All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chinmay Rath <rathc@linux.ibm.com>
To: qemu-devel@nongnu.org, qemu-ppc@nongnu.org,
	harshpb@linux.ibm.com, milesg@linux.ibm.com
Cc: npiggin@gmail.com, richard.henderson@linaro.org,
	vishalc@linux.ibm.com, tshah@linux.ibm.com,
	shivangu@linux.ibm.com, ojaswin@linux.ibm.com,
	aboorvad@linux.ibm.com, amachhiw@linux.ibm.com, sv@linux.ibm.com,
	shivani@linux.ibm.com, mkchauras@gmail.com, uverma@linux.ibm.com,
	nikhilks@linux.ibm.com, Chinmay Rath <rathc@linux.ibm.com>
Subject: [PATCH 11/29] target/ppc: Move fixed-point byte-reversal store insns to decodetree
Date: Thu, 20 Aug 2026 19:30:40 +0530	[thread overview]
Message-ID: <20260820140114.327023-12-rathc@linux.ibm.com> (raw)
In-Reply-To: <20260820140114.327023-1-rathc@linux.ibm.com>

From: Amit Machhiwal <amachhiw@linux.ibm.com>

Move the below PPC instructions to decodetree specification:

  st{d,h,w}brx, st{d,w,h,b}cix				: X-form

The changes were verified by validating that the TCG micro-ops generated
by those insns remain the same. These TCG micro-ops were captured with
the `-d op,in_asm` QEMU flag.

Additionally, remove GEN_STX and GEN_STX_E macros as they are no longer
used anywhere else.

Signed-off-by: Amit Machhiwal <amachhiw@linux.ibm.com>
Signed-off-by: Chinmay Rath <rathc@linux.ibm.com>
---
 target/ppc/insn32.decode                   |  8 +++
 target/ppc/translate.c                     | 52 +++-----------
 target/ppc/translate/fixedpoint-impl.c.inc | 79 ++++++++++++++++++++++
 3 files changed, 95 insertions(+), 44 deletions(-)

diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index d34094d717..8425c70b9d 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -372,6 +372,14 @@ STVDX           011111 ..... ..... ..... 0010010001 -   @X
 STSKU           111110 ..... ..... ............. 0 11   @DD
 STCXU           111110 ..... ..... ............. 1 11   @DD
 
+STDBRX          011111 ..... ..... ..... 1010010100 -   @X
+STDCIX          011111 ..... ..... ..... 1111110101 -   @X
+STWCIX          011111 ..... ..... ..... 1110010101 -   @X
+STHCIX          011111 ..... ..... ..... 1110110101 -   @X
+STBCIX          011111 ..... ..... ..... 1111010101 -   @X
+STHBRX          011111 ..... ..... ..... 1110010110 -   @X
+STWBRX          011111 ..... ..... ..... 1010010110 -   @X
+
 ### Fixed-Point Compare Instructions
 
 CMP             011111 ... - . ..... ..... 0000000000 - @X_bfl
diff --git a/target/ppc/translate.c b/target/ppc/translate.c
index 09a461dd63..548a7c0437 100644
--- a/target/ppc/translate.c
+++ b/target/ppc/translate.c
@@ -2529,23 +2529,6 @@ GEN_LDX_HVRM(lhzcix, ld16u, 0x15, 0x19, PPC_CILDST)
 GEN_LDX_HVRM(lbzcix, ld8u, 0x15, 0x1a, PPC_CILDST)
 #endif
 
-/***                              Integer store                            ***/
-#define GEN_STX_E(name, stop, opc2, opc3, type, type2, chk)                   \
-static void glue(gen_, name##x)(DisasContext *ctx)                            \
-{                                                                             \
-    TCGv EA;                                                                  \
-    chk(ctx);                                                                 \
-    gen_set_access_type(ctx, ACCESS_INT);                                     \
-    EA = tcg_temp_new();                                                      \
-    gen_addr_reg_index(ctx, EA);                                              \
-    gen_qemu_##stop(ctx, cpu_gpr[rS(ctx->opcode)], EA);                       \
-}
-#define GEN_STX(name, stop, opc2, opc3, type)                                 \
-    GEN_STX_E(name, stop, opc2, opc3, type, PPC_NONE, CHK_NONE)
-
-#define GEN_STX_HVRM(name, stop, opc2, opc3, type)                            \
-    GEN_STX_E(name, stop, opc2, opc3, type, PPC_NONE, CHK_HVRM)
-
 #define GEN_STEPX(name, stop, opc2, opc3)                                     \
 static void glue(gen_, name##epx)(DisasContext *ctx)                          \
 {                                                                             \
@@ -2565,12 +2548,6 @@ GEN_STEPX(stw, DEF_MEMOP(MO_UL), 0x1F, 0x04)
 GEN_STEPX(std, DEF_MEMOP(MO_UQ), 0x1d, 0x04)
 #endif
 
-#if defined(TARGET_PPC64)
-GEN_STX_HVRM(stdcix, st64_i64, 0x15, 0x1f, PPC_CILDST)
-GEN_STX_HVRM(stwcix, st32, 0x15, 0x1c, PPC_CILDST)
-GEN_STX_HVRM(sthcix, st16, 0x15, 0x1d, PPC_CILDST)
-GEN_STX_HVRM(stbcix, st8, 0x15, 0x1e, PPC_CILDST)
-#endif
 /***                Integer load and store with byte reverse               ***/
 
 /* lhbrx */
@@ -2582,15 +2559,8 @@ GEN_LDX(lwbr, ld32ur, 0x16, 0x10, PPC_INTEGER);
 #if defined(TARGET_PPC64)
 /* ldbrx */
 GEN_LDX_E(ldbr, ld64ur_i64, 0x14, 0x10, PPC_NONE, PPC2_DBRX, CHK_NONE);
-/* stdbrx */
-GEN_STX_E(stdbr, st64r_i64, 0x14, 0x14, PPC_NONE, PPC2_DBRX, CHK_NONE);
 #endif  /* TARGET_PPC64 */
 
-/* sthbrx */
-GEN_STX(sthbr, st16r, 0x16, 0x1C, PPC_INTEGER);
-/* stwbrx */
-GEN_STX(stwbr, st32r, 0x16, 0x14, PPC_INTEGER);
-
 /***                    Integer load and store multiple                    ***/
 
 /* lmw */
@@ -5117,9 +5087,17 @@ static int64_t dw_compose_ea(DisasContext *ctx, int x)
             return true;                            \
         }                                           \
     } while (0)
+#define REQUIRE_HVRM(CTX)                               \
+    do {                                                \
+        if (unlikely(ctx->pr || !ctx->hv || ctx->dr)) { \
+            gen_priv_opc(CTX);                          \
+            return true;                                \
+        }                                               \
+    } while (0)
 #else
 #define REQUIRE_SV(CTX) do { gen_priv_opc(CTX); return true; } while (0)
 #define REQUIRE_HV(CTX) do { gen_priv_opc(CTX); return true; } while (0)
+#define REQUIRE_HVRM(CTX) do { gen_priv_opc(CTX); return true; } while (0)
 #endif
 
 /*
@@ -5767,20 +5745,6 @@ GEN_LDEPX(lw, DEF_MEMOP(MO_UL), 0x1F, 0x00)
 GEN_LDEPX(ld, DEF_MEMOP(MO_UQ), 0x1D, 0x00)
 #endif
 
-#undef GEN_STX_E
-#define GEN_STX_E(name, stop, opc2, opc3, type, type2, chk)                   \
-GEN_HANDLER_E(name##x, 0x1F, opc2, opc3, 0x00000000, type, type2),
-
-#if defined(TARGET_PPC64)
-GEN_STX_E(stdbr, st64r_i64, 0x14, 0x14, PPC_NONE, PPC2_DBRX, CHK_NONE)
-GEN_STX_HVRM(stdcix, st64_i64, 0x15, 0x1f, PPC_CILDST)
-GEN_STX_HVRM(stwcix, st32, 0x15, 0x1c, PPC_CILDST)
-GEN_STX_HVRM(sthcix, st16, 0x15, 0x1d, PPC_CILDST)
-GEN_STX_HVRM(stbcix, st8, 0x15, 0x1e, PPC_CILDST)
-#endif
-GEN_STX(sthbr, st16r, 0x16, 0x1C, PPC_INTEGER)
-GEN_STX(stwbr, st32r, 0x16, 0x14, PPC_INTEGER)
-
 #undef GEN_STEPX
 #define GEN_STEPX(name, ldop, opc2, opc3)                                     \
 GEN_HANDLER_E(name##epx, 0x1F, opc2, opc3,                                    \
diff --git a/target/ppc/translate/fixedpoint-impl.c.inc b/target/ppc/translate/fixedpoint-impl.c.inc
index 9f669894a3..25a60d3d3a 100644
--- a/target/ppc/translate/fixedpoint-impl.c.inc
+++ b/target/ppc/translate/fixedpoint-impl.c.inc
@@ -566,6 +566,85 @@ TRANS(ADDIC_, do_add_D, false, true, false, true);
 TRANS(SLD, do_shift_X_rc, tcg_gen_shl_tl);
 TRANS(SRD, do_shift_X_rc, tcg_gen_shr_tl);
 
+static bool do_stxx(DisasContext *ctx, arg_X *a,
+                       void(*op)(DisasContext *, TCGv, TCGv), bool is_hvrm)
+{
+    TCGv ea;
+
+    if (is_hvrm) {
+            REQUIRE_HVRM(ctx);
+    }
+
+    gen_set_access_type(ctx, ACCESS_INT);
+    ea = do_ea_calc(ctx, a->ra, cpu_gpr[a->rb]);
+    op(ctx, cpu_gpr[a->rt], ea);
+
+    return true;
+}
+
+TRANS(STHBRX, do_stxx, gen_qemu_st16r, 0);
+TRANS(STWBRX, do_stxx, gen_qemu_st32r, 0);
+
+static bool trans_STDBRX(DisasContext *ctx, arg_STDBRX *a)
+{
+    REQUIRE_64BIT(ctx);
+    REQUIRE_INSNS_FLAGS2(ctx, DBRX);
+#if defined(TARGET_PPC64)
+    return do_stxx(ctx, a, gen_qemu_st64r_i64, false);
+#else
+    qemu_build_not_reached();
+#endif
+    return true;
+}
+
+static bool trans_STDCIX(DisasContext *ctx, arg_STDCIX *a)
+{
+    REQUIRE_64BIT(ctx);
+    REQUIRE_INSNS_FLAGS(ctx, CILDST);
+#if defined(TARGET_PPC64)
+    return do_stxx(ctx, a, gen_qemu_st64_i64, true);
+#else
+    qemu_build_not_reached();
+#endif
+    return true;
+}
+
+static bool trans_STWCIX(DisasContext *ctx, arg_STWCIX *a)
+{
+    REQUIRE_64BIT(ctx);
+    REQUIRE_INSNS_FLAGS(ctx, CILDST);
+#if defined(TARGET_PPC64)
+    return do_stxx(ctx, a, gen_qemu_st32, true);
+#else
+    qemu_build_not_reached();
+#endif
+    return true;
+}
+
+static bool trans_STHCIX(DisasContext *ctx, arg_STHCIX *a)
+{
+    REQUIRE_64BIT(ctx);
+    REQUIRE_INSNS_FLAGS(ctx, CILDST);
+#if defined(TARGET_PPC64)
+    return do_stxx(ctx, a, gen_qemu_st16, true);
+#else
+    qemu_build_not_reached();
+#endif
+    return true;
+}
+
+static bool trans_STBCIX(DisasContext *ctx, arg_STBCIX *a)
+{
+    REQUIRE_64BIT(ctx);
+    REQUIRE_INSNS_FLAGS(ctx, CILDST);
+#if defined(TARGET_PPC64)
+    return do_stxx(ctx, a, gen_qemu_st8, true);
+#else
+    qemu_build_not_reached();
+#endif
+    return true;
+}
+
 static bool trans_SUBFIC(DisasContext *ctx, arg_D *a)
 {
     gen_op_arith_subf(ctx, cpu_gpr[a->rt], cpu_gpr[a->ra],
-- 
2.55.0



  parent reply	other threads:[~2026-08-20 14:05 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-20 14:00 [PATCH 00/29] target/ppc: Moving instructions to decodetree specification Chinmay Rath
2026-08-20 14:00 ` [PATCH 01/29] target/ppc: Migrate extswsli to decodetree Chinmay Rath
2026-08-20 14:00 ` [PATCH 02/29] target/ppc: Migrate atomic loads " Chinmay Rath
2026-08-20 14:00 ` [PATCH 03/29] target/ppc: Convert cache instructions " Chinmay Rath
2026-08-20 14:00 ` [PATCH 04/29] target/ppc: Move vector merge " Chinmay Rath
2026-08-20 14:00 ` [PATCH 05/29] target/ppc: Move vector pack " Chinmay Rath
2026-08-20 14:00 ` [PATCH 06/29] target/ppc: Move st{b, h, w, d, q}cx " Chinmay Rath
2026-08-20 14:00 ` [PATCH 07/29] target/ppc: convert slw, srw instruction via decode spec Chinmay Rath
2026-08-20 14:00 ` [PATCH 08/29] target/ppc: convert sraw[i] " Chinmay Rath
2026-08-20 14:00 ` [PATCH 09/29] target/ppc: Convert mcrf to decode tree Chinmay Rath
2026-08-20 14:00 ` [PATCH 10/29] target/ppc: Move fixed-point Shift insns to decodetree Chinmay Rath
2026-08-20 14:00 ` Chinmay Rath [this message]
2026-08-20 14:00 ` [PATCH 12/29] target/ppc: Move GPR atomic load/store instructions " Chinmay Rath
2026-08-20 14:00 ` [PATCH 13/29] target/ppc: Move isync instruction " Chinmay Rath
2026-08-20 14:00 ` [PATCH 14/29] target/ppc: Convert b{a, l, la} to decode tree Chinmay Rath
2026-08-20 14:00 ` [PATCH 15/29] target/ppc: move various conditional branch insns to decodetree Chinmay Rath
2026-08-20 14:00 ` [PATCH 16/29] target/ppc: Fix TRANS* macro variadic arguments handling Chinmay Rath
2026-08-20 14:00 ` [PATCH 17/29] target/ppc: Move wait instruction to decodetree Chinmay Rath
2026-08-20 14:00 ` [PATCH 18/29] target/ppc: Move sleep & friends " Chinmay Rath
2026-08-20 14:00 ` [PATCH 19/29] target/ppc: Refactor sleep and its variants to use a common helper Chinmay Rath
2026-08-20 15:15   ` Miles Glenn
2026-08-20 14:00 ` [PATCH 20/29] target/ppc: Move Condition Register access instructions to decodetree Chinmay Rath
2026-08-20 14:00 ` [PATCH 21/29] target/ppc: Move Condition Register logical " Chinmay Rath
2026-08-20 14:00 ` [PATCH 22/29] target/ppc: make do_ea_calc_ra available for 32 bit builds Chinmay Rath
2026-08-20 14:00 ` [PATCH 23/29] target/ppc: Move Fixed-Point Load/Store String instructions to decodetree Chinmay Rath
2026-08-20 14:00 ` [PATCH 24/29] target/ppc: Move VMX integer arithmetic and BCD " Chinmay Rath
2026-08-20 14:00 ` [PATCH 25/29] target/ppc: Move rlwimi, rlwinm " Chinmay Rath
2026-08-20 14:00 ` [PATCH 26/29] target/ppc: Move lmw, stmw " Chinmay Rath
2026-08-20 14:00 ` [PATCH 27/29] target/ppc: Move mfmsr, mtmsr[d] " Chinmay Rath
2026-08-20 14:00 ` [PATCH 28/29] target/ppc: Move byte-reverse " Chinmay Rath
2026-08-20 14:00 ` [PATCH 29/29] target/ppc: Move system call and rfi " Chinmay Rath

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260820140114.327023-12-rathc@linux.ibm.com \
    --to=rathc@linux.ibm.com \
    --cc=aboorvad@linux.ibm.com \
    --cc=amachhiw@linux.ibm.com \
    --cc=harshpb@linux.ibm.com \
    --cc=milesg@linux.ibm.com \
    --cc=mkchauras@gmail.com \
    --cc=nikhilks@linux.ibm.com \
    --cc=npiggin@gmail.com \
    --cc=ojaswin@linux.ibm.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-ppc@nongnu.org \
    --cc=richard.henderson@linaro.org \
    --cc=shivangu@linux.ibm.com \
    --cc=shivani@linux.ibm.com \
    --cc=sv@linux.ibm.com \
    --cc=tshah@linux.ibm.com \
    --cc=uverma@linux.ibm.com \
    --cc=vishalc@linux.ibm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.