[Qemu-devel] [PATCH v6 0/8] POWER9 TCG enablements - part15

[Qemu-devel] [PATCH v6 0/8] POWER9 TCG enablements - part15

[Nikunj A Dadhania]

This series contains implentation of CA32 and OV32 bits added to the 
ISA 3.0. Various fixed-point arithmetic instructions are updated to take
care of the newer flags. 

Finally the last patch adds new instruction mcrxrx, that helps reading 
the carry (CA and CA32) and the overflow (OV and OV32) flags

Changelog:
v5:
* Rebase to ppc-for-2.9

v4: 
* Get back to the v3 implementation. Dropped removal of split 
  out variables.
* Remove checking of isa300 on the write side. Read side will do 
  the checking.

v3:
* Get rid of cpu_ca, cpu_ov, cpu_so split out variables
* As most of the patches under went changes, dropped the 
  reviewed-bys(except neg[.] patch)

v2: 
* Add missing condition in narrow mode(add/subf), multiply and divide
* Drop nego patch, subf implementation is sufficient for setting OV and OV32
* Retaining neg[.], as the code is simplified.
* Fix OV resetting in compute_ov()

v1: 
* Use these ISA 3.0 flag to enable CA32 and OV32
* Re-write ca32 compute routine
* Add setting of flags for "neg." and "nego."


Nikunj A Dadhania (8):
  target/ppc: support for 32-bit carry and overflow
  target/ppc: update ca32 in arithmetic add
  target/ppc: update ca32 in arithmetic substract
  target/ppc: update overflow flags for add/sub
  target/ppc: use tcg ops for neg instruction
  target/ppc: add ov32 flag for multiply low insns
  target/ppc: add ov32 flag in divide operations
  target/ppc: add mcrxrx instruction

 target/ppc/cpu.c            |  13 +++++-
 target/ppc/cpu.h            |   7 +++
 target/ppc/translate.c      | 106 ++++++++++++++++++++++++++++++++++++++++----
 target/ppc/translate_init.c |   2 +-
 4 files changed, 118 insertions(+), 10 deletions(-)

-- 
2.7.4

[Qemu-devel] [PATCH v6 1/8] target/ppc: support for 32-bit carry and overflow

[Nikunj A Dadhania]

POWER ISA 3.0 adds CA32 and OV32 status in 64-bit mode. Add the flags
and corresponding defines.

Moreover, CA32 is updated when CA is updated and OV32 is updated when OV
is updated.

Arithmetic instructions:
    * Addition and Substractions:

        addic, addic., subfic, addc, subfc, adde, subfe, addme, subfme,
        addze, and subfze always updates CA and CA32.

        => CA reflects the carry out of bit 0 in 64-bit mode and out of
           bit 32 in 32-bit mode.
        => CA32 reflects the carry out of bit 32 independent of the
           mode.

        => SO and OV reflects overflow of the 64-bit result in 64-bit
           mode and overflow of the low-order 32-bit result in 32-bit
           mode
        => OV32 reflects overflow of the low-order 32-bit independent of
           the mode

    * Multiply Low and Divide:

        For mulld, divd, divde, divdu and divdeu: SO, OV, and OV32 bits
        reflects overflow of the 64-bit result

        For mullw, divw, divwe, divwu and divweu: SO, OV, and OV32 bits
        reflects overflow of the 32-bit result

     * Negate with OE=1 (nego)

       For 64-bit mode if the register RA contains
       0x8000_0000_0000_0000, OV and OV32 are set to 1.

       For 32-bit mode if the register RA contains 0x8000_0000, OV and
       OV32 are set to 1.

Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
---
 target/ppc/cpu.c            | 13 ++++++++++++-
 target/ppc/cpu.h            |  7 +++++++
 target/ppc/translate.c      | 21 ++++++++++++++++++---
 target/ppc/translate_init.c |  2 +-
 4 files changed, 38 insertions(+), 5 deletions(-)

diff --git a/target/ppc/cpu.c b/target/ppc/cpu.c
index de3004b..2801166 100644
--- a/target/ppc/cpu.c
+++ b/target/ppc/cpu.c
@@ -23,6 +23,12 @@
 
 target_ulong cpu_read_xer(CPUPPCState *env)
 {
+    if (is_isa300(env)) {
+        return env->xer | (env->so << XER_SO) |
+            (env->ov << XER_OV) | (env->ca << XER_CA) |
+            (env->ov32 << XER_OV32) | (env->ca32 << XER_CA32);
+    }
+
     return env->xer | (env->so << XER_SO) | (env->ov << XER_OV) |
         (env->ca << XER_CA);
 }
@@ -32,5 +38,10 @@ void cpu_write_xer(CPUPPCState *env, target_ulong xer)
     env->so = (xer >> XER_SO) & 1;
     env->ov = (xer >> XER_OV) & 1;
     env->ca = (xer >> XER_CA) & 1;
-    env->xer = xer & ~((1u << XER_SO) | (1u << XER_OV) | (1u << XER_CA));
+    /* write all the flags, while reading back check of isa300 */
+    env->ov32 = (xer >> XER_OV32) & 1;
+    env->ca32 = (xer >> XER_CA32) & 1;
+    env->xer = xer & ~((1ul << XER_SO) |
+                       (1ul << XER_OV) | (1ul << XER_CA) |
+                       (1ul << XER_OV32) | (1ul << XER_CA32));
 }
diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index b559b67..ee2eb45 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -965,6 +965,8 @@ struct CPUPPCState {
     target_ulong so;
     target_ulong ov;
     target_ulong ca;
+    target_ulong ov32;
+    target_ulong ca32;
     /* Reservation address */
     target_ulong reserve_addr;
     /* Reservation value */
@@ -1372,11 +1374,15 @@ int ppc_compat_max_threads(PowerPCCPU *cpu);
 #define XER_SO  31
 #define XER_OV  30
 #define XER_CA  29
+#define XER_OV32  19
+#define XER_CA32  18
 #define XER_CMP  8
 #define XER_BC   0
 #define xer_so  (env->so)
 #define xer_ov  (env->ov)
 #define xer_ca  (env->ca)
+#define xer_ov32  (env->ov)
+#define xer_ca32  (env->ca)
 #define xer_cmp ((env->xer >> XER_CMP) & 0xFF)
 #define xer_bc  ((env->xer >> XER_BC)  & 0x7F)
 
@@ -2343,6 +2349,7 @@ enum {
 
 /*****************************************************************************/
 
+#define is_isa300(ctx) (!!(ctx->insns_flags2 & PPC2_ISA300))
 target_ulong cpu_read_xer(CPUPPCState *env);
 void cpu_write_xer(CPUPPCState *env, target_ulong xer);
 
diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index b09e16f..be7378b 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -71,7 +71,7 @@ static TCGv cpu_lr;
 #if defined(TARGET_PPC64)
 static TCGv cpu_cfar;
 #endif
-static TCGv cpu_xer, cpu_so, cpu_ov, cpu_ca;
+static TCGv cpu_xer, cpu_so, cpu_ov, cpu_ca, cpu_ov32, cpu_ca32;
 static TCGv cpu_reserve;
 static TCGv cpu_fpscr;
 static TCGv_i32 cpu_access_type;
@@ -173,6 +173,10 @@ void ppc_translate_init(void)
                                 offsetof(CPUPPCState, ov), "OV");
     cpu_ca = tcg_global_mem_new(cpu_env,
                                 offsetof(CPUPPCState, ca), "CA");
+    cpu_ov32 = tcg_global_mem_new(cpu_env,
+                                  offsetof(CPUPPCState, ov32), "OV32");
+    cpu_ca32 = tcg_global_mem_new(cpu_env,
+                                  offsetof(CPUPPCState, ca32), "CA32");
 
     cpu_reserve = tcg_global_mem_new(cpu_env,
                                      offsetof(CPUPPCState, reserve_addr),
@@ -3703,7 +3707,7 @@ static void gen_tdi(DisasContext *ctx)
 
 /***                          Processor control                            ***/
 
-static void gen_read_xer(TCGv dst)
+static void gen_read_xer(DisasContext *ctx, TCGv dst)
 {
     TCGv t0 = tcg_temp_new();
     TCGv t1 = tcg_temp_new();
@@ -3715,6 +3719,12 @@ static void gen_read_xer(TCGv dst)
     tcg_gen_or_tl(t0, t0, t1);
     tcg_gen_or_tl(dst, dst, t2);
     tcg_gen_or_tl(dst, dst, t0);
+    if (is_isa300(ctx)) {
+        tcg_gen_shli_tl(t0, cpu_ov32, XER_OV32);
+        tcg_gen_or_tl(dst, dst, t0);
+        tcg_gen_shli_tl(t0, cpu_ca32, XER_CA32);
+        tcg_gen_or_tl(dst, dst, t0);
+    }
     tcg_temp_free(t0);
     tcg_temp_free(t1);
     tcg_temp_free(t2);
@@ -3722,8 +3732,13 @@ static void gen_read_xer(TCGv dst)
 
 static void gen_write_xer(TCGv src)
 {
+    /* Write all flags, while reading back check for isa300 */
     tcg_gen_andi_tl(cpu_xer, src,
-                    ~((1u << XER_SO) | (1u << XER_OV) | (1u << XER_CA)));
+                    ~((1u << XER_SO) |
+                      (1u << XER_OV) | (1u << XER_OV32) |
+                      (1u << XER_CA) | (1u << XER_CA32)));
+    tcg_gen_extract_tl(cpu_ov32, src, XER_OV32, 1);
+    tcg_gen_extract_tl(cpu_ca32, src, XER_CA32, 1);
     tcg_gen_extract_tl(cpu_so, src, XER_SO, 1);
     tcg_gen_extract_tl(cpu_ov, src, XER_OV, 1);
     tcg_gen_extract_tl(cpu_ca, src, XER_CA, 1);
diff --git a/target/ppc/translate_init.c b/target/ppc/translate_init.c
index be35cbd..e619c27 100644
--- a/target/ppc/translate_init.c
+++ b/target/ppc/translate_init.c
@@ -107,7 +107,7 @@ static void spr_access_nop(DisasContext *ctx, int sprn, int gprn)
 /* XER */
 static void spr_read_xer (DisasContext *ctx, int gprn, int sprn)
 {
-    gen_read_xer(cpu_gpr[gprn]);
+    gen_read_xer(ctx, cpu_gpr[gprn]);
 }
 
 static void spr_write_xer (DisasContext *ctx, int sprn, int gprn)
-- 
2.7.4

[Qemu-devel] [PATCH v6 2/8] target/ppc: update ca32 in arithmetic add

[Nikunj A Dadhania]

Adds routine to compute ca32 - gen_op_arith_compute_ca32

For 64-bit mode use the compute ca32 routine. While for 32-bit mode, CA
and CA32 will have same value.

Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target/ppc/translate.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index be7378b..eba83ef 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -816,6 +816,23 @@ static inline void gen_op_arith_compute_ov(DisasContext *ctx, TCGv arg0,
     tcg_gen_or_tl(cpu_so, cpu_so, cpu_ov);
 }
 
+static inline void gen_op_arith_compute_ca32(DisasContext *ctx,
+                                             TCGv res, TCGv arg0, TCGv arg1,
+                                             int sub)
+{
+    TCGv t0;
+
+    if (!is_isa300(ctx)) {
+        return;
+    }
+
+    t0 = tcg_temp_new();
+    tcg_gen_xor_tl(t0, arg0, arg1);
+    tcg_gen_xor_tl(t0, t0, res);
+    tcg_gen_extract_tl(cpu_ca32, t0, 32, 1);
+    tcg_temp_free(t0);
+}
+
 /* Common add function */
 static inline void gen_op_arith_add(DisasContext *ctx, TCGv ret, TCGv arg1,
                                     TCGv arg2, bool add_ca, bool compute_ca,
@@ -842,6 +859,9 @@ static inline void gen_op_arith_add(DisasContext *ctx, TCGv ret, TCGv arg1,
             tcg_temp_free(t1);
             tcg_gen_shri_tl(cpu_ca, cpu_ca, 32);   /* extract bit 32 */
             tcg_gen_andi_tl(cpu_ca, cpu_ca, 1);
+            if (is_isa300(ctx)) {
+                tcg_gen_mov_tl(cpu_ca32, cpu_ca);
+            }
         } else {
             TCGv zero = tcg_const_tl(0);
             if (add_ca) {
@@ -850,6 +870,7 @@ static inline void gen_op_arith_add(DisasContext *ctx, TCGv ret, TCGv arg1,
             } else {
                 tcg_gen_add2_tl(t0, cpu_ca, arg1, zero, arg2, zero);
             }
+            gen_op_arith_compute_ca32(ctx, t0, arg1, arg2, 0);
             tcg_temp_free(zero);
         }
     } else {
-- 
2.7.4

[Qemu-devel] [PATCH v6 3/8] target/ppc: update ca32 in arithmetic substract

[Nikunj A Dadhania]

Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target/ppc/translate.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index eba83ef..e083082 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -827,7 +827,11 @@ static inline void gen_op_arith_compute_ca32(DisasContext *ctx,
     }
 
     t0 = tcg_temp_new();
-    tcg_gen_xor_tl(t0, arg0, arg1);
+    if (sub) {
+        tcg_gen_eqv_tl(t0, arg0, arg1);
+    } else {
+        tcg_gen_xor_tl(t0, arg0, arg1);
+    }
     tcg_gen_xor_tl(t0, t0, res);
     tcg_gen_extract_tl(cpu_ca32, t0, 32, 1);
     tcg_temp_free(t0);
@@ -1378,17 +1382,22 @@ static inline void gen_op_arith_subf(DisasContext *ctx, TCGv ret, TCGv arg1,
             tcg_temp_free(t1);
             tcg_gen_shri_tl(cpu_ca, cpu_ca, 32);    /* extract bit 32 */
             tcg_gen_andi_tl(cpu_ca, cpu_ca, 1);
+            if (is_isa300(ctx)) {
+                tcg_gen_mov_tl(cpu_ca32, cpu_ca);
+            }
         } else if (add_ca) {
             TCGv zero, inv1 = tcg_temp_new();
             tcg_gen_not_tl(inv1, arg1);
             zero = tcg_const_tl(0);
             tcg_gen_add2_tl(t0, cpu_ca, arg2, zero, cpu_ca, zero);
             tcg_gen_add2_tl(t0, cpu_ca, t0, cpu_ca, inv1, zero);
+            gen_op_arith_compute_ca32(ctx, t0, inv1, arg2, 0);
             tcg_temp_free(zero);
             tcg_temp_free(inv1);
         } else {
             tcg_gen_setcond_tl(TCG_COND_GEU, cpu_ca, arg2, arg1);
             tcg_gen_sub_tl(t0, arg2, arg1);
+            gen_op_arith_compute_ca32(ctx, t0, arg1, arg2, 1);
         }
     } else if (add_ca) {
         /* Since we're ignoring carry-out, we can simplify the
-- 
2.7.4

[Qemu-devel] [PATCH v6 4/8] target/ppc: update overflow flags for add/sub

[Nikunj A Dadhania]

* SO and OV reflects overflow of the 64-bit result in 64-bit mode and
  overflow of the low-order 32-bit result in 32-bit mode

* OV32 reflects overflow of the low-order 32-bit independent of the mode

Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
---
 target/ppc/translate.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index e083082..16f422f 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -810,9 +810,16 @@ static inline void gen_op_arith_compute_ov(DisasContext *ctx, TCGv arg0,
     }
     tcg_temp_free(t0);
     if (NARROW_MODE(ctx)) {
-        tcg_gen_ext32s_tl(cpu_ov, cpu_ov);
+        tcg_gen_extract_tl(cpu_ov, cpu_ov, 31, 1);
+        if (is_isa300(ctx)) {
+            tcg_gen_mov_tl(cpu_ov32, cpu_ov);
+        }
+    } else {
+        if (is_isa300(ctx)) {
+            tcg_gen_extract_tl(cpu_ov32, cpu_ov, 31, 1);
+        }
+        tcg_gen_extract_tl(cpu_ov, cpu_ov, 63, 1);
     }
-    tcg_gen_shri_tl(cpu_ov, cpu_ov, TARGET_LONG_BITS - 1);
     tcg_gen_or_tl(cpu_so, cpu_so, cpu_ov);
 }
 
-- 
2.7.4

[Qemu-devel] [PATCH v6 5/8] target/ppc: use tcg ops for neg instruction

[Nikunj A Dadhania]

Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target/ppc/translate.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index 16f422f..d4d9941 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -1483,7 +1483,10 @@ static inline void gen_op_arith_neg(DisasContext *ctx, bool compute_ov)
 
 static void gen_neg(DisasContext *ctx)
 {
-    gen_op_arith_neg(ctx, 0);
+    tcg_gen_neg_tl(cpu_gpr[rD(ctx->opcode)], cpu_gpr[rA(ctx->opcode)]);
+    if (unlikely(Rc(ctx->opcode))) {
+        gen_set_Rc0(ctx, cpu_gpr[rD(ctx->opcode)]);
+    }
 }
 
 static void gen_nego(DisasContext *ctx)
-- 
2.7.4

[Qemu-devel] [PATCH v6 6/8] target/ppc: add ov32 flag for multiply low insns

[Nikunj A Dadhania]

For Multiply Word:
SO, OV, and OV32 bits reflects overflow of the 32-bit result

For Multiply DoubleWord:
SO, OV, and OV32 bits reflects overflow of the 64-bit result

Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target/ppc/translate.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index d4d9941..ccf3bff 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -1285,6 +1285,9 @@ static void gen_mullwo(DisasContext *ctx)
     tcg_gen_sari_i32(t0, t0, 31);
     tcg_gen_setcond_i32(TCG_COND_NE, t0, t0, t1);
     tcg_gen_extu_i32_tl(cpu_ov, t0);
+    if (is_isa300(ctx)) {
+        tcg_gen_mov_tl(cpu_ov32, cpu_ov);
+    }
     tcg_gen_or_tl(cpu_so, cpu_so, cpu_ov);
 
     tcg_temp_free_i32(t0);
@@ -1346,6 +1349,9 @@ static void gen_mulldo(DisasContext *ctx)
 
     tcg_gen_sari_i64(t0, t0, 63);
     tcg_gen_setcond_i64(TCG_COND_NE, cpu_ov, t0, t1);
+    if (is_isa300(ctx)) {
+        tcg_gen_mov_tl(cpu_ov32, cpu_ov);
+    }
     tcg_gen_or_tl(cpu_so, cpu_so, cpu_ov);
 
     tcg_temp_free_i64(t0);
-- 
2.7.4

[Qemu-devel] [PATCH v6 7/8] target/ppc: add ov32 flag in divide operations

[Nikunj A Dadhania]

Add helper_div_compute_ov() in the int_helper for updating the overflow
flags.

For Divide Word:
SO, OV, and OV32 bits reflects overflow of the 32-bit result

For Divide DoubleWord:
SO, OV, and OV32 bits reflects overflow of the 64-bit result

Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target/ppc/translate.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index ccf3bff..982e66f 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -1021,6 +1021,9 @@ static inline void gen_op_arith_divw(DisasContext *ctx, TCGv ret, TCGv arg1,
     }
     if (compute_ov) {
         tcg_gen_extu_i32_tl(cpu_ov, t2);
+        if (is_isa300(ctx)) {
+            tcg_gen_extu_i32_tl(cpu_ov32, t2);
+        }
         tcg_gen_or_tl(cpu_so, cpu_so, cpu_ov);
     }
     tcg_temp_free_i32(t0);
@@ -1092,6 +1095,9 @@ static inline void gen_op_arith_divd(DisasContext *ctx, TCGv ret, TCGv arg1,
     }
     if (compute_ov) {
         tcg_gen_mov_tl(cpu_ov, t2);
+        if (is_isa300(ctx)) {
+            tcg_gen_mov_tl(cpu_ov32, t2);
+        }
         tcg_gen_or_tl(cpu_so, cpu_so, cpu_ov);
     }
     tcg_temp_free_i64(t0);
@@ -1110,10 +1116,10 @@ static void glue(gen_, name)(DisasContext *ctx)
                       cpu_gpr[rA(ctx->opcode)], cpu_gpr[rB(ctx->opcode)],     \
                       sign, compute_ov);                                      \
 }
-/* divwu  divwu.  divwuo  divwuo.   */
+/* divdu  divdu.  divduo  divduo.   */
 GEN_INT_ARITH_DIVD(divdu, 0x0E, 0, 0);
 GEN_INT_ARITH_DIVD(divduo, 0x1E, 0, 1);
-/* divw  divw.  divwo  divwo.   */
+/* divd  divd.  divdo  divdo.   */
 GEN_INT_ARITH_DIVD(divd, 0x0F, 1, 0);
 GEN_INT_ARITH_DIVD(divdo, 0x1F, 1, 1);
 
-- 
2.7.4

[Qemu-devel] [PATCH v6 8/8] target/ppc: add mcrxrx instruction

[Nikunj A Dadhania]

mcrxrx: Move to CR from XER Extended

Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target/ppc/translate.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index 982e66f..6e6868b 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -3819,6 +3819,28 @@ static void gen_mcrxr(DisasContext *ctx)
     tcg_gen_movi_tl(cpu_ca, 0);
 }
 
+#ifdef TARGET_PPC64
+/* mcrxrx */
+static void gen_mcrxrx(DisasContext *ctx)
+{
+    TCGv t0 = tcg_temp_new();
+    TCGv t1 = tcg_temp_new();
+    TCGv_i32 dst = cpu_crf[crfD(ctx->opcode)];
+
+    /* copy OV and OV32 */
+    tcg_gen_shli_tl(t0, cpu_ov, 1);
+    tcg_gen_or_tl(t0, t0, cpu_ov32);
+    tcg_gen_shli_tl(t0, t0, 2);
+    /* copy CA and CA32 */
+    tcg_gen_shli_tl(t1, cpu_ca, 1);
+    tcg_gen_or_tl(t1, t1, cpu_ca32);
+    tcg_gen_or_tl(t0, t0, t1);
+    tcg_gen_trunc_tl_i32(dst, t0);
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+}
+#endif
+
 /* mfcr mfocrf */
 static void gen_mfcr(DisasContext *ctx)
 {
@@ -6488,6 +6510,7 @@ GEN_HANDLER(mtcrf, 0x1F, 0x10, 0x04, 0x00000801, PPC_MISC),
 #if defined(TARGET_PPC64)
 GEN_HANDLER(mtmsrd, 0x1F, 0x12, 0x05, 0x001EF801, PPC_64B),
 GEN_HANDLER_E(setb, 0x1F, 0x00, 0x04, 0x0003F801, PPC_NONE, PPC2_ISA300),
+GEN_HANDLER_E(mcrxrx, 0x1F, 0x00, 0x12, 0x007FF801, PPC_NONE, PPC2_ISA300),
 #endif
 GEN_HANDLER(mtmsr, 0x1F, 0x12, 0x04, 0x001EF801, PPC_MISC),
 GEN_HANDLER(mtspr, 0x1F, 0x13, 0x0E, 0x00000000, PPC_MISC),
-- 
2.7.4

Re: [Qemu-devel] [PATCH v6 0/8] POWER9 TCG enablements - part15

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 620 bytes --]

On Mon, Feb 27, 2017 at 10:27:53AM +0530, Nikunj A Dadhania wrote:
> This series contains implentation of CA32 and OV32 bits added to the 
> ISA 3.0. Various fixed-point arithmetic instructions are updated to take
> care of the newer flags. 
> 
> Finally the last patch adds new instruction mcrxrx, that helps reading 
> the carry (CA and CA32) and the overflow (OV and OV32) flags

Applied to ppc-for-2.9, thanks.

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 819 bytes --]