aboutsummaryrefslogtreecommitdiff
path: root/target/arm/translate.c
diff options
context:
space:
mode:
Diffstat (limited to 'target/arm/translate.c')
-rw-r--r--target/arm/translate.c241
1 files changed, 228 insertions, 13 deletions
diff --git a/target/arm/translate.c b/target/arm/translate.c
index d34c1d351a..38371db540 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -2490,17 +2490,23 @@ static void gen_goto_tb(DisasContext *s, int n, target_ulong dest)
s->base.is_jmp = DISAS_NORETURN;
}
-static inline void gen_jmp (DisasContext *s, uint32_t dest)
+/* Jump, specifying which TB number to use if we gen_goto_tb() */
+static inline void gen_jmp_tb(DisasContext *s, uint32_t dest, int tbno)
{
if (unlikely(is_singlestepping(s))) {
/* An indirect jump so that we still trigger the debug exception. */
gen_set_pc_im(s, dest);
s->base.is_jmp = DISAS_JUMP;
} else {
- gen_goto_tb(s, 0, dest);
+ gen_goto_tb(s, tbno, dest);
}
}
+static inline void gen_jmp(DisasContext *s, uint32_t dest)
+{
+ gen_jmp_tb(s, dest, 0);
+}
+
static inline void gen_mulxy(TCGv_i32 t0, TCGv_i32 t1, int x, int y)
{
if (x)
@@ -7401,22 +7407,60 @@ static bool op_smlad(DisasContext *s, arg_rrrr *a, bool m_swap, bool sub)
gen_smul_dual(t1, t2);
if (sub) {
- /* This subtraction cannot overflow. */
- tcg_gen_sub_i32(t1, t1, t2);
- } else {
/*
- * This addition cannot overflow 32 bits; however it may
- * overflow considered as a signed operation, in which case
- * we must set the Q flag.
+ * This subtraction cannot overflow, so we can do a simple
+ * 32-bit subtraction and then a possible 32-bit saturating
+ * addition of Ra.
*/
- gen_helper_add_setq(t1, cpu_env, t1, t2);
- }
- tcg_temp_free_i32(t2);
+ tcg_gen_sub_i32(t1, t1, t2);
+ tcg_temp_free_i32(t2);
- if (a->ra != 15) {
- t2 = load_reg(s, a->ra);
+ if (a->ra != 15) {
+ t2 = load_reg(s, a->ra);
+ gen_helper_add_setq(t1, cpu_env, t1, t2);
+ tcg_temp_free_i32(t2);
+ }
+ } else if (a->ra == 15) {
+ /* Single saturation-checking addition */
gen_helper_add_setq(t1, cpu_env, t1, t2);
tcg_temp_free_i32(t2);
+ } else {
+ /*
+ * We need to add the products and Ra together and then
+ * determine whether the final result overflowed. Doing
+ * this as two separate add-and-check-overflow steps incorrectly
+ * sets Q for cases like (-32768 * -32768) + (-32768 * -32768) + -1.
+ * Do all the arithmetic at 64-bits and then check for overflow.
+ */
+ TCGv_i64 p64, q64;
+ TCGv_i32 t3, qf, one;
+
+ p64 = tcg_temp_new_i64();
+ q64 = tcg_temp_new_i64();
+ tcg_gen_ext_i32_i64(p64, t1);
+ tcg_gen_ext_i32_i64(q64, t2);
+ tcg_gen_add_i64(p64, p64, q64);
+ load_reg_var(s, t2, a->ra);
+ tcg_gen_ext_i32_i64(q64, t2);
+ tcg_gen_add_i64(p64, p64, q64);
+ tcg_temp_free_i64(q64);
+
+ tcg_gen_extr_i64_i32(t1, t2, p64);
+ tcg_temp_free_i64(p64);
+ /*
+ * t1 is the low half of the result which goes into Rd.
+ * We have overflow and must set Q if the high half (t2)
+ * is different from the sign-extension of t1.
+ */
+ t3 = tcg_temp_new_i32();
+ tcg_gen_sari_i32(t3, t1, 31);
+ qf = load_cpu_field(QF);
+ one = tcg_const_i32(1);
+ tcg_gen_movcond_i32(TCG_COND_NE, qf, t2, t3, one, qf);
+ store_cpu_field(qf, QF);
+ tcg_temp_free_i32(one);
+ tcg_temp_free_i32(t3);
+ tcg_temp_free_i32(t2);
}
store_reg(s, a->rd, t1);
return true;
@@ -7880,6 +7924,14 @@ static bool trans_BLX_i(DisasContext *s, arg_BLX_i *a)
{
TCGv_i32 tmp;
+ /*
+ * BLX <imm> would be useless on M-profile; the encoding space
+ * is used for other insns from v8.1M onward, and UNDEFs before that.
+ */
+ if (arm_dc_feature(s, ARM_FEATURE_M)) {
+ return false;
+ }
+
/* For A32, ARM_FEATURE_V5 is checked near the start of the uncond block. */
if (s->thumb && (a->imm & 2)) {
return false;
@@ -7925,6 +7977,109 @@ static bool trans_BLX_suffix(DisasContext *s, arg_BLX_suffix *a)
return true;
}
+static bool trans_BF(DisasContext *s, arg_BF *a)
+{
+ /*
+ * M-profile branch future insns. The architecture permits an
+ * implementation to implement these as NOPs (equivalent to
+ * discarding the LO_BRANCH_INFO cache immediately), and we
+ * take that IMPDEF option because for QEMU a "real" implementation
+ * would be complicated and wouldn't execute any faster.
+ */
+ if (!dc_isar_feature(aa32_lob, s)) {
+ return false;
+ }
+ if (a->boff == 0) {
+ /* SEE "Related encodings" (loop insns) */
+ return false;
+ }
+ /* Handle as NOP */
+ return true;
+}
+
+static bool trans_DLS(DisasContext *s, arg_DLS *a)
+{
+ /* M-profile low-overhead loop start */
+ TCGv_i32 tmp;
+
+ if (!dc_isar_feature(aa32_lob, s)) {
+ return false;
+ }
+ if (a->rn == 13 || a->rn == 15) {
+ /* CONSTRAINED UNPREDICTABLE: we choose to UNDEF */
+ return false;
+ }
+
+ /* Not a while loop, no tail predication: just set LR to the count */
+ tmp = load_reg(s, a->rn);
+ store_reg(s, 14, tmp);
+ return true;
+}
+
+static bool trans_WLS(DisasContext *s, arg_WLS *a)
+{
+ /* M-profile low-overhead while-loop start */
+ TCGv_i32 tmp;
+ TCGLabel *nextlabel;
+
+ if (!dc_isar_feature(aa32_lob, s)) {
+ return false;
+ }
+ if (a->rn == 13 || a->rn == 15) {
+ /* CONSTRAINED UNPREDICTABLE: we choose to UNDEF */
+ return false;
+ }
+ if (s->condexec_mask) {
+ /*
+ * WLS in an IT block is CONSTRAINED UNPREDICTABLE;
+ * we choose to UNDEF, because otherwise our use of
+ * gen_goto_tb(1) would clash with the use of TB exit 1
+ * in the dc->condjmp condition-failed codepath in
+ * arm_tr_tb_stop() and we'd get an assertion.
+ */
+ return false;
+ }
+ nextlabel = gen_new_label();
+ tcg_gen_brcondi_i32(TCG_COND_EQ, cpu_R[a->rn], 0, nextlabel);
+ tmp = load_reg(s, a->rn);
+ store_reg(s, 14, tmp);
+ gen_jmp_tb(s, s->base.pc_next, 1);
+
+ gen_set_label(nextlabel);
+ gen_jmp(s, read_pc(s) + a->imm);
+ return true;
+}
+
+static bool trans_LE(DisasContext *s, arg_LE *a)
+{
+ /*
+ * M-profile low-overhead loop end. The architecture permits an
+ * implementation to discard the LO_BRANCH_INFO cache at any time,
+ * and we take the IMPDEF option to never set it in the first place
+ * (equivalent to always discarding it immediately), because for QEMU
+ * a "real" implementation would be complicated and wouldn't execute
+ * any faster.
+ */
+ TCGv_i32 tmp;
+
+ if (!dc_isar_feature(aa32_lob, s)) {
+ return false;
+ }
+
+ if (!a->f) {
+ /* Not loop-forever. If LR <= 1 this is the last loop: do nothing. */
+ arm_gen_condlabel(s);
+ tcg_gen_brcondi_i32(TCG_COND_LEU, cpu_R[14], 1, s->condlabel);
+ /* Decrement LR */
+ tmp = load_reg(s, 14);
+ tcg_gen_addi_i32(tmp, tmp, -1);
+ store_reg(s, 14, tmp);
+ }
+ /* Jump back to the loop start */
+ gen_jmp(s, read_pc(s) - a->imm);
+ return true;
+}
+
static bool op_tbranch(DisasContext *s, arg_tbranch *a, bool half)
{
TCGv_i32 addr, tmp;
@@ -8224,6 +8379,66 @@ static bool trans_IT(DisasContext *s, arg_IT *a)
return true;
}
+/* v8.1M CSEL/CSINC/CSNEG/CSINV */
+static bool trans_CSEL(DisasContext *s, arg_CSEL *a)
+{
+ TCGv_i32 rn, rm, zero;
+ DisasCompare c;
+
+ if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) {
+ return false;
+ }
+
+ if (a->rm == 13) {
+ /* SEE "Related encodings" (MVE shifts) */
+ return false;
+ }
+
+ if (a->rd == 13 || a->rd == 15 || a->rn == 13 || a->fcond >= 14) {
+ /* CONSTRAINED UNPREDICTABLE: we choose to UNDEF */
+ return false;
+ }
+
+ /* In this insn input reg fields of 0b1111 mean "zero", not "PC" */
+ if (a->rn == 15) {
+ rn = tcg_const_i32(0);
+ } else {
+ rn = load_reg(s, a->rn);
+ }
+ if (a->rm == 15) {
+ rm = tcg_const_i32(0);
+ } else {
+ rm = load_reg(s, a->rm);
+ }
+
+ switch (a->op) {
+ case 0: /* CSEL */
+ break;
+ case 1: /* CSINC */
+ tcg_gen_addi_i32(rm, rm, 1);
+ break;
+ case 2: /* CSINV */
+ tcg_gen_not_i32(rm, rm);
+ break;
+ case 3: /* CSNEG */
+ tcg_gen_neg_i32(rm, rm);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ arm_test_cc(&c, a->fcond);
+ zero = tcg_const_i32(0);
+ tcg_gen_movcond_i32(c.cond, rn, c.value, zero, rn, rm);
+ arm_free_cc(&c);
+ tcg_temp_free_i32(zero);
+
+ store_reg(s, a->rd, rn);
+ tcg_temp_free_i32(rm);
+
+ return true;
+}
+
/*
* Legacy decoder.
*/
generated by cgit v1.2.3 (git 2.26.2) at 2025-01-10 03:34:19 +0000