[PATCH v10 09/21] target/s390x: Support AES XTS for cpacf km instruction

[Harald Freudenberger <freude@linux.ibm.com>]

Support the subfunctions XTS-AES-128 and XTS-AES-256
for the cpacf km instruction.

Tested-by: Holger Dengler <dengler@linux.ibm.com>
Signed-off-by: Harald Freudenberger <freude@linux.ibm.com>
---
 target/s390x/gen-features.c      |   2 +
 target/s390x/tcg/cpacf.h         |   4 ++
 target/s390x/tcg/cpacf_aes.c     | 108 +++++++++++++++++++++++++++++++
 target/s390x/tcg/crypto_helper.c |   6 ++
 4 files changed, 120 insertions(+)

diff --git a/target/s390x/gen-features.c b/target/s390x/gen-features.c
index 1b6a874b90..f9b1a40c7c 100644
--- a/target/s390x/gen-features.c
+++ b/target/s390x/gen-features.c
@@ -924,6 +924,8 @@ static uint16_t qemu_MAX[] = {
     S390_FEAT_KM_AES_128,
     S390_FEAT_KM_AES_192,
     S390_FEAT_KM_AES_256,
+    S390_FEAT_KM_XTS_AES_128,
+    S390_FEAT_KM_XTS_AES_256,
     S390_FEAT_KMC_AES_128,
     S390_FEAT_KMC_AES_192,
     S390_FEAT_KMC_AES_256,
diff --git a/target/s390x/tcg/cpacf.h b/target/s390x/tcg/cpacf.h
index 2e8ed72758..e585b77766 100644
--- a/target/s390x/tcg/cpacf.h
+++ b/target/s390x/tcg/cpacf.h
@@ -249,5 +249,9 @@ int cpacf_aes_ctr(CPUS390XState *env, const int mmu_idx, uintptr_t ra,
                   uint8_t fc, uint8_t mod);
 int cpacf_aes_pcc(CPUS390XState *env, const int mmu_idx, uintptr_t ra,
                   uint64_t param_addr, uint8_t fc);
+int cpacf_aes_xts(CPUS390XState *env, const int mmu_idx, uintptr_t ra,
+                  uint64_t param_addr, uint64_t *dst_ptr_reg,
+                  uint64_t *src_ptr_reg, uint64_t *src_len_reg,
+                  uint32_t type, uint8_t fc, uint8_t mod);
 
 #endif /* S390X_CPACF_H */
diff --git a/target/s390x/tcg/cpacf_aes.c b/target/s390x/tcg/cpacf_aes.c
index f41b7dc541..4a28cc3d7c 100644
--- a/target/s390x/tcg/cpacf_aes.c
+++ b/target/s390x/tcg/cpacf_aes.c
@@ -353,3 +353,111 @@ int cpacf_aes_pcc(CPUS390XState *env, const int mmu_idx, uintptr_t ra,
 
     return 0;
 }
+
+static void aes_xts_prep_next_tweak(uint8_t tweak[AES_BLOCK_SIZE])
+{
+    uint8_t carry;
+    int i;
+
+    carry = tweak[AES_BLOCK_SIZE - 1] >> 7;
+
+    for (i = AES_BLOCK_SIZE - 1; i > 0; i--) {
+        tweak[i] = (uint8_t)((tweak[i] << 1) | (tweak[i - 1] >> 7));
+    }
+
+    tweak[i] = (uint8_t)(tweak[i] << 1);
+    tweak[i] ^= (uint8_t)(0x87 & (uint8_t)(-(int8_t)carry));
+}
+
+int cpacf_aes_xts(CPUS390XState *env, const int mmu_idx, uintptr_t ra,
+                  uint64_t param_addr, uint64_t *dst_ptr_reg,
+                  uint64_t *src_ptr_reg, uint64_t *src_len_reg,
+                  uint32_t type, uint8_t fc, uint8_t mod)
+{
+    enum { MAX_BLOCKS_PER_RUN = 8192 / AES_BLOCK_SIZE };
+    uint8_t buf1[AES_BLOCK_SIZE], buf2[AES_BLOCK_SIZE];
+    const MemOpIdx oi = make_memop_idx(MO_8, mmu_idx);
+    uint64_t addr, len = *src_len_reg, done = 0;
+    uint8_t key[32], tweak[AES_BLOCK_SIZE];
+    int i, keysize, addr_reg_size = 64;
+    AES_KEY exkey;
+
+    g_assert(type == S390_FEAT_TYPE_KM);
+
+    switch (fc) {
+    case CPACF_KM_XTS_128:
+        keysize = 16;
+        break;
+    case CPACF_KM_XTS_256:
+        keysize = 32;
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    if (!(env->psw.mask & PSW_MASK_64)) {
+        len = (uint32_t)len;
+        addr_reg_size = (env->psw.mask & PSW_MASK_32) ? 32 : 24;
+    }
+
+    /* length has to be properly aligned. */
+    if (!QEMU_IS_ALIGNED(len, AES_BLOCK_SIZE)) {
+        tcg_s390_program_interrupt(env, PGM_SPECIFICATION, ra);
+    }
+
+    /* fetch key from param block */
+    for (i = 0; i < keysize; i++) {
+        addr = wrap_address(env, param_addr + i);
+        key[i] = cpu_ldb_mmu(env, addr, oi, ra);
+    }
+
+    /* expand key */
+    if (mod) {
+        AES_set_decrypt_key(key, keysize * 8, &exkey);
+    } else {
+        AES_set_encrypt_key(key, keysize * 8, &exkey);
+    }
+
+    /* fetch tweak from param block */
+    for (i = 0; i < AES_BLOCK_SIZE; i++) {
+        addr = wrap_address(env, param_addr + keysize + i);
+        tweak[i] = cpu_ldb_mmu(env, addr, oi, ra);
+    }
+
+    /* process up to MAX_BLOCKS_PER_RUN aes blocks */
+    for (i = 0; i < MAX_BLOCKS_PER_RUN && len >= AES_BLOCK_SIZE; i++) {
+        /* fetch one AES block into buf1  */
+        aes_read_block(env, mmu_idx, *src_ptr_reg + done, buf1, ra);
+        /* buf1 xor tweak => buf2 */
+        aes_xor(buf1, tweak, buf2);
+        if (mod) {
+            /* decrypt buf2 => buf1 */
+            AES_decrypt(buf2, buf1, &exkey);
+        } else {
+            /* encrypt buf2 => buf1 */
+            AES_encrypt(buf2, buf1, &exkey);
+        }
+        /* buf1 xor tweak => buf2 */
+        aes_xor(buf1, tweak, buf2);
+        /* prep tweak for next round */
+        aes_xts_prep_next_tweak(tweak);
+        /* write out this processed block from buf2 */
+        aes_write_block(env, mmu_idx, *dst_ptr_reg + done, buf2, ra);
+        len -= AES_BLOCK_SIZE;
+        done += AES_BLOCK_SIZE;
+    }
+
+    /* update tweak in param block */
+    for (i = 0; i < AES_BLOCK_SIZE; i++) {
+        addr = wrap_address(env, param_addr + keysize + i);
+        cpu_stb_mmu(env, addr, tweak[i], oi, ra);
+    }
+
+    *src_ptr_reg = deposit64(*src_ptr_reg, 0, addr_reg_size,
+                             *src_ptr_reg + done);
+    *dst_ptr_reg = deposit64(*dst_ptr_reg, 0, addr_reg_size,
+                             *dst_ptr_reg + done);
+    *src_len_reg -= done;
+
+    return !len ? 0 : 3;
+}
diff --git a/target/s390x/tcg/crypto_helper.c b/target/s390x/tcg/crypto_helper.c
index 1d447cef30..564f7fa243 100644
--- a/target/s390x/tcg/crypto_helper.c
+++ b/target/s390x/tcg/crypto_helper.c
@@ -103,6 +103,12 @@ static int cpacf_km(CPUS390XState *env, const int mmu_idx, uintptr_t ra,
                            &env->regs[r1], &env->regs[r2], &env->regs[r2 + 1],
                            S390_FEAT_TYPE_KM, fc, mod);
         break;
+    case CPACF_KM_XTS_128:
+    case CPACF_KM_XTS_256:
+        rc = cpacf_aes_xts(env, mmu_idx, ra, env->regs[1],
+                           &env->regs[r1], &env->regs[r2], &env->regs[r2 + 1],
+                           S390_FEAT_TYPE_KM, fc, mod);
+        break;
     default:
         tcg_s390_program_interrupt(env, PGM_SPECIFICATION, ra);
     }
-- 
2.43.0