Merge tag 'pull-sparc-20240911' of https://gitlab.com/rth7680/qemu into staging

target/sparc: Implement single entry FP Queue

# -----BEGIN PGP SIGNATURE-----
#
# iQFRBAABCgA7FiEEekgeeIaLTbaoWgXAZN846K9+IV8FAmbifAAdHHJpY2hhcmQu
# aGVuZGVyc29uQGxpbmFyby5vcmcACgkQZN846K9+IV+XAwgAlj//8JuNoRB/2hi0
# gU3Ifjrs+r+AZrcsG7pTOmYTZa6cYqJX4XsYoNq1S4FHky239vNKPQOQEadkmLGv
# wKH0fBjzvydOKRfrhEK2VLlhMyhGyuv59psfCCUB5HZEiueSHFFAvfjUtKNpjzRT
# KE2fwL6iKK3IXeKC6ynq0bkC/OymnLUYSgSslA6C1x1sReNz5Y6ZsGUEZRwODY4f
# q6s6JS2aBn1L9nJTzwXH/J5Ue8iix53d6EZ42QHqqwzRvAWHtfFqoMLc9P6Dg8P7
# FmiwHAErwr7Pj5cqcnl2C0zTp3LXg5xXpTJysi8CFJvCsObNRh9gL15W3xy9qBFX
# 2WfqWQ==
# =kxM7
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 12 Sep 2024 06:28:32 BST
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* tag 'pull-sparc-20240911' of https://gitlab.com/rth7680/qemu:
  target/sparc: Add gen_trap_if_nofpu_fpexception
  target/sparc: Implement STDFQ
  target/sparc: Add FSR_QNE to tb_flags
  target/sparc: Populate sparc32 FQ when raising fp exception
  target/sparc: Add FQ and FSR.QNE

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

6 files changed, 178 insertions, 51 deletions

diff --git a/target/sparc/cpu.h b/target/sparc/cpu.h
index dfd9512..f517e5a 100644
--- a/target/sparc/cpu.h
+++ b/target/sparc/cpu.h
@@ -184,6 +184,8 @@ enum {
 #define FSR_FTT_SEQ_ERROR (4ULL << 14)
 #define FSR_FTT_INVAL_FPR (6ULL << 14)
 
+#define FSR_QNE    (1ULL << 13)
+
 #define FSR_FCC0_SHIFT    10
 #define FSR_FCC1_SHIFT    32
 #define FSR_FCC2_SHIFT    34
@@ -438,6 +440,26 @@ struct CPUArchState {
     uint32_t fsr_cexc_ftt;           /* cexc, ftt */
     uint32_t fcc[TARGET_FCCREGS];    /* fcc* */
 
+#if !defined(TARGET_SPARC64) && !defined(CONFIG_USER_ONLY)
+    /*
+     * Single-element FPU fault queue, with address and insn,
+     * packaged into the double-word with which it is stored.
+     */
+    uint32_t fsr_qne;                /* qne */
+    union {
+        uint64_t d;
+        struct {
+#if HOST_BIG_ENDIAN
+            uint32_t addr;
+            uint32_t insn;
+#else
+            uint32_t insn;
+            uint32_t addr;
+#endif
+        } s;
+    } fq;
+#endif
+
     CPU_DoubleU fpr[TARGET_DPREGS];  /* floating point registers */
     uint32_t cwp;      /* index of current register window (extracted
                           from PSR) */
@@ -722,6 +744,7 @@ trap_state* cpu_tsptr(CPUSPARCState* env);
 #define TB_FLAG_AM_ENABLED   (1 << 5)
 #define TB_FLAG_SUPER        (1 << 6)
 #define TB_FLAG_HYPER        (1 << 7)
+#define TB_FLAG_FSR_QNE      (1 << 8)
 #define TB_FLAG_ASI_SHIFT    24
 
 static inline void cpu_get_tb_cpu_state(CPUSPARCState *env, vaddr *pc,
@@ -753,7 +776,12 @@ static inline void cpu_get_tb_cpu_state(CPUSPARCState *env, vaddr *pc,
     if (env->psref) {
         flags |= TB_FLAG_FPU_ENABLED;
     }
-#endif
+#ifndef CONFIG_USER_ONLY
+    if (env->fsr_qne) {
+        flags |= TB_FLAG_FSR_QNE;
+    }
+#endif /* !CONFIG_USER_ONLY */
+#endif /* TARGET_SPARC64 */
     *pflags = flags;
 }
 
diff --git a/target/sparc/fop_helper.c b/target/sparc/fop_helper.c
index 0b30665..b669238 100644
--- a/target/sparc/fop_helper.c
+++ b/target/sparc/fop_helper.c
@@ -545,6 +545,8 @@ target_ulong cpu_get_fsr(CPUSPARCState *env)
     fsr |= (uint64_t)env->fcc[1] << FSR_FCC1_SHIFT;
     fsr |= (uint64_t)env->fcc[2] << FSR_FCC2_SHIFT;
     fsr |= (uint64_t)env->fcc[3] << FSR_FCC3_SHIFT;
+#elif !defined(CONFIG_USER_ONLY)
+    fsr |= env->fsr_qne;
 #endif
 
     /* VER is kept completely separate until re-assembly. */
@@ -591,6 +593,8 @@ void cpu_put_fsr(CPUSPARCState *env, target_ulong fsr)
     env->fcc[1] = extract64(fsr, FSR_FCC1_SHIFT, 2);
     env->fcc[2] = extract64(fsr, FSR_FCC2_SHIFT, 2);
     env->fcc[3] = extract64(fsr, FSR_FCC3_SHIFT, 2);
+#elif !defined(CONFIG_USER_ONLY)
+    env->fsr_qne = fsr & FSR_QNE;
 #endif
 
     set_fsr_nonsplit(env, fsr);
diff --git a/target/sparc/insns.decode b/target/sparc/insns.decode
index 5fd4781..923f348 100644
--- a/target/sparc/insns.decode
+++ b/target/sparc/insns.decode
@@ -645,7 +645,7 @@ STFSR       11 00000 100101 ..... . .............          @n_r_ri
 STXFSR      11 00001 100101 ..... . .............          @n_r_ri
 {
   STQF      11 ..... 100110 ..... . .............          @q_r_ri_na # v9
-  STDFQ     11 ----- 100110 ----- - -------------
+  STDFQ     11 ..... 100110 ..... . .............          @r_r_ri    # v7,v8
 }
 STDF        11 ..... 100111 ..... . .............          @d_r_ri_na
 
diff --git a/target/sparc/int32_helper.c b/target/sparc/int32_helper.c
index 6b7d65b..f2dd8bc 100644
--- a/target/sparc/int32_helper.c
+++ b/target/sparc/int32_helper.c
@@ -21,10 +21,10 @@
 #include "qemu/main-loop.h"
 #include "cpu.h"
 #include "trace.h"
+#include "exec/cpu_ldst.h"
 #include "exec/log.h"
 #include "sysemu/runstate.h"
 
-
 static const char * const excp_names[0x80] = {
     [TT_TFAULT] = "Instruction Access Fault",
     [TT_ILL_INSN] = "Illegal Instruction",
@@ -116,22 +116,9 @@ void sparc_cpu_do_interrupt(CPUState *cs)
 
         qemu_log("%6d: %s (v=%02x)\n", count, name, intno);
         log_cpu_state(cs, 0);
-#if 0
-        {
-            int i;
-            uint8_t *ptr;
-
-            qemu_log("       code=");
-            ptr = (uint8_t *)env->pc;
-            for (i = 0; i < 16; i++) {
-                qemu_log(" %02x", ldub(ptr + i));
-            }
-            qemu_log("\n");
-        }
-#endif
         count++;
     }
-#if !defined(CONFIG_USER_ONLY)
+#ifndef CONFIG_USER_ONLY
     if (env->psret == 0) {
         if (cs->exception_index == 0x80 &&
             env->def.features & CPU_FEATURE_TA0_SHUTDOWN) {
@@ -143,6 +130,29 @@ void sparc_cpu_do_interrupt(CPUState *cs)
         }
         return;
     }
+    if (intno == TT_FP_EXCP) {
+        /*
+         * The sparc32 fpu has three states related to exception handling.
+         * The FPop that signals an exception transitions from fp_execute
+         * to fp_exception_pending.  A subsequent FPop transitions from
+         * fp_exception_pending to fp_exception, which forces the trap.
+         *
+         * If the queue is not empty, this trap is due to execution of an
+         * illegal FPop while in fp_exception state.  Here we are to
+         * re-enter fp_exception_pending state without queuing the insn.
+         *
+         * We do not model the fp_exception_pending state, but instead
+         * skip directly to fp_exception state.  We advance pc/npc to
+         * mimic delayed trap delivery as if by the subsequent insn.
+         */
+        if (!env->fsr_qne) {
+            env->fsr_qne = FSR_QNE;
+            env->fq.s.addr = env->pc;
+            env->fq.s.insn = cpu_ldl_code(env, env->pc);
+        }
+        env->pc = env->npc;
+        env->npc = env->npc + 4;
+    }
 #endif
     env->psret = 0;
     cwp = cpu_cwp_dec(env, env->cwp - 1);
diff --git a/target/sparc/machine.c b/target/sparc/machine.c
index 48e0cf2..222e570 100644
--- a/target/sparc/machine.c
+++ b/target/sparc/machine.c
@@ -143,6 +143,24 @@ static const VMStateInfo vmstate_xcc = {
     .get = get_xcc,
     .put = put_xcc,
 };
+#else
+static bool fq_needed(void *opaque)
+{
+    SPARCCPU *cpu = opaque;
+    return cpu->env.fsr_qne;
+}
+
+static const VMStateDescription vmstate_fq = {
+    .name = "cpu/fq",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = fq_needed,
+    .fields = (const VMStateField[]) {
+        VMSTATE_UINT32(env.fq.s.addr, SPARCCPU),
+        VMSTATE_UINT32(env.fq.s.insn, SPARCCPU),
+        VMSTATE_END_OF_LIST()
+    },
+};
 #endif
 
 static int cpu_pre_save(void *opaque)
@@ -265,4 +283,11 @@ const VMStateDescription vmstate_sparc_cpu = {
 #endif
         VMSTATE_END_OF_LIST()
     },
+#ifndef TARGET_SPARC64
+    .subsections = (const VMStateDescription * const []) {
+        &vmstate_fq,
+        NULL
+    },
+#endif
+
 };
diff --git a/target/sparc/translate.c b/target/sparc/translate.c
index c803e8d..cdd0a95 100644
--- a/target/sparc/translate.c
+++ b/target/sparc/translate.c
@@ -185,6 +185,8 @@ typedef struct DisasContext {
     bool supervisor;
 #ifdef TARGET_SPARC64
     bool hypervisor;
+#else
+    bool fsr_qne;
 #endif
 #endif
 
@@ -1463,15 +1465,48 @@ static void gen_op_fpexception_im(DisasContext *dc, int ftt)
     gen_exception(dc, TT_FP_EXCP);
 }
 
-static int gen_trap_ifnofpu(DisasContext *dc)
+static bool gen_trap_ifnofpu(DisasContext *dc)
 {
 #if !defined(CONFIG_USER_ONLY)
     if (!dc->fpu_enabled) {
         gen_exception(dc, TT_NFPU_INSN);
-        return 1;
+        return true;
+    }
+#endif
+    return false;
+}
+
+static bool gen_trap_iffpexception(DisasContext *dc)
+{
+#if !defined(TARGET_SPARC64) && !defined(CONFIG_USER_ONLY)
+    /*
+     * There are 3 states for the sparc32 fpu:
+     * Normally the fpu is in fp_execute, and all insns are allowed.
+     * When an exception is signaled, it moves to fp_exception_pending state.
+     * Upon seeing the next FPop, the fpu moves to fp_exception state,
+     * populates the FQ, and generates an fp_exception trap.
+     * The fpu remains in fp_exception state until FQ becomes empty
+     * after execution of a STDFQ instruction.  While the fpu is in
+     * fp_exception state, and FPop, fp load or fp branch insn will
+     * return to fp_exception_pending state, set FSR.FTT to sequence_error,
+     * and the insn will not be entered into the FQ.
+     *
+     * In QEMU, we do not model the fp_exception_pending state and
+     * instead populate FQ and raise the exception immediately.
+     * But we can still honor fp_exception state by noticing when
+     * the FQ is not empty.
+     */
+    if (dc->fsr_qne) {
+        gen_op_fpexception_im(dc, FSR_FTT_SEQ_ERROR);
+        return true;
     }
 #endif
-    return 0;
+    return false;
+}
+
+static bool gen_trap_if_nofpu_fpexception(DisasContext *dc)
+{
+    return gen_trap_ifnofpu(dc) || gen_trap_iffpexception(dc);
 }
 
 /* asi moves */
@@ -2641,7 +2676,7 @@ static bool do_fbpfcc(DisasContext *dc, arg_bcc *a)
 {
     DisasCompare cmp;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
     gen_fcompare(&cmp, a->cc, a->cond);
@@ -4480,7 +4515,7 @@ static bool do_ld_fpr(DisasContext *dc, arg_r_r_ri_asi *a, MemOp sz)
     if (addr == NULL) {
         return false;
     }
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
     if (sz == MO_128 && gen_trap_float128(dc)) {
@@ -4508,6 +4543,7 @@ static bool do_st_fpr(DisasContext *dc, arg_r_r_ri_asi *a, MemOp sz)
     if (addr == NULL) {
         return false;
     }
+    /* Store insns are ok in fp_exception_pending state. */
     if (gen_trap_ifnofpu(dc)) {
         return true;
     }
@@ -4529,17 +4565,41 @@ TRANS(STQFA, 64, do_st_fpr, a, MO_128)
 
 static bool trans_STDFQ(DisasContext *dc, arg_STDFQ *a)
 {
+    TCGv addr;
+
     if (!avail_32(dc)) {
         return false;
     }
+    addr = gen_ldst_addr(dc, a->rs1, a->imm, a->rs2_or_imm);
+    if (addr == NULL) {
+        return false;
+    }
     if (!supervisor(dc)) {
         return raise_priv(dc);
     }
+#if !defined(TARGET_SPARC64) && !defined(CONFIG_USER_ONLY)
     if (gen_trap_ifnofpu(dc)) {
         return true;
     }
-    gen_op_fpexception_im(dc, FSR_FTT_SEQ_ERROR);
-    return true;
+    if (!dc->fsr_qne) {
+        gen_op_fpexception_im(dc, FSR_FTT_SEQ_ERROR);
+        return true;
+    }
+
+    /* Store the single element from the queue. */
+    TCGv_i64 fq = tcg_temp_new_i64();
+    tcg_gen_ld_i64(fq, tcg_env, offsetof(CPUSPARCState, fq.d));
+    tcg_gen_qemu_st_i64(fq, addr, dc->mem_idx, MO_TEUQ | MO_ALIGN_4);
+
+    /* Mark the queue empty, transitioning to fp_execute state. */
+    tcg_gen_st_i32(tcg_constant_i32(0), tcg_env,
+                   offsetof(CPUSPARCState, fsr_qne));
+    dc->fsr_qne = 0;
+
+    return advance_pc(dc);
+#else
+    qemu_build_not_reached();
+#endif
 }
 
 static bool trans_LDFSR(DisasContext *dc, arg_r_r_ri *a)
@@ -4550,7 +4610,7 @@ static bool trans_LDFSR(DisasContext *dc, arg_r_r_ri *a)
     if (addr == NULL) {
         return false;
     }
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
 
@@ -4574,7 +4634,7 @@ static bool do_ldxfsr(DisasContext *dc, arg_r_r_ri *a, bool entire)
     if (addr == NULL) {
         return false;
     }
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
 
@@ -4611,6 +4671,7 @@ static bool do_stfsr(DisasContext *dc, arg_r_r_ri *a, MemOp mop)
     if (addr == NULL) {
         return false;
     }
+    /* Store insns are ok in fp_exception_pending state. */
     if (gen_trap_ifnofpu(dc)) {
         return true;
     }
@@ -4653,7 +4714,7 @@ static bool do_ff(DisasContext *dc, arg_r_r *a,
 {
     TCGv_i32 tmp;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
 
@@ -4694,7 +4755,7 @@ static bool do_env_ff(DisasContext *dc, arg_r_r *a,
 {
     TCGv_i32 tmp;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
 
@@ -4714,7 +4775,7 @@ static bool do_env_fd(DisasContext *dc, arg_r_r *a,
     TCGv_i32 dst;
     TCGv_i64 src;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
 
@@ -4734,7 +4795,7 @@ static bool do_dd(DisasContext *dc, arg_r_r *a,
 {
     TCGv_i64 dst, src;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
 
@@ -4756,7 +4817,7 @@ static bool do_env_dd(DisasContext *dc, arg_r_r *a,
 {
     TCGv_i64 dst, src;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
 
@@ -4796,7 +4857,7 @@ static bool do_env_df(DisasContext *dc, arg_r_r *a,
     TCGv_i64 dst;
     TCGv_i32 src;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
 
@@ -4839,7 +4900,7 @@ static bool do_env_qq(DisasContext *dc, arg_r_r *a,
 {
     TCGv_i128 t;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
     if (gen_trap_float128(dc)) {
@@ -4860,7 +4921,7 @@ static bool do_env_fq(DisasContext *dc, arg_r_r *a,
     TCGv_i128 src;
     TCGv_i32 dst;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
     if (gen_trap_float128(dc)) {
@@ -4883,7 +4944,7 @@ static bool do_env_dq(DisasContext *dc, arg_r_r *a,
     TCGv_i128 src;
     TCGv_i64 dst;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
     if (gen_trap_float128(dc)) {
@@ -4906,7 +4967,7 @@ static bool do_env_qf(DisasContext *dc, arg_r_r *a,
     TCGv_i32 src;
     TCGv_i128 dst;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
     if (gen_trap_float128(dc)) {
@@ -4929,10 +4990,7 @@ static bool do_env_qd(DisasContext *dc, arg_r_r *a,
     TCGv_i64 src;
     TCGv_i128 dst;
 
-    if (gen_trap_ifnofpu(dc)) {
-        return true;
-    }
-    if (gen_trap_float128(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
 
@@ -4989,7 +5047,7 @@ static bool do_env_fff(DisasContext *dc, arg_r_r_r *a,
 {
     TCGv_i32 src1, src2;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
 
@@ -5198,7 +5256,7 @@ static bool do_env_ddd(DisasContext *dc, arg_r_r_r *a,
 {
     TCGv_i64 dst, src1, src2;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
 
@@ -5222,7 +5280,7 @@ static bool trans_FsMULd(DisasContext *dc, arg_r_r_r *a)
     TCGv_i64 dst;
     TCGv_i32 src1, src2;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
     if (!(dc->def->features & CPU_FEATURE_FSMULD)) {
@@ -5331,7 +5389,7 @@ static bool do_env_qqq(DisasContext *dc, arg_r_r_r *a,
 {
     TCGv_i128 src1, src2;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
     if (gen_trap_float128(dc)) {
@@ -5355,7 +5413,7 @@ static bool trans_FdMULq(DisasContext *dc, arg_r_r_r *a)
     TCGv_i64 src1, src2;
     TCGv_i128 dst;
 
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
     if (gen_trap_float128(dc)) {
@@ -5445,7 +5503,7 @@ static bool do_fcmps(DisasContext *dc, arg_FCMPs *a, bool e)
     if (avail_32(dc) && a->cc != 0) {
         return false;
     }
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
 
@@ -5469,7 +5527,7 @@ static bool do_fcmpd(DisasContext *dc, arg_FCMPd *a, bool e)
     if (avail_32(dc) && a->cc != 0) {
         return false;
     }
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
 
@@ -5493,7 +5551,7 @@ static bool do_fcmpq(DisasContext *dc, arg_FCMPq *a, bool e)
     if (avail_32(dc) && a->cc != 0) {
         return false;
     }
-    if (gen_trap_ifnofpu(dc)) {
+    if (gen_trap_if_nofpu_fpexception(dc)) {
         return true;
     }
     if (gen_trap_float128(dc)) {
@@ -5596,13 +5654,15 @@ static void sparc_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
     dc->address_mask_32bit = tb_am_enabled(dc->base.tb->flags);
 #ifndef CONFIG_USER_ONLY
     dc->supervisor = (dc->base.tb->flags & TB_FLAG_SUPER) != 0;
+# ifdef TARGET_SPARC64
+    dc->hypervisor = (dc->base.tb->flags & TB_FLAG_HYPER) != 0;
+# else
+    dc->fsr_qne = (dc->base.tb->flags & TB_FLAG_FSR_QNE) != 0;
+# endif
 #endif
 #ifdef TARGET_SPARC64
     dc->fprs_dirty = 0;
     dc->asi = (dc->base.tb->flags >> TB_FLAG_ASI_SHIFT) & 0xff;
-#ifndef CONFIG_USER_ONLY
-    dc->hypervisor = (dc->base.tb->flags & TB_FLAG_HYPER) != 0;
-#endif
 #endif
     /*
      * if we reach a page boundary, we stop generation so that the