From: Tsukasa OI <research_trasio@irq.a4lg.com>
To: Tsukasa OI <research_trasio@irq.a4lg.com>,
Jan Beulich <jbeulich@suse.com>, Nelson Chu <nelson@rivosinc.com>,
Kito Cheng <kito.cheng@sifive.com>,
Palmer Dabbelt <palmer@dabbelt.com>
Cc: binutils@sourceware.org
Subject: [PATCH 2/2] RISC-V: Better support for long instructions
Date: Sat, 19 Nov 2022 07:10:34 +0000 [thread overview]
Message-ID: <ed49fad6bc6aa4f59d619fd6b445582331594e08.1668841829.git.research_trasio@irq.a4lg.com> (raw)
In-Reply-To: <cover.1668841829.git.research_trasio@irq.a4lg.com>
From: Tsukasa OI <research_trasio@irq.a4lg.com>
Commit bb996692bd96 ("RISC-V/gas: allow generating up to 176-bit
instructions with .insn") tried to start supporting long instructions but
it was insufficient.
1. It heavily depended on the bignum internals (radix of 2^16),
2. It generates "value conflicts with instruction length" even if a big
number instruction encoding does not exceed its expected length,
3. Because long opcode was handled separately (from struct riscv_cl_insn),
some information like DWARF line number correspondence was missing and
4. On the disassembler, disassembler dump was limited up to 64-bit.
For long (unknown) instructions, instruction bits are incorrectly
zeroed out.
To solve these problems, this commit:
1. Handles bignum (and its encodings) precisely,
2. Incorporates long opcode handling into regular struct
riscv_cl_insn-handling functions.
3. Adds packet argument to support dumping instructions
longer than 64-bits.
gas/ChangeLog:
* config/tc-riscv.c (struct riscv_cl_insn): Add long opcode field.
(create_insn) Clear long opcode marker.
(install_insn) Install longer opcode as well.
(s_riscv_insn) Likewise.
(riscv_ip_hardcode): Make big number handling stricter. Length and
the value conflicts only if the bignum size exceeds the expected
length.
* testsuite/gas/riscv/insn.s: Add testcases such that big number
handling is required.
* testsuite/gas/riscv/insn.d: Likewise.
* testsuite/gas/riscv/insn-na.d: Likewise.
* testsuite/gas/riscv/insn-dwarf.d: Likewise.
opcodes/ChangeLog:
* riscv-dis.c (riscv_disassemble_insn): Print unknown instruction
using the new argument packet.
(riscv_disassemble_data): Add unused argument packet.
(print_insn_riscv): Pass packet to the disassemble function.
---
gas/config/tc-riscv.c | 50 +++++++++++++++++++++++-----
gas/testsuite/gas/riscv/insn-dwarf.d | 10 +++++-
gas/testsuite/gas/riscv/insn-na.d | 8 +++++
gas/testsuite/gas/riscv/insn.d | 22 ++++++++++++
gas/testsuite/gas/riscv/insn.s | 9 +++++
opcodes/riscv-dis.c | 13 +++++---
6 files changed, 98 insertions(+), 14 deletions(-)
diff --git a/gas/config/tc-riscv.c b/gas/config/tc-riscv.c
index 019545171f5e..98e8ea0f5f6b 100644
--- a/gas/config/tc-riscv.c
+++ b/gas/config/tc-riscv.c
@@ -45,6 +45,9 @@ struct riscv_cl_insn
/* The encoded instruction bits. */
insn_t insn_opcode;
+ /* The long encoded instruction bits ([0] is non-zero if used). */
+ char insn_long_opcode[RISCV_MAX_INSN_LEN];
+
/* The frag that contains the instruction. */
struct frag *frag;
@@ -714,6 +717,7 @@ create_insn (struct riscv_cl_insn *insn, const struct riscv_opcode *mo)
{
insn->insn_mo = mo;
insn->insn_opcode = mo->match;
+ insn->insn_long_opcode[0] = 0; /* Long insn has non-zero value. */
insn->frag = NULL;
insn->where = 0;
insn->fixp = NULL;
@@ -725,7 +729,10 @@ static void
install_insn (const struct riscv_cl_insn *insn)
{
char *f = insn->frag->fr_literal + insn->where;
- number_to_chars_littleendian (f, insn->insn_opcode, insn_length (insn));
+ if (insn->insn_long_opcode[0] != 0)
+ memcpy (f, insn->insn_long_opcode, insn_length (insn));
+ else
+ number_to_chars_littleendian (f, insn->insn_opcode, insn_length (insn));
}
/* Move INSN to offset WHERE in FRAG. Adjust the fixups accordingly
@@ -3481,7 +3488,21 @@ riscv_ip_hardcode (char *str,
values[num++] = (insn_t) imm_expr->X_add_number;
break;
case O_big:
- values[num++] = generic_bignum[0];
+ /* Extract lower 16-bits of a big number. */
+ if (CHARS_PER_LITTLENUM == 1)
+ {
+ offsetT n = imm_expr->X_add_number;
+ n = n > 2 ? 2 : n;
+ values[num] = 0;
+ for (offsetT i = 0; i < n; ++i)
+ {
+ values[num] *= (insn_t) LITTLENUM_RADIX;
+ values[num] |= (insn_t) generic_bignum[n - i - 1];
+ }
+ num++;
+ }
+ else
+ values[num++] = (insn_t) generic_bignum[0];
break;
default:
/* The first value isn't constant, so it should be
@@ -3508,12 +3529,25 @@ riscv_ip_hardcode (char *str,
if (imm_expr->X_op == O_big)
{
- if (bytes != imm_expr->X_add_number * CHARS_PER_LITTLENUM)
+ unsigned int llen = 0;
+ for (LITTLENUM_TYPE lval = generic_bignum[imm_expr->X_add_number - 1];
+ lval != 0; llen++)
+ lval >>= BITS_PER_CHAR;
+ unsigned int repr_bytes
+ = (imm_expr->X_add_number - 1) * CHARS_PER_LITTLENUM + llen;
+ if (bytes < repr_bytes)
return _("value conflicts with instruction length");
- char *f = frag_more (bytes);
- for (num = 0; num < imm_expr->X_add_number; ++num)
- number_to_chars_littleendian (f + num * CHARS_PER_LITTLENUM,
- generic_bignum[num], CHARS_PER_LITTLENUM);
+ for (num = 0; num < imm_expr->X_add_number - 1; ++num)
+ number_to_chars_littleendian (
+ ip->insn_long_opcode + num * CHARS_PER_LITTLENUM,
+ generic_bignum[num],
+ CHARS_PER_LITTLENUM);
+ if (llen != 0)
+ number_to_chars_littleendian (
+ ip->insn_long_opcode + num * CHARS_PER_LITTLENUM,
+ generic_bignum[num],
+ llen);
+ memset(ip->insn_long_opcode + repr_bytes, 0, bytes - repr_bytes);
return NULL;
}
@@ -4590,7 +4624,7 @@ s_riscv_insn (int x ATTRIBUTE_UNUSED)
else
as_bad ("%s `%s'", error.msg, error.statement);
}
- else if (imm_expr.X_op != O_big)
+ else
{
gas_assert (insn.insn_mo->pinfo != INSN_MACRO);
append_insn (&insn, &imm_expr, imm_reloc);
diff --git a/gas/testsuite/gas/riscv/insn-dwarf.d b/gas/testsuite/gas/riscv/insn-dwarf.d
index 89dc8d58ff09..b8bd42dff18c 100644
--- a/gas/testsuite/gas/riscv/insn-dwarf.d
+++ b/gas/testsuite/gas/riscv/insn-dwarf.d
@@ -74,5 +74,13 @@ insn.s +69 +0xf6.*
insn.s +70 +0xfe.*
insn.s +71 +0x108.*
insn.s +72 +0x114.*
-insn.s +- +0x12a
+insn.s +74 +0x12a.*
+insn.s +75 +0x134.*
+insn.s +76 +0x13e.*
+insn.s +77 +0x154.*
+insn.s +78 +0x16a.*
+insn.s +79 +0x180.*
+insn.s +80 +0x196.*
+insn.s +81 +0x1ac.*
+insn.s +- +0x1c2
#pass
diff --git a/gas/testsuite/gas/riscv/insn-na.d b/gas/testsuite/gas/riscv/insn-na.d
index be6c9f9dd66a..60024555c71f 100644
--- a/gas/testsuite/gas/riscv/insn-na.d
+++ b/gas/testsuite/gas/riscv/insn-na.d
@@ -73,3 +73,11 @@ Disassembly of section .text:
[^:]+:[ ]+007f 0000 0000 0000 0000[ ]+\.byte[ ]+0x7f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
[^:]+:[ ]+0000107f 00000000 00000000[ ]+\.byte[ ]+0x7f, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
[^:]+:[ ]+607f 0000 0000 0000 0000 0000 0000 0000 0000 0000 0000[ ]+\.byte[ ]+0x7f, 0x60, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+[^:]+:[ ]+007f 0000 0000 0000 8000[ ]+\.byte[ ]+0x7f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80
+[^:]+:[ ]+007f 0000 0000 0000 8000[ ]+\.byte[ ]+0x7f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80
+[^:]+:[ ]+607f 89ab 4567 0123 3210 7654 ba98 fedc 0000 0000 0000[ ]+\.byte[ ]+0x7f, 0x60, 0xab, 0x89, 0x67, 0x45, 0x23, 0x01, 0x10, 0x32, 0x54, 0x76, 0x98, 0xba, 0xdc, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+[^:]+:[ ]+607f 89ab 4567 0123 3210 7654 ba98 fedc 0000 0000 0000[ ]+\.byte[ ]+0x7f, 0x60, 0xab, 0x89, 0x67, 0x45, 0x23, 0x01, 0x10, 0x32, 0x54, 0x76, 0x98, 0xba, 0xdc, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+[^:]+:[ ]+607f 33cc 55aa cdef 89ab 4567 0123 3210 7654 ba98 00dc[ ]+\.byte[ ]+0x7f, 0x60, 0xcc, 0x33, 0xaa, 0x55, 0xef, 0xcd, 0xab, 0x89, 0x67, 0x45, 0x23, 0x01, 0x10, 0x32, 0x54, 0x76, 0x98, 0xba, 0xdc, 0x00
+[^:]+:[ ]+607f 33cc 55aa cdef 89ab 4567 0123 3210 7654 ba98 00dc[ ]+\.byte[ ]+0x7f, 0x60, 0xcc, 0x33, 0xaa, 0x55, 0xef, 0xcd, 0xab, 0x89, 0x67, 0x45, 0x23, 0x01, 0x10, 0x32, 0x54, 0x76, 0x98, 0xba, 0xdc, 0x00
+[^:]+:[ ]+607f 33cc 55aa cdef 89ab 4567 0123 3210 7654 ba98 fedc[ ]+\.byte[ ]+0x7f, 0x60, 0xcc, 0x33, 0xaa, 0x55, 0xef, 0xcd, 0xab, 0x89, 0x67, 0x45, 0x23, 0x01, 0x10, 0x32, 0x54, 0x76, 0x98, 0xba, 0xdc, 0xfe
+[^:]+:[ ]+607f 33cc 55aa cdef 89ab 4567 0123 3210 7654 ba98 fedc[ ]+\.byte[ ]+0x7f, 0x60, 0xcc, 0x33, 0xaa, 0x55, 0xef, 0xcd, 0xab, 0x89, 0x67, 0x45, 0x23, 0x01, 0x10, 0x32, 0x54, 0x76, 0x98, 0xba, 0xdc, 0xfe
diff --git a/gas/testsuite/gas/riscv/insn.d b/gas/testsuite/gas/riscv/insn.d
index cf84f177af39..b02d67c5f120 100644
--- a/gas/testsuite/gas/riscv/insn.d
+++ b/gas/testsuite/gas/riscv/insn.d
@@ -92,3 +92,25 @@ Disassembly of section .text:
[^:]+:[ ]+607f 0000 0000 0000[ ]+\.byte[ ]+0x7f, 0x60, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
[^:]+:[ ]+0000 0000 0000 0000 ?
[^:]+:[ ]+0000 0000 0000 ?
+[^:]+:[ ]+007f 0000 0000 0000[ ]+\.byte[ ]+0x7f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80
+[^:]+:[ ]+8000 ?
+[^:]+:[ ]+007f 0000 0000 0000[ ]+\.byte[ ]+0x7f, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80
+[^:]+:[ ]+8000 ?
+[^:]+:[ ]+607f 89ab 4567 0123[ ]+\.byte[ ]+0x7f, 0x60, 0xab, 0x89, 0x67, 0x45, 0x23, 0x01, 0x10, 0x32, 0x54, 0x76, 0x98, 0xba, 0xdc, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+[^:]+:[ ]+3210 7654 ba98 fedc ?
+[^:]+:[ ]+0000 0000 0000 ?
+[^:]+:[ ]+607f 89ab 4567 0123[ ]+\.byte[ ]+0x7f, 0x60, 0xab, 0x89, 0x67, 0x45, 0x23, 0x01, 0x10, 0x32, 0x54, 0x76, 0x98, 0xba, 0xdc, 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+[^:]+:[ ]+3210 7654 ba98 fedc ?
+[^:]+:[ ]+0000 0000 0000 ?
+[^:]+:[ ]+607f 33cc 55aa cdef[ ]+\.byte[ ]+0x7f, 0x60, 0xcc, 0x33, 0xaa, 0x55, 0xef, 0xcd, 0xab, 0x89, 0x67, 0x45, 0x23, 0x01, 0x10, 0x32, 0x54, 0x76, 0x98, 0xba, 0xdc, 0x00
+[^:]+:[ ]+89ab 4567 0123 3210 ?
+[^:]+:[ ]+7654 ba98 00dc ?
+[^:]+:[ ]+607f 33cc 55aa cdef[ ]+\.byte[ ]+0x7f, 0x60, 0xcc, 0x33, 0xaa, 0x55, 0xef, 0xcd, 0xab, 0x89, 0x67, 0x45, 0x23, 0x01, 0x10, 0x32, 0x54, 0x76, 0x98, 0xba, 0xdc, 0x00
+[^:]+:[ ]+89ab 4567 0123 3210 ?
+[^:]+:[ ]+7654 ba98 00dc ?
+[^:]+:[ ]+607f 33cc 55aa cdef[ ]+\.byte[ ]+0x7f, 0x60, 0xcc, 0x33, 0xaa, 0x55, 0xef, 0xcd, 0xab, 0x89, 0x67, 0x45, 0x23, 0x01, 0x10, 0x32, 0x54, 0x76, 0x98, 0xba, 0xdc, 0xfe
+[^:]+:[ ]+89ab 4567 0123 3210 ?
+[^:]+:[ ]+7654 ba98 fedc ?
+[^:]+:[ ]+607f 33cc 55aa cdef[ ]+\.byte[ ]+0x7f, 0x60, 0xcc, 0x33, 0xaa, 0x55, 0xef, 0xcd, 0xab, 0x89, 0x67, 0x45, 0x23, 0x01, 0x10, 0x32, 0x54, 0x76, 0x98, 0xba, 0xdc, 0xfe
+[^:]+:[ ]+89ab 4567 0123 3210 ?
+[^:]+:[ ]+7654 ba98 fedc ?
diff --git a/gas/testsuite/gas/riscv/insn.s b/gas/testsuite/gas/riscv/insn.s
index 94f62fe5672e..48db59b14e88 100644
--- a/gas/testsuite/gas/riscv/insn.s
+++ b/gas/testsuite/gas/riscv/insn.s
@@ -70,3 +70,12 @@ target:
.insn 10, 0x007f
.insn 12, 0x107f
.insn 22, 0x607f
+
+ .insn 0x8000000000000000007f
+ .insn 10, 0x8000000000000000007f
+ .insn 0x000000000000fedcba98765432100123456789ab607f
+ .insn 22, 0x000000000000fedcba98765432100123456789ab607f
+ .insn 0x00dcba98765432100123456789abcdef55aa33cc607f
+ .insn 22, 0x00dcba98765432100123456789abcdef55aa33cc607f
+ .insn 0xfedcba98765432100123456789abcdef55aa33cc607f
+ .insn 22, 0xfedcba98765432100123456789abcdef55aa33cc607f
diff --git a/opcodes/riscv-dis.c b/opcodes/riscv-dis.c
index 3a31647a2f80..59ebbaf13417 100644
--- a/opcodes/riscv-dis.c
+++ b/opcodes/riscv-dis.c
@@ -641,7 +641,10 @@ print_insn_args (const char *oparg, insn_t l, bfd_vma pc, disassemble_info *info
this is little-endian code. */
static int
-riscv_disassemble_insn (bfd_vma memaddr, insn_t word, disassemble_info *info)
+riscv_disassemble_insn (bfd_vma memaddr,
+ insn_t word,
+ const bfd_byte *packet,
+ disassemble_info *info)
{
const struct riscv_opcode *op;
static bool init = false;
@@ -806,8 +809,7 @@ riscv_disassemble_insn (bfd_vma memaddr, insn_t word, disassemble_info *info)
", ");
(*info->fprintf_styled_func) (info->stream, dis_style_immediate,
"0x%02x",
- (unsigned int) (word & 0xff));
- word >>= 8;
+ (unsigned int) (*packet++));
}
}
break;
@@ -983,6 +985,7 @@ riscv_data_length (bfd_vma memaddr,
static int
riscv_disassemble_data (bfd_vma memaddr ATTRIBUTE_UNUSED,
insn_t data,
+ const bfd_byte *packet ATTRIBUTE_UNUSED,
disassemble_info *info)
{
info->display_endian = info->endian;
@@ -1037,7 +1040,7 @@ print_insn_riscv (bfd_vma memaddr, struct disassemble_info *info)
bfd_vma dump_size;
int status;
enum riscv_seg_mstate mstate;
- int (*riscv_disassembler) (bfd_vma, insn_t, struct disassemble_info *);
+ int (*riscv_disassembler) (bfd_vma, insn_t, const bfd_byte*, struct disassemble_info *);
if (info->disassembler_options != NULL)
{
@@ -1081,7 +1084,7 @@ print_insn_riscv (bfd_vma memaddr, struct disassemble_info *info)
}
insn = (insn_t) bfd_get_bits (packet, dump_size * 8, false);
- return (*riscv_disassembler) (memaddr, insn, info);
+ return (*riscv_disassembler) (memaddr, insn, packet, info);
}
disassembler_ftype
--
2.38.1
next prev parent reply other threads:[~2022-11-19 7:11 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-11-19 7:10 [PATCH 0/2] RISC-V: Better support for long instructions (64 < x <= 176 [bits]) Tsukasa OI
2022-11-19 7:10 ` [PATCH 1/2] RISC-V: Make .insn tests stricter Tsukasa OI
2022-11-21 7:32 ` Jan Beulich
2022-11-23 8:20 ` Tsukasa OI
2022-11-23 8:56 ` Jan Beulich
2022-11-19 7:10 ` Tsukasa OI [this message]
2022-11-21 7:37 ` [PATCH 2/2] RISC-V: Better support for long instructions Jan Beulich
2022-11-23 8:40 ` Tsukasa OI
2022-11-23 8:44 ` Jan Beulich
2022-11-23 8:51 ` Tsukasa OI
2022-11-25 1:38 ` Nelson Chu
2022-11-25 2:33 ` Tsukasa OI
2022-11-22 0:43 ` [PATCH 0/2] RISC-V: Better support for long instructions (64 < x <= 176 [bits]) Nelson Chu
2022-11-23 8:30 ` [PATCH v2 " Tsukasa OI
2022-11-23 8:30 ` [PATCH v2 1/2] RISC-V: Make .insn tests stricter Tsukasa OI
2022-11-23 8:30 ` [PATCH v2 2/2] RISC-V: Better support for long instructions Tsukasa OI
2022-11-23 9:04 ` Jan Beulich
2022-11-24 2:34 ` Tsukasa OI
2022-11-24 7:31 ` Jan Beulich
2022-11-24 7:35 ` Tsukasa OI
2022-11-25 2:17 ` [PATCH v3 0/2] RISC-V: Better support for long instructions (64 < x <= 176 [bits]) Tsukasa OI
2022-11-25 2:17 ` [PATCH v3 1/2] RISC-V: Better support for long instructions (disassembler) Tsukasa OI
2022-11-25 8:03 ` Jan Beulich
2022-11-25 2:17 ` [PATCH v3 2/2] RISC-V: Better support for long instructions (assembler) Tsukasa OI
2022-11-25 8:15 ` Jan Beulich
2022-11-25 8:39 ` Tsukasa OI
2022-11-25 9:04 ` Jan Beulich
2022-11-25 9:18 ` Tsukasa OI
2022-11-25 9:56 ` Jan Beulich
2022-11-25 11:07 ` Tsukasa OI
2022-11-25 11:41 ` [PATCH v3 0/3] RISC-V: Better support for long instructions (64 < x <= 176 [bits]) Tsukasa OI
2022-11-25 11:41 ` [PATCH v3 1/3] RISC-V: Better support for long instructions (disassembler) Tsukasa OI
2022-11-25 11:42 ` [PATCH v4 0/3] RISC-V: Better support for long instructions (64 < x <= 176 [bits]) Tsukasa OI
2022-11-25 11:42 ` [PATCH v4 1/3] RISC-V: Better support for long instructions (disassembler) Tsukasa OI
2022-11-25 11:42 ` [PATCH v4 2/3] RISC-V: Better support for long instructions (assembler) Tsukasa OI
2022-11-25 11:42 ` [PATCH v4 3/3] RISC-V: Better support for long instructions (tests) Tsukasa OI
2022-11-25 13:08 ` [PATCH v4 0/3] RISC-V: Better support for long instructions (64 < x <= 176 [bits]) Jan Beulich
2022-11-28 1:53 ` Nelson Chu
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=ed49fad6bc6aa4f59d619fd6b445582331594e08.1668841829.git.research_trasio@irq.a4lg.com \
--to=research_trasio@irq.a4lg.com \
--cc=binutils@sourceware.org \
--cc=jbeulich@suse.com \
--cc=kito.cheng@sifive.com \
--cc=nelson@rivosinc.com \
--cc=palmer@dabbelt.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 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 read-only IMAP folder(s) and NNTP newsgroup(s).