diff options
author | Marc Schink <dev@zapb.de> | 2020-08-12 13:54:10 +0200 |
---|---|---|
committer | Antonio Borneo <borneo.antonio@gmail.com> | 2020-09-27 17:39:44 +0100 |
commit | 67008e1bea2dd1a89d77802b892d3390e8a55455 (patch) | |
tree | c8fc94be0a33ce94af08526d12564fd4241c33cb /src | |
parent | 762ddcb74948852b0dfb25fcbca0965b09249a2f (diff) | |
download | riscv-openocd-67008e1bea2dd1a89d77802b892d3390e8a55455.zip riscv-openocd-67008e1bea2dd1a89d77802b892d3390e8a55455.tar.gz riscv-openocd-67008e1bea2dd1a89d77802b892d3390e8a55455.tar.bz2 |
Use capstone for ARM disassembler
Change-Id: I1c9bf3f8178d4a06babe23a918e4411833ebc418
Signed-off-by: Marc Schink <dev@zapb.de>
Reviewed-on: http://openocd.zylin.com/4812
Tested-by: jenkins
Reviewed-by: Fredrik Hederstierna <fredrik@hederstierna.com>
Reviewed-by: Tarek BOCHKATI <tarek.bouchkati@gmail.com>
Reviewed-by: Antonio Borneo <borneo.antonio@gmail.com>
Diffstat (limited to 'src')
-rw-r--r-- | src/target/Makefile.am | 6 | ||||
-rw-r--r-- | src/target/arm_disassembler.c | 1662 | ||||
-rw-r--r-- | src/target/arm_disassembler.h | 6 | ||||
-rw-r--r-- | src/target/armv4_5.c | 53 |
4 files changed, 112 insertions, 1615 deletions
diff --git a/src/target/Makefile.am b/src/target/Makefile.am index 42d809d..724f38c 100644 --- a/src/target/Makefile.am +++ b/src/target/Makefile.am @@ -7,6 +7,7 @@ endif %C%_libtarget_la_LIBADD = %D%/openrisc/libopenrisc.la \ %D%/riscv/libriscv.la +%C%_libtarget_la_CPPFLAGS = $(AM_CPPFLAGS) STARTUP_TCL_SRCS += %D%/startup.tcl @@ -33,6 +34,11 @@ noinst_LTLIBRARIES += %D%/libtarget.la $(ARMV8_SRC) \ $(MIPS64_SRC) +if HAVE_CAPSTONE +%C%_libtarget_la_CPPFLAGS += $(CAPSTONE_CFLAGS) +%C%_libtarget_la_LIBADD += $(CAPSTONE_LIBS) +endif + TARGET_CORE_SRC = \ %D%/algorithm.c \ %D%/register.c \ diff --git a/src/target/arm_disassembler.c b/src/target/arm_disassembler.c index 59c0537..9b8c09e 100644 --- a/src/target/arm_disassembler.c +++ b/src/target/arm_disassembler.c @@ -26,6 +26,10 @@ #include "arm_disassembler.h" #include <helper/log.h> +#if HAVE_CAPSTONE +#include <capstone/capstone.h> +#endif + /* * This disassembler supports two main functions for OpenOCD: * @@ -3000,1616 +3004,126 @@ int thumb_evaluate_opcode(uint16_t opcode, uint32_t address, struct arm_instruct return -1; } -static int t2ev_b_bl(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - unsigned offset; - unsigned b21 = 1 << 21; - unsigned b22 = 1 << 22; - - /* instead of combining two smaller 16-bit branch instructions, - * Thumb2 uses only one larger 32-bit instruction. - */ - offset = opcode & 0x7ff; - offset |= (opcode & 0x03ff0000) >> 5; - if (opcode & (1 << 26)) { - offset |= 0xff << 23; - if ((opcode & (1 << 11)) == 0) - b21 = 0; - if ((opcode & (1 << 13)) == 0) - b22 = 0; - } else { - if (opcode & (1 << 11)) - b21 = 0; - if (opcode & (1 << 13)) - b22 = 0; - } - offset |= b21; - offset |= b22; - - - address += 4; - address += offset << 1; - - char *inst; - switch ((opcode >> 12) & 0x5) { - case 0x1: - inst = "B.W"; - instruction->type = ARM_B; - break; - case 0x4: - inst = "BLX"; - instruction->type = ARM_BLX; - address &= 0xfffffffc; - break; - case 0x5: - inst = "BL"; - instruction->type = ARM_BL; - break; - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } - instruction->info.b_bl_bx_blx.reg_operand = -1; - instruction->info.b_bl_bx_blx.target_address = address; - sprintf(cp, "%s\t%#8.8" PRIx32, inst, address); - - return ERROR_OK; -} - -static int t2ev_cond_b(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - unsigned offset; - unsigned b17 = 1 << 17; - unsigned b18 = 1 << 18; - unsigned cond = (opcode >> 22) & 0x0f; - - offset = opcode & 0x7ff; - offset |= (opcode & 0x003f0000) >> 5; - if (opcode & (1 << 26)) { - offset |= 0x1fff << 19; - if ((opcode & (1 << 11)) == 0) - b17 = 0; - if ((opcode & (1 << 13)) == 0) - b18 = 0; - } else { - if (opcode & (1 << 11)) - b17 = 0; - if (opcode & (1 << 13)) - b18 = 0; - } - offset |= b17; - offset |= b18; - - address += 4; - address += offset << 1; - - instruction->type = ARM_B; - instruction->info.b_bl_bx_blx.reg_operand = -1; - instruction->info.b_bl_bx_blx.target_address = address; - sprintf(cp, "B%s.W\t%#8.8" PRIx32, - arm_condition_strings[cond], - address); - - return ERROR_OK; -} - -static const char *special_name(int number) -{ - char *special = "(RESERVED)"; - - switch (number) { - case 0: - special = "apsr"; - break; - case 1: - special = "iapsr"; - break; - case 2: - special = "eapsr"; - break; - case 3: - special = "xpsr"; - break; - case 5: - special = "ipsr"; - break; - case 6: - special = "epsr"; - break; - case 7: - special = "iepsr"; - break; - case 8: - special = "msp"; - break; - case 9: - special = "psp"; - break; - case 16: - special = "primask"; - break; - case 17: - special = "basepri"; - break; - case 18: - special = "basepri_max"; - break; - case 19: - special = "faultmask"; - break; - case 20: - special = "control"; - break; - } - return special; -} - -static int t2ev_hint(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - const char *mnemonic; - - if (opcode & 0x0700) { - instruction->type = ARM_UNDEFINED_INSTRUCTION; - strcpy(cp, "UNDEFINED"); - return ERROR_OK; - } - - if (opcode & 0x00f0) { - sprintf(cp, "DBG\t#%d", (int) opcode & 0xf); - return ERROR_OK; - } - - switch (opcode & 0x0f) { - case 0: - mnemonic = "NOP.W"; - break; - case 1: - mnemonic = "YIELD.W"; - break; - case 2: - mnemonic = "WFE.W"; - break; - case 3: - mnemonic = "WFI.W"; - break; - case 4: - mnemonic = "SEV.W"; - break; - default: - mnemonic = "HINT.W (UNRECOGNIZED)"; - break; - } - strcpy(cp, mnemonic); - return ERROR_OK; -} - -static int t2ev_misc(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - const char *mnemonic; - - switch ((opcode >> 4) & 0x0f) { - case 0: - mnemonic = "LEAVEX"; - break; - case 1: - mnemonic = "ENTERX"; - break; - case 2: - mnemonic = "CLREX"; - break; - case 4: - mnemonic = "DSB"; - break; - case 5: - mnemonic = "DMB"; - break; - case 6: - mnemonic = "ISB"; - break; - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } - strcpy(cp, mnemonic); - return ERROR_OK; -} - -static int t2ev_b_misc(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - /* permanently undefined */ - if ((opcode & 0x07f07000) == 0x07f02000) { - instruction->type = ARM_UNDEFINED_INSTRUCTION; - strcpy(cp, "UNDEFINED"); - return ERROR_OK; - } - - switch ((opcode >> 12) & 0x5) { - case 0x1: - case 0x4: - case 0x5: - return t2ev_b_bl(opcode, address, instruction, cp); - case 0: - if (((opcode >> 23) & 0x07) != 0x07) - return t2ev_cond_b(opcode, address, instruction, cp); - if (opcode & (1 << 26)) - goto undef; - break; - } - - switch ((opcode >> 20) & 0x7f) { - case 0x38: - case 0x39: - sprintf(cp, "MSR\t%s, r%d", special_name(opcode & 0xff), - (int) (opcode >> 16) & 0x0f); - return ERROR_OK; - case 0x3a: - return t2ev_hint(opcode, address, instruction, cp); - case 0x3b: - return t2ev_misc(opcode, address, instruction, cp); - case 0x3c: - sprintf(cp, "BXJ\tr%d", (int) (opcode >> 16) & 0x0f); - return ERROR_OK; - case 0x3e: - case 0x3f: - sprintf(cp, "MRS\tr%d, %s", (int) (opcode >> 8) & 0x0f, - special_name(opcode & 0xff)); - return ERROR_OK; - } - -undef: - return ERROR_COMMAND_SYNTAX_ERROR; -} - -static int t2ev_data_mod_immed(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - char *mnemonic = NULL; - int rn = (opcode >> 16) & 0xf; - int rd = (opcode >> 8) & 0xf; - unsigned immed = opcode & 0xff; - unsigned func; - bool one = false; - char *suffix = ""; - char *suffix2 = ""; - - /* ARMv7-M: A5.3.2 Modified immediate constants */ - func = (opcode >> 11) & 0x0e; - if (immed & 0x80) - func |= 1; - if (opcode & (1 << 26)) - func |= 0x10; - - /* "Modified" immediates */ - switch (func >> 1) { - case 0: - break; - case 2: - immed <<= 8; - /* FALLTHROUGH */ - case 1: - immed += immed << 16; - break; - case 3: - immed += immed << 8; - immed += immed << 16; - break; - default: - immed |= 0x80; - immed = ror(immed, func); - } - - if (opcode & (1 << 20)) - suffix = "S"; - - switch ((opcode >> 21) & 0xf) { - case 0: - if (rd == 0xf) { - instruction->type = ARM_TST; - mnemonic = "TST"; - one = true; - suffix = ""; - rd = rn; - } else { - instruction->type = ARM_AND; - mnemonic = "AND"; - } - break; - case 1: - instruction->type = ARM_BIC; - mnemonic = "BIC"; - break; - case 2: - if (rn == 0xf) { - instruction->type = ARM_MOV; - mnemonic = "MOV"; - one = true; - suffix2 = ".W"; - } else { - instruction->type = ARM_ORR; - mnemonic = "ORR"; - } - break; - case 3: - if (rn == 0xf) { - instruction->type = ARM_MVN; - mnemonic = "MVN"; - one = true; - } else { - /* instruction->type = ARM_ORN; */ - mnemonic = "ORN"; - } - break; - case 4: - if (rd == 0xf) { - instruction->type = ARM_TEQ; - mnemonic = "TEQ"; - one = true; - suffix = ""; - rd = rn; - } else { - instruction->type = ARM_EOR; - mnemonic = "EOR"; - } - break; - case 8: - if (rd == 0xf) { - instruction->type = ARM_CMN; - mnemonic = "CMN"; - one = true; - suffix = ""; - rd = rn; - } else { - instruction->type = ARM_ADD; - mnemonic = "ADD"; - suffix2 = ".W"; - } - break; - case 10: - instruction->type = ARM_ADC; - mnemonic = "ADC"; - suffix2 = ".W"; - break; - case 11: - instruction->type = ARM_SBC; - mnemonic = "SBC"; - break; - case 13: - if (rd == 0xf) { - instruction->type = ARM_CMP; - mnemonic = "CMP"; - one = true; - suffix = ""; - rd = rn; - } else { - instruction->type = ARM_SUB; - mnemonic = "SUB"; - } - suffix2 = ".W"; - break; - case 14: - instruction->type = ARM_RSB; - mnemonic = "RSB"; - suffix2 = ".W"; - break; - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } - - if (one) - sprintf(cp, "%s%s\tr%d, #%d\t; %#8.8x", - mnemonic, suffix2, rd, immed, immed); - else - sprintf(cp, "%s%s%s\tr%d, r%d, #%d\t; %#8.8x", - mnemonic, suffix, suffix2, - rd, rn, immed, immed); - - return ERROR_OK; -} - -static int t2ev_data_immed(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - char *mnemonic = NULL; - int rn = (opcode >> 16) & 0xf; - int rd = (opcode >> 8) & 0xf; - unsigned immed; - bool add = false; - bool is_signed = false; - - immed = (opcode & 0x0ff) | ((opcode & 0x7000) >> 4); - if (opcode & (1 << 26)) - immed |= (1 << 11); - - switch ((opcode >> 20) & 0x1f) { - case 0: - if (rn == 0xf) { - add = true; - goto do_adr; - } - mnemonic = "ADDW"; - break; - case 4: - immed |= (opcode >> 4) & 0xf000; - sprintf(cp, "MOVW\tr%d, #%d\t; %#3.3x", rd, immed, immed); - return ERROR_OK; - case 0x0a: - if (rn == 0xf) - goto do_adr; - mnemonic = "SUBW"; - break; - case 0x0c: - /* move constant to top 16 bits of register */ - immed |= (opcode >> 4) & 0xf000; - sprintf(cp, "MOVT\tr%d, #%d\t; %#4.4x", rd, immed, immed); - return ERROR_OK; - case 0x10: - case 0x12: - is_signed = true; - /* fallthrough */ - case 0x18: - case 0x1a: - /* signed/unsigned saturated add */ - immed = (opcode >> 6) & 0x03; - immed |= (opcode >> 10) & 0x1c; - sprintf(cp, "%sSAT\tr%d, #%d, r%d, %s #%d\t", - is_signed ? "S" : "U", - rd, (int) (opcode & 0x1f) + is_signed, rn, - (opcode & (1 << 21)) ? "ASR" : "LSL", - immed ? immed : 32); - return ERROR_OK; - case 0x14: - is_signed = true; - /* FALLTHROUGH */ - case 0x1c: - /* signed/unsigned bitfield extract */ - immed = (opcode >> 6) & 0x03; - immed |= (opcode >> 10) & 0x1c; - sprintf(cp, "%sBFX\tr%d, r%d, #%d, #%d\t", - is_signed ? "S" : "U", - rd, rn, immed, - (int) (opcode & 0x1f) + 1); - return ERROR_OK; - case 0x16: - immed = (opcode >> 6) & 0x03; - immed |= (opcode >> 10) & 0x1c; - if (rn == 0xf) /* bitfield clear */ - sprintf(cp, "BFC\tr%d, #%d, #%d\t", - rd, immed, - (int) (opcode & 0x1f) + 1 - immed); - else /* bitfield insert */ - sprintf(cp, "BFI\tr%d, r%d, #%d, #%d\t", - rd, rn, immed, - (int) (opcode & 0x1f) + 1 - immed); - return ERROR_OK; - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } - - sprintf(cp, "%s\tr%d, r%d, #%d\t; %#3.3x", mnemonic, - rd, rn, immed, immed); - return ERROR_OK; - -do_adr: - address = thumb_alignpc4(address); - if (add) - address += immed; - else - address -= immed; - /* REVISIT "ADD/SUB Rd, PC, #const ; 0x..." might be better; - * not hiding the pc-relative stuff will sometimes be useful. - */ - sprintf(cp, "ADR.W\tr%d, %#8.8" PRIx32, rd, address); - return ERROR_OK; -} - -static int t2ev_store_single(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - unsigned op = (opcode >> 20) & 0xf; - char *size = ""; - char *suffix = ""; - char *p1 = ""; - char *p2 = "]"; - unsigned immed; - unsigned rn = (opcode >> 16) & 0x0f; - unsigned rt = (opcode >> 12) & 0x0f; - - if (rn == 0xf) - return ERROR_COMMAND_SYNTAX_ERROR; - - if (opcode & 0x0800) - op |= 1; - switch (op) { - /* byte */ - case 0x8: - case 0x9: - size = "B"; - goto imm12; - case 0x1: - size = "B"; - goto imm8; - case 0x0: - size = "B"; - break; - /* halfword */ - case 0xa: - case 0xb: - size = "H"; - goto imm12; - case 0x3: - size = "H"; - goto imm8; - case 0x2: - size = "H"; - break; - /* word */ - case 0xc: - case 0xd: - goto imm12; - case 0x5: - goto imm8; - case 0x4: - break; - /* error */ - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } - - sprintf(cp, "STR%s.W\tr%d, [r%d, r%d, LSL #%d]", - size, rt, rn, (int) opcode & 0x0f, - (int) (opcode >> 4) & 0x03); - return ERROR_OK; - -imm12: - immed = opcode & 0x0fff; - sprintf(cp, "STR%s.W\tr%d, [r%d, #%u]\t; %#3.3x", - size, rt, rn, immed, immed); - return ERROR_OK; - -imm8: - immed = opcode & 0x00ff; - - switch (opcode & 0x700) { - case 0x600: - suffix = "T"; - break; - case 0x000: - case 0x200: - return ERROR_COMMAND_SYNTAX_ERROR; - } - - /* two indexed modes will write back rn */ - if (opcode & 0x100) { - if (opcode & 0x400) /* pre-indexed */ - p2 = "]!"; - else { /* post-indexed */ - p1 = "]"; - p2 = ""; - } - } - - sprintf(cp, "STR%s%s\tr%d, [r%d%s, #%s%u%s\t; %#2.2x", - size, suffix, rt, rn, p1, - (opcode & 0x200) ? "" : "-", - immed, p2, immed); - return ERROR_OK; -} - -static int t2ev_mul32(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - int ra = (opcode >> 12) & 0xf; - - switch (opcode & 0x007000f0) { - case 0: - if (ra == 0xf) - sprintf(cp, "MUL\tr%d, r%d, r%d", - (int) (opcode >> 8) & 0xf, - (int) (opcode >> 16) & 0xf, - (int) (opcode >> 0) & 0xf); - else - sprintf(cp, "MLA\tr%d, r%d, r%d, r%d", - (int) (opcode >> 8) & 0xf, - (int) (opcode >> 16) & 0xf, - (int) (opcode >> 0) & 0xf, ra); - break; - case 0x10: - sprintf(cp, "MLS\tr%d, r%d, r%d, r%d", - (int) (opcode >> 8) & 0xf, - (int) (opcode >> 16) & 0xf, - (int) (opcode >> 0) & 0xf, ra); - break; - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } - return ERROR_OK; -} - -static int t2ev_mul64_div(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - int op = (opcode >> 4) & 0xf; - char *infix = "MUL"; - - op += (opcode >> 16) & 0x70; - switch (op) { - case 0x40: - case 0x60: - infix = "MLA"; - /* FALLTHROUGH */ - case 0: - case 0x20: - sprintf(cp, "%c%sL\tr%d, r%d, r%d, r%d", - (op & 0x20) ? 'U' : 'S', - infix, - (int) (opcode >> 12) & 0xf, - (int) (opcode >> 8) & 0xf, - (int) (opcode >> 16) & 0xf, - (int) (opcode >> 0) & 0xf); - break; - case 0x1f: - case 0x3f: - sprintf(cp, "%cDIV\tr%d, r%d, r%d", - (op & 0x20) ? 'U' : 'S', - (int) (opcode >> 8) & 0xf, - (int) (opcode >> 16) & 0xf, - (int) (opcode >> 0) & 0xf); - break; - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } - - return ERROR_OK; -} - -static int t2ev_ldm_stm(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - int rn = (opcode >> 16) & 0xf; - int op = (opcode >> 22) & 0x6; - int t = (opcode >> 21) & 1; - unsigned registers = opcode & 0xffff; - char *mode = ""; - - if (opcode & (1 << 20)) - op |= 1; - - switch (op) { - case 0: - mode = "DB"; - /* FALL THROUGH */ - case 6: - sprintf(cp, "SRS%s\tsp%s, #%d", mode, - t ? "!" : "", - (unsigned) (opcode & 0x1f)); - return ERROR_OK; - case 1: - mode = "DB"; - /* FALL THROUGH */ - case 7: - sprintf(cp, "RFE%s\tr%d%s", mode, - (unsigned) ((opcode >> 16) & 0xf), - t ? "!" : ""); - return ERROR_OK; - case 2: - sprintf(cp, "STM.W\tr%d%s, ", rn, t ? "!" : ""); - break; - case 3: - if (rn == 13 && t) - sprintf(cp, "POP.W\t"); - else - sprintf(cp, "LDM.W\tr%d%s, ", rn, t ? "!" : ""); - break; - case 4: - if (rn == 13 && t) - sprintf(cp, "PUSH.W\t"); - else - sprintf(cp, "STMDB\tr%d%s, ", rn, t ? "!" : ""); - break; - case 5: - sprintf(cp, "LDMDB.W\tr%d%s, ", rn, t ? "!" : ""); - break; - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } - - cp = strchr(cp, 0); - *cp++ = '{'; - for (t = 0; registers; t++, registers >>= 1) { - if ((registers & 1) == 0) - continue; - registers &= ~1; - sprintf(cp, "r%d%s", t, registers ? ", " : ""); - cp = strchr(cp, 0); - } - *cp++ = '}'; - *cp++ = 0; - - return ERROR_OK; -} - -/* load/store dual or exclusive, table branch */ -static int t2ev_ldrex_strex(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) +int arm_access_size(struct arm_instruction *instruction) { - unsigned op1op2 = (opcode >> 20) & 0x3; - unsigned op3 = (opcode >> 4) & 0xf; - char *mnemonic; - unsigned rn = (opcode >> 16) & 0xf; - unsigned rt = (opcode >> 12) & 0xf; - unsigned rd = (opcode >> 8) & 0xf; - unsigned imm = opcode & 0xff; - char *p1 = ""; - char *p2 = "]"; - - op1op2 |= (opcode >> 21) & 0xc; - switch (op1op2) { - case 0: - mnemonic = "STREX"; - goto strex; - case 1: - mnemonic = "LDREX"; - goto ldrex; - case 2: - case 6: - case 8: - case 10: - case 12: - case 14: - mnemonic = "STRD"; - goto immediate; - case 3: - case 7: - case 9: - case 11: - case 13: - case 15: - mnemonic = "LDRD"; - if (rn == 15) - goto literal; - else - goto immediate; - case 4: - switch (op3) { - case 4: - mnemonic = "STREXB"; - break; - case 5: - mnemonic = "STREXH"; - break; - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } - rd = opcode & 0xf; - imm = 0; - goto strex; - case 5: - switch (op3) { - case 0: - sprintf(cp, "TBB\t[r%u, r%u]", rn, imm & 0xf); - return ERROR_OK; - case 1: - sprintf(cp, "TBH\t[r%u, r%u, LSL #1]", rn, imm & 0xf); - return ERROR_OK; - case 4: - mnemonic = "LDREXB"; - break; - case 5: - mnemonic = "LDREXH"; - break; - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } - imm = 0; - goto ldrex; - } - return ERROR_COMMAND_SYNTAX_ERROR; - -strex: - imm <<= 2; - if (imm) - sprintf(cp, "%s\tr%u, r%u, [r%u, #%u]\t; %#2.2x", - mnemonic, rd, rt, rn, imm, imm); - else - sprintf(cp, "%s\tr%u, r%u, [r%u]", - mnemonic, rd, rt, rn); - return ERROR_OK; - -ldrex: - imm <<= 2; - if (imm) - sprintf(cp, "%s\tr%u, [r%u, #%u]\t; %#2.2x", - mnemonic, rt, rn, imm, imm); - else - sprintf(cp, "%s\tr%u, [r%u]", - mnemonic, rt, rn); - return ERROR_OK; - -immediate: - /* two indexed modes will write back rn */ - if (opcode & (1 << 21)) { - if (opcode & (1 << 24)) /* pre-indexed */ - p2 = "]!"; - else { /* post-indexed */ - p1 = "]"; - p2 = ""; - } + if ((instruction->type == ARM_LDRB) + || (instruction->type == ARM_LDRBT) + || (instruction->type == ARM_LDRSB) + || (instruction->type == ARM_STRB) + || (instruction->type == ARM_STRBT)) + return 1; + else if ((instruction->type == ARM_LDRH) + || (instruction->type == ARM_LDRSH) + || (instruction->type == ARM_STRH)) + return 2; + else if ((instruction->type == ARM_LDR) + || (instruction->type == ARM_LDRT) + || (instruction->type == ARM_STR) + || (instruction->type == ARM_STRT)) + return 4; + else if ((instruction->type == ARM_LDRD) + || (instruction->type == ARM_STRD)) + return 8; + else { + LOG_ERROR("BUG: instruction type %i isn't a load/store instruction", + instruction->type); + return 0; } - - imm <<= 2; - sprintf(cp, "%s\tr%u, r%u, [r%u%s, #%s%u%s\t; %#2.2x", - mnemonic, rt, rd, rn, p1, - (opcode & (1 << 23)) ? "" : "-", - imm, p2, imm); - return ERROR_OK; - -literal: - address = thumb_alignpc4(address); - imm <<= 2; - if (opcode & (1 << 23)) - address += imm; - else - address -= imm; - sprintf(cp, "%s\tr%u, r%u, %#8.8" PRIx32, - mnemonic, rt, rd, address); - return ERROR_OK; } -static int t2ev_data_shift(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) +#if HAVE_CAPSTONE +static void print_opcode(struct command_invocation *cmd, const cs_insn *insn) { - int op = (opcode >> 21) & 0xf; - int rd = (opcode >> 8) & 0xf; - int rn = (opcode >> 16) & 0xf; - int type = (opcode >> 4) & 0x3; - int immed = (opcode >> 6) & 0x3; - char *mnemonic; - char *suffix = ""; - - immed |= (opcode >> 10) & 0x1c; - if (opcode & (1 << 20)) - suffix = "S"; - - switch (op) { - case 0: - if (rd == 0xf) { - if (!(opcode & (1 << 20))) - return ERROR_COMMAND_SYNTAX_ERROR; - instruction->type = ARM_TST; - mnemonic = "TST"; - suffix = ""; - goto two; - } - instruction->type = ARM_AND; - mnemonic = "AND"; - break; - case 1: - instruction->type = ARM_BIC; - mnemonic = "BIC"; - break; - case 2: - if (rn == 0xf) { - instruction->type = ARM_MOV; - switch (type) { - case 0: - if (immed == 0) { - sprintf(cp, "MOV%s.W\tr%d, r%d", - suffix, rd, - (int) (opcode & 0xf)); - return ERROR_OK; - } - mnemonic = "LSL"; - break; - case 1: - mnemonic = "LSR"; - break; - case 2: - mnemonic = "ASR"; - break; - default: - if (immed == 0) { - sprintf(cp, "RRX%s\tr%d, r%d", - suffix, rd, - (int) (opcode & 0xf)); - return ERROR_OK; - } - mnemonic = "ROR"; - break; - } - goto immediate; - } else { - instruction->type = ARM_ORR; - mnemonic = "ORR"; - } - break; - case 3: - if (rn == 0xf) { - instruction->type = ARM_MVN; - mnemonic = "MVN"; - rn = rd; - goto two; - } else { - /* instruction->type = ARM_ORN; */ - mnemonic = "ORN"; - } - break; - case 4: - if (rd == 0xf) { - if (!(opcode & (1 << 20))) - return ERROR_COMMAND_SYNTAX_ERROR; - instruction->type = ARM_TEQ; - mnemonic = "TEQ"; - suffix = ""; - goto two; - } - instruction->type = ARM_EOR; - mnemonic = "EOR"; - break; - case 8: - if (rd == 0xf) { - if (!(opcode & (1 << 20))) - return ERROR_COMMAND_SYNTAX_ERROR; - instruction->type = ARM_CMN; - mnemonic = "CMN"; - suffix = ""; - goto two; - } - instruction->type = ARM_ADD; - mnemonic = "ADD"; - break; - case 0xa: - instruction->type = ARM_ADC; - mnemonic = "ADC"; - break; - case 0xb: - instruction->type = ARM_SBC; - mnemonic = "SBC"; - break; - case 0xd: - if (rd == 0xf) { - if (!(opcode & (1 << 21))) - return ERROR_COMMAND_SYNTAX_ERROR; - instruction->type = ARM_CMP; - mnemonic = "CMP"; - suffix = ""; - goto two; - } - instruction->type = ARM_SUB; - mnemonic = "SUB"; - break; - case 0xe: - instruction->type = ARM_RSB; - mnemonic = "RSB"; - break; - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } + uint32_t opcode = 0; - sprintf(cp, "%s%s.W\tr%d, r%d, r%d", - mnemonic, suffix, rd, rn, (int) (opcode & 0xf)); + memcpy(&opcode, insn->bytes, insn->size); -shift: - cp = strchr(cp, 0); + if (insn->size == 4) { + uint16_t opcode_high = opcode >> 16; + opcode = opcode & 0xffff; - switch (type) { - case 0: - if (immed == 0) - return ERROR_OK; - suffix = "LSL"; - break; - case 1: - suffix = "LSR"; - if (immed == 32) - immed = 0; - break; - case 2: - suffix = "ASR"; - if (immed == 32) - immed = 0; - break; - case 3: - if (immed == 0) { - strcpy(cp, ", RRX"); - return ERROR_OK; - } - suffix = "ROR"; - break; + command_print(cmd, "0x%08" PRIx64" %04x %04x\t%s%s%s", + insn->address, opcode, opcode_high, insn->mnemonic, + insn->op_str[0] ? "\t" : "", insn->op_str); + } else { + command_print(cmd, "0x%08" PRIx64" %04x\t%s%s%s", + insn->address, opcode, insn->mnemonic, + insn->op_str[0] ? "\t" : "", insn->op_str); } - sprintf(cp, ", %s #%d", suffix, immed ? immed : 32); - return ERROR_OK; - -two: - sprintf(cp, "%s%s.W\tr%d, r%d", - mnemonic, suffix, rn, (int) (opcode & 0xf)); - goto shift; - -immediate: - sprintf(cp, "%s%s.W\tr%d, r%d, #%d", - mnemonic, suffix, rd, - (int) (opcode & 0xf), immed ? immed : 32); - return ERROR_OK; } -static int t2ev_data_reg(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) +int arm_disassemble(struct command_invocation *cmd, struct target *target, + target_addr_t address, size_t count, bool thumb_mode) { - char *mnemonic; - char *suffix = ""; + csh handle; + int ret; + cs_insn *insn; + cs_mode mode; - if (((opcode >> 4) & 0xf) == 0) { - switch ((opcode >> 21) & 0x7) { - case 0: - mnemonic = "LSL"; - break; - case 1: - mnemonic = "LSR"; - break; - case 2: - mnemonic = "ASR"; - break; - case 3: - mnemonic = "ROR"; - break; - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } - - instruction->type = ARM_MOV; - if (opcode & (1 << 20)) - suffix = "S"; - sprintf(cp, "%s%s.W\tr%d, r%d, r%d", - mnemonic, suffix, - (int) (opcode >> 8) & 0xf, - (int) (opcode >> 16) & 0xf, - (int) (opcode >> 0) & 0xf); - - } else if (opcode & (1 << 7)) { - switch ((opcode >> 20) & 0xf) { - case 0: - case 1: - case 4: - case 5: - switch ((opcode >> 4) & 0x3) { - case 1: - suffix = ", ROR #8"; - break; - case 2: - suffix = ", ROR #16"; - break; - case 3: - suffix = ", ROR #24"; - break; - } - sprintf(cp, "%cXT%c.W\tr%d, r%d%s", - (opcode & (1 << 24)) ? 'U' : 'S', - (opcode & (1 << 26)) ? 'B' : 'H', - (int) (opcode >> 8) & 0xf, - (int) (opcode >> 0) & 0xf, - suffix); - break; - case 8: - case 9: - case 0xa: - case 0xb: - if (opcode & (1 << 6)) - return ERROR_COMMAND_SYNTAX_ERROR; - if (((opcode >> 12) & 0xf) != 0xf) - return ERROR_COMMAND_SYNTAX_ERROR; - if (!(opcode & (1 << 20))) - return ERROR_COMMAND_SYNTAX_ERROR; - - switch (((opcode >> 19) & 0x04) - | ((opcode >> 4) & 0x3)) { - case 0: - mnemonic = "REV.W"; - break; - case 1: - mnemonic = "REV16.W"; - break; - case 2: - mnemonic = "RBIT"; - break; - case 3: - mnemonic = "REVSH.W"; - break; - case 4: - mnemonic = "CLZ"; - break; - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } - sprintf(cp, "%s\tr%d, r%d", - mnemonic, - (int) (opcode >> 8) & 0xf, - (int) (opcode >> 0) & 0xf); - break; - default: - return ERROR_COMMAND_SYNTAX_ERROR; - } + if (!cs_support(CS_ARCH_ARM)) { + LOG_ERROR("ARM architecture not supported by capstone"); + return ERROR_FAIL; } - return ERROR_OK; -} + mode = CS_MODE_LITTLE_ENDIAN; -static int t2ev_load_word(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - int rn = (opcode >> 16) & 0xf; - int immed; + if (thumb_mode) + mode |= CS_MODE_THUMB; - instruction->type = ARM_LDR; + ret = cs_open(CS_ARCH_ARM, mode, &handle); - if (rn == 0xf) { - immed = opcode & 0x0fff; - if ((opcode & (1 << 23)) == 0) - immed = -immed; - sprintf(cp, "LDR\tr%d, %#8.8" PRIx32, - (int) (opcode >> 12) & 0xf, - thumb_alignpc4(address) + immed); - return ERROR_OK; + if (ret != CS_ERR_OK) { + LOG_ERROR("cs_open() failed: %s", cs_strerror(ret)); + return ERROR_FAIL; } - if (opcode & (1 << 23)) { - immed = opcode & 0x0fff; - sprintf(cp, "LDR.W\tr%d, [r%d, #%d]\t; %#3.3x", - (int) (opcode >> 12) & 0xf, - rn, immed, immed); - return ERROR_OK; - } + ret = cs_option(handle, CS_OPT_SKIPDATA, CS_OPT_ON); - if (!(opcode & (0x3f << 6))) { - sprintf(cp, "LDR.W\tr%d, [r%d, r%d, LSL #%d]", - (int) (opcode >> 12) & 0xf, - rn, - (int) (opcode >> 0) & 0xf, - (int) (opcode >> 4) & 0x3); - return ERROR_OK; + if (ret != CS_ERR_OK) { + LOG_ERROR("cs_option() failed: %s", cs_strerror(ret)); + cs_close(&handle); + return ERROR_FAIL; } + insn = cs_malloc(handle); - if (((opcode >> 8) & 0xf) == 0xe) { - immed = opcode & 0x00ff; - - sprintf(cp, "LDRT\tr%d, [r%d, #%d]\t; %#2.2x", - (int) (opcode >> 12) & 0xf, - rn, immed, immed); - return ERROR_OK; + if (!insn) { + LOG_ERROR("cs_malloc() failed\n"); + cs_close(&handle); + return ERROR_FAIL; } - if (((opcode >> 8) & 0xf) == 0xc || (opcode & 0x0900) == 0x0900) { - char *p1 = "]", *p2 = ""; + while (count > 0) { + uint8_t buffer[4]; - if (!(opcode & 0x0500)) - return ERROR_COMMAND_SYNTAX_ERROR; + ret = target_read_buffer(target, address, sizeof(buffer), buffer); - immed = opcode & 0x00ff; - - /* two indexed modes will write back rn */ - if (opcode & 0x100) { - if (opcode & 0x400) /* pre-indexed */ - p2 = "]!"; - else { /* post-indexed */ - p1 = "]"; - p2 = ""; - } + if (ret != ERROR_OK) { + cs_free(insn, 1); + cs_close(&handle); + return ret; } - sprintf(cp, "LDR\tr%d, [r%d%s, #%s%u%s\t; %#2.2x", - (int) (opcode >> 12) & 0xf, - rn, p1, - (opcode & 0x200) ? "" : "-", - immed, p2, immed); - return ERROR_OK; - } - - return ERROR_COMMAND_SYNTAX_ERROR; -} - -static int t2ev_load_byte_hints(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - int rn = (opcode >> 16) & 0xf; - int rt = (opcode >> 12) & 0xf; - int op2 = (opcode >> 6) & 0x3f; - unsigned immed; - char *p1 = "", *p2 = "]"; - char *mnemonic; - - switch ((opcode >> 23) & 0x3) { - case 0: - if ((rn & rt) == 0xf) { -pld_literal: - immed = opcode & 0xfff; - address = thumb_alignpc4(address); - if (opcode & (1 << 23)) - address += immed; - else - address -= immed; - sprintf(cp, "PLD\tr%d, %#8.8" PRIx32, - rt, address); - return ERROR_OK; - } - if (rn == 0x0f && rt != 0x0f) { -ldrb_literal: - immed = opcode & 0xfff; - address = thumb_alignpc4(address); - if (opcode & (1 << 23)) - address += immed; - else - address -= immed; - sprintf(cp, "LDRB\tr%d, %#8.8" PRIx32, - rt, address); - return ERROR_OK; - } - if (rn == 0x0f) - break; - if ((op2 & 0x3c) == 0x38) { - immed = opcode & 0xff; - sprintf(cp, "LDRBT\tr%d, [r%d, #%d]\t; %#2.2x", - rt, rn, immed, immed); - return ERROR_OK; - } - if ((op2 & 0x3c) == 0x30) { - if (rt == 0x0f) { - immed = opcode & 0xff; - immed = -immed; -preload_immediate: - p1 = (opcode & (1 << 21)) ? "W" : ""; - sprintf(cp, "PLD%s\t[r%d, #%d]\t; %#6.6x", - p1, rn, immed, immed); - return ERROR_OK; - } - mnemonic = "LDRB"; -ldrxb_immediate_t3: - immed = opcode & 0xff; - if (!(opcode & 0x200)) - immed = -immed; - - /* two indexed modes will write back rn */ - if (opcode & 0x100) { - if (opcode & 0x400) /* pre-indexed */ - p2 = "]!"; - else { /* post-indexed */ - p1 = "]"; - p2 = ""; - } - } -ldrxb_immediate_t2: - sprintf(cp, "%s\tr%d, [r%d%s, #%d%s\t; %#8.8x", - mnemonic, rt, rn, p1, - immed, p2, immed); - return ERROR_OK; - } - if ((op2 & 0x24) == 0x24) { - mnemonic = "LDRB"; - goto ldrxb_immediate_t3; - } - if (op2 == 0) { - int rm = opcode & 0xf; - - if (rt == 0x0f) - sprintf(cp, "PLD\t"); - else - sprintf(cp, "LDRB.W\tr%d, ", rt); - immed = (opcode >> 4) & 0x3; - cp = strchr(cp, 0); - sprintf(cp, "[r%d, r%d, LSL #%d]", rn, rm, immed); - return ERROR_OK; - } - break; - case 1: - if ((rn & rt) == 0xf) - goto pld_literal; - if (rt == 0xf) { - immed = opcode & 0xfff; - goto preload_immediate; - } - if (rn == 0x0f) - goto ldrb_literal; - mnemonic = "LDRB.W"; - immed = opcode & 0xfff; - goto ldrxb_immediate_t2; - case 2: - if ((rn & rt) == 0xf) { - immed = opcode & 0xfff; - address = thumb_alignpc4(address); - if (opcode & (1 << 23)) - address += immed; - else - address -= immed; - sprintf(cp, "PLI\t%#8.8" PRIx32, address); - return ERROR_OK; - } - if (rn == 0xf && rt != 0xf) { -ldrsb_literal: - immed = opcode & 0xfff; - address = thumb_alignpc4(address); - if (opcode & (1 << 23)) - address += immed; - else - address -= immed; - sprintf(cp, "LDRSB\t%#8.8" PRIx32, address); - return ERROR_OK; - } - if (rn == 0xf) - break; - if ((op2 & 0x3c) == 0x38) { - immed = opcode & 0xff; - sprintf(cp, "LDRSBT\tr%d, [r%d, #%d]\t; %#2.2x", - rt, rn, immed, immed); - return ERROR_OK; - } - if ((op2 & 0x3c) == 0x30) { - if (rt == 0xf) { - immed = opcode & 0xff; - immed = -immed; /* pli */ - sprintf(cp, "PLI\t[r%d, #%d]\t; -%#2.2x", - rn, immed, -immed); - return ERROR_OK; - } - mnemonic = "LDRSB"; - goto ldrxb_immediate_t3; - } - if ((op2 & 0x24) == 0x24) { - mnemonic = "LDRSB"; - goto ldrxb_immediate_t3; - } - if (op2 == 0) { - int rm = opcode & 0xf; - - if (rt == 0x0f) - sprintf(cp, "PLI\t"); - else - sprintf(cp, "LDRSB.W\tr%d, ", rt); - immed = (opcode >> 4) & 0x3; - cp = strchr(cp, 0); - sprintf(cp, "[r%d, r%d, LSL #%d]", rn, rm, immed); - return ERROR_OK; - } - break; - case 3: - if (rt == 0xf) { - immed = opcode & 0xfff; - sprintf(cp, "PLI\t[r%d, #%d]\t; %#3.3x", - rn, immed, immed); - return ERROR_OK; - } - if (rn == 0xf) - goto ldrsb_literal; - immed = opcode & 0xfff; - mnemonic = "LDRSB"; - goto ldrxb_immediate_t2; - } - - return ERROR_COMMAND_SYNTAX_ERROR; -} - -static int t2ev_load_halfword(uint32_t opcode, uint32_t address, - struct arm_instruction *instruction, char *cp) -{ - int rn = (opcode >> 16) & 0xf; - int rt = (opcode >> 12) & 0xf; - int op2 = (opcode >> 6) & 0x3f; - char *sign = ""; - unsigned immed; - - if (rt == 0xf) { - sprintf(cp, "HINT (UNALLOCATED)"); - return ERROR_OK; - } - - if (opcode & (1 << 24)) - sign = "S"; + size_t size = sizeof(buffer); + const uint8_t *tmp = buffer; - if ((opcode & (1 << 23)) == 0) { - if (rn == 0xf) { -ldrh_literal: - immed = opcode & 0xfff; - address = thumb_alignpc4(address); - if (opcode & (1 << 23)) - address += immed; - else - address -= immed; - sprintf(cp, "LDR%sH\tr%d, %#8.8" PRIx32, - sign, rt, address); - return ERROR_OK; - } - if (op2 == 0) { - int rm = opcode & 0xf; + ret = cs_disasm_iter(handle, &tmp, &size, &address, insn); - immed = (opcode >> 4) & 0x3; - sprintf(cp, "LDR%sH.W\tr%d, [r%d, r%d, LSL #%d]", - sign, rt, rn, rm, immed); - return ERROR_OK; - } - if ((op2 & 0x3c) == 0x38) { - immed = opcode & 0xff; - sprintf(cp, "LDR%sHT\tr%d, [r%d, #%d]\t; %#2.2x", - sign, rt, rn, immed, immed); - return ERROR_OK; - } - if ((op2 & 0x3c) == 0x30 || (op2 & 0x24) == 0x24) { - char *p1 = "", *p2 = "]"; - - immed = opcode & 0xff; - if (!(opcode & 0x200)) - immed = -immed; - - /* two indexed modes will write back rn */ - if (opcode & 0x100) { - if (opcode & 0x400) /* pre-indexed */ - p2 = "]!"; - else { /* post-indexed */ - p1 = "]"; - p2 = ""; - } - } - sprintf(cp, "LDR%sH\tr%d, [r%d%s, #%d%s\t; %#8.8x", - sign, rt, rn, p1, immed, p2, immed); - return ERROR_OK; + if (!ret) { + LOG_ERROR("cs_disasm_iter() failed: %s", + cs_strerror(cs_errno(handle))); + cs_free(insn, 1); + cs_close(&handle); + return ERROR_FAIL; } - } else { - if (rn == 0xf) - goto ldrh_literal; - - immed = opcode & 0xfff; - sprintf(cp, "LDR%sH%s\tr%d, [r%d, #%d]\t; %#6.6x", - sign, *sign ? "" : ".W", - rt, rn, immed, immed); - return ERROR_OK; - } - - return ERROR_COMMAND_SYNTAX_ERROR; -} - -/* - * REVISIT for Thumb2 instructions, instruction->type and friends aren't - * always set. That means eventual arm_simulate_step() support for Thumb2 - * will need work in this area. - */ -int thumb2_opcode(struct target *target, uint32_t address, struct arm_instruction *instruction) -{ - int retval; - uint16_t op; - uint32_t opcode; - char *cp; - - /* clear low bit ... it's set on function pointers */ - address &= ~1; - - /* clear fields, to avoid confusion */ - memset(instruction, 0, sizeof(struct arm_instruction)); - /* read first halfword, see if this is the only one */ - retval = target_read_u16(target, address, &op); - if (retval != ERROR_OK) - return retval; - - switch (op & 0xf800) { - case 0xf800: - case 0xf000: - case 0xe800: - /* 32-bit instructions */ - instruction->instruction_size = 4; - opcode = op << 16; - retval = target_read_u16(target, address + 2, &op); - if (retval != ERROR_OK) - return retval; - opcode |= op; - instruction->opcode = opcode; - break; - default: - /* 16-bit: Thumb1 + IT + CBZ/CBNZ + ... */ - return thumb_evaluate_opcode(op, address, instruction); + print_opcode(cmd, insn); + count--; } - snprintf(instruction->text, 128, - "0x%8.8" PRIx32 " 0x%8.8" PRIx32 "\t", - address, opcode); - cp = strchr(instruction->text, 0); - retval = ERROR_FAIL; - - /* ARMv7-M: A5.3.1 Data processing (modified immediate) */ - if ((opcode & 0x1a008000) == 0x10000000) - retval = t2ev_data_mod_immed(opcode, address, instruction, cp); - - /* ARMv7-M: A5.3.3 Data processing (plain binary immediate) */ - else if ((opcode & 0x1a008000) == 0x12000000) - retval = t2ev_data_immed(opcode, address, instruction, cp); - - /* ARMv7-M: A5.3.4 Branches and miscellaneous control */ - else if ((opcode & 0x18008000) == 0x10008000) - retval = t2ev_b_misc(opcode, address, instruction, cp); - - /* ARMv7-M: A5.3.5 Load/store multiple */ - else if ((opcode & 0x1e400000) == 0x08000000) - retval = t2ev_ldm_stm(opcode, address, instruction, cp); - - /* ARMv7-M: A5.3.6 Load/store dual or exclusive, table branch */ - else if ((opcode & 0x1e400000) == 0x08400000) - retval = t2ev_ldrex_strex(opcode, address, instruction, cp); - - /* ARMv7-M: A5.3.7 Load word */ - else if ((opcode & 0x1f700000) == 0x18500000) - retval = t2ev_load_word(opcode, address, instruction, cp); - - /* ARMv7-M: A5.3.8 Load halfword, unallocated memory hints */ - else if ((opcode & 0x1e700000) == 0x18300000) - retval = t2ev_load_halfword(opcode, address, instruction, cp); - - /* ARMv7-M: A5.3.9 Load byte, memory hints */ - else if ((opcode & 0x1e700000) == 0x18100000) - retval = t2ev_load_byte_hints(opcode, address, instruction, cp); - - /* ARMv7-M: A5.3.10 Store single data item */ - else if ((opcode & 0x1f100000) == 0x18000000) - retval = t2ev_store_single(opcode, address, instruction, cp); - - /* ARMv7-M: A5.3.11 Data processing (shifted register) */ - else if ((opcode & 0x1e000000) == 0x0a000000) - retval = t2ev_data_shift(opcode, address, instruction, cp); + cs_free(insn, 1); + cs_close(&handle); - /* ARMv7-M: A5.3.12 Data processing (register) - * and A5.3.13 Miscellaneous operations - */ - else if ((opcode & 0x1f000000) == 0x1a000000) - retval = t2ev_data_reg(opcode, address, instruction, cp); - - /* ARMv7-M: A5.3.14 Multiply, and multiply accumulate */ - else if ((opcode & 0x1f800000) == 0x1b000000) - retval = t2ev_mul32(opcode, address, instruction, cp); - - /* ARMv7-M: A5.3.15 Long multiply, long multiply accumulate, divide */ - else if ((opcode & 0x1f800000) == 0x1b800000) - retval = t2ev_mul64_div(opcode, address, instruction, cp); - - if (retval == ERROR_OK) - return retval; - - /* - * Thumb2 also supports coprocessor, ThumbEE, and DSP/Media (SIMD) - * instructions; not yet handled here. - */ - - if (retval == ERROR_COMMAND_SYNTAX_ERROR) { - instruction->type = ARM_UNDEFINED_INSTRUCTION; - strcpy(cp, "UNDEFINED OPCODE"); - return ERROR_OK; - } - - LOG_DEBUG("Can't decode 32-bit Thumb2 yet (opcode=%08" PRIx32 ")", - opcode); - - strcpy(cp, "(32-bit Thumb2 ...)"); return ERROR_OK; } - -int arm_access_size(struct arm_instruction *instruction) -{ - if ((instruction->type == ARM_LDRB) - || (instruction->type == ARM_LDRBT) - || (instruction->type == ARM_LDRSB) - || (instruction->type == ARM_STRB) - || (instruction->type == ARM_STRBT)) - return 1; - else if ((instruction->type == ARM_LDRH) - || (instruction->type == ARM_LDRSH) - || (instruction->type == ARM_STRH)) - return 2; - else if ((instruction->type == ARM_LDR) - || (instruction->type == ARM_LDRT) - || (instruction->type == ARM_STR) - || (instruction->type == ARM_STRT)) - return 4; - else if ((instruction->type == ARM_LDRD) - || (instruction->type == ARM_STRD)) - return 8; - else { - LOG_ERROR("BUG: instruction type %i isn't a load/store instruction", - instruction->type); - return 0; - } -} +#endif /* HAVE_CAPSTONE */ diff --git a/src/target/arm_disassembler.h b/src/target/arm_disassembler.h index 486e903..beecb3f 100644 --- a/src/target/arm_disassembler.h +++ b/src/target/arm_disassembler.h @@ -197,9 +197,11 @@ int arm_evaluate_opcode(uint32_t opcode, uint32_t address, struct arm_instruction *instruction); int thumb_evaluate_opcode(uint16_t opcode, uint32_t address, struct arm_instruction *instruction); -int thumb2_opcode(struct target *target, uint32_t address, - struct arm_instruction *instruction); int arm_access_size(struct arm_instruction *instruction); +#if HAVE_CAPSTONE +int arm_disassemble(struct command_invocation *cmd, struct target *target, + target_addr_t address, size_t count, bool thumb_mode); +#endif #define COND(opcode) (arm_condition_strings[(opcode & 0xf0000000) >> 28]) diff --git a/src/target/armv4_5.c b/src/target/armv4_5.c index 58bc339..7da28e3 100644 --- a/src/target/armv4_5.c +++ b/src/target/armv4_5.c @@ -942,7 +942,7 @@ COMMAND_HANDLER(handle_armv4_5_core_state_command) COMMAND_HANDLER(handle_arm_disassemble_command) { - int retval = ERROR_OK; +#if HAVE_CAPSTONE struct target *target = get_current_target(CMD_CTX); if (target == NULL) { @@ -952,8 +952,8 @@ COMMAND_HANDLER(handle_arm_disassemble_command) struct arm *arm = target_to_arm(target); target_addr_t address; - int count = 1; - int thumb = 0; + unsigned int count = 1; + bool thumb = false; if (!is_arm(arm)) { command_print(CMD, "current target isn't an ARM"); @@ -962,62 +962,37 @@ COMMAND_HANDLER(handle_arm_disassemble_command) if (arm->core_type == ARM_CORE_TYPE_M_PROFILE) { /* armv7m is always thumb mode */ - thumb = 1; + thumb = true; } switch (CMD_ARGC) { case 3: if (strcmp(CMD_ARGV[2], "thumb") != 0) - goto usage; - thumb = 1; + return ERROR_COMMAND_SYNTAX_ERROR; + thumb = true; /* FALL THROUGH */ case 2: - COMMAND_PARSE_NUMBER(int, CMD_ARGV[1], count); + COMMAND_PARSE_NUMBER(uint, CMD_ARGV[1], count); /* FALL THROUGH */ case 1: COMMAND_PARSE_ADDRESS(CMD_ARGV[0], address); if (address & 0x01) { if (!thumb) { command_print(CMD, "Disassemble as Thumb"); - thumb = 1; + thumb = true; } address &= ~1; } break; default: -usage: - count = 0; - retval = ERROR_COMMAND_SYNTAX_ERROR; - } - - while (count-- > 0) { - struct arm_instruction cur_instruction; - - if (thumb) { - /* Always use Thumb2 disassembly for best handling - * of 32-bit BL/BLX, and to work with newer cores - * (some ARMv6, all ARMv7) that use Thumb2. - */ - retval = thumb2_opcode(target, address, - &cur_instruction); - if (retval != ERROR_OK) - break; - } else { - uint32_t opcode; - - retval = target_read_u32(target, address, &opcode); - if (retval != ERROR_OK) - break; - retval = arm_evaluate_opcode(opcode, address, - &cur_instruction) != ERROR_OK; - if (retval != ERROR_OK) - break; - } - command_print(CMD, "%s", cur_instruction.text); - address += cur_instruction.instruction_size; + return ERROR_COMMAND_SYNTAX_ERROR; } - return retval; + return arm_disassemble(CMD, target, address, count, thumb); +#else + command_print(CMD, "capstone disassembly framework required"); + return ERROR_FAIL; +#endif } static int jim_mcrmrc(Jim_Interp *interp, int argc, Jim_Obj * const *argv) |