target/arm: Implement FEAT_PACQARMA3

Implement the QARMA3 cryptographic algorithm for PAC calculation.
Implement a cpu feature to select the algorithm and document it.

Signed-off-by: Aaron Lindsay <aaron@os.amperecomputing.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20230829232335.965414-6-richard.henderson@linaro.org
Message-Id: <20230609172324.982888-4-aaron@os.amperecomputing.com>
[rth: Merge cpu feature addition from another patch.]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

docs/system/arm/cpu-features.rst

@@ -210,15 +210,20 @@ TCG VCPU Features
 TCG VCPU features are CPU features that are specific to TCG.
 Below is the list of TCG VCPU features and their descriptions.
 
+``pauth``
+  Enable or disable ``FEAT_Pauth`` entirely.
+
 ``pauth-impdef``
-  When ``FEAT_Pauth`` is enabled, either the *impdef* (Implementation
-  Defined) algorithm is enabled or the *architected* QARMA algorithm
-  is enabled.  By default the impdef algorithm is disabled, and QARMA
-  is enabled.
-
-  The architected QARMA algorithm has good cryptographic properties,
-  but can be quite slow to emulate.  The impdef algorithm used by QEMU
-  is non-cryptographic but significantly faster.
+  When ``pauth`` is enabled, select the QEMU implementation defined algorithm.
+
+``pauth-qarma3``
+  When ``pauth`` is enabled, select the architected QARMA3 algorithm.
+
+Without either ``pauth-impdef`` or ``pauth-qarma3`` enabled,
+the architected QARMA5 algorithm is used.  The architected QARMA5
+and QARMA3 algorithms have good cryptographic properties, but can
+be quite slow to emulate.  The impdef algorithm used by QEMU is
+non-cryptographic but significantly faster.
 
 SVE CPU Properties
 ==================

docs/system/arm/emulation.rst

@@ -57,6 +57,9 @@ the following architecture extensions:
 - FEAT_MTE (Memory Tagging Extension)
 - FEAT_MTE2 (Memory Tagging Extension)
 - FEAT_MTE3 (MTE Asymmetric Fault Handling)
+- FEAT_PACIMP (Pointer authentication - IMPLEMENTATION DEFINED algorithm)
+- FEAT_PACQARMA3 (Pointer authentication - QARMA3 algorithm)
+- FEAT_PACQARMA5 (Pointer authentication - QARMA5 algorithm)
 - FEAT_PAN (Privileged access never)
 - FEAT_PAN2 (AT S1E1R and AT S1E1W instruction variants affected by PSTATE.PAN)
 - FEAT_PAN3 (Support for SCTLR_ELx.EPAN)

target/arm/arm-qmp-cmds.c

@@ -95,7 +95,7 @@ static const char *cpu_model_advertised_features[] = {
     "sve640", "sve768", "sve896", "sve1024", "sve1152", "sve1280",
     "sve1408", "sve1536", "sve1664", "sve1792", "sve1920", "sve2048",
     "kvm-no-adjvtime", "kvm-steal-time",
-    "pauth", "pauth-impdef",
+    "pauth", "pauth-impdef", "pauth-qarma3",
     NULL
 };
 

target/arm/cpu.h

@@ -1072,6 +1072,7 @@ struct ArchCPU {
      */
     bool prop_pauth;
     bool prop_pauth_impdef;
+    bool prop_pauth_qarma3;
     bool prop_lpa2;
 
     /* DCZ blocksize, in log_2(words), ie low 4 bits of DCZID_EL0 */

target/arm/cpu64.c

@@ -474,7 +474,7 @@ void aarch64_add_sme_properties(Object *obj)
 void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp)
 {
     ARMPauthFeature features = cpu_isar_feature(pauth_feature, cpu);
-    uint64_t isar1;
+    uint64_t isar1, isar2;
 
     /*
      * These properties enable or disable Pauth as a whole, or change
@@ -490,6 +490,10 @@ void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp)
     isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, API, 0);
     isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPI, 0);
 
+    isar2 = cpu->isar.id_aa64isar2;
+    isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, APA3, 0);
+    isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, GPA3, 0);
+
     if (kvm_enabled() || hvf_enabled()) {
         /*
          * Exit early if PAuth is enabled and fall through to disable it.
@@ -510,26 +514,39 @@ void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp)
         }
 
         if (cpu->prop_pauth) {
+            if (cpu->prop_pauth_impdef && cpu->prop_pauth_qarma3) {
+                error_setg(errp,
+                           "cannot enable both pauth-impdef and pauth-qarma3");
+                return;
+            }
+
             if (cpu->prop_pauth_impdef) {
                 isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, API, features);
                 isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPI, 1);
+            } else if (cpu->prop_pauth_qarma3) {
+                isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, APA3, features);
+                isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, GPA3, 1);
             } else {
                 isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, APA, features);
                 isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPA, 1);
             }
-        } else if (cpu->prop_pauth_impdef) {
-            error_setg(errp, "cannot enable pauth-impdef without pauth");
+        } else if (cpu->prop_pauth_impdef || cpu->prop_pauth_qarma3) {
+            error_setg(errp, "cannot enable pauth-impdef or "
+                       "pauth-qarma3 without pauth");
             error_append_hint(errp, "Add pauth=on to the CPU property list.\n");
         }
     }
 
     cpu->isar.id_aa64isar1 = isar1;
+    cpu->isar.id_aa64isar2 = isar2;
 }
 
 static Property arm_cpu_pauth_property =
     DEFINE_PROP_BOOL("pauth", ARMCPU, prop_pauth, true);
 static Property arm_cpu_pauth_impdef_property =
     DEFINE_PROP_BOOL("pauth-impdef", ARMCPU, prop_pauth_impdef, false);
+static Property arm_cpu_pauth_qarma3_property =
+    DEFINE_PROP_BOOL("pauth-qarma3", ARMCPU, prop_pauth_qarma3, false);
 
 void aarch64_add_pauth_properties(Object *obj)
 {
@@ -549,6 +566,7 @@ void aarch64_add_pauth_properties(Object *obj)
         cpu->prop_pauth = cpu_isar_feature(aa64_pauth, cpu);
     } else {
         qdev_property_add_static(DEVICE(obj), &arm_cpu_pauth_impdef_property);
+        qdev_property_add_static(DEVICE(obj), &arm_cpu_pauth_qarma3_property);
     }
 }
 

target/arm/tcg/pauth_helper.c

@@ -96,6 +96,21 @@ static uint64_t pac_sub(uint64_t i)
     return o;
 }
 
+static uint64_t pac_sub1(uint64_t i)
+{
+    static const uint8_t sub1[16] = {
+        0xa, 0xd, 0xe, 0x6, 0xf, 0x7, 0x3, 0x5,
+        0x9, 0x8, 0x0, 0xc, 0xb, 0x1, 0x2, 0x4,
+    };
+    uint64_t o = 0;
+    int b;
+
+    for (b = 0; b < 64; b += 4) {
+        o |= (uint64_t)sub1[(i >> b) & 0xf] << b;
+    }
+    return o;
+}
+
 static uint64_t pac_inv_sub(uint64_t i)
 {
     static const uint8_t inv_sub[16] = {
@@ -209,7 +224,7 @@ static uint64_t tweak_inv_shuffle(uint64_t i)
 }
 
 static uint64_t pauth_computepac_architected(uint64_t data, uint64_t modifier,
-                                             ARMPACKey key)
+                                             ARMPACKey key, bool isqarma3)
 {
     static const uint64_t RC[5] = {
         0x0000000000000000ull,
@@ -219,6 +234,7 @@ static uint64_t pauth_computepac_architected(uint64_t data, uint64_t modifier,
         0x452821E638D01377ull,
     };
     const uint64_t alpha = 0xC0AC29B7C97C50DDull;
+    int iterations = isqarma3 ? 2 : 4;
     /*
      * Note that in the ARM pseudocode, key0 contains bits <127:64>
      * and key1 contains bits <63:0> of the 128-bit key.
@@ -231,40 +247,56 @@ static uint64_t pauth_computepac_architected(uint64_t data, uint64_t modifier,
     runningmod = modifier;
     workingval = data ^ key0;
 
-    for (i = 0; i <= 4; ++i) {
+    for (i = 0; i <= iterations; ++i) {
         roundkey = key1 ^ runningmod;
         workingval ^= roundkey;
         workingval ^= RC[i];
         if (i > 0) {
             workingval = pac_cell_shuffle(workingval);
             workingval = pac_mult(workingval);
         }
-        workingval = pac_sub(workingval);
+        if (isqarma3) {
+            workingval = pac_sub1(workingval);
+        } else {
+            workingval = pac_sub(workingval);
+        }
         runningmod = tweak_shuffle(runningmod);
     }
     roundkey = modk0 ^ runningmod;
     workingval ^= roundkey;
     workingval = pac_cell_shuffle(workingval);
     workingval = pac_mult(workingval);
-    workingval = pac_sub(workingval);
+    if (isqarma3) {
+        workingval = pac_sub1(workingval);
+    } else {
+        workingval = pac_sub(workingval);
+    }
     workingval = pac_cell_shuffle(workingval);
     workingval = pac_mult(workingval);
     workingval ^= key1;
     workingval = pac_cell_inv_shuffle(workingval);
-    workingval = pac_inv_sub(workingval);
+    if (isqarma3) {
+        workingval = pac_sub1(workingval);
+    } else {
+        workingval = pac_inv_sub(workingval);
+    }
     workingval = pac_mult(workingval);
     workingval = pac_cell_inv_shuffle(workingval);
     workingval ^= key0;
     workingval ^= runningmod;
-    for (i = 0; i <= 4; ++i) {
-        workingval = pac_inv_sub(workingval);
-        if (i < 4) {
+    for (i = 0; i <= iterations; ++i) {
+        if (isqarma3) {
+            workingval = pac_sub1(workingval);
+        } else {
+            workingval = pac_inv_sub(workingval);
+        }
+        if (i < iterations) {
             workingval = pac_mult(workingval);
             workingval = pac_cell_inv_shuffle(workingval);
         }
         runningmod = tweak_inv_shuffle(runningmod);
         roundkey = key1 ^ runningmod;
-        workingval ^= RC[4 - i];
+        workingval ^= RC[iterations - i];
         workingval ^= roundkey;
         workingval ^= alpha;
     }
@@ -283,7 +315,9 @@ static uint64_t pauth_computepac(CPUARMState *env, uint64_t data,
                                  uint64_t modifier, ARMPACKey key)
 {
     if (cpu_isar_feature(aa64_pauth_qarma5, env_archcpu(env))) {
-        return pauth_computepac_architected(data, modifier, key);
+        return pauth_computepac_architected(data, modifier, key, false);
+    } else if (cpu_isar_feature(aa64_pauth_qarma3, env_archcpu(env))) {
+        return pauth_computepac_architected(data, modifier, key, true);
     } else {
         return pauth_computepac_impdef(data, modifier, key);
     }

tests/qtest/arm-cpu-features.c

@@ -417,12 +417,22 @@ static void pauth_tests_default(QTestState *qts, const char *cpu_type)
 {
     assert_has_feature_enabled(qts, cpu_type, "pauth");
     assert_has_feature_disabled(qts, cpu_type, "pauth-impdef");
+    assert_has_feature_disabled(qts, cpu_type, "pauth-qarma3");
     assert_set_feature(qts, cpu_type, "pauth", false);
     assert_set_feature(qts, cpu_type, "pauth", true);
     assert_set_feature(qts, cpu_type, "pauth-impdef", true);
     assert_set_feature(qts, cpu_type, "pauth-impdef", false);
-    assert_error(qts, cpu_type, "cannot enable pauth-impdef without pauth",
+    assert_set_feature(qts, cpu_type, "pauth-qarma3", true);
+    assert_set_feature(qts, cpu_type, "pauth-qarma3", false);
+    assert_error(qts, cpu_type,
+                 "cannot enable pauth-impdef or pauth-qarma3 without pauth",
                  "{ 'pauth': false, 'pauth-impdef': true }");
+    assert_error(qts, cpu_type,
+                 "cannot enable pauth-impdef or pauth-qarma3 without pauth",
+                 "{ 'pauth': false, 'pauth-qarma3': true }");
+    assert_error(qts, cpu_type,
+                 "cannot enable both pauth-impdef and pauth-qarma3",
+                 "{ 'pauth': true, 'pauth-impdef': true, 'pauth-qarma3': true }");
 }
 
 static void test_query_cpu_model_expansion(const void *data)