[Qemu-devel] [PATCH v6 3/3] target-ppc: tlbie/tlbivax should have global effect

[Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>]

tlbie (BookS) and tlbivax (BookE) plus the H_CALLs(pseries) should have
a global effect.

Introduces TLB_NEED_GLOBAL_FLUSH flag. During lazy tlb flush, after
taking care of pending local flushes, check broadcast flush(at context
synchronizing event ptesync/tlbsync, etc) is needed. Depending on the
bitmask state of the tlb_need_flush, tlb is flushed from other cpus if
needed and the flags are cleared.

Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Nikunj A Dadhania <nikunj@linux.vnet.ibm.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
 hw/ppc/spapr_hcall.c     |  2 ++
 target-ppc/cpu.h         |  1 +
 target-ppc/helper_regs.h | 17 +++++++++++++++++
 target-ppc/mmu-hash64.c  |  2 +-
 target-ppc/mmu_helper.c  | 10 +++++++---
 target-ppc/translate.c   |  6 ++++++
 6 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c
index 0884e3e..c56a9de 100644
--- a/hw/ppc/spapr_hcall.c
+++ b/hw/ppc/spapr_hcall.c
@@ -319,6 +319,8 @@ static target_ulong h_protect(PowerPCCPU *cpu, sPAPRMachineState *spapr,
     ppc_hash64_store_hpte(cpu, pte_index,
                           (v & ~HPTE64_V_VALID) | HPTE64_V_HPTE_DIRTY, 0);
     ppc_hash64_tlb_flush_hpte(cpu, pte_index, v, r);
+    /* Flush the tlb */
+    check_tlb_flush(env, 1);
     /* Don't need a memory barrier, due to qemu's global lock */
     ppc_hash64_store_hpte(cpu, pte_index, v | HPTE64_V_HPTE_DIRTY, r);
     return H_SUCCESS;
diff --git a/target-ppc/cpu.h b/target-ppc/cpu.h
index 96d2def..1c90adb 100644
--- a/target-ppc/cpu.h
+++ b/target-ppc/cpu.h
@@ -1010,6 +1010,7 @@ struct CPUPPCState {
     bool kvm_sw_tlb;  /* non-zero if KVM SW TLB API is active                */
     uint32_t tlb_need_flush; /* Delayed flush needed */
 #define TLB_NEED_LOCAL_FLUSH   0x1
+#define TLB_NEED_GLOBAL_FLUSH  0x2
 #endif
 
     /* Other registers */
diff --git a/target-ppc/helper_regs.h b/target-ppc/helper_regs.h
index dd85fc5..bb9ce60 100644
--- a/target-ppc/helper_regs.h
+++ b/target-ppc/helper_regs.h
@@ -161,6 +161,23 @@ static inline void check_tlb_flush(CPUPPCState *env, bool global)
         tlb_flush(cs, 1);
         env->tlb_need_flush &= ~TLB_NEED_LOCAL_FLUSH;
     }
+
+    /* Propagate TLB invalidations to other CPUs when the guest uses broadcast
+     * TLB invalidation instructions.
+     */
+    if (global && (env->tlb_need_flush & TLB_NEED_GLOBAL_FLUSH)) {
+        CPUState *other_cs;
+        CPU_FOREACH(other_cs) {
+            if (other_cs != cs) {
+                PowerPCCPU *cpu = POWERPC_CPU(other_cs);
+                CPUPPCState *other_env = &cpu->env;
+
+                other_env->tlb_need_flush &= ~TLB_NEED_LOCAL_FLUSH;
+                tlb_flush(other_cs, 1);
+            }
+        }
+        env->tlb_need_flush &= ~TLB_NEED_GLOBAL_FLUSH;
+    }
 }
 #else
 static inline void check_tlb_flush(CPUPPCState *env, bool global) { }
diff --git a/target-ppc/mmu-hash64.c b/target-ppc/mmu-hash64.c
index 1f52b64..fdb7a78 100644
--- a/target-ppc/mmu-hash64.c
+++ b/target-ppc/mmu-hash64.c
@@ -912,7 +912,7 @@ void ppc_hash64_tlb_flush_hpte(PowerPCCPU *cpu,
      * invalidate, and we still don't have a tlb_flush_mask(env, n,
      * mask) in QEMU, we just invalidate all TLBs
      */
-    tlb_flush(CPU(cpu), 1);
+    cpu->env.tlb_need_flush = TLB_NEED_GLOBAL_FLUSH | TLB_NEED_LOCAL_FLUSH;
 }
 
 void ppc_hash64_update_rmls(CPUPPCState *env)
diff --git a/target-ppc/mmu_helper.c b/target-ppc/mmu_helper.c
index 0124150..d09fc0a 100644
--- a/target-ppc/mmu_helper.c
+++ b/target-ppc/mmu_helper.c
@@ -2757,7 +2757,7 @@ static inline void booke206_invalidate_ea_tlb(CPUPPCState *env, int tlbn,
 
 void helper_booke206_tlbivax(CPUPPCState *env, target_ulong address)
 {
-    PowerPCCPU *cpu = ppc_env_get_cpu(env);
+    CPUState *cs;
 
     if (address & 0x4) {
         /* flush all entries */
@@ -2774,11 +2774,15 @@ void helper_booke206_tlbivax(CPUPPCState *env, target_ulong address)
     if (address & 0x8) {
         /* flush TLB1 entries */
         booke206_invalidate_ea_tlb(env, 1, address);
-        tlb_flush(CPU(cpu), 1);
+        CPU_FOREACH(cs) {
+            tlb_flush(cs, 1);
+        }
     } else {
         /* flush TLB0 entries */
         booke206_invalidate_ea_tlb(env, 0, address);
-        tlb_flush_page(CPU(cpu), address & MAS2_EPN_MASK);
+        CPU_FOREACH(cs) {
+            tlb_flush_page(cs, address & MAS2_EPN_MASK);
+        }
     }
 }
 
diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index df63b4f..bfadb3b 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -4422,6 +4422,7 @@ static void gen_tlbie(DisasContext *ctx)
 #if defined(CONFIG_USER_ONLY)
     GEN_PRIV;
 #else
+    TCGv_i32 t1;
     CHK_HV;
 
     if (NARROW_MODE(ctx)) {
@@ -4432,6 +4433,11 @@ static void gen_tlbie(DisasContext *ctx)
     } else {
         gen_helper_tlbie(cpu_env, cpu_gpr[rB(ctx->opcode)]);
     }
+    t1 = tcg_temp_new_i32();
+    tcg_gen_ld_i32(t1, cpu_env, offsetof(CPUPPCState, tlb_need_flush));
+    tcg_gen_ori_i32(t1, t1, TLB_NEED_GLOBAL_FLUSH);
+    tcg_gen_st_i32(t1, cpu_env, offsetof(CPUPPCState, tlb_need_flush));
+    tcg_temp_free_i32(t1);
 #endif /* defined(CONFIG_USER_ONLY) */
 }
 
-- 
2.7.4