MIPS: Optimize uasm insn lookup.
Instead of doing a linear search through the insn_table for each
instruction, use the opcode as direct index into the table. This will
give constant time lookup performance as the number of supported
opcodes increases. Make the tables const as they are only ever read.
For uasm-mips.c sort the table alphabetically, and remove duplicate
entries, uasm-micromips.c was already sorted and duplicate free.
There is a small savings in object size as struct insn loses a field:
$ size arch/mips/mm/uasm-mips.o arch/mips/mm/uasm-mips.o.save
text data bss dec hex filename
10040 0 0 10040 2738 arch/mips/mm/uasm-mips.o
9240 1120 0 10360 2878 arch/mips/mm/uasm-mips.o.save
Signed-off-by: David Daney <david.daney@cavium.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Matt Redfearn <matt.redfearn@imgtec.com>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/16365/
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index 277cf52..c28ff53 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -40,93 +40,92 @@
#include "uasm.c"
-static struct insn insn_table_MM[] = {
- { insn_addu, M(mm_pool32a_op, 0, 0, 0, 0, mm_addu32_op), RT | RS | RD },
- { insn_addiu, M(mm_addiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM },
- { insn_and, M(mm_pool32a_op, 0, 0, 0, 0, mm_and_op), RT | RS | RD },
- { insn_andi, M(mm_andi32_op, 0, 0, 0, 0, 0), RT | RS | UIMM },
- { insn_beq, M(mm_beq32_op, 0, 0, 0, 0, 0), RS | RT | BIMM },
- { insn_beql, 0, 0 },
- { insn_bgez, M(mm_pool32i_op, mm_bgez_op, 0, 0, 0, 0), RS | BIMM },
- { insn_bgezl, 0, 0 },
- { insn_bltz, M(mm_pool32i_op, mm_bltz_op, 0, 0, 0, 0), RS | BIMM },
- { insn_bltzl, 0, 0 },
- { insn_bne, M(mm_bne32_op, 0, 0, 0, 0, 0), RT | RS | BIMM },
- { insn_cache, M(mm_pool32b_op, 0, 0, mm_cache_func, 0, 0), RT | RS | SIMM },
- { insn_cfc1, M(mm_pool32f_op, 0, 0, 0, mm_cfc1_op, mm_32f_73_op), RT | RS },
- { insn_cfcmsa, M(mm_pool32s_op, 0, msa_cfc_op, 0, 0, mm_32s_elm_op), RD | RE },
- { insn_ctc1, M(mm_pool32f_op, 0, 0, 0, mm_ctc1_op, mm_32f_73_op), RT | RS },
- { insn_ctcmsa, M(mm_pool32s_op, 0, msa_ctc_op, 0, 0, mm_32s_elm_op), RD | RE },
- { insn_daddu, 0, 0 },
- { insn_daddiu, 0, 0 },
- { insn_di, M(mm_pool32a_op, 0, 0, 0, mm_di_op, mm_pool32axf_op), RS },
- { insn_divu, M(mm_pool32a_op, 0, 0, 0, mm_divu_op, mm_pool32axf_op), RT | RS },
- { insn_dmfc0, 0, 0 },
- { insn_dmtc0, 0, 0 },
- { insn_dsll, 0, 0 },
- { insn_dsll32, 0, 0 },
- { insn_dsra, 0, 0 },
- { insn_dsrl, 0, 0 },
- { insn_dsrl32, 0, 0 },
- { insn_drotr, 0, 0 },
- { insn_drotr32, 0, 0 },
- { insn_dsubu, 0, 0 },
- { insn_eret, M(mm_pool32a_op, 0, 0, 0, mm_eret_op, mm_pool32axf_op), 0 },
- { insn_ins, M(mm_pool32a_op, 0, 0, 0, 0, mm_ins_op), RT | RS | RD | RE },
- { insn_ext, M(mm_pool32a_op, 0, 0, 0, 0, mm_ext_op), RT | RS | RD | RE },
- { insn_j, M(mm_j32_op, 0, 0, 0, 0, 0), JIMM },
- { insn_jal, M(mm_jal32_op, 0, 0, 0, 0, 0), JIMM },
- { insn_jalr, M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RT | RS },
- { insn_jr, M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RS },
- { insn_lb, M(mm_lb32_op, 0, 0, 0, 0, 0), RT | RS | SIMM },
- { insn_ld, 0, 0 },
- { insn_lh, M(mm_lh32_op, 0, 0, 0, 0, 0), RS | RS | SIMM },
- { insn_ll, M(mm_pool32c_op, 0, 0, (mm_ll_func << 1), 0, 0), RS | RT | SIMM },
- { insn_lld, 0, 0 },
- { insn_lui, M(mm_pool32i_op, mm_lui_op, 0, 0, 0, 0), RS | SIMM },
- { insn_lw, M(mm_lw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM },
- { insn_mfc0, M(mm_pool32a_op, 0, 0, 0, mm_mfc0_op, mm_pool32axf_op), RT | RS | RD },
- { insn_mfhi, M(mm_pool32a_op, 0, 0, 0, mm_mfhi32_op, mm_pool32axf_op), RS },
- { insn_mflo, M(mm_pool32a_op, 0, 0, 0, mm_mflo32_op, mm_pool32axf_op), RS },
- { insn_mtc0, M(mm_pool32a_op, 0, 0, 0, mm_mtc0_op, mm_pool32axf_op), RT | RS | RD },
- { insn_mthi, M(mm_pool32a_op, 0, 0, 0, mm_mthi32_op, mm_pool32axf_op), RS },
- { insn_mtlo, M(mm_pool32a_op, 0, 0, 0, mm_mtlo32_op, mm_pool32axf_op), RS },
- { insn_mul, M(mm_pool32a_op, 0, 0, 0, 0, mm_mul_op), RT | RS | RD },
- { insn_or, M(mm_pool32a_op, 0, 0, 0, 0, mm_or32_op), RT | RS | RD },
- { insn_ori, M(mm_ori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM },
- { insn_pref, M(mm_pool32c_op, 0, 0, (mm_pref_func << 1), 0, 0), RT | RS | SIMM },
- { insn_rfe, 0, 0 },
- { insn_sc, M(mm_pool32c_op, 0, 0, (mm_sc_func << 1), 0, 0), RT | RS | SIMM },
- { insn_scd, 0, 0 },
- { insn_sd, 0, 0 },
- { insn_sll, M(mm_pool32a_op, 0, 0, 0, 0, mm_sll32_op), RT | RS | RD },
- { insn_sllv, M(mm_pool32a_op, 0, 0, 0, 0, mm_sllv32_op), RT | RS | RD },
- { insn_slt, M(mm_pool32a_op, 0, 0, 0, 0, mm_slt_op), RT | RS | RD },
- { insn_sltiu, M(mm_sltiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM },
- { insn_sltu, M(mm_pool32a_op, 0, 0, 0, 0, mm_sltu_op), RT | RS | RD },
- { insn_sra, M(mm_pool32a_op, 0, 0, 0, 0, mm_sra_op), RT | RS | RD },
- { insn_srl, M(mm_pool32a_op, 0, 0, 0, 0, mm_srl32_op), RT | RS | RD },
- { insn_srlv, M(mm_pool32a_op, 0, 0, 0, 0, mm_srlv32_op), RT | RS | RD },
- { insn_rotr, M(mm_pool32a_op, 0, 0, 0, 0, mm_rotr_op), RT | RS | RD },
- { insn_subu, M(mm_pool32a_op, 0, 0, 0, 0, mm_subu32_op), RT | RS | RD },
- { insn_sw, M(mm_sw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM },
- { insn_sync, M(mm_pool32a_op, 0, 0, 0, mm_sync_op, mm_pool32axf_op), RS },
- { insn_tlbp, M(mm_pool32a_op, 0, 0, 0, mm_tlbp_op, mm_pool32axf_op), 0 },
- { insn_tlbr, M(mm_pool32a_op, 0, 0, 0, mm_tlbr_op, mm_pool32axf_op), 0 },
- { insn_tlbwi, M(mm_pool32a_op, 0, 0, 0, mm_tlbwi_op, mm_pool32axf_op), 0 },
- { insn_tlbwr, M(mm_pool32a_op, 0, 0, 0, mm_tlbwr_op, mm_pool32axf_op), 0 },
- { insn_wait, M(mm_pool32a_op, 0, 0, 0, mm_wait_op, mm_pool32axf_op), SCIMM },
- { insn_wsbh, M(mm_pool32a_op, 0, 0, 0, mm_wsbh_op, mm_pool32axf_op), RT | RS },
- { insn_xor, M(mm_pool32a_op, 0, 0, 0, 0, mm_xor32_op), RT | RS | RD },
- { insn_xori, M(mm_xori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM },
- { insn_dins, 0, 0 },
- { insn_dinsm, 0, 0 },
- { insn_syscall, M(mm_pool32a_op, 0, 0, 0, mm_syscall_op, mm_pool32axf_op), SCIMM},
- { insn_bbit0, 0, 0 },
- { insn_bbit1, 0, 0 },
- { insn_lwx, 0, 0 },
- { insn_ldx, 0, 0 },
- { insn_invalid, 0, 0 }
+static const struct insn const insn_table_MM[insn_invalid] = {
+ [insn_addu] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_addu32_op), RT | RS | RD},
+ [insn_addiu] = {M(mm_addiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
+ [insn_and] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_and_op), RT | RS | RD},
+ [insn_andi] = {M(mm_andi32_op, 0, 0, 0, 0, 0), RT | RS | UIMM},
+ [insn_beq] = {M(mm_beq32_op, 0, 0, 0, 0, 0), RS | RT | BIMM},
+ [insn_beql] = {0, 0},
+ [insn_bgez] = {M(mm_pool32i_op, mm_bgez_op, 0, 0, 0, 0), RS | BIMM},
+ [insn_bgezl] = {0, 0},
+ [insn_bltz] = {M(mm_pool32i_op, mm_bltz_op, 0, 0, 0, 0), RS | BIMM},
+ [insn_bltzl] = {0, 0},
+ [insn_bne] = {M(mm_bne32_op, 0, 0, 0, 0, 0), RT | RS | BIMM},
+ [insn_cache] = {M(mm_pool32b_op, 0, 0, mm_cache_func, 0, 0), RT | RS | SIMM},
+ [insn_cfc1] = {M(mm_pool32f_op, 0, 0, 0, mm_cfc1_op, mm_32f_73_op), RT | RS},
+ [insn_cfcmsa] = {M(mm_pool32s_op, 0, msa_cfc_op, 0, 0, mm_32s_elm_op), RD | RE},
+ [insn_ctc1] = {M(mm_pool32f_op, 0, 0, 0, mm_ctc1_op, mm_32f_73_op), RT | RS},
+ [insn_ctcmsa] = {M(mm_pool32s_op, 0, msa_ctc_op, 0, 0, mm_32s_elm_op), RD | RE},
+ [insn_daddu] = {0, 0},
+ [insn_daddiu] = {0, 0},
+ [insn_di] = {M(mm_pool32a_op, 0, 0, 0, mm_di_op, mm_pool32axf_op), RS},
+ [insn_divu] = {M(mm_pool32a_op, 0, 0, 0, mm_divu_op, mm_pool32axf_op), RT | RS},
+ [insn_dmfc0] = {0, 0},
+ [insn_dmtc0] = {0, 0},
+ [insn_dsll] = {0, 0},
+ [insn_dsll32] = {0, 0},
+ [insn_dsra] = {0, 0},
+ [insn_dsrl] = {0, 0},
+ [insn_dsrl32] = {0, 0},
+ [insn_drotr] = {0, 0},
+ [insn_drotr32] = {0, 0},
+ [insn_dsubu] = {0, 0},
+ [insn_eret] = {M(mm_pool32a_op, 0, 0, 0, mm_eret_op, mm_pool32axf_op), 0},
+ [insn_ins] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_ins_op), RT | RS | RD | RE},
+ [insn_ext] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_ext_op), RT | RS | RD | RE},
+ [insn_j] = {M(mm_j32_op, 0, 0, 0, 0, 0), JIMM},
+ [insn_jal] = {M(mm_jal32_op, 0, 0, 0, 0, 0), JIMM},
+ [insn_jalr] = {M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RT | RS},
+ [insn_jr] = {M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RS},
+ [insn_lb] = {M(mm_lb32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
+ [insn_ld] = {0, 0},
+ [insn_lh] = {M(mm_lh32_op, 0, 0, 0, 0, 0), RS | RS | SIMM},
+ [insn_ll] = {M(mm_pool32c_op, 0, 0, (mm_ll_func << 1), 0, 0), RS | RT | SIMM},
+ [insn_lld] = {0, 0},
+ [insn_lui] = {M(mm_pool32i_op, mm_lui_op, 0, 0, 0, 0), RS | SIMM},
+ [insn_lw] = {M(mm_lw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
+ [insn_mfc0] = {M(mm_pool32a_op, 0, 0, 0, mm_mfc0_op, mm_pool32axf_op), RT | RS | RD},
+ [insn_mfhi] = {M(mm_pool32a_op, 0, 0, 0, mm_mfhi32_op, mm_pool32axf_op), RS},
+ [insn_mflo] = {M(mm_pool32a_op, 0, 0, 0, mm_mflo32_op, mm_pool32axf_op), RS},
+ [insn_mtc0] = {M(mm_pool32a_op, 0, 0, 0, mm_mtc0_op, mm_pool32axf_op), RT | RS | RD},
+ [insn_mthi] = {M(mm_pool32a_op, 0, 0, 0, mm_mthi32_op, mm_pool32axf_op), RS},
+ [insn_mtlo] = {M(mm_pool32a_op, 0, 0, 0, mm_mtlo32_op, mm_pool32axf_op), RS},
+ [insn_mul] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_mul_op), RT | RS | RD},
+ [insn_or] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_or32_op), RT | RS | RD},
+ [insn_ori] = {M(mm_ori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM},
+ [insn_pref] = {M(mm_pool32c_op, 0, 0, (mm_pref_func << 1), 0, 0), RT | RS | SIMM},
+ [insn_rfe] = {0, 0},
+ [insn_sc] = {M(mm_pool32c_op, 0, 0, (mm_sc_func << 1), 0, 0), RT | RS | SIMM},
+ [insn_scd] = {0, 0},
+ [insn_sd] = {0, 0},
+ [insn_sll] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_sll32_op), RT | RS | RD},
+ [insn_sllv] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_sllv32_op), RT | RS | RD},
+ [insn_slt] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_slt_op), RT | RS | RD},
+ [insn_sltiu] = {M(mm_sltiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
+ [insn_sltu] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_sltu_op), RT | RS | RD},
+ [insn_sra] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_sra_op), RT | RS | RD},
+ [insn_srl] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_srl32_op), RT | RS | RD},
+ [insn_srlv] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_srlv32_op), RT | RS | RD},
+ [insn_rotr] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_rotr_op), RT | RS | RD},
+ [insn_subu] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_subu32_op), RT | RS | RD},
+ [insn_sw] = {M(mm_sw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
+ [insn_sync] = {M(mm_pool32a_op, 0, 0, 0, mm_sync_op, mm_pool32axf_op), RS},
+ [insn_tlbp] = {M(mm_pool32a_op, 0, 0, 0, mm_tlbp_op, mm_pool32axf_op), 0},
+ [insn_tlbr] = {M(mm_pool32a_op, 0, 0, 0, mm_tlbr_op, mm_pool32axf_op), 0},
+ [insn_tlbwi] = {M(mm_pool32a_op, 0, 0, 0, mm_tlbwi_op, mm_pool32axf_op), 0},
+ [insn_tlbwr] = {M(mm_pool32a_op, 0, 0, 0, mm_tlbwr_op, mm_pool32axf_op), 0},
+ [insn_wait] = {M(mm_pool32a_op, 0, 0, 0, mm_wait_op, mm_pool32axf_op), SCIMM},
+ [insn_wsbh] = {M(mm_pool32a_op, 0, 0, 0, mm_wsbh_op, mm_pool32axf_op), RT | RS},
+ [insn_xor] = {M(mm_pool32a_op, 0, 0, 0, 0, mm_xor32_op), RT | RS | RD},
+ [insn_xori] = {M(mm_xori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM},
+ [insn_dins] = {0, 0},
+ [insn_dinsm] = {0, 0},
+ [insn_syscall] = {M(mm_pool32a_op, 0, 0, 0, mm_syscall_op, mm_pool32axf_op), SCIMM},
+ [insn_bbit0] = {0, 0},
+ [insn_bbit1] = {0, 0},
+ [insn_lwx] = {0, 0},
+ [insn_ldx] = {0, 0},
};
#undef M
@@ -156,20 +155,17 @@ static inline u32 build_jimm(u32 arg)
*/
static void build_insn(u32 **buf, enum opcode opc, ...)
{
- struct insn *ip = NULL;
- unsigned int i;
+ const struct insn *ip;
va_list ap;
u32 op;
- for (i = 0; insn_table_MM[i].opcode != insn_invalid; i++)
- if (insn_table_MM[i].opcode == opc) {
- ip = &insn_table_MM[i];
- break;
- }
-
- if (!ip || (opc == insn_daddiu && r4k_daddiu_bug()))
+ if (opc < 0 || opc >= insn_invalid ||
+ (opc == insn_daddiu && r4k_daddiu_bug()) ||
+ (insn_table_MM[opc].match == 0 && insn_table_MM[opc].fields == 0))
panic("Unsupported Micro-assembler instruction %d", opc);
+ ip = &insn_table_MM[opc];
+
op = ip->match;
va_start(ap, opc);
if (ip->fields & RS) {