[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH 1/3] tcg/s390: Change FACILITY representation
|
From: |
Richard Henderson |
|
Subject: |
[PATCH 1/3] tcg/s390: Change FACILITY representation |
|
Date: |
Fri, 8 May 2020 08:57:43 -0700 |
We will shortly need to be able to check facilities
beyond the first 64. Instead of explicitly masking
against s390_facilities, create a FACILITY macro
that indexes an array.
Signed-off-by: Richard Henderson <address@hidden>
---
tcg/s390/tcg-target.h | 29 ++++++++-------
tcg/s390/tcg-target.inc.c | 74 +++++++++++++++++++--------------------
2 files changed, 52 insertions(+), 51 deletions(-)
diff --git a/tcg/s390/tcg-target.h b/tcg/s390/tcg-target.h
index 07accabbd1..7ca48457ff 100644
--- a/tcg/s390/tcg-target.h
+++ b/tcg/s390/tcg-target.h
@@ -52,16 +52,19 @@ typedef enum TCGReg {
/* A list of relevant facilities used by this translator. Some of these
are required for proper operation, and these are checked at startup. */
-#define FACILITY_ZARCH_ACTIVE (1ULL << (63 - 2))
-#define FACILITY_LONG_DISP (1ULL << (63 - 18))
-#define FACILITY_EXT_IMM (1ULL << (63 - 21))
-#define FACILITY_GEN_INST_EXT (1ULL << (63 - 34))
-#define FACILITY_LOAD_ON_COND (1ULL << (63 - 45))
+#define FACILITY_ZARCH_ACTIVE 2
+#define FACILITY_LONG_DISP 18
+#define FACILITY_EXT_IMM 21
+#define FACILITY_GEN_INST_EXT 34
+#define FACILITY_LOAD_ON_COND 45
#define FACILITY_FAST_BCR_SER FACILITY_LOAD_ON_COND
#define FACILITY_DISTINCT_OPS FACILITY_LOAD_ON_COND
-#define FACILITY_LOAD_ON_COND2 (1ULL << (63 - 53))
+#define FACILITY_LOAD_ON_COND2 53
-extern uint64_t s390_facilities;
+extern uint64_t s390_facilities[1];
+
+#define FACILITY(X) \
+ ((s390_facilities[FACILITY_##X / 64] >> (63 - FACILITY_##X % 64)) & 1)
/* optional instructions */
#define TCG_TARGET_HAS_div2_i32 1
@@ -82,8 +85,8 @@ extern uint64_t s390_facilities;
#define TCG_TARGET_HAS_clz_i32 0
#define TCG_TARGET_HAS_ctz_i32 0
#define TCG_TARGET_HAS_ctpop_i32 0
-#define TCG_TARGET_HAS_deposit_i32 (s390_facilities & FACILITY_GEN_INST_EXT)
-#define TCG_TARGET_HAS_extract_i32 (s390_facilities & FACILITY_GEN_INST_EXT)
+#define TCG_TARGET_HAS_deposit_i32 FACILITY(GEN_INST_EXT)
+#define TCG_TARGET_HAS_extract_i32 FACILITY(GEN_INST_EXT)
#define TCG_TARGET_HAS_sextract_i32 0
#define TCG_TARGET_HAS_extract2_i32 0
#define TCG_TARGET_HAS_movcond_i32 1
@@ -96,7 +99,7 @@ extern uint64_t s390_facilities;
#define TCG_TARGET_HAS_extrl_i64_i32 0
#define TCG_TARGET_HAS_extrh_i64_i32 0
#define TCG_TARGET_HAS_goto_ptr 1
-#define TCG_TARGET_HAS_direct_jump (s390_facilities & FACILITY_GEN_INST_EXT)
+#define TCG_TARGET_HAS_direct_jump FACILITY(GEN_INST_EXT)
#define TCG_TARGET_HAS_div2_i64 1
#define TCG_TARGET_HAS_rot_i64 1
@@ -116,11 +119,11 @@ extern uint64_t s390_facilities;
#define TCG_TARGET_HAS_eqv_i64 0
#define TCG_TARGET_HAS_nand_i64 0
#define TCG_TARGET_HAS_nor_i64 0
-#define TCG_TARGET_HAS_clz_i64 (s390_facilities & FACILITY_EXT_IMM)
+#define TCG_TARGET_HAS_clz_i64 FACILITY(EXT_IMM)
#define TCG_TARGET_HAS_ctz_i64 0
#define TCG_TARGET_HAS_ctpop_i64 0
-#define TCG_TARGET_HAS_deposit_i64 (s390_facilities & FACILITY_GEN_INST_EXT)
-#define TCG_TARGET_HAS_extract_i64 (s390_facilities & FACILITY_GEN_INST_EXT)
+#define TCG_TARGET_HAS_deposit_i64 FACILITY(GEN_INST_EXT)
+#define TCG_TARGET_HAS_extract_i64 FACILITY(GEN_INST_EXT)
#define TCG_TARGET_HAS_sextract_i64 0
#define TCG_TARGET_HAS_extract2_i64 0
#define TCG_TARGET_HAS_movcond_i64 1
diff --git a/tcg/s390/tcg-target.inc.c b/tcg/s390/tcg-target.inc.c
index b07e9ff7d6..123286857f 100644
--- a/tcg/s390/tcg-target.inc.c
+++ b/tcg/s390/tcg-target.inc.c
@@ -53,7 +53,7 @@
We don't need this when we have pc-relative loads with the general
instructions extension facility. */
#define TCG_REG_TB TCG_REG_R12
-#define USE_REG_TB (!(s390_facilities & FACILITY_GEN_INST_EXT))
+#define USE_REG_TB (!FACILITY(GEN_INST_EXT))
#ifndef CONFIG_SOFTMMU
#define TCG_GUEST_BASE_REG TCG_REG_R13
@@ -364,7 +364,7 @@ static void * const qemu_st_helpers[16] = {
#endif
static tcg_insn_unit *tb_ret_addr;
-uint64_t s390_facilities;
+uint64_t s390_facilities[1];
static bool patch_reloc(tcg_insn_unit *code_ptr, int type,
intptr_t value, intptr_t addend)
@@ -610,7 +610,7 @@ static void tcg_out_movi_int(TCGContext *s, TCGType type,
TCGReg ret,
}
/* Try all 48-bit insns that can load it in one go. */
- if (s390_facilities & FACILITY_EXT_IMM) {
+ if (FACILITY(EXT_IMM)) {
if (sval == (int32_t)sval) {
tcg_out_insn(s, RIL, LGFI, ret, sval);
return;
@@ -653,7 +653,7 @@ static void tcg_out_movi_int(TCGContext *s, TCGType type,
TCGReg ret,
}
/* Otherwise, stuff it in the constant pool. */
- if (s390_facilities & FACILITY_GEN_INST_EXT) {
+ if (FACILITY(GEN_INST_EXT)) {
tcg_out_insn(s, RIL, LGRL, ret, 0);
new_pool_label(s, sval, R_390_PC32DBL, s->code_ptr - 2, 2);
} else if (USE_REG_TB && !in_prologue) {
@@ -738,7 +738,7 @@ static void tcg_out_ld_abs(TCGContext *s, TCGType type,
TCGReg dest, void *abs)
{
intptr_t addr = (intptr_t)abs;
- if ((s390_facilities & FACILITY_GEN_INST_EXT) && !(addr & 1)) {
+ if (FACILITY(GEN_INST_EXT) && !(addr & 1)) {
ptrdiff_t disp = tcg_pcrel_diff(s, abs) >> 1;
if (disp == (int32_t)disp) {
if (type == TCG_TYPE_I32) {
@@ -772,7 +772,7 @@ static inline void tcg_out_risbg(TCGContext *s, TCGReg
dest, TCGReg src,
static void tgen_ext8s(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
{
- if (s390_facilities & FACILITY_EXT_IMM) {
+ if (FACILITY(EXT_IMM)) {
tcg_out_insn(s, RRE, LGBR, dest, src);
return;
}
@@ -792,7 +792,7 @@ static void tgen_ext8s(TCGContext *s, TCGType type, TCGReg
dest, TCGReg src)
static void tgen_ext8u(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
{
- if (s390_facilities & FACILITY_EXT_IMM) {
+ if (FACILITY(EXT_IMM)) {
tcg_out_insn(s, RRE, LLGCR, dest, src);
return;
}
@@ -812,7 +812,7 @@ static void tgen_ext8u(TCGContext *s, TCGType type, TCGReg
dest, TCGReg src)
static void tgen_ext16s(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
{
- if (s390_facilities & FACILITY_EXT_IMM) {
+ if (FACILITY(EXT_IMM)) {
tcg_out_insn(s, RRE, LGHR, dest, src);
return;
}
@@ -832,7 +832,7 @@ static void tgen_ext16s(TCGContext *s, TCGType type, TCGReg
dest, TCGReg src)
static void tgen_ext16u(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
{
- if (s390_facilities & FACILITY_EXT_IMM) {
+ if (FACILITY(EXT_IMM)) {
tcg_out_insn(s, RRE, LLGHR, dest, src);
return;
}
@@ -920,7 +920,7 @@ static void tgen_andi(TCGContext *s, TCGType type, TCGReg
dest, uint64_t val)
tgen_ext32u(s, dest, dest);
return;
}
- if (s390_facilities & FACILITY_EXT_IMM) {
+ if (FACILITY(EXT_IMM)) {
if ((val & valid) == 0xff) {
tgen_ext8u(s, TCG_TYPE_I64, dest, dest);
return;
@@ -941,7 +941,7 @@ static void tgen_andi(TCGContext *s, TCGType type, TCGReg
dest, uint64_t val)
}
/* Try all 48-bit insns that can perform it in one go. */
- if (s390_facilities & FACILITY_EXT_IMM) {
+ if (FACILITY(EXT_IMM)) {
for (i = 0; i < 2; i++) {
tcg_target_ulong mask = ~(0xffffffffull << i*32);
if (((val | ~valid) & mask) == mask) {
@@ -950,7 +950,7 @@ static void tgen_andi(TCGContext *s, TCGType type, TCGReg
dest, uint64_t val)
}
}
}
- if ((s390_facilities & FACILITY_GEN_INST_EXT) && risbg_mask(val)) {
+ if (FACILITY(GEN_INST_EXT) && risbg_mask(val)) {
tgen_andi_risbg(s, dest, dest, val);
return;
}
@@ -999,7 +999,7 @@ static void tgen_ori(TCGContext *s, TCGType type, TCGReg
dest, uint64_t val)
}
/* Try all 48-bit insns that can perform it in one go. */
- if (s390_facilities & FACILITY_EXT_IMM) {
+ if (FACILITY(EXT_IMM)) {
for (i = 0; i < 2; i++) {
tcg_target_ulong mask = (0xffffffffull << i*32);
if ((val & mask) != 0 && (val & ~mask) == 0) {
@@ -1024,7 +1024,7 @@ static void tgen_ori(TCGContext *s, TCGType type, TCGReg
dest, uint64_t val)
/* Perform the OR via sequential modifications to the high and
low parts. Do this via recursion to handle 16-bit vs 32-bit
masks in each half. */
- tcg_debug_assert(s390_facilities & FACILITY_EXT_IMM);
+ tcg_debug_assert(FACILITY(EXT_IMM));
tgen_ori(s, type, dest, val & 0x00000000ffffffffull);
tgen_ori(s, type, dest, val & 0xffffffff00000000ull);
}
@@ -1033,7 +1033,7 @@ static void tgen_ori(TCGContext *s, TCGType type, TCGReg
dest, uint64_t val)
static void tgen_xori(TCGContext *s, TCGType type, TCGReg dest, uint64_t val)
{
/* Try all 48-bit insns that can perform it in one go. */
- if (s390_facilities & FACILITY_EXT_IMM) {
+ if (FACILITY(EXT_IMM)) {
if ((val & 0xffffffff00000000ull) == 0) {
tcg_out_insn(s, RIL, XILF, dest, val);
return;
@@ -1057,7 +1057,7 @@ static void tgen_xori(TCGContext *s, TCGType type, TCGReg
dest, uint64_t val)
-(intptr_t)s->code_gen_ptr);
} else {
/* Perform the xor by parts. */
- tcg_debug_assert(s390_facilities & FACILITY_EXT_IMM);
+ tcg_debug_assert(FACILITY(EXT_IMM));
if (val & 0xffffffff) {
tcg_out_insn(s, RIL, XILF, dest, val);
}
@@ -1091,7 +1091,7 @@ static int tgen_cmp(TCGContext *s, TCGType type, TCGCond
c, TCGReg r1,
goto exit;
}
- if (s390_facilities & FACILITY_EXT_IMM) {
+ if (FACILITY(EXT_IMM)) {
if (type == TCG_TYPE_I32) {
op = (is_unsigned ? RIL_CLFI : RIL_CFI);
tcg_out_insn_RIL(s, op, r1, c2);
@@ -1154,7 +1154,7 @@ static void tgen_setcond(TCGContext *s, TCGType type,
TCGCond cond,
bool have_loc;
/* With LOC2, we can always emit the minimum 3 insns. */
- if (s390_facilities & FACILITY_LOAD_ON_COND2) {
+ if (FACILITY(LOAD_ON_COND2)) {
/* Emit: d = 0, d = (cc ? 1 : d). */
cc = tgen_cmp(s, type, cond, c1, c2, c2const, false);
tcg_out_movi(s, TCG_TYPE_I64, dest, 0);
@@ -1162,7 +1162,7 @@ static void tgen_setcond(TCGContext *s, TCGType type,
TCGCond cond,
return;
}
- have_loc = (s390_facilities & FACILITY_LOAD_ON_COND) != 0;
+ have_loc = FACILITY(LOAD_ON_COND);
/* For HAVE_LOC, only the paths through GTU/GT/LEU/LE are smaller. */
restart:
@@ -1248,7 +1248,7 @@ static void tgen_movcond(TCGContext *s, TCGType type,
TCGCond c, TCGReg dest,
TCGArg v3, int v3const)
{
int cc;
- if (s390_facilities & FACILITY_LOAD_ON_COND) {
+ if (FACILITY(LOAD_ON_COND)) {
cc = tgen_cmp(s, type, c, c1, c2, c2const, false);
if (v3const) {
tcg_out_insn(s, RIE, LOCGHI, dest, v3, cc);
@@ -1281,7 +1281,7 @@ static void tgen_clz(TCGContext *s, TCGReg dest, TCGReg
a1,
} else {
tcg_out_mov(s, TCG_TYPE_I64, dest, a2);
}
- if (s390_facilities & FACILITY_LOAD_ON_COND) {
+ if (FACILITY(LOAD_ON_COND)) {
/* Emit: if (one bit found) dest = r0. */
tcg_out_insn(s, RRF, LOCGR, dest, TCG_REG_R0, 2);
} else {
@@ -1373,7 +1373,7 @@ static void tgen_brcond(TCGContext *s, TCGType type,
TCGCond c,
{
int cc;
- if (s390_facilities & FACILITY_GEN_INST_EXT) {
+ if (FACILITY(GEN_INST_EXT)) {
bool is_unsigned = is_unsigned_cond(c);
bool in_range;
S390Opcode opc;
@@ -1567,7 +1567,7 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg
addr_reg, MemOp opc,
cross pages using the address of the last byte of the access. */
a_off = (a_bits >= s_bits ? 0 : s_mask - a_mask);
tlb_mask = (uint64_t)TARGET_PAGE_MASK | a_mask;
- if ((s390_facilities & FACILITY_GEN_INST_EXT) && a_off == 0) {
+ if (FACILITY(GEN_INST_EXT) && a_off == 0) {
tgen_andi_risbg(s, TCG_REG_R3, addr_reg, tlb_mask);
} else {
tcg_out_insn(s, RX, LA, TCG_REG_R3, addr_reg, TCG_REG_NONE, a_off);
@@ -1854,7 +1854,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode
opc,
tcg_out_insn(s, RI, AHI, a0, a2);
break;
}
- if (s390_facilities & FACILITY_EXT_IMM) {
+ if (FACILITY(EXT_IMM)) {
tcg_out_insn(s, RIL, AFI, a0, a2);
break;
}
@@ -2078,7 +2078,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode
opc,
tcg_out_insn(s, RI, AGHI, a0, a2);
break;
}
- if (s390_facilities & FACILITY_EXT_IMM) {
+ if (FACILITY(EXT_IMM)) {
if (a2 == (int32_t)a2) {
tcg_out_insn(s, RIL, AGFI, a0, a2);
break;
@@ -2303,8 +2303,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode
opc,
/* The host memory model is quite strong, we simply need to
serialize the instruction stream. */
if (args[0] & TCG_MO_ST_LD) {
- tcg_out_insn(s, RR, BCR,
- s390_facilities & FACILITY_FAST_BCR_SER ? 14 : 15, 0);
+ tcg_out_insn(s, RR, BCR, FACILITY(FAST_BCR_SER) ? 14 : 15, 0);
}
break;
@@ -2372,20 +2371,20 @@ static const TCGTargetOpDef
*tcg_target_op_def(TCGOpcode op)
case INDEX_op_or_i64:
case INDEX_op_xor_i32:
case INDEX_op_xor_i64:
- return (s390_facilities & FACILITY_DISTINCT_OPS ? &r_r_ri : &r_0_ri);
+ return FACILITY(DISTINCT_OPS) ? &r_r_ri : &r_0_ri;
case INDEX_op_mul_i32:
/* If we have the general-instruction-extensions, then we have
MULTIPLY SINGLE IMMEDIATE with a signed 32-bit, otherwise we
have only MULTIPLY HALFWORD IMMEDIATE, with a signed 16-bit. */
- return (s390_facilities & FACILITY_GEN_INST_EXT ? &r_0_ri : &r_0_rI);
+ return FACILITY(GEN_INST_EXT) ? &r_0_ri : &r_0_rI;
case INDEX_op_mul_i64:
- return (s390_facilities & FACILITY_GEN_INST_EXT ? &r_0_rJ : &r_0_rI);
+ return FACILITY(GEN_INST_EXT) ? &r_0_rJ : &r_0_rI;
case INDEX_op_shl_i32:
case INDEX_op_shr_i32:
case INDEX_op_sar_i32:
- return (s390_facilities & FACILITY_DISTINCT_OPS ? &r_r_ri : &r_0_ri);
+ return FACILITY(DISTINCT_OPS) ? &r_r_ri : &r_0_ri;
case INDEX_op_shl_i64:
case INDEX_op_shr_i64:
@@ -2451,7 +2450,7 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode
op)
= { .args_ct_str = { "r", "r", "ri", "r", "0" } };
static const TCGTargetOpDef movc_l
= { .args_ct_str = { "r", "r", "ri", "rI", "0" } };
- return (s390_facilities & FACILITY_LOAD_ON_COND2 ? &movc_l :
&movc);
+ return FACILITY(LOAD_ON_COND2) ? &movc_l : &movc;
}
case INDEX_op_div2_i32:
case INDEX_op_div2_i64:
@@ -2471,10 +2470,10 @@ static const TCGTargetOpDef
*tcg_target_op_def(TCGOpcode op)
case INDEX_op_add2_i32:
case INDEX_op_sub2_i32:
- return (s390_facilities & FACILITY_EXT_IMM ? &a2_ri : &a2_r);
+ return FACILITY(EXT_IMM) ? &a2_ri : &a2_r;
case INDEX_op_add2_i64:
case INDEX_op_sub2_i64:
- return (s390_facilities & FACILITY_EXT_IMM ? &a2_rA : &a2_r);
+ return FACILITY(EXT_IMM) ? &a2_rA : &a2_r;
default:
break;
@@ -2489,13 +2488,12 @@ static void query_s390_facilities(void)
/* Is STORE FACILITY LIST EXTENDED available? Honestly, I believe this
is present on all 64-bit systems, but let's check for it anyway. */
if (hwcap & HWCAP_S390_STFLE) {
- register int r0 __asm__("0");
- register void *r1 __asm__("1");
+ register int r0 __asm__("0") = ARRAY_SIZE(s390_facilities) - 1;
+ register void *r1 __asm__("1") = s390_facilities;
/* stfle 0(%r1) */
- r1 = &s390_facilities;
asm volatile(".word 0xb2b0,0x1000"
- : "=r"(r0) : "0"(0), "r"(r1) : "memory", "cc");
+ : "=r"(r0) : "r"(r0), "r"(r1) : "memory", "cc");
}
}
--
2.20.1