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 Here's another arm pullreq; nothing too exciting in here I think. thanks -- PMM The following changes since commit 5fee33d97a7f2e95716417bd164f2f5264acd976: Merge tag 'samuel-thibault' of https://people.debian.org/~sthibault/qemu into staging (2024-04-29 14:34:25 -0700) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20240430 for you to fetch changes up to a0c325c4b05cf7815739d6a84e567b95c8c5be7e: tests/qtest : Add testcase for DM163 (2024-04-30 16:05:08 +0100) ---------------------------------------------------------------- target-arm queue: * hw/core/clock: allow clock_propagate on child clocks * hvf: arm: Remove unused PL1_WRITE_MASK define * target/arm: Restrict translation disabled alignment check to VMSA * docs/system/arm/emulation.rst: Add missing implemented features * target/arm: Enable FEAT_CSV2_3, FEAT_ETS2, FEAT_Spec_FPACC for 'max' * tests/avocado: update sunxi kernel from armbian to 6.6.16 * target/arm: Make new CPUs default to 1GHz generic timer * hw/dmax/xlnx_dpdma: fix handling of address_extension descriptor fields * hw/char/stm32l4x5_usart: Fix memory corruption by adding correct class_size * hw/arm/npcm7xx: Store derivative OTP fuse key in little endian * hw/arm: Add DM163 display to B-L475E-IOT01A board ---------------------------------------------------------------- Alexandra Diupina (1): hw/dmax/xlnx_dpdma: fix handling of address_extension descriptor fields Inès Varhol (5): hw/display : Add device DM163 hw/arm : Pass STM32L4x5 SYSCFG gpios to STM32L4x5 SoC hw/arm : Create Bl475eMachineState hw/arm : Connect DM163 to B-L475E-IOT01A tests/qtest : Add testcase for DM163 Peter Maydell (10): docs/system/arm/emulation.rst: Add missing implemented features target/arm: Enable FEAT_CSV2_3 for -cpu max target/arm: Enable FEAT_ETS2 for -cpu max target/arm: Implement ID_AA64MMFR3_EL1 target/arm: Enable FEAT_Spec_FPACC for -cpu max tests/avocado: update sunxi kernel from armbian to 6.6.16 target/arm: Refactor default generic timer frequency handling hw/arm/sbsa-ref: Force CPU generic timer to 62.5MHz hw/watchdog/sbsa_gwdt: Make watchdog timer frequency a QOM property target/arm: Default to 1GHz cntfrq for 'max' and new CPUs Philippe Mathieu-Daudé (1): hw/arm/npcm7xx: Store derivative OTP fuse key in little endian Raphael Poggi (1): hw/core/clock: allow clock_propagate on child clocks Richard Henderson (1): target/arm: Restrict translation disabled alignment check to VMSA Thomas Huth (1): hw/char/stm32l4x5_usart: Fix memory corruption by adding correct class_size Zenghui Yu (1): hvf: arm: Remove PL1_WRITE_MASK docs/system/arm/b-l475e-iot01a.rst | 3 +- docs/system/arm/emulation.rst | 42 ++++- include/hw/display/dm163.h | 59 ++++++ include/hw/watchdog/sbsa_gwdt.h | 3 +- target/arm/cpu.h | 28 +++ target/arm/internals.h | 15 +- hw/arm/b-l475e-iot01a.c | 105 +++++++++-- hw/arm/npcm7xx.c | 3 +- hw/arm/sbsa-ref.c | 16 ++ hw/arm/stm32l4x5_soc.c | 6 +- hw/char/stm32l4x5_usart.c | 1 + hw/core/clock.c | 1 - hw/core/machine.c | 4 +- hw/display/dm163.c | 349 ++++++++++++++++++++++++++++++++++++ hw/dma/xlnx_dpdma.c | 20 +-- hw/watchdog/sbsa_gwdt.c | 15 +- target/arm/cpu.c | 42 +++-- target/arm/cpu64.c | 2 + target/arm/helper.c | 22 +-- target/arm/hvf/hvf.c | 3 +- target/arm/kvm.c | 2 + target/arm/tcg/cpu32.c | 6 +- target/arm/tcg/cpu64.c | 28 ++- target/arm/tcg/hflags.c | 12 +- tests/qtest/dm163-test.c | 194 ++++++++++++++++++++ tests/qtest/stm32l4x5_gpio-test.c | 13 +- tests/qtest/stm32l4x5_syscfg-test.c | 17 +- hw/arm/Kconfig | 1 + hw/display/Kconfig | 3 + hw/display/meson.build | 1 + hw/display/trace-events | 14 ++ tests/avocado/boot_linux_console.py | 70 ++++---- tests/avocado/replay_kernel.py | 8 +- tests/qtest/meson.build | 2 + 34 files changed, 987 insertions(+), 123 deletions(-) create mode 100644 include/hw/display/dm163.h create mode 100644 hw/display/dm163.c create mode 100644 tests/qtest/dm163-test.c From: Raphael Poggi <raphael.poggi@lynxleap.co.uk> clock_propagate() has an assert that clk->source is NULL, i.e. that you are calling it on a clock which has no source clock. This made sense in the original design where the only way for a clock's frequency to change if it had a source clock was when that source clock changed. However, we subsequently added multiplier/divider support, but didn't look at what that meant for propagation. If a clock-management device changes the multiplier or divider value on a clock, it needs to propagate that change down to child clocks, even if the clock has a source clock set. So the assertion is now incorrect. Remove the assertion. Signed-off-by: Raphael Poggi <raphael.poggi@lynxleap.co.uk> Message-id: 20240419162951.23558-1-raphael.poggi@lynxleap.co.uk Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: Rewrote the commit message] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/clock.c | 1 - 1 file changed, 1 deletion(-) diff --git a/hw/core/clock.c b/hw/core/clock.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/clock.c +++ b/hw/core/clock.c @@ -XXX,XX +XXX,XX @@ static void clock_propagate_period(Clock *clk, bool call_callbacks) void clock_propagate(Clock *clk) { - assert(clk->source == NULL); trace_clock_propagate(CLOCK_PATH(clk)); clock_propagate_period(clk, true); } -- 2.34.1 From: Zenghui Yu <zenghui.yu@linux.dev> As it had never been used since the first commit a1477da3ddeb ("hvf: Add Apple Silicon support"). Signed-off-by: Zenghui Yu <zenghui.yu@linux.dev> Message-id: 20240422092715.71973-1-zenghui.yu@linux.dev Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/hvf/hvf.c | 1 - 1 file changed, 1 deletion(-) diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/hvf/hvf.c +++ b/target/arm/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ void hvf_arm_init_debug(void) #define HVF_SYSREG(crn, crm, op0, op1, op2) \ ENCODE_AA64_CP_REG(CP_REG_ARM64_SYSREG_CP, crn, crm, op0, op1, op2) -#define PL1_WRITE_MASK 0x4 #define SYSREG_OP0_SHIFT 20 #define SYSREG_OP0_MASK 0x3 -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> For cpus using PMSA, when the MPU is disabled, the default memory type is Normal, Non-cachable. This means that it should not have alignment restrictions enforced. Cc: qemu-stable@nongnu.org Fixes: 59754f85ed3 ("target/arm: Do memory type alignment check when translation disabled") Reported-by: Clément Chigot <chigot@adacore.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Clément Chigot <chigot@adacore.com> Message-id: 20240422170722.117409-1-richard.henderson@linaro.org [PMM: trivial comment, commit message tweaks] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/hflags.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/hflags.c +++ b/target/arm/tcg/hflags.c @@ -XXX,XX +XXX,XX @@ static bool aprofile_require_alignment(CPUARMState *env, int el, uint64_t sctlr) } /* - * If translation is disabled, then the default memory type is - * Device(-nGnRnE) instead of Normal, which requires that alignment + * With PMSA, when the MPU is disabled, all memory types in the + * default map are Normal, so don't need aligment enforcing. + */ + if (arm_feature(env, ARM_FEATURE_PMSA)) { + return false; + } + + /* + * With VMSA, if translation is disabled, then the default memory type + * is Device(-nGnRnE) instead of Normal, which requires that alignment * be enforced. Since this affects all ram, it is most efficient * to handle this during translation. */ -- 2.34.1 As of version DDI0487K.a of the Arm ARM, some architectural features which previously didn't have official names have been named. Add these to the list of features which QEMU's TCG emulation supports. Mostly these are features which we thought of as part of baseline 8.0 support. For SVE and SVE2, the names have been brought into line with the FEAT_* naming convention of other extensions, and some sub-components split into separate FEAT_ items. In a few cases (eg FEAT_CCIDX, FEAT_DPB2) the omission from our list was just an oversight. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240418152004.2106516-2-peter.maydell@linaro.org --- docs/system/arm/emulation.rst | 38 +++++++++++++++++++++++++++++++++-- 1 file changed, 36 insertions(+), 2 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ Armv8 versions of the A-profile architecture. It also has support for the following architecture extensions: - FEAT_AA32BF16 (AArch32 BFloat16 instructions) +- FEAT_AA32EL0 (Support for AArch32 at EL0) +- FEAT_AA32EL1 (Support for AArch32 at EL1) +- FEAT_AA32EL2 (Support for AArch32 at EL2) +- FEAT_AA32EL3 (Support for AArch32 at EL3) - FEAT_AA32HPD (AArch32 hierarchical permission disables) - FEAT_AA32I8MM (AArch32 Int8 matrix multiplication instructions) +- FEAT_AA64EL0 (Support for AArch64 at EL0) +- FEAT_AA64EL1 (Support for AArch64 at EL1) +- FEAT_AA64EL2 (Support for AArch64 at EL2) +- FEAT_AA64EL3 (Support for AArch64 at EL3) +- FEAT_AdvSIMD (Advanced SIMD Extension) - FEAT_AES (AESD and AESE instructions) +- FEAT_Armv9_Crypto (Armv9 Cryptographic Extension) +- FEAT_ASID16 (16 bit ASID) - FEAT_BBM at level 2 (Translation table break-before-make levels) - FEAT_BF16 (AArch64 BFloat16 instructions) - FEAT_BTI (Branch Target Identification) +- FEAT_CCIDX (Extended cache index) - FEAT_CRC32 (CRC32 instructions) +- FEAT_Crypto (Cryptographic Extension) - FEAT_CSV2 (Cache speculation variant 2) - FEAT_CSV2_1p1 (Cache speculation variant 2, version 1.1) - FEAT_CSV2_1p2 (Cache speculation variant 2, version 1.2) @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_DGH (Data gathering hint) - FEAT_DIT (Data Independent Timing instructions) - FEAT_DPB (DC CVAP instruction) +- FEAT_DPB2 (DC CVADP instruction) +- FEAT_Debugv8p1 (Debug with VHE) - FEAT_Debugv8p2 (Debug changes for v8.2) - FEAT_Debugv8p4 (Debug changes for v8.4) - FEAT_DotProd (Advanced SIMD dot product instructions) - FEAT_DoubleFault (Double Fault Extension) - FEAT_E0PD (Preventing EL0 access to halves of address maps) - FEAT_ECV (Enhanced Counter Virtualization) +- FEAT_EL0 (Support for execution at EL0) +- FEAT_EL1 (Support for execution at EL1) +- FEAT_EL2 (Support for execution at EL2) +- FEAT_EL3 (Support for execution at EL3) - FEAT_EPAC (Enhanced pointer authentication) - FEAT_ETS (Enhanced Translation Synchronization) - FEAT_EVT (Enhanced Virtualization Traps) +- FEAT_F32MM (Single-precision Matrix Multiplication) +- FEAT_F64MM (Double-precision Matrix Multiplication) - FEAT_FCMA (Floating-point complex number instructions) - FEAT_FGT (Fine-Grained Traps) - FEAT_FHM (Floating-point half-precision multiplication instructions) +- FEAT_FP (Floating Point extensions) - FEAT_FP16 (Half-precision floating-point data processing) - FEAT_FPAC (Faulting on AUT* instructions) - FEAT_FPACCOMBINE (Faulting on combined pointer authentication instructions) @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_LSE (Large System Extensions) - FEAT_LSE2 (Large System Extensions v2) - FEAT_LVA (Large Virtual Address space) +- FEAT_MixedEnd (Mixed-endian support) +- FEAT_MixdEndEL0 (Mixed-endian support at EL0) - FEAT_MOPS (Standardization of memory operations) - FEAT_MTE (Memory Tagging Extension) - FEAT_MTE2 (Memory Tagging Extension) - FEAT_MTE3 (MTE Asymmetric Fault Handling) +- FEAT_MTE_ASYM_FAULT (Memory tagging asymmetric faults) - FEAT_NMI (Non-maskable Interrupt) - FEAT_NV (Nested Virtualization) - FEAT_NV2 (Enhanced nested virtualization support) @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_PAuth (Pointer authentication) - FEAT_PAuth2 (Enhancements to pointer authentication) - FEAT_PMULL (PMULL, PMULL2 instructions) +- FEAT_PMUv3 (PMU extension version 3) - FEAT_PMUv3p1 (PMU Extensions v3.1) - FEAT_PMUv3p4 (PMU Extensions v3.4) - FEAT_PMUv3p5 (PMU Extensions v3.5) @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_SME_FA64 (Full A64 instruction set in Streaming SVE mode) - FEAT_SME_F64F64 (Double-precision floating-point outer product instructions) - FEAT_SME_I16I64 (16-bit to 64-bit integer widening outer product instructions) +- FEAT_SVE (Scalable Vector Extension) +- FEAT_SVE_AES (Scalable Vector AES instructions) +- FEAT_SVE_BitPerm (Scalable Vector Bit Permutes instructions) +- FEAT_SVE_PMULL128 (Scalable Vector PMULL instructions) +- FEAT_SVE_SHA3 (Scalable Vector SHA3 instructions) +- FEAT_SVE_SM4 (Scalable Vector SM4 instructions) +- FEAT_SVE2 (Scalable Vector Extension version 2) - FEAT_SPECRES (Speculation restriction instructions) - FEAT_SSBS (Speculative Store Bypass Safe) +- FEAT_TGran16K (Support for 16KB memory translation granule size at stage 1) +- FEAT_TGran4K (Support for 4KB memory translation granule size at stage 1) +- FEAT_TGran64K (Support for 64KB memory translation granule size at stage 1) - FEAT_TIDCP1 (EL0 use of IMPLEMENTATION DEFINED functionality) - FEAT_TLBIOS (TLB invalidate instructions in Outer Shareable domain) - FEAT_TLBIRANGE (TLB invalidate range instructions) @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_VHE (Virtualization Host Extensions) - FEAT_VMID16 (16-bit VMID) - FEAT_XNX (Translation table stage 2 Unprivileged Execute-never) -- SVE (The Scalable Vector Extension) -- SVE2 (The Scalable Vector Extension v2) For information on the specifics of these extensions, please refer to the `Armv8-A Arm Architecture Reference Manual -- 2.34.1 FEAT_CSV2_3 adds a mechanism to identify if hardware cannot disclose information about whether branch targets and branch history trained in one hardware described context can control speculative execution in a different hardware context. There is no branch prediction in TCG, so we don't need to do anything to be compliant with this. Upadte the '-cpu max' ID registers to advertise the feature. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240418152004.2106516-3-peter.maydell@linaro.org --- docs/system/arm/emulation.rst | 1 + target/arm/tcg/cpu64.c | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_CSV2_1p1 (Cache speculation variant 2, version 1.1) - FEAT_CSV2_1p2 (Cache speculation variant 2, version 1.2) - FEAT_CSV2_2 (Cache speculation variant 2, version 2) +- FEAT_CSV2_3 (Cache speculation variant 2, version 3) - FEAT_CSV3 (Cache speculation variant 3) - FEAT_DGH (Data gathering hint) - FEAT_DIT (Data Independent Timing instructions) diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); t = FIELD_DP64(t, ID_AA64PFR0, SEL2, 1); /* FEAT_SEL2 */ t = FIELD_DP64(t, ID_AA64PFR0, DIT, 1); /* FEAT_DIT */ - t = FIELD_DP64(t, ID_AA64PFR0, CSV2, 2); /* FEAT_CSV2_2 */ + t = FIELD_DP64(t, ID_AA64PFR0, CSV2, 3); /* FEAT_CSV2_3 */ t = FIELD_DP64(t, ID_AA64PFR0, CSV3, 1); /* FEAT_CSV3 */ cpu->isar.id_aa64pfr0 = t; @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); /* FEAT_MTE3 */ t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0); /* FEAT_RASv1p1 + FEAT_DoubleFault */ t = FIELD_DP64(t, ID_AA64PFR1, SME, 1); /* FEAT_SME */ - t = FIELD_DP64(t, ID_AA64PFR1, CSV2_FRAC, 0); /* FEAT_CSV2_2 */ + t = FIELD_DP64(t, ID_AA64PFR1, CSV2_FRAC, 0); /* FEAT_CSV2_3 */ t = FIELD_DP64(t, ID_AA64PFR1, NMI, 1); /* FEAT_NMI */ cpu->isar.id_aa64pfr1 = t; -- 2.34.1 FEAT_ETS2 is a tighter set of guarantees about memory ordering involving translation table walks than the old FEAT_ETS; FEAT_ETS has been retired from the Arm ARM and the old ID_AA64MMFR1.ETS == 1 now gives no greater guarantees than ETS == 0. FEAT_ETS2 requires: * the virtual address of a load or store that appears in program order after a DSB cannot be translated until after the DSB completes (section B2.10.9) * TLB maintenance operations that only affect translations without execute permission are guaranteed complete after a DSB (R_BLDZX) * if a memory access RW2 is ordered-before memory access RW2, then RW1 is also ordered-before any translation table walk generated by RW2 that generates a Translation, Address size or Access flag fault (R_NNFPF, I_CLGHP) As with FEAT_ETS, QEMU is already compliant, because we do not reorder translation table walk memory accesses relative to other memory accesses, and we always guarantee to have finished TLB maintenance as soon as the TLB op is done. Update the documentation to list FEAT_ETS2 instead of the no-longer-existent FEAT_ETS, and update the 'max' CPU ID registers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240418152004.2106516-4-peter.maydell@linaro.org --- docs/system/arm/emulation.rst | 2 +- target/arm/tcg/cpu32.c | 2 +- target/arm/tcg/cpu64.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_EL2 (Support for execution at EL2) - FEAT_EL3 (Support for execution at EL3) - FEAT_EPAC (Enhanced pointer authentication) -- FEAT_ETS (Enhanced Translation Synchronization) +- FEAT_ETS2 (Enhanced Translation Synchronization) - FEAT_EVT (Enhanced Virtualization Traps) - FEAT_F32MM (Single-precision Matrix Multiplication) - FEAT_F64MM (Double-precision Matrix Multiplication) diff --git a/target/arm/tcg/cpu32.c b/target/arm/tcg/cpu32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu32.c +++ b/target/arm/tcg/cpu32.c @@ -XXX,XX +XXX,XX @@ void aa32_max_features(ARMCPU *cpu) cpu->isar.id_mmfr4 = t; t = cpu->isar.id_mmfr5; - t = FIELD_DP32(t, ID_MMFR5, ETS, 1); /* FEAT_ETS */ + t = FIELD_DP32(t, ID_MMFR5, ETS, 2); /* FEAT_ETS2 */ cpu->isar.id_mmfr5 = t; t = cpu->isar.id_pfr0; diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64MMFR1, LO, 1); /* FEAT_LOR */ t = FIELD_DP64(t, ID_AA64MMFR1, PAN, 3); /* FEAT_PAN3 */ t = FIELD_DP64(t, ID_AA64MMFR1, XNX, 1); /* FEAT_XNX */ - t = FIELD_DP64(t, ID_AA64MMFR1, ETS, 1); /* FEAT_ETS */ + t = FIELD_DP64(t, ID_AA64MMFR1, ETS, 2); /* FEAT_ETS2 */ t = FIELD_DP64(t, ID_AA64MMFR1, HCX, 1); /* FEAT_HCX */ t = FIELD_DP64(t, ID_AA64MMFR1, TIDCP1, 1); /* FEAT_TIDCP1 */ cpu->isar.id_aa64mmfr1 = t; -- 2.34.1 Newer versions of the Arm ARM (e.g. rev K.a) now define fields for ID_AA64MMFR3_EL1. Implement this register, so that we can set the fields if we need to. There's no behaviour change here since we don't currently set the register value to non-zero. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240418152004.2106516-5-peter.maydell@linaro.org --- target/arm/cpu.h | 17 +++++++++++++++++ target/arm/helper.c | 6 ++++-- target/arm/hvf/hvf.c | 2 ++ target/arm/kvm.c | 2 ++ 4 files changed, 25 insertions(+), 2 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ struct ArchCPU { uint64_t id_aa64mmfr0; uint64_t id_aa64mmfr1; uint64_t id_aa64mmfr2; + uint64_t id_aa64mmfr3; uint64_t id_aa64dfr0; uint64_t id_aa64dfr1; uint64_t id_aa64zfr0; @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64MMFR2, BBM, 52, 4) FIELD(ID_AA64MMFR2, EVT, 56, 4) FIELD(ID_AA64MMFR2, E0PD, 60, 4) +FIELD(ID_AA64MMFR3, TCRX, 0, 4) +FIELD(ID_AA64MMFR3, SCTLRX, 4, 4) +FIELD(ID_AA64MMFR3, S1PIE, 8, 4) +FIELD(ID_AA64MMFR3, S2PIE, 12, 4) +FIELD(ID_AA64MMFR3, S1POE, 16, 4) +FIELD(ID_AA64MMFR3, S2POE, 20, 4) +FIELD(ID_AA64MMFR3, AIE, 24, 4) +FIELD(ID_AA64MMFR3, MEC, 28, 4) +FIELD(ID_AA64MMFR3, D128, 32, 4) +FIELD(ID_AA64MMFR3, D128_2, 36, 4) +FIELD(ID_AA64MMFR3, SNERR, 40, 4) +FIELD(ID_AA64MMFR3, ANERR, 44, 4) +FIELD(ID_AA64MMFR3, SDERR, 52, 4) +FIELD(ID_AA64MMFR3, ADERR, 56, 4) +FIELD(ID_AA64MMFR3, SPEC_FPACC, 60, 4) + FIELD(ID_AA64DFR0, DEBUGVER, 0, 4) FIELD(ID_AA64DFR0, TRACEVER, 4, 4) FIELD(ID_AA64DFR0, PMUVER, 8, 4) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa64_tid3, .resetvalue = cpu->isar.id_aa64mmfr2 }, - { .name = "ID_AA64MMFR3_EL1_RESERVED", .state = ARM_CP_STATE_AA64, + { .name = "ID_AA64MMFR3_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 7, .opc2 = 3, .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa64_tid3, - .resetvalue = 0 }, + .resetvalue = cpu->isar.id_aa64mmfr3 }, { .name = "ID_AA64MMFR4_EL1_RESERVED", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 7, .opc2 = 4, .access = PL1_R, .type = ARM_CP_CONST, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) .exported_bits = R_ID_AA64MMFR1_AFP_MASK }, { .name = "ID_AA64MMFR2_EL1", .exported_bits = R_ID_AA64MMFR2_AT_MASK }, + { .name = "ID_AA64MMFR3_EL1", + .exported_bits = 0 }, { .name = "ID_AA64MMFR*_EL1_RESERVED", .is_glob = true }, { .name = "ID_AA64DFR0_EL1", diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/hvf/hvf.c +++ b/target/arm/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ static struct hvf_sreg_match hvf_sreg_match[] = { #endif { HV_SYS_REG_ID_AA64MMFR1_EL1, HVF_SYSREG(0, 7, 3, 0, 1) }, { HV_SYS_REG_ID_AA64MMFR2_EL1, HVF_SYSREG(0, 7, 3, 0, 2) }, + /* Add ID_AA64MMFR3_EL1 here when HVF supports it */ { HV_SYS_REG_MDSCR_EL1, HVF_SYSREG(0, 2, 2, 0, 2) }, { HV_SYS_REG_SCTLR_EL1, HVF_SYSREG(1, 0, 3, 0, 0) }, @@ -XXX,XX +XXX,XX @@ static bool hvf_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) { HV_SYS_REG_ID_AA64MMFR0_EL1, &host_isar.id_aa64mmfr0 }, { HV_SYS_REG_ID_AA64MMFR1_EL1, &host_isar.id_aa64mmfr1 }, { HV_SYS_REG_ID_AA64MMFR2_EL1, &host_isar.id_aa64mmfr2 }, + /* Add ID_AA64MMFR3_EL1 here when HVF supports it */ }; hv_vcpu_t fd; hv_return_t r = HV_SUCCESS; diff --git a/target/arm/kvm.c b/target/arm/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -XXX,XX +XXX,XX @@ static bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) ARM64_SYS_REG(3, 0, 0, 7, 1)); err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64mmfr2, ARM64_SYS_REG(3, 0, 0, 7, 2)); + err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64mmfr3, + ARM64_SYS_REG(3, 0, 0, 7, 3)); /* * Note that if AArch32 support is not present in the host, -- 2.34.1 FEAT_Spec_FPACC is a feature describing speculative behaviour in the event of a PAC authontication failure when FEAT_FPACCOMBINE is implemented. FEAT_Spec_FPACC means that the speculative use of pointers processed by a PAC Authentication is not materially different in terms of the impact on cached microarchitectural state (caches, TLBs, etc) between passing and failing of the PAC Authentication. QEMU doesn't do speculative execution, so we can advertise this feature. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240418152004.2106516-6-peter.maydell@linaro.org --- docs/system/arm/emulation.rst | 1 + target/arm/tcg/cpu64.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_FP16 (Half-precision floating-point data processing) - FEAT_FPAC (Faulting on AUT* instructions) - FEAT_FPACCOMBINE (Faulting on combined pointer authentication instructions) +- FEAT_FPACC_SPEC (Speculative behavior of combined pointer authentication instructions) - FEAT_FRINTTS (Floating-point to integer instructions) - FEAT_FlagM (Flag manipulation instructions v2) - FEAT_FlagM2 (Enhancements to flag manipulation instructions) diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64MMFR2, E0PD, 1); /* FEAT_E0PD */ cpu->isar.id_aa64mmfr2 = t; + t = cpu->isar.id_aa64mmfr3; + t = FIELD_DP64(t, ID_AA64MMFR3, SPEC_FPACC, 1); /* FEAT_FPACC_SPEC */ + cpu->isar.id_aa64mmfr3 = t; + t = cpu->isar.id_aa64zfr0; t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 1); t = FIELD_DP64(t, ID_AA64ZFR0, AES, 2); /* FEAT_SVE_PMULL128 */ -- 2.34.1 The Linux kernel 5.10.16 binary for sunxi has been removed from apt.armbian.com. This means that the avocado tests for these machines will be skipped (status CANCEL) if the old binary isn't present in the avocado cache. Update to 6.6.16, in the same way we did in commit e384db41d8661 when we moved to 5.10.16 in 2021. Cc: qemu-stable@nongnu.org Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2284 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Tested-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20240415151845.1564201-1-peter.maydell@linaro.org --- tests/avocado/boot_linux_console.py | 70 ++++++++++++++--------------- tests/avocado/replay_kernel.py | 8 ++-- 2 files changed, 39 insertions(+), 39 deletions(-) diff --git a/tests/avocado/boot_linux_console.py b/tests/avocado/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/avocado/boot_linux_console.py +++ b/tests/avocado/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ def test_arm_cubieboard_initrd(self): :avocado: tags=accel:tcg """ deb_url = ('https://apt.armbian.com/pool/main/l/' - 'linux-5.10.16-sunxi/linux-image-current-sunxi_21.02.2_armhf.deb') - deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' + 'linux-6.6.16/linux-image-current-sunxi_24.2.1_armhf__6.6.16-Seb3e-D6b4a-P2359-Ce96bHfe66-HK01ba-V014b-B067e-R448a.deb') + deb_hash = 'f7c3c8c5432f765445dc6e7eab02f3bbe668256b' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-5.10.16-sunxi') - dtb_path = '/usr/lib/linux-image-current-sunxi/sun4i-a10-cubieboard.dtb' + '/boot/vmlinuz-6.6.16-current-sunxi') + dtb_path = '/usr/lib/linux-image-6.6.16-current-sunxi/sun4i-a10-cubieboard.dtb' dtb_path = self.extract_from_deb(deb_path, dtb_path) initrd_url = ('https://github.com/groeck/linux-build-test/raw/' '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' @@ -XXX,XX +XXX,XX @@ def test_arm_cubieboard_sata(self): :avocado: tags=accel:tcg """ deb_url = ('https://apt.armbian.com/pool/main/l/' - 'linux-5.10.16-sunxi/linux-image-current-sunxi_21.02.2_armhf.deb') - deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' + 'linux-6.6.16/linux-image-current-sunxi_24.2.1_armhf__6.6.16-Seb3e-D6b4a-P2359-Ce96bHfe66-HK01ba-V014b-B067e-R448a.deb') + deb_hash = 'f7c3c8c5432f765445dc6e7eab02f3bbe668256b' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-5.10.16-sunxi') - dtb_path = '/usr/lib/linux-image-current-sunxi/sun4i-a10-cubieboard.dtb' + '/boot/vmlinuz-6.6.16-current-sunxi') + dtb_path = '/usr/lib/linux-image-6.6.16-current-sunxi/sun4i-a10-cubieboard.dtb' dtb_path = self.extract_from_deb(deb_path, dtb_path) rootfs_url = ('https://github.com/groeck/linux-build-test/raw/' '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' @@ -XXX,XX +XXX,XX @@ def test_arm_bpim2u(self): :avocado: tags=machine:bpim2u :avocado: tags=accel:tcg """ - deb_url = ('https://apt.armbian.com/pool/main/l/linux-5.10.16-sunxi/' - 'linux-image-current-sunxi_21.02.2_armhf.deb') - deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' + deb_url = ('https://apt.armbian.com/pool/main/l/' + 'linux-6.6.16/linux-image-current-sunxi_24.2.1_armhf__6.6.16-Seb3e-D6b4a-P2359-Ce96bHfe66-HK01ba-V014b-B067e-R448a.deb') + deb_hash = 'f7c3c8c5432f765445dc6e7eab02f3bbe668256b' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-5.10.16-sunxi') - dtb_path = ('/usr/lib/linux-image-current-sunxi/' + '/boot/vmlinuz-6.6.16-current-sunxi') + dtb_path = ('/usr/lib/linux-image-6.6.16-current-sunxi/' 'sun8i-r40-bananapi-m2-ultra.dtb') dtb_path = self.extract_from_deb(deb_path, dtb_path) @@ -XXX,XX +XXX,XX @@ def test_arm_bpim2u_initrd(self): :avocado: tags=accel:tcg :avocado: tags=machine:bpim2u """ - deb_url = ('https://apt.armbian.com/pool/main/l/linux-5.10.16-sunxi/' - 'linux-image-current-sunxi_21.02.2_armhf.deb') - deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' + deb_url = ('https://apt.armbian.com/pool/main/l/' + 'linux-6.6.16/linux-image-current-sunxi_24.2.1_armhf__6.6.16-Seb3e-D6b4a-P2359-Ce96bHfe66-HK01ba-V014b-B067e-R448a.deb') + deb_hash = 'f7c3c8c5432f765445dc6e7eab02f3bbe668256b' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-5.10.16-sunxi') - dtb_path = ('/usr/lib/linux-image-current-sunxi/' + '/boot/vmlinuz-6.6.16-current-sunxi') + dtb_path = ('/usr/lib/linux-image-6.6.16-current-sunxi/' 'sun8i-r40-bananapi-m2-ultra.dtb') dtb_path = self.extract_from_deb(deb_path, dtb_path) initrd_url = ('https://github.com/groeck/linux-build-test/raw/' @@ -XXX,XX +XXX,XX @@ def test_arm_bpim2u_gmac(self): """ self.require_netdev('user') - deb_url = ('https://apt.armbian.com/pool/main/l/linux-5.10.16-sunxi/' - 'linux-image-current-sunxi_21.02.2_armhf.deb') - deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' + deb_url = ('https://apt.armbian.com/pool/main/l/' + 'linux-6.6.16/linux-image-current-sunxi_24.2.1_armhf__6.6.16-Seb3e-D6b4a-P2359-Ce96bHfe66-HK01ba-V014b-B067e-R448a.deb') + deb_hash = 'f7c3c8c5432f765445dc6e7eab02f3bbe668256b' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-5.10.16-sunxi') - dtb_path = ('/usr/lib/linux-image-current-sunxi/' + '/boot/vmlinuz-6.6.16-current-sunxi') + dtb_path = ('/usr/lib/linux-image-6.6.16-current-sunxi/' 'sun8i-r40-bananapi-m2-ultra.dtb') dtb_path = self.extract_from_deb(deb_path, dtb_path) rootfs_url = ('http://storage.kernelci.org/images/rootfs/buildroot/' @@ -XXX,XX +XXX,XX @@ def test_arm_orangepi(self): :avocado: tags=accel:tcg """ deb_url = ('https://apt.armbian.com/pool/main/l/' - 'linux-5.10.16-sunxi/linux-image-current-sunxi_21.02.2_armhf.deb') - deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' + 'linux-6.6.16/linux-image-current-sunxi_24.2.1_armhf__6.6.16-Seb3e-D6b4a-P2359-Ce96bHfe66-HK01ba-V014b-B067e-R448a.deb') + deb_hash = 'f7c3c8c5432f765445dc6e7eab02f3bbe668256b' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-5.10.16-sunxi') - dtb_path = '/usr/lib/linux-image-current-sunxi/sun8i-h3-orangepi-pc.dtb' + '/boot/vmlinuz-6.6.16-current-sunxi') + dtb_path = '/usr/lib/linux-image-6.6.16-current-sunxi/sun8i-h3-orangepi-pc.dtb' dtb_path = self.extract_from_deb(deb_path, dtb_path) self.vm.set_console() @@ -XXX,XX +XXX,XX @@ def test_arm_orangepi_initrd(self): :avocado: tags=machine:orangepi-pc """ deb_url = ('https://apt.armbian.com/pool/main/l/' - 'linux-5.10.16-sunxi/linux-image-current-sunxi_21.02.2_armhf.deb') - deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' + 'linux-6.6.16/linux-image-current-sunxi_24.2.1_armhf__6.6.16-Seb3e-D6b4a-P2359-Ce96bHfe66-HK01ba-V014b-B067e-R448a.deb') + deb_hash = 'f7c3c8c5432f765445dc6e7eab02f3bbe668256b' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-5.10.16-sunxi') - dtb_path = '/usr/lib/linux-image-current-sunxi/sun8i-h3-orangepi-pc.dtb' + '/boot/vmlinuz-6.6.16-current-sunxi') + dtb_path = '/usr/lib/linux-image-6.6.16-current-sunxi/sun8i-h3-orangepi-pc.dtb' dtb_path = self.extract_from_deb(deb_path, dtb_path) initrd_url = ('https://github.com/groeck/linux-build-test/raw/' '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' @@ -XXX,XX +XXX,XX @@ def test_arm_orangepi_sd(self): self.require_netdev('user') deb_url = ('https://apt.armbian.com/pool/main/l/' - 'linux-5.10.16-sunxi/linux-image-current-sunxi_21.02.2_armhf.deb') - deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' + 'linux-6.6.16/linux-image-current-sunxi_24.2.1_armhf__6.6.16-Seb3e-D6b4a-P2359-Ce96bHfe66-HK01ba-V014b-B067e-R448a.deb') + deb_hash = 'f7c3c8c5432f765445dc6e7eab02f3bbe668256b' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-5.10.16-sunxi') - dtb_path = '/usr/lib/linux-image-current-sunxi/sun8i-h3-orangepi-pc.dtb' + '/boot/vmlinuz-6.6.16-current-sunxi') + dtb_path = '/usr/lib/linux-image-6.6.16-current-sunxi/sun8i-h3-orangepi-pc.dtb' dtb_path = self.extract_from_deb(deb_path, dtb_path) rootfs_url = ('http://storage.kernelci.org/images/rootfs/buildroot/' 'buildroot-baseline/20221116.0/armel/rootfs.ext2.xz') diff --git a/tests/avocado/replay_kernel.py b/tests/avocado/replay_kernel.py index XXXXXXX..XXXXXXX 100644 --- a/tests/avocado/replay_kernel.py +++ b/tests/avocado/replay_kernel.py @@ -XXX,XX +XXX,XX @@ def test_arm_cubieboard_initrd(self): :avocado: tags=machine:cubieboard """ deb_url = ('https://apt.armbian.com/pool/main/l/' - 'linux-5.10.16-sunxi/linux-image-current-sunxi_21.02.2_armhf.deb') - deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' + 'linux-6.6.16/linux-image-current-sunxi_24.2.1_armhf__6.6.16-Seb3e-D6b4a-P2359-Ce96bHfe66-HK01ba-V014b-B067e-R448a.deb') + deb_hash = 'f7c3c8c5432f765445dc6e7eab02f3bbe668256b' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-5.10.16-sunxi') - dtb_path = '/usr/lib/linux-image-current-sunxi/sun4i-a10-cubieboard.dtb' + '/boot/vmlinuz-6.6.16-current-sunxi') + dtb_path = '/usr/lib/linux-image-6.6.16-current-sunxi/sun4i-a10-cubieboard.dtb' dtb_path = self.extract_from_deb(deb_path, dtb_path) initrd_url = ('https://github.com/groeck/linux-build-test/raw/' '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' -- 2.34.1 The generic timer frequency is settable by board code via a QOM property "cntfrq", but otherwise defaults to 62.5MHz. The way this is done includes some complication resulting from how this was originally a fixed value with no QOM property. Clean it up: * always set cpu->gt_cntfrq_hz to some sensible value, whether the CPU has the generic timer or not, and whether it's system or user-only emulation * this means we can always use gt_cntfrq_hz, and never need the old GTIMER_SCALE define * set the default value in exactly one place, in the realize fn The aim here is to pave the way for handling the ARMv8.6 requirement that the generic timer frequency is always 1GHz. We're going to do that by having old CPU types keep their legacy-in-QEMU behaviour and having the default for any new CPU types be a 1GHz rather han 62.5MHz cntfrq, so we want the point where the default is decided to be in one place, and in code, not in a DEFINE_PROP_UINT64() initializer. This commit should have no behavioural changes. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240426122913.3427983-2-peter.maydell@linaro.org --- target/arm/internals.h | 7 ++++--- target/arm/cpu.c | 31 +++++++++++++++++-------------- target/arm/helper.c | 16 ++++++++-------- 3 files changed, 29 insertions(+), 25 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline bool excp_is_internal(int excp) || excp == EXCP_SEMIHOST; } -/* Scale factor for generic timers, ie number of ns per tick. - * This gives a 62.5MHz timer. +/* + * Default frequency for the generic timer, in Hz. + * This is 62.5MHz, which gives a 16 ns tick period. */ -#define GTIMER_SCALE 16 +#define GTIMER_DEFAULT_HZ 62500000 /* Bit definitions for the v7M CONTROL register */ FIELD(V7M_CONTROL, NPRIV, 0, 1) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_initfn(Object *obj) } } +/* + * 0 means "unset, use the default value". That default might vary depending + * on the CPU type, and is set in the realize fn. + */ static Property arm_cpu_gt_cntfrq_property = - DEFINE_PROP_UINT64("cntfrq", ARMCPU, gt_cntfrq_hz, - NANOSECONDS_PER_SECOND / GTIMER_SCALE); + DEFINE_PROP_UINT64("cntfrq", ARMCPU, gt_cntfrq_hz, 0); static Property arm_cpu_reset_cbar_property = DEFINE_PROP_UINT64("reset-cbar", ARMCPU, reset_cbar, 0); @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) return; } + if (!cpu->gt_cntfrq_hz) { + /* + * 0 means "the board didn't set a value, use the default". + * The default value of the generic timer frequency (as seen in + * CNTFRQ_EL0) is 62.5MHz, which corresponds to a period of 16ns. + * This is what you get (a) for a CONFIG_USER_ONLY CPU (b) if the + * board doesn't set it. + */ + cpu->gt_cntfrq_hz = GTIMER_DEFAULT_HZ; + } + #ifndef CONFIG_USER_ONLY /* The NVIC and M-profile CPU are two halves of a single piece of * hardware; trying to use one without the other is a command line @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) } { - uint64_t scale; - - if (arm_feature(env, ARM_FEATURE_GENERIC_TIMER)) { - if (!cpu->gt_cntfrq_hz) { - error_setg(errp, "Invalid CNTFRQ: %"PRId64"Hz", - cpu->gt_cntfrq_hz); - return; - } - scale = gt_cntfrq_period_ns(cpu); - } else { - scale = GTIMER_SCALE; - } + uint64_t scale = gt_cntfrq_period_ns(cpu); cpu->gt_timer[GTIMER_PHYS] = timer_new(QEMU_CLOCK_VIRTUAL, scale, arm_gt_ptimer_cb, cpu); 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 const ARMCPRegInfo v6k_cp_reginfo[] = { .resetvalue = 0 }, }; +static void arm_gt_cntfrq_reset(CPUARMState *env, const ARMCPRegInfo *opaque) +{ + ARMCPU *cpu = env_archcpu(env); + + cpu->env.cp15.c14_cntfrq = cpu->gt_cntfrq_hz; +} + #ifndef CONFIG_USER_ONLY static CPAccessResult gt_cntfrq_access(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ void arm_gt_hvtimer_cb(void *opaque) gt_recalc_timer(cpu, GTIMER_HYPVIRT); } -static void arm_gt_cntfrq_reset(CPUARMState *env, const ARMCPRegInfo *opaque) -{ - ARMCPU *cpu = env_archcpu(env); - - cpu->env.cp15.c14_cntfrq = cpu->gt_cntfrq_hz; -} - static const ARMCPRegInfo generic_timer_cp_reginfo[] = { /* * Note that CNTFRQ is purely reads-as-written for the benefit @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = { .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 0, .opc2 = 0, .type = ARM_CP_CONST, .access = PL0_R /* no PL1_RW in linux-user */, .fieldoffset = offsetof(CPUARMState, cp15.c14_cntfrq), - .resetvalue = NANOSECONDS_PER_SECOND / GTIMER_SCALE, + .resetfn = arm_gt_cntfrq_reset, }, { .name = "CNTVCT_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 0, .opc2 = 2, -- 2.34.1 Currently QEMU CPUs always run with a generic timer counter frequency of 62.5MHz, but ARMv8.6 CPUs will run at 1GHz. For older versions of the TF-A firmware that sbsa-ref runs, the frequency of the generic timer is hardcoded into the firmware, and so if the CPU actually has a different frequency then timers in the guest will be set incorrectly. The default frequency used by the 'max' CPU is about to change, so make the sbsa-ref board force the CPU frequency to the value which the firmware expects. Newer versions of TF-A will read the frequency from the CPU's CNTFRQ_EL0 register: https://github.com/ARM-software/arm-trusted-firmware/commit/4c77fac98dac0bebc63798aae9101ac865b87148 so in the longer term we could make this board use the 1GHz frequency. We will need to make sure we update the binaries used by our avocado test Aarch64SbsarefMachine.test_sbsaref_alpine_linux_max_pauth_impdef before we can do that. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Message-id: 20240426122913.3427983-3-peter.maydell@linaro.org --- hw/arm/sbsa-ref.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ #define NUM_SMMU_IRQS 4 #define NUM_SATA_PORTS 6 +/* + * Generic timer frequency in Hz (which drives both the CPU generic timers + * and the SBSA watchdog-timer). Older versions of the TF-A firmware + * typically used with sbsa-ref (including the binaries in our Avocado test + * Aarch64SbsarefMachine.test_sbsaref_alpine_linux_max_pauth_impdef + * assume it is this value. + * + * TODO: this value is not architecturally correct for an Armv8.6 or + * better CPU, so we should move to 1GHz once the TF-A fix above has + * made it into a release and into our Avocado test. + */ +#define SBSA_GTIMER_HZ 62500000 + enum { SBSA_FLASH, SBSA_MEM, @@ -XXX,XX +XXX,XX @@ static void sbsa_ref_init(MachineState *machine) &error_abort); } + object_property_set_int(cpuobj, "cntfrq", SBSA_GTIMER_HZ, &error_abort); + object_property_set_link(cpuobj, "memory", OBJECT(sysmem), &error_abort); -- 2.34.1 Currently the sbsa_gdwt watchdog device hardcodes its frequency at 62.5MHz. In real hardware, this watchdog is supposed to be driven from the system counter, which also drives the CPU generic timers. Newer CPU types (in particular from Armv8.6) should have a CPU generic timer frequency of 1GHz, so we can't leave the watchdog on the old QEMU default of 62.5GHz. Make the frequency a QOM property so it can be set by the board, and have our only board that uses this device set that frequency to the same value it sets the CPU frequency. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240426122913.3427983-4-peter.maydell@linaro.org --- include/hw/watchdog/sbsa_gwdt.h | 3 +-- hw/arm/sbsa-ref.c | 1 + hw/watchdog/sbsa_gwdt.c | 15 ++++++++++++++- 3 files changed, 16 insertions(+), 3 deletions(-) diff --git a/include/hw/watchdog/sbsa_gwdt.h b/include/hw/watchdog/sbsa_gwdt.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/watchdog/sbsa_gwdt.h +++ b/include/hw/watchdog/sbsa_gwdt.h @@ -XXX,XX +XXX,XX @@ #define SBSA_GWDT_RMMIO_SIZE 0x1000 #define SBSA_GWDT_CMMIO_SIZE 0x1000 -#define SBSA_TIMER_FREQ 62500000 /* Hz */ - typedef struct SBSA_GWDTState { /* <private> */ SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ typedef struct SBSA_GWDTState { qemu_irq irq; QEMUTimer *timer; + uint64_t freq; uint32_t id; uint32_t wcs; diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ static void create_wdt(const SBSAMachineState *sms) SysBusDevice *s = SYS_BUS_DEVICE(dev); int irq = sbsa_ref_irqmap[SBSA_GWDT_WS0]; + qdev_prop_set_uint64(dev, "clock-frequency", SBSA_GTIMER_HZ); sysbus_realize_and_unref(s, &error_fatal); sysbus_mmio_map(s, 0, rbase); sysbus_mmio_map(s, 1, cbase); diff --git a/hw/watchdog/sbsa_gwdt.c b/hw/watchdog/sbsa_gwdt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/watchdog/sbsa_gwdt.c +++ b/hw/watchdog/sbsa_gwdt.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "sysemu/reset.h" #include "sysemu/watchdog.h" +#include "hw/qdev-properties.h" #include "hw/watchdog/sbsa_gwdt.h" #include "qemu/timer.h" #include "migration/vmstate.h" @@ -XXX,XX +XXX,XX @@ static void sbsa_gwdt_update_timer(SBSA_GWDTState *s, WdtRefreshType rtype) timeout = s->woru; timeout <<= 32; timeout |= s->worl; - timeout = muldiv64(timeout, NANOSECONDS_PER_SECOND, SBSA_TIMER_FREQ); + timeout = muldiv64(timeout, NANOSECONDS_PER_SECOND, s->freq); timeout += qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); if ((rtype == EXPLICIT_REFRESH) || ((rtype == TIMEOUT_REFRESH) && @@ -XXX,XX +XXX,XX @@ static void wdt_sbsa_gwdt_realize(DeviceState *dev, Error **errp) dev); } +static Property wdt_sbsa_gwdt_props[] = { + /* + * Timer frequency in Hz. This must match the frequency used by + * the CPU's generic timer. Default 62.5Hz matches QEMU's legacy + * CPU timer frequency default. + */ + DEFINE_PROP_UINT64("clock-frequency", struct SBSA_GWDTState, freq, + 62500000), + DEFINE_PROP_END_OF_LIST(), +}; + static void wdt_sbsa_gwdt_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); @@ -XXX,XX +XXX,XX @@ static void wdt_sbsa_gwdt_class_init(ObjectClass *klass, void *data) set_bit(DEVICE_CATEGORY_WATCHDOG, dc->categories); dc->vmsd = &vmstate_sbsa_gwdt; dc->desc = "SBSA-compliant generic watchdog device"; + device_class_set_props(dc, wdt_sbsa_gwdt_props); } static const TypeInfo wdt_sbsa_gwdt_info = { -- 2.34.1 In previous versions of the Arm architecture, the frequency of the generic timers as reported in CNTFRQ_EL0 could be any IMPDEF value, and for QEMU we picked 62.5MHz, giving a timer tick period of 16ns. In Armv8.6, the architecture standardized this frequency to 1GHz. Because there is no ID register feature field that indicates whether a CPU is v8.6 or that it ought to have this counter frequency, we implement this by changing our default CNTFRQ value for all CPUs, with exceptions for backwards compatibility: * CPU types which we already implement will retain the old default value. None of these are v8.6 CPUs, so this is architecturally OK. * CPUs used in versioned machine types with a version of 9.0 or earlier will retain the old default value. The upshot is that the only CPU type that changes is 'max'; but any new type we add in future (whether v8.6 or not) will also get the new 1GHz default. It remains the case that the machine model can override the default value via the 'cntfrq' QOM property (regardless of the CPU type). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240426122913.3427983-5-peter.maydell@linaro.org --- target/arm/cpu.h | 11 +++++++++++ target/arm/internals.h | 12 ++++++++++-- hw/core/machine.c | 4 +++- target/arm/cpu.c | 23 +++++++++++++++++------ target/arm/cpu64.c | 2 ++ target/arm/tcg/cpu32.c | 4 ++++ target/arm/tcg/cpu64.c | 18 ++++++++++++++++++ 7 files changed, 65 insertions(+), 9 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ struct ArchCPU { */ bool host_cpu_probe_failed; + /* QOM property to indicate we should use the back-compat CNTFRQ default */ + bool backcompat_cntfrq; + /* Specify the number of cores in this CPU cluster. Used for the L2CTLR * register. */ @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_M_SECURITY, /* M profile Security Extension */ ARM_FEATURE_M_MAIN, /* M profile Main Extension */ ARM_FEATURE_V8_1M, /* M profile extras only in v8.1M and later */ + /* + * ARM_FEATURE_BACKCOMPAT_CNTFRQ makes the CPU default cntfrq be 62.5MHz + * if the board doesn't set a value, instead of 1GHz. It is for backwards + * compatibility and used only with CPU definitions that were already + * in QEMU before we changed the default. It should not be set on any + * CPU types added in future. + */ + ARM_FEATURE_BACKCOMPAT_CNTFRQ, /* 62.5MHz timer default */ }; static inline int arm_feature(CPUARMState *env, int feature) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline bool excp_is_internal(int excp) /* * Default frequency for the generic timer, in Hz. - * This is 62.5MHz, which gives a 16 ns tick period. + * ARMv8.6 and later CPUs architecturally must use a 1GHz timer; before + * that it was an IMPDEF choice, and QEMU initially picked 62.5MHz, + * which gives a 16ns tick period. + * + * We will use the back-compat value: + * - for QEMU CPU types added before we standardized on 1GHz + * - for versioned machine types with a version of 9.0 or earlier + * In any case, the machine model may override via the cntfrq property. */ -#define GTIMER_DEFAULT_HZ 62500000 +#define GTIMER_DEFAULT_HZ 1000000000 +#define GTIMER_BACKCOMPAT_HZ 62500000 /* Bit definitions for the v7M CONTROL register */ FIELD(V7M_CONTROL, NPRIV, 0, 1) diff --git a/hw/core/machine.c b/hw/core/machine.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -XXX,XX +XXX,XX @@ #include "hw/virtio/virtio-iommu.h" #include "audio/audio.h" -GlobalProperty hw_compat_9_0[] = {}; +GlobalProperty hw_compat_9_0[] = { + {"arm-cpu", "backcompat-cntfrq", "true" }, +}; const size_t hw_compat_9_0_len = G_N_ELEMENTS(hw_compat_9_0); GlobalProperty hw_compat_8_2[] = { diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) if (!cpu->gt_cntfrq_hz) { /* - * 0 means "the board didn't set a value, use the default". - * The default value of the generic timer frequency (as seen in - * CNTFRQ_EL0) is 62.5MHz, which corresponds to a period of 16ns. - * This is what you get (a) for a CONFIG_USER_ONLY CPU (b) if the - * board doesn't set it. + * 0 means "the board didn't set a value, use the default". (We also + * get here for the CONFIG_USER_ONLY case.) + * ARMv8.6 and later CPUs architecturally must use a 1GHz timer; before + * that it was an IMPDEF choice, and QEMU initially picked 62.5MHz, + * which gives a 16ns tick period. + * + * We will use the back-compat value: + * - for QEMU CPU types added before we standardized on 1GHz + * - for versioned machine types with a version of 9.0 or earlier */ - cpu->gt_cntfrq_hz = GTIMER_DEFAULT_HZ; + if (arm_feature(env, ARM_FEATURE_BACKCOMPAT_CNTFRQ) || + cpu->backcompat_cntfrq) { + cpu->gt_cntfrq_hz = GTIMER_BACKCOMPAT_HZ; + } else { + cpu->gt_cntfrq_hz = GTIMER_DEFAULT_HZ; + } } #ifndef CONFIG_USER_ONLY @@ -XXX,XX +XXX,XX @@ static Property arm_cpu_properties[] = { mp_affinity, ARM64_AFFINITY_INVALID), DEFINE_PROP_INT32("node-id", ARMCPU, node_id, CPU_UNSET_NUMA_NODE_ID), DEFINE_PROP_INT32("core-count", ARMCPU, core_count, -1), + /* True to default to the backward-compat old CNTFRQ rather than 1Ghz */ + DEFINE_PROP_BOOL("backcompat-cntfrq", ARMCPU, backcompat_cntfrq, false), DEFINE_PROP_END_OF_LIST() }; diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_a57_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_EL2); @@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_EL2); diff --git a/target/arm/tcg/cpu32.c b/target/arm/tcg/cpu32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu32.c +++ b/target/arm/tcg/cpu32.c @@ -XXX,XX +XXX,XX @@ static void cortex_a7_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_EL2); @@ -XXX,XX +XXX,XX @@ static void cortex_a15_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_EL2); @@ -XXX,XX +XXX,XX @@ static void cortex_r52_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_PMSA); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_AUXCR); cpu->midr = 0x411fd133; /* r1p3 */ @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_EL2); set_feature(&cpu->env, ARM_FEATURE_EL3); diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_a35_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_EL2); @@ -XXX,XX +XXX,XX @@ static void aarch64_a55_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_EL2); @@ -XXX,XX +XXX,XX @@ static void aarch64_a72_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_EL2); @@ -XXX,XX +XXX,XX @@ static void aarch64_a76_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_EL2); @@ -XXX,XX +XXX,XX @@ static void aarch64_a64fx_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_EL2); set_feature(&cpu->env, ARM_FEATURE_EL3); @@ -XXX,XX +XXX,XX @@ static void aarch64_neoverse_n1_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_EL2); @@ -XXX,XX +XXX,XX @@ static void aarch64_neoverse_v1_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_EL2); @@ -XXX,XX +XXX,XX @@ static void aarch64_a710_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_EL2); @@ -XXX,XX +XXX,XX @@ static void aarch64_neoverse_n2_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); set_feature(&cpu->env, ARM_FEATURE_EL2); @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) uint64_t t; uint32_t u; + /* + * Unset ARM_FEATURE_BACKCOMPAT_CNTFRQ, which we would otherwise default + * to because we started with aarch64_a57_initfn(). A 'max' CPU might + * be a v8.6-or-later one, in which case the cntfrq must be 1GHz; and + * because it is our "may change" CPU type we are OK with it not being + * backwards-compatible with how it worked in old QEMU. + */ + unset_feature(&cpu->env, ARM_FEATURE_BACKCOMPAT_CNTFRQ); + /* * Reset MIDR so the guest doesn't mistake our 'max' CPU type for a real * one and try to apply errata workarounds or use impdef features we -- 2.34.1 From: Alexandra Diupina <adiupina@astralinux.ru> The DMA descriptor structures for this device have a set of "address extension" fields which extend the 32 bit source addresses with an extra 16 bits to give a 48 bit address: https://docs.amd.com/r/en-US/ug1085-zynq-ultrascale-trm/ADDR_EXT-Field However, we misimplemented this address extension in several ways: * we only extracted 12 bits of the extension fields, not 16 * we didn't shift the extension field up far enough * we accidentally did the shift as 32-bit arithmetic, which meant that we would have an overflow instead of setting bits [47:32] of the resulting 64-bit address Add a type cast and use extract64() instead of extract32() to avoid integer overflow on addition. Fix bit fields extraction according to documentation. Found by Linux Verification Center (linuxtesting.org) with SVACE. Cc: qemu-stable@nongnu.org Fixes: d3c6369a96 ("introduce xlnx-dpdma") Signed-off-by: Alexandra Diupina <adiupina@astralinux.ru> Message-id: 20240428181131.23801-1-adiupina@astralinux.ru [PMM: adjusted commit message] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/dma/xlnx_dpdma.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/hw/dma/xlnx_dpdma.c b/hw/dma/xlnx_dpdma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/xlnx_dpdma.c +++ b/hw/dma/xlnx_dpdma.c @@ -XXX,XX +XXX,XX @@ static uint64_t xlnx_dpdma_desc_get_source_address(DPDMADescriptor *desc, switch (frag) { case 0: - addr = desc->source_address - + (extract32(desc->address_extension, 16, 12) << 20); + addr = (uint64_t)desc->source_address + + (extract64(desc->address_extension, 16, 16) << 32); break; case 1: - addr = desc->source_address2 - + (extract32(desc->address_extension_23, 0, 12) << 8); + addr = (uint64_t)desc->source_address2 + + (extract64(desc->address_extension_23, 0, 16) << 32); break; case 2: - addr = desc->source_address3 - + (extract32(desc->address_extension_23, 16, 12) << 20); + addr = (uint64_t)desc->source_address3 + + (extract64(desc->address_extension_23, 16, 16) << 32); break; case 3: - addr = desc->source_address4 - + (extract32(desc->address_extension_45, 0, 12) << 8); + addr = (uint64_t)desc->source_address4 + + (extract64(desc->address_extension_45, 0, 16) << 32); break; case 4: - addr = desc->source_address5 - + (extract32(desc->address_extension_45, 16, 12) << 20); + addr = (uint64_t)desc->source_address5 + + (extract64(desc->address_extension_45, 16, 16) << 32); break; default: addr = 0; -- 2.34.1 From: Thomas Huth <thuth@redhat.com> "make check-qtest-aarch64" recently started failing on FreeBSD builds, and valgrind on Linux also detected that there is something fishy with the new stm32l4x5-usart: The code forgot to set the correct class_size here, so the various class_init functions in this file wrote beyond the allocated buffer when setting the subc->type field. Fixes: 4fb37aea7e ("hw/char: Implement STM32L4x5 USART skeleton") Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240429075908.36302-1-thuth@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/stm32l4x5_usart.c | 1 + 1 file changed, 1 insertion(+) diff --git a/hw/char/stm32l4x5_usart.c b/hw/char/stm32l4x5_usart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/stm32l4x5_usart.c +++ b/hw/char/stm32l4x5_usart.c @@ -XXX,XX +XXX,XX @@ static const TypeInfo stm32l4x5_usart_types[] = { .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(Stm32l4x5UsartBaseState), .instance_init = stm32l4x5_usart_base_init, + .class_size = sizeof(Stm32l4x5UsartBaseClass), .class_init = stm32l4x5_usart_base_class_init, .abstract = true, }, { -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Use little endian for derivative OTP fuse key. Cc: qemu-stable@nongnu.org Fixes: c752bb079b ("hw/nvram: NPCM7xx OTP device model") Suggested-by: Avi Fishman <Avi.Fishman@nuvoton.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240422125813.1403-1-philmd@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/npcm7xx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-clock.h" #include "hw/qdev-properties.h" #include "qapi/error.h" +#include "qemu/bswap.h" #include "qemu/units.h" #include "sysemu/sysemu.h" #include "target/arm/cpu-qom.h" @@ -XXX,XX +XXX,XX @@ static void npcm7xx_init_fuses(NPCM7xxState *s) * The initial mask of disabled modules indicates the chip derivative (e.g. * NPCM750 or NPCM730). */ - value = tswap32(nc->disabled_modules); + value = cpu_to_le32(nc->disabled_modules); npcm7xx_otp_array_write(&s->fuse_array, &value, NPCM7XX_FUSE_DERIVATIVE, sizeof(value)); } -- 2.34.1 From: Inès Varhol <ines.varhol@telecom-paris.fr> This device implements the IM120417002 colors shield v1.1 for Arduino (which relies on the DM163 8x3-channel led driving logic) and features a simple display of an 8x8 RGB matrix. The columns of the matrix are driven by the DM163 and the rows are driven externally. Acked-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240424200929.240921-2-ines.varhol@telecom-paris.fr [PMM: updated to new reset hold method prototype] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/b-l475e-iot01a.rst | 3 +- include/hw/display/dm163.h | 59 +++++ hw/display/dm163.c | 349 +++++++++++++++++++++++++++++ hw/display/Kconfig | 3 + hw/display/meson.build | 1 + hw/display/trace-events | 14 ++ 6 files changed, 428 insertions(+), 1 deletion(-) create mode 100644 include/hw/display/dm163.h create mode 100644 hw/display/dm163.c diff --git a/docs/system/arm/b-l475e-iot01a.rst b/docs/system/arm/b-l475e-iot01a.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/b-l475e-iot01a.rst +++ b/docs/system/arm/b-l475e-iot01a.rst @@ -XXX,XX +XXX,XX @@ USART, I2C, SPI, CAN and USB OTG, as well as a variety of sensors. Supported devices """"""""""""""""" -Currently B-L475E-IOT01A machine's only supports the following devices: +Currently B-L475E-IOT01A machines support the following devices: - Cortex-M4F based STM32L4x5 SoC - STM32L4x5 EXTI (Extended interrupts and events controller) @@ -XXX,XX +XXX,XX @@ Currently B-L475E-IOT01A machine's only supports the following devices: - STM32L4x5 RCC (Reset and clock control) - STM32L4x5 GPIOs (General-purpose I/Os) - STM32L4x5 USARTs, UARTs and LPUART (Serial ports) +- optional 8x8 led display (based on DM163 driver) Missing devices """"""""""""""" diff --git a/include/hw/display/dm163.h b/include/hw/display/dm163.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/display/dm163.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU DM163 8x3-channel constant current led driver + * driving columns of associated 8x8 RGB matrix. + * + * Copyright (C) 2024 Samuel Tardieu <sam@rfc1149.net> + * Copyright (C) 2024 Arnaud Minier <arnaud.minier@telecom-paris.fr> + * Copyright (C) 2024 Inès Varhol <ines.varhol@telecom-paris.fr> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_DISPLAY_DM163_H +#define HW_DISPLAY_DM163_H + +#include "qom/object.h" +#include "hw/qdev-core.h" + +#define TYPE_DM163 "dm163" +OBJECT_DECLARE_SIMPLE_TYPE(DM163State, DM163); + +#define RGB_MATRIX_NUM_ROWS 8 +#define RGB_MATRIX_NUM_COLS 8 +#define DM163_NUM_LEDS (RGB_MATRIX_NUM_COLS * 3) +/* The last row is filled with 0 (turned off row) */ +#define COLOR_BUFFER_SIZE (RGB_MATRIX_NUM_ROWS + 1) + +typedef struct DM163State { + DeviceState parent_obj; + + /* DM163 driver */ + uint64_t bank0_shift_register[3]; + uint64_t bank1_shift_register[3]; + uint16_t latched_outputs[DM163_NUM_LEDS]; + uint16_t outputs[DM163_NUM_LEDS]; + qemu_irq sout; + + uint8_t sin; + uint8_t dck; + uint8_t rst_b; + uint8_t lat_b; + uint8_t selbk; + uint8_t en_b; + + /* IM120417002 colors shield */ + uint8_t activated_rows; + + /* 8x8 RGB matrix */ + QemuConsole *console; + uint8_t redraw; + /* Rows currently being displayed on the matrix. */ + /* The last row is filled with 0 (turned off row) */ + uint32_t buffer[COLOR_BUFFER_SIZE][RGB_MATRIX_NUM_COLS]; + uint8_t last_buffer_idx; + uint8_t buffer_idx_of_row[RGB_MATRIX_NUM_ROWS]; + /* Used to simulate retinal persistence of rows */ + uint8_t row_persistence_delay[RGB_MATRIX_NUM_ROWS]; +} DM163State; + +#endif /* HW_DISPLAY_DM163_H */ diff --git a/hw/display/dm163.c b/hw/display/dm163.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/display/dm163.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU DM163 8x3-channel constant current led driver + * driving columns of associated 8x8 RGB matrix. + * + * Copyright (C) 2024 Samuel Tardieu <sam@rfc1149.net> + * Copyright (C) 2024 Arnaud Minier <arnaud.minier@telecom-paris.fr> + * Copyright (C) 2024 Inès Varhol <ines.varhol@telecom-paris.fr> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +/* + * The reference used for the DM163 is the following : + * http://www.siti.com.tw/product/spec/LED/DM163.pdf + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "migration/vmstate.h" +#include "hw/irq.h" +#include "hw/qdev-properties.h" +#include "hw/display/dm163.h" +#include "ui/console.h" +#include "trace.h" + +#define LED_SQUARE_SIZE 100 +/* Number of frames a row stays visible after being turned off. */ +#define ROW_PERSISTENCE 3 +#define TURNED_OFF_ROW (COLOR_BUFFER_SIZE - 1) + +static const VMStateDescription vmstate_dm163 = { + .name = TYPE_DM163, + .version_id = 1, + .minimum_version_id = 1, + .fields = (const VMStateField[]) { + VMSTATE_UINT64_ARRAY(bank0_shift_register, DM163State, 3), + VMSTATE_UINT64_ARRAY(bank1_shift_register, DM163State, 3), + VMSTATE_UINT16_ARRAY(latched_outputs, DM163State, DM163_NUM_LEDS), + VMSTATE_UINT16_ARRAY(outputs, DM163State, DM163_NUM_LEDS), + VMSTATE_UINT8(dck, DM163State), + VMSTATE_UINT8(en_b, DM163State), + VMSTATE_UINT8(lat_b, DM163State), + VMSTATE_UINT8(rst_b, DM163State), + VMSTATE_UINT8(selbk, DM163State), + VMSTATE_UINT8(sin, DM163State), + VMSTATE_UINT8(activated_rows, DM163State), + VMSTATE_UINT32_2DARRAY(buffer, DM163State, COLOR_BUFFER_SIZE, + RGB_MATRIX_NUM_COLS), + VMSTATE_UINT8(last_buffer_idx, DM163State), + VMSTATE_UINT8_ARRAY(buffer_idx_of_row, DM163State, RGB_MATRIX_NUM_ROWS), + VMSTATE_UINT8_ARRAY(row_persistence_delay, DM163State, + RGB_MATRIX_NUM_ROWS), + VMSTATE_END_OF_LIST() + } +}; + +static void dm163_reset_hold(Object *obj, ResetType type) +{ + DM163State *s = DM163(obj); + + s->sin = 0; + s->dck = 0; + s->rst_b = 0; + /* Ensuring the first falling edge of lat_b isn't missed */ + s->lat_b = 1; + s->selbk = 0; + s->en_b = 0; + /* Reset stops the PWM, not the shift and latched registers. */ + memset(s->outputs, 0, sizeof(s->outputs)); + + s->activated_rows = 0; + s->redraw = 0; + trace_dm163_redraw(s->redraw); + for (unsigned i = 0; i < COLOR_BUFFER_SIZE; i++) { + memset(s->buffer[i], 0, sizeof(s->buffer[0])); + } + s->last_buffer_idx = 0; + memset(s->buffer_idx_of_row, TURNED_OFF_ROW, sizeof(s->buffer_idx_of_row)); + memset(s->row_persistence_delay, 0, sizeof(s->row_persistence_delay)); +} + +static void dm163_dck_gpio_handler(void *opaque, int line, int new_state) +{ + DM163State *s = opaque; + + if (new_state && !s->dck) { + /* + * On raising dck, sample selbk to get the bank to use, and + * sample sin for the bit to enter into the bank shift buffer. + */ + uint64_t *sb = + s->selbk ? s->bank1_shift_register : s->bank0_shift_register; + /* Output the outgoing bit on sout */ + const bool sout = (s->selbk ? sb[2] & MAKE_64BIT_MASK(63, 1) : + sb[2] & MAKE_64BIT_MASK(15, 1)) != 0; + qemu_set_irq(s->sout, sout); + /* Enter sin into the shift buffer */ + sb[2] = (sb[2] << 1) | ((sb[1] >> 63) & 1); + sb[1] = (sb[1] << 1) | ((sb[0] >> 63) & 1); + sb[0] = (sb[0] << 1) | s->sin; + } + + s->dck = new_state; + trace_dm163_dck(new_state); +} + +static void dm163_propagate_outputs(DM163State *s) +{ + s->last_buffer_idx = (s->last_buffer_idx + 1) % RGB_MATRIX_NUM_ROWS; + /* Values are output when reset is high and enable is low. */ + if (s->rst_b && !s->en_b) { + memcpy(s->outputs, s->latched_outputs, sizeof(s->outputs)); + } else { + memset(s->outputs, 0, sizeof(s->outputs)); + } + for (unsigned x = 0; x < RGB_MATRIX_NUM_COLS; x++) { + /* Grouping the 3 RGB channels in a pixel value */ + const uint16_t b = extract16(s->outputs[3 * x + 0], 6, 8); + const uint16_t g = extract16(s->outputs[3 * x + 1], 6, 8); + const uint16_t r = extract16(s->outputs[3 * x + 2], 6, 8); + uint32_t rgba = 0; + + trace_dm163_channels(3 * x + 2, r); + trace_dm163_channels(3 * x + 1, g); + trace_dm163_channels(3 * x + 0, b); + + rgba = deposit32(rgba, 0, 8, r); + rgba = deposit32(rgba, 8, 8, g); + rgba = deposit32(rgba, 16, 8, b); + + /* Led values are sent from the last one to the first one */ + s->buffer[s->last_buffer_idx][RGB_MATRIX_NUM_COLS - x - 1] = rgba; + } + for (unsigned row = 0; row < RGB_MATRIX_NUM_ROWS; row++) { + if (s->activated_rows & (1 << row)) { + s->buffer_idx_of_row[row] = s->last_buffer_idx; + s->redraw |= (1 << row); + trace_dm163_redraw(s->redraw); + } + } +} + +static void dm163_en_b_gpio_handler(void *opaque, int line, int new_state) +{ + DM163State *s = opaque; + + s->en_b = new_state; + dm163_propagate_outputs(s); + trace_dm163_en_b(new_state); +} + +static uint8_t dm163_bank0(const DM163State *s, uint8_t led) +{ + /* + * Bank 0 uses 6 bits per led, so a value may be stored accross + * two uint64_t entries. + */ + const uint8_t low_bit = 6 * led; + const uint8_t low_word = low_bit / 64; + const uint8_t high_word = (low_bit + 5) / 64; + const uint8_t low_shift = low_bit % 64; + + if (low_word == high_word) { + /* Simple case: the value belongs to one entry. */ + return extract64(s->bank0_shift_register[low_word], low_shift, 6); + } + + const uint8_t nb_bits_in_low_word = 64 - low_shift; + const uint8_t nb_bits_in_high_word = 6 - nb_bits_in_low_word; + + const uint64_t bits_in_low_word = \ + extract64(s->bank0_shift_register[low_word], low_shift, + nb_bits_in_low_word); + const uint64_t bits_in_high_word = \ + extract64(s->bank0_shift_register[high_word], 0, + nb_bits_in_high_word); + uint8_t val = 0; + + val = deposit32(val, 0, nb_bits_in_low_word, bits_in_low_word); + val = deposit32(val, nb_bits_in_low_word, nb_bits_in_high_word, + bits_in_high_word); + + return val; +} + +static uint8_t dm163_bank1(const DM163State *s, uint8_t led) +{ + const uint64_t entry = s->bank1_shift_register[led / RGB_MATRIX_NUM_COLS]; + return extract64(entry, 8 * (led % RGB_MATRIX_NUM_COLS), 8); +} + +static void dm163_lat_b_gpio_handler(void *opaque, int line, int new_state) +{ + DM163State *s = opaque; + + if (s->lat_b && !new_state) { + for (int led = 0; led < DM163_NUM_LEDS; led++) { + s->latched_outputs[led] = dm163_bank0(s, led) * dm163_bank1(s, led); + } + dm163_propagate_outputs(s); + } + + s->lat_b = new_state; + trace_dm163_lat_b(new_state); +} + +static void dm163_rst_b_gpio_handler(void *opaque, int line, int new_state) +{ + DM163State *s = opaque; + + s->rst_b = new_state; + dm163_propagate_outputs(s); + trace_dm163_rst_b(new_state); +} + +static void dm163_selbk_gpio_handler(void *opaque, int line, int new_state) +{ + DM163State *s = opaque; + + s->selbk = new_state; + trace_dm163_selbk(new_state); +} + +static void dm163_sin_gpio_handler(void *opaque, int line, int new_state) +{ + DM163State *s = opaque; + + s->sin = new_state; + trace_dm163_sin(new_state); +} + +static void dm163_rows_gpio_handler(void *opaque, int line, int new_state) +{ + DM163State *s = opaque; + + if (new_state) { + s->activated_rows |= (1 << line); + s->buffer_idx_of_row[line] = s->last_buffer_idx; + s->redraw |= (1 << line); + trace_dm163_redraw(s->redraw); + } else { + s->activated_rows &= ~(1 << line); + s->row_persistence_delay[line] = ROW_PERSISTENCE; + } + trace_dm163_activated_rows(s->activated_rows); +} + +static void dm163_invalidate_display(void *opaque) +{ + DM163State *s = (DM163State *)opaque; + s->redraw = 0xFF; + trace_dm163_redraw(s->redraw); +} + +static void update_row_persistence_delay(DM163State *s, unsigned row) +{ + if (s->row_persistence_delay[row]) { + s->row_persistence_delay[row]--; + } else { + /* + * If the ROW_PERSISTENCE delay is up, + * the row is turned off. + */ + s->buffer_idx_of_row[row] = TURNED_OFF_ROW; + s->redraw |= (1 << row); + trace_dm163_redraw(s->redraw); + } +} + +static uint32_t *update_display_of_row(DM163State *s, uint32_t *dest, + unsigned row) +{ + for (unsigned _ = 0; _ < LED_SQUARE_SIZE; _++) { + for (int x = 0; x < RGB_MATRIX_NUM_COLS * LED_SQUARE_SIZE; x++) { + /* UI layer guarantees that there's 32 bits per pixel (Mar 2024) */ + *dest++ = s->buffer[s->buffer_idx_of_row[row]][x / LED_SQUARE_SIZE]; + } + } + + dpy_gfx_update(s->console, 0, LED_SQUARE_SIZE * row, + RGB_MATRIX_NUM_COLS * LED_SQUARE_SIZE, LED_SQUARE_SIZE); + s->redraw &= ~(1 << row); + trace_dm163_redraw(s->redraw); + + return dest; +} + +static void dm163_update_display(void *opaque) +{ + DM163State *s = (DM163State *)opaque; + DisplaySurface *surface = qemu_console_surface(s->console); + uint32_t *dest; + + dest = surface_data(surface); + for (unsigned row = 0; row < RGB_MATRIX_NUM_ROWS; row++) { + update_row_persistence_delay(s, row); + if (!extract8(s->redraw, row, 1)) { + dest += LED_SQUARE_SIZE * LED_SQUARE_SIZE * RGB_MATRIX_NUM_COLS; + continue; + } + dest = update_display_of_row(s, dest, row); + } +} + +static const GraphicHwOps dm163_ops = { + .invalidate = dm163_invalidate_display, + .gfx_update = dm163_update_display, +}; + +static void dm163_realize(DeviceState *dev, Error **errp) +{ + DM163State *s = DM163(dev); + + qdev_init_gpio_in(dev, dm163_rows_gpio_handler, RGB_MATRIX_NUM_ROWS); + qdev_init_gpio_in(dev, dm163_sin_gpio_handler, 1); + qdev_init_gpio_in(dev, dm163_dck_gpio_handler, 1); + qdev_init_gpio_in(dev, dm163_rst_b_gpio_handler, 1); + qdev_init_gpio_in(dev, dm163_lat_b_gpio_handler, 1); + qdev_init_gpio_in(dev, dm163_selbk_gpio_handler, 1); + qdev_init_gpio_in(dev, dm163_en_b_gpio_handler, 1); + qdev_init_gpio_out_named(dev, &s->sout, "sout", 1); + + s->console = graphic_console_init(dev, 0, &dm163_ops, s); + qemu_console_resize(s->console, RGB_MATRIX_NUM_COLS * LED_SQUARE_SIZE, + RGB_MATRIX_NUM_ROWS * LED_SQUARE_SIZE); +} + +static void dm163_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + dc->desc = "DM163"; + dc->vmsd = &vmstate_dm163; + dc->realize = dm163_realize; + rc->phases.hold = dm163_reset_hold; + set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories); +} + +static const TypeInfo dm163_types[] = { + { + .name = TYPE_DM163, + .parent = TYPE_DEVICE, + .instance_size = sizeof(DM163State), + .class_init = dm163_class_init + } +}; + +DEFINE_TYPES(dm163_types) diff --git a/hw/display/Kconfig b/hw/display/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/display/Kconfig +++ b/hw/display/Kconfig @@ -XXX,XX +XXX,XX @@ config XLNX_DISPLAYPORT bool # defaults to "N", enabled by specific boards depends on PIXMAN + +config DM163 + bool diff --git a/hw/display/meson.build b/hw/display/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/display/meson.build +++ b/hw/display/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_NEXTCUBE', if_true: files('next-fb.c')) system_ss.add(when: 'CONFIG_VGA', if_true: files('vga.c')) system_ss.add(when: 'CONFIG_VIRTIO', if_true: files('virtio-dmabuf.c')) +system_ss.add(when: 'CONFIG_DM163', if_true: files('dm163.c')) if (config_all_devices.has_key('CONFIG_VGA_CIRRUS') or config_all_devices.has_key('CONFIG_VGA_PCI') or diff --git a/hw/display/trace-events b/hw/display/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/display/trace-events +++ b/hw/display/trace-events @@ -XXX,XX +XXX,XX @@ macfb_ctrl_write(uint64_t addr, uint64_t value, unsigned int size) "addr 0x%"PRI macfb_sense_read(uint32_t value) "video sense: 0x%"PRIx32 macfb_sense_write(uint32_t value) "video sense: 0x%"PRIx32 macfb_update_mode(uint32_t width, uint32_t height, uint8_t depth) "setting mode to width %"PRId32 " height %"PRId32 " size %d" + +# dm163.c +dm163_redraw(uint8_t redraw) "0x%02x" +dm163_dck(unsigned new_state) "dck : %u" +dm163_en_b(unsigned new_state) "en_b : %u" +dm163_rst_b(unsigned new_state) "rst_b : %u" +dm163_lat_b(unsigned new_state) "lat_b : %u" +dm163_sin(unsigned new_state) "sin : %u" +dm163_selbk(unsigned new_state) "selbk : %u" +dm163_activated_rows(int new_state) "Activated rows : 0x%" PRIx32 "" +dm163_bits_ppi(unsigned dest_width) "dest_width : %u" +dm163_leds(int led, uint32_t value) "led %d: 0x%x" +dm163_channels(int channel, uint8_t value) "channel %d: 0x%x" +dm163_refresh_rate(uint32_t rr) "refresh rate %d" -- 2.34.1 From: Inès Varhol <ines.varhol@telecom-paris.fr> Exposing SYSCFG inputs to the SoC is practical in order to wire the SoC to the optional DM163 display from the board code (GPIOs outputs need to be connected to both SYSCFG inputs and DM163 inputs). STM32L4x5 SYSCFG in-irq interception needed to be changed accordingly. Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240424200929.240921-3-ines.varhol@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stm32l4x5_soc.c | 6 ++++-- tests/qtest/stm32l4x5_gpio-test.c | 13 ++++++++----- tests/qtest/stm32l4x5_syscfg-test.c | 17 ++++++++++------- 3 files changed, 22 insertions(+), 14 deletions(-) diff --git a/hw/arm/stm32l4x5_soc.c b/hw/arm/stm32l4x5_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32l4x5_soc.c +++ b/hw/arm/stm32l4x5_soc.c @@ -XXX,XX +XXX,XX @@ /* * STM32L4x5 SoC family * - * Copyright (c) 2023 Arnaud Minier <arnaud.minier@telecom-paris.fr> - * Copyright (c) 2023 Inès Varhol <ines.varhol@telecom-paris.fr> + * Copyright (c) 2023-2024 Arnaud Minier <arnaud.minier@telecom-paris.fr> + * Copyright (c) 2023-2024 Inès Varhol <ines.varhol@telecom-paris.fr> * * SPDX-License-Identifier: GPL-2.0-or-later * @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_soc_realize(DeviceState *dev_soc, Error **errp) } } + qdev_pass_gpios(DEVICE(&s->syscfg), dev_soc, NULL); + /* EXTI device */ busdev = SYS_BUS_DEVICE(&s->exti); if (!sysbus_realize(busdev, errp)) { diff --git a/tests/qtest/stm32l4x5_gpio-test.c b/tests/qtest/stm32l4x5_gpio-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/stm32l4x5_gpio-test.c +++ b/tests/qtest/stm32l4x5_gpio-test.c @@ -XXX,XX +XXX,XX @@ #define OTYPER_PUSH_PULL 0 #define OTYPER_OPEN_DRAIN 1 +/* SoC forwards GPIOs to SysCfg */ +#define SYSCFG "/machine/soc" + const uint32_t moder_reset[NUM_GPIOS] = { 0xABFFFFFF, 0xFFFFFEBF, @@ -XXX,XX +XXX,XX @@ static void test_gpio_output_mode(const void *data) uint32_t gpio = test_gpio_addr(data); unsigned int gpio_id = get_gpio_id(gpio); - qtest_irq_intercept_in(global_qtest, "/machine/soc/syscfg"); + qtest_irq_intercept_in(global_qtest, SYSCFG); /* Set a bit in ODR and check nothing happens */ gpio_set_bit(gpio, ODR, pin, 1); @@ -XXX,XX +XXX,XX @@ static void test_gpio_input_mode(const void *data) uint32_t gpio = test_gpio_addr(data); unsigned int gpio_id = get_gpio_id(gpio); - qtest_irq_intercept_in(global_qtest, "/machine/soc/syscfg"); + qtest_irq_intercept_in(global_qtest, SYSCFG); /* Configure a line as input, raise it, and check that the pin is high */ gpio_set_2bits(gpio, MODER, pin, MODER_INPUT); @@ -XXX,XX +XXX,XX @@ static void test_pull_up_pull_down(const void *data) uint32_t gpio = test_gpio_addr(data); unsigned int gpio_id = get_gpio_id(gpio); - qtest_irq_intercept_in(global_qtest, "/machine/soc/syscfg"); + qtest_irq_intercept_in(global_qtest, SYSCFG); /* Configure a line as input with pull-up, check the line is set high */ gpio_set_2bits(gpio, MODER, pin, MODER_INPUT); @@ -XXX,XX +XXX,XX @@ static void test_push_pull(const void *data) uint32_t gpio = test_gpio_addr(data); uint32_t gpio2 = GPIO_BASE_ADDR + (GPIO_H - gpio); - qtest_irq_intercept_in(global_qtest, "/machine/soc/syscfg"); + qtest_irq_intercept_in(global_qtest, SYSCFG); /* Setting a line high externally, configuring it in push-pull output */ /* And checking the pin was disconnected */ @@ -XXX,XX +XXX,XX @@ static void test_open_drain(const void *data) uint32_t gpio = test_gpio_addr(data); uint32_t gpio2 = GPIO_BASE_ADDR + (GPIO_H - gpio); - qtest_irq_intercept_in(global_qtest, "/machine/soc/syscfg"); + qtest_irq_intercept_in(global_qtest, SYSCFG); /* Setting a line high externally, configuring it in open-drain output */ /* And checking the pin was disconnected */ diff --git a/tests/qtest/stm32l4x5_syscfg-test.c b/tests/qtest/stm32l4x5_syscfg-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/stm32l4x5_syscfg-test.c +++ b/tests/qtest/stm32l4x5_syscfg-test.c @@ -XXX,XX +XXX,XX @@ /* * QTest testcase for STM32L4x5_SYSCFG * - * Copyright (c) 2023 Arnaud Minier <arnaud.minier@telecom-paris.fr> - * Copyright (c) 2023 Inès Varhol <ines.varhol@telecom-paris.fr> + * Copyright (c) 2024 Arnaud Minier <arnaud.minier@telecom-paris.fr> + * Copyright (c) 2024 Inès Varhol <ines.varhol@telecom-paris.fr> * * This work is licensed under the terms of the GNU GPL, version 2 or later. * See the COPYING file in the top-level directory. @@ -XXX,XX +XXX,XX @@ #define SYSCFG_SWPR2 0x28 #define INVALID_ADDR 0x2C +/* SoC forwards GPIOs to SysCfg */ +#define SYSCFG "/machine/soc" +#define EXTI "/machine/soc/exti" + static void syscfg_writel(unsigned int offset, uint32_t value) { writel(SYSCFG_BASE_ADDR + offset, value); @@ -XXX,XX +XXX,XX @@ static uint32_t syscfg_readl(unsigned int offset) static void syscfg_set_irq(int num, int level) { - qtest_set_irq_in(global_qtest, "/machine/soc/syscfg", - NULL, num, level); + qtest_set_irq_in(global_qtest, SYSCFG, NULL, num, level); } static void system_reset(void) @@ -XXX,XX +XXX,XX @@ static void test_interrupt(void) * Test that GPIO rising lines result in an irq * with the right configuration */ - qtest_irq_intercept_in(global_qtest, "/machine/soc/exti"); + qtest_irq_intercept_in(global_qtest, EXTI); /* GPIOA is the default source for EXTI lines 0 to 15 */ @@ -XXX,XX +XXX,XX @@ static void test_irq_pin_multiplexer(void) * Test that syscfg irq sets the right exti irq */ - qtest_irq_intercept_in(global_qtest, "/machine/soc/exti"); + qtest_irq_intercept_in(global_qtest, EXTI); syscfg_set_irq(0, 1); @@ -XXX,XX +XXX,XX @@ static void test_irq_gpio_multiplexer(void) * Test that an irq is generated only by the right GPIO */ - qtest_irq_intercept_in(global_qtest, "/machine/soc/exti"); + qtest_irq_intercept_in(global_qtest, EXTI); /* GPIOA is the default source for EXTI lines 0 to 15 */ -- 2.34.1 From: Inès Varhol <ines.varhol@telecom-paris.fr> Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240424200929.240921-4-ines.varhol@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/b-l475e-iot01a.c | 46 ++++++++++++++++++++++++++++------------- 1 file changed, 32 insertions(+), 14 deletions(-) diff --git a/hw/arm/b-l475e-iot01a.c b/hw/arm/b-l475e-iot01a.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/b-l475e-iot01a.c +++ b/hw/arm/b-l475e-iot01a.c @@ -XXX,XX +XXX,XX @@ * B-L475E-IOT01A Discovery Kit machine * (B-L475E-IOT01A IoT Node) * - * Copyright (c) 2023 Arnaud Minier <arnaud.minier@telecom-paris.fr> - * Copyright (c) 2023 Inès Varhol <ines.varhol@telecom-paris.fr> + * Copyright (c) 2023-2024 Arnaud Minier <arnaud.minier@telecom-paris.fr> + * Copyright (c) 2023-2024 Inès Varhol <ines.varhol@telecom-paris.fr> * * SPDX-License-Identifier: GPL-2.0-or-later * @@ -XXX,XX +XXX,XX @@ /* B-L475E-IOT01A implementation is derived from netduinoplus2 */ -static void b_l475e_iot01a_init(MachineState *machine) +#define TYPE_B_L475E_IOT01A MACHINE_TYPE_NAME("b-l475e-iot01a") +OBJECT_DECLARE_SIMPLE_TYPE(Bl475eMachineState, B_L475E_IOT01A) + +typedef struct Bl475eMachineState { + MachineState parent_obj; + + Stm32l4x5SocState soc; +} Bl475eMachineState; + +static void bl475e_init(MachineState *machine) { + Bl475eMachineState *s = B_L475E_IOT01A(machine); const Stm32l4x5SocClass *sc; - DeviceState *dev; - dev = qdev_new(TYPE_STM32L4X5XG_SOC); - object_property_add_child(OBJECT(machine), "soc", OBJECT(dev)); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); + object_initialize_child(OBJECT(machine), "soc", &s->soc, + TYPE_STM32L4X5XG_SOC); + sysbus_realize(SYS_BUS_DEVICE(&s->soc), &error_fatal); - sc = STM32L4X5_SOC_GET_CLASS(dev); - armv7m_load_kernel(ARM_CPU(first_cpu), - machine->kernel_filename, - 0, sc->flash_size); + sc = STM32L4X5_SOC_GET_CLASS(&s->soc); + armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, 0, + sc->flash_size); } -static void b_l475e_iot01a_machine_init(MachineClass *mc) +static void bl475e_machine_init(ObjectClass *oc, void *data) { + MachineClass *mc = MACHINE_CLASS(oc); static const char *machine_valid_cpu_types[] = { ARM_CPU_TYPE_NAME("cortex-m4"), NULL }; mc->desc = "B-L475E-IOT01A Discovery Kit (Cortex-M4)"; - mc->init = b_l475e_iot01a_init; + mc->init = bl475e_init; mc->valid_cpu_types = machine_valid_cpu_types; /* SRAM pre-allocated as part of the SoC instantiation */ mc->default_ram_size = 0; } -DEFINE_MACHINE("b-l475e-iot01a", b_l475e_iot01a_machine_init) +static const TypeInfo bl475e_machine_type[] = { + { + .name = TYPE_B_L475E_IOT01A, + .parent = TYPE_MACHINE, + .instance_size = sizeof(Bl475eMachineState), + .class_init = bl475e_machine_init, + } +}; + +DEFINE_TYPES(bl475e_machine_type) -- 2.34.1 From: Inès Varhol <ines.varhol@telecom-paris.fr> Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240424200929.240921-5-ines.varhol@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/b-l475e-iot01a.c | 59 +++++++++++++++++++++++++++++++++++++++-- hw/arm/Kconfig | 1 + 2 files changed, 58 insertions(+), 2 deletions(-) diff --git a/hw/arm/b-l475e-iot01a.c b/hw/arm/b-l475e-iot01a.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/b-l475e-iot01a.c +++ b/hw/arm/b-l475e-iot01a.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/qdev-properties.h" #include "qemu/error-report.h" -#include "hw/arm/stm32l4x5_soc.h" #include "hw/arm/boot.h" +#include "hw/core/split-irq.h" +#include "hw/arm/stm32l4x5_soc.h" +#include "hw/gpio/stm32l4x5_gpio.h" +#include "hw/display/dm163.h" -/* B-L475E-IOT01A implementation is derived from netduinoplus2 */ +/* B-L475E-IOT01A implementation is inspired from netduinoplus2 and arduino */ + +/* + * There are actually 14 input pins in the DM163 device. + * Here the DM163 input pin EN isn't connected to the STM32L4x5 + * GPIOs as the IM120417002 colors shield doesn't actually use + * this pin to drive the RGB matrix. + */ +#define NUM_DM163_INPUTS 13 + +static const unsigned dm163_input[NUM_DM163_INPUTS] = { + 1 * GPIO_NUM_PINS + 2, /* ROW0 PB2 */ + 0 * GPIO_NUM_PINS + 15, /* ROW1 PA15 */ + 0 * GPIO_NUM_PINS + 2, /* ROW2 PA2 */ + 0 * GPIO_NUM_PINS + 7, /* ROW3 PA7 */ + 0 * GPIO_NUM_PINS + 6, /* ROW4 PA6 */ + 0 * GPIO_NUM_PINS + 5, /* ROW5 PA5 */ + 1 * GPIO_NUM_PINS + 0, /* ROW6 PB0 */ + 0 * GPIO_NUM_PINS + 3, /* ROW7 PA3 */ + 0 * GPIO_NUM_PINS + 4, /* SIN (SDA) PA4 */ + 1 * GPIO_NUM_PINS + 1, /* DCK (SCK) PB1 */ + 2 * GPIO_NUM_PINS + 3, /* RST_B (RST) PC3 */ + 2 * GPIO_NUM_PINS + 4, /* LAT_B (LAT) PC4 */ + 2 * GPIO_NUM_PINS + 5, /* SELBK (SB) PC5 */ +}; #define TYPE_B_L475E_IOT01A MACHINE_TYPE_NAME("b-l475e-iot01a") OBJECT_DECLARE_SIMPLE_TYPE(Bl475eMachineState, B_L475E_IOT01A) @@ -XXX,XX +XXX,XX @@ typedef struct Bl475eMachineState { MachineState parent_obj; Stm32l4x5SocState soc; + SplitIRQ gpio_splitters[NUM_DM163_INPUTS]; + DM163State dm163; } Bl475eMachineState; static void bl475e_init(MachineState *machine) { Bl475eMachineState *s = B_L475E_IOT01A(machine); const Stm32l4x5SocClass *sc; + DeviceState *dev, *gpio_out_splitter; + unsigned gpio, pin; object_initialize_child(OBJECT(machine), "soc", &s->soc, TYPE_STM32L4X5XG_SOC); @@ -XXX,XX +XXX,XX @@ static void bl475e_init(MachineState *machine) sc = STM32L4X5_SOC_GET_CLASS(&s->soc); armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, 0, sc->flash_size); + + if (object_class_by_name(TYPE_DM163)) { + object_initialize_child(OBJECT(machine), "dm163", + &s->dm163, TYPE_DM163); + dev = DEVICE(&s->dm163); + qdev_realize(dev, NULL, &error_abort); + + for (unsigned i = 0; i < NUM_DM163_INPUTS; i++) { + object_initialize_child(OBJECT(machine), "gpio-out-splitters[*]", + &s->gpio_splitters[i], TYPE_SPLIT_IRQ); + gpio_out_splitter = DEVICE(&s->gpio_splitters[i]); + qdev_prop_set_uint32(gpio_out_splitter, "num-lines", 2); + qdev_realize(gpio_out_splitter, NULL, &error_fatal); + + qdev_connect_gpio_out(gpio_out_splitter, 0, + qdev_get_gpio_in(DEVICE(&s->soc), dm163_input[i])); + qdev_connect_gpio_out(gpio_out_splitter, 1, + qdev_get_gpio_in(dev, i)); + gpio = dm163_input[i] / GPIO_NUM_PINS; + pin = dm163_input[i] % GPIO_NUM_PINS; + qdev_connect_gpio_out(DEVICE(&s->soc.gpio[gpio]), pin, + qdev_get_gpio_in(DEVICE(gpio_out_splitter), 0)); + } + } } static void bl475e_machine_init(ObjectClass *oc, void *data) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config B_L475E_IOT01A default y depends on TCG && ARM select STM32L4X5_SOC + imply DM163 config STM32L4X5_SOC bool -- 2.34.1 From: Inès Varhol <ines.varhol@telecom-paris.fr> `test_dm163_bank()` Checks that the pin "sout" of the DM163 led driver outputs the values received on pin "sin" with the expected latency (depending on the bank). `test_dm163_gpio_connection()` Check that changes to relevant STM32L4x5 GPIO pins are propagated to the DM163 device. Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Acked-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240424200929.240921-6-ines.varhol@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/dm163-test.c | 194 +++++++++++++++++++++++++++++++++++++++ tests/qtest/meson.build | 2 + 2 files changed, 196 insertions(+) create mode 100644 tests/qtest/dm163-test.c diff --git a/tests/qtest/dm163-test.c b/tests/qtest/dm163-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/dm163-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTest testcase for DM163 + * + * Copyright (C) 2024 Samuel Tardieu <sam@rfc1149.net> + * Copyright (C) 2024 Arnaud Minier <arnaud.minier@telecom-paris.fr> + * Copyright (C) 2024 Inès Varhol <ines.varhol@telecom-paris.fr> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "libqtest.h" + +enum DM163_INPUTS { + SIN = 8, + DCK = 9, + RST_B = 10, + LAT_B = 11, + SELBK = 12, + EN_B = 13 +}; + +#define DEVICE_NAME "/machine/dm163" +#define GPIO_OUT(name, value) qtest_set_irq_in(qts, DEVICE_NAME, NULL, name, \ + value) +#define GPIO_PULSE(name) \ + do { \ + GPIO_OUT(name, 1); \ + GPIO_OUT(name, 0); \ + } while (0) + + +static void rise_gpio_pin_dck(QTestState *qts) +{ + /* Configure output mode for pin PB1 */ + qtest_writel(qts, 0x48000400, 0xFFFFFEB7); + /* Write 1 in ODR for PB1 */ + qtest_writel(qts, 0x48000414, 0x00000002); +} + +static void lower_gpio_pin_dck(QTestState *qts) +{ + /* Configure output mode for pin PB1 */ + qtest_writel(qts, 0x48000400, 0xFFFFFEB7); + /* Write 0 in ODR for PB1 */ + qtest_writel(qts, 0x48000414, 0x00000000); +} + +static void rise_gpio_pin_selbk(QTestState *qts) +{ + /* Configure output mode for pin PC5 */ + qtest_writel(qts, 0x48000800, 0xFFFFF7FF); + /* Write 1 in ODR for PC5 */ + qtest_writel(qts, 0x48000814, 0x00000020); +} + +static void lower_gpio_pin_selbk(QTestState *qts) +{ + /* Configure output mode for pin PC5 */ + qtest_writel(qts, 0x48000800, 0xFFFFF7FF); + /* Write 0 in ODR for PC5 */ + qtest_writel(qts, 0x48000814, 0x00000000); +} + +static void rise_gpio_pin_lat_b(QTestState *qts) +{ + /* Configure output mode for pin PC4 */ + qtest_writel(qts, 0x48000800, 0xFFFFFDFF); + /* Write 1 in ODR for PC4 */ + qtest_writel(qts, 0x48000814, 0x00000010); +} + +static void lower_gpio_pin_lat_b(QTestState *qts) +{ + /* Configure output mode for pin PC4 */ + qtest_writel(qts, 0x48000800, 0xFFFFFDFF); + /* Write 0 in ODR for PC4 */ + qtest_writel(qts, 0x48000814, 0x00000000); +} + +static void rise_gpio_pin_rst_b(QTestState *qts) +{ + /* Configure output mode for pin PC3 */ + qtest_writel(qts, 0x48000800, 0xFFFFFF7F); + /* Write 1 in ODR for PC3 */ + qtest_writel(qts, 0x48000814, 0x00000008); +} + +static void lower_gpio_pin_rst_b(QTestState *qts) +{ + /* Configure output mode for pin PC3 */ + qtest_writel(qts, 0x48000800, 0xFFFFFF7F); + /* Write 0 in ODR for PC3 */ + qtest_writel(qts, 0x48000814, 0x00000000); +} + +static void rise_gpio_pin_sin(QTestState *qts) +{ + /* Configure output mode for pin PA4 */ + qtest_writel(qts, 0x48000000, 0xFFFFFDFF); + /* Write 1 in ODR for PA4 */ + qtest_writel(qts, 0x48000014, 0x00000010); +} + +static void lower_gpio_pin_sin(QTestState *qts) +{ + /* Configure output mode for pin PA4 */ + qtest_writel(qts, 0x48000000, 0xFFFFFDFF); + /* Write 0 in ODR for PA4 */ + qtest_writel(qts, 0x48000014, 0x00000000); +} + +static void test_dm163_bank(const void *opaque) +{ + const unsigned bank = (uintptr_t) opaque; + const int width = bank ? 192 : 144; + + QTestState *qts = qtest_initf("-M b-l475e-iot01a"); + qtest_irq_intercept_out_named(qts, DEVICE_NAME, "sout"); + GPIO_OUT(RST_B, 1); + GPIO_OUT(EN_B, 0); + GPIO_OUT(DCK, 0); + GPIO_OUT(SELBK, bank); + GPIO_OUT(LAT_B, 1); + + /* Fill bank with zeroes */ + GPIO_OUT(SIN, 0); + for (int i = 0; i < width; i++) { + GPIO_PULSE(DCK); + } + /* Fill bank with ones, check that we get the previous zeroes */ + GPIO_OUT(SIN, 1); + for (int i = 0; i < width; i++) { + GPIO_PULSE(DCK); + g_assert(!qtest_get_irq(qts, 0)); + } + + /* Pulse one more bit in the bank, check that we get a one */ + GPIO_PULSE(DCK); + g_assert(qtest_get_irq(qts, 0)); + + qtest_quit(qts); +} + +static void test_dm163_gpio_connection(void) +{ + QTestState *qts = qtest_init("-M b-l475e-iot01a"); + qtest_irq_intercept_in(qts, DEVICE_NAME); + + g_assert_false(qtest_get_irq(qts, SIN)); + g_assert_false(qtest_get_irq(qts, DCK)); + g_assert_false(qtest_get_irq(qts, RST_B)); + g_assert_false(qtest_get_irq(qts, LAT_B)); + g_assert_false(qtest_get_irq(qts, SELBK)); + + rise_gpio_pin_dck(qts); + g_assert_true(qtest_get_irq(qts, DCK)); + lower_gpio_pin_dck(qts); + g_assert_false(qtest_get_irq(qts, DCK)); + + rise_gpio_pin_lat_b(qts); + g_assert_true(qtest_get_irq(qts, LAT_B)); + lower_gpio_pin_lat_b(qts); + g_assert_false(qtest_get_irq(qts, LAT_B)); + + rise_gpio_pin_selbk(qts); + g_assert_true(qtest_get_irq(qts, SELBK)); + lower_gpio_pin_selbk(qts); + g_assert_false(qtest_get_irq(qts, SELBK)); + + rise_gpio_pin_rst_b(qts); + g_assert_true(qtest_get_irq(qts, RST_B)); + lower_gpio_pin_rst_b(qts); + g_assert_false(qtest_get_irq(qts, RST_B)); + + rise_gpio_pin_sin(qts); + g_assert_true(qtest_get_irq(qts, SIN)); + lower_gpio_pin_sin(qts); + g_assert_false(qtest_get_irq(qts, SIN)); + + g_assert_false(qtest_get_irq(qts, DCK)); + g_assert_false(qtest_get_irq(qts, LAT_B)); + g_assert_false(qtest_get_irq(qts, SELBK)); + g_assert_false(qtest_get_irq(qts, RST_B)); +} + +int main(int argc, char **argv) +{ + g_test_init(&argc, &argv, NULL); + qtest_add_data_func("/dm163/bank0", (void *)0, test_dm163_bank); + qtest_add_data_func("/dm163/bank1", (void *)1, test_dm163_bank); + qtest_add_func("/dm163/gpio_connection", test_dm163_gpio_connection); + return g_test_run(); +} diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qtests_arm = \ (config_all_devices.has_key('CONFIG_MICROBIT') ? ['microbit-test'] : []) + \ (config_all_devices.has_key('CONFIG_STM32L4X5_SOC') ? qtests_stm32l4x5 : []) + \ (config_all_devices.has_key('CONFIG_FSI_APB2OPB_ASPEED') ? ['aspeed_fsi-test'] : []) + \ + (config_all_devices.has_key('CONFIG_STM32L4X5_SOC') and + config_all_devices.has_key('CONFIG_DM163')? ['dm163-test'] : []) + \ ['arm-cpu-features', 'boot-serial-test'] -- 2.34.1