diff options
Diffstat (limited to 'arch/powerpc/lib')
-rw-r--r-- | arch/powerpc/lib/feature-fixups.c | 8 | ||||
-rw-r--r-- | arch/powerpc/lib/sstep.c | 160 | ||||
-rw-r--r-- | arch/powerpc/lib/test_emulate_step.c | 270 |
3 files changed, 412 insertions, 26 deletions
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 321c12a9ef6b..47821055b94c 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -124,7 +124,7 @@ static void do_stf_entry_barrier_fixups(enum stf_barrier_type types) long *start, *end; int i; - start = PTRRELOC(&__start___stf_entry_barrier_fixup), + start = PTRRELOC(&__start___stf_entry_barrier_fixup); end = PTRRELOC(&__stop___stf_entry_barrier_fixup); instrs[0] = 0x60000000; /* nop */ @@ -176,7 +176,7 @@ static void do_stf_exit_barrier_fixups(enum stf_barrier_type types) long *start, *end; int i; - start = PTRRELOC(&__start___stf_exit_barrier_fixup), + start = PTRRELOC(&__start___stf_exit_barrier_fixup); end = PTRRELOC(&__stop___stf_exit_barrier_fixup); instrs[0] = 0x60000000; /* nop */ @@ -344,7 +344,7 @@ void do_rfi_flush_fixups(enum l1d_flush_type types) long *start, *end; int i; - start = PTRRELOC(&__start___rfi_flush_fixup), + start = PTRRELOC(&__start___rfi_flush_fixup); end = PTRRELOC(&__stop___rfi_flush_fixup); instrs[0] = 0x60000000; /* nop */ @@ -417,7 +417,7 @@ void do_barrier_nospec_fixups(bool enable) { void *start, *end; - start = PTRRELOC(&__start___barrier_nospec_fixup), + start = PTRRELOC(&__start___barrier_nospec_fixup); end = PTRRELOC(&__stop___barrier_nospec_fixup); do_barrier_nospec_fixups_range(enable, start, end); diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 855457ed09b5..bf7a7d62ae8b 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -32,6 +32,10 @@ extern char system_call_vectored_emulate[]; #define XER_OV32 0x00080000U #define XER_CA32 0x00040000U +#ifdef CONFIG_VSX +#define VSX_REGISTER_XTP(rd) ((((rd) & 1) << 5) | ((rd) & 0xfe)) +#endif + #ifdef CONFIG_PPC_FPU /* * Functions in ldstfp.S @@ -279,6 +283,19 @@ static nokprobe_inline void do_byte_reverse(void *ptr, int nb) up[1] = tmp; break; } + case 32: { + unsigned long *up = (unsigned long *)ptr; + unsigned long tmp; + + tmp = byterev_8(up[0]); + up[0] = byterev_8(up[3]); + up[3] = tmp; + tmp = byterev_8(up[2]); + up[2] = byterev_8(up[1]); + up[1] = tmp; + break; + } + #endif default: WARN_ON_ONCE(1); @@ -709,6 +726,8 @@ void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg, reg->d[0] = reg->d[1] = 0; switch (op->element_size) { + case 32: + /* [p]lxvp[x] */ case 16: /* whole vector; lxv[x] or lxvl[l] */ if (size == 0) @@ -717,7 +736,7 @@ void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg, if (IS_LE && (op->vsx_flags & VSX_LDLEFT)) rev = !rev; if (rev) - do_byte_reverse(reg, 16); + do_byte_reverse(reg, size); break; case 8: /* scalar loads, lxvd2x, lxvdsx */ @@ -793,6 +812,20 @@ void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg, size = GETSIZE(op->type); switch (op->element_size) { + case 32: + /* [p]stxvp[x] */ + if (size == 0) + break; + if (rev) { + /* reverse 32 bytes */ + buf.d[0] = byterev_8(reg->d[3]); + buf.d[1] = byterev_8(reg->d[2]); + buf.d[2] = byterev_8(reg->d[1]); + buf.d[3] = byterev_8(reg->d[0]); + reg = &buf; + } + memcpy(mem, reg, size); + break; case 16: /* stxv, stxvx, stxvl, stxvll */ if (size == 0) @@ -861,28 +894,43 @@ static nokprobe_inline int do_vsx_load(struct instruction_op *op, bool cross_endian) { int reg = op->reg; - u8 mem[16]; - union vsx_reg buf; + int i, j, nr_vsx_regs; + u8 mem[32]; + union vsx_reg buf[2]; int size = GETSIZE(op->type); if (!address_ok(regs, ea, size) || copy_mem_in(mem, ea, size, regs)) return -EFAULT; - emulate_vsx_load(op, &buf, mem, cross_endian); + nr_vsx_regs = size / sizeof(__vector128); + emulate_vsx_load(op, buf, mem, cross_endian); preempt_disable(); if (reg < 32) { /* FP regs + extensions */ if (regs->msr & MSR_FP) { - load_vsrn(reg, &buf); + for (i = 0; i < nr_vsx_regs; i++) { + j = IS_LE ? nr_vsx_regs - i - 1 : i; + load_vsrn(reg + i, &buf[j].v); + } } else { - current->thread.fp_state.fpr[reg][0] = buf.d[0]; - current->thread.fp_state.fpr[reg][1] = buf.d[1]; + for (i = 0; i < nr_vsx_regs; i++) { + j = IS_LE ? nr_vsx_regs - i - 1 : i; + current->thread.fp_state.fpr[reg + i][0] = buf[j].d[0]; + current->thread.fp_state.fpr[reg + i][1] = buf[j].d[1]; + } } } else { - if (regs->msr & MSR_VEC) - load_vsrn(reg, &buf); - else - current->thread.vr_state.vr[reg - 32] = buf.v; + if (regs->msr & MSR_VEC) { + for (i = 0; i < nr_vsx_regs; i++) { + j = IS_LE ? nr_vsx_regs - i - 1 : i; + load_vsrn(reg + i, &buf[j].v); + } + } else { + for (i = 0; i < nr_vsx_regs; i++) { + j = IS_LE ? nr_vsx_regs - i - 1 : i; + current->thread.vr_state.vr[reg - 32 + i] = buf[j].v; + } + } } preempt_enable(); return 0; @@ -893,30 +941,45 @@ static nokprobe_inline int do_vsx_store(struct instruction_op *op, bool cross_endian) { int reg = op->reg; - u8 mem[16]; - union vsx_reg buf; + int i, j, nr_vsx_regs; + u8 mem[32]; + union vsx_reg buf[2]; int size = GETSIZE(op->type); if (!address_ok(regs, ea, size)) return -EFAULT; + nr_vsx_regs = size / sizeof(__vector128); preempt_disable(); if (reg < 32) { /* FP regs + extensions */ if (regs->msr & MSR_FP) { - store_vsrn(reg, &buf); + for (i = 0; i < nr_vsx_regs; i++) { + j = IS_LE ? nr_vsx_regs - i - 1 : i; + store_vsrn(reg + i, &buf[j].v); + } } else { - buf.d[0] = current->thread.fp_state.fpr[reg][0]; - buf.d[1] = current->thread.fp_state.fpr[reg][1]; + for (i = 0; i < nr_vsx_regs; i++) { + j = IS_LE ? nr_vsx_regs - i - 1 : i; + buf[j].d[0] = current->thread.fp_state.fpr[reg + i][0]; + buf[j].d[1] = current->thread.fp_state.fpr[reg + i][1]; + } } } else { - if (regs->msr & MSR_VEC) - store_vsrn(reg, &buf); - else - buf.v = current->thread.vr_state.vr[reg - 32]; + if (regs->msr & MSR_VEC) { + for (i = 0; i < nr_vsx_regs; i++) { + j = IS_LE ? nr_vsx_regs - i - 1 : i; + store_vsrn(reg + i, &buf[j].v); + } + } else { + for (i = 0; i < nr_vsx_regs; i++) { + j = IS_LE ? nr_vsx_regs - i - 1 : i; + buf[j].v = current->thread.vr_state.vr[reg - 32 + i]; + } + } } preempt_enable(); - emulate_vsx_store(op, &buf, mem, cross_endian); + emulate_vsx_store(op, buf, mem, cross_endian); return copy_mem_out(mem, ea, size, regs); } #endif /* CONFIG_VSX */ @@ -1346,6 +1409,9 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, switch (opcode) { #ifdef __powerpc64__ case 1: + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return -1; + prefix_r = GET_PREFIX_R(word); ra = GET_PREFIX_RA(suffix); rd = (suffix >> 21) & 0x1f; @@ -2400,6 +2466,14 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, op->vsx_flags = VSX_SPLAT; break; + case 333: /* lxvpx */ + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return -1; + op->reg = VSX_REGISTER_XTP(rd); + op->type = MKOP(LOAD_VSX, 0, 32); + op->element_size = 32; + break; + case 364: /* lxvwsx */ op->reg = rd | ((word & 1) << 5); op->type = MKOP(LOAD_VSX, 0, 4); @@ -2428,6 +2502,13 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, VSX_CHECK_VEC; break; } + case 461: /* stxvpx */ + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return -1; + op->reg = VSX_REGISTER_XTP(rd); + op->type = MKOP(STORE_VSX, 0, 32); + op->element_size = 32; + break; case 524: /* lxsspx */ op->reg = rd | ((word & 1) << 5); op->type = MKOP(LOAD_VSX, 0, 4); @@ -2669,6 +2750,22 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, #endif #ifdef CONFIG_VSX + case 6: + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return -1; + op->ea = dqform_ea(word, regs); + op->reg = VSX_REGISTER_XTP(rd); + op->element_size = 32; + switch (word & 0xf) { + case 0: /* lxvp */ + op->type = MKOP(LOAD_VSX, 0, 32); + break; + case 1: /* stxvp */ + op->type = MKOP(STORE_VSX, 0, 32); + break; + } + break; + case 61: /* stfdp, lxv, stxsd, stxssp, stxv */ switch (word & 7) { case 0: /* stfdp with LSB of DS field = 0 */ @@ -2733,6 +2830,9 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, } break; case 1: /* Prefixed instructions */ + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return -1; + prefix_r = GET_PREFIX_R(word); ra = GET_PREFIX_RA(suffix); op->update_reg = ra; @@ -2751,6 +2851,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, case 41: /* plwa */ op->type = MKOP(LOAD, PREFIXED | SIGNEXT, 4); break; +#ifdef CONFIG_VSX case 42: /* plxsd */ op->reg = rd + 32; op->type = MKOP(LOAD_VSX, PREFIXED, 8); @@ -2791,18 +2892,33 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, op->element_size = 16; op->vsx_flags = VSX_CHECK_VEC; break; +#endif /* CONFIG_VSX */ case 56: /* plq */ op->type = MKOP(LOAD, PREFIXED, 16); break; case 57: /* pld */ op->type = MKOP(LOAD, PREFIXED, 8); break; - case 60: /* stq */ +#ifdef CONFIG_VSX + case 58: /* plxvp */ + op->reg = VSX_REGISTER_XTP(rd); + op->type = MKOP(LOAD_VSX, PREFIXED, 32); + op->element_size = 32; + break; +#endif /* CONFIG_VSX */ + case 60: /* pstq */ op->type = MKOP(STORE, PREFIXED, 16); break; case 61: /* pstd */ op->type = MKOP(STORE, PREFIXED, 8); break; +#ifdef CONFIG_VSX + case 62: /* pstxvp */ + op->reg = VSX_REGISTER_XTP(rd); + op->type = MKOP(STORE_VSX, PREFIXED, 32); + op->element_size = 32; + break; +#endif /* CONFIG_VSX */ } break; case 1: /* Type 01 Eight-Byte Register-to-Register */ diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c index 0a201b771477..783d1b85ecfe 100644 --- a/arch/powerpc/lib/test_emulate_step.c +++ b/arch/powerpc/lib/test_emulate_step.c @@ -612,6 +612,273 @@ static void __init test_lxvd2x_stxvd2x(void) } #endif /* CONFIG_VSX */ +#ifdef CONFIG_VSX +static void __init test_lxvp_stxvp(void) +{ + struct pt_regs regs; + union { + vector128 a; + u32 b[4]; + } c[2]; + u32 cached_b[8]; + int stepped = -1; + + if (!cpu_has_feature(CPU_FTR_ARCH_31)) { + show_result("lxvp", "SKIP (!CPU_FTR_ARCH_31)"); + show_result("stxvp", "SKIP (!CPU_FTR_ARCH_31)"); + return; + } + + init_pt_regs(®s); + + /*** lxvp ***/ + + cached_b[0] = c[0].b[0] = 18233; + cached_b[1] = c[0].b[1] = 34863571; + cached_b[2] = c[0].b[2] = 834; + cached_b[3] = c[0].b[3] = 6138911; + cached_b[4] = c[1].b[0] = 1234; + cached_b[5] = c[1].b[1] = 5678; + cached_b[6] = c[1].b[2] = 91011; + cached_b[7] = c[1].b[3] = 121314; + + regs.gpr[4] = (unsigned long)&c[0].a; + + /* + * lxvp XTp,DQ(RA) + * XTp = 32xTX + 2xTp + * let TX=1 Tp=1 RA=4 DQ=0 + */ + stepped = emulate_step(®s, ppc_inst(PPC_RAW_LXVP(34, 4, 0))); + + if (stepped == 1 && cpu_has_feature(CPU_FTR_VSX)) { + show_result("lxvp", "PASS"); + } else { + if (!cpu_has_feature(CPU_FTR_VSX)) + show_result("lxvp", "PASS (!CPU_FTR_VSX)"); + else + show_result("lxvp", "FAIL"); + } + + /*** stxvp ***/ + + c[0].b[0] = 21379463; + c[0].b[1] = 87; + c[0].b[2] = 374234; + c[0].b[3] = 4; + c[1].b[0] = 90; + c[1].b[1] = 122; + c[1].b[2] = 555; + c[1].b[3] = 32144; + + /* + * stxvp XSp,DQ(RA) + * XSp = 32xSX + 2xSp + * let SX=1 Sp=1 RA=4 DQ=0 + */ + stepped = emulate_step(®s, ppc_inst(PPC_RAW_STXVP(34, 4, 0))); + + if (stepped == 1 && cached_b[0] == c[0].b[0] && cached_b[1] == c[0].b[1] && + cached_b[2] == c[0].b[2] && cached_b[3] == c[0].b[3] && + cached_b[4] == c[1].b[0] && cached_b[5] == c[1].b[1] && + cached_b[6] == c[1].b[2] && cached_b[7] == c[1].b[3] && + cpu_has_feature(CPU_FTR_VSX)) { + show_result("stxvp", "PASS"); + } else { + if (!cpu_has_feature(CPU_FTR_VSX)) + show_result("stxvp", "PASS (!CPU_FTR_VSX)"); + else + show_result("stxvp", "FAIL"); + } +} +#else +static void __init test_lxvp_stxvp(void) +{ + show_result("lxvp", "SKIP (CONFIG_VSX is not set)"); + show_result("stxvp", "SKIP (CONFIG_VSX is not set)"); +} +#endif /* CONFIG_VSX */ + +#ifdef CONFIG_VSX +static void __init test_lxvpx_stxvpx(void) +{ + struct pt_regs regs; + union { + vector128 a; + u32 b[4]; + } c[2]; + u32 cached_b[8]; + int stepped = -1; + + if (!cpu_has_feature(CPU_FTR_ARCH_31)) { + show_result("lxvpx", "SKIP (!CPU_FTR_ARCH_31)"); + show_result("stxvpx", "SKIP (!CPU_FTR_ARCH_31)"); + return; + } + + init_pt_regs(®s); + + /*** lxvpx ***/ + + cached_b[0] = c[0].b[0] = 18233; + cached_b[1] = c[0].b[1] = 34863571; + cached_b[2] = c[0].b[2] = 834; + cached_b[3] = c[0].b[3] = 6138911; + cached_b[4] = c[1].b[0] = 1234; + cached_b[5] = c[1].b[1] = 5678; + cached_b[6] = c[1].b[2] = 91011; + cached_b[7] = c[1].b[3] = 121314; + + regs.gpr[3] = (unsigned long)&c[0].a; + regs.gpr[4] = 0; + + /* + * lxvpx XTp,RA,RB + * XTp = 32xTX + 2xTp + * let TX=1 Tp=1 RA=3 RB=4 + */ + stepped = emulate_step(®s, ppc_inst(PPC_RAW_LXVPX(34, 3, 4))); + + if (stepped == 1 && cpu_has_feature(CPU_FTR_VSX)) { + show_result("lxvpx", "PASS"); + } else { + if (!cpu_has_feature(CPU_FTR_VSX)) + show_result("lxvpx", "PASS (!CPU_FTR_VSX)"); + else + show_result("lxvpx", "FAIL"); + } + + /*** stxvpx ***/ + + c[0].b[0] = 21379463; + c[0].b[1] = 87; + c[0].b[2] = 374234; + c[0].b[3] = 4; + c[1].b[0] = 90; + c[1].b[1] = 122; + c[1].b[2] = 555; + c[1].b[3] = 32144; + + /* + * stxvpx XSp,RA,RB + * XSp = 32xSX + 2xSp + * let SX=1 Sp=1 RA=3 RB=4 + */ + stepped = emulate_step(®s, ppc_inst(PPC_RAW_STXVPX(34, 3, 4))); + + if (stepped == 1 && cached_b[0] == c[0].b[0] && cached_b[1] == c[0].b[1] && + cached_b[2] == c[0].b[2] && cached_b[3] == c[0].b[3] && + cached_b[4] == c[1].b[0] && cached_b[5] == c[1].b[1] && + cached_b[6] == c[1].b[2] && cached_b[7] == c[1].b[3] && + cpu_has_feature(CPU_FTR_VSX)) { + show_result("stxvpx", "PASS"); + } else { + if (!cpu_has_feature(CPU_FTR_VSX)) + show_result("stxvpx", "PASS (!CPU_FTR_VSX)"); + else + show_result("stxvpx", "FAIL"); + } +} +#else +static void __init test_lxvpx_stxvpx(void) +{ + show_result("lxvpx", "SKIP (CONFIG_VSX is not set)"); + show_result("stxvpx", "SKIP (CONFIG_VSX is not set)"); +} +#endif /* CONFIG_VSX */ + +#ifdef CONFIG_VSX +static void __init test_plxvp_pstxvp(void) +{ + struct ppc_inst instr; + struct pt_regs regs; + union { + vector128 a; + u32 b[4]; + } c[2]; + u32 cached_b[8]; + int stepped = -1; + + if (!cpu_has_feature(CPU_FTR_ARCH_31)) { + show_result("plxvp", "SKIP (!CPU_FTR_ARCH_31)"); + show_result("pstxvp", "SKIP (!CPU_FTR_ARCH_31)"); + return; + } + + /*** plxvp ***/ + + cached_b[0] = c[0].b[0] = 18233; + cached_b[1] = c[0].b[1] = 34863571; + cached_b[2] = c[0].b[2] = 834; + cached_b[3] = c[0].b[3] = 6138911; + cached_b[4] = c[1].b[0] = 1234; + cached_b[5] = c[1].b[1] = 5678; + cached_b[6] = c[1].b[2] = 91011; + cached_b[7] = c[1].b[3] = 121314; + + init_pt_regs(®s); + regs.gpr[3] = (unsigned long)&c[0].a; + + /* + * plxvp XTp,D(RA),R + * XTp = 32xTX + 2xTp + * let RA=3 R=0 D=d0||d1=0 R=0 Tp=1 TX=1 + */ + instr = ppc_inst_prefix(PPC_RAW_PLXVP(34, 0, 3, 0) >> 32, + PPC_RAW_PLXVP(34, 0, 3, 0) & 0xffffffff); + + stepped = emulate_step(®s, instr); + if (stepped == 1 && cpu_has_feature(CPU_FTR_VSX)) { + show_result("plxvp", "PASS"); + } else { + if (!cpu_has_feature(CPU_FTR_VSX)) + show_result("plxvp", "PASS (!CPU_FTR_VSX)"); + else + show_result("plxvp", "FAIL"); + } + + /*** pstxvp ***/ + + c[0].b[0] = 21379463; + c[0].b[1] = 87; + c[0].b[2] = 374234; + c[0].b[3] = 4; + c[1].b[0] = 90; + c[1].b[1] = 122; + c[1].b[2] = 555; + c[1].b[3] = 32144; + + /* + * pstxvp XSp,D(RA),R + * XSp = 32xSX + 2xSp + * let RA=3 D=d0||d1=0 R=0 Sp=1 SX=1 + */ + instr = ppc_inst_prefix(PPC_RAW_PSTXVP(34, 0, 3, 0) >> 32, + PPC_RAW_PSTXVP(34, 0, 3, 0) & 0xffffffff); + + stepped = emulate_step(®s, instr); + + if (stepped == 1 && cached_b[0] == c[0].b[0] && cached_b[1] == c[0].b[1] && + cached_b[2] == c[0].b[2] && cached_b[3] == c[0].b[3] && + cached_b[4] == c[1].b[0] && cached_b[5] == c[1].b[1] && + cached_b[6] == c[1].b[2] && cached_b[7] == c[1].b[3] && + cpu_has_feature(CPU_FTR_VSX)) { + show_result("pstxvp", "PASS"); + } else { + if (!cpu_has_feature(CPU_FTR_VSX)) + show_result("pstxvp", "PASS (!CPU_FTR_VSX)"); + else + show_result("pstxvp", "FAIL"); + } +} +#else +static void __init test_plxvp_pstxvp(void) +{ + show_result("plxvp", "SKIP (CONFIG_VSX is not set)"); + show_result("pstxvp", "SKIP (CONFIG_VSX is not set)"); +} +#endif /* CONFIG_VSX */ + static void __init run_tests_load_store(void) { test_ld(); @@ -628,6 +895,9 @@ static void __init run_tests_load_store(void) test_plfd_pstfd(); test_lvx_stvx(); test_lxvd2x_stxvd2x(); + test_lxvp_stxvp(); + test_lxvpx_stxvpx(); + test_plxvp_pstxvp(); } struct compute_test { |