target/ppc: add SMT support to msgsnd broadcast

msgsnd has a broadcast mode that sends hypervisor doorbells to all
threads belonging to the same core as the target. A "subcore" mode
sends to all or one thread depending on 1LPAR mode.

Reviewed-by: Glenn Miles <milesg@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>

target/ppc/cpu.h

@@ -1163,7 +1163,11 @@ FIELD(FPSCR, FI, FPSCR_FI, 1)
 
 #define DBELL_TYPE_DBELL_SERVER        (0x05 << DBELL_TYPE_SHIFT)
 
-#define DBELL_BRDCAST                  PPC_BIT(37)
+#define DBELL_BRDCAST_MASK             PPC_BITMASK(37, 38)
+#define DBELL_BRDCAST_SHIFT            25
+#define DBELL_BRDCAST_SUBPROC          (0x1 << DBELL_BRDCAST_SHIFT)
+#define DBELL_BRDCAST_CORE             (0x2 << DBELL_BRDCAST_SHIFT)
+
 #define DBELL_LPIDTAG_SHIFT            14
 #define DBELL_LPIDTAG_MASK             (0xfff << DBELL_LPIDTAG_SHIFT)
 #define DBELL_PIRTAG_MASK              0x3fff

target/ppc/excp_helper.c

@@ -2969,7 +2969,7 @@ void helper_msgsnd(target_ulong rb)
         PowerPCCPU *cpu = POWERPC_CPU(cs);
         CPUPPCState *cenv = &cpu->env;
 
-        if ((rb & DBELL_BRDCAST) || (cenv->spr[SPR_BOOKE_PIR] == pir)) {
+        if ((rb & DBELL_BRDCAST_MASK) || (cenv->spr[SPR_BOOKE_PIR] == pir)) {
             ppc_set_irq(cpu, irq, 1);
         }
     }
@@ -2988,6 +2988,16 @@ static bool dbell_type_server(target_ulong rb)
     return (rb & DBELL_TYPE_MASK) == DBELL_TYPE_DBELL_SERVER;
 }
 
+static inline bool dbell_bcast_core(target_ulong rb)
+{
+    return (rb & DBELL_BRDCAST_MASK) == DBELL_BRDCAST_CORE;
+}
+
+static inline bool dbell_bcast_subproc(target_ulong rb)
+{
+    return (rb & DBELL_BRDCAST_MASK) == DBELL_BRDCAST_SUBPROC;
+}
+
 void helper_book3s_msgclr(CPUPPCState *env, target_ulong rb)
 {
     if (!dbell_type_server(rb)) {
@@ -2997,32 +3007,43 @@ void helper_book3s_msgclr(CPUPPCState *env, target_ulong rb)
     ppc_set_irq(env_archcpu(env), PPC_INTERRUPT_HDOORBELL, 0);
 }
 
-static void book3s_msgsnd_common(int pir, int irq)
-{
-    CPUState *cs;
-
-    bql_lock();
-    CPU_FOREACH(cs) {
-        PowerPCCPU *cpu = POWERPC_CPU(cs);
-        CPUPPCState *cenv = &cpu->env;
-
-        /* TODO: broadcast message to all threads of the same  processor */
-        if (cenv->spr_cb[SPR_PIR].default_value == pir) {
-            ppc_set_irq(cpu, irq, 1);
-        }
-    }
-    bql_unlock();
-}
-
-void helper_book3s_msgsnd(target_ulong rb)
+void helper_book3s_msgsnd(CPUPPCState *env, target_ulong rb)
 {
     int pir = rb & DBELL_PROCIDTAG_MASK;
+    bool brdcast = false;
+    CPUState *cs, *ccs;
+    PowerPCCPU *cpu;
 
     if (!dbell_type_server(rb)) {
         return;
     }
 
-    book3s_msgsnd_common(pir, PPC_INTERRUPT_HDOORBELL);
+    cpu = ppc_get_vcpu_by_pir(pir);
+    if (!cpu) {
+        return;
+    }
+    cs = CPU(cpu);
+
+    if (dbell_bcast_core(rb) || (dbell_bcast_subproc(rb) &&
+                                 (env->flags & POWERPC_FLAG_SMT_1LPAR))) {
+        brdcast = true;
+    }
+
+    if (cs->nr_threads == 1 || !brdcast) {
+        ppc_set_irq(cpu, PPC_INTERRUPT_HDOORBELL, 1);
+        return;
+    }
+
+    /*
+     * Why is bql needed for walking CPU list? Answer seems to be because ppc
+     * irq handling needs it, but ppc_set_irq takes the lock itself if needed,
+     * so could this be removed?
+     */
+    bql_lock();
+    THREAD_SIBLING_FOREACH(cs, ccs) {
+        ppc_set_irq(POWERPC_CPU(ccs), PPC_INTERRUPT_HDOORBELL, 1);
+    }
+    bql_unlock();
 }
 
 #ifdef TARGET_PPC64

target/ppc/helper.h

@@ -695,7 +695,7 @@ DEF_HELPER_FLAGS_3(store_sr, TCG_CALL_NO_RWG, void, env, tl, tl)
 
 DEF_HELPER_1(msgsnd, void, tl)
 DEF_HELPER_2(msgclr, void, env, tl)
-DEF_HELPER_1(book3s_msgsnd, void, tl)
+DEF_HELPER_2(book3s_msgsnd, void, env, tl)
 DEF_HELPER_2(book3s_msgclr, void, env, tl)
 #endif
 

target/ppc/translate/processor-ctrl-impl.c.inc

@@ -59,7 +59,7 @@ static bool trans_MSGSND(DisasContext *ctx, arg_X_rb *a)
 
 #if !defined(CONFIG_USER_ONLY)
     if (is_book3s_arch2x(ctx)) {
-        gen_helper_book3s_msgsnd(cpu_gpr[a->rb]);
+        gen_helper_book3s_msgsnd(tcg_env, cpu_gpr[a->rb]);
     } else {
         gen_helper_msgsnd(cpu_gpr[a->rb]);
     }