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, 36 insertions, 3 deletions

diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index b757634b11..dfd3010815 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -3275,9 +3275,32 @@ static void gen_eieio(DisasContext *ctx)
 {
 }
 
+#if !defined(CONFIG_USER_ONLY) && defined(TARGET_PPC64)
+static inline void gen_check_tlb_flush(DisasContext *ctx)
+{
+    TCGv_i32 t = tcg_temp_new_i32();
+    TCGLabel *l = gen_new_label();
+
+    tcg_gen_ld_i32(t, cpu_env, offsetof(CPUPPCState, tlb_need_flush));
+    tcg_gen_brcondi_i32(TCG_COND_EQ, t, 0, l);
+    gen_helper_check_tlb_flush(cpu_env);
+    gen_set_label(l);
+    tcg_temp_free_i32(t);
+}
+#else
+static inline void gen_check_tlb_flush(DisasContext *ctx) { }
+#endif
+
 /* isync */
 static void gen_isync(DisasContext *ctx)
 {
+    /*
+     * We need to check for a pending TLB flush. This can only happen in
+     * kernel mode however so check MSR_PR
+     */
+    if (!ctx->pr) {
+        gen_check_tlb_flush(ctx);
+    }
     gen_stop_exception(ctx);
 }
 
@@ -3434,6 +3457,15 @@ STCX(stqcx_, 16);
 /* sync */
 static void gen_sync(DisasContext *ctx)
 {
+    uint32_t l = (ctx->opcode >> 21) & 3;
+
+    /*
+     * For l == 2, it's a ptesync, We need to check for a pending TLB flush.
+     * This can only happen in kernel mode however so check MSR_PR as well.
+     */
+    if (l == 2 && !ctx->pr) {
+        gen_check_tlb_flush(ctx);
+    }
 }
 
 /* wait */
@@ -4851,10 +4883,11 @@ static void gen_tlbsync(DisasContext *ctx)
         gen_inval_exception(ctx, POWERPC_EXCP_PRIV_OPC);
         return;
     }
-    /* This has no effect: it should ensure that all previous
-     * tlbie have completed
+    /* tlbsync is a nop for server, ptesync handles delayed tlb flush,
+     * embedded however needs to deal with tlbsync. We don't try to be
+     * fancy and swallow the overhead of checking for both.
      */
-    gen_stop_exception(ctx);
+    gen_check_tlb_flush(ctx);
 #endif
 }