Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-2…

…0191220' into staging

target-arm queue:
 * Support emulating the generic timers at frequencies other than 62.5MHz
 * Various fixes for SMMUv3 emulation bugs
 * Improve assert error message for hflags mismatches
 * arm-powerctl: rebuild hflags after setting CP15 bits in arm_set_cpu_on()

# gpg: Signature made Fri 20 Dec 2019 14:25:51 GMT
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [ultimate]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [ultimate]
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20191220:
  arm/arm-powerctl: rebuild hflags after setting CP15 bits in arm_set_cpu_on()
  target/arm: Display helpful message when hflags mismatch
  hw/arm/smmuv3: Report F_STE_FETCH fault address in correct word position
  hw/arm/smmuv3: Use correct bit positions in EVT_SET_ADDR2 macro
  hw/arm/smmuv3: Align stream table base address to table size
  hw/arm/smmuv3: Check stream IDs against actual table LOG2SIZE
  hw/arm/smmuv3: Correct SMMU_BASE_ADDR_MASK value
  hw/arm/smmuv3: Apply address mask to linear strtab base address
  ast2600: Configure CNTFRQ at 1125MHz
  target/arm: Prepare generic timer for per-platform CNTFRQ
  target/arm: Abstract the generic timer frequency
  target/arm: Remove redundant scaling of nexttick

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

hw/arm/aspeed_ast2600.c

@@ -250,6 +250,9 @@ static void aspeed_soc_ast2600_realize(DeviceState *dev, Error **errp)
         object_property_set_int(OBJECT(&s->cpu[i]), aspeed_calc_affinity(i),
                                 "mp-affinity", &error_abort);
 
+        object_property_set_int(OBJECT(&s->cpu[i]), 1125000000, "cntfrq",
+                                &error_abort);
+
         /*
          * TODO: the secondary CPUs are started and a boot helper
          * is needed when using -kernel

hw/arm/smmuv3-internal.h

@@ -99,7 +99,7 @@ REG32(GERROR_IRQ_CFG2, 0x74)
 
 #define A_STRTAB_BASE      0x80 /* 64b */
 
-#define SMMU_BASE_ADDR_MASK 0xffffffffffe0
+#define SMMU_BASE_ADDR_MASK 0xfffffffffffc0
 
 REG32(STRTAB_BASE_CFG,     0x88)
     FIELD(STRTAB_BASE_CFG, FMT,      16, 2)
@@ -461,8 +461,8 @@ typedef struct SMMUEventInfo {
     } while (0)
 #define EVT_SET_ADDR2(x, addr)                            \
     do {                                                  \
-            (x)->word[7] = deposit32((x)->word[7], 3, 29, addr >> 16);   \
-            (x)->word[7] = deposit32((x)->word[7], 0, 16, addr & 0xffff);\
+            (x)->word[7] = (uint32_t)(addr >> 32);        \
+            (x)->word[6] = (uint32_t)(addr & 0xffffffff); \
     } while (0)
 
 void smmuv3_record_event(SMMUv3State *s, SMMUEventInfo *event);

hw/arm/smmuv3.c

@@ -172,7 +172,7 @@ void smmuv3_record_event(SMMUv3State *s, SMMUEventInfo *info)
     case SMMU_EVT_F_STE_FETCH:
         EVT_SET_SSID(&evt, info->u.f_ste_fetch.ssid);
         EVT_SET_SSV(&evt,  info->u.f_ste_fetch.ssv);
-        EVT_SET_ADDR(&evt, info->u.f_ste_fetch.addr);
+        EVT_SET_ADDR2(&evt, info->u.f_ste_fetch.addr);
         break;
     case SMMU_EVT_C_BAD_STE:
         EVT_SET_SSID(&evt, info->u.c_bad_ste.ssid);
@@ -376,21 +376,32 @@ static int decode_ste(SMMUv3State *s, SMMUTransCfg *cfg,
 static int smmu_find_ste(SMMUv3State *s, uint32_t sid, STE *ste,
                          SMMUEventInfo *event)
 {
-    dma_addr_t addr;
+    dma_addr_t addr, strtab_base;
+    uint32_t log2size;
+    int strtab_size_shift;
     int ret;
 
     trace_smmuv3_find_ste(sid, s->features, s->sid_split);
-    /* Check SID range */
-    if (sid > (1 << SMMU_IDR1_SIDSIZE)) {
+    log2size = FIELD_EX32(s->strtab_base_cfg, STRTAB_BASE_CFG, LOG2SIZE);
+    /*
+     * Check SID range against both guest-configured and implementation limits
+     */
+    if (sid >= (1 << MIN(log2size, SMMU_IDR1_SIDSIZE))) {
         event->type = SMMU_EVT_C_BAD_STREAMID;
         return -EINVAL;
     }
     if (s->features & SMMU_FEATURE_2LVL_STE) {
         int l1_ste_offset, l2_ste_offset, max_l2_ste, span;
-        dma_addr_t strtab_base, l1ptr, l2ptr;
+        dma_addr_t l1ptr, l2ptr;
         STEDesc l1std;
 
-        strtab_base = s->strtab_base & SMMU_BASE_ADDR_MASK;
+        /*
+         * Align strtab base address to table size. For this purpose, assume it
+         * is not bounded by SMMU_IDR1_SIDSIZE.
+         */
+        strtab_size_shift = MAX(5, (int)log2size - s->sid_split - 1 + 3);
+        strtab_base = s->strtab_base & SMMU_BASE_ADDR_MASK &
+                      ~MAKE_64BIT_MASK(0, strtab_size_shift);
         l1_ste_offset = sid >> s->sid_split;
         l2_ste_offset = sid & ((1 << s->sid_split) - 1);
         l1ptr = (dma_addr_t)(strtab_base + l1_ste_offset * sizeof(l1std));
@@ -429,7 +440,10 @@ static int smmu_find_ste(SMMUv3State *s, uint32_t sid, STE *ste,
         }
         addr = l2ptr + l2_ste_offset * sizeof(*ste);
     } else {
-        addr = s->strtab_base + sid * sizeof(*ste);
+        strtab_size_shift = log2size + 5;
+        strtab_base = s->strtab_base & SMMU_BASE_ADDR_MASK &
+                      ~MAKE_64BIT_MASK(0, strtab_size_shift);
+        addr = strtab_base + sid * sizeof(*ste);
     }
 
     if (smmu_get_ste(s, addr, ste, event)) {

target/arm/arm-powerctl.c

@@ -127,6 +127,9 @@ static void arm_set_cpu_on_async_work(CPUState *target_cpu_state,
         target_cpu->env.regs[0] = info->context_id;
     }
 
+    /* CP15 update requires rebuilding hflags */
+    arm_rebuild_hflags(&target_cpu->env);
+
     /* Start the new CPU at the requested address */
     cpu_set_pc(target_cpu_state, info->entry);
 

target/arm/cpu.c

@@ -976,6 +976,10 @@ static void arm_cpu_initfn(Object *obj)
     }
 }
 
+static Property arm_cpu_gt_cntfrq_property =
+            DEFINE_PROP_UINT64("cntfrq", ARMCPU, gt_cntfrq_hz,
+                               NANOSECONDS_PER_SECOND / GTIMER_SCALE);
+
 static Property arm_cpu_reset_cbar_property =
             DEFINE_PROP_UINT64("reset-cbar", ARMCPU, reset_cbar, 0);
 
@@ -1055,6 +1059,30 @@ static void arm_set_init_svtor(Object *obj, Visitor *v, const char *name,
     visit_type_uint32(v, name, &cpu->init_svtor, errp);
 }
 
+unsigned int gt_cntfrq_period_ns(ARMCPU *cpu)
+{
+    /*
+     * The exact approach to calculating guest ticks is:
+     *
+     *     muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), cpu->gt_cntfrq_hz,
+     *              NANOSECONDS_PER_SECOND);
+     *
+     * We don't do that. Rather we intentionally use integer division
+     * truncation below and in the caller for the conversion of host monotonic
+     * time to guest ticks to provide the exact inverse for the semantics of
+     * the QEMUTimer scale factor. QEMUTimer's scale facter is an integer, so
+     * it loses precision when representing frequencies where
+     * `(NANOSECONDS_PER_SECOND % cpu->gt_cntfrq) > 0` holds. Failing to
+     * provide an exact inverse leads to scheduling timers with negative
+     * periods, which in turn leads to sticky behaviour in the guest.
+     *
+     * Finally, CNTFRQ is effectively capped at 1GHz to ensure our scale factor
+     * cannot become zero.
+     */
+    return NANOSECONDS_PER_SECOND > cpu->gt_cntfrq_hz ?
+      NANOSECONDS_PER_SECOND / cpu->gt_cntfrq_hz : 1;
+}
+
 void arm_cpu_post_init(Object *obj)
 {
     ARMCPU *cpu = ARM_CPU(obj);
@@ -1172,6 +1200,11 @@ void arm_cpu_post_init(Object *obj)
 
     qdev_property_add_static(DEVICE(obj), &arm_cpu_cfgend_property,
                              &error_abort);
+
+    if (arm_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER)) {
+        qdev_property_add_static(DEVICE(cpu), &arm_cpu_gt_cntfrq_property,
+                                 &error_abort);
+    }
 }
 
 static void arm_cpu_finalizefn(Object *obj)
@@ -1251,14 +1284,30 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp)
         }
     }
 
-    cpu->gt_timer[GTIMER_PHYS] = timer_new(QEMU_CLOCK_VIRTUAL, GTIMER_SCALE,
-                                           arm_gt_ptimer_cb, cpu);
-    cpu->gt_timer[GTIMER_VIRT] = timer_new(QEMU_CLOCK_VIRTUAL, GTIMER_SCALE,
-                                           arm_gt_vtimer_cb, cpu);
-    cpu->gt_timer[GTIMER_HYP] = timer_new(QEMU_CLOCK_VIRTUAL, GTIMER_SCALE,
-                                          arm_gt_htimer_cb, cpu);
-    cpu->gt_timer[GTIMER_SEC] = timer_new(QEMU_CLOCK_VIRTUAL, GTIMER_SCALE,
-                                          arm_gt_stimer_cb, cpu);
+
+    {
+        uint64_t scale;
+
+        if (arm_feature(env, ARM_FEATURE_GENERIC_TIMER)) {
+            if (!cpu->gt_cntfrq_hz) {
+                error_setg(errp, "Invalid CNTFRQ: %"PRId64"Hz",
+                           cpu->gt_cntfrq_hz);
+                return;
+            }
+            scale = gt_cntfrq_period_ns(cpu);
+        } else {
+            scale = GTIMER_SCALE;
+        }
+
+        cpu->gt_timer[GTIMER_PHYS] = timer_new(QEMU_CLOCK_VIRTUAL, scale,
+                                               arm_gt_ptimer_cb, cpu);
+        cpu->gt_timer[GTIMER_VIRT] = timer_new(QEMU_CLOCK_VIRTUAL, scale,
+                                               arm_gt_vtimer_cb, cpu);
+        cpu->gt_timer[GTIMER_HYP] = timer_new(QEMU_CLOCK_VIRTUAL, scale,
+                                              arm_gt_htimer_cb, cpu);
+        cpu->gt_timer[GTIMER_SEC] = timer_new(QEMU_CLOCK_VIRTUAL, scale,
+                                              arm_gt_stimer_cb, cpu);
+    }
 #endif
 
     cpu_exec_realizefn(cs, &local_err);

target/arm/cpu.h

@@ -932,8 +932,13 @@ struct ARMCPU {
      */
     DECLARE_BITMAP(sve_vq_map, ARM_MAX_VQ);
     DECLARE_BITMAP(sve_vq_init, ARM_MAX_VQ);
+
+    /* Generic timer counter frequency, in Hz */
+    uint64_t gt_cntfrq_hz;
 };
 
+unsigned int gt_cntfrq_period_ns(ARMCPU *cpu);
+
 void arm_cpu_post_init(Object *obj);
 
 uint64_t arm_cpu_mp_affinity(int idx, uint8_t clustersz);

target/arm/helper.c

@@ -2449,7 +2449,9 @@ static CPAccessResult gt_stimer_access(CPUARMState *env,
 
 static uint64_t gt_get_countervalue(CPUARMState *env)
 {
-    return qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) / GTIMER_SCALE;
+    ARMCPU *cpu = env_archcpu(env);
+
+    return qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) / gt_cntfrq_period_ns(cpu);
 }
 
 static void gt_recalc_timer(ARMCPU *cpu, int timeridx)
@@ -2485,10 +2487,11 @@ static void gt_recalc_timer(ARMCPU *cpu, int timeridx)
          * set the timer for as far in the future as possible. When the
          * timer expires we will reset the timer for any remaining period.
          */
-        if (nexttick > INT64_MAX / GTIMER_SCALE) {
-            nexttick = INT64_MAX / GTIMER_SCALE;
+        if (nexttick > INT64_MAX / gt_cntfrq_period_ns(cpu)) {
+            timer_mod_ns(cpu->gt_timer[timeridx], INT64_MAX);
+        } else {
+            timer_mod(cpu->gt_timer[timeridx], nexttick);
         }
-        timer_mod(cpu->gt_timer[timeridx], nexttick);
         trace_arm_gt_recalc(timeridx, irqstate, nexttick);
     } else {
         /* Timer disabled: ISTATUS and timer output always clear */
@@ -2720,6 +2723,13 @@ void arm_gt_stimer_cb(void *opaque)
     gt_recalc_timer(cpu, GTIMER_SEC);
 }
 
+static void arm_gt_cntfrq_reset(CPUARMState *env, const ARMCPRegInfo *opaque)
+{
+    ARMCPU *cpu = env_archcpu(env);
+
+    cpu->env.cp15.c14_cntfrq = cpu->gt_cntfrq_hz;
+}
+
 static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
     /* Note that CNTFRQ is purely reads-as-written for the benefit
      * of software; writing it doesn't actually change the timer frequency.
@@ -2734,7 +2744,7 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
       .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 0, .opc2 = 0,
       .access = PL1_RW | PL0_R, .accessfn = gt_cntfrq_access,
       .fieldoffset = offsetof(CPUARMState, cp15.c14_cntfrq),
-      .resetvalue = (1000 * 1000 * 1000) / GTIMER_SCALE,
+      .resetfn = arm_gt_cntfrq_reset,
     },
     /* overall control: mostly access permissions */
     { .name = "CNTKCTL", .state = ARM_CP_STATE_BOTH,
@@ -2913,11 +2923,13 @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
 
 static uint64_t gt_virt_cnt_read(CPUARMState *env, const ARMCPRegInfo *ri)
 {
+    ARMCPU *cpu = env_archcpu(env);
+
     /* Currently we have no support for QEMUTimer in linux-user so we
      * can't call gt_get_countervalue(env), instead we directly
      * call the lower level functions.
      */
-    return cpu_get_clock() / GTIMER_SCALE;
+    return cpu_get_clock() / gt_cntfrq_period_ns(cpu);
 }
 
 static const ARMCPRegInfo generic_timer_cp_reginfo[] = {
@@ -11500,16 +11512,28 @@ void HELPER(rebuild_hflags_a64)(CPUARMState *env, int el)
     env->hflags = rebuild_hflags_a64(env, el, fp_el, mmu_idx);
 }
 
+static inline void assert_hflags_rebuild_correctly(CPUARMState *env)
+{
+#ifdef CONFIG_DEBUG_TCG
+    uint32_t env_flags_current = env->hflags;
+    uint32_t env_flags_rebuilt = rebuild_hflags_internal(env);
+
+    if (unlikely(env_flags_current != env_flags_rebuilt)) {
+        fprintf(stderr, "TCG hflags mismatch (current:0x%08x rebuilt:0x%08x)\n",
+                env_flags_current, env_flags_rebuilt);
+        abort();
+    }
+#endif
+}
+
 void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc,
                           target_ulong *cs_base, uint32_t *pflags)
 {
     uint32_t flags = env->hflags;
     uint32_t pstate_for_ss;
 
     *cs_base = 0;
-#ifdef CONFIG_DEBUG_TCG
-    assert(flags == rebuild_hflags_internal(env));
-#endif
+    assert_hflags_rebuild_correctly(env);
 
     if (FIELD_EX32(flags, TBFLAG_ANY, AARCH64_STATE)) {
         *pc = env->pc;