ppc: Do some batching of TCG tlb flushes

On ppc64 especially, we flush the tlb on any slbie or tlbie instruction.

However, those instructions often come in bursts of 3 or more (context
switch will favor a series of slbie's for example to an slbia if the
SLB has less than a certain number of entries in it, and tlbie's can
happen in a series, with PAPR, H_BULK_REMOVE can remove up to 4 entries
at a time.

Doing a tlb_flush() each time is a waste of time. We end up doing a memset
of the whole TLB, reloading it for the next instruction, memset'ing again,
etc...

Those instructions don't have to take effect immediately. For slbie, they
can wait for the next context synchronizing event. For tlbie, the next
tlbsync.

This implements batching by keeping a flag that indicates that we have a
TLB in need of flushing. We check it on interrupts, rfi's, isync's and
tlbsync and flush the TLB if needed.

This reduces the number of tlb_flush() on a boot to a ubuntu installer
first dialog screen from roughly 360K down to 36K.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
[clg: added a 'CPUPPCState *' variable in h_remove() and
      h_bulk_remove() ]
Signed-off-by: Cédric Le Goater <clg@kaod.org>
[dwg: removed spurious whitespace change, use 0/1 not true/false
      consistently, since tlb_need_flush has int type]
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

1 files changed, 11 insertions, 3 deletions

diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c
index feb3629664..9a3f4ecc1e 100644
--- a/hw/ppc/spapr_hcall.c
+++ b/hw/ppc/spapr_hcall.c
@@ -186,6 +186,7 @@ static RemoveResult remove_hpte(PowerPCCPU *cpu, target_ulong ptex,
 static target_ulong h_remove(PowerPCCPU *cpu, sPAPRMachineState *spapr,
                              target_ulong opcode, target_ulong *args)
 {
+    CPUPPCState *env = &cpu->env;
     target_ulong flags = args[0];
     target_ulong pte_index = args[1];
     target_ulong avpn = args[2];
@@ -196,6 +197,7 @@ static target_ulong h_remove(PowerPCCPU *cpu, sPAPRMachineState *spapr,
 
     switch (ret) {
     case REMOVE_SUCCESS:
+        check_tlb_flush(env);
         return H_SUCCESS;
 
     case REMOVE_NOT_FOUND:
@@ -232,7 +234,9 @@ static target_ulong h_remove(PowerPCCPU *cpu, sPAPRMachineState *spapr,
 static target_ulong h_bulk_remove(PowerPCCPU *cpu, sPAPRMachineState *spapr,
                                   target_ulong opcode, target_ulong *args)
 {
+    CPUPPCState *env = &cpu->env;
     int i;
+    target_ulong rc = H_SUCCESS;
 
     for (i = 0; i < H_BULK_REMOVE_MAX_BATCH; i++) {
         target_ulong *tsh = &args[i*2];
@@ -265,14 +269,18 @@ static target_ulong h_bulk_remove(PowerPCCPU *cpu, sPAPRMachineState *spapr,
             break;
 
         case REMOVE_PARM:
-            return H_PARAMETER;
+            rc = H_PARAMETER;
+            goto exit;
 
         case REMOVE_HW:
-            return H_HARDWARE;
+            rc = H_HARDWARE;
+            goto exit;
         }
     }
+ exit:
+    check_tlb_flush(env);
 
-    return H_SUCCESS;
+    return rc;
 }
 
 static target_ulong h_protect(PowerPCCPU *cpu, sPAPRMachineState *spapr,