCha extends ChaCha's nonce to 192 bits, while provably retaining ChaCha's
+ * security.  Here they share the same key size, tfm context, and setkey
+ * function; only their IV size and encrypt/decrypt function differ.
+ *
+ * The ChaCha paper specifies 20, 12, and 8-round variants.  In general, it is
+ * recommended to use the 20-round variant ChaCha20.  However, the other
+ * variants can be needed in some performance-sensitive scenarios.  The generic
+ * ChaCha code currently allows only the 20 and 12-round variants.
+ */
+
+#ifndef _CRYPTO_CHACHA_H
+#define _CRYPTO_CHACHA_H
+
+#include <linux/unaligned.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+/* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */
+#define CHACHA_IV_SIZE		16
+
+#define CHACHA_KEY_SIZE		32
+#define CHACHA_BLOCK_SIZE	64
+#define CHACHAPOLY_IV_SIZE	12
+
+#define CHACHA_KEY_WORDS	8
+#define CHACHA_STATE_WORDS	16
+#define HCHACHA_OUT_WORDS	8
+
+/* 192-bit nonce, then 64-bit stream position */
+#define XCHACHA_IV_SIZE		32
+
+struct chacha_state {
+	u32 x[CHACHA_STATE_WORDS];
+};
+
+void chacha_block_generic(struct chacha_state *state,
+			  u8 out[at_least CHACHA_BLOCK_SIZE], int nrounds);
+static inline void chacha20_block(struct chacha_state *state,
+				  u8 out[at_least CHACHA_BLOCK_SIZE])
+{
+	chacha_block_generic(state, out, 20);
+}
+
+void hchacha_block_generic(const struct chacha_state *state,
+			   u32 out[at_least HCHACHA_OUT_WORDS], int nrounds);
+
+void hchacha_block(const struct chacha_state *state,
+		   u32 out[at_least HCHACHA_OUT_WORDS], int nrounds);
+
+enum chacha_constants { /* expand 32-byte k */
+	CHACHA_CONSTANT_EXPA = 0x61707865U,
+	CHACHA_CONSTANT_ND_3 = 0x3320646eU,
+	CHACHA_CONSTANT_2_BY = 0x79622d32U,
+	CHACHA_CONSTANT_TE_K = 0x6b206574U
+};
+
+static inline void chacha_init_consts(struct chacha_state *state)
+{
+	state->x[0]  = CHACHA_CONSTANT_EXPA;
+	state->x[1]  = CHACHA_CONSTANT_ND_3;
+	state->x[2]  = CHACHA_CONSTANT_2_BY;
+	state->x[3]  = CHACHA_CONSTANT_TE_K;
+}
+
+static inline void chacha_init(struct chacha_state *state,
+			       const u32 key[at_least CHACHA_KEY_WORDS],
+			       const u8 iv[at_least CHACHA_IV_SIZE])
+{
+	chacha_init_consts(state);
+	state->x[4]  = key[0];
+	state->x[5]  = key[1];
+	state->x[6]  = key[2];
+	state->x[7]  = key[3];
+	state->x[8]  = key[4];
+	state->x[9]  = key[5];
+	state->x[10] = key[6];
+	state->x[11] = key[7];
+	state->x[12] = get_unaligned_le32(iv +  0);
+	state->x[13] = get_unaligned_le32(iv +  4);
+	state->x[14] = get_unaligned_le32(iv +  8);
+	state->x[15] = get_unaligned_le32(iv + 12);
+}
+
+void chacha_crypt(struct chacha_state *state, u8 *dst, const u8 *src,
+		  unsigned int bytes, int nrounds);
+
+static inline void chacha20_crypt(struct chacha_state *state,
+				  u8 *dst, const u8 *src, unsigned int bytes)
+{
+	chacha_crypt(state, dst, src, bytes, 20);
+}
+
+static inline void chacha_zeroize_state(struct chacha_state *state)
+{
+	memzero_explicit(state, sizeof(*state));
+}
+
+#endif /* _CRYPTO_CHACHA_H */