Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20140310' into staging

target-arm queue:
 * implement WFE as yield (improves performance with emulated SMP)
 * fixes to avoid undefined behaviour shifting left into sign bit
 * libvixl format string fixes for 32 bit hosts
 * fix build error when intptr_t and tcg_target_long are different
   sizes (eg x32)
 * implement PMCCNTR register
 * fix incorrect setting of E bit in CPSR (broke booting under
   KVM on ARM)

# gpg: Signature made Mon 10 Mar 2014 15:05:25 GMT using RSA key ID 14360CDE
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>"

* remotes/pmaydell/tags/pull-target-arm-20140310:
  target-arm: Implement WFE as a yield operation
  hw/arm/musicpal: Avoid shifting left into sign bit
  hw/ssi/xilinx_spips.c: Avoid shifting left into sign bit
  hw/arm/omap1.c: Avoid shifting left into sign bit
  pxa2xx: Don't shift into sign bit
  libvixl: Fix format strings for several int64_t values
  target-arm: Fix intptr_t vs tcg_target_long
  target-arm: Implements the ARM PMCCNTR register
  target-arm: Fix incorrect setting of E bit in CPSR

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

15 files changed, 144 insertions, 36 deletions

diff --git a/disas/libvixl/a64/disasm-a64.cc b/disas/libvixl/a64/disasm-a64.cc
index 5c6b898ea6..5f172da7d3 100644
--- a/disas/libvixl/a64/disasm-a64.cc
+++ b/disas/libvixl/a64/disasm-a64.cc
@@ -1342,7 +1342,7 @@ int Disassembler::SubstituteImmediateField(Instruction* instr,
         ASSERT(format[5] == 'L');
         AppendToOutput("#0x%" PRIx64, instr->ImmMoveWide());
         if (instr->ShiftMoveWide() > 0) {
-          AppendToOutput(", lsl #%d", 16 * instr->ShiftMoveWide());
+          AppendToOutput(", lsl #%" PRId64, 16 * instr->ShiftMoveWide());
         }
       }
       return 8;
@@ -1391,7 +1391,7 @@ int Disassembler::SubstituteImmediateField(Instruction* instr,
     }
     case 'F': {  // IFPSingle, IFPDouble or IFPFBits.
       if (format[3] == 'F') {  // IFPFbits.
-        AppendToOutput("#%d", 64 - instr->FPScale());
+        AppendToOutput("#%" PRId64, 64 - instr->FPScale());
         return 8;
       } else {
         AppendToOutput("#0x%" PRIx64 " (%.4f)", instr->ImmFP(),
@@ -1412,23 +1412,23 @@ int Disassembler::SubstituteImmediateField(Instruction* instr,
       return 5;
     }
     case 'P': {  // IP - Conditional compare.
-      AppendToOutput("#%d", instr->ImmCondCmp());
+      AppendToOutput("#%" PRId64, instr->ImmCondCmp());
       return 2;
     }
     case 'B': {  // Bitfields.
       return SubstituteBitfieldImmediateField(instr, format);
     }
     case 'E': {  // IExtract.
-      AppendToOutput("#%d", instr->ImmS());
+      AppendToOutput("#%" PRId64, instr->ImmS());
       return 8;
     }
     case 'S': {  // IS - Test and branch bit.
-      AppendToOutput("#%d", (instr->ImmTestBranchBit5() << 5) |
-                            instr->ImmTestBranchBit40());
+      AppendToOutput("#%" PRId64, (instr->ImmTestBranchBit5() << 5) |
+                                  instr->ImmTestBranchBit40());
       return 2;
     }
     case 'D': {  // IDebug - HLT and BRK instructions.
-      AppendToOutput("#0x%x", instr->ImmException());
+      AppendToOutput("#0x%" PRIx64, instr->ImmException());
       return 6;
     }
     default: {
@@ -1598,12 +1598,12 @@ int Disassembler::SubstituteExtendField(Instruction* instr,
       (((instr->ExtendMode() == UXTW) && (instr->SixtyFourBits() == 0)) ||
        (instr->ExtendMode() == UXTX))) {
     if (instr->ImmExtendShift() > 0) {
-      AppendToOutput(", lsl #%d", instr->ImmExtendShift());
+      AppendToOutput(", lsl #%" PRId64, instr->ImmExtendShift());
     }
   } else {
     AppendToOutput(", %s", extend_mode[instr->ExtendMode()]);
     if (instr->ImmExtendShift() > 0) {
-      AppendToOutput(" #%d", instr->ImmExtendShift());
+      AppendToOutput(" #%" PRId64, instr->ImmExtendShift());
     }
   }
   return 3;
@@ -1632,7 +1632,7 @@ int Disassembler::SubstituteLSRegOffsetField(Instruction* instr,
   if (!((ext == UXTX) && (shift == 0))) {
     AppendToOutput(", %s", extend_mode[ext]);
     if (shift != 0) {
-      AppendToOutput(" #%d", instr->SizeLS());
+      AppendToOutput(" #%" PRId64, instr->SizeLS());
     }
   }
   return 9;
diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c
index d10b5dbb49..de542010aa 100644
--- a/hw/arm/musicpal.c
+++ b/hw/arm/musicpal.c
@@ -110,10 +110,10 @@
 #define MP_PHY_88E3015          0x01410E20
 
 /* TX descriptor status */
-#define MP_ETH_TX_OWN           (1 << 31)
+#define MP_ETH_TX_OWN           (1U << 31)
 
 /* RX descriptor status */
-#define MP_ETH_RX_OWN           (1 << 31)
+#define MP_ETH_RX_OWN           (1U << 31)
 
 /* Interrupt cause/mask bits */
 #define MP_ETH_IRQ_RX_BIT       0
diff --git a/hw/arm/omap1.c b/hw/arm/omap1.c
index 47511d2cae..b433748c60 100644
--- a/hw/arm/omap1.c
+++ b/hw/arm/omap1.c
@@ -809,22 +809,26 @@ static inline void omap_pin_funcmux1_update(struct omap_mpu_state_s *s,
                 uint32_t diff, uint32_t value)
 {
     if (s->compat1509) {
-        if (diff & (1 << 31))			/* MCBSP3_CLK_HIZ_DI */
-            omap_clk_onoff(omap_findclk(s, "mcbsp3.clkx"),
-                            (value >> 31) & 1);
-        if (diff & (1 << 1))			/* CLK32K */
-            omap_clk_onoff(omap_findclk(s, "clk32k_out"),
-                            (~value >> 1) & 1);
+        if (diff & (1U << 31)) {
+            /* MCBSP3_CLK_HIZ_DI */
+            omap_clk_onoff(omap_findclk(s, "mcbsp3.clkx"), (value >> 31) & 1);
+        }
+        if (diff & (1 << 1)) {
+            /* CLK32K */
+            omap_clk_onoff(omap_findclk(s, "clk32k_out"), (~value >> 1) & 1);
+        }
     }
 }
 
 static inline void omap_pin_modconf1_update(struct omap_mpu_state_s *s,
                 uint32_t diff, uint32_t value)
 {
-    if (diff & (1 << 31))			/* CONF_MOD_UART3_CLK_MODE_R */
-         omap_clk_reparent(omap_findclk(s, "uart3_ck"),
-                         omap_findclk(s, ((value >> 31) & 1) ?
-                                 "ck_48m" : "armper_ck"));
+    if (diff & (1U << 31)) {
+        /* CONF_MOD_UART3_CLK_MODE_R */
+        omap_clk_reparent(omap_findclk(s, "uart3_ck"),
+                          omap_findclk(s, ((value >> 31) & 1) ?
+                                       "ck_48m" : "armper_ck"));
+    }
     if (diff & (1 << 30))			/* CONF_MOD_UART2_CLK_MODE_R */
          omap_clk_reparent(omap_findclk(s, "uart2_ck"),
                          omap_findclk(s, ((value >> 30) & 1) ?
diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c
index 904277a9da..04291488e4 100644
--- a/hw/arm/pxa2xx.c
+++ b/hw/arm/pxa2xx.c
@@ -259,7 +259,7 @@ static void pxa2xx_pwrmode_write(CPUARMState *env, const ARMCPRegInfo *ri,
 
     case 1:
         /* Idle */
-        if (!(s->cm_regs[CCCR >> 2] & (1 << 31))) { /* CPDIS */
+        if (!(s->cm_regs[CCCR >> 2] & (1U << 31))) { /* CPDIS */
             cpu_interrupt(CPU(s->cpu), CPU_INTERRUPT_HALT);
             break;
         }
@@ -496,7 +496,7 @@ typedef struct {
 #define SSCR0_SSE	(1 << 7)
 #define SSCR0_RIM	(1 << 22)
 #define SSCR0_TIM	(1 << 23)
-#define SSCR0_MOD	(1 << 31)
+#define SSCR0_MOD       (1U << 31)
 #define SSCR0_DSS(x)	(((((x) >> 16) & 0x10) | ((x) & 0xf)) + 1)
 #define SSCR1_RIE	(1 << 0)
 #define SSCR1_TIE	(1 << 1)
@@ -1006,7 +1006,7 @@ static void pxa2xx_rtc_write(void *opaque, hwaddr addr,
 
     switch (addr) {
     case RTTR:
-        if (!(s->rttr & (1 << 31))) {
+        if (!(s->rttr & (1U << 31))) {
             pxa2xx_rtc_hzupdate(s);
             s->rttr = value;
             pxa2xx_rtc_alarm_update(s, s->rtsr);
diff --git a/hw/arm/pxa2xx_gpio.c b/hw/arm/pxa2xx_gpio.c
index ca77f56c9f..07274285ab 100644
--- a/hw/arm/pxa2xx_gpio.c
+++ b/hw/arm/pxa2xx_gpio.c
@@ -110,7 +110,7 @@ static void pxa2xx_gpio_set(void *opaque, int line, int level)
     }
 
     bank = line >> 5;
-    mask = 1 << (line & 31);
+    mask = 1U << (line & 31);
 
     if (level) {
         s->status[bank] |= s->rising[bank] & mask &
diff --git a/hw/arm/pxa2xx_pic.c b/hw/arm/pxa2xx_pic.c
index 345fa4a491..d37fb543e8 100644
--- a/hw/arm/pxa2xx_pic.c
+++ b/hw/arm/pxa2xx_pic.c
@@ -105,7 +105,7 @@ static inline uint32_t pxa2xx_pic_highest(PXA2xxPICState *s) {
 
     for (i = PXA2XX_PIC_SRCS - 1; i >= 0; i --) {
         irq = s->priority[i] & 0x3f;
-        if ((s->priority[i] & (1 << 31)) && irq < PXA2XX_PIC_SRCS) {
+        if ((s->priority[i] & (1U << 31)) && irq < PXA2XX_PIC_SRCS) {
             /* Source peripheral ID is valid.  */
             bit = 1 << (irq & 31);
             int_set = (irq >= 32);
@@ -119,7 +119,7 @@ static inline uint32_t pxa2xx_pic_highest(PXA2xxPICState *s) {
             if (mask[int_set] & bit & ~s->is_fiq[int_set]) {
                 /* IRQ asserted */
                 ichp &= 0x0000ffff;
-                ichp |= (1 << 31) | (irq << 16);
+                ichp |= (1U << 31) | (irq << 16);
             }
         }
     }
diff --git a/hw/ssi/xilinx_spips.c b/hw/ssi/xilinx_spips.c
index 6a287464bf..8977243725 100644
--- a/hw/ssi/xilinx_spips.c
+++ b/hw/ssi/xilinx_spips.c
@@ -43,7 +43,7 @@
 
 /* config register */
 #define R_CONFIG            (0x00 / 4)
-#define IFMODE              (1 << 31)
+#define IFMODE              (1U << 31)
 #define ENDIAN              (1 << 26)
 #define MODEFAIL_GEN_EN     (1 << 17)
 #define MAN_START_COM       (1 << 16)
@@ -87,7 +87,7 @@
 
 #define R_LQSPI_CFG         (0xa0 / 4)
 #define R_LQSPI_CFG_RESET       0x03A002EB
-#define LQSPI_CFG_LQ_MODE       (1 << 31)
+#define LQSPI_CFG_LQ_MODE       (1U << 31)
 #define LQSPI_CFG_TWO_MEM       (1 << 30)
 #define LQSPI_CFG_SEP_BUS       (1 << 30)
 #define LQSPI_CFG_U_PAGE        (1 << 28)
diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h
index 01cd8c7a2b..66a3d46938 100644
--- a/include/exec/cpu-defs.h
+++ b/include/exec/cpu-defs.h
@@ -59,6 +59,7 @@ typedef uint64_t target_ulong;
 #define EXCP_HLT        0x10001 /* hlt instruction reached */
 #define EXCP_DEBUG      0x10002 /* cpu stopped after a breakpoint or singlestep */
 #define EXCP_HALTED     0x10003 /* cpu is halted (waiting for external event) */
+#define EXCP_YIELD      0x10004 /* cpu wants to yield timeslice to another */
 
 #define TB_JMP_CACHE_BITS 12
 #define TB_JMP_CACHE_SIZE (1 << TB_JMP_CACHE_BITS)
diff --git a/target-arm/cpu.h b/target-arm/cpu.h
index 49fef3fcbe..0a7edfe6cb 100644
--- a/target-arm/cpu.h
+++ b/target-arm/cpu.h
@@ -222,6 +222,10 @@ typedef struct CPUARMState {
         uint64_t dbgbcr[16]; /* breakpoint control registers */
         uint64_t dbgwvr[16]; /* watchpoint value registers */
         uint64_t dbgwcr[16]; /* watchpoint control registers */
+        /* If the counter is enabled, this stores the last time the counter
+         * was reset. Otherwise it stores the counter value
+         */
+        uint32_t c15_ccnt;
     } cp15;
 
     struct {
diff --git a/target-arm/helper.c b/target-arm/helper.c
index 90f85f1899..f65cbac1ee 100644
--- a/target-arm/helper.c
+++ b/target-arm/helper.c
@@ -13,6 +13,11 @@ static inline int get_phys_addr(CPUARMState *env, uint32_t address,
                                 int access_type, int is_user,
                                 hwaddr *phys_ptr, int *prot,
                                 target_ulong *page_size);
+
+/* Definitions for the PMCCNTR and PMCR registers */
+#define PMCRD   0x8
+#define PMCRC   0x4
+#define PMCRE   0x1
 #endif
 
 static int vfp_gdb_get_reg(CPUARMState *env, uint8_t *buf, int reg)
@@ -478,13 +483,84 @@ static CPAccessResult pmreg_access(CPUARMState *env, const ARMCPRegInfo *ri)
     return CP_ACCESS_OK;
 }
 
+#ifndef CONFIG_USER_ONLY
 static void pmcr_write(CPUARMState *env, const ARMCPRegInfo *ri,
                        uint64_t value)
 {
+    /* Don't computer the number of ticks in user mode */
+    uint32_t temp_ticks;
+
+    temp_ticks = qemu_clock_get_us(QEMU_CLOCK_VIRTUAL) *
+                  get_ticks_per_sec() / 1000000;
+
+    if (env->cp15.c9_pmcr & PMCRE) {
+        /* If the counter is enabled */
+        if (env->cp15.c9_pmcr & PMCRD) {
+            /* Increment once every 64 processor clock cycles */
+            env->cp15.c15_ccnt = (temp_ticks/64) - env->cp15.c15_ccnt;
+        } else {
+            env->cp15.c15_ccnt = temp_ticks - env->cp15.c15_ccnt;
+        }
+    }
+
+    if (value & PMCRC) {
+        /* The counter has been reset */
+        env->cp15.c15_ccnt = 0;
+    }
+
     /* only the DP, X, D and E bits are writable */
     env->cp15.c9_pmcr &= ~0x39;
     env->cp15.c9_pmcr |= (value & 0x39);
+
+    if (env->cp15.c9_pmcr & PMCRE) {
+        if (env->cp15.c9_pmcr & PMCRD) {
+            /* Increment once every 64 processor clock cycles */
+            temp_ticks /= 64;
+        }
+        env->cp15.c15_ccnt = temp_ticks - env->cp15.c15_ccnt;
+    }
+}
+
+static uint64_t pmccntr_read(CPUARMState *env, const ARMCPRegInfo *ri)
+{
+    uint32_t total_ticks;
+
+    if (!(env->cp15.c9_pmcr & PMCRE)) {
+        /* Counter is disabled, do not change value */
+        return env->cp15.c15_ccnt;
+    }
+
+    total_ticks = qemu_clock_get_us(QEMU_CLOCK_VIRTUAL) *
+                  get_ticks_per_sec() / 1000000;
+
+    if (env->cp15.c9_pmcr & PMCRD) {
+        /* Increment once every 64 processor clock cycles */
+        total_ticks /= 64;
+    }
+    return total_ticks - env->cp15.c15_ccnt;
+}
+
+static void pmccntr_write(CPUARMState *env, const ARMCPRegInfo *ri,
+                        uint64_t value)
+{
+    uint32_t total_ticks;
+
+    if (!(env->cp15.c9_pmcr & PMCRE)) {
+        /* Counter is disabled, set the absolute value */
+        env->cp15.c15_ccnt = value;
+        return;
+    }
+
+    total_ticks = qemu_clock_get_us(QEMU_CLOCK_VIRTUAL) *
+                  get_ticks_per_sec() / 1000000;
+
+    if (env->cp15.c9_pmcr & PMCRD) {
+        /* Increment once every 64 processor clock cycles */
+        total_ticks /= 64;
+    }
+    env->cp15.c15_ccnt = total_ticks - value;
 }
+#endif
 
 static void pmcntenset_write(CPUARMState *env, const ARMCPRegInfo *ri,
                             uint64_t value)
@@ -604,10 +680,12 @@ static const ARMCPRegInfo v7_cp_reginfo[] = {
     { .name = "PMSELR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 5,
       .access = PL0_RW, .type = ARM_CP_CONST, .resetvalue = 0,
       .accessfn = pmreg_access },
-    /* Unimplemented, RAZ/WI. */
+#ifndef CONFIG_USER_ONLY
     { .name = "PMCCNTR", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 0,
-      .access = PL0_RW, .type = ARM_CP_CONST, .resetvalue = 0,
+      .access = PL0_RW, .resetvalue = 0, .type = ARM_CP_IO,
+      .readfn = pmccntr_read, .writefn = pmccntr_write,
       .accessfn = pmreg_access },
+#endif
     { .name = "PMXEVTYPER", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 1,
       .access = PL0_RW,
       .fieldoffset = offsetof(CPUARMState, cp15.c9_pmxevtyper),
@@ -1873,8 +1951,10 @@ void register_cp_regs_for_features(ARMCPU *cpu)
     }
     if (arm_feature(env, ARM_FEATURE_V7)) {
         /* v7 performance monitor control register: same implementor
-         * field as main ID register, and we implement no event counters.
+         * field as main ID register, and we implement only the cycle
+         * count register.
          */
+#ifndef CONFIG_USER_ONLY
         ARMCPRegInfo pmcr = {
             .name = "PMCR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 0,
             .access = PL0_RW, .resetvalue = cpu->midr & 0xff000000,
@@ -1882,12 +1962,13 @@ void register_cp_regs_for_features(ARMCPU *cpu)
             .accessfn = pmreg_access, .writefn = pmcr_write,
             .raw_writefn = raw_write,
         };
+        define_one_arm_cp_reg(cpu, &pmcr);
+#endif
         ARMCPRegInfo clidr = {
             .name = "CLIDR", .state = ARM_CP_STATE_BOTH,
             .opc0 = 3, .crn = 0, .crm = 0, .opc1 = 1, .opc2 = 1,
             .access = PL1_R, .type = ARM_CP_CONST, .resetvalue = cpu->clidr
         };
-        define_one_arm_cp_reg(cpu, &pmcr);
         define_one_arm_cp_reg(cpu, &clidr);
         define_arm_cp_regs(cpu, v7_cp_reginfo);
     } else {
@@ -2478,7 +2559,7 @@ uint32_t cpsr_read(CPUARMState *env)
         (env->CF << 29) | ((env->VF & 0x80000000) >> 3) | (env->QF << 27)
         | (env->thumb << 5) | ((env->condexec_bits & 3) << 25)
         | ((env->condexec_bits & 0xfc) << 8)
-        | (env->GE << 16) | env->daif;
+        | (env->GE << 16) | (env->daif & CPSR_AIF);
 }
 
 void cpsr_write(CPUARMState *env, uint32_t val, uint32_t mask)
diff --git a/target-arm/helper.h b/target-arm/helper.h
index 276f3a9149..8923f8ae71 100644
--- a/target-arm/helper.h
+++ b/target-arm/helper.h
@@ -50,6 +50,7 @@ DEF_HELPER_FLAGS_3(sel_flags, TCG_CALL_NO_RWG_SE,
                    i32, i32, i32, i32)
 DEF_HELPER_2(exception, void, env, i32)
 DEF_HELPER_1(wfi, void, env)
+DEF_HELPER_1(wfe, void, env)
 
 DEF_HELPER_3(cpsr_write, void, env, i32, i32)
 DEF_HELPER_1(cpsr_read, i32, env)
diff --git a/target-arm/op_helper.c b/target-arm/op_helper.c
index 7d06d2f9a5..5851e041a0 100644
--- a/target-arm/op_helper.c
+++ b/target-arm/op_helper.c
@@ -225,6 +225,15 @@ void HELPER(wfi)(CPUARMState *env)
     cpu_loop_exit(env);
 }
 
+void HELPER(wfe)(CPUARMState *env)
+{
+    /* Don't actually halt the CPU, just yield back to top
+     * level loop
+     */
+    env->exception_index = EXCP_YIELD;
+    cpu_loop_exit(env);
+}
+
 void HELPER(exception)(CPUARMState *env, uint32_t excp)
 {
     env->exception_index = excp;
diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 08ac6591b6..37e05e81f7 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -210,7 +210,7 @@ static inline void gen_goto_tb(DisasContext *s, int n, uint64_t dest)
     if (use_goto_tb(s, n, dest)) {
         tcg_gen_goto_tb(n);
         gen_a64_set_pc_im(dest);
-        tcg_gen_exit_tb((tcg_target_long)tb + n);
+        tcg_gen_exit_tb((intptr_t)tb + n);
         s->is_jmp = DISAS_TB_JUMP;
     } else {
         gen_a64_set_pc_im(dest);
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 253d2a13eb..df259debcc 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -3939,6 +3939,9 @@ static void gen_nop_hint(DisasContext *s, int val)
         s->is_jmp = DISAS_WFI;
         break;
     case 2: /* wfe */
+        gen_set_pc_im(s, s->pc);
+        s->is_jmp = DISAS_WFE;
+        break;
     case 4: /* sev */
     case 5: /* sevl */
         /* TODO: Implement SEV, SEVL and WFE.  May help SMP performance.  */
@@ -10857,6 +10860,9 @@ static inline void gen_intermediate_code_internal(ARMCPU *cpu,
         case DISAS_WFI:
             gen_helper_wfi(cpu_env);
             break;
+        case DISAS_WFE:
+            gen_helper_wfe(cpu_env);
+            break;
         case DISAS_SWI:
             gen_exception(EXCP_SWI);
             break;
diff --git a/target-arm/translate.h b/target-arm/translate.h
index 67da6996c9..2f491f9ff6 100644
--- a/target-arm/translate.h
+++ b/target-arm/translate.h
@@ -44,6 +44,8 @@ extern TCGv_ptr cpu_env;
  * emitting unreachable code at the end of the TB in the A64 decoder
  */
 #define DISAS_EXC 6
+/* WFE */
+#define DISAS_WFE 7
 
 #ifdef TARGET_AARCH64
 void a64_translate_init(void);