Merge tag 'pull-target-arm-20240813' of https://git.linaro.org/people/pmaydell/qemu-arm into staging

target-arm queue:
 * hw/misc/stm32l4x5_rcc: Add validation for MCOPRE and MCOSEL values
 * target/arm: Clear high SVE elements in handle_vec_simd_wshli
 * target/arm: Fix usage of MMU indexes when EL3 is AArch32

# -----BEGIN PGP SIGNATURE-----
#
# iQJNBAABCAA3FiEE4aXFk81BneKOgxXPPCUl7RQ2DN4FAma7eSIZHHBldGVyLm1h
# eWRlbGxAbGluYXJvLm9yZwAKCRA8JSXtFDYM3gbJEACHhZAvP4f1vic8DNGPw8Yr
# v+pRQON+vF+PDBSyNkYCRL5Gy1P257Aujw1ed2dpoDhMemC/co67W2zdzToCvDd5
# XZxlHb/iUCTeZbA/Zp66ZADlvVOdvvQL8EHbd4mSBEZp9rvPSmxatx4I5jstLiAV
# 5HimP+AjjGMfklMu+RelW7A7WDRJ0h7F4PwXCA8tLeHPH5XHSkweGYt3OVfSlUAs
# +RKiltByC/quujLHxrQcVtLZON1KKiB0P8VPRcaR1QIFARiR1IfLvzhKVpqyOlnV
# 3a+ZILtCJE1YEM+h7Aunz/l9MQ0DZe5DzbIdKOQ7NUkerlhq81kriPp67yLv25lk
# zgqkHGGDEnIGpSXdmbXTNLcGlH+5O+fWl2RMzYrSFJqvwyRu9egLLi6E0xaNCRvY
# gdb6CGPhhu21C1o5Nax0CiaZe3vzzRvC5QsIJ0yww6y7VaGFVt/XRaKBdLHB97nZ
# t/9ifa3fmhVEW6pQEy8VdAeFoxIT2lJ2xJgBdMwpZCJlCxB8xKU/rZfrXKS/UUqV
# 9Klbcfrx1WFT7zrAWS0Ig7nPttJ+XgjYfgHI3q2e80F6xRmAmaAjnbtVRS+L3It9
# eZ4SmuzurWipRLpdmxdOX1IXdZD9rJMzk9IUIZoklctlR/D+75Iuy0N7gY8G2dbp
# fmh38lEQZ0IC90VmNtWltw==
# =So/3
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 14 Aug 2024 01:17:54 AM AEST
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [full]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [full]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [full]
# gpg:                 aka "Peter Maydell <peter@archaic.org.uk>" [unknown]

* tag 'pull-target-arm-20240813' of https://git.linaro.org/people/pmaydell/qemu-arm:
  target/arm: Fix usage of MMU indexes when EL3 is AArch32
  target/arm: Update translation regime comment for new features
  target/arm: Clear high SVE elements in handle_vec_simd_wshli
  hw/misc/stm32l4x5_rcc: Add validation for MCOPRE and MCOSEL values

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

8 files changed, 96 insertions, 39 deletions

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index a12859fc53..9a3fd59562 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -2772,14 +2772,19 @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync);
  *  + NonSecure EL1 & 0 stage 2
  *  + NonSecure EL2
  *  + NonSecure EL2 & 0   (ARMv8.1-VHE)
- *  + Secure EL1 & 0
- *  + Secure EL3
+ *  + Secure EL1 & 0 stage 1
+ *  + Secure EL1 & 0 stage 2 (FEAT_SEL2)
+ *  + Secure EL2 (FEAT_SEL2)
+ *  + Secure EL2 & 0 (FEAT_SEL2)
+ *  + Realm EL1 & 0 stage 1 (FEAT_RME)
+ *  + Realm EL1 & 0 stage 2 (FEAT_RME)
+ *  + Realm EL2 (FEAT_RME)
+ *  + EL3
  * If EL3 is 32-bit:
  *  + NonSecure PL1 & 0 stage 1
  *  + NonSecure PL1 & 0 stage 2
  *  + NonSecure PL2
- *  + Secure PL0
- *  + Secure PL1
+ *  + Secure PL1 & 0
  * (reminder: for 32 bit EL3, Secure PL1 is *EL3*, not EL1.)
  *
  * For QEMU, an mmu_idx is not quite the same as a translation regime because:
@@ -2797,37 +2802,42 @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync);
  *     The only use of stage 2 translations is either as part of an s1+2
  *     lookup or when loading the descriptors during a stage 1 page table walk,
  *     and in both those cases we don't use the TLB.
- *  4. we can also safely fold together the "32 bit EL3" and "64 bit EL3"
- *     translation regimes, because they map reasonably well to each other
- *     and they can't both be active at the same time.
- *  5. we want to be able to use the TLB for accesses done as part of a
+ *  4. we want to be able to use the TLB for accesses done as part of a
  *     stage1 page table walk, rather than having to walk the stage2 page
  *     table over and over.
- *  6. we need separate EL1/EL2 mmu_idx for handling the Privileged Access
+ *  5. we need separate EL1/EL2 mmu_idx for handling the Privileged Access
  *     Never (PAN) bit within PSTATE.
- *  7. we fold together the secure and non-secure regimes for A-profile,
+ *  6. we fold together most secure and non-secure regimes for A-profile,
  *     because there are no banked system registers for aarch64, so the
  *     process of switching between secure and non-secure is
  *     already heavyweight.
+ *  7. we cannot fold together Stage 2 Secure and Stage 2 NonSecure,
+ *     because both are in use simultaneously for Secure EL2.
  *
  * This gives us the following list of cases:
  *
- * EL0 EL1&0 stage 1+2 (aka NS PL0)
- * EL1 EL1&0 stage 1+2 (aka NS PL1)
- * EL1 EL1&0 stage 1+2 +PAN
+ * EL0 EL1&0 stage 1+2 (or AArch32 PL0 PL1&0 stage 1+2)
+ * EL1 EL1&0 stage 1+2 (or AArch32 PL1 PL1&0 stage 1+2)
+ * EL1 EL1&0 stage 1+2 +PAN (or AArch32 PL1 PL1&0 stage 1+2 +PAN)
  * EL0 EL2&0
  * EL2 EL2&0
  * EL2 EL2&0 +PAN
  * EL2 (aka NS PL2)
- * EL3 (aka S PL1)
- * Physical (NS & S)
- * Stage2 (NS & S)
+ * EL3 (not used when EL3 is AArch32)
+ * Stage2 Secure
+ * Stage2 NonSecure
+ * plus one TLB per Physical address space: S, NS, Realm, Root
  *
- * for a total of 12 different mmu_idx.
+ * for a total of 14 different mmu_idx.
+ *
+ * Note that when EL3 is AArch32, the usage is potentially confusing
+ * because the MMU indexes are named for their AArch64 use, so code
+ * using the ARMMMUIdx_E10_1 might be at EL3, not EL1. This is because
+ * Secure PL1 is always at EL3.
  *
  * R profile CPUs have an MPU, but can use the same set of MMU indexes
  * as A profile. They only need to distinguish EL0 and EL1 (and
- * EL2 if we ever model a Cortex-R52).
+ * EL2 for cores like the Cortex-R52).
  *
  * M profile CPUs are rather different as they do not have a true MMU.
  * They have the following different MMU indexes:
@@ -3117,6 +3127,10 @@ FIELD(TBFLAG_A32, NS, 10, 1)
  * This requires an SME trap from AArch32 mode when using NEON.
  */
 FIELD(TBFLAG_A32, SME_TRAP_NONSTREAMING, 11, 1)
+/*
+ * Indicates whether we are in the Secure PL1&0 translation regime
+ */
+FIELD(TBFLAG_A32, S_PL1_0, 12, 1)
 
 /*
  * Bit usage when in AArch32 state, for M-profile only.
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 8fb4b474e8..0a582c1cd3 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -3700,7 +3700,7 @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value,
          */
         format64 = arm_s1_regime_using_lpae_format(env, mmu_idx);
 
-        if (arm_feature(env, ARM_FEATURE_EL2)) {
+        if (arm_feature(env, ARM_FEATURE_EL2) && !arm_aa32_secure_pl1_0(env)) {
             if (mmu_idx == ARMMMUIdx_E10_0 ||
                 mmu_idx == ARMMMUIdx_E10_1 ||
                 mmu_idx == ARMMMUIdx_E10_1_PAN) {
@@ -3774,13 +3774,11 @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value)
     case 0:
         /* stage 1 current state PL1: ATS1CPR, ATS1CPW, ATS1CPRP, ATS1CPWP */
         switch (el) {
-        case 3:
-            mmu_idx = ARMMMUIdx_E3;
-            break;
         case 2:
             g_assert(ss != ARMSS_Secure);  /* ARMv8.4-SecEL2 is 64-bit only */
             /* fall through */
         case 1:
+        case 3:
             if (ri->crm == 9 && arm_pan_enabled(env)) {
                 mmu_idx = ARMMMUIdx_Stage1_E1_PAN;
             } else {
@@ -11861,8 +11859,11 @@ void arm_cpu_do_interrupt(CPUState *cs)
 
 uint64_t arm_sctlr(CPUARMState *env, int el)
 {
-    /* Only EL0 needs to be adjusted for EL1&0 or EL2&0. */
-    if (el == 0) {
+    if (arm_aa32_secure_pl1_0(env)) {
+        /* In Secure PL1&0 SCTLR_S is always controlling */
+        el = 3;
+    } else if (el == 0) {
+        /* Only EL0 needs to be adjusted for EL1&0 or EL2&0. */
         ARMMMUIdx mmu_idx = arm_mmu_idx_el(env, 0);
         el = mmu_idx == ARMMMUIdx_E20_0 ? 2 : 1;
     }
@@ -12522,8 +12523,12 @@ int fp_exception_el(CPUARMState *env, int cur_el)
     return 0;
 }
 
-/* Return the exception level we're running at if this is our mmu_idx */
-int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx)
+/*
+ * Return the exception level we're running at if this is our mmu_idx.
+ * s_pl1_0 should be true if this is the AArch32 Secure PL1&0 translation
+ * regime.
+ */
+int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx, bool s_pl1_0)
 {
     if (mmu_idx & ARM_MMU_IDX_M) {
         return mmu_idx & ARM_MMU_IDX_M_PRIV;
@@ -12535,7 +12540,7 @@ int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx)
         return 0;
     case ARMMMUIdx_E10_1:
     case ARMMMUIdx_E10_1_PAN:
-        return 1;
+        return s_pl1_0 ? 3 : 1;
     case ARMMMUIdx_E2:
     case ARMMMUIdx_E20_2:
     case ARMMMUIdx_E20_2_PAN:
@@ -12573,6 +12578,15 @@ ARMMMUIdx arm_mmu_idx_el(CPUARMState *env, int el)
             idx = ARMMMUIdx_E10_0;
         }
         break;
+    case 3:
+        /*
+         * AArch64 EL3 has its own translation regime; AArch32 EL3
+         * uses the Secure PL1&0 translation regime.
+         */
+        if (arm_el_is_aa64(env, 3)) {
+            return ARMMMUIdx_E3;
+        }
+        /* fall through */
     case 1:
         if (arm_pan_enabled(env)) {
             idx = ARMMMUIdx_E10_1_PAN;
@@ -12592,8 +12606,6 @@ ARMMMUIdx arm_mmu_idx_el(CPUARMState *env, int el)
             idx = ARMMMUIdx_E2;
         }
         break;
-    case 3:
-        return ARMMMUIdx_E3;
     default:
         g_assert_not_reached();
     }
diff --git a/target/arm/internals.h b/target/arm/internals.h
index 757b1fae92..203a2dae14 100644
--- a/target/arm/internals.h
+++ b/target/arm/internals.h
@@ -276,6 +276,20 @@ FIELD(CNTHCTL, CNTPMASK, 19, 1)
 #define M_FAKE_FSR_SFAULT 0xe /* SecureFault INVTRAN, INVEP or AUVIOL */
 
 /**
+ * arm_aa32_secure_pl1_0(): Return true if in Secure PL1&0 regime
+ *
+ * Return true if the CPU is in the Secure PL1&0 translation regime.
+ * This requires that EL3 exists and is AArch32 and we are currently
+ * Secure. If this is the case then the ARMMMUIdx_E10* apply and
+ * mean we are in EL3, not EL1.
+ */
+static inline bool arm_aa32_secure_pl1_0(CPUARMState *env)
+{
+    return arm_feature(env, ARM_FEATURE_EL3) &&
+        !arm_el_is_aa64(env, 3) && arm_is_secure(env);
+}
+
+/**
  * raise_exception: Raise the specified exception.
  * Raise a guest exception with the specified value, syndrome register
  * and target exception level. This should be called from helper functions,
@@ -808,7 +822,12 @@ static inline ARMMMUIdx core_to_aa64_mmu_idx(int mmu_idx)
     return mmu_idx | ARM_MMU_IDX_A;
 }
 
-int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx);
+/**
+ * Return the exception level we're running at if our current MMU index
+ * is @mmu_idx. @s_pl1_0 should be true if this is the AArch32
+ * Secure PL1&0 translation regime.
+ */
+int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx, bool s_pl1_0);
 
 /* Return the MMU index for a v7M CPU in the specified security state */
 ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate);
@@ -903,11 +922,11 @@ static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx)
         return 3;
     case ARMMMUIdx_E10_0:
     case ARMMMUIdx_Stage1_E0:
-        return arm_el_is_aa64(env, 3) || !arm_is_secure_below_el3(env) ? 1 : 3;
-    case ARMMMUIdx_Stage1_E1:
-    case ARMMMUIdx_Stage1_E1_PAN:
     case ARMMMUIdx_E10_1:
     case ARMMMUIdx_E10_1_PAN:
+    case ARMMMUIdx_Stage1_E1:
+    case ARMMMUIdx_Stage1_E1_PAN:
+        return arm_el_is_aa64(env, 3) || !arm_is_secure_below_el3(env) ? 1 : 3;
     case ARMMMUIdx_MPrivNegPri:
     case ARMMMUIdx_MUserNegPri:
     case ARMMMUIdx_MPriv:
diff --git a/target/arm/ptw.c b/target/arm/ptw.c
index 4476b32ff5..278004661b 100644
--- a/target/arm/ptw.c
+++ b/target/arm/ptw.c
@@ -3576,7 +3576,11 @@ bool get_phys_addr(CPUARMState *env, target_ulong address,
     case ARMMMUIdx_Stage1_E1:
     case ARMMMUIdx_Stage1_E1_PAN:
     case ARMMMUIdx_E2:
-        ss = arm_security_space_below_el3(env);
+        if (arm_aa32_secure_pl1_0(env)) {
+            ss = ARMSS_Secure;
+        } else {
+            ss = arm_security_space_below_el3(env);
+        }
         break;
     case ARMMMUIdx_Stage2:
         /*
diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c
index f03977b4b0..bab7822ef6 100644
--- a/target/arm/tcg/hflags.c
+++ b/target/arm/tcg/hflags.c
@@ -198,6 +198,10 @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el,
         DP_TBFLAG_A32(flags, SME_TRAP_NONSTREAMING, 1);
     }
 
+    if (arm_aa32_secure_pl1_0(env)) {
+        DP_TBFLAG_A32(flags, S_PL1_0, 1);
+    }
+
     return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags);
 }
 
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 28a1013503..4684e7eb6e 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -10756,6 +10756,7 @@ static void handle_vec_simd_wshli(DisasContext *s, bool is_q, bool is_u,
         tcg_gen_shli_i64(tcg_rd, tcg_rd, shift);
         write_vec_element(s, tcg_rd, rd, i, size + 1);
     }
+    clear_vec_high(s, true, rd);
 }
 
 /* SHRN/RSHRN - Shift right with narrowing (and potential rounding) */
@@ -11978,7 +11979,7 @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase,
     dc->tbii = EX_TBFLAG_A64(tb_flags, TBII);
     dc->tbid = EX_TBFLAG_A64(tb_flags, TBID);
     dc->tcma = EX_TBFLAG_A64(tb_flags, TCMA);
-    dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx);
+    dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx, false);
 #if !defined(CONFIG_USER_ONLY)
     dc->user = (dc->current_el == 0);
 #endif
diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c
index c5bc691d92..e2748ff2bb 100644
--- a/target/arm/tcg/translate.c
+++ b/target/arm/tcg/translate.c
@@ -7546,10 +7546,6 @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
 
     core_mmu_idx = EX_TBFLAG_ANY(tb_flags, MMUIDX);
     dc->mmu_idx = core_to_arm_mmu_idx(env, core_mmu_idx);
-    dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx);
-#if !defined(CONFIG_USER_ONLY)
-    dc->user = (dc->current_el == 0);
-#endif
     dc->fp_excp_el = EX_TBFLAG_ANY(tb_flags, FPEXC_EL);
     dc->align_mem = EX_TBFLAG_ANY(tb_flags, ALIGN_MEM);
     dc->pstate_il = EX_TBFLAG_ANY(tb_flags, PSTATE__IL);
@@ -7580,7 +7576,12 @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
         }
         dc->sme_trap_nonstreaming =
             EX_TBFLAG_A32(tb_flags, SME_TRAP_NONSTREAMING);
+        dc->s_pl1_0 = EX_TBFLAG_A32(tb_flags, S_PL1_0);
     }
+    dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx, dc->s_pl1_0);
+#if !defined(CONFIG_USER_ONLY)
+    dc->user = (dc->current_el == 0);
+#endif
     dc->lse2 = false; /* applies only to aarch64 */
     dc->cp_regs = cpu->cp_regs;
     dc->features = env->features;
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index 01c217f4a4..3f0e9ceaa3 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -165,6 +165,8 @@ typedef struct DisasContext {
     uint8_t gm_blocksize;
     /* True if the current insn_start has been updated. */
     bool insn_start_updated;
+    /* True if this is the AArch32 Secure PL1&0 translation regime */
+    bool s_pl1_0;
     /* Bottom two bits of XScale c15_cpar coprocessor access control reg */
     int c15_cpar;
     /* Offset from VNCR_EL2 when FEAT_NV2 redirects this reg to memory */