Small pile of bug fixes for rc1. I've included my patches to get our docs building with Sphinx 3, just for convenience... -- PMM The following changes since commit b149dea55cce97cb226683d06af61984a1c11e96: Merge remote-tracking branch 'remotes/cschoenebeck/tags/pull-9p-20201102' into staging (2020-11-02 10:57:48 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20201102 for you to fetch changes up to ffb4fbf90a2f63c9cb33e4bb9f854c79bf04ca4a: tests/qtest/npcm7xx_rng-test: Disable randomness tests (2020-11-02 16:52:18 +0000) ---------------------------------------------------------------- target-arm queue: * target/arm: Fix Neon emulation bugs on big-endian hosts * target/arm: fix handling of HCR.FB * target/arm: fix LORID_EL1 access check * disas/capstone: Fix monitor disassembly of >32 bytes * hw/arm/smmuv3: Fix potential integer overflow (CID 1432363) * hw/arm/boot: fix SVE for EL3 direct kernel boot * hw/display/omap_lcdc: Fix potential NULL pointer dereference * hw/display/exynos4210_fimd: Fix potential NULL pointer dereference * target/arm: Get correct MMU index for other-security-state * configure: Test that gio libs from pkg-config work * hw/intc/arm_gicv3_cpuif: Make GIC maintenance interrupts work * docs: Fix building with Sphinx 3 * tests/qtest/npcm7xx_rng-test: Disable randomness tests ---------------------------------------------------------------- AlexChen (2): hw/display/omap_lcdc: Fix potential NULL pointer dereference hw/display/exynos4210_fimd: Fix potential NULL pointer dereference Peter Maydell (9): target/arm: Fix float16 pairwise Neon ops on big-endian hosts target/arm: Fix VUDOT/VSDOT (scalar) on big-endian hosts disas/capstone: Fix monitor disassembly of >32 bytes target/arm: Get correct MMU index for other-security-state configure: Test that gio libs from pkg-config work hw/intc/arm_gicv3_cpuif: Make GIC maintenance interrupts work scripts/kerneldoc: For Sphinx 3 use c:macro for macros with arguments qemu-option-trace.rst.inc: Don't use option:: markup tests/qtest/npcm7xx_rng-test: Disable randomness tests Philippe Mathieu-Daudé (1): hw/arm/smmuv3: Fix potential integer overflow (CID 1432363) Richard Henderson (11): target/arm: Introduce neon_full_reg_offset target/arm: Move neon_element_offset to translate.c target/arm: Use neon_element_offset in neon_load/store_reg target/arm: Use neon_element_offset in vfp_reg_offset target/arm: Add read/write_neon_element32 target/arm: Expand read/write_neon_element32 to all MemOp target/arm: Rename neon_load_reg32 to vfp_load_reg32 target/arm: Add read/write_neon_element64 target/arm: Rename neon_load_reg64 to vfp_load_reg64 target/arm: Simplify do_long_3d and do_2scalar_long target/arm: Improve do_prewiden_3d Rémi Denis-Courmont (3): target/arm: fix handling of HCR.FB target/arm: fix LORID_EL1 access check hw/arm/boot: fix SVE for EL3 direct kernel boot docs/qemu-option-trace.rst.inc | 6 +- configure | 10 +- include/hw/intc/arm_gicv3_common.h | 1 - disas/capstone.c | 2 +- hw/arm/boot.c | 3 + hw/arm/smmuv3.c | 3 +- hw/display/exynos4210_fimd.c | 4 +- hw/display/omap_lcdc.c | 10 +- hw/intc/arm_gicv3_cpuif.c | 5 +- target/arm/helper.c | 24 +- target/arm/m_helper.c | 3 +- target/arm/translate.c | 153 +++++++++--- target/arm/vec_helper.c | 12 +- tests/qtest/npcm7xx_rng-test.c | 14 +- scripts/kernel-doc | 18 +- target/arm/translate-neon.c.inc | 472 ++++++++++++++++++++----------------- target/arm/translate-vfp.c.inc | 341 +++++++++++---------------- 17 files changed, 588 insertions(+), 493 deletions(-) From: Richard Henderson <richard.henderson@linaro.org> This function makes it clear that we're talking about the whole register, and not the 32-bit piece at index 0. This fixes a bug when running on a big-endian host. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 8 ++++++ target/arm/translate-neon.c.inc | 44 ++++++++++++++++----------------- target/arm/translate-vfp.c.inc | 2 +- 3 files changed, 31 insertions(+), 23 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void gen_hlt(DisasContext *s, int imm) unallocated_encoding(s); } +/* + * Return the offset of a "full" NEON Dreg. + */ +static long neon_full_reg_offset(unsigned reg) +{ + return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); +} + static inline long vfp_reg_offset(bool dp, unsigned reg) { if (dp) { diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ neon_element_offset(int reg, int element, MemOp size) ofs ^= 8 - element_size; } #endif - return neon_reg_offset(reg, 0) + ofs; + return neon_full_reg_offset(reg) + ofs; } static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop) @@ -XXX,XX +XXX,XX @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a) * We cannot write 16 bytes at once because the * destination is unaligned. */ - tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0), + tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(vd), 8, 8, tmp); - tcg_gen_gvec_mov(0, neon_reg_offset(vd + 1, 0), - neon_reg_offset(vd, 0), 8, 8); + tcg_gen_gvec_mov(0, neon_full_reg_offset(vd + 1), + neon_full_reg_offset(vd), 8, 8); } else { - tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0), + tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(vd), vec_size, vec_size, tmp); } tcg_gen_addi_i32(addr, addr, 1 << size); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a) static bool do_3same(DisasContext *s, arg_3same *a, GVecGen3Fn fn) { int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rn_ofs = neon_reg_offset(a->vn, 0); - int rm_ofs = neon_reg_offset(a->vm, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rn_ofs = neon_full_reg_offset(a->vn); + int rm_ofs = neon_full_reg_offset(a->vm); if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn) { /* Handle a 2-reg-shift insn which can be vectorized. */ int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rm_ofs = neon_reg_offset(a->vm, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rm_ofs = neon_full_reg_offset(a->vm); if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, { /* FP operations in 2-reg-and-shift group */ int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rm_ofs = neon_reg_offset(a->vm, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rm_ofs = neon_full_reg_offset(a->vm); TCGv_ptr fpst; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_1reg_imm(DisasContext *s, arg_1reg_imm *a, return true; } - reg_ofs = neon_reg_offset(a->vd, 0); + reg_ofs = neon_full_reg_offset(a->vd); vec_size = a->q ? 16 : 8; imm = asimd_imm_const(a->imm, a->cmode, a->op); @@ -XXX,XX +XXX,XX @@ static bool trans_VMULL_P_3d(DisasContext *s, arg_3diff *a) return true; } - tcg_gen_gvec_3_ool(neon_reg_offset(a->vd, 0), - neon_reg_offset(a->vn, 0), - neon_reg_offset(a->vm, 0), + tcg_gen_gvec_3_ool(neon_full_reg_offset(a->vd), + neon_full_reg_offset(a->vn), + neon_full_reg_offset(a->vm), 16, 16, 0, fn_gvec); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a, { /* Two registers and a scalar, using gvec */ int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rn_ofs = neon_reg_offset(a->vn, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rn_ofs = neon_full_reg_offset(a->vn); int rm_ofs; int idx; TCGv_ptr fpstatus; @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a, /* a->vm is M:Vm, which encodes both register and index */ idx = extract32(a->vm, a->size + 2, 2); a->vm = extract32(a->vm, 0, a->size + 2); - rm_ofs = neon_reg_offset(a->vm, 0); + rm_ofs = neon_full_reg_offset(a->vm); fpstatus = fpstatus_ptr(a->size == 1 ? FPST_STD_F16 : FPST_STD); tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpstatus, @@ -XXX,XX +XXX,XX @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a) return true; } - tcg_gen_gvec_dup_mem(a->size, neon_reg_offset(a->vd, 0), + tcg_gen_gvec_dup_mem(a->size, neon_full_reg_offset(a->vd), neon_element_offset(a->vm, a->index, a->size), a->q ? 16 : 8, a->q ? 16 : 8); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_F32_F16(DisasContext *s, arg_2misc *a) static bool do_2misc_vec(DisasContext *s, arg_2misc *a, GVecGen2Fn *fn) { int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rm_ofs = neon_reg_offset(a->vm, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rm_ofs = neon_full_reg_offset(a->vm); if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VDUP(DisasContext *s, arg_VDUP *a) } tmp = load_reg(s, a->rt); - tcg_gen_gvec_dup_i32(size, neon_reg_offset(a->vn, 0), + tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(a->vn), vec_size, vec_size, tmp); tcg_temp_free_i32(tmp); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This will shortly have users outside of translate-neon.c.inc. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 20 ++++++++++++++++++++ target/arm/translate-neon.c.inc | 19 ------------------- 2 files changed, 20 insertions(+), 19 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static long neon_full_reg_offset(unsigned reg) return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); } +/* + * Return the offset of a 2**SIZE piece of a NEON register, at index ELE, + * where 0 is the least significant end of the register. + */ +static long neon_element_offset(int reg, int element, MemOp size) +{ + int element_size = 1 << size; + int ofs = element * element_size; +#ifdef HOST_WORDS_BIGENDIAN + /* + * Calculate the offset assuming fully little-endian, + * then XOR to account for the order of the 8-byte units. + */ + if (element_size < 8) { + ofs ^= 8 - element_size; + } +#endif + return neon_full_reg_offset(reg) + ofs; +} + static inline long vfp_reg_offset(bool dp, unsigned reg) { if (dp) { diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static inline int neon_3same_fp_size(DisasContext *s, int x) #include "decode-neon-ls.c.inc" #include "decode-neon-shared.c.inc" -/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE, - * where 0 is the least significant end of the register. - */ -static inline long -neon_element_offset(int reg, int element, MemOp size) -{ - int element_size = 1 << size; - int ofs = element * element_size; -#ifdef HOST_WORDS_BIGENDIAN - /* Calculate the offset assuming fully little-endian, - * then XOR to account for the order of the 8-byte units. - */ - if (element_size < 8) { - ofs ^= 8 - element_size; - } -#endif - return neon_full_reg_offset(reg) + ofs; -} - static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop) { long offset = neon_element_offset(reg, ele, mop & MO_SIZE); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> These are the only users of neon_reg_offset, so remove that. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-4-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline long vfp_reg_offset(bool dp, unsigned reg) } } -/* Return the offset of a 32-bit piece of a NEON register. - zero is the least significant end of the register. */ -static inline long -neon_reg_offset (int reg, int n) -{ - int sreg; - sreg = reg * 2 + n; - return vfp_reg_offset(0, sreg); -} - static TCGv_i32 neon_load_reg(int reg, int pass) { TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_ld_i32(tmp, cpu_env, neon_reg_offset(reg, pass)); + tcg_gen_ld_i32(tmp, cpu_env, neon_element_offset(reg, pass, MO_32)); return tmp; } static void neon_store_reg(int reg, int pass, TCGv_i32 var) { - tcg_gen_st_i32(var, cpu_env, neon_reg_offset(reg, pass)); + tcg_gen_st_i32(var, cpu_env, neon_element_offset(reg, pass, MO_32)); tcg_temp_free_i32(var); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This seems a bit more readable than using offsetof CPU_DoubleU. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static long neon_element_offset(int reg, int element, MemOp size) return neon_full_reg_offset(reg) + ofs; } -static inline long vfp_reg_offset(bool dp, unsigned reg) +/* Return the offset of a VFP Dreg (dp = true) or VFP Sreg (dp = false). */ +static long vfp_reg_offset(bool dp, unsigned reg) { if (dp) { - return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); + return neon_element_offset(reg, 0, MO_64); } else { - long ofs = offsetof(CPUARMState, vfp.zregs[reg >> 2].d[(reg >> 1) & 1]); - if (reg & 1) { - ofs += offsetof(CPU_DoubleU, l.upper); - } else { - ofs += offsetof(CPU_DoubleU, l.lower); - } - return ofs; + return neon_element_offset(reg >> 1, reg & 1, MO_32); } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Model these off the aa64 read/write_vec_element functions. Use it within translate-neon.c.inc. The new functions do not allocate or free temps, so this rearranges the calling code a bit. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-6-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 26 ++++ target/arm/translate-neon.c.inc | 256 ++++++++++++++++++++------------ 2 files changed, 183 insertions(+), 99 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void neon_store_reg32(TCGv_i32 var, int reg) tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); } +static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp size) +{ + long off = neon_element_offset(reg, ele, size); + + switch (size) { + case MO_32: + tcg_gen_ld_i32(dest, cpu_env, off); + break; + default: + g_assert_not_reached(); + } +} + +static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp size) +{ + long off = neon_element_offset(reg, ele, size); + + switch (size) { + case MO_32: + tcg_gen_st_i32(src, cpu_env, off); + break; + default: + g_assert_not_reached(); + } +} + static TCGv_ptr vfp_reg_ptr(bool dp, int reg) { TCGv_ptr ret = tcg_temp_new_ptr(); diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_3same_pair(DisasContext *s, arg_3same *a, NeonGenTwoOpFn *fn) * early. Since Q is 0 there are always just two passes, so instead * of a complicated loop over each pass we just unroll. */ - tmp = neon_load_reg(a->vn, 0); - tmp2 = neon_load_reg(a->vn, 1); + tmp = tcg_temp_new_i32(); + tmp2 = tcg_temp_new_i32(); + tmp3 = tcg_temp_new_i32(); + + read_neon_element32(tmp, a->vn, 0, MO_32); + read_neon_element32(tmp2, a->vn, 1, MO_32); fn(tmp, tmp, tmp2); - tcg_temp_free_i32(tmp2); - tmp3 = neon_load_reg(a->vm, 0); - tmp2 = neon_load_reg(a->vm, 1); + read_neon_element32(tmp3, a->vm, 0, MO_32); + read_neon_element32(tmp2, a->vm, 1, MO_32); fn(tmp3, tmp3, tmp2); - tcg_temp_free_i32(tmp2); - neon_store_reg(a->vd, 0, tmp); - neon_store_reg(a->vd, 1, tmp3); + write_neon_element32(tmp, a->vd, 0, MO_32); + write_neon_element32(tmp3, a->vd, 1, MO_32); + + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(tmp2); + tcg_temp_free_i32(tmp3); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a, * 2-reg-and-shift operations, size < 3 case, where the * helper needs to be passed cpu_env. */ - TCGv_i32 constimm; + TCGv_i32 constimm, tmp; int pass; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a, * by immediate using the variable shift operations. */ constimm = tcg_const_i32(dup_const(a->size, a->shift)); + tmp = tcg_temp_new_i32(); for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vm, pass); + read_neon_element32(tmp, a->vm, pass, MO_32); fn(tmp, cpu_env, tmp, constimm); - neon_store_reg(a->vd, pass, tmp); + write_neon_element32(tmp, a->vd, pass, MO_32); } + tcg_temp_free_i32(tmp); tcg_temp_free_i32(constimm); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a, constimm = tcg_const_i64(-a->shift); rm1 = tcg_temp_new_i64(); rm2 = tcg_temp_new_i64(); + rd = tcg_temp_new_i32(); /* Load both inputs first to avoid potential overwrite if rm == rd */ neon_load_reg64(rm1, a->vm); neon_load_reg64(rm2, a->vm + 1); shiftfn(rm1, rm1, constimm); - rd = tcg_temp_new_i32(); narrowfn(rd, cpu_env, rm1); - neon_store_reg(a->vd, 0, rd); + write_neon_element32(rd, a->vd, 0, MO_32); shiftfn(rm2, rm2, constimm); - rd = tcg_temp_new_i32(); narrowfn(rd, cpu_env, rm2); - neon_store_reg(a->vd, 1, rd); + write_neon_element32(rd, a->vd, 1, MO_32); + tcg_temp_free_i32(rd); tcg_temp_free_i64(rm1); tcg_temp_free_i64(rm2); tcg_temp_free_i64(constimm); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a, constimm = tcg_const_i32(imm); /* Load all inputs first to avoid potential overwrite */ - rm1 = neon_load_reg(a->vm, 0); - rm2 = neon_load_reg(a->vm, 1); - rm3 = neon_load_reg(a->vm + 1, 0); - rm4 = neon_load_reg(a->vm + 1, 1); + rm1 = tcg_temp_new_i32(); + rm2 = tcg_temp_new_i32(); + rm3 = tcg_temp_new_i32(); + rm4 = tcg_temp_new_i32(); + read_neon_element32(rm1, a->vm, 0, MO_32); + read_neon_element32(rm2, a->vm, 1, MO_32); + read_neon_element32(rm3, a->vm, 2, MO_32); + read_neon_element32(rm4, a->vm, 3, MO_32); rtmp = tcg_temp_new_i64(); shiftfn(rm1, rm1, constimm); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a, tcg_temp_free_i32(rm2); narrowfn(rm1, cpu_env, rtmp); - neon_store_reg(a->vd, 0, rm1); + write_neon_element32(rm1, a->vd, 0, MO_32); + tcg_temp_free_i32(rm1); shiftfn(rm3, rm3, constimm); shiftfn(rm4, rm4, constimm); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a, narrowfn(rm3, cpu_env, rtmp); tcg_temp_free_i64(rtmp); - neon_store_reg(a->vd, 1, rm3); + write_neon_element32(rm3, a->vd, 1, MO_32); + tcg_temp_free_i32(rm3); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, widen_mask = dup_const(a->size + 1, widen_mask); } - rm0 = neon_load_reg(a->vm, 0); - rm1 = neon_load_reg(a->vm, 1); + rm0 = tcg_temp_new_i32(); + rm1 = tcg_temp_new_i32(); + read_neon_element32(rm0, a->vm, 0, MO_32); + read_neon_element32(rm1, a->vm, 1, MO_32); tmp = tcg_temp_new_i64(); widenfn(tmp, rm0); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, if (src1_wide) { neon_load_reg64(rn0_64, a->vn); } else { - TCGv_i32 tmp = neon_load_reg(a->vn, 0); + TCGv_i32 tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vn, 0, MO_32); widenfn(rn0_64, tmp); tcg_temp_free_i32(tmp); } - rm = neon_load_reg(a->vm, 0); + rm = tcg_temp_new_i32(); + read_neon_element32(rm, a->vm, 0, MO_32); widenfn(rm_64, rm); tcg_temp_free_i32(rm); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, if (src1_wide) { neon_load_reg64(rn1_64, a->vn + 1); } else { - TCGv_i32 tmp = neon_load_reg(a->vn, 1); + TCGv_i32 tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vn, 1, MO_32); widenfn(rn1_64, tmp); tcg_temp_free_i32(tmp); } - rm = neon_load_reg(a->vm, 1); + rm = tcg_temp_new_i32(); + read_neon_element32(rm, a->vm, 1, MO_32); neon_store_reg64(rn0_64, a->vd); @@ -XXX,XX +XXX,XX @@ static bool do_narrow_3d(DisasContext *s, arg_3diff *a, narrowfn(rd1, rn_64); - neon_store_reg(a->vd, 0, rd0); - neon_store_reg(a->vd, 1, rd1); + write_neon_element32(rd0, a->vd, 0, MO_32); + write_neon_element32(rd1, a->vd, 1, MO_32); + tcg_temp_free_i32(rd0); + tcg_temp_free_i32(rd1); tcg_temp_free_i64(rn_64); tcg_temp_free_i64(rm_64); @@ -XXX,XX +XXX,XX @@ static bool do_long_3d(DisasContext *s, arg_3diff *a, rd0 = tcg_temp_new_i64(); rd1 = tcg_temp_new_i64(); - rn = neon_load_reg(a->vn, 0); - rm = neon_load_reg(a->vm, 0); + rn = tcg_temp_new_i32(); + rm = tcg_temp_new_i32(); + read_neon_element32(rn, a->vn, 0, MO_32); + read_neon_element32(rm, a->vm, 0, MO_32); opfn(rd0, rn, rm); - tcg_temp_free_i32(rn); - tcg_temp_free_i32(rm); - rn = neon_load_reg(a->vn, 1); - rm = neon_load_reg(a->vm, 1); + read_neon_element32(rn, a->vn, 1, MO_32); + read_neon_element32(rm, a->vm, 1, MO_32); opfn(rd1, rn, rm); tcg_temp_free_i32(rn); tcg_temp_free_i32(rm); @@ -XXX,XX +XXX,XX @@ static void gen_neon_dup_high16(TCGv_i32 var) static inline TCGv_i32 neon_get_scalar(int size, int reg) { - TCGv_i32 tmp; - if (size == 1) { - tmp = neon_load_reg(reg & 7, reg >> 4); + TCGv_i32 tmp = tcg_temp_new_i32(); + if (size == MO_16) { + read_neon_element32(tmp, reg & 7, reg >> 4, MO_32); if (reg & 8) { gen_neon_dup_high16(tmp); } else { gen_neon_dup_low16(tmp); } } else { - tmp = neon_load_reg(reg & 15, reg >> 4); + read_neon_element32(tmp, reg & 15, reg >> 4, MO_32); } return tmp; } @@ -XXX,XX +XXX,XX @@ static bool do_2scalar(DisasContext *s, arg_2scalar *a, * perform an accumulation operation of that result into the * destination. */ - TCGv_i32 scalar; + TCGv_i32 scalar, tmp; int pass; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_2scalar(DisasContext *s, arg_2scalar *a, } scalar = neon_get_scalar(a->size, a->vm); + tmp = tcg_temp_new_i32(); for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vn, pass); + read_neon_element32(tmp, a->vn, pass, MO_32); opfn(tmp, tmp, scalar); if (accfn) { - TCGv_i32 rd = neon_load_reg(a->vd, pass); + TCGv_i32 rd = tcg_temp_new_i32(); + read_neon_element32(rd, a->vd, pass, MO_32); accfn(tmp, rd, tmp); tcg_temp_free_i32(rd); } - neon_store_reg(a->vd, pass, tmp); + write_neon_element32(tmp, a->vd, pass, MO_32); } + tcg_temp_free_i32(tmp); tcg_temp_free_i32(scalar); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_vqrdmlah_2sc(DisasContext *s, arg_2scalar *a, * performs a kind of fused op-then-accumulate using a helper * function that takes all of rd, rn and the scalar at once. */ - TCGv_i32 scalar; + TCGv_i32 scalar, rn, rd; int pass; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_vqrdmlah_2sc(DisasContext *s, arg_2scalar *a, } scalar = neon_get_scalar(a->size, a->vm); + rn = tcg_temp_new_i32(); + rd = tcg_temp_new_i32(); for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 rn = neon_load_reg(a->vn, pass); - TCGv_i32 rd = neon_load_reg(a->vd, pass); + read_neon_element32(rn, a->vn, pass, MO_32); + read_neon_element32(rd, a->vd, pass, MO_32); opfn(rd, cpu_env, rn, scalar, rd); - tcg_temp_free_i32(rn); - neon_store_reg(a->vd, pass, rd); + write_neon_element32(rd, a->vd, pass, MO_32); } + tcg_temp_free_i32(rn); + tcg_temp_free_i32(rd); tcg_temp_free_i32(scalar); return true; @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_long(DisasContext *s, arg_2scalar *a, scalar = neon_get_scalar(a->size, a->vm); /* Load all inputs before writing any outputs, in case of overlap */ - rn = neon_load_reg(a->vn, 0); + rn = tcg_temp_new_i32(); + read_neon_element32(rn, a->vn, 0, MO_32); rn0_64 = tcg_temp_new_i64(); opfn(rn0_64, rn, scalar); - tcg_temp_free_i32(rn); - rn = neon_load_reg(a->vn, 1); + read_neon_element32(rn, a->vn, 1, MO_32); rn1_64 = tcg_temp_new_i64(); opfn(rn1_64, rn, scalar); tcg_temp_free_i32(rn); @@ -XXX,XX +XXX,XX @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a) return false; } n <<= 3; + tmp = tcg_temp_new_i32(); if (a->op) { - tmp = neon_load_reg(a->vd, 0); + read_neon_element32(tmp, a->vd, 0, MO_32); } else { - tmp = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp, 0); } - tmp2 = neon_load_reg(a->vm, 0); + tmp2 = tcg_temp_new_i32(); + read_neon_element32(tmp2, a->vm, 0, MO_32); ptr1 = vfp_reg_ptr(true, a->vn); tmp4 = tcg_const_i32(n); gen_helper_neon_tbl(tmp2, tmp2, tmp, ptr1, tmp4); - tcg_temp_free_i32(tmp); + if (a->op) { - tmp = neon_load_reg(a->vd, 1); + read_neon_element32(tmp, a->vd, 1, MO_32); } else { - tmp = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp, 0); } - tmp3 = neon_load_reg(a->vm, 1); + tmp3 = tcg_temp_new_i32(); + read_neon_element32(tmp3, a->vm, 1, MO_32); gen_helper_neon_tbl(tmp3, tmp3, tmp, ptr1, tmp4); + tcg_temp_free_i32(tmp); tcg_temp_free_i32(tmp4); tcg_temp_free_ptr(ptr1); - neon_store_reg(a->vd, 0, tmp2); - neon_store_reg(a->vd, 1, tmp3); - tcg_temp_free_i32(tmp); + + write_neon_element32(tmp2, a->vd, 0, MO_32); + write_neon_element32(tmp3, a->vd, 1, MO_32); + tcg_temp_free_i32(tmp2); + tcg_temp_free_i32(tmp3); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a) static bool trans_VREV64(DisasContext *s, arg_VREV64 *a) { int pass, half; + TCGv_i32 tmp[2]; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VREV64(DisasContext *s, arg_VREV64 *a) return true; } - for (pass = 0; pass < (a->q ? 2 : 1); pass++) { - TCGv_i32 tmp[2]; + tmp[0] = tcg_temp_new_i32(); + tmp[1] = tcg_temp_new_i32(); + for (pass = 0; pass < (a->q ? 2 : 1); pass++) { for (half = 0; half < 2; half++) { - tmp[half] = neon_load_reg(a->vm, pass * 2 + half); + read_neon_element32(tmp[half], a->vm, pass * 2 + half, MO_32); switch (a->size) { case 0: tcg_gen_bswap32_i32(tmp[half], tmp[half]); @@ -XXX,XX +XXX,XX @@ static bool trans_VREV64(DisasContext *s, arg_VREV64 *a) g_assert_not_reached(); } } - neon_store_reg(a->vd, pass * 2, tmp[1]); - neon_store_reg(a->vd, pass * 2 + 1, tmp[0]); + write_neon_element32(tmp[1], a->vd, pass * 2, MO_32); + write_neon_element32(tmp[0], a->vd, pass * 2 + 1, MO_32); } + + tcg_temp_free_i32(tmp[0]); + tcg_temp_free_i32(tmp[1]); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a, rm0_64 = tcg_temp_new_i64(); rm1_64 = tcg_temp_new_i64(); rd_64 = tcg_temp_new_i64(); - tmp = neon_load_reg(a->vm, pass * 2); + + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, pass * 2, MO_32); widenfn(rm0_64, tmp); - tcg_temp_free_i32(tmp); - tmp = neon_load_reg(a->vm, pass * 2 + 1); + read_neon_element32(tmp, a->vm, pass * 2 + 1, MO_32); widenfn(rm1_64, tmp); tcg_temp_free_i32(tmp); + opfn(rd_64, rm0_64, rm1_64); tcg_temp_free_i64(rm0_64); tcg_temp_free_i64(rm1_64); @@ -XXX,XX +XXX,XX @@ static bool do_vmovn(DisasContext *s, arg_2misc *a, narrowfn(rd0, cpu_env, rm); neon_load_reg64(rm, a->vm + 1); narrowfn(rd1, cpu_env, rm); - neon_store_reg(a->vd, 0, rd0); - neon_store_reg(a->vd, 1, rd1); + write_neon_element32(rd0, a->vd, 0, MO_32); + write_neon_element32(rd1, a->vd, 1, MO_32); + tcg_temp_free_i32(rd0); + tcg_temp_free_i32(rd1); tcg_temp_free_i64(rm); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLL(DisasContext *s, arg_2misc *a) } rd = tcg_temp_new_i64(); + rm0 = tcg_temp_new_i32(); + rm1 = tcg_temp_new_i32(); - rm0 = neon_load_reg(a->vm, 0); - rm1 = neon_load_reg(a->vm, 1); + read_neon_element32(rm0, a->vm, 0, MO_32); + read_neon_element32(rm1, a->vm, 1, MO_32); widenfn(rd, rm0); tcg_gen_shli_i64(rd, rd, 8 << a->size); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_F16_F32(DisasContext *s, arg_2misc *a) fpst = fpstatus_ptr(FPST_STD); ahp = get_ahp_flag(); - tmp = neon_load_reg(a->vm, 0); + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, 0, MO_32); gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); - tmp2 = neon_load_reg(a->vm, 1); + tmp2 = tcg_temp_new_i32(); + read_neon_element32(tmp2, a->vm, 1, MO_32); gen_helper_vfp_fcvt_f32_to_f16(tmp2, tmp2, fpst, ahp); tcg_gen_shli_i32(tmp2, tmp2, 16); tcg_gen_or_i32(tmp2, tmp2, tmp); - tcg_temp_free_i32(tmp); - tmp = neon_load_reg(a->vm, 2); + read_neon_element32(tmp, a->vm, 2, MO_32); gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); - tmp3 = neon_load_reg(a->vm, 3); - neon_store_reg(a->vd, 0, tmp2); + tmp3 = tcg_temp_new_i32(); + read_neon_element32(tmp3, a->vm, 3, MO_32); + write_neon_element32(tmp2, a->vd, 0, MO_32); + tcg_temp_free_i32(tmp2); gen_helper_vfp_fcvt_f32_to_f16(tmp3, tmp3, fpst, ahp); tcg_gen_shli_i32(tmp3, tmp3, 16); tcg_gen_or_i32(tmp3, tmp3, tmp); - neon_store_reg(a->vd, 1, tmp3); + write_neon_element32(tmp3, a->vd, 1, MO_32); + tcg_temp_free_i32(tmp3); tcg_temp_free_i32(tmp); tcg_temp_free_i32(ahp); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_F32_F16(DisasContext *s, arg_2misc *a) fpst = fpstatus_ptr(FPST_STD); ahp = get_ahp_flag(); tmp3 = tcg_temp_new_i32(); - tmp = neon_load_reg(a->vm, 0); - tmp2 = neon_load_reg(a->vm, 1); + tmp2 = tcg_temp_new_i32(); + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, 0, MO_32); + read_neon_element32(tmp2, a->vm, 1, MO_32); tcg_gen_ext16u_i32(tmp3, tmp); gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp); - neon_store_reg(a->vd, 0, tmp3); + write_neon_element32(tmp3, a->vd, 0, MO_32); tcg_gen_shri_i32(tmp, tmp, 16); gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp); - neon_store_reg(a->vd, 1, tmp); - tmp3 = tcg_temp_new_i32(); + write_neon_element32(tmp, a->vd, 1, MO_32); + tcg_temp_free_i32(tmp); tcg_gen_ext16u_i32(tmp3, tmp2); gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp); - neon_store_reg(a->vd, 2, tmp3); + write_neon_element32(tmp3, a->vd, 2, MO_32); + tcg_temp_free_i32(tmp3); tcg_gen_shri_i32(tmp2, tmp2, 16); gen_helper_vfp_fcvt_f16_to_f32(tmp2, tmp2, fpst, ahp); - neon_store_reg(a->vd, 3, tmp2); + write_neon_element32(tmp2, a->vd, 3, MO_32); + tcg_temp_free_i32(tmp2); tcg_temp_free_i32(ahp); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ DO_2M_CRYPTO(SHA256SU0, aa32_sha2, 2) static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn) { + TCGv_i32 tmp; int pass; /* Handle a 2-reg-misc operation by iterating 32 bits at a time */ @@ -XXX,XX +XXX,XX @@ static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn) return true; } + tmp = tcg_temp_new_i32(); for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vm, pass); + read_neon_element32(tmp, a->vm, pass, MO_32); fn(tmp, tmp); - neon_store_reg(a->vd, pass, tmp); + write_neon_element32(tmp, a->vd, pass, MO_32); } + tcg_temp_free_i32(tmp); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VTRN(DisasContext *s, arg_2misc *a) return true; } - if (a->size == 2) { + tmp = tcg_temp_new_i32(); + tmp2 = tcg_temp_new_i32(); + if (a->size == MO_32) { for (pass = 0; pass < (a->q ? 4 : 2); pass += 2) { - tmp = neon_load_reg(a->vm, pass); - tmp2 = neon_load_reg(a->vd, pass + 1); - neon_store_reg(a->vm, pass, tmp2); - neon_store_reg(a->vd, pass + 1, tmp); + read_neon_element32(tmp, a->vm, pass, MO_32); + read_neon_element32(tmp2, a->vd, pass + 1, MO_32); + write_neon_element32(tmp2, a->vm, pass, MO_32); + write_neon_element32(tmp, a->vd, pass + 1, MO_32); } } else { for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - tmp = neon_load_reg(a->vm, pass); - tmp2 = neon_load_reg(a->vd, pass); - if (a->size == 0) { + read_neon_element32(tmp, a->vm, pass, MO_32); + read_neon_element32(tmp2, a->vd, pass, MO_32); + if (a->size == MO_8) { gen_neon_trn_u8(tmp, tmp2); } else { gen_neon_trn_u16(tmp, tmp2); } - neon_store_reg(a->vm, pass, tmp2); - neon_store_reg(a->vd, pass, tmp); + write_neon_element32(tmp2, a->vm, pass, MO_32); + write_neon_element32(tmp, a->vd, pass, MO_32); } } + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(tmp2); return true; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We can then use this to improve VMOV (scalar to gp) and VMOV (gp to scalar) so that we simply perform the memory operation that we wanted, rather than inserting or extracting from a 32-bit quantity. These were the last uses of neon_load/store_reg, so remove them. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 50 +++++++++++++----------- target/arm/translate-vfp.c.inc | 71 +++++----------------------------- 2 files changed, 37 insertions(+), 84 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static long neon_full_reg_offset(unsigned reg) * Return the offset of a 2**SIZE piece of a NEON register, at index ELE, * where 0 is the least significant end of the register. */ -static long neon_element_offset(int reg, int element, MemOp size) +static long neon_element_offset(int reg, int element, MemOp memop) { - int element_size = 1 << size; + int element_size = 1 << (memop & MO_SIZE); int ofs = element * element_size; #ifdef HOST_WORDS_BIGENDIAN /* @@ -XXX,XX +XXX,XX @@ static long vfp_reg_offset(bool dp, unsigned reg) } } -static TCGv_i32 neon_load_reg(int reg, int pass) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_ld_i32(tmp, cpu_env, neon_element_offset(reg, pass, MO_32)); - return tmp; -} - -static void neon_store_reg(int reg, int pass, TCGv_i32 var) -{ - tcg_gen_st_i32(var, cpu_env, neon_element_offset(reg, pass, MO_32)); - tcg_temp_free_i32(var); -} - static inline void neon_load_reg64(TCGv_i64 var, int reg) { tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg)); @@ -XXX,XX +XXX,XX @@ static inline void neon_store_reg32(TCGv_i32 var, int reg) tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); } -static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp size) +static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) { - long off = neon_element_offset(reg, ele, size); + long off = neon_element_offset(reg, ele, memop); - switch (size) { - case MO_32: + switch (memop) { + case MO_SB: + tcg_gen_ld8s_i32(dest, cpu_env, off); + break; + case MO_UB: + tcg_gen_ld8u_i32(dest, cpu_env, off); + break; + case MO_SW: + tcg_gen_ld16s_i32(dest, cpu_env, off); + break; + case MO_UW: + tcg_gen_ld16u_i32(dest, cpu_env, off); + break; + case MO_UL: + case MO_SL: tcg_gen_ld_i32(dest, cpu_env, off); break; default: @@ -XXX,XX +XXX,XX @@ static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp size) } } -static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp size) +static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) { - long off = neon_element_offset(reg, ele, size); + long off = neon_element_offset(reg, ele, memop); - switch (size) { + switch (memop) { + case MO_8: + tcg_gen_st8_i32(src, cpu_env, off); + break; + case MO_16: + tcg_gen_st16_i32(src, cpu_env, off); + break; case MO_32: tcg_gen_st_i32(src, cpu_env, off); break; diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a) { /* VMOV scalar to general purpose register */ TCGv_i32 tmp; - int pass; - uint32_t offset; - /* SIZE == 2 is a VFP instruction; otherwise NEON. */ - if (a->size == 2 + /* SIZE == MO_32 is a VFP instruction; otherwise NEON. */ + if (a->size == MO_32 ? !dc_isar_feature(aa32_fpsp_v2, s) : !arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a) return false; } - offset = a->index << a->size; - pass = extract32(offset, 2, 1); - offset = extract32(offset, 0, 2) * 8; - if (!vfp_access_check(s)) { return true; } - tmp = neon_load_reg(a->vn, pass); - switch (a->size) { - case 0: - if (offset) { - tcg_gen_shri_i32(tmp, tmp, offset); - } - if (a->u) { - gen_uxtb(tmp); - } else { - gen_sxtb(tmp); - } - break; - case 1: - if (a->u) { - if (offset) { - tcg_gen_shri_i32(tmp, tmp, 16); - } else { - gen_uxth(tmp); - } - } else { - if (offset) { - tcg_gen_sari_i32(tmp, tmp, 16); - } else { - gen_sxth(tmp); - } - } - break; - case 2: - break; - } + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vn, a->index, a->size | (a->u ? 0 : MO_SIGN)); store_reg(s, a->rt, tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a) static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a) { /* VMOV general purpose register to scalar */ - TCGv_i32 tmp, tmp2; - int pass; - uint32_t offset; + TCGv_i32 tmp; - /* SIZE == 2 is a VFP instruction; otherwise NEON. */ - if (a->size == 2 + /* SIZE == MO_32 is a VFP instruction; otherwise NEON. */ + if (a->size == MO_32 ? !dc_isar_feature(aa32_fpsp_v2, s) : !arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a) return false; } - offset = a->index << a->size; - pass = extract32(offset, 2, 1); - offset = extract32(offset, 0, 2) * 8; - if (!vfp_access_check(s)) { return true; } tmp = load_reg(s, a->rt); - switch (a->size) { - case 0: - tmp2 = neon_load_reg(a->vn, pass); - tcg_gen_deposit_i32(tmp, tmp2, tmp, offset, 8); - tcg_temp_free_i32(tmp2); - break; - case 1: - tmp2 = neon_load_reg(a->vn, pass); - tcg_gen_deposit_i32(tmp, tmp2, tmp, offset, 16); - tcg_temp_free_i32(tmp2); - break; - case 2: - break; - } - neon_store_reg(a->vn, pass, tmp); + write_neon_element32(tmp, a->vn, a->index, a->size); + tcg_temp_free_i32(tmp); return true; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The only uses of this function are for loading VFP single-precision values, and nothing to do with NEON. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-8-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 4 +- target/arm/translate-vfp.c.inc | 184 ++++++++++++++++----------------- 2 files changed, 94 insertions(+), 94 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void neon_store_reg64(TCGv_i64 var, int reg) tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(1, reg)); } -static inline void neon_load_reg32(TCGv_i32 var, int reg) +static inline void vfp_load_reg32(TCGv_i32 var, int reg) { tcg_gen_ld_i32(var, cpu_env, vfp_reg_offset(false, reg)); } -static inline void neon_store_reg32(TCGv_i32 var, int reg) +static inline void vfp_store_reg32(TCGv_i32 var, int reg) { tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); } diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) frn = tcg_temp_new_i32(); frm = tcg_temp_new_i32(); dest = tcg_temp_new_i32(); - neon_load_reg32(frn, rn); - neon_load_reg32(frm, rm); + vfp_load_reg32(frn, rn); + vfp_load_reg32(frm, rm); switch (a->cc) { case 0: /* eq: Z */ tcg_gen_movcond_i32(TCG_COND_EQ, dest, cpu_ZF, zero, @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) if (sz == 1) { tcg_gen_andi_i32(dest, dest, 0xffff); } - neon_store_reg32(dest, rd); + vfp_store_reg32(dest, rd); tcg_temp_free_i32(frn); tcg_temp_free_i32(frm); tcg_temp_free_i32(dest); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) TCGv_i32 tcg_res; tcg_op = tcg_temp_new_i32(); tcg_res = tcg_temp_new_i32(); - neon_load_reg32(tcg_op, rm); + vfp_load_reg32(tcg_op, rm); if (sz == 1) { gen_helper_rinth(tcg_res, tcg_op, fpst); } else { gen_helper_rints(tcg_res, tcg_op, fpst); } - neon_store_reg32(tcg_res, rd); + vfp_store_reg32(tcg_res, rd); tcg_temp_free_i32(tcg_op); tcg_temp_free_i32(tcg_res); } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) gen_helper_vfp_tould(tcg_res, tcg_double, tcg_shift, fpst); } tcg_gen_extrl_i64_i32(tcg_tmp, tcg_res); - neon_store_reg32(tcg_tmp, rd); + vfp_store_reg32(tcg_tmp, rd); tcg_temp_free_i32(tcg_tmp); tcg_temp_free_i64(tcg_res); tcg_temp_free_i64(tcg_double); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) TCGv_i32 tcg_single, tcg_res; tcg_single = tcg_temp_new_i32(); tcg_res = tcg_temp_new_i32(); - neon_load_reg32(tcg_single, rm); + vfp_load_reg32(tcg_single, rm); if (sz == 1) { if (is_signed) { gen_helper_vfp_toslh(tcg_res, tcg_single, tcg_shift, fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) gen_helper_vfp_touls(tcg_res, tcg_single, tcg_shift, fpst); } } - neon_store_reg32(tcg_res, rd); + vfp_store_reg32(tcg_res, rd); tcg_temp_free_i32(tcg_res); tcg_temp_free_i32(tcg_single); } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_half(DisasContext *s, arg_VMOV_single *a) if (a->l) { /* VFP to general purpose register */ tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vn); + vfp_load_reg32(tmp, a->vn); tcg_gen_andi_i32(tmp, tmp, 0xffff); store_reg(s, a->rt, tmp); } else { /* general purpose register to VFP */ tmp = load_reg(s, a->rt); tcg_gen_andi_i32(tmp, tmp, 0xffff); - neon_store_reg32(tmp, a->vn); + vfp_store_reg32(tmp, a->vn); tcg_temp_free_i32(tmp); } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a) if (a->l) { /* VFP to general purpose register */ tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vn); + vfp_load_reg32(tmp, a->vn); if (a->rt == 15) { /* Set the 4 flag bits in the CPSR. */ gen_set_nzcv(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a) } else { /* general purpose register to VFP */ tmp = load_reg(s, a->rt); - neon_store_reg32(tmp, a->vn); + vfp_store_reg32(tmp, a->vn); tcg_temp_free_i32(tmp); } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_64_sp(DisasContext *s, arg_VMOV_64_sp *a) if (a->op) { /* fpreg to gpreg */ tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); store_reg(s, a->rt, tmp); tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm + 1); + vfp_load_reg32(tmp, a->vm + 1); store_reg(s, a->rt2, tmp); } else { /* gpreg to fpreg */ tmp = load_reg(s, a->rt); - neon_store_reg32(tmp, a->vm); + vfp_store_reg32(tmp, a->vm); tcg_temp_free_i32(tmp); tmp = load_reg(s, a->rt2); - neon_store_reg32(tmp, a->vm + 1); + vfp_store_reg32(tmp, a->vm + 1); tcg_temp_free_i32(tmp); } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_dp *a) if (a->op) { /* fpreg to gpreg */ tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm * 2); + vfp_load_reg32(tmp, a->vm * 2); store_reg(s, a->rt, tmp); tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm * 2 + 1); + vfp_load_reg32(tmp, a->vm * 2 + 1); store_reg(s, a->rt2, tmp); } else { /* gpreg to fpreg */ tmp = load_reg(s, a->rt); - neon_store_reg32(tmp, a->vm * 2); + vfp_store_reg32(tmp, a->vm * 2); tcg_temp_free_i32(tmp); tmp = load_reg(s, a->rt2); - neon_store_reg32(tmp, a->vm * 2 + 1); + vfp_store_reg32(tmp, a->vm * 2 + 1); tcg_temp_free_i32(tmp); } @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_hp(DisasContext *s, arg_VLDR_VSTR_sp *a) tmp = tcg_temp_new_i32(); if (a->l) { gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); } else { - neon_load_reg32(tmp, a->vd); + vfp_load_reg32(tmp, a->vd); gen_aa32_st16(s, tmp, addr, get_mem_index(s)); } tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a) tmp = tcg_temp_new_i32(); if (a->l) { gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); } else { - neon_load_reg32(tmp, a->vd); + vfp_load_reg32(tmp, a->vd); gen_aa32_st32(s, tmp, addr, get_mem_index(s)); } tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_sp(DisasContext *s, arg_VLDM_VSTM_sp *a) if (a->l) { /* load */ gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - neon_store_reg32(tmp, a->vd + i); + vfp_store_reg32(tmp, a->vd + i); } else { /* store */ - neon_load_reg32(tmp, a->vd + i); + vfp_load_reg32(tmp, a->vd + i); gen_aa32_st32(s, tmp, addr, get_mem_index(s)); } tcg_gen_addi_i32(addr, addr, offset); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_sp(DisasContext *s, VFPGen3OpSPFn *fn, fd = tcg_temp_new_i32(); fpst = fpstatus_ptr(FPST_FPCR); - neon_load_reg32(f0, vn); - neon_load_reg32(f1, vm); + vfp_load_reg32(f0, vn); + vfp_load_reg32(f1, vm); for (;;) { if (reads_vd) { - neon_load_reg32(fd, vd); + vfp_load_reg32(fd, vd); } fn(fd, f0, f1, fpst); - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_sp(DisasContext *s, VFPGen3OpSPFn *fn, veclen--; vd = vfp_advance_sreg(vd, delta_d); vn = vfp_advance_sreg(vn, delta_d); - neon_load_reg32(f0, vn); + vfp_load_reg32(f0, vn); if (delta_m) { vm = vfp_advance_sreg(vm, delta_m); - neon_load_reg32(f1, vm); + vfp_load_reg32(f1, vm); } } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_hp(DisasContext *s, VFPGen3OpSPFn *fn, fd = tcg_temp_new_i32(); fpst = fpstatus_ptr(FPST_FPCR_F16); - neon_load_reg32(f0, vn); - neon_load_reg32(f1, vm); + vfp_load_reg32(f0, vn); + vfp_load_reg32(f1, vm); if (reads_vd) { - neon_load_reg32(fd, vd); + vfp_load_reg32(fd, vd); } fn(fd, f0, f1, fpst); - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); tcg_temp_free_i32(f0); tcg_temp_free_i32(f1); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) f0 = tcg_temp_new_i32(); fd = tcg_temp_new_i32(); - neon_load_reg32(f0, vm); + vfp_load_reg32(f0, vm); for (;;) { fn(fd, f0); - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) /* single source one-many */ while (veclen--) { vd = vfp_advance_sreg(vd, delta_d); - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); } break; } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) veclen--; vd = vfp_advance_sreg(vd, delta_d); vm = vfp_advance_sreg(vm, delta_m); - neon_load_reg32(f0, vm); + vfp_load_reg32(f0, vm); } tcg_temp_free_i32(f0); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_hp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) } f0 = tcg_temp_new_i32(); - neon_load_reg32(f0, vm); + vfp_load_reg32(f0, vm); fn(f0, f0); - neon_store_reg32(f0, vd); + vfp_store_reg32(f0, vd); tcg_temp_free_i32(f0); return true; @@ -XXX,XX +XXX,XX @@ static bool do_vfm_hp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i32(); - neon_load_reg32(vn, a->vn); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vn, a->vn); + vfp_load_reg32(vm, a->vm); if (neg_n) { /* VFNMS, VFMS */ gen_helper_vfp_negh(vn, vn); } - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); if (neg_d) { /* VFNMA, VFNMS */ gen_helper_vfp_negh(vd, vd); } fpst = fpstatus_ptr(FPST_FPCR_F16); gen_helper_vfp_muladdh(vd, vn, vm, vd, fpst); - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(vn); @@ -XXX,XX +XXX,XX @@ static bool do_vfm_sp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i32(); - neon_load_reg32(vn, a->vn); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vn, a->vn); + vfp_load_reg32(vm, a->vm); if (neg_n) { /* VFNMS, VFMS */ gen_helper_vfp_negs(vn, vn); } - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); if (neg_d) { /* VFNMA, VFNMS */ gen_helper_vfp_negs(vd, vd); } fpst = fpstatus_ptr(FPST_FPCR); gen_helper_vfp_muladds(vd, vn, vm, vd, fpst); - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(vn); @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_hp(DisasContext *s, arg_VMOV_imm_sp *a) } fd = tcg_const_i32(vfp_expand_imm(MO_16, a->imm)); - neon_store_reg32(fd, a->vd); + vfp_store_reg32(fd, a->vd); tcg_temp_free_i32(fd); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a) fd = tcg_const_i32(vfp_expand_imm(MO_32, a->imm)); for (;;) { - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_hp(DisasContext *s, arg_VCMP_sp *a) vd = tcg_temp_new_i32(); vm = tcg_temp_new_i32(); - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); if (a->z) { tcg_gen_movi_i32(vm, 0); } else { - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); } if (a->e) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_sp(DisasContext *s, arg_VCMP_sp *a) vd = tcg_temp_new_i32(); vm = tcg_temp_new_i32(); - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); if (a->z) { tcg_gen_movi_i32(vm, 0); } else { - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); } if (a->e) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f32_f16(DisasContext *s, arg_VCVT_f32_f16 *a) /* The T bit tells us if we want the low or high 16 bits of Vm */ tcg_gen_ld16u_i32(tmp, cpu_env, vfp_f16_offset(a->vm, a->t)); gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp_mode); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_i32(ahp_mode); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f32(DisasContext *s, arg_VCVT_f16_f32 *a) ahp_mode = get_ahp_flag(); tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp_mode); tcg_gen_st16_i32(tmp, cpu_env, vfp_f16_offset(a->vd, a->t)); tcg_temp_free_i32(ahp_mode); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_hp(DisasContext *s, arg_VRINTR_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); gen_helper_rinth(tmp, tmp, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_sp(DisasContext *s, arg_VRINTR_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); gen_helper_rints(tmp, tmp, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_hp(DisasContext *s, arg_VRINTZ_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); tcg_rmode = tcg_const_i32(float_round_to_zero); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); gen_helper_rinth(tmp, tmp, fpst); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tcg_rmode); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_sp(DisasContext *s, arg_VRINTZ_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); tcg_rmode = tcg_const_i32(float_round_to_zero); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); gen_helper_rints(tmp, tmp, fpst); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tcg_rmode); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_hp(DisasContext *s, arg_VRINTX_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); gen_helper_rinth_exact(tmp, tmp, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_sp(DisasContext *s, arg_VRINTX_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); gen_helper_rints_exact(tmp, tmp, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp(DisasContext *s, arg_VCVT_sp *a) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i64(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); gen_helper_vfp_fcvtds(vd, vm, cpu_env); neon_store_reg64(vd, a->vd); tcg_temp_free_i32(vm); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) vm = tcg_temp_new_i64(); neon_load_reg64(vm, a->vm); gen_helper_vfp_fcvtsd(vd, vm, cpu_env); - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); tcg_temp_free_i64(vm); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_hp(DisasContext *s, arg_VCVT_int_sp *a) } vm = tcg_temp_new_i32(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); if (a->s) { /* i32 -> f16 */ @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_hp(DisasContext *s, arg_VCVT_int_sp *a) /* u32 -> f16 */ gen_helper_vfp_uitoh(vm, vm, fpst); } - neon_store_reg32(vm, a->vd); + vfp_store_reg32(vm, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_ptr(fpst); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_sp(DisasContext *s, arg_VCVT_int_sp *a) } vm = tcg_temp_new_i32(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); fpst = fpstatus_ptr(FPST_FPCR); if (a->s) { /* i32 -> f32 */ @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_sp(DisasContext *s, arg_VCVT_int_sp *a) /* u32 -> f32 */ gen_helper_vfp_uitos(vm, vm, fpst); } - neon_store_reg32(vm, a->vd); + vfp_store_reg32(vm, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_ptr(fpst); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_dp(DisasContext *s, arg_VCVT_int_dp *a) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i64(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); fpst = fpstatus_ptr(FPST_FPCR); if (a->s) { /* i32 -> f64 */ @@ -XXX,XX +XXX,XX @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a) vd = tcg_temp_new_i32(); neon_load_reg64(vm, a->vm); gen_helper_vjcvt(vd, vm, cpu_env); - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i64(vm); tcg_temp_free_i32(vd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_hp(DisasContext *s, arg_VCVT_fix_sp *a) frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm); vd = tcg_temp_new_i32(); - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); fpst = fpstatus_ptr(FPST_FPCR_F16); shift = tcg_const_i32(frac_bits); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_hp(DisasContext *s, arg_VCVT_fix_sp *a) g_assert_not_reached(); } - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); tcg_temp_free_i32(shift); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a) frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm); vd = tcg_temp_new_i32(); - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); fpst = fpstatus_ptr(FPST_FPCR); shift = tcg_const_i32(frac_bits); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a) g_assert_not_reached(); } - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); tcg_temp_free_i32(shift); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_hp_int(DisasContext *s, arg_VCVT_sp_int *a) fpst = fpstatus_ptr(FPST_FPCR_F16); vm = tcg_temp_new_i32(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); if (a->s) { if (a->rz) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_hp_int(DisasContext *s, arg_VCVT_sp_int *a) gen_helper_vfp_touih(vm, vm, fpst); } } - neon_store_reg32(vm, a->vd); + vfp_store_reg32(vm, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_ptr(fpst); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp_int(DisasContext *s, arg_VCVT_sp_int *a) fpst = fpstatus_ptr(FPST_FPCR); vm = tcg_temp_new_i32(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); if (a->s) { if (a->rz) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp_int(DisasContext *s, arg_VCVT_sp_int *a) gen_helper_vfp_touis(vm, vm, fpst); } } - neon_store_reg32(vm, a->vd); + vfp_store_reg32(vm, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_ptr(fpst); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) gen_helper_vfp_touid(vd, vm, fpst); } } - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); tcg_temp_free_i64(vm); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VINS(DisasContext *s, arg_VINS *a) /* Insert low half of Vm into high half of Vd */ rm = tcg_temp_new_i32(); rd = tcg_temp_new_i32(); - neon_load_reg32(rm, a->vm); - neon_load_reg32(rd, a->vd); + vfp_load_reg32(rm, a->vm); + vfp_load_reg32(rd, a->vd); tcg_gen_deposit_i32(rd, rd, rm, 16, 16); - neon_store_reg32(rd, a->vd); + vfp_store_reg32(rd, a->vd); tcg_temp_free_i32(rm); tcg_temp_free_i32(rd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOVX(DisasContext *s, arg_VINS *a) /* Set Vd to high half of Vm */ rm = tcg_temp_new_i32(); - neon_load_reg32(rm, a->vm); + vfp_load_reg32(rm, a->vm); tcg_gen_shri_i32(rm, rm, 16); - neon_store_reg32(rm, a->vd); + vfp_store_reg32(rm, a->vd); tcg_temp_free_i32(rm); return true; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Replace all uses of neon_load/store_reg64 within translate-neon.c.inc. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-9-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 26 +++++++++ target/arm/translate-neon.c.inc | 94 ++++++++++++++++----------------- 2 files changed, 73 insertions(+), 47 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) } } +static void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) +{ + long off = neon_element_offset(reg, ele, memop); + + switch (memop) { + case MO_Q: + tcg_gen_ld_i64(dest, cpu_env, off); + break; + default: + g_assert_not_reached(); + } +} + static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) { long off = neon_element_offset(reg, ele, memop); @@ -XXX,XX +XXX,XX @@ static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) } } +static void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) +{ + long off = neon_element_offset(reg, ele, memop); + + switch (memop) { + case MO_64: + tcg_gen_st_i64(src, cpu_env, off); + break; + default: + g_assert_not_reached(); + } +} + static TCGv_ptr vfp_reg_ptr(bool dp, int reg) { TCGv_ptr ret = tcg_temp_new_ptr(); diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a, for (pass = 0; pass < a->q + 1; pass++) { TCGv_i64 tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vm + pass); + read_neon_element64(tmp, a->vm, pass, MO_64); fn(tmp, cpu_env, tmp, constimm); - neon_store_reg64(tmp, a->vd + pass); + write_neon_element64(tmp, a->vd, pass, MO_64); tcg_temp_free_i64(tmp); } tcg_temp_free_i64(constimm); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a, rd = tcg_temp_new_i32(); /* Load both inputs first to avoid potential overwrite if rm == rd */ - neon_load_reg64(rm1, a->vm); - neon_load_reg64(rm2, a->vm + 1); + read_neon_element64(rm1, a->vm, 0, MO_64); + read_neon_element64(rm2, a->vm, 1, MO_64); shiftfn(rm1, rm1, constimm); narrowfn(rd, cpu_env, rm1); @@ -XXX,XX +XXX,XX @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, tcg_gen_shli_i64(tmp, tmp, a->shift); tcg_gen_andi_i64(tmp, tmp, ~widen_mask); } - neon_store_reg64(tmp, a->vd); + write_neon_element64(tmp, a->vd, 0, MO_64); widenfn(tmp, rm1); tcg_temp_free_i32(rm1); @@ -XXX,XX +XXX,XX @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, tcg_gen_shli_i64(tmp, tmp, a->shift); tcg_gen_andi_i64(tmp, tmp, ~widen_mask); } - neon_store_reg64(tmp, a->vd + 1); + write_neon_element64(tmp, a->vd, 1, MO_64); tcg_temp_free_i64(tmp); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, rm_64 = tcg_temp_new_i64(); if (src1_wide) { - neon_load_reg64(rn0_64, a->vn); + read_neon_element64(rn0_64, a->vn, 0, MO_64); } else { TCGv_i32 tmp = tcg_temp_new_i32(); read_neon_element32(tmp, a->vn, 0, MO_32); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, * avoid incorrect results if a narrow input overlaps with the result. */ if (src1_wide) { - neon_load_reg64(rn1_64, a->vn + 1); + read_neon_element64(rn1_64, a->vn, 1, MO_64); } else { TCGv_i32 tmp = tcg_temp_new_i32(); read_neon_element32(tmp, a->vn, 1, MO_32); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, rm = tcg_temp_new_i32(); read_neon_element32(rm, a->vm, 1, MO_32); - neon_store_reg64(rn0_64, a->vd); + write_neon_element64(rn0_64, a->vd, 0, MO_64); widenfn(rm_64, rm); tcg_temp_free_i32(rm); opfn(rn1_64, rn1_64, rm_64); - neon_store_reg64(rn1_64, a->vd + 1); + write_neon_element64(rn1_64, a->vd, 1, MO_64); tcg_temp_free_i64(rn0_64); tcg_temp_free_i64(rn1_64); @@ -XXX,XX +XXX,XX @@ static bool do_narrow_3d(DisasContext *s, arg_3diff *a, rd0 = tcg_temp_new_i32(); rd1 = tcg_temp_new_i32(); - neon_load_reg64(rn_64, a->vn); - neon_load_reg64(rm_64, a->vm); + read_neon_element64(rn_64, a->vn, 0, MO_64); + read_neon_element64(rm_64, a->vm, 0, MO_64); opfn(rn_64, rn_64, rm_64); narrowfn(rd0, rn_64); - neon_load_reg64(rn_64, a->vn + 1); - neon_load_reg64(rm_64, a->vm + 1); + read_neon_element64(rn_64, a->vn, 1, MO_64); + read_neon_element64(rm_64, a->vm, 1, MO_64); opfn(rn_64, rn_64, rm_64); @@ -XXX,XX +XXX,XX @@ static bool do_long_3d(DisasContext *s, arg_3diff *a, /* Don't store results until after all loads: they might overlap */ if (accfn) { tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vd); + read_neon_element64(tmp, a->vd, 0, MO_64); accfn(tmp, tmp, rd0); - neon_store_reg64(tmp, a->vd); - neon_load_reg64(tmp, a->vd + 1); + write_neon_element64(tmp, a->vd, 0, MO_64); + read_neon_element64(tmp, a->vd, 1, MO_64); accfn(tmp, tmp, rd1); - neon_store_reg64(tmp, a->vd + 1); + write_neon_element64(tmp, a->vd, 1, MO_64); tcg_temp_free_i64(tmp); } else { - neon_store_reg64(rd0, a->vd); - neon_store_reg64(rd1, a->vd + 1); + write_neon_element64(rd0, a->vd, 0, MO_64); + write_neon_element64(rd1, a->vd, 1, MO_64); } tcg_temp_free_i64(rd0); @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_long(DisasContext *s, arg_2scalar *a, if (accfn) { TCGv_i64 t64 = tcg_temp_new_i64(); - neon_load_reg64(t64, a->vd); + read_neon_element64(t64, a->vd, 0, MO_64); accfn(t64, t64, rn0_64); - neon_store_reg64(t64, a->vd); - neon_load_reg64(t64, a->vd + 1); + write_neon_element64(t64, a->vd, 0, MO_64); + read_neon_element64(t64, a->vd, 1, MO_64); accfn(t64, t64, rn1_64); - neon_store_reg64(t64, a->vd + 1); + write_neon_element64(t64, a->vd, 1, MO_64); tcg_temp_free_i64(t64); } else { - neon_store_reg64(rn0_64, a->vd); - neon_store_reg64(rn1_64, a->vd + 1); + write_neon_element64(rn0_64, a->vd, 0, MO_64); + write_neon_element64(rn1_64, a->vd, 1, MO_64); } tcg_temp_free_i64(rn0_64); tcg_temp_free_i64(rn1_64); @@ -XXX,XX +XXX,XX @@ static bool trans_VEXT(DisasContext *s, arg_VEXT *a) right = tcg_temp_new_i64(); dest = tcg_temp_new_i64(); - neon_load_reg64(right, a->vn); - neon_load_reg64(left, a->vm); + read_neon_element64(right, a->vn, 0, MO_64); + read_neon_element64(left, a->vm, 0, MO_64); tcg_gen_extract2_i64(dest, right, left, a->imm * 8); - neon_store_reg64(dest, a->vd); + write_neon_element64(dest, a->vd, 0, MO_64); tcg_temp_free_i64(left); tcg_temp_free_i64(right); @@ -XXX,XX +XXX,XX @@ static bool trans_VEXT(DisasContext *s, arg_VEXT *a) destright = tcg_temp_new_i64(); if (a->imm < 8) { - neon_load_reg64(right, a->vn); - neon_load_reg64(middle, a->vn + 1); + read_neon_element64(right, a->vn, 0, MO_64); + read_neon_element64(middle, a->vn, 1, MO_64); tcg_gen_extract2_i64(destright, right, middle, a->imm * 8); - neon_load_reg64(left, a->vm); + read_neon_element64(left, a->vm, 0, MO_64); tcg_gen_extract2_i64(destleft, middle, left, a->imm * 8); } else { - neon_load_reg64(right, a->vn + 1); - neon_load_reg64(middle, a->vm); + read_neon_element64(right, a->vn, 1, MO_64); + read_neon_element64(middle, a->vm, 0, MO_64); tcg_gen_extract2_i64(destright, right, middle, (a->imm - 8) * 8); - neon_load_reg64(left, a->vm + 1); + read_neon_element64(left, a->vm, 1, MO_64); tcg_gen_extract2_i64(destleft, middle, left, (a->imm - 8) * 8); } - neon_store_reg64(destright, a->vd); - neon_store_reg64(destleft, a->vd + 1); + write_neon_element64(destright, a->vd, 0, MO_64); + write_neon_element64(destleft, a->vd, 1, MO_64); tcg_temp_free_i64(destright); tcg_temp_free_i64(destleft); @@ -XXX,XX +XXX,XX @@ static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a, if (accfn) { TCGv_i64 tmp64 = tcg_temp_new_i64(); - neon_load_reg64(tmp64, a->vd + pass); + read_neon_element64(tmp64, a->vd, pass, MO_64); accfn(rd_64, tmp64, rd_64); tcg_temp_free_i64(tmp64); } - neon_store_reg64(rd_64, a->vd + pass); + write_neon_element64(rd_64, a->vd, pass, MO_64); tcg_temp_free_i64(rd_64); } return true; @@ -XXX,XX +XXX,XX @@ static bool do_vmovn(DisasContext *s, arg_2misc *a, rd0 = tcg_temp_new_i32(); rd1 = tcg_temp_new_i32(); - neon_load_reg64(rm, a->vm); + read_neon_element64(rm, a->vm, 0, MO_64); narrowfn(rd0, cpu_env, rm); - neon_load_reg64(rm, a->vm + 1); + read_neon_element64(rm, a->vm, 1, MO_64); narrowfn(rd1, cpu_env, rm); write_neon_element32(rd0, a->vd, 0, MO_32); write_neon_element32(rd1, a->vd, 1, MO_32); @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLL(DisasContext *s, arg_2misc *a) widenfn(rd, rm0); tcg_gen_shli_i64(rd, rd, 8 << a->size); - neon_store_reg64(rd, a->vd); + write_neon_element64(rd, a->vd, 0, MO_64); widenfn(rd, rm1); tcg_gen_shli_i64(rd, rd, 8 << a->size); - neon_store_reg64(rd, a->vd + 1); + write_neon_element64(rd, a->vd, 1, MO_64); tcg_temp_free_i64(rd); tcg_temp_free_i32(rm0); @@ -XXX,XX +XXX,XX @@ static bool trans_VSWP(DisasContext *s, arg_2misc *a) rm = tcg_temp_new_i64(); rd = tcg_temp_new_i64(); for (pass = 0; pass < (a->q ? 2 : 1); pass++) { - neon_load_reg64(rm, a->vm + pass); - neon_load_reg64(rd, a->vd + pass); - neon_store_reg64(rm, a->vd + pass); - neon_store_reg64(rd, a->vm + pass); + read_neon_element64(rm, a->vm, pass, MO_64); + read_neon_element64(rd, a->vd, pass, MO_64); + write_neon_element64(rm, a->vd, pass, MO_64); + write_neon_element64(rd, a->vm, pass, MO_64); } tcg_temp_free_i64(rm); tcg_temp_free_i64(rd); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The only uses of this function are for loading VFP double-precision values, and nothing to do with NEON. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-10-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 8 ++-- target/arm/translate-vfp.c.inc | 84 +++++++++++++++++----------------- 2 files changed, 46 insertions(+), 46 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static long vfp_reg_offset(bool dp, unsigned reg) } } -static inline void neon_load_reg64(TCGv_i64 var, int reg) +static inline void vfp_load_reg64(TCGv_i64 var, int reg) { - tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg)); + tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(true, reg)); } -static inline void neon_store_reg64(TCGv_i64 var, int reg) +static inline void vfp_store_reg64(TCGv_i64 var, int reg) { - tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(1, reg)); + tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(true, reg)); } static inline void vfp_load_reg32(TCGv_i32 var, int reg) diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) tcg_gen_ext_i32_i64(nf, cpu_NF); tcg_gen_ext_i32_i64(vf, cpu_VF); - neon_load_reg64(frn, rn); - neon_load_reg64(frm, rm); + vfp_load_reg64(frn, rn); + vfp_load_reg64(frm, rm); switch (a->cc) { case 0: /* eq: Z */ tcg_gen_movcond_i64(TCG_COND_EQ, dest, zf, zero, @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) tcg_temp_free_i64(tmp); break; } - neon_store_reg64(dest, rd); + vfp_store_reg64(dest, rd); tcg_temp_free_i64(frn); tcg_temp_free_i64(frm); tcg_temp_free_i64(dest); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) TCGv_i64 tcg_res; tcg_op = tcg_temp_new_i64(); tcg_res = tcg_temp_new_i64(); - neon_load_reg64(tcg_op, rm); + vfp_load_reg64(tcg_op, rm); gen_helper_rintd(tcg_res, tcg_op, fpst); - neon_store_reg64(tcg_res, rd); + vfp_store_reg64(tcg_res, rd); tcg_temp_free_i64(tcg_op); tcg_temp_free_i64(tcg_res); } else { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) tcg_double = tcg_temp_new_i64(); tcg_res = tcg_temp_new_i64(); tcg_tmp = tcg_temp_new_i32(); - neon_load_reg64(tcg_double, rm); + vfp_load_reg64(tcg_double, rm); if (is_signed) { gen_helper_vfp_tosld(tcg_res, tcg_double, tcg_shift, fpst); } else { @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_dp(DisasContext *s, arg_VLDR_VSTR_dp *a) tmp = tcg_temp_new_i64(); if (a->l) { gen_aa32_ld64(s, tmp, addr, get_mem_index(s)); - neon_store_reg64(tmp, a->vd); + vfp_store_reg64(tmp, a->vd); } else { - neon_load_reg64(tmp, a->vd); + vfp_load_reg64(tmp, a->vd); gen_aa32_st64(s, tmp, addr, get_mem_index(s)); } tcg_temp_free_i64(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_dp(DisasContext *s, arg_VLDM_VSTM_dp *a) if (a->l) { /* load */ gen_aa32_ld64(s, tmp, addr, get_mem_index(s)); - neon_store_reg64(tmp, a->vd + i); + vfp_store_reg64(tmp, a->vd + i); } else { /* store */ - neon_load_reg64(tmp, a->vd + i); + vfp_load_reg64(tmp, a->vd + i); gen_aa32_st64(s, tmp, addr, get_mem_index(s)); } tcg_gen_addi_i32(addr, addr, offset); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn, fd = tcg_temp_new_i64(); fpst = fpstatus_ptr(FPST_FPCR); - neon_load_reg64(f0, vn); - neon_load_reg64(f1, vm); + vfp_load_reg64(f0, vn); + vfp_load_reg64(f1, vm); for (;;) { if (reads_vd) { - neon_load_reg64(fd, vd); + vfp_load_reg64(fd, vd); } fn(fd, f0, f1, fpst); - neon_store_reg64(fd, vd); + vfp_store_reg64(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn, veclen--; vd = vfp_advance_dreg(vd, delta_d); vn = vfp_advance_dreg(vn, delta_d); - neon_load_reg64(f0, vn); + vfp_load_reg64(f0, vn); if (delta_m) { vm = vfp_advance_dreg(vm, delta_m); - neon_load_reg64(f1, vm); + vfp_load_reg64(f1, vm); } } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) f0 = tcg_temp_new_i64(); fd = tcg_temp_new_i64(); - neon_load_reg64(f0, vm); + vfp_load_reg64(f0, vm); for (;;) { fn(fd, f0); - neon_store_reg64(fd, vd); + vfp_store_reg64(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) /* single source one-many */ while (veclen--) { vd = vfp_advance_dreg(vd, delta_d); - neon_store_reg64(fd, vd); + vfp_store_reg64(fd, vd); } break; } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) veclen--; vd = vfp_advance_dreg(vd, delta_d); vd = vfp_advance_dreg(vm, delta_m); - neon_load_reg64(f0, vm); + vfp_load_reg64(f0, vm); } tcg_temp_free_i64(f0); @@ -XXX,XX +XXX,XX @@ static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d) vm = tcg_temp_new_i64(); vd = tcg_temp_new_i64(); - neon_load_reg64(vn, a->vn); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vn, a->vn); + vfp_load_reg64(vm, a->vm); if (neg_n) { /* VFNMS, VFMS */ gen_helper_vfp_negd(vn, vn); } - neon_load_reg64(vd, a->vd); + vfp_load_reg64(vd, a->vd); if (neg_d) { /* VFNMA, VFNMS */ gen_helper_vfp_negd(vd, vd); } fpst = fpstatus_ptr(FPST_FPCR); gen_helper_vfp_muladdd(vd, vn, vm, vd, fpst); - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i64(vn); @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) fd = tcg_const_i64(vfp_expand_imm(MO_64, a->imm)); for (;;) { - neon_store_reg64(fd, vd); + vfp_store_reg64(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_dp(DisasContext *s, arg_VCMP_dp *a) vd = tcg_temp_new_i64(); vm = tcg_temp_new_i64(); - neon_load_reg64(vd, a->vd); + vfp_load_reg64(vd, a->vd); if (a->z) { tcg_gen_movi_i64(vm, 0); } else { - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); } if (a->e) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f64_f16(DisasContext *s, arg_VCVT_f64_f16 *a) tcg_gen_ld16u_i32(tmp, cpu_env, vfp_f16_offset(a->vm, a->t)); vd = tcg_temp_new_i64(); gen_helper_vfp_fcvt_f16_to_f64(vd, tmp, fpst, ahp_mode); - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_i32(ahp_mode); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f64(DisasContext *s, arg_VCVT_f16_f64 *a) tmp = tcg_temp_new_i32(); vm = tcg_temp_new_i64(); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); gen_helper_vfp_fcvt_f64_to_f16(tmp, vm, fpst, ahp_mode); tcg_temp_free_i64(vm); tcg_gen_st16_i32(tmp, cpu_env, vfp_f16_offset(a->vd, a->t)); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_dp *a) } tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vm); + vfp_load_reg64(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); gen_helper_rintd(tmp, tmp, fpst); - neon_store_reg64(tmp, a->vd); + vfp_store_reg64(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i64(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_dp *a) } tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vm); + vfp_load_reg64(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); tcg_rmode = tcg_const_i32(float_round_to_zero); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); gen_helper_rintd(tmp, tmp, fpst); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); - neon_store_reg64(tmp, a->vd); + vfp_store_reg64(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i64(tmp); tcg_temp_free_i32(tcg_rmode); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_dp(DisasContext *s, arg_VRINTX_dp *a) } tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vm); + vfp_load_reg64(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); gen_helper_rintd_exact(tmp, tmp, fpst); - neon_store_reg64(tmp, a->vd); + vfp_store_reg64(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i64(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp(DisasContext *s, arg_VCVT_sp *a) vd = tcg_temp_new_i64(); vfp_load_reg32(vm, a->vm); gen_helper_vfp_fcvtds(vd, vm, cpu_env); - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_i64(vd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) vd = tcg_temp_new_i32(); vm = tcg_temp_new_i64(); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); gen_helper_vfp_fcvtsd(vd, vm, cpu_env); vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_dp(DisasContext *s, arg_VCVT_int_dp *a) /* u32 -> f64 */ gen_helper_vfp_uitod(vd, vm, fpst); } - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_i64(vd); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a) vm = tcg_temp_new_i64(); vd = tcg_temp_new_i32(); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); gen_helper_vjcvt(vd, vm, cpu_env); vfp_store_reg32(vd, a->vd); tcg_temp_free_i64(vm); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm); vd = tcg_temp_new_i64(); - neon_load_reg64(vd, a->vd); + vfp_load_reg64(vd, a->vd); fpst = fpstatus_ptr(FPST_FPCR); shift = tcg_const_i32(frac_bits); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) g_assert_not_reached(); } - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_i64(vd); tcg_temp_free_i32(shift); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) fpst = fpstatus_ptr(FPST_FPCR); vm = tcg_temp_new_i64(); vd = tcg_temp_new_i32(); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); if (a->s) { if (a->rz) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> In both cases, we can sink the write-back and perform the accumulate into the normal destination temps. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-11-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-neon.c.inc | 23 +++++++++-------------- 1 file changed, 9 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_long_3d(DisasContext *s, arg_3diff *a, if (accfn) { tmp = tcg_temp_new_i64(); read_neon_element64(tmp, a->vd, 0, MO_64); - accfn(tmp, tmp, rd0); - write_neon_element64(tmp, a->vd, 0, MO_64); + accfn(rd0, tmp, rd0); read_neon_element64(tmp, a->vd, 1, MO_64); - accfn(tmp, tmp, rd1); - write_neon_element64(tmp, a->vd, 1, MO_64); + accfn(rd1, tmp, rd1); tcg_temp_free_i64(tmp); - } else { - write_neon_element64(rd0, a->vd, 0, MO_64); - write_neon_element64(rd1, a->vd, 1, MO_64); } + write_neon_element64(rd0, a->vd, 0, MO_64); + write_neon_element64(rd1, a->vd, 1, MO_64); tcg_temp_free_i64(rd0); tcg_temp_free_i64(rd1); @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_long(DisasContext *s, arg_2scalar *a, if (accfn) { TCGv_i64 t64 = tcg_temp_new_i64(); read_neon_element64(t64, a->vd, 0, MO_64); - accfn(t64, t64, rn0_64); - write_neon_element64(t64, a->vd, 0, MO_64); + accfn(rn0_64, t64, rn0_64); read_neon_element64(t64, a->vd, 1, MO_64); - accfn(t64, t64, rn1_64); - write_neon_element64(t64, a->vd, 1, MO_64); + accfn(rn1_64, t64, rn1_64); tcg_temp_free_i64(t64); - } else { - write_neon_element64(rn0_64, a->vd, 0, MO_64); - write_neon_element64(rn1_64, a->vd, 1, MO_64); } + + write_neon_element64(rn0_64, a->vd, 0, MO_64); + write_neon_element64(rn1_64, a->vd, 1, MO_64); tcg_temp_free_i64(rn0_64); tcg_temp_free_i64(rn1_64); return true; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We can use proper widening loads to extend 32-bit inputs, and skip the "widenfn" step. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-12-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 6 +++ target/arm/translate-neon.c.inc | 66 ++++++++++++++++++--------------- 2 files changed, 43 insertions(+), 29 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) long off = neon_element_offset(reg, ele, memop); switch (memop) { + case MO_SL: + tcg_gen_ld32s_i64(dest, cpu_env, off); + break; + case MO_UL: + tcg_gen_ld32u_i64(dest, cpu_env, off); + break; case MO_Q: tcg_gen_ld_i64(dest, cpu_env, off); break; diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_Vimm_1r(DisasContext *s, arg_1reg_imm *a) static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, NeonGenWidenFn *widenfn, NeonGenTwo64OpFn *opfn, - bool src1_wide) + int src1_mop, int src2_mop) { /* 3-regs different lengths, prewidening case (VADDL/VSUBL/VAADW/VSUBW) */ TCGv_i64 rn0_64, rn1_64, rm_64; - TCGv_i32 rm; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, return false; } - if (!widenfn || !opfn) { + if (!opfn) { /* size == 3 case, which is an entirely different insn group */ return false; } - if ((a->vd & 1) || (src1_wide && (a->vn & 1))) { + if ((a->vd & 1) || (src1_mop == MO_Q && (a->vn & 1))) { return false; } @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, rn1_64 = tcg_temp_new_i64(); rm_64 = tcg_temp_new_i64(); - if (src1_wide) { - read_neon_element64(rn0_64, a->vn, 0, MO_64); + if (src1_mop >= 0) { + read_neon_element64(rn0_64, a->vn, 0, src1_mop); } else { TCGv_i32 tmp = tcg_temp_new_i32(); read_neon_element32(tmp, a->vn, 0, MO_32); widenfn(rn0_64, tmp); tcg_temp_free_i32(tmp); } - rm = tcg_temp_new_i32(); - read_neon_element32(rm, a->vm, 0, MO_32); + if (src2_mop >= 0) { + read_neon_element64(rm_64, a->vm, 0, src2_mop); + } else { + TCGv_i32 tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, 0, MO_32); + widenfn(rm_64, tmp); + tcg_temp_free_i32(tmp); + } - widenfn(rm_64, rm); - tcg_temp_free_i32(rm); opfn(rn0_64, rn0_64, rm_64); /* * Load second pass inputs before storing the first pass result, to * avoid incorrect results if a narrow input overlaps with the result. */ - if (src1_wide) { - read_neon_element64(rn1_64, a->vn, 1, MO_64); + if (src1_mop >= 0) { + read_neon_element64(rn1_64, a->vn, 1, src1_mop); } else { TCGv_i32 tmp = tcg_temp_new_i32(); read_neon_element32(tmp, a->vn, 1, MO_32); widenfn(rn1_64, tmp); tcg_temp_free_i32(tmp); } - rm = tcg_temp_new_i32(); - read_neon_element32(rm, a->vm, 1, MO_32); + if (src2_mop >= 0) { + read_neon_element64(rm_64, a->vm, 1, src2_mop); + } else { + TCGv_i32 tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, 1, MO_32); + widenfn(rm_64, tmp); + tcg_temp_free_i32(tmp); + } write_neon_element64(rn0_64, a->vd, 0, MO_64); - widenfn(rm_64, rm); - tcg_temp_free_i32(rm); opfn(rn1_64, rn1_64, rm_64); write_neon_element64(rn1_64, a->vd, 1, MO_64); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, return true; } -#define DO_PREWIDEN(INSN, S, EXT, OP, SRC1WIDE) \ +#define DO_PREWIDEN(INSN, S, OP, SRC1WIDE, SIGN) \ static bool trans_##INSN##_3d(DisasContext *s, arg_3diff *a) \ { \ static NeonGenWidenFn * const widenfn[] = { \ gen_helper_neon_widen_##S##8, \ gen_helper_neon_widen_##S##16, \ - tcg_gen_##EXT##_i32_i64, \ - NULL, \ + NULL, NULL, \ }; \ static NeonGenTwo64OpFn * const addfn[] = { \ gen_helper_neon_##OP##l_u16, \ @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, tcg_gen_##OP##_i64, \ NULL, \ }; \ - return do_prewiden_3d(s, a, widenfn[a->size], \ - addfn[a->size], SRC1WIDE); \ + int narrow_mop = a->size == MO_32 ? MO_32 | SIGN : -1; \ + return do_prewiden_3d(s, a, widenfn[a->size], addfn[a->size], \ + SRC1WIDE ? MO_Q : narrow_mop, \ + narrow_mop); \ } -DO_PREWIDEN(VADDL_S, s, ext, add, false) -DO_PREWIDEN(VADDL_U, u, extu, add, false) -DO_PREWIDEN(VSUBL_S, s, ext, sub, false) -DO_PREWIDEN(VSUBL_U, u, extu, sub, false) -DO_PREWIDEN(VADDW_S, s, ext, add, true) -DO_PREWIDEN(VADDW_U, u, extu, add, true) -DO_PREWIDEN(VSUBW_S, s, ext, sub, true) -DO_PREWIDEN(VSUBW_U, u, extu, sub, true) +DO_PREWIDEN(VADDL_S, s, add, false, MO_SIGN) +DO_PREWIDEN(VADDL_U, u, add, false, 0) +DO_PREWIDEN(VSUBL_S, s, sub, false, MO_SIGN) +DO_PREWIDEN(VSUBL_U, u, sub, false, 0) +DO_PREWIDEN(VADDW_S, s, add, true, MO_SIGN) +DO_PREWIDEN(VADDW_U, u, add, true, 0) +DO_PREWIDEN(VSUBW_S, s, sub, true, MO_SIGN) +DO_PREWIDEN(VSUBW_U, u, sub, true, 0) static bool do_narrow_3d(DisasContext *s, arg_3diff *a, NeonGenTwo64OpFn *opfn, NeonGenNarrowFn *narrowfn) -- 2.20.1 In the neon_padd/pmax/pmin helpers for float16, a cut-and-paste error meant we were using the H4() address swizzler macro rather than the H2() which is required for 2-byte data. This had no effect on little-endian hosts but meant we put the result data into the destination Dreg in the wrong order on big-endian hosts. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20201028191712.4910-2-peter.maydell@linaro.org --- target/arm/vec_helper.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ DO_ABA(gvec_uaba_d, uint64_t) r2 = float16_##OP(m[H2(0)], m[H2(1)], fpst); \ r3 = float16_##OP(m[H2(2)], m[H2(3)], fpst); \ \ - d[H4(0)] = r0; \ - d[H4(1)] = r1; \ - d[H4(2)] = r2; \ - d[H4(3)] = r3; \ + d[H2(0)] = r0; \ + d[H2(1)] = r1; \ + d[H2(2)] = r2; \ + d[H2(3)] = r3; \ } DO_NEON_PAIRWISE(neon_padd, add) -- 2.20.1 The helper functions for performing the udot/sdot operations against a scalar were not using an address-swizzling macro when converting the index of the scalar element into a pointer into the vm array. This had no effect on little-endian hosts but meant we generated incorrect results on big-endian hosts. For these insns, the index is indexing over group of 4 8-bit values, so 32 bits per indexed entity, and H4() is therefore what we want. (For Neon the only possible input indexes are 0 and 1.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20201028191712.4910-3-peter.maydell@linaro.org --- target/arm/vec_helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) intptr_t index = simd_data(desc); uint32_t *d = vd; int8_t *n = vn; - int8_t *m_indexed = (int8_t *)vm + index * 4; + int8_t *m_indexed = (int8_t *)vm + H4(index) * 4; /* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd. * Otherwise opr_sz is a multiple of 16. @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) intptr_t index = simd_data(desc); uint32_t *d = vd; uint8_t *n = vn; - uint8_t *m_indexed = (uint8_t *)vm + index * 4; + uint8_t *m_indexed = (uint8_t *)vm + H4(index) * 4; /* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd. * Otherwise opr_sz is a multiple of 16. -- 2.20.1 From: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> HCR should be applied when NS is set, not when it is cleared. Signed-off-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void tlbimvaa_is_write(CPUARMState *env, const ARMCPRegInfo *ri, /* * Non-IS variants of TLB operations are upgraded to - * IS versions if we are at NS EL1 and HCR_EL2.FB is set to + * IS versions if we are at EL1 and HCR_EL2.FB is effectively set to * force broadcast of these operations. */ static bool tlb_force_broadcast(CPUARMState *env) { - return (env->cp15.hcr_el2 & HCR_FB) && - arm_current_el(env) == 1 && arm_is_secure_below_el3(env); + return arm_current_el(env) == 1 && (arm_hcr_el2_eff(env) & HCR_FB); } static void tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri, -- 2.20.1 From: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Secure mode is not exempted from checking SCR_EL3.TLOR, and in the future HCR_EL2.TLOR when S-EL2 is enabled. Signed-off-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t id_aa64pfr0_read(CPUARMState *env, const ARMCPRegInfo *ri) #endif /* Shared logic between LORID and the rest of the LOR* registers. - * Secure state has already been delt with. + * Secure state exclusion has already been dealt with. */ -static CPAccessResult access_lor_ns(CPUARMState *env) +static CPAccessResult access_lor_ns(CPUARMState *env, + const ARMCPRegInfo *ri, bool isread) { int el = arm_current_el(env); @@ -XXX,XX +XXX,XX @@ static CPAccessResult access_lor_ns(CPUARMState *env) return CP_ACCESS_OK; } -static CPAccessResult access_lorid(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread) -{ - if (arm_is_secure_below_el3(env)) { - /* Access ok in secure mode. */ - return CP_ACCESS_OK; - } - return access_lor_ns(env); -} - static CPAccessResult access_lor_other(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { @@ -XXX,XX +XXX,XX @@ static CPAccessResult access_lor_other(CPUARMState *env, /* Access denied in secure mode. */ return CP_ACCESS_TRAP; } - return access_lor_ns(env); + return access_lor_ns(env, ri, isread); } /* @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo lor_reginfo[] = { .type = ARM_CP_CONST, .resetvalue = 0 }, { .name = "LORID_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 7, - .access = PL1_R, .accessfn = access_lorid, + .access = PL1_R, .accessfn = access_lor_ns, .type = ARM_CP_CONST, .resetvalue = 0 }, REGINFO_SENTINEL }; -- 2.20.1 If we're using the capstone disassembler, disassembly of a run of instructions more than 32 bytes long disassembles the wrong data for instructions beyond the 32 byte mark: (qemu) xp /16x 0x100 0000000000000100: 0x00000005 0x54410001 0x00000001 0x00001000 0000000000000110: 0x00000000 0x00000004 0x54410002 0x3c000000 0000000000000120: 0x00000000 0x00000004 0x54410009 0x74736574 0000000000000130: 0x00000000 0x00000000 0x00000000 0x00000000 (qemu) xp /16i 0x100 0x00000100: 00000005 andeq r0, r0, r5 0x00000104: 54410001 strbpl r0, [r1], #-1 0x00000108: 00000001 andeq r0, r0, r1 0x0000010c: 00001000 andeq r1, r0, r0 0x00000110: 00000000 andeq r0, r0, r0 0x00000114: 00000004 andeq r0, r0, r4 0x00000118: 54410002 strbpl r0, [r1], #-2 0x0000011c: 3c000000 .byte 0x00, 0x00, 0x00, 0x3c 0x00000120: 54410001 strbpl r0, [r1], #-1 0x00000124: 00000001 andeq r0, r0, r1 0x00000128: 00001000 andeq r1, r0, r0 0x0000012c: 00000000 andeq r0, r0, r0 0x00000130: 00000004 andeq r0, r0, r4 0x00000134: 54410002 strbpl r0, [r1], #-2 0x00000138: 3c000000 .byte 0x00, 0x00, 0x00, 0x3c 0x0000013c: 00000000 andeq r0, r0, r0 Here the disassembly of 0x120..0x13f is using the data that is in 0x104..0x123. This is caused by passing the wrong value to the read_memory_func(). The intention is that at this point in the loop the 'cap_buf' buffer already contains 'csize' bytes of data for the instruction at guest addr 'pc', and we want to read in an extra 'tsize' bytes. Those extra bytes are therefore at 'pc + csize', not 'pc'. On the first time through the loop 'csize' happens to be zero, so the initial read of 32 bytes into cap_buf is correct and as long as the disassembly never needs to read more data we return the correct information. Use the correct guest address in the call to read_memory_func(). Cc: qemu-stable@nongnu.org Fixes: https://bugs.launchpad.net/qemu/+bug/1900779 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20201022132445.25039-1-peter.maydell@linaro.org --- disas/capstone.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/disas/capstone.c b/disas/capstone.c index XXXXXXX..XXXXXXX 100644 --- a/disas/capstone.c +++ b/disas/capstone.c @@ -XXX,XX +XXX,XX @@ bool cap_disas_monitor(disassemble_info *info, uint64_t pc, int count) /* Make certain that we can make progress. */ assert(tsize != 0); - info->read_memory_func(pc, cap_buf + csize, tsize, info); + info->read_memory_func(pc + csize, cap_buf + csize, tsize, info); csize += tsize; if (cs_disasm_iter(handle, &cbuf, &csize, &pc, insn)) { -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Use the BIT_ULL() macro to ensure we use 64-bit arithmetic. This fixes the following Coverity issue (OVERFLOW_BEFORE_WIDEN): CID 1432363 (#1 of 1): Unintentional integer overflow: overflow_before_widen: Potentially overflowing expression 1 << scale with type int (32 bits, signed) is evaluated using 32-bit arithmetic, and then used in a context that expects an expression of type hwaddr (64 bits, unsigned). Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Acked-by: Eric Auger <eric.auger@redhat.com> Message-id: 20201030144617.1535064-1-philmd@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/smmuv3.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/bitops.h" #include "hw/irq.h" #include "hw/sysbus.h" #include "migration/vmstate.h" @@ -XXX,XX +XXX,XX @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd) scale = CMD_SCALE(cmd); num = CMD_NUM(cmd); ttl = CMD_TTL(cmd); - num_pages = (num + 1) * (1 << (scale)); + num_pages = (num + 1) * BIT_ULL(scale); } if (type == SMMU_CMD_TLBI_NH_VA) { -- 2.20.1 From: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> When booting a CPU with EL3 using the -kernel flag, set up CPTR_EL3 so that SVE will not trap to EL3. Signed-off-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030151541.11976-1-remi@remlab.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/boot.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ static void do_cpu_reset(void *opaque) if (cpu_isar_feature(aa64_mte, cpu)) { env->cp15.scr_el3 |= SCR_ATA; } + if (cpu_isar_feature(aa64_sve, cpu)) { + env->cp15.cptr_el[3] |= CPTR_EZ; + } /* AArch64 kernels never boot in secure mode */ assert(!info->secure_boot); /* This hook is only supported for AArch32 currently: -- 2.20.1 From: AlexChen <alex.chen@huawei.com> In omap_lcd_interrupts(), the pointer omap_lcd is dereferinced before being check if it is valid, which may lead to NULL pointer dereference. So move the assignment to surface after checking that the omap_lcd is valid and move surface_bits_per_pixel(surface) to after the surface assignment. Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: AlexChen <alex.chen@huawei.com> Message-id: 5F9CDB8A.9000001@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/display/omap_lcdc.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/hw/display/omap_lcdc.c b/hw/display/omap_lcdc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcdc.c +++ b/hw/display/omap_lcdc.c @@ -XXX,XX +XXX,XX @@ static void omap_lcd_interrupts(struct omap_lcd_panel_s *s) static void omap_update_display(void *opaque) { struct omap_lcd_panel_s *omap_lcd = (struct omap_lcd_panel_s *) opaque; - DisplaySurface *surface = qemu_console_surface(omap_lcd->con); + DisplaySurface *surface; draw_line_func draw_line; int size, height, first, last; int width, linesize, step, bpp, frame_offset; hwaddr frame_base; - if (!omap_lcd || omap_lcd->plm == 1 || !omap_lcd->enable || - !surface_bits_per_pixel(surface)) { + if (!omap_lcd || omap_lcd->plm == 1 || !omap_lcd->enable) { + return; + } + + surface = qemu_console_surface(omap_lcd->con); + if (!surface_bits_per_pixel(surface)) { return; } -- 2.20.1 From: AlexChen <alex.chen@huawei.com> In exynos4210_fimd_update(), the pointer s is dereferinced before being check if it is valid, which may lead to NULL pointer dereference. So move the assignment to global_width after checking that the s is valid. Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 5F9F8D88.9030102@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/display/exynos4210_fimd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/hw/display/exynos4210_fimd.c b/hw/display/exynos4210_fimd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/exynos4210_fimd.c +++ b/hw/display/exynos4210_fimd.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_fimd_update(void *opaque) bool blend = false; uint8_t *host_fb_addr; bool is_dirty = false; - const int global_width = (s->vidtcon[2] & FIMD_VIDTCON2_SIZE_MASK) + 1; + int global_width; if (!s || !s->console || !s->enabled || surface_bits_per_pixel(qemu_console_surface(s->console)) == 0) { return; } + + global_width = (s->vidtcon[2] & FIMD_VIDTCON2_SIZE_MASK) + 1; exynos4210_update_resolution(s); surface = qemu_console_surface(s->console); -- 2.20.1 In arm_v7m_mmu_idx_for_secstate() we get the 'priv' level to pass to armv7m_mmu_idx_for_secstate_and_priv() by calling arm_current_el(). This is incorrect when the security state being queried is not the current one, because arm_current_el() uses the current security state to determine which of the banked CONTROL.nPRIV bits to look at. The effect was that if (for instance) Secure state was in privileged mode but Non-Secure was not then we would return the wrong MMU index. The only places where we are using this function in a way that could trigger this bug are for the stack loads during a v8M function-return and for the instruction fetch of a v8M SG insn. Fix the bug by expanding out the M-profile version of the arm_current_el() logic inline so it can use the passed in secstate rather than env->v7m.secure. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201022164408.13214-1-peter.maydell@linaro.org --- target/arm/m_helper.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -XXX,XX +XXX,XX @@ ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env, /* Return the MMU index for a v7M CPU in the specified security state */ ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate) { - bool priv = arm_current_el(env) != 0; + bool priv = arm_v7m_is_handler_mode(env) || + !(env->v7m.control[secstate] & 1); return arm_v7m_mmu_idx_for_secstate_and_priv(env, secstate, priv); } -- 2.20.1 On some hosts (eg Ubuntu Bionic) pkg-config returns a set of libraries for gio-2.0 which don't actually work when compiling statically. (Specifically, the returned library string includes -lmount, but not -lblkid which -lmount depends upon, so linking fails due to missing symbols.) Check that the libraries work, and don't enable gio if they don't, in the same way we do for gnutls. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200928160402.7961-1-peter.maydell@linaro.org --- configure | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ if test "$static" = yes && test "$mingw32" = yes; then fi if $pkg_config --atleast-version=$glib_req_ver gio-2.0; then - gio=yes gio_cflags=$($pkg_config --cflags gio-2.0) gio_libs=$($pkg_config --libs gio-2.0) gdbus_codegen=$($pkg_config --variable=gdbus_codegen gio-2.0) if [ ! -x "$gdbus_codegen" ]; then gdbus_codegen= fi + # Check that the libraries actually work -- Ubuntu 18.04 ships + # with pkg-config --static --libs data for gio-2.0 that is missing + # -lblkid and will give a link error. + write_c_skeleton + if compile_prog "" "gio_libs" ; then + gio=yes + else + gio=no + fi else gio=no fi -- 2.20.1 In gicv3_init_cpuif() we copy the ARMCPU gicv3_maintenance_interrupt into the GICv3CPUState struct's maintenance_irq field. This will only work if the board happens to have already wired up the CPU maintenance IRQ before the GIC was realized. Unfortunately this is not the case for the 'virt' board, and so the value that gets copied is NULL (since a qemu_irq is really a pointer to an IRQState struct under the hood). The effect is that the CPU interface code never actually raises the maintenance interrupt line. Instead, since the GICv3CPUState has a pointer to the CPUState, make the dereference at the point where we want to raise the interrupt, to avoid an implicit requirement on board code to wire things up in a particular order. Reported-by: Jose Martins <josemartins90@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20201009153904.28529-1-peter.maydell@linaro.org Reviewed-by: Luc Michel <luc@lmichel.fr> --- include/hw/intc/arm_gicv3_common.h | 1 - hw/intc/arm_gicv3_cpuif.c | 5 ++--- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3CPUState { qemu_irq parent_fiq; qemu_irq parent_virq; qemu_irq parent_vfiq; - qemu_irq maintenance_irq; /* Redistributor */ uint32_t level; /* Current IRQ level */ diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static void gicv3_cpuif_virt_update(GICv3CPUState *cs) int irqlevel = 0; int fiqlevel = 0; int maintlevel = 0; + ARMCPU *cpu = ARM_CPU(cs->cpu); idx = hppvi_index(cs); trace_gicv3_cpuif_virt_update(gicv3_redist_affid(cs), idx); @@ -XXX,XX +XXX,XX @@ static void gicv3_cpuif_virt_update(GICv3CPUState *cs) qemu_set_irq(cs->parent_vfiq, fiqlevel); qemu_set_irq(cs->parent_virq, irqlevel); - qemu_set_irq(cs->maintenance_irq, maintlevel); + qemu_set_irq(cpu->gicv3_maintenance_interrupt, maintlevel); } static uint64_t icv_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) @@ -XXX,XX +XXX,XX @@ void gicv3_init_cpuif(GICv3State *s) && cpu->gic_num_lrs) { int j; - cs->maintenance_irq = cpu->gicv3_maintenance_interrupt; - cs->num_list_regs = cpu->gic_num_lrs; cs->vpribits = cpu->gic_vpribits; cs->vprebits = cpu->gic_vprebits; -- 2.20.1 The kerneldoc script currently emits Sphinx markup for a macro with arguments that uses the c:function directive. This is correct for Sphinx versions earlier than Sphinx 3, where c:macro doesn't allow documentation of macros with arguments and c:function is not picky about the syntax of what it is passed. However, in Sphinx 3 the c:macro directive was enhanced to support macros with arguments, and c:function was made more picky about what syntax it accepted. When kerneldoc is told that it needs to produce output for Sphinx 3 or later, make it emit c:function only for functions and c:macro for macros with arguments. We assume that anything with a return type is a function and anything without is a macro. This fixes the Sphinx error: /home/petmay01/linaro/qemu-from-laptop/qemu/docs/../include/qom/object.h:155:Error in declarator If declarator-id with parameters (e.g., 'void f(int arg)'): Invalid C declaration: Expected identifier in nested name. [error at 25] DECLARE_INSTANCE_CHECKER ( InstanceType, OBJ_NAME, TYPENAME) -------------------------^ If parenthesis in noptr-declarator (e.g., 'void (*f(int arg))(double)'): Error in declarator or parameters Invalid C declaration: Expecting "(" in parameters. [error at 39] DECLARE_INSTANCE_CHECKER ( InstanceType, OBJ_NAME, TYPENAME) ---------------------------------------^ Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Tested-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20201030174700.7204-2-peter.maydell@linaro.org --- scripts/kernel-doc | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index XXXXXXX..XXXXXXX 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -XXX,XX +XXX,XX @@ sub output_function_rst(%) { output_highlight_rst($args{'purpose'}); $start = "\n\n**Syntax**\n\n ``"; } else { - print ".. c:function:: "; + if ((split(/\./, $sphinx_version))[0] >= 3) { + # Sphinx 3 and later distinguish macros and functions and + # complain if you use c:function with something that's not + # syntactically valid as a function declaration. + # We assume that anything with a return type is a function + # and anything without is a macro. + if ($args{'functiontype'} ne "") { + print ".. c:function:: "; + } else { + print ".. c:macro:: "; + } + } else { + # Older Sphinx don't support documenting macros that take + # arguments with c:macro, and don't complain about the use + # of c:function for this. + print ".. c:function:: "; + } } if ($args{'functiontype'} ne "") { $start .= $args{'functiontype'} . " " . $args{'function'} . " ("; -- 2.20.1 Sphinx 3.2 is pickier than earlier versions about the option:: markup, and complains about our usage in qemu-option-trace.rst: ../../docs/qemu-option-trace.rst.inc:4:Malformed option description '[enable=]PATTERN', should look like "opt", "-opt args", "--opt args", "/opt args" or "+opt args" In this file, we're really trying to document the different parts of the top-level --trace option, which qemu-nbd.rst and qemu-img.rst have already introduced with an option:: markup. So it's not right to use option:: here anyway. Switch to a different markup (definition lists) which gives about the same formatted output. (Unlike option::, this markup doesn't produce index entries; but at the moment we don't do anything much with indexes anyway, and in any case I think it doesn't make much sense to have individual index entries for the sub-parts of the --trace option.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Tested-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20201030174700.7204-3-peter.maydell@linaro.org --- docs/qemu-option-trace.rst.inc | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/qemu-option-trace.rst.inc b/docs/qemu-option-trace.rst.inc index XXXXXXX..XXXXXXX 100644 --- a/docs/qemu-option-trace.rst.inc +++ b/docs/qemu-option-trace.rst.inc @@ -XXX,XX +XXX,XX @@ Specify tracing options. -.. option:: [enable=]PATTERN +``[enable=]PATTERN`` Immediately enable events matching *PATTERN* (either event name or a globbing pattern). This option is only @@ -XXX,XX +XXX,XX @@ Specify tracing options. Use :option:`-trace help` to print a list of names of trace points. -.. option:: events=FILE +``events=FILE`` Immediately enable events listed in *FILE*. The file must contain one event name (as listed in the ``trace-events-all`` @@ -XXX,XX +XXX,XX @@ Specify tracing options. available if QEMU has been compiled with the ``simple``, ``log`` or ``ftrace`` tracing backend. -.. option:: file=FILE +``file=FILE`` Log output traces to *FILE*. This option is only available if QEMU has been compiled with -- 2.20.1 The randomness tests in the NPCM7xx RNG test fail intermittently but fairly frequently. On my machine running the test in a loop: while QTEST_QEMU_BINARY=./qemu-system-aarch64 ./tests/qtest/npcm7xx_rng-test; do true; done will fail in less than a minute with an error like: ERROR:../../tests/qtest/npcm7xx_rng-test.c:256:test_first_byte_runs: assertion failed (calc_runs_p(buf.l, sizeof(buf) * BITS_PER_BYTE) > 0.01): (0.00286205989 > 0.01) (Failures have been observed on all 4 of the randomness tests, not just first_byte_runs.) It's not clear why these tests are failing like this, but intermittent failures make CI and merge testing awkward, so disable running them unless a developer specifically sets QEMU_TEST_FLAKY_RNG_TESTS when running the test suite, until we work out the cause. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20201102152454.8287-1-peter.maydell@linaro.org Reviewed-by: Havard Skinnemoen <hskinnemoen@google.com> --- tests/qtest/npcm7xx_rng-test.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/tests/qtest/npcm7xx_rng-test.c b/tests/qtest/npcm7xx_rng-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/npcm7xx_rng-test.c +++ b/tests/qtest/npcm7xx_rng-test.c @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) qtest_add_func("npcm7xx_rng/enable_disable", test_enable_disable); qtest_add_func("npcm7xx_rng/rosel", test_rosel); - qtest_add_func("npcm7xx_rng/continuous/monobit", test_continuous_monobit); - qtest_add_func("npcm7xx_rng/continuous/runs", test_continuous_runs); - qtest_add_func("npcm7xx_rng/first_byte/monobit", test_first_byte_monobit); - qtest_add_func("npcm7xx_rng/first_byte/runs", test_first_byte_runs); + /* + * These tests fail intermittently; only run them on explicit + * request until we figure out why. + */ + if (getenv("QEMU_TEST_FLAKY_RNG_TESTS")) { + qtest_add_func("npcm7xx_rng/continuous/monobit", test_continuous_monobit); + qtest_add_func("npcm7xx_rng/continuous/runs", test_continuous_runs); + qtest_add_func("npcm7xx_rng/first_byte/monobit", test_first_byte_monobit); + qtest_add_func("npcm7xx_rng/first_byte/runs", test_first_byte_runs); + } qtest_start("-machine npcm750-evb"); ret = g_test_run(); -- 2.20.1 First arm pullreq for 6.1 cycle. The big stuff here is RTH's alignment series. thanks -- PMM The following changes since commit ccdf06c1db192152ac70a1dd974c624f566cb7d4: Open 6.1 development tree (2021-04-30 11:15:40 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210430 for you to fetch changes up to a6091108aa44e9017af4ca13c43f55a629e3744c: hw/pci-host/gpex: Don't fault for unmapped parts of MMIO and PIO windows (2021-04-30 11:16:52 +0100) ---------------------------------------------------------------- target-arm queue: * hw/pci-host/gpex: Don't fault for unmapped parts of MMIO and PIO windows * hw: add compat machines for 6.1 * Fault misaligned accesses where the architecture requires it * Fix some corner cases of MTE faults (notably with misaligned accesses) * Make Thumb store insns UNDEF for Rn==1111 * hw/arm/smmuv3: Support 16K translation granule ---------------------------------------------------------------- Cornelia Huck (1): hw: add compat machines for 6.1 Kunkun Jiang (1): hw/arm/smmuv3: Support 16K translation granule Peter Maydell (2): target/arm: Make Thumb store insns UNDEF for Rn==1111 hw/pci-host/gpex: Don't fault for unmapped parts of MMIO and PIO windows Richard Henderson (39): target/arm: Fix mte_checkN target/arm: Split out mte_probe_int target/arm: Fix unaligned checks for mte_check1, mte_probe1 test/tcg/aarch64: Add mte-5 target/arm: Replace MTEDESC ESIZE+TSIZE with SIZEM1 target/arm: Merge mte_check1, mte_checkN target/arm: Rename mte_probe1 to mte_probe target/arm: Simplify sve mte checking target/arm: Remove log2_esize parameter to gen_mte_checkN target/arm: Fix decode of align in VLDST_single target/arm: Rename TBFLAG_A32, SCTLR_B target/arm: Rename TBFLAG_ANY, PSTATE_SS target/arm: Add wrapper macros for accessing tbflags target/arm: Introduce CPUARMTBFlags target/arm: Move mode specific TB flags to tb->cs_base target/arm: Move TBFLAG_AM32 bits to the top target/arm: Move TBFLAG_ANY bits to the bottom target/arm: Add ALIGN_MEM to TBFLAG_ANY target/arm: Adjust gen_aa32_{ld, st}_i32 for align+endianness target/arm: Merge gen_aa32_frob64 into gen_aa32_ld_i64 target/arm: Fix SCTLR_B test for TCGv_i64 load/store target/arm: Adjust gen_aa32_{ld, st}_i64 for align+endianness target/arm: Enforce word alignment for LDRD/STRD target/arm: Enforce alignment for LDA/LDAH/STL/STLH target/arm: Enforce alignment for LDM/STM target/arm: Enforce alignment for RFE target/arm: Enforce alignment for SRS target/arm: Enforce alignment for VLDM/VSTM target/arm: Enforce alignment for VLDR/VSTR target/arm: Enforce alignment for VLDn (all lanes) target/arm: Enforce alignment for VLDn/VSTn (multiple) target/arm: Enforce alignment for VLDn/VSTn (single) target/arm: Use finalize_memop for aa64 gpr load/store target/arm: Use finalize_memop for aa64 fpr load/store target/arm: Enforce alignment for aa64 load-acq/store-rel target/arm: Use MemOp for size + endian in aa64 vector ld/st target/arm: Enforce alignment for aa64 vector LDn/STn (multiple) target/arm: Enforce alignment for aa64 vector LDn/STn (single) target/arm: Enforce alignment for sve LD1R include/hw/boards.h | 3 + include/hw/i386/pc.h | 3 + include/hw/pci-host/gpex.h | 4 + target/arm/cpu.h | 105 ++++++++++----- target/arm/helper-a64.h | 3 +- target/arm/internals.h | 11 +- target/arm/translate-a64.h | 2 +- target/arm/translate.h | 38 ++++++ target/arm/neon-ls.decode | 4 +- hw/arm/smmuv3.c | 6 +- hw/arm/virt.c | 7 +- hw/core/machine.c | 5 + hw/i386/pc.c | 3 + hw/i386/pc_piix.c | 14 +- hw/i386/pc_q35.c | 13 +- hw/pci-host/gpex.c | 56 +++++++- hw/ppc/spapr.c | 17 ++- hw/s390x/s390-virtio-ccw.c | 14 +- target/arm/helper-a64.c | 2 +- target/arm/helper.c | 162 ++++++++++++---------- target/arm/mte_helper.c | 185 ++++++++++--------------- target/arm/sve_helper.c | 100 +++++--------- target/arm/translate-a64.c | 236 ++++++++++++++++---------------- target/arm/translate-sve.c | 11 +- target/arm/translate.c | 274 ++++++++++++++++++++++---------------- tests/tcg/aarch64/mte-5.c | 44 ++++++ target/arm/translate-neon.c.inc | 117 ++++++++++++---- target/arm/translate-vfp.c.inc | 20 +-- tests/tcg/aarch64/Makefile.target | 2 +- 29 files changed, 878 insertions(+), 583 deletions(-) create mode 100644 tests/tcg/aarch64/mte-5.c From: Kunkun Jiang <jiangkunkun@huawei.com> The driver can query some bits in SMMUv3 IDR5 to learn which translation granules are supported. Arm recommends that SMMUv3 implementations support at least 4K and 64K granules. But in the vSMMUv3, there seems to be no reason not to support 16K translation granule. In addition, if 16K is not supported, vSVA will failed to be enabled in the future for 16K guest kernel. So it'd better to support it. Signed-off-by: Kunkun Jiang <jiangkunkun@huawei.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/smmuv3.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ static void smmuv3_init_regs(SMMUv3State *s) s->idr[3] = FIELD_DP32(s->idr[3], IDR3, RIL, 1); s->idr[3] = FIELD_DP32(s->idr[3], IDR3, HAD, 1); - /* 4K and 64K granule support */ + /* 4K, 16K and 64K granule support */ s->idr[5] = FIELD_DP32(s->idr[5], IDR5, GRAN4K, 1); + s->idr[5] = FIELD_DP32(s->idr[5], IDR5, GRAN16K, 1); s->idr[5] = FIELD_DP32(s->idr[5], IDR5, GRAN64K, 1); s->idr[5] = FIELD_DP32(s->idr[5], IDR5, OAS, SMMU_IDR5_OAS); /* 44 bits */ @@ -XXX,XX +XXX,XX @@ static int decode_cd(SMMUTransCfg *cfg, CD *cd, SMMUEventInfo *event) tg = CD_TG(cd, i); tt->granule_sz = tg2granule(tg, i); - if ((tt->granule_sz != 12 && tt->granule_sz != 16) || CD_ENDI(cd)) { + if ((tt->granule_sz != 12 && tt->granule_sz != 14 && + tt->granule_sz != 16) || CD_ENDI(cd)) { goto bad_cd; } -- 2.20.1 The Arm ARM specifies that for Thumb encodings of the various plain store insns, if the Rn field is 1111 then we must UNDEF. This is different from the Arm encodings, where this case is either UNPREDICTABLE or has well-defined behaviour. The exclusive stores, store-release and STRD do not have this UNDEF case for any encoding. Enforce the UNDEF for this case in the Thumb plain store insns. Fixes: https://bugs.launchpad.net/qemu/+bug/1922887 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210408162402.5822-1-peter.maydell@linaro.org --- target/arm/translate.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool op_store_rr(DisasContext *s, arg_ldst_rr *a, ISSInfo issinfo = make_issinfo(s, a->rt, a->p, a->w) | ISSIsWrite; TCGv_i32 addr, tmp; + /* + * In Thumb encodings of stores Rn=1111 is UNDEF; for Arm it + * is either UNPREDICTABLE or has defined behaviour + */ + if (s->thumb && a->rn == 15) { + return false; + } + addr = op_addr_rr_pre(s, a); tmp = load_reg(s, a->rt); @@ -XXX,XX +XXX,XX @@ static bool op_store_ri(DisasContext *s, arg_ldst_ri *a, ISSInfo issinfo = make_issinfo(s, a->rt, a->p, a->w) | ISSIsWrite; TCGv_i32 addr, tmp; + /* + * In Thumb encodings of stores Rn=1111 is UNDEF; for Arm it + * is either UNPREDICTABLE or has defined behaviour + */ + if (s->thumb && a->rn == 15) { + return false; + } + addr = op_addr_ri_pre(s, a); tmp = load_reg(s, a->rt); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We were incorrectly assuming that only the first byte of an MTE access is checked against the tags. But per the ARM, unaligned accesses are pre-decomposed into single-byte accesses. So by the time we reach the actual MTE check in the ARM pseudocode, all accesses are aligned. Therefore, the first failure is always either the first byte of the access, or the first byte of the granule. In addition, some of the arithmetic is off for last-first -> count. This does not become directly visible until a later patch that passes single bytes into this function, so ptr == ptr_last. Buglink: https://bugs.launchpad.net/bugs/1921948 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210416183106.1516563-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: tweaked a comment] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/mte_helper.c | 40 ++++++++++++++++++---------------------- 1 file changed, 18 insertions(+), 22 deletions(-) diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mte_helper.c +++ b/target/arm/mte_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t mte_checkN(CPUARMState *env, uint32_t desc, uint64_t ptr, uintptr_t ra) { int mmu_idx, ptr_tag, bit55; - uint64_t ptr_last, ptr_end, prev_page, next_page; - uint64_t tag_first, tag_end; - uint64_t tag_byte_first, tag_byte_end; - uint32_t esize, total, tag_count, tag_size, n, c; + uint64_t ptr_last, prev_page, next_page; + uint64_t tag_first, tag_last; + uint64_t tag_byte_first, tag_byte_last; + uint32_t total, tag_count, tag_size, n, c; uint8_t *mem1, *mem2; MMUAccessType type; @@ -XXX,XX +XXX,XX @@ uint64_t mte_checkN(CPUARMState *env, uint32_t desc, mmu_idx = FIELD_EX32(desc, MTEDESC, MIDX); type = FIELD_EX32(desc, MTEDESC, WRITE) ? MMU_DATA_STORE : MMU_DATA_LOAD; - esize = FIELD_EX32(desc, MTEDESC, ESIZE); total = FIELD_EX32(desc, MTEDESC, TSIZE); - /* Find the addr of the end of the access, and of the last element. */ - ptr_end = ptr + total; - ptr_last = ptr_end - esize; + /* Find the addr of the end of the access */ + ptr_last = ptr + total - 1; /* Round the bounds to the tag granule, and compute the number of tags. */ tag_first = QEMU_ALIGN_DOWN(ptr, TAG_GRANULE); - tag_end = QEMU_ALIGN_UP(ptr_last, TAG_GRANULE); - tag_count = (tag_end - tag_first) / TAG_GRANULE; + tag_last = QEMU_ALIGN_DOWN(ptr_last, TAG_GRANULE); + tag_count = ((tag_last - tag_first) / TAG_GRANULE) + 1; /* Round the bounds to twice the tag granule, and compute the bytes. */ tag_byte_first = QEMU_ALIGN_DOWN(ptr, 2 * TAG_GRANULE); - tag_byte_end = QEMU_ALIGN_UP(ptr_last, 2 * TAG_GRANULE); + tag_byte_last = QEMU_ALIGN_DOWN(ptr_last, 2 * TAG_GRANULE); /* Locate the page boundaries. */ prev_page = ptr & TARGET_PAGE_MASK; next_page = prev_page + TARGET_PAGE_SIZE; - if (likely(tag_end - prev_page <= TARGET_PAGE_SIZE)) { + if (likely(tag_last - prev_page <= TARGET_PAGE_SIZE)) { /* Memory access stays on one page. */ - tag_size = (tag_byte_end - tag_byte_first) / (2 * TAG_GRANULE); + tag_size = ((tag_byte_last - tag_byte_first) / (2 * TAG_GRANULE)) + 1; mem1 = allocation_tag_mem(env, mmu_idx, ptr, type, total, MMU_DATA_LOAD, tag_size, ra); if (!mem1) { @@ -XXX,XX +XXX,XX @@ uint64_t mte_checkN(CPUARMState *env, uint32_t desc, mem1 = allocation_tag_mem(env, mmu_idx, ptr, type, next_page - ptr, MMU_DATA_LOAD, tag_size, ra); - tag_size = (tag_byte_end - next_page) / (2 * TAG_GRANULE); + tag_size = ((tag_byte_last - next_page) / (2 * TAG_GRANULE)) + 1; mem2 = allocation_tag_mem(env, mmu_idx, next_page, type, - ptr_end - next_page, + ptr_last - next_page + 1, MMU_DATA_LOAD, tag_size, ra); /* @@ -XXX,XX +XXX,XX @@ uint64_t mte_checkN(CPUARMState *env, uint32_t desc, } /* - * If we failed, we know which granule. Compute the element that - * is first in that granule, and signal failure on that element. + * If we failed, we know which granule. For the first granule, the + * failure address is @ptr, the first byte accessed. Otherwise the + * failure address is the first byte of the nth granule. */ if (unlikely(n < tag_count)) { - uint64_t fail_ofs; - - fail_ofs = tag_first + n * TAG_GRANULE - ptr; - fail_ofs = ROUND_UP(fail_ofs, esize); - mte_check_fail(env, desc, ptr + fail_ofs, ra); + uint64_t fault = (n == 0 ? ptr : tag_first + n * TAG_GRANULE); + mte_check_fail(env, desc, fault, ra); } done: -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Split out a helper function from mte_checkN to perform all of the checking and address manpulation. So far, just use this in mte_checkN itself. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210416183106.1516563-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/mte_helper.c | 52 +++++++++++++++++++++++++++++++---------- 1 file changed, 40 insertions(+), 12 deletions(-) diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mte_helper.c +++ b/target/arm/mte_helper.c @@ -XXX,XX +XXX,XX @@ static int checkN(uint8_t *mem, int odd, int cmp, int count) return n; } -uint64_t mte_checkN(CPUARMState *env, uint32_t desc, - uint64_t ptr, uintptr_t ra) +/** + * mte_probe_int() - helper for mte_probe and mte_check + * @env: CPU environment + * @desc: MTEDESC descriptor + * @ptr: virtual address of the base of the access + * @fault: return virtual address of the first check failure + * + * Internal routine for both mte_probe and mte_check. + * Return zero on failure, filling in *fault. + * Return negative on trivial success for tbi disabled. + * Return positive on success with tbi enabled. + */ +static int mte_probe_int(CPUARMState *env, uint32_t desc, uint64_t ptr, + uintptr_t ra, uint32_t total, uint64_t *fault) { int mmu_idx, ptr_tag, bit55; uint64_t ptr_last, prev_page, next_page; uint64_t tag_first, tag_last; uint64_t tag_byte_first, tag_byte_last; - uint32_t total, tag_count, tag_size, n, c; + uint32_t tag_count, tag_size, n, c; uint8_t *mem1, *mem2; MMUAccessType type; bit55 = extract64(ptr, 55, 1); + *fault = ptr; /* If TBI is disabled, the access is unchecked, and ptr is not dirty. */ if (unlikely(!tbi_check(desc, bit55))) { - return ptr; + return -1; } ptr_tag = allocation_tag_from_addr(ptr); if (tcma_check(desc, bit55, ptr_tag)) { - goto done; + return 1; } mmu_idx = FIELD_EX32(desc, MTEDESC, MIDX); type = FIELD_EX32(desc, MTEDESC, WRITE) ? MMU_DATA_STORE : MMU_DATA_LOAD; - total = FIELD_EX32(desc, MTEDESC, TSIZE); /* Find the addr of the end of the access */ ptr_last = ptr + total - 1; @@ -XXX,XX +XXX,XX @@ uint64_t mte_checkN(CPUARMState *env, uint32_t desc, mem1 = allocation_tag_mem(env, mmu_idx, ptr, type, total, MMU_DATA_LOAD, tag_size, ra); if (!mem1) { - goto done; + return 1; } /* Perform all of the comparisons. */ n = checkN(mem1, ptr & TAG_GRANULE, ptr_tag, tag_count); @@ -XXX,XX +XXX,XX @@ uint64_t mte_checkN(CPUARMState *env, uint32_t desc, } if (n == c) { if (!mem2) { - goto done; + return 1; } n += checkN(mem2, 0, ptr_tag, tag_count - c); } } + if (likely(n == tag_count)) { + return 1; + } + /* * If we failed, we know which granule. For the first granule, the * failure address is @ptr, the first byte accessed. Otherwise the * failure address is the first byte of the nth granule. */ - if (unlikely(n < tag_count)) { - uint64_t fault = (n == 0 ? ptr : tag_first + n * TAG_GRANULE); - mte_check_fail(env, desc, fault, ra); + if (n > 0) { + *fault = tag_first + n * TAG_GRANULE; } + return 0; +} - done: +uint64_t mte_checkN(CPUARMState *env, uint32_t desc, + uint64_t ptr, uintptr_t ra) +{ + uint64_t fault; + uint32_t total = FIELD_EX32(desc, MTEDESC, TSIZE); + int ret = mte_probe_int(env, desc, ptr, ra, total, &fault); + + if (unlikely(ret == 0)) { + mte_check_fail(env, desc, fault, ra); + } else if (ret < 0) { + return ptr; + } return useronly_clean_ptr(ptr); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We were incorrectly assuming that only the first byte of an MTE access is checked against the tags. But per the ARM, unaligned accesses are pre-decomposed into single-byte accesses. So by the time we reach the actual MTE check in the ARM pseudocode, all accesses are aligned. We cannot tell a priori whether or not a given scalar access is aligned, therefore we must at least check. Use mte_probe_int, which is already set up for checking multiple granules. Buglink: https://bugs.launchpad.net/bugs/1921948 Tested-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210416183106.1516563-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/mte_helper.c | 109 +++++++++++++--------------------------- 1 file changed, 35 insertions(+), 74 deletions(-) diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mte_helper.c +++ b/target/arm/mte_helper.c @@ -XXX,XX +XXX,XX @@ static void mte_check_fail(CPUARMState *env, uint32_t desc, } } -/* - * Perform an MTE checked access for a single logical or atomic access. - */ -static bool mte_probe1_int(CPUARMState *env, uint32_t desc, uint64_t ptr, - uintptr_t ra, int bit55) -{ - int mem_tag, mmu_idx, ptr_tag, size; - MMUAccessType type; - uint8_t *mem; - - ptr_tag = allocation_tag_from_addr(ptr); - - if (tcma_check(desc, bit55, ptr_tag)) { - return true; - } - - mmu_idx = FIELD_EX32(desc, MTEDESC, MIDX); - type = FIELD_EX32(desc, MTEDESC, WRITE) ? MMU_DATA_STORE : MMU_DATA_LOAD; - size = FIELD_EX32(desc, MTEDESC, ESIZE); - - mem = allocation_tag_mem(env, mmu_idx, ptr, type, size, - MMU_DATA_LOAD, 1, ra); - if (!mem) { - return true; - } - - mem_tag = load_tag1(ptr, mem); - return ptr_tag == mem_tag; -} - -/* - * No-fault version of mte_check1, to be used by SVE for MemSingleNF. - * Returns false if the access is Checked and the check failed. This - * is only intended to probe the tag -- the validity of the page must - * be checked beforehand. - */ -bool mte_probe1(CPUARMState *env, uint32_t desc, uint64_t ptr) -{ - int bit55 = extract64(ptr, 55, 1); - - /* If TBI is disabled, the access is unchecked. */ - if (unlikely(!tbi_check(desc, bit55))) { - return true; - } - - return mte_probe1_int(env, desc, ptr, 0, bit55); -} - -uint64_t mte_check1(CPUARMState *env, uint32_t desc, - uint64_t ptr, uintptr_t ra) -{ - int bit55 = extract64(ptr, 55, 1); - - /* If TBI is disabled, the access is unchecked, and ptr is not dirty. */ - if (unlikely(!tbi_check(desc, bit55))) { - return ptr; - } - - if (unlikely(!mte_probe1_int(env, desc, ptr, ra, bit55))) { - mte_check_fail(env, desc, ptr, ra); - } - - return useronly_clean_ptr(ptr); -} - -uint64_t HELPER(mte_check1)(CPUARMState *env, uint32_t desc, uint64_t ptr) -{ - return mte_check1(env, desc, ptr, GETPC()); -} - -/* - * Perform an MTE checked access for multiple logical accesses. - */ - /** * checkN: * @tag: tag memory to test @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mte_checkN)(CPUARMState *env, uint32_t desc, uint64_t ptr) return mte_checkN(env, desc, ptr, GETPC()); } +uint64_t mte_check1(CPUARMState *env, uint32_t desc, + uint64_t ptr, uintptr_t ra) +{ + uint64_t fault; + uint32_t total = FIELD_EX32(desc, MTEDESC, ESIZE); + int ret = mte_probe_int(env, desc, ptr, ra, total, &fault); + + if (unlikely(ret == 0)) { + mte_check_fail(env, desc, fault, ra); + } else if (ret < 0) { + return ptr; + } + return useronly_clean_ptr(ptr); +} + +uint64_t HELPER(mte_check1)(CPUARMState *env, uint32_t desc, uint64_t ptr) +{ + return mte_check1(env, desc, ptr, GETPC()); +} + +/* + * No-fault version of mte_check1, to be used by SVE for MemSingleNF. + * Returns false if the access is Checked and the check failed. This + * is only intended to probe the tag -- the validity of the page must + * be checked beforehand. + */ +bool mte_probe1(CPUARMState *env, uint32_t desc, uint64_t ptr) +{ + uint64_t fault; + uint32_t total = FIELD_EX32(desc, MTEDESC, ESIZE); + int ret = mte_probe_int(env, desc, ptr, 0, total, &fault); + + return ret != 0; +} + /* * Perform an MTE checked access for DC_ZVA. */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Buglink: https://bugs.launchpad.net/bugs/1921948 Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210416183106.1516563-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/tcg/aarch64/mte-5.c | 44 +++++++++++++++++++++++++++++++ tests/tcg/aarch64/Makefile.target | 2 +- 2 files changed, 45 insertions(+), 1 deletion(-) create mode 100644 tests/tcg/aarch64/mte-5.c diff --git a/tests/tcg/aarch64/mte-5.c b/tests/tcg/aarch64/mte-5.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/tcg/aarch64/mte-5.c @@ -XXX,XX +XXX,XX @@ +/* + * Memory tagging, faulting unaligned access. + * + * Copyright (c) 2021 Linaro Ltd + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "mte.h" + +void pass(int sig, siginfo_t *info, void *uc) +{ + assert(info->si_code == SEGV_MTESERR); + exit(0); +} + +int main(int ac, char **av) +{ + struct sigaction sa; + void *p0, *p1, *p2; + long excl = 1; + + enable_mte(PR_MTE_TCF_SYNC); + p0 = alloc_mte_mem(sizeof(*p0)); + + /* Create two differently tagged pointers. */ + asm("irg %0,%1,%2" : "=r"(p1) : "r"(p0), "r"(excl)); + asm("gmi %0,%1,%0" : "+r"(excl) : "r" (p1)); + assert(excl != 1); + asm("irg %0,%1,%2" : "=r"(p2) : "r"(p0), "r"(excl)); + assert(p1 != p2); + + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = pass; + sa.sa_flags = SA_SIGINFO; + sigaction(SIGSEGV, &sa, NULL); + + /* Store store two different tags in sequential granules. */ + asm("stg %0, [%0]" : : "r"(p1)); + asm("stg %0, [%0]" : : "r"(p2 + 16)); + + /* Perform an unaligned load crossing the granules. */ + asm volatile("ldr %0, [%1]" : "=r"(p0) : "r"(p1 + 12)); + abort(); +} diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target index XXXXXXX..XXXXXXX 100644 --- a/tests/tcg/aarch64/Makefile.target +++ b/tests/tcg/aarch64/Makefile.target @@ -XXX,XX +XXX,XX @@ AARCH64_TESTS += bti-2 # MTE Tests ifneq ($(DOCKER_IMAGE)$(CROSS_CC_HAS_ARMV8_MTE),) -AARCH64_TESTS += mte-1 mte-2 mte-3 mte-4 mte-6 +AARCH64_TESTS += mte-1 mte-2 mte-3 mte-4 mte-5 mte-6 mte-%: CFLAGS += -march=armv8.5-a+memtag endif -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> After recent changes, mte_checkN does not use ESIZE, and mte_check1 never used TSIZE. We can combine the two into a single field: SIZEM1. Choose to pass size - 1 because size == 0 is never used, our immediate need in mte_probe_int is for the address of the last byte (ptr + size - 1), and since almost all operations are powers of 2, this makes the immediate constant one bit smaller. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210416183106.1516563-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 4 ++-- target/arm/mte_helper.c | 18 ++++++++---------- target/arm/translate-a64.c | 5 ++--- target/arm/translate-sve.c | 5 ++--- 4 files changed, 14 insertions(+), 18 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ #define TARGET_ARM_INTERNALS_H #include "hw/registerfields.h" +#include "tcg/tcg-gvec-desc.h" #include "syndrome.h" /* register banks for CPU modes */ @@ -XXX,XX +XXX,XX @@ FIELD(MTEDESC, MIDX, 0, 4) FIELD(MTEDESC, TBI, 4, 2) FIELD(MTEDESC, TCMA, 6, 2) FIELD(MTEDESC, WRITE, 8, 1) -FIELD(MTEDESC, ESIZE, 9, 5) -FIELD(MTEDESC, TSIZE, 14, 10) /* mte_checkN only */ +FIELD(MTEDESC, SIZEM1, 9, SIMD_DATA_BITS - 9) /* size - 1 */ bool mte_probe1(CPUARMState *env, uint32_t desc, uint64_t ptr); uint64_t mte_check1(CPUARMState *env, uint32_t desc, diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mte_helper.c +++ b/target/arm/mte_helper.c @@ -XXX,XX +XXX,XX @@ static int checkN(uint8_t *mem, int odd, int cmp, int count) * Return positive on success with tbi enabled. */ static int mte_probe_int(CPUARMState *env, uint32_t desc, uint64_t ptr, - uintptr_t ra, uint32_t total, uint64_t *fault) + uintptr_t ra, uint64_t *fault) { int mmu_idx, ptr_tag, bit55; uint64_t ptr_last, prev_page, next_page; uint64_t tag_first, tag_last; uint64_t tag_byte_first, tag_byte_last; - uint32_t tag_count, tag_size, n, c; + uint32_t sizem1, tag_count, tag_size, n, c; uint8_t *mem1, *mem2; MMUAccessType type; @@ -XXX,XX +XXX,XX @@ static int mte_probe_int(CPUARMState *env, uint32_t desc, uint64_t ptr, mmu_idx = FIELD_EX32(desc, MTEDESC, MIDX); type = FIELD_EX32(desc, MTEDESC, WRITE) ? MMU_DATA_STORE : MMU_DATA_LOAD; + sizem1 = FIELD_EX32(desc, MTEDESC, SIZEM1); /* Find the addr of the end of the access */ - ptr_last = ptr + total - 1; + ptr_last = ptr + sizem1; /* Round the bounds to the tag granule, and compute the number of tags. */ tag_first = QEMU_ALIGN_DOWN(ptr, TAG_GRANULE); @@ -XXX,XX +XXX,XX @@ static int mte_probe_int(CPUARMState *env, uint32_t desc, uint64_t ptr, if (likely(tag_last - prev_page <= TARGET_PAGE_SIZE)) { /* Memory access stays on one page. */ tag_size = ((tag_byte_last - tag_byte_first) / (2 * TAG_GRANULE)) + 1; - mem1 = allocation_tag_mem(env, mmu_idx, ptr, type, total, + mem1 = allocation_tag_mem(env, mmu_idx, ptr, type, sizem1 + 1, MMU_DATA_LOAD, tag_size, ra); if (!mem1) { return 1; @@ -XXX,XX +XXX,XX @@ uint64_t mte_checkN(CPUARMState *env, uint32_t desc, uint64_t ptr, uintptr_t ra) { uint64_t fault; - uint32_t total = FIELD_EX32(desc, MTEDESC, TSIZE); - int ret = mte_probe_int(env, desc, ptr, ra, total, &fault); + int ret = mte_probe_int(env, desc, ptr, ra, &fault); if (unlikely(ret == 0)) { mte_check_fail(env, desc, fault, ra); @@ -XXX,XX +XXX,XX @@ uint64_t mte_check1(CPUARMState *env, uint32_t desc, uint64_t ptr, uintptr_t ra) { uint64_t fault; - uint32_t total = FIELD_EX32(desc, MTEDESC, ESIZE); - int ret = mte_probe_int(env, desc, ptr, ra, total, &fault); + int ret = mte_probe_int(env, desc, ptr, ra, &fault); if (unlikely(ret == 0)) { mte_check_fail(env, desc, fault, ra); @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mte_check1)(CPUARMState *env, uint32_t desc, uint64_t ptr) bool mte_probe1(CPUARMState *env, uint32_t desc, uint64_t ptr) { uint64_t fault; - uint32_t total = FIELD_EX32(desc, MTEDESC, ESIZE); - int ret = mte_probe_int(env, desc, ptr, 0, total, &fault); + int ret = mte_probe_int(env, desc, ptr, 0, &fault); return ret != 0; } diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static TCGv_i64 gen_mte_check1_mmuidx(DisasContext *s, TCGv_i64 addr, desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write); - desc = FIELD_DP32(desc, MTEDESC, ESIZE, 1 << log2_size); + desc = FIELD_DP32(desc, MTEDESC, SIZEM1, (1 << log2_size) - 1); tcg_desc = tcg_const_i32(desc); ret = new_tmp_a64(s); @@ -XXX,XX +XXX,XX @@ TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write, desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write); - desc = FIELD_DP32(desc, MTEDESC, ESIZE, 1 << log2_esize); - desc = FIELD_DP32(desc, MTEDESC, TSIZE, total_size); + desc = FIELD_DP32(desc, MTEDESC, SIZEM1, total_size - 1); tcg_desc = tcg_const_i32(desc); ret = new_tmp_a64(s); diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write); - desc = FIELD_DP32(desc, MTEDESC, ESIZE, 1 << msz); - desc = FIELD_DP32(desc, MTEDESC, TSIZE, mte_n << msz); + desc = FIELD_DP32(desc, MTEDESC, SIZEM1, (mte_n << msz) - 1); desc <<= SVE_MTEDESC_SHIFT; } else { addr = clean_data_tbi(s, addr); @@ -XXX,XX +XXX,XX @@ static void do_mem_zpz(DisasContext *s, int zt, int pg, int zm, desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write); - desc = FIELD_DP32(desc, MTEDESC, ESIZE, 1 << msz); + desc = FIELD_DP32(desc, MTEDESC, SIZEM1, (1 << msz) - 1); desc <<= SVE_MTEDESC_SHIFT; } desc = simd_desc(vsz, vsz, desc | scale); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The mte_check1 and mte_checkN functions are now identical. Drop mte_check1 and rename mte_checkN to mte_check. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210416183106.1516563-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 3 +-- target/arm/internals.h | 5 +---- target/arm/mte_helper.c | 26 +++----------------------- target/arm/sve_helper.c | 14 +++++++------- target/arm/translate-a64.c | 4 ++-- 5 files changed, 14 insertions(+), 38 deletions(-) diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(autdb, TCG_CALL_NO_WG, i64, env, i64, i64) DEF_HELPER_FLAGS_2(xpaci, TCG_CALL_NO_RWG_SE, i64, env, i64) DEF_HELPER_FLAGS_2(xpacd, TCG_CALL_NO_RWG_SE, i64, env, i64) -DEF_HELPER_FLAGS_3(mte_check1, TCG_CALL_NO_WG, i64, env, i32, i64) -DEF_HELPER_FLAGS_3(mte_checkN, TCG_CALL_NO_WG, i64, env, i32, i64) +DEF_HELPER_FLAGS_3(mte_check, TCG_CALL_NO_WG, i64, env, i32, i64) DEF_HELPER_FLAGS_3(mte_check_zva, TCG_CALL_NO_WG, i64, env, i32, i64) DEF_HELPER_FLAGS_3(irg, TCG_CALL_NO_RWG, i64, env, i64, i64) DEF_HELPER_FLAGS_4(addsubg, TCG_CALL_NO_RWG_SE, i64, env, i64, s32, i32) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ FIELD(MTEDESC, WRITE, 8, 1) FIELD(MTEDESC, SIZEM1, 9, SIMD_DATA_BITS - 9) /* size - 1 */ bool mte_probe1(CPUARMState *env, uint32_t desc, uint64_t ptr); -uint64_t mte_check1(CPUARMState *env, uint32_t desc, - uint64_t ptr, uintptr_t ra); -uint64_t mte_checkN(CPUARMState *env, uint32_t desc, - uint64_t ptr, uintptr_t ra); +uint64_t mte_check(CPUARMState *env, uint32_t desc, uint64_t ptr, uintptr_t ra); static inline int allocation_tag_from_addr(uint64_t ptr) { diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mte_helper.c +++ b/target/arm/mte_helper.c @@ -XXX,XX +XXX,XX @@ static int mte_probe_int(CPUARMState *env, uint32_t desc, uint64_t ptr, return 0; } -uint64_t mte_checkN(CPUARMState *env, uint32_t desc, - uint64_t ptr, uintptr_t ra) +uint64_t mte_check(CPUARMState *env, uint32_t desc, uint64_t ptr, uintptr_t ra) { uint64_t fault; int ret = mte_probe_int(env, desc, ptr, ra, &fault); @@ -XXX,XX +XXX,XX @@ uint64_t mte_checkN(CPUARMState *env, uint32_t desc, return useronly_clean_ptr(ptr); } -uint64_t HELPER(mte_checkN)(CPUARMState *env, uint32_t desc, uint64_t ptr) +uint64_t HELPER(mte_check)(CPUARMState *env, uint32_t desc, uint64_t ptr) { - return mte_checkN(env, desc, ptr, GETPC()); -} - -uint64_t mte_check1(CPUARMState *env, uint32_t desc, - uint64_t ptr, uintptr_t ra) -{ - uint64_t fault; - int ret = mte_probe_int(env, desc, ptr, ra, &fault); - - if (unlikely(ret == 0)) { - mte_check_fail(env, desc, fault, ra); - } else if (ret < 0) { - return ptr; - } - return useronly_clean_ptr(ptr); -} - -uint64_t HELPER(mte_check1)(CPUARMState *env, uint32_t desc, uint64_t ptr) -{ - return mte_check1(env, desc, ptr, GETPC()); + return mte_check(env, desc, ptr, GETPC()); } /* diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ static void sve_cont_ldst_mte_check1(SVEContLdSt *info, CPUARMState *env, uintptr_t ra) { sve_cont_ldst_mte_check_int(info, env, vg, addr, esize, msize, - mtedesc, ra, mte_check1); + mtedesc, ra, mte_check); } static void sve_cont_ldst_mte_checkN(SVEContLdSt *info, CPUARMState *env, @@ -XXX,XX +XXX,XX @@ static void sve_cont_ldst_mte_checkN(SVEContLdSt *info, CPUARMState *env, uintptr_t ra) { sve_cont_ldst_mte_check_int(info, env, vg, addr, esize, msize, - mtedesc, ra, mte_checkN); + mtedesc, ra, mte_check); } @@ -XXX,XX +XXX,XX @@ void sve_ldnfff1_r(CPUARMState *env, void *vg, const target_ulong addr, if (fault == FAULT_FIRST) { /* Trapping mte check for the first-fault element. */ if (mtedesc) { - mte_check1(env, mtedesc, addr + mem_off, retaddr); + mte_check(env, mtedesc, addr + mem_off, retaddr); } /* @@ -XXX,XX +XXX,XX @@ void sve_ld1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm, info.attrs, BP_MEM_READ, retaddr); } if (mtedesc && arm_tlb_mte_tagged(&info.attrs)) { - mte_check1(env, mtedesc, addr, retaddr); + mte_check(env, mtedesc, addr, retaddr); } host_fn(&scratch, reg_off, info.host); } else { @@ -XXX,XX +XXX,XX @@ void sve_ld1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm, BP_MEM_READ, retaddr); } if (mtedesc && arm_tlb_mte_tagged(&info.attrs)) { - mte_check1(env, mtedesc, addr, retaddr); + mte_check(env, mtedesc, addr, retaddr); } tlb_fn(env, &scratch, reg_off, addr, retaddr); } @@ -XXX,XX +XXX,XX @@ void sve_ldff1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm, */ addr = base + (off_fn(vm, reg_off) << scale); if (mtedesc) { - mte_check1(env, mtedesc, addr, retaddr); + mte_check(env, mtedesc, addr, retaddr); } tlb_fn(env, vd, reg_off, addr, retaddr); @@ -XXX,XX +XXX,XX @@ void sve_st1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm, } if (mtedesc && arm_tlb_mte_tagged(&info.attrs)) { - mte_check1(env, mtedesc, addr, retaddr); + mte_check(env, mtedesc, addr, retaddr); } } i += 1; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static TCGv_i64 gen_mte_check1_mmuidx(DisasContext *s, TCGv_i64 addr, tcg_desc = tcg_const_i32(desc); ret = new_tmp_a64(s); - gen_helper_mte_check1(ret, cpu_env, tcg_desc, addr); + gen_helper_mte_check(ret, cpu_env, tcg_desc, addr); tcg_temp_free_i32(tcg_desc); return ret; @@ -XXX,XX +XXX,XX @@ TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write, tcg_desc = tcg_const_i32(desc); ret = new_tmp_a64(s); - gen_helper_mte_checkN(ret, cpu_env, tcg_desc, addr); + gen_helper_mte_check(ret, cpu_env, tcg_desc, addr); tcg_temp_free_i32(tcg_desc); return ret; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> For consistency with the mte_check1 + mte_checkN merge to mte_check, rename the probe function as well. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210416183106.1516563-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 2 +- target/arm/mte_helper.c | 6 +++--- target/arm/sve_helper.c | 6 +++--- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ FIELD(MTEDESC, TCMA, 6, 2) FIELD(MTEDESC, WRITE, 8, 1) FIELD(MTEDESC, SIZEM1, 9, SIMD_DATA_BITS - 9) /* size - 1 */ -bool mte_probe1(CPUARMState *env, uint32_t desc, uint64_t ptr); +bool mte_probe(CPUARMState *env, uint32_t desc, uint64_t ptr); uint64_t mte_check(CPUARMState *env, uint32_t desc, uint64_t ptr, uintptr_t ra); static inline int allocation_tag_from_addr(uint64_t ptr) diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mte_helper.c +++ b/target/arm/mte_helper.c @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, * exception for inaccessible pages, and resolves the virtual address * into the softmmu tlb. * - * When RA == 0, this is for mte_probe1. The page is expected to be + * When RA == 0, this is for mte_probe. The page is expected to be * valid. Indicate to probe_access_flags no-fault, then assert that * we received a valid page. */ @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mte_check)(CPUARMState *env, uint32_t desc, uint64_t ptr) } /* - * No-fault version of mte_check1, to be used by SVE for MemSingleNF. + * No-fault version of mte_check, to be used by SVE for MemSingleNF. * Returns false if the access is Checked and the check failed. This * is only intended to probe the tag -- the validity of the page must * be checked beforehand. */ -bool mte_probe1(CPUARMState *env, uint32_t desc, uint64_t ptr) +bool mte_probe(CPUARMState *env, uint32_t desc, uint64_t ptr) { uint64_t fault; int ret = mte_probe_int(env, desc, ptr, 0, &fault); diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void sve_ldnfff1_r(CPUARMState *env, void *vg, const target_ulong addr, /* Watchpoint hit, see below. */ goto do_fault; } - if (mtedesc && !mte_probe1(env, mtedesc, addr + mem_off)) { + if (mtedesc && !mte_probe(env, mtedesc, addr + mem_off)) { goto do_fault; } /* @@ -XXX,XX +XXX,XX @@ void sve_ldnfff1_r(CPUARMState *env, void *vg, const target_ulong addr, & BP_MEM_READ)) { goto do_fault; } - if (mtedesc && !mte_probe1(env, mtedesc, addr + mem_off)) { + if (mtedesc && !mte_probe(env, mtedesc, addr + mem_off)) { goto do_fault; } host_fn(vd, reg_off, host + mem_off); @@ -XXX,XX +XXX,XX @@ void sve_ldff1_z(CPUARMState *env, void *vd, uint64_t *vg, void *vm, } if (mtedesc && arm_tlb_mte_tagged(&info.attrs) && - !mte_probe1(env, mtedesc, addr)) { + !mte_probe(env, mtedesc, addr)) { goto fault; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Now that mte_check1 and mte_checkN have been merged, we can merge sve_cont_ldst_mte_check1 and sve_cont_ldst_mte_checkN. Which means that we can eliminate the function pointer into sve_ldN_r and sve_stN_r, calling sve_cont_ldst_mte_check directly. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210416183106.1516563-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 84 +++++++++++++---------------------------- 1 file changed, 26 insertions(+), 58 deletions(-) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ static void sve_cont_ldst_watchpoints(SVEContLdSt *info, CPUARMState *env, #endif } -typedef uint64_t mte_check_fn(CPUARMState *, uint32_t, uint64_t, uintptr_t); - -static inline QEMU_ALWAYS_INLINE -void sve_cont_ldst_mte_check_int(SVEContLdSt *info, CPUARMState *env, - uint64_t *vg, target_ulong addr, int esize, - int msize, uint32_t mtedesc, uintptr_t ra, - mte_check_fn *check) +static void sve_cont_ldst_mte_check(SVEContLdSt *info, CPUARMState *env, + uint64_t *vg, target_ulong addr, int esize, + int msize, uint32_t mtedesc, uintptr_t ra) { intptr_t mem_off, reg_off, reg_last; @@ -XXX,XX +XXX,XX @@ void sve_cont_ldst_mte_check_int(SVEContLdSt *info, CPUARMState *env, uint64_t pg = vg[reg_off >> 6]; do { if ((pg >> (reg_off & 63)) & 1) { - check(env, mtedesc, addr, ra); + mte_check(env, mtedesc, addr, ra); } reg_off += esize; mem_off += msize; @@ -XXX,XX +XXX,XX @@ void sve_cont_ldst_mte_check_int(SVEContLdSt *info, CPUARMState *env, uint64_t pg = vg[reg_off >> 6]; do { if ((pg >> (reg_off & 63)) & 1) { - check(env, mtedesc, addr, ra); + mte_check(env, mtedesc, addr, ra); } reg_off += esize; mem_off += msize; @@ -XXX,XX +XXX,XX @@ void sve_cont_ldst_mte_check_int(SVEContLdSt *info, CPUARMState *env, } } -typedef void sve_cont_ldst_mte_check_fn(SVEContLdSt *info, CPUARMState *env, - uint64_t *vg, target_ulong addr, - int esize, int msize, uint32_t mtedesc, - uintptr_t ra); - -static void sve_cont_ldst_mte_check1(SVEContLdSt *info, CPUARMState *env, - uint64_t *vg, target_ulong addr, - int esize, int msize, uint32_t mtedesc, - uintptr_t ra) -{ - sve_cont_ldst_mte_check_int(info, env, vg, addr, esize, msize, - mtedesc, ra, mte_check); -} - -static void sve_cont_ldst_mte_checkN(SVEContLdSt *info, CPUARMState *env, - uint64_t *vg, target_ulong addr, - int esize, int msize, uint32_t mtedesc, - uintptr_t ra) -{ - sve_cont_ldst_mte_check_int(info, env, vg, addr, esize, msize, - mtedesc, ra, mte_check); -} - - /* * Common helper for all contiguous 1,2,3,4-register predicated stores. */ @@ -XXX,XX +XXX,XX @@ void sve_ldN_r(CPUARMState *env, uint64_t *vg, const target_ulong addr, uint32_t desc, const uintptr_t retaddr, const int esz, const int msz, const int N, uint32_t mtedesc, sve_ldst1_host_fn *host_fn, - sve_ldst1_tlb_fn *tlb_fn, - sve_cont_ldst_mte_check_fn *mte_check_fn) + sve_ldst1_tlb_fn *tlb_fn) { const unsigned rd = simd_data(desc); const intptr_t reg_max = simd_oprsz(desc); @@ -XXX,XX +XXX,XX @@ void sve_ldN_r(CPUARMState *env, uint64_t *vg, const target_ulong addr, * Handle mte checks for all active elements. * Since TBI must be set for MTE, !mtedesc => !mte_active. */ - if (mte_check_fn && mtedesc) { - mte_check_fn(&info, env, vg, addr, 1 << esz, N << msz, - mtedesc, retaddr); + if (mtedesc) { + sve_cont_ldst_mte_check(&info, env, vg, addr, 1 << esz, N << msz, + mtedesc, retaddr); } flags = info.page[0].flags | info.page[1].flags; @@ -XXX,XX +XXX,XX @@ void sve_ldN_r_mte(CPUARMState *env, uint64_t *vg, target_ulong addr, mtedesc = 0; } - sve_ldN_r(env, vg, addr, desc, ra, esz, msz, N, mtedesc, host_fn, tlb_fn, - N == 1 ? sve_cont_ldst_mte_check1 : sve_cont_ldst_mte_checkN); + sve_ldN_r(env, vg, addr, desc, ra, esz, msz, N, mtedesc, host_fn, tlb_fn); } #define DO_LD1_1(NAME, ESZ) \ @@ -XXX,XX +XXX,XX @@ void HELPER(sve_##NAME##_r)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ { \ sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, MO_8, 1, 0, \ - sve_##NAME##_host, sve_##NAME##_tlb, NULL); \ + sve_##NAME##_host, sve_##NAME##_tlb); \ } \ void HELPER(sve_##NAME##_r_mte)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ @@ -XXX,XX +XXX,XX @@ void HELPER(sve_##NAME##_le_r)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ { \ sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, 1, 0, \ - sve_##NAME##_le_host, sve_##NAME##_le_tlb, NULL); \ + sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ } \ void HELPER(sve_##NAME##_be_r)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ { \ sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, 1, 0, \ - sve_##NAME##_be_host, sve_##NAME##_be_tlb, NULL); \ + sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ } \ void HELPER(sve_##NAME##_le_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint32_t desc) \ { \ sve_ldN_r_mte(env, vg, addr, desc, GETPC(), ESZ, MSZ, 1, \ sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ } \ void HELPER(sve_##NAME##_be_r_mte)(CPUARMState *env, void *vg, \ - target_ulong addr, uint32_t desc) \ + target_ulong addr, uint32_t desc) \ { \ sve_ldN_r_mte(env, vg, addr, desc, GETPC(), ESZ, MSZ, 1, \ sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ @@ -XXX,XX +XXX,XX @@ void HELPER(sve_ld##N##bb_r)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ { \ sve_ldN_r(env, vg, addr, desc, GETPC(), MO_8, MO_8, N, 0, \ - sve_ld1bb_host, sve_ld1bb_tlb, NULL); \ + sve_ld1bb_host, sve_ld1bb_tlb); \ } \ void HELPER(sve_ld##N##bb_r_mte)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ @@ -XXX,XX +XXX,XX @@ void HELPER(sve_ld##N##SUFF##_le_r)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ { \ sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, ESZ, N, 0, \ - sve_ld1##SUFF##_le_host, sve_ld1##SUFF##_le_tlb, NULL); \ + sve_ld1##SUFF##_le_host, sve_ld1##SUFF##_le_tlb); \ } \ void HELPER(sve_ld##N##SUFF##_be_r)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ { \ sve_ldN_r(env, vg, addr, desc, GETPC(), ESZ, ESZ, N, 0, \ - sve_ld1##SUFF##_be_host, sve_ld1##SUFF##_be_tlb, NULL); \ + sve_ld1##SUFF##_be_host, sve_ld1##SUFF##_be_tlb); \ } \ void HELPER(sve_ld##N##SUFF##_le_r_mte)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ @@ -XXX,XX +XXX,XX @@ void sve_stN_r(CPUARMState *env, uint64_t *vg, target_ulong addr, uint32_t desc, const uintptr_t retaddr, const int esz, const int msz, const int N, uint32_t mtedesc, sve_ldst1_host_fn *host_fn, - sve_ldst1_tlb_fn *tlb_fn, - sve_cont_ldst_mte_check_fn *mte_check_fn) + sve_ldst1_tlb_fn *tlb_fn) { const unsigned rd = simd_data(desc); const intptr_t reg_max = simd_oprsz(desc); @@ -XXX,XX +XXX,XX @@ void sve_stN_r(CPUARMState *env, uint64_t *vg, target_ulong addr, * Handle mte checks for all active elements. * Since TBI must be set for MTE, !mtedesc => !mte_active. */ - if (mte_check_fn && mtedesc) { - mte_check_fn(&info, env, vg, addr, 1 << esz, N << msz, - mtedesc, retaddr); + if (mtedesc) { + sve_cont_ldst_mte_check(&info, env, vg, addr, 1 << esz, N << msz, + mtedesc, retaddr); } flags = info.page[0].flags | info.page[1].flags; @@ -XXX,XX +XXX,XX @@ void sve_stN_r_mte(CPUARMState *env, uint64_t *vg, target_ulong addr, mtedesc = 0; } - sve_stN_r(env, vg, addr, desc, ra, esz, msz, N, mtedesc, host_fn, tlb_fn, - N == 1 ? sve_cont_ldst_mte_check1 : sve_cont_ldst_mte_checkN); + sve_stN_r(env, vg, addr, desc, ra, esz, msz, N, mtedesc, host_fn, tlb_fn); } #define DO_STN_1(N, NAME, ESZ) \ @@ -XXX,XX +XXX,XX @@ void HELPER(sve_st##N##NAME##_r)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ { \ sve_stN_r(env, vg, addr, desc, GETPC(), ESZ, MO_8, N, 0, \ - sve_st1##NAME##_host, sve_st1##NAME##_tlb, NULL); \ + sve_st1##NAME##_host, sve_st1##NAME##_tlb); \ } \ void HELPER(sve_st##N##NAME##_r_mte)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ @@ -XXX,XX +XXX,XX @@ void HELPER(sve_st##N##NAME##_le_r)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ { \ sve_stN_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, N, 0, \ - sve_st1##NAME##_le_host, sve_st1##NAME##_le_tlb, NULL); \ + sve_st1##NAME##_le_host, sve_st1##NAME##_le_tlb); \ } \ void HELPER(sve_st##N##NAME##_be_r)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ { \ sve_stN_r(env, vg, addr, desc, GETPC(), ESZ, MSZ, N, 0, \ - sve_st1##NAME##_be_host, sve_st1##NAME##_be_tlb, NULL); \ + sve_st1##NAME##_be_host, sve_st1##NAME##_be_tlb); \ } \ void HELPER(sve_st##N##NAME##_le_r_mte)(CPUARMState *env, void *vg, \ target_ulong addr, uint32_t desc) \ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The log2_esize parameter is not used except trivially. Drop the parameter and the deferral to gen_mte_check1. This fixes a bug in that the parameters as documented in the header file were the reverse from those in the implementation. Which meant that translate-sve.c was passing the parameters in the wrong order. Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210416183106.1516563-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 2 +- target/arm/translate-a64.c | 15 +++++++-------- target/arm/translate-sve.c | 4 ++-- 3 files changed, 10 insertions(+), 11 deletions(-) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ TCGv_i64 clean_data_tbi(DisasContext *s, TCGv_i64 addr); TCGv_i64 gen_mte_check1(DisasContext *s, TCGv_i64 addr, bool is_write, bool tag_checked, int log2_size); TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write, - bool tag_checked, int count, int log2_esize); + bool tag_checked, int size); /* We should have at some point before trying to access an FP register * done the necessary access check, so assert that diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ TCGv_i64 gen_mte_check1(DisasContext *s, TCGv_i64 addr, bool is_write, * For MTE, check multiple logical sequential accesses. */ TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write, - bool tag_checked, int log2_esize, int total_size) + bool tag_checked, int size) { - if (tag_checked && s->mte_active[0] && total_size != (1 << log2_esize)) { + if (tag_checked && s->mte_active[0]) { TCGv_i32 tcg_desc; TCGv_i64 ret; int desc = 0; @@ -XXX,XX +XXX,XX @@ TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write, desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write); - desc = FIELD_DP32(desc, MTEDESC, SIZEM1, total_size - 1); + desc = FIELD_DP32(desc, MTEDESC, SIZEM1, size - 1); tcg_desc = tcg_const_i32(desc); ret = new_tmp_a64(s); @@ -XXX,XX +XXX,XX @@ TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write, return ret; } - return gen_mte_check1(s, addr, is_write, tag_checked, log2_esize); + return clean_data_tbi(s, addr); } typedef struct DisasCompare64 { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) } clean_addr = gen_mte_checkN(s, dirty_addr, !is_load, - (wback || rn != 31) && !set_tag, - size, 2 << size); + (wback || rn != 31) && !set_tag, 2 << size); if (is_vector) { if (is_load) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) * promote consecutive little-endian elements below. */ clean_addr = gen_mte_checkN(s, tcg_rn, is_store, is_postidx || rn != 31, - size, total); + total); /* * Consecutive little-endian elements from a single register @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) tcg_rn = cpu_reg_sp(s, rn); clean_addr = gen_mte_checkN(s, tcg_rn, !is_load, is_postidx || rn != 31, - scale, total); + total); tcg_ebytes = tcg_const_i64(1 << scale); for (xs = 0; xs < selem; xs++) { diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) dirty_addr = tcg_temp_new_i64(); tcg_gen_addi_i64(dirty_addr, cpu_reg_sp(s, rn), imm); - clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len, MO_8); + clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len); tcg_temp_free_i64(dirty_addr); /* @@ -XXX,XX +XXX,XX @@ static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm) dirty_addr = tcg_temp_new_i64(); tcg_gen_addi_i64(dirty_addr, cpu_reg_sp(s, rn), imm); - clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len, MO_8); + clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len); tcg_temp_free_i64(dirty_addr); /* Note that unpredicated load/store of vector/predicate registers -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The encoding of size = 2 and size = 3 had the incorrect decode for align, overlapping the stride field. This error was hidden by what should have been unnecessary masking in translate. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/neon-ls.decode | 4 ++-- target/arm/translate-neon.c.inc | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/target/arm/neon-ls.decode b/target/arm/neon-ls.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-ls.decode +++ b/target/arm/neon-ls.decode @@ -XXX,XX +XXX,XX @@ VLD_all_lanes 1111 0100 1 . 1 0 rn:4 .... 11 n:2 size:2 t:1 a:1 rm:4 \ VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 00 n:2 reg_idx:3 align:1 rm:4 \ vd=%vd_dp size=0 stride=1 -VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 01 n:2 reg_idx:2 align:2 rm:4 \ +VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 01 n:2 reg_idx:2 . align:1 rm:4 \ vd=%vd_dp size=1 stride=%imm1_5_p1 -VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 10 n:2 reg_idx:1 align:3 rm:4 \ +VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 10 n:2 reg_idx:1 . align:2 rm:4 \ vd=%vd_dp size=2 stride=%imm1_6_p1 diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a) switch (nregs) { case 1: if (((a->align & (1 << a->size)) != 0) || - (a->size == 2 && ((a->align & 3) == 1 || (a->align & 3) == 2))) { + (a->size == 2 && (a->align == 1 || a->align == 2))) { return false; } break; @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a) } break; case 4: - if ((a->size == 2) && ((a->align & 3) == 3)) { + if (a->size == 2 && a->align == 3) { return false; } break; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We're about to rearrange the macro expansion surrounding tbflags, and this field name will be expanded using the bit definition of the same name, resulting in a token pasting error. So SCTLR_B -> SCTLR__B in the 3 uses, and document it. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 +- target/arm/helper.c | 2 +- target/arm/translate.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A32, VECSTRIDE, 12, 2) /* Not cached. */ */ FIELD(TBFLAG_A32, XSCALE_CPAR, 12, 2) FIELD(TBFLAG_A32, VFPEN, 14, 1) /* Partially cached, minus FPEXC. */ -FIELD(TBFLAG_A32, SCTLR_B, 15, 1) +FIELD(TBFLAG_A32, SCTLR__B, 15, 1) /* Cannot overlap with SCTLR_B */ FIELD(TBFLAG_A32, HSTR_ACTIVE, 16, 1) /* * Indicates whether cp register reads and writes by guest code should access diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_common_32(CPUARMState *env, int fp_el, bool sctlr_b = arm_sctlr_b(env); if (sctlr_b) { - flags = FIELD_DP32(flags, TBFLAG_A32, SCTLR_B, 1); + flags = FIELD_DP32(flags, TBFLAG_A32, SCTLR__B, 1); } if (arm_cpu_data_is_big_endian_a32(env, sctlr_b)) { flags = FIELD_DP32(flags, TBFLAG_ANY, BE_DATA, 1); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) FIELD_EX32(tb_flags, TBFLAG_ANY, BE_DATA) ? MO_BE : MO_LE; dc->debug_target_el = FIELD_EX32(tb_flags, TBFLAG_ANY, DEBUG_TARGET_EL); - dc->sctlr_b = FIELD_EX32(tb_flags, TBFLAG_A32, SCTLR_B); + dc->sctlr_b = FIELD_EX32(tb_flags, TBFLAG_A32, SCTLR__B); dc->hstr_active = FIELD_EX32(tb_flags, TBFLAG_A32, HSTR_ACTIVE); dc->ns = FIELD_EX32(tb_flags, TBFLAG_A32, NS); dc->vfp_enabled = FIELD_EX32(tb_flags, TBFLAG_A32, VFPEN); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We're about to rearrange the macro expansion surrounding tbflags, and this field name will be expanded using the bit definition of the same name, resulting in a token pasting error. So PSTATE_SS -> PSTATE__SS in the uses, and document it. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 +- target/arm/helper.c | 4 ++-- target/arm/translate-a64.c | 2 +- target/arm/translate.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef ARMCPU ArchCPU; */ FIELD(TBFLAG_ANY, AARCH64_STATE, 31, 1) FIELD(TBFLAG_ANY, SS_ACTIVE, 30, 1) -FIELD(TBFLAG_ANY, PSTATE_SS, 29, 1) /* Not cached. */ +FIELD(TBFLAG_ANY, PSTATE__SS, 29, 1) /* Not cached. */ FIELD(TBFLAG_ANY, BE_DATA, 28, 1) FIELD(TBFLAG_ANY, MMUIDX, 24, 4) /* Target EL if we take a floating-point-disabled exception */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, * 0 x Inactive (the TB flag for SS is always 0) * 1 0 Active-pending * 1 1 Active-not-pending - * SS_ACTIVE is set in hflags; PSTATE_SS is computed every TB. + * SS_ACTIVE is set in hflags; PSTATE__SS is computed every TB. */ if (FIELD_EX32(flags, TBFLAG_ANY, SS_ACTIVE) && (env->pstate & PSTATE_SS)) { - flags = FIELD_DP32(flags, TBFLAG_ANY, PSTATE_SS, 1); + flags = FIELD_DP32(flags, TBFLAG_ANY, PSTATE__SS, 1); } *pflags = flags; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, * end the TB */ dc->ss_active = FIELD_EX32(tb_flags, TBFLAG_ANY, SS_ACTIVE); - dc->pstate_ss = FIELD_EX32(tb_flags, TBFLAG_ANY, PSTATE_SS); + dc->pstate_ss = FIELD_EX32(tb_flags, TBFLAG_ANY, PSTATE__SS); dc->is_ldex = false; dc->debug_target_el = FIELD_EX32(tb_flags, TBFLAG_ANY, DEBUG_TARGET_EL); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) * end the TB */ dc->ss_active = FIELD_EX32(tb_flags, TBFLAG_ANY, SS_ACTIVE); - dc->pstate_ss = FIELD_EX32(tb_flags, TBFLAG_ANY, PSTATE_SS); + dc->pstate_ss = FIELD_EX32(tb_flags, TBFLAG_ANY, PSTATE__SS); dc->is_ldex = false; dc->page_start = dc->base.pc_first & TARGET_PAGE_MASK; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We're about to split tbflags into two parts. These macros will ensure that the correct part is used with the correct set of bits. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 22 +++++++++- target/arm/helper-a64.c | 2 +- target/arm/helper.c | 85 +++++++++++++++++--------------------- target/arm/translate-a64.c | 36 ++++++++-------- target/arm/translate.c | 48 ++++++++++----------- 5 files changed, 101 insertions(+), 92 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, TCMA, 16, 2) FIELD(TBFLAG_A64, MTE_ACTIVE, 18, 1) FIELD(TBFLAG_A64, MTE0_ACTIVE, 19, 1) +/* + * Helpers for using the above. + */ +#define DP_TBFLAG_ANY(DST, WHICH, VAL) \ + (DST = FIELD_DP32(DST, TBFLAG_ANY, WHICH, VAL)) +#define DP_TBFLAG_A64(DST, WHICH, VAL) \ + (DST = FIELD_DP32(DST, TBFLAG_A64, WHICH, VAL)) +#define DP_TBFLAG_A32(DST, WHICH, VAL) \ + (DST = FIELD_DP32(DST, TBFLAG_A32, WHICH, VAL)) +#define DP_TBFLAG_M32(DST, WHICH, VAL) \ + (DST = FIELD_DP32(DST, TBFLAG_M32, WHICH, VAL)) +#define DP_TBFLAG_AM32(DST, WHICH, VAL) \ + (DST = FIELD_DP32(DST, TBFLAG_AM32, WHICH, VAL)) + +#define EX_TBFLAG_ANY(IN, WHICH) FIELD_EX32(IN, TBFLAG_ANY, WHICH) +#define EX_TBFLAG_A64(IN, WHICH) FIELD_EX32(IN, TBFLAG_A64, WHICH) +#define EX_TBFLAG_A32(IN, WHICH) FIELD_EX32(IN, TBFLAG_A32, WHICH) +#define EX_TBFLAG_M32(IN, WHICH) FIELD_EX32(IN, TBFLAG_M32, WHICH) +#define EX_TBFLAG_AM32(IN, WHICH) FIELD_EX32(IN, TBFLAG_AM32, WHICH) + /** * cpu_mmu_index: * @env: The cpu environment @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, MTE0_ACTIVE, 19, 1) */ static inline int cpu_mmu_index(CPUARMState *env, bool ifetch) { - return FIELD_EX32(env->hflags, TBFLAG_ANY, MMUIDX); + return EX_TBFLAG_ANY(env->hflags, MMUIDX); } static inline bool bswap_code(bool sctlr_b) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ void HELPER(exception_return)(CPUARMState *env, uint64_t new_pc) * the hflags rebuild, since we can pull the composite TBII field * from there. */ - tbii = FIELD_EX32(env->hflags, TBFLAG_A64, TBII); + tbii = EX_TBFLAG_A64(env->hflags, TBII); if ((tbii >> extract64(new_pc, 55, 1)) & 1) { /* TBI is enabled. */ int core_mmu_idx = cpu_mmu_index(env, false); diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env) static uint32_t rebuild_hflags_common(CPUARMState *env, int fp_el, ARMMMUIdx mmu_idx, uint32_t flags) { - flags = FIELD_DP32(flags, TBFLAG_ANY, FPEXC_EL, fp_el); - flags = FIELD_DP32(flags, TBFLAG_ANY, MMUIDX, - arm_to_core_mmu_idx(mmu_idx)); + DP_TBFLAG_ANY(flags, FPEXC_EL, fp_el); + DP_TBFLAG_ANY(flags, MMUIDX, arm_to_core_mmu_idx(mmu_idx)); if (arm_singlestep_active(env)) { - flags = FIELD_DP32(flags, TBFLAG_ANY, SS_ACTIVE, 1); + DP_TBFLAG_ANY(flags, SS_ACTIVE, 1); } return flags; } @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_common_32(CPUARMState *env, int fp_el, bool sctlr_b = arm_sctlr_b(env); if (sctlr_b) { - flags = FIELD_DP32(flags, TBFLAG_A32, SCTLR__B, 1); + DP_TBFLAG_A32(flags, SCTLR__B, 1); } if (arm_cpu_data_is_big_endian_a32(env, sctlr_b)) { - flags = FIELD_DP32(flags, TBFLAG_ANY, BE_DATA, 1); + DP_TBFLAG_ANY(flags, BE_DATA, 1); } - flags = FIELD_DP32(flags, TBFLAG_A32, NS, !access_secure_reg(env)); + DP_TBFLAG_A32(flags, NS, !access_secure_reg(env)); return rebuild_hflags_common(env, fp_el, mmu_idx, flags); } @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_m32(CPUARMState *env, int fp_el, uint32_t flags = 0; if (arm_v7m_is_handler_mode(env)) { - flags = FIELD_DP32(flags, TBFLAG_M32, HANDLER, 1); + DP_TBFLAG_M32(flags, HANDLER, 1); } /* @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_m32(CPUARMState *env, int fp_el, if (arm_feature(env, ARM_FEATURE_V8) && !((mmu_idx & ARM_MMU_IDX_M_NEGPRI) && (env->v7m.ccr[env->v7m.secure] & R_V7M_CCR_STKOFHFNMIGN_MASK))) { - flags = FIELD_DP32(flags, TBFLAG_M32, STACKCHECK, 1); + DP_TBFLAG_M32(flags, STACKCHECK, 1); } return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_aprofile(CPUARMState *env) { int flags = 0; - flags = FIELD_DP32(flags, TBFLAG_ANY, DEBUG_TARGET_EL, - arm_debug_target_el(env)); + DP_TBFLAG_ANY(flags, DEBUG_TARGET_EL, arm_debug_target_el(env)); return flags; } @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_a32(CPUARMState *env, int fp_el, uint32_t flags = rebuild_hflags_aprofile(env); if (arm_el_is_aa64(env, 1)) { - flags = FIELD_DP32(flags, TBFLAG_A32, VFPEN, 1); + DP_TBFLAG_A32(flags, VFPEN, 1); } if (arm_current_el(env) < 2 && env->cp15.hstr_el2 && (arm_hcr_el2_eff(env) & (HCR_E2H | HCR_TGE)) != (HCR_E2H | HCR_TGE)) { - flags = FIELD_DP32(flags, TBFLAG_A32, HSTR_ACTIVE, 1); + DP_TBFLAG_A32(flags, HSTR_ACTIVE, 1); } return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, uint64_t sctlr; int tbii, tbid; - flags = FIELD_DP32(flags, TBFLAG_ANY, AARCH64_STATE, 1); + DP_TBFLAG_ANY(flags, AARCH64_STATE, 1); /* Get control bits for tagged addresses. */ tbid = aa64_va_parameter_tbi(tcr, mmu_idx); tbii = tbid & ~aa64_va_parameter_tbid(tcr, mmu_idx); - flags = FIELD_DP32(flags, TBFLAG_A64, TBII, tbii); - flags = FIELD_DP32(flags, TBFLAG_A64, TBID, tbid); + DP_TBFLAG_A64(flags, TBII, tbii); + DP_TBFLAG_A64(flags, TBID, tbid); if (cpu_isar_feature(aa64_sve, env_archcpu(env))) { int sve_el = sve_exception_el(env, el); @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, } else { zcr_len = sve_zcr_len_for_el(env, el); } - flags = FIELD_DP32(flags, TBFLAG_A64, SVEEXC_EL, sve_el); - flags = FIELD_DP32(flags, TBFLAG_A64, ZCR_LEN, zcr_len); + DP_TBFLAG_A64(flags, SVEEXC_EL, sve_el); + DP_TBFLAG_A64(flags, ZCR_LEN, zcr_len); } sctlr = regime_sctlr(env, stage1); if (arm_cpu_data_is_big_endian_a64(el, sctlr)) { - flags = FIELD_DP32(flags, TBFLAG_ANY, BE_DATA, 1); + DP_TBFLAG_ANY(flags, BE_DATA, 1); } if (cpu_isar_feature(aa64_pauth, env_archcpu(env))) { @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, * The decision of which action to take is left to a helper. */ if (sctlr & (SCTLR_EnIA | SCTLR_EnIB | SCTLR_EnDA | SCTLR_EnDB)) { - flags = FIELD_DP32(flags, TBFLAG_A64, PAUTH_ACTIVE, 1); + DP_TBFLAG_A64(flags, PAUTH_ACTIVE, 1); } } if (cpu_isar_feature(aa64_bti, env_archcpu(env))) { /* Note that SCTLR_EL[23].BT == SCTLR_BT1. */ if (sctlr & (el == 0 ? SCTLR_BT0 : SCTLR_BT1)) { - flags = FIELD_DP32(flags, TBFLAG_A64, BT, 1); + DP_TBFLAG_A64(flags, BT, 1); } } @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, case ARMMMUIdx_SE10_1: case ARMMMUIdx_SE10_1_PAN: /* TODO: ARMv8.3-NV */ - flags = FIELD_DP32(flags, TBFLAG_A64, UNPRIV, 1); + DP_TBFLAG_A64(flags, UNPRIV, 1); break; case ARMMMUIdx_E20_2: case ARMMMUIdx_E20_2_PAN: @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, * gated by HCR_EL2.<E2H,TGE> == '11', and so is LDTR. */ if (env->cp15.hcr_el2 & HCR_TGE) { - flags = FIELD_DP32(flags, TBFLAG_A64, UNPRIV, 1); + DP_TBFLAG_A64(flags, UNPRIV, 1); } break; default: @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, * 4) If no Allocation Tag Access, then all accesses are Unchecked. */ if (allocation_tag_access_enabled(env, el, sctlr)) { - flags = FIELD_DP32(flags, TBFLAG_A64, ATA, 1); + DP_TBFLAG_A64(flags, ATA, 1); if (tbid && !(env->pstate & PSTATE_TCO) && (sctlr & (el == 0 ? SCTLR_TCF0 : SCTLR_TCF))) { - flags = FIELD_DP32(flags, TBFLAG_A64, MTE_ACTIVE, 1); + DP_TBFLAG_A64(flags, MTE_ACTIVE, 1); } } /* And again for unprivileged accesses, if required. */ - if (FIELD_EX32(flags, TBFLAG_A64, UNPRIV) + if (EX_TBFLAG_A64(flags, UNPRIV) && tbid && !(env->pstate & PSTATE_TCO) && (sctlr & SCTLR_TCF0) && allocation_tag_access_enabled(env, 0, sctlr)) { - flags = FIELD_DP32(flags, TBFLAG_A64, MTE0_ACTIVE, 1); + DP_TBFLAG_A64(flags, MTE0_ACTIVE, 1); } /* Cache TCMA as well as TBI. */ - flags = FIELD_DP32(flags, TBFLAG_A64, TCMA, - aa64_va_parameter_tcma(tcr, mmu_idx)); + DP_TBFLAG_A64(flags, TCMA, aa64_va_parameter_tcma(tcr, mmu_idx)); } return rebuild_hflags_common(env, fp_el, mmu_idx, flags); @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, *cs_base = 0; assert_hflags_rebuild_correctly(env); - if (FIELD_EX32(flags, TBFLAG_ANY, AARCH64_STATE)) { + if (EX_TBFLAG_ANY(flags, AARCH64_STATE)) { *pc = env->pc; if (cpu_isar_feature(aa64_bti, env_archcpu(env))) { - flags = FIELD_DP32(flags, TBFLAG_A64, BTYPE, env->btype); + DP_TBFLAG_A64(flags, BTYPE, env->btype); } } else { *pc = env->regs[15]; @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, if (arm_feature(env, ARM_FEATURE_M_SECURITY) && FIELD_EX32(env->v7m.fpccr[M_REG_S], V7M_FPCCR, S) != env->v7m.secure) { - flags = FIELD_DP32(flags, TBFLAG_M32, FPCCR_S_WRONG, 1); + DP_TBFLAG_M32(flags, FPCCR_S_WRONG, 1); } if ((env->v7m.fpccr[env->v7m.secure] & R_V7M_FPCCR_ASPEN_MASK) && @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, * active FP context; we must create a new FP context before * executing any FP insn. */ - flags = FIELD_DP32(flags, TBFLAG_M32, NEW_FP_CTXT_NEEDED, 1); + DP_TBFLAG_M32(flags, NEW_FP_CTXT_NEEDED, 1); } bool is_secure = env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_S_MASK; if (env->v7m.fpccr[is_secure] & R_V7M_FPCCR_LSPACT_MASK) { - flags = FIELD_DP32(flags, TBFLAG_M32, LSPACT, 1); + DP_TBFLAG_M32(flags, LSPACT, 1); } } else { /* @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, * Note that VECLEN+VECSTRIDE are RES0 for M-profile. */ if (arm_feature(env, ARM_FEATURE_XSCALE)) { - flags = FIELD_DP32(flags, TBFLAG_A32, - XSCALE_CPAR, env->cp15.c15_cpar); + DP_TBFLAG_A32(flags, XSCALE_CPAR, env->cp15.c15_cpar); } else { - flags = FIELD_DP32(flags, TBFLAG_A32, VECLEN, - env->vfp.vec_len); - flags = FIELD_DP32(flags, TBFLAG_A32, VECSTRIDE, - env->vfp.vec_stride); + DP_TBFLAG_A32(flags, VECLEN, env->vfp.vec_len); + DP_TBFLAG_A32(flags, VECSTRIDE, env->vfp.vec_stride); } if (env->vfp.xregs[ARM_VFP_FPEXC] & (1 << 30)) { - flags = FIELD_DP32(flags, TBFLAG_A32, VFPEN, 1); + DP_TBFLAG_A32(flags, VFPEN, 1); } } - flags = FIELD_DP32(flags, TBFLAG_AM32, THUMB, env->thumb); - flags = FIELD_DP32(flags, TBFLAG_AM32, CONDEXEC, env->condexec_bits); + DP_TBFLAG_AM32(flags, THUMB, env->thumb); + DP_TBFLAG_AM32(flags, CONDEXEC, env->condexec_bits); } /* @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, * 1 1 Active-not-pending * SS_ACTIVE is set in hflags; PSTATE__SS is computed every TB. */ - if (FIELD_EX32(flags, TBFLAG_ANY, SS_ACTIVE) && - (env->pstate & PSTATE_SS)) { - flags = FIELD_DP32(flags, TBFLAG_ANY, PSTATE__SS, 1); + if (EX_TBFLAG_ANY(flags, SS_ACTIVE) && (env->pstate & PSTATE_SS)) { + DP_TBFLAG_ANY(flags, PSTATE__SS, 1); } *pflags = flags; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, !arm_el_is_aa64(env, 3); dc->thumb = 0; dc->sctlr_b = 0; - dc->be_data = FIELD_EX32(tb_flags, TBFLAG_ANY, BE_DATA) ? MO_BE : MO_LE; + dc->be_data = EX_TBFLAG_ANY(tb_flags, BE_DATA) ? MO_BE : MO_LE; dc->condexec_mask = 0; dc->condexec_cond = 0; - core_mmu_idx = FIELD_EX32(tb_flags, TBFLAG_ANY, MMUIDX); + core_mmu_idx = EX_TBFLAG_ANY(tb_flags, MMUIDX); dc->mmu_idx = core_to_aa64_mmu_idx(core_mmu_idx); - dc->tbii = FIELD_EX32(tb_flags, TBFLAG_A64, TBII); - dc->tbid = FIELD_EX32(tb_flags, TBFLAG_A64, TBID); - dc->tcma = FIELD_EX32(tb_flags, TBFLAG_A64, TCMA); + dc->tbii = EX_TBFLAG_A64(tb_flags, TBII); + dc->tbid = EX_TBFLAG_A64(tb_flags, TBID); + dc->tcma = EX_TBFLAG_A64(tb_flags, TCMA); dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx); #if !defined(CONFIG_USER_ONLY) dc->user = (dc->current_el == 0); #endif - dc->fp_excp_el = FIELD_EX32(tb_flags, TBFLAG_ANY, FPEXC_EL); - dc->sve_excp_el = FIELD_EX32(tb_flags, TBFLAG_A64, SVEEXC_EL); - dc->sve_len = (FIELD_EX32(tb_flags, TBFLAG_A64, ZCR_LEN) + 1) * 16; - dc->pauth_active = FIELD_EX32(tb_flags, TBFLAG_A64, PAUTH_ACTIVE); - dc->bt = FIELD_EX32(tb_flags, TBFLAG_A64, BT); - dc->btype = FIELD_EX32(tb_flags, TBFLAG_A64, BTYPE); - dc->unpriv = FIELD_EX32(tb_flags, TBFLAG_A64, UNPRIV); - dc->ata = FIELD_EX32(tb_flags, TBFLAG_A64, ATA); - dc->mte_active[0] = FIELD_EX32(tb_flags, TBFLAG_A64, MTE_ACTIVE); - dc->mte_active[1] = FIELD_EX32(tb_flags, TBFLAG_A64, MTE0_ACTIVE); + dc->fp_excp_el = EX_TBFLAG_ANY(tb_flags, FPEXC_EL); + dc->sve_excp_el = EX_TBFLAG_A64(tb_flags, SVEEXC_EL); + dc->sve_len = (EX_TBFLAG_A64(tb_flags, ZCR_LEN) + 1) * 16; + dc->pauth_active = EX_TBFLAG_A64(tb_flags, PAUTH_ACTIVE); + dc->bt = EX_TBFLAG_A64(tb_flags, BT); + dc->btype = EX_TBFLAG_A64(tb_flags, BTYPE); + dc->unpriv = EX_TBFLAG_A64(tb_flags, UNPRIV); + dc->ata = EX_TBFLAG_A64(tb_flags, ATA); + dc->mte_active[0] = EX_TBFLAG_A64(tb_flags, MTE_ACTIVE); + dc->mte_active[1] = EX_TBFLAG_A64(tb_flags, MTE0_ACTIVE); dc->vec_len = 0; dc->vec_stride = 0; dc->cp_regs = arm_cpu->cp_regs; @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, * emit code to generate a software step exception * end the TB */ - dc->ss_active = FIELD_EX32(tb_flags, TBFLAG_ANY, SS_ACTIVE); - dc->pstate_ss = FIELD_EX32(tb_flags, TBFLAG_ANY, PSTATE__SS); + dc->ss_active = EX_TBFLAG_ANY(tb_flags, SS_ACTIVE); + dc->pstate_ss = EX_TBFLAG_ANY(tb_flags, PSTATE__SS); dc->is_ldex = false; - dc->debug_target_el = FIELD_EX32(tb_flags, TBFLAG_ANY, DEBUG_TARGET_EL); + dc->debug_target_el = EX_TBFLAG_ANY(tb_flags, DEBUG_TARGET_EL); /* Bound the number of insns to execute to those left on the page. */ bound = -(dc->base.pc_first | TARGET_PAGE_MASK) / 4; diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) */ dc->secure_routed_to_el3 = arm_feature(env, ARM_FEATURE_EL3) && !arm_el_is_aa64(env, 3); - dc->thumb = FIELD_EX32(tb_flags, TBFLAG_AM32, THUMB); - dc->be_data = FIELD_EX32(tb_flags, TBFLAG_ANY, BE_DATA) ? MO_BE : MO_LE; - condexec = FIELD_EX32(tb_flags, TBFLAG_AM32, CONDEXEC); + dc->thumb = EX_TBFLAG_AM32(tb_flags, THUMB); + dc->be_data = EX_TBFLAG_ANY(tb_flags, BE_DATA) ? MO_BE : MO_LE; + condexec = EX_TBFLAG_AM32(tb_flags, CONDEXEC); dc->condexec_mask = (condexec & 0xf) << 1; dc->condexec_cond = condexec >> 4; - core_mmu_idx = FIELD_EX32(tb_flags, TBFLAG_ANY, MMUIDX); + core_mmu_idx = EX_TBFLAG_ANY(tb_flags, MMUIDX); dc->mmu_idx = core_to_arm_mmu_idx(env, core_mmu_idx); dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx); #if !defined(CONFIG_USER_ONLY) dc->user = (dc->current_el == 0); #endif - dc->fp_excp_el = FIELD_EX32(tb_flags, TBFLAG_ANY, FPEXC_EL); + dc->fp_excp_el = EX_TBFLAG_ANY(tb_flags, FPEXC_EL); if (arm_feature(env, ARM_FEATURE_M)) { dc->vfp_enabled = 1; dc->be_data = MO_TE; - dc->v7m_handler_mode = FIELD_EX32(tb_flags, TBFLAG_M32, HANDLER); + dc->v7m_handler_mode = EX_TBFLAG_M32(tb_flags, HANDLER); dc->v8m_secure = arm_feature(env, ARM_FEATURE_M_SECURITY) && regime_is_secure(env, dc->mmu_idx); - dc->v8m_stackcheck = FIELD_EX32(tb_flags, TBFLAG_M32, STACKCHECK); - dc->v8m_fpccr_s_wrong = - FIELD_EX32(tb_flags, TBFLAG_M32, FPCCR_S_WRONG); + dc->v8m_stackcheck = EX_TBFLAG_M32(tb_flags, STACKCHECK); + dc->v8m_fpccr_s_wrong = EX_TBFLAG_M32(tb_flags, FPCCR_S_WRONG); dc->v7m_new_fp_ctxt_needed = - FIELD_EX32(tb_flags, TBFLAG_M32, NEW_FP_CTXT_NEEDED); - dc->v7m_lspact = FIELD_EX32(tb_flags, TBFLAG_M32, LSPACT); + EX_TBFLAG_M32(tb_flags, NEW_FP_CTXT_NEEDED); + dc->v7m_lspact = EX_TBFLAG_M32(tb_flags, LSPACT); } else { - dc->be_data = - FIELD_EX32(tb_flags, TBFLAG_ANY, BE_DATA) ? MO_BE : MO_LE; - dc->debug_target_el = - FIELD_EX32(tb_flags, TBFLAG_ANY, DEBUG_TARGET_EL); - dc->sctlr_b = FIELD_EX32(tb_flags, TBFLAG_A32, SCTLR__B); - dc->hstr_active = FIELD_EX32(tb_flags, TBFLAG_A32, HSTR_ACTIVE); - dc->ns = FIELD_EX32(tb_flags, TBFLAG_A32, NS); - dc->vfp_enabled = FIELD_EX32(tb_flags, TBFLAG_A32, VFPEN); + dc->debug_target_el = EX_TBFLAG_ANY(tb_flags, DEBUG_TARGET_EL); + dc->sctlr_b = EX_TBFLAG_A32(tb_flags, SCTLR__B); + dc->hstr_active = EX_TBFLAG_A32(tb_flags, HSTR_ACTIVE); + dc->ns = EX_TBFLAG_A32(tb_flags, NS); + dc->vfp_enabled = EX_TBFLAG_A32(tb_flags, VFPEN); if (arm_feature(env, ARM_FEATURE_XSCALE)) { - dc->c15_cpar = FIELD_EX32(tb_flags, TBFLAG_A32, XSCALE_CPAR); + dc->c15_cpar = EX_TBFLAG_A32(tb_flags, XSCALE_CPAR); } else { - dc->vec_len = FIELD_EX32(tb_flags, TBFLAG_A32, VECLEN); - dc->vec_stride = FIELD_EX32(tb_flags, TBFLAG_A32, VECSTRIDE); + dc->vec_len = EX_TBFLAG_A32(tb_flags, VECLEN); + dc->vec_stride = EX_TBFLAG_A32(tb_flags, VECSTRIDE); } } dc->cp_regs = cpu->cp_regs; @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) * emit code to generate a software step exception * end the TB */ - dc->ss_active = FIELD_EX32(tb_flags, TBFLAG_ANY, SS_ACTIVE); - dc->pstate_ss = FIELD_EX32(tb_flags, TBFLAG_ANY, PSTATE__SS); + dc->ss_active = EX_TBFLAG_ANY(tb_flags, SS_ACTIVE); + dc->pstate_ss = EX_TBFLAG_ANY(tb_flags, PSTATE__SS); dc->is_ldex = false; dc->page_start = dc->base.pc_first & TARGET_PAGE_MASK; @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb, int max_insns) DisasContext dc = { }; const TranslatorOps *ops = &arm_translator_ops; - if (FIELD_EX32(tb->flags, TBFLAG_AM32, THUMB)) { + if (EX_TBFLAG_AM32(tb->flags, THUMB)) { ops = &thumb_translator_ops; } #ifdef TARGET_AARCH64 - if (FIELD_EX32(tb->flags, TBFLAG_ANY, AARCH64_STATE)) { + if (EX_TBFLAG_ANY(tb->flags, AARCH64_STATE)) { ops = &aarch64_translator_ops; } #endif -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> In preparation for splitting tb->flags across multiple fields, introduce a structure to hold the value(s). So far this only migrates the one uint32_t and fixes all of the places that require adjustment to match. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 26 ++++++++++++--------- target/arm/translate.h | 11 +++++++++ target/arm/helper.c | 48 +++++++++++++++++++++----------------- target/arm/translate-a64.c | 2 +- target/arm/translate.c | 7 +++--- 5 files changed, 57 insertions(+), 37 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct ARMPACKey { } ARMPACKey; #endif +/* See the commentary above the TBFLAG field definitions. */ +typedef struct CPUARMTBFlags { + uint32_t flags; +} CPUARMTBFlags; typedef struct CPUARMState { /* Regs for current mode. */ @@ -XXX,XX +XXX,XX @@ typedef struct CPUARMState { uint32_t aarch64; /* 1 if CPU is in aarch64 state; inverse of PSTATE.nRW */ /* Cached TBFLAGS state. See below for which bits are included. */ - uint32_t hflags; + CPUARMTBFlags hflags; /* Frequently accessed CPSR bits are stored separately for efficiency. This contains all the other bits. Use cpsr_{read,write} to access @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, MTE0_ACTIVE, 19, 1) * Helpers for using the above. */ #define DP_TBFLAG_ANY(DST, WHICH, VAL) \ - (DST = FIELD_DP32(DST, TBFLAG_ANY, WHICH, VAL)) + (DST.flags = FIELD_DP32(DST.flags, TBFLAG_ANY, WHICH, VAL)) #define DP_TBFLAG_A64(DST, WHICH, VAL) \ - (DST = FIELD_DP32(DST, TBFLAG_A64, WHICH, VAL)) + (DST.flags = FIELD_DP32(DST.flags, TBFLAG_A64, WHICH, VAL)) #define DP_TBFLAG_A32(DST, WHICH, VAL) \ - (DST = FIELD_DP32(DST, TBFLAG_A32, WHICH, VAL)) + (DST.flags = FIELD_DP32(DST.flags, TBFLAG_A32, WHICH, VAL)) #define DP_TBFLAG_M32(DST, WHICH, VAL) \ - (DST = FIELD_DP32(DST, TBFLAG_M32, WHICH, VAL)) + (DST.flags = FIELD_DP32(DST.flags, TBFLAG_M32, WHICH, VAL)) #define DP_TBFLAG_AM32(DST, WHICH, VAL) \ - (DST = FIELD_DP32(DST, TBFLAG_AM32, WHICH, VAL)) + (DST.flags = FIELD_DP32(DST.flags, TBFLAG_AM32, WHICH, VAL)) -#define EX_TBFLAG_ANY(IN, WHICH) FIELD_EX32(IN, TBFLAG_ANY, WHICH) -#define EX_TBFLAG_A64(IN, WHICH) FIELD_EX32(IN, TBFLAG_A64, WHICH) -#define EX_TBFLAG_A32(IN, WHICH) FIELD_EX32(IN, TBFLAG_A32, WHICH) -#define EX_TBFLAG_M32(IN, WHICH) FIELD_EX32(IN, TBFLAG_M32, WHICH) -#define EX_TBFLAG_AM32(IN, WHICH) FIELD_EX32(IN, TBFLAG_AM32, WHICH) +#define EX_TBFLAG_ANY(IN, WHICH) FIELD_EX32(IN.flags, TBFLAG_ANY, WHICH) +#define EX_TBFLAG_A64(IN, WHICH) FIELD_EX32(IN.flags, TBFLAG_A64, WHICH) +#define EX_TBFLAG_A32(IN, WHICH) FIELD_EX32(IN.flags, TBFLAG_A32, WHICH) +#define EX_TBFLAG_M32(IN, WHICH) FIELD_EX32(IN.flags, TBFLAG_M32, WHICH) +#define EX_TBFLAG_AM32(IN, WHICH) FIELD_EX32(IN.flags, TBFLAG_AM32, WHICH) /** * cpu_mmu_index: diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); +/** + * arm_tbflags_from_tb: + * @tb: the TranslationBlock + * + * Extract the flag values from @tb. + */ +static inline CPUARMTBFlags arm_tbflags_from_tb(const TranslationBlock *tb) +{ + return (CPUARMTBFlags){ tb->flags }; +} + /* * Enum for argument to fpstatus_ptr(). */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env) } #endif -static uint32_t rebuild_hflags_common(CPUARMState *env, int fp_el, - ARMMMUIdx mmu_idx, uint32_t flags) +static CPUARMTBFlags rebuild_hflags_common(CPUARMState *env, int fp_el, + ARMMMUIdx mmu_idx, + CPUARMTBFlags flags) { DP_TBFLAG_ANY(flags, FPEXC_EL, fp_el); DP_TBFLAG_ANY(flags, MMUIDX, arm_to_core_mmu_idx(mmu_idx)); @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_common(CPUARMState *env, int fp_el, return flags; } -static uint32_t rebuild_hflags_common_32(CPUARMState *env, int fp_el, - ARMMMUIdx mmu_idx, uint32_t flags) +static CPUARMTBFlags rebuild_hflags_common_32(CPUARMState *env, int fp_el, + ARMMMUIdx mmu_idx, + CPUARMTBFlags flags) { bool sctlr_b = arm_sctlr_b(env); @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_common_32(CPUARMState *env, int fp_el, return rebuild_hflags_common(env, fp_el, mmu_idx, flags); } -static uint32_t rebuild_hflags_m32(CPUARMState *env, int fp_el, - ARMMMUIdx mmu_idx) +static CPUARMTBFlags rebuild_hflags_m32(CPUARMState *env, int fp_el, + ARMMMUIdx mmu_idx) { - uint32_t flags = 0; + CPUARMTBFlags flags = {}; if (arm_v7m_is_handler_mode(env)) { DP_TBFLAG_M32(flags, HANDLER, 1); @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_m32(CPUARMState *env, int fp_el, return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); } -static uint32_t rebuild_hflags_aprofile(CPUARMState *env) +static CPUARMTBFlags rebuild_hflags_aprofile(CPUARMState *env) { - int flags = 0; + CPUARMTBFlags flags = {}; DP_TBFLAG_ANY(flags, DEBUG_TARGET_EL, arm_debug_target_el(env)); return flags; } -static uint32_t rebuild_hflags_a32(CPUARMState *env, int fp_el, - ARMMMUIdx mmu_idx) +static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el, + ARMMMUIdx mmu_idx) { - uint32_t flags = rebuild_hflags_aprofile(env); + CPUARMTBFlags flags = rebuild_hflags_aprofile(env); if (arm_el_is_aa64(env, 1)) { DP_TBFLAG_A32(flags, VFPEN, 1); @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_a32(CPUARMState *env, int fp_el, return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); } -static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, - ARMMMUIdx mmu_idx) +static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, + ARMMMUIdx mmu_idx) { - uint32_t flags = rebuild_hflags_aprofile(env); + CPUARMTBFlags flags = rebuild_hflags_aprofile(env); ARMMMUIdx stage1 = stage_1_mmu_idx(mmu_idx); uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; uint64_t sctlr; @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, return rebuild_hflags_common(env, fp_el, mmu_idx, flags); } -static uint32_t rebuild_hflags_internal(CPUARMState *env) +static CPUARMTBFlags rebuild_hflags_internal(CPUARMState *env) { int el = arm_current_el(env); int fp_el = fp_exception_el(env, el); @@ -XXX,XX +XXX,XX @@ void HELPER(rebuild_hflags_m32_newel)(CPUARMState *env) int el = arm_current_el(env); int fp_el = fp_exception_el(env, el); ARMMMUIdx mmu_idx = arm_mmu_idx_el(env, el); + env->hflags = rebuild_hflags_m32(env, fp_el, mmu_idx); } @@ -XXX,XX +XXX,XX @@ void HELPER(rebuild_hflags_a64)(CPUARMState *env, int el) static inline void assert_hflags_rebuild_correctly(CPUARMState *env) { #ifdef CONFIG_DEBUG_TCG - uint32_t env_flags_current = env->hflags; - uint32_t env_flags_rebuilt = rebuild_hflags_internal(env); + CPUARMTBFlags c = env->hflags; + CPUARMTBFlags r = rebuild_hflags_internal(env); - if (unlikely(env_flags_current != env_flags_rebuilt)) { + if (unlikely(c.flags != r.flags)) { fprintf(stderr, "TCG hflags mismatch (current:0x%08x rebuilt:0x%08x)\n", - env_flags_current, env_flags_rebuilt); + c.flags, r.flags); abort(); } #endif @@ -XXX,XX +XXX,XX @@ static inline void assert_hflags_rebuild_correctly(CPUARMState *env) void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *pflags) { - uint32_t flags = env->hflags; + CPUARMTBFlags flags; *cs_base = 0; assert_hflags_rebuild_correctly(env); + flags = env->hflags; if (EX_TBFLAG_ANY(flags, AARCH64_STATE)) { *pc = env->pc; @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, DP_TBFLAG_ANY(flags, PSTATE__SS, 1); } - *pflags = flags; + *pflags = flags.flags; } #ifdef TARGET_AARCH64 diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, DisasContext *dc = container_of(dcbase, DisasContext, base); CPUARMState *env = cpu->env_ptr; ARMCPU *arm_cpu = env_archcpu(env); - uint32_t tb_flags = dc->base.tb->flags; + CPUARMTBFlags tb_flags = arm_tbflags_from_tb(dc->base.tb); int bound, core_mmu_idx; dc->isar = &arm_cpu->isar; diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) DisasContext *dc = container_of(dcbase, DisasContext, base); CPUARMState *env = cs->env_ptr; ARMCPU *cpu = env_archcpu(env); - uint32_t tb_flags = dc->base.tb->flags; + CPUARMTBFlags tb_flags = arm_tbflags_from_tb(dc->base.tb); uint32_t condexec, core_mmu_idx; dc->isar = &cpu->isar; @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb, int max_insns) { DisasContext dc = { }; const TranslatorOps *ops = &arm_translator_ops; + CPUARMTBFlags tb_flags = arm_tbflags_from_tb(tb); - if (EX_TBFLAG_AM32(tb->flags, THUMB)) { + if (EX_TBFLAG_AM32(tb_flags, THUMB)) { ops = &thumb_translator_ops; } #ifdef TARGET_AARCH64 - if (EX_TBFLAG_ANY(tb->flags, AARCH64_STATE)) { + if (EX_TBFLAG_ANY(tb_flags, AARCH64_STATE)) { ops = &aarch64_translator_ops; } #endif -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Now that we have all of the proper macros defined, expanding the CPUARMTBFlags structure and populating the two TB fields is relatively simple. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 49 ++++++++++++++++++++++++------------------ target/arm/translate.h | 2 +- target/arm/helper.c | 10 +++++---- 3 files changed, 35 insertions(+), 26 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct ARMPACKey { /* See the commentary above the TBFLAG field definitions. */ typedef struct CPUARMTBFlags { uint32_t flags; + target_ulong flags2; } CPUARMTBFlags; typedef struct CPUARMState { @@ -XXX,XX +XXX,XX @@ typedef ARMCPU ArchCPU; #include "exec/cpu-all.h" /* - * Bit usage in the TB flags field: bit 31 indicates whether we are - * in 32 or 64 bit mode. The meaning of the other bits depends on that. - * We put flags which are shared between 32 and 64 bit mode at the top - * of the word, and flags which apply to only one mode at the bottom. + * We have more than 32-bits worth of state per TB, so we split the data + * between tb->flags and tb->cs_base, which is otherwise unused for ARM. + * We collect these two parts in CPUARMTBFlags where they are named + * flags and flags2 respectively. * - * 31 20 18 14 9 0 - * +--------------+-----+-----+----------+--------------+ - * | | | TBFLAG_A32 | | - * | | +-----+----------+ TBFLAG_AM32 | - * | TBFLAG_ANY | |TBFLAG_M32| | - * | +-----------+----------+--------------| - * | | TBFLAG_A64 | - * +--------------+-------------------------------------+ - * 31 20 0 + * The flags that are shared between all execution modes, TBFLAG_ANY, + * are stored in flags. The flags that are specific to a given mode + * are stores in flags2. Since cs_base is sized on the configured + * address size, flags2 always has 64-bits for A64, and a minimum of + * 32-bits for A32 and M32. + * + * The bits for 32-bit A-profile and M-profile partially overlap: + * + * 18 9 0 + * +----------------+--------------+ + * | TBFLAG_A32 | | + * +-----+----------+ TBFLAG_AM32 | + * | |TBFLAG_M32| | + * +-----+----------+--------------+ + * 14 9 0 * * Unless otherwise noted, these bits are cached in env->hflags. */ @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, MTE0_ACTIVE, 19, 1) #define DP_TBFLAG_ANY(DST, WHICH, VAL) \ (DST.flags = FIELD_DP32(DST.flags, TBFLAG_ANY, WHICH, VAL)) #define DP_TBFLAG_A64(DST, WHICH, VAL) \ - (DST.flags = FIELD_DP32(DST.flags, TBFLAG_A64, WHICH, VAL)) + (DST.flags2 = FIELD_DP32(DST.flags2, TBFLAG_A64, WHICH, VAL)) #define DP_TBFLAG_A32(DST, WHICH, VAL) \ - (DST.flags = FIELD_DP32(DST.flags, TBFLAG_A32, WHICH, VAL)) + (DST.flags2 = FIELD_DP32(DST.flags2, TBFLAG_A32, WHICH, VAL)) #define DP_TBFLAG_M32(DST, WHICH, VAL) \ - (DST.flags = FIELD_DP32(DST.flags, TBFLAG_M32, WHICH, VAL)) + (DST.flags2 = FIELD_DP32(DST.flags2, TBFLAG_M32, WHICH, VAL)) #define DP_TBFLAG_AM32(DST, WHICH, VAL) \ - (DST.flags = FIELD_DP32(DST.flags, TBFLAG_AM32, WHICH, VAL)) + (DST.flags2 = FIELD_DP32(DST.flags2, TBFLAG_AM32, WHICH, VAL)) #define EX_TBFLAG_ANY(IN, WHICH) FIELD_EX32(IN.flags, TBFLAG_ANY, WHICH) -#define EX_TBFLAG_A64(IN, WHICH) FIELD_EX32(IN.flags, TBFLAG_A64, WHICH) -#define EX_TBFLAG_A32(IN, WHICH) FIELD_EX32(IN.flags, TBFLAG_A32, WHICH) -#define EX_TBFLAG_M32(IN, WHICH) FIELD_EX32(IN.flags, TBFLAG_M32, WHICH) -#define EX_TBFLAG_AM32(IN, WHICH) FIELD_EX32(IN.flags, TBFLAG_AM32, WHICH) +#define EX_TBFLAG_A64(IN, WHICH) FIELD_EX32(IN.flags2, TBFLAG_A64, WHICH) +#define EX_TBFLAG_A32(IN, WHICH) FIELD_EX32(IN.flags2, TBFLAG_A32, WHICH) +#define EX_TBFLAG_M32(IN, WHICH) FIELD_EX32(IN.flags2, TBFLAG_M32, WHICH) +#define EX_TBFLAG_AM32(IN, WHICH) FIELD_EX32(IN.flags2, TBFLAG_AM32, WHICH) /** * cpu_mmu_index: diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); */ static inline CPUARMTBFlags arm_tbflags_from_tb(const TranslationBlock *tb) { - return (CPUARMTBFlags){ tb->flags }; + return (CPUARMTBFlags){ tb->flags, tb->cs_base }; } /* diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static inline void assert_hflags_rebuild_correctly(CPUARMState *env) CPUARMTBFlags c = env->hflags; CPUARMTBFlags r = rebuild_hflags_internal(env); - if (unlikely(c.flags != r.flags)) { - fprintf(stderr, "TCG hflags mismatch (current:0x%08x rebuilt:0x%08x)\n", - c.flags, r.flags); + if (unlikely(c.flags != r.flags || c.flags2 != r.flags2)) { + fprintf(stderr, "TCG hflags mismatch " + "(current:(0x%08x,0x" TARGET_FMT_lx ")" + " rebuilt:(0x%08x,0x" TARGET_FMT_lx ")\n", + c.flags, c.flags2, r.flags, r.flags2); abort(); } #endif @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, { CPUARMTBFlags flags; - *cs_base = 0; assert_hflags_rebuild_correctly(env); flags = env->hflags; @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, } *pflags = flags.flags; + *cs_base = flags.flags2; } #ifdef TARGET_AARCH64 -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Now that these bits have been moved out of tb->flags, where TBFLAG_ANY was filling from the top, move AM32 to fill from the top, and A32 and M32 to fill from the bottom. This means fewer changes when adding new bits. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef ARMCPU ArchCPU; * * The bits for 32-bit A-profile and M-profile partially overlap: * - * 18 9 0 - * +----------------+--------------+ - * | TBFLAG_A32 | | - * +-----+----------+ TBFLAG_AM32 | - * | |TBFLAG_M32| | - * +-----+----------+--------------+ - * 14 9 0 + * 31 23 11 10 0 + * +-------------+----------+----------------+ + * | | | TBFLAG_A32 | + * | TBFLAG_AM32 | +-----+----------+ + * | | |TBFLAG_M32| + * +-------------+----------------+----------+ + * 31 23 5 4 0 * * Unless otherwise noted, these bits are cached in env->hflags. */ @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_ANY, DEBUG_TARGET_EL, 20, 2) /* * Bit usage when in AArch32 state, both A- and M-profile. */ -FIELD(TBFLAG_AM32, CONDEXEC, 0, 8) /* Not cached. */ -FIELD(TBFLAG_AM32, THUMB, 8, 1) /* Not cached. */ +FIELD(TBFLAG_AM32, CONDEXEC, 24, 8) /* Not cached. */ +FIELD(TBFLAG_AM32, THUMB, 23, 1) /* Not cached. */ /* * Bit usage when in AArch32 state, for A-profile only. */ -FIELD(TBFLAG_A32, VECLEN, 9, 3) /* Not cached. */ -FIELD(TBFLAG_A32, VECSTRIDE, 12, 2) /* Not cached. */ +FIELD(TBFLAG_A32, VECLEN, 0, 3) /* Not cached. */ +FIELD(TBFLAG_A32, VECSTRIDE, 3, 2) /* Not cached. */ /* * We store the bottom two bits of the CPAR as TB flags and handle * checks on the other bits at runtime. This shares the same bits as * VECSTRIDE, which is OK as no XScale CPU has VFP. * Not cached, because VECLEN+VECSTRIDE are not cached. */ -FIELD(TBFLAG_A32, XSCALE_CPAR, 12, 2) -FIELD(TBFLAG_A32, VFPEN, 14, 1) /* Partially cached, minus FPEXC. */ -FIELD(TBFLAG_A32, SCTLR__B, 15, 1) /* Cannot overlap with SCTLR_B */ -FIELD(TBFLAG_A32, HSTR_ACTIVE, 16, 1) +FIELD(TBFLAG_A32, XSCALE_CPAR, 5, 2) +FIELD(TBFLAG_A32, VFPEN, 7, 1) /* Partially cached, minus FPEXC. */ +FIELD(TBFLAG_A32, SCTLR__B, 8, 1) /* Cannot overlap with SCTLR_B */ +FIELD(TBFLAG_A32, HSTR_ACTIVE, 9, 1) /* * Indicates whether cp register reads and writes by guest code should access * the secure or nonsecure bank of banked registers; note that this is not * the same thing as the current security state of the processor! */ -FIELD(TBFLAG_A32, NS, 17, 1) +FIELD(TBFLAG_A32, NS, 10, 1) /* * Bit usage when in AArch32 state, for M-profile only. */ /* Handler (ie not Thread) mode */ -FIELD(TBFLAG_M32, HANDLER, 9, 1) +FIELD(TBFLAG_M32, HANDLER, 0, 1) /* Whether we should generate stack-limit checks */ -FIELD(TBFLAG_M32, STACKCHECK, 10, 1) +FIELD(TBFLAG_M32, STACKCHECK, 1, 1) /* Set if FPCCR.LSPACT is set */ -FIELD(TBFLAG_M32, LSPACT, 11, 1) /* Not cached. */ +FIELD(TBFLAG_M32, LSPACT, 2, 1) /* Not cached. */ /* Set if we must create a new FP context */ -FIELD(TBFLAG_M32, NEW_FP_CTXT_NEEDED, 12, 1) /* Not cached. */ +FIELD(TBFLAG_M32, NEW_FP_CTXT_NEEDED, 3, 1) /* Not cached. */ /* Set if FPCCR.S does not match current security state */ -FIELD(TBFLAG_M32, FPCCR_S_WRONG, 13, 1) /* Not cached. */ +FIELD(TBFLAG_M32, FPCCR_S_WRONG, 4, 1) /* Not cached. */ /* * Bit usage when in AArch64 state -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Now that other bits have been moved out of tb->flags, there's no point in filling from the top. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef ARMCPU ArchCPU; * * Unless otherwise noted, these bits are cached in env->hflags. */ -FIELD(TBFLAG_ANY, AARCH64_STATE, 31, 1) -FIELD(TBFLAG_ANY, SS_ACTIVE, 30, 1) -FIELD(TBFLAG_ANY, PSTATE__SS, 29, 1) /* Not cached. */ -FIELD(TBFLAG_ANY, BE_DATA, 28, 1) -FIELD(TBFLAG_ANY, MMUIDX, 24, 4) +FIELD(TBFLAG_ANY, AARCH64_STATE, 0, 1) +FIELD(TBFLAG_ANY, SS_ACTIVE, 1, 1) +FIELD(TBFLAG_ANY, PSTATE__SS, 2, 1) /* Not cached. */ +FIELD(TBFLAG_ANY, BE_DATA, 3, 1) +FIELD(TBFLAG_ANY, MMUIDX, 4, 4) /* Target EL if we take a floating-point-disabled exception */ -FIELD(TBFLAG_ANY, FPEXC_EL, 22, 2) +FIELD(TBFLAG_ANY, FPEXC_EL, 8, 2) /* For A-profile only, target EL for debug exceptions. */ -FIELD(TBFLAG_ANY, DEBUG_TARGET_EL, 20, 2) +FIELD(TBFLAG_ANY, DEBUG_TARGET_EL, 10, 2) /* * Bit usage when in AArch32 state, both A- and M-profile. -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Use this to signal when memory access alignment is required. This value comes from the CCR register for M-profile, and from the SCTLR register for A-profile. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 ++ target/arm/translate.h | 2 ++ target/arm/helper.c | 19 +++++++++++++++++-- target/arm/translate-a64.c | 1 + target/arm/translate.c | 7 +++---- 5 files changed, 25 insertions(+), 6 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_ANY, MMUIDX, 4, 4) FIELD(TBFLAG_ANY, FPEXC_EL, 8, 2) /* For A-profile only, target EL for debug exceptions. */ FIELD(TBFLAG_ANY, DEBUG_TARGET_EL, 10, 2) +/* Memory operations require alignment: SCTLR_ELx.A or CCR.UNALIGN_TRP */ +FIELD(TBFLAG_ANY, ALIGN_MEM, 12, 1) /* * Bit usage when in AArch32 state, both A- and M-profile. diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { bool bt; /* True if any CP15 access is trapped by HSTR_EL2 */ bool hstr_active; + /* True if memory operations require alignment */ + bool align_mem; /* * >= 0, a copy of PSTATE.BTYPE, which will be 0 without v8.5-BTI. * < 0, set by the current instruction. diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_m32(CPUARMState *env, int fp_el, ARMMMUIdx mmu_idx) { CPUARMTBFlags flags = {}; + uint32_t ccr = env->v7m.ccr[env->v7m.secure]; + + /* Without HaveMainExt, CCR.UNALIGN_TRP is RES1. */ + if (ccr & R_V7M_CCR_UNALIGN_TRP_MASK) { + DP_TBFLAG_ANY(flags, ALIGN_MEM, 1); + } if (arm_v7m_is_handler_mode(env)) { DP_TBFLAG_M32(flags, HANDLER, 1); @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_m32(CPUARMState *env, int fp_el, */ if (arm_feature(env, ARM_FEATURE_V8) && !((mmu_idx & ARM_MMU_IDX_M_NEGPRI) && - (env->v7m.ccr[env->v7m.secure] & R_V7M_CCR_STKOFHFNMIGN_MASK))) { + (ccr & R_V7M_CCR_STKOFHFNMIGN_MASK))) { DP_TBFLAG_M32(flags, STACKCHECK, 1); } @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el, ARMMMUIdx mmu_idx) { CPUARMTBFlags flags = rebuild_hflags_aprofile(env); + int el = arm_current_el(env); + + if (arm_sctlr(env, el) & SCTLR_A) { + DP_TBFLAG_ANY(flags, ALIGN_MEM, 1); + } if (arm_el_is_aa64(env, 1)) { DP_TBFLAG_A32(flags, VFPEN, 1); } - if (arm_current_el(env) < 2 && env->cp15.hstr_el2 && + if (el < 2 && env->cp15.hstr_el2 && (arm_hcr_el2_eff(env) & (HCR_E2H | HCR_TGE)) != (HCR_E2H | HCR_TGE)) { DP_TBFLAG_A32(flags, HSTR_ACTIVE, 1); } @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, sctlr = regime_sctlr(env, stage1); + if (sctlr & SCTLR_A) { + DP_TBFLAG_ANY(flags, ALIGN_MEM, 1); + } + if (arm_cpu_data_is_big_endian_a64(el, sctlr)) { DP_TBFLAG_ANY(flags, BE_DATA, 1); } diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->user = (dc->current_el == 0); #endif dc->fp_excp_el = EX_TBFLAG_ANY(tb_flags, FPEXC_EL); + dc->align_mem = EX_TBFLAG_ANY(tb_flags, ALIGN_MEM); dc->sve_excp_el = EX_TBFLAG_A64(tb_flags, SVEEXC_EL); dc->sve_len = (EX_TBFLAG_A64(tb_flags, ZCR_LEN) + 1) * 16; dc->pauth_active = EX_TBFLAG_A64(tb_flags, PAUTH_ACTIVE); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, { TCGv addr; - if (arm_dc_feature(s, ARM_FEATURE_M) && - !arm_dc_feature(s, ARM_FEATURE_M_MAIN)) { + if (s->align_mem) { opc |= MO_ALIGN; } @@ -XXX,XX +XXX,XX @@ static void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, { TCGv addr; - if (arm_dc_feature(s, ARM_FEATURE_M) && - !arm_dc_feature(s, ARM_FEATURE_M_MAIN)) { + if (s->align_mem) { opc |= MO_ALIGN; } @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) dc->user = (dc->current_el == 0); #endif dc->fp_excp_el = EX_TBFLAG_ANY(tb_flags, FPEXC_EL); + dc->align_mem = EX_TBFLAG_ANY(tb_flags, ALIGN_MEM); if (arm_feature(env, ARM_FEATURE_M)) { dc->vfp_enabled = 1; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Create a finalize_memop function that computes alignment and endianness and returns the final MemOp for the operation. Split out gen_aa32_{ld,st}_internal_i32 which bypasses any special handling of endianness or alignment. Adjust gen_aa32_{ld,st}_i32 so that s->be_data is not added by the callers. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 24 ++++++++ target/arm/translate.c | 100 +++++++++++++++++--------------- target/arm/translate-neon.c.inc | 9 +-- 3 files changed, 79 insertions(+), 54 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline TCGv_ptr fpstatus_ptr(ARMFPStatusFlavour flavour) return statusptr; } +/** + * finalize_memop: + * @s: DisasContext + * @opc: size+sign+align of the memory operation + * + * Build the complete MemOp for a memory operation, including alignment + * and endianness. + * + * If (op & MO_AMASK) then the operation already contains the required + * alignment, e.g. for AccType_ATOMIC. Otherwise, this an optionally + * unaligned operation, e.g. for AccType_NORMAL. + * + * In the latter case, there are configuration bits that require alignment, + * and this is applied here. Note that there is no way to indicate that + * no alignment should ever be enforced; this must be handled manually. + */ +static inline MemOp finalize_memop(DisasContext *s, MemOp opc) +{ + if (s->align_mem && !(opc & MO_AMASK)) { + opc |= MO_ALIGN; + } + return opc | s->be_data; +} + #endif /* TARGET_ARM_TRANSLATE_H */ diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void store_reg_from_load(DisasContext *s, int reg, TCGv_i32 var) #define IS_USER_ONLY 0 #endif -/* Abstractions of "generate code to do a guest load/store for +/* + * Abstractions of "generate code to do a guest load/store for * AArch32", where a vaddr is always 32 bits (and is zero * extended if we're a 64 bit core) and data is also * 32 bits unless specifically doing a 64 bit access. @@ -XXX,XX +XXX,XX @@ static inline void store_reg_from_load(DisasContext *s, int reg, TCGv_i32 var) * that the address argument is TCGv_i32 rather than TCGv. */ -static inline TCGv gen_aa32_addr(DisasContext *s, TCGv_i32 a32, MemOp op) +static TCGv gen_aa32_addr(DisasContext *s, TCGv_i32 a32, MemOp op) { TCGv addr = tcg_temp_new(); tcg_gen_extu_i32_tl(addr, a32); @@ -XXX,XX +XXX,XX @@ static inline TCGv gen_aa32_addr(DisasContext *s, TCGv_i32 a32, MemOp op) return addr; } +/* + * Internal routines are used for NEON cases where the endianness + * and/or alignment has already been taken into account and manipulated. + */ +static void gen_aa32_ld_internal_i32(DisasContext *s, TCGv_i32 val, + TCGv_i32 a32, int index, MemOp opc) +{ + TCGv addr = gen_aa32_addr(s, a32, opc); + tcg_gen_qemu_ld_i32(val, addr, index, opc); + tcg_temp_free(addr); +} + +static void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val, + TCGv_i32 a32, int index, MemOp opc) +{ + TCGv addr = gen_aa32_addr(s, a32, opc); + tcg_gen_qemu_st_i32(val, addr, index, opc); + tcg_temp_free(addr); +} + static void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, int index, MemOp opc) { - TCGv addr; - - if (s->align_mem) { - opc |= MO_ALIGN; - } - - addr = gen_aa32_addr(s, a32, opc); - tcg_gen_qemu_ld_i32(val, addr, index, opc); - tcg_temp_free(addr); + gen_aa32_ld_internal_i32(s, val, a32, index, finalize_memop(s, opc)); } static void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, int index, MemOp opc) { - TCGv addr; + gen_aa32_st_internal_i32(s, val, a32, index, finalize_memop(s, opc)); +} - if (s->align_mem) { - opc |= MO_ALIGN; +#define DO_GEN_LD(SUFF, OPC) \ + static inline void gen_aa32_ld##SUFF(DisasContext *s, TCGv_i32 val, \ + TCGv_i32 a32, int index) \ + { \ + gen_aa32_ld_i32(s, val, a32, index, OPC); \ } - addr = gen_aa32_addr(s, a32, opc); - tcg_gen_qemu_st_i32(val, addr, index, opc); - tcg_temp_free(addr); -} - -#define DO_GEN_LD(SUFF, OPC) \ -static inline void gen_aa32_ld##SUFF(DisasContext *s, TCGv_i32 val, \ - TCGv_i32 a32, int index) \ -{ \ - gen_aa32_ld_i32(s, val, a32, index, OPC | s->be_data); \ -} - -#define DO_GEN_ST(SUFF, OPC) \ -static inline void gen_aa32_st##SUFF(DisasContext *s, TCGv_i32 val, \ - TCGv_i32 a32, int index) \ -{ \ - gen_aa32_st_i32(s, val, a32, index, OPC | s->be_data); \ -} +#define DO_GEN_ST(SUFF, OPC) \ + static inline void gen_aa32_st##SUFF(DisasContext *s, TCGv_i32 val, \ + TCGv_i32 a32, int index) \ + { \ + gen_aa32_st_i32(s, val, a32, index, OPC); \ + } static inline void gen_aa32_frob64(DisasContext *s, TCGv_i64 val) { @@ -XXX,XX +XXX,XX @@ static bool op_load_rr(DisasContext *s, arg_ldst_rr *a, addr = op_addr_rr_pre(s, a); tmp = tcg_temp_new_i32(); - gen_aa32_ld_i32(s, tmp, addr, mem_idx, mop | s->be_data); + gen_aa32_ld_i32(s, tmp, addr, mem_idx, mop); disas_set_da_iss(s, mop, issinfo); /* @@ -XXX,XX +XXX,XX @@ static bool op_store_rr(DisasContext *s, arg_ldst_rr *a, addr = op_addr_rr_pre(s, a); tmp = load_reg(s, a->rt); - gen_aa32_st_i32(s, tmp, addr, mem_idx, mop | s->be_data); + gen_aa32_st_i32(s, tmp, addr, mem_idx, mop); disas_set_da_iss(s, mop, issinfo); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_LDRD_rr(DisasContext *s, arg_ldst_rr *a) addr = op_addr_rr_pre(s, a); tmp = tcg_temp_new_i32(); - gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data); + gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL); store_reg(s, a->rt, tmp); tcg_gen_addi_i32(addr, addr, 4); tmp = tcg_temp_new_i32(); - gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data); + gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL); store_reg(s, a->rt + 1, tmp); /* LDRD w/ base writeback is undefined if the registers overlap. */ @@ -XXX,XX +XXX,XX @@ static bool trans_STRD_rr(DisasContext *s, arg_ldst_rr *a) addr = op_addr_rr_pre(s, a); tmp = load_reg(s, a->rt); - gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data); + gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL); tcg_temp_free_i32(tmp); tcg_gen_addi_i32(addr, addr, 4); tmp = load_reg(s, a->rt + 1); - gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data); + gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL); tcg_temp_free_i32(tmp); op_addr_rr_post(s, a, addr, -4); @@ -XXX,XX +XXX,XX @@ static bool op_load_ri(DisasContext *s, arg_ldst_ri *a, addr = op_addr_ri_pre(s, a); tmp = tcg_temp_new_i32(); - gen_aa32_ld_i32(s, tmp, addr, mem_idx, mop | s->be_data); + gen_aa32_ld_i32(s, tmp, addr, mem_idx, mop); disas_set_da_iss(s, mop, issinfo); /* @@ -XXX,XX +XXX,XX @@ static bool op_store_ri(DisasContext *s, arg_ldst_ri *a, addr = op_addr_ri_pre(s, a); tmp = load_reg(s, a->rt); - gen_aa32_st_i32(s, tmp, addr, mem_idx, mop | s->be_data); + gen_aa32_st_i32(s, tmp, addr, mem_idx, mop); disas_set_da_iss(s, mop, issinfo); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool op_ldrd_ri(DisasContext *s, arg_ldst_ri *a, int rt2) addr = op_addr_ri_pre(s, a); tmp = tcg_temp_new_i32(); - gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data); + gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL); store_reg(s, a->rt, tmp); tcg_gen_addi_i32(addr, addr, 4); tmp = tcg_temp_new_i32(); - gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data); + gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL); store_reg(s, rt2, tmp); /* LDRD w/ base writeback is undefined if the registers overlap. */ @@ -XXX,XX +XXX,XX @@ static bool op_strd_ri(DisasContext *s, arg_ldst_ri *a, int rt2) addr = op_addr_ri_pre(s, a); tmp = load_reg(s, a->rt); - gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data); + gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL); tcg_temp_free_i32(tmp); tcg_gen_addi_i32(addr, addr, 4); tmp = load_reg(s, rt2); - gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | s->be_data); + gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL); tcg_temp_free_i32(tmp); op_addr_ri_post(s, a, addr, -4); @@ -XXX,XX +XXX,XX @@ static bool op_stl(DisasContext *s, arg_STL *a, MemOp mop) addr = load_reg(s, a->rn); tmp = load_reg(s, a->rt); tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); - gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), mop | s->be_data); + gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), mop); disas_set_da_iss(s, mop, a->rt | ISSIsAcqRel | ISSIsWrite); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool op_lda(DisasContext *s, arg_LDA *a, MemOp mop) addr = load_reg(s, a->rn); tmp = tcg_temp_new_i32(); - gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), mop | s->be_data); + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), mop); disas_set_da_iss(s, mop, a->rt | ISSIsAcqRel); tcg_temp_free_i32(addr); @@ -XXX,XX +XXX,XX @@ static bool op_tbranch(DisasContext *s, arg_tbranch *a, bool half) addr = load_reg(s, a->rn); tcg_gen_add_i32(addr, addr, tmp); - gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), - half ? MO_UW | s->be_data : MO_UB); + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), half ? MO_UW : MO_UB); tcg_temp_free_i32(addr); tcg_gen_add_i32(tmp, tmp, tmp); diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a) addr = tcg_temp_new_i32(); load_reg_var(s, addr, a->rn); for (reg = 0; reg < nregs; reg++) { - gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), - s->be_data | size); + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), size); if ((vd & 1) && vec_size == 16) { /* * We cannot write 16 bytes at once because the @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a) */ for (reg = 0; reg < nregs; reg++) { if (a->l) { - gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), - s->be_data | a->size); + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), a->size); neon_store_element(vd, a->reg_idx, a->size, tmp); } else { /* Store */ neon_load_element(tmp, vd, a->reg_idx, a->size); - gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), - s->be_data | a->size); + gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), a->size); } vd += a->stride; tcg_gen_addi_i32(addr, addr, 1 << a->size); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This is the only caller. Adjust some commentary to talk about SCTLR_B instead of the vanishing function. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 37 ++++++++++++++++--------------------- 1 file changed, 16 insertions(+), 21 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, gen_aa32_st_i32(s, val, a32, index, OPC); \ } -static inline void gen_aa32_frob64(DisasContext *s, TCGv_i64 val) -{ - /* Not needed for user-mode BE32, where we use MO_BE instead. */ - if (!IS_USER_ONLY && s->sctlr_b) { - tcg_gen_rotri_i64(val, val, 32); - } -} - static void gen_aa32_ld_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, int index, MemOp opc) { TCGv addr = gen_aa32_addr(s, a32, opc); tcg_gen_qemu_ld_i64(val, addr, index, opc); - gen_aa32_frob64(s, val); + + /* Not needed for user-mode BE32, where we use MO_BE instead. */ + if (!IS_USER_ONLY && s->sctlr_b) { + tcg_gen_rotri_i64(val, val, 32); + } + tcg_temp_free(addr); } @@ -XXX,XX +XXX,XX @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2, TCGv_i32 tmp2 = tcg_temp_new_i32(); TCGv_i64 t64 = tcg_temp_new_i64(); - /* For AArch32, architecturally the 32-bit word at the lowest + /* + * For AArch32, architecturally the 32-bit word at the lowest * address is always Rt and the one at addr+4 is Rt2, even if * the CPU is big-endian. That means we don't want to do a - * gen_aa32_ld_i64(), which invokes gen_aa32_frob64() as if - * for an architecturally 64-bit access, but instead do a - * 64-bit access using MO_BE if appropriate and then split - * the two halves. - * This only makes a difference for BE32 user-mode, where - * frob64() must not flip the two halves of the 64-bit data - * but this code must treat BE32 user-mode like BE32 system. + * gen_aa32_ld_i64(), which checks SCTLR_B as if for an + * architecturally 64-bit access, but instead do a 64-bit access + * using MO_BE if appropriate and then split the two halves. */ TCGv taddr = gen_aa32_addr(s, addr, opc); @@ -XXX,XX +XXX,XX @@ static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2, TCGv_i64 n64 = tcg_temp_new_i64(); t2 = load_reg(s, rt2); - /* For AArch32, architecturally the 32-bit word at the lowest + + /* + * For AArch32, architecturally the 32-bit word at the lowest * address is always Rt and the one at addr+4 is Rt2, even if * the CPU is big-endian. Since we're going to treat this as a * single 64-bit BE store, we need to put the two halves in the * opposite order for BE to LE, so that they end up in the right - * places. - * We don't want gen_aa32_frob64() because that does the wrong - * thing for BE32 usermode. + * places. We don't want gen_aa32_st_i64, because that checks + * SCTLR_B as if for an architectural 64-bit access. */ if (s->be_data == MO_BE) { tcg_gen_concat_i32_i64(n64, t2, t1); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Just because operating on a TCGv_i64 temporary does not mean that we're performing a 64-bit operation. Restrict the frobbing to actual 64-bit operations. This bug is not currently visible because all current users of these two functions always pass MO_64. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_aa32_ld_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, tcg_gen_qemu_ld_i64(val, addr, index, opc); /* Not needed for user-mode BE32, where we use MO_BE instead. */ - if (!IS_USER_ONLY && s->sctlr_b) { + if (!IS_USER_ONLY && s->sctlr_b && (opc & MO_SIZE) == MO_64) { tcg_gen_rotri_i64(val, val, 32); } @@ -XXX,XX +XXX,XX @@ static void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, TCGv addr = gen_aa32_addr(s, a32, opc); /* Not needed for user-mode BE32, where we use MO_BE instead. */ - if (!IS_USER_ONLY && s->sctlr_b) { + if (!IS_USER_ONLY && s->sctlr_b && (opc & MO_SIZE) == MO_64) { TCGv_i64 tmp = tcg_temp_new_i64(); tcg_gen_rotri_i64(tmp, val, 32); tcg_gen_qemu_st_i64(tmp, addr, index, opc); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Adjust the interface to match what has been done to the TCGv_i32 load/store functions. This is less obvious, because at present the only user of these functions, trans_VLDST_multiple, also wants to manipulate the endianness to speed up loading multiple bytes. Thus we retain an "internal" interface which is identical to the current gen_aa32_{ld,st}_i64 interface. The "new" interface will gain users as we remove the legacy interfaces, gen_aa32_ld64 and gen_aa32_st64. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 78 +++++++++++++++++++-------------- target/arm/translate-neon.c.inc | 6 ++- 2 files changed, 49 insertions(+), 35 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val, tcg_temp_free(addr); } +static void gen_aa32_ld_internal_i64(DisasContext *s, TCGv_i64 val, + TCGv_i32 a32, int index, MemOp opc) +{ + TCGv addr = gen_aa32_addr(s, a32, opc); + + tcg_gen_qemu_ld_i64(val, addr, index, opc); + + /* Not needed for user-mode BE32, where we use MO_BE instead. */ + if (!IS_USER_ONLY && s->sctlr_b && (opc & MO_SIZE) == MO_64) { + tcg_gen_rotri_i64(val, val, 32); + } + tcg_temp_free(addr); +} + +static void gen_aa32_st_internal_i64(DisasContext *s, TCGv_i64 val, + TCGv_i32 a32, int index, MemOp opc) +{ + TCGv addr = gen_aa32_addr(s, a32, opc); + + /* Not needed for user-mode BE32, where we use MO_BE instead. */ + if (!IS_USER_ONLY && s->sctlr_b && (opc & MO_SIZE) == MO_64) { + TCGv_i64 tmp = tcg_temp_new_i64(); + tcg_gen_rotri_i64(tmp, val, 32); + tcg_gen_qemu_st_i64(tmp, addr, index, opc); + tcg_temp_free_i64(tmp); + } else { + tcg_gen_qemu_st_i64(val, addr, index, opc); + } + tcg_temp_free(addr); +} + static void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, int index, MemOp opc) { @@ -XXX,XX +XXX,XX @@ static void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, gen_aa32_st_internal_i32(s, val, a32, index, finalize_memop(s, opc)); } +static void gen_aa32_ld_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, + int index, MemOp opc) +{ + gen_aa32_ld_internal_i64(s, val, a32, index, finalize_memop(s, opc)); +} + +static void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, + int index, MemOp opc) +{ + gen_aa32_st_internal_i64(s, val, a32, index, finalize_memop(s, opc)); +} + #define DO_GEN_LD(SUFF, OPC) \ static inline void gen_aa32_ld##SUFF(DisasContext *s, TCGv_i32 val, \ TCGv_i32 a32, int index) \ @@ -XXX,XX +XXX,XX @@ static void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, gen_aa32_st_i32(s, val, a32, index, OPC); \ } -static void gen_aa32_ld_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, - int index, MemOp opc) -{ - TCGv addr = gen_aa32_addr(s, a32, opc); - tcg_gen_qemu_ld_i64(val, addr, index, opc); - - /* Not needed for user-mode BE32, where we use MO_BE instead. */ - if (!IS_USER_ONLY && s->sctlr_b && (opc & MO_SIZE) == MO_64) { - tcg_gen_rotri_i64(val, val, 32); - } - - tcg_temp_free(addr); -} - static inline void gen_aa32_ld64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, int index) { - gen_aa32_ld_i64(s, val, a32, index, MO_Q | s->be_data); -} - -static void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, - int index, MemOp opc) -{ - TCGv addr = gen_aa32_addr(s, a32, opc); - - /* Not needed for user-mode BE32, where we use MO_BE instead. */ - if (!IS_USER_ONLY && s->sctlr_b && (opc & MO_SIZE) == MO_64) { - TCGv_i64 tmp = tcg_temp_new_i64(); - tcg_gen_rotri_i64(tmp, val, 32); - tcg_gen_qemu_st_i64(tmp, addr, index, opc); - tcg_temp_free_i64(tmp); - } else { - tcg_gen_qemu_st_i64(val, addr, index, opc); - } - tcg_temp_free(addr); + gen_aa32_ld_i64(s, val, a32, index, MO_Q); } static inline void gen_aa32_st64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, int index) { - gen_aa32_st_i64(s, val, a32, index, MO_Q | s->be_data); + gen_aa32_st_i64(s, val, a32, index, MO_Q); } DO_GEN_LD(8u, MO_UB) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a) int tt = a->vd + reg + spacing * xs; if (a->l) { - gen_aa32_ld_i64(s, tmp64, addr, mmu_idx, endian | size); + gen_aa32_ld_internal_i64(s, tmp64, addr, mmu_idx, + endian | size); neon_store_element64(tt, n, size, tmp64); } else { neon_load_element64(tmp64, tt, n, size); - gen_aa32_st_i64(s, tmp64, addr, mmu_idx, endian | size); + gen_aa32_st_internal_i64(s, tmp64, addr, mmu_idx, + endian | size); } tcg_gen_add_i32(addr, addr, tmp); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Buglink: https://bugs.launchpad.net/qemu/+bug/1905356 Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_LDRD_rr(DisasContext *s, arg_ldst_rr *a) addr = op_addr_rr_pre(s, a); tmp = tcg_temp_new_i32(); - gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL); + gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN); store_reg(s, a->rt, tmp); tcg_gen_addi_i32(addr, addr, 4); tmp = tcg_temp_new_i32(); - gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL); + gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN); store_reg(s, a->rt + 1, tmp); /* LDRD w/ base writeback is undefined if the registers overlap. */ @@ -XXX,XX +XXX,XX @@ static bool trans_STRD_rr(DisasContext *s, arg_ldst_rr *a) addr = op_addr_rr_pre(s, a); tmp = load_reg(s, a->rt); - gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL); + gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN); tcg_temp_free_i32(tmp); tcg_gen_addi_i32(addr, addr, 4); tmp = load_reg(s, a->rt + 1); - gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL); + gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN); tcg_temp_free_i32(tmp); op_addr_rr_post(s, a, addr, -4); @@ -XXX,XX +XXX,XX @@ static bool op_ldrd_ri(DisasContext *s, arg_ldst_ri *a, int rt2) addr = op_addr_ri_pre(s, a); tmp = tcg_temp_new_i32(); - gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL); + gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN); store_reg(s, a->rt, tmp); tcg_gen_addi_i32(addr, addr, 4); tmp = tcg_temp_new_i32(); - gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL); + gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN); store_reg(s, rt2, tmp); /* LDRD w/ base writeback is undefined if the registers overlap. */ @@ -XXX,XX +XXX,XX @@ static bool op_strd_ri(DisasContext *s, arg_ldst_ri *a, int rt2) addr = op_addr_ri_pre(s, a); tmp = load_reg(s, a->rt); - gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL); + gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN); tcg_temp_free_i32(tmp); tcg_gen_addi_i32(addr, addr, 4); tmp = load_reg(s, rt2); - gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL); + gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN); tcg_temp_free_i32(tmp); op_addr_ri_post(s, a, addr, -4); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool op_stl(DisasContext *s, arg_STL *a, MemOp mop) addr = load_reg(s, a->rn); tmp = load_reg(s, a->rt); tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); - gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), mop); + gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), mop | MO_ALIGN); disas_set_da_iss(s, mop, a->rt | ISSIsAcqRel | ISSIsWrite); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool op_lda(DisasContext *s, arg_LDA *a, MemOp mop) addr = load_reg(s, a->rn); tmp = tcg_temp_new_i32(); - gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), mop); + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), mop | MO_ALIGN); disas_set_da_iss(s, mop, a->rt | ISSIsAcqRel); tcg_temp_free_i32(addr); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool op_stm(DisasContext *s, arg_ldst_block *a, int min_n) } else { tmp = load_reg(s, i); } - gen_aa32_st32(s, tmp, addr, mem_idx); + gen_aa32_st_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN); tcg_temp_free_i32(tmp); /* No need to add after the last transfer. */ @@ -XXX,XX +XXX,XX @@ static bool do_ldm(DisasContext *s, arg_ldst_block *a, int min_n) } tmp = tcg_temp_new_i32(); - gen_aa32_ld32u(s, tmp, addr, mem_idx); + gen_aa32_ld_i32(s, tmp, addr, mem_idx, MO_UL | MO_ALIGN); if (user) { tmp2 = tcg_const_i32(i); gen_helper_set_user_reg(cpu_env, tmp2, tmp); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_RFE(DisasContext *s, arg_RFE *a) /* Load PC into tmp and CPSR into tmp2. */ t1 = tcg_temp_new_i32(); - gen_aa32_ld32u(s, t1, addr, get_mem_index(s)); + gen_aa32_ld_i32(s, t1, addr, get_mem_index(s), MO_UL | MO_ALIGN); tcg_gen_addi_i32(addr, addr, 4); t2 = tcg_temp_new_i32(); - gen_aa32_ld32u(s, t2, addr, get_mem_index(s)); + gen_aa32_ld_i32(s, t2, addr, get_mem_index(s), MO_UL | MO_ALIGN); if (a->w) { /* Base writeback. */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_srs(DisasContext *s, } tcg_gen_addi_i32(addr, addr, offset); tmp = load_reg(s, 14); - gen_aa32_st32(s, tmp, addr, get_mem_index(s)); + gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), MO_UL | MO_ALIGN); tcg_temp_free_i32(tmp); tmp = load_cpu_field(spsr); tcg_gen_addi_i32(addr, addr, 4); - gen_aa32_st32(s, tmp, addr, get_mem_index(s)); + gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), MO_UL | MO_ALIGN); tcg_temp_free_i32(tmp); if (writeback) { switch (amode) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-vfp.c.inc | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_sp(DisasContext *s, arg_VLDM_VSTM_sp *a) for (i = 0; i < n; i++) { if (a->l) { /* load */ - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), MO_UL | MO_ALIGN); vfp_store_reg32(tmp, a->vd + i); } else { /* store */ vfp_load_reg32(tmp, a->vd + i); - gen_aa32_st32(s, tmp, addr, get_mem_index(s)); + gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), MO_UL | MO_ALIGN); } tcg_gen_addi_i32(addr, addr, offset); } @@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_dp(DisasContext *s, arg_VLDM_VSTM_dp *a) for (i = 0; i < n; i++) { if (a->l) { /* load */ - gen_aa32_ld64(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld_i64(s, tmp, addr, get_mem_index(s), MO_Q | MO_ALIGN_4); vfp_store_reg64(tmp, a->vd + i); } else { /* store */ vfp_load_reg64(tmp, a->vd + i); - gen_aa32_st64(s, tmp, addr, get_mem_index(s)); + gen_aa32_st_i64(s, tmp, addr, get_mem_index(s), MO_Q | MO_ALIGN_4); } tcg_gen_addi_i32(addr, addr, offset); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-22-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-vfp.c.inc | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_hp(DisasContext *s, arg_VLDR_VSTR_sp *a) addr = add_reg_for_lit(s, a->rn, offset); tmp = tcg_temp_new_i32(); if (a->l) { - gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), MO_UW | MO_ALIGN); vfp_store_reg32(tmp, a->vd); } else { vfp_load_reg32(tmp, a->vd); - gen_aa32_st16(s, tmp, addr, get_mem_index(s)); + gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), MO_UW | MO_ALIGN); } tcg_temp_free_i32(tmp); tcg_temp_free_i32(addr); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a) addr = add_reg_for_lit(s, a->rn, offset); tmp = tcg_temp_new_i32(); if (a->l) { - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), MO_UL | MO_ALIGN); vfp_store_reg32(tmp, a->vd); } else { vfp_load_reg32(tmp, a->vd); - gen_aa32_st32(s, tmp, addr, get_mem_index(s)); + gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), MO_UL | MO_ALIGN); } tcg_temp_free_i32(tmp); tcg_temp_free_i32(addr); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_dp(DisasContext *s, arg_VLDR_VSTR_dp *a) addr = add_reg_for_lit(s, a->rn, offset); tmp = tcg_temp_new_i64(); if (a->l) { - gen_aa32_ld64(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld_i64(s, tmp, addr, get_mem_index(s), MO_Q | MO_ALIGN_4); vfp_store_reg64(tmp, a->vd); } else { vfp_load_reg64(tmp, a->vd); - gen_aa32_st64(s, tmp, addr, get_mem_index(s)); + gen_aa32_st_i64(s, tmp, addr, get_mem_index(s), MO_Q | MO_ALIGN_4); } tcg_temp_free_i64(tmp); tcg_temp_free_i32(addr); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-23-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 1 + target/arm/translate.c | 15 +++++++++++++ target/arm/translate-neon.c.inc | 37 +++++++++++++++++++++++++-------- 3 files changed, 44 insertions(+), 9 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ void arm_test_cc(DisasCompare *cmp, int cc); void arm_free_cc(DisasCompare *cmp); void arm_jump_cc(DisasCompare *cmp, TCGLabel *label); void arm_gen_test_cc(int cc, TCGLabel *label); +MemOp pow2_align(unsigned i); /* Return state of Alternate Half-precision flag, caller frees result */ static inline TCGv_i32 get_ahp_flag(void) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void store_reg_from_load(DisasContext *s, int reg, TCGv_i32 var) #define IS_USER_ONLY 0 #endif +MemOp pow2_align(unsigned i) +{ + static const MemOp mop_align[] = { + 0, MO_ALIGN_2, MO_ALIGN_4, MO_ALIGN_8, MO_ALIGN_16, + /* + * FIXME: TARGET_PAGE_BITS_MIN affects TLB_FLAGS_MASK such + * that 256-bit alignment (MO_ALIGN_32) cannot be supported: + * see get_alignment_bits(). Enforce only 128-bit alignment for now. + */ + MO_ALIGN_16 + }; + g_assert(i < ARRAY_SIZE(mop_align)); + return mop_align[i]; +} + /* * Abstractions of "generate code to do a guest load/store for * AArch32", where a vaddr is always 32 bits (and is zero diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a) int size = a->size; int nregs = a->n + 1; TCGv_i32 addr, tmp; + MemOp mop, align; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a) return false; } + align = 0; if (size == 3) { if (nregs != 4 || a->a == 0) { return false; } /* For VLD4 size == 3 a == 1 means 32 bits at 16 byte alignment */ - size = 2; - } - if (nregs == 1 && a->a == 1 && size == 0) { - return false; - } - if (nregs == 3 && a->a == 1) { - return false; + size = MO_32; + align = MO_ALIGN_16; + } else if (a->a) { + switch (nregs) { + case 1: + if (size == 0) { + return false; + } + align = MO_ALIGN; + break; + case 2: + align = pow2_align(size + 1); + break; + case 3: + return false; + case 4: + align = pow2_align(size + 2); + break; + default: + g_assert_not_reached(); + } } if (!vfp_access_check(s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a) */ stride = a->t ? 2 : 1; vec_size = nregs == 1 ? stride * 8 : 8; - + mop = size | align; tmp = tcg_temp_new_i32(); addr = tcg_temp_new_i32(); load_reg_var(s, addr, a->rn); for (reg = 0; reg < nregs; reg++) { - gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), size); + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), mop); if ((vd & 1) && vec_size == 16) { /* * We cannot write 16 bytes at once because the @@ -XXX,XX +XXX,XX @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a) } tcg_gen_addi_i32(addr, addr, 1 << size); vd += stride; + + /* Subsequent memory operations inherit alignment */ + mop &= ~MO_AMASK; } tcg_temp_free_i32(tmp); tcg_temp_free_i32(addr); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-24-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-neon.c.inc | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a) { /* Neon load/store multiple structures */ int nregs, interleave, spacing, reg, n; - MemOp endian = s->be_data; + MemOp mop, align, endian; int mmu_idx = get_mem_index(s); int size = a->size; TCGv_i64 tmp64; @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a) } /* For our purposes, bytes are always little-endian. */ + endian = s->be_data; if (size == 0) { endian = MO_LE; } + + /* Enforce alignment requested by the instruction */ + if (a->align) { + align = pow2_align(a->align + 2); /* 4 ** a->align */ + } else { + align = s->align_mem ? MO_ALIGN : 0; + } + /* * Consecutive little-endian elements from a single register * can be promoted to a larger little-endian operation. */ if (interleave == 1 && endian == MO_LE) { + /* Retain any natural alignment. */ + if (align == MO_ALIGN) { + align = pow2_align(size); + } size = 3; } + tmp64 = tcg_temp_new_i64(); addr = tcg_temp_new_i32(); tmp = tcg_const_i32(1 << size); load_reg_var(s, addr, a->rn); + + mop = endian | size | align; for (reg = 0; reg < nregs; reg++) { for (n = 0; n < 8 >> size; n++) { int xs; @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a) int tt = a->vd + reg + spacing * xs; if (a->l) { - gen_aa32_ld_internal_i64(s, tmp64, addr, mmu_idx, - endian | size); + gen_aa32_ld_internal_i64(s, tmp64, addr, mmu_idx, mop); neon_store_element64(tt, n, size, tmp64); } else { neon_load_element64(tmp64, tt, n, size); - gen_aa32_st_internal_i64(s, tmp64, addr, mmu_idx, - endian | size); + gen_aa32_st_internal_i64(s, tmp64, addr, mmu_idx, mop); } tcg_gen_add_i32(addr, addr, tmp); + + /* Subsequent memory operations inherit alignment */ + mop &= ~MO_AMASK; } } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-neon.c.inc | 48 ++++++++++++++++++++++++++++----- 1 file changed, 42 insertions(+), 6 deletions(-) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a) int nregs = a->n + 1; int vd = a->vd; TCGv_i32 addr, tmp; + MemOp mop; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a) return true; } + /* Pick up SCTLR settings */ + mop = finalize_memop(s, a->size); + + if (a->align) { + MemOp align_op; + + switch (nregs) { + case 1: + /* For VLD1, use natural alignment. */ + align_op = MO_ALIGN; + break; + case 2: + /* For VLD2, use double alignment. */ + align_op = pow2_align(a->size + 1); + break; + case 4: + if (a->size == MO_32) { + /* + * For VLD4.32, align = 1 is double alignment, align = 2 is + * quad alignment; align = 3 is rejected above. + */ + align_op = pow2_align(a->size + a->align); + } else { + /* For VLD4.8 and VLD.16, we want quad alignment. */ + align_op = pow2_align(a->size + 2); + } + break; + default: + /* For VLD3, the alignment field is zero and rejected above. */ + g_assert_not_reached(); + } + + mop = (mop & ~MO_AMASK) | align_op; + } + tmp = tcg_temp_new_i32(); addr = tcg_temp_new_i32(); load_reg_var(s, addr, a->rn); - /* - * TODO: if we implemented alignment exceptions, we should check - * addr against the alignment encoded in a->align here. - */ + for (reg = 0; reg < nregs; reg++) { if (a->l) { - gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), a->size); + gen_aa32_ld_internal_i32(s, tmp, addr, get_mem_index(s), mop); neon_store_element(vd, a->reg_idx, a->size, tmp); } else { /* Store */ neon_load_element(tmp, vd, a->reg_idx, a->size); - gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), a->size); + gen_aa32_st_internal_i32(s, tmp, addr, get_mem_index(s), mop); } vd += a->stride; tcg_gen_addi_i32(addr, addr, 1 << a->size); + + /* Subsequent memory operations inherit alignment */ + mop &= ~MO_AMASK; } tcg_temp_free_i32(addr); tcg_temp_free_i32(tmp); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> In the case of gpr load, merge the size and is_signed arguments; otherwise, simply convert size to memop. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-26-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 78 ++++++++++++++++---------------------- 1 file changed, 33 insertions(+), 45 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_adc_CC(int sf, TCGv_i64 dest, TCGv_i64 t0, TCGv_i64 t1) * Store from GPR register to memory. */ static void do_gpr_st_memidx(DisasContext *s, TCGv_i64 source, - TCGv_i64 tcg_addr, int size, int memidx, + TCGv_i64 tcg_addr, MemOp memop, int memidx, bool iss_valid, unsigned int iss_srt, bool iss_sf, bool iss_ar) { - g_assert(size <= 3); - tcg_gen_qemu_st_i64(source, tcg_addr, memidx, s->be_data + size); + memop = finalize_memop(s, memop); + tcg_gen_qemu_st_i64(source, tcg_addr, memidx, memop); if (iss_valid) { uint32_t syn; syn = syn_data_abort_with_iss(0, - size, + (memop & MO_SIZE), false, iss_srt, iss_sf, @@ -XXX,XX +XXX,XX @@ static void do_gpr_st_memidx(DisasContext *s, TCGv_i64 source, } static void do_gpr_st(DisasContext *s, TCGv_i64 source, - TCGv_i64 tcg_addr, int size, + TCGv_i64 tcg_addr, MemOp memop, bool iss_valid, unsigned int iss_srt, bool iss_sf, bool iss_ar) { - do_gpr_st_memidx(s, source, tcg_addr, size, get_mem_index(s), + do_gpr_st_memidx(s, source, tcg_addr, memop, get_mem_index(s), iss_valid, iss_srt, iss_sf, iss_ar); } /* * Load from memory to GPR register */ -static void do_gpr_ld_memidx(DisasContext *s, - TCGv_i64 dest, TCGv_i64 tcg_addr, - int size, bool is_signed, - bool extend, int memidx, +static void do_gpr_ld_memidx(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr, + MemOp memop, bool extend, int memidx, bool iss_valid, unsigned int iss_srt, bool iss_sf, bool iss_ar) { - MemOp memop = s->be_data + size; - - g_assert(size <= 3); - - if (is_signed) { - memop += MO_SIGN; - } - + memop = finalize_memop(s, memop); tcg_gen_qemu_ld_i64(dest, tcg_addr, memidx, memop); - if (extend && is_signed) { - g_assert(size < 3); + if (extend && (memop & MO_SIGN)) { + g_assert((memop & MO_SIZE) <= MO_32); tcg_gen_ext32u_i64(dest, dest); } @@ -XXX,XX +XXX,XX @@ static void do_gpr_ld_memidx(DisasContext *s, uint32_t syn; syn = syn_data_abort_with_iss(0, - size, - is_signed, + (memop & MO_SIZE), + (memop & MO_SIGN) != 0, iss_srt, iss_sf, iss_ar, @@ -XXX,XX +XXX,XX @@ static void do_gpr_ld_memidx(DisasContext *s, } } -static void do_gpr_ld(DisasContext *s, - TCGv_i64 dest, TCGv_i64 tcg_addr, - int size, bool is_signed, bool extend, +static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr, + MemOp memop, bool extend, bool iss_valid, unsigned int iss_srt, bool iss_sf, bool iss_ar) { - do_gpr_ld_memidx(s, dest, tcg_addr, size, is_signed, extend, - get_mem_index(s), + do_gpr_ld_memidx(s, dest, tcg_addr, memop, extend, get_mem_index(s), iss_valid, iss_srt, iss_sf, iss_ar); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) } clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), false, rn != 31, size); - do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size, false, false, true, rt, + do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size, false, true, rt, disas_ldst_compute_iss_sf(size, false, 0), is_lasr); tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); return; @@ -XXX,XX +XXX,XX @@ static void disas_ld_lit(DisasContext *s, uint32_t insn) /* Only unsigned 32bit loads target 32bit registers. */ bool iss_sf = opc != 0; - do_gpr_ld(s, tcg_rt, clean_addr, size, is_signed, false, - true, rt, iss_sf, false); + do_gpr_ld(s, tcg_rt, clean_addr, size + is_signed * MO_SIGN, + false, true, rt, iss_sf, false); } tcg_temp_free_i64(clean_addr); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) /* Do not modify tcg_rt before recognizing any exception * from the second load. */ - do_gpr_ld(s, tmp, clean_addr, size, is_signed, false, - false, 0, false, false); + do_gpr_ld(s, tmp, clean_addr, size + is_signed * MO_SIGN, + false, false, 0, false, false); tcg_gen_addi_i64(clean_addr, clean_addr, 1 << size); - do_gpr_ld(s, tcg_rt2, clean_addr, size, is_signed, false, - false, 0, false, false); + do_gpr_ld(s, tcg_rt2, clean_addr, size + is_signed * MO_SIGN, + false, false, 0, false, false); tcg_gen_mov_i64(tcg_rt, tmp); tcg_temp_free_i64(tmp); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, do_gpr_st_memidx(s, tcg_rt, clean_addr, size, memidx, iss_valid, rt, iss_sf, false); } else { - do_gpr_ld_memidx(s, tcg_rt, clean_addr, size, - is_signed, is_extended, memidx, + do_gpr_ld_memidx(s, tcg_rt, clean_addr, size + is_signed * MO_SIGN, + is_extended, memidx, iss_valid, rt, iss_sf, false); } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, do_gpr_st(s, tcg_rt, clean_addr, size, true, rt, iss_sf, false); } else { - do_gpr_ld(s, tcg_rt, clean_addr, size, - is_signed, is_extended, - true, rt, iss_sf, false); + do_gpr_ld(s, tcg_rt, clean_addr, size + is_signed * MO_SIGN, + is_extended, true, rt, iss_sf, false); } } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn, do_gpr_st(s, tcg_rt, clean_addr, size, true, rt, iss_sf, false); } else { - do_gpr_ld(s, tcg_rt, clean_addr, size, is_signed, is_extended, - true, rt, iss_sf, false); + do_gpr_ld(s, tcg_rt, clean_addr, size + is_signed * MO_SIGN, + is_extended, true, rt, iss_sf, false); } } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, * full load-acquire (we only need "load-acquire processor consistent"), * but we choose to implement them as full LDAQ. */ - do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size, false, false, + do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size, false, true, rt, disas_ldst_compute_iss_sf(size, false, 0), true); tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); return; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pac(DisasContext *s, uint32_t insn, is_wback || rn != 31, size); tcg_rt = cpu_reg(s, rt); - do_gpr_ld(s, tcg_rt, clean_addr, size, /* is_signed */ false, + do_gpr_ld(s, tcg_rt, clean_addr, size, /* extend */ false, /* iss_valid */ !is_wback, /* iss_srt */ rt, /* iss_sf */ true, /* iss_ar */ false); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_ldapr_stlr(DisasContext *s, uint32_t insn) * Load-AcquirePC semantics; we implement as the slightly more * restrictive Load-Acquire. */ - do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size, is_signed, extend, - true, rt, iss_sf, true); + do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size + is_signed * MO_SIGN, + extend, true, rt, iss_sf, true); tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> For 128-bit load/store, use 16-byte alignment. This requires that we perform the two operations in the correct order so that we generate the alignment fault before modifying memory. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-27-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 42 +++++++++++++++++++++++--------------- 1 file changed, 26 insertions(+), 16 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr, static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, int size) { /* This writes the bottom N bits of a 128 bit wide vector to memory */ - TCGv_i64 tmp = tcg_temp_new_i64(); - tcg_gen_ld_i64(tmp, cpu_env, fp_reg_offset(s, srcidx, MO_64)); + TCGv_i64 tmplo = tcg_temp_new_i64(); + MemOp mop; + + tcg_gen_ld_i64(tmplo, cpu_env, fp_reg_offset(s, srcidx, MO_64)); + if (size < 4) { - tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s), - s->be_data + size); + mop = finalize_memop(s, size); + tcg_gen_qemu_st_i64(tmplo, tcg_addr, get_mem_index(s), mop); } else { bool be = s->be_data == MO_BE; TCGv_i64 tcg_hiaddr = tcg_temp_new_i64(); + TCGv_i64 tmphi = tcg_temp_new_i64(); + tcg_gen_ld_i64(tmphi, cpu_env, fp_reg_hi_offset(s, srcidx)); + + mop = s->be_data | MO_Q; + tcg_gen_qemu_st_i64(be ? tmphi : tmplo, tcg_addr, get_mem_index(s), + mop | (s->align_mem ? MO_ALIGN_16 : 0)); tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8); - tcg_gen_qemu_st_i64(tmp, be ? tcg_hiaddr : tcg_addr, get_mem_index(s), - s->be_data | MO_Q); - tcg_gen_ld_i64(tmp, cpu_env, fp_reg_hi_offset(s, srcidx)); - tcg_gen_qemu_st_i64(tmp, be ? tcg_addr : tcg_hiaddr, get_mem_index(s), - s->be_data | MO_Q); + tcg_gen_qemu_st_i64(be ? tmplo : tmphi, tcg_hiaddr, + get_mem_index(s), mop); + tcg_temp_free_i64(tcg_hiaddr); + tcg_temp_free_i64(tmphi); } - tcg_temp_free_i64(tmp); + tcg_temp_free_i64(tmplo); } /* @@ -XXX,XX +XXX,XX @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size) /* This always zero-extends and writes to a full 128 bit wide vector */ TCGv_i64 tmplo = tcg_temp_new_i64(); TCGv_i64 tmphi = NULL; + MemOp mop; if (size < 4) { - MemOp memop = s->be_data + size; - tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), memop); + mop = finalize_memop(s, size); + tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), mop); } else { bool be = s->be_data == MO_BE; TCGv_i64 tcg_hiaddr; @@ -XXX,XX +XXX,XX @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size) tmphi = tcg_temp_new_i64(); tcg_hiaddr = tcg_temp_new_i64(); + mop = s->be_data | MO_Q; + tcg_gen_qemu_ld_i64(be ? tmphi : tmplo, tcg_addr, get_mem_index(s), + mop | (s->align_mem ? MO_ALIGN_16 : 0)); tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8); - tcg_gen_qemu_ld_i64(tmplo, be ? tcg_hiaddr : tcg_addr, get_mem_index(s), - s->be_data | MO_Q); - tcg_gen_qemu_ld_i64(tmphi, be ? tcg_addr : tcg_hiaddr, get_mem_index(s), - s->be_data | MO_Q); + tcg_gen_qemu_ld_i64(be ? tmplo : tmphi, tcg_hiaddr, + get_mem_index(s), mop); tcg_temp_free_i64(tcg_hiaddr); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-28-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), true, rn != 31, size); - do_gpr_st(s, cpu_reg(s, rt), clean_addr, size, true, rt, + /* TODO: ARMv8.4-LSE SCTLR.nAA */ + do_gpr_st(s, cpu_reg(s, rt), clean_addr, size | MO_ALIGN, true, rt, disas_ldst_compute_iss_sf(size, false, 0), is_lasr); return; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) } clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), false, rn != 31, size); - do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size, false, true, rt, - disas_ldst_compute_iss_sf(size, false, 0), is_lasr); + /* TODO: ARMv8.4-LSE SCTLR.nAA */ + do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size | MO_ALIGN, false, true, + rt, disas_ldst_compute_iss_sf(size, false, 0), is_lasr); tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); return; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_ldapr_stlr(DisasContext *s, uint32_t insn) int size = extract32(insn, 30, 2); TCGv_i64 clean_addr, dirty_addr; bool is_store = false; - bool is_signed = false; bool extend = false; bool iss_sf; + MemOp mop; if (!dc_isar_feature(aa64_rcpc_8_4, s)) { unallocated_encoding(s); return; } + /* TODO: ARMv8.4-LSE SCTLR.nAA */ + mop = size | MO_ALIGN; + switch (opc) { case 0: /* STLURB */ is_store = true; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_ldapr_stlr(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - is_signed = true; + mop |= MO_SIGN; break; case 3: /* LDAPURS* 32-bit variant */ if (size > 1) { unallocated_encoding(s); return; } - is_signed = true; + mop |= MO_SIGN; extend = true; /* zero-extend 32->64 after signed load */ break; default: g_assert_not_reached(); } - iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc); + iss_sf = disas_ldst_compute_iss_sf(size, (mop & MO_SIGN) != 0, opc); if (rn == 31) { gen_check_sp_alignment(s); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_ldapr_stlr(DisasContext *s, uint32_t insn) if (is_store) { /* Store-Release semantics */ tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); - do_gpr_st(s, cpu_reg(s, rt), clean_addr, size, true, rt, iss_sf, true); + do_gpr_st(s, cpu_reg(s, rt), clean_addr, mop, true, rt, iss_sf, true); } else { /* * Load-AcquirePC semantics; we implement as the slightly more * restrictive Load-Acquire. */ - do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size + is_signed * MO_SIGN, + do_gpr_ld(s, cpu_reg(s, rt), clean_addr, mop, extend, true, rt, iss_sf, true); tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-29-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void write_vec_element_i32(DisasContext *s, TCGv_i32 tcg_src, /* Store from vector register to memory */ static void do_vec_st(DisasContext *s, int srcidx, int element, - TCGv_i64 tcg_addr, int size, MemOp endian) + TCGv_i64 tcg_addr, MemOp mop) { TCGv_i64 tcg_tmp = tcg_temp_new_i64(); - read_vec_element(s, tcg_tmp, srcidx, element, size); - tcg_gen_qemu_st_i64(tcg_tmp, tcg_addr, get_mem_index(s), endian | size); + read_vec_element(s, tcg_tmp, srcidx, element, mop & MO_SIZE); + tcg_gen_qemu_st_i64(tcg_tmp, tcg_addr, get_mem_index(s), mop); tcg_temp_free_i64(tcg_tmp); } /* Load from memory to vector register */ static void do_vec_ld(DisasContext *s, int destidx, int element, - TCGv_i64 tcg_addr, int size, MemOp endian) + TCGv_i64 tcg_addr, MemOp mop) { TCGv_i64 tcg_tmp = tcg_temp_new_i64(); - tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, get_mem_index(s), endian | size); - write_vec_element(s, tcg_tmp, destidx, element, size); + tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, get_mem_index(s), mop); + write_vec_element(s, tcg_tmp, destidx, element, mop & MO_SIZE); tcg_temp_free_i64(tcg_tmp); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) for (xs = 0; xs < selem; xs++) { int tt = (rt + r + xs) % 32; if (is_store) { - do_vec_st(s, tt, e, clean_addr, size, endian); + do_vec_st(s, tt, e, clean_addr, size | endian); } else { - do_vec_ld(s, tt, e, clean_addr, size, endian); + do_vec_ld(s, tt, e, clean_addr, size | endian); } tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) } else { /* Load/store one element per register */ if (is_load) { - do_vec_ld(s, rt, index, clean_addr, scale, s->be_data); + do_vec_ld(s, rt, index, clean_addr, scale | s->be_data); } else { - do_vec_st(s, rt, index, clean_addr, scale, s->be_data); + do_vec_st(s, rt, index, clean_addr, scale | s->be_data); } } tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-30-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) bool is_postidx = extract32(insn, 23, 1); bool is_q = extract32(insn, 30, 1); TCGv_i64 clean_addr, tcg_rn, tcg_ebytes; - MemOp endian = s->be_data; + MemOp endian, align, mop; int total; /* total bytes */ int elements; /* elements per vector */ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) } /* For our purposes, bytes are always little-endian. */ + endian = s->be_data; if (size == 0) { endian = MO_LE; } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) * Consecutive little-endian elements from a single register * can be promoted to a larger little-endian operation. */ + align = MO_ALIGN; if (selem == 1 && endian == MO_LE) { + align = pow2_align(size); size = 3; } - elements = (is_q ? 16 : 8) >> size; + if (!s->align_mem) { + align = 0; + } + mop = endian | size | align; + elements = (is_q ? 16 : 8) >> size; tcg_ebytes = tcg_const_i64(1 << size); for (r = 0; r < rpt; r++) { int e; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) for (xs = 0; xs < selem; xs++) { int tt = (rt + r + xs) % 32; if (is_store) { - do_vec_st(s, tt, e, clean_addr, size | endian); + do_vec_st(s, tt, e, clean_addr, mop); } else { - do_vec_ld(s, tt, e, clean_addr, size | endian); + do_vec_ld(s, tt, e, clean_addr, mop); } tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-31-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) int index = is_q << 3 | S << 2 | size; int xs, total; TCGv_i64 clean_addr, tcg_rn, tcg_ebytes; + MemOp mop; if (extract32(insn, 31, 1)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) clean_addr = gen_mte_checkN(s, tcg_rn, !is_load, is_postidx || rn != 31, total); + mop = finalize_memop(s, scale); tcg_ebytes = tcg_const_i64(1 << scale); for (xs = 0; xs < selem; xs++) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) /* Load and replicate to all elements */ TCGv_i64 tcg_tmp = tcg_temp_new_i64(); - tcg_gen_qemu_ld_i64(tcg_tmp, clean_addr, - get_mem_index(s), s->be_data + scale); + tcg_gen_qemu_ld_i64(tcg_tmp, clean_addr, get_mem_index(s), mop); tcg_gen_gvec_dup_i64(scale, vec_full_reg_offset(s, rt), (is_q + 1) * 8, vec_full_reg_size(s), tcg_tmp); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) } else { /* Load/store one element per register */ if (is_load) { - do_vec_ld(s, rt, index, clean_addr, scale | s->be_data); + do_vec_ld(s, rt, index, clean_addr, mop); } else { - do_vec_st(s, rt, index, clean_addr, scale | s->be_data); + do_vec_st(s, rt, index, clean_addr, mop); } } tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210419202257.161730-32-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LD1R_zpri(DisasContext *s, arg_rpri_load *a) clean_addr = gen_mte_check1(s, temp, false, true, msz); tcg_gen_qemu_ld_i64(temp, clean_addr, get_mem_index(s), - s->be_data | dtype_mop[a->dtype]); + finalize_memop(s, dtype_mop[a->dtype])); /* Broadcast to *all* elements. */ tcg_gen_gvec_dup_i64(esz, vec_full_reg_offset(s, a->rd), -- 2.20.1 From: Cornelia Huck <cohuck@redhat.com> Add 6.1 machine types for arm/i440fx/q35/s390x/spapr. Signed-off-by: Cornelia Huck <cohuck@redhat.com> Acked-by: Greg Kurz <groug@kaod.org> Message-id: 20210331111900.118274-1-cohuck@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/boards.h | 3 +++ include/hw/i386/pc.h | 3 +++ hw/arm/virt.c | 7 ++++++- hw/core/machine.c | 3 +++ hw/i386/pc.c | 3 +++ hw/i386/pc_piix.c | 14 +++++++++++++- hw/i386/pc_q35.c | 13 ++++++++++++- hw/ppc/spapr.c | 17 ++++++++++++++--- hw/s390x/s390-virtio-ccw.c | 14 +++++++++++++- 9 files changed, 70 insertions(+), 7 deletions(-) diff --git a/include/hw/boards.h b/include/hw/boards.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -XXX,XX +XXX,XX @@ struct MachineState { } \ type_init(machine_initfn##_register_types) +extern GlobalProperty hw_compat_6_0[]; +extern const size_t hw_compat_6_0_len; + extern GlobalProperty hw_compat_5_2[]; extern const size_t hw_compat_5_2_len; diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -XXX,XX +XXX,XX @@ bool pc_system_ovmf_table_find(const char *entry, uint8_t **data, void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid, const CPUArchIdList *apic_ids, GArray *entry); +extern GlobalProperty pc_compat_6_0[]; +extern const size_t pc_compat_6_0_len; + extern GlobalProperty pc_compat_5_2[]; extern const size_t pc_compat_5_2_len; diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void machvirt_machine_init(void) } type_init(machvirt_machine_init); +static void virt_machine_6_1_options(MachineClass *mc) +{ +} +DEFINE_VIRT_MACHINE_AS_LATEST(6, 1) + static void virt_machine_6_0_options(MachineClass *mc) { } -DEFINE_VIRT_MACHINE_AS_LATEST(6, 0) +DEFINE_VIRT_MACHINE(6, 0) static void virt_machine_5_2_options(MachineClass *mc) { diff --git a/hw/core/machine.c b/hw/core/machine.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -XXX,XX +XXX,XX @@ #include "hw/virtio/virtio.h" #include "hw/virtio/virtio-pci.h" +GlobalProperty hw_compat_6_0[] = {}; +const size_t hw_compat_6_0_len = G_N_ELEMENTS(hw_compat_6_0); + GlobalProperty hw_compat_5_2[] = { { "ICH9-LPC", "smm-compat", "on"}, { "PIIX4_PM", "smm-compat", "on"}, diff --git a/hw/i386/pc.c b/hw/i386/pc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -XXX,XX +XXX,XX @@ #include "trace.h" #include CONFIG_DEVICES +GlobalProperty pc_compat_6_0[] = {}; +const size_t pc_compat_6_0_len = G_N_ELEMENTS(pc_compat_6_0); + GlobalProperty pc_compat_5_2[] = { { "ICH9-LPC", "x-smi-cpu-hotunplug", "off" }, }; diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -XXX,XX +XXX,XX @@ static void pc_i440fx_machine_options(MachineClass *m) machine_class_allow_dynamic_sysbus_dev(m, TYPE_VMBUS_BRIDGE); } -static void pc_i440fx_6_0_machine_options(MachineClass *m) +static void pc_i440fx_6_1_machine_options(MachineClass *m) { PCMachineClass *pcmc = PC_MACHINE_CLASS(m); pc_i440fx_machine_options(m); @@ -XXX,XX +XXX,XX @@ static void pc_i440fx_6_0_machine_options(MachineClass *m) pcmc->default_cpu_version = 1; } +DEFINE_I440FX_MACHINE(v6_1, "pc-i440fx-6.1", NULL, + pc_i440fx_6_1_machine_options); + +static void pc_i440fx_6_0_machine_options(MachineClass *m) +{ + pc_i440fx_6_1_machine_options(m); + m->alias = NULL; + m->is_default = false; + compat_props_add(m->compat_props, hw_compat_6_0, hw_compat_6_0_len); + compat_props_add(m->compat_props, pc_compat_6_0, pc_compat_6_0_len); +} + DEFINE_I440FX_MACHINE(v6_0, "pc-i440fx-6.0", NULL, pc_i440fx_6_0_machine_options); diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -XXX,XX +XXX,XX @@ static void pc_q35_machine_options(MachineClass *m) m->max_cpus = 288; } -static void pc_q35_6_0_machine_options(MachineClass *m) +static void pc_q35_6_1_machine_options(MachineClass *m) { PCMachineClass *pcmc = PC_MACHINE_CLASS(m); pc_q35_machine_options(m); @@ -XXX,XX +XXX,XX @@ static void pc_q35_6_0_machine_options(MachineClass *m) pcmc->default_cpu_version = 1; } +DEFINE_Q35_MACHINE(v6_1, "pc-q35-6.1", NULL, + pc_q35_6_1_machine_options); + +static void pc_q35_6_0_machine_options(MachineClass *m) +{ + pc_q35_6_1_machine_options(m); + m->alias = NULL; + compat_props_add(m->compat_props, hw_compat_6_0, hw_compat_6_0_len); + compat_props_add(m->compat_props, pc_compat_6_0, pc_compat_6_0_len); +} + DEFINE_Q35_MACHINE(v6_0, "pc-q35-6.0", NULL, pc_q35_6_0_machine_options); diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -XXX,XX +XXX,XX @@ static void spapr_machine_latest_class_options(MachineClass *mc) type_init(spapr_machine_register_##suffix) /* - * pseries-6.0 + * pseries-6.1 */ -static void spapr_machine_6_0_class_options(MachineClass *mc) +static void spapr_machine_6_1_class_options(MachineClass *mc) { /* Defaults for the latest behaviour inherited from the base class */ } -DEFINE_SPAPR_MACHINE(6_0, "6.0", true); +DEFINE_SPAPR_MACHINE(6_1, "6.1", true); + +/* + * pseries-6.0 + */ +static void spapr_machine_6_0_class_options(MachineClass *mc) +{ + spapr_machine_6_1_class_options(mc); + compat_props_add(mc->compat_props, hw_compat_6_0, hw_compat_6_0_len); +} + +DEFINE_SPAPR_MACHINE(6_0, "6.0", false); /* * pseries-5.2 diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index XXXXXXX..XXXXXXX 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -XXX,XX +XXX,XX @@ bool css_migration_enabled(void) } \ type_init(ccw_machine_register_##suffix) +static void ccw_machine_6_1_instance_options(MachineState *machine) +{ +} + +static void ccw_machine_6_1_class_options(MachineClass *mc) +{ +} +DEFINE_CCW_MACHINE(6_1, "6.1", true); + static void ccw_machine_6_0_instance_options(MachineState *machine) { + ccw_machine_6_1_instance_options(machine); } static void ccw_machine_6_0_class_options(MachineClass *mc) { + ccw_machine_6_1_class_options(mc); + compat_props_add(mc->compat_props, hw_compat_6_0, hw_compat_6_0_len); } -DEFINE_CCW_MACHINE(6_0, "6.0", true); +DEFINE_CCW_MACHINE(6_0, "6.0", false); static void ccw_machine_5_2_instance_options(MachineState *machine) { -- 2.20.1 Currently the gpex PCI controller implements no special behaviour for guest accesses to areas of the PIO and MMIO where it has not mapped any PCI devices, which means that for Arm you end up with a CPU exception due to a data abort. Most host OSes expect "like an x86 PC" behaviour, where bad accesses like this return -1 for reads and ignore writes. In the interests of not being surprising, make host CPU accesses to these windows behave as -1/discard where there's no mapped PCI device. The old behaviour generally didn't cause any problems, because almost always the guest OS will map the PCI devices and then only access where it has mapped them. One corner case where you will see this kind of access is if Linux attempts to probe legacy ISA devices via a PIO window access. So far the only case where we've seen this has been via the syzkaller fuzzer. Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Acked-by: Michael S. Tsirkin <mst@redhat.com> Message-id: 20210325163315.27724-1-peter.maydell@linaro.org Fixes: https://bugs.launchpad.net/qemu/+bug/1918917 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/pci-host/gpex.h | 4 +++ hw/core/machine.c | 4 ++- hw/pci-host/gpex.c | 56 ++++++++++++++++++++++++++++++++++++-- 3 files changed, 60 insertions(+), 4 deletions(-) diff --git a/include/hw/pci-host/gpex.h b/include/hw/pci-host/gpex.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/pci-host/gpex.h +++ b/include/hw/pci-host/gpex.h @@ -XXX,XX +XXX,XX @@ struct GPEXHost { MemoryRegion io_ioport; MemoryRegion io_mmio; + MemoryRegion io_ioport_window; + MemoryRegion io_mmio_window; qemu_irq irq[GPEX_NUM_IRQS]; int irq_num[GPEX_NUM_IRQS]; + + bool allow_unmapped_accesses; }; struct GPEXConfig { diff --git a/hw/core/machine.c b/hw/core/machine.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -XXX,XX +XXX,XX @@ #include "hw/virtio/virtio.h" #include "hw/virtio/virtio-pci.h" -GlobalProperty hw_compat_6_0[] = {}; +GlobalProperty hw_compat_6_0[] = { + { "gpex-pcihost", "allow-unmapped-accesses", "false" }, +}; const size_t hw_compat_6_0_len = G_N_ELEMENTS(hw_compat_6_0); GlobalProperty hw_compat_5_2[] = { diff --git a/hw/pci-host/gpex.c b/hw/pci-host/gpex.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-host/gpex.c +++ b/hw/pci-host/gpex.c @@ -XXX,XX +XXX,XX @@ static void gpex_host_realize(DeviceState *dev, Error **errp) int i; pcie_host_mmcfg_init(pex, PCIE_MMCFG_SIZE_MAX); + sysbus_init_mmio(sbd, &pex->mmio); + + /* + * Note that the MemoryRegions io_mmio and io_ioport that we pass + * to pci_register_root_bus() are not the same as the + * MemoryRegions io_mmio_window and io_ioport_window that we + * expose as SysBus MRs. The difference is in the behaviour of + * accesses to addresses where no PCI device has been mapped. + * + * io_mmio and io_ioport are the underlying PCI view of the PCI + * address space, and when a PCI device does a bus master access + * to a bad address this is reported back to it as a transaction + * failure. + * + * io_mmio_window and io_ioport_window implement "unmapped + * addresses read as -1 and ignore writes"; this is traditional + * x86 PC behaviour, which is not mandated by the PCI spec proper + * but expected by much PCI-using guest software, including Linux. + * + * In the interests of not being unnecessarily surprising, we + * implement it in the gpex PCI host controller, by providing the + * _window MRs, which are containers with io ops that implement + * the 'background' behaviour and which hold the real PCI MRs as + * subregions. + */ memory_region_init(&s->io_mmio, OBJECT(s), "gpex_mmio", UINT64_MAX); memory_region_init(&s->io_ioport, OBJECT(s), "gpex_ioport", 64 * 1024); - sysbus_init_mmio(sbd, &pex->mmio); - sysbus_init_mmio(sbd, &s->io_mmio); - sysbus_init_mmio(sbd, &s->io_ioport); + if (s->allow_unmapped_accesses) { + memory_region_init_io(&s->io_mmio_window, OBJECT(s), + &unassigned_io_ops, OBJECT(s), + "gpex_mmio_window", UINT64_MAX); + memory_region_init_io(&s->io_ioport_window, OBJECT(s), + &unassigned_io_ops, OBJECT(s), + "gpex_ioport_window", 64 * 1024); + + memory_region_add_subregion(&s->io_mmio_window, 0, &s->io_mmio); + memory_region_add_subregion(&s->io_ioport_window, 0, &s->io_ioport); + sysbus_init_mmio(sbd, &s->io_mmio_window); + sysbus_init_mmio(sbd, &s->io_ioport_window); + } else { + sysbus_init_mmio(sbd, &s->io_mmio); + sysbus_init_mmio(sbd, &s->io_ioport); + } + for (i = 0; i < GPEX_NUM_IRQS; i++) { sysbus_init_irq(sbd, &s->irq[i]); s->irq_num[i] = -1; @@ -XXX,XX +XXX,XX @@ static const char *gpex_host_root_bus_path(PCIHostState *host_bridge, return "0000:00"; } +static Property gpex_host_properties[] = { + /* + * Permit CPU accesses to unmapped areas of the PIO and MMIO windows + * (discarding writes and returning -1 for reads) rather than aborting. + */ + DEFINE_PROP_BOOL("allow-unmapped-accesses", GPEXHost, + allow_unmapped_accesses, true), + DEFINE_PROP_END_OF_LIST(), +}; + static void gpex_host_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); @@ -XXX,XX +XXX,XX @@ static void gpex_host_class_init(ObjectClass *klass, void *data) dc->realize = gpex_host_realize; set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); dc->fw_name = "pci"; + device_class_set_props(dc, gpex_host_properties); } static void gpex_host_initfn(Object *obj) -- 2.20.1