ARM pullreq; contains some patches that arrived while I was on holiday, plus the series I sent off before going away, which got reviewed while I was away. thanks -- PMM The following changes since commit c077a998eb3fcae2d048e3baeb5bc592d30fddde: Merge remote-tracking branch 'remotes/riku/tags/pull-linux-user-20170531' into staging (2017-06-01 15:50:40 +0100) are available in the git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20170601 for you to fetch changes up to cdc58be430b0bdeaef282e2e70f8135ae531616d: hw/arm/virt: fdt: generate distance-map when needed (2017-06-01 17:27:07 +0100) ---------------------------------------------------------------- target-arm queue: * virt: numa: provide ACPI distance info when needed * aspeed: fix i2c controller bugs * aspeed: add temperature sensor device * M profile: support MPU * gicv3: fix mishandling of BPR1, VBPR1 * load_uboot_image: don't assume a full header read * libvixl: Correct build failures on NetBSD ---------------------------------------------------------------- Andrew Jones (3): load_uboot_image: don't assume a full header read hw/arm/virt-acpi-build: build SLIT when needed hw/arm/virt: fdt: generate distance-map when needed Cédric Le Goater (6): aspeed/i2c: improve command handling aspeed/i2c: handle LAST command under the RX command aspeed/i2c: introduce a state machine aspeed: add some I2C devices to the Aspeed machines hw/misc: add a TMP42{1,2,3} device model aspeed: add a temp sensor device on I2C bus 3 Kamil Rytarowski (1): libvixl: Correct build failures on NetBSD Michael Davidsaver (4): armv7m: Improve "-d mmu" tracing for PMSAv7 MPU armv7m: Implement M profile default memory map armv7m: Classify faults as MemManage or BusFault arm: add MPU support to M profile CPUs Peter Maydell (12): hw/intc/arm_gicv3_cpuif: Fix reset value for VMCR_EL2.VBPR1 hw/intc/arm_gicv3_cpuif: Don't let BPR be set below its minimum hw/intc/arm_gicv3_cpuif: Fix priority masking for NS BPR1 arm: Use the mmu_idx we're passed in arm_cpu_do_unaligned_access() arm: Add support for M profile CPUs having different MMU index semantics arm: Use different ARMMMUIdx values for M profile arm: Clean up handling of no-MPU PMSA CPUs arm: Don't clear ARM_FEATURE_PMSA for no-mpu configs arm: Don't let no-MPU PMSA cores write to SCTLR.M arm: Remove unnecessary check on cpu->pmsav7_dregion arm: All M profile cores are PMSA arm: Implement HFNMIENA support for M profile MPU Wei Huang (1): target/arm: clear PMUVER field of AA64DFR0 when vPMU=off disas/libvixl/Makefile.objs | 3 + hw/misc/Makefile.objs | 1 + target/arm/cpu.h | 118 ++++++++++-- target/arm/translate.h | 2 +- hw/arm/aspeed.c | 36 ++++ hw/arm/virt-acpi-build.c | 4 + hw/arm/virt.c | 21 +++ hw/core/loader.c | 3 +- hw/i2c/aspeed_i2c.c | 65 ++++++- hw/intc/arm_gicv3_cpuif.c | 50 ++++- hw/intc/armv7m_nvic.c | 104 +++++++++++ hw/misc/tmp421.c | 401 ++++++++++++++++++++++++++++++++++++++++ target/arm/cpu.c | 28 ++- target/arm/helper.c | 338 ++++++++++++++++++++++----------- target/arm/machine.c | 7 +- target/arm/op_helper.c | 3 +- target/arm/translate-a64.c | 18 +- target/arm/translate.c | 14 +- default-configs/arm-softmmu.mak | 1 + 19 files changed, 1060 insertions(+), 157 deletions(-) create mode 100644 hw/misc/tmp421.c From: Kamil Rytarowski <n54@gmx.com> Ensure that C99 macros are defined regardless of the inclusion order of headers in vixl. This is required at least on NetBSD. The vixl/globals.h headers defines __STDC_CONSTANT_MACROS and must be included before other system headers. This file defines unconditionally the following macros, without altering the original sources: - __STDC_CONSTANT_MACROS - __STDC_LIMIT_MACROS - __STDC_FORMAT_MACROS Signed-off-by: Kamil Rytarowski <n54@gmx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20170514051820.15985-1-n54@gmx.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- disas/libvixl/Makefile.objs | 3 +++ 1 file changed, 3 insertions(+) diff --git a/disas/libvixl/Makefile.objs b/disas/libvixl/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/disas/libvixl/Makefile.objs +++ b/disas/libvixl/Makefile.objs @@ -XXX,XX +XXX,XX @@ libvixl_OBJS = vixl/utils.o \ # The -Wno-sign-compare is needed only for gcc 4.6, which complains about # some signed-unsigned equality comparisons which later gcc versions do not. $(addprefix $(obj)/,$(libvixl_OBJS)): QEMU_CFLAGS := -I$(SRC_PATH)/disas/libvixl $(QEMU_CFLAGS) -Wno-sign-compare +# Ensure that C99 macros are defined regardless of the inclusion order of +# headers in vixl. This is required at least on NetBSD. +$(addprefix $(obj)/,$(libvixl_OBJS)): QEMU_CFLAGS += -D__STDC_CONSTANT_MACROS -D__STDC_LIMIT_MACROS -D__STDC_FORMAT_MACROS common-obj-$(CONFIG_ARM_A64_DIS) += $(libvixl_OBJS) -- 2.7.4 From: Andrew Jones <drjones@redhat.com> Don't allow load_uboot_image() to proceed when less bytes than header-size was read. Signed-off-by: Andrew Jones <drjones@redhat.com> Message-id: 20170524091315.20284-1-drjones@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/loader.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) 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 @@ static int load_uboot_image(const char *filename, hwaddr *ep, hwaddr *loadaddr, return -1; size = read(fd, hdr, sizeof(uboot_image_header_t)); - if (size < 0) + if (size < sizeof(uboot_image_header_t)) { goto out; + } bswap_uboot_header(hdr); -- 2.7.4 We were setting the VBPR1 field of VMCR_EL2 to icv_min_vbpr() on reset, but this is not correct. The field should reset to the minimum value of ICV_BPR0_EL1 plus one. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493226792-3237-2-git-send-email-peter.maydell@linaro.org --- hw/intc/arm_gicv3_cpuif.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 icc_reset(CPUARMState *env, const ARMCPRegInfo *ri) cs->ich_hcr_el2 = 0; memset(cs->ich_lr_el2, 0, sizeof(cs->ich_lr_el2)); cs->ich_vmcr_el2 = ICH_VMCR_EL2_VFIQEN | - (icv_min_vbpr(cs) << ICH_VMCR_EL2_VBPR1_SHIFT) | + ((icv_min_vbpr(cs) + 1) << ICH_VMCR_EL2_VBPR1_SHIFT) | (icv_min_vbpr(cs) << ICH_VMCR_EL2_VBPR0_SHIFT); } -- 2.7.4 icc_bpr_write() was not enforcing that writing a value below the minimum for the BPR should behave as if the BPR was set to the minimum value. This doesn't make a difference for the secure BPRs (since we define the minimum for the QEMU implementation as zero) but did mean we were allowing the NS BPR1 to be set to 0 when 1 should be the lowest value. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493226792-3237-3-git-send-email-peter.maydell@linaro.org --- hw/intc/arm_gicv3_cpuif.c | 6 ++++++ 1 file changed, 6 insertions(+) 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 icc_bpr_write(CPUARMState *env, const ARMCPRegInfo *ri, { GICv3CPUState *cs = icc_cs_from_env(env); int grp = (ri->crm == 8) ? GICV3_G0 : GICV3_G1; + uint64_t minval; if (icv_access(env, grp == GICV3_G0 ? HCR_FMO : HCR_IMO)) { icv_bpr_write(env, ri, value); @@ -XXX,XX +XXX,XX @@ static void icc_bpr_write(CPUARMState *env, const ARMCPRegInfo *ri, return; } + minval = (grp == GICV3_G1NS) ? GIC_MIN_BPR_NS : GIC_MIN_BPR; + if (value < minval) { + value = minval; + } + cs->icc_bpr[grp] = value & 7; gicv3_cpuif_update(cs); } -- 2.7.4 When we calculate the mask to use to get the group priority from an interrupt priority, the way that NS BPR1 is handled differs from how BPR0 and S BPR1 work -- a BPR1 value of 1 means the group priority is in bits [7:1], whereas for BPR0 and S BPR1 this is indicated by a 0 BPR value. Subtract 1 from the BPR value before creating the mask if we're using the NS BPR value, for both hardware and virtual interrupts, as the GICv3 pseudocode does, and fix the comments accordingly. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493226792-3237-4-git-send-email-peter.maydell@linaro.org --- hw/intc/arm_gicv3_cpuif.c | 42 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 38 insertions(+), 4 deletions(-) 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 uint32_t icv_gprio_mask(GICv3CPUState *cs, int group) { /* Return a mask word which clears the subpriority bits from * a priority value for a virtual interrupt in the specified group. - * This depends on the VBPR value: + * This depends on the VBPR value. + * If using VBPR0 then: * a BPR of 0 means the group priority bits are [7:1]; * a BPR of 1 means they are [7:2], and so on down to * a BPR of 7 meaning no group priority bits at all. + * If using VBPR1 then: + * a BPR of 0 is impossible (the minimum value is 1) + * a BPR of 1 means the group priority bits are [7:1]; + * a BPR of 2 means they are [7:2], and so on down to + * a BPR of 7 meaning the group priority is [7]. + * * Which BPR to use depends on the group of the interrupt and * the current ICH_VMCR_EL2.VCBPR settings. + * + * This corresponds to the VGroupBits() pseudocode. */ + int bpr; + if (group == GICV3_G1NS && cs->ich_vmcr_el2 & ICH_VMCR_EL2_VCBPR) { group = GICV3_G0; } - return ~0U << (read_vbpr(cs, group) + 1); + bpr = read_vbpr(cs, group); + if (group == GICV3_G1NS) { + assert(bpr > 0); + bpr--; + } + + return ~0U << (bpr + 1); } static bool icv_hppi_can_preempt(GICv3CPUState *cs, uint64_t lr) @@ -XXX,XX +XXX,XX @@ static uint32_t icc_gprio_mask(GICv3CPUState *cs, int group) { /* Return a mask word which clears the subpriority bits from * a priority value for an interrupt in the specified group. - * This depends on the BPR value: + * This depends on the BPR value. For CBPR0 (S or NS): * a BPR of 0 means the group priority bits are [7:1]; * a BPR of 1 means they are [7:2], and so on down to * a BPR of 7 meaning no group priority bits at all. + * For CBPR1 NS: + * a BPR of 0 is impossible (the minimum value is 1) + * a BPR of 1 means the group priority bits are [7:1]; + * a BPR of 2 means they are [7:2], and so on down to + * a BPR of 7 meaning the group priority is [7]. + * * Which BPR to use depends on the group of the interrupt and * the current ICC_CTLR.CBPR settings. + * + * This corresponds to the GroupBits() pseudocode. */ + int bpr; + if ((group == GICV3_G1 && cs->icc_ctlr_el1[GICV3_S] & ICC_CTLR_EL1_CBPR) || (group == GICV3_G1NS && cs->icc_ctlr_el1[GICV3_NS] & ICC_CTLR_EL1_CBPR)) { group = GICV3_G0; } - return ~0U << ((cs->icc_bpr[group] & 7) + 1); + bpr = cs->icc_bpr[group] & 7; + + if (group == GICV3_G1NS) { + assert(bpr > 0); + bpr--; + } + + return ~0U << (bpr + 1); } static bool icc_no_enabled_hppi(GICv3CPUState *cs) -- 2.7.4 From: Wei Huang <wei@redhat.com> The PMUv3 driver of linux kernel (in arch/arm64/kernel/perf_event.c) relies on the PMUVER field of id_aa64dfr0_el1 to decide if PMU support is present or not. This patch clears the PMUVER field under TCG mode when vPMU=off. Without it, PMUv3 will init insider guest VMs even with vPMU=off. This patch also removes a redundant line inside the if-statement. Signed-off-by: Wei Huang <wei@redhat.com> Message-id: 1495123889-32301-1-git-send-email-wei@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) } if (!cpu->has_pmu) { - cpu->has_pmu = false; unset_feature(env, ARM_FEATURE_PMU); + cpu->id_aa64dfr0 &= ~0xf00; } if (!arm_feature(env, ARM_FEATURE_EL2)) { -- 2.7.4 When identifying the DFSR format for an alignment fault, use the mmu index that we are passed, rather than calling cpu_mmu_index() to get the mmu index for the current CPU state. This doesn't actually make any difference since the only cases where the current MMU index differs from the index used for the load are the "unprivileged load/store" instructions, and in that case the mmu index may differ but the translation regime is the same (apart from the "use from Hyp mode" case which is UNPREDICTABLE). However it's the more logical thing to do. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-2-git-send-email-peter.maydell@linaro.org --- target/arm/op_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr, /* the DFSR for an alignment fault depends on whether we're using * the LPAE long descriptor format, or the short descriptor format */ - if (arm_s1_regime_using_lpae_format(env, cpu_mmu_index(env, false))) { + if (arm_s1_regime_using_lpae_format(env, mmu_idx)) { env->exception.fsr = (1 << 9) | 0x21; } else { env->exception.fsr = 0x1; -- 2.7.4 The M profile CPU's MPU has an awkward corner case which we would like to implement with a different MMU index. We can avoid having to bump the number of MMU modes ARM uses, because some of our existing MMU indexes are only used by non-M-profile CPUs, so we can borrow one. To avoid that getting too confusing, clean up the code to try to keep the two meanings of the index separate. Instead of ARMMMUIdx enum values being identical to core QEMU MMU index values, they are now the core index values with some high bits set. Any particular CPU always uses the same high bits (so eventually A profile cores and M profile cores will use different bits). New functions arm_to_core_mmu_idx() and core_to_arm_mmu_idx() convert between the two. In general core index values are stored in 'int' types, and ARM values are stored in ARMMMUIdx types. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1493122030-32191-3-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 71 ++++++++++++++++----- target/arm/translate.h | 2 +- target/arm/helper.c | 151 ++++++++++++++++++++++++--------------------- target/arm/op_helper.c | 3 +- target/arm/translate-a64.c | 18 ++++-- target/arm/translate.c | 10 +-- 6 files changed, 156 insertions(+), 99 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 @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, * for the accesses done as part of a stage 1 page table walk, rather than * having to walk the stage 2 page table over and over.) * + * The ARMMMUIdx and the mmu index value used by the core QEMU TLB code + * are not quite the same -- different CPU types (most notably M profile + * vs A/R profile) would like to use MMU indexes with different semantics, + * but since we don't ever need to use all of those in a single CPU we + * can avoid setting NB_MMU_MODES to more than 8. The lower bits of + * ARMMMUIdx are the core TLB mmu index, and the higher bits are always + * the same for any particular CPU. + * Variables of type ARMMUIdx are always full values, and the core + * index values are in variables of type 'int'. + * * Our enumeration includes at the end some entries which are not "true" * mmu_idx values in that they don't have corresponding TLBs and are only * valid for doing slow path page table walks. @@ -XXX,XX +XXX,XX @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, * of the AT/ATS operations. * The values used are carefully arranged to make mmu_idx => EL lookup easy. */ +#define ARM_MMU_IDX_A 0x10 /* A profile (and M profile, for the moment) */ +#define ARM_MMU_IDX_NOTLB 0x20 /* does not have a TLB */ + +#define ARM_MMU_IDX_TYPE_MASK (~0x7) +#define ARM_MMU_IDX_COREIDX_MASK 0x7 + typedef enum ARMMMUIdx { - ARMMMUIdx_S12NSE0 = 0, - ARMMMUIdx_S12NSE1 = 1, - ARMMMUIdx_S1E2 = 2, - ARMMMUIdx_S1E3 = 3, - ARMMMUIdx_S1SE0 = 4, - ARMMMUIdx_S1SE1 = 5, - ARMMMUIdx_S2NS = 6, + ARMMMUIdx_S12NSE0 = 0 | ARM_MMU_IDX_A, + ARMMMUIdx_S12NSE1 = 1 | ARM_MMU_IDX_A, + ARMMMUIdx_S1E2 = 2 | ARM_MMU_IDX_A, + ARMMMUIdx_S1E3 = 3 | ARM_MMU_IDX_A, + ARMMMUIdx_S1SE0 = 4 | ARM_MMU_IDX_A, + ARMMMUIdx_S1SE1 = 5 | ARM_MMU_IDX_A, + ARMMMUIdx_S2NS = 6 | ARM_MMU_IDX_A, /* Indexes below here don't have TLBs and are used only for AT system * instructions or for the first stage of an S12 page table walk. */ - ARMMMUIdx_S1NSE0 = 7, - ARMMMUIdx_S1NSE1 = 8, + ARMMMUIdx_S1NSE0 = 0 | ARM_MMU_IDX_NOTLB, + ARMMMUIdx_S1NSE1 = 1 | ARM_MMU_IDX_NOTLB, } ARMMMUIdx; +/* Bit macros for the core-mmu-index values for each index, + * for use when calling tlb_flush_by_mmuidx() and friends. + */ +typedef enum ARMMMUIdxBit { + ARMMMUIdxBit_S12NSE0 = 1 << 0, + ARMMMUIdxBit_S12NSE1 = 1 << 1, + ARMMMUIdxBit_S1E2 = 1 << 2, + ARMMMUIdxBit_S1E3 = 1 << 3, + ARMMMUIdxBit_S1SE0 = 1 << 4, + ARMMMUIdxBit_S1SE1 = 1 << 5, + ARMMMUIdxBit_S2NS = 1 << 6, +} ARMMMUIdxBit; + #define MMU_USER_IDX 0 +static inline int arm_to_core_mmu_idx(ARMMMUIdx mmu_idx) +{ + return mmu_idx & ARM_MMU_IDX_COREIDX_MASK; +} + +static inline ARMMMUIdx core_to_arm_mmu_idx(CPUARMState *env, int mmu_idx) +{ + return mmu_idx | ARM_MMU_IDX_A; +} + /* Return the exception level we're running at if this is our mmu_idx */ static inline int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx) { - assert(mmu_idx < ARMMMUIdx_S2NS); - return mmu_idx & 3; + switch (mmu_idx & ARM_MMU_IDX_TYPE_MASK) { + case ARM_MMU_IDX_A: + return mmu_idx & 3; + default: + g_assert_not_reached(); + } } /* Determine the current mmu_idx to use for normal loads/stores */ @@ -XXX,XX +XXX,XX @@ static inline int cpu_mmu_index(CPUARMState *env, bool ifetch) int el = arm_current_el(env); if (el < 2 && arm_is_secure_below_el3(env)) { - return ARMMMUIdx_S1SE0 + el; + return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0 + el); } return el; } @@ -XXX,XX +XXX,XX @@ static inline uint32_t arm_regime_tbi1(CPUARMState *env, ARMMMUIdx mmu_idx) static inline void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *flags) { - ARMMMUIdx mmu_idx = cpu_mmu_index(env, false); + ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); if (is_a64(env)) { *pc = env->pc; *flags = ARM_TBFLAG_AARCH64_STATE_MASK; @@ -XXX,XX +XXX,XX @@ static inline void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, << ARM_TBFLAG_XSCALE_CPAR_SHIFT); } - *flags |= (mmu_idx << ARM_TBFLAG_MMUIDX_SHIFT); + *flags |= (arm_to_core_mmu_idx(mmu_idx) << ARM_TBFLAG_MMUIDX_SHIFT); /* The SS_ACTIVE and PSTATE_SS bits correspond to the state machine * states defined in the ARM ARM for software singlestep: diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline int arm_dc_feature(DisasContext *dc, int feature) static inline int get_mem_index(DisasContext *s) { - return s->mmu_idx; + return arm_to_core_mmu_idx(s->mmu_idx); } /* Function used to determine the target exception EL when otherwise not known 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 tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri, CPUState *cs = ENV_GET_CPU(env); tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0) | - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0 | + ARMMMUIdxBit_S2NS); } static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri, CPUState *cs = ENV_GET_CPU(env); tlb_flush_by_mmuidx_all_cpus_synced(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0) | - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0 | + ARMMMUIdxBit_S2NS); } static void tlbiipas2_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbiipas2_write(CPUARMState *env, const ARMCPRegInfo *ri, pageaddr = sextract64(value << 12, 0, 40); - tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S2NS)); + tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S2NS); } static void tlbiipas2_is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbiipas2_is_write(CPUARMState *env, const ARMCPRegInfo *ri, pageaddr = sextract64(value << 12, 0, 40); tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S2NS); } static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, { CPUState *cs = ENV_GET_CPU(env); - tlb_flush_by_mmuidx(cs, (1 << ARMMMUIdx_S1E2)); + tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_S1E2); } static void tlbiall_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbiall_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, { CPUState *cs = ENV_GET_CPU(env); - tlb_flush_by_mmuidx_all_cpus_synced(cs, (1 << ARMMMUIdx_S1E2)); + tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_S1E2); } static void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, CPUState *cs = ENV_GET_CPU(env); uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12); - tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S1E2)); + tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S1E2); } static void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12); tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S1E2)); + ARMMMUIdxBit_S1E2); } static const ARMCPRegInfo cp_reginfo[] = { @@ -XXX,XX +XXX,XX @@ static void vttbr_write(CPUARMState *env, const ARMCPRegInfo *ri, /* Accesses to VTTBR may change the VMID so we must flush the TLB. */ if (raw_read(env, ri) != value) { tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0) | - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0 | + ARMMMUIdxBit_S2NS); raw_write(env, ri, value); } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vmalle1_write(CPUARMState *env, const ARMCPRegInfo *ri, if (arm_is_secure_below_el3(env)) { tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S1SE1) | - (1 << ARMMMUIdx_S1SE0)); + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); } else { tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, if (sec) { tlb_flush_by_mmuidx_all_cpus_synced(cs, - (1 << ARMMMUIdx_S1SE1) | - (1 << ARMMMUIdx_S1SE0)); + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); } else { tlb_flush_by_mmuidx_all_cpus_synced(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle1_write(CPUARMState *env, const ARMCPRegInfo *ri, if (arm_is_secure_below_el3(env)) { tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S1SE1) | - (1 << ARMMMUIdx_S1SE0)); + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); } else { if (arm_feature(env, ARM_FEATURE_EL2)) { tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0) | - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0 | + ARMMMUIdxBit_S2NS); } else { tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); } } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle2_write(CPUARMState *env, const ARMCPRegInfo *ri, ARMCPU *cpu = arm_env_get_cpu(env); CPUState *cs = CPU(cpu); - tlb_flush_by_mmuidx(cs, (1 << ARMMMUIdx_S1E2)); + tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_S1E2); } static void tlbi_aa64_alle3_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle3_write(CPUARMState *env, const ARMCPRegInfo *ri, ARMCPU *cpu = arm_env_get_cpu(env); CPUState *cs = CPU(cpu); - tlb_flush_by_mmuidx(cs, (1 << ARMMMUIdx_S1E3)); + tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_S1E3); } static void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, if (sec) { tlb_flush_by_mmuidx_all_cpus_synced(cs, - (1 << ARMMMUIdx_S1SE1) | - (1 << ARMMMUIdx_S1SE0)); + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); } else if (has_el2) { tlb_flush_by_mmuidx_all_cpus_synced(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0) | - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0 | + ARMMMUIdxBit_S2NS); } else { tlb_flush_by_mmuidx_all_cpus_synced(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle2is_write(CPUARMState *env, const ARMCPRegInfo *ri, { CPUState *cs = ENV_GET_CPU(env); - tlb_flush_by_mmuidx_all_cpus_synced(cs, (1 << ARMMMUIdx_S1E2)); + tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_S1E2); } static void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri, { CPUState *cs = ENV_GET_CPU(env); - tlb_flush_by_mmuidx_all_cpus_synced(cs, (1 << ARMMMUIdx_S1E3)); + tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_S1E3); } static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, if (arm_is_secure_below_el3(env)) { tlb_flush_page_by_mmuidx(cs, pageaddr, - (1 << ARMMMUIdx_S1SE1) | - (1 << ARMMMUIdx_S1SE0)); + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); } else { tlb_flush_page_by_mmuidx(cs, pageaddr, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri, CPUState *cs = CPU(cpu); uint64_t pageaddr = sextract64(value << 12, 0, 56); - tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S1E2)); + tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S1E2); } static void tlbi_aa64_vae3_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae3_write(CPUARMState *env, const ARMCPRegInfo *ri, CPUState *cs = CPU(cpu); uint64_t pageaddr = sextract64(value << 12, 0, 56); - tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S1E3)); + tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S1E3); } static void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, if (sec) { tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S1SE1) | - (1 << ARMMMUIdx_S1SE0)); + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); } else { tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t pageaddr = sextract64(value << 12, 0, 56); tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S1E2)); + ARMMMUIdxBit_S1E2); } static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t pageaddr = sextract64(value << 12, 0, 56); tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S1E3)); + ARMMMUIdxBit_S1E3); } static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri, pageaddr = sextract64(value << 12, 0, 48); - tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S2NS)); + tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S2NS); } static void tlbi_aa64_ipas2e1is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_ipas2e1is_write(CPUARMState *env, const ARMCPRegInfo *ri, pageaddr = sextract64(value << 12, 0, 48); tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S2NS); } static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static inline TCR *regime_tcr(CPUARMState *env, ARMMMUIdx mmu_idx) return &env->cp15.tcr_el[regime_el(env, mmu_idx)]; } +/* Convert a possible stage1+2 MMU index into the appropriate + * stage 1 MMU index + */ +static inline ARMMMUIdx stage_1_mmu_idx(ARMMMUIdx mmu_idx) +{ + if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) { + mmu_idx += (ARMMMUIdx_S1NSE0 - ARMMMUIdx_S12NSE0); + } + return mmu_idx; +} + /* Returns TBI0 value for current regime el */ uint32_t arm_regime_tbi0(CPUARMState *env, ARMMMUIdx mmu_idx) { @@ -XXX,XX +XXX,XX @@ uint32_t arm_regime_tbi0(CPUARMState *env, ARMMMUIdx mmu_idx) uint32_t el; /* For EL0 and EL1, TBI is controlled by stage 1's TCR, so convert - * a stage 1+2 mmu index into the appropriate stage 1 mmu index. - */ - if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) { - mmu_idx += ARMMMUIdx_S1NSE0; - } + * a stage 1+2 mmu index into the appropriate stage 1 mmu index. + */ + mmu_idx = stage_1_mmu_idx(mmu_idx); tcr = regime_tcr(env, mmu_idx); el = regime_el(env, mmu_idx); @@ -XXX,XX +XXX,XX @@ uint32_t arm_regime_tbi1(CPUARMState *env, ARMMMUIdx mmu_idx) uint32_t el; /* For EL0 and EL1, TBI is controlled by stage 1's TCR, so convert - * a stage 1+2 mmu index into the appropriate stage 1 mmu index. - */ - if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) { - mmu_idx += ARMMMUIdx_S1NSE0; - } + * a stage 1+2 mmu index into the appropriate stage 1 mmu index. + */ + mmu_idx = stage_1_mmu_idx(mmu_idx); tcr = regime_tcr(env, mmu_idx); el = regime_el(env, mmu_idx); @@ -XXX,XX +XXX,XX @@ static inline bool regime_using_lpae_format(CPUARMState *env, * on whether the long or short descriptor format is in use. */ bool arm_s1_regime_using_lpae_format(CPUARMState *env, ARMMMUIdx mmu_idx) { - if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) { - mmu_idx += ARMMMUIdx_S1NSE0; - } + mmu_idx = stage_1_mmu_idx(mmu_idx); return regime_using_lpae_format(env, mmu_idx); } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, int ret; ret = get_phys_addr(env, address, access_type, - mmu_idx + ARMMMUIdx_S1NSE0, &ipa, attrs, + stage_1_mmu_idx(mmu_idx), &ipa, attrs, prot, page_size, fsr, fi); /* If S1 fails or S2 is disabled, return early. */ @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, /* * For non-EL2 CPUs a stage1+stage2 translation is just stage 1. */ - mmu_idx += ARMMMUIdx_S1NSE0; + mmu_idx = stage_1_mmu_idx(mmu_idx); } } @@ -XXX,XX +XXX,XX @@ bool arm_tlb_fill(CPUState *cs, vaddr address, int ret; MemTxAttrs attrs = {}; - ret = get_phys_addr(env, address, access_type, mmu_idx, &phys_addr, + ret = get_phys_addr(env, address, access_type, + core_to_arm_mmu_idx(env, mmu_idx), &phys_addr, &attrs, &prot, &page_size, fsr, fi); if (!ret) { /* Map a single [sub]page. */ @@ -XXX,XX +XXX,XX @@ hwaddr arm_cpu_get_phys_page_attrs_debug(CPUState *cs, vaddr addr, bool ret; uint32_t fsr; ARMMMUFaultInfo fi = {}; + ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); *attrs = (MemTxAttrs) {}; - ret = get_phys_addr(env, addr, 0, cpu_mmu_index(env, false), &phys_addr, + ret = get_phys_addr(env, addr, 0, mmu_idx, &phys_addr, attrs, &prot, &page_size, &fsr, &fi); if (ret) { diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr, int target_el; bool same_el; uint32_t syn; + ARMMMUIdx arm_mmu_idx = core_to_arm_mmu_idx(env, mmu_idx); if (retaddr) { /* now we have a real cpu fault */ @@ -XXX,XX +XXX,XX @@ void arm_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr, /* the DFSR for an alignment fault depends on whether we're using * the LPAE long descriptor format, or the short descriptor format */ - if (arm_s1_regime_using_lpae_format(env, mmu_idx)) { + if (arm_s1_regime_using_lpae_format(env, arm_mmu_idx)) { env->exception.fsr = (1 << 9) | 0x21; } else { env->exception.fsr = 0x1; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ void a64_translate_init(void) offsetof(CPUARMState, exclusive_high), "exclusive_high"); } -static inline ARMMMUIdx get_a64_user_mem_index(DisasContext *s) +static inline int get_a64_user_mem_index(DisasContext *s) { - /* Return the mmu_idx to use for A64 "unprivileged load/store" insns: + /* Return the core mmu_idx to use for A64 "unprivileged load/store" insns: * if EL1, access as if EL0; otherwise access at current EL */ + ARMMMUIdx useridx; + switch (s->mmu_idx) { case ARMMMUIdx_S12NSE1: - return ARMMMUIdx_S12NSE0; + useridx = ARMMMUIdx_S12NSE0; + break; case ARMMMUIdx_S1SE1: - return ARMMMUIdx_S1SE0; + useridx = ARMMMUIdx_S1SE0; + break; case ARMMMUIdx_S2NS: g_assert_not_reached(); default: - return s->mmu_idx; + useridx = s->mmu_idx; + break; } + return arm_to_core_mmu_idx(useridx); } void aarch64_cpu_dump_state(CPUState *cs, FILE *f, @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code_a64(ARMCPU *cpu, TranslationBlock *tb) dc->be_data = ARM_TBFLAG_BE_DATA(tb->flags) ? MO_BE : MO_LE; dc->condexec_mask = 0; dc->condexec_cond = 0; - dc->mmu_idx = ARM_TBFLAG_MMUIDX(tb->flags); + dc->mmu_idx = core_to_arm_mmu_idx(env, ARM_TBFLAG_MMUIDX(tb->flags)); dc->tbi0 = ARM_TBFLAG_TBI0(tb->flags); dc->tbi1 = ARM_TBFLAG_TBI1(tb->flags); dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx); 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 disas_set_da_iss(DisasContext *s, TCGMemOp memop, ISSInfo issinfo) disas_set_insn_syndrome(s, syn); } -static inline ARMMMUIdx get_a32_user_mem_index(DisasContext *s) +static inline int get_a32_user_mem_index(DisasContext *s) { - /* Return the mmu_idx to use for A32/T32 "unprivileged load/store" + /* Return the core mmu_idx to use for A32/T32 "unprivileged load/store" * insns: * if PL2, UNPREDICTABLE (we choose to implement as if PL0) * otherwise, access as if at PL0. @@ -XXX,XX +XXX,XX @@ static inline ARMMMUIdx get_a32_user_mem_index(DisasContext *s) case ARMMMUIdx_S1E2: /* this one is UNPREDICTABLE */ case ARMMMUIdx_S12NSE0: case ARMMMUIdx_S12NSE1: - return ARMMMUIdx_S12NSE0; + return arm_to_core_mmu_idx(ARMMMUIdx_S12NSE0); case ARMMMUIdx_S1E3: case ARMMMUIdx_S1SE0: case ARMMMUIdx_S1SE1: - return ARMMMUIdx_S1SE0; + return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0); case ARMMMUIdx_S2NS: default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) dc->be_data = ARM_TBFLAG_BE_DATA(tb->flags) ? MO_BE : MO_LE; dc->condexec_mask = (ARM_TBFLAG_CONDEXEC(tb->flags) & 0xf) << 1; dc->condexec_cond = ARM_TBFLAG_CONDEXEC(tb->flags) >> 4; - dc->mmu_idx = ARM_TBFLAG_MMUIDX(tb->flags); + dc->mmu_idx = core_to_arm_mmu_idx(env, ARM_TBFLAG_MMUIDX(tb->flags)); dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx); #if !defined(CONFIG_USER_ONLY) dc->user = (dc->current_el == 0); -- 2.7.4 Make M profile use completely separate ARMMMUIdx values from those that A profile CPUs use. This is a prelude to adding support for the MPU and for v8M, which together will require 6 MMU indexes which don't map cleanly onto the A profile uses: non secure User non secure Privileged non secure Privileged, execution priority < 0 secure User secure Privileged secure Privileged, execution priority < 0 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1493122030-32191-4-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 21 +++++++++++++++++++-- target/arm/helper.c | 5 +++++ target/arm/translate.c | 3 +++ 3 files changed, 27 insertions(+), 2 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, * of the AT/ATS operations. * The values used are carefully arranged to make mmu_idx => EL lookup easy. */ -#define ARM_MMU_IDX_A 0x10 /* A profile (and M profile, for the moment) */ +#define ARM_MMU_IDX_A 0x10 /* A profile */ #define ARM_MMU_IDX_NOTLB 0x20 /* does not have a TLB */ +#define ARM_MMU_IDX_M 0x40 /* M profile */ #define ARM_MMU_IDX_TYPE_MASK (~0x7) #define ARM_MMU_IDX_COREIDX_MASK 0x7 @@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdx { ARMMMUIdx_S1SE0 = 4 | ARM_MMU_IDX_A, ARMMMUIdx_S1SE1 = 5 | ARM_MMU_IDX_A, ARMMMUIdx_S2NS = 6 | ARM_MMU_IDX_A, + ARMMMUIdx_MUser = 0 | ARM_MMU_IDX_M, + ARMMMUIdx_MPriv = 1 | ARM_MMU_IDX_M, /* Indexes below here don't have TLBs and are used only for AT system * instructions or for the first stage of an S12 page table walk. */ @@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdxBit { ARMMMUIdxBit_S1SE0 = 1 << 4, ARMMMUIdxBit_S1SE1 = 1 << 5, ARMMMUIdxBit_S2NS = 1 << 6, + ARMMMUIdxBit_MUser = 1 << 0, + ARMMMUIdxBit_MPriv = 1 << 1, } ARMMMUIdxBit; #define MMU_USER_IDX 0 @@ -XXX,XX +XXX,XX @@ static inline int arm_to_core_mmu_idx(ARMMMUIdx mmu_idx) static inline ARMMMUIdx core_to_arm_mmu_idx(CPUARMState *env, int mmu_idx) { - return mmu_idx | ARM_MMU_IDX_A; + if (arm_feature(env, ARM_FEATURE_M)) { + return mmu_idx | ARM_MMU_IDX_M; + } else { + return mmu_idx | ARM_MMU_IDX_A; + } } /* Return the exception level we're running at if this is our mmu_idx */ @@ -XXX,XX +XXX,XX @@ static inline int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx) switch (mmu_idx & ARM_MMU_IDX_TYPE_MASK) { case ARM_MMU_IDX_A: return mmu_idx & 3; + case ARM_MMU_IDX_M: + return mmu_idx & 1; default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static inline int cpu_mmu_index(CPUARMState *env, bool ifetch) { int el = arm_current_el(env); + if (arm_feature(env, ARM_FEATURE_M)) { + ARMMMUIdx mmu_idx = el == 0 ? ARMMMUIdx_MUser : ARMMMUIdx_MPriv; + + return arm_to_core_mmu_idx(mmu_idx); + } + if (el < 2 && arm_is_secure_below_el3(env)) { return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0 + el); } diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx) case ARMMMUIdx_S1SE1: case ARMMMUIdx_S1NSE0: case ARMMMUIdx_S1NSE1: + case ARMMMUIdx_MPriv: + case ARMMMUIdx_MUser: return 1; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static inline bool regime_is_secure(CPUARMState *env, ARMMMUIdx mmu_idx) case ARMMMUIdx_S1NSE1: case ARMMMUIdx_S1E2: case ARMMMUIdx_S2NS: + case ARMMMUIdx_MPriv: + case ARMMMUIdx_MUser: return false; case ARMMMUIdx_S1E3: case ARMMMUIdx_S1SE0: @@ -XXX,XX +XXX,XX @@ static inline bool regime_is_user(CPUARMState *env, ARMMMUIdx mmu_idx) switch (mmu_idx) { case ARMMMUIdx_S1SE0: case ARMMMUIdx_S1NSE0: + case ARMMMUIdx_MUser: return true; default: return false; 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 int get_a32_user_mem_index(DisasContext *s) case ARMMMUIdx_S1SE0: case ARMMMUIdx_S1SE1: return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0); + case ARMMMUIdx_MUser: + case ARMMMUIdx_MPriv: + return arm_to_core_mmu_idx(ARMMMUIdx_MUser); case ARMMMUIdx_S2NS: default: g_assert_not_reached(); -- 2.7.4 ARM CPUs come in two flavours: * proper MMU ("VMSA") * only an MPU ("PMSA") For PMSA, the MPU may be implemented, or not (in which case there is default "always acts the same" behaviour, but it isn't guest programmable). QEMU is a bit confused about how we indicate this: we have an ARM_FEATURE_MPU, but it's not clear whether this indicates "PMSA, not VMSA" or "PMSA and MPU present" , and sometimes we use it for one purpose and sometimes the other. Currently trying to implement a PMSA-without-MPU core won't work correctly because we turn off the ARM_FEATURE_MPU bit and then a lot of things which should still exist get turned off too. As the first step in cleaning this up, rename the feature bit to ARM_FEATURE_PMSA, which indicates a PMSA CPU (with or without MPU). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-5-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 2 +- target/arm/cpu.c | 12 ++++++------ target/arm/helper.c | 12 ++++++------ target/arm/machine.c | 2 +- 4 files changed, 14 insertions(+), 14 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 @@ enum arm_features { ARM_FEATURE_V6K, ARM_FEATURE_V7, ARM_FEATURE_THUMB2, - ARM_FEATURE_MPU, /* Only has Memory Protection Unit, not full MMU. */ + ARM_FEATURE_PMSA, /* no MMU; may have Memory Protection Unit */ ARM_FEATURE_VFP3, ARM_FEATURE_VFP_FP16, ARM_FEATURE_NEON, diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_post_init(Object *obj) &error_abort); } - if (arm_feature(&cpu->env, ARM_FEATURE_MPU)) { + if (arm_feature(&cpu->env, ARM_FEATURE_PMSA)) { qdev_property_add_static(DEVICE(obj), &arm_cpu_has_mpu_property, &error_abort); if (arm_feature(&cpu->env, ARM_FEATURE_V7)) { @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) if (arm_feature(env, ARM_FEATURE_V7) && !arm_feature(env, ARM_FEATURE_M) && - !arm_feature(env, ARM_FEATURE_MPU)) { + !arm_feature(env, ARM_FEATURE_PMSA)) { /* v7VMSA drops support for the old ARMv5 tiny pages, so we * can use 4K pages. */ @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) } if (!cpu->has_mpu) { - unset_feature(env, ARM_FEATURE_MPU); + unset_feature(env, ARM_FEATURE_PMSA); } - if (arm_feature(env, ARM_FEATURE_MPU) && + if (arm_feature(env, ARM_FEATURE_PMSA) && arm_feature(env, ARM_FEATURE_V7)) { uint32_t nr = cpu->pmsav7_dregion; @@ -XXX,XX +XXX,XX @@ static void arm946_initfn(Object *obj) cpu->dtb_compatible = "arm,arm946"; set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_MPU); + set_feature(&cpu->env, ARM_FEATURE_PMSA); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); cpu->midr = 0x41059461; cpu->ctr = 0x0f004006; @@ -XXX,XX +XXX,XX @@ static void cortex_r5_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_THUMB_DIV); set_feature(&cpu->env, ARM_FEATURE_ARM_DIV); set_feature(&cpu->env, ARM_FEATURE_V7MP); - set_feature(&cpu->env, ARM_FEATURE_MPU); + set_feature(&cpu->env, ARM_FEATURE_PMSA); cpu->midr = 0x411fc153; /* r1p3 */ cpu->id_pfr0 = 0x0131; cpu->id_pfr1 = 0x001; 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 contextidr_write(CPUARMState *env, const ARMCPRegInfo *ri, { ARMCPU *cpu = arm_env_get_cpu(env); - if (raw_read(env, ri) != value && !arm_feature(env, ARM_FEATURE_MPU) + if (raw_read(env, ri) != value && !arm_feature(env, ARM_FEATURE_PMSA) && !extended_addresses_enabled(env)) { /* For VMSA (when not using the LPAE long descriptor page table * format) this register includes the ASID, so do a TLB flush. @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_arm_cp_regs(cpu, v6k_cp_reginfo); } if (arm_feature(env, ARM_FEATURE_V7MP) && - !arm_feature(env, ARM_FEATURE_MPU)) { + !arm_feature(env, ARM_FEATURE_PMSA)) { define_arm_cp_regs(cpu, v7mp_cp_reginfo); } if (arm_feature(env, ARM_FEATURE_V7)) { @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) } } - if (arm_feature(env, ARM_FEATURE_MPU)) { + if (arm_feature(env, ARM_FEATURE_PMSA)) { if (arm_feature(env, ARM_FEATURE_V6)) { /* PMSAv6 not implemented */ assert(arm_feature(env, ARM_FEATURE_V7)); @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_arm_cp_regs(cpu, id_pre_v8_midr_cp_reginfo); } define_arm_cp_regs(cpu, id_cp_reginfo); - if (!arm_feature(env, ARM_FEATURE_MPU)) { + if (!arm_feature(env, ARM_FEATURE_PMSA)) { define_one_arm_cp_reg(cpu, &id_tlbtr_reginfo); } else if (arm_feature(env, ARM_FEATURE_V7)) { define_one_arm_cp_reg(cpu, &id_mpuir_reginfo); @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, /* pmsav7 has special handling for when MPU is disabled so call it before * the common MMU/MPU disabled check below. */ - if (arm_feature(env, ARM_FEATURE_MPU) && + if (arm_feature(env, ARM_FEATURE_PMSA) && arm_feature(env, ARM_FEATURE_V7)) { *page_size = TARGET_PAGE_SIZE; return get_phys_addr_pmsav7(env, address, access_type, mmu_idx, @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, return 0; } - if (arm_feature(env, ARM_FEATURE_MPU)) { + if (arm_feature(env, ARM_FEATURE_PMSA)) { /* Pre-v7 MPU */ *page_size = TARGET_PAGE_SIZE; return get_phys_addr_pmsav5(env, address, access_type, mmu_idx, diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static bool pmsav7_needed(void *opaque) ARMCPU *cpu = opaque; CPUARMState *env = &cpu->env; - return arm_feature(env, ARM_FEATURE_MPU) && + return arm_feature(env, ARM_FEATURE_PMSA) && arm_feature(env, ARM_FEATURE_V7); } -- 2.7.4 Fix the handling of QOM properties for PMSA CPUs with no MPU: Allow no-MPU to be specified by either: * has-mpu = false * pmsav7_dregion = 0 and make setting one imply the other. Don't clear the PMSA feature bit in this situation. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-6-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) cpu->id_pfr1 &= ~0xf000; } + /* MPU can be configured out of a PMSA CPU either by setting has-mpu + * to false or by setting pmsav7-dregion to 0. + */ if (!cpu->has_mpu) { - unset_feature(env, ARM_FEATURE_PMSA); + cpu->pmsav7_dregion = 0; + } + if (cpu->pmsav7_dregion == 0) { + cpu->has_mpu = false; } if (arm_feature(env, ARM_FEATURE_PMSA) && -- 2.7.4 If the CPU is a PMSA config with no MPU implemented, then the SCTLR.M bit should be RAZ/WI, so that the guest can never turn on the non-existent MPU. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-7-git-send-email-peter.maydell@linaro.org --- target/arm/helper.c | 5 +++++ 1 file changed, 5 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 @@ static void sctlr_write(CPUARMState *env, const ARMCPRegInfo *ri, return; } + if (arm_feature(env, ARM_FEATURE_PMSA) && !cpu->has_mpu) { + /* M bit is RAZ/WI for PMSA with no MPU implemented */ + value &= ~SCTLR_M; + } + raw_write(env, ri, value); /* ??? Lots of these bits are not implemented. */ /* This may enable/disable the MMU, so do a TLB flush. */ -- 2.7.4 Now that we enforce both: * pmsav7_dregion == 0 implies has_mpu == false * PMSA with has_mpu == false means SCTLR.M cannot be set we can remove a check on pmsav7_dregion from get_phys_addr_pmsav7(), because we can only reach this code path if the MPU is enabled (and so region_translation_disabled() returned false). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-8-git-send-email-peter.maydell@linaro.org --- target/arm/helper.c | 3 +-- 1 file changed, 1 insertion(+), 2 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 bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, } if (n == -1) { /* no hits */ - if (cpu->pmsav7_dregion && - (is_user || !(regime_sctlr(env, mmu_idx) & SCTLR_BR))) { + if (is_user || !(regime_sctlr(env, mmu_idx) & SCTLR_BR)) { /* background fault */ *fsr = 0; return true; -- 2.7.4 From: Michael Davidsaver <mdavidsaver@gmail.com> Improve the "-d mmu" tracing for the PMSAv7 MPU translation process as an aid in debugging guest MPU configurations: * fix a missing newline for a guest-error log * report the region number with guest-error or unimp logs of bad region register values * add a log message for the overall result of the lookup * print "0x" prefix for hex values Signed-off-by: Michael Davidsaver <mdavidsaver@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-9-git-send-email-peter.maydell@linaro.org [PMM: a little tidyup, report region number in all messages rather than just one] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 39 +++++++++++++++++++++++++++------------ 1 file changed, 27 insertions(+), 12 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 bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, } if (!rsize) { - qemu_log_mask(LOG_GUEST_ERROR, "DRSR.Rsize field can not be 0"); + qemu_log_mask(LOG_GUEST_ERROR, + "DRSR[%d]: Rsize field cannot be 0\n", n); continue; } rsize++; rmask = (1ull << rsize) - 1; if (base & rmask) { - qemu_log_mask(LOG_GUEST_ERROR, "DRBAR %" PRIx32 " misaligned " - "to DRSR region size, mask = %" PRIx32, - base, rmask); + qemu_log_mask(LOG_GUEST_ERROR, + "DRBAR[%d]: 0x%" PRIx32 " misaligned " + "to DRSR region size, mask = 0x%" PRIx32 "\n", + n, base, rmask); continue; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, } } if (rsize < TARGET_PAGE_BITS) { - qemu_log_mask(LOG_UNIMP, "No support for MPU (sub)region" + qemu_log_mask(LOG_UNIMP, + "DRSR[%d]: No support for MPU (sub)region " "alignment of %" PRIu32 " bits. Minimum is %d\n", - rsize, TARGET_PAGE_BITS); + n, rsize, TARGET_PAGE_BITS); continue; } if (srdis) { @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, break; default: qemu_log_mask(LOG_GUEST_ERROR, - "Bad value for AP bits in DRACR %" - PRIx32 "\n", ap); + "DRACR[%d]: Bad value for AP bits: 0x%" + PRIx32 "\n", n, ap); } } else { /* Priv. mode AP bits decoding */ switch (ap) { @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, break; default: qemu_log_mask(LOG_GUEST_ERROR, - "Bad value for AP bits in DRACR %" - PRIx32 "\n", ap); + "DRACR[%d]: Bad value for AP bits: 0x%" + PRIx32 "\n", n, ap); } } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, */ if (arm_feature(env, ARM_FEATURE_PMSA) && arm_feature(env, ARM_FEATURE_V7)) { + bool ret; *page_size = TARGET_PAGE_SIZE; - return get_phys_addr_pmsav7(env, address, access_type, mmu_idx, - phys_ptr, prot, fsr); + ret = get_phys_addr_pmsav7(env, address, access_type, mmu_idx, + phys_ptr, prot, fsr); + qemu_log_mask(CPU_LOG_MMU, "PMSAv7 MPU lookup for %s at 0x%08" PRIx32 + " mmu_idx %u -> %s (prot %c%c%c)\n", + access_type == 1 ? "reading" : + (access_type == 2 ? "writing" : "execute"), + (uint32_t)address, mmu_idx, + ret ? "Miss" : "Hit", + *prot & PAGE_READ ? 'r' : '-', + *prot & PAGE_WRITE ? 'w' : '-', + *prot & PAGE_EXEC ? 'x' : '-'); + + return ret; } if (regime_translation_disabled(env, mmu_idx)) { -- 2.7.4 From: Michael Davidsaver <mdavidsaver@gmail.com> Add support for the M profile default memory map which is used if the MPU is not present or disabled. The main differences in behaviour from implementing this correctly are that we set the PAGE_EXEC attribute on the right regions of memory, such that device regions are not executable. Signed-off-by: Michael Davidsaver <mdavidsaver@gmail.com> Message-id: 1493122030-32191-10-git-send-email-peter.maydell@linaro.org [PMM: rephrased comment and commit message; don't mark the flash memory region as not-writable; list all the cases in the default map explicitly rather than using a 'default' case for the non-executable regions] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 41 ++++++++++++++++++++++++++++++++--------- 1 file changed, 32 insertions(+), 9 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 inline void get_phys_addr_pmsav7_default(CPUARMState *env, ARMMMUIdx mmu_idx, int32_t address, int *prot) { - *prot = PAGE_READ | PAGE_WRITE; - switch (address) { - case 0xF0000000 ... 0xFFFFFFFF: - if (regime_sctlr(env, mmu_idx) & SCTLR_V) { /* hivecs execing is ok */ + if (!arm_feature(env, ARM_FEATURE_M)) { + *prot = PAGE_READ | PAGE_WRITE; + switch (address) { + case 0xF0000000 ... 0xFFFFFFFF: + if (regime_sctlr(env, mmu_idx) & SCTLR_V) { + /* hivecs execing is ok */ + *prot |= PAGE_EXEC; + } + break; + case 0x00000000 ... 0x7FFFFFFF: *prot |= PAGE_EXEC; + break; + } + } else { + /* Default system address map for M profile cores. + * The architecture specifies which regions are execute-never; + * at the MPU level no other checks are defined. + */ + switch (address) { + case 0x00000000 ... 0x1fffffff: /* ROM */ + case 0x20000000 ... 0x3fffffff: /* SRAM */ + case 0x60000000 ... 0x7fffffff: /* RAM */ + case 0x80000000 ... 0x9fffffff: /* RAM */ + *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC; + break; + case 0x40000000 ... 0x5fffffff: /* Peripheral */ + case 0xa0000000 ... 0xbfffffff: /* Device */ + case 0xc0000000 ... 0xdfffffff: /* Device */ + case 0xe0000000 ... 0xffffffff: /* System */ + *prot = PAGE_READ | PAGE_WRITE; + break; + default: + g_assert_not_reached(); } - break; - case 0x00000000 ... 0x7FFFFFFF: - *prot |= PAGE_EXEC; - break; } - } static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, -- 2.7.4 All M profile CPUs are PMSA, so set the feature bit. (We haven't actually implemented the M profile MPU register interface yet, but setting this feature bit gives us closer to correct behaviour for the MPU-disabled case.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-11-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_post_init(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); + /* M profile implies PMSA. We have to do this here rather than + * in realize with the other feature-implication checks because + * we look at the PMSA bit to see if we should add some properties. + */ + if (arm_feature(&cpu->env, ARM_FEATURE_M)) { + set_feature(&cpu->env, ARM_FEATURE_PMSA); + } + if (arm_feature(&cpu->env, ARM_FEATURE_CBAR) || arm_feature(&cpu->env, ARM_FEATURE_CBAR_RO)) { qdev_property_add_static(DEVICE(obj), &arm_cpu_reset_cbar_property, -- 2.7.4 From: Michael Davidsaver <mdavidsaver@gmail.com> General logic is that operations stopped by the MPU are MemManage, and those which go through the MPU and are caught by the unassigned handle are BusFault. Distinguish these by looking at the exception.fsr values, and set the CFSR bits and (if appropriate) fill in the BFAR or MMFAR with the exception address. Signed-off-by: Michael Davidsaver <mdavidsaver@gmail.com> Message-id: 1493122030-32191-12-git-send-email-peter.maydell@linaro.org [PMM: i-side faults do not set BFAR/MMFAR, only d-side; added some CPU_LOG_INT logging] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> --- target/arm/helper.c | 45 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 42 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 @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) break; case EXCP_PREFETCH_ABORT: case EXCP_DATA_ABORT: - /* TODO: if we implemented the MPU registers, this is where we - * should set the MMFAR, etc from exception.fsr and exception.vaddress. + /* Note that for M profile we don't have a guest facing FSR, but + * the env->exception.fsr will be populated by the code that + * raises the fault, in the A profile short-descriptor format. */ - armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_MEM); + switch (env->exception.fsr & 0xf) { + case 0x8: /* External Abort */ + switch (cs->exception_index) { + case EXCP_PREFETCH_ABORT: + env->v7m.cfsr |= R_V7M_CFSR_PRECISERR_MASK; + qemu_log_mask(CPU_LOG_INT, "...with CFSR.PRECISERR\n"); + break; + case EXCP_DATA_ABORT: + env->v7m.cfsr |= + (R_V7M_CFSR_IBUSERR_MASK | R_V7M_CFSR_BFARVALID_MASK); + env->v7m.bfar = env->exception.vaddress; + qemu_log_mask(CPU_LOG_INT, + "...with CFSR.IBUSERR and BFAR 0x%x\n", + env->v7m.bfar); + break; + } + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_BUS); + break; + default: + /* All other FSR values are either MPU faults or "can't happen + * for M profile" cases. + */ + switch (cs->exception_index) { + case EXCP_PREFETCH_ABORT: + env->v7m.cfsr |= R_V7M_CFSR_IACCVIOL_MASK; + qemu_log_mask(CPU_LOG_INT, "...with CFSR.IACCVIOL\n"); + break; + case EXCP_DATA_ABORT: + env->v7m.cfsr |= + (R_V7M_CFSR_DACCVIOL_MASK | R_V7M_CFSR_MMARVALID_MASK); + env->v7m.mmfar = env->exception.vaddress; + qemu_log_mask(CPU_LOG_INT, + "...with CFSR.DACCVIOL and MMFAR 0x%x\n", + env->v7m.mmfar); + break; + } + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_MEM); + break; + } break; case EXCP_BKPT: if (semihosting_enabled()) { -- 2.7.4 From: Michael Davidsaver <mdavidsaver@gmail.com> The M series MPU is almost the same as the already implemented R profile MPU (v7 PMSA). So all we need to implement here is the MPU register interface in the system register space. This implementation has the same restriction as the R profile MPU that it doesn't permit regions to be sized down smaller than 1K. We also do not yet implement support for MPU_CTRL.HFNMIENA; this bit should if zero disable use of the MPU when running HardFault, NMI or with FAULTMASK set to 1 (ie at an execution priority of less than zero) -- if the MPU is enabled we don't treat these cases any differently. Signed-off-by: Michael Davidsaver <mdavidsaver@gmail.com> Message-id: 1493122030-32191-13-git-send-email-peter.maydell@linaro.org [PMM: Keep all the bits in mpu_ctrl field, rather than using SCTLR bits for them; drop broken HFNMIENA support; various cleanup] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 6 +++ hw/intc/armv7m_nvic.c | 104 ++++++++++++++++++++++++++++++++++++++++++++++++++ target/arm/helper.c | 25 +++++++++++- target/arm/machine.c | 5 ++- 4 files changed, 137 insertions(+), 3 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUARMState { uint32_t dfsr; /* Debug Fault Status Register */ uint32_t mmfar; /* MemManage Fault Address */ uint32_t bfar; /* BusFault Address */ + unsigned mpu_ctrl; /* MPU_CTRL (some bits kept in sctlr_el[1]) */ int exception; } v7m; @@ -XXX,XX +XXX,XX @@ FIELD(V7M_DFSR, DWTTRAP, 2, 1) FIELD(V7M_DFSR, VCATCH, 3, 1) FIELD(V7M_DFSR, EXTERNAL, 4, 1) +/* v7M MPU_CTRL bits */ +FIELD(V7M_MPU_CTRL, ENABLE, 0, 1) +FIELD(V7M_MPU_CTRL, HFNMIENA, 1, 1) +FIELD(V7M_MPU_CTRL, PRIVDEFENA, 2, 1) + /* If adding a feature bit which corresponds to a Linux ELF * HWCAP bit, remember to update the feature-bit-to-hwcap * mapping in linux-user/elfload.c:get_elf_hwcap(). diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/arm.h" #include "hw/arm/armv7m_nvic.h" #include "target/arm/cpu.h" +#include "exec/exec-all.h" #include "qemu/log.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset) case 0xd70: /* ISAR4. */ return 0x01310102; /* TODO: Implement debug registers. */ + case 0xd90: /* MPU_TYPE */ + /* Unified MPU; if the MPU is not present this value is zero */ + return cpu->pmsav7_dregion << 8; + break; + case 0xd94: /* MPU_CTRL */ + return cpu->env.v7m.mpu_ctrl; + case 0xd98: /* MPU_RNR */ + return cpu->env.cp15.c6_rgnr; + case 0xd9c: /* MPU_RBAR */ + case 0xda4: /* MPU_RBAR_A1 */ + case 0xdac: /* MPU_RBAR_A2 */ + case 0xdb4: /* MPU_RBAR_A3 */ + { + int region = cpu->env.cp15.c6_rgnr; + + if (region >= cpu->pmsav7_dregion) { + return 0; + } + return (cpu->env.pmsav7.drbar[region] & 0x1f) | (region & 0xf); + } + case 0xda0: /* MPU_RASR */ + case 0xda8: /* MPU_RASR_A1 */ + case 0xdb0: /* MPU_RASR_A2 */ + case 0xdb8: /* MPU_RASR_A3 */ + { + int region = cpu->env.cp15.c6_rgnr; + + if (region >= cpu->pmsav7_dregion) { + return 0; + } + return ((cpu->env.pmsav7.dracr[region] & 0xffff) << 16) | + (cpu->env.pmsav7.drsr[region] & 0xffff); + } default: qemu_log_mask(LOG_GUEST_ERROR, "NVIC: Bad read offset 0x%x\n", offset); return 0; @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value) qemu_log_mask(LOG_UNIMP, "NVIC: Aux fault status registers unimplemented\n"); break; + case 0xd90: /* MPU_TYPE */ + return; /* RO */ + case 0xd94: /* MPU_CTRL */ + if ((value & + (R_V7M_MPU_CTRL_HFNMIENA_MASK | R_V7M_MPU_CTRL_ENABLE_MASK)) + == R_V7M_MPU_CTRL_HFNMIENA_MASK) { + qemu_log_mask(LOG_GUEST_ERROR, "MPU_CTRL: HFNMIENA and !ENABLE is " + "UNPREDICTABLE\n"); + } + cpu->env.v7m.mpu_ctrl = value & (R_V7M_MPU_CTRL_ENABLE_MASK | + R_V7M_MPU_CTRL_HFNMIENA_MASK | + R_V7M_MPU_CTRL_PRIVDEFENA_MASK); + tlb_flush(CPU(cpu)); + break; + case 0xd98: /* MPU_RNR */ + if (value >= cpu->pmsav7_dregion) { + qemu_log_mask(LOG_GUEST_ERROR, "MPU region out of range %" + PRIu32 "/%" PRIu32 "\n", + value, cpu->pmsav7_dregion); + } else { + cpu->env.cp15.c6_rgnr = value; + } + break; + case 0xd9c: /* MPU_RBAR */ + case 0xda4: /* MPU_RBAR_A1 */ + case 0xdac: /* MPU_RBAR_A2 */ + case 0xdb4: /* MPU_RBAR_A3 */ + { + int region; + + if (value & (1 << 4)) { + /* VALID bit means use the region number specified in this + * value and also update MPU_RNR.REGION with that value. + */ + region = extract32(value, 0, 4); + if (region >= cpu->pmsav7_dregion) { + qemu_log_mask(LOG_GUEST_ERROR, + "MPU region out of range %u/%" PRIu32 "\n", + region, cpu->pmsav7_dregion); + return; + } + cpu->env.cp15.c6_rgnr = region; + } else { + region = cpu->env.cp15.c6_rgnr; + } + + if (region >= cpu->pmsav7_dregion) { + return; + } + + cpu->env.pmsav7.drbar[region] = value & ~0x1f; + tlb_flush(CPU(cpu)); + break; + } + case 0xda0: /* MPU_RASR */ + case 0xda8: /* MPU_RASR_A1 */ + case 0xdb0: /* MPU_RASR_A2 */ + case 0xdb8: /* MPU_RASR_A3 */ + { + int region = cpu->env.cp15.c6_rgnr; + + if (region >= cpu->pmsav7_dregion) { + return; + } + + cpu->env.pmsav7.drsr[region] = value & 0xff3f; + cpu->env.pmsav7.dracr[region] = (value >> 16) & 0x173f; + tlb_flush(CPU(cpu)); + break; + } case 0xf00: /* Software Triggered Interrupt Register */ { /* user mode can only write to STIR if CCR.USERSETMPEND permits it */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t regime_sctlr(CPUARMState *env, ARMMMUIdx mmu_idx) static inline bool regime_translation_disabled(CPUARMState *env, ARMMMUIdx mmu_idx) { + if (arm_feature(env, ARM_FEATURE_M)) { + return !(env->v7m.mpu_ctrl & R_V7M_MPU_CTRL_ENABLE_MASK); + } + if (mmu_idx == ARMMMUIdx_S2NS) { return (env->cp15.hcr_el2 & HCR_VM) == 0; } @@ -XXX,XX +XXX,XX @@ static inline void get_phys_addr_pmsav7_default(CPUARMState *env, } } +static bool pmsav7_use_background_region(ARMCPU *cpu, + ARMMMUIdx mmu_idx, bool is_user) +{ + /* Return true if we should use the default memory map as a + * "background" region if there are no hits against any MPU regions. + */ + CPUARMState *env = &cpu->env; + + if (is_user) { + return false; + } + + if (arm_feature(env, ARM_FEATURE_M)) { + return env->v7m.mpu_ctrl & R_V7M_MPU_CTRL_PRIVDEFENA_MASK; + } else { + return regime_sctlr(env, mmu_idx) & SCTLR_BR; + } +} + static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, int access_type, ARMMMUIdx mmu_idx, hwaddr *phys_ptr, int *prot, uint32_t *fsr) @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, } if (n == -1) { /* no hits */ - if (is_user || !(regime_sctlr(env, mmu_idx) & SCTLR_BR)) { + if (!pmsav7_use_background_region(cpu, mmu_idx, is_user)) { /* background fault */ *fsr = 0; return true; diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static bool m_needed(void *opaque) static const VMStateDescription vmstate_m = { .name = "cpu/m", - .version_id = 3, - .minimum_version_id = 3, + .version_id = 4, + .minimum_version_id = 4, .needed = m_needed, .fields = (VMStateField[]) { VMSTATE_UINT32(env.v7m.vecbase, ARMCPU), @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_m = { VMSTATE_UINT32(env.v7m.dfsr, ARMCPU), VMSTATE_UINT32(env.v7m.mmfar, ARMCPU), VMSTATE_UINT32(env.v7m.bfar, ARMCPU), + VMSTATE_UINT32(env.v7m.mpu_ctrl, ARMCPU), VMSTATE_INT32(env.v7m.exception, ARMCPU), VMSTATE_END_OF_LIST() } -- 2.7.4 Implement HFNMIENA support for the M profile MPU. This bit controls whether the MPU is treated as enabled when executing at execution priorities of less than zero (in NMI, HardFault or with the FAULTMASK bit set). Doing this requires us to use a different MMU index for "running at execution priority < 0", because we will have different access permissions for that case versus the normal case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1493122030-32191-14-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 24 +++++++++++++++++++++++- target/arm/helper.c | 18 +++++++++++++++++- target/arm/translate.c | 1 + 3 files changed, 41 insertions(+), 2 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, * for the accesses done as part of a stage 1 page table walk, rather than * having to walk the stage 2 page table over and over.) * + * R profile CPUs have an MPU, but can use the same set of MMU indexes + * as A profile. They only need to distinguish NS EL0 and NS EL1 (and + * NS EL2 if we ever model a Cortex-R52). + * + * M profile CPUs are rather different as they do not have a true MMU. + * They have the following different MMU indexes: + * User + * Privileged + * Execution priority negative (this is like privileged, but the + * MPU HFNMIENA bit means that it may have different access permission + * check results to normal privileged code, so can't share a TLB). + * * The ARMMMUIdx and the mmu index value used by the core QEMU TLB code * are not quite the same -- different CPU types (most notably M profile * vs A/R profile) would like to use MMU indexes with different semantics, @@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdx { ARMMMUIdx_S2NS = 6 | ARM_MMU_IDX_A, ARMMMUIdx_MUser = 0 | ARM_MMU_IDX_M, ARMMMUIdx_MPriv = 1 | ARM_MMU_IDX_M, + ARMMMUIdx_MNegPri = 2 | ARM_MMU_IDX_M, /* Indexes below here don't have TLBs and are used only for AT system * instructions or for the first stage of an S12 page table walk. */ @@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdxBit { ARMMMUIdxBit_S2NS = 1 << 6, ARMMMUIdxBit_MUser = 1 << 0, ARMMMUIdxBit_MPriv = 1 << 1, + ARMMMUIdxBit_MNegPri = 1 << 2, } ARMMMUIdxBit; #define MMU_USER_IDX 0 @@ -XXX,XX +XXX,XX @@ static inline int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx) case ARM_MMU_IDX_A: return mmu_idx & 3; case ARM_MMU_IDX_M: - return mmu_idx & 1; + return mmu_idx == ARMMMUIdx_MUser ? 0 : 1; default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static inline int cpu_mmu_index(CPUARMState *env, bool ifetch) if (arm_feature(env, ARM_FEATURE_M)) { ARMMMUIdx mmu_idx = el == 0 ? ARMMMUIdx_MUser : ARMMMUIdx_MPriv; + /* Execution priority is negative if FAULTMASK is set or + * we're in a HardFault or NMI handler. + */ + if ((env->v7m.exception > 0 && env->v7m.exception <= 3) + || env->daif & PSTATE_F) { + return arm_to_core_mmu_idx(ARMMMUIdx_MNegPri); + } + return arm_to_core_mmu_idx(mmu_idx); } diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx) case ARMMMUIdx_S1NSE0: case ARMMMUIdx_S1NSE1: case ARMMMUIdx_MPriv: + case ARMMMUIdx_MNegPri: case ARMMMUIdx_MUser: return 1; default: @@ -XXX,XX +XXX,XX @@ static inline bool regime_is_secure(CPUARMState *env, ARMMMUIdx mmu_idx) case ARMMMUIdx_S1E2: case ARMMMUIdx_S2NS: case ARMMMUIdx_MPriv: + case ARMMMUIdx_MNegPri: case ARMMMUIdx_MUser: return false; case ARMMMUIdx_S1E3: @@ -XXX,XX +XXX,XX @@ static inline bool regime_translation_disabled(CPUARMState *env, ARMMMUIdx mmu_idx) { if (arm_feature(env, ARM_FEATURE_M)) { - return !(env->v7m.mpu_ctrl & R_V7M_MPU_CTRL_ENABLE_MASK); + switch (env->v7m.mpu_ctrl & + (R_V7M_MPU_CTRL_ENABLE_MASK | R_V7M_MPU_CTRL_HFNMIENA_MASK)) { + case R_V7M_MPU_CTRL_ENABLE_MASK: + /* Enabled, but not for HardFault and NMI */ + return mmu_idx == ARMMMUIdx_MNegPri; + case R_V7M_MPU_CTRL_ENABLE_MASK | R_V7M_MPU_CTRL_HFNMIENA_MASK: + /* Enabled for all cases */ + return false; + case 0: + default: + /* HFNMIENA set and ENABLE clear is UNPREDICTABLE, but + * we warned about that in armv7m_nvic.c when the guest set it. + */ + return true; + } } if (mmu_idx == ARMMMUIdx_S2NS) { 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 int get_a32_user_mem_index(DisasContext *s) return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0); case ARMMMUIdx_MUser: case ARMMMUIdx_MPriv: + case ARMMMUIdx_MNegPri: return arm_to_core_mmu_idx(ARMMMUIdx_MUser); case ARMMMUIdx_S2NS: default: -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> Multiple I2C commands can be fired simultaneously and the controller execute the commands following these priorities: (1) Master Start Command (2) Master Transmit Command (3) Slave Transmit Command or Master Receive Command (4) Master Stop Command The current code is incorrect with respect to the above sequence and needs to be reworked to handle each individual command. Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 1494827476-1487-2-git-send-email-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/i2c/aspeed_i2c.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/hw/i2c/aspeed_i2c.c b/hw/i2c/aspeed_i2c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/aspeed_i2c.c +++ b/hw/i2c/aspeed_i2c.c @@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_i2c_bus_read(void *opaque, hwaddr offset, static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) { + bus->cmd &= ~0xFFFF; bus->cmd |= value & 0xFFFF; bus->intr_status = 0; @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) bus->intr_status |= I2CD_INTR_TX_ACK; } - } else if (bus->cmd & I2CD_M_TX_CMD) { + /* START command is also a TX command, as the slave address is + * sent on the bus */ + bus->cmd &= ~(I2CD_M_START_CMD | I2CD_M_TX_CMD); + + /* No slave found */ + if (!i2c_bus_busy(bus->bus)) { + return; + } + } + + if (bus->cmd & I2CD_M_TX_CMD) { if (i2c_send(bus->bus, bus->buf)) { bus->intr_status |= (I2CD_INTR_TX_NAK | I2CD_INTR_ABNORMAL); i2c_end_transfer(bus->bus); } else { bus->intr_status |= I2CD_INTR_TX_ACK; } + bus->cmd &= ~I2CD_M_TX_CMD; + } - } else if (bus->cmd & I2CD_M_RX_CMD) { + if (bus->cmd & I2CD_M_RX_CMD) { int ret = i2c_recv(bus->bus); if (ret < 0) { qemu_log_mask(LOG_GUEST_ERROR, "%s: read failed\n", __func__); @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) bus->intr_status |= I2CD_INTR_RX_DONE; } bus->buf = (ret & I2CD_BYTE_BUF_RX_MASK) << I2CD_BYTE_BUF_RX_SHIFT; + bus->cmd &= ~I2CD_M_RX_CMD; } if (bus->cmd & (I2CD_M_STOP_CMD | I2CD_M_S_RX_CMD_LAST)) { @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) i2c_end_transfer(bus->bus); bus->intr_status |= I2CD_INTR_NORMAL_STOP; } + bus->cmd &= ~I2CD_M_STOP_CMD; } - - /* command is handled, reset it and check for interrupts */ - bus->cmd &= ~0xFFFF; - aspeed_i2c_bus_raise_interrupt(bus); } static void aspeed_i2c_bus_write(void *opaque, hwaddr offset, @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_write(void *opaque, hwaddr offset, } aspeed_i2c_bus_handle_cmd(bus, value); + aspeed_i2c_bus_raise_interrupt(bus); break; default: -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> Today, the LAST command is handled with the STOP command but this is incorrect. Also nack the I2C bus when a LAST is issued. Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 1494827476-1487-3-git-send-email-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/i2c/aspeed_i2c.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/hw/i2c/aspeed_i2c.c b/hw/i2c/aspeed_i2c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/aspeed_i2c.c +++ b/hw/i2c/aspeed_i2c.c @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) bus->cmd &= ~I2CD_M_TX_CMD; } - if (bus->cmd & I2CD_M_RX_CMD) { + if (bus->cmd & (I2CD_M_RX_CMD | I2CD_M_S_RX_CMD_LAST)) { int ret = i2c_recv(bus->bus); if (ret < 0) { qemu_log_mask(LOG_GUEST_ERROR, "%s: read failed\n", __func__); @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) bus->intr_status |= I2CD_INTR_RX_DONE; } bus->buf = (ret & I2CD_BYTE_BUF_RX_MASK) << I2CD_BYTE_BUF_RX_SHIFT; - bus->cmd &= ~I2CD_M_RX_CMD; + if (bus->cmd & I2CD_M_S_RX_CMD_LAST) { + i2c_nack(bus->bus); + } + bus->cmd &= ~(I2CD_M_RX_CMD | I2CD_M_S_RX_CMD_LAST); } - if (bus->cmd & (I2CD_M_STOP_CMD | I2CD_M_S_RX_CMD_LAST)) { + if (bus->cmd & I2CD_M_STOP_CMD) { if (!i2c_bus_busy(bus->bus)) { bus->intr_status |= I2CD_INTR_ABNORMAL; } else { -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> The Aspeed I2C controller maintains a state machine in the command register, which is mostly used for debug. Let's start adding a few states to handle abnormal STOP commands. Today, the model uses the busy status of the bus as a condition to do so but it is not precise enough. Also remove the ABNORMAL bit for failing TX commands. This is incorrect with respect to the specs. Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 1494827476-1487-4-git-send-email-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/i2c/aspeed_i2c.c | 36 +++++++++++++++++++++++++++++++++--- 1 file changed, 33 insertions(+), 3 deletions(-) diff --git a/hw/i2c/aspeed_i2c.c b/hw/i2c/aspeed_i2c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/aspeed_i2c.c +++ b/hw/i2c/aspeed_i2c.c @@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_i2c_bus_read(void *opaque, hwaddr offset, } } +static void aspeed_i2c_set_state(AspeedI2CBus *bus, uint8_t state) +{ + bus->cmd &= ~(I2CD_TX_STATE_MASK << I2CD_TX_STATE_SHIFT); + bus->cmd |= (state & I2CD_TX_STATE_MASK) << I2CD_TX_STATE_SHIFT; +} + +static uint8_t aspeed_i2c_get_state(AspeedI2CBus *bus) +{ + return (bus->cmd >> I2CD_TX_STATE_SHIFT) & I2CD_TX_STATE_MASK; +} + +/* + * The state machine needs some refinement. It is only used to track + * invalid STOP commands for the moment. + */ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) { bus->cmd &= ~0xFFFF; @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) bus->intr_status = 0; if (bus->cmd & I2CD_M_START_CMD) { + uint8_t state = aspeed_i2c_get_state(bus) & I2CD_MACTIVE ? + I2CD_MSTARTR : I2CD_MSTART; + + aspeed_i2c_set_state(bus, state); + if (i2c_start_transfer(bus->bus, extract32(bus->buf, 1, 7), extract32(bus->buf, 0, 1))) { bus->intr_status |= I2CD_INTR_TX_NAK; @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) if (!i2c_bus_busy(bus->bus)) { return; } + aspeed_i2c_set_state(bus, I2CD_MACTIVE); } if (bus->cmd & I2CD_M_TX_CMD) { + aspeed_i2c_set_state(bus, I2CD_MTXD); if (i2c_send(bus->bus, bus->buf)) { - bus->intr_status |= (I2CD_INTR_TX_NAK | I2CD_INTR_ABNORMAL); + bus->intr_status |= (I2CD_INTR_TX_NAK); i2c_end_transfer(bus->bus); } else { bus->intr_status |= I2CD_INTR_TX_ACK; } bus->cmd &= ~I2CD_M_TX_CMD; + aspeed_i2c_set_state(bus, I2CD_MACTIVE); } if (bus->cmd & (I2CD_M_RX_CMD | I2CD_M_S_RX_CMD_LAST)) { - int ret = i2c_recv(bus->bus); + int ret; + + aspeed_i2c_set_state(bus, I2CD_MRXD); + ret = i2c_recv(bus->bus); if (ret < 0) { qemu_log_mask(LOG_GUEST_ERROR, "%s: read failed\n", __func__); ret = 0xff; @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) i2c_nack(bus->bus); } bus->cmd &= ~(I2CD_M_RX_CMD | I2CD_M_S_RX_CMD_LAST); + aspeed_i2c_set_state(bus, I2CD_MACTIVE); } if (bus->cmd & I2CD_M_STOP_CMD) { - if (!i2c_bus_busy(bus->bus)) { + if (!(aspeed_i2c_get_state(bus) & I2CD_MACTIVE)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: abnormal stop\n", __func__); bus->intr_status |= I2CD_INTR_ABNORMAL; } else { + aspeed_i2c_set_state(bus, I2CD_MSTOP); i2c_end_transfer(bus->bus); bus->intr_status |= I2CD_INTR_NORMAL_STOP; } bus->cmd &= ~I2CD_M_STOP_CMD; + aspeed_i2c_set_state(bus, I2CD_IDLE); } } -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> Let's add an RTC to the palmetto BMC and a LM75 temperature sensor to the AST2500 EVB to start with. Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 1494827476-1487-5-git-send-email-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ typedef struct AspeedBoardConfig { const char *fmc_model; const char *spi_model; uint32_t num_cs; + void (*i2c_init)(AspeedBoardState *bmc); } AspeedBoardConfig; enum { @@ -XXX,XX +XXX,XX @@ enum { SCU_AST2500_HW_STRAP_ACPI_ENABLE | \ SCU_HW_STRAP_SPI_MODE(SCU_HW_STRAP_SPI_MASTER)) +static void palmetto_bmc_i2c_init(AspeedBoardState *bmc); +static void ast2500_evb_i2c_init(AspeedBoardState *bmc); + static const AspeedBoardConfig aspeed_boards[] = { [PALMETTO_BMC] = { .soc_name = "ast2400-a1", @@ -XXX,XX +XXX,XX @@ static const AspeedBoardConfig aspeed_boards[] = { .fmc_model = "n25q256a", .spi_model = "mx25l25635e", .num_cs = 1, + .i2c_init = palmetto_bmc_i2c_init, }, [AST2500_EVB] = { .soc_name = "ast2500-a1", @@ -XXX,XX +XXX,XX @@ static const AspeedBoardConfig aspeed_boards[] = { .fmc_model = "n25q256a", .spi_model = "mx25l25635e", .num_cs = 1, + .i2c_init = ast2500_evb_i2c_init, }, [ROMULUS_BMC] = { .soc_name = "ast2500-a1", @@ -XXX,XX +XXX,XX @@ static void aspeed_board_init(MachineState *machine, aspeed_board_binfo.ram_size = ram_size; aspeed_board_binfo.loader_start = sc->info->sdram_base; + if (cfg->i2c_init) { + cfg->i2c_init(bmc); + } + arm_load_kernel(ARM_CPU(first_cpu), &aspeed_board_binfo); } +static void palmetto_bmc_i2c_init(AspeedBoardState *bmc) +{ + AspeedSoCState *soc = &bmc->soc; + + /* The palmetto platform expects a ds3231 RTC but a ds1338 is + * enough to provide basic RTC features. Alarms will be missing */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 0), "ds1338", 0x68); +} + static void palmetto_bmc_init(MachineState *machine) { aspeed_board_init(machine, &aspeed_boards[PALMETTO_BMC]); @@ -XXX,XX +XXX,XX @@ static const TypeInfo palmetto_bmc_type = { .class_init = palmetto_bmc_class_init, }; +static void ast2500_evb_i2c_init(AspeedBoardState *bmc) +{ + AspeedSoCState *soc = &bmc->soc; + + /* The AST2500 EVB expects a LM75 but a TMP105 is compatible */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 7), "tmp105", 0x4d); +} + static void ast2500_evb_init(MachineState *machine) { aspeed_board_init(machine, &aspeed_boards[AST2500_EVB]); -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> Largely inspired by the TMP105 temperature sensor, here is a model for the TMP42{1,2,3} temperature sensors. Specs can be found here : http://www.ti.com/lit/gpn/tmp421 Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 1494827476-1487-6-git-send-email-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + hw/misc/tmp421.c | 401 ++++++++++++++++++++++++++++++++++++++++ default-configs/arm-softmmu.mak | 1 + 3 files changed, 403 insertions(+) create mode 100644 hw/misc/tmp421.c diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_APPLESMC) += applesmc.o common-obj-$(CONFIG_MAX111X) += max111x.o common-obj-$(CONFIG_TMP105) += tmp105.o +common-obj-$(CONFIG_TMP421) += tmp421.o common-obj-$(CONFIG_ISA_DEBUG) += debugexit.o common-obj-$(CONFIG_SGA) += sga.o common-obj-$(CONFIG_ISA_TESTDEV) += pc-testdev.o diff --git a/hw/misc/tmp421.c b/hw/misc/tmp421.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/tmp421.c @@ -XXX,XX +XXX,XX @@ +/* + * Texas Instruments TMP421 temperature sensor. + * + * Copyright (c) 2016 IBM Corporation. + * + * Largely inspired by : + * + * Texas Instruments TMP105 temperature sensor. + * + * Copyright (C) 2008 Nokia Corporation + * Written by Andrzej Zaborowski <andrew@openedhand.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 or + * (at your option) version 3 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "hw/hw.h" +#include "hw/i2c/i2c.h" +#include "qapi/error.h" +#include "qapi/visitor.h" + +/* Manufacturer / Device ID's */ +#define TMP421_MANUFACTURER_ID 0x55 +#define TMP421_DEVICE_ID 0x21 +#define TMP422_DEVICE_ID 0x22 +#define TMP423_DEVICE_ID 0x23 + +typedef struct DeviceInfo { + int model; + const char *name; +} DeviceInfo; + +static const DeviceInfo devices[] = { + { TMP421_DEVICE_ID, "tmp421" }, + { TMP422_DEVICE_ID, "tmp422" }, + { TMP423_DEVICE_ID, "tmp423" }, +}; + +typedef struct TMP421State { + /*< private >*/ + I2CSlave i2c; + /*< public >*/ + + int16_t temperature[4]; + + uint8_t status; + uint8_t config[2]; + uint8_t rate; + + uint8_t len; + uint8_t buf[2]; + uint8_t pointer; + +} TMP421State; + +typedef struct TMP421Class { + I2CSlaveClass parent_class; + DeviceInfo *dev; +} TMP421Class; + +#define TYPE_TMP421 "tmp421-generic" +#define TMP421(obj) OBJECT_CHECK(TMP421State, (obj), TYPE_TMP421) + +#define TMP421_CLASS(klass) \ + OBJECT_CLASS_CHECK(TMP421Class, (klass), TYPE_TMP421) +#define TMP421_GET_CLASS(obj) \ + OBJECT_GET_CLASS(TMP421Class, (obj), TYPE_TMP421) + +/* the TMP421 registers */ +#define TMP421_STATUS_REG 0x08 +#define TMP421_STATUS_BUSY (1 << 7) +#define TMP421_CONFIG_REG_1 0x09 +#define TMP421_CONFIG_RANGE (1 << 2) +#define TMP421_CONFIG_SHUTDOWN (1 << 6) +#define TMP421_CONFIG_REG_2 0x0A +#define TMP421_CONFIG_RC (1 << 2) +#define TMP421_CONFIG_LEN (1 << 3) +#define TMP421_CONFIG_REN (1 << 4) +#define TMP421_CONFIG_REN2 (1 << 5) +#define TMP421_CONFIG_REN3 (1 << 6) + +#define TMP421_CONVERSION_RATE_REG 0x0B +#define TMP421_ONE_SHOT 0x0F + +#define TMP421_RESET 0xFC +#define TMP421_MANUFACTURER_ID_REG 0xFE +#define TMP421_DEVICE_ID_REG 0xFF + +#define TMP421_TEMP_MSB0 0x00 +#define TMP421_TEMP_MSB1 0x01 +#define TMP421_TEMP_MSB2 0x02 +#define TMP421_TEMP_MSB3 0x03 +#define TMP421_TEMP_LSB0 0x10 +#define TMP421_TEMP_LSB1 0x11 +#define TMP421_TEMP_LSB2 0x12 +#define TMP421_TEMP_LSB3 0x13 + +static const int32_t mins[2] = { -40000, -55000 }; +static const int32_t maxs[2] = { 127000, 150000 }; + +static void tmp421_get_temperature(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + TMP421State *s = TMP421(obj); + bool ext_range = (s->config[0] & TMP421_CONFIG_RANGE); + int offset = ext_range * 64 * 256; + int64_t value; + int tempid; + + if (sscanf(name, "temperature%d", &tempid) != 1) { + error_setg(errp, "error reading %s: %m", name); + return; + } + + if (tempid >= 4 || tempid < 0) { + error_setg(errp, "error reading %s", name); + return; + } + + value = ((s->temperature[tempid] - offset) * 1000 + 128) / 256; + + visit_type_int(v, name, &value, errp); +} + +/* Units are 0.001 centigrades relative to 0 C. s->temperature is 8.8 + * fixed point, so units are 1/256 centigrades. A simple ratio will do. + */ +static void tmp421_set_temperature(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + TMP421State *s = TMP421(obj); + Error *local_err = NULL; + int64_t temp; + bool ext_range = (s->config[0] & TMP421_CONFIG_RANGE); + int offset = ext_range * 64 * 256; + int tempid; + + visit_type_int(v, name, &temp, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + + if (temp >= maxs[ext_range] || temp < mins[ext_range]) { + error_setg(errp, "value %" PRId64 ".%03" PRIu64 " °C is out of range", + temp / 1000, temp % 1000); + return; + } + + if (sscanf(name, "temperature%d", &tempid) != 1) { + error_setg(errp, "error reading %s: %m", name); + return; + } + + if (tempid >= 4 || tempid < 0) { + error_setg(errp, "error reading %s", name); + return; + } + + s->temperature[tempid] = (int16_t) ((temp * 256 - 128) / 1000) + offset; +} + +static void tmp421_read(TMP421State *s) +{ + TMP421Class *sc = TMP421_GET_CLASS(s); + + s->len = 0; + + switch (s->pointer) { + case TMP421_MANUFACTURER_ID_REG: + s->buf[s->len++] = TMP421_MANUFACTURER_ID; + break; + case TMP421_DEVICE_ID_REG: + s->buf[s->len++] = sc->dev->model; + break; + case TMP421_CONFIG_REG_1: + s->buf[s->len++] = s->config[0]; + break; + case TMP421_CONFIG_REG_2: + s->buf[s->len++] = s->config[1]; + break; + case TMP421_CONVERSION_RATE_REG: + s->buf[s->len++] = s->rate; + break; + case TMP421_STATUS_REG: + s->buf[s->len++] = s->status; + break; + + /* FIXME: check for channel enablement in config registers */ + case TMP421_TEMP_MSB0: + s->buf[s->len++] = (((uint16_t) s->temperature[0]) >> 8); + s->buf[s->len++] = (((uint16_t) s->temperature[0]) >> 0) & 0xf0; + break; + case TMP421_TEMP_MSB1: + s->buf[s->len++] = (((uint16_t) s->temperature[1]) >> 8); + s->buf[s->len++] = (((uint16_t) s->temperature[1]) >> 0) & 0xf0; + break; + case TMP421_TEMP_MSB2: + s->buf[s->len++] = (((uint16_t) s->temperature[2]) >> 8); + s->buf[s->len++] = (((uint16_t) s->temperature[2]) >> 0) & 0xf0; + break; + case TMP421_TEMP_MSB3: + s->buf[s->len++] = (((uint16_t) s->temperature[3]) >> 8); + s->buf[s->len++] = (((uint16_t) s->temperature[3]) >> 0) & 0xf0; + break; + case TMP421_TEMP_LSB0: + s->buf[s->len++] = (((uint16_t) s->temperature[0]) >> 0) & 0xf0; + break; + case TMP421_TEMP_LSB1: + s->buf[s->len++] = (((uint16_t) s->temperature[1]) >> 0) & 0xf0; + break; + case TMP421_TEMP_LSB2: + s->buf[s->len++] = (((uint16_t) s->temperature[2]) >> 0) & 0xf0; + break; + case TMP421_TEMP_LSB3: + s->buf[s->len++] = (((uint16_t) s->temperature[3]) >> 0) & 0xf0; + break; + } +} + +static void tmp421_reset(I2CSlave *i2c); + +static void tmp421_write(TMP421State *s) +{ + switch (s->pointer) { + case TMP421_CONVERSION_RATE_REG: + s->rate = s->buf[0]; + break; + case TMP421_CONFIG_REG_1: + s->config[0] = s->buf[0]; + break; + case TMP421_CONFIG_REG_2: + s->config[1] = s->buf[0]; + break; + case TMP421_RESET: + tmp421_reset(I2C_SLAVE(s)); + break; + } +} + +static int tmp421_rx(I2CSlave *i2c) +{ + TMP421State *s = TMP421(i2c); + + if (s->len < 2) { + return s->buf[s->len++]; + } else { + return 0xff; + } +} + +static int tmp421_tx(I2CSlave *i2c, uint8_t data) +{ + TMP421State *s = TMP421(i2c); + + if (s->len == 0) { + /* first byte is the register pointer for a read or write + * operation */ + s->pointer = data; + s->len++; + } else if (s->len == 1) { + /* second byte is the data to write. The device only supports + * one byte writes */ + s->buf[0] = data; + tmp421_write(s); + } + + return 0; +} + +static int tmp421_event(I2CSlave *i2c, enum i2c_event event) +{ + TMP421State *s = TMP421(i2c); + + if (event == I2C_START_RECV) { + tmp421_read(s); + } + + s->len = 0; + return 0; +} + +static const VMStateDescription vmstate_tmp421 = { + .name = "TMP421", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT8(len, TMP421State), + VMSTATE_UINT8_ARRAY(buf, TMP421State, 2), + VMSTATE_UINT8(pointer, TMP421State), + VMSTATE_UINT8_ARRAY(config, TMP421State, 2), + VMSTATE_UINT8(status, TMP421State), + VMSTATE_UINT8(rate, TMP421State), + VMSTATE_INT16_ARRAY(temperature, TMP421State, 4), + VMSTATE_I2C_SLAVE(i2c, TMP421State), + VMSTATE_END_OF_LIST() + } +}; + +static void tmp421_reset(I2CSlave *i2c) +{ + TMP421State *s = TMP421(i2c); + TMP421Class *sc = TMP421_GET_CLASS(s); + + memset(s->temperature, 0, sizeof(s->temperature)); + s->pointer = 0; + + s->config[0] = 0; /* TMP421_CONFIG_RANGE */ + + /* resistance correction and channel enablement */ + switch (sc->dev->model) { + case TMP421_DEVICE_ID: + s->config[1] = 0x1c; + break; + case TMP422_DEVICE_ID: + s->config[1] = 0x3c; + break; + case TMP423_DEVICE_ID: + s->config[1] = 0x7c; + break; + } + + s->rate = 0x7; /* 8Hz */ + s->status = 0; +} + +static int tmp421_init(I2CSlave *i2c) +{ + TMP421State *s = TMP421(i2c); + + tmp421_reset(&s->i2c); + + return 0; +} + +static void tmp421_initfn(Object *obj) +{ + object_property_add(obj, "temperature0", "int", + tmp421_get_temperature, + tmp421_set_temperature, NULL, NULL, NULL); + object_property_add(obj, "temperature1", "int", + tmp421_get_temperature, + tmp421_set_temperature, NULL, NULL, NULL); + object_property_add(obj, "temperature2", "int", + tmp421_get_temperature, + tmp421_set_temperature, NULL, NULL, NULL); + object_property_add(obj, "temperature3", "int", + tmp421_get_temperature, + tmp421_set_temperature, NULL, NULL, NULL); +} + +static void tmp421_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + I2CSlaveClass *k = I2C_SLAVE_CLASS(klass); + TMP421Class *sc = TMP421_CLASS(klass); + + k->init = tmp421_init; + k->event = tmp421_event; + k->recv = tmp421_rx; + k->send = tmp421_tx; + dc->vmsd = &vmstate_tmp421; + sc->dev = (DeviceInfo *) data; +} + +static const TypeInfo tmp421_info = { + .name = TYPE_TMP421, + .parent = TYPE_I2C_SLAVE, + .instance_size = sizeof(TMP421State), + .instance_init = tmp421_initfn, + .class_init = tmp421_class_init, +}; + +static void tmp421_register_types(void) +{ + int i; + + type_register_static(&tmp421_info); + for (i = 0; i < ARRAY_SIZE(devices); ++i) { + TypeInfo ti = { + .name = devices[i].name, + .parent = TYPE_TMP421, + .class_init = tmp421_class_init, + .class_data = (void *) &devices[i], + }; + type_register(&ti); + } +} + +type_init(tmp421_register_types) diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/arm-softmmu.mak +++ b/default-configs/arm-softmmu.mak @@ -XXX,XX +XXX,XX @@ CONFIG_TWL92230=y CONFIG_TSC2005=y CONFIG_LM832X=y CONFIG_TMP105=y +CONFIG_TMP421=y CONFIG_STELLARIS=y CONFIG_STELLARIS_INPUT=y CONFIG_STELLARIS_ENET=y -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> Temperatures can be changed from the monitor with : (qemu) qom-set /machine/unattached/device[2] temperature0 12000 Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 1494827476-1487-7-git-send-email-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ static void aspeed_board_init(MachineState *machine, static void palmetto_bmc_i2c_init(AspeedBoardState *bmc) { AspeedSoCState *soc = &bmc->soc; + DeviceState *dev; /* The palmetto platform expects a ds3231 RTC but a ds1338 is * enough to provide basic RTC features. Alarms will be missing */ i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 0), "ds1338", 0x68); + + /* add a TMP423 temperature sensor */ + dev = i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 2), + "tmp423", 0x4c); + object_property_set_int(OBJECT(dev), 31000, "temperature0", &error_abort); + object_property_set_int(OBJECT(dev), 28000, "temperature1", &error_abort); + object_property_set_int(OBJECT(dev), 20000, "temperature2", &error_abort); + object_property_set_int(OBJECT(dev), 110000, "temperature3", &error_abort); } static void palmetto_bmc_init(MachineState *machine) -- 2.7.4 From: Andrew Jones <drjones@redhat.com> Cc: Shannon Zhao <zhaoshenglong@huawei.com> Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Reviewed-by: Shannon Zhao <shannon.zhao@linaro.org> Message-id: 20170529173751.3443-2-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt-acpi-build.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -XXX,XX +XXX,XX @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) if (nb_numa_nodes > 0) { acpi_add_table(table_offsets, tables_blob); build_srat(tables_blob, tables->linker, vms); + if (have_numa_distance) { + acpi_add_table(table_offsets, tables_blob); + build_slit(tables_blob, tables->linker); + } } if (its_class_name() && !vmc->no_its) { -- 2.7.4 From: Andrew Jones <drjones@redhat.com> This is based on patch Shannon Zhao originally posted. Cc: Shannon Zhao <zhaoshenglong@huawei.com> Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Shannon Zhao <shannon.zhao@linaro.org> Message-id: 20170529173751.3443-3-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void create_fdt(VirtMachineState *vms) "clk24mhz"); qemu_fdt_setprop_cell(fdt, "/apb-pclk", "phandle", vms->clock_phandle); + if (have_numa_distance) { + int size = nb_numa_nodes * nb_numa_nodes * 3 * sizeof(uint32_t); + uint32_t *matrix = g_malloc0(size); + int idx, i, j; + + for (i = 0; i < nb_numa_nodes; i++) { + for (j = 0; j < nb_numa_nodes; j++) { + idx = (i * nb_numa_nodes + j) * 3; + matrix[idx + 0] = cpu_to_be32(i); + matrix[idx + 1] = cpu_to_be32(j); + matrix[idx + 2] = cpu_to_be32(numa_info[i].distance[j]); + } + } + + qemu_fdt_add_subnode(fdt, "/distance-map"); + qemu_fdt_setprop_string(fdt, "/distance-map", "compatible", + "numa-distance-map-v1"); + qemu_fdt_setprop(fdt, "/distance-map", "distance-matrix", + matrix, size); + g_free(matrix); + } } static void fdt_add_psci_node(const VirtMachineState *vms) -- 2.7.4 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