[PULL 26/34] target/ppc: Implement lwsync with weaker memory ordering

[Daniel Henrique Barboza]

From: Nicholas Piggin <npiggin@gmail.com>

This allows an x86 host to no-op lwsyncs, and ppc host can use lwsync
rather than sync.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220519135908.21282-5-npiggin@gmail.com>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
---
 target/ppc/cpu.h       |  4 +++-
 target/ppc/cpu_init.c  | 13 +++++++------
 target/ppc/machine.c   |  3 ++-
 target/ppc/translate.c |  8 +++++++-
 4 files changed, 19 insertions(+), 9 deletions(-)

diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h
index 901ded79e9..bf8f8aad2c 100644
--- a/target/ppc/cpu.h
+++ b/target/ppc/cpu.h
@@ -2273,6 +2273,8 @@ enum {
     PPC2_ISA300        = 0x0000000000080000ULL,
     /* POWER ISA 3.1                                                         */
     PPC2_ISA310        = 0x0000000000100000ULL,
+    /*   lwsync instruction                                                  */
+    PPC2_MEM_LWSYNC    = 0x0000000000200000ULL,
 
 #define PPC_TCG_INSNS2 (PPC2_BOOKE206 | PPC2_VSX | PPC2_PRCNTL | PPC2_DBRX | \
                         PPC2_ISA205 | PPC2_VSX207 | PPC2_PERM_ISA206 | \
@@ -2281,7 +2283,7 @@ enum {
                         PPC2_BCTAR_ISA207 | PPC2_LSQ_ISA207 | \
                         PPC2_ALTIVEC_207 | PPC2_ISA207S | PPC2_DFP | \
                         PPC2_FP_CVT_S64 | PPC2_TM | PPC2_PM_ISA206 | \
-                        PPC2_ISA300 | PPC2_ISA310)
+                        PPC2_ISA300 | PPC2_ISA310 | PPC2_MEM_LWSYNC)
 };
 
 /*****************************************************************************/
diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c
index 527ad40fcb..0f891afa04 100644
--- a/target/ppc/cpu_init.c
+++ b/target/ppc/cpu_init.c
@@ -5769,7 +5769,7 @@ POWERPC_FAMILY(970)(ObjectClass *oc, void *data)
                        PPC_MEM_TLBIE | PPC_MEM_TLBSYNC |
                        PPC_64B | PPC_ALTIVEC |
                        PPC_SEGMENT_64B | PPC_SLBI;
-    pcc->insns_flags2 = PPC2_FP_CVT_S64;
+    pcc->insns_flags2 = PPC2_FP_CVT_S64 | PPC2_MEM_LWSYNC;
     pcc->msr_mask = (1ull << MSR_SF) |
                     (1ull << MSR_VR) |
                     (1ull << MSR_POW) |
@@ -5846,7 +5846,7 @@ POWERPC_FAMILY(POWER5P)(ObjectClass *oc, void *data)
                        PPC_64B |
                        PPC_POPCNTB |
                        PPC_SEGMENT_64B | PPC_SLBI;
-    pcc->insns_flags2 = PPC2_FP_CVT_S64;
+    pcc->insns_flags2 = PPC2_FP_CVT_S64 | PPC2_MEM_LWSYNC;
     pcc->msr_mask = (1ull << MSR_SF) |
                     (1ull << MSR_VR) |
                     (1ull << MSR_POW) |
@@ -5985,7 +5985,7 @@ POWERPC_FAMILY(POWER7)(ObjectClass *oc, void *data)
                         PPC2_PERM_ISA206 | PPC2_DIVE_ISA206 |
                         PPC2_ATOMIC_ISA206 | PPC2_FP_CVT_ISA206 |
                         PPC2_FP_TST_ISA206 | PPC2_FP_CVT_S64 |
-                        PPC2_PM_ISA206;
+                        PPC2_PM_ISA206 | PPC2_MEM_LWSYNC;
     pcc->msr_mask = (1ull << MSR_SF) |
                     (1ull << MSR_VR) |
                     (1ull << MSR_VSX) |
@@ -6159,7 +6159,7 @@ POWERPC_FAMILY(POWER8)(ObjectClass *oc, void *data)
                         PPC2_FP_TST_ISA206 | PPC2_BCTAR_ISA207 |
                         PPC2_LSQ_ISA207 | PPC2_ALTIVEC_207 |
                         PPC2_ISA205 | PPC2_ISA207S | PPC2_FP_CVT_S64 |
-                        PPC2_TM | PPC2_PM_ISA206;
+                        PPC2_TM | PPC2_PM_ISA206 | PPC2_MEM_LWSYNC;
     pcc->msr_mask = (1ull << MSR_SF) |
                     (1ull << MSR_HV) |
                     (1ull << MSR_TM) |
@@ -6379,7 +6379,7 @@ POWERPC_FAMILY(POWER9)(ObjectClass *oc, void *data)
                         PPC2_FP_TST_ISA206 | PPC2_BCTAR_ISA207 |
                         PPC2_LSQ_ISA207 | PPC2_ALTIVEC_207 |
                         PPC2_ISA205 | PPC2_ISA207S | PPC2_FP_CVT_S64 |
-                        PPC2_TM | PPC2_ISA300 | PPC2_PRCNTL;
+                        PPC2_TM | PPC2_ISA300 | PPC2_PRCNTL | PPC2_MEM_LWSYNC;
     pcc->msr_mask = (1ull << MSR_SF) |
                     (1ull << MSR_HV) |
                     (1ull << MSR_TM) |
@@ -6596,7 +6596,8 @@ POWERPC_FAMILY(POWER10)(ObjectClass *oc, void *data)
                         PPC2_FP_TST_ISA206 | PPC2_BCTAR_ISA207 |
                         PPC2_LSQ_ISA207 | PPC2_ALTIVEC_207 |
                         PPC2_ISA205 | PPC2_ISA207S | PPC2_FP_CVT_S64 |
-                        PPC2_TM | PPC2_ISA300 | PPC2_PRCNTL | PPC2_ISA310;
+                        PPC2_TM | PPC2_ISA300 | PPC2_PRCNTL | PPC2_ISA310 |
+                        PPC2_MEM_LWSYNC;
     pcc->msr_mask = (1ull << MSR_SF) |
                     (1ull << MSR_HV) |
                     (1ull << MSR_TM) |
diff --git a/target/ppc/machine.c b/target/ppc/machine.c
index 7104a5c67e..a7d9036c09 100644
--- a/target/ppc/machine.c
+++ b/target/ppc/machine.c
@@ -157,7 +157,8 @@ static int cpu_pre_save(void *opaque)
         | PPC2_ATOMIC_ISA206 | PPC2_FP_CVT_ISA206
         | PPC2_FP_TST_ISA206 | PPC2_BCTAR_ISA207
         | PPC2_LSQ_ISA207 | PPC2_ALTIVEC_207
-        | PPC2_ISA205 | PPC2_ISA207S | PPC2_FP_CVT_S64 | PPC2_TM;
+        | PPC2_ISA205 | PPC2_ISA207S | PPC2_FP_CVT_S64 | PPC2_TM
+        | PPC2_MEM_LWSYNC;
 
     env->spr[SPR_LR] = env->lr;
     env->spr[SPR_CTR] = env->ctr;
diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index eb42f7e459..1d6daa4608 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -4041,8 +4041,13 @@ static void gen_stqcx_(DisasContext *ctx)
 /* sync */
 static void gen_sync(DisasContext *ctx)
 {
+    TCGBar bar = TCG_MO_ALL;
     uint32_t l = (ctx->opcode >> 21) & 3;
 
+    if ((l == 1) && (ctx->insns_flags2 & PPC2_MEM_LWSYNC)) {
+        bar = TCG_MO_LD_LD | TCG_MO_LD_ST | TCG_MO_ST_ST;
+    }
+
     /*
      * We may need to check for a pending TLB flush.
      *
@@ -4054,7 +4059,8 @@ static void gen_sync(DisasContext *ctx)
     if (((l == 2) || !(ctx->insns_flags & PPC_64B)) && !ctx->pr) {
         gen_check_tlb_flush(ctx, true);
     }
-    tcg_gen_mb(TCG_MO_ALL | TCG_BAR_SC);
+
+    tcg_gen_mb(bar | TCG_BAR_SC);
 }
 
 /* wait */
-- 
2.36.1