Small pile of bug fixes for rc1. I've included my patches to get our docs building with Sphinx 3, just for convenience... -- PMM The following changes since commit b149dea55cce97cb226683d06af61984a1c11e96: Merge remote-tracking branch 'remotes/cschoenebeck/tags/pull-9p-20201102' into staging (2020-11-02 10:57:48 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20201102 for you to fetch changes up to ffb4fbf90a2f63c9cb33e4bb9f854c79bf04ca4a: tests/qtest/npcm7xx_rng-test: Disable randomness tests (2020-11-02 16:52:18 +0000) ---------------------------------------------------------------- target-arm queue: * target/arm: Fix Neon emulation bugs on big-endian hosts * target/arm: fix handling of HCR.FB * target/arm: fix LORID_EL1 access check * disas/capstone: Fix monitor disassembly of >32 bytes * hw/arm/smmuv3: Fix potential integer overflow (CID 1432363) * hw/arm/boot: fix SVE for EL3 direct kernel boot * hw/display/omap_lcdc: Fix potential NULL pointer dereference * hw/display/exynos4210_fimd: Fix potential NULL pointer dereference * target/arm: Get correct MMU index for other-security-state * configure: Test that gio libs from pkg-config work * hw/intc/arm_gicv3_cpuif: Make GIC maintenance interrupts work * docs: Fix building with Sphinx 3 * tests/qtest/npcm7xx_rng-test: Disable randomness tests ---------------------------------------------------------------- AlexChen (2): hw/display/omap_lcdc: Fix potential NULL pointer dereference hw/display/exynos4210_fimd: Fix potential NULL pointer dereference Peter Maydell (9): target/arm: Fix float16 pairwise Neon ops on big-endian hosts target/arm: Fix VUDOT/VSDOT (scalar) on big-endian hosts disas/capstone: Fix monitor disassembly of >32 bytes target/arm: Get correct MMU index for other-security-state configure: Test that gio libs from pkg-config work hw/intc/arm_gicv3_cpuif: Make GIC maintenance interrupts work scripts/kerneldoc: For Sphinx 3 use c:macro for macros with arguments qemu-option-trace.rst.inc: Don't use option:: markup tests/qtest/npcm7xx_rng-test: Disable randomness tests Philippe Mathieu-Daudé (1): hw/arm/smmuv3: Fix potential integer overflow (CID 1432363) Richard Henderson (11): target/arm: Introduce neon_full_reg_offset target/arm: Move neon_element_offset to translate.c target/arm: Use neon_element_offset in neon_load/store_reg target/arm: Use neon_element_offset in vfp_reg_offset target/arm: Add read/write_neon_element32 target/arm: Expand read/write_neon_element32 to all MemOp target/arm: Rename neon_load_reg32 to vfp_load_reg32 target/arm: Add read/write_neon_element64 target/arm: Rename neon_load_reg64 to vfp_load_reg64 target/arm: Simplify do_long_3d and do_2scalar_long target/arm: Improve do_prewiden_3d Rémi Denis-Courmont (3): target/arm: fix handling of HCR.FB target/arm: fix LORID_EL1 access check hw/arm/boot: fix SVE for EL3 direct kernel boot docs/qemu-option-trace.rst.inc | 6 +- configure | 10 +- include/hw/intc/arm_gicv3_common.h | 1 - disas/capstone.c | 2 +- hw/arm/boot.c | 3 + hw/arm/smmuv3.c | 3 +- hw/display/exynos4210_fimd.c | 4 +- hw/display/omap_lcdc.c | 10 +- hw/intc/arm_gicv3_cpuif.c | 5 +- target/arm/helper.c | 24 +- target/arm/m_helper.c | 3 +- target/arm/translate.c | 153 +++++++++--- target/arm/vec_helper.c | 12 +- tests/qtest/npcm7xx_rng-test.c | 14 +- scripts/kernel-doc | 18 +- target/arm/translate-neon.c.inc | 472 ++++++++++++++++++++----------------- target/arm/translate-vfp.c.inc | 341 +++++++++++---------------- 17 files changed, 588 insertions(+), 493 deletions(-) From: Richard Henderson <richard.henderson@linaro.org> This function makes it clear that we're talking about the whole register, and not the 32-bit piece at index 0. This fixes a bug when running on a big-endian host. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 8 ++++++ target/arm/translate-neon.c.inc | 44 ++++++++++++++++----------------- target/arm/translate-vfp.c.inc | 2 +- 3 files changed, 31 insertions(+), 23 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void gen_hlt(DisasContext *s, int imm) unallocated_encoding(s); } +/* + * Return the offset of a "full" NEON Dreg. + */ +static long neon_full_reg_offset(unsigned reg) +{ + return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); +} + static inline long vfp_reg_offset(bool dp, unsigned reg) { if (dp) { diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ neon_element_offset(int reg, int element, MemOp size) ofs ^= 8 - element_size; } #endif - return neon_reg_offset(reg, 0) + ofs; + return neon_full_reg_offset(reg) + ofs; } static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop) @@ -XXX,XX +XXX,XX @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a) * We cannot write 16 bytes at once because the * destination is unaligned. */ - tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0), + tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(vd), 8, 8, tmp); - tcg_gen_gvec_mov(0, neon_reg_offset(vd + 1, 0), - neon_reg_offset(vd, 0), 8, 8); + tcg_gen_gvec_mov(0, neon_full_reg_offset(vd + 1), + neon_full_reg_offset(vd), 8, 8); } else { - tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0), + tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(vd), vec_size, vec_size, tmp); } tcg_gen_addi_i32(addr, addr, 1 << size); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a) static bool do_3same(DisasContext *s, arg_3same *a, GVecGen3Fn fn) { int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rn_ofs = neon_reg_offset(a->vn, 0); - int rm_ofs = neon_reg_offset(a->vm, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rn_ofs = neon_full_reg_offset(a->vn); + int rm_ofs = neon_full_reg_offset(a->vm); if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn) { /* Handle a 2-reg-shift insn which can be vectorized. */ int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rm_ofs = neon_reg_offset(a->vm, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rm_ofs = neon_full_reg_offset(a->vm); if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, { /* FP operations in 2-reg-and-shift group */ int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rm_ofs = neon_reg_offset(a->vm, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rm_ofs = neon_full_reg_offset(a->vm); TCGv_ptr fpst; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_1reg_imm(DisasContext *s, arg_1reg_imm *a, return true; } - reg_ofs = neon_reg_offset(a->vd, 0); + reg_ofs = neon_full_reg_offset(a->vd); vec_size = a->q ? 16 : 8; imm = asimd_imm_const(a->imm, a->cmode, a->op); @@ -XXX,XX +XXX,XX @@ static bool trans_VMULL_P_3d(DisasContext *s, arg_3diff *a) return true; } - tcg_gen_gvec_3_ool(neon_reg_offset(a->vd, 0), - neon_reg_offset(a->vn, 0), - neon_reg_offset(a->vm, 0), + tcg_gen_gvec_3_ool(neon_full_reg_offset(a->vd), + neon_full_reg_offset(a->vn), + neon_full_reg_offset(a->vm), 16, 16, 0, fn_gvec); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a, { /* Two registers and a scalar, using gvec */ int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rn_ofs = neon_reg_offset(a->vn, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rn_ofs = neon_full_reg_offset(a->vn); int rm_ofs; int idx; TCGv_ptr fpstatus; @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a, /* a->vm is M:Vm, which encodes both register and index */ idx = extract32(a->vm, a->size + 2, 2); a->vm = extract32(a->vm, 0, a->size + 2); - rm_ofs = neon_reg_offset(a->vm, 0); + rm_ofs = neon_full_reg_offset(a->vm); fpstatus = fpstatus_ptr(a->size == 1 ? FPST_STD_F16 : FPST_STD); tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpstatus, @@ -XXX,XX +XXX,XX @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a) return true; } - tcg_gen_gvec_dup_mem(a->size, neon_reg_offset(a->vd, 0), + tcg_gen_gvec_dup_mem(a->size, neon_full_reg_offset(a->vd), neon_element_offset(a->vm, a->index, a->size), a->q ? 16 : 8, a->q ? 16 : 8); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_F32_F16(DisasContext *s, arg_2misc *a) static bool do_2misc_vec(DisasContext *s, arg_2misc *a, GVecGen2Fn *fn) { int vec_size = a->q ? 16 : 8; - int rd_ofs = neon_reg_offset(a->vd, 0); - int rm_ofs = neon_reg_offset(a->vm, 0); + int rd_ofs = neon_full_reg_offset(a->vd); + int rm_ofs = neon_full_reg_offset(a->vm); if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VDUP(DisasContext *s, arg_VDUP *a) } tmp = load_reg(s, a->rt); - tcg_gen_gvec_dup_i32(size, neon_reg_offset(a->vn, 0), + tcg_gen_gvec_dup_i32(size, neon_full_reg_offset(a->vn), vec_size, vec_size, tmp); tcg_temp_free_i32(tmp); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This will shortly have users outside of translate-neon.c.inc. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 20 ++++++++++++++++++++ target/arm/translate-neon.c.inc | 19 ------------------- 2 files changed, 20 insertions(+), 19 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static long neon_full_reg_offset(unsigned reg) return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); } +/* + * Return the offset of a 2**SIZE piece of a NEON register, at index ELE, + * where 0 is the least significant end of the register. + */ +static long neon_element_offset(int reg, int element, MemOp size) +{ + int element_size = 1 << size; + int ofs = element * element_size; +#ifdef HOST_WORDS_BIGENDIAN + /* + * Calculate the offset assuming fully little-endian, + * then XOR to account for the order of the 8-byte units. + */ + if (element_size < 8) { + ofs ^= 8 - element_size; + } +#endif + return neon_full_reg_offset(reg) + ofs; +} + static inline long vfp_reg_offset(bool dp, unsigned reg) { if (dp) { diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static inline int neon_3same_fp_size(DisasContext *s, int x) #include "decode-neon-ls.c.inc" #include "decode-neon-shared.c.inc" -/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE, - * where 0 is the least significant end of the register. - */ -static inline long -neon_element_offset(int reg, int element, MemOp size) -{ - int element_size = 1 << size; - int ofs = element * element_size; -#ifdef HOST_WORDS_BIGENDIAN - /* Calculate the offset assuming fully little-endian, - * then XOR to account for the order of the 8-byte units. - */ - if (element_size < 8) { - ofs ^= 8 - element_size; - } -#endif - return neon_full_reg_offset(reg) + ofs; -} - static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop) { long offset = neon_element_offset(reg, ele, mop & MO_SIZE); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> These are the only users of neon_reg_offset, so remove that. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-4-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline long vfp_reg_offset(bool dp, unsigned reg) } } -/* Return the offset of a 32-bit piece of a NEON register. - zero is the least significant end of the register. */ -static inline long -neon_reg_offset (int reg, int n) -{ - int sreg; - sreg = reg * 2 + n; - return vfp_reg_offset(0, sreg); -} - static TCGv_i32 neon_load_reg(int reg, int pass) { TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_ld_i32(tmp, cpu_env, neon_reg_offset(reg, pass)); + tcg_gen_ld_i32(tmp, cpu_env, neon_element_offset(reg, pass, MO_32)); return tmp; } static void neon_store_reg(int reg, int pass, TCGv_i32 var) { - tcg_gen_st_i32(var, cpu_env, neon_reg_offset(reg, pass)); + tcg_gen_st_i32(var, cpu_env, neon_element_offset(reg, pass, MO_32)); tcg_temp_free_i32(var); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This seems a bit more readable than using offsetof CPU_DoubleU. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static long neon_element_offset(int reg, int element, MemOp size) return neon_full_reg_offset(reg) + ofs; } -static inline long vfp_reg_offset(bool dp, unsigned reg) +/* Return the offset of a VFP Dreg (dp = true) or VFP Sreg (dp = false). */ +static long vfp_reg_offset(bool dp, unsigned reg) { if (dp) { - return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); + return neon_element_offset(reg, 0, MO_64); } else { - long ofs = offsetof(CPUARMState, vfp.zregs[reg >> 2].d[(reg >> 1) & 1]); - if (reg & 1) { - ofs += offsetof(CPU_DoubleU, l.upper); - } else { - ofs += offsetof(CPU_DoubleU, l.lower); - } - return ofs; + return neon_element_offset(reg >> 1, reg & 1, MO_32); } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Model these off the aa64 read/write_vec_element functions. Use it within translate-neon.c.inc. The new functions do not allocate or free temps, so this rearranges the calling code a bit. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-6-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 26 ++++ target/arm/translate-neon.c.inc | 256 ++++++++++++++++++++------------ 2 files changed, 183 insertions(+), 99 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void neon_store_reg32(TCGv_i32 var, int reg) tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); } +static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp size) +{ + long off = neon_element_offset(reg, ele, size); + + switch (size) { + case MO_32: + tcg_gen_ld_i32(dest, cpu_env, off); + break; + default: + g_assert_not_reached(); + } +} + +static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp size) +{ + long off = neon_element_offset(reg, ele, size); + + switch (size) { + case MO_32: + tcg_gen_st_i32(src, cpu_env, off); + break; + default: + g_assert_not_reached(); + } +} + static TCGv_ptr vfp_reg_ptr(bool dp, int reg) { TCGv_ptr ret = tcg_temp_new_ptr(); diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_3same_pair(DisasContext *s, arg_3same *a, NeonGenTwoOpFn *fn) * early. Since Q is 0 there are always just two passes, so instead * of a complicated loop over each pass we just unroll. */ - tmp = neon_load_reg(a->vn, 0); - tmp2 = neon_load_reg(a->vn, 1); + tmp = tcg_temp_new_i32(); + tmp2 = tcg_temp_new_i32(); + tmp3 = tcg_temp_new_i32(); + + read_neon_element32(tmp, a->vn, 0, MO_32); + read_neon_element32(tmp2, a->vn, 1, MO_32); fn(tmp, tmp, tmp2); - tcg_temp_free_i32(tmp2); - tmp3 = neon_load_reg(a->vm, 0); - tmp2 = neon_load_reg(a->vm, 1); + read_neon_element32(tmp3, a->vm, 0, MO_32); + read_neon_element32(tmp2, a->vm, 1, MO_32); fn(tmp3, tmp3, tmp2); - tcg_temp_free_i32(tmp2); - neon_store_reg(a->vd, 0, tmp); - neon_store_reg(a->vd, 1, tmp3); + write_neon_element32(tmp, a->vd, 0, MO_32); + write_neon_element32(tmp3, a->vd, 1, MO_32); + + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(tmp2); + tcg_temp_free_i32(tmp3); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a, * 2-reg-and-shift operations, size < 3 case, where the * helper needs to be passed cpu_env. */ - TCGv_i32 constimm; + TCGv_i32 constimm, tmp; int pass; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a, * by immediate using the variable shift operations. */ constimm = tcg_const_i32(dup_const(a->size, a->shift)); + tmp = tcg_temp_new_i32(); for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vm, pass); + read_neon_element32(tmp, a->vm, pass, MO_32); fn(tmp, cpu_env, tmp, constimm); - neon_store_reg(a->vd, pass, tmp); + write_neon_element32(tmp, a->vd, pass, MO_32); } + tcg_temp_free_i32(tmp); tcg_temp_free_i32(constimm); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a, constimm = tcg_const_i64(-a->shift); rm1 = tcg_temp_new_i64(); rm2 = tcg_temp_new_i64(); + rd = tcg_temp_new_i32(); /* Load both inputs first to avoid potential overwrite if rm == rd */ neon_load_reg64(rm1, a->vm); neon_load_reg64(rm2, a->vm + 1); shiftfn(rm1, rm1, constimm); - rd = tcg_temp_new_i32(); narrowfn(rd, cpu_env, rm1); - neon_store_reg(a->vd, 0, rd); + write_neon_element32(rd, a->vd, 0, MO_32); shiftfn(rm2, rm2, constimm); - rd = tcg_temp_new_i32(); narrowfn(rd, cpu_env, rm2); - neon_store_reg(a->vd, 1, rd); + write_neon_element32(rd, a->vd, 1, MO_32); + tcg_temp_free_i32(rd); tcg_temp_free_i64(rm1); tcg_temp_free_i64(rm2); tcg_temp_free_i64(constimm); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a, constimm = tcg_const_i32(imm); /* Load all inputs first to avoid potential overwrite */ - rm1 = neon_load_reg(a->vm, 0); - rm2 = neon_load_reg(a->vm, 1); - rm3 = neon_load_reg(a->vm + 1, 0); - rm4 = neon_load_reg(a->vm + 1, 1); + rm1 = tcg_temp_new_i32(); + rm2 = tcg_temp_new_i32(); + rm3 = tcg_temp_new_i32(); + rm4 = tcg_temp_new_i32(); + read_neon_element32(rm1, a->vm, 0, MO_32); + read_neon_element32(rm2, a->vm, 1, MO_32); + read_neon_element32(rm3, a->vm, 2, MO_32); + read_neon_element32(rm4, a->vm, 3, MO_32); rtmp = tcg_temp_new_i64(); shiftfn(rm1, rm1, constimm); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a, tcg_temp_free_i32(rm2); narrowfn(rm1, cpu_env, rtmp); - neon_store_reg(a->vd, 0, rm1); + write_neon_element32(rm1, a->vd, 0, MO_32); + tcg_temp_free_i32(rm1); shiftfn(rm3, rm3, constimm); shiftfn(rm4, rm4, constimm); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a, narrowfn(rm3, cpu_env, rtmp); tcg_temp_free_i64(rtmp); - neon_store_reg(a->vd, 1, rm3); + write_neon_element32(rm3, a->vd, 1, MO_32); + tcg_temp_free_i32(rm3); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, widen_mask = dup_const(a->size + 1, widen_mask); } - rm0 = neon_load_reg(a->vm, 0); - rm1 = neon_load_reg(a->vm, 1); + rm0 = tcg_temp_new_i32(); + rm1 = tcg_temp_new_i32(); + read_neon_element32(rm0, a->vm, 0, MO_32); + read_neon_element32(rm1, a->vm, 1, MO_32); tmp = tcg_temp_new_i64(); widenfn(tmp, rm0); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, if (src1_wide) { neon_load_reg64(rn0_64, a->vn); } else { - TCGv_i32 tmp = neon_load_reg(a->vn, 0); + TCGv_i32 tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vn, 0, MO_32); widenfn(rn0_64, tmp); tcg_temp_free_i32(tmp); } - rm = neon_load_reg(a->vm, 0); + rm = tcg_temp_new_i32(); + read_neon_element32(rm, a->vm, 0, MO_32); widenfn(rm_64, rm); tcg_temp_free_i32(rm); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, if (src1_wide) { neon_load_reg64(rn1_64, a->vn + 1); } else { - TCGv_i32 tmp = neon_load_reg(a->vn, 1); + TCGv_i32 tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vn, 1, MO_32); widenfn(rn1_64, tmp); tcg_temp_free_i32(tmp); } - rm = neon_load_reg(a->vm, 1); + rm = tcg_temp_new_i32(); + read_neon_element32(rm, a->vm, 1, MO_32); neon_store_reg64(rn0_64, a->vd); @@ -XXX,XX +XXX,XX @@ static bool do_narrow_3d(DisasContext *s, arg_3diff *a, narrowfn(rd1, rn_64); - neon_store_reg(a->vd, 0, rd0); - neon_store_reg(a->vd, 1, rd1); + write_neon_element32(rd0, a->vd, 0, MO_32); + write_neon_element32(rd1, a->vd, 1, MO_32); + tcg_temp_free_i32(rd0); + tcg_temp_free_i32(rd1); tcg_temp_free_i64(rn_64); tcg_temp_free_i64(rm_64); @@ -XXX,XX +XXX,XX @@ static bool do_long_3d(DisasContext *s, arg_3diff *a, rd0 = tcg_temp_new_i64(); rd1 = tcg_temp_new_i64(); - rn = neon_load_reg(a->vn, 0); - rm = neon_load_reg(a->vm, 0); + rn = tcg_temp_new_i32(); + rm = tcg_temp_new_i32(); + read_neon_element32(rn, a->vn, 0, MO_32); + read_neon_element32(rm, a->vm, 0, MO_32); opfn(rd0, rn, rm); - tcg_temp_free_i32(rn); - tcg_temp_free_i32(rm); - rn = neon_load_reg(a->vn, 1); - rm = neon_load_reg(a->vm, 1); + read_neon_element32(rn, a->vn, 1, MO_32); + read_neon_element32(rm, a->vm, 1, MO_32); opfn(rd1, rn, rm); tcg_temp_free_i32(rn); tcg_temp_free_i32(rm); @@ -XXX,XX +XXX,XX @@ static void gen_neon_dup_high16(TCGv_i32 var) static inline TCGv_i32 neon_get_scalar(int size, int reg) { - TCGv_i32 tmp; - if (size == 1) { - tmp = neon_load_reg(reg & 7, reg >> 4); + TCGv_i32 tmp = tcg_temp_new_i32(); + if (size == MO_16) { + read_neon_element32(tmp, reg & 7, reg >> 4, MO_32); if (reg & 8) { gen_neon_dup_high16(tmp); } else { gen_neon_dup_low16(tmp); } } else { - tmp = neon_load_reg(reg & 15, reg >> 4); + read_neon_element32(tmp, reg & 15, reg >> 4, MO_32); } return tmp; } @@ -XXX,XX +XXX,XX @@ static bool do_2scalar(DisasContext *s, arg_2scalar *a, * perform an accumulation operation of that result into the * destination. */ - TCGv_i32 scalar; + TCGv_i32 scalar, tmp; int pass; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_2scalar(DisasContext *s, arg_2scalar *a, } scalar = neon_get_scalar(a->size, a->vm); + tmp = tcg_temp_new_i32(); for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vn, pass); + read_neon_element32(tmp, a->vn, pass, MO_32); opfn(tmp, tmp, scalar); if (accfn) { - TCGv_i32 rd = neon_load_reg(a->vd, pass); + TCGv_i32 rd = tcg_temp_new_i32(); + read_neon_element32(rd, a->vd, pass, MO_32); accfn(tmp, rd, tmp); tcg_temp_free_i32(rd); } - neon_store_reg(a->vd, pass, tmp); + write_neon_element32(tmp, a->vd, pass, MO_32); } + tcg_temp_free_i32(tmp); tcg_temp_free_i32(scalar); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_vqrdmlah_2sc(DisasContext *s, arg_2scalar *a, * performs a kind of fused op-then-accumulate using a helper * function that takes all of rd, rn and the scalar at once. */ - TCGv_i32 scalar; + TCGv_i32 scalar, rn, rd; int pass; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_vqrdmlah_2sc(DisasContext *s, arg_2scalar *a, } scalar = neon_get_scalar(a->size, a->vm); + rn = tcg_temp_new_i32(); + rd = tcg_temp_new_i32(); for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 rn = neon_load_reg(a->vn, pass); - TCGv_i32 rd = neon_load_reg(a->vd, pass); + read_neon_element32(rn, a->vn, pass, MO_32); + read_neon_element32(rd, a->vd, pass, MO_32); opfn(rd, cpu_env, rn, scalar, rd); - tcg_temp_free_i32(rn); - neon_store_reg(a->vd, pass, rd); + write_neon_element32(rd, a->vd, pass, MO_32); } + tcg_temp_free_i32(rn); + tcg_temp_free_i32(rd); tcg_temp_free_i32(scalar); return true; @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_long(DisasContext *s, arg_2scalar *a, scalar = neon_get_scalar(a->size, a->vm); /* Load all inputs before writing any outputs, in case of overlap */ - rn = neon_load_reg(a->vn, 0); + rn = tcg_temp_new_i32(); + read_neon_element32(rn, a->vn, 0, MO_32); rn0_64 = tcg_temp_new_i64(); opfn(rn0_64, rn, scalar); - tcg_temp_free_i32(rn); - rn = neon_load_reg(a->vn, 1); + read_neon_element32(rn, a->vn, 1, MO_32); rn1_64 = tcg_temp_new_i64(); opfn(rn1_64, rn, scalar); tcg_temp_free_i32(rn); @@ -XXX,XX +XXX,XX @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a) return false; } n <<= 3; + tmp = tcg_temp_new_i32(); if (a->op) { - tmp = neon_load_reg(a->vd, 0); + read_neon_element32(tmp, a->vd, 0, MO_32); } else { - tmp = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp, 0); } - tmp2 = neon_load_reg(a->vm, 0); + tmp2 = tcg_temp_new_i32(); + read_neon_element32(tmp2, a->vm, 0, MO_32); ptr1 = vfp_reg_ptr(true, a->vn); tmp4 = tcg_const_i32(n); gen_helper_neon_tbl(tmp2, tmp2, tmp, ptr1, tmp4); - tcg_temp_free_i32(tmp); + if (a->op) { - tmp = neon_load_reg(a->vd, 1); + read_neon_element32(tmp, a->vd, 1, MO_32); } else { - tmp = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp, 0); } - tmp3 = neon_load_reg(a->vm, 1); + tmp3 = tcg_temp_new_i32(); + read_neon_element32(tmp3, a->vm, 1, MO_32); gen_helper_neon_tbl(tmp3, tmp3, tmp, ptr1, tmp4); + tcg_temp_free_i32(tmp); tcg_temp_free_i32(tmp4); tcg_temp_free_ptr(ptr1); - neon_store_reg(a->vd, 0, tmp2); - neon_store_reg(a->vd, 1, tmp3); - tcg_temp_free_i32(tmp); + + write_neon_element32(tmp2, a->vd, 0, MO_32); + write_neon_element32(tmp3, a->vd, 1, MO_32); + tcg_temp_free_i32(tmp2); + tcg_temp_free_i32(tmp3); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a) static bool trans_VREV64(DisasContext *s, arg_VREV64 *a) { int pass, half; + TCGv_i32 tmp[2]; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VREV64(DisasContext *s, arg_VREV64 *a) return true; } - for (pass = 0; pass < (a->q ? 2 : 1); pass++) { - TCGv_i32 tmp[2]; + tmp[0] = tcg_temp_new_i32(); + tmp[1] = tcg_temp_new_i32(); + for (pass = 0; pass < (a->q ? 2 : 1); pass++) { for (half = 0; half < 2; half++) { - tmp[half] = neon_load_reg(a->vm, pass * 2 + half); + read_neon_element32(tmp[half], a->vm, pass * 2 + half, MO_32); switch (a->size) { case 0: tcg_gen_bswap32_i32(tmp[half], tmp[half]); @@ -XXX,XX +XXX,XX @@ static bool trans_VREV64(DisasContext *s, arg_VREV64 *a) g_assert_not_reached(); } } - neon_store_reg(a->vd, pass * 2, tmp[1]); - neon_store_reg(a->vd, pass * 2 + 1, tmp[0]); + write_neon_element32(tmp[1], a->vd, pass * 2, MO_32); + write_neon_element32(tmp[0], a->vd, pass * 2 + 1, MO_32); } + + tcg_temp_free_i32(tmp[0]); + tcg_temp_free_i32(tmp[1]); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a, rm0_64 = tcg_temp_new_i64(); rm1_64 = tcg_temp_new_i64(); rd_64 = tcg_temp_new_i64(); - tmp = neon_load_reg(a->vm, pass * 2); + + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, pass * 2, MO_32); widenfn(rm0_64, tmp); - tcg_temp_free_i32(tmp); - tmp = neon_load_reg(a->vm, pass * 2 + 1); + read_neon_element32(tmp, a->vm, pass * 2 + 1, MO_32); widenfn(rm1_64, tmp); tcg_temp_free_i32(tmp); + opfn(rd_64, rm0_64, rm1_64); tcg_temp_free_i64(rm0_64); tcg_temp_free_i64(rm1_64); @@ -XXX,XX +XXX,XX @@ static bool do_vmovn(DisasContext *s, arg_2misc *a, narrowfn(rd0, cpu_env, rm); neon_load_reg64(rm, a->vm + 1); narrowfn(rd1, cpu_env, rm); - neon_store_reg(a->vd, 0, rd0); - neon_store_reg(a->vd, 1, rd1); + write_neon_element32(rd0, a->vd, 0, MO_32); + write_neon_element32(rd1, a->vd, 1, MO_32); + tcg_temp_free_i32(rd0); + tcg_temp_free_i32(rd1); tcg_temp_free_i64(rm); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLL(DisasContext *s, arg_2misc *a) } rd = tcg_temp_new_i64(); + rm0 = tcg_temp_new_i32(); + rm1 = tcg_temp_new_i32(); - rm0 = neon_load_reg(a->vm, 0); - rm1 = neon_load_reg(a->vm, 1); + read_neon_element32(rm0, a->vm, 0, MO_32); + read_neon_element32(rm1, a->vm, 1, MO_32); widenfn(rd, rm0); tcg_gen_shli_i64(rd, rd, 8 << a->size); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_F16_F32(DisasContext *s, arg_2misc *a) fpst = fpstatus_ptr(FPST_STD); ahp = get_ahp_flag(); - tmp = neon_load_reg(a->vm, 0); + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, 0, MO_32); gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); - tmp2 = neon_load_reg(a->vm, 1); + tmp2 = tcg_temp_new_i32(); + read_neon_element32(tmp2, a->vm, 1, MO_32); gen_helper_vfp_fcvt_f32_to_f16(tmp2, tmp2, fpst, ahp); tcg_gen_shli_i32(tmp2, tmp2, 16); tcg_gen_or_i32(tmp2, tmp2, tmp); - tcg_temp_free_i32(tmp); - tmp = neon_load_reg(a->vm, 2); + read_neon_element32(tmp, a->vm, 2, MO_32); gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); - tmp3 = neon_load_reg(a->vm, 3); - neon_store_reg(a->vd, 0, tmp2); + tmp3 = tcg_temp_new_i32(); + read_neon_element32(tmp3, a->vm, 3, MO_32); + write_neon_element32(tmp2, a->vd, 0, MO_32); + tcg_temp_free_i32(tmp2); gen_helper_vfp_fcvt_f32_to_f16(tmp3, tmp3, fpst, ahp); tcg_gen_shli_i32(tmp3, tmp3, 16); tcg_gen_or_i32(tmp3, tmp3, tmp); - neon_store_reg(a->vd, 1, tmp3); + write_neon_element32(tmp3, a->vd, 1, MO_32); + tcg_temp_free_i32(tmp3); tcg_temp_free_i32(tmp); tcg_temp_free_i32(ahp); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_F32_F16(DisasContext *s, arg_2misc *a) fpst = fpstatus_ptr(FPST_STD); ahp = get_ahp_flag(); tmp3 = tcg_temp_new_i32(); - tmp = neon_load_reg(a->vm, 0); - tmp2 = neon_load_reg(a->vm, 1); + tmp2 = tcg_temp_new_i32(); + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, 0, MO_32); + read_neon_element32(tmp2, a->vm, 1, MO_32); tcg_gen_ext16u_i32(tmp3, tmp); gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp); - neon_store_reg(a->vd, 0, tmp3); + write_neon_element32(tmp3, a->vd, 0, MO_32); tcg_gen_shri_i32(tmp, tmp, 16); gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp); - neon_store_reg(a->vd, 1, tmp); - tmp3 = tcg_temp_new_i32(); + write_neon_element32(tmp, a->vd, 1, MO_32); + tcg_temp_free_i32(tmp); tcg_gen_ext16u_i32(tmp3, tmp2); gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp); - neon_store_reg(a->vd, 2, tmp3); + write_neon_element32(tmp3, a->vd, 2, MO_32); + tcg_temp_free_i32(tmp3); tcg_gen_shri_i32(tmp2, tmp2, 16); gen_helper_vfp_fcvt_f16_to_f32(tmp2, tmp2, fpst, ahp); - neon_store_reg(a->vd, 3, tmp2); + write_neon_element32(tmp2, a->vd, 3, MO_32); + tcg_temp_free_i32(tmp2); tcg_temp_free_i32(ahp); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ DO_2M_CRYPTO(SHA256SU0, aa32_sha2, 2) static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn) { + TCGv_i32 tmp; int pass; /* Handle a 2-reg-misc operation by iterating 32 bits at a time */ @@ -XXX,XX +XXX,XX @@ static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn) return true; } + tmp = tcg_temp_new_i32(); for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vm, pass); + read_neon_element32(tmp, a->vm, pass, MO_32); fn(tmp, tmp); - neon_store_reg(a->vd, pass, tmp); + write_neon_element32(tmp, a->vd, pass, MO_32); } + tcg_temp_free_i32(tmp); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VTRN(DisasContext *s, arg_2misc *a) return true; } - if (a->size == 2) { + tmp = tcg_temp_new_i32(); + tmp2 = tcg_temp_new_i32(); + if (a->size == MO_32) { for (pass = 0; pass < (a->q ? 4 : 2); pass += 2) { - tmp = neon_load_reg(a->vm, pass); - tmp2 = neon_load_reg(a->vd, pass + 1); - neon_store_reg(a->vm, pass, tmp2); - neon_store_reg(a->vd, pass + 1, tmp); + read_neon_element32(tmp, a->vm, pass, MO_32); + read_neon_element32(tmp2, a->vd, pass + 1, MO_32); + write_neon_element32(tmp2, a->vm, pass, MO_32); + write_neon_element32(tmp, a->vd, pass + 1, MO_32); } } else { for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - tmp = neon_load_reg(a->vm, pass); - tmp2 = neon_load_reg(a->vd, pass); - if (a->size == 0) { + read_neon_element32(tmp, a->vm, pass, MO_32); + read_neon_element32(tmp2, a->vd, pass, MO_32); + if (a->size == MO_8) { gen_neon_trn_u8(tmp, tmp2); } else { gen_neon_trn_u16(tmp, tmp2); } - neon_store_reg(a->vm, pass, tmp2); - neon_store_reg(a->vd, pass, tmp); + write_neon_element32(tmp2, a->vm, pass, MO_32); + write_neon_element32(tmp, a->vd, pass, MO_32); } } + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(tmp2); return true; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We can then use this to improve VMOV (scalar to gp) and VMOV (gp to scalar) so that we simply perform the memory operation that we wanted, rather than inserting or extracting from a 32-bit quantity. These were the last uses of neon_load/store_reg, so remove them. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 50 +++++++++++++----------- target/arm/translate-vfp.c.inc | 71 +++++----------------------------- 2 files changed, 37 insertions(+), 84 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static long neon_full_reg_offset(unsigned reg) * Return the offset of a 2**SIZE piece of a NEON register, at index ELE, * where 0 is the least significant end of the register. */ -static long neon_element_offset(int reg, int element, MemOp size) +static long neon_element_offset(int reg, int element, MemOp memop) { - int element_size = 1 << size; + int element_size = 1 << (memop & MO_SIZE); int ofs = element * element_size; #ifdef HOST_WORDS_BIGENDIAN /* @@ -XXX,XX +XXX,XX @@ static long vfp_reg_offset(bool dp, unsigned reg) } } -static TCGv_i32 neon_load_reg(int reg, int pass) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_ld_i32(tmp, cpu_env, neon_element_offset(reg, pass, MO_32)); - return tmp; -} - -static void neon_store_reg(int reg, int pass, TCGv_i32 var) -{ - tcg_gen_st_i32(var, cpu_env, neon_element_offset(reg, pass, MO_32)); - tcg_temp_free_i32(var); -} - static inline void neon_load_reg64(TCGv_i64 var, int reg) { tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg)); @@ -XXX,XX +XXX,XX @@ static inline void neon_store_reg32(TCGv_i32 var, int reg) tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); } -static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp size) +static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) { - long off = neon_element_offset(reg, ele, size); + long off = neon_element_offset(reg, ele, memop); - switch (size) { - case MO_32: + switch (memop) { + case MO_SB: + tcg_gen_ld8s_i32(dest, cpu_env, off); + break; + case MO_UB: + tcg_gen_ld8u_i32(dest, cpu_env, off); + break; + case MO_SW: + tcg_gen_ld16s_i32(dest, cpu_env, off); + break; + case MO_UW: + tcg_gen_ld16u_i32(dest, cpu_env, off); + break; + case MO_UL: + case MO_SL: tcg_gen_ld_i32(dest, cpu_env, off); break; default: @@ -XXX,XX +XXX,XX @@ static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp size) } } -static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp size) +static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) { - long off = neon_element_offset(reg, ele, size); + long off = neon_element_offset(reg, ele, memop); - switch (size) { + switch (memop) { + case MO_8: + tcg_gen_st8_i32(src, cpu_env, off); + break; + case MO_16: + tcg_gen_st16_i32(src, cpu_env, off); + break; case MO_32: tcg_gen_st_i32(src, cpu_env, off); break; diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a) { /* VMOV scalar to general purpose register */ TCGv_i32 tmp; - int pass; - uint32_t offset; - /* SIZE == 2 is a VFP instruction; otherwise NEON. */ - if (a->size == 2 + /* SIZE == MO_32 is a VFP instruction; otherwise NEON. */ + if (a->size == MO_32 ? !dc_isar_feature(aa32_fpsp_v2, s) : !arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a) return false; } - offset = a->index << a->size; - pass = extract32(offset, 2, 1); - offset = extract32(offset, 0, 2) * 8; - if (!vfp_access_check(s)) { return true; } - tmp = neon_load_reg(a->vn, pass); - switch (a->size) { - case 0: - if (offset) { - tcg_gen_shri_i32(tmp, tmp, offset); - } - if (a->u) { - gen_uxtb(tmp); - } else { - gen_sxtb(tmp); - } - break; - case 1: - if (a->u) { - if (offset) { - tcg_gen_shri_i32(tmp, tmp, 16); - } else { - gen_uxth(tmp); - } - } else { - if (offset) { - tcg_gen_sari_i32(tmp, tmp, 16); - } else { - gen_sxth(tmp); - } - } - break; - case 2: - break; - } + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vn, a->index, a->size | (a->u ? 0 : MO_SIGN)); store_reg(s, a->rt, tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a) static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a) { /* VMOV general purpose register to scalar */ - TCGv_i32 tmp, tmp2; - int pass; - uint32_t offset; + TCGv_i32 tmp; - /* SIZE == 2 is a VFP instruction; otherwise NEON. */ - if (a->size == 2 + /* SIZE == MO_32 is a VFP instruction; otherwise NEON. */ + if (a->size == MO_32 ? !dc_isar_feature(aa32_fpsp_v2, s) : !arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a) return false; } - offset = a->index << a->size; - pass = extract32(offset, 2, 1); - offset = extract32(offset, 0, 2) * 8; - if (!vfp_access_check(s)) { return true; } tmp = load_reg(s, a->rt); - switch (a->size) { - case 0: - tmp2 = neon_load_reg(a->vn, pass); - tcg_gen_deposit_i32(tmp, tmp2, tmp, offset, 8); - tcg_temp_free_i32(tmp2); - break; - case 1: - tmp2 = neon_load_reg(a->vn, pass); - tcg_gen_deposit_i32(tmp, tmp2, tmp, offset, 16); - tcg_temp_free_i32(tmp2); - break; - case 2: - break; - } - neon_store_reg(a->vn, pass, tmp); + write_neon_element32(tmp, a->vn, a->index, a->size); + tcg_temp_free_i32(tmp); return true; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The only uses of this function are for loading VFP single-precision values, and nothing to do with NEON. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-8-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 4 +- target/arm/translate-vfp.c.inc | 184 ++++++++++++++++----------------- 2 files changed, 94 insertions(+), 94 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void neon_store_reg64(TCGv_i64 var, int reg) tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(1, reg)); } -static inline void neon_load_reg32(TCGv_i32 var, int reg) +static inline void vfp_load_reg32(TCGv_i32 var, int reg) { tcg_gen_ld_i32(var, cpu_env, vfp_reg_offset(false, reg)); } -static inline void neon_store_reg32(TCGv_i32 var, int reg) +static inline void vfp_store_reg32(TCGv_i32 var, int reg) { tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); } diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) frn = tcg_temp_new_i32(); frm = tcg_temp_new_i32(); dest = tcg_temp_new_i32(); - neon_load_reg32(frn, rn); - neon_load_reg32(frm, rm); + vfp_load_reg32(frn, rn); + vfp_load_reg32(frm, rm); switch (a->cc) { case 0: /* eq: Z */ tcg_gen_movcond_i32(TCG_COND_EQ, dest, cpu_ZF, zero, @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) if (sz == 1) { tcg_gen_andi_i32(dest, dest, 0xffff); } - neon_store_reg32(dest, rd); + vfp_store_reg32(dest, rd); tcg_temp_free_i32(frn); tcg_temp_free_i32(frm); tcg_temp_free_i32(dest); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) TCGv_i32 tcg_res; tcg_op = tcg_temp_new_i32(); tcg_res = tcg_temp_new_i32(); - neon_load_reg32(tcg_op, rm); + vfp_load_reg32(tcg_op, rm); if (sz == 1) { gen_helper_rinth(tcg_res, tcg_op, fpst); } else { gen_helper_rints(tcg_res, tcg_op, fpst); } - neon_store_reg32(tcg_res, rd); + vfp_store_reg32(tcg_res, rd); tcg_temp_free_i32(tcg_op); tcg_temp_free_i32(tcg_res); } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) gen_helper_vfp_tould(tcg_res, tcg_double, tcg_shift, fpst); } tcg_gen_extrl_i64_i32(tcg_tmp, tcg_res); - neon_store_reg32(tcg_tmp, rd); + vfp_store_reg32(tcg_tmp, rd); tcg_temp_free_i32(tcg_tmp); tcg_temp_free_i64(tcg_res); tcg_temp_free_i64(tcg_double); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) TCGv_i32 tcg_single, tcg_res; tcg_single = tcg_temp_new_i32(); tcg_res = tcg_temp_new_i32(); - neon_load_reg32(tcg_single, rm); + vfp_load_reg32(tcg_single, rm); if (sz == 1) { if (is_signed) { gen_helper_vfp_toslh(tcg_res, tcg_single, tcg_shift, fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) gen_helper_vfp_touls(tcg_res, tcg_single, tcg_shift, fpst); } } - neon_store_reg32(tcg_res, rd); + vfp_store_reg32(tcg_res, rd); tcg_temp_free_i32(tcg_res); tcg_temp_free_i32(tcg_single); } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_half(DisasContext *s, arg_VMOV_single *a) if (a->l) { /* VFP to general purpose register */ tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vn); + vfp_load_reg32(tmp, a->vn); tcg_gen_andi_i32(tmp, tmp, 0xffff); store_reg(s, a->rt, tmp); } else { /* general purpose register to VFP */ tmp = load_reg(s, a->rt); tcg_gen_andi_i32(tmp, tmp, 0xffff); - neon_store_reg32(tmp, a->vn); + vfp_store_reg32(tmp, a->vn); tcg_temp_free_i32(tmp); } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a) if (a->l) { /* VFP to general purpose register */ tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vn); + vfp_load_reg32(tmp, a->vn); if (a->rt == 15) { /* Set the 4 flag bits in the CPSR. */ gen_set_nzcv(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a) } else { /* general purpose register to VFP */ tmp = load_reg(s, a->rt); - neon_store_reg32(tmp, a->vn); + vfp_store_reg32(tmp, a->vn); tcg_temp_free_i32(tmp); } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_64_sp(DisasContext *s, arg_VMOV_64_sp *a) if (a->op) { /* fpreg to gpreg */ tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); store_reg(s, a->rt, tmp); tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm + 1); + vfp_load_reg32(tmp, a->vm + 1); store_reg(s, a->rt2, tmp); } else { /* gpreg to fpreg */ tmp = load_reg(s, a->rt); - neon_store_reg32(tmp, a->vm); + vfp_store_reg32(tmp, a->vm); tcg_temp_free_i32(tmp); tmp = load_reg(s, a->rt2); - neon_store_reg32(tmp, a->vm + 1); + vfp_store_reg32(tmp, a->vm + 1); tcg_temp_free_i32(tmp); } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_dp *a) if (a->op) { /* fpreg to gpreg */ tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm * 2); + vfp_load_reg32(tmp, a->vm * 2); store_reg(s, a->rt, tmp); tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm * 2 + 1); + vfp_load_reg32(tmp, a->vm * 2 + 1); store_reg(s, a->rt2, tmp); } else { /* gpreg to fpreg */ tmp = load_reg(s, a->rt); - neon_store_reg32(tmp, a->vm * 2); + vfp_store_reg32(tmp, a->vm * 2); tcg_temp_free_i32(tmp); tmp = load_reg(s, a->rt2); - neon_store_reg32(tmp, a->vm * 2 + 1); + vfp_store_reg32(tmp, a->vm * 2 + 1); tcg_temp_free_i32(tmp); } @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_hp(DisasContext *s, arg_VLDR_VSTR_sp *a) tmp = tcg_temp_new_i32(); if (a->l) { gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); } else { - neon_load_reg32(tmp, a->vd); + vfp_load_reg32(tmp, a->vd); gen_aa32_st16(s, tmp, addr, get_mem_index(s)); } tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a) tmp = tcg_temp_new_i32(); if (a->l) { gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); } else { - neon_load_reg32(tmp, a->vd); + vfp_load_reg32(tmp, a->vd); gen_aa32_st32(s, tmp, addr, get_mem_index(s)); } tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_sp(DisasContext *s, arg_VLDM_VSTM_sp *a) if (a->l) { /* load */ gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - neon_store_reg32(tmp, a->vd + i); + vfp_store_reg32(tmp, a->vd + i); } else { /* store */ - neon_load_reg32(tmp, a->vd + i); + vfp_load_reg32(tmp, a->vd + i); gen_aa32_st32(s, tmp, addr, get_mem_index(s)); } tcg_gen_addi_i32(addr, addr, offset); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_sp(DisasContext *s, VFPGen3OpSPFn *fn, fd = tcg_temp_new_i32(); fpst = fpstatus_ptr(FPST_FPCR); - neon_load_reg32(f0, vn); - neon_load_reg32(f1, vm); + vfp_load_reg32(f0, vn); + vfp_load_reg32(f1, vm); for (;;) { if (reads_vd) { - neon_load_reg32(fd, vd); + vfp_load_reg32(fd, vd); } fn(fd, f0, f1, fpst); - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_sp(DisasContext *s, VFPGen3OpSPFn *fn, veclen--; vd = vfp_advance_sreg(vd, delta_d); vn = vfp_advance_sreg(vn, delta_d); - neon_load_reg32(f0, vn); + vfp_load_reg32(f0, vn); if (delta_m) { vm = vfp_advance_sreg(vm, delta_m); - neon_load_reg32(f1, vm); + vfp_load_reg32(f1, vm); } } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_hp(DisasContext *s, VFPGen3OpSPFn *fn, fd = tcg_temp_new_i32(); fpst = fpstatus_ptr(FPST_FPCR_F16); - neon_load_reg32(f0, vn); - neon_load_reg32(f1, vm); + vfp_load_reg32(f0, vn); + vfp_load_reg32(f1, vm); if (reads_vd) { - neon_load_reg32(fd, vd); + vfp_load_reg32(fd, vd); } fn(fd, f0, f1, fpst); - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); tcg_temp_free_i32(f0); tcg_temp_free_i32(f1); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) f0 = tcg_temp_new_i32(); fd = tcg_temp_new_i32(); - neon_load_reg32(f0, vm); + vfp_load_reg32(f0, vm); for (;;) { fn(fd, f0); - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) /* single source one-many */ while (veclen--) { vd = vfp_advance_sreg(vd, delta_d); - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); } break; } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) veclen--; vd = vfp_advance_sreg(vd, delta_d); vm = vfp_advance_sreg(vm, delta_m); - neon_load_reg32(f0, vm); + vfp_load_reg32(f0, vm); } tcg_temp_free_i32(f0); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_hp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) } f0 = tcg_temp_new_i32(); - neon_load_reg32(f0, vm); + vfp_load_reg32(f0, vm); fn(f0, f0); - neon_store_reg32(f0, vd); + vfp_store_reg32(f0, vd); tcg_temp_free_i32(f0); return true; @@ -XXX,XX +XXX,XX @@ static bool do_vfm_hp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i32(); - neon_load_reg32(vn, a->vn); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vn, a->vn); + vfp_load_reg32(vm, a->vm); if (neg_n) { /* VFNMS, VFMS */ gen_helper_vfp_negh(vn, vn); } - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); if (neg_d) { /* VFNMA, VFNMS */ gen_helper_vfp_negh(vd, vd); } fpst = fpstatus_ptr(FPST_FPCR_F16); gen_helper_vfp_muladdh(vd, vn, vm, vd, fpst); - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(vn); @@ -XXX,XX +XXX,XX @@ static bool do_vfm_sp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i32(); - neon_load_reg32(vn, a->vn); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vn, a->vn); + vfp_load_reg32(vm, a->vm); if (neg_n) { /* VFNMS, VFMS */ gen_helper_vfp_negs(vn, vn); } - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); if (neg_d) { /* VFNMA, VFNMS */ gen_helper_vfp_negs(vd, vd); } fpst = fpstatus_ptr(FPST_FPCR); gen_helper_vfp_muladds(vd, vn, vm, vd, fpst); - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(vn); @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_hp(DisasContext *s, arg_VMOV_imm_sp *a) } fd = tcg_const_i32(vfp_expand_imm(MO_16, a->imm)); - neon_store_reg32(fd, a->vd); + vfp_store_reg32(fd, a->vd); tcg_temp_free_i32(fd); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a) fd = tcg_const_i32(vfp_expand_imm(MO_32, a->imm)); for (;;) { - neon_store_reg32(fd, vd); + vfp_store_reg32(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_hp(DisasContext *s, arg_VCMP_sp *a) vd = tcg_temp_new_i32(); vm = tcg_temp_new_i32(); - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); if (a->z) { tcg_gen_movi_i32(vm, 0); } else { - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); } if (a->e) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_sp(DisasContext *s, arg_VCMP_sp *a) vd = tcg_temp_new_i32(); vm = tcg_temp_new_i32(); - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); if (a->z) { tcg_gen_movi_i32(vm, 0); } else { - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); } if (a->e) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f32_f16(DisasContext *s, arg_VCVT_f32_f16 *a) /* The T bit tells us if we want the low or high 16 bits of Vm */ tcg_gen_ld16u_i32(tmp, cpu_env, vfp_f16_offset(a->vm, a->t)); gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp_mode); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_i32(ahp_mode); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f32(DisasContext *s, arg_VCVT_f16_f32 *a) ahp_mode = get_ahp_flag(); tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp_mode); tcg_gen_st16_i32(tmp, cpu_env, vfp_f16_offset(a->vd, a->t)); tcg_temp_free_i32(ahp_mode); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_hp(DisasContext *s, arg_VRINTR_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); gen_helper_rinth(tmp, tmp, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_sp(DisasContext *s, arg_VRINTR_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); gen_helper_rints(tmp, tmp, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_hp(DisasContext *s, arg_VRINTZ_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); tcg_rmode = tcg_const_i32(float_round_to_zero); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); gen_helper_rinth(tmp, tmp, fpst); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tcg_rmode); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_sp(DisasContext *s, arg_VRINTZ_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); tcg_rmode = tcg_const_i32(float_round_to_zero); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); gen_helper_rints(tmp, tmp, fpst); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tcg_rmode); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_hp(DisasContext *s, arg_VRINTX_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); gen_helper_rinth_exact(tmp, tmp, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_sp(DisasContext *s, arg_VRINTX_sp *a) } tmp = tcg_temp_new_i32(); - neon_load_reg32(tmp, a->vm); + vfp_load_reg32(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); gen_helper_rints_exact(tmp, tmp, fpst); - neon_store_reg32(tmp, a->vd); + vfp_store_reg32(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp(DisasContext *s, arg_VCVT_sp *a) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i64(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); gen_helper_vfp_fcvtds(vd, vm, cpu_env); neon_store_reg64(vd, a->vd); tcg_temp_free_i32(vm); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) vm = tcg_temp_new_i64(); neon_load_reg64(vm, a->vm); gen_helper_vfp_fcvtsd(vd, vm, cpu_env); - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); tcg_temp_free_i64(vm); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_hp(DisasContext *s, arg_VCVT_int_sp *a) } vm = tcg_temp_new_i32(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); fpst = fpstatus_ptr(FPST_FPCR_F16); if (a->s) { /* i32 -> f16 */ @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_hp(DisasContext *s, arg_VCVT_int_sp *a) /* u32 -> f16 */ gen_helper_vfp_uitoh(vm, vm, fpst); } - neon_store_reg32(vm, a->vd); + vfp_store_reg32(vm, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_ptr(fpst); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_sp(DisasContext *s, arg_VCVT_int_sp *a) } vm = tcg_temp_new_i32(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); fpst = fpstatus_ptr(FPST_FPCR); if (a->s) { /* i32 -> f32 */ @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_sp(DisasContext *s, arg_VCVT_int_sp *a) /* u32 -> f32 */ gen_helper_vfp_uitos(vm, vm, fpst); } - neon_store_reg32(vm, a->vd); + vfp_store_reg32(vm, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_ptr(fpst); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_dp(DisasContext *s, arg_VCVT_int_dp *a) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i64(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); fpst = fpstatus_ptr(FPST_FPCR); if (a->s) { /* i32 -> f64 */ @@ -XXX,XX +XXX,XX @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a) vd = tcg_temp_new_i32(); neon_load_reg64(vm, a->vm); gen_helper_vjcvt(vd, vm, cpu_env); - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i64(vm); tcg_temp_free_i32(vd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_hp(DisasContext *s, arg_VCVT_fix_sp *a) frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm); vd = tcg_temp_new_i32(); - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); fpst = fpstatus_ptr(FPST_FPCR_F16); shift = tcg_const_i32(frac_bits); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_hp(DisasContext *s, arg_VCVT_fix_sp *a) g_assert_not_reached(); } - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); tcg_temp_free_i32(shift); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a) frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm); vd = tcg_temp_new_i32(); - neon_load_reg32(vd, a->vd); + vfp_load_reg32(vd, a->vd); fpst = fpstatus_ptr(FPST_FPCR); shift = tcg_const_i32(frac_bits); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a) g_assert_not_reached(); } - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); tcg_temp_free_i32(shift); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_hp_int(DisasContext *s, arg_VCVT_sp_int *a) fpst = fpstatus_ptr(FPST_FPCR_F16); vm = tcg_temp_new_i32(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); if (a->s) { if (a->rz) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_hp_int(DisasContext *s, arg_VCVT_sp_int *a) gen_helper_vfp_touih(vm, vm, fpst); } } - neon_store_reg32(vm, a->vd); + vfp_store_reg32(vm, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_ptr(fpst); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp_int(DisasContext *s, arg_VCVT_sp_int *a) fpst = fpstatus_ptr(FPST_FPCR); vm = tcg_temp_new_i32(); - neon_load_reg32(vm, a->vm); + vfp_load_reg32(vm, a->vm); if (a->s) { if (a->rz) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp_int(DisasContext *s, arg_VCVT_sp_int *a) gen_helper_vfp_touis(vm, vm, fpst); } } - neon_store_reg32(vm, a->vd); + vfp_store_reg32(vm, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_ptr(fpst); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) gen_helper_vfp_touid(vd, vm, fpst); } } - neon_store_reg32(vd, a->vd); + vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); tcg_temp_free_i64(vm); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VINS(DisasContext *s, arg_VINS *a) /* Insert low half of Vm into high half of Vd */ rm = tcg_temp_new_i32(); rd = tcg_temp_new_i32(); - neon_load_reg32(rm, a->vm); - neon_load_reg32(rd, a->vd); + vfp_load_reg32(rm, a->vm); + vfp_load_reg32(rd, a->vd); tcg_gen_deposit_i32(rd, rd, rm, 16, 16); - neon_store_reg32(rd, a->vd); + vfp_store_reg32(rd, a->vd); tcg_temp_free_i32(rm); tcg_temp_free_i32(rd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOVX(DisasContext *s, arg_VINS *a) /* Set Vd to high half of Vm */ rm = tcg_temp_new_i32(); - neon_load_reg32(rm, a->vm); + vfp_load_reg32(rm, a->vm); tcg_gen_shri_i32(rm, rm, 16); - neon_store_reg32(rm, a->vd); + vfp_store_reg32(rm, a->vd); tcg_temp_free_i32(rm); return true; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Replace all uses of neon_load/store_reg64 within translate-neon.c.inc. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-9-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 26 +++++++++ target/arm/translate-neon.c.inc | 94 ++++++++++++++++----------------- 2 files changed, 73 insertions(+), 47 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) } } +static void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) +{ + long off = neon_element_offset(reg, ele, memop); + + switch (memop) { + case MO_Q: + tcg_gen_ld_i64(dest, cpu_env, off); + break; + default: + g_assert_not_reached(); + } +} + static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) { long off = neon_element_offset(reg, ele, memop); @@ -XXX,XX +XXX,XX @@ static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) } } +static void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) +{ + long off = neon_element_offset(reg, ele, memop); + + switch (memop) { + case MO_64: + tcg_gen_st_i64(src, cpu_env, off); + break; + default: + g_assert_not_reached(); + } +} + static TCGv_ptr vfp_reg_ptr(bool dp, int reg) { TCGv_ptr ret = tcg_temp_new_ptr(); diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a, for (pass = 0; pass < a->q + 1; pass++) { TCGv_i64 tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vm + pass); + read_neon_element64(tmp, a->vm, pass, MO_64); fn(tmp, cpu_env, tmp, constimm); - neon_store_reg64(tmp, a->vd + pass); + write_neon_element64(tmp, a->vd, pass, MO_64); tcg_temp_free_i64(tmp); } tcg_temp_free_i64(constimm); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a, rd = tcg_temp_new_i32(); /* Load both inputs first to avoid potential overwrite if rm == rd */ - neon_load_reg64(rm1, a->vm); - neon_load_reg64(rm2, a->vm + 1); + read_neon_element64(rm1, a->vm, 0, MO_64); + read_neon_element64(rm2, a->vm, 1, MO_64); shiftfn(rm1, rm1, constimm); narrowfn(rd, cpu_env, rm1); @@ -XXX,XX +XXX,XX @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, tcg_gen_shli_i64(tmp, tmp, a->shift); tcg_gen_andi_i64(tmp, tmp, ~widen_mask); } - neon_store_reg64(tmp, a->vd); + write_neon_element64(tmp, a->vd, 0, MO_64); widenfn(tmp, rm1); tcg_temp_free_i32(rm1); @@ -XXX,XX +XXX,XX @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, tcg_gen_shli_i64(tmp, tmp, a->shift); tcg_gen_andi_i64(tmp, tmp, ~widen_mask); } - neon_store_reg64(tmp, a->vd + 1); + write_neon_element64(tmp, a->vd, 1, MO_64); tcg_temp_free_i64(tmp); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, rm_64 = tcg_temp_new_i64(); if (src1_wide) { - neon_load_reg64(rn0_64, a->vn); + read_neon_element64(rn0_64, a->vn, 0, MO_64); } else { TCGv_i32 tmp = tcg_temp_new_i32(); read_neon_element32(tmp, a->vn, 0, MO_32); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, * avoid incorrect results if a narrow input overlaps with the result. */ if (src1_wide) { - neon_load_reg64(rn1_64, a->vn + 1); + read_neon_element64(rn1_64, a->vn, 1, MO_64); } else { TCGv_i32 tmp = tcg_temp_new_i32(); read_neon_element32(tmp, a->vn, 1, MO_32); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, rm = tcg_temp_new_i32(); read_neon_element32(rm, a->vm, 1, MO_32); - neon_store_reg64(rn0_64, a->vd); + write_neon_element64(rn0_64, a->vd, 0, MO_64); widenfn(rm_64, rm); tcg_temp_free_i32(rm); opfn(rn1_64, rn1_64, rm_64); - neon_store_reg64(rn1_64, a->vd + 1); + write_neon_element64(rn1_64, a->vd, 1, MO_64); tcg_temp_free_i64(rn0_64); tcg_temp_free_i64(rn1_64); @@ -XXX,XX +XXX,XX @@ static bool do_narrow_3d(DisasContext *s, arg_3diff *a, rd0 = tcg_temp_new_i32(); rd1 = tcg_temp_new_i32(); - neon_load_reg64(rn_64, a->vn); - neon_load_reg64(rm_64, a->vm); + read_neon_element64(rn_64, a->vn, 0, MO_64); + read_neon_element64(rm_64, a->vm, 0, MO_64); opfn(rn_64, rn_64, rm_64); narrowfn(rd0, rn_64); - neon_load_reg64(rn_64, a->vn + 1); - neon_load_reg64(rm_64, a->vm + 1); + read_neon_element64(rn_64, a->vn, 1, MO_64); + read_neon_element64(rm_64, a->vm, 1, MO_64); opfn(rn_64, rn_64, rm_64); @@ -XXX,XX +XXX,XX @@ static bool do_long_3d(DisasContext *s, arg_3diff *a, /* Don't store results until after all loads: they might overlap */ if (accfn) { tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vd); + read_neon_element64(tmp, a->vd, 0, MO_64); accfn(tmp, tmp, rd0); - neon_store_reg64(tmp, a->vd); - neon_load_reg64(tmp, a->vd + 1); + write_neon_element64(tmp, a->vd, 0, MO_64); + read_neon_element64(tmp, a->vd, 1, MO_64); accfn(tmp, tmp, rd1); - neon_store_reg64(tmp, a->vd + 1); + write_neon_element64(tmp, a->vd, 1, MO_64); tcg_temp_free_i64(tmp); } else { - neon_store_reg64(rd0, a->vd); - neon_store_reg64(rd1, a->vd + 1); + write_neon_element64(rd0, a->vd, 0, MO_64); + write_neon_element64(rd1, a->vd, 1, MO_64); } tcg_temp_free_i64(rd0); @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_long(DisasContext *s, arg_2scalar *a, if (accfn) { TCGv_i64 t64 = tcg_temp_new_i64(); - neon_load_reg64(t64, a->vd); + read_neon_element64(t64, a->vd, 0, MO_64); accfn(t64, t64, rn0_64); - neon_store_reg64(t64, a->vd); - neon_load_reg64(t64, a->vd + 1); + write_neon_element64(t64, a->vd, 0, MO_64); + read_neon_element64(t64, a->vd, 1, MO_64); accfn(t64, t64, rn1_64); - neon_store_reg64(t64, a->vd + 1); + write_neon_element64(t64, a->vd, 1, MO_64); tcg_temp_free_i64(t64); } else { - neon_store_reg64(rn0_64, a->vd); - neon_store_reg64(rn1_64, a->vd + 1); + write_neon_element64(rn0_64, a->vd, 0, MO_64); + write_neon_element64(rn1_64, a->vd, 1, MO_64); } tcg_temp_free_i64(rn0_64); tcg_temp_free_i64(rn1_64); @@ -XXX,XX +XXX,XX @@ static bool trans_VEXT(DisasContext *s, arg_VEXT *a) right = tcg_temp_new_i64(); dest = tcg_temp_new_i64(); - neon_load_reg64(right, a->vn); - neon_load_reg64(left, a->vm); + read_neon_element64(right, a->vn, 0, MO_64); + read_neon_element64(left, a->vm, 0, MO_64); tcg_gen_extract2_i64(dest, right, left, a->imm * 8); - neon_store_reg64(dest, a->vd); + write_neon_element64(dest, a->vd, 0, MO_64); tcg_temp_free_i64(left); tcg_temp_free_i64(right); @@ -XXX,XX +XXX,XX @@ static bool trans_VEXT(DisasContext *s, arg_VEXT *a) destright = tcg_temp_new_i64(); if (a->imm < 8) { - neon_load_reg64(right, a->vn); - neon_load_reg64(middle, a->vn + 1); + read_neon_element64(right, a->vn, 0, MO_64); + read_neon_element64(middle, a->vn, 1, MO_64); tcg_gen_extract2_i64(destright, right, middle, a->imm * 8); - neon_load_reg64(left, a->vm); + read_neon_element64(left, a->vm, 0, MO_64); tcg_gen_extract2_i64(destleft, middle, left, a->imm * 8); } else { - neon_load_reg64(right, a->vn + 1); - neon_load_reg64(middle, a->vm); + read_neon_element64(right, a->vn, 1, MO_64); + read_neon_element64(middle, a->vm, 0, MO_64); tcg_gen_extract2_i64(destright, right, middle, (a->imm - 8) * 8); - neon_load_reg64(left, a->vm + 1); + read_neon_element64(left, a->vm, 1, MO_64); tcg_gen_extract2_i64(destleft, middle, left, (a->imm - 8) * 8); } - neon_store_reg64(destright, a->vd); - neon_store_reg64(destleft, a->vd + 1); + write_neon_element64(destright, a->vd, 0, MO_64); + write_neon_element64(destleft, a->vd, 1, MO_64); tcg_temp_free_i64(destright); tcg_temp_free_i64(destleft); @@ -XXX,XX +XXX,XX @@ static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a, if (accfn) { TCGv_i64 tmp64 = tcg_temp_new_i64(); - neon_load_reg64(tmp64, a->vd + pass); + read_neon_element64(tmp64, a->vd, pass, MO_64); accfn(rd_64, tmp64, rd_64); tcg_temp_free_i64(tmp64); } - neon_store_reg64(rd_64, a->vd + pass); + write_neon_element64(rd_64, a->vd, pass, MO_64); tcg_temp_free_i64(rd_64); } return true; @@ -XXX,XX +XXX,XX @@ static bool do_vmovn(DisasContext *s, arg_2misc *a, rd0 = tcg_temp_new_i32(); rd1 = tcg_temp_new_i32(); - neon_load_reg64(rm, a->vm); + read_neon_element64(rm, a->vm, 0, MO_64); narrowfn(rd0, cpu_env, rm); - neon_load_reg64(rm, a->vm + 1); + read_neon_element64(rm, a->vm, 1, MO_64); narrowfn(rd1, cpu_env, rm); write_neon_element32(rd0, a->vd, 0, MO_32); write_neon_element32(rd1, a->vd, 1, MO_32); @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLL(DisasContext *s, arg_2misc *a) widenfn(rd, rm0); tcg_gen_shli_i64(rd, rd, 8 << a->size); - neon_store_reg64(rd, a->vd); + write_neon_element64(rd, a->vd, 0, MO_64); widenfn(rd, rm1); tcg_gen_shli_i64(rd, rd, 8 << a->size); - neon_store_reg64(rd, a->vd + 1); + write_neon_element64(rd, a->vd, 1, MO_64); tcg_temp_free_i64(rd); tcg_temp_free_i32(rm0); @@ -XXX,XX +XXX,XX @@ static bool trans_VSWP(DisasContext *s, arg_2misc *a) rm = tcg_temp_new_i64(); rd = tcg_temp_new_i64(); for (pass = 0; pass < (a->q ? 2 : 1); pass++) { - neon_load_reg64(rm, a->vm + pass); - neon_load_reg64(rd, a->vd + pass); - neon_store_reg64(rm, a->vd + pass); - neon_store_reg64(rd, a->vm + pass); + read_neon_element64(rm, a->vm, pass, MO_64); + read_neon_element64(rd, a->vd, pass, MO_64); + write_neon_element64(rm, a->vd, pass, MO_64); + write_neon_element64(rd, a->vm, pass, MO_64); } tcg_temp_free_i64(rm); tcg_temp_free_i64(rd); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The only uses of this function are for loading VFP double-precision values, and nothing to do with NEON. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-10-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 8 ++-- target/arm/translate-vfp.c.inc | 84 +++++++++++++++++----------------- 2 files changed, 46 insertions(+), 46 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static long vfp_reg_offset(bool dp, unsigned reg) } } -static inline void neon_load_reg64(TCGv_i64 var, int reg) +static inline void vfp_load_reg64(TCGv_i64 var, int reg) { - tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg)); + tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(true, reg)); } -static inline void neon_store_reg64(TCGv_i64 var, int reg) +static inline void vfp_store_reg64(TCGv_i64 var, int reg) { - tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(1, reg)); + tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(true, reg)); } static inline void vfp_load_reg32(TCGv_i32 var, int reg) diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) tcg_gen_ext_i32_i64(nf, cpu_NF); tcg_gen_ext_i32_i64(vf, cpu_VF); - neon_load_reg64(frn, rn); - neon_load_reg64(frm, rm); + vfp_load_reg64(frn, rn); + vfp_load_reg64(frm, rm); switch (a->cc) { case 0: /* eq: Z */ tcg_gen_movcond_i64(TCG_COND_EQ, dest, zf, zero, @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) tcg_temp_free_i64(tmp); break; } - neon_store_reg64(dest, rd); + vfp_store_reg64(dest, rd); tcg_temp_free_i64(frn); tcg_temp_free_i64(frm); tcg_temp_free_i64(dest); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) TCGv_i64 tcg_res; tcg_op = tcg_temp_new_i64(); tcg_res = tcg_temp_new_i64(); - neon_load_reg64(tcg_op, rm); + vfp_load_reg64(tcg_op, rm); gen_helper_rintd(tcg_res, tcg_op, fpst); - neon_store_reg64(tcg_res, rd); + vfp_store_reg64(tcg_res, rd); tcg_temp_free_i64(tcg_op); tcg_temp_free_i64(tcg_res); } else { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) tcg_double = tcg_temp_new_i64(); tcg_res = tcg_temp_new_i64(); tcg_tmp = tcg_temp_new_i32(); - neon_load_reg64(tcg_double, rm); + vfp_load_reg64(tcg_double, rm); if (is_signed) { gen_helper_vfp_tosld(tcg_res, tcg_double, tcg_shift, fpst); } else { @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_dp(DisasContext *s, arg_VLDR_VSTR_dp *a) tmp = tcg_temp_new_i64(); if (a->l) { gen_aa32_ld64(s, tmp, addr, get_mem_index(s)); - neon_store_reg64(tmp, a->vd); + vfp_store_reg64(tmp, a->vd); } else { - neon_load_reg64(tmp, a->vd); + vfp_load_reg64(tmp, a->vd); gen_aa32_st64(s, tmp, addr, get_mem_index(s)); } tcg_temp_free_i64(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_dp(DisasContext *s, arg_VLDM_VSTM_dp *a) if (a->l) { /* load */ gen_aa32_ld64(s, tmp, addr, get_mem_index(s)); - neon_store_reg64(tmp, a->vd + i); + vfp_store_reg64(tmp, a->vd + i); } else { /* store */ - neon_load_reg64(tmp, a->vd + i); + vfp_load_reg64(tmp, a->vd + i); gen_aa32_st64(s, tmp, addr, get_mem_index(s)); } tcg_gen_addi_i32(addr, addr, offset); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn, fd = tcg_temp_new_i64(); fpst = fpstatus_ptr(FPST_FPCR); - neon_load_reg64(f0, vn); - neon_load_reg64(f1, vm); + vfp_load_reg64(f0, vn); + vfp_load_reg64(f1, vm); for (;;) { if (reads_vd) { - neon_load_reg64(fd, vd); + vfp_load_reg64(fd, vd); } fn(fd, f0, f1, fpst); - neon_store_reg64(fd, vd); + vfp_store_reg64(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn, veclen--; vd = vfp_advance_dreg(vd, delta_d); vn = vfp_advance_dreg(vn, delta_d); - neon_load_reg64(f0, vn); + vfp_load_reg64(f0, vn); if (delta_m) { vm = vfp_advance_dreg(vm, delta_m); - neon_load_reg64(f1, vm); + vfp_load_reg64(f1, vm); } } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) f0 = tcg_temp_new_i64(); fd = tcg_temp_new_i64(); - neon_load_reg64(f0, vm); + vfp_load_reg64(f0, vm); for (;;) { fn(fd, f0); - neon_store_reg64(fd, vd); + vfp_store_reg64(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) /* single source one-many */ while (veclen--) { vd = vfp_advance_dreg(vd, delta_d); - neon_store_reg64(fd, vd); + vfp_store_reg64(fd, vd); } break; } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) veclen--; vd = vfp_advance_dreg(vd, delta_d); vd = vfp_advance_dreg(vm, delta_m); - neon_load_reg64(f0, vm); + vfp_load_reg64(f0, vm); } tcg_temp_free_i64(f0); @@ -XXX,XX +XXX,XX @@ static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d) vm = tcg_temp_new_i64(); vd = tcg_temp_new_i64(); - neon_load_reg64(vn, a->vn); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vn, a->vn); + vfp_load_reg64(vm, a->vm); if (neg_n) { /* VFNMS, VFMS */ gen_helper_vfp_negd(vn, vn); } - neon_load_reg64(vd, a->vd); + vfp_load_reg64(vd, a->vd); if (neg_d) { /* VFNMA, VFNMS */ gen_helper_vfp_negd(vd, vd); } fpst = fpstatus_ptr(FPST_FPCR); gen_helper_vfp_muladdd(vd, vn, vm, vd, fpst); - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i64(vn); @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) fd = tcg_const_i64(vfp_expand_imm(MO_64, a->imm)); for (;;) { - neon_store_reg64(fd, vd); + vfp_store_reg64(fd, vd); if (veclen == 0) { break; @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_dp(DisasContext *s, arg_VCMP_dp *a) vd = tcg_temp_new_i64(); vm = tcg_temp_new_i64(); - neon_load_reg64(vd, a->vd); + vfp_load_reg64(vd, a->vd); if (a->z) { tcg_gen_movi_i64(vm, 0); } else { - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); } if (a->e) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f64_f16(DisasContext *s, arg_VCVT_f64_f16 *a) tcg_gen_ld16u_i32(tmp, cpu_env, vfp_f16_offset(a->vm, a->t)); vd = tcg_temp_new_i64(); gen_helper_vfp_fcvt_f16_to_f64(vd, tmp, fpst, ahp_mode); - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_i32(ahp_mode); tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f64(DisasContext *s, arg_VCVT_f16_f64 *a) tmp = tcg_temp_new_i32(); vm = tcg_temp_new_i64(); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); gen_helper_vfp_fcvt_f64_to_f16(tmp, vm, fpst, ahp_mode); tcg_temp_free_i64(vm); tcg_gen_st16_i32(tmp, cpu_env, vfp_f16_offset(a->vd, a->t)); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_dp *a) } tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vm); + vfp_load_reg64(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); gen_helper_rintd(tmp, tmp, fpst); - neon_store_reg64(tmp, a->vd); + vfp_store_reg64(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i64(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_dp *a) } tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vm); + vfp_load_reg64(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); tcg_rmode = tcg_const_i32(float_round_to_zero); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); gen_helper_rintd(tmp, tmp, fpst); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); - neon_store_reg64(tmp, a->vd); + vfp_store_reg64(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i64(tmp); tcg_temp_free_i32(tcg_rmode); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_dp(DisasContext *s, arg_VRINTX_dp *a) } tmp = tcg_temp_new_i64(); - neon_load_reg64(tmp, a->vm); + vfp_load_reg64(tmp, a->vm); fpst = fpstatus_ptr(FPST_FPCR); gen_helper_rintd_exact(tmp, tmp, fpst); - neon_store_reg64(tmp, a->vd); + vfp_store_reg64(tmp, a->vd); tcg_temp_free_ptr(fpst); tcg_temp_free_i64(tmp); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp(DisasContext *s, arg_VCVT_sp *a) vd = tcg_temp_new_i64(); vfp_load_reg32(vm, a->vm); gen_helper_vfp_fcvtds(vd, vm, cpu_env); - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_i64(vd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) vd = tcg_temp_new_i32(); vm = tcg_temp_new_i64(); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); gen_helper_vfp_fcvtsd(vd, vm, cpu_env); vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_dp(DisasContext *s, arg_VCVT_int_dp *a) /* u32 -> f64 */ gen_helper_vfp_uitod(vd, vm, fpst); } - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_i32(vm); tcg_temp_free_i64(vd); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a) vm = tcg_temp_new_i64(); vd = tcg_temp_new_i32(); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); gen_helper_vjcvt(vd, vm, cpu_env); vfp_store_reg32(vd, a->vd); tcg_temp_free_i64(vm); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm); vd = tcg_temp_new_i64(); - neon_load_reg64(vd, a->vd); + vfp_load_reg64(vd, a->vd); fpst = fpstatus_ptr(FPST_FPCR); shift = tcg_const_i32(frac_bits); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) g_assert_not_reached(); } - neon_store_reg64(vd, a->vd); + vfp_store_reg64(vd, a->vd); tcg_temp_free_i64(vd); tcg_temp_free_i32(shift); tcg_temp_free_ptr(fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) fpst = fpstatus_ptr(FPST_FPCR); vm = tcg_temp_new_i64(); vd = tcg_temp_new_i32(); - neon_load_reg64(vm, a->vm); + vfp_load_reg64(vm, a->vm); if (a->s) { if (a->rz) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> In both cases, we can sink the write-back and perform the accumulate into the normal destination temps. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-11-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-neon.c.inc | 23 +++++++++-------------- 1 file changed, 9 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_long_3d(DisasContext *s, arg_3diff *a, if (accfn) { tmp = tcg_temp_new_i64(); read_neon_element64(tmp, a->vd, 0, MO_64); - accfn(tmp, tmp, rd0); - write_neon_element64(tmp, a->vd, 0, MO_64); + accfn(rd0, tmp, rd0); read_neon_element64(tmp, a->vd, 1, MO_64); - accfn(tmp, tmp, rd1); - write_neon_element64(tmp, a->vd, 1, MO_64); + accfn(rd1, tmp, rd1); tcg_temp_free_i64(tmp); - } else { - write_neon_element64(rd0, a->vd, 0, MO_64); - write_neon_element64(rd1, a->vd, 1, MO_64); } + write_neon_element64(rd0, a->vd, 0, MO_64); + write_neon_element64(rd1, a->vd, 1, MO_64); tcg_temp_free_i64(rd0); tcg_temp_free_i64(rd1); @@ -XXX,XX +XXX,XX @@ static bool do_2scalar_long(DisasContext *s, arg_2scalar *a, if (accfn) { TCGv_i64 t64 = tcg_temp_new_i64(); read_neon_element64(t64, a->vd, 0, MO_64); - accfn(t64, t64, rn0_64); - write_neon_element64(t64, a->vd, 0, MO_64); + accfn(rn0_64, t64, rn0_64); read_neon_element64(t64, a->vd, 1, MO_64); - accfn(t64, t64, rn1_64); - write_neon_element64(t64, a->vd, 1, MO_64); + accfn(rn1_64, t64, rn1_64); tcg_temp_free_i64(t64); - } else { - write_neon_element64(rn0_64, a->vd, 0, MO_64); - write_neon_element64(rn1_64, a->vd, 1, MO_64); } + + write_neon_element64(rn0_64, a->vd, 0, MO_64); + write_neon_element64(rn1_64, a->vd, 1, MO_64); tcg_temp_free_i64(rn0_64); tcg_temp_free_i64(rn1_64); return true; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We can use proper widening loads to extend 32-bit inputs, and skip the "widenfn" step. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030022618.785675-12-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 6 +++ target/arm/translate-neon.c.inc | 66 ++++++++++++++++++--------------- 2 files changed, 43 insertions(+), 29 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) long off = neon_element_offset(reg, ele, memop); switch (memop) { + case MO_SL: + tcg_gen_ld32s_i64(dest, cpu_env, off); + break; + case MO_UL: + tcg_gen_ld32u_i64(dest, cpu_env, off); + break; case MO_Q: tcg_gen_ld_i64(dest, cpu_env, off); break; diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_Vimm_1r(DisasContext *s, arg_1reg_imm *a) static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, NeonGenWidenFn *widenfn, NeonGenTwo64OpFn *opfn, - bool src1_wide) + int src1_mop, int src2_mop) { /* 3-regs different lengths, prewidening case (VADDL/VSUBL/VAADW/VSUBW) */ TCGv_i64 rn0_64, rn1_64, rm_64; - TCGv_i32 rm; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, return false; } - if (!widenfn || !opfn) { + if (!opfn) { /* size == 3 case, which is an entirely different insn group */ return false; } - if ((a->vd & 1) || (src1_wide && (a->vn & 1))) { + if ((a->vd & 1) || (src1_mop == MO_Q && (a->vn & 1))) { return false; } @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, rn1_64 = tcg_temp_new_i64(); rm_64 = tcg_temp_new_i64(); - if (src1_wide) { - read_neon_element64(rn0_64, a->vn, 0, MO_64); + if (src1_mop >= 0) { + read_neon_element64(rn0_64, a->vn, 0, src1_mop); } else { TCGv_i32 tmp = tcg_temp_new_i32(); read_neon_element32(tmp, a->vn, 0, MO_32); widenfn(rn0_64, tmp); tcg_temp_free_i32(tmp); } - rm = tcg_temp_new_i32(); - read_neon_element32(rm, a->vm, 0, MO_32); + if (src2_mop >= 0) { + read_neon_element64(rm_64, a->vm, 0, src2_mop); + } else { + TCGv_i32 tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, 0, MO_32); + widenfn(rm_64, tmp); + tcg_temp_free_i32(tmp); + } - widenfn(rm_64, rm); - tcg_temp_free_i32(rm); opfn(rn0_64, rn0_64, rm_64); /* * Load second pass inputs before storing the first pass result, to * avoid incorrect results if a narrow input overlaps with the result. */ - if (src1_wide) { - read_neon_element64(rn1_64, a->vn, 1, MO_64); + if (src1_mop >= 0) { + read_neon_element64(rn1_64, a->vn, 1, src1_mop); } else { TCGv_i32 tmp = tcg_temp_new_i32(); read_neon_element32(tmp, a->vn, 1, MO_32); widenfn(rn1_64, tmp); tcg_temp_free_i32(tmp); } - rm = tcg_temp_new_i32(); - read_neon_element32(rm, a->vm, 1, MO_32); + if (src2_mop >= 0) { + read_neon_element64(rm_64, a->vm, 1, src2_mop); + } else { + TCGv_i32 tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, a->vm, 1, MO_32); + widenfn(rm_64, tmp); + tcg_temp_free_i32(tmp); + } write_neon_element64(rn0_64, a->vd, 0, MO_64); - widenfn(rm_64, rm); - tcg_temp_free_i32(rm); opfn(rn1_64, rn1_64, rm_64); write_neon_element64(rn1_64, a->vd, 1, MO_64); @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, return true; } -#define DO_PREWIDEN(INSN, S, EXT, OP, SRC1WIDE) \ +#define DO_PREWIDEN(INSN, S, OP, SRC1WIDE, SIGN) \ static bool trans_##INSN##_3d(DisasContext *s, arg_3diff *a) \ { \ static NeonGenWidenFn * const widenfn[] = { \ gen_helper_neon_widen_##S##8, \ gen_helper_neon_widen_##S##16, \ - tcg_gen_##EXT##_i32_i64, \ - NULL, \ + NULL, NULL, \ }; \ static NeonGenTwo64OpFn * const addfn[] = { \ gen_helper_neon_##OP##l_u16, \ @@ -XXX,XX +XXX,XX @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, tcg_gen_##OP##_i64, \ NULL, \ }; \ - return do_prewiden_3d(s, a, widenfn[a->size], \ - addfn[a->size], SRC1WIDE); \ + int narrow_mop = a->size == MO_32 ? MO_32 | SIGN : -1; \ + return do_prewiden_3d(s, a, widenfn[a->size], addfn[a->size], \ + SRC1WIDE ? MO_Q : narrow_mop, \ + narrow_mop); \ } -DO_PREWIDEN(VADDL_S, s, ext, add, false) -DO_PREWIDEN(VADDL_U, u, extu, add, false) -DO_PREWIDEN(VSUBL_S, s, ext, sub, false) -DO_PREWIDEN(VSUBL_U, u, extu, sub, false) -DO_PREWIDEN(VADDW_S, s, ext, add, true) -DO_PREWIDEN(VADDW_U, u, extu, add, true) -DO_PREWIDEN(VSUBW_S, s, ext, sub, true) -DO_PREWIDEN(VSUBW_U, u, extu, sub, true) +DO_PREWIDEN(VADDL_S, s, add, false, MO_SIGN) +DO_PREWIDEN(VADDL_U, u, add, false, 0) +DO_PREWIDEN(VSUBL_S, s, sub, false, MO_SIGN) +DO_PREWIDEN(VSUBL_U, u, sub, false, 0) +DO_PREWIDEN(VADDW_S, s, add, true, MO_SIGN) +DO_PREWIDEN(VADDW_U, u, add, true, 0) +DO_PREWIDEN(VSUBW_S, s, sub, true, MO_SIGN) +DO_PREWIDEN(VSUBW_U, u, sub, true, 0) static bool do_narrow_3d(DisasContext *s, arg_3diff *a, NeonGenTwo64OpFn *opfn, NeonGenNarrowFn *narrowfn) -- 2.20.1 In the neon_padd/pmax/pmin helpers for float16, a cut-and-paste error meant we were using the H4() address swizzler macro rather than the H2() which is required for 2-byte data. This had no effect on little-endian hosts but meant we put the result data into the destination Dreg in the wrong order on big-endian hosts. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20201028191712.4910-2-peter.maydell@linaro.org --- target/arm/vec_helper.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ DO_ABA(gvec_uaba_d, uint64_t) r2 = float16_##OP(m[H2(0)], m[H2(1)], fpst); \ r3 = float16_##OP(m[H2(2)], m[H2(3)], fpst); \ \ - d[H4(0)] = r0; \ - d[H4(1)] = r1; \ - d[H4(2)] = r2; \ - d[H4(3)] = r3; \ + d[H2(0)] = r0; \ + d[H2(1)] = r1; \ + d[H2(2)] = r2; \ + d[H2(3)] = r3; \ } DO_NEON_PAIRWISE(neon_padd, add) -- 2.20.1 The helper functions for performing the udot/sdot operations against a scalar were not using an address-swizzling macro when converting the index of the scalar element into a pointer into the vm array. This had no effect on little-endian hosts but meant we generated incorrect results on big-endian hosts. For these insns, the index is indexing over group of 4 8-bit values, so 32 bits per indexed entity, and H4() is therefore what we want. (For Neon the only possible input indexes are 0 and 1.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20201028191712.4910-3-peter.maydell@linaro.org --- target/arm/vec_helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) intptr_t index = simd_data(desc); uint32_t *d = vd; int8_t *n = vn; - int8_t *m_indexed = (int8_t *)vm + index * 4; + int8_t *m_indexed = (int8_t *)vm + H4(index) * 4; /* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd. * Otherwise opr_sz is a multiple of 16. @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) intptr_t index = simd_data(desc); uint32_t *d = vd; uint8_t *n = vn; - uint8_t *m_indexed = (uint8_t *)vm + index * 4; + uint8_t *m_indexed = (uint8_t *)vm + H4(index) * 4; /* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd. * Otherwise opr_sz is a multiple of 16. -- 2.20.1 From: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> HCR should be applied when NS is set, not when it is cleared. Signed-off-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void tlbimvaa_is_write(CPUARMState *env, const ARMCPRegInfo *ri, /* * Non-IS variants of TLB operations are upgraded to - * IS versions if we are at NS EL1 and HCR_EL2.FB is set to + * IS versions if we are at EL1 and HCR_EL2.FB is effectively set to * force broadcast of these operations. */ static bool tlb_force_broadcast(CPUARMState *env) { - return (env->cp15.hcr_el2 & HCR_FB) && - arm_current_el(env) == 1 && arm_is_secure_below_el3(env); + return arm_current_el(env) == 1 && (arm_hcr_el2_eff(env) & HCR_FB); } static void tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri, -- 2.20.1 From: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Secure mode is not exempted from checking SCR_EL3.TLOR, and in the future HCR_EL2.TLOR when S-EL2 is enabled. Signed-off-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t id_aa64pfr0_read(CPUARMState *env, const ARMCPRegInfo *ri) #endif /* Shared logic between LORID and the rest of the LOR* registers. - * Secure state has already been delt with. + * Secure state exclusion has already been dealt with. */ -static CPAccessResult access_lor_ns(CPUARMState *env) +static CPAccessResult access_lor_ns(CPUARMState *env, + const ARMCPRegInfo *ri, bool isread) { int el = arm_current_el(env); @@ -XXX,XX +XXX,XX @@ static CPAccessResult access_lor_ns(CPUARMState *env) return CP_ACCESS_OK; } -static CPAccessResult access_lorid(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread) -{ - if (arm_is_secure_below_el3(env)) { - /* Access ok in secure mode. */ - return CP_ACCESS_OK; - } - return access_lor_ns(env); -} - static CPAccessResult access_lor_other(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { @@ -XXX,XX +XXX,XX @@ static CPAccessResult access_lor_other(CPUARMState *env, /* Access denied in secure mode. */ return CP_ACCESS_TRAP; } - return access_lor_ns(env); + return access_lor_ns(env, ri, isread); } /* @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo lor_reginfo[] = { .type = ARM_CP_CONST, .resetvalue = 0 }, { .name = "LORID_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 10, .crm = 4, .opc2 = 7, - .access = PL1_R, .accessfn = access_lorid, + .access = PL1_R, .accessfn = access_lor_ns, .type = ARM_CP_CONST, .resetvalue = 0 }, REGINFO_SENTINEL }; -- 2.20.1 If we're using the capstone disassembler, disassembly of a run of instructions more than 32 bytes long disassembles the wrong data for instructions beyond the 32 byte mark: (qemu) xp /16x 0x100 0000000000000100: 0x00000005 0x54410001 0x00000001 0x00001000 0000000000000110: 0x00000000 0x00000004 0x54410002 0x3c000000 0000000000000120: 0x00000000 0x00000004 0x54410009 0x74736574 0000000000000130: 0x00000000 0x00000000 0x00000000 0x00000000 (qemu) xp /16i 0x100 0x00000100: 00000005 andeq r0, r0, r5 0x00000104: 54410001 strbpl r0, [r1], #-1 0x00000108: 00000001 andeq r0, r0, r1 0x0000010c: 00001000 andeq r1, r0, r0 0x00000110: 00000000 andeq r0, r0, r0 0x00000114: 00000004 andeq r0, r0, r4 0x00000118: 54410002 strbpl r0, [r1], #-2 0x0000011c: 3c000000 .byte 0x00, 0x00, 0x00, 0x3c 0x00000120: 54410001 strbpl r0, [r1], #-1 0x00000124: 00000001 andeq r0, r0, r1 0x00000128: 00001000 andeq r1, r0, r0 0x0000012c: 00000000 andeq r0, r0, r0 0x00000130: 00000004 andeq r0, r0, r4 0x00000134: 54410002 strbpl r0, [r1], #-2 0x00000138: 3c000000 .byte 0x00, 0x00, 0x00, 0x3c 0x0000013c: 00000000 andeq r0, r0, r0 Here the disassembly of 0x120..0x13f is using the data that is in 0x104..0x123. This is caused by passing the wrong value to the read_memory_func(). The intention is that at this point in the loop the 'cap_buf' buffer already contains 'csize' bytes of data for the instruction at guest addr 'pc', and we want to read in an extra 'tsize' bytes. Those extra bytes are therefore at 'pc + csize', not 'pc'. On the first time through the loop 'csize' happens to be zero, so the initial read of 32 bytes into cap_buf is correct and as long as the disassembly never needs to read more data we return the correct information. Use the correct guest address in the call to read_memory_func(). Cc: qemu-stable@nongnu.org Fixes: https://bugs.launchpad.net/qemu/+bug/1900779 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20201022132445.25039-1-peter.maydell@linaro.org --- disas/capstone.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/disas/capstone.c b/disas/capstone.c index XXXXXXX..XXXXXXX 100644 --- a/disas/capstone.c +++ b/disas/capstone.c @@ -XXX,XX +XXX,XX @@ bool cap_disas_monitor(disassemble_info *info, uint64_t pc, int count) /* Make certain that we can make progress. */ assert(tsize != 0); - info->read_memory_func(pc, cap_buf + csize, tsize, info); + info->read_memory_func(pc + csize, cap_buf + csize, tsize, info); csize += tsize; if (cs_disasm_iter(handle, &cbuf, &csize, &pc, insn)) { -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Use the BIT_ULL() macro to ensure we use 64-bit arithmetic. This fixes the following Coverity issue (OVERFLOW_BEFORE_WIDEN): CID 1432363 (#1 of 1): Unintentional integer overflow: overflow_before_widen: Potentially overflowing expression 1 << scale with type int (32 bits, signed) is evaluated using 32-bit arithmetic, and then used in a context that expects an expression of type hwaddr (64 bits, unsigned). Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Acked-by: Eric Auger <eric.auger@redhat.com> Message-id: 20201030144617.1535064-1-philmd@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/smmuv3.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/bitops.h" #include "hw/irq.h" #include "hw/sysbus.h" #include "migration/vmstate.h" @@ -XXX,XX +XXX,XX @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd) scale = CMD_SCALE(cmd); num = CMD_NUM(cmd); ttl = CMD_TTL(cmd); - num_pages = (num + 1) * (1 << (scale)); + num_pages = (num + 1) * BIT_ULL(scale); } if (type == SMMU_CMD_TLBI_NH_VA) { -- 2.20.1 From: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> When booting a CPU with EL3 using the -kernel flag, set up CPTR_EL3 so that SVE will not trap to EL3. Signed-off-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201030151541.11976-1-remi@remlab.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/boot.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ static void do_cpu_reset(void *opaque) if (cpu_isar_feature(aa64_mte, cpu)) { env->cp15.scr_el3 |= SCR_ATA; } + if (cpu_isar_feature(aa64_sve, cpu)) { + env->cp15.cptr_el[3] |= CPTR_EZ; + } /* AArch64 kernels never boot in secure mode */ assert(!info->secure_boot); /* This hook is only supported for AArch32 currently: -- 2.20.1 From: AlexChen <alex.chen@huawei.com> In omap_lcd_interrupts(), the pointer omap_lcd is dereferinced before being check if it is valid, which may lead to NULL pointer dereference. So move the assignment to surface after checking that the omap_lcd is valid and move surface_bits_per_pixel(surface) to after the surface assignment. Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: AlexChen <alex.chen@huawei.com> Message-id: 5F9CDB8A.9000001@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/display/omap_lcdc.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/hw/display/omap_lcdc.c b/hw/display/omap_lcdc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcdc.c +++ b/hw/display/omap_lcdc.c @@ -XXX,XX +XXX,XX @@ static void omap_lcd_interrupts(struct omap_lcd_panel_s *s) static void omap_update_display(void *opaque) { struct omap_lcd_panel_s *omap_lcd = (struct omap_lcd_panel_s *) opaque; - DisplaySurface *surface = qemu_console_surface(omap_lcd->con); + DisplaySurface *surface; draw_line_func draw_line; int size, height, first, last; int width, linesize, step, bpp, frame_offset; hwaddr frame_base; - if (!omap_lcd || omap_lcd->plm == 1 || !omap_lcd->enable || - !surface_bits_per_pixel(surface)) { + if (!omap_lcd || omap_lcd->plm == 1 || !omap_lcd->enable) { + return; + } + + surface = qemu_console_surface(omap_lcd->con); + if (!surface_bits_per_pixel(surface)) { return; } -- 2.20.1 From: AlexChen <alex.chen@huawei.com> In exynos4210_fimd_update(), the pointer s is dereferinced before being check if it is valid, which may lead to NULL pointer dereference. So move the assignment to global_width after checking that the s is valid. Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 5F9F8D88.9030102@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/display/exynos4210_fimd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/hw/display/exynos4210_fimd.c b/hw/display/exynos4210_fimd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/exynos4210_fimd.c +++ b/hw/display/exynos4210_fimd.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_fimd_update(void *opaque) bool blend = false; uint8_t *host_fb_addr; bool is_dirty = false; - const int global_width = (s->vidtcon[2] & FIMD_VIDTCON2_SIZE_MASK) + 1; + int global_width; if (!s || !s->console || !s->enabled || surface_bits_per_pixel(qemu_console_surface(s->console)) == 0) { return; } + + global_width = (s->vidtcon[2] & FIMD_VIDTCON2_SIZE_MASK) + 1; exynos4210_update_resolution(s); surface = qemu_console_surface(s->console); -- 2.20.1 In arm_v7m_mmu_idx_for_secstate() we get the 'priv' level to pass to armv7m_mmu_idx_for_secstate_and_priv() by calling arm_current_el(). This is incorrect when the security state being queried is not the current one, because arm_current_el() uses the current security state to determine which of the banked CONTROL.nPRIV bits to look at. The effect was that if (for instance) Secure state was in privileged mode but Non-Secure was not then we would return the wrong MMU index. The only places where we are using this function in a way that could trigger this bug are for the stack loads during a v8M function-return and for the instruction fetch of a v8M SG insn. Fix the bug by expanding out the M-profile version of the arm_current_el() logic inline so it can use the passed in secstate rather than env->v7m.secure. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201022164408.13214-1-peter.maydell@linaro.org --- target/arm/m_helper.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -XXX,XX +XXX,XX @@ ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env, /* Return the MMU index for a v7M CPU in the specified security state */ ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate) { - bool priv = arm_current_el(env) != 0; + bool priv = arm_v7m_is_handler_mode(env) || + !(env->v7m.control[secstate] & 1); return arm_v7m_mmu_idx_for_secstate_and_priv(env, secstate, priv); } -- 2.20.1 On some hosts (eg Ubuntu Bionic) pkg-config returns a set of libraries for gio-2.0 which don't actually work when compiling statically. (Specifically, the returned library string includes -lmount, but not -lblkid which -lmount depends upon, so linking fails due to missing symbols.) Check that the libraries work, and don't enable gio if they don't, in the same way we do for gnutls. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200928160402.7961-1-peter.maydell@linaro.org --- configure | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ if test "$static" = yes && test "$mingw32" = yes; then fi if $pkg_config --atleast-version=$glib_req_ver gio-2.0; then - gio=yes gio_cflags=$($pkg_config --cflags gio-2.0) gio_libs=$($pkg_config --libs gio-2.0) gdbus_codegen=$($pkg_config --variable=gdbus_codegen gio-2.0) if [ ! -x "$gdbus_codegen" ]; then gdbus_codegen= fi + # Check that the libraries actually work -- Ubuntu 18.04 ships + # with pkg-config --static --libs data for gio-2.0 that is missing + # -lblkid and will give a link error. + write_c_skeleton + if compile_prog "" "gio_libs" ; then + gio=yes + else + gio=no + fi else gio=no fi -- 2.20.1 In gicv3_init_cpuif() we copy the ARMCPU gicv3_maintenance_interrupt into the GICv3CPUState struct's maintenance_irq field. This will only work if the board happens to have already wired up the CPU maintenance IRQ before the GIC was realized. Unfortunately this is not the case for the 'virt' board, and so the value that gets copied is NULL (since a qemu_irq is really a pointer to an IRQState struct under the hood). The effect is that the CPU interface code never actually raises the maintenance interrupt line. Instead, since the GICv3CPUState has a pointer to the CPUState, make the dereference at the point where we want to raise the interrupt, to avoid an implicit requirement on board code to wire things up in a particular order. Reported-by: Jose Martins <josemartins90@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20201009153904.28529-1-peter.maydell@linaro.org Reviewed-by: Luc Michel <luc@lmichel.fr> --- include/hw/intc/arm_gicv3_common.h | 1 - hw/intc/arm_gicv3_cpuif.c | 5 ++--- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3CPUState { qemu_irq parent_fiq; qemu_irq parent_virq; qemu_irq parent_vfiq; - qemu_irq maintenance_irq; /* Redistributor */ uint32_t level; /* Current IRQ level */ diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static void gicv3_cpuif_virt_update(GICv3CPUState *cs) int irqlevel = 0; int fiqlevel = 0; int maintlevel = 0; + ARMCPU *cpu = ARM_CPU(cs->cpu); idx = hppvi_index(cs); trace_gicv3_cpuif_virt_update(gicv3_redist_affid(cs), idx); @@ -XXX,XX +XXX,XX @@ static void gicv3_cpuif_virt_update(GICv3CPUState *cs) qemu_set_irq(cs->parent_vfiq, fiqlevel); qemu_set_irq(cs->parent_virq, irqlevel); - qemu_set_irq(cs->maintenance_irq, maintlevel); + qemu_set_irq(cpu->gicv3_maintenance_interrupt, maintlevel); } static uint64_t icv_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) @@ -XXX,XX +XXX,XX @@ void gicv3_init_cpuif(GICv3State *s) && cpu->gic_num_lrs) { int j; - cs->maintenance_irq = cpu->gicv3_maintenance_interrupt; - cs->num_list_regs = cpu->gic_num_lrs; cs->vpribits = cpu->gic_vpribits; cs->vprebits = cpu->gic_vprebits; -- 2.20.1 The kerneldoc script currently emits Sphinx markup for a macro with arguments that uses the c:function directive. This is correct for Sphinx versions earlier than Sphinx 3, where c:macro doesn't allow documentation of macros with arguments and c:function is not picky about the syntax of what it is passed. However, in Sphinx 3 the c:macro directive was enhanced to support macros with arguments, and c:function was made more picky about what syntax it accepted. When kerneldoc is told that it needs to produce output for Sphinx 3 or later, make it emit c:function only for functions and c:macro for macros with arguments. We assume that anything with a return type is a function and anything without is a macro. This fixes the Sphinx error: /home/petmay01/linaro/qemu-from-laptop/qemu/docs/../include/qom/object.h:155:Error in declarator If declarator-id with parameters (e.g., 'void f(int arg)'): Invalid C declaration: Expected identifier in nested name. [error at 25] DECLARE_INSTANCE_CHECKER ( InstanceType, OBJ_NAME, TYPENAME) -------------------------^ If parenthesis in noptr-declarator (e.g., 'void (*f(int arg))(double)'): Error in declarator or parameters Invalid C declaration: Expecting "(" in parameters. [error at 39] DECLARE_INSTANCE_CHECKER ( InstanceType, OBJ_NAME, TYPENAME) ---------------------------------------^ Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Tested-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20201030174700.7204-2-peter.maydell@linaro.org --- scripts/kernel-doc | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index XXXXXXX..XXXXXXX 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -XXX,XX +XXX,XX @@ sub output_function_rst(%) { output_highlight_rst($args{'purpose'}); $start = "\n\n**Syntax**\n\n ``"; } else { - print ".. c:function:: "; + if ((split(/\./, $sphinx_version))[0] >= 3) { + # Sphinx 3 and later distinguish macros and functions and + # complain if you use c:function with something that's not + # syntactically valid as a function declaration. + # We assume that anything with a return type is a function + # and anything without is a macro. + if ($args{'functiontype'} ne "") { + print ".. c:function:: "; + } else { + print ".. c:macro:: "; + } + } else { + # Older Sphinx don't support documenting macros that take + # arguments with c:macro, and don't complain about the use + # of c:function for this. + print ".. c:function:: "; + } } if ($args{'functiontype'} ne "") { $start .= $args{'functiontype'} . " " . $args{'function'} . " ("; -- 2.20.1 Sphinx 3.2 is pickier than earlier versions about the option:: markup, and complains about our usage in qemu-option-trace.rst: ../../docs/qemu-option-trace.rst.inc:4:Malformed option description '[enable=]PATTERN', should look like "opt", "-opt args", "--opt args", "/opt args" or "+opt args" In this file, we're really trying to document the different parts of the top-level --trace option, which qemu-nbd.rst and qemu-img.rst have already introduced with an option:: markup. So it's not right to use option:: here anyway. Switch to a different markup (definition lists) which gives about the same formatted output. (Unlike option::, this markup doesn't produce index entries; but at the moment we don't do anything much with indexes anyway, and in any case I think it doesn't make much sense to have individual index entries for the sub-parts of the --trace option.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Tested-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20201030174700.7204-3-peter.maydell@linaro.org --- docs/qemu-option-trace.rst.inc | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/qemu-option-trace.rst.inc b/docs/qemu-option-trace.rst.inc index XXXXXXX..XXXXXXX 100644 --- a/docs/qemu-option-trace.rst.inc +++ b/docs/qemu-option-trace.rst.inc @@ -XXX,XX +XXX,XX @@ Specify tracing options. -.. option:: [enable=]PATTERN +``[enable=]PATTERN`` Immediately enable events matching *PATTERN* (either event name or a globbing pattern). This option is only @@ -XXX,XX +XXX,XX @@ Specify tracing options. Use :option:`-trace help` to print a list of names of trace points. -.. option:: events=FILE +``events=FILE`` Immediately enable events listed in *FILE*. The file must contain one event name (as listed in the ``trace-events-all`` @@ -XXX,XX +XXX,XX @@ Specify tracing options. available if QEMU has been compiled with the ``simple``, ``log`` or ``ftrace`` tracing backend. -.. option:: file=FILE +``file=FILE`` Log output traces to *FILE*. This option is only available if QEMU has been compiled with -- 2.20.1 The randomness tests in the NPCM7xx RNG test fail intermittently but fairly frequently. On my machine running the test in a loop: while QTEST_QEMU_BINARY=./qemu-system-aarch64 ./tests/qtest/npcm7xx_rng-test; do true; done will fail in less than a minute with an error like: ERROR:../../tests/qtest/npcm7xx_rng-test.c:256:test_first_byte_runs: assertion failed (calc_runs_p(buf.l, sizeof(buf) * BITS_PER_BYTE) > 0.01): (0.00286205989 > 0.01) (Failures have been observed on all 4 of the randomness tests, not just first_byte_runs.) It's not clear why these tests are failing like this, but intermittent failures make CI and merge testing awkward, so disable running them unless a developer specifically sets QEMU_TEST_FLAKY_RNG_TESTS when running the test suite, until we work out the cause. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20201102152454.8287-1-peter.maydell@linaro.org Reviewed-by: Havard Skinnemoen <hskinnemoen@google.com> --- tests/qtest/npcm7xx_rng-test.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/tests/qtest/npcm7xx_rng-test.c b/tests/qtest/npcm7xx_rng-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/npcm7xx_rng-test.c +++ b/tests/qtest/npcm7xx_rng-test.c @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) qtest_add_func("npcm7xx_rng/enable_disable", test_enable_disable); qtest_add_func("npcm7xx_rng/rosel", test_rosel); - qtest_add_func("npcm7xx_rng/continuous/monobit", test_continuous_monobit); - qtest_add_func("npcm7xx_rng/continuous/runs", test_continuous_runs); - qtest_add_func("npcm7xx_rng/first_byte/monobit", test_first_byte_monobit); - qtest_add_func("npcm7xx_rng/first_byte/runs", test_first_byte_runs); + /* + * These tests fail intermittently; only run them on explicit + * request until we figure out why. + */ + if (getenv("QEMU_TEST_FLAKY_RNG_TESTS")) { + qtest_add_func("npcm7xx_rng/continuous/monobit", test_continuous_monobit); + qtest_add_func("npcm7xx_rng/continuous/runs", test_continuous_runs); + qtest_add_func("npcm7xx_rng/first_byte/monobit", test_first_byte_monobit); + qtest_add_func("npcm7xx_rng/first_byte/runs", test_first_byte_runs); + } qtest_start("-machine npcm750-evb"); ret = g_test_run(); -- 2.20.1 The following changes since commit f003dd8d81f7d88f4b1f8802309eaa76f6eb223a: Merge tag 'pull-tcg-20230305' of https://gitlab.com/rth7680/qemu into staging (2023-03-06 10:20:04 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20230306 for you to fetch changes up to 2ddc45954f97cd1d7ee5cbca0def05e980d1da9f: hw: arm: allwinner-h3: Fix and complete H3 i2c devices (2023-03-06 15:31:24 +0000) ---------------------------------------------------------------- target-arm queue: * allwinner-h3: Fix I2C controller model for Sun6i SoCs * allwinner-h3: Add missing i2c controllers * Expose M-profile system registers to gdbstub * Expose pauth information to gdbstub * Support direct boot for Linux/arm64 EFI zboot images * Fix incorrect stage 2 MMU setup validation ---------------------------------------------------------------- Ard Biesheuvel (1): hw: arm: Support direct boot for Linux/arm64 EFI zboot images David Reiss (2): target/arm: Export arm_v7m_mrs_control target/arm: Export arm_v7m_get_sp_ptr Richard Henderson (16): target/arm: Normalize aarch64 gdbstub get/set function names target/arm: Unexport arm_gen_dynamic_sysreg_xml target/arm: Move arm_gen_dynamic_svereg_xml to gdbstub64.c target/arm: Split out output_vector_union_type target/arm: Simplify register counting in arm_gen_dynamic_svereg_xml target/arm: Hoist pred_width in arm_gen_dynamic_svereg_xml target/arm: Fix svep width in arm_gen_dynamic_svereg_xml target/arm: Add name argument to output_vector_union_type target/arm: Simplify iteration over bit widths target/arm: Create pauth_ptr_mask target/arm: Implement gdbstub pauth extension target/arm: Implement gdbstub m-profile systemreg and secext target/arm: Handle m-profile in arm_is_secure target/arm: Stub arm_hcr_el2_eff for m-profile target/arm: Diagnose incorrect usage of arm_is_secure subroutines target/arm: Rewrite check_s2_mmu_setup qianfan Zhao (2): hw: allwinner-i2c: Fix TWI_CNTR_INT_FLAG on SUN6i SoCs hw: arm: allwinner-h3: Fix and complete H3 i2c devices configs/targets/aarch64-linux-user.mak | 2 +- configs/targets/aarch64-softmmu.mak | 2 +- configs/targets/aarch64_be-linux-user.mak | 2 +- include/hw/arm/allwinner-h3.h | 6 + include/hw/i2c/allwinner-i2c.h | 6 + include/hw/loader.h | 19 ++ target/arm/cpu.h | 17 +- target/arm/internals.h | 34 +++- hw/arm/allwinner-h3.c | 29 +++- hw/arm/boot.c | 6 + hw/core/loader.c | 91 ++++++++++ hw/i2c/allwinner-i2c.c | 26 ++- target/arm/gdbstub.c | 278 ++++++++++++++++++------------ target/arm/gdbstub64.c | 175 ++++++++++++++++++- target/arm/helper.c | 3 + target/arm/ptw.c | 173 +++++++++++-------- target/arm/tcg/m_helper.c | 90 +++++----- target/arm/tcg/pauth_helper.c | 26 ++- gdb-xml/aarch64-pauth.xml | 15 ++ 19 files changed, 742 insertions(+), 258 deletions(-) create mode 100644 gdb-xml/aarch64-pauth.xml From: Richard Henderson <richard.henderson@linaro.org> Make the form of the function names between fp and sve the same: - arm_gdb_*_svereg -> aarch64_gdb_*_sve_reg. - aarch64_fpu_gdb_*_reg -> aarch64_gdb_*_fpu_reg. Reviewed-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 8 ++++---- target/arm/gdbstub.c | 9 +++++---- target/arm/gdbstub64.c | 8 ++++---- 3 files changed, 13 insertions(+), 12 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 uint64_t pmu_counter_mask(CPUARMState *env) } #ifdef TARGET_AARCH64 -int arm_gdb_get_svereg(CPUARMState *env, GByteArray *buf, int reg); -int arm_gdb_set_svereg(CPUARMState *env, uint8_t *buf, int reg); -int aarch64_fpu_gdb_get_reg(CPUARMState *env, GByteArray *buf, int reg); -int aarch64_fpu_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg); +int aarch64_gdb_get_sve_reg(CPUARMState *env, GByteArray *buf, int reg); +int aarch64_gdb_set_sve_reg(CPUARMState *env, uint8_t *buf, int reg); +int aarch64_gdb_get_fpu_reg(CPUARMState *env, GByteArray *buf, int reg); +int aarch64_gdb_set_fpu_reg(CPUARMState *env, uint8_t *buf, int reg); void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp); void arm_cpu_sme_finalize(ARMCPU *cpu, Error **errp); void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp); diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub.c +++ b/target/arm/gdbstub.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu) */ #ifdef TARGET_AARCH64 if (isar_feature_aa64_sve(&cpu->isar)) { - gdb_register_coprocessor(cs, arm_gdb_get_svereg, arm_gdb_set_svereg, - arm_gen_dynamic_svereg_xml(cs, cs->gdb_num_regs), + int nreg = arm_gen_dynamic_svereg_xml(cs, cs->gdb_num_regs); + gdb_register_coprocessor(cs, aarch64_gdb_get_sve_reg, + aarch64_gdb_set_sve_reg, nreg, "sve-registers.xml", 0); } else { - gdb_register_coprocessor(cs, aarch64_fpu_gdb_get_reg, - aarch64_fpu_gdb_set_reg, + gdb_register_coprocessor(cs, aarch64_gdb_get_fpu_reg, + aarch64_gdb_set_fpu_reg, 34, "aarch64-fpu.xml", 0); } #endif diff --git a/target/arm/gdbstub64.c b/target/arm/gdbstub64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub64.c +++ b/target/arm/gdbstub64.c @@ -XXX,XX +XXX,XX @@ int aarch64_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n) return 0; } -int aarch64_fpu_gdb_get_reg(CPUARMState *env, GByteArray *buf, int reg) +int aarch64_gdb_get_fpu_reg(CPUARMState *env, GByteArray *buf, int reg) { switch (reg) { case 0 ... 31: @@ -XXX,XX +XXX,XX @@ int aarch64_fpu_gdb_get_reg(CPUARMState *env, GByteArray *buf, int reg) } } -int aarch64_fpu_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg) +int aarch64_gdb_set_fpu_reg(CPUARMState *env, uint8_t *buf, int reg) { switch (reg) { case 0 ... 31: @@ -XXX,XX +XXX,XX @@ int aarch64_fpu_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg) } } -int arm_gdb_get_svereg(CPUARMState *env, GByteArray *buf, int reg) +int aarch64_gdb_get_sve_reg(CPUARMState *env, GByteArray *buf, int reg) { ARMCPU *cpu = env_archcpu(env); @@ -XXX,XX +XXX,XX @@ int arm_gdb_get_svereg(CPUARMState *env, GByteArray *buf, int reg) return 0; } -int arm_gdb_set_svereg(CPUARMState *env, uint8_t *buf, int reg) +int aarch64_gdb_set_sve_reg(CPUARMState *env, uint8_t *buf, int reg) { ARMCPU *cpu = env_archcpu(env); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> This function is not used outside gdbstub.c. Reviewed-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 1 - target/arm/gdbstub.c | 2 +- 2 files changed, 1 insertion(+), 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 @@ int arm_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); * Helpers to dynamically generates XML descriptions of the sysregs * and SVE registers. Returns the number of registers in each set. */ -int arm_gen_dynamic_sysreg_xml(CPUState *cpu, int base_reg); int arm_gen_dynamic_svereg_xml(CPUState *cpu, int base_reg); /* Returns the dynamically generated XML for the gdb stub. diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub.c +++ b/target/arm/gdbstub.c @@ -XXX,XX +XXX,XX @@ static void arm_register_sysreg_for_xml(gpointer key, gpointer value, } } -int arm_gen_dynamic_sysreg_xml(CPUState *cs, int base_reg) +static int arm_gen_dynamic_sysreg_xml(CPUState *cs, int base_reg) { ARMCPU *cpu = ARM_CPU(cs); GString *s = g_string_new(NULL); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> The function is only used for aarch64, so move it to the file that has the other aarch64 gdbstub stuff. Move the declaration to internals.h. Reviewed-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 6 --- target/arm/internals.h | 1 + target/arm/gdbstub.c | 120 ----------------------------------------- target/arm/gdbstub64.c | 118 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 119 insertions(+), 126 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 @@ hwaddr arm_cpu_get_phys_page_attrs_debug(CPUState *cpu, vaddr addr, int arm_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); int arm_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); -/* - * Helpers to dynamically generates XML descriptions of the sysregs - * and SVE registers. Returns the number of registers in each set. - */ -int arm_gen_dynamic_svereg_xml(CPUState *cpu, int base_reg); - /* Returns the dynamically generated XML for the gdb stub. * Returns a pointer to the XML contents for the specified XML file or NULL * if the XML name doesn't match the predefined one. 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 uint64_t pmu_counter_mask(CPUARMState *env) } #ifdef TARGET_AARCH64 +int arm_gen_dynamic_svereg_xml(CPUState *cpu, int base_reg); int aarch64_gdb_get_sve_reg(CPUARMState *env, GByteArray *buf, int reg); int aarch64_gdb_set_sve_reg(CPUARMState *env, uint8_t *buf, int reg); int aarch64_gdb_get_fpu_reg(CPUARMState *env, GByteArray *buf, int reg); diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub.c +++ b/target/arm/gdbstub.c @@ -XXX,XX +XXX,XX @@ static int arm_gen_dynamic_sysreg_xml(CPUState *cs, int base_reg) return cpu->dyn_sysreg_xml.num; } -struct TypeSize { - const char *gdb_type; - int size; - const char sz, suffix; -}; - -static const struct TypeSize vec_lanes[] = { - /* quads */ - { "uint128", 128, 'q', 'u' }, - { "int128", 128, 'q', 's' }, - /* 64 bit */ - { "ieee_double", 64, 'd', 'f' }, - { "uint64", 64, 'd', 'u' }, - { "int64", 64, 'd', 's' }, - /* 32 bit */ - { "ieee_single", 32, 's', 'f' }, - { "uint32", 32, 's', 'u' }, - { "int32", 32, 's', 's' }, - /* 16 bit */ - { "ieee_half", 16, 'h', 'f' }, - { "uint16", 16, 'h', 'u' }, - { "int16", 16, 'h', 's' }, - /* bytes */ - { "uint8", 8, 'b', 'u' }, - { "int8", 8, 'b', 's' }, -}; - - -int arm_gen_dynamic_svereg_xml(CPUState *cs, int base_reg) -{ - ARMCPU *cpu = ARM_CPU(cs); - GString *s = g_string_new(NULL); - DynamicGDBXMLInfo *info = &cpu->dyn_svereg_xml; - g_autoptr(GString) ts = g_string_new(""); - int i, j, bits, reg_width = (cpu->sve_max_vq * 128); - info->num = 0; - g_string_printf(s, "<?xml version=\"1.0\"?>"); - g_string_append_printf(s, "<!DOCTYPE target SYSTEM \"gdb-target.dtd\">"); - g_string_append_printf(s, "<feature name=\"org.gnu.gdb.aarch64.sve\">"); - - /* First define types and totals in a whole VL */ - for (i = 0; i < ARRAY_SIZE(vec_lanes); i++) { - int count = reg_width / vec_lanes[i].size; - g_string_printf(ts, "svev%c%c", vec_lanes[i].sz, vec_lanes[i].suffix); - g_string_append_printf(s, - "<vector id=\"%s\" type=\"%s\" count=\"%d\"/>", - ts->str, vec_lanes[i].gdb_type, count); - } - /* - * Now define a union for each size group containing unsigned and - * signed and potentially float versions of each size from 128 to - * 8 bits. - */ - for (bits = 128, i = 0; bits >= 8; bits /= 2, i++) { - const char suf[] = { 'q', 'd', 's', 'h', 'b' }; - g_string_append_printf(s, "<union id=\"svevn%c\">", suf[i]); - for (j = 0; j < ARRAY_SIZE(vec_lanes); j++) { - if (vec_lanes[j].size == bits) { - g_string_append_printf(s, "<field name=\"%c\" type=\"svev%c%c\"/>", - vec_lanes[j].suffix, - vec_lanes[j].sz, vec_lanes[j].suffix); - } - } - g_string_append(s, "</union>"); - } - /* And now the final union of unions */ - g_string_append(s, "<union id=\"svev\">"); - for (bits = 128, i = 0; bits >= 8; bits /= 2, i++) { - const char suf[] = { 'q', 'd', 's', 'h', 'b' }; - g_string_append_printf(s, "<field name=\"%c\" type=\"svevn%c\"/>", - suf[i], suf[i]); - } - g_string_append(s, "</union>"); - - /* Finally the sve prefix type */ - g_string_append_printf(s, - "<vector id=\"svep\" type=\"uint8\" count=\"%d\"/>", - reg_width / 8); - - /* Then define each register in parts for each vq */ - for (i = 0; i < 32; i++) { - g_string_append_printf(s, - "<reg name=\"z%d\" bitsize=\"%d\"" - " regnum=\"%d\" type=\"svev\"/>", - i, reg_width, base_reg++); - info->num++; - } - /* fpscr & status registers */ - g_string_append_printf(s, "<reg name=\"fpsr\" bitsize=\"32\"" - " regnum=\"%d\" group=\"float\"" - " type=\"int\"/>", base_reg++); - g_string_append_printf(s, "<reg name=\"fpcr\" bitsize=\"32\"" - " regnum=\"%d\" group=\"float\"" - " type=\"int\"/>", base_reg++); - info->num += 2; - - for (i = 0; i < 16; i++) { - g_string_append_printf(s, - "<reg name=\"p%d\" bitsize=\"%d\"" - " regnum=\"%d\" type=\"svep\"/>", - i, cpu->sve_max_vq * 16, base_reg++); - info->num++; - } - g_string_append_printf(s, - "<reg name=\"ffr\" bitsize=\"%d\"" - " regnum=\"%d\" group=\"vector\"" - " type=\"svep\"/>", - cpu->sve_max_vq * 16, base_reg++); - g_string_append_printf(s, - "<reg name=\"vg\" bitsize=\"64\"" - " regnum=\"%d\" type=\"int\"/>", - base_reg++); - info->num += 2; - g_string_append_printf(s, "</feature>"); - cpu->dyn_svereg_xml.desc = g_string_free(s, false); - - return cpu->dyn_svereg_xml.num; -} - - const char *arm_gdb_get_dynamic_xml(CPUState *cs, const char *xmlname) { ARMCPU *cpu = ARM_CPU(cs); diff --git a/target/arm/gdbstub64.c b/target/arm/gdbstub64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub64.c +++ b/target/arm/gdbstub64.c @@ -XXX,XX +XXX,XX @@ int aarch64_gdb_set_sve_reg(CPUARMState *env, uint8_t *buf, int reg) return 0; } + +struct TypeSize { + const char *gdb_type; + short size; + char sz, suffix; +}; + +static const struct TypeSize vec_lanes[] = { + /* quads */ + { "uint128", 128, 'q', 'u' }, + { "int128", 128, 'q', 's' }, + /* 64 bit */ + { "ieee_double", 64, 'd', 'f' }, + { "uint64", 64, 'd', 'u' }, + { "int64", 64, 'd', 's' }, + /* 32 bit */ + { "ieee_single", 32, 's', 'f' }, + { "uint32", 32, 's', 'u' }, + { "int32", 32, 's', 's' }, + /* 16 bit */ + { "ieee_half", 16, 'h', 'f' }, + { "uint16", 16, 'h', 'u' }, + { "int16", 16, 'h', 's' }, + /* bytes */ + { "uint8", 8, 'b', 'u' }, + { "int8", 8, 'b', 's' }, +}; + +int arm_gen_dynamic_svereg_xml(CPUState *cs, int base_reg) +{ + ARMCPU *cpu = ARM_CPU(cs); + GString *s = g_string_new(NULL); + DynamicGDBXMLInfo *info = &cpu->dyn_svereg_xml; + g_autoptr(GString) ts = g_string_new(""); + int i, j, bits, reg_width = (cpu->sve_max_vq * 128); + info->num = 0; + g_string_printf(s, "<?xml version=\"1.0\"?>"); + g_string_append_printf(s, "<!DOCTYPE target SYSTEM \"gdb-target.dtd\">"); + g_string_append_printf(s, "<feature name=\"org.gnu.gdb.aarch64.sve\">"); + + /* First define types and totals in a whole VL */ + for (i = 0; i < ARRAY_SIZE(vec_lanes); i++) { + int count = reg_width / vec_lanes[i].size; + g_string_printf(ts, "svev%c%c", vec_lanes[i].sz, vec_lanes[i].suffix); + g_string_append_printf(s, + "<vector id=\"%s\" type=\"%s\" count=\"%d\"/>", + ts->str, vec_lanes[i].gdb_type, count); + } + /* + * Now define a union for each size group containing unsigned and + * signed and potentially float versions of each size from 128 to + * 8 bits. + */ + for (bits = 128, i = 0; bits >= 8; bits /= 2, i++) { + const char suf[] = { 'q', 'd', 's', 'h', 'b' }; + g_string_append_printf(s, "<union id=\"svevn%c\">", suf[i]); + for (j = 0; j < ARRAY_SIZE(vec_lanes); j++) { + if (vec_lanes[j].size == bits) { + g_string_append_printf(s, "<field name=\"%c\" type=\"svev%c%c\"/>", + vec_lanes[j].suffix, + vec_lanes[j].sz, vec_lanes[j].suffix); + } + } + g_string_append(s, "</union>"); + } + /* And now the final union of unions */ + g_string_append(s, "<union id=\"svev\">"); + for (bits = 128, i = 0; bits >= 8; bits /= 2, i++) { + const char suf[] = { 'q', 'd', 's', 'h', 'b' }; + g_string_append_printf(s, "<field name=\"%c\" type=\"svevn%c\"/>", + suf[i], suf[i]); + } + g_string_append(s, "</union>"); + + /* Finally the sve prefix type */ + g_string_append_printf(s, + "<vector id=\"svep\" type=\"uint8\" count=\"%d\"/>", + reg_width / 8); + + /* Then define each register in parts for each vq */ + for (i = 0; i < 32; i++) { + g_string_append_printf(s, + "<reg name=\"z%d\" bitsize=\"%d\"" + " regnum=\"%d\" type=\"svev\"/>", + i, reg_width, base_reg++); + info->num++; + } + /* fpscr & status registers */ + g_string_append_printf(s, "<reg name=\"fpsr\" bitsize=\"32\"" + " regnum=\"%d\" group=\"float\"" + " type=\"int\"/>", base_reg++); + g_string_append_printf(s, "<reg name=\"fpcr\" bitsize=\"32\"" + " regnum=\"%d\" group=\"float\"" + " type=\"int\"/>", base_reg++); + info->num += 2; + + for (i = 0; i < 16; i++) { + g_string_append_printf(s, + "<reg name=\"p%d\" bitsize=\"%d\"" + " regnum=\"%d\" type=\"svep\"/>", + i, cpu->sve_max_vq * 16, base_reg++); + info->num++; + } + g_string_append_printf(s, + "<reg name=\"ffr\" bitsize=\"%d\"" + " regnum=\"%d\" group=\"vector\"" + " type=\"svep\"/>", + cpu->sve_max_vq * 16, base_reg++); + g_string_append_printf(s, + "<reg name=\"vg\" bitsize=\"64\"" + " regnum=\"%d\" type=\"int\"/>", + base_reg++); + info->num += 2; + g_string_append_printf(s, "</feature>"); + info->desc = g_string_free(s, false); + + return info->num; +} -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Create a subroutine for creating the union of unions of the various type sizes that a vector may contain. Reviewed-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/gdbstub64.c | 83 +++++++++++++++++++++++------------------- 1 file changed, 45 insertions(+), 38 deletions(-) diff --git a/target/arm/gdbstub64.c b/target/arm/gdbstub64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub64.c +++ b/target/arm/gdbstub64.c @@ -XXX,XX +XXX,XX @@ int aarch64_gdb_set_sve_reg(CPUARMState *env, uint8_t *buf, int reg) return 0; } -struct TypeSize { - const char *gdb_type; - short size; - char sz, suffix; -}; - -static const struct TypeSize vec_lanes[] = { - /* quads */ - { "uint128", 128, 'q', 'u' }, - { "int128", 128, 'q', 's' }, - /* 64 bit */ - { "ieee_double", 64, 'd', 'f' }, - { "uint64", 64, 'd', 'u' }, - { "int64", 64, 'd', 's' }, - /* 32 bit */ - { "ieee_single", 32, 's', 'f' }, - { "uint32", 32, 's', 'u' }, - { "int32", 32, 's', 's' }, - /* 16 bit */ - { "ieee_half", 16, 'h', 'f' }, - { "uint16", 16, 'h', 'u' }, - { "int16", 16, 'h', 's' }, - /* bytes */ - { "uint8", 8, 'b', 'u' }, - { "int8", 8, 'b', 's' }, -}; - -int arm_gen_dynamic_svereg_xml(CPUState *cs, int base_reg) +static void output_vector_union_type(GString *s, int reg_width) { - ARMCPU *cpu = ARM_CPU(cs); - GString *s = g_string_new(NULL); - DynamicGDBXMLInfo *info = &cpu->dyn_svereg_xml; + struct TypeSize { + const char *gdb_type; + short size; + char sz, suffix; + }; + + static const struct TypeSize vec_lanes[] = { + /* quads */ + { "uint128", 128, 'q', 'u' }, + { "int128", 128, 'q', 's' }, + /* 64 bit */ + { "ieee_double", 64, 'd', 'f' }, + { "uint64", 64, 'd', 'u' }, + { "int64", 64, 'd', 's' }, + /* 32 bit */ + { "ieee_single", 32, 's', 'f' }, + { "uint32", 32, 's', 'u' }, + { "int32", 32, 's', 's' }, + /* 16 bit */ + { "ieee_half", 16, 'h', 'f' }, + { "uint16", 16, 'h', 'u' }, + { "int16", 16, 'h', 's' }, + /* bytes */ + { "uint8", 8, 'b', 'u' }, + { "int8", 8, 'b', 's' }, + }; + + static const char suf[] = { 'q', 'd', 's', 'h', 'b' }; + g_autoptr(GString) ts = g_string_new(""); - int i, j, bits, reg_width = (cpu->sve_max_vq * 128); - info->num = 0; - g_string_printf(s, "<?xml version=\"1.0\"?>"); - g_string_append_printf(s, "<!DOCTYPE target SYSTEM \"gdb-target.dtd\">"); - g_string_append_printf(s, "<feature name=\"org.gnu.gdb.aarch64.sve\">"); + int i, j, bits; /* First define types and totals in a whole VL */ for (i = 0; i < ARRAY_SIZE(vec_lanes); i++) { @@ -XXX,XX +XXX,XX @@ int arm_gen_dynamic_svereg_xml(CPUState *cs, int base_reg) * 8 bits. */ for (bits = 128, i = 0; bits >= 8; bits /= 2, i++) { - const char suf[] = { 'q', 'd', 's', 'h', 'b' }; g_string_append_printf(s, "<union id=\"svevn%c\">", suf[i]); for (j = 0; j < ARRAY_SIZE(vec_lanes); j++) { if (vec_lanes[j].size == bits) { @@ -XXX,XX +XXX,XX @@ int arm_gen_dynamic_svereg_xml(CPUState *cs, int base_reg) /* And now the final union of unions */ g_string_append(s, "<union id=\"svev\">"); for (bits = 128, i = 0; bits >= 8; bits /= 2, i++) { - const char suf[] = { 'q', 'd', 's', 'h', 'b' }; g_string_append_printf(s, "<field name=\"%c\" type=\"svevn%c\"/>", suf[i], suf[i]); } g_string_append(s, "</union>"); +} + +int arm_gen_dynamic_svereg_xml(CPUState *cs, int base_reg) +{ + ARMCPU *cpu = ARM_CPU(cs); + GString *s = g_string_new(NULL); + DynamicGDBXMLInfo *info = &cpu->dyn_svereg_xml; + int i, reg_width = (cpu->sve_max_vq * 128); + info->num = 0; + g_string_printf(s, "<?xml version=\"1.0\"?>"); + g_string_append_printf(s, "<!DOCTYPE target SYSTEM \"gdb-target.dtd\">"); + g_string_append_printf(s, "<feature name=\"org.gnu.gdb.aarch64.sve\">"); + + output_vector_union_type(s, reg_width); /* Finally the sve prefix type */ g_string_append_printf(s, -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Rather than increment base_reg and num, compute num from the change to base_reg at the end. Clean up some nearby comments. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/gdbstub64.c | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) diff --git a/target/arm/gdbstub64.c b/target/arm/gdbstub64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub64.c +++ b/target/arm/gdbstub64.c @@ -XXX,XX +XXX,XX @@ static void output_vector_union_type(GString *s, int reg_width) g_string_append(s, "</union>"); } -int arm_gen_dynamic_svereg_xml(CPUState *cs, int base_reg) +int arm_gen_dynamic_svereg_xml(CPUState *cs, int orig_base_reg) { ARMCPU *cpu = ARM_CPU(cs); GString *s = g_string_new(NULL); DynamicGDBXMLInfo *info = &cpu->dyn_svereg_xml; - int i, reg_width = (cpu->sve_max_vq * 128); - info->num = 0; + int reg_width = cpu->sve_max_vq * 128; + int base_reg = orig_base_reg; + int i; + g_string_printf(s, "<?xml version=\"1.0\"?>"); g_string_append_printf(s, "<!DOCTYPE target SYSTEM \"gdb-target.dtd\">"); g_string_append_printf(s, "<feature name=\"org.gnu.gdb.aarch64.sve\">"); + /* Create the vector union type. */ output_vector_union_type(s, reg_width); - /* Finally the sve prefix type */ + /* Create the predicate vector type. */ g_string_append_printf(s, "<vector id=\"svep\" type=\"uint8\" count=\"%d\"/>", reg_width / 8); - /* Then define each register in parts for each vq */ + /* Define the vector registers. */ for (i = 0; i < 32; i++) { g_string_append_printf(s, "<reg name=\"z%d\" bitsize=\"%d\"" " regnum=\"%d\" type=\"svev\"/>", i, reg_width, base_reg++); - info->num++; } + /* fpscr & status registers */ g_string_append_printf(s, "<reg name=\"fpsr\" bitsize=\"32\"" " regnum=\"%d\" group=\"float\"" @@ -XXX,XX +XXX,XX @@ int arm_gen_dynamic_svereg_xml(CPUState *cs, int base_reg) g_string_append_printf(s, "<reg name=\"fpcr\" bitsize=\"32\"" " regnum=\"%d\" group=\"float\"" " type=\"int\"/>", base_reg++); - info->num += 2; + /* Define the predicate registers. */ for (i = 0; i < 16; i++) { g_string_append_printf(s, "<reg name=\"p%d\" bitsize=\"%d\"" " regnum=\"%d\" type=\"svep\"/>", i, cpu->sve_max_vq * 16, base_reg++); - info->num++; } g_string_append_printf(s, "<reg name=\"ffr\" bitsize=\"%d\"" " regnum=\"%d\" group=\"vector\"" " type=\"svep\"/>", cpu->sve_max_vq * 16, base_reg++); + + /* Define the vector length pseudo-register. */ g_string_append_printf(s, "<reg name=\"vg\" bitsize=\"64\"" " regnum=\"%d\" type=\"int\"/>", base_reg++); - info->num += 2; - g_string_append_printf(s, "</feature>"); - info->desc = g_string_free(s, false); + g_string_append_printf(s, "</feature>"); + + info->desc = g_string_free(s, false); + info->num = base_reg - orig_base_reg; return info->num; } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/gdbstub64.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/target/arm/gdbstub64.c b/target/arm/gdbstub64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub64.c +++ b/target/arm/gdbstub64.c @@ -XXX,XX +XXX,XX @@ int arm_gen_dynamic_svereg_xml(CPUState *cs, int orig_base_reg) GString *s = g_string_new(NULL); DynamicGDBXMLInfo *info = &cpu->dyn_svereg_xml; int reg_width = cpu->sve_max_vq * 128; + int pred_width = cpu->sve_max_vq * 16; int base_reg = orig_base_reg; int i; @@ -XXX,XX +XXX,XX @@ int arm_gen_dynamic_svereg_xml(CPUState *cs, int orig_base_reg) g_string_append_printf(s, "<reg name=\"p%d\" bitsize=\"%d\"" " regnum=\"%d\" type=\"svep\"/>", - i, cpu->sve_max_vq * 16, base_reg++); + i, pred_width, base_reg++); } g_string_append_printf(s, "<reg name=\"ffr\" bitsize=\"%d\"" " regnum=\"%d\" group=\"vector\"" " type=\"svep\"/>", - cpu->sve_max_vq * 16, base_reg++); + pred_width, base_reg++); /* Define the vector length pseudo-register. */ g_string_append_printf(s, -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Define svep based on the size of the predicates, not the primary vector registers. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/gdbstub64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/gdbstub64.c b/target/arm/gdbstub64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub64.c +++ b/target/arm/gdbstub64.c @@ -XXX,XX +XXX,XX @@ int arm_gen_dynamic_svereg_xml(CPUState *cs, int orig_base_reg) /* Create the predicate vector type. */ g_string_append_printf(s, "<vector id=\"svep\" type=\"uint8\" count=\"%d\"/>", - reg_width / 8); + pred_width / 8); /* Define the vector registers. */ for (i = 0; i < 32; i++) { -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> This will make the function usable between SVE and SME. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/gdbstub64.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/target/arm/gdbstub64.c b/target/arm/gdbstub64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub64.c +++ b/target/arm/gdbstub64.c @@ -XXX,XX +XXX,XX @@ int aarch64_gdb_set_sve_reg(CPUARMState *env, uint8_t *buf, int reg) return 0; } -static void output_vector_union_type(GString *s, int reg_width) +static void output_vector_union_type(GString *s, int reg_width, + const char *name) { struct TypeSize { const char *gdb_type; @@ -XXX,XX +XXX,XX @@ static void output_vector_union_type(GString *s, int reg_width) }; static const char suf[] = { 'q', 'd', 's', 'h', 'b' }; - - g_autoptr(GString) ts = g_string_new(""); int i, j, bits; /* First define types and totals in a whole VL */ for (i = 0; i < ARRAY_SIZE(vec_lanes); i++) { - int count = reg_width / vec_lanes[i].size; - g_string_printf(ts, "svev%c%c", vec_lanes[i].sz, vec_lanes[i].suffix); g_string_append_printf(s, - "<vector id=\"%s\" type=\"%s\" count=\"%d\"/>", - ts->str, vec_lanes[i].gdb_type, count); + "<vector id=\"%s%c%c\" type=\"%s\" count=\"%d\"/>", + name, vec_lanes[i].sz, vec_lanes[i].suffix, + vec_lanes[i].gdb_type, reg_width / vec_lanes[i].size); } + /* * Now define a union for each size group containing unsigned and * signed and potentially float versions of each size from 128 to * 8 bits. */ for (bits = 128, i = 0; bits >= 8; bits /= 2, i++) { - g_string_append_printf(s, "<union id=\"svevn%c\">", suf[i]); + g_string_append_printf(s, "<union id=\"%sn%c\">", name, suf[i]); for (j = 0; j < ARRAY_SIZE(vec_lanes); j++) { if (vec_lanes[j].size == bits) { - g_string_append_printf(s, "<field name=\"%c\" type=\"svev%c%c\"/>", - vec_lanes[j].suffix, + g_string_append_printf(s, "<field name=\"%c\" type=\"%s%c%c\"/>", + vec_lanes[j].suffix, name, vec_lanes[j].sz, vec_lanes[j].suffix); } } g_string_append(s, "</union>"); } + /* And now the final union of unions */ - g_string_append(s, "<union id=\"svev\">"); + g_string_append_printf(s, "<union id=\"%s\">", name); for (bits = 128, i = 0; bits >= 8; bits /= 2, i++) { - g_string_append_printf(s, "<field name=\"%c\" type=\"svevn%c\"/>", - suf[i], suf[i]); + g_string_append_printf(s, "<field name=\"%c\" type=\"%sn%c\"/>", + suf[i], name, suf[i]); } g_string_append(s, "</union>"); } @@ -XXX,XX +XXX,XX @@ int arm_gen_dynamic_svereg_xml(CPUState *cs, int orig_base_reg) g_string_append_printf(s, "<feature name=\"org.gnu.gdb.aarch64.sve\">"); /* Create the vector union type. */ - output_vector_union_type(s, reg_width); + output_vector_union_type(s, reg_width, "svev"); /* Create the predicate vector type. */ g_string_append_printf(s, -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Order suf[] by the log8 of the width. Use ARRAY_SIZE instead of hard-coding 128. This changes the order of the union definitions, but retains the order of the union-of-union members. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/gdbstub64.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/target/arm/gdbstub64.c b/target/arm/gdbstub64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub64.c +++ b/target/arm/gdbstub64.c @@ -XXX,XX +XXX,XX @@ static void output_vector_union_type(GString *s, int reg_width, { "int8", 8, 'b', 's' }, }; - static const char suf[] = { 'q', 'd', 's', 'h', 'b' }; - int i, j, bits; + static const char suf[] = { 'b', 'h', 's', 'd', 'q' }; + int i, j; /* First define types and totals in a whole VL */ for (i = 0; i < ARRAY_SIZE(vec_lanes); i++) { @@ -XXX,XX +XXX,XX @@ static void output_vector_union_type(GString *s, int reg_width, * signed and potentially float versions of each size from 128 to * 8 bits. */ - for (bits = 128, i = 0; bits >= 8; bits /= 2, i++) { + for (i = 0; i < ARRAY_SIZE(suf); i++) { + int bits = 8 << i; + g_string_append_printf(s, "<union id=\"%sn%c\">", name, suf[i]); for (j = 0; j < ARRAY_SIZE(vec_lanes); j++) { if (vec_lanes[j].size == bits) { @@ -XXX,XX +XXX,XX @@ static void output_vector_union_type(GString *s, int reg_width, /* And now the final union of unions */ g_string_append_printf(s, "<union id=\"%s\">", name); - for (bits = 128, i = 0; bits >= 8; bits /= 2, i++) { + for (i = ARRAY_SIZE(suf) - 1; i >= 0; i--) { g_string_append_printf(s, "<field name=\"%c\" type=\"%sn%c\"/>", suf[i], name, suf[i]); } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Keep the logic for pauth within pauth_helper.c, and expose a helper function for use with the gdbstub pac extension. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 10 ++++++++++ target/arm/tcg/pauth_helper.c | 26 ++++++++++++++++++++++---- 2 files changed, 32 insertions(+), 4 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 @@ int exception_target_el(CPUARMState *env); bool arm_singlestep_active(CPUARMState *env); bool arm_generate_debug_exceptions(CPUARMState *env); +/** + * pauth_ptr_mask: + * @env: cpu context + * @ptr: selects between TTBR0 and TTBR1 + * @data: selects between TBI and TBID + * + * Return a mask of the bits of @ptr that contain the authentication code. + */ +uint64_t pauth_ptr_mask(CPUARMState *env, uint64_t ptr, bool data); + /* Add the cpreg definitions for debug related system registers */ void define_debug_regs(ARMCPU *cpu); diff --git a/target/arm/tcg/pauth_helper.c b/target/arm/tcg/pauth_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/pauth_helper.c +++ b/target/arm/tcg/pauth_helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t pauth_addpac(CPUARMState *env, uint64_t ptr, uint64_t modifier, return pac | ext | ptr; } -static uint64_t pauth_original_ptr(uint64_t ptr, ARMVAParameters param) +static uint64_t pauth_ptr_mask_internal(ARMVAParameters param) { - /* Note that bit 55 is used whether or not the regime has 2 ranges. */ - uint64_t extfield = sextract64(ptr, 55, 1); int bot_pac_bit = 64 - param.tsz; int top_pac_bit = 64 - 8 * param.tbi; - return deposit64(ptr, bot_pac_bit, top_pac_bit - bot_pac_bit, extfield); + return MAKE_64BIT_MASK(bot_pac_bit, top_pac_bit - bot_pac_bit); +} + +static uint64_t pauth_original_ptr(uint64_t ptr, ARMVAParameters param) +{ + uint64_t mask = pauth_ptr_mask_internal(param); + + /* Note that bit 55 is used whether or not the regime has 2 ranges. */ + if (extract64(ptr, 55, 1)) { + return ptr | mask; + } else { + return ptr & ~mask; + } +} + +uint64_t pauth_ptr_mask(CPUARMState *env, uint64_t ptr, bool data) +{ + ARMMMUIdx mmu_idx = arm_stage1_mmu_idx(env); + ARMVAParameters param = aa64_va_parameters(env, ptr, mmu_idx, data); + + return pauth_ptr_mask_internal(param); } static uint64_t pauth_auth(CPUARMState *env, uint64_t ptr, uint64_t modifier, -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> The extension is primarily defined by the Linux kernel NT_ARM_PAC_MASK ptrace register set. The original gdb feature consists of two masks, data and code, which are used to mask out the authentication code within a pointer. Following discussion with Luis Machado, add two more masks in order to support pointers within the high half of the address space (i.e. TTBR1 vs TTBR0). Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1105 Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- configs/targets/aarch64-linux-user.mak | 2 +- configs/targets/aarch64-softmmu.mak | 2 +- configs/targets/aarch64_be-linux-user.mak | 2 +- target/arm/internals.h | 2 ++ target/arm/gdbstub.c | 5 ++++ target/arm/gdbstub64.c | 34 +++++++++++++++++++++++ gdb-xml/aarch64-pauth.xml | 15 ++++++++++ 7 files changed, 59 insertions(+), 3 deletions(-) create mode 100644 gdb-xml/aarch64-pauth.xml diff --git a/configs/targets/aarch64-linux-user.mak b/configs/targets/aarch64-linux-user.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/targets/aarch64-linux-user.mak +++ b/configs/targets/aarch64-linux-user.mak @@ -XXX,XX +XXX,XX @@ TARGET_ARCH=aarch64 TARGET_BASE_ARCH=arm -TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml +TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml gdb-xml/aarch64-pauth.xml TARGET_HAS_BFLT=y CONFIG_SEMIHOSTING=y CONFIG_ARM_COMPATIBLE_SEMIHOSTING=y diff --git a/configs/targets/aarch64-softmmu.mak b/configs/targets/aarch64-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/targets/aarch64-softmmu.mak +++ b/configs/targets/aarch64-softmmu.mak @@ -XXX,XX +XXX,XX @@ TARGET_ARCH=aarch64 TARGET_BASE_ARCH=arm TARGET_SUPPORTS_MTTCG=y -TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml gdb-xml/arm-core.xml gdb-xml/arm-vfp.xml gdb-xml/arm-vfp3.xml gdb-xml/arm-vfp-sysregs.xml gdb-xml/arm-neon.xml gdb-xml/arm-m-profile.xml gdb-xml/arm-m-profile-mve.xml +TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml gdb-xml/arm-core.xml gdb-xml/arm-vfp.xml gdb-xml/arm-vfp3.xml gdb-xml/arm-vfp-sysregs.xml gdb-xml/arm-neon.xml gdb-xml/arm-m-profile.xml gdb-xml/arm-m-profile-mve.xml gdb-xml/aarch64-pauth.xml TARGET_NEED_FDT=y diff --git a/configs/targets/aarch64_be-linux-user.mak b/configs/targets/aarch64_be-linux-user.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/targets/aarch64_be-linux-user.mak +++ b/configs/targets/aarch64_be-linux-user.mak @@ -XXX,XX +XXX,XX @@ TARGET_ARCH=aarch64 TARGET_BASE_ARCH=arm TARGET_BIG_ENDIAN=y -TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml +TARGET_XML_FILES= gdb-xml/aarch64-core.xml gdb-xml/aarch64-fpu.xml gdb-xml/aarch64-pauth.xml TARGET_HAS_BFLT=y CONFIG_SEMIHOSTING=y CONFIG_ARM_COMPATIBLE_SEMIHOSTING=y 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 @@ int aarch64_gdb_get_sve_reg(CPUARMState *env, GByteArray *buf, int reg); int aarch64_gdb_set_sve_reg(CPUARMState *env, uint8_t *buf, int reg); int aarch64_gdb_get_fpu_reg(CPUARMState *env, GByteArray *buf, int reg); int aarch64_gdb_set_fpu_reg(CPUARMState *env, uint8_t *buf, int reg); +int aarch64_gdb_get_pauth_reg(CPUARMState *env, GByteArray *buf, int reg); +int aarch64_gdb_set_pauth_reg(CPUARMState *env, uint8_t *buf, int reg); void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp); void arm_cpu_sme_finalize(ARMCPU *cpu, Error **errp); void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp); diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub.c +++ b/target/arm/gdbstub.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu) aarch64_gdb_set_fpu_reg, 34, "aarch64-fpu.xml", 0); } + if (isar_feature_aa64_pauth(&cpu->isar)) { + gdb_register_coprocessor(cs, aarch64_gdb_get_pauth_reg, + aarch64_gdb_set_pauth_reg, + 4, "aarch64-pauth.xml", 0); + } #endif } else { if (arm_feature(env, ARM_FEATURE_NEON)) { diff --git a/target/arm/gdbstub64.c b/target/arm/gdbstub64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub64.c +++ b/target/arm/gdbstub64.c @@ -XXX,XX +XXX,XX @@ int aarch64_gdb_set_sve_reg(CPUARMState *env, uint8_t *buf, int reg) return 0; } +int aarch64_gdb_get_pauth_reg(CPUARMState *env, GByteArray *buf, int reg) +{ + switch (reg) { + case 0: /* pauth_dmask */ + case 1: /* pauth_cmask */ + case 2: /* pauth_dmask_high */ + case 3: /* pauth_cmask_high */ + /* + * Note that older versions of this feature only contained + * pauth_{d,c}mask, for use with Linux user processes, and + * thus exclusively in the low half of the address space. + * + * To support system mode, and to debug kernels, two new regs + * were added to cover the high half of the address space. + * For the purpose of pauth_ptr_mask, we can use any well-formed + * address within the address space half -- here, 0 and -1. + */ + { + bool is_data = !(reg & 1); + bool is_high = reg & 2; + uint64_t mask = pauth_ptr_mask(env, -is_high, is_data); + return gdb_get_reg64(buf, mask); + } + default: + return 0; + } +} + +int aarch64_gdb_set_pauth_reg(CPUARMState *env, uint8_t *buf, int reg) +{ + /* All pseudo registers are read-only. */ + return 0; +} + static void output_vector_union_type(GString *s, int reg_width, const char *name) { diff --git a/gdb-xml/aarch64-pauth.xml b/gdb-xml/aarch64-pauth.xml new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/gdb-xml/aarch64-pauth.xml @@ -XXX,XX +XXX,XX @@ +<?xml version="1.0"?> +<!-- Copyright (C) 2018-2022 Free Software Foundation, Inc. + + Copying and distribution of this file, with or without modification, + are permitted in any medium without royalty provided the copyright + notice and this notice are preserved. --> + +<!DOCTYPE feature SYSTEM "gdb-target.dtd"> +<feature name="org.gnu.gdb.aarch64.pauth"> + <reg name="pauth_dmask" bitsize="64"/> + <reg name="pauth_cmask" bitsize="64"/> + <reg name="pauth_dmask_high" bitsize="64"/> + <reg name="pauth_cmask_high" bitsize="64"/> +</feature> + -- 2.34.1 From: David Reiss <dreiss@meta.com> Allow the function to be used outside of m_helper.c. Rename with an "arm_" prefix. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: David Reiss <dreiss@meta.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-13-richard.henderson@linaro.org [rth: Split out of a larger patch] Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 3 +++ target/arm/tcg/m_helper.c | 6 +++--- 2 files changed, 6 insertions(+), 3 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 @@ void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp); void arm_cpu_lpa2_finalize(ARMCPU *cpu, Error **errp); #endif +/* Read the CONTROL register as the MRS instruction would. */ +uint32_t arm_v7m_mrs_control(CPUARMState *env, uint32_t secure); + #ifdef CONFIG_USER_ONLY static inline void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu) { } #else diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t v7m_mrs_xpsr(CPUARMState *env, uint32_t reg, unsigned el) return xpsr_read(env) & mask; } -static uint32_t v7m_mrs_control(CPUARMState *env, uint32_t secure) +uint32_t arm_v7m_mrs_control(CPUARMState *env, uint32_t secure) { uint32_t value = env->v7m.control[secure]; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_mrs)(CPUARMState *env, uint32_t reg) case 0 ... 7: /* xPSR sub-fields */ return v7m_mrs_xpsr(env, reg, 0); case 20: /* CONTROL */ - return v7m_mrs_control(env, 0); + return arm_v7m_mrs_control(env, 0); default: /* Unprivileged reads others as zero. */ return 0; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_mrs)(CPUARMState *env, uint32_t reg) case 0 ... 7: /* xPSR sub-fields */ return v7m_mrs_xpsr(env, reg, el); case 20: /* CONTROL */ - return v7m_mrs_control(env, env->v7m.secure); + return arm_v7m_mrs_control(env, env->v7m.secure); case 0x94: /* CONTROL_NS */ /* * We have to handle this here because unprivileged Secure code -- 2.34.1 From: David Reiss <dreiss@meta.com> Allow the function to be used outside of m_helper.c. Move to be outside of ifndef CONFIG_USER_ONLY block. Rename from get_v7m_sp_ptr. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: David Reiss <dreiss@meta.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-14-richard.henderson@linaro.org [rth: Split out of a larger patch] Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 10 +++++ target/arm/tcg/m_helper.c | 84 +++++++++++++++++++-------------------- 2 files changed, 51 insertions(+), 43 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 @@ void arm_cpu_lpa2_finalize(ARMCPU *cpu, Error **errp); /* Read the CONTROL register as the MRS instruction would. */ uint32_t arm_v7m_mrs_control(CPUARMState *env, uint32_t secure); +/* + * Return a pointer to the location where we currently store the + * stack pointer for the requested security state and thread mode. + * This pointer will become invalid if the CPU state is updated + * such that the stack pointers are switched around (eg changing + * the SPSEL control bit). + */ +uint32_t *arm_v7m_get_sp_ptr(CPUARMState *env, bool secure, + bool threadmode, bool spsel); + #ifdef CONFIG_USER_ONLY static inline void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu) { } #else diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) arm_rebuild_hflags(env); } -static uint32_t *get_v7m_sp_ptr(CPUARMState *env, bool secure, bool threadmode, - bool spsel) -{ - /* - * Return a pointer to the location where we currently store the - * stack pointer for the requested security state and thread mode. - * This pointer will become invalid if the CPU state is updated - * such that the stack pointers are switched around (eg changing - * the SPSEL control bit). - * Compare the v8M ARM ARM pseudocode LookUpSP_with_security_mode(). - * Unlike that pseudocode, we require the caller to pass us in the - * SPSEL control bit value; this is because we also use this - * function in handling of pushing of the callee-saves registers - * part of the v8M stack frame (pseudocode PushCalleeStack()), - * and in the tailchain codepath the SPSEL bit comes from the exception - * return magic LR value from the previous exception. The pseudocode - * opencodes the stack-selection in PushCalleeStack(), but we prefer - * to make this utility function generic enough to do the job. - */ - bool want_psp = threadmode && spsel; - - if (secure == env->v7m.secure) { - if (want_psp == v7m_using_psp(env)) { - return &env->regs[13]; - } else { - return &env->v7m.other_sp; - } - } else { - if (want_psp) { - return &env->v7m.other_ss_psp; - } else { - return &env->v7m.other_ss_msp; - } - } -} - static bool arm_v7m_load_vector(ARMCPU *cpu, int exc, bool targets_secure, uint32_t *pvec) { @@ -XXX,XX +XXX,XX @@ static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain, !mode; mmu_idx = arm_v7m_mmu_idx_for_secstate_and_priv(env, M_REG_S, priv); - frame_sp_p = get_v7m_sp_ptr(env, M_REG_S, mode, - lr & R_V7M_EXCRET_SPSEL_MASK); + frame_sp_p = arm_v7m_get_sp_ptr(env, M_REG_S, mode, + lr & R_V7M_EXCRET_SPSEL_MASK); want_psp = mode && (lr & R_V7M_EXCRET_SPSEL_MASK); if (want_psp) { limit = env->v7m.psplim[M_REG_S]; @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) * use 'frame_sp_p' after we do something that makes it invalid. */ bool spsel = env->v7m.control[return_to_secure] & R_V7M_CONTROL_SPSEL_MASK; - uint32_t *frame_sp_p = get_v7m_sp_ptr(env, - return_to_secure, - !return_to_handler, - spsel); + uint32_t *frame_sp_p = arm_v7m_get_sp_ptr(env, return_to_secure, + !return_to_handler, spsel); uint32_t frameptr = *frame_sp_p; bool pop_ok = true; ARMMMUIdx mmu_idx; @@ -XXX,XX +XXX,XX @@ static bool do_v7m_function_return(ARMCPU *cpu) threadmode = !arm_v7m_is_handler_mode(env); spsel = env->v7m.control[M_REG_S] & R_V7M_CONTROL_SPSEL_MASK; - frame_sp_p = get_v7m_sp_ptr(env, true, threadmode, spsel); + frame_sp_p = arm_v7m_get_sp_ptr(env, true, threadmode, spsel); frameptr = *frame_sp_p; /* @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op) } #endif /* !CONFIG_USER_ONLY */ + +uint32_t *arm_v7m_get_sp_ptr(CPUARMState *env, bool secure, bool threadmode, + bool spsel) +{ + /* + * Return a pointer to the location where we currently store the + * stack pointer for the requested security state and thread mode. + * This pointer will become invalid if the CPU state is updated + * such that the stack pointers are switched around (eg changing + * the SPSEL control bit). + * Compare the v8M ARM ARM pseudocode LookUpSP_with_security_mode(). + * Unlike that pseudocode, we require the caller to pass us in the + * SPSEL control bit value; this is because we also use this + * function in handling of pushing of the callee-saves registers + * part of the v8M stack frame (pseudocode PushCalleeStack()), + * and in the tailchain codepath the SPSEL bit comes from the exception + * return magic LR value from the previous exception. The pseudocode + * opencodes the stack-selection in PushCalleeStack(), but we prefer + * to make this utility function generic enough to do the job. + */ + bool want_psp = threadmode && spsel; + + if (secure == env->v7m.secure) { + if (want_psp == v7m_using_psp(env)) { + return &env->regs[13]; + } else { + return &env->v7m.other_sp; + } + } else { + if (want_psp) { + return &env->v7m.other_ss_psp; + } else { + return &env->v7m.other_ss_msp; + } + } +} -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> The upstream gdb xml only implements {MSP,PSP}{,_NS,S}, but go ahead and implement the other system registers as well. Since there is significant overlap between the two, implement them with common code. The only exception is the systemreg view of CONTROL, which merges the banked bits as per MRS. Signed-off-by: David Reiss <dreiss@meta.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227213329.793795-15-richard.henderson@linaro.org [rth: Substatial rewrite using enumerator and shared code.] Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 + target/arm/gdbstub.c | 178 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 180 insertions(+) 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 { DynamicGDBXMLInfo dyn_sysreg_xml; DynamicGDBXMLInfo dyn_svereg_xml; + DynamicGDBXMLInfo dyn_m_systemreg_xml; + DynamicGDBXMLInfo dyn_m_secextreg_xml; /* Timers used by the generic (architected) timer */ QEMUTimer *gt_timer[NUM_GTIMERS]; diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub.c +++ b/target/arm/gdbstub.c @@ -XXX,XX +XXX,XX @@ static int arm_gen_dynamic_sysreg_xml(CPUState *cs, int base_reg) return cpu->dyn_sysreg_xml.num; } +typedef enum { + M_SYSREG_MSP, + M_SYSREG_PSP, + M_SYSREG_PRIMASK, + M_SYSREG_CONTROL, + M_SYSREG_BASEPRI, + M_SYSREG_FAULTMASK, + M_SYSREG_MSPLIM, + M_SYSREG_PSPLIM, +} MProfileSysreg; + +static const struct { + const char *name; + int feature; +} m_sysreg_def[] = { + [M_SYSREG_MSP] = { "msp", ARM_FEATURE_M }, + [M_SYSREG_PSP] = { "psp", ARM_FEATURE_M }, + [M_SYSREG_PRIMASK] = { "primask", ARM_FEATURE_M }, + [M_SYSREG_CONTROL] = { "control", ARM_FEATURE_M }, + [M_SYSREG_BASEPRI] = { "basepri", ARM_FEATURE_M_MAIN }, + [M_SYSREG_FAULTMASK] = { "faultmask", ARM_FEATURE_M_MAIN }, + [M_SYSREG_MSPLIM] = { "msplim", ARM_FEATURE_V8 }, + [M_SYSREG_PSPLIM] = { "psplim", ARM_FEATURE_V8 }, +}; + +static uint32_t *m_sysreg_ptr(CPUARMState *env, MProfileSysreg reg, bool sec) +{ + uint32_t *ptr; + + switch (reg) { + case M_SYSREG_MSP: + ptr = arm_v7m_get_sp_ptr(env, sec, false, true); + break; + case M_SYSREG_PSP: + ptr = arm_v7m_get_sp_ptr(env, sec, true, true); + break; + case M_SYSREG_MSPLIM: + ptr = &env->v7m.msplim[sec]; + break; + case M_SYSREG_PSPLIM: + ptr = &env->v7m.psplim[sec]; + break; + case M_SYSREG_PRIMASK: + ptr = &env->v7m.primask[sec]; + break; + case M_SYSREG_BASEPRI: + ptr = &env->v7m.basepri[sec]; + break; + case M_SYSREG_FAULTMASK: + ptr = &env->v7m.faultmask[sec]; + break; + case M_SYSREG_CONTROL: + ptr = &env->v7m.control[sec]; + break; + default: + return NULL; + } + return arm_feature(env, m_sysreg_def[reg].feature) ? ptr : NULL; +} + +static int m_sysreg_get(CPUARMState *env, GByteArray *buf, + MProfileSysreg reg, bool secure) +{ + uint32_t *ptr = m_sysreg_ptr(env, reg, secure); + + if (ptr == NULL) { + return 0; + } + return gdb_get_reg32(buf, *ptr); +} + +static int arm_gdb_get_m_systemreg(CPUARMState *env, GByteArray *buf, int reg) +{ + /* + * Here, we emulate MRS instruction, where CONTROL has a mix of + * banked and non-banked bits. + */ + if (reg == M_SYSREG_CONTROL) { + return gdb_get_reg32(buf, arm_v7m_mrs_control(env, env->v7m.secure)); + } + return m_sysreg_get(env, buf, reg, env->v7m.secure); +} + +static int arm_gdb_set_m_systemreg(CPUARMState *env, uint8_t *buf, int reg) +{ + return 0; /* TODO */ +} + +static int arm_gen_dynamic_m_systemreg_xml(CPUState *cs, int orig_base_reg) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + GString *s = g_string_new(NULL); + int base_reg = orig_base_reg; + int i; + + g_string_printf(s, "<?xml version=\"1.0\"?>"); + g_string_append_printf(s, "<!DOCTYPE target SYSTEM \"gdb-target.dtd\">"); + g_string_append_printf(s, "<feature name=\"org.gnu.gdb.arm.m-system\">\n"); + + for (i = 0; i < ARRAY_SIZE(m_sysreg_def); i++) { + if (arm_feature(env, m_sysreg_def[i].feature)) { + g_string_append_printf(s, + "<reg name=\"%s\" bitsize=\"32\" regnum=\"%d\"/>\n", + m_sysreg_def[i].name, base_reg++); + } + } + + g_string_append_printf(s, "</feature>"); + cpu->dyn_m_systemreg_xml.desc = g_string_free(s, false); + cpu->dyn_m_systemreg_xml.num = base_reg - orig_base_reg; + + return cpu->dyn_m_systemreg_xml.num; +} + +#ifndef CONFIG_USER_ONLY +/* + * For user-only, we see the non-secure registers via m_systemreg above. + * For secext, encode the non-secure view as even and secure view as odd. + */ +static int arm_gdb_get_m_secextreg(CPUARMState *env, GByteArray *buf, int reg) +{ + return m_sysreg_get(env, buf, reg >> 1, reg & 1); +} + +static int arm_gdb_set_m_secextreg(CPUARMState *env, uint8_t *buf, int reg) +{ + return 0; /* TODO */ +} + +static int arm_gen_dynamic_m_secextreg_xml(CPUState *cs, int orig_base_reg) +{ + ARMCPU *cpu = ARM_CPU(cs); + GString *s = g_string_new(NULL); + int base_reg = orig_base_reg; + int i; + + g_string_printf(s, "<?xml version=\"1.0\"?>"); + g_string_append_printf(s, "<!DOCTYPE target SYSTEM \"gdb-target.dtd\">"); + g_string_append_printf(s, "<feature name=\"org.gnu.gdb.arm.secext\">\n"); + + for (i = 0; i < ARRAY_SIZE(m_sysreg_def); i++) { + g_string_append_printf(s, + "<reg name=\"%s_ns\" bitsize=\"32\" regnum=\"%d\"/>\n", + m_sysreg_def[i].name, base_reg++); + g_string_append_printf(s, + "<reg name=\"%s_s\" bitsize=\"32\" regnum=\"%d\"/>\n", + m_sysreg_def[i].name, base_reg++); + } + + g_string_append_printf(s, "</feature>"); + cpu->dyn_m_secextreg_xml.desc = g_string_free(s, false); + cpu->dyn_m_secextreg_xml.num = base_reg - orig_base_reg; + + return cpu->dyn_m_secextreg_xml.num; +} +#endif + const char *arm_gdb_get_dynamic_xml(CPUState *cs, const char *xmlname) { ARMCPU *cpu = ARM_CPU(cs); @@ -XXX,XX +XXX,XX @@ const char *arm_gdb_get_dynamic_xml(CPUState *cs, const char *xmlname) return cpu->dyn_sysreg_xml.desc; } else if (strcmp(xmlname, "sve-registers.xml") == 0) { return cpu->dyn_svereg_xml.desc; + } else if (strcmp(xmlname, "arm-m-system.xml") == 0) { + return cpu->dyn_m_systemreg_xml.desc; +#ifndef CONFIG_USER_ONLY + } else if (strcmp(xmlname, "arm-m-secext.xml") == 0) { + return cpu->dyn_m_secextreg_xml.desc; +#endif } return NULL; } @@ -XXX,XX +XXX,XX @@ void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu) arm_gen_dynamic_sysreg_xml(cs, cs->gdb_num_regs), "system-registers.xml", 0); + if (arm_feature(env, ARM_FEATURE_M)) { + gdb_register_coprocessor(cs, + arm_gdb_get_m_systemreg, arm_gdb_set_m_systemreg, + arm_gen_dynamic_m_systemreg_xml(cs, cs->gdb_num_regs), + "arm-m-system.xml", 0); +#ifndef CONFIG_USER_ONLY + if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { + gdb_register_coprocessor(cs, + arm_gdb_get_m_secextreg, arm_gdb_set_m_secextreg, + arm_gen_dynamic_m_secextreg_xml(cs, cs->gdb_num_regs), + "arm-m-secext.xml", 0); + } +#endif + } } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1421 Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227225832.816605-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 3 +++ 1 file changed, 3 insertions(+) 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 @@ static inline bool arm_is_el3_or_mon(CPUARMState *env) /* Return true if the processor is in secure state */ static inline bool arm_is_secure(CPUARMState *env) { + if (arm_feature(env, ARM_FEATURE_M)) { + return env->v7m.secure; + } if (arm_is_el3_or_mon(env)) { return true; } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> M-profile doesn't have HCR_EL2. While we could test features before each call, zero is a generally safe return value to disable the code in the caller. This test is required to avoid an assert in arm_is_secure_below_el3. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227225832.816605-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 3 +++ 1 file changed, 3 insertions(+) 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 @@ uint64_t arm_hcr_el2_eff_secstate(CPUARMState *env, bool secure) uint64_t arm_hcr_el2_eff(CPUARMState *env) { + if (arm_feature(env, ARM_FEATURE_M)) { + return 0; + } return arm_hcr_el2_eff_secstate(env, arm_is_secure_below_el3(env)); } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> In several places we use arm_is_secure_below_el3 and arm_is_el3_or_mon separately from arm_is_secure. These functions make no sense for m-profile, and would indicate prior incorrect feature testing. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227225832.816605-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) 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 @@ static inline int arm_feature(CPUARMState *env, int feature) void arm_cpu_finalize_features(ARMCPU *cpu, Error **errp); #if !defined(CONFIG_USER_ONLY) -/* Return true if exception levels below EL3 are in secure state, +/* + * Return true if exception levels below EL3 are in secure state, * or would be following an exception return to that level. * Unlike arm_is_secure() (which is always a question about the * _current_ state of the CPU) this doesn't care about the current @@ -XXX,XX +XXX,XX @@ void arm_cpu_finalize_features(ARMCPU *cpu, Error **errp); */ static inline bool arm_is_secure_below_el3(CPUARMState *env) { + assert(!arm_feature(env, ARM_FEATURE_M)); if (arm_feature(env, ARM_FEATURE_EL3)) { return !(env->cp15.scr_el3 & SCR_NS); } else { @@ -XXX,XX +XXX,XX @@ static inline bool arm_is_secure_below_el3(CPUARMState *env) /* Return true if the CPU is AArch64 EL3 or AArch32 Mon */ static inline bool arm_is_el3_or_mon(CPUARMState *env) { + assert(!arm_feature(env, ARM_FEATURE_M)); if (arm_feature(env, ARM_FEATURE_EL3)) { if (is_a64(env) && extract32(env->pstate, 2, 2) == 3) { /* CPU currently in AArch64 state and EL3 */ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Integrate neighboring code from get_phys_addr_lpae which computed starting level, as it is easier to validate when doing both at the same time. Mirror the checks at the start of AArch{64,32}.S2Walk, especially S2InvalidSL and S2InconsistentSL. This reverts 49ba115bb74, which was incorrect -- there is nothing in the ARM pseudocode that depends on TxSZ, i.e. outputsize; the pseudocode is consistent in referencing PAMax. Fixes: 49ba115bb74 ("target/arm: Pass outputsize down to check_s2_mmu_setup") Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230227225832.816605-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/ptw.c | 173 ++++++++++++++++++++++++++--------------------- 1 file changed, 97 insertions(+), 76 deletions(-) diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va, * check_s2_mmu_setup * @cpu: ARMCPU * @is_aa64: True if the translation regime is in AArch64 state - * @startlevel: Suggested starting level - * @inputsize: Bitsize of IPAs + * @tcr: VTCR_EL2 or VSTCR_EL2 + * @ds: Effective value of TCR.DS. + * @iasize: Bitsize of IPAs * @stride: Page-table stride (See the ARM ARM) * - * Returns true if the suggested S2 translation parameters are OK and - * false otherwise. + * Decode the starting level of the S2 lookup, returning INT_MIN if + * the configuration is invalid. */ -static bool check_s2_mmu_setup(ARMCPU *cpu, bool is_aa64, int level, - int inputsize, int stride, int outputsize) +static int check_s2_mmu_setup(ARMCPU *cpu, bool is_aa64, uint64_t tcr, + bool ds, int iasize, int stride) { - const int grainsize = stride + 3; - int startsizecheck; - - /* - * Negative levels are usually not allowed... - * Except for FEAT_LPA2, 4k page table, 52-bit address space, which - * begins with level -1. Note that previous feature tests will have - * eliminated this combination if it is not enabled. - */ - if (level < (inputsize == 52 && stride == 9 ? -1 : 0)) { - return false; - } - - startsizecheck = inputsize - ((3 - level) * stride + grainsize); - if (startsizecheck < 1 || startsizecheck > stride + 4) { - return false; - } + int sl0, sl2, startlevel, granulebits, levels; + int s1_min_iasize, s1_max_iasize; + sl0 = extract32(tcr, 6, 2); if (is_aa64) { + /* + * AArch64.S2InvalidTxSZ: While we checked tsz_oob near the top of + * get_phys_addr_lpae, that used aa64_va_parameters which apply + * to aarch64. If Stage1 is aarch32, the min_txsz is larger. + * See AArch64.S2MinTxSZ, where min_tsz is 24, translated to + * inputsize is 64 - 24 = 40. + */ + if (iasize < 40 && !arm_el_is_aa64(&cpu->env, 1)) { + goto fail; + } + + /* + * AArch64.S2InvalidSL: Interpretation of SL depends on the page size, + * so interleave AArch64.S2StartLevel. + */ switch (stride) { - case 13: /* 64KB Pages. */ - if (level == 0 || (level == 1 && outputsize <= 42)) { - return false; + case 9: /* 4KB */ + /* SL2 is RES0 unless DS=1 & 4KB granule. */ + sl2 = extract64(tcr, 33, 1); + if (ds && sl2) { + if (sl0 != 0) { + goto fail; + } + startlevel = -1; + } else { + startlevel = 2 - sl0; + switch (sl0) { + case 2: + if (arm_pamax(cpu) < 44) { + goto fail; + } + break; + case 3: + if (!cpu_isar_feature(aa64_st, cpu)) { + goto fail; + } + startlevel = 3; + break; + } } break; - case 11: /* 16KB Pages. */ - if (level == 0 || (level == 1 && outputsize <= 40)) { - return false; + case 11: /* 16KB */ + switch (sl0) { + case 2: + if (arm_pamax(cpu) < 42) { + goto fail; + } + break; + case 3: + if (!ds) { + goto fail; + } + break; } + startlevel = 3 - sl0; break; - case 9: /* 4KB Pages. */ - if (level == 0 && outputsize <= 42) { - return false; + case 13: /* 64KB */ + switch (sl0) { + case 2: + if (arm_pamax(cpu) < 44) { + goto fail; + } + break; + case 3: + goto fail; } + startlevel = 3 - sl0; break; default: g_assert_not_reached(); } - - /* Inputsize checks. */ - if (inputsize > outputsize && - (arm_el_is_aa64(&cpu->env, 1) || inputsize > 40)) { - /* This is CONSTRAINED UNPREDICTABLE and we choose to fault. */ - return false; - } } else { - /* AArch32 only supports 4KB pages. Assert on that. */ + /* + * Things are simpler for AArch32 EL2, with only 4k pages. + * There is no separate S2InvalidSL function, but AArch32.S2Walk + * begins with walkparms.sl0 in {'1x'}. + */ assert(stride == 9); - - if (level == 0) { - return false; + if (sl0 >= 2) { + goto fail; } + startlevel = 2 - sl0; } - return true; + + /* AArch{64,32}.S2InconsistentSL are functionally equivalent. */ + levels = 3 - startlevel; + granulebits = stride + 3; + + s1_min_iasize = levels * stride + granulebits + 1; + s1_max_iasize = s1_min_iasize + (stride - 1) + 4; + + if (iasize >= s1_min_iasize && iasize <= s1_max_iasize) { + return startlevel; + } + + fail: + return INT_MIN; } /** @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, */ level = 4 - (inputsize - 4) / stride; } else { - /* - * For stage 2 translations the starting level is specified by the - * VTCR_EL2.SL0 field (whose interpretation depends on the page size) - */ - uint32_t sl0 = extract32(tcr, 6, 2); - uint32_t sl2 = extract64(tcr, 33, 1); - int32_t startlevel; - bool ok; - - /* SL2 is RES0 unless DS=1 & 4kb granule. */ - if (param.ds && stride == 9 && sl2) { - if (sl0 != 0) { - level = 0; - goto do_translation_fault; - } - startlevel = -1; - } else if (!aarch64 || stride == 9) { - /* AArch32 or 4KB pages */ - startlevel = 2 - sl0; - - if (cpu_isar_feature(aa64_st, cpu)) { - startlevel &= 3; - } - } else { - /* 16KB or 64KB pages */ - startlevel = 3 - sl0; - } - - /* Check that the starting level is valid. */ - ok = check_s2_mmu_setup(cpu, aarch64, startlevel, - inputsize, stride, outputsize); - if (!ok) { + int startlevel = check_s2_mmu_setup(cpu, aarch64, tcr, param.ds, + inputsize, stride); + if (startlevel == INT_MIN) { + level = 0; goto do_translation_fault; } level = startlevel; -- 2.34.1 From: Ard Biesheuvel <ardb@kernel.org> Fedora 39 will ship its arm64 kernels in the new generic EFI zboot format, using gzip compression for the payload. For doing EFI boot in QEMU, this is completely transparent, as the firmware or bootloader will take care of this. However, for direct kernel boot without firmware, we will lose the ability to boot such distro kernels unless we deal with the new format directly. EFI zboot images contain metadata in the header regarding the placement of the compressed payload inside the image, and the type of compression used. This means we can wire up the existing gzip support without too much hassle, by parsing the header and grabbing the payload from inside the loaded zboot image. Cc: Peter Maydell <peter.maydell@linaro.org> Cc: Alex Bennée <alex.bennee@linaro.org> Cc: Richard Henderson <richard.henderson@linaro.org> Cc: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Message-id: 20230303160109.3626966-1-ardb@kernel.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: tweaked comment formatting, fixed checkpatch nits] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/loader.h | 19 ++++++++++ hw/arm/boot.c | 6 +++ hw/core/loader.c | 91 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 116 insertions(+) diff --git a/include/hw/loader.h b/include/hw/loader.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/loader.h +++ b/include/hw/loader.h @@ -XXX,XX +XXX,XX @@ ssize_t load_image_gzipped_buffer(const char *filename, uint64_t max_sz, uint8_t **buffer); ssize_t load_image_gzipped(const char *filename, hwaddr addr, uint64_t max_sz); +/** + * unpack_efi_zboot_image: + * @buffer: pointer to a variable holding the address of a buffer containing the + * image + * @size: pointer to a variable holding the size of the buffer + * + * Check whether the buffer contains a EFI zboot image, and if it does, extract + * the compressed payload and decompress it into a new buffer. If successful, + * the old buffer is freed, and the *buffer and size variables pointed to by the + * function arguments are updated to refer to the newly populated buffer. + * + * Returns 0 if the image could not be identified as a EFI zboot image. + * Returns -1 if the buffer contents were identified as a EFI zboot image, but + * unpacking failed for any reason. + * Returns the size of the decompressed payload if decompression was performed + * successfully. + */ +ssize_t unpack_efi_zboot_image(uint8_t **buffer, int *size); + #define ELF_LOAD_FAILED -1 #define ELF_LOAD_NOT_ELF -2 #define ELF_LOAD_WRONG_ARCH -3 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 uint64_t load_aarch64_image(const char *filename, hwaddr mem_base, return -1; } size = len; + + /* Unpack the image if it is a EFI zboot image */ + if (unpack_efi_zboot_image(&buffer, &size) < 0) { + g_free(buffer); + return -1; + } } /* check the arm64 magic header value -- very old kernels may not have it */ diff --git a/hw/core/loader.c b/hw/core/loader.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/loader.c +++ b/hw/core/loader.c @@ -XXX,XX +XXX,XX @@ ssize_t load_image_gzipped(const char *filename, hwaddr addr, uint64_t max_sz) return bytes; } +/* The PE/COFF MS-DOS stub magic number */ +#define EFI_PE_MSDOS_MAGIC "MZ" + +/* + * The Linux header magic number for a EFI PE/COFF + * image targetting an unspecified architecture. + */ +#define EFI_PE_LINUX_MAGIC "\xcd\x23\x82\x81" + +/* + * Bootable Linux kernel images may be packaged as EFI zboot images, which are + * self-decompressing executables when loaded via EFI. The compressed payload + * can also be extracted from the image and decompressed by a non-EFI loader. + * + * The de facto specification for this format is at the following URL: + * + * https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/firmware/efi/libstub/zboot-header.S + * + * This definition is based on Linux upstream commit 29636a5ce87beba. + */ +struct linux_efi_zboot_header { + uint8_t msdos_magic[2]; /* PE/COFF 'MZ' magic number */ + uint8_t reserved0[2]; + uint8_t zimg[4]; /* "zimg" for Linux EFI zboot images */ + uint32_t payload_offset; /* LE offset to compressed payload */ + uint32_t payload_size; /* LE size of the compressed payload */ + uint8_t reserved1[8]; + char compression_type[32]; /* Compression type, NUL terminated */ + uint8_t linux_magic[4]; /* Linux header magic */ + uint32_t pe_header_offset; /* LE offset to the PE header */ +}; + +/* + * Check whether *buffer points to a Linux EFI zboot image in memory. + * + * If it does, attempt to decompress it to a new buffer, and free the old one. + * If any of this fails, return an error to the caller. + * + * If the image is not a Linux EFI zboot image, do nothing and return success. + */ +ssize_t unpack_efi_zboot_image(uint8_t **buffer, int *size) +{ + const struct linux_efi_zboot_header *header; + uint8_t *data = NULL; + int ploff, plsize; + ssize_t bytes; + + /* ignore if this is too small to be a EFI zboot image */ + if (*size < sizeof(*header)) { + return 0; + } + + header = (struct linux_efi_zboot_header *)*buffer; + + /* ignore if this is not a Linux EFI zboot image */ + if (memcmp(&header->msdos_magic, EFI_PE_MSDOS_MAGIC, 2) != 0 || + memcmp(&header->zimg, "zimg", 4) != 0 || + memcmp(&header->linux_magic, EFI_PE_LINUX_MAGIC, 4) != 0) { + return 0; + } + + if (strcmp(header->compression_type, "gzip") != 0) { + fprintf(stderr, + "unable to handle EFI zboot image with \"%.*s\" compression\n", + (int)sizeof(header->compression_type) - 1, + header->compression_type); + return -1; + } + + ploff = ldl_le_p(&header->payload_offset); + plsize = ldl_le_p(&header->payload_size); + + if (ploff < 0 || plsize < 0 || ploff + plsize > *size) { + fprintf(stderr, "unable to handle corrupt EFI zboot image\n"); + return -1; + } + + data = g_malloc(LOAD_IMAGE_MAX_GUNZIP_BYTES); + bytes = gunzip(data, LOAD_IMAGE_MAX_GUNZIP_BYTES, *buffer + ploff, plsize); + if (bytes < 0) { + fprintf(stderr, "failed to decompress EFI zboot image\n"); + g_free(data); + return -1; + } + + g_free(*buffer); + *buffer = g_realloc(data, bytes); + *size = bytes; + return bytes; +} + /* * Functions for reboot-persistent memory regions. * - used for vga bios and option roms. -- 2.34.1 From: qianfan Zhao <qianfanguijin@163.com> TWI_CNTR_INT_FLAG is W1C(write 1 to clear and write 0 has non-effect) register on SUN6i based SoCs, we should lower interrupt when the guest set this bit. The linux kernel will hang in irq handler(mv64xxx_i2c_intr) if no device connected on the i2c bus, next is the trace log: allwinner_i2c_write write CNTR(0x0c): 0xc4 A_ACK BUS_EN INT_EN allwinner_i2c_write write CNTR(0x0c): 0xcc A_ACK INT_FLAG BUS_EN INT_EN allwinner_i2c_read read CNTR(0x0c): 0xcc A_ACK INT_FLAG BUS_EN INT_EN allwinner_i2c_read read STAT(0x10): 0x20 STAT_M_ADDR_WR_NACK allwinner_i2c_write write CNTR(0x0c): 0x54 A_ACK M_STP BUS_EN allwinner_i2c_write write CNTR(0x0c): 0x4c A_ACK INT_FLAG BUS_EN allwinner_i2c_read read CNTR(0x0c): 0x4c A_ACK INT_FLAG BUS_EN allwinner_i2c_read read STAT(0x10): 0xf8 STAT_IDLE allwinner_i2c_write write CNTR(0x0c): 0x54 A_ACK M_STP BUS_EN allwinner_i2c_write write CNTR(0x0c): 0x4c A_ACK INT_FLAG BUS_EN allwinner_i2c_read read CNTR(0x0c): 0x4c A_ACK INT_FLAG BUS_EN allwinner_i2c_read read STAT(0x10): 0xf8 STAT_IDLE ... Fix it. Signed-off-by: qianfan Zhao <qianfanguijin@163.com> Reviewed-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Tested-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/i2c/allwinner-i2c.h | 6 ++++++ hw/i2c/allwinner-i2c.c | 26 ++++++++++++++++++++++++-- 2 files changed, 30 insertions(+), 2 deletions(-) diff --git a/include/hw/i2c/allwinner-i2c.h b/include/hw/i2c/allwinner-i2c.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/i2c/allwinner-i2c.h +++ b/include/hw/i2c/allwinner-i2c.h @@ -XXX,XX +XXX,XX @@ #include "qom/object.h" #define TYPE_AW_I2C "allwinner.i2c" + +/** Allwinner I2C sun6i family and newer (A31, H2+, H3, etc) */ +#define TYPE_AW_I2C_SUN6I TYPE_AW_I2C "-sun6i" + OBJECT_DECLARE_SIMPLE_TYPE(AWI2CState, AW_I2C) #define AW_I2C_MEM_SIZE 0x24 @@ -XXX,XX +XXX,XX @@ struct AWI2CState { uint8_t srst; uint8_t efr; uint8_t lcr; + + bool irq_clear_inverted; }; #endif /* ALLWINNER_I2C_H */ diff --git a/hw/i2c/allwinner-i2c.c b/hw/i2c/allwinner-i2c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/allwinner-i2c.c +++ b/hw/i2c/allwinner-i2c.c @@ -XXX,XX +XXX,XX @@ static void allwinner_i2c_write(void *opaque, hwaddr offset, s->stat = STAT_FROM_STA(STAT_IDLE); s->cntr &= ~TWI_CNTR_M_STP; } - if ((s->cntr & TWI_CNTR_INT_FLAG) == 0) { - /* Interrupt flag cleared */ + + if (!s->irq_clear_inverted && !(s->cntr & TWI_CNTR_INT_FLAG)) { + /* Write 0 to clear this flag */ + qemu_irq_lower(s->irq); + } else if (s->irq_clear_inverted && (s->cntr & TWI_CNTR_INT_FLAG)) { + /* Write 1 to clear this flag */ + s->cntr &= ~TWI_CNTR_INT_FLAG; qemu_irq_lower(s->irq); } + if ((s->cntr & TWI_CNTR_A_ACK) == 0) { if (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_ACK) { s->stat = STAT_FROM_STA(STAT_M_DATA_RX_NACK); @@ -XXX,XX +XXX,XX @@ static const TypeInfo allwinner_i2c_type_info = { .class_init = allwinner_i2c_class_init, }; +static void allwinner_i2c_sun6i_init(Object *obj) +{ + AWI2CState *s = AW_I2C(obj); + + s->irq_clear_inverted = true; +} + +static const TypeInfo allwinner_i2c_sun6i_type_info = { + .name = TYPE_AW_I2C_SUN6I, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(AWI2CState), + .instance_init = allwinner_i2c_sun6i_init, + .class_init = allwinner_i2c_class_init, +}; + static void allwinner_i2c_register_types(void) { type_register_static(&allwinner_i2c_type_info); + type_register_static(&allwinner_i2c_sun6i_type_info); } type_init(allwinner_i2c_register_types) -- 2.34.1 From: qianfan Zhao <qianfanguijin@163.com> Allwinner h3 has 4 twi(i2c) devices named twi0, twi1, twi2 and r_twi. The registers are compatible with TYPE_AW_I2C_SUN6I, write 1 to clear control register's INT_FLAG bit. Signed-off-by: qianfan Zhao <qianfanguijin@163.com> Reviewed-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-h3.h | 6 ++++++ hw/arm/allwinner-h3.c | 29 +++++++++++++++++++++++++---- 2 files changed, 31 insertions(+), 4 deletions(-) diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ enum { AW_H3_DEV_UART3, AW_H3_DEV_EMAC, AW_H3_DEV_TWI0, + AW_H3_DEV_TWI1, + AW_H3_DEV_TWI2, AW_H3_DEV_DRAMCOM, AW_H3_DEV_DRAMCTL, AW_H3_DEV_DRAMPHY, @@ -XXX,XX +XXX,XX @@ enum { AW_H3_DEV_GIC_VCPU, AW_H3_DEV_RTC, AW_H3_DEV_CPUCFG, + AW_H3_DEV_R_TWI, AW_H3_DEV_SDRAM }; @@ -XXX,XX +XXX,XX @@ struct AwH3State { AwSidState sid; AwSdHostState mmc0; AWI2CState i2c0; + AWI2CState i2c1; + AWI2CState i2c2; + AWI2CState r_twi; AwSun8iEmacState emac; AwRtcState rtc; GICState gic; diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_DEV_UART2] = 0x01c28800, [AW_H3_DEV_UART3] = 0x01c28c00, [AW_H3_DEV_TWI0] = 0x01c2ac00, + [AW_H3_DEV_TWI1] = 0x01c2b000, + [AW_H3_DEV_TWI2] = 0x01c2b400, [AW_H3_DEV_EMAC] = 0x01c30000, [AW_H3_DEV_DRAMCOM] = 0x01c62000, [AW_H3_DEV_DRAMCTL] = 0x01c63000, @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_DEV_GIC_VCPU] = 0x01c86000, [AW_H3_DEV_RTC] = 0x01f00000, [AW_H3_DEV_CPUCFG] = 0x01f01c00, + [AW_H3_DEV_R_TWI] = 0x01f02400, [AW_H3_DEV_SDRAM] = 0x40000000 }; @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "uart1", 0x01c28400, 1 * KiB }, { "uart2", 0x01c28800, 1 * KiB }, { "uart3", 0x01c28c00, 1 * KiB }, - { "twi1", 0x01c2b000, 1 * KiB }, - { "twi2", 0x01c2b400, 1 * KiB }, { "scr", 0x01c2c400, 1 * KiB }, { "gpu", 0x01c40000, 64 * KiB }, { "hstmr", 0x01c60000, 4 * KiB }, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "r_prcm", 0x01f01400, 1 * KiB }, { "r_twd", 0x01f01800, 1 * KiB }, { "r_cir-rx", 0x01f02000, 1 * KiB }, - { "r_twi", 0x01f02400, 1 * KiB }, { "r_uart", 0x01f02800, 1 * KiB }, { "r_pio", 0x01f02c00, 1 * KiB }, { "r_pwm", 0x01f03800, 1 * KiB }, @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_SPI_UART2 = 2, AW_H3_GIC_SPI_UART3 = 3, AW_H3_GIC_SPI_TWI0 = 6, + AW_H3_GIC_SPI_TWI1 = 7, + AW_H3_GIC_SPI_TWI2 = 8, AW_H3_GIC_SPI_TIMER0 = 18, AW_H3_GIC_SPI_TIMER1 = 19, + AW_H3_GIC_SPI_R_TWI = 44, AW_H3_GIC_SPI_MMC0 = 60, AW_H3_GIC_SPI_EHCI0 = 72, AW_H3_GIC_SPI_OHCI0 = 73, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) object_initialize_child(obj, "rtc", &s->rtc, TYPE_AW_RTC_SUN6I); - object_initialize_child(obj, "twi0", &s->i2c0, TYPE_AW_I2C); + object_initialize_child(obj, "twi0", &s->i2c0, TYPE_AW_I2C_SUN6I); + object_initialize_child(obj, "twi1", &s->i2c1, TYPE_AW_I2C_SUN6I); + object_initialize_child(obj, "twi2", &s->i2c2, TYPE_AW_I2C_SUN6I); + object_initialize_child(obj, "r_twi", &s->r_twi, TYPE_AW_I2C_SUN6I); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c0), 0, qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_TWI0)); + sysbus_realize(SYS_BUS_DEVICE(&s->i2c1), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c1), 0, s->memmap[AW_H3_DEV_TWI1]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c1), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_TWI1)); + + sysbus_realize(SYS_BUS_DEVICE(&s->i2c2), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c2), 0, s->memmap[AW_H3_DEV_TWI2]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c2), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_TWI2)); + + sysbus_realize(SYS_BUS_DEVICE(&s->r_twi), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->r_twi), 0, s->memmap[AW_H3_DEV_R_TWI]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->r_twi), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_R_TWI)); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(unimplemented); i++) { create_unimplemented_device(unimplemented[i].device_name, -- 2.34.1