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 The following changes since commit 4cc10cae64c51e17844dc4358481c393d7bf1ed4: Merge remote-tracking branch 'remotes/bonzini-gitlab/tags/for-upstream' into staging (2021-05-06 18:56:17 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210510 for you to fetch changes up to 8f96812baa53005f32aece3e30b140826c20aa19: hw/arm/xlnx: Fix PHY address for xilinx-zynq-a9 (2021-05-10 13:24:09 +0100) ---------------------------------------------------------------- target-arm queue: * docs: fix link in sbsa description * linux-user/aarch64: Enable hwcap for RND, BTI, and MTE * target/arm: Fix tlbbits calculation in tlbi_aa64_vae2is_write() * target/arm: Split neon and vfp translation to their own compilation units * target/arm: Make WFI a NOP for userspace emulators * hw/sd/omap_mmc: Use device_cold_reset() instead of device_legacy_reset() * include: More fixes for 'extern "C"' block use * hw/arm/imx25_pdk: Fix error message for invalid RAM size * hw/arm/mps2-tz: Implement AN524 memory remapping via machine property * hw/arm/xlnx: Fix PHY address for xilinx-zynq-a9 ---------------------------------------------------------------- Alex Bennée (1): docs: fix link in sbsa description Guenter Roeck (1): hw/arm/xlnx: Fix PHY address for xilinx-zynq-a9 Peter Maydell (22): target/arm: Fix tlbbits calculation in tlbi_aa64_vae2is_write() target/arm: Move constant expanders to translate.h target/arm: Share unallocated_encoding() and gen_exception_insn() target/arm: Make functions used by m-nocp global target/arm: Split m-nocp trans functions into their own file target/arm: Move gen_aa32 functions to translate-a32.h target/arm: Move vfp_{load, store}_reg{32, 64} to translate-vfp.c.inc target/arm: Make functions used by translate-vfp global target/arm: Make translate-vfp.c.inc its own compilation unit target/arm: Move vfp_reg_ptr() to translate-neon.c.inc target/arm: Delete unused typedef target/arm: Move NeonGenThreeOpEnvFn typedef to translate.h target/arm: Make functions used by translate-neon global target/arm: Make translate-neon.c.inc its own compilation unit target/arm: Make WFI a NOP for userspace emulators hw/sd/omap_mmc: Use device_cold_reset() instead of device_legacy_reset() osdep: Make os-win32.h and os-posix.h handle 'extern "C"' themselves include/qemu/bswap.h: Handle being included outside extern "C" block include/disas/dis-asm.h: Handle being included outside 'extern "C"' hw/misc/mps2-scc: Add "QEMU interface" comment hw/misc/mps2-scc: Support using CFG0 bit 0 for remapping hw/arm/mps2-tz: Implement AN524 memory remapping via machine property Philippe Mathieu-Daudé (1): hw/arm/imx25_pdk: Fix error message for invalid RAM size Richard Henderson (1): linux-user/aarch64: Enable hwcap for RND, BTI, and MTE docs/system/arm/mps2.rst | 10 + docs/system/arm/sbsa.rst | 2 +- include/disas/dis-asm.h | 12 +- include/hw/misc/mps2-scc.h | 21 ++ include/qemu/bswap.h | 26 ++- include/qemu/osdep.h | 8 +- include/sysemu/os-posix.h | 8 + include/sysemu/os-win32.h | 8 + target/arm/translate-a32.h | 144 +++++++++++++ target/arm/translate-a64.h | 2 - target/arm/translate.h | 29 +++ hw/arm/imx25_pdk.c | 5 +- hw/arm/mps2-tz.c | 108 +++++++++- hw/arm/xilinx_zynq.c | 2 +- hw/misc/mps2-scc.c | 13 +- hw/sd/omap_mmc.c | 2 +- linux-user/elfload.c | 13 ++ target/arm/helper.c | 2 +- target/arm/op_helper.c | 12 ++ target/arm/translate-a64.c | 15 -- target/arm/translate-m-nocp.c | 221 ++++++++++++++++++++ .../arm/{translate-neon.c.inc => translate-neon.c} | 19 +- .../arm/{translate-vfp.c.inc => translate-vfp.c} | 230 +++------------------ target/arm/translate.c | 200 ++++-------------- disas/arm-a64.cc | 2 - disas/nanomips.cpp | 2 - target/arm/meson.build | 15 +- 27 files changed, 718 insertions(+), 413 deletions(-) create mode 100644 target/arm/translate-a32.h create mode 100644 target/arm/translate-m-nocp.c rename target/arm/{translate-neon.c.inc => translate-neon.c} (99%) rename target/arm/{translate-vfp.c.inc => translate-vfp.c} (94%) From: Alex Bennée <alex.bennee@linaro.org> A trailing _ makes all the difference to the rendered link. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20210428131316.31390-1-alex.bennee@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/sbsa.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/system/arm/sbsa.rst b/docs/system/arm/sbsa.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/sbsa.rst +++ b/docs/system/arm/sbsa.rst @@ -XXX,XX +XXX,XX @@ Arm Server Base System Architecture Reference board (``sbsa-ref``) While the `virt` board is a generic board platform that doesn't match any real hardware the `sbsa-ref` board intends to look like real hardware. The `Server Base System Architecture -<https://developer.arm.com/documentation/den0029/latest>` defines a +<https://developer.arm.com/documentation/den0029/latest>`_ defines a minimum base line of hardware support and importantly how the firmware reports that to any operating system. It is a static system that reports a very minimal DT to the firmware for non-discoverable -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> These three features are already enabled by TCG, but are missing their hwcap bits. Update HWCAP2 from linux v5.12. Cc: qemu-stable@nongnu.org (for 6.0.1) Buglink: https://bugs.launchpad.net/bugs/1926044 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210427214108.88503-1-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/elfload.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ enum { ARM_HWCAP2_A64_SVESM4 = 1 << 6, ARM_HWCAP2_A64_FLAGM2 = 1 << 7, ARM_HWCAP2_A64_FRINT = 1 << 8, + ARM_HWCAP2_A64_SVEI8MM = 1 << 9, + ARM_HWCAP2_A64_SVEF32MM = 1 << 10, + ARM_HWCAP2_A64_SVEF64MM = 1 << 11, + ARM_HWCAP2_A64_SVEBF16 = 1 << 12, + ARM_HWCAP2_A64_I8MM = 1 << 13, + ARM_HWCAP2_A64_BF16 = 1 << 14, + ARM_HWCAP2_A64_DGH = 1 << 15, + ARM_HWCAP2_A64_RNG = 1 << 16, + ARM_HWCAP2_A64_BTI = 1 << 17, + ARM_HWCAP2_A64_MTE = 1 << 18, }; #define ELF_HWCAP get_elf_hwcap() @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap2(void) GET_FEATURE_ID(aa64_dcpodp, ARM_HWCAP2_A64_DCPODP); GET_FEATURE_ID(aa64_condm_5, ARM_HWCAP2_A64_FLAGM2); GET_FEATURE_ID(aa64_frint, ARM_HWCAP2_A64_FRINT); + GET_FEATURE_ID(aa64_rndr, ARM_HWCAP2_A64_RNG); + GET_FEATURE_ID(aa64_bti, ARM_HWCAP2_A64_BTI); + GET_FEATURE_ID(aa64_mte, ARM_HWCAP2_A64_MTE); return hwcaps; } -- 2.20.1 In tlbi_aa64_vae2is_write() the calculation bits = tlbbits_for_regime(env, secure ? ARMMMUIdx_E2 : ARMMMUIdx_SE2, pageaddr) has the two arms of the ?: expression reversed. Fix the bug. Fixes: b6ad6062f1e5 Reported-by: Rebecca Cran <rebecca@nuviainc.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Rebecca Cran <rebecca@nuviainc.com> Message-id: 20210420123106.10861-1-peter.maydell@linaro.org --- target/arm/helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t pageaddr = sextract64(value << 12, 0, 56); bool secure = arm_is_secure_below_el3(env); int mask = secure ? ARMMMUIdxBit_SE2 : ARMMMUIdxBit_E2; - int bits = tlbbits_for_regime(env, secure ? ARMMMUIdx_E2 : ARMMMUIdx_SE2, + int bits = tlbbits_for_regime(env, secure ? ARMMMUIdx_SE2 : ARMMMUIdx_E2, pageaddr); tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, mask, bits); -- 2.20.1 Some of the constant expanders defined in translate.c are generically useful and will be used by the separate C files for VFP and Neon once they are created; move the expander definitions to translate.h. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-2-peter.maydell@linaro.org --- target/arm/translate.h | 24 ++++++++++++++++++++++++ target/arm/translate.c | 24 ------------------------ 2 files changed, 24 insertions(+), 24 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 @@ extern TCGv_i32 cpu_NF, cpu_ZF, cpu_CF, cpu_VF; extern TCGv_i64 cpu_exclusive_addr; extern TCGv_i64 cpu_exclusive_val; +/* + * Constant expanders for the decoders. + */ + +static inline int negate(DisasContext *s, int x) +{ + return -x; +} + +static inline int plus_2(DisasContext *s, int x) +{ + return x + 2; +} + +static inline int times_2(DisasContext *s, int x) +{ + return x * 2; +} + +static inline int times_4(DisasContext *s, int x) +{ + return x * 4; +} + static inline int arm_dc_feature(DisasContext *dc, int feature) { return (dc->features & (1ULL << feature)) != 0; 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_gen_condlabel(DisasContext *s) } } -/* - * Constant expanders for the decoders. - */ - -static int negate(DisasContext *s, int x) -{ - return -x; -} - -static int plus_2(DisasContext *s, int x) -{ - return x + 2; -} - -static int times_2(DisasContext *s, int x) -{ - return x * 2; -} - -static int times_4(DisasContext *s, int x) -{ - return x * 4; -} - /* Flags for the disas_set_da_iss info argument: * lower bits hold the Rt register number, higher bits are flags. */ -- 2.20.1 The unallocated_encoding() function is the same in both translate-a64.c and translate.c; make the translate.c function global and drop the translate-a64.c version. To do this we need to also share gen_exception_insn(), which currently exists in two slightly different versions for A32 and A64: merge those into a single function that can work for both. This will be useful for splitting up translate.c, which will require unallocated_encoding() to no longer be file-local. It's also hopefully less confusing to have only one version of the function rather than two. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-3-peter.maydell@linaro.org --- target/arm/translate-a64.h | 2 -- target/arm/translate.h | 3 +++ target/arm/translate-a64.c | 15 --------------- target/arm/translate.c | 14 +++++++++----- 4 files changed, 12 insertions(+), 22 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 @@ #ifndef TARGET_ARM_TRANSLATE_A64_H #define TARGET_ARM_TRANSLATE_A64_H -void unallocated_encoding(DisasContext *s); - #define unsupported_encoding(s, insn) \ do { \ qemu_log_mask(LOG_UNIMP, \ 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_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); +void unallocated_encoding(DisasContext *s); +void gen_exception_insn(DisasContext *s, uint64_t pc, int excp, + uint32_t syn, uint32_t target_el); /* Return state of Alternate Half-precision flag, caller frees result */ static inline TCGv_i32 get_ahp_flag(void) 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_exception_internal_insn(DisasContext *s, uint64_t pc, int excp) s->base.is_jmp = DISAS_NORETURN; } -static void gen_exception_insn(DisasContext *s, uint64_t pc, int excp, - uint32_t syndrome, uint32_t target_el) -{ - gen_a64_set_pc_im(pc); - gen_exception(excp, syndrome, target_el); - s->base.is_jmp = DISAS_NORETURN; -} - static void gen_exception_bkpt_insn(DisasContext *s, uint32_t syndrome) { TCGv_i32 tcg_syn; @@ -XXX,XX +XXX,XX @@ static inline void gen_goto_tb(DisasContext *s, int n, uint64_t dest) } } -void unallocated_encoding(DisasContext *s) -{ - /* Unallocated and reserved encodings are uncategorized */ - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), - default_exception_el(s)); -} - static void init_tmp_a64_array(DisasContext *s) { #ifdef CONFIG_DEBUG_TCG 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_exception_internal_insn(DisasContext *s, uint32_t pc, int excp) s->base.is_jmp = DISAS_NORETURN; } -static void gen_exception_insn(DisasContext *s, uint32_t pc, int excp, - int syn, uint32_t target_el) +void gen_exception_insn(DisasContext *s, uint64_t pc, int excp, + uint32_t syn, uint32_t target_el) { - gen_set_condexec(s); - gen_set_pc_im(s, pc); + if (s->aarch64) { + gen_a64_set_pc_im(pc); + } else { + gen_set_condexec(s); + gen_set_pc_im(s, pc); + } gen_exception(excp, syn, target_el); s->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static void gen_exception_bkpt_insn(DisasContext *s, uint32_t syn) s->base.is_jmp = DISAS_NORETURN; } -static void unallocated_encoding(DisasContext *s) +void unallocated_encoding(DisasContext *s) { /* Unallocated and reserved encodings are uncategorized */ gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), -- 2.20.1 We want to split out the .c.inc files which are currently included into translate.c so they are separate compilation units. To do this we need to make some functions which are currently file-local to translate.c have global scope; create a translate-a32.h paralleling the existing translate-a64.h as a place for these declarations to live, so that code moved into the new compilation units can call them. The functions made global here are those required by the m-nocp.decode functions, except that I have converted the whole family of {read,write}_neon_element* and also both the load_cpu and store_cpu functions for consistency, even though m-nocp only wants a few functions from each. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-4-peter.maydell@linaro.org --- target/arm/translate-a32.h | 57 ++++++++++++++++++++++++++++++++++ target/arm/translate.c | 39 +++++------------------ target/arm/translate-vfp.c.inc | 2 +- 3 files changed, 65 insertions(+), 33 deletions(-) create mode 100644 target/arm/translate-a32.h diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ +/* + * AArch32 translation, common definitions. + * + * Copyright (c) 2021 Linaro, Ltd. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef TARGET_ARM_TRANSLATE_A64_H +#define TARGET_ARM_TRANSLATE_A64_H + +void load_reg_var(DisasContext *s, TCGv_i32 var, int reg); +void arm_gen_condlabel(DisasContext *s); +bool vfp_access_check(DisasContext *s); +void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop); +void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop); +void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop); +void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop); + +static inline TCGv_i32 load_cpu_offset(int offset) +{ + TCGv_i32 tmp = tcg_temp_new_i32(); + tcg_gen_ld_i32(tmp, cpu_env, offset); + return tmp; +} + +#define load_cpu_field(name) load_cpu_offset(offsetof(CPUARMState, name)) + +static inline void store_cpu_offset(TCGv_i32 var, int offset) +{ + tcg_gen_st_i32(var, cpu_env, offset); + tcg_temp_free_i32(var); +} + +#define store_cpu_field(var, name) \ + store_cpu_offset(var, offsetof(CPUARMState, name)) + +/* Create a new temporary and set it to the value of a CPU register. */ +static inline TCGv_i32 load_reg(DisasContext *s, int reg) +{ + TCGv_i32 tmp = tcg_temp_new_i32(); + load_reg_var(s, tmp, reg); + return tmp; +} + +#endif 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 @@ #define ENABLE_ARCH_8 arm_dc_feature(s, ARM_FEATURE_V8) #include "translate.h" +#include "translate-a32.h" #if defined(CONFIG_USER_ONLY) #define IS_USER(s) 1 @@ -XXX,XX +XXX,XX @@ void arm_translate_init(void) } /* Generate a label used for skipping this instruction */ -static void arm_gen_condlabel(DisasContext *s) +void arm_gen_condlabel(DisasContext *s) { if (!s->condjmp) { s->condlabel = gen_new_label(); @@ -XXX,XX +XXX,XX @@ static inline int get_a32_user_mem_index(DisasContext *s) } } -static inline TCGv_i32 load_cpu_offset(int offset) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_ld_i32(tmp, cpu_env, offset); - return tmp; -} - -#define load_cpu_field(name) load_cpu_offset(offsetof(CPUARMState, name)) - -static inline void store_cpu_offset(TCGv_i32 var, int offset) -{ - tcg_gen_st_i32(var, cpu_env, offset); - tcg_temp_free_i32(var); -} - -#define store_cpu_field(var, name) \ - store_cpu_offset(var, offsetof(CPUARMState, name)) - /* The architectural value of PC. */ static uint32_t read_pc(DisasContext *s) { @@ -XXX,XX +XXX,XX @@ static uint32_t read_pc(DisasContext *s) } /* Set a variable to the value of a CPU register. */ -static void load_reg_var(DisasContext *s, TCGv_i32 var, int reg) +void load_reg_var(DisasContext *s, TCGv_i32 var, int reg) { if (reg == 15) { tcg_gen_movi_i32(var, read_pc(s)); @@ -XXX,XX +XXX,XX @@ static void load_reg_var(DisasContext *s, TCGv_i32 var, int reg) } } -/* Create a new temporary and set it to the value of a CPU register. */ -static inline TCGv_i32 load_reg(DisasContext *s, int reg) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - load_reg_var(s, tmp, reg); - return tmp; -} - /* * Create a new temp, REG + OFS, except PC is ALIGN(PC, 4). * This is used for load/store for which use of PC implies (literal), @@ -XXX,XX +XXX,XX @@ static inline void vfp_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 memop) +void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) { long off = neon_element_offset(reg, ele, memop); @@ -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) +void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) { long off = neon_element_offset(reg, ele, memop); @@ -XXX,XX +XXX,XX @@ static void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) } } -static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) +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) +void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) { long off = neon_element_offset(reg, ele, memop); 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 full_vfp_access_check(DisasContext *s, bool ignore_vfp_enabled) * The most usual kind of VFP access check, for everything except * FMXR/FMRX to the always-available special registers. */ -static bool vfp_access_check(DisasContext *s) +bool vfp_access_check(DisasContext *s) { return full_vfp_access_check(s, false); } -- 2.20.1 Currently the trans functions for m-nocp.decode all live in translate-vfp.inc.c; move them out into their own translation unit, translate-m-nocp.c. The trans_* functions here are pure code motion with no changes. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-5-peter.maydell@linaro.org --- target/arm/translate-a32.h | 3 + target/arm/translate-m-nocp.c | 221 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 1 - target/arm/translate-vfp.c.inc | 196 ----------------------------- target/arm/meson.build | 3 +- 5 files changed, 226 insertions(+), 198 deletions(-) create mode 100644 target/arm/translate-m-nocp.c diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ #ifndef TARGET_ARM_TRANSLATE_A64_H #define TARGET_ARM_TRANSLATE_A64_H +/* Prototypes for autogenerated disassembler functions */ +bool disas_m_nocp(DisasContext *dc, uint32_t insn); + void load_reg_var(DisasContext *s, TCGv_i32 var, int reg); void arm_gen_condlabel(DisasContext *s); bool vfp_access_check(DisasContext *s); diff --git a/target/arm/translate-m-nocp.c b/target/arm/translate-m-nocp.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/translate-m-nocp.c @@ -XXX,XX +XXX,XX @@ +/* + * ARM translation: M-profile NOCP special-case instructions + * + * Copyright (c) 2020 Linaro, Ltd. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "tcg/tcg-op.h" +#include "translate.h" +#include "translate-a32.h" + +#include "decode-m-nocp.c.inc" + +/* + * Decode VLLDM and VLSTM are nonstandard because: + * * if there is no FPU then these insns must NOP in + * Secure state and UNDEF in Nonsecure state + * * if there is an FPU then these insns do not have + * the usual behaviour that vfp_access_check() provides of + * being controlled by CPACR/NSACR enable bits or the + * lazy-stacking logic. + */ +static bool trans_VLLDM_VLSTM(DisasContext *s, arg_VLLDM_VLSTM *a) +{ + TCGv_i32 fptr; + + if (!arm_dc_feature(s, ARM_FEATURE_M) || + !arm_dc_feature(s, ARM_FEATURE_V8)) { + return false; + } + + if (a->op) { + /* + * T2 encoding ({D0-D31} reglist): v8.1M and up. We choose not + * to take the IMPDEF option to make memory accesses to the stack + * slots that correspond to the D16-D31 registers (discarding + * read data and writing UNKNOWN values), so for us the T2 + * encoding behaves identically to the T1 encoding. + */ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + } else { + /* + * T1 encoding ({D0-D15} reglist); undef if we have 32 Dregs. + * This is currently architecturally impossible, but we add the + * check to stay in line with the pseudocode. Note that we must + * emit code for the UNDEF so it takes precedence over the NOCP. + */ + if (dc_isar_feature(aa32_simd_r32, s)) { + unallocated_encoding(s); + return true; + } + } + + /* + * If not secure, UNDEF. We must emit code for this + * rather than returning false so that this takes + * precedence over the m-nocp.decode NOCP fallback. + */ + if (!s->v8m_secure) { + unallocated_encoding(s); + return true; + } + /* If no fpu, NOP. */ + if (!dc_isar_feature(aa32_vfp, s)) { + return true; + } + + fptr = load_reg(s, a->rn); + if (a->l) { + gen_helper_v7m_vlldm(cpu_env, fptr); + } else { + gen_helper_v7m_vlstm(cpu_env, fptr); + } + tcg_temp_free_i32(fptr); + + /* End the TB, because we have updated FP control bits */ + s->base.is_jmp = DISAS_UPDATE_EXIT; + return true; +} + +static bool trans_VSCCLRM(DisasContext *s, arg_VSCCLRM *a) +{ + int btmreg, topreg; + TCGv_i64 zero; + TCGv_i32 aspen, sfpa; + + if (!dc_isar_feature(aa32_m_sec_state, s)) { + /* Before v8.1M, fall through in decode to NOCP check */ + return false; + } + + /* Explicitly UNDEF because this takes precedence over NOCP */ + if (!arm_dc_feature(s, ARM_FEATURE_M_MAIN) || !s->v8m_secure) { + unallocated_encoding(s); + return true; + } + + if (!dc_isar_feature(aa32_vfp_simd, s)) { + /* NOP if we have neither FP nor MVE */ + return true; + } + + /* + * If FPCCR.ASPEN != 0 && CONTROL_S.SFPA == 0 then there is no + * active floating point context so we must NOP (without doing + * any lazy state preservation or the NOCP check). + */ + aspen = load_cpu_field(v7m.fpccr[M_REG_S]); + sfpa = load_cpu_field(v7m.control[M_REG_S]); + tcg_gen_andi_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); + tcg_gen_xori_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); + tcg_gen_andi_i32(sfpa, sfpa, R_V7M_CONTROL_SFPA_MASK); + tcg_gen_or_i32(sfpa, sfpa, aspen); + arm_gen_condlabel(s); + tcg_gen_brcondi_i32(TCG_COND_EQ, sfpa, 0, s->condlabel); + + if (s->fp_excp_el != 0) { + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, + syn_uncategorized(), s->fp_excp_el); + return true; + } + + topreg = a->vd + a->imm - 1; + btmreg = a->vd; + + /* Convert to Sreg numbers if the insn specified in Dregs */ + if (a->size == 3) { + topreg = topreg * 2 + 1; + btmreg *= 2; + } + + if (topreg > 63 || (topreg > 31 && !(topreg & 1))) { + /* UNPREDICTABLE: we choose to undef */ + unallocated_encoding(s); + return true; + } + + /* Silently ignore requests to clear D16-D31 if they don't exist */ + if (topreg > 31 && !dc_isar_feature(aa32_simd_r32, s)) { + topreg = 31; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* Zero the Sregs from btmreg to topreg inclusive. */ + zero = tcg_const_i64(0); + if (btmreg & 1) { + write_neon_element64(zero, btmreg >> 1, 1, MO_32); + btmreg++; + } + for (; btmreg + 1 <= topreg; btmreg += 2) { + write_neon_element64(zero, btmreg >> 1, 0, MO_64); + } + if (btmreg == topreg) { + write_neon_element64(zero, btmreg >> 1, 0, MO_32); + btmreg++; + } + assert(btmreg == topreg + 1); + /* TODO: when MVE is implemented, zero VPR here */ + return true; +} + +static bool trans_NOCP(DisasContext *s, arg_nocp *a) +{ + /* + * Handle M-profile early check for disabled coprocessor: + * all we need to do here is emit the NOCP exception if + * the coprocessor is disabled. Otherwise we return false + * and the real VFP/etc decode will handle the insn. + */ + assert(arm_dc_feature(s, ARM_FEATURE_M)); + + if (a->cp == 11) { + a->cp = 10; + } + if (arm_dc_feature(s, ARM_FEATURE_V8_1M) && + (a->cp == 8 || a->cp == 9 || a->cp == 14 || a->cp == 15)) { + /* in v8.1M cp 8, 9, 14, 15 also are governed by the cp10 enable */ + a->cp = 10; + } + + if (a->cp != 10) { + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, + syn_uncategorized(), default_exception_el(s)); + return true; + } + + if (s->fp_excp_el != 0) { + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, + syn_uncategorized(), s->fp_excp_el); + return true; + } + + return false; +} + +static bool trans_NOCP_8_1(DisasContext *s, arg_nocp *a) +{ + /* This range needs a coprocessor check for v8.1M and later only */ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + return trans_NOCP(s, a); +} 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 TCGv_ptr vfp_reg_ptr(bool dp, int reg) #define ARM_CP_RW_BIT (1 << 20) /* Include the VFP and Neon decoders */ -#include "decode-m-nocp.c.inc" #include "translate-vfp.c.inc" #include "translate-neon.c.inc" 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_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) return true; } -/* - * Decode VLLDM and VLSTM are nonstandard because: - * * if there is no FPU then these insns must NOP in - * Secure state and UNDEF in Nonsecure state - * * if there is an FPU then these insns do not have - * the usual behaviour that vfp_access_check() provides of - * being controlled by CPACR/NSACR enable bits or the - * lazy-stacking logic. - */ -static bool trans_VLLDM_VLSTM(DisasContext *s, arg_VLLDM_VLSTM *a) -{ - TCGv_i32 fptr; - - if (!arm_dc_feature(s, ARM_FEATURE_M) || - !arm_dc_feature(s, ARM_FEATURE_V8)) { - return false; - } - - if (a->op) { - /* - * T2 encoding ({D0-D31} reglist): v8.1M and up. We choose not - * to take the IMPDEF option to make memory accesses to the stack - * slots that correspond to the D16-D31 registers (discarding - * read data and writing UNKNOWN values), so for us the T2 - * encoding behaves identically to the T1 encoding. - */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { - return false; - } - } else { - /* - * T1 encoding ({D0-D15} reglist); undef if we have 32 Dregs. - * This is currently architecturally impossible, but we add the - * check to stay in line with the pseudocode. Note that we must - * emit code for the UNDEF so it takes precedence over the NOCP. - */ - if (dc_isar_feature(aa32_simd_r32, s)) { - unallocated_encoding(s); - return true; - } - } - - /* - * If not secure, UNDEF. We must emit code for this - * rather than returning false so that this takes - * precedence over the m-nocp.decode NOCP fallback. - */ - if (!s->v8m_secure) { - unallocated_encoding(s); - return true; - } - /* If no fpu, NOP. */ - if (!dc_isar_feature(aa32_vfp, s)) { - return true; - } - - fptr = load_reg(s, a->rn); - if (a->l) { - gen_helper_v7m_vlldm(cpu_env, fptr); - } else { - gen_helper_v7m_vlstm(cpu_env, fptr); - } - tcg_temp_free_i32(fptr); - - /* End the TB, because we have updated FP control bits */ - s->base.is_jmp = DISAS_UPDATE_EXIT; - return true; -} - -static bool trans_VSCCLRM(DisasContext *s, arg_VSCCLRM *a) -{ - int btmreg, topreg; - TCGv_i64 zero; - TCGv_i32 aspen, sfpa; - - if (!dc_isar_feature(aa32_m_sec_state, s)) { - /* Before v8.1M, fall through in decode to NOCP check */ - return false; - } - - /* Explicitly UNDEF because this takes precedence over NOCP */ - if (!arm_dc_feature(s, ARM_FEATURE_M_MAIN) || !s->v8m_secure) { - unallocated_encoding(s); - return true; - } - - if (!dc_isar_feature(aa32_vfp_simd, s)) { - /* NOP if we have neither FP nor MVE */ - return true; - } - - /* - * If FPCCR.ASPEN != 0 && CONTROL_S.SFPA == 0 then there is no - * active floating point context so we must NOP (without doing - * any lazy state preservation or the NOCP check). - */ - aspen = load_cpu_field(v7m.fpccr[M_REG_S]); - sfpa = load_cpu_field(v7m.control[M_REG_S]); - tcg_gen_andi_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); - tcg_gen_xori_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); - tcg_gen_andi_i32(sfpa, sfpa, R_V7M_CONTROL_SFPA_MASK); - tcg_gen_or_i32(sfpa, sfpa, aspen); - arm_gen_condlabel(s); - tcg_gen_brcondi_i32(TCG_COND_EQ, sfpa, 0, s->condlabel); - - if (s->fp_excp_el != 0) { - gen_exception_insn(s, s->pc_curr, EXCP_NOCP, - syn_uncategorized(), s->fp_excp_el); - return true; - } - - topreg = a->vd + a->imm - 1; - btmreg = a->vd; - - /* Convert to Sreg numbers if the insn specified in Dregs */ - if (a->size == 3) { - topreg = topreg * 2 + 1; - btmreg *= 2; - } - - if (topreg > 63 || (topreg > 31 && !(topreg & 1))) { - /* UNPREDICTABLE: we choose to undef */ - unallocated_encoding(s); - return true; - } - - /* Silently ignore requests to clear D16-D31 if they don't exist */ - if (topreg > 31 && !dc_isar_feature(aa32_simd_r32, s)) { - topreg = 31; - } - - if (!vfp_access_check(s)) { - return true; - } - - /* Zero the Sregs from btmreg to topreg inclusive. */ - zero = tcg_const_i64(0); - if (btmreg & 1) { - write_neon_element64(zero, btmreg >> 1, 1, MO_32); - btmreg++; - } - for (; btmreg + 1 <= topreg; btmreg += 2) { - write_neon_element64(zero, btmreg >> 1, 0, MO_64); - } - if (btmreg == topreg) { - write_neon_element64(zero, btmreg >> 1, 0, MO_32); - btmreg++; - } - assert(btmreg == topreg + 1); - /* TODO: when MVE is implemented, zero VPR here */ - return true; -} - -static bool trans_NOCP(DisasContext *s, arg_nocp *a) -{ - /* - * Handle M-profile early check for disabled coprocessor: - * all we need to do here is emit the NOCP exception if - * the coprocessor is disabled. Otherwise we return false - * and the real VFP/etc decode will handle the insn. - */ - assert(arm_dc_feature(s, ARM_FEATURE_M)); - - if (a->cp == 11) { - a->cp = 10; - } - if (arm_dc_feature(s, ARM_FEATURE_V8_1M) && - (a->cp == 8 || a->cp == 9 || a->cp == 14 || a->cp == 15)) { - /* in v8.1M cp 8, 9, 14, 15 also are governed by the cp10 enable */ - a->cp = 10; - } - - if (a->cp != 10) { - gen_exception_insn(s, s->pc_curr, EXCP_NOCP, - syn_uncategorized(), default_exception_el(s)); - return true; - } - - if (s->fp_excp_el != 0) { - gen_exception_insn(s, s->pc_curr, EXCP_NOCP, - syn_uncategorized(), s->fp_excp_el); - return true; - } - - return false; -} - -static bool trans_NOCP_8_1(DisasContext *s, arg_nocp *a) -{ - /* This range needs a coprocessor check for v8.1M and later only */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { - return false; - } - return trans_NOCP(s, a); -} - static bool trans_VINS(DisasContext *s, arg_VINS *a) { TCGv_i32 rd, rm; diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ gen = [ decodetree.process('neon-ls.decode', extra_args: '--static-decode=disas_neon_ls'), decodetree.process('vfp.decode', extra_args: '--static-decode=disas_vfp'), decodetree.process('vfp-uncond.decode', extra_args: '--static-decode=disas_vfp_uncond'), - decodetree.process('m-nocp.decode', extra_args: '--static-decode=disas_m_nocp'), + decodetree.process('m-nocp.decode', extra_args: '--decode=disas_m_nocp'), decodetree.process('a32.decode', extra_args: '--static-decode=disas_a32'), decodetree.process('a32-uncond.decode', extra_args: '--static-decode=disas_a32_uncond'), decodetree.process('t32.decode', extra_args: '--static-decode=disas_t32'), @@ -XXX,XX +XXX,XX @@ arm_ss.add(files( 'op_helper.c', 'tlb_helper.c', 'translate.c', + 'translate-m-nocp.c', 'vec_helper.c', 'vfp_helper.c', 'cpu_tcg.c', -- 2.20.1 Move the various gen_aa32* functions and macros out of translate.c and into translate-a32.h. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-6-peter.maydell@linaro.org --- target/arm/translate-a32.h | 53 ++++++++++++++++++++++++++++++++++++++ target/arm/translate.c | 51 ++++++++++++------------------------ 2 files changed, 69 insertions(+), 35 deletions(-) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 load_reg(DisasContext *s, int reg) return tmp; } +void gen_aa32_ld_internal_i32(DisasContext *s, TCGv_i32 val, + TCGv_i32 a32, int index, MemOp opc); +void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val, + TCGv_i32 a32, int index, MemOp opc); +void gen_aa32_ld_internal_i64(DisasContext *s, TCGv_i64 val, + TCGv_i32 a32, int index, MemOp opc); +void gen_aa32_st_internal_i64(DisasContext *s, TCGv_i64 val, + TCGv_i32 a32, int index, MemOp opc); +void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, + int index, MemOp opc); +void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, + int index, MemOp opc); +void gen_aa32_ld_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, + int index, MemOp opc); +void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, + int index, MemOp opc); + +#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); \ + } + +#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_ld64(DisasContext *s, TCGv_i64 val, + TCGv_i32 a32, int index) +{ + 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); +} + +DO_GEN_LD(8u, MO_UB) +DO_GEN_LD(16u, MO_UW) +DO_GEN_LD(32u, MO_UL) +DO_GEN_ST(8, MO_UB) +DO_GEN_ST(16, MO_UW) +DO_GEN_ST(32, MO_UL) + +#undef DO_GEN_LD +#undef DO_GEN_ST + #endif 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 TCGv gen_aa32_addr(DisasContext *s, TCGv_i32 a32, MemOp op) * 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) +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) +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_internal_i64(DisasContext *s, TCGv_i64 val, - TCGv_i32 a32, int index, MemOp opc) +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); @@ -XXX,XX +XXX,XX @@ static void gen_aa32_ld_internal_i64(DisasContext *s, TCGv_i64 val, tcg_temp_free(addr); } -static void gen_aa32_st_internal_i64(DisasContext *s, TCGv_i64 val, - TCGv_i32 a32, int index, MemOp opc) +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); @@ -XXX,XX +XXX,XX @@ static void gen_aa32_st_internal_i64(DisasContext *s, TCGv_i64 val, tcg_temp_free(addr); } -static void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, - int index, MemOp opc) +void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, + int index, MemOp opc) { 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) +void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, + int index, MemOp opc) { 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) +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) +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)); } @@ -XXX,XX +XXX,XX @@ static void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, gen_aa32_st_i32(s, val, a32, index, OPC); \ } -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); -} - -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); -} - -DO_GEN_LD(8u, MO_UB) -DO_GEN_LD(16u, MO_UW) -DO_GEN_LD(32u, MO_UL) -DO_GEN_ST(8, MO_UB) -DO_GEN_ST(16, MO_UW) -DO_GEN_ST(32, MO_UL) - static inline void gen_hvc(DisasContext *s, int imm16) { /* The pre HVC helper handles cases when HVC gets trapped -- 2.20.1 The functions vfp_load_reg32(), vfp_load_reg64(), vfp_store_reg32() and vfp_store_reg64() are used only in translate-vfp.c.inc. Move them to that file. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-7-peter.maydell@linaro.org --- target/arm/translate.c | 20 -------------------- target/arm/translate-vfp.c.inc | 20 ++++++++++++++++++++ 2 files changed, 20 insertions(+), 20 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 vfp_load_reg64(TCGv_i64 var, int reg) -{ - tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(true, reg)); -} - -static inline void vfp_store_reg64(TCGv_i64 var, int reg) -{ - tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(true, 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 vfp_store_reg32(TCGv_i32 var, int reg) -{ - tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); -} - void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) { long off = neon_element_offset(reg, ele, memop); 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 @@ #include "decode-vfp.c.inc" #include "decode-vfp-uncond.c.inc" +static inline void vfp_load_reg64(TCGv_i64 var, int reg) +{ + tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(true, reg)); +} + +static inline void vfp_store_reg64(TCGv_i64 var, int reg) +{ + tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(true, 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 vfp_store_reg32(TCGv_i32 var, int reg) +{ + tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); +} + /* * The imm8 encodes the sign bit, enough bits to represent an exponent in * the range 01....1xx to 10....0xx, and the most significant 4 bits of -- 2.20.1 Make the remaining functions which are needed by translate-vfp.c.inc global. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-8-peter.maydell@linaro.org --- target/arm/translate-a32.h | 18 ++++++++++++++++++ target/arm/translate.c | 25 ++++++++----------------- 2 files changed, 26 insertions(+), 17 deletions(-) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop); void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop); void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop); void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop); +TCGv_i32 add_reg_for_lit(DisasContext *s, int reg, int ofs); +void gen_set_cpsr(TCGv_i32 var, uint32_t mask); +void gen_set_condexec(DisasContext *s); +void gen_set_pc_im(DisasContext *s, target_ulong val); +void gen_lookup_tb(DisasContext *s); +long vfp_reg_offset(bool dp, unsigned reg); +long neon_full_reg_offset(unsigned reg); static inline TCGv_i32 load_cpu_offset(int offset) { @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 load_reg(DisasContext *s, int reg) return tmp; } +void store_reg(DisasContext *s, int reg, TCGv_i32 var); + void gen_aa32_ld_internal_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, int index, MemOp opc); void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val, @@ -XXX,XX +XXX,XX @@ DO_GEN_ST(32, MO_UL) #undef DO_GEN_LD #undef DO_GEN_ST +#if defined(CONFIG_USER_ONLY) +#define IS_USER(s) 1 +#else +#define IS_USER(s) (s->user) +#endif + +/* Set NZCV flags from the high 4 bits of var. */ +#define gen_set_nzcv(var) gen_set_cpsr(var, CPSR_NZCV) + #endif 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 @@ #include "translate.h" #include "translate-a32.h" -#if defined(CONFIG_USER_ONLY) -#define IS_USER(s) 1 -#else -#define IS_USER(s) (s->user) -#endif - /* These are TCG temporaries used only by the legacy iwMMXt decoder */ static TCGv_i64 cpu_V0, cpu_V1, cpu_M0; /* These are TCG globals which alias CPUARMState fields */ @@ -XXX,XX +XXX,XX @@ void load_reg_var(DisasContext *s, TCGv_i32 var, int reg) * This is used for load/store for which use of PC implies (literal), * or ADD that implies ADR. */ -static TCGv_i32 add_reg_for_lit(DisasContext *s, int reg, int ofs) +TCGv_i32 add_reg_for_lit(DisasContext *s, int reg, int ofs) { TCGv_i32 tmp = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static TCGv_i32 add_reg_for_lit(DisasContext *s, int reg, int ofs) /* Set a CPU register. The source must be a temporary and will be marked as dead. */ -static void store_reg(DisasContext *s, int reg, TCGv_i32 var) +void store_reg(DisasContext *s, int reg, TCGv_i32 var) { if (reg == 15) { /* In Thumb mode, we must ignore bit 0. @@ -XXX,XX +XXX,XX @@ static void store_sp_checked(DisasContext *s, TCGv_i32 var) #define gen_sxtb16(var) gen_helper_sxtb16(var, var) #define gen_uxtb16(var) gen_helper_uxtb16(var, var) - -static inline void gen_set_cpsr(TCGv_i32 var, uint32_t mask) +void gen_set_cpsr(TCGv_i32 var, uint32_t mask) { TCGv_i32 tmp_mask = tcg_const_i32(mask); gen_helper_cpsr_write(cpu_env, var, tmp_mask); tcg_temp_free_i32(tmp_mask); } -/* Set NZCV flags from the high 4 bits of var. */ -#define gen_set_nzcv(var) gen_set_cpsr(var, CPSR_NZCV) static void gen_exception_internal(int excp) { @@ -XXX,XX +XXX,XX @@ void arm_gen_test_cc(int cc, TCGLabel *label) arm_free_cc(&cmp); } -static inline void gen_set_condexec(DisasContext *s) +void gen_set_condexec(DisasContext *s) { if (s->condexec_mask) { uint32_t val = (s->condexec_cond << 4) | (s->condexec_mask >> 1); @@ -XXX,XX +XXX,XX @@ static inline void gen_set_condexec(DisasContext *s) } } -static inline void gen_set_pc_im(DisasContext *s, target_ulong val) +void gen_set_pc_im(DisasContext *s, target_ulong val) { tcg_gen_movi_i32(cpu_R[15], val); } @@ -XXX,XX +XXX,XX @@ static void gen_exception_el(DisasContext *s, int excp, uint32_t syn, } /* Force a TB lookup after an instruction that changes the CPU state. */ -static inline void gen_lookup_tb(DisasContext *s) +void gen_lookup_tb(DisasContext *s) { tcg_gen_movi_i32(cpu_R[15], s->base.pc_next); s->base.is_jmp = DISAS_EXIT; @@ -XXX,XX +XXX,XX @@ static inline void gen_hlt(DisasContext *s, int imm) /* * Return the offset of a "full" NEON Dreg. */ -static long neon_full_reg_offset(unsigned reg) +long neon_full_reg_offset(unsigned reg) { return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); } @@ -XXX,XX +XXX,XX @@ static long neon_element_offset(int reg, int element, MemOp memop) } /* Return the offset of a VFP Dreg (dp = true) or VFP Sreg (dp = false). */ -static long vfp_reg_offset(bool dp, unsigned reg) +long vfp_reg_offset(bool dp, unsigned reg) { if (dp) { return neon_element_offset(reg, 0, MO_64); -- 2.20.1 Switch translate-vfp.c.inc from being #included into translate.c to being its own compilation unit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-9-peter.maydell@linaro.org --- target/arm/translate-a32.h | 2 ++ target/arm/{translate-vfp.c.inc => translate-vfp.c} | 12 +++++++----- target/arm/translate.c | 3 +-- target/arm/meson.build | 5 +++-- 4 files changed, 13 insertions(+), 9 deletions(-) rename target/arm/{translate-vfp.c.inc => translate-vfp.c} (99%) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ /* Prototypes for autogenerated disassembler functions */ bool disas_m_nocp(DisasContext *dc, uint32_t insn); +bool disas_vfp(DisasContext *s, uint32_t insn); +bool disas_vfp_uncond(DisasContext *s, uint32_t insn); void load_reg_var(DisasContext *s, TCGv_i32 var, int reg); void arm_gen_condlabel(DisasContext *s); diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c similarity index 99% rename from target/arm/translate-vfp.c.inc rename to target/arm/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c @@ -XXX,XX +XXX,XX @@ * License along with this library; if not, see <http://www.gnu.org/licenses/>. */ -/* - * This file is intended to be included from translate.c; it uses - * some macros and definitions provided by that file. - * It might be possible to convert it to a standalone .c file eventually. - */ +#include "qemu/osdep.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" +#include "exec/exec-all.h" +#include "exec/gen-icount.h" +#include "translate.h" +#include "translate-a32.h" /* Include the generated VFP decoder */ #include "decode-vfp.c.inc" 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 TCGv_ptr vfp_reg_ptr(bool dp, int reg) #define ARM_CP_RW_BIT (1 << 20) -/* Include the VFP and Neon decoders */ -#include "translate-vfp.c.inc" +/* Include the Neon decoder */ #include "translate-neon.c.inc" static inline void iwmmxt_load_reg(TCGv_i64 var, int reg) diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ gen = [ decodetree.process('neon-shared.decode', extra_args: '--static-decode=disas_neon_shared'), decodetree.process('neon-dp.decode', extra_args: '--static-decode=disas_neon_dp'), decodetree.process('neon-ls.decode', extra_args: '--static-decode=disas_neon_ls'), - decodetree.process('vfp.decode', extra_args: '--static-decode=disas_vfp'), - decodetree.process('vfp-uncond.decode', extra_args: '--static-decode=disas_vfp_uncond'), + decodetree.process('vfp.decode', extra_args: '--decode=disas_vfp'), + decodetree.process('vfp-uncond.decode', extra_args: '--decode=disas_vfp_uncond'), decodetree.process('m-nocp.decode', extra_args: '--decode=disas_m_nocp'), decodetree.process('a32.decode', extra_args: '--static-decode=disas_a32'), decodetree.process('a32-uncond.decode', extra_args: '--static-decode=disas_a32_uncond'), @@ -XXX,XX +XXX,XX @@ arm_ss.add(files( 'tlb_helper.c', 'translate.c', 'translate-m-nocp.c', + 'translate-vfp.c', 'vec_helper.c', 'vfp_helper.c', 'cpu_tcg.c', -- 2.20.1 The function vfp_reg_ptr() is used only in translate-neon.c.inc; move it there. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-10-peter.maydell@linaro.org --- target/arm/translate.c | 7 ------- target/arm/translate-neon.c.inc | 7 +++++++ 2 files changed, 7 insertions(+), 7 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 @@ void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) } } -static TCGv_ptr vfp_reg_ptr(bool dp, int reg) -{ - TCGv_ptr ret = tcg_temp_new_ptr(); - tcg_gen_addi_ptr(ret, cpu_env, vfp_reg_offset(dp, reg)); - return ret; -} - #define ARM_CP_RW_BIT (1 << 20) /* Include the Neon decoder */ 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" +static TCGv_ptr vfp_reg_ptr(bool dp, int reg) +{ + TCGv_ptr ret = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(ret, cpu_env, vfp_reg_offset(dp, reg)); + return ret; +} + 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 The VFPGenFixPointFn typedef is unused; delete it. 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: 20210430132740.10391-11-peter.maydell@linaro.org --- target/arm/translate.c | 2 -- 1 file changed, 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 const char * const regnames[] = /* Function prototypes for gen_ functions calling Neon helpers. */ typedef void NeonGenThreeOpEnvFn(TCGv_i32, TCGv_env, TCGv_i32, TCGv_i32, TCGv_i32); -/* Function prototypes for gen_ functions for fix point conversions */ -typedef void VFPGenFixPointFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); /* initialize TCG globals. */ void arm_translate_init(void) -- 2.20.1 Move the NeonGenThreeOpEnvFn typedef to translate.h together with the other similar typedefs. 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: 20210430132740.10391-12-peter.maydell@linaro.org --- target/arm/translate.h | 2 ++ target/arm/translate.c | 3 --- 2 files changed, 2 insertions(+), 3 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 @@ typedef void NeonGenOneOpFn(TCGv_i32, TCGv_i32); typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32); typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32); typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); +typedef void NeonGenThreeOpEnvFn(TCGv_i32, TCGv_env, TCGv_i32, + TCGv_i32, TCGv_i32); typedef void NeonGenTwo64OpFn(TCGv_i64, TCGv_i64, TCGv_i64); typedef void NeonGenTwo64OpEnvFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i64); typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64); 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 const char * const regnames[] = { "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "pc" }; -/* Function prototypes for gen_ functions calling Neon helpers. */ -typedef void NeonGenThreeOpEnvFn(TCGv_i32, TCGv_env, TCGv_i32, - TCGv_i32, TCGv_i32); /* initialize TCG globals. */ void arm_translate_init(void) -- 2.20.1 Make the remaining functions needed by the translate-neon code global. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-13-peter.maydell@linaro.org --- target/arm/translate-a32.h | 8 ++++++++ target/arm/translate.c | 10 ++-------- 2 files changed, 10 insertions(+), 8 deletions(-) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ void gen_set_pc_im(DisasContext *s, target_ulong val); void gen_lookup_tb(DisasContext *s); long vfp_reg_offset(bool dp, unsigned reg); long neon_full_reg_offset(unsigned reg); +long neon_element_offset(int reg, int element, MemOp memop); +void gen_rev16(TCGv_i32 dest, TCGv_i32 var); static inline TCGv_i32 load_cpu_offset(int offset) { @@ -XXX,XX +XXX,XX @@ DO_GEN_ST(32, MO_UL) /* Set NZCV flags from the high 4 bits of var. */ #define gen_set_nzcv(var) gen_set_cpsr(var, CPSR_NZCV) +/* Swap low and high halfwords. */ +static inline void gen_swap_half(TCGv_i32 dest, TCGv_i32 var) +{ + tcg_gen_rotri_i32(dest, var, 16); +} + #endif 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_smul_dual(TCGv_i32 a, TCGv_i32 b) } /* Byteswap each halfword. */ -static void gen_rev16(TCGv_i32 dest, TCGv_i32 var) +void gen_rev16(TCGv_i32 dest, TCGv_i32 var) { TCGv_i32 tmp = tcg_temp_new_i32(); TCGv_i32 mask = tcg_const_i32(0x00ff00ff); @@ -XXX,XX +XXX,XX @@ static void gen_revsh(TCGv_i32 dest, TCGv_i32 var) tcg_gen_ext16s_i32(dest, var); } -/* Swap low and high halfwords. */ -static void gen_swap_half(TCGv_i32 dest, TCGv_i32 var) -{ - tcg_gen_rotri_i32(dest, var, 16); -} - /* Dual 16-bit add. Result placed in t0 and t1 is marked as dead. tmp = (t0 ^ t1) & 0x8000; t0 &= ~0x8000; @@ -XXX,XX +XXX,XX @@ 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 memop) +long neon_element_offset(int reg, int element, MemOp memop) { int element_size = 1 << (memop & MO_SIZE); int ofs = element * element_size; -- 2.20.1 Switch translate-neon.c.inc from being #included into translate.c to being its own compilation unit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-14-peter.maydell@linaro.org --- target/arm/translate-a32.h | 3 +++ .../arm/{translate-neon.c.inc => translate-neon.c} | 12 +++++++----- target/arm/translate.c | 3 --- target/arm/meson.build | 7 ++++--- 4 files changed, 14 insertions(+), 11 deletions(-) rename target/arm/{translate-neon.c.inc => translate-neon.c} (99%) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ bool disas_m_nocp(DisasContext *dc, uint32_t insn); bool disas_vfp(DisasContext *s, uint32_t insn); bool disas_vfp_uncond(DisasContext *s, uint32_t insn); +bool disas_neon_dp(DisasContext *s, uint32_t insn); +bool disas_neon_ls(DisasContext *s, uint32_t insn); +bool disas_neon_shared(DisasContext *s, uint32_t insn); void load_reg_var(DisasContext *s, TCGv_i32 var, int reg); void arm_gen_condlabel(DisasContext *s); diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c similarity index 99% rename from target/arm/translate-neon.c.inc rename to target/arm/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c @@ -XXX,XX +XXX,XX @@ * License along with this library; if not, see <http://www.gnu.org/licenses/>. */ -/* - * This file is intended to be included from translate.c; it uses - * some macros and definitions provided by that file. - * It might be possible to convert it to a standalone .c file eventually. - */ +#include "qemu/osdep.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" +#include "exec/exec-all.h" +#include "exec/gen-icount.h" +#include "translate.h" +#include "translate-a32.h" static inline int plus1(DisasContext *s, int x) { 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 @@ void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) #define ARM_CP_RW_BIT (1 << 20) -/* Include the Neon decoder */ -#include "translate-neon.c.inc" - static inline void iwmmxt_load_reg(TCGv_i64 var, int reg) { tcg_gen_ld_i64(var, cpu_env, offsetof(CPUARMState, iwmmxt.regs[reg])); diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ gen = [ decodetree.process('sve.decode', extra_args: '--decode=disas_sve'), - decodetree.process('neon-shared.decode', extra_args: '--static-decode=disas_neon_shared'), - decodetree.process('neon-dp.decode', extra_args: '--static-decode=disas_neon_dp'), - decodetree.process('neon-ls.decode', extra_args: '--static-decode=disas_neon_ls'), + decodetree.process('neon-shared.decode', extra_args: '--decode=disas_neon_shared'), + decodetree.process('neon-dp.decode', extra_args: '--decode=disas_neon_dp'), + decodetree.process('neon-ls.decode', extra_args: '--decode=disas_neon_ls'), decodetree.process('vfp.decode', extra_args: '--decode=disas_vfp'), decodetree.process('vfp-uncond.decode', extra_args: '--decode=disas_vfp_uncond'), decodetree.process('m-nocp.decode', extra_args: '--decode=disas_m_nocp'), @@ -XXX,XX +XXX,XX @@ arm_ss.add(files( 'tlb_helper.c', 'translate.c', 'translate-m-nocp.c', + 'translate-neon.c', 'translate-vfp.c', 'vec_helper.c', 'vfp_helper.c', -- 2.20.1 The WFI insn is not system-mode only, though it doesn't usually make a huge amount of sense for userspace code to execute it. Currently if you try it in qemu-arm then the helper function will raise an EXCP_HLT exception, which is not covered by the switch in cpu_loop() and results in an abort: qemu: unhandled CPU exception 0x10001 - aborting R00=00000001 R01=408003e4 R02=408003ec R03=000102ec R04=00010a28 R05=00010158 R06=00087460 R07=00010158 R08=00000000 R09=00000000 R10=00085b7c R11=408002a4 R12=408002b8 R13=408002a0 R14=0001057c R15=000102f8 PSR=60000010 -ZC- A usr32 qemu:handle_cpu_signal received signal outside vCPU context @ pc=0x7fcbfa4f0a12 Make the WFI helper function return immediately in the usermode emulator. This turns WFI into a NOP, which is OK because: * architecturally "WFI is a NOP" is a permitted implementation * aarch64 Linux kernels use the SCTLR_EL1.nTWI bit to trap userspace WFI and NOP it (though aarch32 kernels currently just let WFI do whatever it would do) We could in theory make the translate.c code special case user-mode emulation and NOP the insn entirely rather than making the helper do nothing, but because no real world code will be trying to execute WFI we don't care about efficiency and the helper provides a single place where we can make the change rather than having to touch multiple places in translate.c and translate-a64.c. Fixes: https://bugs.launchpad.net/qemu/+bug/1926759 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430162212.825-1-peter.maydell@linaro.org --- target/arm/op_helper.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ static inline int check_wfx_trap(CPUARMState *env, bool is_wfe) void HELPER(wfi)(CPUARMState *env, uint32_t insn_len) { +#ifdef CONFIG_USER_ONLY + /* + * WFI in the user-mode emulator is technically permitted but not + * something any real-world code would do. AArch64 Linux kernels + * trap it via SCTRL_EL1.nTWI and make it an (expensive) NOP; + * AArch32 kernels don't trap it so it will delay a bit. + * For QEMU, make it NOP here, because trying to raise EXCP_HLT + * would trigger an abort. + */ + return; +#else CPUState *cs = env_cpu(env); int target_el = check_wfx_trap(env, false); @@ -XXX,XX +XXX,XX @@ void HELPER(wfi)(CPUARMState *env, uint32_t insn_len) cs->exception_index = EXCP_HLT; cs->halted = 1; cpu_loop_exit(cs); +#endif } void HELPER(wfe)(CPUARMState *env) -- 2.20.1 The omap_mmc_reset() function resets its SD card via device_legacy_reset(). We know that the SD card does not have a qbus of its own, so the new device_cold_reset() function (which resets both the device and its child buses) is equivalent here to device_legacy_reset() and we can just switch to the new API. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210430222348.8514-1-peter.maydell@linaro.org --- hw/sd/omap_mmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/sd/omap_mmc.c b/hw/sd/omap_mmc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/omap_mmc.c +++ b/hw/sd/omap_mmc.c @@ -XXX,XX +XXX,XX @@ void omap_mmc_reset(struct omap_mmc_s *host) * into any bus, and we must reset it manually. When omap_mmc is * QOMified this must move into the QOM reset function. */ - device_legacy_reset(DEVICE(host->card)); + device_cold_reset(DEVICE(host->card)); } static uint64_t omap_mmc_read(void *opaque, hwaddr offset, -- 2.20.1 Both os-win32.h and os-posix.h include system header files. Instead of having osdep.h include them inside its 'extern "C"' block, make these headers handle that themselves, so that we don't include the system headers inside 'extern "C"'. This doesn't fix any current problems, but it's conceptually the right way to handle system headers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- include/qemu/osdep.h | 8 ++++---- include/sysemu/os-posix.h | 8 ++++++++ include/sysemu/os-win32.h | 8 ++++++++ 3 files changed, 20 insertions(+), 4 deletions(-) diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/osdep.h +++ b/include/qemu/osdep.h @@ -XXX,XX +XXX,XX @@ QEMU_EXTERN_C int daemon(int, int); */ #include "glib-compat.h" -#ifdef __cplusplus -extern "C" { -#endif - #ifdef _WIN32 #include "sysemu/os-win32.h" #endif @@ -XXX,XX +XXX,XX @@ extern "C" { #include "sysemu/os-posix.h" #endif +#ifdef __cplusplus +extern "C" { +#endif + #include "qemu/typedefs.h" /* diff --git a/include/sysemu/os-posix.h b/include/sysemu/os-posix.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/os-posix.h +++ b/include/sysemu/os-posix.h @@ -XXX,XX +XXX,XX @@ #include <sys/sysmacros.h> #endif +#ifdef __cplusplus +extern "C" { +#endif + void os_set_line_buffering(void); void os_set_proc_name(const char *s); void os_setup_signal_handling(void); @@ -XXX,XX +XXX,XX @@ static inline void qemu_funlockfile(FILE *f) funlockfile(f); } +#ifdef __cplusplus +} +#endif + #endif diff --git a/include/sysemu/os-win32.h b/include/sysemu/os-win32.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/os-win32.h +++ b/include/sysemu/os-win32.h @@ -XXX,XX +XXX,XX @@ #include <windows.h> #include <ws2tcpip.h> +#ifdef __cplusplus +extern "C" { +#endif + #if defined(_WIN64) /* On w64, setjmp is implemented by _setjmp which needs a second parameter. * If this parameter is NULL, longjump does no stack unwinding. @@ -XXX,XX +XXX,XX @@ ssize_t qemu_recv_wrap(int sockfd, void *buf, size_t len, int flags); ssize_t qemu_recvfrom_wrap(int sockfd, void *buf, size_t len, int flags, struct sockaddr *addr, socklen_t *addrlen); +#ifdef __cplusplus +} +#endif + #endif -- 2.20.1 Make bswap.h handle being included outside an 'extern "C"' block: all system headers are included first, then all declarations are put inside an 'extern "C"' block. This requires a little rearrangement as currently we have an ifdef ladder that has some system includes and some local declarations or definitions, and we need to separate those out. We want to do this because dis-asm.h includes bswap.h, dis-asm.h may need to be included from C++ files, and system headers should not be included within 'extern "C"' blocks. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- include/qemu/bswap.h | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) diff --git a/include/qemu/bswap.h b/include/qemu/bswap.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/bswap.h +++ b/include/qemu/bswap.h @@ -XXX,XX +XXX,XX @@ #ifndef BSWAP_H #define BSWAP_H -#include "fpu/softfloat-types.h" - #ifdef CONFIG_MACHINE_BSWAP_H # include <sys/endian.h> # include <machine/bswap.h> @@ -XXX,XX +XXX,XX @@ # include <endian.h> #elif defined(CONFIG_BYTESWAP_H) # include <byteswap.h> +#define BSWAP_FROM_BYTESWAP +# else +#define BSWAP_FROM_FALLBACKS +#endif /* ! CONFIG_MACHINE_BSWAP_H */ +#ifdef __cplusplus +extern "C" { +#endif + +#include "fpu/softfloat-types.h" + +#ifdef BSWAP_FROM_BYTESWAP static inline uint16_t bswap16(uint16_t x) { return bswap_16(x); @@ -XXX,XX +XXX,XX @@ static inline uint64_t bswap64(uint64_t x) { return bswap_64(x); } -# else +#endif + +#ifdef BSWAP_FROM_FALLBACKS static inline uint16_t bswap16(uint16_t x) { return (((x & 0x00ff) << 8) | @@ -XXX,XX +XXX,XX @@ static inline uint64_t bswap64(uint64_t x) ((x & 0x00ff000000000000ULL) >> 40) | ((x & 0xff00000000000000ULL) >> 56)); } -#endif /* ! CONFIG_MACHINE_BSWAP_H */ +#endif + +#undef BSWAP_FROM_BYTESWAP +#undef BSWAP_FROM_FALLBACKS static inline void bswap16s(uint16_t *s) { @@ -XXX,XX +XXX,XX @@ DO_STN_LDN_P(be) #undef le_bswaps #undef be_bswaps +#ifdef __cplusplus +} +#endif + #endif /* BSWAP_H */ -- 2.20.1 Make dis-asm.h handle being included outside an 'extern "C"' block; this allows us to remove the 'extern "C"' blocks that our two C++ files that include it are using. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- include/disas/dis-asm.h | 12 ++++++++++-- disas/arm-a64.cc | 2 -- disas/nanomips.cpp | 2 -- 3 files changed, 10 insertions(+), 6 deletions(-) diff --git a/include/disas/dis-asm.h b/include/disas/dis-asm.h index XXXXXXX..XXXXXXX 100644 --- a/include/disas/dis-asm.h +++ b/include/disas/dis-asm.h @@ -XXX,XX +XXX,XX @@ #ifndef DISAS_DIS_ASM_H #define DISAS_DIS_ASM_H +#include "qemu/bswap.h" + +#ifdef __cplusplus +extern "C" { +#endif + typedef void *PTR; typedef uint64_t bfd_vma; typedef int64_t bfd_signed_vma; @@ -XXX,XX +XXX,XX @@ bool cap_disas_plugin(disassemble_info *info, uint64_t pc, size_t size); /* from libbfd */ -#include "qemu/bswap.h" - static inline bfd_vma bfd_getl64(const bfd_byte *addr) { return ldq_le_p(addr); @@ -XXX,XX +XXX,XX @@ static inline bfd_vma bfd_getb16(const bfd_byte *addr) typedef bool bfd_boolean; +#ifdef __cplusplus +} +#endif + #endif /* DISAS_DIS_ASM_H */ diff --git a/disas/arm-a64.cc b/disas/arm-a64.cc index XXXXXXX..XXXXXXX 100644 --- a/disas/arm-a64.cc +++ b/disas/arm-a64.cc @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -extern "C" { #include "disas/dis-asm.h" -} #include "vixl/a64/disasm-a64.h" diff --git a/disas/nanomips.cpp b/disas/nanomips.cpp index XXXXXXX..XXXXXXX 100644 --- a/disas/nanomips.cpp +++ b/disas/nanomips.cpp @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -extern "C" { #include "disas/dis-asm.h" -} #include <cstring> #include <stdexcept> -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> The i.MX25 PDK board has 2 banks for SDRAM, each can address up to 256 MiB. So the total RAM usable for this board is 512M. When we ask for more we get a misleading error message: $ qemu-system-arm -M imx25-pdk -m 513M qemu-system-arm: Invalid RAM size, should be 128 MiB Update the error message to better match the reality: $ qemu-system-arm -M imx25-pdk -m 513M qemu-system-arm: RAM size more than 512 MiB is not supported Fixes: bf350daae02 ("arm/imx25_pdk: drop RAM size fixup") Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20210407225608.1882855-1-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/imx25_pdk.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/hw/arm/imx25_pdk.c b/hw/arm/imx25_pdk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/imx25_pdk.c +++ b/hw/arm/imx25_pdk.c @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info imx25_pdk_binfo; static void imx25_pdk_init(MachineState *machine) { - MachineClass *mc = MACHINE_GET_CLASS(machine); IMX25PDK *s = g_new0(IMX25PDK, 1); unsigned int ram_size; unsigned int alias_offset; @@ -XXX,XX +XXX,XX @@ static void imx25_pdk_init(MachineState *machine) /* We need to initialize our memory */ if (machine->ram_size > (FSL_IMX25_SDRAM0_SIZE + FSL_IMX25_SDRAM1_SIZE)) { - char *sz = size_to_str(mc->default_ram_size); - error_report("Invalid RAM size, should be %s", sz); + char *sz = size_to_str(FSL_IMX25_SDRAM0_SIZE + FSL_IMX25_SDRAM1_SIZE); + error_report("RAM size more than %s is not supported", sz); g_free(sz); exit(EXIT_FAILURE); } -- 2.20.1 The MPS2 SCC device doesn't have any documentation of its properties; add a "QEMU interface" format comment describing them. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210504120912.23094-2-peter.maydell@linaro.org --- include/hw/misc/mps2-scc.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/include/hw/misc/mps2-scc.h b/include/hw/misc/mps2-scc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-scc.h +++ b/include/hw/misc/mps2-scc.h @@ -XXX,XX +XXX,XX @@ * (at your option) any later version. */ +/* + * This is a model of the Serial Communication Controller (SCC) + * block found in most MPS FPGA images. + * + * QEMU interface: + * + sysbus MMIO region 0: the register bank + * + QOM property "scc-cfg4": value of the read-only CFG4 register + * + QOM property "scc-aid": value of the read-only SCC_AID register + * + QOM property "scc-id": value of the read-only SCC_ID register + * + QOM property array "oscclk": reset values of the OSCCLK registers + * (which are accessed via the SYS_CFG channel provided by this device) + */ #ifndef MPS2_SCC_H #define MPS2_SCC_H -- 2.20.1 On some boards, SCC config register CFG0 bit 0 controls whether parts of the board memory map are remapped. Support this with: * a device property scc-cfg0 so the board can specify the initial value of the CFG0 register * an outbound GPIO line which tracks bit 0 and which the board can wire up to provide the remapping 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: 20210504120912.23094-3-peter.maydell@linaro.org --- include/hw/misc/mps2-scc.h | 9 +++++++++ hw/misc/mps2-scc.c | 13 ++++++++++--- 2 files changed, 19 insertions(+), 3 deletions(-) diff --git a/include/hw/misc/mps2-scc.h b/include/hw/misc/mps2-scc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-scc.h +++ b/include/hw/misc/mps2-scc.h @@ -XXX,XX +XXX,XX @@ * + QOM property "scc-cfg4": value of the read-only CFG4 register * + QOM property "scc-aid": value of the read-only SCC_AID register * + QOM property "scc-id": value of the read-only SCC_ID register + * + QOM property "scc-cfg0": reset value of the CFG0 register * + QOM property array "oscclk": reset values of the OSCCLK registers * (which are accessed via the SYS_CFG channel provided by this device) + * + named GPIO output "remap": this tracks the value of CFG0 register + * bit 0. Boards where this bit controls memory remapping should + * connect this GPIO line to a function performing that mapping. + * Boards where bit 0 has no special function should leave the GPIO + * output disconnected. */ #ifndef MPS2_SCC_H #define MPS2_SCC_H @@ -XXX,XX +XXX,XX @@ struct MPS2SCC { uint32_t num_oscclk; uint32_t *oscclk; uint32_t *oscclk_reset; + uint32_t cfg0_reset; + + qemu_irq remap; }; #endif diff --git a/hw/misc/mps2-scc.c b/hw/misc/mps2-scc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-scc.c +++ b/hw/misc/mps2-scc.c @@ -XXX,XX +XXX,XX @@ #include "qemu/bitops.h" #include "trace.h" #include "hw/sysbus.h" +#include "hw/irq.h" #include "migration/vmstate.h" #include "hw/registerfields.h" #include "hw/misc/mps2-scc.h" @@ -XXX,XX +XXX,XX @@ static void mps2_scc_write(void *opaque, hwaddr offset, uint64_t value, switch (offset) { case A_CFG0: /* - * TODO on some boards bit 0 controls RAM remapping; - * on others bit 1 is CPU_WAIT. + * On some boards bit 0 controls board-specific remapping; + * we always reflect bit 0 in the 'remap' GPIO output line, + * and let the board wire it up or not as it chooses. + * TODO on some boards bit 1 is CPU_WAIT. */ s->cfg0 = value; + qemu_set_irq(s->remap, s->cfg0 & 1); break; case A_CFG1: s->cfg1 = value; @@ -XXX,XX +XXX,XX @@ static void mps2_scc_reset(DeviceState *dev) int i; trace_mps2_scc_reset(); - s->cfg0 = 0; + s->cfg0 = s->cfg0_reset; s->cfg1 = 0; s->cfg2 = 0; s->cfg5 = 0; @@ -XXX,XX +XXX,XX @@ static void mps2_scc_init(Object *obj) memory_region_init_io(&s->iomem, obj, &mps2_scc_ops, s, "mps2-scc", 0x1000); sysbus_init_mmio(sbd, &s->iomem); + qdev_init_gpio_out_named(DEVICE(obj), &s->remap, "remap", 1); } static void mps2_scc_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static Property mps2_scc_properties[] = { DEFINE_PROP_UINT32("scc-cfg4", MPS2SCC, cfg4, 0), DEFINE_PROP_UINT32("scc-aid", MPS2SCC, aid, 0), DEFINE_PROP_UINT32("scc-id", MPS2SCC, id, 0), + /* Reset value for CFG0 register */ + DEFINE_PROP_UINT32("scc-cfg0", MPS2SCC, cfg0_reset, 0), /* * These are the initial settings for the source clocks on the board. * In hardware they can be configured via a config file read by the -- 2.20.1 The AN524 FPGA image supports two memory maps, which differ in where the QSPI and BRAM are. In the default map, the BRAM is at 0x0000_0000, and the QSPI at 0x2800_0000. In the second map, they are the other way around. In hardware, the initial mapping can be selected by the user by writing either "REMAP: BRAM" (the default) or "REMAP: QSPI" in the board configuration file. The board config file is acted on by the "Motherboard Configuration Controller", which is an entirely separate microcontroller on the dev board but outside the FPGA. The guest can also dynamically change the mapping via the SCC CFG_REG0 register. Implement this functionality for QEMU, using a machine property "remap" with valid values "BRAM" and "QSPI" to allow the user to set the initial mapping, in the same way they can on the FPGA, and wiring up the bit from the SCC register to also switch the mapping. 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: 20210504120912.23094-4-peter.maydell@linaro.org --- docs/system/arm/mps2.rst | 10 ++++ hw/arm/mps2-tz.c | 108 ++++++++++++++++++++++++++++++++++++++- 2 files changed, 117 insertions(+), 1 deletion(-) diff --git a/docs/system/arm/mps2.rst b/docs/system/arm/mps2.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/mps2.rst +++ b/docs/system/arm/mps2.rst @@ -XXX,XX +XXX,XX @@ Differences between QEMU and real hardware: flash, but only as simple ROM, so attempting to rewrite the flash from the guest will fail - QEMU does not model the USB controller in MPS3 boards + +Machine-specific options +"""""""""""""""""""""""" + +The following machine-specific options are supported: + +remap + Supported for ``mps3-an524`` only. + Set ``BRAM``/``QSPI`` to select the initial memory mapping. The + default is ``BRAM``. diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "exec/address-spaces.h" #include "sysemu/sysemu.h" +#include "sysemu/reset.h" #include "hw/misc/unimp.h" #include "hw/char/cmsdk-apb-uart.h" #include "hw/timer/cmsdk-apb-timer.h" @@ -XXX,XX +XXX,XX @@ #include "hw/core/split-irq.h" #include "hw/qdev-clock.h" #include "qom/object.h" +#include "hw/irq.h" #define MPS2TZ_NUMIRQ_MAX 96 #define MPS2TZ_RAM_MAX 5 @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { SplitIRQ cpu_irq_splitter[MPS2TZ_NUMIRQ_MAX]; Clock *sysclk; Clock *s32kclk; + + bool remap; + qemu_irq remap_irq; }; #define TYPE_MPS2TZ_MACHINE "mps2tz" @@ -XXX,XX +XXX,XX @@ static const RAMInfo an505_raminfo[] = { { }, }; +/* + * Note that the addresses and MPC numbering here should match up + * with those used in remap_memory(), which can swap the BRAM and QSPI. + */ static const RAMInfo an524_raminfo[] = { { .name = "bram", .base = 0x00000000, @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, object_initialize_child(OBJECT(mms), "scc", scc, TYPE_MPS2_SCC); sccdev = DEVICE(scc); + qdev_prop_set_uint32(sccdev, "scc-cfg0", mms->remap ? 1 : 0); qdev_prop_set_uint32(sccdev, "scc-cfg4", 0x2); qdev_prop_set_uint32(sccdev, "scc-aid", 0x00200008); qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, return sysbus_mmio_get_region(SYS_BUS_DEVICE(mpc), 0); } +static hwaddr boot_mem_base(MPS2TZMachineState *mms) +{ + /* + * Return the canonical address of the block which will be mapped + * at address 0x0 (i.e. where the vector table is). + * This is usually 0, but if the AN524 alternate memory map is + * enabled it will be the base address of the QSPI block. + */ + return mms->remap ? 0x28000000 : 0; +} + +static void remap_memory(MPS2TZMachineState *mms, int map) +{ + /* + * Remap the memory for the AN524. 'map' is the value of + * SCC CFG_REG0 bit 0, i.e. 0 for the default map and 1 + * for the "option 1" mapping where QSPI is at address 0. + * + * Effectively we need to swap around the "upstream" ends of + * MPC 0 and MPC 1. + */ + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + int i; + + if (mmc->fpga_type != FPGA_AN524) { + return; + } + + memory_region_transaction_begin(); + for (i = 0; i < 2; i++) { + TZMPC *mpc = &mms->mpc[i]; + MemoryRegion *upstream = sysbus_mmio_get_region(SYS_BUS_DEVICE(mpc), 1); + hwaddr addr = (i ^ map) ? 0x28000000 : 0; + + memory_region_set_address(upstream, addr); + } + memory_region_transaction_commit(); +} + +static void remap_irq_fn(void *opaque, int n, int level) +{ + MPS2TZMachineState *mms = opaque; + + remap_memory(mms, level); +} + static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, const int *irqs) @@ -XXX,XX +XXX,XX @@ static uint32_t boot_ram_size(MPS2TZMachineState *mms) MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); for (p = mmc->raminfo; p->name; p++) { - if (p->base == 0) { + if (p->base == boot_mem_base(mms)) { return p->size; } } @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) create_non_mpc_ram(mms); + if (mmc->fpga_type == FPGA_AN524) { + /* + * Connect the line from the SCC so that we can remap when the + * guest updates that register. + */ + mms->remap_irq = qemu_allocate_irq(remap_irq_fn, mms, 0); + qdev_connect_gpio_out_named(DEVICE(&mms->scc), "remap", 0, + mms->remap_irq); + } + armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, boot_ram_size(mms)); } @@ -XXX,XX +XXX,XX @@ static void mps2_tz_idau_check(IDAUInterface *ii, uint32_t address, *iregion = region; } +static char *mps2_get_remap(Object *obj, Error **errp) +{ + MPS2TZMachineState *mms = MPS2TZ_MACHINE(obj); + const char *val = mms->remap ? "QSPI" : "BRAM"; + return g_strdup(val); +} + +static void mps2_set_remap(Object *obj, const char *value, Error **errp) +{ + MPS2TZMachineState *mms = MPS2TZ_MACHINE(obj); + + if (!strcmp(value, "BRAM")) { + mms->remap = false; + } else if (!strcmp(value, "QSPI")) { + mms->remap = true; + } else { + error_setg(errp, "Invalid remap value"); + error_append_hint(errp, "Valid values are BRAM and QSPI.\n"); + } +} + +static void mps2_machine_reset(MachineState *machine) +{ + MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine); + + /* + * Set the initial memory mapping before triggering the reset of + * the rest of the system, so that the guest image loader and CPU + * reset see the correct mapping. + */ + remap_memory(mms, mms->remap); + qemu_devices_reset(); +} + static void mps2tz_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); IDAUInterfaceClass *iic = IDAU_INTERFACE_CLASS(oc); mc->init = mps2tz_common_init; + mc->reset = mps2_machine_reset; iic->check = mps2_tz_idau_check; } @@ -XXX,XX +XXX,XX @@ static void mps3tz_an524_class_init(ObjectClass *oc, void *data) mmc->raminfo = an524_raminfo; mmc->armsse_type = TYPE_SSE200; mps2tz_set_default_ram_info(mmc); + + object_class_property_add_str(oc, "remap", mps2_get_remap, mps2_set_remap); + object_class_property_set_description(oc, "remap", + "Set memory mapping. Valid values " + "are BRAM (default) and QSPI."); } static void mps3tz_an547_class_init(ObjectClass *oc, void *data) -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Commit dfc388797cc4 ("hw/arm: xlnx: Set all boards' GEM 'phy-addr' property value to 23") configured the PHY address for xilinx-zynq-a9 to 23. When trying to boot xilinx-zynq-a9 with zynq-zc702.dtb or zynq-zc706.dtb, this results in the following error message when trying to use the Ethernet interface. macb e000b000.ethernet eth0: Could not attach PHY (-19) The devicetree files for ZC702 and ZC706 configure PHY address 7. The documentation for the ZC702 and ZC706 evaluation boards suggest that the PHY address is 7, not 23. Other boards use PHY address 0, 1, 3, or 7. I was unable to find a documentation or a devicetree file suggesting or using PHY address 23. The Ethernet interface starts working with zynq-zc702.dtb and zynq-zc706.dtb when setting the PHY address to 7, so let's use it. Cc: Bin Meng <bin.meng@windriver.com> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Bin Meng <bmeng.cn@gmail.com> Acked-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20210504124140.1100346-1-linux@roeck-us.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xilinx_zynq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ static void gem_init(NICInfo *nd, uint32_t base, qemu_irq irq) qemu_check_nic_model(nd, TYPE_CADENCE_GEM); qdev_set_nic_properties(dev, nd); } - object_property_set_int(OBJECT(dev), "phy-addr", 23, &error_abort); + object_property_set_int(OBJECT(dev), "phy-addr", 7, &error_abort); s = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(s, &error_fatal); sysbus_mmio_map(s, 0, base); -- 2.20.1