From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: Peter Maydell <peter.maydell@linaro.org>
Subject: [PATCH v3 27/29] tcg/arm: Unset TCG_TARGET_HAS_MEMORY_BSWAP
Date: Fri, 25 Jun 2021 23:36:29 -0700 [thread overview]
Message-ID: <20210626063631.2411938-28-richard.henderson@linaro.org> (raw)
In-Reply-To: <20210626063631.2411938-1-richard.henderson@linaro.org>
Now that the middle-end can replicate the same tricks as tcg/arm
used for optimizing bswap for signed loads and for stores, do not
pretend to have these memory ops in the backend.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
tcg/arm/tcg-target.h | 2 +-
tcg/arm/tcg-target.c.inc | 214 ++++++++++++++-------------------------
2 files changed, 77 insertions(+), 139 deletions(-)
diff --git a/tcg/arm/tcg-target.h b/tcg/arm/tcg-target.h
index 57fd0c0c74..95fcef33bc 100644
--- a/tcg/arm/tcg-target.h
+++ b/tcg/arm/tcg-target.h
@@ -174,7 +174,7 @@ extern bool use_neon_instructions;
#define TCG_TARGET_HAS_cmpsel_vec 0
#define TCG_TARGET_DEFAULT_MO (0)
-#define TCG_TARGET_HAS_MEMORY_BSWAP 1
+#define TCG_TARGET_HAS_MEMORY_BSWAP 0
/* not defined -- call should be eliminated at compile time */
void tb_target_set_jmp_target(uintptr_t, uintptr_t, uintptr_t, uintptr_t);
diff --git a/tcg/arm/tcg-target.c.inc b/tcg/arm/tcg-target.c.inc
index 73e0455511..7a761a602e 100644
--- a/tcg/arm/tcg-target.c.inc
+++ b/tcg/arm/tcg-target.c.inc
@@ -1393,34 +1393,38 @@ static void tcg_out_vldst(TCGContext *s, ARMInsn insn,
/* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr,
* int mmu_idx, uintptr_t ra)
*/
-static void * const qemu_ld_helpers[16] = {
+static void * const qemu_ld_helpers[8] = {
[MO_UB] = helper_ret_ldub_mmu,
[MO_SB] = helper_ret_ldsb_mmu,
-
- [MO_LEUW] = helper_le_lduw_mmu,
- [MO_LEUL] = helper_le_ldul_mmu,
- [MO_LEQ] = helper_le_ldq_mmu,
- [MO_LESW] = helper_le_ldsw_mmu,
- [MO_LESL] = helper_le_ldul_mmu,
-
- [MO_BEUW] = helper_be_lduw_mmu,
- [MO_BEUL] = helper_be_ldul_mmu,
- [MO_BEQ] = helper_be_ldq_mmu,
- [MO_BESW] = helper_be_ldsw_mmu,
- [MO_BESL] = helper_be_ldul_mmu,
+#ifdef HOST_WORDS_BIGENDIAN
+ [MO_UW] = helper_be_lduw_mmu,
+ [MO_UL] = helper_be_ldul_mmu,
+ [MO_Q] = helper_be_ldq_mmu,
+ [MO_SW] = helper_be_ldsw_mmu,
+ [MO_SL] = helper_be_ldul_mmu,
+#else
+ [MO_UW] = helper_le_lduw_mmu,
+ [MO_UL] = helper_le_ldul_mmu,
+ [MO_Q] = helper_le_ldq_mmu,
+ [MO_SW] = helper_le_ldsw_mmu,
+ [MO_SL] = helper_le_ldul_mmu,
+#endif
};
/* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr,
* uintxx_t val, int mmu_idx, uintptr_t ra)
*/
-static void * const qemu_st_helpers[16] = {
- [MO_UB] = helper_ret_stb_mmu,
- [MO_LEUW] = helper_le_stw_mmu,
- [MO_LEUL] = helper_le_stl_mmu,
- [MO_LEQ] = helper_le_stq_mmu,
- [MO_BEUW] = helper_be_stw_mmu,
- [MO_BEUL] = helper_be_stl_mmu,
- [MO_BEQ] = helper_be_stq_mmu,
+static void * const qemu_st_helpers[4] = {
+ [MO_8] = helper_ret_stb_mmu,
+#ifdef HOST_WORDS_BIGENDIAN
+ [MO_16] = helper_be_stw_mmu,
+ [MO_32] = helper_be_stl_mmu,
+ [MO_64] = helper_be_stq_mmu,
+#else
+ [MO_16] = helper_le_stw_mmu,
+ [MO_32] = helper_le_stl_mmu,
+ [MO_64] = helper_le_stq_mmu,
+#endif
};
/* Helper routines for marshalling helper function arguments into
@@ -1625,9 +1629,9 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
icache usage. For pre-armv6, use the signed helpers since we do
not have a single insn sign-extend. */
if (use_armv6_instructions) {
- func = qemu_ld_helpers[opc & (MO_BSWAP | MO_SIZE)];
+ func = qemu_ld_helpers[opc & MO_SIZE];
} else {
- func = qemu_ld_helpers[opc & (MO_BSWAP | MO_SSIZE)];
+ func = qemu_ld_helpers[opc & MO_SSIZE];
if (opc & MO_SIGN) {
opc = MO_UL;
}
@@ -1705,7 +1709,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
argreg = tcg_out_arg_reg32(s, argreg, TCG_REG_R14);
/* Tail-call to the helper, which will return to the fast path. */
- tcg_out_goto(s, COND_AL, qemu_st_helpers[opc & (MO_BSWAP | MO_SIZE)]);
+ tcg_out_goto(s, COND_AL, qemu_st_helpers[opc & MO_SIZE]);
return true;
}
#endif /* SOFTMMU */
@@ -1714,7 +1718,8 @@ static inline void tcg_out_qemu_ld_index(TCGContext *s, MemOp opc,
TCGReg datalo, TCGReg datahi,
TCGReg addrlo, TCGReg addend)
{
- MemOp bswap = opc & MO_BSWAP;
+ /* Byte swapping is left to middle-end expansion. */
+ tcg_debug_assert((opc & MO_BSWAP) == 0);
switch (opc & MO_SSIZE) {
case MO_UB:
@@ -1725,51 +1730,30 @@ static inline void tcg_out_qemu_ld_index(TCGContext *s, MemOp opc,
break;
case MO_UW:
tcg_out_ld16u_r(s, COND_AL, datalo, addrlo, addend);
- if (bswap) {
- tcg_out_bswap16(s, COND_AL, datalo, datalo,
- TCG_BSWAP_IZ | TCG_BSWAP_OZ);
- }
break;
case MO_SW:
- if (bswap) {
- tcg_out_ld16u_r(s, COND_AL, datalo, addrlo, addend);
- tcg_out_bswap16(s, COND_AL, datalo, datalo,
- TCG_BSWAP_IZ | TCG_BSWAP_OS);
- } else {
- tcg_out_ld16s_r(s, COND_AL, datalo, addrlo, addend);
- }
+ tcg_out_ld16s_r(s, COND_AL, datalo, addrlo, addend);
break;
case MO_UL:
- default:
tcg_out_ld32_r(s, COND_AL, datalo, addrlo, addend);
- if (bswap) {
- tcg_out_bswap32(s, COND_AL, datalo, datalo);
- }
break;
case MO_Q:
- {
- TCGReg dl = (bswap ? datahi : datalo);
- TCGReg dh = (bswap ? datalo : datahi);
-
- /* Avoid ldrd for user-only emulation, to handle unaligned. */
- if (USING_SOFTMMU && use_armv6_instructions
- && (dl & 1) == 0 && dh == dl + 1) {
- tcg_out_ldrd_r(s, COND_AL, dl, addrlo, addend);
- } else if (dl != addend) {
- tcg_out_ld32_rwb(s, COND_AL, dl, addend, addrlo);
- tcg_out_ld32_12(s, COND_AL, dh, addend, 4);
- } else {
- tcg_out_dat_reg(s, COND_AL, ARITH_ADD, TCG_REG_TMP,
- addend, addrlo, SHIFT_IMM_LSL(0));
- tcg_out_ld32_12(s, COND_AL, dl, TCG_REG_TMP, 0);
- tcg_out_ld32_12(s, COND_AL, dh, TCG_REG_TMP, 4);
- }
- if (bswap) {
- tcg_out_bswap32(s, COND_AL, dl, dl);
- tcg_out_bswap32(s, COND_AL, dh, dh);
- }
+ /* Avoid ldrd for user-only emulation, to handle unaligned. */
+ if (USING_SOFTMMU && use_armv6_instructions
+ && (datalo & 1) == 0 && datahi == datalo + 1) {
+ tcg_out_ldrd_r(s, COND_AL, datalo, addrlo, addend);
+ } else if (datalo != addend) {
+ tcg_out_ld32_rwb(s, COND_AL, datalo, addend, addrlo);
+ tcg_out_ld32_12(s, COND_AL, datahi, addend, 4);
+ } else {
+ tcg_out_dat_reg(s, COND_AL, ARITH_ADD, TCG_REG_TMP,
+ addend, addrlo, SHIFT_IMM_LSL(0));
+ tcg_out_ld32_12(s, COND_AL, datalo, TCG_REG_TMP, 0);
+ tcg_out_ld32_12(s, COND_AL, datahi, TCG_REG_TMP, 4);
}
break;
+ default:
+ g_assert_not_reached();
}
}
@@ -1777,7 +1761,8 @@ static inline void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc,
TCGReg datalo, TCGReg datahi,
TCGReg addrlo)
{
- MemOp bswap = opc & MO_BSWAP;
+ /* Byte swapping is left to middle-end expansion. */
+ tcg_debug_assert((opc & MO_BSWAP) == 0);
switch (opc & MO_SSIZE) {
case MO_UB:
@@ -1788,49 +1773,28 @@ static inline void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc,
break;
case MO_UW:
tcg_out_ld16u_8(s, COND_AL, datalo, addrlo, 0);
- if (bswap) {
- tcg_out_bswap16(s, COND_AL, datalo, datalo,
- TCG_BSWAP_IZ | TCG_BSWAP_OZ);
- }
break;
case MO_SW:
- if (bswap) {
- tcg_out_ld16u_8(s, COND_AL, datalo, addrlo, 0);
- tcg_out_bswap16(s, COND_AL, datalo, datalo,
- TCG_BSWAP_IZ | TCG_BSWAP_OS);
- } else {
- tcg_out_ld16s_8(s, COND_AL, datalo, addrlo, 0);
- }
+ tcg_out_ld16s_8(s, COND_AL, datalo, addrlo, 0);
break;
case MO_UL:
- default:
tcg_out_ld32_12(s, COND_AL, datalo, addrlo, 0);
- if (bswap) {
- tcg_out_bswap32(s, COND_AL, datalo, datalo);
- }
break;
case MO_Q:
- {
- TCGReg dl = (bswap ? datahi : datalo);
- TCGReg dh = (bswap ? datalo : datahi);
-
- /* Avoid ldrd for user-only emulation, to handle unaligned. */
- if (USING_SOFTMMU && use_armv6_instructions
- && (dl & 1) == 0 && dh == dl + 1) {
- tcg_out_ldrd_8(s, COND_AL, dl, addrlo, 0);
- } else if (dl == addrlo) {
- tcg_out_ld32_12(s, COND_AL, dh, addrlo, bswap ? 0 : 4);
- tcg_out_ld32_12(s, COND_AL, dl, addrlo, bswap ? 4 : 0);
- } else {
- tcg_out_ld32_12(s, COND_AL, dl, addrlo, bswap ? 4 : 0);
- tcg_out_ld32_12(s, COND_AL, dh, addrlo, bswap ? 0 : 4);
- }
- if (bswap) {
- tcg_out_bswap32(s, COND_AL, dl, dl);
- tcg_out_bswap32(s, COND_AL, dh, dh);
- }
+ /* Avoid ldrd for user-only emulation, to handle unaligned. */
+ if (USING_SOFTMMU && use_armv6_instructions
+ && (datalo & 1) == 0 && datahi == datalo + 1) {
+ tcg_out_ldrd_8(s, COND_AL, datalo, addrlo, 0);
+ } else if (datalo == addrlo) {
+ tcg_out_ld32_12(s, COND_AL, datahi, addrlo, 4);
+ tcg_out_ld32_12(s, COND_AL, datalo, addrlo, 0);
+ } else {
+ tcg_out_ld32_12(s, COND_AL, datalo, addrlo, 0);
+ tcg_out_ld32_12(s, COND_AL, datahi, addrlo, 4);
}
break;
+ default:
+ g_assert_not_reached();
}
}
@@ -1879,44 +1843,31 @@ static inline void tcg_out_qemu_st_index(TCGContext *s, int cond, MemOp opc,
TCGReg datalo, TCGReg datahi,
TCGReg addrlo, TCGReg addend)
{
- MemOp bswap = opc & MO_BSWAP;
+ /* Byte swapping is left to middle-end expansion. */
+ tcg_debug_assert((opc & MO_BSWAP) == 0);
switch (opc & MO_SIZE) {
case MO_8:
tcg_out_st8_r(s, cond, datalo, addrlo, addend);
break;
case MO_16:
- if (bswap) {
- tcg_out_bswap16(s, cond, TCG_REG_R0, datalo, 0);
- tcg_out_st16_r(s, cond, TCG_REG_R0, addrlo, addend);
- } else {
- tcg_out_st16_r(s, cond, datalo, addrlo, addend);
- }
+ tcg_out_st16_r(s, cond, datalo, addrlo, addend);
break;
case MO_32:
- default:
- if (bswap) {
- tcg_out_bswap32(s, cond, TCG_REG_R0, datalo);
- tcg_out_st32_r(s, cond, TCG_REG_R0, addrlo, addend);
- } else {
- tcg_out_st32_r(s, cond, datalo, addrlo, addend);
- }
+ tcg_out_st32_r(s, cond, datalo, addrlo, addend);
break;
case MO_64:
/* Avoid strd for user-only emulation, to handle unaligned. */
- if (bswap) {
- tcg_out_bswap32(s, cond, TCG_REG_R0, datahi);
- tcg_out_st32_rwb(s, cond, TCG_REG_R0, addend, addrlo);
- tcg_out_bswap32(s, cond, TCG_REG_R0, datalo);
- tcg_out_st32_12(s, cond, TCG_REG_R0, addend, 4);
- } else if (USING_SOFTMMU && use_armv6_instructions
- && (datalo & 1) == 0 && datahi == datalo + 1) {
+ if (USING_SOFTMMU && use_armv6_instructions
+ && (datalo & 1) == 0 && datahi == datalo + 1) {
tcg_out_strd_r(s, cond, datalo, addrlo, addend);
} else {
tcg_out_st32_rwb(s, cond, datalo, addend, addrlo);
tcg_out_st32_12(s, cond, datahi, addend, 4);
}
break;
+ default:
+ g_assert_not_reached();
}
}
@@ -1924,44 +1875,31 @@ static inline void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc,
TCGReg datalo, TCGReg datahi,
TCGReg addrlo)
{
- MemOp bswap = opc & MO_BSWAP;
+ /* Byte swapping is left to middle-end expansion. */
+ tcg_debug_assert((opc & MO_BSWAP) == 0);
switch (opc & MO_SIZE) {
case MO_8:
tcg_out_st8_12(s, COND_AL, datalo, addrlo, 0);
break;
case MO_16:
- if (bswap) {
- tcg_out_bswap16(s, COND_AL, TCG_REG_R0, datalo, 0);
- tcg_out_st16_8(s, COND_AL, TCG_REG_R0, addrlo, 0);
- } else {
- tcg_out_st16_8(s, COND_AL, datalo, addrlo, 0);
- }
+ tcg_out_st16_8(s, COND_AL, datalo, addrlo, 0);
break;
case MO_32:
- default:
- if (bswap) {
- tcg_out_bswap32(s, COND_AL, TCG_REG_R0, datalo);
- tcg_out_st32_12(s, COND_AL, TCG_REG_R0, addrlo, 0);
- } else {
- tcg_out_st32_12(s, COND_AL, datalo, addrlo, 0);
- }
+ tcg_out_st32_12(s, COND_AL, datalo, addrlo, 0);
break;
case MO_64:
/* Avoid strd for user-only emulation, to handle unaligned. */
- if (bswap) {
- tcg_out_bswap32(s, COND_AL, TCG_REG_R0, datahi);
- tcg_out_st32_12(s, COND_AL, TCG_REG_R0, addrlo, 0);
- tcg_out_bswap32(s, COND_AL, TCG_REG_R0, datalo);
- tcg_out_st32_12(s, COND_AL, TCG_REG_R0, addrlo, 4);
- } else if (USING_SOFTMMU && use_armv6_instructions
- && (datalo & 1) == 0 && datahi == datalo + 1) {
+ if (USING_SOFTMMU && use_armv6_instructions
+ && (datalo & 1) == 0 && datahi == datalo + 1) {
tcg_out_strd_8(s, COND_AL, datalo, addrlo, 0);
} else {
tcg_out_st32_12(s, COND_AL, datalo, addrlo, 0);
tcg_out_st32_12(s, COND_AL, datahi, addrlo, 4);
}
break;
+ default:
+ g_assert_not_reached();
}
}
--
2.25.1
next prev parent reply other threads:[~2021-06-26 6:53 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-26 6:36 [PATCH v3 00/29] tcg: bswap improvements Richard Henderson
2021-06-26 6:36 ` [PATCH v3 01/29] tcg: Add flags argument to bswap opcodes Richard Henderson
2021-06-26 6:36 ` [PATCH v3 02/29] tcg/i386: Support bswap flags Richard Henderson
2021-06-26 6:36 ` [PATCH v3 03/29] tcg/aarch64: Merge tcg_out_rev{16,32,64} Richard Henderson
2021-06-28 14:16 ` Peter Maydell
2021-06-26 6:36 ` [PATCH v3 04/29] tcg/aarch64: Support bswap flags Richard Henderson
2021-06-26 9:38 ` Philippe Mathieu-Daudé
2021-06-26 6:36 ` [PATCH v3 05/29] tcg/arm: " Richard Henderson
2021-06-26 6:36 ` [PATCH v3 06/29] tcg/ppc: Split out tcg_out_ext{8,16,32}s Richard Henderson
2021-06-26 6:36 ` [PATCH v3 07/29] tcg/ppc: Split out tcg_out_sari{32,64} Richard Henderson
2021-06-26 6:36 ` [PATCH v3 08/29] tcg/ppc: Split out tcg_out_bswap16 Richard Henderson
2021-06-26 6:36 ` [PATCH v3 09/29] tcg/ppc: Split out tcg_out_bswap32 Richard Henderson
2021-06-26 6:36 ` [PATCH v3 10/29] tcg/ppc: Split out tcg_out_bswap64 Richard Henderson
2021-06-26 6:36 ` [PATCH v3 11/29] tcg/ppc: Support bswap flags Richard Henderson
2021-06-26 9:32 ` Philippe Mathieu-Daudé
2021-06-26 6:36 ` [PATCH v3 12/29] tcg/ppc: Use power10 byte-reverse instructions Richard Henderson
2021-06-28 14:33 ` Peter Maydell
2021-06-28 14:45 ` Richard Henderson
2021-06-28 16:22 ` Bruno Piazera Larsen
2021-06-26 6:36 ` [PATCH v3 13/29] tcg/s390: Support bswap flags Richard Henderson
2021-06-28 14:43 ` Peter Maydell
2021-06-28 14:50 ` Richard Henderson
2021-06-26 6:36 ` [PATCH v3 14/29] tcg/mips: Support bswap flags in tcg_out_bswap16 Richard Henderson
2021-06-26 9:30 ` Philippe Mathieu-Daudé
2021-06-26 6:36 ` [PATCH v3 15/29] tcg/mips: Support bswap flags in tcg_out_bswap32 Richard Henderson
2021-06-26 6:36 ` [PATCH v3 16/29] tcg/tci: Support bswap flags Richard Henderson
2021-06-26 6:36 ` [PATCH v3 17/29] tcg: Handle new bswap flags during optimize Richard Henderson
2021-06-26 6:36 ` [PATCH v3 18/29] tcg: Add flags argument to tcg_gen_bswap16_*, tcg_gen_bswap32_i64 Richard Henderson
2021-06-26 6:36 ` [PATCH v3 19/29] tcg: Make use of bswap flags in tcg_gen_qemu_ld_* Richard Henderson
2021-06-26 6:36 ` [PATCH v3 20/29] tcg: Make use of bswap flags in tcg_gen_qemu_st_* Richard Henderson
2021-06-26 6:36 ` [PATCH v3 21/29] target/arm: Improve REV32 Richard Henderson
2021-06-26 6:36 ` [PATCH v3 22/29] target/arm: Improve vector REV Richard Henderson
2021-06-26 6:36 ` [PATCH v3 23/29] target/arm: Improve REVSH Richard Henderson
2021-06-26 6:36 ` [PATCH v3 24/29] target/i386: Improve bswap translation Richard Henderson
2021-06-26 6:36 ` [PATCH v3 25/29] target/sh4: Improve swap.b translation Richard Henderson
2021-06-26 6:36 ` [PATCH v3 26/29] target/mips: Fix gen_mxu_s32ldd_s32lddr Richard Henderson
2021-06-26 6:36 ` Richard Henderson [this message]
2021-06-26 6:36 ` [PATCH v3 28/29] tcg/aarch64: Unset TCG_TARGET_HAS_MEMORY_BSWAP Richard Henderson
2021-06-26 6:36 ` [PATCH v3 29/29] tcg/riscv: Remove MO_BSWAP handling Richard Henderson
2021-06-26 7:03 ` [PATCH v3 00/29] tcg: bswap improvements no-reply
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=20210626063631.2411938-28-richard.henderson@linaro.org \
--to=richard.henderson@linaro.org \
--cc=peter.maydell@linaro.org \
--cc=qemu-devel@nongnu.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).