[PATCH 3/4] target/ppc: Add msgsndp and DPDES SMT support

[Nicholas Piggin <npiggin@gmail.com>]

Doorbells in SMT need to coordinate msgsndp/msgclrp and DPDES access from
multiple threads that affect the same state.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 hw/ppc/ppc.c             |  6 ++++++
 include/hw/ppc/ppc.h     |  1 +
 target/ppc/excp_helper.c | 30 ++++++++++++++++++++++-----
 target/ppc/gdbstub.c     |  2 +-
 target/ppc/misc_helper.c | 44 ++++++++++++++++++++++++++++++++++------
 target/ppc/translate.c   |  8 ++++++++
 6 files changed, 79 insertions(+), 12 deletions(-)

diff --git a/hw/ppc/ppc.c b/hw/ppc/ppc.c
index 80b4706db2..5bd4f6708f 100644
--- a/hw/ppc/ppc.c
+++ b/hw/ppc/ppc.c
@@ -1434,6 +1434,12 @@ int ppc_cpu_pir(PowerPCCPU *cpu)
     return env->spr_cb[SPR_PIR].default_value;
 }
 
+int ppc_cpu_tir(PowerPCCPU *cpu)
+{
+    CPUPPCState *env = &cpu->env;
+    return env->spr_cb[SPR_TIR].default_value;
+}
+
 PowerPCCPU *ppc_get_vcpu_by_pir(int pir)
 {
     CPUState *cs;
diff --git a/include/hw/ppc/ppc.h b/include/hw/ppc/ppc.h
index 02af03ada2..e095c002dc 100644
--- a/include/hw/ppc/ppc.h
+++ b/include/hw/ppc/ppc.h
@@ -6,6 +6,7 @@
 void ppc_set_irq(PowerPCCPU *cpu, int n_IRQ, int level);
 PowerPCCPU *ppc_get_vcpu_by_pir(int pir);
 int ppc_cpu_pir(PowerPCCPU *cpu);
+int ppc_cpu_tir(PowerPCCPU *cpu);
 
 /* PowerPC hardware exceptions management helpers */
 typedef void (*clk_setup_cb)(void *opaque, uint32_t freq);
diff --git a/target/ppc/excp_helper.c b/target/ppc/excp_helper.c
index 4925996cf3..1e04452614 100644
--- a/target/ppc/excp_helper.c
+++ b/target/ppc/excp_helper.c
@@ -3154,22 +3154,42 @@ void helper_book3s_msgclrp(CPUPPCState *env, target_ulong rb)
 }
 
 /*
- * sends a message to other threads that are on the same
+ * sends a message to another thread  on the same
  * multi-threaded processor
  */
 void helper_book3s_msgsndp(CPUPPCState *env, target_ulong rb)
 {
-    int pir = env->spr_cb[SPR_PIR].default_value;
+    CPUState *cs = env_cpu(env);
+    PowerPCCPU *cpu = POWERPC_CPU(cs);
+    CPUState *ccs;
+    uint32_t nr_threads = cs->nr_threads;
+    int ttir = rb & PPC_BITMASK(57, 63);
 
     helper_hfscr_facility_check(env, HFSCR_MSGP, "msgsndp", HFSCR_IC_MSGP);
 
-    if (!dbell_type_server(rb)) {
+    if (!dbell_type_server(rb) || ttir >= nr_threads) {
+        return;
+    }
+
+    if (nr_threads == 1) {
+        ppc_set_irq(cpu, PPC_INTERRUPT_DOORBELL, 1);
         return;
     }
 
-    /* TODO: TCG supports only one thread */
+    /* WHy does iothread need to be locked for walking CPU list? */
+    qemu_mutex_lock_iothread();
+    THREAD_SIBLING_FOREACH(cs, ccs) {
+        PowerPCCPU *ccpu = POWERPC_CPU(ccs);
+        uint32_t thread_id = ppc_cpu_tir(ccpu);
+
+        if (ttir == thread_id) {
+            ppc_set_irq(ccpu, PPC_INTERRUPT_DOORBELL, 1);
+            qemu_mutex_unlock_iothread();
+            return;
+        }
+    }
 
-    book3s_msgsnd_common(pir, PPC_INTERRUPT_DOORBELL);
+    assert(0);
 }
 #endif /* TARGET_PPC64 */
 
diff --git a/target/ppc/gdbstub.c b/target/ppc/gdbstub.c
index ca39efdc35..f0304e5bb6 100644
--- a/target/ppc/gdbstub.c
+++ b/target/ppc/gdbstub.c
@@ -117,7 +117,7 @@ void ppc_maybe_bswap_register(CPUPPCState *env, uint8_t *mem_buf, int len)
  * regs and PC, MSR, CR, and so forth.  We hack round this by giving
  * the FP regs zero size when talking to a newer gdb.
  */
-
+/* XXX: read/write dpdes correctly */
 int ppc_cpu_gdb_read_register(CPUState *cs, GByteArray *buf, int n)
 {
     PowerPCCPU *cpu = POWERPC_CPU(cs);
diff --git a/target/ppc/misc_helper.c b/target/ppc/misc_helper.c
index a058eb24cd..9688774139 100644
--- a/target/ppc/misc_helper.c
+++ b/target/ppc/misc_helper.c
@@ -184,14 +184,31 @@ void helper_store_pcr(CPUPPCState *env, target_ulong value)
  */
 target_ulong helper_load_dpdes(CPUPPCState *env)
 {
+    CPUState *cs = env_cpu(env);
+    CPUState *ccs;
+    uint32_t nr_threads = cs->nr_threads;
     target_ulong dpdes = 0;
 
     helper_hfscr_facility_check(env, HFSCR_MSGP, "load DPDES", HFSCR_IC_MSGP);
 
-    /* TODO: TCG supports only one thread */
-    if (env->pending_interrupts & PPC_INTERRUPT_DOORBELL) {
-        dpdes = 1;
+    if (nr_threads == 1) {
+        if (env->pending_interrupts & PPC_INTERRUPT_DOORBELL) {
+            dpdes = 1;
+        }
+        return dpdes;
+    }
+
+    qemu_mutex_lock_iothread();
+    THREAD_SIBLING_FOREACH(cs, ccs) {
+        PowerPCCPU *ccpu = POWERPC_CPU(ccs);
+        CPUPPCState *cenv = &ccpu->env;
+        uint32_t thread_id = ppc_cpu_tir(ccpu);
+
+        if (cenv->pending_interrupts & PPC_INTERRUPT_DOORBELL) {
+            dpdes |= (0x1 << thread_id);
+        }
     }
+    qemu_mutex_unlock_iothread();
 
     return dpdes;
 }
@@ -199,17 +216,32 @@ target_ulong helper_load_dpdes(CPUPPCState *env)
 void helper_store_dpdes(CPUPPCState *env, target_ulong val)
 {
     PowerPCCPU *cpu = env_archcpu(env);
+    CPUState *cs = env_cpu(env);
+    CPUState *ccs;
+    uint32_t nr_threads = cs->nr_threads;
 
     helper_hfscr_facility_check(env, HFSCR_MSGP, "store DPDES", HFSCR_IC_MSGP);
 
-    /* TODO: TCG supports only one thread */
-    if (val & ~0x1) {
+    if (val & ~(nr_threads - 1)) {
         qemu_log_mask(LOG_GUEST_ERROR, "Invalid DPDES register value "
                       TARGET_FMT_lx"\n", val);
+        val &= (nr_threads - 1); /* Ignore the invalid bits */
+    }
+
+    if (nr_threads == 1) {
+        /* XXX: don't need iothread lock (does ppc_set_irq takes it?) */
+        ppc_set_irq(cpu, PPC_INTERRUPT_DOORBELL, val & 0x1);
         return;
     }
 
-    ppc_set_irq(cpu, PPC_INTERRUPT_DOORBELL, val & 0x1);
+    qemu_mutex_lock_iothread();
+    THREAD_SIBLING_FOREACH(cs, ccs) {
+        PowerPCCPU *ccpu = POWERPC_CPU(ccs);
+        uint32_t thread_id = ppc_cpu_tir(ccpu);
+
+        ppc_set_irq(cpu, PPC_INTERRUPT_DOORBELL, val & (0x1 << thread_id));
+    }
+    qemu_mutex_unlock_iothread();
 }
 #endif /* defined(TARGET_PPC64) */
 
diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index 31821f92f5..0aa49323d3 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -820,11 +820,19 @@ void spr_write_pcr(DisasContext *ctx, int sprn, int gprn)
 /* DPDES */
 void spr_read_dpdes(DisasContext *ctx, int gprn, int sprn)
 {
+    if (!gen_serialize_core(ctx)) {
+        return;
+    }
+
     gen_helper_load_dpdes(cpu_gpr[gprn], cpu_env);
 }
 
 void spr_write_dpdes(DisasContext *ctx, int sprn, int gprn)
 {
+    if (!gen_serialize_core(ctx)) {
+        return;
+    }
+
     gen_helper_store_dpdes(cpu_env, cpu_gpr[gprn]);
 }
 #endif
-- 
2.40.1