target/arm: Make number of counters in PMCR follow the CPU

Currently we give all the v7-and-up CPUs a PMU with 4 counters.  This
means that we don't provide the 6 counters that are required by the
Arm BSA (Base System Architecture) specification if the CPU supports
the Virtualization extensions.

Instead of having a single PMCR_NUM_COUNTERS, make each CPU type
specify the PMCR reset value (obtained from the appropriate TRM), and
use the 'N' field of that value to define the number of counters
provided.

This means that we now supply 6 counters instead of 4 for:
 Cortex-A9, Cortex-A15, Cortex-A53, Cortex-A57, Cortex-A72,
 Cortex-A76, Neoverse-N1, '-cpu max'
This CPU goes from 4 to 8 counters:
 A64FX
These CPUs remain with 4 counters:
 Cortex-A7, Cortex-A8
This CPU goes down from 4 to 3 counters:
 Cortex-R5

Note that because we now use the PMCR reset value of the specific
implementation, we no longer set the LC bit out of reset.  This has
an UNKNOWN value out of reset for all cores with any AArch32 support,
so guest software should be setting it anyway if it wants it.

This change was originally landed in commit f7fb73b (during
the 6.0 release cycle) but was then reverted by commit
21c2dd7 before that release because it did not work with KVM.
This version fixes that by creating the scratch vCPU in
kvm_arm_get_host_cpu_features() with the KVM_ARM_VCPU_PMU_V3 feature
if KVM supports it, and then only asking KVM for the PMCR_EL0 value
if the vCPU has a PMU.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
[PMM: Added the correct value for a64fx]
Message-id: 20220513122852.4063586-1-peter.maydell@linaro.org

target/arm/cpu.h

@@ -965,6 +965,7 @@ struct ArchCPU {
         uint64_t id_aa64dfr0;
         uint64_t id_aa64dfr1;
         uint64_t id_aa64zfr0;
+        uint64_t reset_pmcr_el0;
     } isar;
     uint64_t midr;
     uint32_t revidr;

target/arm/cpu64.c

@@ -79,6 +79,7 @@ static void aarch64_a57_initfn(Object *obj)
     cpu->isar.id_aa64isar0 = 0x00011120;
     cpu->isar.id_aa64mmfr0 = 0x00001124;
     cpu->isar.dbgdidr = 0x3516d000;
+    cpu->isar.reset_pmcr_el0 = 0x41013000;
     cpu->clidr = 0x0a200023;
     cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */
     cpu->ccsidr[1] = 0x201fe012; /* 48KB L1 icache */
@@ -133,6 +134,7 @@ static void aarch64_a53_initfn(Object *obj)
     cpu->isar.id_aa64isar0 = 0x00011120;
     cpu->isar.id_aa64mmfr0 = 0x00001122; /* 40 bit physical addr */
     cpu->isar.dbgdidr = 0x3516d000;
+    cpu->isar.reset_pmcr_el0 = 0x41033000;
     cpu->clidr = 0x0a200023;
     cpu->ccsidr[0] = 0x700fe01a; /* 32KB L1 dcache */
     cpu->ccsidr[1] = 0x201fe00a; /* 32KB L1 icache */
@@ -185,6 +187,7 @@ static void aarch64_a72_initfn(Object *obj)
     cpu->isar.id_aa64isar0 = 0x00011120;
     cpu->isar.id_aa64mmfr0 = 0x00001124;
     cpu->isar.dbgdidr = 0x3516d000;
+    cpu->isar.reset_pmcr_el0 = 0x41023000;
     cpu->clidr = 0x0a200023;
     cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */
     cpu->ccsidr[1] = 0x201fe012; /* 48KB L1 icache */
@@ -261,6 +264,9 @@ static void aarch64_a76_initfn(Object *obj)
     cpu->isar.mvfr0 = 0x10110222;
     cpu->isar.mvfr1 = 0x13211111;
     cpu->isar.mvfr2 = 0x00000043;
+
+    /* From D5.1 AArch64 PMU register summary */
+    cpu->isar.reset_pmcr_el0 = 0x410b3000;
 }
 
 static void aarch64_neoverse_n1_initfn(Object *obj)
@@ -327,6 +333,9 @@ static void aarch64_neoverse_n1_initfn(Object *obj)
     cpu->isar.mvfr0 = 0x10110222;
     cpu->isar.mvfr1 = 0x13211111;
     cpu->isar.mvfr2 = 0x00000043;
+
+    /* From D5.1 AArch64 PMU register summary */
+    cpu->isar.reset_pmcr_el0 = 0x410c3000;
 }
 
 void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
@@ -1022,6 +1031,8 @@ static void aarch64_a64fx_initfn(Object *obj)
     set_bit(1, cpu->sve_vq_supported); /* 256bit */
     set_bit(3, cpu->sve_vq_supported); /* 512bit */
 
+    cpu->isar.reset_pmcr_el0 = 0x46014040;
+
     /* TODO:  Add A64FX specific HPC extension registers */
 }
 

target/arm/cpu_tcg.c

@@ -425,6 +425,7 @@ static void cortex_a8_initfn(Object *obj)
     cpu->ccsidr[1] = 0x2007e01a; /* 16k L1 icache. */
     cpu->ccsidr[2] = 0xf0000000; /* No L2 icache. */
     cpu->reset_auxcr = 2;
+    cpu->isar.reset_pmcr_el0 = 0x41002000;
     define_arm_cp_regs(cpu, cortexa8_cp_reginfo);
 }
 
@@ -496,6 +497,7 @@ static void cortex_a9_initfn(Object *obj)
     cpu->clidr = (1 << 27) | (1 << 24) | 3;
     cpu->ccsidr[0] = 0xe00fe019; /* 16k L1 dcache. */
     cpu->ccsidr[1] = 0x200fe019; /* 16k L1 icache. */
+    cpu->isar.reset_pmcr_el0 = 0x41093000;
     define_arm_cp_regs(cpu, cortexa9_cp_reginfo);
 }
 
@@ -565,6 +567,7 @@ static void cortex_a7_initfn(Object *obj)
     cpu->ccsidr[0] = 0x701fe00a; /* 32K L1 dcache */
     cpu->ccsidr[1] = 0x201fe00a; /* 32K L1 icache */
     cpu->ccsidr[2] = 0x711fe07a; /* 4096K L2 unified cache */
+    cpu->isar.reset_pmcr_el0 = 0x41072000;
     define_arm_cp_regs(cpu, cortexa15_cp_reginfo); /* Same as A15 */
 }
 
@@ -607,6 +610,7 @@ static void cortex_a15_initfn(Object *obj)
     cpu->ccsidr[0] = 0x701fe00a; /* 32K L1 dcache */
     cpu->ccsidr[1] = 0x201fe00a; /* 32K L1 icache */
     cpu->ccsidr[2] = 0x711fe07a; /* 4096K L2 unified cache */
+    cpu->isar.reset_pmcr_el0 = 0x410F3000;
     define_arm_cp_regs(cpu, cortexa15_cp_reginfo);
 }
 
@@ -835,6 +839,7 @@ static void cortex_r5_initfn(Object *obj)
     cpu->isar.id_isar6 = 0x0;
     cpu->mp_is_up = true;
     cpu->pmsav7_dregion = 16;
+    cpu->isar.reset_pmcr_el0 = 0x41151800;
     define_arm_cp_regs(cpu, cortexr5_cp_reginfo);
 }
 
@@ -1093,6 +1098,7 @@ static void arm_max_initfn(Object *obj)
     cpu->isar.id_isar5 = 0x00011121;
     cpu->isar.id_isar6 = 0;
     cpu->isar.dbgdidr = 0x3516d000;
+    cpu->isar.reset_pmcr_el0 = 0x41013000;
     cpu->clidr = 0x0a200023;
     cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */
     cpu->ccsidr[1] = 0x201fe012; /* 48KB L1 icache */

target/arm/helper.c

@@ -39,7 +39,6 @@
 #include "cpregs.h"
 
 #define ARM_CPU_FREQ 1000000000 /* FIXME: 1 GHz, should be configurable */
-#define PMCR_NUM_COUNTERS 4 /* QEMU IMPDEF choice */
 
 #ifndef CONFIG_USER_ONLY
 
@@ -5544,13 +5543,6 @@ static const ARMCPRegInfo el2_cp_reginfo[] = {
       .resetvalue = 0,
       .writefn = gt_hyp_ctl_write, .raw_writefn = raw_write },
 #endif
-    /* The only field of MDCR_EL2 that has a defined architectural reset value
-     * is MDCR_EL2.HPMN which should reset to the value of PMCR_EL0.N.
-     */
-    { .name = "MDCR_EL2", .state = ARM_CP_STATE_BOTH,
-      .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 1,
-      .access = PL2_RW, .resetvalue = PMCR_NUM_COUNTERS,
-      .fieldoffset = offsetof(CPUARMState, cp15.mdcr_el2), },
     { .name = "HPFAR", .state = ARM_CP_STATE_AA32,
       .cp = 15, .opc1 = 4, .crn = 6, .crm = 0, .opc2 = 4,
       .access = PL2_RW, .accessfn = access_el3_aa32ns,
@@ -6604,7 +6596,7 @@ static void define_pmu_regs(ARMCPU *cpu)
      * field as main ID register, and we implement four counters in
      * addition to the cycle count register.
      */
-    unsigned int i, pmcrn = PMCR_NUM_COUNTERS;
+    unsigned int i, pmcrn = pmu_num_counters(&cpu->env);
     ARMCPRegInfo pmcr = {
         .name = "PMCR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 0,
         .access = PL0_RW,
@@ -6619,10 +6611,10 @@ static void define_pmu_regs(ARMCPU *cpu)
         .access = PL0_RW, .accessfn = pmreg_access,
         .type = ARM_CP_IO,
         .fieldoffset = offsetof(CPUARMState, cp15.c9_pmcr),
-        .resetvalue = (cpu->midr & 0xff000000) | (pmcrn << PMCRN_SHIFT) |
-                      PMCRLC,
+        .resetvalue = cpu->isar.reset_pmcr_el0,
         .writefn = pmcr_write, .raw_writefn = raw_write,
     };
+
     define_one_arm_cp_reg(cpu, &pmcr);
     define_one_arm_cp_reg(cpu, &pmcr64);
     for (i = 0; i < pmcrn; i++) {
@@ -7979,6 +7971,17 @@ void register_cp_regs_for_features(ARMCPU *cpu)
               .type = ARM_CP_EL3_NO_EL2_C_NZ,
               .fieldoffset = offsetof(CPUARMState, cp15.vmpidr_el2) },
         };
+        /*
+         * The only field of MDCR_EL2 that has a defined architectural reset
+         * value is MDCR_EL2.HPMN which should reset to the value of PMCR_EL0.N.
+         */
+        ARMCPRegInfo mdcr_el2 = {
+            .name = "MDCR_EL2", .state = ARM_CP_STATE_BOTH,
+            .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 1,
+            .access = PL2_RW, .resetvalue = pmu_num_counters(env),
+            .fieldoffset = offsetof(CPUARMState, cp15.mdcr_el2),
+        };
+        define_one_arm_cp_reg(cpu, &mdcr_el2);
         define_arm_cp_regs(cpu, vpidr_regs);
         define_arm_cp_regs(cpu, el2_cp_reginfo);
         if (arm_feature(env, ARM_FEATURE_V8)) {

target/arm/internals.h

@@ -1304,7 +1304,9 @@ enum MVEECIState {
 
 static inline uint32_t pmu_num_counters(CPUARMState *env)
 {
-  return (env->cp15.c9_pmcr & PMCRN_MASK) >> PMCRN_SHIFT;
+    ARMCPU *cpu = env_archcpu(env);
+
+    return (cpu->isar.reset_pmcr_el0 & PMCRN_MASK) >> PMCRN_SHIFT;
 }
 
 /* Bits allowed to be set/cleared for PMCNTEN* and PMINTEN* */

target/arm/kvm64.c

@@ -505,6 +505,7 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
      */
     int fdarray[3];
     bool sve_supported;
+    bool pmu_supported = false;
     uint64_t features = 0;
     uint64_t t;
     int err;
@@ -537,6 +538,11 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
                              1 << KVM_ARM_VCPU_PTRAUTH_GENERIC);
     }
 
+    if (kvm_arm_pmu_supported()) {
+        init.features[0] |= 1 << KVM_ARM_VCPU_PMU_V3;
+        pmu_supported = true;
+    }
+
     if (!kvm_arm_create_scratch_host_vcpu(cpus_to_try, fdarray, &init)) {
         return false;
     }
@@ -659,6 +665,12 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
             dbgdidr |= (1 << 15); /* RES1 bit */
             ahcf->isar.dbgdidr = dbgdidr;
         }
+
+        if (pmu_supported) {
+            /* PMCR_EL0 is only accessible if the vCPU has feature PMU_V3 */
+            err |= read_sys_reg64(fdarray[2], &ahcf->isar.reset_pmcr_el0,
+                                  ARM64_SYS_REG(3, 3, 9, 12, 0));
+        }
     }
 
     sve_supported = ioctl(fdarray[0], KVM_CHECK_EXTENSION, KVM_CAP_ARM_SVE) > 0;