Merge branch 'usb.64' of git://git.kraxel.org/qemu
* 'usb.64' of git://git.kraxel.org/qemu: (54 commits)
xhci: allow bytewise capability register reads
xhci: kill xhci_mem_{read,write} dispatcher functions
xhci: support multiple interrupters
xhci: pick target interrupter
xhci: prepare xhci_runtime_{read,write} for multiple interrupters
xhci: add XHCIInterrupter
xhci: move register update into xhci_intr_raise
xhci: add msix support
xhci: rework interrupt handling
xhci: fix & cleanup msi.
usb-storage: usb3 support
usb3: bos decriptor
usb3: superspeed endpoint companion
usb3: superspeed descriptors
xhci: update port handling
xhci: update register layout
xhci: fix runtime write tracepoint
xhci: add trace_usb_xhci_ep_set_dequeue
xhci: trace cc codes in cleartext
xhci: iso xfer support
...
diff --git a/tcg/optimize.c b/tcg/optimize.c
index 9c65474..fba0ed9 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -267,6 +267,67 @@
return res;
}
+static TCGArg do_constant_folding_cond(TCGOpcode op, TCGArg x,
+ TCGArg y, TCGCond c)
+{
+ switch (op_bits(op)) {
+ case 32:
+ switch (c) {
+ case TCG_COND_EQ:
+ return (uint32_t)x == (uint32_t)y;
+ case TCG_COND_NE:
+ return (uint32_t)x != (uint32_t)y;
+ case TCG_COND_LT:
+ return (int32_t)x < (int32_t)y;
+ case TCG_COND_GE:
+ return (int32_t)x >= (int32_t)y;
+ case TCG_COND_LE:
+ return (int32_t)x <= (int32_t)y;
+ case TCG_COND_GT:
+ return (int32_t)x > (int32_t)y;
+ case TCG_COND_LTU:
+ return (uint32_t)x < (uint32_t)y;
+ case TCG_COND_GEU:
+ return (uint32_t)x >= (uint32_t)y;
+ case TCG_COND_LEU:
+ return (uint32_t)x <= (uint32_t)y;
+ case TCG_COND_GTU:
+ return (uint32_t)x > (uint32_t)y;
+ }
+ break;
+ case 64:
+ switch (c) {
+ case TCG_COND_EQ:
+ return (uint64_t)x == (uint64_t)y;
+ case TCG_COND_NE:
+ return (uint64_t)x != (uint64_t)y;
+ case TCG_COND_LT:
+ return (int64_t)x < (int64_t)y;
+ case TCG_COND_GE:
+ return (int64_t)x >= (int64_t)y;
+ case TCG_COND_LE:
+ return (int64_t)x <= (int64_t)y;
+ case TCG_COND_GT:
+ return (int64_t)x > (int64_t)y;
+ case TCG_COND_LTU:
+ return (uint64_t)x < (uint64_t)y;
+ case TCG_COND_GEU:
+ return (uint64_t)x >= (uint64_t)y;
+ case TCG_COND_LEU:
+ return (uint64_t)x <= (uint64_t)y;
+ case TCG_COND_GTU:
+ return (uint64_t)x > (uint64_t)y;
+ }
+ break;
+ }
+
+ fprintf(stderr,
+ "Unrecognized bitness %d or condition %d in "
+ "do_constant_folding_cond.\n", op_bits(op), c);
+ tcg_abort();
+}
+
+
/* Propagate constants and copies, fold constant expressions. */
static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
TCGArg *args, TCGOpDef *tcg_op_defs)
@@ -318,11 +379,49 @@
args[2] = tmp;
}
break;
+ CASE_OP_32_64(brcond):
+ if (temps[args[0]].state == TCG_TEMP_CONST
+ && temps[args[1]].state != TCG_TEMP_CONST) {
+ tmp = args[0];
+ args[0] = args[1];
+ args[1] = tmp;
+ args[2] = tcg_swap_cond(args[2]);
+ }
+ break;
+ CASE_OP_32_64(setcond):
+ if (temps[args[1]].state == TCG_TEMP_CONST
+ && temps[args[2]].state != TCG_TEMP_CONST) {
+ tmp = args[1];
+ args[1] = args[2];
+ args[2] = tmp;
+ args[3] = tcg_swap_cond(args[3]);
+ }
+ break;
default:
break;
}
- /* Simplify expression if possible. */
+ /* Simplify expressions for "shift/rot r, 0, a => movi r, 0" */
+ switch (op) {
+ CASE_OP_32_64(shl):
+ CASE_OP_32_64(shr):
+ CASE_OP_32_64(sar):
+ CASE_OP_32_64(rotl):
+ CASE_OP_32_64(rotr):
+ if (temps[args[1]].state == TCG_TEMP_CONST
+ && temps[args[1]].val == 0) {
+ gen_opc_buf[op_index] = op_to_movi(op);
+ tcg_opt_gen_movi(gen_args, args[0], 0, nb_temps, nb_globals);
+ args += 3;
+ gen_args += 2;
+ continue;
+ }
+ break;
+ default:
+ break;
+ }
+
+ /* Simplify expression for "op r, a, 0 => mov r, a" cases */
switch (op) {
CASE_OP_32_64(add):
CASE_OP_32_64(sub):
@@ -331,6 +430,8 @@
CASE_OP_32_64(sar):
CASE_OP_32_64(rotl):
CASE_OP_32_64(rotr):
+ CASE_OP_32_64(or):
+ CASE_OP_32_64(xor):
if (temps[args[1]].state == TCG_TEMP_CONST) {
/* Proceed with possible constant folding. */
break;
@@ -340,18 +441,24 @@
if ((temps[args[0]].state == TCG_TEMP_COPY
&& temps[args[0]].val == args[1])
|| args[0] == args[1]) {
- args += 3;
gen_opc_buf[op_index] = INDEX_op_nop;
} else {
gen_opc_buf[op_index] = op_to_mov(op);
tcg_opt_gen_mov(s, gen_args, args[0], args[1],
nb_temps, nb_globals);
gen_args += 2;
- args += 3;
}
+ args += 3;
continue;
}
break;
+ default:
+ break;
+ }
+
+ /* Simplify expression for "op r, a, 0 => movi r, 0" cases */
+ switch (op) {
+ CASE_OP_32_64(and):
CASE_OP_32_64(mul):
if ((temps[args[2]].state == TCG_TEMP_CONST
&& temps[args[2]].val == 0)) {
@@ -362,19 +469,24 @@
continue;
}
break;
+ default:
+ break;
+ }
+
+ /* Simplify expression for "op r, a, a => mov r, a" cases */
+ switch (op) {
CASE_OP_32_64(or):
CASE_OP_32_64(and):
if (args[1] == args[2]) {
if (args[1] == args[0]) {
- args += 3;
gen_opc_buf[op_index] = INDEX_op_nop;
} else {
gen_opc_buf[op_index] = op_to_mov(op);
tcg_opt_gen_mov(s, gen_args, args[0], args[1], nb_temps,
nb_globals);
gen_args += 2;
- args += 3;
}
+ args += 3;
continue;
}
break;
@@ -424,17 +536,14 @@
gen_opc_buf[op_index] = op_to_movi(op);
tmp = do_constant_folding(op, temps[args[1]].val, 0);
tcg_opt_gen_movi(gen_args, args[0], tmp, nb_temps, nb_globals);
- gen_args += 2;
- args += 2;
- break;
} else {
reset_temp(args[0], nb_temps, nb_globals);
gen_args[0] = args[0];
gen_args[1] = args[1];
- gen_args += 2;
- args += 2;
- break;
}
+ gen_args += 2;
+ args += 2;
+ break;
CASE_OP_32_64(add):
CASE_OP_32_64(sub):
CASE_OP_32_64(mul):
@@ -458,17 +567,56 @@
temps[args[2]].val);
tcg_opt_gen_movi(gen_args, args[0], tmp, nb_temps, nb_globals);
gen_args += 2;
- args += 3;
- break;
} else {
reset_temp(args[0], nb_temps, nb_globals);
gen_args[0] = args[0];
gen_args[1] = args[1];
gen_args[2] = args[2];
gen_args += 3;
- args += 3;
- break;
}
+ args += 3;
+ break;
+ CASE_OP_32_64(setcond):
+ if (temps[args[1]].state == TCG_TEMP_CONST
+ && temps[args[2]].state == TCG_TEMP_CONST) {
+ gen_opc_buf[op_index] = op_to_movi(op);
+ tmp = do_constant_folding_cond(op, temps[args[1]].val,
+ temps[args[2]].val, args[3]);
+ tcg_opt_gen_movi(gen_args, args[0], tmp, nb_temps, nb_globals);
+ gen_args += 2;
+ } else {
+ reset_temp(args[0], nb_temps, nb_globals);
+ gen_args[0] = args[0];
+ gen_args[1] = args[1];
+ gen_args[2] = args[2];
+ gen_args[3] = args[3];
+ gen_args += 4;
+ }
+ args += 4;
+ break;
+ CASE_OP_32_64(brcond):
+ if (temps[args[0]].state == TCG_TEMP_CONST
+ && temps[args[1]].state == TCG_TEMP_CONST) {
+ if (do_constant_folding_cond(op, temps[args[0]].val,
+ temps[args[1]].val, args[2])) {
+ memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
+ gen_opc_buf[op_index] = INDEX_op_br;
+ gen_args[0] = args[3];
+ gen_args += 1;
+ } else {
+ gen_opc_buf[op_index] = INDEX_op_nop;
+ }
+ } else {
+ memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
+ reset_temp(args[0], nb_temps, nb_globals);
+ gen_args[0] = args[0];
+ gen_args[1] = args[1];
+ gen_args[2] = args[2];
+ gen_args[3] = args[3];
+ gen_args += 4;
+ }
+ args += 4;
+ break;
case INDEX_op_call:
nb_call_args = (args[0] >> 16) + (args[0] & 0xffff);
if (!(args[nb_call_args + 1] & (TCG_CALL_CONST | TCG_CALL_PURE))) {
@@ -490,7 +638,6 @@
case INDEX_op_set_label:
case INDEX_op_jmp:
case INDEX_op_br:
- CASE_OP_32_64(brcond):
memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
for (i = 0; i < def->nb_args; i++) {
*gen_args = *args;
diff --git a/tcg/tcg.c b/tcg/tcg.c
index 8386b70..a4e7f42 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -2059,22 +2059,29 @@
}
#endif
+#ifdef CONFIG_PROFILER
+ s->opt_time -= profile_getclock();
+#endif
+
#ifdef USE_TCG_OPTIMIZATIONS
gen_opparam_ptr =
tcg_optimize(s, gen_opc_ptr, gen_opparam_buf, tcg_op_defs);
#endif
#ifdef CONFIG_PROFILER
+ s->opt_time += profile_getclock();
s->la_time -= profile_getclock();
#endif
+
tcg_liveness_analysis(s);
+
#ifdef CONFIG_PROFILER
s->la_time += profile_getclock();
#endif
#ifdef DEBUG_DISAS
if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP_OPT))) {
- qemu_log("OP after liveness analysis:\n");
+ qemu_log("OP after optimization and liveness analysis:\n");
tcg_dump_ops(s);
qemu_log("\n");
}
@@ -2241,6 +2248,9 @@
(double)s->interm_time / tot * 100.0);
cpu_fprintf(f, " gen_code time %0.1f%%\n",
(double)s->code_time / tot * 100.0);
+ cpu_fprintf(f, "optim./code time %0.1f%%\n",
+ (double)s->opt_time / (s->code_time ? s->code_time : 1)
+ * 100.0);
cpu_fprintf(f, "liveness/code time %0.1f%%\n",
(double)s->la_time / (s->code_time ? s->code_time : 1) * 100.0);
cpu_fprintf(f, "cpu_restore count %" PRId64 "\n",
diff --git a/tcg/tcg.h b/tcg/tcg.h
index d710694..7a72729 100644
--- a/tcg/tcg.h
+++ b/tcg/tcg.h
@@ -382,6 +382,7 @@
int64_t interm_time;
int64_t code_time;
int64_t la_time;
+ int64_t opt_time;
int64_t restore_count;
int64_t restore_time;
#endif
