Most of this is the Neon decodetree patches, followed by Edgar's versal cleanups. thanks -- PMM The following changes since commit 2ef486e76d64436be90f7359a3071fb2a56ce835: Merge remote-tracking branch 'remotes/marcel/tags/rdma-pull-request' into staging (2020-05-03 14:12:56 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200504 for you to fetch changes up to 9aefc6cf9b73f66062d2f914a0136756e7a28211: target/arm: Move gen_ function typedefs to translate.h (2020-05-04 12:59:26 +0100) ---------------------------------------------------------------- target-arm queue: * Start of conversion of Neon insns to decodetree * versal board: support SD and RTC * Implement ARMv8.2-TTS2UXN * Make VQDMULL undefined when U=1 * Some minor code cleanups ---------------------------------------------------------------- Edgar E. Iglesias (11): hw/arm: versal: Remove inclusion of arm_gicv3_common.h hw/arm: versal: Move misplaced comment hw/arm: versal-virt: Fix typo xlnx-ve -> xlnx-versal hw/arm: versal: Embed the UARTs into the SoC type hw/arm: versal: Embed the GEMs into the SoC type hw/arm: versal: Embed the ADMAs into the SoC type hw/arm: versal: Embed the APUs into the SoC type hw/arm: versal: Add support for SD hw/arm: versal: Add support for the RTC hw/arm: versal-virt: Add support for SD hw/arm: versal-virt: Add support for the RTC Fredrik Strupe (1): target/arm: Make VQDMULL undefined when U=1 Peter Maydell (25): target/arm: Don't use a TLB for ARMMMUIdx_Stage2 target/arm: Use enum constant in get_phys_addr_lpae() call target/arm: Add new 's1_is_el0' argument to get_phys_addr_lpae() target/arm: Implement ARMv8.2-TTS2UXN target/arm: Use correct variable for setting 'max' cpu's ID_AA64DFR0 target/arm/translate-vfp.inc.c: Remove duplicate simd_r32 check target/arm: Don't allow Thumb Neon insns without FEATURE_NEON target/arm: Add stubs for AArch32 Neon decodetree target/arm: Convert VCMLA (vector) to decodetree target/arm: Convert VCADD (vector) to decodetree target/arm: Convert V[US]DOT (vector) to decodetree target/arm: Convert VFM[AS]L (vector) to decodetree target/arm: Convert VCMLA (scalar) to decodetree target/arm: Convert V[US]DOT (scalar) to decodetree target/arm: Convert VFM[AS]L (scalar) to decodetree target/arm: Convert Neon load/store multiple structures to decodetree target/arm: Convert Neon 'load single structure to all lanes' to decodetree target/arm: Convert Neon 'load/store single structure' to decodetree target/arm: Convert Neon 3-reg-same VADD/VSUB to decodetree target/arm: Convert Neon 3-reg-same logic ops to decodetree target/arm: Convert Neon 3-reg-same VMAX/VMIN to decodetree target/arm: Convert Neon 3-reg-same comparisons to decodetree target/arm: Convert Neon 3-reg-same VQADD/VQSUB to decodetree target/arm: Convert Neon 3-reg-same VMUL, VMLA, VMLS, VSHL to decodetree target/arm: Move gen_ function typedefs to translate.h Philippe Mathieu-Daudé (2): hw/arm/mps2-tz: Use TYPE_IOTKIT instead of hardcoded string target/arm: Use uint64_t for midr field in CPU state struct include/hw/arm/xlnx-versal.h | 31 +- target/arm/cpu-param.h | 2 +- target/arm/cpu.h | 38 ++- target/arm/translate-a64.h | 9 - target/arm/translate.h | 26 ++ target/arm/neon-dp.decode | 86 +++++ target/arm/neon-ls.decode | 52 +++ target/arm/neon-shared.decode | 66 ++++ hw/arm/mps2-tz.c | 2 +- hw/arm/xlnx-versal-virt.c | 74 ++++- hw/arm/xlnx-versal.c | 115 +++++-- target/arm/cpu.c | 3 +- target/arm/cpu64.c | 8 +- target/arm/helper.c | 183 ++++------ target/arm/translate-a64.c | 17 - target/arm/translate-neon.inc.c | 714 +++++++++++++++++++++++++++++++++++++++ target/arm/translate-vfp.inc.c | 6 - target/arm/translate.c | 716 +++------------------------------------- target/arm/Makefile.objs | 18 + 19 files changed, 1302 insertions(+), 864 deletions(-) create mode 100644 target/arm/neon-dp.decode create mode 100644 target/arm/neon-ls.decode create mode 100644 target/arm/neon-shared.decode create mode 100644 target/arm/translate-neon.inc.c From: Fredrik Strupe <fredrik@strupe.net> According to Arm ARM, VQDMULL is only valid when U=0, while having U=1 is unallocated. Signed-off-by: Fredrik Strupe <fredrik@strupe.net> Fixes: 695272dcb976 ("target-arm: Handle UNDEF cases for Neon 3-regs-different-widths") Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 int disas_neon_data_insn(DisasContext *s, uint32_t insn) {0, 0, 0, 0}, /* VMLSL */ {0, 0, 0, 9}, /* VQDMLSL */ {0, 0, 0, 0}, /* Integer VMULL */ - {0, 0, 0, 1}, /* VQDMULL */ + {0, 0, 0, 9}, /* VQDMULL */ {0, 0, 0, 0xa}, /* Polynomial VMULL */ {0, 0, 0, 7}, /* Reserved: always UNDEF */ }; -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> By using the TYPE_* definitions for devices, we can: - quickly find where devices are used with 'git-grep' - easily rename a device (one-line change). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200428154650.21991-1-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/mps2-tz.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) exit(EXIT_FAILURE); } - sysbus_init_child_obj(OBJECT(machine), "iotkit", &mms->iotkit, + sysbus_init_child_obj(OBJECT(machine), TYPE_IOTKIT, &mms->iotkit, sizeof(mms->iotkit), mmc->armsse_type); iotkitdev = DEVICE(&mms->iotkit); object_property_set_link(OBJECT(&mms->iotkit), OBJECT(system_memory), -- 2.20.1 We define ARMMMUIdx_Stage2 as being an MMU index which uses a QEMU TLB. However we never actually use the TLB -- all stage 2 lookups are done by direct calls to get_phys_addr_lpae() followed by a physical address load via address_space_ld*(). Remove Stage2 from the list of ARM MMU indexes which correspond to real core MMU indexes, and instead put it in the set of "NOTLB" ARM MMU indexes. This allows us to drop NB_MMU_MODES to 11. It also means we can safely add support for the ARMv8.3-TTS2UXN extension, which adds permission bits to the stage 2 descriptors which define execute permission separatel for EL0 and EL1; supporting that while keeping Stage2 in a QEMU TLB would require us to use separate TLBs for "Stage2 for an EL0 access" and "Stage2 for an EL1 access", which is a lot of extra complication given we aren't even using the QEMU TLB. In the process of updating the comment on our MMU index use, fix a couple of other minor errors: * NS EL2 EL2&0 was missing from the list in the comment * some text hadn't been updated from when we bumped NB_MMU_MODES above 8 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200330210400.11724-2-peter.maydell@linaro.org --- target/arm/cpu-param.h | 2 +- target/arm/cpu.h | 21 +++++--- target/arm/helper.c | 112 ++++------------------------------------- 3 files changed, 27 insertions(+), 108 deletions(-) diff --git a/target/arm/cpu-param.h b/target/arm/cpu-param.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-param.h +++ b/target/arm/cpu-param.h @@ -XXX,XX +XXX,XX @@ # define TARGET_PAGE_BITS_MIN 10 #endif -#define NB_MMU_MODES 12 +#define NB_MMU_MODES 11 #endif 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 @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync); * handling via the TLB. The only way to do a stage 1 translation without * the immediate stage 2 translation is via the ATS or AT system insns, * which can be slow-pathed and always do a page table walk. + * The only use of stage 2 translations is either as part of an s1+2 + * lookup or when loading the descriptors during a stage 1 page table walk, + * and in both those cases we don't use the TLB. * 4. we can also safely fold together the "32 bit EL3" and "64 bit EL3" * translation regimes, because they map reasonably well to each other * and they can't both be active at the same time. @@ -XXX,XX +XXX,XX @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync); * NS EL1 EL1&0 stage 1+2 (aka NS PL1) * NS EL1 EL1&0 stage 1+2 +PAN * NS EL0 EL2&0 + * NS EL2 EL2&0 * NS EL2 EL2&0 +PAN * NS EL2 (aka NS PL2) * S EL0 EL1&0 (aka S PL0) * S EL1 EL1&0 (not used if EL3 is 32 bit) * S EL1 EL1&0 +PAN * S EL3 (aka S PL1) - * NS EL1&0 stage 2 * - * for a total of 12 different mmu_idx. + * for a total of 11 different mmu_idx. * * 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 @@ -XXX,XX +XXX,XX @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync); * 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 + * can avoid having to set NB_MMU_MODES to "total number of A profile MMU + * modes + total number of M profile MMU modes". 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 @@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdx { ARMMMUIdx_SE10_1_PAN = 9 | ARM_MMU_IDX_A, ARMMMUIdx_SE3 = 10 | ARM_MMU_IDX_A, - ARMMMUIdx_Stage2 = 11 | ARM_MMU_IDX_A, - /* * These are not allocated 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 ARMMMUIdx { ARMMMUIdx_Stage1_E0 = 0 | ARM_MMU_IDX_NOTLB, ARMMMUIdx_Stage1_E1 = 1 | ARM_MMU_IDX_NOTLB, ARMMMUIdx_Stage1_E1_PAN = 2 | ARM_MMU_IDX_NOTLB, + /* + * Not allocated a TLB: used only for second stage of an S12 page + * table walk, or for descriptor loads during first stage of an S1 + * page table walk. Note that if we ever want to have a TLB for this + * then various TLB flush insns which currently are no-ops or flush + * only stage 1 MMU indexes will need to change to flush stage 2. + */ + ARMMMUIdx_Stage2 = 3 | ARM_MMU_IDX_NOTLB, /* * M-profile. @@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdxBit { TO_CORE_BIT(SE10_1), TO_CORE_BIT(SE10_1_PAN), TO_CORE_BIT(SE3), - TO_CORE_BIT(Stage2), TO_CORE_BIT(MUser), TO_CORE_BIT(MPriv), 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, tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_E10_1 | ARMMMUIdxBit_E10_1_PAN | - ARMMMUIdxBit_E10_0 | - ARMMMUIdxBit_Stage2); + ARMMMUIdxBit_E10_0); } 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, tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_E10_1 | ARMMMUIdxBit_E10_1_PAN | - ARMMMUIdxBit_E10_0 | - ARMMMUIdxBit_Stage2); + ARMMMUIdxBit_E10_0); } -static void tlbiipas2_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate by IPA. This has to invalidate any structures that - * contain only stage 2 translation information, but does not need - * to apply to structures that contain combined stage 1 and stage 2 - * translation information. - * This must NOP if EL2 isn't implemented or SCR_EL3.NS is zero. - */ - CPUState *cs = env_cpu(env); - uint64_t pageaddr; - - if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) { - return; - } - - pageaddr = sextract64(value << 12, 0, 40); - - tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_Stage2); -} - -static void tlbiipas2_is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - uint64_t pageaddr; - - if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) { - return; - } - - pageaddr = sextract64(value << 12, 0, 40); - - tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - ARMMMUIdxBit_Stage2); -} static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) @@ -XXX,XX +XXX,XX @@ static void vttbr_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_E10_1 | ARMMMUIdxBit_E10_1_PAN | - ARMMMUIdxBit_E10_0 | - ARMMMUIdxBit_Stage2); + ARMMMUIdxBit_E10_0); raw_write(env, ri, value); } } @@ -XXX,XX +XXX,XX @@ static int alle1_tlbmask(CPUARMState *env) return ARMMMUIdxBit_SE10_1 | ARMMMUIdxBit_SE10_1_PAN | ARMMMUIdxBit_SE10_0; - } else if (arm_feature(env, ARM_FEATURE_EL2)) { - return ARMMMUIdxBit_E10_1 | - ARMMMUIdxBit_E10_1_PAN | - ARMMMUIdxBit_E10_0 | - ARMMMUIdxBit_Stage2; } else { return ARMMMUIdxBit_E10_1 | ARMMMUIdxBit_E10_1_PAN | @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, ARMMMUIdxBit_SE3); } -static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate by IPA. This has to invalidate any structures that - * contain only stage 2 translation information, but does not need - * to apply to structures that contain combined stage 1 and stage 2 - * translation information. - * This must NOP if EL2 isn't implemented or SCR_EL3.NS is zero. - */ - ARMCPU *cpu = env_archcpu(env); - CPUState *cs = CPU(cpu); - uint64_t pageaddr; - - if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) { - return; - } - - pageaddr = sextract64(value << 12, 0, 48); - - tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_Stage2); -} - -static void tlbi_aa64_ipas2e1is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - uint64_t pageaddr; - - if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) { - return; - } - - pageaddr = sextract64(value << 12, 0, 48); - - tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - ARMMMUIdxBit_Stage2); -} - static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v8_cp_reginfo[] = { .writefn = tlbi_aa64_vae1_write }, { .name = "TLBI_IPAS2E1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_ipas2e1is_write }, + .access = PL2_W, .type = ARM_CP_NOP }, { .name = "TLBI_IPAS2LE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_ipas2e1is_write }, + .access = PL2_W, .type = ARM_CP_NOP }, { .name = "TLBI_ALLE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 4, .access = PL2_W, .type = ARM_CP_NO_RAW, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v8_cp_reginfo[] = { .writefn = tlbi_aa64_alle1is_write }, { .name = "TLBI_IPAS2E1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_ipas2e1_write }, + .access = PL2_W, .type = ARM_CP_NOP }, { .name = "TLBI_IPAS2LE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_ipas2e1_write }, + .access = PL2_W, .type = ARM_CP_NOP }, { .name = "TLBI_ALLE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 4, .access = PL2_W, .type = ARM_CP_NO_RAW, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v8_cp_reginfo[] = { .writefn = tlbimva_hyp_is_write }, { .name = "TLBIIPAS2", .cp = 15, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 1, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbiipas2_write }, + .type = ARM_CP_NOP, .access = PL2_W }, { .name = "TLBIIPAS2IS", .cp = 15, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 1, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbiipas2_is_write }, + .type = ARM_CP_NOP, .access = PL2_W }, { .name = "TLBIIPAS2L", .cp = 15, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 5, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbiipas2_write }, + .type = ARM_CP_NOP, .access = PL2_W }, { .name = "TLBIIPAS2LIS", .cp = 15, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 5, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbiipas2_is_write }, + .type = ARM_CP_NOP, .access = PL2_W }, /* 32 bit cache operations */ { .name = "ICIALLUIS", .cp = 15, .opc1 = 0, .crn = 7, .crm = 1, .opc2 = 0, .type = ARM_CP_NOP, .access = PL1_W, .accessfn = aa64_cacheop_pou_access }, -- 2.20.1 The access_type argument to get_phys_addr_lpae() is an MMUAccessType; use the enum constant MMU_DATA_LOAD rather than a literal 0 when we call it in S1_ptw_translate(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200330210400.11724-3-peter.maydell@linaro.org --- target/arm/helper.c | 5 +++-- 1 file changed, 3 insertions(+), 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 hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx, pcacheattrs = &cacheattrs; } - ret = get_phys_addr_lpae(env, addr, 0, ARMMMUIdx_Stage2, &s2pa, - &txattrs, &s2prot, &s2size, fi, pcacheattrs); + ret = get_phys_addr_lpae(env, addr, MMU_DATA_LOAD, ARMMMUIdx_Stage2, + &s2pa, &txattrs, &s2prot, &s2size, fi, + pcacheattrs); if (ret) { assert(fi->type != ARMFault_None); fi->s2addr = addr; -- 2.20.1 For ARMv8.2-TTS2UXN, the stage 2 page table walk wants to know whether the stage 1 access is for EL0 or not, because whether exec permission is given can depend on whether this is an EL0 or EL1 access. Add a new argument to get_phys_addr_lpae() so the call sites can pass this information in. Since get_phys_addr_lpae() doesn't already have a doc comment, add one so we have a place to put the documentation of the semantics of the new s1_is_el0 argument. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200330210400.11724-4-peter.maydell@linaro.org --- target/arm/helper.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, MMUAccessType access_type, ARMMMUIdx mmu_idx, + bool s1_is_el0, hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot, target_ulong *page_size_ptr, ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs); @@ -XXX,XX +XXX,XX @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx, } ret = get_phys_addr_lpae(env, addr, MMU_DATA_LOAD, ARMMMUIdx_Stage2, + false, &s2pa, &txattrs, &s2prot, &s2size, fi, pcacheattrs); if (ret) { @@ -XXX,XX +XXX,XX @@ static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va, }; } +/** + * get_phys_addr_lpae: perform one stage of page table walk, LPAE format + * + * Returns false if the translation was successful. Otherwise, phys_ptr, attrs, + * prot and page_size may not be filled in, and the populated fsr value provides + * information on why the translation aborted, in the format of a long-format + * DFSR/IFSR fault register, with the following caveats: + * * the WnR bit is never set (the caller must do this). + * + * @env: CPUARMState + * @address: virtual address to get physical address for + * @access_type: MMU_DATA_LOAD, MMU_DATA_STORE or MMU_INST_FETCH + * @mmu_idx: MMU index indicating required translation regime + * @s1_is_el0: if @mmu_idx is ARMMMUIdx_Stage2 (so this is a stage 2 page table + * walk), must be true if this is stage 2 of a stage 1+2 walk for an + * EL0 access). If @mmu_idx is anything else, @s1_is_el0 is ignored. + * @phys_ptr: set to the physical address corresponding to the virtual address + * @attrs: set to the memory transaction attributes to use + * @prot: set to the permissions for the page containing phys_ptr + * @page_size_ptr: set to the size of the page containing phys_ptr + * @fi: set to fault info if the translation fails + * @cacheattrs: (if non-NULL) set to the cacheability/shareability attributes + */ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, MMUAccessType access_type, ARMMMUIdx mmu_idx, + bool s1_is_el0, hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot, target_ulong *page_size_ptr, ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs) @@ -XXX,XX +XXX,XX @@ bool get_phys_addr(CPUARMState *env, target_ulong address, /* S1 is done. Now do S2 translation. */ ret = get_phys_addr_lpae(env, ipa, access_type, ARMMMUIdx_Stage2, + mmu_idx == ARMMMUIdx_E10_0, phys_ptr, attrs, &s2_prot, page_size, fi, cacheattrs != NULL ? &cacheattrs2 : NULL); @@ -XXX,XX +XXX,XX @@ bool get_phys_addr(CPUARMState *env, target_ulong address, } if (regime_using_lpae_format(env, mmu_idx)) { - return get_phys_addr_lpae(env, address, access_type, mmu_idx, + return get_phys_addr_lpae(env, address, access_type, mmu_idx, false, phys_ptr, attrs, prot, page_size, fi, cacheattrs); } else if (regime_sctlr(env, mmu_idx) & SCTLR_XP) { -- 2.20.1 The ARMv8.2-TTS2UXN feature extends the XN field in stage 2 translation table descriptors from just bit [54] to bits [54:53], allowing stage 2 to control execution permissions separately for EL0 and EL1. Implement the new semantics of the XN field and enable the feature for our 'max' CPU. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200330210400.11724-5-peter.maydell@linaro.org --- target/arm/cpu.h | 15 +++++++++++++++ target/arm/cpu.c | 1 + target/arm/cpu64.c | 2 ++ target/arm/helper.c | 37 +++++++++++++++++++++++++++++++------ 4 files changed, 49 insertions(+), 6 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_ccidx(const ARMISARegisters *id) return FIELD_EX32(id->id_mmfr4, ID_MMFR4, CCIDX) != 0; } +static inline bool isar_feature_aa32_tts2uxn(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, XNX) != 0; +} + /* * 64-bit feature tests via id registers. */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0; } +static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0; +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_any_ccidx(const ARMISARegisters *id) return isar_feature_aa64_ccidx(id) || isar_feature_aa32_ccidx(id); } +static inline bool isar_feature_any_tts2uxn(const ARMISARegisters *id) +{ + return isar_feature_aa64_tts2uxn(id) || isar_feature_aa32_tts2uxn(id); +} + /* * Forward to the above feature tests given an ARMCPU pointer. */ 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_max_initfn(Object *obj) t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */ t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* TTCNP */ + t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* TTS2UXN */ cpu->isar.id_mmfr4 = t; } #endif diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64MMFR1, VH, 1); t = FIELD_DP64(t, ID_AA64MMFR1, PAN, 2); /* ATS1E1 */ t = FIELD_DP64(t, ID_AA64MMFR1, VMIDBITS, 2); /* VMID16 */ + t = FIELD_DP64(t, ID_AA64MMFR1, XNX, 1); /* TTS2UXN */ cpu->isar.id_aa64mmfr1 = t; t = cpu->isar.id_aa64mmfr2; @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) u = FIELD_DP32(u, ID_MMFR4, HPDS, 1); /* AA32HPD */ u = FIELD_DP32(u, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ u = FIELD_DP32(u, ID_MMFR4, CNP, 1); /* TTCNP */ + u = FIELD_DP32(u, ID_MMFR4, XNX, 1); /* TTS2UXN */ cpu->isar.id_mmfr4 = u; u = cpu->isar.id_aa64dfr0; 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 @@ simple_ap_to_rw_prot(CPUARMState *env, ARMMMUIdx mmu_idx, int ap) * * @env: CPUARMState * @s2ap: The 2-bit stage2 access permissions (S2AP) - * @xn: XN (execute-never) bit + * @xn: XN (execute-never) bits + * @s1_is_el0: true if this is S2 of an S1+2 walk for EL0 */ -static int get_S2prot(CPUARMState *env, int s2ap, int xn) +static int get_S2prot(CPUARMState *env, int s2ap, int xn, bool s1_is_el0) { int prot = 0; @@ -XXX,XX +XXX,XX @@ static int get_S2prot(CPUARMState *env, int s2ap, int xn) if (s2ap & 2) { prot |= PAGE_WRITE; } - if (!xn) { - if (arm_el_is_aa64(env, 2) || prot & PAGE_READ) { + + if (cpu_isar_feature(any_tts2uxn, env_archcpu(env))) { + switch (xn) { + case 0: prot |= PAGE_EXEC; + break; + case 1: + if (s1_is_el0) { + prot |= PAGE_EXEC; + } + break; + case 2: + break; + case 3: + if (!s1_is_el0) { + prot |= PAGE_EXEC; + } + break; + default: + g_assert_not_reached(); + } + } else { + if (!extract32(xn, 1, 1)) { + if (arm_el_is_aa64(env, 2) || prot & PAGE_READ) { + prot |= PAGE_EXEC; + } } } return prot; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, } ap = extract32(attrs, 4, 2); - xn = extract32(attrs, 12, 1); if (mmu_idx == ARMMMUIdx_Stage2) { ns = true; - *prot = get_S2prot(env, ap, xn); + xn = extract32(attrs, 11, 2); + *prot = get_S2prot(env, ap, xn, s1_is_el0); } else { ns = extract32(attrs, 3, 1); + xn = extract32(attrs, 12, 1); pxn = extract32(attrs, 11, 1); *prot = get_S1prot(env, mmu_idx, aarch64, ap, ns, xn, pxn); } -- 2.20.1 In aarch64_max_initfn() we update both 32-bit and 64-bit ID registers. The intended pattern is that for 64-bit ID registers we use FIELD_DP64 and the uint64_t 't' register, while 32-bit ID registers use FIELD_DP32 and the uint32_t 'u' register. For ID_AA64DFR0 we accidentally used 'u', meaning that the top 32 bits of this 64-bit ID register would end up always zero. Luckily at the moment that's what they should be anyway, so this bug has no visible effects. Use the right-sized variable. Fixes: 3bec78447a958d481991 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200423110915.10527-1-peter.maydell@linaro.org --- target/arm/cpu64.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) u = FIELD_DP32(u, ID_MMFR4, XNX, 1); /* TTS2UXN */ cpu->isar.id_mmfr4 = u; - u = cpu->isar.id_aa64dfr0; - u = FIELD_DP64(u, ID_AA64DFR0, PMUVER, 5); /* v8.4-PMU */ - cpu->isar.id_aa64dfr0 = u; + t = cpu->isar.id_aa64dfr0; + t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 5); /* v8.4-PMU */ + cpu->isar.id_aa64dfr0 = t; u = cpu->isar.id_dfr0; u = FIELD_DP32(u, ID_DFR0, PERFMON, 5); /* v8.4-PMU */ -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> MIDR_EL1 is a 64-bit system register with the top 32-bit being RES0. Represent it in QEMU's ARMCPU struct with a uint64_t, not a uint32_t. This fixes an error when compiling with -Werror=conversion because we were manipulating the register value using a local uint64_t variable: target/arm/cpu64.c: In function ‘aarch64_max_initfn’: target/arm/cpu64.c:628:21: error: conversion from ‘uint64_t’ {aka ‘long unsigned int’} to ‘uint32_t’ {aka ‘unsigned int’} may change value [-Werror=conversion] 628 | cpu->midr = t; | ^ and future-proofs us against a possible future architecture change using some of the top 32 bits. Suggested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Suggested-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20200428172634.29707-1-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 +- target/arm/cpu.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ struct ARMCPU { uint64_t id_aa64dfr0; uint64_t id_aa64dfr1; } isar; - uint32_t midr; + uint64_t midr; uint32_t revidr; uint32_t reset_fpsid; uint32_t ctr; 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 const ARMCPUInfo arm_cpus[] = { static Property arm_cpu_properties[] = { DEFINE_PROP_BOOL("start-powered-off", ARMCPU, start_powered_off, false), DEFINE_PROP_UINT32("psci-conduit", ARMCPU, psci_conduit, 0), - DEFINE_PROP_UINT32("midr", ARMCPU, midr, 0), + DEFINE_PROP_UINT64("midr", ARMCPU, midr, 0), DEFINE_PROP_UINT64("mp-affinity", ARMCPU, mp_affinity, ARM64_AFFINITY_INVALID), DEFINE_PROP_INT32("node-id", ARMCPU, node_id, CPU_UNSET_NUMA_NODE_ID), -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Remove inclusion of arm_gicv3_common.h, this already gets included via xlnx-versal.h. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200427181649.26851-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-versal.c | 1 - 1 file changed, 1 deletion(-) diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/boot.h" #include "kvm_arm.h" #include "hw/misc/unimp.h" -#include "hw/intc/arm_gicv3_common.h" #include "hw/arm/xlnx-versal.h" #include "hw/char/pl011.h" -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Move misplaced comment. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200427181649.26851-3-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-versal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s) obj = object_new(XLNX_VERSAL_ACPU_TYPE); if (!obj) { - /* Secondary CPUs start in PSCI powered-down state */ error_report("Unable to create apu.cpu[%d] of type %s", i, XLNX_VERSAL_ACPU_TYPE); exit(EXIT_FAILURE); @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s) object_property_set_int(obj, s->cfg.psci_conduit, "psci-conduit", &error_abort); if (i) { + /* Secondary CPUs start in PSCI powered-down state */ object_property_set_bool(obj, true, "start-powered-off", &error_abort); } -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Fix typo xlnx-ve -> xlnx-versal. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200427181649.26851-4-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-versal-virt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine) psci_conduit = QEMU_PSCI_CONDUIT_SMC; } - sysbus_init_child_obj(OBJECT(machine), "xlnx-ve", &s->soc, + sysbus_init_child_obj(OBJECT(machine), "xlnx-versal", &s->soc, sizeof(s->soc), TYPE_XLNX_VERSAL); object_property_set_link(OBJECT(&s->soc), OBJECT(machine->ram), "ddr", &error_abort); -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Embed the UARTs into the SoC type. Suggested-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200427181649.26851-5-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 3 ++- hw/arm/xlnx-versal.c | 12 ++++++------ 2 files changed, 8 insertions(+), 7 deletions(-) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/arm/boot.h" #include "hw/intc/arm_gicv3.h" +#include "hw/char/pl011.h" #define TYPE_XLNX_VERSAL "xlnx-versal" #define XLNX_VERSAL(obj) OBJECT_CHECK(Versal, (obj), TYPE_XLNX_VERSAL) @@ -XXX,XX +XXX,XX @@ typedef struct Versal { MemoryRegion mr_ocm; struct { - SysBusDevice *uart[XLNX_VERSAL_NR_UARTS]; + PL011State uart[XLNX_VERSAL_NR_UARTS]; SysBusDevice *gem[XLNX_VERSAL_NR_GEMS]; SysBusDevice *adma[XLNX_VERSAL_NR_ADMAS]; } iou; diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ #include "kvm_arm.h" #include "hw/misc/unimp.h" #include "hw/arm/xlnx-versal.h" -#include "hw/char/pl011.h" #define XLNX_VERSAL_ACPU_TYPE ARM_CPU_TYPE_NAME("cortex-a72") #define GEM_REVISION 0x40070106 @@ -XXX,XX +XXX,XX @@ static void versal_create_uarts(Versal *s, qemu_irq *pic) DeviceState *dev; MemoryRegion *mr; - dev = qdev_create(NULL, TYPE_PL011); - s->lpd.iou.uart[i] = SYS_BUS_DEVICE(dev); + sysbus_init_child_obj(OBJECT(s), name, + &s->lpd.iou.uart[i], sizeof(s->lpd.iou.uart[i]), + TYPE_PL011); + dev = DEVICE(&s->lpd.iou.uart[i]); qdev_prop_set_chr(dev, "chardev", serial_hd(i)); - object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal); qdev_init_nofail(dev); - mr = sysbus_mmio_get_region(s->lpd.iou.uart[i], 0); + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0); memory_region_add_subregion(&s->mr_ps, addrs[i], mr); - sysbus_connect_irq(s->lpd.iou.uart[i], 0, pic[irqs[i]]); + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[irqs[i]]); g_free(name); } } -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Embed the GEMs into the SoC type. Suggested-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200427181649.26851-6-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 3 ++- hw/arm/xlnx-versal.c | 15 ++++++++------- 2 files changed, 10 insertions(+), 8 deletions(-) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ #include "hw/arm/boot.h" #include "hw/intc/arm_gicv3.h" #include "hw/char/pl011.h" +#include "hw/net/cadence_gem.h" #define TYPE_XLNX_VERSAL "xlnx-versal" #define XLNX_VERSAL(obj) OBJECT_CHECK(Versal, (obj), TYPE_XLNX_VERSAL) @@ -XXX,XX +XXX,XX @@ typedef struct Versal { struct { PL011State uart[XLNX_VERSAL_NR_UARTS]; - SysBusDevice *gem[XLNX_VERSAL_NR_GEMS]; + CadenceGEMState gem[XLNX_VERSAL_NR_GEMS]; SysBusDevice *adma[XLNX_VERSAL_NR_ADMAS]; } iou; } lpd; diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_gems(Versal *s, qemu_irq *pic) DeviceState *dev; MemoryRegion *mr; - dev = qdev_create(NULL, "cadence_gem"); - s->lpd.iou.gem[i] = SYS_BUS_DEVICE(dev); - object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal); + sysbus_init_child_obj(OBJECT(s), name, + &s->lpd.iou.gem[i], sizeof(s->lpd.iou.gem[i]), + TYPE_CADENCE_GEM); + dev = DEVICE(&s->lpd.iou.gem[i]); if (nd->used) { qemu_check_nic_model(nd, "cadence_gem"); qdev_set_nic_properties(dev, nd); } - object_property_set_int(OBJECT(s->lpd.iou.gem[i]), + object_property_set_int(OBJECT(dev), 2, "num-priority-queues", &error_abort); - object_property_set_link(OBJECT(s->lpd.iou.gem[i]), + object_property_set_link(OBJECT(dev), OBJECT(&s->mr_ps), "dma", &error_abort); qdev_init_nofail(dev); - mr = sysbus_mmio_get_region(s->lpd.iou.gem[i], 0); + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0); memory_region_add_subregion(&s->mr_ps, addrs[i], mr); - sysbus_connect_irq(s->lpd.iou.gem[i], 0, pic[irqs[i]]); + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[irqs[i]]); g_free(name); } } -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Embed the ADMAs into the SoC type. Suggested-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200427181649.26851-7-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 3 ++- hw/arm/xlnx-versal.c | 14 +++++++------- 2 files changed, 9 insertions(+), 8 deletions(-) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ #include "hw/arm/boot.h" #include "hw/intc/arm_gicv3.h" #include "hw/char/pl011.h" +#include "hw/dma/xlnx-zdma.h" #include "hw/net/cadence_gem.h" #define TYPE_XLNX_VERSAL "xlnx-versal" @@ -XXX,XX +XXX,XX @@ typedef struct Versal { struct { PL011State uart[XLNX_VERSAL_NR_UARTS]; CadenceGEMState gem[XLNX_VERSAL_NR_GEMS]; - SysBusDevice *adma[XLNX_VERSAL_NR_ADMAS]; + XlnxZDMA adma[XLNX_VERSAL_NR_ADMAS]; } iou; } lpd; diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_admas(Versal *s, qemu_irq *pic) DeviceState *dev; MemoryRegion *mr; - dev = qdev_create(NULL, "xlnx.zdma"); - s->lpd.iou.adma[i] = SYS_BUS_DEVICE(dev); - object_property_set_int(OBJECT(s->lpd.iou.adma[i]), 128, "bus-width", - &error_abort); - object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal); + sysbus_init_child_obj(OBJECT(s), name, + &s->lpd.iou.adma[i], sizeof(s->lpd.iou.adma[i]), + TYPE_XLNX_ZDMA); + dev = DEVICE(&s->lpd.iou.adma[i]); + object_property_set_int(OBJECT(dev), 128, "bus-width", &error_abort); qdev_init_nofail(dev); - mr = sysbus_mmio_get_region(s->lpd.iou.adma[i], 0); + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0); memory_region_add_subregion(&s->mr_ps, MM_ADMA_CH0 + i * MM_ADMA_CH0_SIZE, mr); - sysbus_connect_irq(s->lpd.iou.adma[i], 0, pic[VERSAL_ADMA_IRQ_0 + i]); + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[VERSAL_ADMA_IRQ_0 + i]); g_free(name); } } -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Embed the APUs into the SoC type. Suggested-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200427181649.26851-8-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 2 +- hw/arm/xlnx-versal-virt.c | 4 ++-- hw/arm/xlnx-versal.c | 19 +++++-------------- 3 files changed, 8 insertions(+), 17 deletions(-) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ typedef struct Versal { struct { struct { MemoryRegion mr; - ARMCPU *cpu[XLNX_VERSAL_NR_ACPUS]; + ARMCPU cpu[XLNX_VERSAL_NR_ACPUS]; GICv3State gic; } apu; } fpd; diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine) s->binfo.get_dtb = versal_virt_get_dtb; s->binfo.modify_dtb = versal_virt_modify_dtb; if (machine->kernel_filename) { - arm_load_kernel(s->soc.fpd.apu.cpu[0], machine, &s->binfo); + arm_load_kernel(&s->soc.fpd.apu.cpu[0], machine, &s->binfo); } else { - AddressSpace *as = arm_boot_address_space(s->soc.fpd.apu.cpu[0], + AddressSpace *as = arm_boot_address_space(&s->soc.fpd.apu.cpu[0], &s->binfo); /* Some boot-loaders (e.g u-boot) don't like blobs at address 0 (NULL). * Offset things by 4K. */ diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s) for (i = 0; i < ARRAY_SIZE(s->fpd.apu.cpu); i++) { Object *obj; - char *name; - - obj = object_new(XLNX_VERSAL_ACPU_TYPE); - if (!obj) { - error_report("Unable to create apu.cpu[%d] of type %s", - i, XLNX_VERSAL_ACPU_TYPE); - exit(EXIT_FAILURE); - } - - name = g_strdup_printf("apu-cpu[%d]", i); - object_property_add_child(OBJECT(s), name, obj, &error_fatal); - g_free(name); + object_initialize_child(OBJECT(s), "apu-cpu[*]", + &s->fpd.apu.cpu[i], sizeof(s->fpd.apu.cpu[i]), + XLNX_VERSAL_ACPU_TYPE, &error_abort, NULL); + obj = OBJECT(&s->fpd.apu.cpu[i]); object_property_set_int(obj, s->cfg.psci_conduit, "psci-conduit", &error_abort); if (i) { @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s) object_property_set_link(obj, OBJECT(&s->fpd.apu.mr), "memory", &error_abort); object_property_set_bool(obj, true, "realized", &error_fatal); - s->fpd.apu.cpu[i] = ARM_CPU(obj); } } @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_gic(Versal *s, qemu_irq *pic) } for (i = 0; i < nr_apu_cpus; i++) { - DeviceState *cpudev = DEVICE(s->fpd.apu.cpu[i]); + DeviceState *cpudev = DEVICE(&s->fpd.apu.cpu[i]); int ppibase = XLNX_VERSAL_NR_IRQS + i * GIC_INTERNAL + GIC_NR_SGIS; qemu_irq maint_irq; int ti; -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Add support for SD. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200427181649.26851-9-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 12 ++++++++++++ hw/arm/xlnx-versal.c | 31 +++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/arm/boot.h" +#include "hw/sd/sdhci.h" #include "hw/intc/arm_gicv3.h" #include "hw/char/pl011.h" #include "hw/dma/xlnx-zdma.h" @@ -XXX,XX +XXX,XX @@ #define XLNX_VERSAL_NR_UARTS 2 #define XLNX_VERSAL_NR_GEMS 2 #define XLNX_VERSAL_NR_ADMAS 8 +#define XLNX_VERSAL_NR_SDS 2 #define XLNX_VERSAL_NR_IRQS 192 typedef struct Versal { @@ -XXX,XX +XXX,XX @@ typedef struct Versal { } iou; } lpd; + /* The Platform Management Controller subsystem. */ + struct { + struct { + SDHCIState sd[XLNX_VERSAL_NR_SDS]; + } iou; + } pmc; + struct { MemoryRegion *mr_ddr; uint32_t psci_conduit; @@ -XXX,XX +XXX,XX @@ typedef struct Versal { #define VERSAL_GEM1_IRQ_0 58 #define VERSAL_GEM1_WAKE_IRQ_0 59 #define VERSAL_ADMA_IRQ_0 60 +#define VERSAL_SD0_IRQ_0 126 /* Architecturally reserved IRQs suitable for virtualization. */ #define VERSAL_RSVD_IRQ_FIRST 111 @@ -XXX,XX +XXX,XX @@ typedef struct Versal { #define MM_FPD_CRF 0xfd1a0000U #define MM_FPD_CRF_SIZE 0x140000 +#define MM_PMC_SD0 0xf1040000U +#define MM_PMC_SD0_SIZE 0x10000 #define MM_PMC_CRP 0xf1260000U #define MM_PMC_CRP_SIZE 0x10000 #endif diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_admas(Versal *s, qemu_irq *pic) } } +#define SDHCI_CAPABILITIES 0x280737ec6481 /* Same as on ZynqMP. */ +static void versal_create_sds(Versal *s, qemu_irq *pic) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(s->pmc.iou.sd); i++) { + DeviceState *dev; + MemoryRegion *mr; + + sysbus_init_child_obj(OBJECT(s), "sd[*]", + &s->pmc.iou.sd[i], sizeof(s->pmc.iou.sd[i]), + TYPE_SYSBUS_SDHCI); + dev = DEVICE(&s->pmc.iou.sd[i]); + + object_property_set_uint(OBJECT(dev), + 3, "sd-spec-version", &error_fatal); + object_property_set_uint(OBJECT(dev), SDHCI_CAPABILITIES, "capareg", + &error_fatal); + object_property_set_uint(OBJECT(dev), UHS_I, "uhs", &error_fatal); + qdev_init_nofail(dev); + + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0); + memory_region_add_subregion(&s->mr_ps, + MM_PMC_SD0 + i * MM_PMC_SD0_SIZE, mr); + + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, + pic[VERSAL_SD0_IRQ_0 + i * 2]); + } +} + /* This takes the board allocated linear DDR memory and creates aliases * for each split DDR range/aperture on the Versal address map. */ @@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp) versal_create_uarts(s, pic); versal_create_gems(s, pic); versal_create_admas(s, pic); + versal_create_sds(s, pic); versal_map_ddr(s); versal_unimp(s); -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> hw/arm: versal: Add support for the RTC. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200427181649.26851-10-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 8 ++++++++ hw/arm/xlnx-versal.c | 21 +++++++++++++++++++++ 2 files changed, 29 insertions(+) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ #include "hw/char/pl011.h" #include "hw/dma/xlnx-zdma.h" #include "hw/net/cadence_gem.h" +#include "hw/rtc/xlnx-zynqmp-rtc.h" #define TYPE_XLNX_VERSAL "xlnx-versal" #define XLNX_VERSAL(obj) OBJECT_CHECK(Versal, (obj), TYPE_XLNX_VERSAL) @@ -XXX,XX +XXX,XX @@ typedef struct Versal { struct { SDHCIState sd[XLNX_VERSAL_NR_SDS]; } iou; + + XlnxZynqMPRTC rtc; } pmc; struct { @@ -XXX,XX +XXX,XX @@ typedef struct Versal { #define VERSAL_GEM1_IRQ_0 58 #define VERSAL_GEM1_WAKE_IRQ_0 59 #define VERSAL_ADMA_IRQ_0 60 +#define VERSAL_RTC_APB_ERR_IRQ 121 #define VERSAL_SD0_IRQ_0 126 +#define VERSAL_RTC_ALARM_IRQ 142 +#define VERSAL_RTC_SECONDS_IRQ 143 /* Architecturally reserved IRQs suitable for virtualization. */ #define VERSAL_RSVD_IRQ_FIRST 111 @@ -XXX,XX +XXX,XX @@ typedef struct Versal { #define MM_PMC_SD0_SIZE 0x10000 #define MM_PMC_CRP 0xf1260000U #define MM_PMC_CRP_SIZE 0x10000 +#define MM_PMC_RTC 0xf12a0000 +#define MM_PMC_RTC_SIZE 0x10000 #endif diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_sds(Versal *s, qemu_irq *pic) } } +static void versal_create_rtc(Versal *s, qemu_irq *pic) +{ + SysBusDevice *sbd; + MemoryRegion *mr; + + sysbus_init_child_obj(OBJECT(s), "rtc", &s->pmc.rtc, sizeof(s->pmc.rtc), + TYPE_XLNX_ZYNQMP_RTC); + sbd = SYS_BUS_DEVICE(&s->pmc.rtc); + qdev_init_nofail(DEVICE(sbd)); + + mr = sysbus_mmio_get_region(sbd, 0); + memory_region_add_subregion(&s->mr_ps, MM_PMC_RTC, mr); + + /* + * TODO: Connect the ALARM and SECONDS interrupts once our RTC model + * supports them. + */ + sysbus_connect_irq(sbd, 1, pic[VERSAL_RTC_APB_ERR_IRQ]); +} + /* This takes the board allocated linear DDR memory and creates aliases * for each split DDR range/aperture on the Versal address map. */ @@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp) versal_create_gems(s, pic); versal_create_admas(s, pic); versal_create_sds(s, pic); + versal_create_rtc(s, pic); versal_map_ddr(s); versal_unimp(s); -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Add support for SD. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200427181649.26851-11-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-versal-virt.c | 46 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/sysbus-fdt.h" #include "hw/arm/fdt.h" #include "cpu.h" +#include "hw/qdev-properties.h" #include "hw/arm/xlnx-versal.h" #define TYPE_XLNX_VERSAL_VIRT_MACHINE MACHINE_TYPE_NAME("xlnx-versal-virt") @@ -XXX,XX +XXX,XX @@ static void fdt_add_zdma_nodes(VersalVirt *s) } } +static void fdt_add_sd_nodes(VersalVirt *s) +{ + const char clocknames[] = "clk_xin\0clk_ahb"; + const char compat[] = "arasan,sdhci-8.9a"; + int i; + + for (i = ARRAY_SIZE(s->soc.pmc.iou.sd) - 1; i >= 0; i--) { + uint64_t addr = MM_PMC_SD0 + MM_PMC_SD0_SIZE * i; + char *name = g_strdup_printf("/sdhci@%" PRIx64, addr); + + qemu_fdt_add_subnode(s->fdt, name); + + qemu_fdt_setprop_cells(s->fdt, name, "clocks", + s->phandle.clk_25Mhz, s->phandle.clk_25Mhz); + qemu_fdt_setprop(s->fdt, name, "clock-names", + clocknames, sizeof(clocknames)); + qemu_fdt_setprop_cells(s->fdt, name, "interrupts", + GIC_FDT_IRQ_TYPE_SPI, VERSAL_SD0_IRQ_0 + i * 2, + GIC_FDT_IRQ_FLAGS_LEVEL_HI); + qemu_fdt_setprop_sized_cells(s->fdt, name, "reg", + 2, addr, 2, MM_PMC_SD0_SIZE); + qemu_fdt_setprop(s->fdt, name, "compatible", compat, sizeof(compat)); + g_free(name); + } +} + static void fdt_nop_memory_nodes(void *fdt, Error **errp) { Error *err = NULL; @@ -XXX,XX +XXX,XX @@ static void create_virtio_regions(VersalVirt *s) } } +static void sd_plugin_card(SDHCIState *sd, DriveInfo *di) +{ + BlockBackend *blk = di ? blk_by_legacy_dinfo(di) : NULL; + DeviceState *card; + + card = qdev_create(qdev_get_child_bus(DEVICE(sd), "sd-bus"), TYPE_SD_CARD); + object_property_add_child(OBJECT(sd), "card[*]", OBJECT(card), + &error_fatal); + qdev_prop_set_drive(card, "drive", blk, &error_fatal); + object_property_set_bool(OBJECT(card), true, "realized", &error_fatal); +} + static void versal_virt_init(MachineState *machine) { VersalVirt *s = XLNX_VERSAL_VIRT_MACHINE(machine); int psci_conduit = QEMU_PSCI_CONDUIT_DISABLED; + int i; /* * If the user provides an Operating System to be loaded, we expect them @@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine) fdt_add_gic_nodes(s); fdt_add_timer_nodes(s); fdt_add_zdma_nodes(s); + fdt_add_sd_nodes(s); fdt_add_cpu_nodes(s, psci_conduit); fdt_add_clk_node(s, "/clk125", 125000000, s->phandle.clk_125Mhz); fdt_add_clk_node(s, "/clk25", 25000000, s->phandle.clk_25Mhz); @@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine) memory_region_add_subregion_overlap(get_system_memory(), 0, &s->soc.fpd.apu.mr, 0); + /* Plugin SD cards. */ + for (i = 0; i < ARRAY_SIZE(s->soc.pmc.iou.sd); i++) { + sd_plugin_card(&s->soc.pmc.iou.sd[i], drive_get_next(IF_SD)); + } + s->binfo.ram_size = machine->ram_size; s->binfo.loader_start = 0x0; s->binfo.get_dtb = versal_virt_get_dtb; -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Add support for the RTC. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200427181649.26851-12-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-versal-virt.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -XXX,XX +XXX,XX @@ static void fdt_add_sd_nodes(VersalVirt *s) } } +static void fdt_add_rtc_node(VersalVirt *s) +{ + const char compat[] = "xlnx,zynqmp-rtc"; + const char interrupt_names[] = "alarm\0sec"; + char *name = g_strdup_printf("/rtc@%x", MM_PMC_RTC); + + qemu_fdt_add_subnode(s->fdt, name); + + qemu_fdt_setprop_cells(s->fdt, name, "interrupts", + GIC_FDT_IRQ_TYPE_SPI, VERSAL_RTC_ALARM_IRQ, + GIC_FDT_IRQ_FLAGS_LEVEL_HI, + GIC_FDT_IRQ_TYPE_SPI, VERSAL_RTC_SECONDS_IRQ, + GIC_FDT_IRQ_FLAGS_LEVEL_HI); + qemu_fdt_setprop(s->fdt, name, "interrupt-names", + interrupt_names, sizeof(interrupt_names)); + qemu_fdt_setprop_sized_cells(s->fdt, name, "reg", + 2, MM_PMC_RTC, 2, MM_PMC_RTC_SIZE); + qemu_fdt_setprop(s->fdt, name, "compatible", compat, sizeof(compat)); + g_free(name); +} + static void fdt_nop_memory_nodes(void *fdt, Error **errp) { Error *err = NULL; @@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine) fdt_add_timer_nodes(s); fdt_add_zdma_nodes(s); fdt_add_sd_nodes(s); + fdt_add_rtc_node(s); fdt_add_cpu_nodes(s, psci_conduit); fdt_add_clk_node(s, "/clk125", 125000000, s->phandle.clk_125Mhz); fdt_add_clk_node(s, "/clk25", 25000000, s->phandle.clk_25Mhz); -- 2.20.1 Somewhere along theline we accidentally added a duplicate "using D16-D31 when they don't exist" check to do_vfm_dp() (probably an artifact of a patchseries rebase). Remove it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200430181003.21682-2-peter.maydell@linaro.org --- target/arm/translate-vfp.inc.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -XXX,XX +XXX,XX @@ static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d) return false; } - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vn | a->vm) & 0x10)) { - return false; - } - if (!vfp_access_check(s)) { return true; } -- 2.20.1 We were accidentally permitting decode of Thumb Neon insns even if the CPU didn't have the FEATURE_NEON bit set, because the feature check was being done before the call to disas_neon_data_insn() and disas_neon_ls_insn() in the Arm decoder but was omitted from the Thumb decoder. Push the feature bit check down into the called functions so it is done for both Arm and Thumb encodings. 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: 20200430181003.21682-3-peter.maydell@linaro.org --- target/arm/translate.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) TCGv_i32 tmp2; TCGv_i64 tmp64; + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return 1; + } + /* FIXME: this access check should not take precedence over UNDEF * for invalid encodings; we will generate incorrect syndrome information * for attempts to execute invalid vfp/neon encodings with FP disabled. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) TCGv_ptr ptr1, ptr2, ptr3; TCGv_i64 tmp64; + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return 1; + } + /* FIXME: this access check should not take precedence over UNDEF * for invalid encodings; we will generate incorrect syndrome information * for attempts to execute invalid vfp/neon encodings with FP disabled. @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) if (((insn >> 25) & 7) == 1) { /* NEON Data processing. */ - if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { - goto illegal_op; - } - if (disas_neon_data_insn(s, insn)) { goto illegal_op; } @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) } if ((insn & 0x0f100000) == 0x04000000) { /* NEON load/store. */ - if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { - goto illegal_op; - } - if (disas_neon_ls_insn(s, insn)) { goto illegal_op; } -- 2.20.1 Add the infrastructure for building and invoking a decodetree decoder for the AArch32 Neon encodings. At the moment the new decoder covers nothing, so we always fall back to the existing hand-written decode. We follow the same pattern we did for the VFP decodetree conversion (commit 78e138bc1f672c145ef6ace74617d and following): code that deals with Neon will be moving gradually out to translate-neon.vfp.inc, which we #include into translate.c. In order to share the decode files between A32 and T32, we split Neon into 3 parts: * data-processing * load-store * 'shared' encodings The first two groups of instructions have similar but not identical A32 and T32 encodings, so we need to manually transform the T32 encoding into the A32 one before calling the decoder; the third group covers the Neon instructions which are identical in A32 and T32. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-4-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 29 ++++++++++++++++++++++++++ target/arm/neon-ls.decode | 29 ++++++++++++++++++++++++++ target/arm/neon-shared.decode | 27 +++++++++++++++++++++++++ target/arm/translate-neon.inc.c | 32 +++++++++++++++++++++++++++++ target/arm/translate.c | 36 +++++++++++++++++++++++++++++++-- target/arm/Makefile.objs | 18 +++++++++++++++++ 6 files changed, 169 insertions(+), 2 deletions(-) create mode 100644 target/arm/neon-dp.decode create mode 100644 target/arm/neon-ls.decode create mode 100644 target/arm/neon-shared.decode create mode 100644 target/arm/translate-neon.inc.c diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ +# AArch32 Neon data-processing instruction descriptions +# +# Copyright (c) 2020 Linaro, Ltd +# +# This library is free software; you can redistribute it and/or +# modify it under the terms of the GNU Lesser General Public +# License as published by the Free Software Foundation; either +# version 2 of the License, or (at your option) any later version. +# +# This library is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# Lesser General Public License for more details. +# +# You should have received a copy of the GNU Lesser General Public +# License along with this library; if not, see <http://www.gnu.org/licenses/>. + +# +# This file is processed by scripts/decodetree.py +# + +# Encodings for Neon data processing instructions where the T32 encoding +# is a simple transformation of the A32 encoding. +# More specifically, this file covers instructions where the A32 encoding is +# 0b1111_001p_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq +# and the T32 encoding is +# 0b111p_1111_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq +# This file works on the A32 encoding only; calling code for T32 has to +# transform the insn into the A32 version first. diff --git a/target/arm/neon-ls.decode b/target/arm/neon-ls.decode new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/neon-ls.decode @@ -XXX,XX +XXX,XX @@ +# AArch32 Neon load/store instruction descriptions +# +# Copyright (c) 2020 Linaro, Ltd +# +# This library is free software; you can redistribute it and/or +# modify it under the terms of the GNU Lesser General Public +# License as published by the Free Software Foundation; either +# version 2 of the License, or (at your option) any later version. +# +# This library is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# Lesser General Public License for more details. +# +# You should have received a copy of the GNU Lesser General Public +# License along with this library; if not, see <http://www.gnu.org/licenses/>. + +# +# This file is processed by scripts/decodetree.py +# + +# Encodings for Neon load/store instructions where the T32 encoding +# is a simple transformation of the A32 encoding. +# More specifically, this file covers instructions where the A32 encoding is +# 0b1111_0100_xxx0_xxxx_xxxx_xxxx_xxxx_xxxx +# and the T32 encoding is +# 0b1111_1001_xxx0_xxxx_xxxx_xxxx_xxxx_xxxx +# This file works on the A32 encoding only; calling code for T32 has to +# transform the insn into the A32 version first. diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/neon-shared.decode @@ -XXX,XX +XXX,XX @@ +# AArch32 Neon instruction descriptions +# +# Copyright (c) 2020 Linaro, Ltd +# +# This library is free software; you can redistribute it and/or +# modify it under the terms of the GNU Lesser General Public +# License as published by the Free Software Foundation; either +# version 2 of the License, or (at your option) any later version. +# +# This library is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# Lesser General Public License for more details. +# +# You should have received a copy of the GNU Lesser General Public +# License along with this library; if not, see <http://www.gnu.org/licenses/>. + +# +# This file is processed by scripts/decodetree.py +# + +# Encodings for Neon instructions whose encoding is the same for +# both A32 and T32. + +# More specifically, this covers: +# 2reg scalar ext: 0b1111_1110_xxxx_xxxx_xxxx_1x0x_xxxx_xxxx +# 3same ext: 0b1111_110x_xxxx_xxxx_xxxx_1x0x_xxxx_xxxx diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ +/* + * ARM translation: AArch32 Neon instructions + * + * Copyright (c) 2003 Fabrice Bellard + * Copyright (c) 2005-2007 CodeSourcery + * Copyright (c) 2007 OpenedHand, Ltd. + * Copyright (c) 2020 Linaro, Ltd. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +/* + * This file is intended to be included from translate.c; it uses + * some macros and definitions provided by that file. + * It might be possible to convert it to a standalone .c file eventually. + */ + +/* Include the generated Neon decoder */ +#include "decode-neon-dp.inc.c" +#include "decode-neon-ls.inc.c" +#include "decode-neon-shared.inc.c" diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv_ptr vfp_reg_ptr(bool dp, int reg) #define ARM_CP_RW_BIT (1 << 20) -/* Include the VFP decoder */ +/* Include the VFP and Neon decoders */ #include "translate-vfp.inc.c" +#include "translate-neon.inc.c" static inline void iwmmxt_load_reg(TCGv_i64 var, int reg) { @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) /* Unconditional instructions. */ /* TODO: Perhaps merge these into one decodetree output file. */ if (disas_a32_uncond(s, insn) || - disas_vfp_uncond(s, insn)) { + disas_vfp_uncond(s, insn) || + disas_neon_dp(s, insn) || + disas_neon_ls(s, insn) || + disas_neon_shared(s, insn)) { return; } /* fall back to legacy decoder */ @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) ARCH(6T2); } + if ((insn & 0xef000000) == 0xef000000) { + /* + * T32 encodings 0b111p_1111_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq + * transform into + * A32 encodings 0b1111_001p_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq + */ + uint32_t a32_insn = (insn & 0xe2ffffff) | + ((insn & (1 << 28)) >> 4) | (1 << 28); + + if (disas_neon_dp(s, a32_insn)) { + return; + } + } + + if ((insn & 0xff100000) == 0xf9000000) { + /* + * T32 encodings 0b1111_1001_ppp0_qqqq_qqqq_qqqq_qqqq_qqqq + * transform into + * A32 encodings 0b1111_0100_ppp0_qqqq_qqqq_qqqq_qqqq_qqqq + */ + uint32_t a32_insn = (insn & 0x00ffffff) | 0xf4000000; + + if (disas_neon_ls(s, a32_insn)) { + return; + } + } + /* * TODO: Perhaps merge these into one decodetree output file. * Note disas_vfp is written for a32 with cond field in the @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) */ if (disas_t32(s, insn) || disas_vfp_uncond(s, insn) || + disas_neon_shared(s, insn) || ((insn >> 28) == 0xe && disas_vfp(s, insn))) { return; } diff --git a/target/arm/Makefile.objs b/target/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/target/arm/Makefile.objs +++ b/target/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ target/arm/decode-sve.inc.c: $(SRC_PATH)/target/arm/sve.decode $(DECODETREE) $(PYTHON) $(DECODETREE) --decode disas_sve -o $@ $<,\ "GEN", $(TARGET_DIR)$@) +target/arm/decode-neon-shared.inc.c: $(SRC_PATH)/target/arm/neon-shared.decode $(DECODETREE) + $(call quiet-command,\ + $(PYTHON) $(DECODETREE) --static-decode disas_neon_shared -o $@ $<,\ + "GEN", $(TARGET_DIR)$@) + +target/arm/decode-neon-dp.inc.c: $(SRC_PATH)/target/arm/neon-dp.decode $(DECODETREE) + $(call quiet-command,\ + $(PYTHON) $(DECODETREE) --static-decode disas_neon_dp -o $@ $<,\ + "GEN", $(TARGET_DIR)$@) + +target/arm/decode-neon-ls.inc.c: $(SRC_PATH)/target/arm/neon-ls.decode $(DECODETREE) + $(call quiet-command,\ + $(PYTHON) $(DECODETREE) --static-decode disas_neon_ls -o $@ $<,\ + "GEN", $(TARGET_DIR)$@) + target/arm/decode-vfp.inc.c: $(SRC_PATH)/target/arm/vfp.decode $(DECODETREE) $(call quiet-command,\ $(PYTHON) $(DECODETREE) --static-decode disas_vfp -o $@ $<,\ @@ -XXX,XX +XXX,XX @@ target/arm/decode-t16.inc.c: $(SRC_PATH)/target/arm/t16.decode $(DECODETREE) "GEN", $(TARGET_DIR)$@) target/arm/translate-sve.o: target/arm/decode-sve.inc.c +target/arm/translate.o: target/arm/decode-neon-shared.inc.c +target/arm/translate.o: target/arm/decode-neon-dp.inc.c +target/arm/translate.o: target/arm/decode-neon-ls.inc.c target/arm/translate.o: target/arm/decode-vfp.inc.c target/arm/translate.o: target/arm/decode-vfp-uncond.inc.c target/arm/translate.o: target/arm/decode-a32.inc.c -- 2.20.1 Convert the VCMLA (vector) insns in the 3same extension group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-5-peter.maydell@linaro.org --- target/arm/neon-shared.decode | 11 ++++++++++ target/arm/translate-neon.inc.c | 37 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 11 +--------- 3 files changed, 49 insertions(+), 10 deletions(-) diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-shared.decode +++ b/target/arm/neon-shared.decode @@ -XXX,XX +XXX,XX @@ # More specifically, this covers: # 2reg scalar ext: 0b1111_1110_xxxx_xxxx_xxxx_1x0x_xxxx_xxxx # 3same ext: 0b1111_110x_xxxx_xxxx_xxxx_1x0x_xxxx_xxxx + +# VFP/Neon register fields; same as vfp.decode +%vm_dp 5:1 0:4 +%vm_sp 0:4 5:1 +%vn_dp 7:1 16:4 +%vn_sp 16:4 7:1 +%vd_dp 22:1 12:4 +%vd_sp 12:4 22:1 + +VCMLA 1111 110 rot:2 . 1 size:1 .... .... 1000 . q:1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ #include "decode-neon-dp.inc.c" #include "decode-neon-ls.inc.c" #include "decode-neon-shared.inc.c" + +static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) +{ + int opr_sz; + TCGv_ptr fpst; + gen_helper_gvec_3_ptr *fn_gvec_ptr; + + if (!dc_isar_feature(aa32_vcma, s) + || (!a->size && !dc_isar_feature(aa32_fp16_arith, s))) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if ((a->vn | a->vm | a->vd) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + opr_sz = (1 + a->q) * 8; + fpst = get_fpstatus_ptr(1); + fn_gvec_ptr = a->size ? gen_helper_gvec_fcmlas : gen_helper_gvec_fcmlah; + tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), + vfp_reg_offset(1, a->vn), + vfp_reg_offset(1, a->vm), + fpst, opr_sz, opr_sz, a->rot, + fn_gvec_ptr); + tcg_temp_free_ptr(fpst); + return true; +} 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 int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) bool is_long = false, q = extract32(insn, 6, 1); bool ptr_is_env = false; - if ((insn & 0xfe200f10) == 0xfc200800) { - /* VCMLA -- 1111 110R R.1S .... .... 1000 ...0 .... */ - int size = extract32(insn, 20, 1); - data = extract32(insn, 23, 2); /* rot */ - if (!dc_isar_feature(aa32_vcma, s) - || (!size && !dc_isar_feature(aa32_fp16_arith, s))) { - return 1; - } - fn_gvec_ptr = size ? gen_helper_gvec_fcmlas : gen_helper_gvec_fcmlah; - } else if ((insn & 0xfea00f10) == 0xfc800800) { + if ((insn & 0xfea00f10) == 0xfc800800) { /* VCADD -- 1111 110R 1.0S .... .... 1000 ...0 .... */ int size = extract32(insn, 20, 1); data = extract32(insn, 24, 1); /* rot */ -- 2.20.1 Convert the VCADD (vector) insns to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-6-peter.maydell@linaro.org --- target/arm/neon-shared.decode | 3 +++ target/arm/translate-neon.inc.c | 37 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 11 +--------- 3 files changed, 41 insertions(+), 10 deletions(-) diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-shared.decode +++ b/target/arm/neon-shared.decode @@ -XXX,XX +XXX,XX @@ VCMLA 1111 110 rot:2 . 1 size:1 .... .... 1000 . q:1 . 0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp + +VCADD 1111 110 rot:1 1 . 0 size:1 .... .... 1000 . q:1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) tcg_temp_free_ptr(fpst); return true; } + +static bool trans_VCADD(DisasContext *s, arg_VCADD *a) +{ + int opr_sz; + TCGv_ptr fpst; + gen_helper_gvec_3_ptr *fn_gvec_ptr; + + if (!dc_isar_feature(aa32_vcma, s) + || (!a->size && !dc_isar_feature(aa32_fp16_arith, s))) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if ((a->vn | a->vm | a->vd) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + opr_sz = (1 + a->q) * 8; + fpst = get_fpstatus_ptr(1); + fn_gvec_ptr = a->size ? gen_helper_gvec_fcadds : gen_helper_gvec_fcaddh; + tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), + vfp_reg_offset(1, a->vn), + vfp_reg_offset(1, a->vm), + fpst, opr_sz, opr_sz, a->rot, + fn_gvec_ptr); + tcg_temp_free_ptr(fpst); + return true; +} 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 int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) bool is_long = false, q = extract32(insn, 6, 1); bool ptr_is_env = false; - if ((insn & 0xfea00f10) == 0xfc800800) { - /* VCADD -- 1111 110R 1.0S .... .... 1000 ...0 .... */ - int size = extract32(insn, 20, 1); - data = extract32(insn, 24, 1); /* rot */ - if (!dc_isar_feature(aa32_vcma, s) - || (!size && !dc_isar_feature(aa32_fp16_arith, s))) { - return 1; - } - fn_gvec_ptr = size ? gen_helper_gvec_fcadds : gen_helper_gvec_fcaddh; - } else if ((insn & 0xfeb00f00) == 0xfc200d00) { + if ((insn & 0xfeb00f00) == 0xfc200d00) { /* V[US]DOT -- 1111 1100 0.10 .... .... 1101 .Q.U .... */ bool u = extract32(insn, 4, 1); if (!dc_isar_feature(aa32_dp, s)) { -- 2.20.1 Convert the V[US]DOT (vector) insns to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-7-peter.maydell@linaro.org --- target/arm/neon-shared.decode | 4 ++++ target/arm/translate-neon.inc.c | 32 ++++++++++++++++++++++++++++++++ target/arm/translate.c | 9 +-------- 3 files changed, 37 insertions(+), 8 deletions(-) diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-shared.decode +++ b/target/arm/neon-shared.decode @@ -XXX,XX +XXX,XX @@ VCMLA 1111 110 rot:2 . 1 size:1 .... .... 1000 . q:1 . 0 .... \ VCADD 1111 110 rot:1 1 . 0 size:1 .... .... 1000 . q:1 . 0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp + +# VUDOT and VSDOT +VDOT 1111 110 00 . 10 .... .... 1101 . q:1 . u:1 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a) tcg_temp_free_ptr(fpst); return true; } + +static bool trans_VDOT(DisasContext *s, arg_VDOT *a) +{ + int opr_sz; + gen_helper_gvec_3 *fn_gvec; + + if (!dc_isar_feature(aa32_dp, s)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if ((a->vn | a->vm | a->vd) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + opr_sz = (1 + a->q) * 8; + fn_gvec = a->u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b; + tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd), + vfp_reg_offset(1, a->vn), + vfp_reg_offset(1, a->vm), + opr_sz, opr_sz, 0, fn_gvec); + return true; +} 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 int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) bool is_long = false, q = extract32(insn, 6, 1); bool ptr_is_env = false; - if ((insn & 0xfeb00f00) == 0xfc200d00) { - /* V[US]DOT -- 1111 1100 0.10 .... .... 1101 .Q.U .... */ - bool u = extract32(insn, 4, 1); - if (!dc_isar_feature(aa32_dp, s)) { - return 1; - } - fn_gvec = u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b; - } else if ((insn & 0xff300f10) == 0xfc200810) { + if ((insn & 0xff300f10) == 0xfc200810) { /* VFM[AS]L -- 1111 1100 S.10 .... .... 1000 .Q.1 .... */ int is_s = extract32(insn, 23, 1); if (!dc_isar_feature(aa32_fhm, s)) { -- 2.20.1 Convert the VFM[AS]L (vector) insns to decodetree. This is the last insn in the legacy decoder for the 3same_ext group, so we can delete the legacy decoder function for the group entirely. Note that in disas_thumb2_insn() the parts of this encoding space where the decodetree decoder returns false will correctly be directed to illegal_op by the "(insn & (1 << 28))" check so they won't fall into disas_coproc_insn() by mistake. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-8-peter.maydell@linaro.org --- target/arm/neon-shared.decode | 6 +++ target/arm/translate-neon.inc.c | 31 +++++++++++ target/arm/translate.c | 92 +-------------------------------- 3 files changed, 38 insertions(+), 91 deletions(-) diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-shared.decode +++ b/target/arm/neon-shared.decode @@ -XXX,XX +XXX,XX @@ VCADD 1111 110 rot:1 1 . 0 size:1 .... .... 1000 . q:1 . 0 .... \ # VUDOT and VSDOT VDOT 1111 110 00 . 10 .... .... 1101 . q:1 . u:1 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp + +# VFM[AS]L +VFML 1111 110 0 s:1 . 10 .... .... 1000 . 0 . 1 .... \ + vm=%vm_sp vn=%vn_sp vd=%vd_dp q=0 +VFML 1111 110 0 s:1 . 10 .... .... 1000 . 1 . 1 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp q=1 diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VDOT(DisasContext *s, arg_VDOT *a) opr_sz, opr_sz, 0, fn_gvec); return true; } + +static bool trans_VFML(DisasContext *s, arg_VFML *a) +{ + int opr_sz; + + if (!dc_isar_feature(aa32_fhm, s)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + (a->vd & 0x10)) { + return false; + } + + if (a->vd & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + opr_sz = (1 + a->q) * 8; + tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), + vfp_reg_offset(a->q, a->vn), + vfp_reg_offset(a->q, a->vm), + cpu_env, opr_sz, opr_sz, a->s, /* is_2 == 0 */ + gen_helper_gvec_fmlal_a32); + return true; +} 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 int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 0; } -/* Advanced SIMD three registers of the same length extension. - * 31 25 23 22 20 16 12 11 10 9 8 3 0 - * +---------------+-----+---+-----+----+----+---+----+---+----+---------+----+ - * | 1 1 1 1 1 1 0 | op1 | D | op2 | Vn | Vd | 1 | o3 | 0 | o4 | N Q M U | Vm | - * +---------------+-----+---+-----+----+----+---+----+---+----+---------+----+ - */ -static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) -{ - gen_helper_gvec_3 *fn_gvec = NULL; - gen_helper_gvec_3_ptr *fn_gvec_ptr = NULL; - int rd, rn, rm, opr_sz; - int data = 0; - int off_rn, off_rm; - bool is_long = false, q = extract32(insn, 6, 1); - bool ptr_is_env = false; - - if ((insn & 0xff300f10) == 0xfc200810) { - /* VFM[AS]L -- 1111 1100 S.10 .... .... 1000 .Q.1 .... */ - int is_s = extract32(insn, 23, 1); - if (!dc_isar_feature(aa32_fhm, s)) { - return 1; - } - is_long = true; - data = is_s; /* is_2 == 0 */ - fn_gvec_ptr = gen_helper_gvec_fmlal_a32; - ptr_is_env = true; - } else { - return 1; - } - - VFP_DREG_D(rd, insn); - if (rd & q) { - return 1; - } - if (q || !is_long) { - VFP_DREG_N(rn, insn); - VFP_DREG_M(rm, insn); - if ((rn | rm) & q & !is_long) { - return 1; - } - off_rn = vfp_reg_offset(1, rn); - off_rm = vfp_reg_offset(1, rm); - } else { - rn = VFP_SREG_N(insn); - rm = VFP_SREG_M(insn); - off_rn = vfp_reg_offset(0, rn); - off_rm = vfp_reg_offset(0, rm); - } - - if (s->fp_excp_el) { - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, - syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); - return 0; - } - if (!s->vfp_enabled) { - return 1; - } - - opr_sz = (1 + q) * 8; - if (fn_gvec_ptr) { - TCGv_ptr ptr; - if (ptr_is_env) { - ptr = cpu_env; - } else { - ptr = get_fpstatus_ptr(1); - } - tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), off_rn, off_rm, ptr, - opr_sz, opr_sz, data, fn_gvec_ptr); - if (!ptr_is_env) { - tcg_temp_free_ptr(ptr); - } - } else { - tcg_gen_gvec_3_ool(vfp_reg_offset(1, rd), off_rn, off_rm, - opr_sz, opr_sz, data, fn_gvec); - } - return 0; -} - /* Advanced SIMD two registers and a scalar extension. * 31 24 23 22 20 16 12 11 10 9 8 3 0 * +-----------------+----+---+----+----+----+---+----+---+----+---------+----+ @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) } } } - } else if ((insn & 0x0e000a00) == 0x0c000800 - && arm_dc_feature(s, ARM_FEATURE_V8)) { - if (disas_neon_insn_3same_ext(s, insn)) { - goto illegal_op; - } - return; } else if ((insn & 0x0f000a00) == 0x0e000800 && arm_dc_feature(s, ARM_FEATURE_V8)) { if (disas_neon_insn_2reg_scalar_ext(s, insn)) { @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) } break; } - if ((insn & 0xfe000a00) == 0xfc000800 + if ((insn & 0xff000a00) == 0xfe000800 && arm_dc_feature(s, ARM_FEATURE_V8)) { /* The Thumb2 and ARM encodings are identical. */ - if (disas_neon_insn_3same_ext(s, insn)) { - goto illegal_op; - } - } else if ((insn & 0xff000a00) == 0xfe000800 - && arm_dc_feature(s, ARM_FEATURE_V8)) { - /* The Thumb2 and ARM encodings are identical. */ if (disas_neon_insn_2reg_scalar_ext(s, insn)) { goto illegal_op; } -- 2.20.1 Convert VCMLA (scalar) in the 2reg-scalar-ext group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-9-peter.maydell@linaro.org --- target/arm/neon-shared.decode | 5 +++++ target/arm/translate-neon.inc.c | 40 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 26 +-------------------- 3 files changed, 46 insertions(+), 25 deletions(-) diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-shared.decode +++ b/target/arm/neon-shared.decode @@ -XXX,XX +XXX,XX @@ VFML 1111 110 0 s:1 . 10 .... .... 1000 . 0 . 1 .... \ vm=%vm_sp vn=%vn_sp vd=%vd_dp q=0 VFML 1111 110 0 s:1 . 10 .... .... 1000 . 1 . 1 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp q=1 + +VCMLA_scalar 1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \ + vn=%vn_dp vd=%vd_dp size=0 +VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp size=1 index=0 diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VFML(DisasContext *s, arg_VFML *a) gen_helper_gvec_fmlal_a32); return true; } + +static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a) +{ + gen_helper_gvec_3_ptr *fn_gvec_ptr; + int opr_sz; + TCGv_ptr fpst; + + if (!dc_isar_feature(aa32_vcma, s)) { + return false; + } + if (a->size == 0 && !dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if ((a->vd | a->vn) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fn_gvec_ptr = (a->size ? gen_helper_gvec_fcmlas_idx + : gen_helper_gvec_fcmlah_idx); + opr_sz = (1 + a->q) * 8; + fpst = get_fpstatus_ptr(1); + tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), + vfp_reg_offset(1, a->vn), + vfp_reg_offset(1, a->vm), + fpst, opr_sz, opr_sz, + (a->index << 2) | a->rot, fn_gvec_ptr); + tcg_temp_free_ptr(fpst); + return true; +} 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 int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) bool is_long = false, q = extract32(insn, 6, 1); bool ptr_is_env = false; - if ((insn & 0xff000f10) == 0xfe000800) { - /* VCMLA (indexed) -- 1111 1110 S.RR .... .... 1000 ...0 .... */ - int rot = extract32(insn, 20, 2); - int size = extract32(insn, 23, 1); - int index; - - if (!dc_isar_feature(aa32_vcma, s)) { - return 1; - } - if (size == 0) { - if (!dc_isar_feature(aa32_fp16_arith, s)) { - return 1; - } - /* For fp16, rm is just Vm, and index is M. */ - rm = extract32(insn, 0, 4); - index = extract32(insn, 5, 1); - } else { - /* For fp32, rm is the usual M:Vm, and index is 0. */ - VFP_DREG_M(rm, insn); - index = 0; - } - data = (index << 2) | rot; - fn_gvec_ptr = (size ? gen_helper_gvec_fcmlas_idx - : gen_helper_gvec_fcmlah_idx); - } else if ((insn & 0xffb00f00) == 0xfe200d00) { + if ((insn & 0xffb00f00) == 0xfe200d00) { /* V[US]DOT -- 1111 1110 0.10 .... .... 1101 .Q.U .... */ int u = extract32(insn, 4, 1); -- 2.20.1 Convert the V[US]DOT (scalar) insns in the 2reg-scalar-ext group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-10-peter.maydell@linaro.org --- target/arm/neon-shared.decode | 3 +++ target/arm/translate-neon.inc.c | 35 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 13 +----------- 3 files changed, 39 insertions(+), 12 deletions(-) diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-shared.decode +++ b/target/arm/neon-shared.decode @@ -XXX,XX +XXX,XX @@ VCMLA_scalar 1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \ vn=%vn_dp vd=%vd_dp size=0 VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp size=1 index=0 + +VDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 u:1 rm:4 \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a) tcg_temp_free_ptr(fpst); return true; } + +static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a) +{ + gen_helper_gvec_3 *fn_gvec; + int opr_sz; + TCGv_ptr fpst; + + if (!dc_isar_feature(aa32_dp, s)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn) & 0x10)) { + return false; + } + + if ((a->vd | a->vn) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fn_gvec = a->u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b; + opr_sz = (1 + a->q) * 8; + fpst = get_fpstatus_ptr(1); + tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd), + vfp_reg_offset(1, a->vn), + vfp_reg_offset(1, a->rm), + opr_sz, opr_sz, a->index, fn_gvec); + tcg_temp_free_ptr(fpst); + return true; +} 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 int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) bool is_long = false, q = extract32(insn, 6, 1); bool ptr_is_env = false; - if ((insn & 0xffb00f00) == 0xfe200d00) { - /* V[US]DOT -- 1111 1110 0.10 .... .... 1101 .Q.U .... */ - int u = extract32(insn, 4, 1); - - if (!dc_isar_feature(aa32_dp, s)) { - return 1; - } - fn_gvec = u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b; - /* rm is just Vm, and index is M. */ - data = extract32(insn, 5, 1); /* index */ - rm = extract32(insn, 0, 4); - } else if ((insn & 0xffa00f10) == 0xfe000810) { + if ((insn & 0xffa00f10) == 0xfe000810) { /* VFM[AS]L -- 1111 1110 0.0S .... .... 1000 .Q.1 .... */ int is_s = extract32(insn, 20, 1); int vm20 = extract32(insn, 0, 3); -- 2.20.1 Convert the VFM[AS]L (scalar) insns in the 2reg-scalar-ext group to decodetree. These are the last ones in the group so we can remove all the legacy decode for the group. Note that in disas_thumb2_insn() the parts of this encoding space where the decodetree decoder returns false will correctly be directed to illegal_op by the "(insn & (1 << 28))" check so they won't fall into disas_coproc_insn() by mistake. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-11-peter.maydell@linaro.org --- target/arm/neon-shared.decode | 7 +++ target/arm/translate-neon.inc.c | 32 ++++++++++ target/arm/translate.c | 107 +------------------------------- 3 files changed, 40 insertions(+), 106 deletions(-) diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-shared.decode +++ b/target/arm/neon-shared.decode @@ -XXX,XX +XXX,XX @@ VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \ VDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 u:1 rm:4 \ vm=%vm_dp vn=%vn_dp vd=%vd_dp + +%vfml_scalar_q0_rm 0:3 5:1 +%vfml_scalar_q1_index 5:1 3:1 +VFML_scalar 1111 1110 0 . 0 s:1 .... .... 1000 . 0 . 1 index:1 ... \ + rm=%vfml_scalar_q0_rm vn=%vn_sp vd=%vd_dp q=0 +VFML_scalar 1111 1110 0 . 0 s:1 .... .... 1000 . 1 . 1 . rm:3 \ + index=%vfml_scalar_q1_index vn=%vn_dp vd=%vd_dp q=1 diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a) tcg_temp_free_ptr(fpst); return true; } + +static bool trans_VFML_scalar(DisasContext *s, arg_VFML_scalar *a) +{ + int opr_sz; + + if (!dc_isar_feature(aa32_fhm, s)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd & 0x10) || (a->q && (a->vn & 0x10)))) { + return false; + } + + if (a->vd & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + opr_sz = (1 + a->q) * 8; + tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), + vfp_reg_offset(a->q, a->vn), + vfp_reg_offset(a->q, a->rm), + cpu_env, opr_sz, opr_sz, + (a->index << 2) | a->s, /* is_2 == 0 */ + gen_helper_gvec_fmlal_idx_a32); + return true; +} 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 int disas_dsp_insn(DisasContext *s, uint32_t insn) } #define VFP_REG_SHR(x, n) (((n) > 0) ? (x) >> (n) : (x) << -(n)) -#define VFP_SREG(insn, bigbit, smallbit) \ - ((VFP_REG_SHR(insn, bigbit - 1) & 0x1e) | (((insn) >> (smallbit)) & 1)) #define VFP_DREG(reg, insn, bigbit, smallbit) do { \ if (dc_isar_feature(aa32_simd_r32, s)) { \ reg = (((insn) >> (bigbit)) & 0x0f) \ @@ -XXX,XX +XXX,XX @@ static int disas_dsp_insn(DisasContext *s, uint32_t insn) reg = ((insn) >> (bigbit)) & 0x0f; \ }} while (0) -#define VFP_SREG_D(insn) VFP_SREG(insn, 12, 22) #define VFP_DREG_D(reg, insn) VFP_DREG(reg, insn, 12, 22) -#define VFP_SREG_N(insn) VFP_SREG(insn, 16, 7) #define VFP_DREG_N(reg, insn) VFP_DREG(reg, insn, 16, 7) -#define VFP_SREG_M(insn) VFP_SREG(insn, 0, 5) #define VFP_DREG_M(reg, insn) VFP_DREG(reg, insn, 0, 5) static void gen_neon_dup_low16(TCGv_i32 var) @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 0; } -/* Advanced SIMD two registers and a scalar extension. - * 31 24 23 22 20 16 12 11 10 9 8 3 0 - * +-----------------+----+---+----+----+----+---+----+---+----+---------+----+ - * | 1 1 1 1 1 1 1 0 | o1 | D | o2 | Vn | Vd | 1 | o3 | 0 | o4 | N Q M U | Vm | - * +-----------------+----+---+----+----+----+---+----+---+----+---------+----+ - * - */ - -static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) -{ - gen_helper_gvec_3 *fn_gvec = NULL; - gen_helper_gvec_3_ptr *fn_gvec_ptr = NULL; - int rd, rn, rm, opr_sz, data; - int off_rn, off_rm; - bool is_long = false, q = extract32(insn, 6, 1); - bool ptr_is_env = false; - - if ((insn & 0xffa00f10) == 0xfe000810) { - /* VFM[AS]L -- 1111 1110 0.0S .... .... 1000 .Q.1 .... */ - int is_s = extract32(insn, 20, 1); - int vm20 = extract32(insn, 0, 3); - int vm3 = extract32(insn, 3, 1); - int m = extract32(insn, 5, 1); - int index; - - if (!dc_isar_feature(aa32_fhm, s)) { - return 1; - } - if (q) { - rm = vm20; - index = m * 2 + vm3; - } else { - rm = vm20 * 2 + m; - index = vm3; - } - is_long = true; - data = (index << 2) | is_s; /* is_2 == 0 */ - fn_gvec_ptr = gen_helper_gvec_fmlal_idx_a32; - ptr_is_env = true; - } else { - return 1; - } - - VFP_DREG_D(rd, insn); - if (rd & q) { - return 1; - } - if (q || !is_long) { - VFP_DREG_N(rn, insn); - if (rn & q & !is_long) { - return 1; - } - off_rn = vfp_reg_offset(1, rn); - off_rm = vfp_reg_offset(1, rm); - } else { - rn = VFP_SREG_N(insn); - off_rn = vfp_reg_offset(0, rn); - off_rm = vfp_reg_offset(0, rm); - } - if (s->fp_excp_el) { - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, - syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); - return 0; - } - if (!s->vfp_enabled) { - return 1; - } - - opr_sz = (1 + q) * 8; - if (fn_gvec_ptr) { - TCGv_ptr ptr; - if (ptr_is_env) { - ptr = cpu_env; - } else { - ptr = get_fpstatus_ptr(1); - } - tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), off_rn, off_rm, ptr, - opr_sz, opr_sz, data, fn_gvec_ptr); - if (!ptr_is_env) { - tcg_temp_free_ptr(ptr); - } - } else { - tcg_gen_gvec_3_ool(vfp_reg_offset(1, rd), off_rn, off_rm, - opr_sz, opr_sz, data, fn_gvec); - } - return 0; -} - static int disas_coproc_insn(DisasContext *s, uint32_t insn) { int cpnum, is64, crn, crm, opc1, opc2, isread, rt, rt2; @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) } } } - } else if ((insn & 0x0f000a00) == 0x0e000800 - && arm_dc_feature(s, ARM_FEATURE_V8)) { - if (disas_neon_insn_2reg_scalar_ext(s, insn)) { - goto illegal_op; - } - return; } goto illegal_op; } @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) } break; } - if ((insn & 0xff000a00) == 0xfe000800 - && arm_dc_feature(s, ARM_FEATURE_V8)) { - /* The Thumb2 and ARM encodings are identical. */ - if (disas_neon_insn_2reg_scalar_ext(s, insn)) { - goto illegal_op; - } - } else if (((insn >> 24) & 3) == 3) { + if (((insn >> 24) & 3) == 3) { /* Translate into the equivalent ARM encoding. */ insn = (insn & 0xe2ffffff) | ((insn & (1 << 28)) >> 4) | (1 << 28); if (disas_neon_data_insn(s, insn)) { -- 2.20.1 Convert the Neon "load/store multiple structures" insns to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-12-peter.maydell@linaro.org --- target/arm/neon-ls.decode | 7 ++ target/arm/translate-neon.inc.c | 124 ++++++++++++++++++++++++++++++++ target/arm/translate.c | 91 +---------------------- 3 files changed, 133 insertions(+), 89 deletions(-) diff --git a/target/arm/neon-ls.decode b/target/arm/neon-ls.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-ls.decode +++ b/target/arm/neon-ls.decode @@ -XXX,XX +XXX,XX @@ # 0b1111_1001_xxx0_xxxx_xxxx_xxxx_xxxx_xxxx # This file works on the A32 encoding only; calling code for T32 has to # transform the insn into the A32 version first. + +%vd_dp 22:1 12:4 + +# Neon load/store multiple structures + +VLDST_multiple 1111 0100 0 . l:1 0 rn:4 .... itype:4 size:2 align:2 rm:4 \ + vd=%vd_dp diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VFML_scalar(DisasContext *s, arg_VFML_scalar *a) gen_helper_gvec_fmlal_idx_a32); return true; } + +static struct { + int nregs; + int interleave; + int spacing; +} const neon_ls_element_type[11] = { + {1, 4, 1}, + {1, 4, 2}, + {4, 1, 1}, + {2, 2, 2}, + {1, 3, 1}, + {1, 3, 2}, + {3, 1, 1}, + {1, 1, 1}, + {1, 2, 1}, + {1, 2, 2}, + {2, 1, 1} +}; + +static void gen_neon_ldst_base_update(DisasContext *s, int rm, int rn, + int stride) +{ + if (rm != 15) { + TCGv_i32 base; + + base = load_reg(s, rn); + if (rm == 13) { + tcg_gen_addi_i32(base, base, stride); + } else { + TCGv_i32 index; + index = load_reg(s, rm); + tcg_gen_add_i32(base, base, index); + tcg_temp_free_i32(index); + } + store_reg(s, rn, base); + } +} + +static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a) +{ + /* Neon load/store multiple structures */ + int nregs, interleave, spacing, reg, n; + MemOp endian = s->be_data; + int mmu_idx = get_mem_index(s); + int size = a->size; + TCGv_i64 tmp64; + TCGv_i32 addr, tmp; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist */ + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { + return false; + } + if (a->itype > 10) { + return false; + } + /* Catch UNDEF cases for bad values of align field */ + switch (a->itype & 0xc) { + case 4: + if (a->align >= 2) { + return false; + } + break; + case 8: + if (a->align == 3) { + return false; + } + break; + default: + break; + } + nregs = neon_ls_element_type[a->itype].nregs; + interleave = neon_ls_element_type[a->itype].interleave; + spacing = neon_ls_element_type[a->itype].spacing; + if (size == 3 && (interleave | spacing) != 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* For our purposes, bytes are always little-endian. */ + if (size == 0) { + endian = MO_LE; + } + /* + * Consecutive little-endian elements from a single register + * can be promoted to a larger little-endian operation. + */ + if (interleave == 1 && endian == MO_LE) { + size = 3; + } + tmp64 = tcg_temp_new_i64(); + addr = tcg_temp_new_i32(); + tmp = tcg_const_i32(1 << size); + load_reg_var(s, addr, a->rn); + for (reg = 0; reg < nregs; reg++) { + for (n = 0; n < 8 >> size; n++) { + int xs; + for (xs = 0; xs < interleave; xs++) { + int tt = a->vd + reg + spacing * xs; + + if (a->l) { + gen_aa32_ld_i64(s, tmp64, addr, mmu_idx, endian | size); + neon_store_element64(tt, n, size, tmp64); + } else { + neon_load_element64(tmp64, tt, n, size); + gen_aa32_st_i64(s, tmp64, addr, mmu_idx, endian | size); + } + tcg_gen_add_i32(addr, addr, tmp); + } + } + } + tcg_temp_free_i32(addr); + tcg_temp_free_i32(tmp); + tcg_temp_free_i64(tmp64); + + gen_neon_ldst_base_update(s, a->rm, a->rn, nregs * interleave * 8); + return true; +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1) } -static struct { - int nregs; - int interleave; - int spacing; -} const neon_ls_element_type[11] = { - {1, 4, 1}, - {1, 4, 2}, - {4, 1, 1}, - {2, 2, 2}, - {1, 3, 1}, - {1, 3, 2}, - {3, 1, 1}, - {1, 1, 1}, - {1, 2, 1}, - {1, 2, 2}, - {2, 1, 1} -}; - /* Translate a NEON load/store element instruction. Return nonzero if the instruction is invalid. */ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) { int rd, rn, rm; - int op; int nregs; - int interleave; - int spacing; int stride; int size; int reg; int load; - int n; int vec_size; - int mmu_idx; - MemOp endian; TCGv_i32 addr; TCGv_i32 tmp; - TCGv_i32 tmp2; - TCGv_i64 tmp64; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return 1; @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) rn = (insn >> 16) & 0xf; rm = insn & 0xf; load = (insn & (1 << 21)) != 0; - endian = s->be_data; - mmu_idx = get_mem_index(s); if ((insn & (1 << 23)) == 0) { - /* Load store all elements. */ - op = (insn >> 8) & 0xf; - size = (insn >> 6) & 3; - if (op > 10) - return 1; - /* Catch UNDEF cases for bad values of align field */ - switch (op & 0xc) { - case 4: - if (((insn >> 5) & 1) == 1) { - return 1; - } - break; - case 8: - if (((insn >> 4) & 3) == 3) { - return 1; - } - break; - default: - break; - } - nregs = neon_ls_element_type[op].nregs; - interleave = neon_ls_element_type[op].interleave; - spacing = neon_ls_element_type[op].spacing; - if (size == 3 && (interleave | spacing) != 1) { - return 1; - } - /* For our purposes, bytes are always little-endian. */ - if (size == 0) { - endian = MO_LE; - } - /* Consecutive little-endian elements from a single register - * can be promoted to a larger little-endian operation. - */ - if (interleave == 1 && endian == MO_LE) { - size = 3; - } - tmp64 = tcg_temp_new_i64(); - addr = tcg_temp_new_i32(); - tmp2 = tcg_const_i32(1 << size); - load_reg_var(s, addr, rn); - for (reg = 0; reg < nregs; reg++) { - for (n = 0; n < 8 >> size; n++) { - int xs; - for (xs = 0; xs < interleave; xs++) { - int tt = rd + reg + spacing * xs; - - if (load) { - gen_aa32_ld_i64(s, tmp64, addr, mmu_idx, endian | size); - neon_store_element64(tt, n, size, tmp64); - } else { - neon_load_element64(tmp64, tt, n, size); - gen_aa32_st_i64(s, tmp64, addr, mmu_idx, endian | size); - } - tcg_gen_add_i32(addr, addr, tmp2); - } - } - } - tcg_temp_free_i32(addr); - tcg_temp_free_i32(tmp2); - tcg_temp_free_i64(tmp64); - stride = nregs * interleave * 8; + /* Load store all elements -- handled already by decodetree */ + return 1; } else { size = (insn >> 10) & 3; if (size == 3) { -- 2.20.1 Convert the Neon "load single structure to all lanes" insns to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-13-peter.maydell@linaro.org --- target/arm/neon-ls.decode | 5 +++ target/arm/translate-neon.inc.c | 73 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 55 +------------------------ 3 files changed, 80 insertions(+), 53 deletions(-) diff --git a/target/arm/neon-ls.decode b/target/arm/neon-ls.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-ls.decode +++ b/target/arm/neon-ls.decode @@ -XXX,XX +XXX,XX @@ VLDST_multiple 1111 0100 0 . l:1 0 rn:4 .... itype:4 size:2 align:2 rm:4 \ vd=%vd_dp + +# Neon load single element to all lanes + +VLD_all_lanes 1111 0100 1 . 1 0 rn:4 .... 11 n:2 size:2 t:1 a:1 rm:4 \ + vd=%vd_dp diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a) gen_neon_ldst_base_update(s, a->rm, a->rn, nregs * interleave * 8); return true; } + +static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a) +{ + /* Neon load single structure to all lanes */ + int reg, stride, vec_size; + int vd = a->vd; + int size = a->size; + int nregs = a->n + 1; + TCGv_i32 addr, tmp; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist */ + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { + return false; + } + + if (size == 3) { + if (nregs != 4 || a->a == 0) { + return false; + } + /* For VLD4 size == 3 a == 1 means 32 bits at 16 byte alignment */ + size = 2; + } + if (nregs == 1 && a->a == 1 && size == 0) { + return false; + } + if (nregs == 3 && a->a == 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* + * VLD1 to all lanes: T bit indicates how many Dregs to write. + * VLD2/3/4 to all lanes: T bit indicates register stride. + */ + stride = a->t ? 2 : 1; + vec_size = nregs == 1 ? stride * 8 : 8; + + tmp = tcg_temp_new_i32(); + addr = tcg_temp_new_i32(); + load_reg_var(s, addr, a->rn); + for (reg = 0; reg < nregs; reg++) { + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), + s->be_data | size); + if ((vd & 1) && vec_size == 16) { + /* + * We cannot write 16 bytes at once because the + * destination is unaligned. + */ + tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0), + 8, 8, tmp); + tcg_gen_gvec_mov(0, neon_reg_offset(vd + 1, 0), + neon_reg_offset(vd, 0), 8, 8); + } else { + tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0), + vec_size, vec_size, tmp); + } + tcg_gen_addi_i32(addr, addr, 1 << size); + vd += stride; + } + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(addr); + + gen_neon_ldst_base_update(s, a->rm, a->rn, (1 << size) * nregs); + + return true; +} 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 int disas_neon_ls_insn(DisasContext *s, uint32_t insn) int size; int reg; int load; - int vec_size; TCGv_i32 addr; TCGv_i32 tmp; @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) } else { size = (insn >> 10) & 3; if (size == 3) { - /* Load single element to all lanes. */ - int a = (insn >> 4) & 1; - if (!load) { - return 1; - } - size = (insn >> 6) & 3; - nregs = ((insn >> 8) & 3) + 1; - - if (size == 3) { - if (nregs != 4 || a == 0) { - return 1; - } - /* For VLD4 size==3 a == 1 means 32 bits at 16 byte alignment */ - size = 2; - } - if (nregs == 1 && a == 1 && size == 0) { - return 1; - } - if (nregs == 3 && a == 1) { - return 1; - } - addr = tcg_temp_new_i32(); - load_reg_var(s, addr, rn); - - /* VLD1 to all lanes: bit 5 indicates how many Dregs to write. - * VLD2/3/4 to all lanes: bit 5 indicates register stride. - */ - stride = (insn & (1 << 5)) ? 2 : 1; - vec_size = nregs == 1 ? stride * 8 : 8; - - tmp = tcg_temp_new_i32(); - for (reg = 0; reg < nregs; reg++) { - gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), - s->be_data | size); - if ((rd & 1) && vec_size == 16) { - /* We cannot write 16 bytes at once because the - * destination is unaligned. - */ - tcg_gen_gvec_dup_i32(size, neon_reg_offset(rd, 0), - 8, 8, tmp); - tcg_gen_gvec_mov(0, neon_reg_offset(rd + 1, 0), - neon_reg_offset(rd, 0), 8, 8); - } else { - tcg_gen_gvec_dup_i32(size, neon_reg_offset(rd, 0), - vec_size, vec_size, tmp); - } - tcg_gen_addi_i32(addr, addr, 1 << size); - rd += stride; - } - tcg_temp_free_i32(tmp); - tcg_temp_free_i32(addr); - stride = (1 << size) * nregs; + /* Load single element to all lanes -- handled by decodetree */ + return 1; } else { /* Single element. */ int idx = (insn >> 4) & 0xf; -- 2.20.1 Convert the Neon "load/store single structure to one lane" insns to decodetree. As this is the last set of insns in the neon load/store group, we can remove the whole disas_neon_ls_insn() function. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-14-peter.maydell@linaro.org --- target/arm/neon-ls.decode | 11 +++ target/arm/translate-neon.inc.c | 89 +++++++++++++++++++ target/arm/translate.c | 147 -------------------------------- 3 files changed, 100 insertions(+), 147 deletions(-) diff --git a/target/arm/neon-ls.decode b/target/arm/neon-ls.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-ls.decode +++ b/target/arm/neon-ls.decode @@ -XXX,XX +XXX,XX @@ VLDST_multiple 1111 0100 0 . l:1 0 rn:4 .... itype:4 size:2 align:2 rm:4 \ VLD_all_lanes 1111 0100 1 . 1 0 rn:4 .... 11 n:2 size:2 t:1 a:1 rm:4 \ vd=%vd_dp + +# Neon load/store single structure to one lane +%imm1_5_p1 5:1 !function=plus1 +%imm1_6_p1 6:1 !function=plus1 + +VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 00 n:2 reg_idx:3 align:1 rm:4 \ + vd=%vd_dp size=0 stride=1 +VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 01 n:2 reg_idx:2 align:2 rm:4 \ + vd=%vd_dp size=1 stride=%imm1_5_p1 +VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 10 n:2 reg_idx:1 align:3 rm:4 \ + vd=%vd_dp size=2 stride=%imm1_6_p1 diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ * It might be possible to convert it to a standalone .c file eventually. */ +static inline int plus1(DisasContext *s, int x) +{ + return x + 1; +} + /* Include the generated Neon decoder */ #include "decode-neon-dp.inc.c" #include "decode-neon-ls.inc.c" @@ -XXX,XX +XXX,XX @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a) return true; } + +static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a) +{ + /* Neon load/store single structure to one lane */ + int reg; + int nregs = a->n + 1; + int vd = a->vd; + TCGv_i32 addr, tmp; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist */ + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { + return false; + } + + /* Catch the UNDEF cases. This is unavoidably a bit messy. */ + switch (nregs) { + case 1: + if (((a->align & (1 << a->size)) != 0) || + (a->size == 2 && ((a->align & 3) == 1 || (a->align & 3) == 2))) { + return false; + } + break; + case 3: + if ((a->align & 1) != 0) { + return false; + } + /* fall through */ + case 2: + if (a->size == 2 && (a->align & 2) != 0) { + return false; + } + break; + case 4: + if ((a->size == 2) && ((a->align & 3) == 3)) { + return false; + } + break; + default: + abort(); + } + if ((vd + a->stride * (nregs - 1)) > 31) { + /* + * Attempts to write off the end of the register file are + * UNPREDICTABLE; we choose to UNDEF because otherwise we would + * access off the end of the array that holds the register data. + */ + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + tmp = tcg_temp_new_i32(); + addr = tcg_temp_new_i32(); + load_reg_var(s, addr, a->rn); + /* + * TODO: if we implemented alignment exceptions, we should check + * addr against the alignment encoded in a->align here. + */ + for (reg = 0; reg < nregs; reg++) { + if (a->l) { + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), + s->be_data | a->size); + neon_store_element(vd, a->reg_idx, a->size, tmp); + } else { /* Store */ + neon_load_element(tmp, vd, a->reg_idx, a->size); + gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), + s->be_data | a->size); + } + vd += a->stride; + tcg_gen_addi_i32(addr, addr, 1 << a->size); + } + tcg_temp_free_i32(addr); + tcg_temp_free_i32(tmp); + + gen_neon_ldst_base_update(s, a->rm, a->rn, (1 << a->size) * nregs); + + return true; +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1) tcg_temp_free_i32(rd); } - -/* Translate a NEON load/store element instruction. Return nonzero if the - instruction is invalid. */ -static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) -{ - int rd, rn, rm; - int nregs; - int stride; - int size; - int reg; - int load; - TCGv_i32 addr; - TCGv_i32 tmp; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { - return 1; - } - - /* FIXME: this access check should not take precedence over UNDEF - * for invalid encodings; we will generate incorrect syndrome information - * for attempts to execute invalid vfp/neon encodings with FP disabled. - */ - if (s->fp_excp_el) { - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, - syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); - return 0; - } - - if (!s->vfp_enabled) - return 1; - VFP_DREG_D(rd, insn); - rn = (insn >> 16) & 0xf; - rm = insn & 0xf; - load = (insn & (1 << 21)) != 0; - if ((insn & (1 << 23)) == 0) { - /* Load store all elements -- handled already by decodetree */ - return 1; - } else { - size = (insn >> 10) & 3; - if (size == 3) { - /* Load single element to all lanes -- handled by decodetree */ - return 1; - } else { - /* Single element. */ - int idx = (insn >> 4) & 0xf; - int reg_idx; - switch (size) { - case 0: - reg_idx = (insn >> 5) & 7; - stride = 1; - break; - case 1: - reg_idx = (insn >> 6) & 3; - stride = (insn & (1 << 5)) ? 2 : 1; - break; - case 2: - reg_idx = (insn >> 7) & 1; - stride = (insn & (1 << 6)) ? 2 : 1; - break; - default: - abort(); - } - nregs = ((insn >> 8) & 3) + 1; - /* Catch the UNDEF cases. This is unavoidably a bit messy. */ - switch (nregs) { - case 1: - if (((idx & (1 << size)) != 0) || - (size == 2 && ((idx & 3) == 1 || (idx & 3) == 2))) { - return 1; - } - break; - case 3: - if ((idx & 1) != 0) { - return 1; - } - /* fall through */ - case 2: - if (size == 2 && (idx & 2) != 0) { - return 1; - } - break; - case 4: - if ((size == 2) && ((idx & 3) == 3)) { - return 1; - } - break; - default: - abort(); - } - if ((rd + stride * (nregs - 1)) > 31) { - /* Attempts to write off the end of the register file - * are UNPREDICTABLE; we choose to UNDEF because otherwise - * the neon_load_reg() would write off the end of the array. - */ - return 1; - } - tmp = tcg_temp_new_i32(); - addr = tcg_temp_new_i32(); - load_reg_var(s, addr, rn); - for (reg = 0; reg < nregs; reg++) { - if (load) { - gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), - s->be_data | size); - neon_store_element(rd, reg_idx, size, tmp); - } else { /* Store */ - neon_load_element(tmp, rd, reg_idx, size); - gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), - s->be_data | size); - } - rd += stride; - tcg_gen_addi_i32(addr, addr, 1 << size); - } - tcg_temp_free_i32(addr); - tcg_temp_free_i32(tmp); - stride = nregs * (1 << size); - } - } - if (rm != 15) { - TCGv_i32 base; - - base = load_reg(s, rn); - if (rm == 13) { - tcg_gen_addi_i32(base, base, stride); - } else { - TCGv_i32 index; - index = load_reg(s, rm); - tcg_gen_add_i32(base, base, index); - tcg_temp_free_i32(index); - } - store_reg(s, rn, base); - } - return 0; -} - static inline void gen_neon_narrow(int size, TCGv_i32 dest, TCGv_i64 src) { switch (size) { @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) } return; } - if ((insn & 0x0f100000) == 0x04000000) { - /* NEON load/store. */ - if (disas_neon_ls_insn(s, insn)) { - goto illegal_op; - } - return; - } if ((insn & 0x0e000f00) == 0x0c000100) { if (arm_dc_feature(s, ARM_FEATURE_IWMMXT)) { /* iWMMXt register transfer. */ @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) } break; case 12: - if ((insn & 0x01100000) == 0x01000000) { - if (disas_neon_ls_insn(s, insn)) { - goto illegal_op; - } - break; - } goto illegal_op; default: illegal_op: -- 2.20.1 Convert the Neon 3-reg-same VADD and VSUB insns to decodetree. Note that we don't need the neon_3r_sizes[op] check here because all size values are OK for VADD and VSUB; we'll add this when we convert the first insn that has size restrictions. For this we need one of the GVecGen*Fn typedefs currently in translate-a64.h; move them all to translate.h as a block so they are visible to the 32-bit decoder. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-15-peter.maydell@linaro.org --- target/arm/translate-a64.h | 9 -------- target/arm/translate.h | 9 ++++++++ target/arm/neon-dp.decode | 17 +++++++++++++++ target/arm/translate-neon.inc.c | 38 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 14 ++++-------- 5 files changed, 68 insertions(+), 19 deletions(-) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline int vec_full_reg_size(DisasContext *s) bool disas_sve(DisasContext *, uint32_t); -/* Note that the gvec expanders operate on offsets + sizes. */ -typedef void GVecGen2Fn(unsigned, uint32_t, uint32_t, uint32_t, uint32_t); -typedef void GVecGen2iFn(unsigned, uint32_t, uint32_t, int64_t, - uint32_t, uint32_t); -typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t, - uint32_t, uint32_t, uint32_t); -typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t, - uint32_t, uint32_t, uint32_t); - #endif /* TARGET_ARM_TRANSLATE_A64_H */ diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ void gen_sshl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); #define dc_isar_feature(name, ctx) \ ({ DisasContext *ctx_ = (ctx); isar_feature_##name(ctx_->isar); }) +/* Note that the gvec expanders operate on offsets + sizes. */ +typedef void GVecGen2Fn(unsigned, uint32_t, uint32_t, uint32_t, uint32_t); +typedef void GVecGen2iFn(unsigned, uint32_t, uint32_t, int64_t, + uint32_t, uint32_t); +typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t, + uint32_t, uint32_t, uint32_t); +typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t, + uint32_t, uint32_t, uint32_t); + #endif /* TARGET_ARM_TRANSLATE_H */ diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ # # This file is processed by scripts/decodetree.py # +# VFP/Neon register fields; same as vfp.decode +%vm_dp 5:1 0:4 +%vn_dp 7:1 16:4 +%vd_dp 22:1 12:4 # Encodings for Neon data processing instructions where the T32 encoding # is a simple transformation of the A32 encoding. @@ -XXX,XX +XXX,XX @@ # 0b111p_1111_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq # This file works on the A32 encoding only; calling code for T32 has to # transform the insn into the A32 version first. + +###################################################################### +# 3-reg-same grouping: +# 1111 001 U 0 D sz:2 Vn:4 Vd:4 opc:4 N Q M op Vm:4 +###################################################################### + +&3same vm vn vd q size + +@3same .... ... . . . size:2 .... .... .... . q:1 . . .... \ + &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp + +VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same +VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a) return true; } + +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); + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if ((a->vn | a->vm | a->vd) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fn(a->size, rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); + return true; +} + +#define DO_3SAME(INSN, FUNC) \ + static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ + { \ + return do_3same(s, a, FUNC); \ + } + +DO_3SAME(VADD, tcg_gen_gvec_add) +DO_3SAME(VSUB, tcg_gen_gvec_sub) 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 int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 0; - case NEON_3R_VADD_VSUB: - if (u) { - tcg_gen_gvec_sub(size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - } else { - tcg_gen_gvec_add(size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - } - return 0; - case NEON_3R_VQADD: tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), rn_ofs, rm_ofs, vec_size, vec_size, @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, vec_size, vec_size, u ? &ushl_op[size] : &sshl_op[size]); return 0; + + case NEON_3R_VADD_VSUB: + /* Already handled by decodetree */ + return 1; } if (size == 3) { -- 2.20.1 Convert the Neon logic ops in the 3-reg-same grouping to decodetree. Note that for the logic ops the 'size' field forms part of their decode and the actual operations are always bitwise. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-16-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 12 +++++++++++ target/arm/translate-neon.inc.c | 19 +++++++++++++++++ target/arm/translate.c | 38 +-------------------------------- 3 files changed, 32 insertions(+), 37 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ @3same .... ... . . . size:2 .... .... .... . q:1 . . .... \ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp +@3same_logic .... ... . . . .. .... .... .... . q:1 .. .... \ + &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=0 + +VAND_3s 1111 001 0 0 . 00 .... .... 0001 ... 1 .... @3same_logic +VBIC_3s 1111 001 0 0 . 01 .... .... 0001 ... 1 .... @3same_logic +VORR_3s 1111 001 0 0 . 10 .... .... 0001 ... 1 .... @3same_logic +VORN_3s 1111 001 0 0 . 11 .... .... 0001 ... 1 .... @3same_logic +VEOR_3s 1111 001 1 0 . 00 .... .... 0001 ... 1 .... @3same_logic +VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic +VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic +VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic + VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool do_3same(DisasContext *s, arg_3same *a, GVecGen3Fn fn) DO_3SAME(VADD, tcg_gen_gvec_add) DO_3SAME(VSUB, tcg_gen_gvec_sub) +DO_3SAME(VAND, tcg_gen_gvec_and) +DO_3SAME(VBIC, tcg_gen_gvec_andc) +DO_3SAME(VORR, tcg_gen_gvec_or) +DO_3SAME(VORN, tcg_gen_gvec_orc) +DO_3SAME(VEOR, tcg_gen_gvec_xor) + +/* These insns are all gvec_bitsel but with the inputs in various orders. */ +#define DO_3SAME_BITSEL(INSN, O1, O2, O3) \ + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ + uint32_t rn_ofs, uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + tcg_gen_gvec_bitsel(vece, rd_ofs, O1, O2, O3, oprsz, maxsz); \ + } \ + DO_3SAME(INSN, gen_##INSN##_3s) + +DO_3SAME_BITSEL(VBSL, rd_ofs, rn_ofs, rm_ofs) +DO_3SAME_BITSEL(VBIT, rm_ofs, rn_ofs, rd_ofs) +DO_3SAME_BITSEL(VBIF, rm_ofs, rd_ofs, rn_ofs) 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 int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 1; - case NEON_3R_LOGIC: /* Logic ops. */ - switch ((u << 2) | size) { - case 0: /* VAND */ - tcg_gen_gvec_and(0, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - break; - case 1: /* VBIC */ - tcg_gen_gvec_andc(0, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - break; - case 2: /* VORR */ - tcg_gen_gvec_or(0, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - break; - case 3: /* VORN */ - tcg_gen_gvec_orc(0, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - break; - case 4: /* VEOR */ - tcg_gen_gvec_xor(0, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - break; - case 5: /* VBSL */ - tcg_gen_gvec_bitsel(MO_8, rd_ofs, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - break; - case 6: /* VBIT */ - tcg_gen_gvec_bitsel(MO_8, rd_ofs, rm_ofs, rn_ofs, rd_ofs, - vec_size, vec_size); - break; - case 7: /* VBIF */ - tcg_gen_gvec_bitsel(MO_8, rd_ofs, rm_ofs, rd_ofs, rn_ofs, - vec_size, vec_size); - break; - } - return 0; - case NEON_3R_VQADD: tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), rn_ofs, rm_ofs, vec_size, vec_size, @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 0; case NEON_3R_VADD_VSUB: + case NEON_3R_LOGIC: /* Already handled by decodetree */ return 1; } -- 2.20.1 Convert the Neon 3-reg-same VMAX and VMIN insns to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-17-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 5 +++++ target/arm/translate-neon.inc.c | 14 ++++++++++++++ target/arm/translate.c | 21 ++------------------- 3 files changed, 21 insertions(+), 19 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic +VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same +VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same +VMIN_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same +VMIN_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 1 .... @3same + VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME(VEOR, tcg_gen_gvec_xor) DO_3SAME_BITSEL(VBSL, rd_ofs, rn_ofs, rm_ofs) DO_3SAME_BITSEL(VBIT, rm_ofs, rn_ofs, rd_ofs) DO_3SAME_BITSEL(VBIF, rm_ofs, rd_ofs, rn_ofs) + +#define DO_3SAME_NO_SZ_3(INSN, FUNC) \ + static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ + { \ + if (a->size == 3) { \ + return false; \ + } \ + return do_3same(s, a, FUNC); \ + } + +DO_3SAME_NO_SZ_3(VMAX_S, tcg_gen_gvec_smax) +DO_3SAME_NO_SZ_3(VMAX_U, tcg_gen_gvec_umax) +DO_3SAME_NO_SZ_3(VMIN_S, tcg_gen_gvec_smin) +DO_3SAME_NO_SZ_3(VMIN_U, tcg_gen_gvec_umin) 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 int disas_neon_data_insn(DisasContext *s, uint32_t insn) rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); return 0; - case NEON_3R_VMAX: - if (u) { - tcg_gen_gvec_umax(size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - } else { - tcg_gen_gvec_smax(size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - } - return 0; - case NEON_3R_VMIN: - if (u) { - tcg_gen_gvec_umin(size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - } else { - tcg_gen_gvec_smin(size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - } - return 0; - case NEON_3R_VSHL: /* Note the operation is vshl vd,vm,vn */ tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, vec_size, vec_size, @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VADD_VSUB: case NEON_3R_LOGIC: + case NEON_3R_VMAX: + case NEON_3R_VMIN: /* Already handled by decodetree */ return 1; } -- 2.20.1 Convert the Neon comparison ops in the 3-reg-same grouping to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-18-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 8 ++++++++ target/arm/translate-neon.inc.c | 22 ++++++++++++++++++++++ target/arm/translate.c | 23 +++-------------------- 3 files changed, 33 insertions(+), 20 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic +VCGT_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 0 .... @3same +VCGT_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 0 .... @3same +VCGE_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 1 .... @3same +VCGE_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same + VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same VMIN_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same @@ -XXX,XX +XXX,XX @@ VMIN_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 1 .... @3same VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same + +VTST_3s 1111 001 0 0 . .. .... .... 1000 . . . 1 .... @3same +VCEQ_3s 1111 001 1 0 . .. .... .... 1000 . . . 1 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_NO_SZ_3(VMAX_S, tcg_gen_gvec_smax) DO_3SAME_NO_SZ_3(VMAX_U, tcg_gen_gvec_umax) DO_3SAME_NO_SZ_3(VMIN_S, tcg_gen_gvec_smin) DO_3SAME_NO_SZ_3(VMIN_U, tcg_gen_gvec_umin) + +#define DO_3SAME_CMP(INSN, COND) \ + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ + uint32_t rn_ofs, uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + tcg_gen_gvec_cmp(COND, vece, rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz); \ + } \ + DO_3SAME_NO_SZ_3(INSN, gen_##INSN##_3s) + +DO_3SAME_CMP(VCGT_S, TCG_COND_GT) +DO_3SAME_CMP(VCGT_U, TCG_COND_GTU) +DO_3SAME_CMP(VCGE_S, TCG_COND_GE) +DO_3SAME_CMP(VCGE_U, TCG_COND_GEU) +DO_3SAME_CMP(VCEQ, TCG_COND_EQ) + +static void gen_VTST_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz) +{ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &cmtst_op[vece]); +} +DO_3SAME_NO_SZ_3(VTST, gen_VTST_3s) 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 int disas_neon_data_insn(DisasContext *s, uint32_t insn) u ? &mls_op[size] : &mla_op[size]); return 0; - case NEON_3R_VTST_VCEQ: - if (u) { /* VCEQ */ - tcg_gen_gvec_cmp(TCG_COND_EQ, size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - } else { /* VTST */ - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size, &cmtst_op[size]); - } - return 0; - - case NEON_3R_VCGT: - tcg_gen_gvec_cmp(u ? TCG_COND_GTU : TCG_COND_GT, size, - rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); - return 0; - - case NEON_3R_VCGE: - tcg_gen_gvec_cmp(u ? TCG_COND_GEU : TCG_COND_GE, size, - rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); - return 0; - case NEON_3R_VSHL: /* Note the operation is vshl vd,vm,vn */ tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, vec_size, vec_size, @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_LOGIC: case NEON_3R_VMAX: case NEON_3R_VMIN: + case NEON_3R_VTST_VCEQ: + case NEON_3R_VCGT: + case NEON_3R_VCGE: /* Already handled by decodetree */ return 1; } -- 2.20.1 Convert the Neon VQADD/VQSUB insns in the 3-reg-same grouping to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-19-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 6 ++++++ target/arm/translate-neon.inc.c | 15 +++++++++++++++ target/arm/translate.c | 14 ++------------ 3 files changed, 23 insertions(+), 12 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ @3same .... ... . . . size:2 .... .... .... . q:1 . . .... \ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp +VQADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 1 .... @3same +VQADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 1 .... @3same + @3same_logic .... ... . . . .. .... .... .... . q:1 .. .... \ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=0 @@ -XXX,XX +XXX,XX @@ VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic +VQSUB_S_3s 1111 001 0 0 . .. .... .... 0010 . . . 1 .... @3same +VQSUB_U_3s 1111 001 1 0 . .. .... .... 0010 . . . 1 .... @3same + VCGT_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 0 .... @3same VCGT_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 0 .... @3same VCGE_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 1 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static void gen_VTST_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &cmtst_op[vece]); } DO_3SAME_NO_SZ_3(VTST, gen_VTST_3s) + +#define DO_3SAME_GVEC4(INSN, OPARRAY) \ + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ + uint32_t rn_ofs, uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), \ + rn_ofs, rm_ofs, oprsz, maxsz, &OPARRAY[vece]); \ + } \ + DO_3SAME(INSN, gen_##INSN##_3s) + +DO_3SAME_GVEC4(VQADD_S, sqadd_op) +DO_3SAME_GVEC4(VQADD_U, uqadd_op) +DO_3SAME_GVEC4(VQSUB_S, sqsub_op) +DO_3SAME_GVEC4(VQSUB_U, uqsub_op) 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 int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 1; - case NEON_3R_VQADD: - tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), - rn_ofs, rm_ofs, vec_size, vec_size, - (u ? uqadd_op : sqadd_op) + size); - return 0; - - case NEON_3R_VQSUB: - tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), - rn_ofs, rm_ofs, vec_size, vec_size, - (u ? uqsub_op : sqsub_op) + size); - return 0; - case NEON_3R_VMUL: /* VMUL */ if (u) { /* Polynomial case allows only P8. */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VTST_VCEQ: case NEON_3R_VCGT: case NEON_3R_VCGE: + case NEON_3R_VQADD: + case NEON_3R_VQSUB: /* Already handled by decodetree */ return 1; } -- 2.20.1 Convert the Neon VMUL, VMLA, VMLS and VSHL insns in the 3-reg-same grouping to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-20-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 9 +++++++ target/arm/translate-neon.inc.c | 44 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 28 +++------------------ 3 files changed, 56 insertions(+), 25 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VCGT_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 0 .... @3same VCGE_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 1 .... @3same VCGE_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same +VSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 0 .... @3same +VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same + VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same VMIN_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same @@ -XXX,XX +XXX,XX @@ VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same VTST_3s 1111 001 0 0 . .. .... .... 1000 . . . 1 .... @3same VCEQ_3s 1111 001 1 0 . .. .... .... 1000 . . . 1 .... @3same + +VMLA_3s 1111 001 0 0 . .. .... .... 1001 . . . 0 .... @3same +VMLS_3s 1111 001 1 0 . .. .... .... 1001 . . . 0 .... @3same + +VMUL_3s 1111 001 0 0 . .. .... .... 1001 . . . 1 .... @3same +VMUL_p_3s 1111 001 1 0 . .. .... .... 1001 . . . 1 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_NO_SZ_3(VMAX_S, tcg_gen_gvec_smax) DO_3SAME_NO_SZ_3(VMAX_U, tcg_gen_gvec_umax) DO_3SAME_NO_SZ_3(VMIN_S, tcg_gen_gvec_smin) DO_3SAME_NO_SZ_3(VMIN_U, tcg_gen_gvec_umin) +DO_3SAME_NO_SZ_3(VMUL, tcg_gen_gvec_mul) #define DO_3SAME_CMP(INSN, COND) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_3SAME_GVEC4(VQADD_S, sqadd_op) DO_3SAME_GVEC4(VQADD_U, uqadd_op) DO_3SAME_GVEC4(VQSUB_S, sqsub_op) DO_3SAME_GVEC4(VQSUB_U, uqsub_op) + +static void gen_VMUL_p_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz) +{ + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, + 0, gen_helper_gvec_pmul_b); +} + +static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a) +{ + if (a->size != 0) { + return false; + } + return do_3same(s, a, gen_VMUL_p_3s); +} + +#define DO_3SAME_GVEC3_NO_SZ_3(INSN, OPARRAY) \ + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ + uint32_t rn_ofs, uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, \ + oprsz, maxsz, &OPARRAY[vece]); \ + } \ + DO_3SAME_NO_SZ_3(INSN, gen_##INSN##_3s) + + +DO_3SAME_GVEC3_NO_SZ_3(VMLA, mla_op) +DO_3SAME_GVEC3_NO_SZ_3(VMLS, mls_op) + +#define DO_3SAME_GVEC3_SHIFT(INSN, OPARRAY) \ + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ + uint32_t rn_ofs, uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + /* Note the operation is vshl vd,vm,vn */ \ + tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, \ + oprsz, maxsz, &OPARRAY[vece]); \ + } \ + DO_3SAME(INSN, gen_##INSN##_3s) + +DO_3SAME_GVEC3_SHIFT(VSHL_S, sshl_op) +DO_3SAME_GVEC3_SHIFT(VSHL_U, ushl_op) 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 int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 1; - case NEON_3R_VMUL: /* VMUL */ - if (u) { - /* Polynomial case allows only P8. */ - if (size != 0) { - return 1; - } - tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size, - 0, gen_helper_gvec_pmul_b); - } else { - tcg_gen_gvec_mul(size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - } - return 0; - - case NEON_3R_VML: /* VMLA, VMLS */ - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size, - u ? &mls_op[size] : &mla_op[size]); - return 0; - - case NEON_3R_VSHL: - /* Note the operation is vshl vd,vm,vn */ - tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, vec_size, vec_size, - u ? &ushl_op[size] : &sshl_op[size]); - return 0; - case NEON_3R_VADD_VSUB: case NEON_3R_LOGIC: case NEON_3R_VMAX: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VCGE: case NEON_3R_VQADD: case NEON_3R_VQSUB: + case NEON_3R_VMUL: + case NEON_3R_VML: + case NEON_3R_VSHL: /* Already handled by decodetree */ return 1; } -- 2.20.1 We're going to want at least some of the NeonGen* typedefs for the refactored 32-bit Neon decoder, so move them all to translate.h since it makes more sense to keep them in one group. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200430181003.21682-23-peter.maydell@linaro.org --- target/arm/translate.h | 17 +++++++++++++++++ target/arm/translate-a64.c | 17 ----------------- 2 files changed, 17 insertions(+), 17 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t, typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t, uint32_t, uint32_t, uint32_t); +/* Function prototype for gen_ functions for calling Neon helpers */ +typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32); +typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32); +typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); +typedef void NeonGenTwo64OpFn(TCGv_i64, TCGv_i64, TCGv_i64); +typedef void NeonGenTwo64OpEnvFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i64); +typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64); +typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64); +typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32); +typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); +typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr); +typedef void NeonGenOneOpFn(TCGv_i64, TCGv_i64); +typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr); +typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); +typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); + #endif /* TARGET_ARM_TRANSLATE_H */ 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 @@ typedef struct AArch64DecodeTable { AArch64DecodeFn *disas_fn; } AArch64DecodeTable; -/* Function prototype for gen_ functions for calling Neon helpers */ -typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32); -typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32); -typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); -typedef void NeonGenTwo64OpFn(TCGv_i64, TCGv_i64, TCGv_i64); -typedef void NeonGenTwo64OpEnvFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i64); -typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64); -typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64); -typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32); -typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); -typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr); -typedef void NeonGenOneOpFn(TCGv_i64, TCGv_i64); -typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr); -typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32); -typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); -typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); - /* initialize TCG globals. */ void a64_translate_init(void) { -- 2.20.1 Nuvoton new board models, and some more minor stuff. I also put in the deprecation patches for unicore32 and lm32. thanks -- PMM The following changes since commit a68694cd1f3e5448cca814ff39b871f9ebd71ed5: Merge remote-tracking branch 'remotes/philmd-gitlab/tags/edk2-next-20200914' into staging (2020-09-14 12:18:58 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200914 for you to fetch changes up to dd44ae00fc5342ed99acb68ec3508f76a71d523a: MAINTAINERS: Add maintainer entry for Xilinx ZynqMP CAN controller (2020-09-14 14:27:08 +0100) ---------------------------------------------------------------- target-arm queue: * hw/misc/a9scu: Do not allow invalid CPU count * hw/misc/a9scu: Minor cleanups * hw/timer/armv7m_systick: assert that board code set system_clock_scale * decodetree: Improve identifier matching * target/arm: Clean up neon fp insn size field decode * target/arm: Remove KVM support for 32-bit Arm hosts * hw/arm/mps2: New board models mps2-an386, mps2-an500 * Deprecate Unicore32 port * Deprecate lm32 port * target/arm: Count PMU events when MDCR.SPME is set * hw/arm: versal-virt: Correct the tx/rx GEM clocks * New Nuvoton iBMC board models npcm750-evb, quanta-gsj * xlnx-zynqmp: implement ZynqMP CAN controllers ---------------------------------------------------------------- Aaron Lindsay (1): target/arm: Count PMU events when MDCR.SPME is set Edgar E. Iglesias (1): hw/arm: versal-virt: Correct the tx/rx GEM clocks Havard Skinnemoen (14): hw/misc: Add NPCM7xx System Global Control Registers device model hw/misc: Add NPCM7xx Clock Controller device model hw/timer: Add NPCM7xx Timer device model hw/arm: Add NPCM730 and NPCM750 SoC models hw/arm: Add two NPCM7xx-based machines roms: Add virtual Boot ROM for NPCM7xx SoCs hw/arm: Load -bios image as a boot ROM for npcm7xx hw/nvram: NPCM7xx OTP device model hw/mem: Stubbed out NPCM7xx Memory Controller model hw/ssi: NPCM7xx Flash Interface Unit device model hw/arm: Wire up BMC boot flash for npcm750-evb and quanta-gsj hw/arm/npcm7xx: add board setup stub for CPU and UART clocks docs/system: Add Nuvoton machine documentation tests/acceptance: console boot tests for quanta-gsj Peter Maydell (11): hw/timer/armv7m_systick: assert that board code set system_clock_scale target/arm: Convert Neon 3-same-fp size field to MO_* in decode target/arm: Convert Neon VCVT fp size field to MO_* in decode target/arm: Convert VCMLA, VCADD size field to MO_* in decode target/arm: Remove KVM support for 32-bit Arm hosts target/arm: Remove no-longer-reachable 32-bit KVM code hw/arm/mps2: New board model mps2-an386 hw/arm/mps2: New board model mps2-an500 docs/system/arm/mps2.rst: Make board list consistent Deprecate Unicore32 port Deprecate lm32 port Philippe Mathieu-Daudé (4): hw/misc/a9scu: Do not allow invalid CPU count hw/misc/a9scu: Simplify setting MemoryRegionOps::valid fields hw/misc/a9scu: Simplify setting MemoryRegionOps::impl fields hw/misc/a9scu: Report unimplemented accesses with qemu_log_mask(UNIMP) Richard Henderson (1): decodetree: Improve identifier matching Vikram Garhwal (4): hw/net/can: Introduce Xilinx ZynqMP CAN controller xlnx-zynqmp: Connect Xilinx ZynqMP CAN controllers tests/qtest: Introduce tests for Xilinx ZynqMP CAN controller MAINTAINERS: Add maintainer entry for Xilinx ZynqMP CAN controller docs/system/arm/mps2.rst | 20 +- docs/system/arm/nuvoton.rst | 92 +++ docs/system/deprecated.rst | 32 +- docs/system/target-arm.rst | 1 + configure | 2 +- default-configs/arm-softmmu.mak | 1 + include/hw/arm/npcm7xx.h | 112 +++ include/hw/arm/xlnx-zynqmp.h | 8 + include/hw/mem/npcm7xx_mc.h | 36 + include/hw/misc/npcm7xx_clk.h | 48 ++ include/hw/misc/npcm7xx_gcr.h | 43 ++ include/hw/net/xlnx-zynqmp-can.h | 78 +++ include/hw/nvram/npcm7xx_otp.h | 79 +++ include/hw/ssi/npcm7xx_fiu.h | 73 ++ include/hw/timer/npcm7xx_timer.h | 78 +++ target/arm/kvm-consts.h | 7 - target/arm/kvm_arm.h | 6 - target/arm/neon-dp.decode | 18 +- target/arm/neon-shared.decode | 18 +- tests/decode/succ_ident1.decode | 7 + hw/arm/mps2.c | 97 ++- hw/arm/npcm7xx.c | 532 +++++++++++++++ hw/arm/npcm7xx_boards.c | 197 ++++++ hw/arm/xlnx-versal-virt.c | 2 +- hw/arm/xlnx-zcu102.c | 20 + hw/arm/xlnx-zynqmp.c | 34 + hw/mem/npcm7xx_mc.c | 84 +++ hw/misc/a9scu.c | 59 +- hw/misc/npcm7xx_clk.c | 266 ++++++++ hw/misc/npcm7xx_gcr.c | 269 ++++++++ hw/net/can/xlnx-zynqmp-can.c | 1165 ++++++++++++++++++++++++++++++++ hw/nvram/npcm7xx_otp.c | 440 ++++++++++++ hw/ssi/npcm7xx_fiu.c | 572 ++++++++++++++++ hw/timer/armv7m_systick.c | 8 + hw/timer/npcm7xx_timer.c | 543 +++++++++++++++ target/arm/cpu.c | 101 ++- target/arm/helper.c | 2 +- target/arm/kvm.c | 7 - target/arm/kvm32.c | 595 ---------------- tests/qtest/xlnx-can-test.c | 359 ++++++++++ .gitmodules | 3 + MAINTAINERS | 18 + hw/arm/Kconfig | 9 + hw/arm/meson.build | 1 + hw/mem/meson.build | 1 + hw/misc/meson.build | 4 + hw/misc/trace-events | 8 + hw/net/can/meson.build | 1 + hw/nvram/meson.build | 1 + hw/ssi/meson.build | 1 + hw/ssi/trace-events | 11 + hw/timer/meson.build | 1 + hw/timer/trace-events | 5 + pc-bios/README | 6 + pc-bios/meson.build | 1 + pc-bios/npcm7xx_bootrom.bin | Bin 0 -> 768 bytes roms/Makefile | 7 + roms/vbootrom | 1 + scripts/decodetree.py | 46 +- target/arm/meson.build | 5 +- target/arm/translate-neon.c.inc | 42 +- tests/acceptance/boot_linux_console.py | 83 +++ tests/qtest/meson.build | 1 + 63 files changed, 5584 insertions(+), 783 deletions(-) create mode 100644 docs/system/arm/nuvoton.rst create mode 100644 include/hw/arm/npcm7xx.h create mode 100644 include/hw/mem/npcm7xx_mc.h create mode 100644 include/hw/misc/npcm7xx_clk.h create mode 100644 include/hw/misc/npcm7xx_gcr.h create mode 100644 include/hw/net/xlnx-zynqmp-can.h create mode 100644 include/hw/nvram/npcm7xx_otp.h create mode 100644 include/hw/ssi/npcm7xx_fiu.h create mode 100644 include/hw/timer/npcm7xx_timer.h create mode 100644 tests/decode/succ_ident1.decode create mode 100644 hw/arm/npcm7xx.c create mode 100644 hw/arm/npcm7xx_boards.c create mode 100644 hw/mem/npcm7xx_mc.c create mode 100644 hw/misc/npcm7xx_clk.c create mode 100644 hw/misc/npcm7xx_gcr.c create mode 100644 hw/net/can/xlnx-zynqmp-can.c create mode 100644 hw/nvram/npcm7xx_otp.c create mode 100644 hw/ssi/npcm7xx_fiu.c create mode 100644 hw/timer/npcm7xx_timer.c delete mode 100644 target/arm/kvm32.c create mode 100644 tests/qtest/xlnx-can-test.c create mode 100644 pc-bios/npcm7xx_bootrom.bin create mode 160000 roms/vbootrom From: Philippe Mathieu-Daudé <f4bug@amsat.org> Per the datasheet (DDI0407 r2p0): "The SCU connects one to four Cortex-A9 processors to the memory system through the AXI interfaces." Change the instance_init() handler to a device_realize() one so we can verify the property is in range, and return an error to the caller if not. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200901144100.116742-2-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/a9scu.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/hw/misc/a9scu.c b/hw/misc/a9scu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/a9scu.c +++ b/hw/misc/a9scu.c @@ -XXX,XX +XXX,XX @@ #include "hw/misc/a9scu.h" #include "hw/qdev-properties.h" #include "migration/vmstate.h" +#include "qapi/error.h" #include "qemu/module.h" +#define A9_SCU_CPU_MAX 4 + static uint64_t a9_scu_read(void *opaque, hwaddr offset, unsigned size) { @@ -XXX,XX +XXX,XX @@ static void a9_scu_reset(DeviceState *dev) s->control = 0; } -static void a9_scu_init(Object *obj) +static void a9_scu_realize(DeviceState *dev, Error **errp) { - A9SCUState *s = A9_SCU(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + A9SCUState *s = A9_SCU(dev); + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - memory_region_init_io(&s->iomem, obj, &a9_scu_ops, s, + if (!s->num_cpu || s->num_cpu > A9_SCU_CPU_MAX) { + error_setg(errp, "Illegal CPU count: %u", s->num_cpu); + return; + } + + memory_region_init_io(&s->iomem, OBJECT(s), &a9_scu_ops, s, "a9-scu", 0x100); sysbus_init_mmio(sbd, &s->iomem); } @@ -XXX,XX +XXX,XX @@ static void a9_scu_class_init(ObjectClass *klass, void *data) device_class_set_props(dc, a9_scu_properties); dc->vmsd = &vmstate_a9_scu; dc->reset = a9_scu_reset; + dc->realize = a9_scu_realize; } static const TypeInfo a9_scu_info = { .name = TYPE_A9_SCU, .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(A9SCUState), - .instance_init = a9_scu_init, .class_init = a9_scu_class_init, }; -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Per the datasheet (DDI0407 r2p0): "All SCU registers are byte accessible" and are 32-bit aligned. Set MemoryRegionOps::valid min/max fields and simplify the write() handler. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200901144100.116742-3-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/a9scu.c | 21 +++++---------------- 1 file changed, 5 insertions(+), 16 deletions(-) diff --git a/hw/misc/a9scu.c b/hw/misc/a9scu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/a9scu.c +++ b/hw/misc/a9scu.c @@ -XXX,XX +XXX,XX @@ static void a9_scu_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { A9SCUState *s = (A9SCUState *)opaque; - uint32_t mask; + uint32_t mask = MAKE_64BIT_MASK(0, size * 8); uint32_t shift; - switch (size) { - case 1: - mask = 0xff; - break; - case 2: - mask = 0xffff; - break; - case 4: - mask = 0xffffffff; - break; - default: - fprintf(stderr, "Invalid size %u in write to a9 scu register %x\n", - size, (unsigned)offset); - return; - } switch (offset) { case 0x00: /* Control */ @@ -XXX,XX +XXX,XX @@ static void a9_scu_write(void *opaque, hwaddr offset, static const MemoryRegionOps a9_scu_ops = { .read = a9_scu_read, .write = a9_scu_write, + .valid = { + .min_access_size = 1, + .max_access_size = 4, + }, .endianness = DEVICE_NATIVE_ENDIAN, }; -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> This model implementation is designed for 32-bit accesses. We can simplify setting the MemoryRegionOps::impl min/max fields to 32-bit (memory::access_with_adjusted_size() will take care of the 8/16-bit accesses). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200901144100.116742-4-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/a9scu.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/hw/misc/a9scu.c b/hw/misc/a9scu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/a9scu.c +++ b/hw/misc/a9scu.c @@ -XXX,XX +XXX,XX @@ static uint64_t a9_scu_read(void *opaque, hwaddr offset, return (((1 << s->num_cpu) - 1) << 4) | (s->num_cpu - 1); case 0x08: /* CPU Power Status */ return s->status; - case 0x09: /* CPU status. */ - return s->status >> 8; - case 0x0a: /* CPU status. */ - return s->status >> 16; - case 0x0b: /* CPU status. */ - return s->status >> 24; case 0x0c: /* Invalidate All Registers In Secure State */ return 0; case 0x40: /* Filtering Start Address Register */ @@ -XXX,XX +XXX,XX @@ static void a9_scu_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { A9SCUState *s = (A9SCUState *)opaque; - uint32_t mask = MAKE_64BIT_MASK(0, size * 8); - uint32_t shift; switch (offset) { case 0x00: /* Control */ @@ -XXX,XX +XXX,XX @@ static void a9_scu_write(void *opaque, hwaddr offset, case 0x4: /* Configuration: RO */ break; case 0x08: case 0x09: case 0x0A: case 0x0B: /* Power Control */ - shift = (offset - 0x8) * 8; - s->status &= ~(mask << shift); - s->status |= ((value & mask) << shift); + s->status = value; break; case 0x0c: /* Invalidate All Registers In Secure State */ /* no-op as we do not implement caches */ @@ -XXX,XX +XXX,XX @@ static void a9_scu_write(void *opaque, hwaddr offset, static const MemoryRegionOps a9_scu_ops = { .read = a9_scu_read, .write = a9_scu_write, + .impl = { + .min_access_size = 4, + .max_access_size = 4, + }, .valid = { .min_access_size = 1, .max_access_size = 4, -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Report unimplemented register accesses using qemu_log_mask(UNIMP). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200901144100.116742-5-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/a9scu.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/misc/a9scu.c b/hw/misc/a9scu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/a9scu.c +++ b/hw/misc/a9scu.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties.h" #include "migration/vmstate.h" #include "qapi/error.h" +#include "qemu/log.h" #include "qemu/module.h" #define A9_SCU_CPU_MAX 4 @@ -XXX,XX +XXX,XX @@ static uint64_t a9_scu_read(void *opaque, hwaddr offset, case 0x54: /* SCU Non-secure Access Control Register */ /* unimplemented, fall through */ default: + qemu_log_mask(LOG_UNIMP, "%s: Unsupported offset 0x%"HWADDR_PRIx"\n", + __func__, offset); return 0; } } @@ -XXX,XX +XXX,XX @@ static void a9_scu_write(void *opaque, hwaddr offset, case 0x54: /* SCU Non-secure Access Control Register */ /* unimplemented, fall through */ default: + qemu_log_mask(LOG_UNIMP, "%s: Unsupported offset 0x%"HWADDR_PRIx + " value 0x%"PRIx64"\n", + __func__, offset, value); break; } } -- 2.20.1 It is the responsibility of board code for an armv7m system to set system_clock_scale appropriately for the CPU speed of the core. If it forgets to do this, then QEMU will hang if the guest tries to use the systick timer in the "tick at the CPU clock frequency" mode. We forgot that in a couple of our boards (see commits ce4f70e81ed23c93f, e7e5a9595ab1136). Add an assertion in the systick reset method so we don't let any new boards in with the same bug. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200825160847.18091-1-peter.maydell@linaro.org --- hw/timer/armv7m_systick.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/hw/timer/armv7m_systick.c b/hw/timer/armv7m_systick.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/armv7m_systick.c +++ b/hw/timer/armv7m_systick.c @@ -XXX,XX +XXX,XX @@ static void systick_reset(DeviceState *dev) { SysTickState *s = SYSTICK(dev); + /* + * Forgetting to set system_clock_scale is always a board code + * bug. We can't check this earlier because for some boards + * (like stellaris) it is not yet configured at the point where + * the systick device is realized. + */ + assert(system_clock_scale != 0); + s->control = 0; s->reload = 0; s->tick = 0; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Only argument set members have to be C identifiers, everything else gets prefixed during conversion to C. Some places just checked the leading character, and some places matched a leading character plus a C identifier. Convert everything to match full identifiers, including the [&%@&] prefix, and drop the full C identifier requirement. Reported-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200903192334.1603773-1-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/decode/succ_ident1.decode | 7 +++++ scripts/decodetree.py | 46 +++++++++++++++++++++------------ 2 files changed, 37 insertions(+), 16 deletions(-) create mode 100644 tests/decode/succ_ident1.decode diff --git a/tests/decode/succ_ident1.decode b/tests/decode/succ_ident1.decode new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/decode/succ_ident1.decode @@ -XXX,XX +XXX,XX @@ +%1f 0:8 +%2f 8:8 +%3f 16:8 + +&3arg a b c +@3arg ........ ........ ........ ........ &3arg a=%1f b=%2f c=%3f +3insn 00000000 ........ ........ ........ @3arg diff --git a/scripts/decodetree.py b/scripts/decodetree.py index XXXXXXX..XXXXXXX 100644 --- a/scripts/decodetree.py +++ b/scripts/decodetree.py @@ -XXX,XX +XXX,XX @@ output_fd = None insntype = 'uint32_t' decode_function = 'decode' -re_ident = '[a-zA-Z][a-zA-Z0-9_]*' +# An identifier for C. +re_C_ident = '[a-zA-Z][a-zA-Z0-9_]*' +# Identifiers for Arguments, Fields, Formats and Patterns. +re_arg_ident = '&[a-zA-Z0-9_]*' +re_fld_ident = '%[a-zA-Z0-9_]*' +re_fmt_ident = '@[a-zA-Z0-9_]*' +re_pat_ident = '[a-zA-Z0-9_]*' def error_with_file(file, lineno, *args): """Print an error message from file:line and args and exit.""" @@ -XXX,XX +XXX,XX @@ class ExcMultiPattern(MultiPattern): def parse_field(lineno, name, toks): """Parse one instruction field from TOKS at LINENO""" global fields - global re_ident global insnwidth # A "simple" field will have only one entry; @@ -XXX,XX +XXX,XX @@ def parse_field(lineno, name, toks): width = 0 func = None for t in toks: - if re.fullmatch('!function=' + re_ident, t): + if re.match('^!function=', t): if func: error(lineno, 'duplicate function') func = t.split('=') @@ -XXX,XX +XXX,XX @@ def parse_field(lineno, name, toks): def parse_arguments(lineno, name, toks): """Parse one argument set from TOKS at LINENO""" global arguments - global re_ident + global re_C_ident global anyextern flds = [] @@ -XXX,XX +XXX,XX @@ def parse_arguments(lineno, name, toks): extern = True anyextern = True continue - if not re.fullmatch(re_ident, t): + if not re.fullmatch(re_C_ident, t): error(lineno, 'invalid argument set token "{0}"'.format(t)) if t in flds: error(lineno, 'duplicate argument "{0}"'.format(t)) @@ -XXX,XX +XXX,XX @@ def parse_generic(lineno, parent_pat, name, toks): global arguments global formats global allpatterns - global re_ident + global re_arg_ident + global re_fld_ident + global re_fmt_ident + global re_C_ident global insnwidth global insnmask global variablewidth @@ -XXX,XX +XXX,XX @@ def parse_generic(lineno, parent_pat, name, toks): fmt = None for t in toks: # '&Foo' gives a format an explcit argument set. - if t[0] == '&': + if re.fullmatch(re_arg_ident, t): tt = t[1:] if arg: error(lineno, 'multiple argument sets') @@ -XXX,XX +XXX,XX @@ def parse_generic(lineno, parent_pat, name, toks): continue # '@Foo' gives a pattern an explicit format. - if t[0] == '@': + if re.fullmatch(re_fmt_ident, t): tt = t[1:] if fmt: error(lineno, 'multiple formats') @@ -XXX,XX +XXX,XX @@ def parse_generic(lineno, parent_pat, name, toks): continue # '%Foo' imports a field. - if t[0] == '%': + if re.fullmatch(re_fld_ident, t): tt = t[1:] flds = add_field_byname(lineno, flds, tt, tt) continue # 'Foo=%Bar' imports a field with a different name. - if re.fullmatch(re_ident + '=%' + re_ident, t): + if re.fullmatch(re_C_ident + '=' + re_fld_ident, t): (fname, iname) = t.split('=%') flds = add_field_byname(lineno, flds, fname, iname) continue # 'Foo=number' sets an argument field to a constant value - if re.fullmatch(re_ident + '=[+-]?[0-9]+', t): + if re.fullmatch(re_C_ident + '=[+-]?[0-9]+', t): (fname, value) = t.split('=') value = int(value) flds = add_field(lineno, flds, fname, ConstField(value)) @@ -XXX,XX +XXX,XX @@ def parse_generic(lineno, parent_pat, name, toks): fixedmask = (fixedmask << shift) | fms undefmask = (undefmask << shift) | ubm # Otherwise, fieldname:fieldwidth - elif re.fullmatch(re_ident + ':s?[0-9]+', t): + elif re.fullmatch(re_C_ident + ':s?[0-9]+', t): (fname, flen) = t.split(':') sign = False if flen[0] == 's': @@ -XXX,XX +XXX,XX @@ def parse_generic(lineno, parent_pat, name, toks): def parse_file(f, parent_pat): """Parse all of the patterns within a file""" + global re_arg_ident + global re_fld_ident + global re_fmt_ident + global re_pat_ident # Read all of the lines of the file. Concatenate lines # ending in backslash; discard empty lines and comments. @@ -XXX,XX +XXX,XX @@ def parse_file(f, parent_pat): continue # Determine the type of object needing to be parsed. - if name[0] == '%': + if re.fullmatch(re_fld_ident, name): parse_field(start_lineno, name[1:], toks) - elif name[0] == '&': + elif re.fullmatch(re_arg_ident, name): parse_arguments(start_lineno, name[1:], toks) - elif name[0] == '@': + elif re.fullmatch(re_fmt_ident, name): parse_generic(start_lineno, None, name[1:], toks) - else: + elif re.fullmatch(re_pat_ident, name): parse_generic(start_lineno, parent_pat, name, toks) + else: + error(lineno, 'invalid token "{0}"'.format(name)) toks = [] if nesting != 0: -- 2.20.1 In the Neon instructions, some instruction formats have a 2-bit size field which corresponds exactly to QEMU's MO_8/16/32/64. However the floating-point insns in the 3-same group have a 1-bit size field which is "0 for 32-bit float and 1 for 16-bit float". Currently we pass these values directly through to trans_ functions, which means that when reading a particular trans_ function you need to know if that insn uses a 2-bit size or a 1-bit size. Move the handling of the 1-bit size to the decodetree file, so that all these insns consistently pass a size to the trans_ function which is an MO_8/16/32/64 value. In this commit we switch over the insns using the 3same_fp and 3same_fp_q0 formats. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200903133209.5141-2-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 15 ++++++++++----- target/arm/translate-neon.c.inc | 16 +++++++++++----- 2 files changed, 21 insertions(+), 10 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ @3same_q0 .... ... . . . size:2 .... .... .... . 0 . . .... \ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0 -# For FP insns the high bit of 'size' is used as part of opcode decode -@3same_fp .... ... . . . . size:1 .... .... .... . q:1 . . .... \ - &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp -@3same_fp_q0 .... ... . . . . size:1 .... .... .... . 0 . . .... \ - &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0 +# For FP insns the high bit of 'size' is used as part of opcode decode, +# and the 'size' bit is 0 for 32-bit float and 1 for 16-bit float. +# This converts this encoding to the same MO_8/16/32/64 values that the +# integer neon insns use. +%3same_fp_size 20:1 !function=neon_3same_fp_size + +@3same_fp .... ... . . . . . .... .... .... . q:1 . . .... \ + &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=%3same_fp_size +@3same_fp_q0 .... ... . . . . . .... .... .... . 0 . . .... \ + &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0 size=%3same_fp_size VHADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 0 .... @3same VHADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 0 .... @3same 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 rsub_8(DisasContext *s, int x) return 8 - x; } +static inline int neon_3same_fp_size(DisasContext *s, int x) +{ + /* Convert 0==fp32, 1==fp16 into a MO_* value */ + return MO_32 - x; +} + /* Include the generated Neon decoder */ #include "decode-neon-dp.c.inc" #include "decode-neon-ls.c.inc" @@ -XXX,XX +XXX,XX @@ DO_3SAME_VQDMULH(VQRDMULH, qrdmulh) WRAP_FP_GVEC(gen_##INSN##_fp16_3s, FPST_STD_F16, HFUNC) \ static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ { \ - if (a->size != 0) { \ + if (a->size == MO_16) { \ if (!dc_isar_feature(aa32_fp16_arith, s)) { \ return false; \ } \ @@ -XXX,XX +XXX,XX @@ static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a) return false; } - if (a->size != 0) { + if (a->size == MO_16) { if (!dc_isar_feature(aa32_fp16_arith, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) return false; } - if (a->size != 0) { + if (a->size == MO_16) { if (!dc_isar_feature(aa32_fp16_arith, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, assert(a->q == 0); /* enforced by decode patterns */ - fpstatus = fpstatus_ptr(a->size != 0 ? FPST_STD_F16 : FPST_STD); + fpstatus = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->vm), @@ -XXX,XX +XXX,XX @@ static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, #define DO_3S_FP_PAIR(INSN,FUNC) \ static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ { \ - if (a->size != 0) { \ + if (a->size == MO_16) { \ if (!dc_isar_feature(aa32_fp16_arith, s)) { \ return false; \ } \ -- 2.20.1 Convert the insns using the 2reg_vcvt and 2reg_vcvt_f16 formats to pass the size through to the trans function as a MO_* value rather than the '0==f32, 1==f16' used in the fp 3-same encodings. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200903133209.5141-3-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 3 +-- target/arm/translate-neon.c.inc | 4 ++-- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp @2reg_shll_b .... ... . . . 001 shift:3 .... .... 0 . . . .... \ &2reg_shift vm=%vm_dp vd=%vd_dp size=0 q=0 -# We use size=0 for fp32 and size=1 for fp16 to match the 3-same encodings. @2reg_vcvt .... ... . . . 1 ..... .... .... . q:1 . . .... \ - &2reg_shift vm=%vm_dp vd=%vd_dp size=0 shift=%neon_rshift_i5 + &2reg_shift vm=%vm_dp vd=%vd_dp size=2 shift=%neon_rshift_i5 @2reg_vcvt_f16 .... ... . . . 11 .... .... .... . q:1 . . .... \ &2reg_shift vm=%vm_dp vd=%vd_dp size=1 shift=%neon_rshift_i4 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_fp_2sh(DisasContext *s, arg_2reg_shift *a, return false; } - if (a->size != 0) { + if (a->size == MO_16) { if (!dc_isar_feature(aa32_fp16_arith, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, return true; } - fpst = fpstatus_ptr(a->size ? FPST_STD_F16 : FPST_STD); + fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); tcg_gen_gvec_2_ptr(rd_ofs, rm_ofs, fpst, vec_size, vec_size, a->shift, fn); tcg_temp_free_ptr(fpst); return true; -- 2.20.1 The VCMLA and VCADD insns have a size field which is 0 for fp16 and 1 for fp32 (note that this is the reverse of the Neon 3-same encoding!). Convert it to MO_* values in decode for consistency. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200903133209.5141-4-peter.maydell@linaro.org --- target/arm/neon-shared.decode | 18 ++++++++++++------ target/arm/translate-neon.c.inc | 22 ++++++++++++---------- 2 files changed, 24 insertions(+), 16 deletions(-) diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-shared.decode +++ b/target/arm/neon-shared.decode @@ -XXX,XX +XXX,XX @@ %vd_dp 22:1 12:4 %vd_sp 12:4 22:1 -VCMLA 1111 110 rot:2 . 1 size:1 .... .... 1000 . q:1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +# For VCMLA/VCADD insns, convert the single-bit size field +# which is 0 for fp16 and 1 for fp32 into a MO_* constant. +# (Note that this is the reverse of the sense of the 1-bit size +# field in the 3same_fp Neon insns.) +%vcadd_size 20:1 !function=plus1 -VCADD 1111 110 rot:1 1 . 0 size:1 .... .... 1000 . q:1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +VCMLA 1111 110 rot:2 . 1 . .... .... 1000 . q:1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp size=%vcadd_size + +VCADD 1111 110 rot:1 1 . 0 . .... .... 1000 . q:1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp size=%vcadd_size # VUDOT and VSDOT VDOT 1111 110 00 . 10 .... .... 1101 . q:1 . u:1 .... \ @@ -XXX,XX +XXX,XX @@ VFML 1111 110 0 s:1 . 10 .... .... 1000 . 1 . 1 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp q=1 VCMLA_scalar 1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \ - vn=%vn_dp vd=%vd_dp size=0 + vn=%vn_dp vd=%vd_dp size=1 VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp size=1 index=0 + vm=%vm_dp vn=%vn_dp vd=%vd_dp size=2 index=0 VDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 u:1 rm:4 \ vm=%vm_dp vn=%vn_dp vd=%vd_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 bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) gen_helper_gvec_3_ptr *fn_gvec_ptr; if (!dc_isar_feature(aa32_vcma, s) - || (!a->size && !dc_isar_feature(aa32_fp16_arith, s))) { + || (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s))) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) } opr_sz = (1 + a->q) * 8; - fpst = fpstatus_ptr(a->size == 0 ? FPST_STD_F16 : FPST_STD); - fn_gvec_ptr = a->size ? gen_helper_gvec_fcmlas : gen_helper_gvec_fcmlah; + fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); + fn_gvec_ptr = (a->size == MO_16) ? + gen_helper_gvec_fcmlah : gen_helper_gvec_fcmlas; tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->vm), @@ -XXX,XX +XXX,XX @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a) gen_helper_gvec_3_ptr *fn_gvec_ptr; if (!dc_isar_feature(aa32_vcma, s) - || (!a->size && !dc_isar_feature(aa32_fp16_arith, s))) { + || (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s))) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a) } opr_sz = (1 + a->q) * 8; - fpst = fpstatus_ptr(a->size == 0 ? FPST_STD_F16 : FPST_STD); - fn_gvec_ptr = a->size ? gen_helper_gvec_fcadds : gen_helper_gvec_fcaddh; + fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); + fn_gvec_ptr = (a->size == MO_16) ? + gen_helper_gvec_fcaddh : gen_helper_gvec_fcadds; tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->vm), @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a) if (!dc_isar_feature(aa32_vcma, s)) { return false; } - if (a->size == 0 && !dc_isar_feature(aa32_fp16_arith, s)) { + if (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a) return true; } - fn_gvec_ptr = (a->size ? gen_helper_gvec_fcmlas_idx - : gen_helper_gvec_fcmlah_idx); + fn_gvec_ptr = (a->size == MO_16) ? + gen_helper_gvec_fcmlah_idx : gen_helper_gvec_fcmlas_idx; opr_sz = (1 + a->q) * 8; - fpst = fpstatus_ptr(a->size == 0 ? FPST_STD_F16 : FPST_STD); + fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD); tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), vfp_reg_offset(1, a->vn), vfp_reg_offset(1, a->vm), -- 2.20.1 We deprecated the support for KVM on 32-bit Arm hosts in time for release 5.0, which means that our deprecation policy allows us to drop it in release 5.2. Remove the code. To repeat the rationale from the deprecation note: the Linux kernel dropped support for 32-bit Arm KVM hosts in 5.7. Running 32-bit guests on a 64-bit Arm host remains supported. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200904154156.31943-2-peter.maydell@linaro.org --- docs/system/deprecated.rst | 16 +- configure | 2 +- target/arm/kvm32.c | 595 ------------------------------------- target/arm/meson.build | 5 +- 4 files changed, 10 insertions(+), 608 deletions(-) delete mode 100644 target/arm/kvm32.c diff --git a/docs/system/deprecated.rst b/docs/system/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/deprecated.rst +++ b/docs/system/deprecated.rst @@ -XXX,XX +XXX,XX @@ The ``compat`` property used to set backwards compatibility modes for the processor has been deprecated. The ``max-cpu-compat`` property of the ``pseries`` machine type should be used instead. -KVM guest support on 32-bit Arm hosts (since 5.0) -''''''''''''''''''''''''''''''''''''''''''''''''' - -The Linux kernel has dropped support for allowing 32-bit Arm systems -to host KVM guests as of the 5.7 kernel. Accordingly, QEMU is deprecating -its support for this configuration and will remove it in a future version. -Running 32-bit guests on a 64-bit Arm host remains supported. - System emulator devices ----------------------- @@ -XXX,XX +XXX,XX @@ should be used instead of the 1.09.1 version. System emulator CPUS -------------------- +KVM guest support on 32-bit Arm hosts (removed in 5.2) +'''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The Linux kernel has dropped support for allowing 32-bit Arm systems +to host KVM guests as of the 5.7 kernel. Accordingly, QEMU is deprecating +its support for this configuration and will remove it in a future version. +Running 32-bit guests on a 64-bit Arm host remains supported. + RISC-V ISA Specific CPUs (removed in 5.1) ''''''''''''''''''''''''''''''''''''''''' diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ supported_kvm_target() { test "$kvm" = "yes" || return 1 glob "$1" "*-softmmu" || return 1 case "${1%-softmmu}:$cpu" in - arm:arm | aarch64:aarch64 | \ + aarch64:aarch64 | \ i386:i386 | i386:x86_64 | i386:x32 | \ x86_64:i386 | x86_64:x86_64 | x86_64:x32 | \ mips:mips | mipsel:mips | mips64:mips | mips64el:mips | \ diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/target/arm/kvm32.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * ARM implementation of KVM hooks, 32 bit specific code. - * - * Copyright Christoffer Dall 2009-2010 - * - * This work is licensed under the terms of the GNU GPL, version 2 or later. - * See the COPYING file in the top-level directory. - * - */ - -#include "qemu/osdep.h" -#include <sys/ioctl.h> - -#include <linux/kvm.h> - -#include "qemu-common.h" -#include "cpu.h" -#include "qemu/timer.h" -#include "sysemu/runstate.h" -#include "sysemu/kvm.h" -#include "kvm_arm.h" -#include "internals.h" -#include "qemu/log.h" - -static int read_sys_reg32(int fd, uint32_t *pret, uint64_t id) -{ - struct kvm_one_reg idreg = { .id = id, .addr = (uintptr_t)pret }; - - assert((id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U32); - return ioctl(fd, KVM_GET_ONE_REG, &idreg); -} - -bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) -{ - /* Identify the feature bits corresponding to the host CPU, and - * fill out the ARMHostCPUClass fields accordingly. To do this - * we have to create a scratch VM, create a single CPU inside it, - * and then query that CPU for the relevant ID registers. - */ - int err = 0, fdarray[3]; - uint32_t midr, id_pfr0; - uint64_t features = 0; - - /* Old kernels may not know about the PREFERRED_TARGET ioctl: however - * we know these will only support creating one kind of guest CPU, - * which is its preferred CPU type. - */ - static const uint32_t cpus_to_try[] = { - QEMU_KVM_ARM_TARGET_CORTEX_A15, - QEMU_KVM_ARM_TARGET_NONE - }; - /* - * target = -1 informs kvm_arm_create_scratch_host_vcpu() - * to use the preferred target - */ - struct kvm_vcpu_init init = { .target = -1, }; - - if (!kvm_arm_create_scratch_host_vcpu(cpus_to_try, fdarray, &init)) { - return false; - } - - ahcf->target = init.target; - - /* This is not strictly blessed by the device tree binding docs yet, - * but in practice the kernel does not care about this string so - * there is no point maintaining an KVM_ARM_TARGET_* -> string table. - */ - ahcf->dtb_compatible = "arm,arm-v7"; - - err |= read_sys_reg32(fdarray[2], &midr, ARM_CP15_REG32(0, 0, 0, 0)); - err |= read_sys_reg32(fdarray[2], &id_pfr0, ARM_CP15_REG32(0, 0, 1, 0)); - - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar0, - ARM_CP15_REG32(0, 0, 2, 0)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar1, - ARM_CP15_REG32(0, 0, 2, 1)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar2, - ARM_CP15_REG32(0, 0, 2, 2)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar3, - ARM_CP15_REG32(0, 0, 2, 3)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar4, - ARM_CP15_REG32(0, 0, 2, 4)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar5, - ARM_CP15_REG32(0, 0, 2, 5)); - if (read_sys_reg32(fdarray[2], &ahcf->isar.id_isar6, - ARM_CP15_REG32(0, 0, 2, 7))) { - /* - * Older kernels don't support reading ID_ISAR6. This register was - * only introduced in ARMv8, so we can assume that it is zero on a - * CPU that a kernel this old is running on. - */ - ahcf->isar.id_isar6 = 0; - } - - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_dfr0, - ARM_CP15_REG32(0, 0, 1, 2)); - - err |= read_sys_reg32(fdarray[2], &ahcf->isar.mvfr0, - KVM_REG_ARM | KVM_REG_SIZE_U32 | - KVM_REG_ARM_VFP | KVM_REG_ARM_VFP_MVFR0); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.mvfr1, - KVM_REG_ARM | KVM_REG_SIZE_U32 | - KVM_REG_ARM_VFP | KVM_REG_ARM_VFP_MVFR1); - /* - * FIXME: There is not yet a way to read MVFR2. - * Fortunately there is not yet anything in there that affects migration. - */ - - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr0, - ARM_CP15_REG32(0, 0, 1, 4)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr1, - ARM_CP15_REG32(0, 0, 1, 5)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr2, - ARM_CP15_REG32(0, 0, 1, 6)); - err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr3, - ARM_CP15_REG32(0, 0, 1, 7)); - if (read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr4, - ARM_CP15_REG32(0, 0, 2, 6))) { - /* - * Older kernels don't support reading ID_MMFR4 (a new in v8 - * register); assume it's zero. - */ - ahcf->isar.id_mmfr4 = 0; - } - - /* - * There is no way to read DBGDIDR, because currently 32-bit KVM - * doesn't implement debug at all. Leave it at zero. - */ - - kvm_arm_destroy_scratch_host_vcpu(fdarray); - - if (err < 0) { - return false; - } - - /* Now we've retrieved all the register information we can - * set the feature bits based on the ID register fields. - * We can assume any KVM supporting CPU is at least a v7 - * with VFPv3, virtualization extensions, and the generic - * timers; this in turn implies most of the other feature - * bits, but a few must be tested. - */ - features |= 1ULL << ARM_FEATURE_V7VE; - features |= 1ULL << ARM_FEATURE_GENERIC_TIMER; - - if (extract32(id_pfr0, 12, 4) == 1) { - features |= 1ULL << ARM_FEATURE_THUMB2EE; - } - if (extract32(ahcf->isar.mvfr1, 12, 4) == 1) { - features |= 1ULL << ARM_FEATURE_NEON; - } - - ahcf->features = features; - - return true; -} - -bool kvm_arm_reg_syncs_via_cpreg_list(uint64_t regidx) -{ - /* Return true if the regidx is a register we should synchronize - * via the cpreg_tuples array (ie is not a core reg we sync by - * hand in kvm_arch_get/put_registers()) - */ - switch (regidx & KVM_REG_ARM_COPROC_MASK) { - case KVM_REG_ARM_CORE: - case KVM_REG_ARM_VFP: - return false; - default: - return true; - } -} - -typedef struct CPRegStateLevel { - uint64_t regidx; - int level; -} CPRegStateLevel; - -/* All coprocessor registers not listed in the following table are assumed to - * be of the level KVM_PUT_RUNTIME_STATE. If a register should be written less - * often, you must add it to this table with a state of either - * KVM_PUT_RESET_STATE or KVM_PUT_FULL_STATE. - */ -static const CPRegStateLevel non_runtime_cpregs[] = { - { KVM_REG_ARM_TIMER_CNT, KVM_PUT_FULL_STATE }, -}; - -int kvm_arm_cpreg_level(uint64_t regidx) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(non_runtime_cpregs); i++) { - const CPRegStateLevel *l = &non_runtime_cpregs[i]; - if (l->regidx == regidx) { - return l->level; - } - } - - return KVM_PUT_RUNTIME_STATE; -} - -#define ARM_CPU_ID_MPIDR 0, 0, 0, 5 - -int kvm_arch_init_vcpu(CPUState *cs) -{ - int ret; - uint64_t v; - uint32_t mpidr; - struct kvm_one_reg r; - ARMCPU *cpu = ARM_CPU(cs); - - if (cpu->kvm_target == QEMU_KVM_ARM_TARGET_NONE) { - fprintf(stderr, "KVM is not supported for this guest CPU type\n"); - return -EINVAL; - } - - qemu_add_vm_change_state_handler(kvm_arm_vm_state_change, cs); - - /* Determine init features for this CPU */ - memset(cpu->kvm_init_features, 0, sizeof(cpu->kvm_init_features)); - if (cs->start_powered_off) { - cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_POWER_OFF; - } - if (kvm_check_extension(cs->kvm_state, KVM_CAP_ARM_PSCI_0_2)) { - cpu->psci_version = 2; - cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_PSCI_0_2; - } - - /* Do KVM_ARM_VCPU_INIT ioctl */ - ret = kvm_arm_vcpu_init(cs); - if (ret) { - return ret; - } - - /* Query the kernel to make sure it supports 32 VFP - * registers: QEMU's "cortex-a15" CPU is always a - * VFP-D32 core. The simplest way to do this is just - * to attempt to read register d31. - */ - r.id = KVM_REG_ARM | KVM_REG_SIZE_U64 | KVM_REG_ARM_VFP | 31; - r.addr = (uintptr_t)(&v); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &r); - if (ret == -ENOENT) { - return -EINVAL; - } - - /* - * When KVM is in use, PSCI is emulated in-kernel and not by qemu. - * Currently KVM has its own idea about MPIDR assignment, so we - * override our defaults with what we get from KVM. - */ - ret = kvm_get_one_reg(cs, ARM_CP15_REG32(ARM_CPU_ID_MPIDR), &mpidr); - if (ret) { - return ret; - } - cpu->mp_affinity = mpidr & ARM32_AFFINITY_MASK; - - /* Check whether userspace can specify guest syndrome value */ - kvm_arm_init_serror_injection(cs); - - return kvm_arm_init_cpreg_list(cpu); -} - -int kvm_arch_destroy_vcpu(CPUState *cs) -{ - return 0; -} - -typedef struct Reg { - uint64_t id; - int offset; -} Reg; - -#define COREREG(KERNELNAME, QEMUFIELD) \ - { \ - KVM_REG_ARM | KVM_REG_SIZE_U32 | \ - KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(KERNELNAME), \ - offsetof(CPUARMState, QEMUFIELD) \ - } - -#define VFPSYSREG(R) \ - { \ - KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_VFP | \ - KVM_REG_ARM_VFP_##R, \ - offsetof(CPUARMState, vfp.xregs[ARM_VFP_##R]) \ - } - -/* Like COREREG, but handle fields which are in a uint64_t in CPUARMState. */ -#define COREREG64(KERNELNAME, QEMUFIELD) \ - { \ - KVM_REG_ARM | KVM_REG_SIZE_U32 | \ - KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(KERNELNAME), \ - offsetoflow32(CPUARMState, QEMUFIELD) \ - } - -static const Reg regs[] = { - /* R0_usr .. R14_usr */ - COREREG(usr_regs.uregs[0], regs[0]), - COREREG(usr_regs.uregs[1], regs[1]), - COREREG(usr_regs.uregs[2], regs[2]), - COREREG(usr_regs.uregs[3], regs[3]), - COREREG(usr_regs.uregs[4], regs[4]), - COREREG(usr_regs.uregs[5], regs[5]), - COREREG(usr_regs.uregs[6], regs[6]), - COREREG(usr_regs.uregs[7], regs[7]), - COREREG(usr_regs.uregs[8], usr_regs[0]), - COREREG(usr_regs.uregs[9], usr_regs[1]), - COREREG(usr_regs.uregs[10], usr_regs[2]), - COREREG(usr_regs.uregs[11], usr_regs[3]), - COREREG(usr_regs.uregs[12], usr_regs[4]), - COREREG(usr_regs.uregs[13], banked_r13[BANK_USRSYS]), - COREREG(usr_regs.uregs[14], banked_r14[BANK_USRSYS]), - /* R13, R14, SPSR for SVC, ABT, UND, IRQ banks */ - COREREG(svc_regs[0], banked_r13[BANK_SVC]), - COREREG(svc_regs[1], banked_r14[BANK_SVC]), - COREREG64(svc_regs[2], banked_spsr[BANK_SVC]), - COREREG(abt_regs[0], banked_r13[BANK_ABT]), - COREREG(abt_regs[1], banked_r14[BANK_ABT]), - COREREG64(abt_regs[2], banked_spsr[BANK_ABT]), - COREREG(und_regs[0], banked_r13[BANK_UND]), - COREREG(und_regs[1], banked_r14[BANK_UND]), - COREREG64(und_regs[2], banked_spsr[BANK_UND]), - COREREG(irq_regs[0], banked_r13[BANK_IRQ]), - COREREG(irq_regs[1], banked_r14[BANK_IRQ]), - COREREG64(irq_regs[2], banked_spsr[BANK_IRQ]), - /* R8_fiq .. R14_fiq and SPSR_fiq */ - COREREG(fiq_regs[0], fiq_regs[0]), - COREREG(fiq_regs[1], fiq_regs[1]), - COREREG(fiq_regs[2], fiq_regs[2]), - COREREG(fiq_regs[3], fiq_regs[3]), - COREREG(fiq_regs[4], fiq_regs[4]), - COREREG(fiq_regs[5], banked_r13[BANK_FIQ]), - COREREG(fiq_regs[6], banked_r14[BANK_FIQ]), - COREREG64(fiq_regs[7], banked_spsr[BANK_FIQ]), - /* R15 */ - COREREG(usr_regs.uregs[15], regs[15]), - /* VFP system registers */ - VFPSYSREG(FPSID), - VFPSYSREG(MVFR1), - VFPSYSREG(MVFR0), - VFPSYSREG(FPEXC), - VFPSYSREG(FPINST), - VFPSYSREG(FPINST2), -}; - -int kvm_arch_put_registers(CPUState *cs, int level) -{ - ARMCPU *cpu = ARM_CPU(cs); - CPUARMState *env = &cpu->env; - struct kvm_one_reg r; - int mode, bn; - int ret, i; - uint32_t cpsr, fpscr; - - /* Make sure the banked regs are properly set */ - mode = env->uncached_cpsr & CPSR_M; - bn = bank_number(mode); - if (mode == ARM_CPU_MODE_FIQ) { - memcpy(env->fiq_regs, env->regs + 8, 5 * sizeof(uint32_t)); - } else { - memcpy(env->usr_regs, env->regs + 8, 5 * sizeof(uint32_t)); - } - env->banked_r13[bn] = env->regs[13]; - env->banked_spsr[bn] = env->spsr; - env->banked_r14[r14_bank_number(mode)] = env->regs[14]; - - /* Now we can safely copy stuff down to the kernel */ - for (i = 0; i < ARRAY_SIZE(regs); i++) { - r.id = regs[i].id; - r.addr = (uintptr_t)(env) + regs[i].offset; - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &r); - if (ret) { - return ret; - } - } - - /* Special cases which aren't a single CPUARMState field */ - cpsr = cpsr_read(env); - r.id = KVM_REG_ARM | KVM_REG_SIZE_U32 | - KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(usr_regs.ARM_cpsr); - r.addr = (uintptr_t)(&cpsr); - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &r); - if (ret) { - return ret; - } - - /* VFP registers */ - r.id = KVM_REG_ARM | KVM_REG_SIZE_U64 | KVM_REG_ARM_VFP; - for (i = 0; i < 32; i++) { - r.addr = (uintptr_t)aa32_vfp_dreg(env, i); - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &r); - if (ret) { - return ret; - } - r.id++; - } - - r.id = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_VFP | - KVM_REG_ARM_VFP_FPSCR; - fpscr = vfp_get_fpscr(env); - r.addr = (uintptr_t)&fpscr; - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &r); - if (ret) { - return ret; - } - - write_cpustate_to_list(cpu, true); - - if (!write_list_to_kvmstate(cpu, level)) { - return EINVAL; - } - - /* - * Setting VCPU events should be triggered after syncing the registers - * to avoid overwriting potential changes made by KVM upon calling - * KVM_SET_VCPU_EVENTS ioctl - */ - ret = kvm_put_vcpu_events(cpu); - if (ret) { - return ret; - } - - kvm_arm_sync_mpstate_to_kvm(cpu); - - return ret; -} - -int kvm_arch_get_registers(CPUState *cs) -{ - ARMCPU *cpu = ARM_CPU(cs); - CPUARMState *env = &cpu->env; - struct kvm_one_reg r; - int mode, bn; - int ret, i; - uint32_t cpsr, fpscr; - - for (i = 0; i < ARRAY_SIZE(regs); i++) { - r.id = regs[i].id; - r.addr = (uintptr_t)(env) + regs[i].offset; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &r); - if (ret) { - return ret; - } - } - - /* Special cases which aren't a single CPUARMState field */ - r.id = KVM_REG_ARM | KVM_REG_SIZE_U32 | - KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(usr_regs.ARM_cpsr); - r.addr = (uintptr_t)(&cpsr); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &r); - if (ret) { - return ret; - } - cpsr_write(env, cpsr, 0xffffffff, CPSRWriteRaw); - - /* Make sure the current mode regs are properly set */ - mode = env->uncached_cpsr & CPSR_M; - bn = bank_number(mode); - if (mode == ARM_CPU_MODE_FIQ) { - memcpy(env->regs + 8, env->fiq_regs, 5 * sizeof(uint32_t)); - } else { - memcpy(env->regs + 8, env->usr_regs, 5 * sizeof(uint32_t)); - } - env->regs[13] = env->banked_r13[bn]; - env->spsr = env->banked_spsr[bn]; - env->regs[14] = env->banked_r14[r14_bank_number(mode)]; - - /* VFP registers */ - r.id = KVM_REG_ARM | KVM_REG_SIZE_U64 | KVM_REG_ARM_VFP; - for (i = 0; i < 32; i++) { - r.addr = (uintptr_t)aa32_vfp_dreg(env, i); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &r); - if (ret) { - return ret; - } - r.id++; - } - - r.id = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_VFP | - KVM_REG_ARM_VFP_FPSCR; - r.addr = (uintptr_t)&fpscr; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &r); - if (ret) { - return ret; - } - vfp_set_fpscr(env, fpscr); - - ret = kvm_get_vcpu_events(cpu); - if (ret) { - return ret; - } - - if (!write_kvmstate_to_list(cpu)) { - return EINVAL; - } - /* Note that it's OK to have registers which aren't in CPUState, - * so we can ignore a failure return here. - */ - write_list_to_cpustate(cpu); - - kvm_arm_sync_mpstate_to_qemu(cpu); - - return 0; -} - -int kvm_arch_insert_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp) -{ - qemu_log_mask(LOG_UNIMP, "%s: guest debug not yet implemented\n", __func__); - return -EINVAL; -} - -int kvm_arch_remove_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp) -{ - qemu_log_mask(LOG_UNIMP, "%s: guest debug not yet implemented\n", __func__); - return -EINVAL; -} - -bool kvm_arm_handle_debug(CPUState *cs, struct kvm_debug_exit_arch *debug_exit) -{ - qemu_log_mask(LOG_UNIMP, "%s: guest debug not yet implemented\n", __func__); - return false; -} - -int kvm_arch_insert_hw_breakpoint(target_ulong addr, - target_ulong len, int type) -{ - qemu_log_mask(LOG_UNIMP, "%s: not implemented\n", __func__); - return -EINVAL; -} - -int kvm_arch_remove_hw_breakpoint(target_ulong addr, - target_ulong len, int type) -{ - qemu_log_mask(LOG_UNIMP, "%s: not implemented\n", __func__); - return -EINVAL; -} - -void kvm_arch_remove_all_hw_breakpoints(void) -{ - qemu_log_mask(LOG_UNIMP, "%s: not implemented\n", __func__); -} - -void kvm_arm_copy_hw_debug_data(struct kvm_guest_debug_arch *ptr) -{ - qemu_log_mask(LOG_UNIMP, "%s: not implemented\n", __func__); -} - -bool kvm_arm_hw_debug_active(CPUState *cs) -{ - return false; -} - -void kvm_arm_pmu_set_irq(CPUState *cs, int irq) -{ - qemu_log_mask(LOG_UNIMP, "%s: not implemented\n", __func__); -} - -void kvm_arm_pmu_init(CPUState *cs) -{ - qemu_log_mask(LOG_UNIMP, "%s: not implemented\n", __func__); -} - -#define ARM_REG_DFSR ARM_CP15_REG32(0, 5, 0, 0) -#define ARM_REG_TTBCR ARM_CP15_REG32(0, 2, 0, 2) -/* - *DFSR: - * TTBCR.EAE == 0 - * FS[4] - DFSR[10] - * FS[3:0] - DFSR[3:0] - * TTBCR.EAE == 1 - * FS, bits [5:0] - */ -#define DFSR_FSC(lpae, v) \ - ((lpae) ? ((v) & 0x3F) : (((v) >> 6) | ((v) & 0x1F))) - -#define DFSC_EXTABT(lpae) ((lpae) ? 0x10 : 0x08) - -bool kvm_arm_verify_ext_dabt_pending(CPUState *cs) -{ - uint32_t dfsr_val; - - if (!kvm_get_one_reg(cs, ARM_REG_DFSR, &dfsr_val)) { - ARMCPU *cpu = ARM_CPU(cs); - CPUARMState *env = &cpu->env; - uint32_t ttbcr; - int lpae = 0; - - if (!kvm_get_one_reg(cs, ARM_REG_TTBCR, &ttbcr)) { - lpae = arm_feature(env, ARM_FEATURE_LPAE) && (ttbcr & TTBCR_EAE); - } - /* The verification is based on FS filed of the DFSR reg only*/ - return (DFSR_FSC(lpae, dfsr_val) == DFSC_EXTABT(lpae)); - } - return false; -} diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(zlib) arm_ss.add(when: 'CONFIG_TCG', if_true: files('arm-semi.c')) -kvm_ss = ss.source_set() -kvm_ss.add(when: 'TARGET_AARCH64', if_true: files('kvm64.c'), if_false: files('kvm32.c')) -arm_ss.add_all(when: 'CONFIG_KVM', if_true: kvm_ss) -arm_ss.add(when: 'CONFIG_KVM', if_true: files('kvm.c'), if_false: files('kvm-stub.c')) +arm_ss.add(when: 'CONFIG_KVM', if_true: files('kvm.c', 'kvm64.c'), if_false: files('kvm-stub.c')) arm_ss.add(when: 'TARGET_AARCH64', if_true: files( 'cpu64.c', -- 2.20.1 Now that 32-bit KVM host support is gone, KVM can never be enabled unless CONFIG_AARCH64 is true, and some code paths are no longer reachable and can be deleted. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200904154156.31943-3-peter.maydell@linaro.org --- target/arm/kvm-consts.h | 7 --- target/arm/kvm_arm.h | 6 --- target/arm/cpu.c | 101 +++++++++++++++++++--------------------- target/arm/kvm.c | 7 --- 4 files changed, 47 insertions(+), 74 deletions(-) diff --git a/target/arm/kvm-consts.h b/target/arm/kvm-consts.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm-consts.h +++ b/target/arm/kvm-consts.h @@ -XXX,XX +XXX,XX @@ MISMATCH_CHECK(QEMU_PSCI_RET_DISABLED, PSCI_RET_DISABLED); */ #define QEMU_KVM_ARM_TARGET_NONE UINT_MAX -#ifdef TARGET_AARCH64 MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_AEM_V8, KVM_ARM_TARGET_AEM_V8); MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_FOUNDATION_V8, KVM_ARM_TARGET_FOUNDATION_V8); MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_CORTEX_A57, KVM_ARM_TARGET_CORTEX_A57); MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_XGENE_POTENZA, KVM_ARM_TARGET_XGENE_POTENZA); MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_CORTEX_A53, KVM_ARM_TARGET_CORTEX_A53); -#else -MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_CORTEX_A15, KVM_ARM_TARGET_CORTEX_A15); -MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_CORTEX_A7, KVM_ARM_TARGET_CORTEX_A7); -#endif #define CP_REG_ARM64 0x6000000000000000ULL #define CP_REG_ARM_COPROC_MASK 0x000000000FFF0000 @@ -XXX,XX +XXX,XX @@ MISMATCH_CHECK(QEMU_KVM_ARM_TARGET_CORTEX_A7, KVM_ARM_TARGET_CORTEX_A7); /* No kernel define but it's useful to QEMU */ #define CP_REG_ARM64_SYSREG_CP (CP_REG_ARM64_SYSREG >> CP_REG_ARM_COPROC_SHIFT) -#ifdef TARGET_AARCH64 MISMATCH_CHECK(CP_REG_ARM64, KVM_REG_ARM64); MISMATCH_CHECK(CP_REG_ARM_COPROC_MASK, KVM_REG_ARM_COPROC_MASK); MISMATCH_CHECK(CP_REG_ARM_COPROC_SHIFT, KVM_REG_ARM_COPROC_SHIFT); @@ -XXX,XX +XXX,XX @@ MISMATCH_CHECK(CP_REG_ARM64_SYSREG_CRM_MASK, KVM_REG_ARM64_SYSREG_CRM_MASK); MISMATCH_CHECK(CP_REG_ARM64_SYSREG_CRM_SHIFT, KVM_REG_ARM64_SYSREG_CRM_SHIFT); MISMATCH_CHECK(CP_REG_ARM64_SYSREG_OP2_MASK, KVM_REG_ARM64_SYSREG_OP2_MASK); MISMATCH_CHECK(CP_REG_ARM64_SYSREG_OP2_SHIFT, KVM_REG_ARM64_SYSREG_OP2_SHIFT); -#endif #undef MISMATCH_CHECK diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm_arm.h +++ b/target/arm/kvm_arm.h @@ -XXX,XX +XXX,XX @@ static inline const char *gic_class_name(void) static inline const char *gicv3_class_name(void) { if (kvm_irqchip_in_kernel()) { -#ifdef TARGET_AARCH64 return "kvm-arm-gicv3"; -#else - error_report("KVM GICv3 acceleration is not supported on this " - "platform"); - exit(1); -#endif } else { if (kvm_enabled()) { error_report("Userspace GICv3 is not supported with KVM"); 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 cortex_a15_initfn(Object *obj) } #ifndef TARGET_AARCH64 -/* -cpu max: if KVM is enabled, like -cpu host (best possible with this host); - * otherwise, a CPU with as many features enabled as our emulation supports. +/* + * -cpu max: a CPU with as many features enabled as our emulation supports. * The version of '-cpu max' for qemu-system-aarch64 is defined in cpu64.c; - * this only needs to handle 32 bits. + * this only needs to handle 32 bits, and need not care about KVM. */ static void arm_max_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); - if (kvm_enabled()) { - kvm_arm_set_cpu_features_from_host(cpu); - } else { - cortex_a15_initfn(obj); + cortex_a15_initfn(obj); - /* old-style VFP short-vector support */ - cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1); + /* old-style VFP short-vector support */ + cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1); #ifdef CONFIG_USER_ONLY - /* We don't set these in system emulation mode for the moment, - * since we don't correctly set (all of) the ID registers to - * advertise them. - */ - set_feature(&cpu->env, ARM_FEATURE_V8); - { - uint32_t t; + /* + * We don't set these in system emulation mode for the moment, + * since we don't correctly set (all of) the ID registers to + * advertise them. + */ + set_feature(&cpu->env, ARM_FEATURE_V8); + { + uint32_t t; - t = cpu->isar.id_isar5; - t = FIELD_DP32(t, ID_ISAR5, AES, 2); - t = FIELD_DP32(t, ID_ISAR5, SHA1, 1); - t = FIELD_DP32(t, ID_ISAR5, SHA2, 1); - t = FIELD_DP32(t, ID_ISAR5, CRC32, 1); - t = FIELD_DP32(t, ID_ISAR5, RDM, 1); - t = FIELD_DP32(t, ID_ISAR5, VCMA, 1); - cpu->isar.id_isar5 = t; + t = cpu->isar.id_isar5; + t = FIELD_DP32(t, ID_ISAR5, AES, 2); + t = FIELD_DP32(t, ID_ISAR5, SHA1, 1); + t = FIELD_DP32(t, ID_ISAR5, SHA2, 1); + t = FIELD_DP32(t, ID_ISAR5, CRC32, 1); + t = FIELD_DP32(t, ID_ISAR5, RDM, 1); + t = FIELD_DP32(t, ID_ISAR5, VCMA, 1); + cpu->isar.id_isar5 = t; - t = cpu->isar.id_isar6; - t = FIELD_DP32(t, ID_ISAR6, JSCVT, 1); - t = FIELD_DP32(t, ID_ISAR6, DP, 1); - t = FIELD_DP32(t, ID_ISAR6, FHM, 1); - t = FIELD_DP32(t, ID_ISAR6, SB, 1); - t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1); - cpu->isar.id_isar6 = t; + t = cpu->isar.id_isar6; + t = FIELD_DP32(t, ID_ISAR6, JSCVT, 1); + t = FIELD_DP32(t, ID_ISAR6, DP, 1); + t = FIELD_DP32(t, ID_ISAR6, FHM, 1); + t = FIELD_DP32(t, ID_ISAR6, SB, 1); + t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1); + cpu->isar.id_isar6 = t; - t = cpu->isar.mvfr1; - t = FIELD_DP32(t, MVFR1, FPHP, 3); /* v8.2-FP16 */ - t = FIELD_DP32(t, MVFR1, SIMDHP, 2); /* v8.2-FP16 */ - cpu->isar.mvfr1 = t; + t = cpu->isar.mvfr1; + t = FIELD_DP32(t, MVFR1, FPHP, 3); /* v8.2-FP16 */ + t = FIELD_DP32(t, MVFR1, SIMDHP, 2); /* v8.2-FP16 */ + cpu->isar.mvfr1 = t; - t = cpu->isar.mvfr2; - t = FIELD_DP32(t, MVFR2, SIMDMISC, 3); /* SIMD MaxNum */ - t = FIELD_DP32(t, MVFR2, FPMISC, 4); /* FP MaxNum */ - cpu->isar.mvfr2 = t; + t = cpu->isar.mvfr2; + t = FIELD_DP32(t, MVFR2, SIMDMISC, 3); /* SIMD MaxNum */ + t = FIELD_DP32(t, MVFR2, FPMISC, 4); /* FP MaxNum */ + cpu->isar.mvfr2 = t; - t = cpu->isar.id_mmfr3; - t = FIELD_DP32(t, ID_MMFR3, PAN, 2); /* ATS1E1 */ - cpu->isar.id_mmfr3 = t; + t = cpu->isar.id_mmfr3; + t = FIELD_DP32(t, ID_MMFR3, PAN, 2); /* ATS1E1 */ + cpu->isar.id_mmfr3 = t; - t = cpu->isar.id_mmfr4; - t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */ - t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ - t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* TTCNP */ - t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* TTS2UXN */ - cpu->isar.id_mmfr4 = t; - } -#endif + t = cpu->isar.id_mmfr4; + t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */ + t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ + t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* TTCNP */ + t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* TTS2UXN */ + cpu->isar.id_mmfr4 = t; } +#endif } #endif @@ -XXX,XX +XXX,XX @@ static void arm_host_initfn(Object *obj) static const TypeInfo host_arm_cpu_type_info = { .name = TYPE_ARM_HOST_CPU, -#ifdef TARGET_AARCH64 .parent = TYPE_AARCH64_CPU, -#else - .parent = TYPE_ARM_CPU, -#endif .instance_init = arm_host_initfn, }; diff --git a/target/arm/kvm.c b/target/arm/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_process_async_events(CPUState *cs) return 0; } -/* The #ifdef protections are until 32bit headers are imported and can - * be removed once both 32 and 64 bit reach feature parity. - */ void kvm_arch_update_guest_debug(CPUState *cs, struct kvm_guest_debug *dbg) { -#ifdef KVM_GUESTDBG_USE_SW_BP if (kvm_sw_breakpoints_active(cs)) { dbg->control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP; } -#endif -#ifdef KVM_GUESTDBG_USE_HW if (kvm_arm_hw_debug_active(cs)) { dbg->control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW; kvm_arm_copy_hw_debug_data(&dbg->arch); } -#endif } void kvm_arch_init_irq_routing(KVMState *s) -- 2.20.1 Implement a model of the MPS2 with the AN386 firmware. This is essentially identical to the AN385 firmware, but it has a Cortex-M4 rather than a Cortex-M3. 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: 20200903202048.15370-2-peter.maydell@linaro.org --- docs/system/arm/mps2.rst | 8 +++++--- hw/arm/mps2.c | 34 +++++++++++++++++++++++++++++----- 2 files changed, 34 insertions(+), 8 deletions(-) diff --git a/docs/system/arm/mps2.rst b/docs/system/arm/mps2.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/mps2.rst +++ b/docs/system/arm/mps2.rst @@ -XXX,XX +XXX,XX @@ -Arm MPS2 boards (``mps2-an385``, ``mps2-an505``, ``mps2-an511``, ``mps2-an521``) -================================================================================ +Arm MPS2 boards (``mps2-an385``, ``mps2-an386``, ``mps2-an505``, ``mps2-an511``, ``mps2-an521``) +================================================================================================ These board models all use Arm M-profile CPUs. @@ -XXX,XX +XXX,XX @@ QEMU models the following FPGA images: ``mps2-an385`` Cortex-M3 as documented in ARM Application Note AN385 +``mps2-an386`` + Cortex-M4 as documented in ARM Application Note AN386 ``mps2-an511`` Cortex-M3 'DesignStart' as documented in AN511 ``mps2-an505`` @@ -XXX,XX +XXX,XX @@ QEMU models the following FPGA images: Differences between QEMU and real hardware: -- AN385 remapping of low 16K of memory to either ZBT SSRAM1 or to +- AN385/AN386 remapping of low 16K of memory to either ZBT SSRAM1 or to block RAM is unimplemented (QEMU always maps this to ZBT SSRAM1, as if zbt_boot_ctrl is always zero) - QEMU provides a LAN9118 ethernet rather than LAN9220; the only guest diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2.c +++ b/hw/arm/mps2.c @@ -XXX,XX +XXX,XX @@ * as seen by the guest depend significantly on the FPGA image. * We model the following FPGA images: * "mps2-an385" -- Cortex-M3 as documented in ARM Application Note AN385 + * "mps2-an386" -- Cortex-M4 as documented in ARM Application Note AN386 * "mps2-an511" -- Cortex-M3 'DesignStart' as documented in AN511 * * Links to the TRM for the board itself and to the various Application @@ -XXX,XX +XXX,XX @@ typedef enum MPS2FPGAType { FPGA_AN385, + FPGA_AN386, FPGA_AN511, } MPS2FPGAType; @@ -XXX,XX +XXX,XX @@ typedef struct MPS2MachineState MPS2MachineState; #define TYPE_MPS2_MACHINE "mps2" #define TYPE_MPS2_AN385_MACHINE MACHINE_TYPE_NAME("mps2-an385") +#define TYPE_MPS2_AN386_MACHINE MACHINE_TYPE_NAME("mps2-an386") #define TYPE_MPS2_AN511_MACHINE MACHINE_TYPE_NAME("mps2-an511") DECLARE_OBJ_CHECKERS(MPS2MachineState, MPS2MachineClass, @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) * tradeoffs. For QEMU they're all just RAM, though. We arbitrarily * call the 16MB our "system memory", as it's the largest lump. * - * Common to both boards: - * 0x21000000..0x21ffffff : PSRAM (16MB) - * AN385 only: + * AN385/AN386/AN511: + * 0x21000000 .. 0x21ffffff : PSRAM (16MB) + * AN385/AN386 only: * 0x00000000 .. 0x003fffff : ZBT SSRAM1 * 0x00400000 .. 0x007fffff : mirror of ZBT SSRAM1 * 0x20000000 .. 0x203fffff : ZBT SSRAM 2&3 @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) * 0x20000000 .. 0x2001ffff : SRAM * 0x20400000 .. 0x207fffff : ZBT SSRAM 2&3 * - * The AN385 has a feature where the lowest 16K can be mapped + * The AN385/AN386 has a feature where the lowest 16K can be mapped * either to the bottom of the ZBT SSRAM1 or to the block RAM. * This is of no use for QEMU so we don't implement it (as if * zbt_boot_ctrl is always zero). @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) switch (mmc->fpga_type) { case FPGA_AN385: + case FPGA_AN386: make_ram(&mms->ssram1, "mps.ssram1", 0x0, 0x400000); make_ram_alias(&mms->ssram1_m, "mps.ssram1_m", &mms->ssram1, 0x400000); make_ram(&mms->ssram23, "mps.ssram23", 0x20000000, 0x400000); @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) armv7m = DEVICE(&mms->armv7m); switch (mmc->fpga_type) { case FPGA_AN385: + case FPGA_AN386: qdev_prop_set_uint32(armv7m, "num-irq", 32); break; case FPGA_AN511: @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) switch (mmc->fpga_type) { case FPGA_AN385: + case FPGA_AN386: { /* The overflow IRQs for UARTs 0, 1 and 2 are ORed together. * Overflow for UARTs 4 and 5 doesn't trigger any interrupt. @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) */ lan9118_init(&nd_table[0], 0x40200000, qdev_get_gpio_in(armv7m, - mmc->fpga_type == FPGA_AN385 ? 13 : 47)); + mmc->fpga_type == FPGA_AN511 ? 47 : 13)); system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; @@ -XXX,XX +XXX,XX @@ static void mps2_an385_class_init(ObjectClass *oc, void *data) mmc->scc_id = 0x41043850; } +static void mps2_an386_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + MPS2MachineClass *mmc = MPS2_MACHINE_CLASS(oc); + + mc->desc = "ARM MPS2 with AN386 FPGA image for Cortex-M4"; + mmc->fpga_type = FPGA_AN386; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m4"); + mmc->scc_id = 0x41043860; +} + static void mps2_an511_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); @@ -XXX,XX +XXX,XX @@ static const TypeInfo mps2_an385_info = { .class_init = mps2_an385_class_init, }; +static const TypeInfo mps2_an386_info = { + .name = TYPE_MPS2_AN386_MACHINE, + .parent = TYPE_MPS2_MACHINE, + .class_init = mps2_an386_class_init, +}; + static const TypeInfo mps2_an511_info = { .name = TYPE_MPS2_AN511_MACHINE, .parent = TYPE_MPS2_MACHINE, @@ -XXX,XX +XXX,XX @@ static void mps2_machine_init(void) { type_register_static(&mps2_info); type_register_static(&mps2_an385_info); + type_register_static(&mps2_an386_info); type_register_static(&mps2_an511_info); } -- 2.20.1 Implement a model of the MPS2 with the AN500 firmware. This is similar to the AN385, with the following differences: * Cortex-M7 CPU * PSRAM is at 0x6000_0000 * Ethernet is at 0xa000_0000 * No zbt_boot_ctrl remapping of the low 16K (but QEMU doesn't implement this anyway) * no "block RAM" at 0x01000000 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200903202048.15370-3-peter.maydell@linaro.org --- docs/system/arm/mps2.rst | 6 ++-- hw/arm/mps2.c | 67 +++++++++++++++++++++++++++++++++------- 2 files changed, 60 insertions(+), 13 deletions(-) diff --git a/docs/system/arm/mps2.rst b/docs/system/arm/mps2.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/mps2.rst +++ b/docs/system/arm/mps2.rst @@ -XXX,XX +XXX,XX @@ -Arm MPS2 boards (``mps2-an385``, ``mps2-an386``, ``mps2-an505``, ``mps2-an511``, ``mps2-an521``) -================================================================================================ +Arm MPS2 boards (``mps2-an385``, ``mps2-an386``, ``mps2-an500``, ``mps2-an505``, ``mps2-an511``, ``mps2-an521``) +================================================================================================================ These board models all use Arm M-profile CPUs. @@ -XXX,XX +XXX,XX @@ QEMU models the following FPGA images: Cortex-M3 as documented in ARM Application Note AN385 ``mps2-an386`` Cortex-M4 as documented in ARM Application Note AN386 +``mps2-an500`` + Cortex-M7 as documented in ARM Application Note AN500 ``mps2-an511`` Cortex-M3 'DesignStart' as documented in AN511 ``mps2-an505`` diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2.c +++ b/hw/arm/mps2.c @@ -XXX,XX +XXX,XX @@ * We model the following FPGA images: * "mps2-an385" -- Cortex-M3 as documented in ARM Application Note AN385 * "mps2-an386" -- Cortex-M4 as documented in ARM Application Note AN386 + * "mps2-an500" -- Cortex-M7 as documented in ARM Application Note AN500 * "mps2-an511" -- Cortex-M3 'DesignStart' as documented in AN511 * * Links to the TRM for the board itself and to the various Application @@ -XXX,XX +XXX,XX @@ typedef enum MPS2FPGAType { FPGA_AN385, FPGA_AN386, + FPGA_AN500, FPGA_AN511, } MPS2FPGAType; @@ -XXX,XX +XXX,XX @@ struct MPS2MachineClass { MachineClass parent; MPS2FPGAType fpga_type; uint32_t scc_id; + bool has_block_ram; + hwaddr ethernet_base; + hwaddr psram_base; }; typedef struct MPS2MachineClass MPS2MachineClass; @@ -XXX,XX +XXX,XX @@ typedef struct MPS2MachineState MPS2MachineState; #define TYPE_MPS2_MACHINE "mps2" #define TYPE_MPS2_AN385_MACHINE MACHINE_TYPE_NAME("mps2-an385") #define TYPE_MPS2_AN386_MACHINE MACHINE_TYPE_NAME("mps2-an386") +#define TYPE_MPS2_AN500_MACHINE MACHINE_TYPE_NAME("mps2-an500") #define TYPE_MPS2_AN511_MACHINE MACHINE_TYPE_NAME("mps2-an511") DECLARE_OBJ_CHECKERS(MPS2MachineState, MPS2MachineClass, @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) * * AN385/AN386/AN511: * 0x21000000 .. 0x21ffffff : PSRAM (16MB) - * AN385/AN386 only: + * AN385/AN386/AN500: * 0x00000000 .. 0x003fffff : ZBT SSRAM1 * 0x00400000 .. 0x007fffff : mirror of ZBT SSRAM1 * 0x20000000 .. 0x203fffff : ZBT SSRAM 2&3 * 0x20400000 .. 0x207fffff : mirror of ZBT SSRAM 2&3 + * AN385/AN386 only: * 0x01000000 .. 0x01003fff : block RAM (16K) * 0x01004000 .. 0x01007fff : mirror of above * 0x01008000 .. 0x0100bfff : mirror of above @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) * 0x00400000 .. 0x007fffff : ZBT SSRAM1 * 0x20000000 .. 0x2001ffff : SRAM * 0x20400000 .. 0x207fffff : ZBT SSRAM 2&3 + * AN500 only: + * 0x60000000 .. 0x60ffffff : PSRAM (16MB) * * The AN385/AN386 has a feature where the lowest 16K can be mapped * either to the bottom of the ZBT SSRAM1 or to the block RAM. * This is of no use for QEMU so we don't implement it (as if * zbt_boot_ctrl is always zero). */ - memory_region_add_subregion(system_memory, 0x21000000, machine->ram); + memory_region_add_subregion(system_memory, mmc->psram_base, machine->ram); - switch (mmc->fpga_type) { - case FPGA_AN385: - case FPGA_AN386: - make_ram(&mms->ssram1, "mps.ssram1", 0x0, 0x400000); - make_ram_alias(&mms->ssram1_m, "mps.ssram1_m", &mms->ssram1, 0x400000); - make_ram(&mms->ssram23, "mps.ssram23", 0x20000000, 0x400000); - make_ram_alias(&mms->ssram23_m, "mps.ssram23_m", - &mms->ssram23, 0x20400000); + if (mmc->has_block_ram) { make_ram(&mms->blockram, "mps.blockram", 0x01000000, 0x4000); make_ram_alias(&mms->blockram_m1, "mps.blockram_m1", &mms->blockram, 0x01004000); @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) &mms->blockram, 0x01008000); make_ram_alias(&mms->blockram_m3, "mps.blockram_m3", &mms->blockram, 0x0100c000); + } + + switch (mmc->fpga_type) { + case FPGA_AN385: + case FPGA_AN386: + case FPGA_AN500: + make_ram(&mms->ssram1, "mps.ssram1", 0x0, 0x400000); + make_ram_alias(&mms->ssram1_m, "mps.ssram1_m", &mms->ssram1, 0x400000); + make_ram(&mms->ssram23, "mps.ssram23", 0x20000000, 0x400000); + make_ram_alias(&mms->ssram23_m, "mps.ssram23_m", + &mms->ssram23, 0x20400000); break; case FPGA_AN511: make_ram(&mms->blockram, "mps.blockram", 0x0, 0x40000); @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) switch (mmc->fpga_type) { case FPGA_AN385: case FPGA_AN386: + case FPGA_AN500: qdev_prop_set_uint32(armv7m, "num-irq", 32); break; case FPGA_AN511: @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) switch (mmc->fpga_type) { case FPGA_AN385: case FPGA_AN386: + case FPGA_AN500: { /* The overflow IRQs for UARTs 0, 1 and 2 are ORed together. * Overflow for UARTs 4 and 5 doesn't trigger any interrupt. @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) /* In hardware this is a LAN9220; the LAN9118 is software compatible * except that it doesn't support the checksum-offload feature. */ - lan9118_init(&nd_table[0], 0x40200000, + lan9118_init(&nd_table[0], mmc->ethernet_base, qdev_get_gpio_in(armv7m, mmc->fpga_type == FPGA_AN511 ? 47 : 13)); @@ -XXX,XX +XXX,XX @@ static void mps2_an385_class_init(ObjectClass *oc, void *data) mmc->fpga_type = FPGA_AN385; mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m3"); mmc->scc_id = 0x41043850; + mmc->psram_base = 0x21000000; + mmc->ethernet_base = 0x40200000; + mmc->has_block_ram = true; } static void mps2_an386_class_init(ObjectClass *oc, void *data) @@ -XXX,XX +XXX,XX @@ static void mps2_an386_class_init(ObjectClass *oc, void *data) mmc->fpga_type = FPGA_AN386; mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m4"); mmc->scc_id = 0x41043860; + mmc->psram_base = 0x21000000; + mmc->ethernet_base = 0x40200000; + mmc->has_block_ram = true; +} + +static void mps2_an500_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + MPS2MachineClass *mmc = MPS2_MACHINE_CLASS(oc); + + mc->desc = "ARM MPS2 with AN500 FPGA image for Cortex-M7"; + mmc->fpga_type = FPGA_AN500; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m7"); + mmc->scc_id = 0x41045000; + mmc->psram_base = 0x60000000; + mmc->ethernet_base = 0xa0000000; + mmc->has_block_ram = false; } static void mps2_an511_class_init(ObjectClass *oc, void *data) @@ -XXX,XX +XXX,XX @@ static void mps2_an511_class_init(ObjectClass *oc, void *data) mmc->fpga_type = FPGA_AN511; mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m3"); mmc->scc_id = 0x41045110; + mmc->psram_base = 0x21000000; + mmc->ethernet_base = 0x40200000; + mmc->has_block_ram = false; } static const TypeInfo mps2_info = { @@ -XXX,XX +XXX,XX @@ static const TypeInfo mps2_an386_info = { .class_init = mps2_an386_class_init, }; +static const TypeInfo mps2_an500_info = { + .name = TYPE_MPS2_AN500_MACHINE, + .parent = TYPE_MPS2_MACHINE, + .class_init = mps2_an500_class_init, +}; + static const TypeInfo mps2_an511_info = { .name = TYPE_MPS2_AN511_MACHINE, .parent = TYPE_MPS2_MACHINE, @@ -XXX,XX +XXX,XX @@ static void mps2_machine_init(void) type_register_static(&mps2_info); type_register_static(&mps2_an385_info); type_register_static(&mps2_an386_info); + type_register_static(&mps2_an500_info); type_register_static(&mps2_an511_info); } -- 2.20.1 Make the list of MPS2 boards consistent in the phrasing of each entry, use the correct casing of "Arm", and move the mps2-an511 entry so the list is in numeric order. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200903202048.15370-4-peter.maydell@linaro.org --- docs/system/arm/mps2.rst | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/docs/system/arm/mps2.rst b/docs/system/arm/mps2.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/mps2.rst +++ b/docs/system/arm/mps2.rst @@ -XXX,XX +XXX,XX @@ as seen by the guest depend significantly on the FPGA image. QEMU models the following FPGA images: ``mps2-an385`` - Cortex-M3 as documented in ARM Application Note AN385 + Cortex-M3 as documented in Arm Application Note AN385 ``mps2-an386`` - Cortex-M4 as documented in ARM Application Note AN386 + Cortex-M4 as documented in Arm Application Note AN386 ``mps2-an500`` - Cortex-M7 as documented in ARM Application Note AN500 -``mps2-an511`` - Cortex-M3 'DesignStart' as documented in AN511 + Cortex-M7 as documented in Arm Application Note AN500 ``mps2-an505`` - Cortex-M33 as documented in ARM Application Note AN505 + Cortex-M33 as documented in Arm Application Note AN505 +``mps2-an511`` + Cortex-M3 'DesignStart' as documented in Arm Application Note AN511 ``mps2-an521`` - Dual Cortex-M33 as documented in Application Note AN521 + Dual Cortex-M33 as documented in Arm Application Note AN521 Differences between QEMU and real hardware: -- 2.20.1 Deprecate our Unicore32 target support: * the Linux kernel dropped support for unicore32 in commit 05119217a9bd199c for its 5.9 release (with rationale in the cover letter: https://lkml.org/lkml/2020/8/3/232 ) * there is apparently no upstream toolchain that can create unicore32 binaries * the maintainer doesn't seem to have made any contributions to QEMU since the port first landed in 2012 * nobody else seems to have made changes to the unicore code except for generic cleanups either Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Message-id: 20200825172719.19422-1-peter.maydell@linaro.org --- docs/system/deprecated.rst | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/docs/system/deprecated.rst b/docs/system/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/deprecated.rst +++ b/docs/system/deprecated.rst @@ -XXX,XX +XXX,XX @@ The above, converted to the current supported format:: linux-user mode CPUs -------------------- +``unicore32`` CPUs (since 5.2.0) +'''''''''''''''''''''''''''''''' + +The ``unicore32`` guest CPU support is deprecated and will be removed in +a future version of QEMU. Support for this CPU was removed from the +upstream Linux kernel, and there is no available upstream toolchain +to build binaries for it. + ``tilegx`` CPUs (since 5.1.0) ''''''''''''''''''''''''''''' -- 2.20.1 Deprecate our lm32 target support. Michael Walle (former lm32 maintainer) suggested that we do this in 2019: https://www.mail-archive.com/qemu-devel@nongnu.org/msg605024.html because the only public user of the architecture is the many-years-dead milkymist project. (The Linux port to lm32 was never merged upstream.) In commit 4b4d96c776f552e (March 2020) we marked it as 'orphan' in the MAINTAINERS file, but didn't officially deprecate it. Mark it deprecated now, with the intention of removing it from QEMU in mid-2021 before the 6.1 release. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Acked-by: Michael Walle <michael@walle.cc> Message-id: 20200827113259.25064-1-peter.maydell@linaro.org --- docs/system/deprecated.rst | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/docs/system/deprecated.rst b/docs/system/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/deprecated.rst +++ b/docs/system/deprecated.rst @@ -XXX,XX +XXX,XX @@ The above, converted to the current supported format:: linux-user mode CPUs -------------------- +``lm32`` CPUs (since 5.2.0) +''''''''''''''''''''''''''' + +The ``lm32`` guest CPU support is deprecated and will be removed in +a future version of QEMU. The only public user of this architecture +was the milkymist project, which has been dead for years; there was +never an upstream Linux port. + ``unicore32`` CPUs (since 5.2.0) '''''''''''''''''''''''''''''''' -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> This check was backwards when introduced in commit 033614c47de78409ad3fb39bb7bd1483b71c6789: target/arm: Filter cycle counter based on PMCCFILTR_EL0 Cc: qemu-stable@nongnu.org Signed-off-by: Aaron Lindsay <aaron@os.amperecomputing.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static bool pmu_counter_enabled(CPUARMState *env, uint8_t counter) } } else { prohibited = arm_feature(env, ARM_FEATURE_EL3) && - (env->cp15.mdcr_el3 & MDCR_SPME); + !(env->cp15.mdcr_el3 & MDCR_SPME); } if (prohibited && counter == 31) { -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Correct the GEMs tx/rx clocks to use the 125Mhz fixed-clock. This matches the setup with the fixed-link 100Mbit PHY. It also avoids the following warnings from the Linux kernel driver: eth0: unable to generate target frequency: 125000000 Hz Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200909174647.662864-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-versal-virt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -XXX,XX +XXX,XX @@ static void fdt_add_gem_nodes(VersalVirt *s) s->phandle.ethernet_phy[i]); qemu_fdt_setprop_cells(s->fdt, name, "clocks", s->phandle.clk_25Mhz, s->phandle.clk_25Mhz, - s->phandle.clk_25Mhz, s->phandle.clk_25Mhz); + s->phandle.clk_125Mhz, s->phandle.clk_125Mhz); qemu_fdt_setprop(s->fdt, name, "clock-names", clocknames, sizeof(clocknames)); qemu_fdt_setprop_cells(s->fdt, name, "interrupts", -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> Implement a device model for the System Global Control Registers in the NPCM730 and NPCM750 BMC SoCs. This is primarily used to enable SMP boot (the boot ROM spins reading the SCRPAD register) and DDR memory initialization; other registers are best effort for now. The reset values of the MDLR and PWRON registers are determined by the SoC variant (730 vs 750) and board straps respectively. Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-2-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/npcm7xx_gcr.h | 43 ++++++ hw/misc/npcm7xx_gcr.c | 269 ++++++++++++++++++++++++++++++++++ MAINTAINERS | 8 + hw/arm/Kconfig | 3 + hw/misc/meson.build | 3 + hw/misc/trace-events | 4 + 6 files changed, 330 insertions(+) create mode 100644 include/hw/misc/npcm7xx_gcr.h create mode 100644 hw/misc/npcm7xx_gcr.c diff --git a/include/hw/misc/npcm7xx_gcr.h b/include/hw/misc/npcm7xx_gcr.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/npcm7xx_gcr.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx System Global Control Registers. + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ +#ifndef NPCM7XX_GCR_H +#define NPCM7XX_GCR_H + +#include "exec/memory.h" +#include "hw/sysbus.h" + +/* + * Number of registers in our device state structure. Don't change this without + * incrementing the version_id in the vmstate. + */ +#define NPCM7XX_GCR_NR_REGS (0x148 / sizeof(uint32_t)) + +typedef struct NPCM7xxGCRState { + SysBusDevice parent; + + MemoryRegion iomem; + + uint32_t regs[NPCM7XX_GCR_NR_REGS]; + + uint32_t reset_pwron; + uint32_t reset_mdlr; + uint32_t reset_intcr3; +} NPCM7xxGCRState; + +#define TYPE_NPCM7XX_GCR "npcm7xx-gcr" +#define NPCM7XX_GCR(obj) OBJECT_CHECK(NPCM7xxGCRState, (obj), TYPE_NPCM7XX_GCR) + +#endif /* NPCM7XX_GCR_H */ diff --git a/hw/misc/npcm7xx_gcr.c b/hw/misc/npcm7xx_gcr.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/npcm7xx_gcr.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx System Global Control Registers. + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ + +#include "qemu/osdep.h" + +#include "hw/misc/npcm7xx_gcr.h" +#include "hw/qdev-properties.h" +#include "migration/vmstate.h" +#include "qapi/error.h" +#include "qemu/cutils.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/units.h" + +#include "trace.h" + +#define NPCM7XX_GCR_MIN_DRAM_SIZE (128 * MiB) +#define NPCM7XX_GCR_MAX_DRAM_SIZE (2 * GiB) + +enum NPCM7xxGCRRegisters { + NPCM7XX_GCR_PDID, + NPCM7XX_GCR_PWRON, + NPCM7XX_GCR_MFSEL1 = 0x0c / sizeof(uint32_t), + NPCM7XX_GCR_MFSEL2, + NPCM7XX_GCR_MISCPE, + NPCM7XX_GCR_SPSWC = 0x038 / sizeof(uint32_t), + NPCM7XX_GCR_INTCR, + NPCM7XX_GCR_INTSR, + NPCM7XX_GCR_HIFCR = 0x050 / sizeof(uint32_t), + NPCM7XX_GCR_INTCR2 = 0x060 / sizeof(uint32_t), + NPCM7XX_GCR_MFSEL3, + NPCM7XX_GCR_SRCNT, + NPCM7XX_GCR_RESSR, + NPCM7XX_GCR_RLOCKR1, + NPCM7XX_GCR_FLOCKR1, + NPCM7XX_GCR_DSCNT, + NPCM7XX_GCR_MDLR, + NPCM7XX_GCR_SCRPAD3, + NPCM7XX_GCR_SCRPAD2, + NPCM7XX_GCR_DAVCLVLR = 0x098 / sizeof(uint32_t), + NPCM7XX_GCR_INTCR3, + NPCM7XX_GCR_VSINTR = 0x0ac / sizeof(uint32_t), + NPCM7XX_GCR_MFSEL4, + NPCM7XX_GCR_CPBPNTR = 0x0c4 / sizeof(uint32_t), + NPCM7XX_GCR_CPCTL = 0x0d0 / sizeof(uint32_t), + NPCM7XX_GCR_CP2BST, + NPCM7XX_GCR_B2CPNT, + NPCM7XX_GCR_CPPCTL, + NPCM7XX_GCR_I2CSEGSEL, + NPCM7XX_GCR_I2CSEGCTL, + NPCM7XX_GCR_VSRCR, + NPCM7XX_GCR_MLOCKR, + NPCM7XX_GCR_SCRPAD = 0x013c / sizeof(uint32_t), + NPCM7XX_GCR_USB1PHYCTL, + NPCM7XX_GCR_USB2PHYCTL, + NPCM7XX_GCR_REGS_END, +}; + +static const uint32_t cold_reset_values[NPCM7XX_GCR_NR_REGS] = { + [NPCM7XX_GCR_PDID] = 0x04a92750, /* Poleg A1 */ + [NPCM7XX_GCR_MISCPE] = 0x0000ffff, + [NPCM7XX_GCR_SPSWC] = 0x00000003, + [NPCM7XX_GCR_INTCR] = 0x0000035e, + [NPCM7XX_GCR_HIFCR] = 0x0000004e, + [NPCM7XX_GCR_INTCR2] = (1U << 19), /* DDR initialized */ + [NPCM7XX_GCR_RESSR] = 0x80000000, + [NPCM7XX_GCR_DSCNT] = 0x000000c0, + [NPCM7XX_GCR_DAVCLVLR] = 0x5a00f3cf, + [NPCM7XX_GCR_SCRPAD] = 0x00000008, + [NPCM7XX_GCR_USB1PHYCTL] = 0x034730e4, + [NPCM7XX_GCR_USB2PHYCTL] = 0x034730e4, +}; + +static uint64_t npcm7xx_gcr_read(void *opaque, hwaddr offset, unsigned size) +{ + uint32_t reg = offset / sizeof(uint32_t); + NPCM7xxGCRState *s = opaque; + + if (reg >= NPCM7XX_GCR_NR_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: offset 0x%04" HWADDR_PRIx " out of range\n", + __func__, offset); + return 0; + } + + trace_npcm7xx_gcr_read(offset, s->regs[reg]); + + return s->regs[reg]; +} + +static void npcm7xx_gcr_write(void *opaque, hwaddr offset, + uint64_t v, unsigned size) +{ + uint32_t reg = offset / sizeof(uint32_t); + NPCM7xxGCRState *s = opaque; + uint32_t value = v; + + trace_npcm7xx_gcr_write(offset, value); + + if (reg >= NPCM7XX_GCR_NR_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: offset 0x%04" HWADDR_PRIx " out of range\n", + __func__, offset); + return; + } + + switch (reg) { + case NPCM7XX_GCR_PDID: + case NPCM7XX_GCR_PWRON: + case NPCM7XX_GCR_INTSR: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: register @ 0x%04" HWADDR_PRIx " is read-only\n", + __func__, offset); + return; + + case NPCM7XX_GCR_RESSR: + case NPCM7XX_GCR_CP2BST: + /* Write 1 to clear */ + value = s->regs[reg] & ~value; + break; + + case NPCM7XX_GCR_RLOCKR1: + case NPCM7XX_GCR_MDLR: + /* Write 1 to set */ + value |= s->regs[reg]; + break; + }; + + s->regs[reg] = value; +} + +static const struct MemoryRegionOps npcm7xx_gcr_ops = { + .read = npcm7xx_gcr_read, + .write = npcm7xx_gcr_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void npcm7xx_gcr_enter_reset(Object *obj, ResetType type) +{ + NPCM7xxGCRState *s = NPCM7XX_GCR(obj); + + QEMU_BUILD_BUG_ON(sizeof(s->regs) != sizeof(cold_reset_values)); + + switch (type) { + case RESET_TYPE_COLD: + memcpy(s->regs, cold_reset_values, sizeof(s->regs)); + s->regs[NPCM7XX_GCR_PWRON] = s->reset_pwron; + s->regs[NPCM7XX_GCR_MDLR] = s->reset_mdlr; + s->regs[NPCM7XX_GCR_INTCR3] = s->reset_intcr3; + break; + } +} + +static void npcm7xx_gcr_realize(DeviceState *dev, Error **errp) +{ + ERRP_GUARD(); + NPCM7xxGCRState *s = NPCM7XX_GCR(dev); + uint64_t dram_size; + Object *obj; + + obj = object_property_get_link(OBJECT(dev), "dram-mr", errp); + if (!obj) { + error_prepend(errp, "%s: required dram-mr link not found: ", __func__); + return; + } + dram_size = memory_region_size(MEMORY_REGION(obj)); + if (!is_power_of_2(dram_size) || + dram_size < NPCM7XX_GCR_MIN_DRAM_SIZE || + dram_size > NPCM7XX_GCR_MAX_DRAM_SIZE) { + g_autofree char *sz = size_to_str(dram_size); + g_autofree char *min_sz = size_to_str(NPCM7XX_GCR_MIN_DRAM_SIZE); + g_autofree char *max_sz = size_to_str(NPCM7XX_GCR_MAX_DRAM_SIZE); + error_setg(errp, "%s: unsupported DRAM size %s", __func__, sz); + error_append_hint(errp, + "DRAM size must be a power of two between %s and %s," + " inclusive.\n", min_sz, max_sz); + return; + } + + /* Power-on reset value */ + s->reset_intcr3 = 0x00001002; + + /* + * The GMMAP (Graphics Memory Map) field is used by u-boot to detect the + * DRAM size, and is normally initialized by the boot block as part of DRAM + * training. However, since we don't have a complete emulation of the + * memory controller and try to make it look like it has already been + * initialized, the boot block will skip this initialization, and we need + * to make sure this field is set correctly up front. + * + * WARNING: some versions of u-boot only looks at bits 8 and 9, so 2 GiB of + * DRAM will be interpreted as 128 MiB. + * + * https://github.com/Nuvoton-Israel/u-boot/blob/2aef993bd2aafeb5408dbaad0f3ce099ee40c4aa/board/nuvoton/poleg/poleg.c#L244 + */ + s->reset_intcr3 |= ctz64(dram_size / NPCM7XX_GCR_MIN_DRAM_SIZE) << 8; +} + +static void npcm7xx_gcr_init(Object *obj) +{ + NPCM7xxGCRState *s = NPCM7XX_GCR(obj); + + memory_region_init_io(&s->iomem, obj, &npcm7xx_gcr_ops, s, + TYPE_NPCM7XX_GCR, 4 * KiB); + sysbus_init_mmio(&s->parent, &s->iomem); +} + +static const VMStateDescription vmstate_npcm7xx_gcr = { + .name = "npcm7xx-gcr", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, NPCM7xxGCRState, NPCM7XX_GCR_NR_REGS), + VMSTATE_END_OF_LIST(), + }, +}; + +static Property npcm7xx_gcr_properties[] = { + DEFINE_PROP_UINT32("disabled-modules", NPCM7xxGCRState, reset_mdlr, 0), + DEFINE_PROP_UINT32("power-on-straps", NPCM7xxGCRState, reset_pwron, 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static void npcm7xx_gcr_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + QEMU_BUILD_BUG_ON(NPCM7XX_GCR_REGS_END > NPCM7XX_GCR_NR_REGS); + + dc->desc = "NPCM7xx System Global Control Registers"; + dc->realize = npcm7xx_gcr_realize; + dc->vmsd = &vmstate_npcm7xx_gcr; + rc->phases.enter = npcm7xx_gcr_enter_reset; + + device_class_set_props(dc, npcm7xx_gcr_properties); +} + +static const TypeInfo npcm7xx_gcr_info = { + .name = TYPE_NPCM7XX_GCR, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxGCRState), + .instance_init = npcm7xx_gcr_init, + .class_init = npcm7xx_gcr_class_init, +}; + +static void npcm7xx_gcr_register_type(void) +{ + type_register_static(&npcm7xx_gcr_info); +} +type_init(npcm7xx_gcr_register_type); diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ S: Odd Fixes F: hw/arm/musicpal.c F: docs/system/arm/musicpal.rst +Nuvoton NPCM7xx +M: Havard Skinnemoen <hskinnemoen@google.com> +M: Tyrone Ting <kfting@nuvoton.com> +L: qemu-arm@nongnu.org +S: Supported +F: hw/*/npcm7xx* +F: include/hw/*/npcm7xx* + nSeries M: Andrzej Zaborowski <balrogg@gmail.com> M: Peter Maydell <peter.maydell@linaro.org> diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config XLNX_VERSAL select VIRTIO_MMIO select UNIMP +config NPCM7XX + bool + config FSL_IMX25 bool select IMX diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_IMX', if_true: files( )) softmmu_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-hpdmc.c', 'milkymist-pfpu.c')) softmmu_ss.add(when: 'CONFIG_MAINSTONE', if_true: files('mst_fpga.c')) +softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files( + 'npcm7xx_gcr.c', +)) softmmu_ss.add(when: 'CONFIG_OMAP', if_true: files( 'omap_clk.c', 'omap_gpmc.c', diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ mos6522_set_sr_int(void) "set sr_int" mos6522_write(uint64_t addr, uint64_t val) "reg=0x%"PRIx64 " val=0x%"PRIx64 mos6522_read(uint64_t addr, unsigned val) "reg=0x%"PRIx64 " val=0x%x" +# npcm7xx_gcr.c +npcm7xx_gcr_read(uint64_t offset, uint32_t value) " offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 +npcm7xx_gcr_write(uint64_t offset, uint32_t value) "offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 + # stm32f4xx_syscfg.c stm32f4xx_syscfg_set_irq(int gpio, int line, int level) "Interupt: GPIO: %d, Line: %d; Level: %d" stm32f4xx_pulse_exti(int irq) "Pulse EXTI: %d" -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> Enough functionality to boot the Linux kernel has been implemented. This includes: - Correct power-on reset values so the various clock rates can be accurately calculated. - Clock enables stick around when written. In addition, a best effort attempt to implement SECCNT and CNTR25M was made even though I don't think the kernel needs them. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-3-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/npcm7xx_clk.h | 48 ++++++ hw/misc/npcm7xx_clk.c | 266 ++++++++++++++++++++++++++++++++++ hw/misc/meson.build | 1 + hw/misc/trace-events | 4 + 4 files changed, 319 insertions(+) create mode 100644 include/hw/misc/npcm7xx_clk.h create mode 100644 hw/misc/npcm7xx_clk.c diff --git a/include/hw/misc/npcm7xx_clk.h b/include/hw/misc/npcm7xx_clk.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/npcm7xx_clk.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Clock Control Registers. + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ +#ifndef NPCM7XX_CLK_H +#define NPCM7XX_CLK_H + +#include "exec/memory.h" +#include "hw/sysbus.h" + +/* + * The reference clock frequency for the timer modules, and the SECCNT and + * CNTR25M registers in this module, is always 25 MHz. + */ +#define NPCM7XX_TIMER_REF_HZ (25000000) + +/* + * Number of registers in our device state structure. Don't change this without + * incrementing the version_id in the vmstate. + */ +#define NPCM7XX_CLK_NR_REGS (0x70 / sizeof(uint32_t)) + +typedef struct NPCM7xxCLKState { + SysBusDevice parent; + + MemoryRegion iomem; + + uint32_t regs[NPCM7XX_CLK_NR_REGS]; + + /* Time reference for SECCNT and CNTR25M, initialized by power on reset */ + int64_t ref_ns; +} NPCM7xxCLKState; + +#define TYPE_NPCM7XX_CLK "npcm7xx-clk" +#define NPCM7XX_CLK(obj) OBJECT_CHECK(NPCM7xxCLKState, (obj), TYPE_NPCM7XX_CLK) + +#endif /* NPCM7XX_CLK_H */ diff --git a/hw/misc/npcm7xx_clk.c b/hw/misc/npcm7xx_clk.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/npcm7xx_clk.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Clock Control Registers. + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ + +#include "qemu/osdep.h" + +#include "hw/misc/npcm7xx_clk.h" +#include "migration/vmstate.h" +#include "qemu/error-report.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/timer.h" +#include "qemu/units.h" +#include "trace.h" + +#define PLLCON_LOKI BIT(31) +#define PLLCON_LOKS BIT(30) +#define PLLCON_PWDEN BIT(12) + +enum NPCM7xxCLKRegisters { + NPCM7XX_CLK_CLKEN1, + NPCM7XX_CLK_CLKSEL, + NPCM7XX_CLK_CLKDIV1, + NPCM7XX_CLK_PLLCON0, + NPCM7XX_CLK_PLLCON1, + NPCM7XX_CLK_SWRSTR, + NPCM7XX_CLK_IPSRST1 = 0x20 / sizeof(uint32_t), + NPCM7XX_CLK_IPSRST2, + NPCM7XX_CLK_CLKEN2, + NPCM7XX_CLK_CLKDIV2, + NPCM7XX_CLK_CLKEN3, + NPCM7XX_CLK_IPSRST3, + NPCM7XX_CLK_WD0RCR, + NPCM7XX_CLK_WD1RCR, + NPCM7XX_CLK_WD2RCR, + NPCM7XX_CLK_SWRSTC1, + NPCM7XX_CLK_SWRSTC2, + NPCM7XX_CLK_SWRSTC3, + NPCM7XX_CLK_SWRSTC4, + NPCM7XX_CLK_PLLCON2, + NPCM7XX_CLK_CLKDIV3, + NPCM7XX_CLK_CORSTC, + NPCM7XX_CLK_PLLCONG, + NPCM7XX_CLK_AHBCKFI, + NPCM7XX_CLK_SECCNT, + NPCM7XX_CLK_CNTR25M, + NPCM7XX_CLK_REGS_END, +}; + +/* + * These reset values were taken from version 0.91 of the NPCM750R data sheet. + * + * All are loaded on power-up reset. CLKENx and SWRSTR should also be loaded on + * core domain reset, but this reset type is not yet supported by QEMU. + */ +static const uint32_t cold_reset_values[NPCM7XX_CLK_NR_REGS] = { + [NPCM7XX_CLK_CLKEN1] = 0xffffffff, + [NPCM7XX_CLK_CLKSEL] = 0x004aaaaa, + [NPCM7XX_CLK_CLKDIV1] = 0x5413f855, + [NPCM7XX_CLK_PLLCON0] = 0x00222101 | PLLCON_LOKI, + [NPCM7XX_CLK_PLLCON1] = 0x00202101 | PLLCON_LOKI, + [NPCM7XX_CLK_IPSRST1] = 0x00001000, + [NPCM7XX_CLK_IPSRST2] = 0x80000000, + [NPCM7XX_CLK_CLKEN2] = 0xffffffff, + [NPCM7XX_CLK_CLKDIV2] = 0xaa4f8f9f, + [NPCM7XX_CLK_CLKEN3] = 0xffffffff, + [NPCM7XX_CLK_IPSRST3] = 0x03000000, + [NPCM7XX_CLK_WD0RCR] = 0xffffffff, + [NPCM7XX_CLK_WD1RCR] = 0xffffffff, + [NPCM7XX_CLK_WD2RCR] = 0xffffffff, + [NPCM7XX_CLK_SWRSTC1] = 0x00000003, + [NPCM7XX_CLK_PLLCON2] = 0x00c02105 | PLLCON_LOKI, + [NPCM7XX_CLK_CORSTC] = 0x04000003, + [NPCM7XX_CLK_PLLCONG] = 0x01228606 | PLLCON_LOKI, + [NPCM7XX_CLK_AHBCKFI] = 0x000000c8, +}; + +static uint64_t npcm7xx_clk_read(void *opaque, hwaddr offset, unsigned size) +{ + uint32_t reg = offset / sizeof(uint32_t); + NPCM7xxCLKState *s = opaque; + int64_t now_ns; + uint32_t value = 0; + + if (reg >= NPCM7XX_CLK_NR_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: offset 0x%04" HWADDR_PRIx " out of range\n", + __func__, offset); + return 0; + } + + switch (reg) { + case NPCM7XX_CLK_SWRSTR: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: register @ 0x%04" HWADDR_PRIx " is write-only\n", + __func__, offset); + break; + + case NPCM7XX_CLK_SECCNT: + now_ns = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + value = (now_ns - s->ref_ns) / NANOSECONDS_PER_SECOND; + break; + + case NPCM7XX_CLK_CNTR25M: + now_ns = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + /* + * This register counts 25 MHz cycles, updating every 640 ns. It rolls + * over to zero every second. + * + * The 4 LSBs are always zero: (1e9 / 640) << 4 = 25000000. + */ + value = (((now_ns - s->ref_ns) / 640) << 4) % NPCM7XX_TIMER_REF_HZ; + break; + + default: + value = s->regs[reg]; + break; + }; + + trace_npcm7xx_clk_read(offset, value); + + return value; +} + +static void npcm7xx_clk_write(void *opaque, hwaddr offset, + uint64_t v, unsigned size) +{ + uint32_t reg = offset / sizeof(uint32_t); + NPCM7xxCLKState *s = opaque; + uint32_t value = v; + + trace_npcm7xx_clk_write(offset, value); + + if (reg >= NPCM7XX_CLK_NR_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: offset 0x%04" HWADDR_PRIx " out of range\n", + __func__, offset); + return; + } + + switch (reg) { + case NPCM7XX_CLK_SWRSTR: + qemu_log_mask(LOG_UNIMP, "%s: SW reset not implemented: 0x%02x\n", + __func__, value); + value = 0; + break; + + case NPCM7XX_CLK_PLLCON0: + case NPCM7XX_CLK_PLLCON1: + case NPCM7XX_CLK_PLLCON2: + case NPCM7XX_CLK_PLLCONG: + if (value & PLLCON_PWDEN) { + /* Power down -- clear lock and indicate loss of lock */ + value &= ~PLLCON_LOKI; + value |= PLLCON_LOKS; + } else { + /* Normal mode -- assume always locked */ + value |= PLLCON_LOKI; + /* Keep LOKS unchanged unless cleared by writing 1 */ + if (value & PLLCON_LOKS) { + value &= ~PLLCON_LOKS; + } else { + value |= (value & PLLCON_LOKS); + } + } + break; + + case NPCM7XX_CLK_CNTR25M: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: register @ 0x%04" HWADDR_PRIx " is read-only\n", + __func__, offset); + return; + } + + s->regs[reg] = value; +} + +static const struct MemoryRegionOps npcm7xx_clk_ops = { + .read = npcm7xx_clk_read, + .write = npcm7xx_clk_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void npcm7xx_clk_enter_reset(Object *obj, ResetType type) +{ + NPCM7xxCLKState *s = NPCM7XX_CLK(obj); + + QEMU_BUILD_BUG_ON(sizeof(s->regs) != sizeof(cold_reset_values)); + + switch (type) { + case RESET_TYPE_COLD: + memcpy(s->regs, cold_reset_values, sizeof(cold_reset_values)); + s->ref_ns = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + return; + } + + /* + * A small number of registers need to be reset on a core domain reset, + * but no such reset type exists yet. + */ + qemu_log_mask(LOG_UNIMP, "%s: reset type %d not implemented.", + __func__, type); +} + +static void npcm7xx_clk_init(Object *obj) +{ + NPCM7xxCLKState *s = NPCM7XX_CLK(obj); + + memory_region_init_io(&s->iomem, obj, &npcm7xx_clk_ops, s, + TYPE_NPCM7XX_CLK, 4 * KiB); + sysbus_init_mmio(&s->parent, &s->iomem); +} + +static const VMStateDescription vmstate_npcm7xx_clk = { + .name = "npcm7xx-clk", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, NPCM7xxCLKState, NPCM7XX_CLK_NR_REGS), + VMSTATE_INT64(ref_ns, NPCM7xxCLKState), + VMSTATE_END_OF_LIST(), + }, +}; + +static void npcm7xx_clk_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + QEMU_BUILD_BUG_ON(NPCM7XX_CLK_REGS_END > NPCM7XX_CLK_NR_REGS); + + dc->desc = "NPCM7xx Clock Control Registers"; + dc->vmsd = &vmstate_npcm7xx_clk; + rc->phases.enter = npcm7xx_clk_enter_reset; +} + +static const TypeInfo npcm7xx_clk_info = { + .name = TYPE_NPCM7XX_CLK, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxCLKState), + .instance_init = npcm7xx_clk_init, + .class_init = npcm7xx_clk_class_init, +}; + +static void npcm7xx_clk_register_type(void) +{ + type_register_static(&npcm7xx_clk_info); +} +type_init(npcm7xx_clk_register_type); diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_IMX', if_true: files( softmmu_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-hpdmc.c', 'milkymist-pfpu.c')) softmmu_ss.add(when: 'CONFIG_MAINSTONE', if_true: files('mst_fpga.c')) softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files( + 'npcm7xx_clk.c', 'npcm7xx_gcr.c', )) softmmu_ss.add(when: 'CONFIG_OMAP', if_true: files( diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ mos6522_set_sr_int(void) "set sr_int" mos6522_write(uint64_t addr, uint64_t val) "reg=0x%"PRIx64 " val=0x%"PRIx64 mos6522_read(uint64_t addr, unsigned val) "reg=0x%"PRIx64 " val=0x%x" +# npcm7xx_clk.c +npcm7xx_clk_read(uint64_t offset, uint32_t value) " offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 +npcm7xx_clk_write(uint64_t offset, uint32_t value) "offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 + # npcm7xx_gcr.c npcm7xx_gcr_read(uint64_t offset, uint32_t value) " offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 npcm7xx_gcr_write(uint64_t offset, uint32_t value) "offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> The NPCM730 and NPCM750 SoCs have three timer modules each holding five timers and some shared registers (e.g. interrupt status). Each timer runs at 25 MHz divided by a prescaler, and counts down from a configurable initial value to zero. When zero is reached, the interrupt flag for the timer is set, and the timer is disabled (one-shot mode) or reloaded from its initial value (periodic mode). This implementation is sufficient to boot a Linux kernel configured for NPCM750. Note that the kernel does not seem to actually turn on the interrupts. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-4-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/timer/npcm7xx_timer.h | 78 +++++ hw/timer/npcm7xx_timer.c | 543 +++++++++++++++++++++++++++++++ hw/timer/meson.build | 1 + hw/timer/trace-events | 5 + 4 files changed, 627 insertions(+) create mode 100644 include/hw/timer/npcm7xx_timer.h create mode 100644 hw/timer/npcm7xx_timer.c diff --git a/include/hw/timer/npcm7xx_timer.h b/include/hw/timer/npcm7xx_timer.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/timer/npcm7xx_timer.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Timer Controller + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ +#ifndef NPCM7XX_TIMER_H +#define NPCM7XX_TIMER_H + +#include "exec/memory.h" +#include "hw/sysbus.h" +#include "qemu/timer.h" + +/* Each Timer Module (TIM) instance holds five 25 MHz timers. */ +#define NPCM7XX_TIMERS_PER_CTRL (5) + +/* + * Number of registers in our device state structure. Don't change this without + * incrementing the version_id in the vmstate. + */ +#define NPCM7XX_TIMER_NR_REGS (0x54 / sizeof(uint32_t)) + +typedef struct NPCM7xxTimerCtrlState NPCM7xxTimerCtrlState; + +/** + * struct NPCM7xxTimer - Individual timer state. + * @irq: GIC interrupt line to fire on expiration (if enabled). + * @qtimer: QEMU timer that notifies us on expiration. + * @expires_ns: Absolute virtual expiration time. + * @remaining_ns: Remaining time until expiration if timer is paused. + * @tcsr: The Timer Control and Status Register. + * @ticr: The Timer Initial Count Register. + */ +typedef struct NPCM7xxTimer { + NPCM7xxTimerCtrlState *ctrl; + + qemu_irq irq; + QEMUTimer qtimer; + int64_t expires_ns; + int64_t remaining_ns; + + uint32_t tcsr; + uint32_t ticr; +} NPCM7xxTimer; + +/** + * struct NPCM7xxTimerCtrlState - Timer Module device state. + * @parent: System bus device. + * @iomem: Memory region through which registers are accessed. + * @tisr: The Timer Interrupt Status Register. + * @wtcr: The Watchdog Timer Control Register. + * @timer: The five individual timers managed by this module. + */ +struct NPCM7xxTimerCtrlState { + SysBusDevice parent; + + MemoryRegion iomem; + + uint32_t tisr; + uint32_t wtcr; + + NPCM7xxTimer timer[NPCM7XX_TIMERS_PER_CTRL]; +}; + +#define TYPE_NPCM7XX_TIMER "npcm7xx-timer" +#define NPCM7XX_TIMER(obj) \ + OBJECT_CHECK(NPCM7xxTimerCtrlState, (obj), TYPE_NPCM7XX_TIMER) + +#endif /* NPCM7XX_TIMER_H */ diff --git a/hw/timer/npcm7xx_timer.c b/hw/timer/npcm7xx_timer.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/timer/npcm7xx_timer.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Timer Controller + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ + +#include "qemu/osdep.h" + +#include "hw/irq.h" +#include "hw/misc/npcm7xx_clk.h" +#include "hw/timer/npcm7xx_timer.h" +#include "migration/vmstate.h" +#include "qemu/bitops.h" +#include "qemu/error-report.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/timer.h" +#include "qemu/units.h" +#include "trace.h" + +/* 32-bit register indices. */ +enum NPCM7xxTimerRegisters { + NPCM7XX_TIMER_TCSR0, + NPCM7XX_TIMER_TCSR1, + NPCM7XX_TIMER_TICR0, + NPCM7XX_TIMER_TICR1, + NPCM7XX_TIMER_TDR0, + NPCM7XX_TIMER_TDR1, + NPCM7XX_TIMER_TISR, + NPCM7XX_TIMER_WTCR, + NPCM7XX_TIMER_TCSR2, + NPCM7XX_TIMER_TCSR3, + NPCM7XX_TIMER_TICR2, + NPCM7XX_TIMER_TICR3, + NPCM7XX_TIMER_TDR2, + NPCM7XX_TIMER_TDR3, + NPCM7XX_TIMER_TCSR4 = 0x0040 / sizeof(uint32_t), + NPCM7XX_TIMER_TICR4 = 0x0048 / sizeof(uint32_t), + NPCM7XX_TIMER_TDR4 = 0x0050 / sizeof(uint32_t), + NPCM7XX_TIMER_REGS_END, +}; + +/* Register field definitions. */ +#define NPCM7XX_TCSR_CEN BIT(30) +#define NPCM7XX_TCSR_IE BIT(29) +#define NPCM7XX_TCSR_PERIODIC BIT(27) +#define NPCM7XX_TCSR_CRST BIT(26) +#define NPCM7XX_TCSR_CACT BIT(25) +#define NPCM7XX_TCSR_RSVD 0x01ffff00 +#define NPCM7XX_TCSR_PRESCALE_START 0 +#define NPCM7XX_TCSR_PRESCALE_LEN 8 + +/* + * Returns the index of timer in the tc->timer array. This can be used to + * locate the registers that belong to this timer. + */ +static int npcm7xx_timer_index(NPCM7xxTimerCtrlState *tc, NPCM7xxTimer *timer) +{ + int index = timer - tc->timer; + + g_assert(index >= 0 && index < NPCM7XX_TIMERS_PER_CTRL); + + return index; +} + +/* Return the value by which to divide the reference clock rate. */ +static uint32_t npcm7xx_tcsr_prescaler(uint32_t tcsr) +{ + return extract32(tcsr, NPCM7XX_TCSR_PRESCALE_START, + NPCM7XX_TCSR_PRESCALE_LEN) + 1; +} + +/* Convert a timer cycle count to a time interval in nanoseconds. */ +static int64_t npcm7xx_timer_count_to_ns(NPCM7xxTimer *t, uint32_t count) +{ + int64_t ns = count; + + ns *= NANOSECONDS_PER_SECOND / NPCM7XX_TIMER_REF_HZ; + ns *= npcm7xx_tcsr_prescaler(t->tcsr); + + return ns; +} + +/* Convert a time interval in nanoseconds to a timer cycle count. */ +static uint32_t npcm7xx_timer_ns_to_count(NPCM7xxTimer *t, int64_t ns) +{ + int64_t count; + + count = ns / (NANOSECONDS_PER_SECOND / NPCM7XX_TIMER_REF_HZ); + count /= npcm7xx_tcsr_prescaler(t->tcsr); + + return count; +} + +/* + * Raise the interrupt line if there's a pending interrupt and interrupts are + * enabled for this timer. If not, lower it. + */ +static void npcm7xx_timer_check_interrupt(NPCM7xxTimer *t) +{ + NPCM7xxTimerCtrlState *tc = t->ctrl; + int index = npcm7xx_timer_index(tc, t); + bool pending = (t->tcsr & NPCM7XX_TCSR_IE) && (tc->tisr & BIT(index)); + + qemu_set_irq(t->irq, pending); + trace_npcm7xx_timer_irq(DEVICE(tc)->canonical_path, index, pending); +} + +/* Start or resume the timer. */ +static void npcm7xx_timer_start(NPCM7xxTimer *t) +{ + int64_t now; + + now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + t->expires_ns = now + t->remaining_ns; + timer_mod(&t->qtimer, t->expires_ns); +} + +/* + * Called when the counter reaches zero. Sets the interrupt flag, and either + * restarts or disables the timer. + */ +static void npcm7xx_timer_reached_zero(NPCM7xxTimer *t) +{ + NPCM7xxTimerCtrlState *tc = t->ctrl; + int index = npcm7xx_timer_index(tc, t); + + tc->tisr |= BIT(index); + + if (t->tcsr & NPCM7XX_TCSR_PERIODIC) { + t->remaining_ns = npcm7xx_timer_count_to_ns(t, t->ticr); + if (t->tcsr & NPCM7XX_TCSR_CEN) { + npcm7xx_timer_start(t); + } + } else { + t->tcsr &= ~(NPCM7XX_TCSR_CEN | NPCM7XX_TCSR_CACT); + } + + npcm7xx_timer_check_interrupt(t); +} + +/* Stop counting. Record the time remaining so we can continue later. */ +static void npcm7xx_timer_pause(NPCM7xxTimer *t) +{ + int64_t now; + + timer_del(&t->qtimer); + now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + t->remaining_ns = t->expires_ns - now; + if (t->remaining_ns <= 0) { + npcm7xx_timer_reached_zero(t); + } +} + +/* + * Restart the timer from its initial value. If the timer was enabled and stays + * enabled, adjust the QEMU timer according to the new count. If the timer is + * transitioning from disabled to enabled, the caller is expected to start the + * timer later. + */ +static void npcm7xx_timer_restart(NPCM7xxTimer *t, uint32_t old_tcsr) +{ + t->remaining_ns = npcm7xx_timer_count_to_ns(t, t->ticr); + + if (old_tcsr & t->tcsr & NPCM7XX_TCSR_CEN) { + npcm7xx_timer_start(t); + } +} + +/* Register read and write handlers */ + +static uint32_t npcm7xx_timer_read_tdr(NPCM7xxTimer *t) +{ + if (t->tcsr & NPCM7XX_TCSR_CEN) { + int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + + return npcm7xx_timer_ns_to_count(t, t->expires_ns - now); + } + + return npcm7xx_timer_ns_to_count(t, t->remaining_ns); +} + +static void npcm7xx_timer_write_tcsr(NPCM7xxTimer *t, uint32_t new_tcsr) +{ + uint32_t old_tcsr = t->tcsr; + uint32_t tdr; + + if (new_tcsr & NPCM7XX_TCSR_RSVD) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: reserved bits in 0x%08x ignored\n", + __func__, new_tcsr); + new_tcsr &= ~NPCM7XX_TCSR_RSVD; + } + if (new_tcsr & NPCM7XX_TCSR_CACT) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: read-only bits in 0x%08x ignored\n", + __func__, new_tcsr); + new_tcsr &= ~NPCM7XX_TCSR_CACT; + } + if ((new_tcsr & NPCM7XX_TCSR_CRST) && (new_tcsr & NPCM7XX_TCSR_CEN)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: both CRST and CEN set; ignoring CEN.\n", + __func__); + new_tcsr &= ~NPCM7XX_TCSR_CEN; + } + + /* Calculate the value of TDR before potentially changing the prescaler. */ + tdr = npcm7xx_timer_read_tdr(t); + + t->tcsr = (t->tcsr & NPCM7XX_TCSR_CACT) | new_tcsr; + + if (npcm7xx_tcsr_prescaler(old_tcsr) != npcm7xx_tcsr_prescaler(new_tcsr)) { + /* Recalculate time remaining based on the current TDR value. */ + t->remaining_ns = npcm7xx_timer_count_to_ns(t, tdr); + if (old_tcsr & t->tcsr & NPCM7XX_TCSR_CEN) { + npcm7xx_timer_start(t); + } + } + + if ((old_tcsr ^ new_tcsr) & NPCM7XX_TCSR_IE) { + npcm7xx_timer_check_interrupt(t); + } + if (new_tcsr & NPCM7XX_TCSR_CRST) { + npcm7xx_timer_restart(t, old_tcsr); + t->tcsr &= ~NPCM7XX_TCSR_CRST; + } + if ((old_tcsr ^ new_tcsr) & NPCM7XX_TCSR_CEN) { + if (new_tcsr & NPCM7XX_TCSR_CEN) { + t->tcsr |= NPCM7XX_TCSR_CACT; + npcm7xx_timer_start(t); + } else { + t->tcsr &= ~NPCM7XX_TCSR_CACT; + npcm7xx_timer_pause(t); + } + } +} + +static void npcm7xx_timer_write_ticr(NPCM7xxTimer *t, uint32_t new_ticr) +{ + t->ticr = new_ticr; + + npcm7xx_timer_restart(t, t->tcsr); +} + +static void npcm7xx_timer_write_tisr(NPCM7xxTimerCtrlState *s, uint32_t value) +{ + int i; + + s->tisr &= ~value; + for (i = 0; i < ARRAY_SIZE(s->timer); i++) { + if (value & (1U << i)) { + npcm7xx_timer_check_interrupt(&s->timer[i]); + } + } +} + +static hwaddr npcm7xx_tcsr_index(hwaddr reg) +{ + switch (reg) { + case NPCM7XX_TIMER_TCSR0: + return 0; + case NPCM7XX_TIMER_TCSR1: + return 1; + case NPCM7XX_TIMER_TCSR2: + return 2; + case NPCM7XX_TIMER_TCSR3: + return 3; + case NPCM7XX_TIMER_TCSR4: + return 4; + default: + g_assert_not_reached(); + } +} + +static hwaddr npcm7xx_ticr_index(hwaddr reg) +{ + switch (reg) { + case NPCM7XX_TIMER_TICR0: + return 0; + case NPCM7XX_TIMER_TICR1: + return 1; + case NPCM7XX_TIMER_TICR2: + return 2; + case NPCM7XX_TIMER_TICR3: + return 3; + case NPCM7XX_TIMER_TICR4: + return 4; + default: + g_assert_not_reached(); + } +} + +static hwaddr npcm7xx_tdr_index(hwaddr reg) +{ + switch (reg) { + case NPCM7XX_TIMER_TDR0: + return 0; + case NPCM7XX_TIMER_TDR1: + return 1; + case NPCM7XX_TIMER_TDR2: + return 2; + case NPCM7XX_TIMER_TDR3: + return 3; + case NPCM7XX_TIMER_TDR4: + return 4; + default: + g_assert_not_reached(); + } +} + +static uint64_t npcm7xx_timer_read(void *opaque, hwaddr offset, unsigned size) +{ + NPCM7xxTimerCtrlState *s = opaque; + uint64_t value = 0; + hwaddr reg; + + reg = offset / sizeof(uint32_t); + switch (reg) { + case NPCM7XX_TIMER_TCSR0: + case NPCM7XX_TIMER_TCSR1: + case NPCM7XX_TIMER_TCSR2: + case NPCM7XX_TIMER_TCSR3: + case NPCM7XX_TIMER_TCSR4: + value = s->timer[npcm7xx_tcsr_index(reg)].tcsr; + break; + + case NPCM7XX_TIMER_TICR0: + case NPCM7XX_TIMER_TICR1: + case NPCM7XX_TIMER_TICR2: + case NPCM7XX_TIMER_TICR3: + case NPCM7XX_TIMER_TICR4: + value = s->timer[npcm7xx_ticr_index(reg)].ticr; + break; + + case NPCM7XX_TIMER_TDR0: + case NPCM7XX_TIMER_TDR1: + case NPCM7XX_TIMER_TDR2: + case NPCM7XX_TIMER_TDR3: + case NPCM7XX_TIMER_TDR4: + value = npcm7xx_timer_read_tdr(&s->timer[npcm7xx_tdr_index(reg)]); + break; + + case NPCM7XX_TIMER_TISR: + value = s->tisr; + break; + + case NPCM7XX_TIMER_WTCR: + value = s->wtcr; + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid offset 0x%04" HWADDR_PRIx "\n", + __func__, offset); + break; + } + + trace_npcm7xx_timer_read(DEVICE(s)->canonical_path, offset, value); + + return value; +} + +static void npcm7xx_timer_write(void *opaque, hwaddr offset, + uint64_t v, unsigned size) +{ + uint32_t reg = offset / sizeof(uint32_t); + NPCM7xxTimerCtrlState *s = opaque; + uint32_t value = v; + + trace_npcm7xx_timer_write(DEVICE(s)->canonical_path, offset, value); + + switch (reg) { + case NPCM7XX_TIMER_TCSR0: + case NPCM7XX_TIMER_TCSR1: + case NPCM7XX_TIMER_TCSR2: + case NPCM7XX_TIMER_TCSR3: + case NPCM7XX_TIMER_TCSR4: + npcm7xx_timer_write_tcsr(&s->timer[npcm7xx_tcsr_index(reg)], value); + return; + + case NPCM7XX_TIMER_TICR0: + case NPCM7XX_TIMER_TICR1: + case NPCM7XX_TIMER_TICR2: + case NPCM7XX_TIMER_TICR3: + case NPCM7XX_TIMER_TICR4: + npcm7xx_timer_write_ticr(&s->timer[npcm7xx_ticr_index(reg)], value); + return; + + case NPCM7XX_TIMER_TDR0: + case NPCM7XX_TIMER_TDR1: + case NPCM7XX_TIMER_TDR2: + case NPCM7XX_TIMER_TDR3: + case NPCM7XX_TIMER_TDR4: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: register @ 0x%04" HWADDR_PRIx " is read-only\n", + __func__, offset); + return; + + case NPCM7XX_TIMER_TISR: + npcm7xx_timer_write_tisr(s, value); + return; + + case NPCM7XX_TIMER_WTCR: + qemu_log_mask(LOG_UNIMP, "%s: WTCR write not implemented: 0x%08x\n", + __func__, value); + return; + } + + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid offset 0x%04" HWADDR_PRIx "\n", + __func__, offset); +} + +static const struct MemoryRegionOps npcm7xx_timer_ops = { + .read = npcm7xx_timer_read, + .write = npcm7xx_timer_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +/* Called when the QEMU timer expires. */ +static void npcm7xx_timer_expired(void *opaque) +{ + NPCM7xxTimer *t = opaque; + + if (t->tcsr & NPCM7XX_TCSR_CEN) { + npcm7xx_timer_reached_zero(t); + } +} + +static void npcm7xx_timer_enter_reset(Object *obj, ResetType type) +{ + NPCM7xxTimerCtrlState *s = NPCM7XX_TIMER(obj); + int i; + + for (i = 0; i < NPCM7XX_TIMERS_PER_CTRL; i++) { + NPCM7xxTimer *t = &s->timer[i]; + + timer_del(&t->qtimer); + t->expires_ns = 0; + t->remaining_ns = 0; + t->tcsr = 0x00000005; + t->ticr = 0x00000000; + } + + s->tisr = 0x00000000; + s->wtcr = 0x00000400; +} + +static void npcm7xx_timer_hold_reset(Object *obj) +{ + NPCM7xxTimerCtrlState *s = NPCM7XX_TIMER(obj); + int i; + + for (i = 0; i < NPCM7XX_TIMERS_PER_CTRL; i++) { + qemu_irq_lower(s->timer[i].irq); + } +} + +static void npcm7xx_timer_realize(DeviceState *dev, Error **errp) +{ + NPCM7xxTimerCtrlState *s = NPCM7XX_TIMER(dev); + SysBusDevice *sbd = &s->parent; + int i; + + for (i = 0; i < NPCM7XX_TIMERS_PER_CTRL; i++) { + NPCM7xxTimer *t = &s->timer[i]; + t->ctrl = s; + timer_init_ns(&t->qtimer, QEMU_CLOCK_VIRTUAL, npcm7xx_timer_expired, t); + sysbus_init_irq(sbd, &t->irq); + } + + memory_region_init_io(&s->iomem, OBJECT(s), &npcm7xx_timer_ops, s, + TYPE_NPCM7XX_TIMER, 4 * KiB); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription vmstate_npcm7xx_timer = { + .name = "npcm7xx-timer", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_TIMER(qtimer, NPCM7xxTimer), + VMSTATE_INT64(expires_ns, NPCM7xxTimer), + VMSTATE_INT64(remaining_ns, NPCM7xxTimer), + VMSTATE_UINT32(tcsr, NPCM7xxTimer), + VMSTATE_UINT32(ticr, NPCM7xxTimer), + VMSTATE_END_OF_LIST(), + }, +}; + +static const VMStateDescription vmstate_npcm7xx_timer_ctrl = { + .name = "npcm7xx-timer-ctrl", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT32(tisr, NPCM7xxTimerCtrlState), + VMSTATE_UINT32(wtcr, NPCM7xxTimerCtrlState), + VMSTATE_STRUCT_ARRAY(timer, NPCM7xxTimerCtrlState, + NPCM7XX_TIMERS_PER_CTRL, 0, vmstate_npcm7xx_timer, + NPCM7xxTimer), + VMSTATE_END_OF_LIST(), + }, +}; + +static void npcm7xx_timer_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + QEMU_BUILD_BUG_ON(NPCM7XX_TIMER_REGS_END > NPCM7XX_TIMER_NR_REGS); + + dc->desc = "NPCM7xx Timer Controller"; + dc->realize = npcm7xx_timer_realize; + dc->vmsd = &vmstate_npcm7xx_timer_ctrl; + rc->phases.enter = npcm7xx_timer_enter_reset; + rc->phases.hold = npcm7xx_timer_hold_reset; +} + +static const TypeInfo npcm7xx_timer_info = { + .name = TYPE_NPCM7XX_TIMER, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxTimerCtrlState), + .class_init = npcm7xx_timer_class_init, +}; + +static void npcm7xx_timer_register_type(void) +{ + type_register_static(&npcm7xx_timer_info); +} +type_init(npcm7xx_timer_register_type); diff --git a/hw/timer/meson.build b/hw/timer/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/meson.build +++ b/hw/timer/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_LM32', if_true: files('lm32_timer.c')) softmmu_ss.add(when: 'CONFIG_MILKYMIST', if_true: files('milkymist-sysctl.c')) softmmu_ss.add(when: 'CONFIG_MIPS_CPS', if_true: files('mips_gictimer.c')) softmmu_ss.add(when: 'CONFIG_MSF2', if_true: files('mss-timer.c')) +softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_timer.c')) softmmu_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_timer.c')) softmmu_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_gptimer.c')) softmmu_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_synctimer.c')) diff --git a/hw/timer/trace-events b/hw/timer/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/trace-events +++ b/hw/timer/trace-events @@ -XXX,XX +XXX,XX @@ cmsdk_apb_dualtimer_read(uint64_t offset, uint64_t data, unsigned size) "CMSDK A cmsdk_apb_dualtimer_write(uint64_t offset, uint64_t data, unsigned size) "CMSDK APB dualtimer write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" cmsdk_apb_dualtimer_reset(void) "CMSDK APB dualtimer: reset" +# npcm7xx_timer.c +npcm7xx_timer_read(const char *id, uint64_t offset, uint64_t value) " %s offset: 0x%04" PRIx64 " value 0x%08" PRIx64 +npcm7xx_timer_write(const char *id, uint64_t offset, uint64_t value) "%s offset: 0x%04" PRIx64 " value 0x%08" PRIx64 +npcm7xx_timer_irq(const char *id, int timer, int state) "%s timer %d state %d" + # nrf51_timer.c nrf51_timer_read(uint8_t timer_id, uint64_t addr, uint32_t value, unsigned size) "timer %u read addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u" nrf51_timer_write(uint8_t timer_id, uint64_t addr, uint32_t value, unsigned size) "timer %u write addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u" -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> The Nuvoton NPCM7xx SoC family are used to implement Baseboard Management Controllers in servers. While the family includes four SoCs, this patch implements limited support for two of them: NPCM730 (targeted for Data Center applications) and NPCM750 (targeted for Enterprise applications). This patch includes little more than the bare minimum needed to boot a Linux kernel built with NPCM7xx support in direct-kernel mode: - Two Cortex-A9 CPU cores with built-in periperhals. - Global Configuration Registers. - Clock Management. - 3 Timer Modules with 5 timers each. - 4 serial ports. The chips themselves have a lot more features, some of which will be added to the model at a later stage. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-5-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/npcm7xx.h | 85 ++++++++ hw/arm/npcm7xx.c | 407 +++++++++++++++++++++++++++++++++++++++ hw/arm/Kconfig | 5 + hw/arm/meson.build | 1 + 4 files changed, 498 insertions(+) create mode 100644 include/hw/arm/npcm7xx.h create mode 100644 hw/arm/npcm7xx.c diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx SoC family. + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ +#ifndef NPCM7XX_H +#define NPCM7XX_H + +#include "hw/boards.h" +#include "hw/cpu/a9mpcore.h" +#include "hw/misc/npcm7xx_clk.h" +#include "hw/misc/npcm7xx_gcr.h" +#include "hw/timer/npcm7xx_timer.h" +#include "target/arm/cpu.h" + +#define NPCM7XX_MAX_NUM_CPUS (2) + +/* The first half of the address space is reserved for DDR4 DRAM. */ +#define NPCM7XX_DRAM_BA (0x00000000) +#define NPCM7XX_DRAM_SZ (2 * GiB) + +/* Magic addresses for setting up direct kernel booting and SMP boot stubs. */ +#define NPCM7XX_LOADER_START (0x00000000) /* Start of SDRAM */ +#define NPCM7XX_SMP_LOADER_START (0xffff0000) /* Boot ROM */ +#define NPCM7XX_SMP_BOOTREG_ADDR (0xf080013c) /* GCR.SCRPAD */ +#define NPCM7XX_GIC_CPU_IF_ADDR (0xf03fe100) /* GIC within A9 */ + +typedef struct NPCM7xxState { + DeviceState parent; + + ARMCPU cpu[NPCM7XX_MAX_NUM_CPUS]; + A9MPPrivState a9mpcore; + + MemoryRegion sram; + MemoryRegion irom; + MemoryRegion ram3; + MemoryRegion *dram; + + NPCM7xxGCRState gcr; + NPCM7xxCLKState clk; + NPCM7xxTimerCtrlState tim[3]; +} NPCM7xxState; + +#define TYPE_NPCM7XX "npcm7xx" +#define NPCM7XX(obj) OBJECT_CHECK(NPCM7xxState, (obj), TYPE_NPCM7XX) + +#define TYPE_NPCM730 "npcm730" +#define TYPE_NPCM750 "npcm750" + +typedef struct NPCM7xxClass { + DeviceClass parent; + + /* Bitmask of modules that are permanently disabled on this chip. */ + uint32_t disabled_modules; + /* Number of CPU cores enabled in this SoC class (may be 1 or 2). */ + uint32_t num_cpus; +} NPCM7xxClass; + +#define NPCM7XX_CLASS(klass) \ + OBJECT_CLASS_CHECK(NPCM7xxClass, (klass), TYPE_NPCM7XX) +#define NPCM7XX_GET_CLASS(obj) \ + OBJECT_GET_CLASS(NPCM7xxClass, (obj), TYPE_NPCM7XX) + +/** + * npcm7xx_load_kernel - Loads memory with everything needed to boot + * @machine - The machine containing the SoC to be booted. + * @soc - The SoC containing the CPU to be booted. + * + * This will set up the ARM boot info structure for the specific NPCM7xx + * derivative and call arm_load_kernel() to set up loading of the kernel, etc. + * into memory, if requested by the user. + */ +void npcm7xx_load_kernel(MachineState *machine, NPCM7xxState *soc); + +#endif /* NPCM7XX_H */ diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx SoC family. + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ + +#include "qemu/osdep.h" + +#include "exec/address-spaces.h" +#include "hw/arm/boot.h" +#include "hw/arm/npcm7xx.h" +#include "hw/char/serial.h" +#include "hw/loader.h" +#include "hw/misc/unimp.h" +#include "hw/qdev-properties.h" +#include "qapi/error.h" +#include "qemu/units.h" +#include "sysemu/sysemu.h" + +/* + * This covers the whole MMIO space. We'll use this to catch any MMIO accesses + * that aren't handled by any device. + */ +#define NPCM7XX_MMIO_BA (0x80000000) +#define NPCM7XX_MMIO_SZ (0x7ffd0000) + +/* Core system modules. */ +#define NPCM7XX_L2C_BA (0xf03fc000) +#define NPCM7XX_CPUP_BA (0xf03fe000) +#define NPCM7XX_GCR_BA (0xf0800000) +#define NPCM7XX_CLK_BA (0xf0801000) + +/* Internal AHB SRAM */ +#define NPCM7XX_RAM3_BA (0xc0008000) +#define NPCM7XX_RAM3_SZ (4 * KiB) + +/* Memory blocks at the end of the address space */ +#define NPCM7XX_RAM2_BA (0xfffd0000) +#define NPCM7XX_RAM2_SZ (128 * KiB) +#define NPCM7XX_ROM_BA (0xffff0000) +#define NPCM7XX_ROM_SZ (64 * KiB) + +/* + * Interrupt lines going into the GIC. This does not include internal Cortex-A9 + * interrupts. + */ +enum NPCM7xxInterrupt { + NPCM7XX_UART0_IRQ = 2, + NPCM7XX_UART1_IRQ, + NPCM7XX_UART2_IRQ, + NPCM7XX_UART3_IRQ, + NPCM7XX_TIMER0_IRQ = 32, /* Timer Module 0 */ + NPCM7XX_TIMER1_IRQ, + NPCM7XX_TIMER2_IRQ, + NPCM7XX_TIMER3_IRQ, + NPCM7XX_TIMER4_IRQ, + NPCM7XX_TIMER5_IRQ, /* Timer Module 1 */ + NPCM7XX_TIMER6_IRQ, + NPCM7XX_TIMER7_IRQ, + NPCM7XX_TIMER8_IRQ, + NPCM7XX_TIMER9_IRQ, + NPCM7XX_TIMER10_IRQ, /* Timer Module 2 */ + NPCM7XX_TIMER11_IRQ, + NPCM7XX_TIMER12_IRQ, + NPCM7XX_TIMER13_IRQ, + NPCM7XX_TIMER14_IRQ, +}; + +/* Total number of GIC interrupts, including internal Cortex-A9 interrupts. */ +#define NPCM7XX_NUM_IRQ (160) + +/* Register base address for each Timer Module */ +static const hwaddr npcm7xx_tim_addr[] = { + 0xf0008000, + 0xf0009000, + 0xf000a000, +}; + +/* Register base address for each 16550 UART */ +static const hwaddr npcm7xx_uart_addr[] = { + 0xf0001000, + 0xf0002000, + 0xf0003000, + 0xf0004000, +}; + +static void npcm7xx_write_secondary_boot(ARMCPU *cpu, + const struct arm_boot_info *info) +{ + /* + * The default smpboot stub halts the secondary CPU with a 'wfi' + * instruction, but the arch/arm/mach-npcm/platsmp.c in the Linux kernel + * does not send an IPI to wake it up, so the second CPU fails to boot. So + * we need to provide our own smpboot stub that can not use 'wfi', it has + * to spin the secondary CPU until the first CPU writes to the SCRPAD reg. + */ + uint32_t smpboot[] = { + 0xe59f2018, /* ldr r2, bootreg_addr */ + 0xe3a00000, /* mov r0, #0 */ + 0xe5820000, /* str r0, [r2] */ + 0xe320f002, /* wfe */ + 0xe5921000, /* ldr r1, [r2] */ + 0xe1110001, /* tst r1, r1 */ + 0x0afffffb, /* beq <wfe> */ + 0xe12fff11, /* bx r1 */ + NPCM7XX_SMP_BOOTREG_ADDR, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(smpboot); i++) { + smpboot[i] = tswap32(smpboot[i]); + } + + rom_add_blob_fixed("smpboot", smpboot, sizeof(smpboot), + NPCM7XX_SMP_LOADER_START); +} + +static struct arm_boot_info npcm7xx_binfo = { + .loader_start = NPCM7XX_LOADER_START, + .smp_loader_start = NPCM7XX_SMP_LOADER_START, + .smp_bootreg_addr = NPCM7XX_SMP_BOOTREG_ADDR, + .gic_cpu_if_addr = NPCM7XX_GIC_CPU_IF_ADDR, + .write_secondary_boot = npcm7xx_write_secondary_boot, + .board_id = -1, +}; + +void npcm7xx_load_kernel(MachineState *machine, NPCM7xxState *soc) +{ + NPCM7xxClass *sc = NPCM7XX_GET_CLASS(soc); + + npcm7xx_binfo.ram_size = machine->ram_size; + npcm7xx_binfo.nb_cpus = sc->num_cpus; + + arm_load_kernel(&soc->cpu[0], machine, &npcm7xx_binfo); +} + +static qemu_irq npcm7xx_irq(NPCM7xxState *s, int n) +{ + return qdev_get_gpio_in(DEVICE(&s->a9mpcore), n); +} + +static void npcm7xx_init(Object *obj) +{ + NPCM7xxState *s = NPCM7XX(obj); + int i; + + for (i = 0; i < NPCM7XX_MAX_NUM_CPUS; i++) { + object_initialize_child(obj, "cpu[*]", &s->cpu[i], + ARM_CPU_TYPE_NAME("cortex-a9")); + } + + object_initialize_child(obj, "a9mpcore", &s->a9mpcore, TYPE_A9MPCORE_PRIV); + object_initialize_child(obj, "gcr", &s->gcr, TYPE_NPCM7XX_GCR); + object_property_add_alias(obj, "power-on-straps", OBJECT(&s->gcr), + "power-on-straps"); + object_initialize_child(obj, "clk", &s->clk, TYPE_NPCM7XX_CLK); + + for (i = 0; i < ARRAY_SIZE(s->tim); i++) { + object_initialize_child(obj, "tim[*]", &s->tim[i], TYPE_NPCM7XX_TIMER); + } +} + +static void npcm7xx_realize(DeviceState *dev, Error **errp) +{ + NPCM7xxState *s = NPCM7XX(dev); + NPCM7xxClass *nc = NPCM7XX_GET_CLASS(s); + int i; + + if (memory_region_size(s->dram) > NPCM7XX_DRAM_SZ) { + error_setg(errp, "%s: NPCM7xx cannot address more than %" PRIu64 + " MiB of DRAM", __func__, NPCM7XX_DRAM_SZ / MiB); + return; + } + + /* CPUs */ + for (i = 0; i < nc->num_cpus; i++) { + object_property_set_int(OBJECT(&s->cpu[i]), "mp-affinity", + arm_cpu_mp_affinity(i, NPCM7XX_MAX_NUM_CPUS), + &error_abort); + object_property_set_int(OBJECT(&s->cpu[i]), "reset-cbar", + NPCM7XX_GIC_CPU_IF_ADDR, &error_abort); + object_property_set_bool(OBJECT(&s->cpu[i]), "reset-hivecs", true, + &error_abort); + + /* Disable security extensions. */ + object_property_set_bool(OBJECT(&s->cpu[i]), "has_el3", false, + &error_abort); + + if (!qdev_realize(DEVICE(&s->cpu[i]), NULL, errp)) { + return; + } + } + + /* A9MPCORE peripherals. Can only fail if we pass bad parameters here. */ + object_property_set_int(OBJECT(&s->a9mpcore), "num-cpu", nc->num_cpus, + &error_abort); + object_property_set_int(OBJECT(&s->a9mpcore), "num-irq", NPCM7XX_NUM_IRQ, + &error_abort); + sysbus_realize(SYS_BUS_DEVICE(&s->a9mpcore), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->a9mpcore), 0, NPCM7XX_CPUP_BA); + + for (i = 0; i < nc->num_cpus; i++) { + sysbus_connect_irq(SYS_BUS_DEVICE(&s->a9mpcore), i, + qdev_get_gpio_in(DEVICE(&s->cpu[i]), ARM_CPU_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->a9mpcore), i + nc->num_cpus, + qdev_get_gpio_in(DEVICE(&s->cpu[i]), ARM_CPU_FIQ)); + } + + /* L2 cache controller */ + sysbus_create_simple("l2x0", NPCM7XX_L2C_BA, NULL); + + /* System Global Control Registers (GCR). Can fail due to user input. */ + object_property_set_int(OBJECT(&s->gcr), "disabled-modules", + nc->disabled_modules, &error_abort); + object_property_add_const_link(OBJECT(&s->gcr), "dram-mr", OBJECT(s->dram)); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->gcr), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gcr), 0, NPCM7XX_GCR_BA); + + /* Clock Control Registers (CLK). Cannot fail. */ + sysbus_realize(SYS_BUS_DEVICE(&s->clk), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->clk), 0, NPCM7XX_CLK_BA); + + /* Timer Modules (TIM). Cannot fail. */ + QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_tim_addr) != ARRAY_SIZE(s->tim)); + for (i = 0; i < ARRAY_SIZE(s->tim); i++) { + SysBusDevice *sbd = SYS_BUS_DEVICE(&s->tim[i]); + int first_irq; + int j; + + sysbus_realize(sbd, &error_abort); + sysbus_mmio_map(sbd, 0, npcm7xx_tim_addr[i]); + + first_irq = NPCM7XX_TIMER0_IRQ + i * NPCM7XX_TIMERS_PER_CTRL; + for (j = 0; j < NPCM7XX_TIMERS_PER_CTRL; j++) { + qemu_irq irq = npcm7xx_irq(s, first_irq + j); + sysbus_connect_irq(sbd, j, irq); + } + } + + /* UART0..3 (16550 compatible) */ + for (i = 0; i < ARRAY_SIZE(npcm7xx_uart_addr); i++) { + serial_mm_init(get_system_memory(), npcm7xx_uart_addr[i], 2, + npcm7xx_irq(s, NPCM7XX_UART0_IRQ + i), 115200, + serial_hd(i), DEVICE_LITTLE_ENDIAN); + } + + /* RAM2 (SRAM) */ + memory_region_init_ram(&s->sram, OBJECT(dev), "ram2", + NPCM7XX_RAM2_SZ, &error_abort); + memory_region_add_subregion(get_system_memory(), NPCM7XX_RAM2_BA, &s->sram); + + /* RAM3 (SRAM) */ + memory_region_init_ram(&s->ram3, OBJECT(dev), "ram3", + NPCM7XX_RAM3_SZ, &error_abort); + memory_region_add_subregion(get_system_memory(), NPCM7XX_RAM3_BA, &s->ram3); + + /* Internal ROM */ + memory_region_init_rom(&s->irom, OBJECT(dev), "irom", NPCM7XX_ROM_SZ, + &error_abort); + memory_region_add_subregion(get_system_memory(), NPCM7XX_ROM_BA, &s->irom); + + create_unimplemented_device("npcm7xx.shm", 0xc0001000, 4 * KiB); + create_unimplemented_device("npcm7xx.vdmx", 0xe0800000, 4 * KiB); + create_unimplemented_device("npcm7xx.pcierc", 0xe1000000, 64 * KiB); + create_unimplemented_device("npcm7xx.kcs", 0xf0007000, 4 * KiB); + create_unimplemented_device("npcm7xx.rng", 0xf000b000, 4 * KiB); + create_unimplemented_device("npcm7xx.adc", 0xf000c000, 4 * KiB); + create_unimplemented_device("npcm7xx.gfxi", 0xf000e000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[0]", 0xf0010000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[1]", 0xf0011000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[2]", 0xf0012000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[3]", 0xf0013000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[4]", 0xf0014000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[5]", 0xf0015000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[6]", 0xf0016000, 4 * KiB); + create_unimplemented_device("npcm7xx.gpio[7]", 0xf0017000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[0]", 0xf0080000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[1]", 0xf0081000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[2]", 0xf0082000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[3]", 0xf0083000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[4]", 0xf0084000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[5]", 0xf0085000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[6]", 0xf0086000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[7]", 0xf0087000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[8]", 0xf0088000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[9]", 0xf0089000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[10]", 0xf008a000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[11]", 0xf008b000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[12]", 0xf008c000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[13]", 0xf008d000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[14]", 0xf008e000, 4 * KiB); + create_unimplemented_device("npcm7xx.smbus[15]", 0xf008f000, 4 * KiB); + create_unimplemented_device("npcm7xx.espi", 0xf009f000, 4 * KiB); + create_unimplemented_device("npcm7xx.peci", 0xf0100000, 4 * KiB); + create_unimplemented_device("npcm7xx.siox[1]", 0xf0101000, 4 * KiB); + create_unimplemented_device("npcm7xx.siox[2]", 0xf0102000, 4 * KiB); + create_unimplemented_device("npcm7xx.pwm[0]", 0xf0103000, 4 * KiB); + create_unimplemented_device("npcm7xx.pwm[1]", 0xf0104000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[0]", 0xf0180000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[1]", 0xf0181000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[2]", 0xf0182000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[3]", 0xf0183000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[4]", 0xf0184000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[5]", 0xf0185000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[6]", 0xf0186000, 4 * KiB); + create_unimplemented_device("npcm7xx.mft[7]", 0xf0187000, 4 * KiB); + create_unimplemented_device("npcm7xx.pspi1", 0xf0200000, 4 * KiB); + create_unimplemented_device("npcm7xx.pspi2", 0xf0201000, 4 * KiB); + create_unimplemented_device("npcm7xx.ahbpci", 0xf0400000, 1 * MiB); + create_unimplemented_device("npcm7xx.mcphy", 0xf05f0000, 64 * KiB); + create_unimplemented_device("npcm7xx.gmac1", 0xf0802000, 8 * KiB); + create_unimplemented_device("npcm7xx.gmac2", 0xf0804000, 8 * KiB); + create_unimplemented_device("npcm7xx.ehci", 0xf0806000, 4 * KiB); + create_unimplemented_device("npcm7xx.ohci", 0xf0807000, 4 * KiB); + create_unimplemented_device("npcm7xx.vcd", 0xf0810000, 64 * KiB); + create_unimplemented_device("npcm7xx.ece", 0xf0820000, 8 * KiB); + create_unimplemented_device("npcm7xx.vdma", 0xf0822000, 8 * KiB); + create_unimplemented_device("npcm7xx.emc1", 0xf0825000, 4 * KiB); + create_unimplemented_device("npcm7xx.emc2", 0xf0826000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[0]", 0xf0830000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[1]", 0xf0831000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[2]", 0xf0832000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[3]", 0xf0833000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[4]", 0xf0834000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[5]", 0xf0835000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[6]", 0xf0836000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[7]", 0xf0837000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[8]", 0xf0838000, 4 * KiB); + create_unimplemented_device("npcm7xx.usbd[9]", 0xf0839000, 4 * KiB); + create_unimplemented_device("npcm7xx.sd", 0xf0840000, 8 * KiB); + create_unimplemented_device("npcm7xx.mmc", 0xf0842000, 8 * KiB); + create_unimplemented_device("npcm7xx.pcimbx", 0xf0848000, 512 * KiB); + create_unimplemented_device("npcm7xx.aes", 0xf0858000, 4 * KiB); + create_unimplemented_device("npcm7xx.des", 0xf0859000, 4 * KiB); + create_unimplemented_device("npcm7xx.sha", 0xf085a000, 4 * KiB); + create_unimplemented_device("npcm7xx.secacc", 0xf085b000, 4 * KiB); + create_unimplemented_device("npcm7xx.spixcs0", 0xf8000000, 16 * MiB); + create_unimplemented_device("npcm7xx.spixcs1", 0xf9000000, 16 * MiB); + create_unimplemented_device("npcm7xx.spix", 0xfb001000, 4 * KiB); +} + +static Property npcm7xx_properties[] = { + DEFINE_PROP_LINK("dram-mr", NPCM7xxState, dram, TYPE_MEMORY_REGION, + MemoryRegion *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void npcm7xx_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + + dc->realize = npcm7xx_realize; + dc->user_creatable = false; + device_class_set_props(dc, npcm7xx_properties); +} + +static void npcm730_class_init(ObjectClass *oc, void *data) +{ + NPCM7xxClass *nc = NPCM7XX_CLASS(oc); + + /* NPCM730 is optimized for data center use, so no graphics, etc. */ + nc->disabled_modules = 0x00300395; + nc->num_cpus = 2; +} + +static void npcm750_class_init(ObjectClass *oc, void *data) +{ + NPCM7xxClass *nc = NPCM7XX_CLASS(oc); + + /* NPCM750 has 2 cores and a full set of peripherals */ + nc->disabled_modules = 0x00000000; + nc->num_cpus = 2; +} + +static const TypeInfo npcm7xx_soc_types[] = { + { + .name = TYPE_NPCM7XX, + .parent = TYPE_DEVICE, + .instance_size = sizeof(NPCM7xxState), + .instance_init = npcm7xx_init, + .class_size = sizeof(NPCM7xxClass), + .class_init = npcm7xx_class_init, + .abstract = true, + }, { + .name = TYPE_NPCM730, + .parent = TYPE_NPCM7XX, + .class_init = npcm730_class_init, + }, { + .name = TYPE_NPCM750, + .parent = TYPE_NPCM7XX, + .class_init = npcm750_class_init, + }, +}; + +DEFINE_TYPES(npcm7xx_soc_types); diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config XLNX_VERSAL config NPCM7XX bool + select A9MPCORE + select ARM_GIC + select PL310 # cache controller + select SERIAL + select UNIMP config FSL_IMX25 bool diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_MICROBIT', if_true: files('microbit.c')) arm_ss.add(when: 'CONFIG_MUSICPAL', if_true: files('musicpal.c')) arm_ss.add(when: 'CONFIG_NETDUINO2', if_true: files('netduino2.c')) arm_ss.add(when: 'CONFIG_NETDUINOPLUS2', if_true: files('netduinoplus2.c')) +arm_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx.c')) arm_ss.add(when: 'CONFIG_NSERIES', if_true: files('nseries.c')) arm_ss.add(when: 'CONFIG_SX1', if_true: files('omap_sx1.c')) arm_ss.add(when: 'CONFIG_CHEETAH', if_true: files('palm.c')) -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This adds two new machines, both supported by OpenBMC: - npcm750-evb: Nuvoton NPCM750 Evaluation Board. - quanta-gsj: A board with a NPCM730 chip. They rely on the NPCM7xx SoC device to do the heavy lifting. They are almost completely identical at the moment, apart from the SoC type, which currently only changes the reset contents of one register (GCR.MDLR), but they might grow apart a bit more as more functionality is added. Both machines can boot the Linux kernel into /bin/sh. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-6-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- default-configs/arm-softmmu.mak | 1 + include/hw/arm/npcm7xx.h | 19 +++++ hw/arm/npcm7xx_boards.c | 145 ++++++++++++++++++++++++++++++++ hw/arm/meson.build | 2 +- 4 files changed, 166 insertions(+), 1 deletion(-) create mode 100644 hw/arm/npcm7xx_boards.c 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_GUMSTIX=y CONFIG_SPITZ=y CONFIG_TOSA=y CONFIG_Z2=y +CONFIG_NPCM7XX=y CONFIG_COLLIE=y CONFIG_ASPEED_SOC=y CONFIG_NETDUINO2=y diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_SMP_BOOTREG_ADDR (0xf080013c) /* GCR.SCRPAD */ #define NPCM7XX_GIC_CPU_IF_ADDR (0xf03fe100) /* GIC within A9 */ +typedef struct NPCM7xxMachine { + MachineState parent; +} NPCM7xxMachine; + +#define TYPE_NPCM7XX_MACHINE MACHINE_TYPE_NAME("npcm7xx") +#define NPCM7XX_MACHINE(obj) \ + OBJECT_CHECK(NPCM7xxMachine, (obj), TYPE_NPCM7XX_MACHINE) + +typedef struct NPCM7xxMachineClass { + MachineClass parent; + + const char *soc_type; +} NPCM7xxMachineClass; + +#define NPCM7XX_MACHINE_CLASS(klass) \ + OBJECT_CLASS_CHECK(NPCM7xxMachineClass, (klass), TYPE_NPCM7XX_MACHINE) +#define NPCM7XX_MACHINE_GET_CLASS(obj) \ + OBJECT_GET_CLASS(NPCM7xxMachineClass, (obj), TYPE_NPCM7XX_MACHINE) + typedef struct NPCM7xxState { DeviceState parent; diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/npcm7xx_boards.c @@ -XXX,XX +XXX,XX @@ +/* + * Machine definitions for boards featuring an NPCM7xx SoC. + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ + +#include "qemu/osdep.h" + +#include "exec/address-spaces.h" +#include "hw/arm/npcm7xx.h" +#include "hw/core/cpu.h" +#include "qapi/error.h" +#include "qemu/units.h" + +#define NPCM750_EVB_POWER_ON_STRAPS 0x00001ff7 +#define QUANTA_GSJ_POWER_ON_STRAPS 0x00001fff + +static void npcm7xx_connect_dram(NPCM7xxState *soc, MemoryRegion *dram) +{ + memory_region_add_subregion(get_system_memory(), NPCM7XX_DRAM_BA, dram); + + object_property_set_link(OBJECT(soc), "dram-mr", OBJECT(dram), + &error_abort); +} + +static NPCM7xxState *npcm7xx_create_soc(MachineState *machine, + uint32_t hw_straps) +{ + NPCM7xxMachineClass *nmc = NPCM7XX_MACHINE_GET_CLASS(machine); + MachineClass *mc = &nmc->parent; + Object *obj; + + if (strcmp(machine->cpu_type, mc->default_cpu_type) != 0) { + error_report("This board can only be used with %s", + mc->default_cpu_type); + exit(1); + } + + obj = object_new_with_props(nmc->soc_type, OBJECT(machine), "soc", + &error_abort, NULL); + object_property_set_uint(obj, "power-on-straps", hw_straps, &error_abort); + + return NPCM7XX(obj); +} + +static void npcm750_evb_init(MachineState *machine) +{ + NPCM7xxState *soc; + + soc = npcm7xx_create_soc(machine, NPCM750_EVB_POWER_ON_STRAPS); + npcm7xx_connect_dram(soc, machine->ram); + qdev_realize(DEVICE(soc), NULL, &error_fatal); + + npcm7xx_load_kernel(machine, soc); +} + +static void quanta_gsj_init(MachineState *machine) +{ + NPCM7xxState *soc; + + soc = npcm7xx_create_soc(machine, QUANTA_GSJ_POWER_ON_STRAPS); + npcm7xx_connect_dram(soc, machine->ram); + qdev_realize(DEVICE(soc), NULL, &error_fatal); + + npcm7xx_load_kernel(machine, soc); +} + +static void npcm7xx_set_soc_type(NPCM7xxMachineClass *nmc, const char *type) +{ + NPCM7xxClass *sc = NPCM7XX_CLASS(object_class_by_name(type)); + MachineClass *mc = MACHINE_CLASS(nmc); + + nmc->soc_type = type; + mc->default_cpus = mc->min_cpus = mc->max_cpus = sc->num_cpus; +} + +static void npcm7xx_machine_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + + mc->no_floppy = 1; + mc->no_cdrom = 1; + mc->no_parallel = 1; + mc->default_ram_id = "ram"; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a9"); +} + +/* + * Schematics: + * https://github.com/Nuvoton-Israel/nuvoton-info/blob/master/npcm7xx-poleg/evaluation-board/board_deliverables/NPCM750x_EB_ver.A1.1_COMPLETE.pdf + */ +static void npcm750_evb_machine_class_init(ObjectClass *oc, void *data) +{ + NPCM7xxMachineClass *nmc = NPCM7XX_MACHINE_CLASS(oc); + MachineClass *mc = MACHINE_CLASS(oc); + + npcm7xx_set_soc_type(nmc, TYPE_NPCM750); + + mc->desc = "Nuvoton NPCM750 Evaluation Board (Cortex A9)"; + mc->init = npcm750_evb_init; + mc->default_ram_size = 512 * MiB; +}; + +static void gsj_machine_class_init(ObjectClass *oc, void *data) +{ + NPCM7xxMachineClass *nmc = NPCM7XX_MACHINE_CLASS(oc); + MachineClass *mc = MACHINE_CLASS(oc); + + npcm7xx_set_soc_type(nmc, TYPE_NPCM730); + + mc->desc = "Quanta GSJ (Cortex A9)"; + mc->init = quanta_gsj_init; + mc->default_ram_size = 512 * MiB; +}; + +static const TypeInfo npcm7xx_machine_types[] = { + { + .name = TYPE_NPCM7XX_MACHINE, + .parent = TYPE_MACHINE, + .instance_size = sizeof(NPCM7xxMachine), + .class_size = sizeof(NPCM7xxMachineClass), + .class_init = npcm7xx_machine_class_init, + .abstract = true, + }, { + .name = MACHINE_TYPE_NAME("npcm750-evb"), + .parent = TYPE_NPCM7XX_MACHINE, + .class_init = npcm750_evb_machine_class_init, + }, { + .name = MACHINE_TYPE_NAME("quanta-gsj"), + .parent = TYPE_NPCM7XX_MACHINE, + .class_init = gsj_machine_class_init, + }, +}; + +DEFINE_TYPES(npcm7xx_machine_types) diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_MICROBIT', if_true: files('microbit.c')) arm_ss.add(when: 'CONFIG_MUSICPAL', if_true: files('musicpal.c')) arm_ss.add(when: 'CONFIG_NETDUINO2', if_true: files('netduino2.c')) arm_ss.add(when: 'CONFIG_NETDUINOPLUS2', if_true: files('netduinoplus2.c')) -arm_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx.c')) +arm_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx.c', 'npcm7xx_boards.c')) arm_ss.add(when: 'CONFIG_NSERIES', if_true: files('nseries.c')) arm_ss.add(when: 'CONFIG_SX1', if_true: files('omap_sx1.c')) arm_ss.add(when: 'CONFIG_CHEETAH', if_true: files('palm.c')) -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This is a minimalistic boot ROM written specifically for use with QEMU. It supports loading the second-stage loader from SPI flash into RAM, SMP boot, and not much else. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-7-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- .gitmodules | 3 +++ MAINTAINERS | 2 ++ pc-bios/README | 6 ++++++ pc-bios/meson.build | 1 + pc-bios/npcm7xx_bootrom.bin | Bin 0 -> 768 bytes roms/Makefile | 7 +++++++ roms/vbootrom | 1 + 7 files changed, 20 insertions(+) create mode 100644 pc-bios/npcm7xx_bootrom.bin create mode 160000 roms/vbootrom diff --git a/.gitmodules b/.gitmodules index XXXXXXX..XXXXXXX 100644 --- a/.gitmodules +++ b/.gitmodules @@ -XXX,XX +XXX,XX @@ [submodule "meson"] path = meson url = https://github.com/mesonbuild/meson/ +[submodule "roms/vbootrom"] + path = roms/vbootrom + url = https://github.com/google/vbootrom.git diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ L: qemu-arm@nongnu.org S: Supported F: hw/*/npcm7xx* F: include/hw/*/npcm7xx* +F: pc-bios/npcm7xx_bootrom.bin +F: roms/vbootrom nSeries M: Andrzej Zaborowski <balrogg@gmail.com> diff --git a/pc-bios/README b/pc-bios/README index XXXXXXX..XXXXXXX 100644 --- a/pc-bios/README +++ b/pc-bios/README @@ -XXX,XX +XXX,XX @@ ("Simplified BSD License" or "FreeBSD License", SPDX: BSD-2-Clause). OpenSBI source code also contains code reused from other projects desribed here: https://github.com/riscv/opensbi/blob/master/ThirdPartyNotices.md. + +- npcm7xx_bootrom.bin is a simplified, free (Apache 2.0) boot ROM for Nuvoton + NPCM7xx BMC devices. It currently implements the bare minimum to load, parse, + initialize and run boot images stored in SPI flash, but may grow more + features over time as needed. The source code is available at: + https://github.com/google/vbootrom diff --git a/pc-bios/meson.build b/pc-bios/meson.build index XXXXXXX..XXXXXXX 100644 --- a/pc-bios/meson.build +++ b/pc-bios/meson.build @@ -XXX,XX +XXX,XX @@ blobs = files( 'opensbi-riscv64-generic-fw_dynamic.bin', 'opensbi-riscv32-generic-fw_dynamic.elf', 'opensbi-riscv64-generic-fw_dynamic.elf', + 'npcm7xx_bootrom.bin', ) if install_blobs diff --git a/pc-bios/npcm7xx_bootrom.bin b/pc-bios/npcm7xx_bootrom.bin new file mode 100644 index XXXXXXX..XXXXXXX GIT binary patch literal 768 zcmd5)JxClu6n-<aczPbVhZYusb8wKx;7TklHfmuZdYT9pDRLwd1p_t-DFpWpyA+8( zwKtZg3J4a0aCM3_X(ZL&4g;46VVk5e$K;z;L99|b@aE%v^S$rQ8)h(Vm@cB9IYc+2 z2SHd4^NwTIGE%w>9S05p1#kf90Sj5Z(jG8}+)IZIp~iXK=T&)dL`%d-q*8aR#mq{7 z9`=6;Dr(H0ACe72R5x?!)^86Qj-X%{+!K9iZNA@*wkBAV&iZ(l^I9?!Gz=S2I_*1d zr+tTQDHjvyzKnw(hu00yX`u!Fv<!~XVcX?@kr#<B0(gGU?$W{gSsQa}CF^8Cfzp2X z@P}yDV-bci(K9XL$FU!som2C`c)?Uc&294s^}Wzumap{hg1X^jN|V25M5tQZ=<9lN z%(zKz#t-qCwHKb;HygOCpvCNL_4@1tXV1YGf^XUE_$zr{g8zWh-6gz-teI(eibtxo z?0OZI4%rU0741PgUD`2xq@H|*4=+Rs?%N)Ox5G+q>C;DilBe_YlkeSUVHA-crNk+k jtiF_MudA<CB(}8|fqYwCf3re&=&@_s761P#-ID$TwgmBa literal 0 HcmV?d00001 diff --git a/roms/Makefile b/roms/Makefile index XXXXXXX..XXXXXXX 100644 --- a/roms/Makefile +++ b/roms/Makefile @@ -XXX,XX +XXX,XX @@ find-cross-gcc = $(firstword $(wildcard $(patsubst %ld,%gcc,$(call find-cross-ld # finally strip off path + toolname so we get the prefix find-cross-prefix = $(subst gcc,,$(notdir $(call find-cross-gcc,$(1)))) +arm_cross_prefix := $(call find-cross-prefix,arm) powerpc64_cross_prefix := $(call find-cross-prefix,powerpc64) powerpc_cross_prefix := $(call find-cross-prefix,powerpc) x86_64_cross_prefix := $(call find-cross-prefix,x86_64) @@ -XXX,XX +XXX,XX @@ default help: @echo " skiboot -- update skiboot.lid" @echo " u-boot.e500 -- update u-boot.e500" @echo " u-boot.sam460 -- update u-boot.sam460" + @echo " npcm7xx_bootrom -- update vbootrom for npcm7xx" @echo " efi -- update UEFI (edk2) platform firmware" @echo " opensbi32-generic -- update OpenSBI for 32-bit generic machine" @echo " opensbi64-generic -- update OpenSBI for 64-bit generic machine" @@ -XXX,XX +XXX,XX @@ bios-microvm: $(MAKE) -C qboot cp qboot/bios.bin ../pc-bios/bios-microvm.bin +npcm7xx_bootrom: + $(MAKE) -C vbootrom CROSS_COMPILE=$(arm_cross_prefix) + cp vbootrom/npcm7xx_bootrom.bin ../pc-bios/npcm7xx_bootrom.bin + clean: rm -rf seabios/.config seabios/out seabios/builds $(MAKE) -C sgabios clean @@ -XXX,XX +XXX,XX @@ clean: $(MAKE) -f Makefile.edk2 clean $(MAKE) -C opensbi clean $(MAKE) -C qboot clean + $(MAKE) -C vbootrom clean diff --git a/roms/vbootrom b/roms/vbootrom new file mode 160000 index XXXXXXX..XXXXXXX --- /dev/null +++ b/roms/vbootrom @@ -0,0 +1 @@ +Subproject commit 0c37a43527f0ee2b9584e7fb2fdc805e902635ac -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> If a -bios option is specified on the command line, load the image into the internal ROM memory region, which contains the first instructions run by the CPU after reset. If -bios is not specified, the vbootrom included with qemu is loaded by default. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-8-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/npcm7xx_boards.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx_boards.c +++ b/hw/arm/npcm7xx_boards.c @@ -XXX,XX +XXX,XX @@ #include "exec/address-spaces.h" #include "hw/arm/npcm7xx.h" #include "hw/core/cpu.h" +#include "hw/loader.h" #include "qapi/error.h" +#include "qemu-common.h" #include "qemu/units.h" +#include "sysemu/sysemu.h" #define NPCM750_EVB_POWER_ON_STRAPS 0x00001ff7 #define QUANTA_GSJ_POWER_ON_STRAPS 0x00001fff +static const char npcm7xx_default_bootrom[] = "npcm7xx_bootrom.bin"; + +static void npcm7xx_load_bootrom(MachineState *machine, NPCM7xxState *soc) +{ + g_autofree char *filename = NULL; + int ret; + + if (!bios_name) { + bios_name = npcm7xx_default_bootrom; + } + + filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name); + if (!filename) { + error_report("Could not find ROM image '%s'", bios_name); + if (!machine->kernel_filename) { + /* We can't boot without a bootrom or a kernel image. */ + exit(1); + } + return; + } + ret = load_image_mr(filename, &soc->irom); + if (ret < 0) { + error_report("Failed to load ROM image '%s'", filename); + exit(1); + } +} + static void npcm7xx_connect_dram(NPCM7xxState *soc, MemoryRegion *dram) { memory_region_add_subregion(get_system_memory(), NPCM7XX_DRAM_BA, dram); @@ -XXX,XX +XXX,XX @@ static void npcm750_evb_init(MachineState *machine) npcm7xx_connect_dram(soc, machine->ram); qdev_realize(DEVICE(soc), NULL, &error_fatal); + npcm7xx_load_bootrom(machine, soc); npcm7xx_load_kernel(machine, soc); } @@ -XXX,XX +XXX,XX @@ static void quanta_gsj_init(MachineState *machine) npcm7xx_connect_dram(soc, machine->ram); qdev_realize(DEVICE(soc), NULL, &error_fatal); + npcm7xx_load_bootrom(machine, soc); npcm7xx_load_kernel(machine, soc); } -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This supports reading and writing OTP fuses and keys. Only fuse reading has been tested. Protection is not implemented. Reviewed-by: Avi Fishman <avi.fishman@nuvoton.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-9-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/npcm7xx.h | 3 + include/hw/nvram/npcm7xx_otp.h | 79 ++++++ hw/arm/npcm7xx.c | 29 +++ hw/nvram/npcm7xx_otp.c | 440 +++++++++++++++++++++++++++++++++ hw/nvram/meson.build | 1 + 5 files changed, 552 insertions(+) create mode 100644 include/hw/nvram/npcm7xx_otp.h create mode 100644 hw/nvram/npcm7xx_otp.c diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #include "hw/cpu/a9mpcore.h" #include "hw/misc/npcm7xx_clk.h" #include "hw/misc/npcm7xx_gcr.h" +#include "hw/nvram/npcm7xx_otp.h" #include "hw/timer/npcm7xx_timer.h" #include "target/arm/cpu.h" @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { NPCM7xxGCRState gcr; NPCM7xxCLKState clk; NPCM7xxTimerCtrlState tim[3]; + NPCM7xxOTPState key_storage; + NPCM7xxOTPState fuse_array; } NPCM7xxState; #define TYPE_NPCM7XX "npcm7xx" diff --git a/include/hw/nvram/npcm7xx_otp.h b/include/hw/nvram/npcm7xx_otp.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/nvram/npcm7xx_otp.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx OTP (Fuse Array) Interface + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ +#ifndef NPCM7XX_OTP_H +#define NPCM7XX_OTP_H + +#include "exec/memory.h" +#include "hw/sysbus.h" + +/* Each OTP module holds 8192 bits of one-time programmable storage */ +#define NPCM7XX_OTP_ARRAY_BITS (8192) +#define NPCM7XX_OTP_ARRAY_BYTES (NPCM7XX_OTP_ARRAY_BITS / BITS_PER_BYTE) + +/* Fuse array offsets */ +#define NPCM7XX_FUSE_FUSTRAP (0) +#define NPCM7XX_FUSE_CP_FUSTRAP (12) +#define NPCM7XX_FUSE_DAC_CALIB (16) +#define NPCM7XX_FUSE_ADC_CALIB (24) +#define NPCM7XX_FUSE_DERIVATIVE (64) +#define NPCM7XX_FUSE_TEST_SIG (72) +#define NPCM7XX_FUSE_DIE_LOCATION (74) +#define NPCM7XX_FUSE_GP1 (80) +#define NPCM7XX_FUSE_GP2 (128) + +/* + * Number of registers in our device state structure. Don't change this without + * incrementing the version_id in the vmstate. + */ +#define NPCM7XX_OTP_NR_REGS (0x18 / sizeof(uint32_t)) + +/** + * struct NPCM7xxOTPState - Device state for one OTP module. + * @parent: System bus device. + * @mmio: Memory region through which registers are accessed. + * @regs: Register contents. + * @array: OTP storage array. + */ +typedef struct NPCM7xxOTPState { + SysBusDevice parent; + + MemoryRegion mmio; + uint32_t regs[NPCM7XX_OTP_NR_REGS]; + uint8_t array[NPCM7XX_OTP_ARRAY_BYTES]; +} NPCM7xxOTPState; + +#define TYPE_NPCM7XX_OTP "npcm7xx-otp" +#define NPCM7XX_OTP(obj) OBJECT_CHECK(NPCM7xxOTPState, (obj), TYPE_NPCM7XX_OTP) + +#define TYPE_NPCM7XX_KEY_STORAGE "npcm7xx-key-storage" +#define TYPE_NPCM7XX_FUSE_ARRAY "npcm7xx-fuse-array" + +typedef struct NPCM7xxOTPClass NPCM7xxOTPClass; + +/** + * npcm7xx_otp_array_write - ECC encode and write data to OTP array. + * @s: OTP module. + * @data: Data to be encoded and written. + * @offset: Offset of first byte to be written in the OTP array. + * @len: Number of bytes before ECC encoding. + * + * Each nibble of data is encoded into a byte, so the number of bytes written + * to the array will be @len * 2. + */ +extern void npcm7xx_otp_array_write(NPCM7xxOTPState *s, const void *data, + unsigned int offset, unsigned int len); + +#endif /* NPCM7XX_OTP_H */ diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_MMIO_BA (0x80000000) #define NPCM7XX_MMIO_SZ (0x7ffd0000) +/* OTP key storage and fuse strap array */ +#define NPCM7XX_OTP1_BA (0xf0189000) +#define NPCM7XX_OTP2_BA (0xf018a000) + /* Core system modules. */ #define NPCM7XX_L2C_BA (0xf03fc000) #define NPCM7XX_CPUP_BA (0xf03fe000) @@ -XXX,XX +XXX,XX @@ void npcm7xx_load_kernel(MachineState *machine, NPCM7xxState *soc) arm_load_kernel(&soc->cpu[0], machine, &npcm7xx_binfo); } +static void npcm7xx_init_fuses(NPCM7xxState *s) +{ + NPCM7xxClass *nc = NPCM7XX_GET_CLASS(s); + uint32_t value; + + /* + * The initial mask of disabled modules indicates the chip derivative (e.g. + * NPCM750 or NPCM730). + */ + value = tswap32(nc->disabled_modules); + npcm7xx_otp_array_write(&s->fuse_array, &value, NPCM7XX_FUSE_DERIVATIVE, + sizeof(value)); +} + static qemu_irq npcm7xx_irq(NPCM7xxState *s, int n) { return qdev_get_gpio_in(DEVICE(&s->a9mpcore), n); @@ -XXX,XX +XXX,XX @@ static void npcm7xx_init(Object *obj) object_property_add_alias(obj, "power-on-straps", OBJECT(&s->gcr), "power-on-straps"); object_initialize_child(obj, "clk", &s->clk, TYPE_NPCM7XX_CLK); + object_initialize_child(obj, "otp1", &s->key_storage, + TYPE_NPCM7XX_KEY_STORAGE); + object_initialize_child(obj, "otp2", &s->fuse_array, + TYPE_NPCM7XX_FUSE_ARRAY); for (i = 0; i < ARRAY_SIZE(s->tim); i++) { object_initialize_child(obj, "tim[*]", &s->tim[i], TYPE_NPCM7XX_TIMER); @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->clk), &error_abort); sysbus_mmio_map(SYS_BUS_DEVICE(&s->clk), 0, NPCM7XX_CLK_BA); + /* OTP key storage and fuse strap array. Cannot fail. */ + sysbus_realize(SYS_BUS_DEVICE(&s->key_storage), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->key_storage), 0, NPCM7XX_OTP1_BA); + sysbus_realize(SYS_BUS_DEVICE(&s->fuse_array), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->fuse_array), 0, NPCM7XX_OTP2_BA); + npcm7xx_init_fuses(s); + /* Timer Modules (TIM). Cannot fail. */ QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_tim_addr) != ARRAY_SIZE(s->tim)); for (i = 0; i < ARRAY_SIZE(s->tim); i++) { diff --git a/hw/nvram/npcm7xx_otp.c b/hw/nvram/npcm7xx_otp.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/nvram/npcm7xx_otp.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx OTP (Fuse Array) Interface + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ + +#include "qemu/osdep.h" + +#include "hw/nvram/npcm7xx_otp.h" +#include "migration/vmstate.h" +#include "qapi/error.h" +#include "qemu/bitops.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/units.h" + +/* Each module has 4 KiB of register space. Only a fraction of it is used. */ +#define NPCM7XX_OTP_REGS_SIZE (4 * KiB) + +/* 32-bit register indices. */ +typedef enum NPCM7xxOTPRegister { + NPCM7XX_OTP_FST, + NPCM7XX_OTP_FADDR, + NPCM7XX_OTP_FDATA, + NPCM7XX_OTP_FCFG, + /* Offset 0x10 is FKEYIND in OTP1, FUSTRAP in OTP2 */ + NPCM7XX_OTP_FKEYIND = 0x0010 / sizeof(uint32_t), + NPCM7XX_OTP_FUSTRAP = 0x0010 / sizeof(uint32_t), + NPCM7XX_OTP_FCTL, + NPCM7XX_OTP_REGS_END, +} NPCM7xxOTPRegister; + +/* Register field definitions. */ +#define FST_RIEN BIT(2) +#define FST_RDST BIT(1) +#define FST_RDY BIT(0) +#define FST_RO_MASK (FST_RDST | FST_RDY) + +#define FADDR_BYTEADDR(rv) extract32((rv), 0, 10) +#define FADDR_BITPOS(rv) extract32((rv), 10, 3) + +#define FDATA_CLEAR 0x00000001 + +#define FCFG_FDIS BIT(31) +#define FCFG_FCFGLK_MASK 0x00ff0000 + +#define FCTL_PROG_CMD1 0x00000001 +#define FCTL_PROG_CMD2 0xbf79e5d0 +#define FCTL_READ_CMD 0x00000002 + +/** + * struct NPCM7xxOTPClass - OTP module class. + * @parent: System bus device class. + * @mmio_ops: MMIO register operations for this type of module. + * + * The two OTP modules (key-storage and fuse-array) have slightly different + * behavior, so we give them different MMIO register operations. + */ +struct NPCM7xxOTPClass { + SysBusDeviceClass parent; + + const MemoryRegionOps *mmio_ops; +}; + +#define NPCM7XX_OTP_CLASS(klass) \ + OBJECT_CLASS_CHECK(NPCM7xxOTPClass, (klass), TYPE_NPCM7XX_OTP) +#define NPCM7XX_OTP_GET_CLASS(obj) \ + OBJECT_GET_CLASS(NPCM7xxOTPClass, (obj), TYPE_NPCM7XX_OTP) + +static uint8_t ecc_encode_nibble(uint8_t n) +{ + uint8_t result = n; + + result |= (((n >> 0) & 1) ^ ((n >> 1) & 1)) << 4; + result |= (((n >> 2) & 1) ^ ((n >> 3) & 1)) << 5; + result |= (((n >> 0) & 1) ^ ((n >> 2) & 1)) << 6; + result |= (((n >> 1) & 1) ^ ((n >> 3) & 1)) << 7; + + return result; +} + +void npcm7xx_otp_array_write(NPCM7xxOTPState *s, const void *data, + unsigned int offset, unsigned int len) +{ + const uint8_t *src = data; + uint8_t *dst = &s->array[offset]; + + while (len-- > 0) { + uint8_t c = *src++; + + *dst++ = ecc_encode_nibble(extract8(c, 0, 4)); + *dst++ = ecc_encode_nibble(extract8(c, 4, 4)); + } +} + +/* Common register read handler for both OTP classes. */ +static uint64_t npcm7xx_otp_read(NPCM7xxOTPState *s, NPCM7xxOTPRegister reg) +{ + uint32_t value = 0; + + switch (reg) { + case NPCM7XX_OTP_FST: + case NPCM7XX_OTP_FADDR: + case NPCM7XX_OTP_FDATA: + case NPCM7XX_OTP_FCFG: + value = s->regs[reg]; + break; + + case NPCM7XX_OTP_FCTL: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: read from write-only FCTL register\n", + DEVICE(s)->canonical_path); + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: read from invalid offset 0x%zx\n", + DEVICE(s)->canonical_path, reg * sizeof(uint32_t)); + break; + } + + return value; +} + +/* Read a byte from the OTP array into the data register. */ +static void npcm7xx_otp_read_array(NPCM7xxOTPState *s) +{ + uint32_t faddr = s->regs[NPCM7XX_OTP_FADDR]; + + s->regs[NPCM7XX_OTP_FDATA] = s->array[FADDR_BYTEADDR(faddr)]; + s->regs[NPCM7XX_OTP_FST] |= FST_RDST | FST_RDY; +} + +/* Program a byte from the data register into the OTP array. */ +static void npcm7xx_otp_program_array(NPCM7xxOTPState *s) +{ + uint32_t faddr = s->regs[NPCM7XX_OTP_FADDR]; + + /* Bits can only go 0->1, never 1->0. */ + s->array[FADDR_BYTEADDR(faddr)] |= (1U << FADDR_BITPOS(faddr)); + s->regs[NPCM7XX_OTP_FST] |= FST_RDST | FST_RDY; +} + +/* Compute the next value of the FCFG register. */ +static uint32_t npcm7xx_otp_compute_fcfg(uint32_t cur_value, uint32_t new_value) +{ + uint32_t lock_mask; + uint32_t value; + + /* + * FCFGLK holds sticky bits 16..23, indicating which bits in FPRGLK (8..15) + * and FRDLK (0..7) that are read-only. + */ + lock_mask = (cur_value & FCFG_FCFGLK_MASK) >> 8; + lock_mask |= lock_mask >> 8; + /* FDIS and FCFGLK bits are sticky (write 1 to set; can't clear). */ + value = cur_value & (FCFG_FDIS | FCFG_FCFGLK_MASK); + /* Preserve read-only bits in FPRGLK and FRDLK */ + value |= cur_value & lock_mask; + /* Set all bits that aren't read-only. */ + value |= new_value & ~lock_mask; + + return value; +} + +/* Common register write handler for both OTP classes. */ +static void npcm7xx_otp_write(NPCM7xxOTPState *s, NPCM7xxOTPRegister reg, + uint32_t value) +{ + switch (reg) { + case NPCM7XX_OTP_FST: + /* RDST is cleared by writing 1 to it. */ + if (value & FST_RDST) { + s->regs[NPCM7XX_OTP_FST] &= ~FST_RDST; + } + /* Preserve read-only and write-one-to-clear bits */ + value &= ~FST_RO_MASK; + value |= s->regs[NPCM7XX_OTP_FST] & FST_RO_MASK; + break; + + case NPCM7XX_OTP_FADDR: + break; + + case NPCM7XX_OTP_FDATA: + /* + * This register is cleared by writing a magic value to it; no other + * values can be written. + */ + if (value == FDATA_CLEAR) { + value = 0; + } else { + value = s->regs[NPCM7XX_OTP_FDATA]; + } + break; + + case NPCM7XX_OTP_FCFG: + value = npcm7xx_otp_compute_fcfg(s->regs[NPCM7XX_OTP_FCFG], value); + break; + + case NPCM7XX_OTP_FCTL: + switch (value) { + case FCTL_READ_CMD: + npcm7xx_otp_read_array(s); + break; + + case FCTL_PROG_CMD1: + /* + * Programming requires writing two separate magic values to this + * register; this is the first one. Just store it so it can be + * verified later when the second magic value is received. + */ + break; + + case FCTL_PROG_CMD2: + /* + * Only initiate programming if we received the first half of the + * command immediately before this one. + */ + if (s->regs[NPCM7XX_OTP_FCTL] == FCTL_PROG_CMD1) { + npcm7xx_otp_program_array(s); + } + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: unrecognized FCNTL value 0x%" PRIx32 "\n", + DEVICE(s)->canonical_path, value); + break; + } + if (value != FCTL_PROG_CMD1) { + value = 0; + } + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: write to invalid offset 0x%zx\n", + DEVICE(s)->canonical_path, reg * sizeof(uint32_t)); + return; + } + + s->regs[reg] = value; +} + +/* Register read handler specific to the fuse array OTP module. */ +static uint64_t npcm7xx_fuse_array_read(void *opaque, hwaddr addr, + unsigned int size) +{ + NPCM7xxOTPRegister reg = addr / sizeof(uint32_t); + NPCM7xxOTPState *s = opaque; + uint32_t value; + + /* + * Only the Fuse Strap register needs special handling; all other registers + * work the same way for both kinds of OTP modules. + */ + if (reg != NPCM7XX_OTP_FUSTRAP) { + value = npcm7xx_otp_read(s, reg); + } else { + /* FUSTRAP is stored as three copies in the OTP array. */ + uint32_t fustrap[3]; + + memcpy(fustrap, &s->array[0], sizeof(fustrap)); + + /* Determine value by a majority vote on each bit. */ + value = (fustrap[0] & fustrap[1]) | (fustrap[0] & fustrap[2]) | + (fustrap[1] & fustrap[2]); + } + + return value; +} + +/* Register write handler specific to the fuse array OTP module. */ +static void npcm7xx_fuse_array_write(void *opaque, hwaddr addr, uint64_t v, + unsigned int size) +{ + NPCM7xxOTPRegister reg = addr / sizeof(uint32_t); + NPCM7xxOTPState *s = opaque; + + /* + * The Fuse Strap register is read-only. Other registers are handled by + * common code. + */ + if (reg != NPCM7XX_OTP_FUSTRAP) { + npcm7xx_otp_write(s, reg, v); + } +} + +static const MemoryRegionOps npcm7xx_fuse_array_ops = { + .read = npcm7xx_fuse_array_read, + .write = npcm7xx_fuse_array_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +/* Register read handler specific to the key storage OTP module. */ +static uint64_t npcm7xx_key_storage_read(void *opaque, hwaddr addr, + unsigned int size) +{ + NPCM7xxOTPRegister reg = addr / sizeof(uint32_t); + NPCM7xxOTPState *s = opaque; + + /* + * Only the Fuse Key Index register needs special handling; all other + * registers work the same way for both kinds of OTP modules. + */ + if (reg != NPCM7XX_OTP_FKEYIND) { + return npcm7xx_otp_read(s, reg); + } + + qemu_log_mask(LOG_UNIMP, "%s: FKEYIND is not implemented\n", __func__); + + return s->regs[NPCM7XX_OTP_FKEYIND]; +} + +/* Register write handler specific to the key storage OTP module. */ +static void npcm7xx_key_storage_write(void *opaque, hwaddr addr, uint64_t v, + unsigned int size) +{ + NPCM7xxOTPRegister reg = addr / sizeof(uint32_t); + NPCM7xxOTPState *s = opaque; + + /* + * Only the Fuse Key Index register needs special handling; all other + * registers work the same way for both kinds of OTP modules. + */ + if (reg != NPCM7XX_OTP_FKEYIND) { + npcm7xx_otp_write(s, reg, v); + return; + } + + qemu_log_mask(LOG_UNIMP, "%s: FKEYIND is not implemented\n", __func__); + + s->regs[NPCM7XX_OTP_FKEYIND] = v; +} + +static const MemoryRegionOps npcm7xx_key_storage_ops = { + .read = npcm7xx_key_storage_read, + .write = npcm7xx_key_storage_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void npcm7xx_otp_enter_reset(Object *obj, ResetType type) +{ + NPCM7xxOTPState *s = NPCM7XX_OTP(obj); + + memset(s->regs, 0, sizeof(s->regs)); + + s->regs[NPCM7XX_OTP_FST] = 0x00000001; + s->regs[NPCM7XX_OTP_FCFG] = 0x20000000; +} + +static void npcm7xx_otp_realize(DeviceState *dev, Error **errp) +{ + NPCM7xxOTPClass *oc = NPCM7XX_OTP_GET_CLASS(dev); + NPCM7xxOTPState *s = NPCM7XX_OTP(dev); + SysBusDevice *sbd = &s->parent; + + memset(s->array, 0, sizeof(s->array)); + + memory_region_init_io(&s->mmio, OBJECT(s), oc->mmio_ops, s, "regs", + NPCM7XX_OTP_REGS_SIZE); + sysbus_init_mmio(sbd, &s->mmio); +} + +static const VMStateDescription vmstate_npcm7xx_otp = { + .name = "npcm7xx-otp", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, NPCM7xxOTPState, NPCM7XX_OTP_NR_REGS), + VMSTATE_UINT8_ARRAY(array, NPCM7xxOTPState, NPCM7XX_OTP_ARRAY_BYTES), + VMSTATE_END_OF_LIST(), + }, +}; + +static void npcm7xx_otp_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + QEMU_BUILD_BUG_ON(NPCM7XX_OTP_REGS_END > NPCM7XX_OTP_NR_REGS); + + dc->realize = npcm7xx_otp_realize; + dc->vmsd = &vmstate_npcm7xx_otp; + rc->phases.enter = npcm7xx_otp_enter_reset; +} + +static void npcm7xx_key_storage_class_init(ObjectClass *klass, void *data) +{ + NPCM7xxOTPClass *oc = NPCM7XX_OTP_CLASS(klass); + + oc->mmio_ops = &npcm7xx_key_storage_ops; +} + +static void npcm7xx_fuse_array_class_init(ObjectClass *klass, void *data) +{ + NPCM7xxOTPClass *oc = NPCM7XX_OTP_CLASS(klass); + + oc->mmio_ops = &npcm7xx_fuse_array_ops; +} + +static const TypeInfo npcm7xx_otp_types[] = { + { + .name = TYPE_NPCM7XX_OTP, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxOTPState), + .class_size = sizeof(NPCM7xxOTPClass), + .class_init = npcm7xx_otp_class_init, + .abstract = true, + }, + { + .name = TYPE_NPCM7XX_KEY_STORAGE, + .parent = TYPE_NPCM7XX_OTP, + .class_init = npcm7xx_key_storage_class_init, + }, + { + .name = TYPE_NPCM7XX_FUSE_ARRAY, + .parent = TYPE_NPCM7XX_OTP, + .class_init = npcm7xx_fuse_array_class_init, + }, +}; +DEFINE_TYPES(npcm7xx_otp_types); diff --git a/hw/nvram/meson.build b/hw/nvram/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/meson.build +++ b/hw/nvram/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_DS1225Y', if_true: files('ds1225y.c')) softmmu_ss.add(when: 'CONFIG_NMC93XX_EEPROM', if_true: files('eeprom93xx.c')) softmmu_ss.add(when: 'CONFIG_AT24C', if_true: files('eeprom_at24c.c')) softmmu_ss.add(when: 'CONFIG_MAC_NVRAM', if_true: files('mac_nvram.c')) +softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_otp.c')) softmmu_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_nvm.c')) specific_ss.add(when: 'CONFIG_PSERIES', if_true: files('spapr_nvram.c')) -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This just implements the bare minimum to cause the boot block to skip memory initialization. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-10-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/npcm7xx.h | 2 + include/hw/mem/npcm7xx_mc.h | 36 ++++++++++++++++ hw/arm/npcm7xx.c | 6 +++ hw/mem/npcm7xx_mc.c | 84 +++++++++++++++++++++++++++++++++++++ hw/mem/meson.build | 1 + 5 files changed, 129 insertions(+) create mode 100644 include/hw/mem/npcm7xx_mc.h create mode 100644 hw/mem/npcm7xx_mc.c diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/cpu/a9mpcore.h" +#include "hw/mem/npcm7xx_mc.h" #include "hw/misc/npcm7xx_clk.h" #include "hw/misc/npcm7xx_gcr.h" #include "hw/nvram/npcm7xx_otp.h" @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { NPCM7xxTimerCtrlState tim[3]; NPCM7xxOTPState key_storage; NPCM7xxOTPState fuse_array; + NPCM7xxMCState mc; } NPCM7xxState; #define TYPE_NPCM7XX "npcm7xx" diff --git a/include/hw/mem/npcm7xx_mc.h b/include/hw/mem/npcm7xx_mc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/mem/npcm7xx_mc.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Memory Controller stub + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ +#ifndef NPCM7XX_MC_H +#define NPCM7XX_MC_H + +#include "exec/memory.h" +#include "hw/sysbus.h" + +/** + * struct NPCM7xxMCState - Device state for the memory controller. + * @parent: System bus device. + * @mmio: Memory region through which registers are accessed. + */ +typedef struct NPCM7xxMCState { + SysBusDevice parent; + + MemoryRegion mmio; +} NPCM7xxMCState; + +#define TYPE_NPCM7XX_MC "npcm7xx-mc" +#define NPCM7XX_MC(obj) OBJECT_CHECK(NPCM7xxMCState, (obj), TYPE_NPCM7XX_MC) + +#endif /* NPCM7XX_MC_H */ diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_CPUP_BA (0xf03fe000) #define NPCM7XX_GCR_BA (0xf0800000) #define NPCM7XX_CLK_BA (0xf0801000) +#define NPCM7XX_MC_BA (0xf0824000) /* Internal AHB SRAM */ #define NPCM7XX_RAM3_BA (0xc0008000) @@ -XXX,XX +XXX,XX @@ static void npcm7xx_init(Object *obj) TYPE_NPCM7XX_KEY_STORAGE); object_initialize_child(obj, "otp2", &s->fuse_array, TYPE_NPCM7XX_FUSE_ARRAY); + object_initialize_child(obj, "mc", &s->mc, TYPE_NPCM7XX_MC); for (i = 0; i < ARRAY_SIZE(s->tim); i++) { object_initialize_child(obj, "tim[*]", &s->tim[i], TYPE_NPCM7XX_TIMER); @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->fuse_array), 0, NPCM7XX_OTP2_BA); npcm7xx_init_fuses(s); + /* Fake Memory Controller (MC). Cannot fail. */ + sysbus_realize(SYS_BUS_DEVICE(&s->mc), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->mc), 0, NPCM7XX_MC_BA); + /* Timer Modules (TIM). Cannot fail. */ QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_tim_addr) != ARRAY_SIZE(s->tim)); for (i = 0; i < ARRAY_SIZE(s->tim); i++) { diff --git a/hw/mem/npcm7xx_mc.c b/hw/mem/npcm7xx_mc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/mem/npcm7xx_mc.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Memory Controller stub + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ + +#include "qemu/osdep.h" + +#include "hw/mem/npcm7xx_mc.h" +#include "qapi/error.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/units.h" + +#define NPCM7XX_MC_REGS_SIZE (4 * KiB) + +static uint64_t npcm7xx_mc_read(void *opaque, hwaddr addr, unsigned int size) +{ + /* + * If bits 8..11 @ offset 0 are not zero, the boot block thinks the memory + * controller has already been initialized and will skip DDR training. + */ + if (addr == 0) { + return 0x100; + } + + qemu_log_mask(LOG_UNIMP, "%s: mostly unimplemented\n", __func__); + + return 0; +} + +static void npcm7xx_mc_write(void *opaque, hwaddr addr, uint64_t v, + unsigned int size) +{ + qemu_log_mask(LOG_UNIMP, "%s: mostly unimplemented\n", __func__); +} + +static const MemoryRegionOps npcm7xx_mc_ops = { + .read = npcm7xx_mc_read, + .write = npcm7xx_mc_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void npcm7xx_mc_realize(DeviceState *dev, Error **errp) +{ + NPCM7xxMCState *s = NPCM7XX_MC(dev); + + memory_region_init_io(&s->mmio, OBJECT(s), &npcm7xx_mc_ops, s, "regs", + NPCM7XX_MC_REGS_SIZE); + sysbus_init_mmio(&s->parent, &s->mmio); +} + +static void npcm7xx_mc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->desc = "NPCM7xx Memory Controller stub"; + dc->realize = npcm7xx_mc_realize; +} + +static const TypeInfo npcm7xx_mc_types[] = { + { + .name = TYPE_NPCM7XX_MC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxMCState), + .class_init = npcm7xx_mc_class_init, + }, +}; +DEFINE_TYPES(npcm7xx_mc_types); diff --git a/hw/mem/meson.build b/hw/mem/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/mem/meson.build +++ b/hw/mem/meson.build @@ -XXX,XX +XXX,XX @@ mem_ss = ss.source_set() mem_ss.add(files('memory-device.c')) mem_ss.add(when: 'CONFIG_DIMM', if_true: files('pc-dimm.c')) +mem_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_mc.c')) mem_ss.add(when: 'CONFIG_NVDIMM', if_true: files('nvdimm.c')) softmmu_ss.add_all(when: 'CONFIG_MEM_DEVICE', if_true: mem_ss) -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This implements a device model for the NPCM7xx SPI flash controller. Direct reads and writes, and user-mode transactions have been tested in various modes. Protection features are not implemented yet. All the FIU instances are available in the SoC's address space, regardless of whether or not they're connected to actual flash chips. Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-11-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/npcm7xx.h | 2 + include/hw/ssi/npcm7xx_fiu.h | 73 +++++ hw/arm/npcm7xx.c | 58 ++++ hw/ssi/npcm7xx_fiu.c | 572 +++++++++++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/ssi/meson.build | 1 + hw/ssi/trace-events | 11 + 7 files changed, 718 insertions(+) create mode 100644 include/hw/ssi/npcm7xx_fiu.h create mode 100644 hw/ssi/npcm7xx_fiu.c diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/npcm7xx_gcr.h" #include "hw/nvram/npcm7xx_otp.h" #include "hw/timer/npcm7xx_timer.h" +#include "hw/ssi/npcm7xx_fiu.h" #include "target/arm/cpu.h" #define NPCM7XX_MAX_NUM_CPUS (2) @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { NPCM7xxOTPState key_storage; NPCM7xxOTPState fuse_array; NPCM7xxMCState mc; + NPCM7xxFIUState fiu[2]; } NPCM7xxState; #define TYPE_NPCM7XX "npcm7xx" diff --git a/include/hw/ssi/npcm7xx_fiu.h b/include/hw/ssi/npcm7xx_fiu.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/ssi/npcm7xx_fiu.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Flash Interface Unit (FIU) + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ +#ifndef NPCM7XX_FIU_H +#define NPCM7XX_FIU_H + +#include "hw/ssi/ssi.h" +#include "hw/sysbus.h" + +/* + * Number of registers in our device state structure. Don't change this without + * incrementing the version_id in the vmstate. + */ +#define NPCM7XX_FIU_NR_REGS (0x7c / sizeof(uint32_t)) + +typedef struct NPCM7xxFIUState NPCM7xxFIUState; + +/** + * struct NPCM7xxFIUFlash - Per-chipselect flash controller state. + * @direct_access: Memory region for direct flash access. + * @fiu: Pointer to flash controller shared state. + */ +typedef struct NPCM7xxFIUFlash { + MemoryRegion direct_access; + NPCM7xxFIUState *fiu; +} NPCM7xxFIUFlash; + +/** + * NPCM7xxFIUState - Device state for one Flash Interface Unit. + * @parent: System bus device. + * @mmio: Memory region for register access. + * @cs_count: Number of flash chips that may be connected to this module. + * @active_cs: Currently active chip select, or -1 if no chip is selected. + * @cs_lines: GPIO lines that may be wired to flash chips. + * @flash: Array of @cs_count per-flash-chip state objects. + * @spi: The SPI bus mastered by this controller. + * @regs: Register contents. + * + * Each FIU has a shared bank of registers, and controls up to four chip + * selects. Each chip select has a dedicated memory region which may be used to + * read and write the flash connected to that chip select as if it were memory. + */ +struct NPCM7xxFIUState { + SysBusDevice parent; + + MemoryRegion mmio; + + int32_t cs_count; + int32_t active_cs; + qemu_irq *cs_lines; + NPCM7xxFIUFlash *flash; + + SSIBus *spi; + + uint32_t regs[NPCM7XX_FIU_NR_REGS]; +}; + +#define TYPE_NPCM7XX_FIU "npcm7xx-fiu" +#define NPCM7XX_FIU(obj) OBJECT_CHECK(NPCM7xxFIUState, (obj), TYPE_NPCM7XX_FIU) + +#endif /* NPCM7XX_FIU_H */ diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ static const hwaddr npcm7xx_uart_addr[] = { 0xf0004000, }; +/* Direct memory-mapped access to SPI0 CS0-1. */ +static const hwaddr npcm7xx_fiu0_flash_addr[] = { + 0x80000000, /* CS0 */ + 0x88000000, /* CS1 */ +}; + +/* Direct memory-mapped access to SPI3 CS0-3. */ +static const hwaddr npcm7xx_fiu3_flash_addr[] = { + 0xa0000000, /* CS0 */ + 0xa8000000, /* CS1 */ + 0xb0000000, /* CS2 */ + 0xb8000000, /* CS3 */ +}; + +static const struct { + const char *name; + hwaddr regs_addr; + int cs_count; + const hwaddr *flash_addr; +} npcm7xx_fiu[] = { + { + .name = "fiu0", + .regs_addr = 0xfb000000, + .cs_count = ARRAY_SIZE(npcm7xx_fiu0_flash_addr), + .flash_addr = npcm7xx_fiu0_flash_addr, + }, { + .name = "fiu3", + .regs_addr = 0xc0000000, + .cs_count = ARRAY_SIZE(npcm7xx_fiu3_flash_addr), + .flash_addr = npcm7xx_fiu3_flash_addr, + }, +}; + static void npcm7xx_write_secondary_boot(ARMCPU *cpu, const struct arm_boot_info *info) { @@ -XXX,XX +XXX,XX @@ static void npcm7xx_init(Object *obj) for (i = 0; i < ARRAY_SIZE(s->tim); i++) { object_initialize_child(obj, "tim[*]", &s->tim[i], TYPE_NPCM7XX_TIMER); } + + QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_fiu) != ARRAY_SIZE(s->fiu)); + for (i = 0; i < ARRAY_SIZE(s->fiu); i++) { + object_initialize_child(obj, npcm7xx_fiu[i].name, &s->fiu[i], + TYPE_NPCM7XX_FIU); + } } static void npcm7xx_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) serial_hd(i), DEVICE_LITTLE_ENDIAN); } + /* + * Flash Interface Unit (FIU). Can fail if incorrect number of chip selects + * specified, but this is a programming error. + */ + QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_fiu) != ARRAY_SIZE(s->fiu)); + for (i = 0; i < ARRAY_SIZE(s->fiu); i++) { + SysBusDevice *sbd = SYS_BUS_DEVICE(&s->fiu[i]); + int j; + + object_property_set_int(OBJECT(sbd), "cs-count", + npcm7xx_fiu[i].cs_count, &error_abort); + sysbus_realize(sbd, &error_abort); + + sysbus_mmio_map(sbd, 0, npcm7xx_fiu[i].regs_addr); + for (j = 0; j < npcm7xx_fiu[i].cs_count; j++) { + sysbus_mmio_map(sbd, j + 1, npcm7xx_fiu[i].flash_addr[j]); + } + } + /* RAM2 (SRAM) */ memory_region_init_ram(&s->sram, OBJECT(dev), "ram2", NPCM7XX_RAM2_SZ, &error_abort); diff --git a/hw/ssi/npcm7xx_fiu.c b/hw/ssi/npcm7xx_fiu.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/ssi/npcm7xx_fiu.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx Flash Interface Unit (FIU) + * + * Copyright 2020 Google LLC + * + * 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 of the License, or + * (at your option) any later version. + * + * 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. + */ + +#include "qemu/osdep.h" + +#include "hw/irq.h" +#include "hw/qdev-properties.h" +#include "hw/ssi/npcm7xx_fiu.h" +#include "migration/vmstate.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/units.h" + +#include "trace.h" + +/* Up to 128 MiB of flash may be accessed directly as memory. */ +#define NPCM7XX_FIU_FLASH_WINDOW_SIZE (128 * MiB) + +/* Each module has 4 KiB of register space. Only a fraction of it is used. */ +#define NPCM7XX_FIU_CTRL_REGS_SIZE (4 * KiB) + +/* 32-bit FIU register indices. */ +enum NPCM7xxFIURegister { + NPCM7XX_FIU_DRD_CFG, + NPCM7XX_FIU_DWR_CFG, + NPCM7XX_FIU_UMA_CFG, + NPCM7XX_FIU_UMA_CTS, + NPCM7XX_FIU_UMA_CMD, + NPCM7XX_FIU_UMA_ADDR, + NPCM7XX_FIU_PRT_CFG, + NPCM7XX_FIU_UMA_DW0 = 0x0020 / sizeof(uint32_t), + NPCM7XX_FIU_UMA_DW1, + NPCM7XX_FIU_UMA_DW2, + NPCM7XX_FIU_UMA_DW3, + NPCM7XX_FIU_UMA_DR0, + NPCM7XX_FIU_UMA_DR1, + NPCM7XX_FIU_UMA_DR2, + NPCM7XX_FIU_UMA_DR3, + NPCM7XX_FIU_PRT_CMD0, + NPCM7XX_FIU_PRT_CMD1, + NPCM7XX_FIU_PRT_CMD2, + NPCM7XX_FIU_PRT_CMD3, + NPCM7XX_FIU_PRT_CMD4, + NPCM7XX_FIU_PRT_CMD5, + NPCM7XX_FIU_PRT_CMD6, + NPCM7XX_FIU_PRT_CMD7, + NPCM7XX_FIU_PRT_CMD8, + NPCM7XX_FIU_PRT_CMD9, + NPCM7XX_FIU_CFG = 0x78 / sizeof(uint32_t), + NPCM7XX_FIU_REGS_END, +}; + +/* FIU_{DRD,DWR,UMA,PTR}_CFG cannot be written when this bit is set. */ +#define NPCM7XX_FIU_CFG_LCK BIT(31) + +/* Direct Read configuration register fields. */ +#define FIU_DRD_CFG_ADDSIZ(rv) extract32(rv, 16, 2) +#define FIU_ADDSIZ_3BYTES 0 +#define FIU_ADDSIZ_4BYTES 1 +#define FIU_DRD_CFG_DBW(rv) extract32(rv, 12, 2) +#define FIU_DRD_CFG_ACCTYPE(rv) extract32(rv, 8, 2) +#define FIU_DRD_CFG_RDCMD(rv) extract32(rv, 0, 8) + +/* Direct Write configuration register fields. */ +#define FIU_DWR_CFG_ADDSIZ(rv) extract32(rv, 16, 2) +#define FIU_DWR_CFG_WRCMD(rv) extract32(rv, 0, 8) + +/* User-Mode Access register fields. */ + +/* Command Mode Lock and the bits protected by it. */ +#define FIU_UMA_CFG_CMMLCK BIT(30) +#define FIU_UMA_CFG_CMMLCK_MASK 0x00000403 + +#define FIU_UMA_CFG_RDATSIZ(rv) extract32(rv, 24, 5) +#define FIU_UMA_CFG_DBSIZ(rv) extract32(rv, 21, 3) +#define FIU_UMA_CFG_WDATSIZ(rv) extract32(rv, 16, 5) +#define FIU_UMA_CFG_ADDSIZ(rv) extract32(rv, 11, 3) +#define FIU_UMA_CFG_CMDSIZ(rv) extract32(rv, 10, 1) +#define FIU_UMA_CFG_DBPCK(rv) extract32(rv, 6, 2) + +#define FIU_UMA_CTS_RDYIE BIT(25) +#define FIU_UMA_CTS_RDYST BIT(24) +#define FIU_UMA_CTS_SW_CS BIT(16) +#define FIU_UMA_CTS_DEV_NUM(rv) extract32(rv, 8, 2) +#define FIU_UMA_CTS_EXEC_DONE BIT(0) + +/* + * Returns the index of flash in the fiu->flash array. This corresponds to the + * chip select ID of the flash. + */ +static int npcm7xx_fiu_cs_index(NPCM7xxFIUState *fiu, NPCM7xxFIUFlash *flash) +{ + int index = flash - fiu->flash; + + g_assert(index >= 0 && index < fiu->cs_count); + + return index; +} + +/* Assert the chip select specified in the UMA Control/Status Register. */ +static void npcm7xx_fiu_select(NPCM7xxFIUState *s, int cs_id) +{ + trace_npcm7xx_fiu_select(DEVICE(s)->canonical_path, cs_id); + + if (cs_id < s->cs_count) { + qemu_irq_lower(s->cs_lines[cs_id]); + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: UMA to CS%d; this module has only %d chip selects", + DEVICE(s)->canonical_path, cs_id, s->cs_count); + cs_id = -1; + } + + s->active_cs = cs_id; +} + +/* Deassert the currently active chip select. */ +static void npcm7xx_fiu_deselect(NPCM7xxFIUState *s) +{ + if (s->active_cs < 0) { + return; + } + + trace_npcm7xx_fiu_deselect(DEVICE(s)->canonical_path, s->active_cs); + + qemu_irq_raise(s->cs_lines[s->active_cs]); + s->active_cs = -1; +} + +/* Direct flash memory read handler. */ +static uint64_t npcm7xx_fiu_flash_read(void *opaque, hwaddr addr, + unsigned int size) +{ + NPCM7xxFIUFlash *f = opaque; + NPCM7xxFIUState *fiu = f->fiu; + uint64_t value = 0; + uint32_t drd_cfg; + int dummy_cycles; + int i; + + if (fiu->active_cs != -1) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: direct flash read with CS%d already active", + DEVICE(fiu)->canonical_path, fiu->active_cs); + } + + npcm7xx_fiu_select(fiu, npcm7xx_fiu_cs_index(fiu, f)); + + drd_cfg = fiu->regs[NPCM7XX_FIU_DRD_CFG]; + ssi_transfer(fiu->spi, FIU_DRD_CFG_RDCMD(drd_cfg)); + + switch (FIU_DRD_CFG_ADDSIZ(drd_cfg)) { + case FIU_ADDSIZ_4BYTES: + ssi_transfer(fiu->spi, extract32(addr, 24, 8)); + /* fall through */ + case FIU_ADDSIZ_3BYTES: + ssi_transfer(fiu->spi, extract32(addr, 16, 8)); + ssi_transfer(fiu->spi, extract32(addr, 8, 8)); + ssi_transfer(fiu->spi, extract32(addr, 0, 8)); + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: bad address size %d\n", + DEVICE(fiu)->canonical_path, FIU_DRD_CFG_ADDSIZ(drd_cfg)); + break; + } + + /* Flash chip model expects one transfer per dummy bit, not byte */ + dummy_cycles = + (FIU_DRD_CFG_DBW(drd_cfg) * 8) >> FIU_DRD_CFG_ACCTYPE(drd_cfg); + for (i = 0; i < dummy_cycles; i++) { + ssi_transfer(fiu->spi, 0); + } + + for (i = 0; i < size; i++) { + value = deposit64(value, 8 * i, 8, ssi_transfer(fiu->spi, 0)); + } + + trace_npcm7xx_fiu_flash_read(DEVICE(fiu)->canonical_path, fiu->active_cs, + addr, size, value); + + npcm7xx_fiu_deselect(fiu); + + return value; +} + +/* Direct flash memory write handler. */ +static void npcm7xx_fiu_flash_write(void *opaque, hwaddr addr, uint64_t v, + unsigned int size) +{ + NPCM7xxFIUFlash *f = opaque; + NPCM7xxFIUState *fiu = f->fiu; + uint32_t dwr_cfg; + int cs_id; + int i; + + if (fiu->active_cs != -1) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: direct flash write with CS%d already active", + DEVICE(fiu)->canonical_path, fiu->active_cs); + } + + cs_id = npcm7xx_fiu_cs_index(fiu, f); + trace_npcm7xx_fiu_flash_write(DEVICE(fiu)->canonical_path, cs_id, addr, + size, v); + npcm7xx_fiu_select(fiu, cs_id); + + dwr_cfg = fiu->regs[NPCM7XX_FIU_DWR_CFG]; + ssi_transfer(fiu->spi, FIU_DWR_CFG_WRCMD(dwr_cfg)); + + switch (FIU_DWR_CFG_ADDSIZ(dwr_cfg)) { + case FIU_ADDSIZ_4BYTES: + ssi_transfer(fiu->spi, extract32(addr, 24, 8)); + /* fall through */ + case FIU_ADDSIZ_3BYTES: + ssi_transfer(fiu->spi, extract32(addr, 16, 8)); + ssi_transfer(fiu->spi, extract32(addr, 8, 8)); + ssi_transfer(fiu->spi, extract32(addr, 0, 8)); + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: bad address size %d\n", + DEVICE(fiu)->canonical_path, FIU_DWR_CFG_ADDSIZ(dwr_cfg)); + break; + } + + for (i = 0; i < size; i++) { + ssi_transfer(fiu->spi, extract64(v, i * 8, 8)); + } + + npcm7xx_fiu_deselect(fiu); +} + +static const MemoryRegionOps npcm7xx_fiu_flash_ops = { + .read = npcm7xx_fiu_flash_read, + .write = npcm7xx_fiu_flash_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 1, + .max_access_size = 8, + .unaligned = true, + }, +}; + +/* Control register read handler. */ +static uint64_t npcm7xx_fiu_ctrl_read(void *opaque, hwaddr addr, + unsigned int size) +{ + hwaddr reg = addr / sizeof(uint32_t); + NPCM7xxFIUState *s = opaque; + uint32_t value; + + if (reg < NPCM7XX_FIU_NR_REGS) { + value = s->regs[reg]; + } else { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: read from invalid offset 0x%" PRIx64 "\n", + DEVICE(s)->canonical_path, addr); + value = 0; + } + + trace_npcm7xx_fiu_ctrl_read(DEVICE(s)->canonical_path, addr, value); + + return value; +} + +/* Send the specified number of address bytes from the UMA address register. */ +static void send_address(SSIBus *spi, unsigned int addsiz, uint32_t addr) +{ + switch (addsiz) { + case 4: + ssi_transfer(spi, extract32(addr, 24, 8)); + /* fall through */ + case 3: + ssi_transfer(spi, extract32(addr, 16, 8)); + /* fall through */ + case 2: + ssi_transfer(spi, extract32(addr, 8, 8)); + /* fall through */ + case 1: + ssi_transfer(spi, extract32(addr, 0, 8)); + /* fall through */ + case 0: + break; + } +} + +/* Send the number of dummy bits specified in the UMA config register. */ +static void send_dummy_bits(SSIBus *spi, uint32_t uma_cfg, uint32_t uma_cmd) +{ + unsigned int bits_per_clock = 1U << FIU_UMA_CFG_DBPCK(uma_cfg); + unsigned int i; + + for (i = 0; i < FIU_UMA_CFG_DBSIZ(uma_cfg); i++) { + /* Use bytes 0 and 1 first, then keep repeating byte 2 */ + unsigned int field = (i < 2) ? ((i + 1) * 8) : 24; + unsigned int j; + + for (j = 0; j < 8; j += bits_per_clock) { + ssi_transfer(spi, extract32(uma_cmd, field + j, bits_per_clock)); + } + } +} + +/* Perform a User-Mode Access transaction. */ +static void npcm7xx_fiu_uma_transaction(NPCM7xxFIUState *s) +{ + uint32_t uma_cts = s->regs[NPCM7XX_FIU_UMA_CTS]; + uint32_t uma_cfg; + unsigned int i; + + /* SW_CS means the CS is already forced low, so don't touch it. */ + if (uma_cts & FIU_UMA_CTS_SW_CS) { + int cs_id = FIU_UMA_CTS_DEV_NUM(s->regs[NPCM7XX_FIU_UMA_CTS]); + npcm7xx_fiu_select(s, cs_id); + } + + /* Send command, if present. */ + uma_cfg = s->regs[NPCM7XX_FIU_UMA_CFG]; + if (FIU_UMA_CFG_CMDSIZ(uma_cfg) > 0) { + ssi_transfer(s->spi, extract32(s->regs[NPCM7XX_FIU_UMA_CMD], 0, 8)); + } + + /* Send address, if present. */ + send_address(s->spi, FIU_UMA_CFG_ADDSIZ(uma_cfg), + s->regs[NPCM7XX_FIU_UMA_ADDR]); + + /* Write data, if present. */ + for (i = 0; i < FIU_UMA_CFG_WDATSIZ(uma_cfg); i++) { + unsigned int reg = + (i < 16) ? (NPCM7XX_FIU_UMA_DW0 + i / 4) : NPCM7XX_FIU_UMA_DW3; + unsigned int field = (i % 4) * 8; + + ssi_transfer(s->spi, extract32(s->regs[reg], field, 8)); + } + + /* Send dummy bits, if present. */ + send_dummy_bits(s->spi, uma_cfg, s->regs[NPCM7XX_FIU_UMA_CMD]); + + /* Read data, if present. */ + for (i = 0; i < FIU_UMA_CFG_RDATSIZ(uma_cfg); i++) { + unsigned int reg = NPCM7XX_FIU_UMA_DR0 + i / 4; + unsigned int field = (i % 4) * 8; + uint8_t c; + + c = ssi_transfer(s->spi, 0); + if (reg <= NPCM7XX_FIU_UMA_DR3) { + s->regs[reg] = deposit32(s->regs[reg], field, 8, c); + } + } + + /* Again, don't touch CS if the user is forcing it low. */ + if (uma_cts & FIU_UMA_CTS_SW_CS) { + npcm7xx_fiu_deselect(s); + } + + /* RDYST means a command has completed since it was cleared. */ + s->regs[NPCM7XX_FIU_UMA_CTS] |= FIU_UMA_CTS_RDYST; + /* EXEC_DONE means Execute Command / Not Done, so clear it here. */ + s->regs[NPCM7XX_FIU_UMA_CTS] &= ~FIU_UMA_CTS_EXEC_DONE; +} + +/* Control register write handler. */ +static void npcm7xx_fiu_ctrl_write(void *opaque, hwaddr addr, uint64_t v, + unsigned int size) +{ + hwaddr reg = addr / sizeof(uint32_t); + NPCM7xxFIUState *s = opaque; + uint32_t value = v; + + trace_npcm7xx_fiu_ctrl_write(DEVICE(s)->canonical_path, addr, value); + + switch (reg) { + case NPCM7XX_FIU_UMA_CFG: + if (s->regs[reg] & FIU_UMA_CFG_CMMLCK) { + value &= ~FIU_UMA_CFG_CMMLCK_MASK; + value |= (s->regs[reg] & FIU_UMA_CFG_CMMLCK_MASK); + } + /* fall through */ + case NPCM7XX_FIU_DRD_CFG: + case NPCM7XX_FIU_DWR_CFG: + if (s->regs[reg] & NPCM7XX_FIU_CFG_LCK) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: write to locked register @ 0x%" PRIx64 "\n", + DEVICE(s)->canonical_path, addr); + return; + } + s->regs[reg] = value; + break; + + case NPCM7XX_FIU_UMA_CTS: + if (value & FIU_UMA_CTS_RDYST) { + value &= ~FIU_UMA_CTS_RDYST; + } else { + value |= s->regs[reg] & FIU_UMA_CTS_RDYST; + } + if ((s->regs[reg] ^ value) & FIU_UMA_CTS_SW_CS) { + if (value & FIU_UMA_CTS_SW_CS) { + /* + * Don't drop CS if there's a transfer in progress, or we're + * about to start one. + */ + if (!((value | s->regs[reg]) & FIU_UMA_CTS_EXEC_DONE)) { + npcm7xx_fiu_deselect(s); + } + } else { + int cs_id = FIU_UMA_CTS_DEV_NUM(s->regs[NPCM7XX_FIU_UMA_CTS]); + npcm7xx_fiu_select(s, cs_id); + } + } + s->regs[reg] = value | (s->regs[reg] & FIU_UMA_CTS_EXEC_DONE); + if (value & FIU_UMA_CTS_EXEC_DONE) { + npcm7xx_fiu_uma_transaction(s); + } + break; + + case NPCM7XX_FIU_UMA_DR0 ... NPCM7XX_FIU_UMA_DR3: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: write to read-only register @ 0x%" PRIx64 "\n", + DEVICE(s)->canonical_path, addr); + return; + + case NPCM7XX_FIU_PRT_CFG: + case NPCM7XX_FIU_PRT_CMD0 ... NPCM7XX_FIU_PRT_CMD9: + qemu_log_mask(LOG_UNIMP, "%s: PRT is not implemented\n", __func__); + break; + + case NPCM7XX_FIU_UMA_CMD: + case NPCM7XX_FIU_UMA_ADDR: + case NPCM7XX_FIU_UMA_DW0 ... NPCM7XX_FIU_UMA_DW3: + case NPCM7XX_FIU_CFG: + s->regs[reg] = value; + break; + + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: write to invalid offset 0x%" PRIx64 "\n", + DEVICE(s)->canonical_path, addr); + return; + } +} + +static const MemoryRegionOps npcm7xx_fiu_ctrl_ops = { + .read = npcm7xx_fiu_ctrl_read, + .write = npcm7xx_fiu_ctrl_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void npcm7xx_fiu_enter_reset(Object *obj, ResetType type) +{ + NPCM7xxFIUState *s = NPCM7XX_FIU(obj); + + trace_npcm7xx_fiu_enter_reset(DEVICE(obj)->canonical_path, type); + + memset(s->regs, 0, sizeof(s->regs)); + + s->regs[NPCM7XX_FIU_DRD_CFG] = 0x0300100b; + s->regs[NPCM7XX_FIU_DWR_CFG] = 0x03000002; + s->regs[NPCM7XX_FIU_UMA_CFG] = 0x00000400; + s->regs[NPCM7XX_FIU_UMA_CTS] = 0x00010000; + s->regs[NPCM7XX_FIU_UMA_CMD] = 0x0000000b; + s->regs[NPCM7XX_FIU_PRT_CFG] = 0x00000400; + s->regs[NPCM7XX_FIU_CFG] = 0x0000000b; +} + +static void npcm7xx_fiu_hold_reset(Object *obj) +{ + NPCM7xxFIUState *s = NPCM7XX_FIU(obj); + int i; + + trace_npcm7xx_fiu_hold_reset(DEVICE(obj)->canonical_path); + + for (i = 0; i < s->cs_count; i++) { + qemu_irq_raise(s->cs_lines[i]); + } +} + +static void npcm7xx_fiu_realize(DeviceState *dev, Error **errp) +{ + NPCM7xxFIUState *s = NPCM7XX_FIU(dev); + SysBusDevice *sbd = &s->parent; + int i; + + if (s->cs_count <= 0) { + error_setg(errp, "%s: %d chip selects specified, need at least one", + dev->canonical_path, s->cs_count); + return; + } + + s->spi = ssi_create_bus(dev, "spi"); + s->cs_lines = g_new0(qemu_irq, s->cs_count); + qdev_init_gpio_out_named(DEVICE(s), s->cs_lines, "cs", s->cs_count); + s->flash = g_new0(NPCM7xxFIUFlash, s->cs_count); + + /* + * Register the control registers region first. It may be followed by one + * or more direct flash access regions. + */ + memory_region_init_io(&s->mmio, OBJECT(s), &npcm7xx_fiu_ctrl_ops, s, "ctrl", + NPCM7XX_FIU_CTRL_REGS_SIZE); + sysbus_init_mmio(sbd, &s->mmio); + + for (i = 0; i < s->cs_count; i++) { + NPCM7xxFIUFlash *flash = &s->flash[i]; + flash->fiu = s; + memory_region_init_io(&flash->direct_access, OBJECT(s), + &npcm7xx_fiu_flash_ops, &s->flash[i], "flash", + NPCM7XX_FIU_FLASH_WINDOW_SIZE); + sysbus_init_mmio(sbd, &flash->direct_access); + } +} + +static const VMStateDescription vmstate_npcm7xx_fiu = { + .name = "npcm7xx-fiu", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_INT32(active_cs, NPCM7xxFIUState), + VMSTATE_UINT32_ARRAY(regs, NPCM7xxFIUState, NPCM7XX_FIU_NR_REGS), + VMSTATE_END_OF_LIST(), + }, +}; + +static Property npcm7xx_fiu_properties[] = { + DEFINE_PROP_INT32("cs-count", NPCM7xxFIUState, cs_count, 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static void npcm7xx_fiu_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + QEMU_BUILD_BUG_ON(NPCM7XX_FIU_REGS_END > NPCM7XX_FIU_NR_REGS); + + dc->desc = "NPCM7xx Flash Interface Unit"; + dc->realize = npcm7xx_fiu_realize; + dc->vmsd = &vmstate_npcm7xx_fiu; + rc->phases.enter = npcm7xx_fiu_enter_reset; + rc->phases.hold = npcm7xx_fiu_hold_reset; + device_class_set_props(dc, npcm7xx_fiu_properties); +} + +static const TypeInfo npcm7xx_fiu_types[] = { + { + .name = TYPE_NPCM7XX_FIU, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxFIUState), + .class_init = npcm7xx_fiu_class_init, + }, +}; +DEFINE_TYPES(npcm7xx_fiu_types); diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config NPCM7XX select ARM_GIC select PL310 # cache controller select SERIAL + select SSI select UNIMP config FSL_IMX25 diff --git a/hw/ssi/meson.build b/hw/ssi/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/meson.build +++ b/hw/ssi/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_ASPEED_SOC', if_true: files('aspeed_smc.c')) softmmu_ss.add(when: 'CONFIG_MSF2', if_true: files('mss-spi.c')) +softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_fiu.c')) softmmu_ss.add(when: 'CONFIG_PL022', if_true: files('pl022.c')) softmmu_ss.add(when: 'CONFIG_SSI', if_true: files('ssi.c')) softmmu_ss.add(when: 'CONFIG_STM32F2XX_SPI', if_true: files('stm32f2xx_spi.c')) diff --git a/hw/ssi/trace-events b/hw/ssi/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/trace-events +++ b/hw/ssi/trace-events @@ -XXX,XX +XXX,XX @@ aspeed_smc_dma_checksum(uint32_t addr, uint32_t data) "0x%08x: 0x%08x" aspeed_smc_dma_rw(const char *dir, uint32_t flash_addr, uint32_t dram_addr, uint32_t size) "%s flash:@0x%08x dram:@0x%08x size:0x%08x" aspeed_smc_write(uint64_t addr, uint32_t size, uint64_t data) "@0x%" PRIx64 " size %u: 0x%" PRIx64 aspeed_smc_flash_select(int cs, const char *prefix) "CS%d %sselect" + +# npcm7xx_fiu.c + +npcm7xx_fiu_enter_reset(const char *id, int reset_type) "%s reset type: %d" +npcm7xx_fiu_hold_reset(const char *id) "%s" +npcm7xx_fiu_select(const char *id, int cs) "%s select CS%d" +npcm7xx_fiu_deselect(const char *id, int cs) "%s deselect CS%d" +npcm7xx_fiu_ctrl_read(const char *id, uint64_t addr, uint32_t data) "%s offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 +npcm7xx_fiu_ctrl_write(const char *id, uint64_t addr, uint32_t data) "%s offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 +npcm7xx_fiu_flash_read(const char *id, int cs, uint64_t addr, unsigned int size, uint64_t value) "%s[%d] offset: 0x%08" PRIx64 " size: %u value: 0x%" PRIx64 +npcm7xx_fiu_flash_write(const char *id, int cs, uint64_t addr, unsigned int size, uint64_t value) "%s[%d] offset: 0x%08" PRIx64 " size: %u value: 0x%" PRIx64 -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This allows these NPCM7xx-based boards to boot from a flash image, e.g. one built with OpenBMC. For example like this: IMAGE=${OPENBMC}/build/tmp/deploy/images/gsj/image-bmc qemu-system-arm -machine quanta-gsj -nographic \ -drive file=${IMAGE},if=mtd,bus=0,unit=0,format=raw,snapshot=on Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Tested-by: Cédric Le Goater <clg@kaod.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200911052101.2602693-12-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/npcm7xx_boards.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx_boards.c +++ b/hw/arm/npcm7xx_boards.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/npcm7xx.h" #include "hw/core/cpu.h" #include "hw/loader.h" +#include "hw/qdev-properties.h" #include "qapi/error.h" #include "qemu-common.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ static void npcm7xx_load_bootrom(MachineState *machine, NPCM7xxState *soc) } } +static void npcm7xx_connect_flash(NPCM7xxFIUState *fiu, int cs_no, + const char *flash_type, DriveInfo *dinfo) +{ + DeviceState *flash; + qemu_irq flash_cs; + + flash = qdev_new(flash_type); + if (dinfo) { + qdev_prop_set_drive(flash, "drive", blk_by_legacy_dinfo(dinfo)); + } + qdev_realize_and_unref(flash, BUS(fiu->spi), &error_fatal); + + flash_cs = qdev_get_gpio_in_named(flash, SSI_GPIO_CS, 0); + qdev_connect_gpio_out_named(DEVICE(fiu), "cs", cs_no, flash_cs); +} + static void npcm7xx_connect_dram(NPCM7xxState *soc, MemoryRegion *dram) { memory_region_add_subregion(get_system_memory(), NPCM7XX_DRAM_BA, dram); @@ -XXX,XX +XXX,XX @@ static void npcm750_evb_init(MachineState *machine) qdev_realize(DEVICE(soc), NULL, &error_fatal); npcm7xx_load_bootrom(machine, soc); + npcm7xx_connect_flash(&soc->fiu[0], 0, "w25q256", drive_get(IF_MTD, 0, 0)); npcm7xx_load_kernel(machine, soc); } @@ -XXX,XX +XXX,XX @@ static void quanta_gsj_init(MachineState *machine) qdev_realize(DEVICE(soc), NULL, &error_fatal); npcm7xx_load_bootrom(machine, soc); + npcm7xx_connect_flash(&soc->fiu[0], 0, "mx25l25635e", + drive_get(IF_MTD, 0, 0)); npcm7xx_load_kernel(machine, soc); } -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> When booting directly into a kernel, bypassing the boot loader, the CPU and UART clocks are not set up correctly. This makes the system appear very slow, and causes the initrd boot test to fail when optimization is off. The UART clock must run at 24 MHz. The default 25 MHz reference clock cannot achieve this, so switch to PLL2/2 @ 480 MHz, which works perfectly with the default /20 divider. The CPU clock should run at 800 MHz, so switch it to PLL1/2. PLL1 runs at 800 MHz by default, so we need to double the feedback divider as well to make it run at 1600 MHz (so PLL1/2 runs at 800 MHz). We don't bother checking for PLL lock because we know our emulated PLLs lock instantly. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-13-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/npcm7xx.h | 1 + hw/arm/npcm7xx.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+) diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_SMP_LOADER_START (0xffff0000) /* Boot ROM */ #define NPCM7XX_SMP_BOOTREG_ADDR (0xf080013c) /* GCR.SCRPAD */ #define NPCM7XX_GIC_CPU_IF_ADDR (0xf03fe100) /* GIC within A9 */ +#define NPCM7XX_BOARD_SETUP_ADDR (0xffff1000) /* Boot ROM */ typedef struct NPCM7xxMachine { MachineState parent; diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_ROM_BA (0xffff0000) #define NPCM7XX_ROM_SZ (64 * KiB) +/* Clock configuration values to be fixed up when bypassing bootloader */ + +/* Run PLL1 at 1600 MHz */ +#define NPCM7XX_PLLCON1_FIXUP_VAL (0x00402101) +/* Run the CPU from PLL1 and UART from PLL2 */ +#define NPCM7XX_CLKSEL_FIXUP_VAL (0x004aaba9) + /* * Interrupt lines going into the GIC. This does not include internal Cortex-A9 * interrupts. @@ -XXX,XX +XXX,XX @@ static const struct { }, }; +static void npcm7xx_write_board_setup(ARMCPU *cpu, + const struct arm_boot_info *info) +{ + uint32_t board_setup[] = { + 0xe59f0010, /* ldr r0, clk_base_addr */ + 0xe59f1010, /* ldr r1, pllcon1_value */ + 0xe5801010, /* str r1, [r0, #16] */ + 0xe59f100c, /* ldr r1, clksel_value */ + 0xe5801004, /* str r1, [r0, #4] */ + 0xe12fff1e, /* bx lr */ + NPCM7XX_CLK_BA, + NPCM7XX_PLLCON1_FIXUP_VAL, + NPCM7XX_CLKSEL_FIXUP_VAL, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(board_setup); i++) { + board_setup[i] = tswap32(board_setup[i]); + } + rom_add_blob_fixed("board-setup", board_setup, sizeof(board_setup), + info->board_setup_addr); +} + static void npcm7xx_write_secondary_boot(ARMCPU *cpu, const struct arm_boot_info *info) { @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info npcm7xx_binfo = { .gic_cpu_if_addr = NPCM7XX_GIC_CPU_IF_ADDR, .write_secondary_boot = npcm7xx_write_secondary_boot, .board_id = -1, + .board_setup_addr = NPCM7XX_BOARD_SETUP_ADDR, + .write_board_setup = npcm7xx_write_board_setup, }; void npcm7xx_load_kernel(MachineState *machine, NPCM7xxState *soc) -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-14-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/nuvoton.rst | 92 +++++++++++++++++++++++++++++++++++++ docs/system/target-arm.rst | 1 + 2 files changed, 93 insertions(+) create mode 100644 docs/system/arm/nuvoton.rst diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/system/arm/nuvoton.rst @@ -XXX,XX +XXX,XX @@ +Nuvoton iBMC boards (``npcm750-evb``, ``quanta-gsj``) +===================================================== + +The `Nuvoton iBMC`_ chips (NPCM7xx) are a family of ARM-based SoCs that are +designed to be used as Baseboard Management Controllers (BMCs) in various +servers. They all feature one or two ARM Cortex A9 CPU cores, as well as an +assortment of peripherals targeted for either Enterprise or Data Center / +Hyperscale applications. The former is a superset of the latter, so NPCM750 has +all the peripherals of NPCM730 and more. + +.. _Nuvoton iBMC: https://www.nuvoton.com/products/cloud-computing/ibmc/ + +The NPCM750 SoC has two Cortex A9 cores and is targeted for the Enterprise +segment. The following machines are based on this chip : + +- ``npcm750-evb`` Nuvoton NPCM750 Evaluation board + +The NPCM730 SoC has two Cortex A9 cores and is targeted for Data Center and +Hyperscale applications. The following machines are based on this chip : + +- ``quanta-gsj`` Quanta GSJ server BMC + +There are also two more SoCs, NPCM710 and NPCM705, which are single-core +variants of NPCM750 and NPCM730, respectively. These are currently not +supported by QEMU. + +Supported devices +----------------- + + * SMP (Dual Core Cortex-A9) + * Cortex-A9MPCore built-in peripherals: SCU, GIC, Global Timer, Private Timer + and Watchdog. + * SRAM, ROM and DRAM mappings + * System Global Control Registers (GCR) + * Clock and reset controller (CLK) + * Timer controller (TIM) + * Serial ports (16550-based) + * DDR4 memory controller (dummy interface indicating memory training is done) + * OTP controllers (no protection features) + * Flash Interface Unit (FIU; no protection features) + +Missing devices +--------------- + + * GPIO controller + * LPC/eSPI host-to-BMC interface, including + + * Keyboard and mouse controller interface (KBCI) + * Keyboard Controller Style (KCS) channels + * BIOS POST code FIFO + * System Wake-up Control (SWC) + * Shared memory (SHM) + * eSPI slave interface + + * Ethernet controllers (GMAC and EMC) + * USB host (USBH) + * USB device (USBD) + * SMBus controller (SMBF) + * Peripheral SPI controller (PSPI) + * Analog to Digital Converter (ADC) + * SD/MMC host + * Random Number Generator (RNG) + * PECI interface + * Pulse Width Modulation (PWM) + * Tachometer + * PCI and PCIe root complex and bridges + * VDM and MCTP support + * Serial I/O expansion + * LPC/eSPI host + * Coprocessor + * Graphics + * Video capture + * Encoding compression engine + * Security features + +Boot options +------------ + +The Nuvoton machines can boot from an OpenBMC firmware image, or directly into +a kernel using the ``-kernel`` option. OpenBMC images for `quanta-gsj` and +possibly others can be downloaded from the OpenPOWER jenkins : + + https://openpower.xyz/ + +The firmware image should be attached as an MTD drive. Example : + +.. code-block:: bash + + $ qemu-system-arm -machine quanta-gsj -nographic \ + -drive file=image-bmc,if=mtd,bus=0,unit=0,format=raw + +The default root password for test images is usually ``0penBmc``. diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/musicpal arm/gumstix arm/nseries + arm/nuvoton arm/orangepi arm/palm arm/xscale -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> This adds two acceptance tests for the quanta-gsj machine. One test downloads a lightly patched openbmc flash image from github and verifies that it boots all the way to the login prompt. The other test downloads a kernel, initrd and dtb built from the same openbmc source and verifies that the kernel detects all CPUs and boots to the point where it can't find the root filesystem (because we have no flash image in this case). Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Message-id: 20200911052101.2602693-15-hskinnemoen@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 83 ++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(LinuxKernelTest): 'sda') # cubieboard's reboot is not functioning; omit reboot test. + def test_arm_quanta_gsj(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:quanta-gsj + """ + # 25 MiB compressed, 32 MiB uncompressed. + image_url = ( + 'https://github.com/hskinnemoen/openbmc/releases/download/' + '20200711-gsj-qemu-0/obmc-phosphor-image-gsj.static.mtd.gz') + image_hash = '14895e634923345cb5c8776037ff7876df96f6b1' + image_path_gz = self.fetch_asset(image_url, asset_hash=image_hash) + image_name = 'obmc.mtd' + image_path = os.path.join(self.workdir, image_name) + archive.gzip_uncompress(image_path_gz, image_path) + + self.vm.set_console() + drive_args = 'file=' + image_path + ',if=mtd,bus=0,unit=0' + self.vm.add_args('-drive', drive_args) + self.vm.launch() + + # Disable drivers and services that stall for a long time during boot, + # to avoid running past the 90-second timeout. These may be removed + # as the corresponding device support is added. + kernel_command_line = self.KERNEL_COMMON_COMMAND_LINE + ( + 'console=${console} ' + 'mem=${mem} ' + 'initcall_blacklist=npcm_i2c_bus_driver_init ' + 'systemd.mask=systemd-random-seed.service ' + 'systemd.mask=dropbearkey.service ' + ) + + self.wait_for_console_pattern('> BootBlock by Nuvoton') + self.wait_for_console_pattern('>Device: Poleg BMC NPCM730') + self.wait_for_console_pattern('>Skip DDR init.') + self.wait_for_console_pattern('U-Boot ') + interrupt_interactive_console_until_pattern( + self, 'Hit any key to stop autoboot:', 'U-Boot>') + exec_command_and_wait_for_pattern( + self, "setenv bootargs ${bootargs} " + kernel_command_line, + 'U-Boot>') + exec_command_and_wait_for_pattern( + self, 'run romboot', 'Booting Kernel from flash') + self.wait_for_console_pattern('Booting Linux on physical CPU 0x0') + self.wait_for_console_pattern('CPU1: thread -1, cpu 1, socket 0') + self.wait_for_console_pattern('OpenBMC Project Reference Distro') + self.wait_for_console_pattern('gsj login:') + + def test_arm_quanta_gsj_initrd(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:quanta-gsj + """ + initrd_url = ( + 'https://github.com/hskinnemoen/openbmc/releases/download/' + '20200711-gsj-qemu-0/obmc-phosphor-initramfs-gsj.cpio.xz') + initrd_hash = '98fefe5d7e56727b1eb17d5c00311b1b5c945300' + initrd_path = self.fetch_asset(initrd_url, asset_hash=initrd_hash) + kernel_url = ( + 'https://github.com/hskinnemoen/openbmc/releases/download/' + '20200711-gsj-qemu-0/uImage-gsj.bin') + kernel_hash = 'fa67b2f141d56d39b3c54305c0e8a899c99eb2c7' + kernel_path = self.fetch_asset(kernel_url, asset_hash=kernel_hash) + dtb_url = ( + 'https://github.com/hskinnemoen/openbmc/releases/download/' + '20200711-gsj-qemu-0/nuvoton-npcm730-gsj.dtb') + dtb_hash = '18315f7006d7b688d8312d5c727eecd819aa36a4' + dtb_path = self.fetch_asset(dtb_url, asset_hash=dtb_hash) + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyS0,115200n8 ' + 'earlycon=uart8250,mmio32,0xf0001000') + self.vm.add_args('-kernel', kernel_path, + '-initrd', initrd_path, + '-dtb', dtb_path, + '-append', kernel_command_line) + self.vm.launch() + + self.wait_for_console_pattern('Booting Linux on physical CPU 0x0') + self.wait_for_console_pattern('CPU1: thread -1, cpu 1, socket 0') + self.wait_for_console_pattern( + 'Give root password for system maintenance') + def test_arm_orangepi(self): """ :avocado: tags=arch:arm -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> The Xilinx ZynqMP CAN controller is developed based on SocketCAN, QEMU CAN bus implementation. Bus connection and socketCAN connection for each CAN module can be set through command lines. Example for using single CAN: -object can-bus,id=canbus0 \ -machine xlnx-zcu102.canbus0=canbus0 \ -object can-host-socketcan,id=socketcan0,if=vcan0,canbus=canbus0 Example for connecting both CAN to same virtual CAN on host machine: -object can-bus,id=canbus0 -object can-bus,id=canbus1 \ -machine xlnx-zcu102.canbus0=canbus0 \ -machine xlnx-zcu102.canbus1=canbus1 \ -object can-host-socketcan,id=socketcan0,if=vcan0,canbus=canbus0 \ -object can-host-socketcan,id=socketcan1,if=vcan0,canbus=canbus1 To create virtual CAN on the host machine, please check the QEMU CAN docs: https://github.com/qemu/qemu/blob/master/docs/can.txt Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 1597278668-339715-2-git-send-email-fnu.vikram@xilinx.com [PMM: updated to meson build system] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/net/xlnx-zynqmp-can.h | 78 ++ hw/net/can/xlnx-zynqmp-can.c | 1165 ++++++++++++++++++++++++++++++ hw/net/can/meson.build | 1 + 3 files changed, 1244 insertions(+) create mode 100644 include/hw/net/xlnx-zynqmp-can.h create mode 100644 hw/net/can/xlnx-zynqmp-can.c diff --git a/include/hw/net/xlnx-zynqmp-can.h b/include/hw/net/xlnx-zynqmp-can.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/xlnx-zynqmp-can.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx ZynqMP CAN controller. + * + * Copyright (c) 2020 Xilinx Inc. + * + * Written-by: Vikram Garhwal<fnu.vikram@xilinx.com> + * + * Based on QEMU CAN Device emulation implemented by Jin Yang, Deniz Eren and + * Pavel Pisa. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef XLNX_ZYNQMP_CAN_H +#define XLNX_ZYNQMP_CAN_H + +#include "hw/register.h" +#include "net/can_emu.h" +#include "net/can_host.h" +#include "qemu/fifo32.h" +#include "hw/ptimer.h" +#include "hw/qdev-clock.h" + +#define TYPE_XLNX_ZYNQMP_CAN "xlnx.zynqmp-can" + +#define XLNX_ZYNQMP_CAN(obj) \ + OBJECT_CHECK(XlnxZynqMPCANState, (obj), TYPE_XLNX_ZYNQMP_CAN) + +#define MAX_CAN_CTRLS 2 +#define XLNX_ZYNQMP_CAN_R_MAX (0x84 / 4) +#define MAILBOX_CAPACITY 64 +#define CAN_TIMER_MAX 0XFFFFUL +#define CAN_DEFAULT_CLOCK (24 * 1000 * 1000) + +/* Each CAN_FRAME will have 4 * 32bit size. */ +#define CAN_FRAME_SIZE 4 +#define RXFIFO_SIZE (MAILBOX_CAPACITY * CAN_FRAME_SIZE) + +typedef struct XlnxZynqMPCANState { + SysBusDevice parent_obj; + MemoryRegion iomem; + + qemu_irq irq; + + CanBusClientState bus_client; + CanBusState *canbus; + + struct { + uint32_t ext_clk_freq; + } cfg; + + RegisterInfo reg_info[XLNX_ZYNQMP_CAN_R_MAX]; + uint32_t regs[XLNX_ZYNQMP_CAN_R_MAX]; + + Fifo32 rx_fifo; + Fifo32 tx_fifo; + Fifo32 txhpb_fifo; + + ptimer_state *can_timer; +} XlnxZynqMPCANState; + +#endif diff --git a/hw/net/can/xlnx-zynqmp-can.c b/hw/net/can/xlnx-zynqmp-can.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/can/xlnx-zynqmp-can.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx ZynqMP CAN controller. + * This implementation is based on the following datasheet: + * https://www.xilinx.com/support/documentation/user_guides/ug1085-zynq-ultrascale-trm.pdf + * + * Copyright (c) 2020 Xilinx Inc. + * + * Written-by: Vikram Garhwal<fnu.vikram@xilinx.com> + * + * Based on QEMU CAN Device emulation implemented by Jin Yang, Deniz Eren and + * Pavel Pisa + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "hw/sysbus.h" +#include "hw/register.h" +#include "hw/irq.h" +#include "qapi/error.h" +#include "qemu/bitops.h" +#include "qemu/log.h" +#include "qemu/cutils.h" +#include "sysemu/sysemu.h" +#include "migration/vmstate.h" +#include "hw/qdev-properties.h" +#include "net/can_emu.h" +#include "net/can_host.h" +#include "qemu/event_notifier.h" +#include "qom/object_interfaces.h" +#include "hw/net/xlnx-zynqmp-can.h" + +#ifndef XLNX_ZYNQMP_CAN_ERR_DEBUG +#define XLNX_ZYNQMP_CAN_ERR_DEBUG 0 +#endif + +#define DB_PRINT(dev, ...) do { \ + if (XLNX_ZYNQMP_CAN_ERR_DEBUG) { \ + g_autofree char *path = object_get_canonical_path(OBJECT(dev)); \ + qemu_log("%s: %s", path, ## __VA_ARGS__); \ + } \ +} while (0) + +#define MAX_DLC 8 +#undef ERROR + +REG32(SOFTWARE_RESET_REGISTER, 0x0) + FIELD(SOFTWARE_RESET_REGISTER, CEN, 1, 1) + FIELD(SOFTWARE_RESET_REGISTER, SRST, 0, 1) +REG32(MODE_SELECT_REGISTER, 0x4) + FIELD(MODE_SELECT_REGISTER, SNOOP, 2, 1) + FIELD(MODE_SELECT_REGISTER, LBACK, 1, 1) + FIELD(MODE_SELECT_REGISTER, SLEEP, 0, 1) +REG32(ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, 0x8) + FIELD(ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, BRP, 0, 8) +REG32(ARBITRATION_PHASE_BIT_TIMING_REGISTER, 0xc) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, SJW, 7, 2) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, TS2, 4, 3) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, TS1, 0, 4) +REG32(ERROR_COUNTER_REGISTER, 0x10) + FIELD(ERROR_COUNTER_REGISTER, REC, 8, 8) + FIELD(ERROR_COUNTER_REGISTER, TEC, 0, 8) +REG32(ERROR_STATUS_REGISTER, 0x14) + FIELD(ERROR_STATUS_REGISTER, ACKER, 4, 1) + FIELD(ERROR_STATUS_REGISTER, BERR, 3, 1) + FIELD(ERROR_STATUS_REGISTER, STER, 2, 1) + FIELD(ERROR_STATUS_REGISTER, FMER, 1, 1) + FIELD(ERROR_STATUS_REGISTER, CRCER, 0, 1) +REG32(STATUS_REGISTER, 0x18) + FIELD(STATUS_REGISTER, SNOOP, 12, 1) + FIELD(STATUS_REGISTER, ACFBSY, 11, 1) + FIELD(STATUS_REGISTER, TXFLL, 10, 1) + FIELD(STATUS_REGISTER, TXBFLL, 9, 1) + FIELD(STATUS_REGISTER, ESTAT, 7, 2) + FIELD(STATUS_REGISTER, ERRWRN, 6, 1) + FIELD(STATUS_REGISTER, BBSY, 5, 1) + FIELD(STATUS_REGISTER, BIDLE, 4, 1) + FIELD(STATUS_REGISTER, NORMAL, 3, 1) + FIELD(STATUS_REGISTER, SLEEP, 2, 1) + FIELD(STATUS_REGISTER, LBACK, 1, 1) + FIELD(STATUS_REGISTER, CONFIG, 0, 1) +REG32(INTERRUPT_STATUS_REGISTER, 0x1c) + FIELD(INTERRUPT_STATUS_REGISTER, TXFEMP, 14, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXFWMEMP, 13, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXFWMFLL, 12, 1) + FIELD(INTERRUPT_STATUS_REGISTER, WKUP, 11, 1) + FIELD(INTERRUPT_STATUS_REGISTER, SLP, 10, 1) + FIELD(INTERRUPT_STATUS_REGISTER, BSOFF, 9, 1) + FIELD(INTERRUPT_STATUS_REGISTER, ERROR, 8, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXNEMP, 7, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXOFLW, 6, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXUFLW, 5, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXOK, 4, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXBFLL, 3, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXFLL, 2, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXOK, 1, 1) + FIELD(INTERRUPT_STATUS_REGISTER, ARBLST, 0, 1) +REG32(INTERRUPT_ENABLE_REGISTER, 0x20) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXFEMP, 14, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXFWMEMP, 13, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXFWMFLL, 12, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EWKUP, 11, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ESLP, 10, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EBSOFF, 9, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EERROR, 8, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXNEMP, 7, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXOFLW, 6, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXUFLW, 5, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXOK, 4, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXBFLL, 3, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXFLL, 2, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXOK, 1, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EARBLST, 0, 1) +REG32(INTERRUPT_CLEAR_REGISTER, 0x24) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXFEMP, 14, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXFWMEMP, 13, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXFWMFLL, 12, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CWKUP, 11, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CSLP, 10, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CBSOFF, 9, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CERROR, 8, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXNEMP, 7, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXOFLW, 6, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXUFLW, 5, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXOK, 4, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXBFLL, 3, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXFLL, 2, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXOK, 1, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CARBLST, 0, 1) +REG32(TIMESTAMP_REGISTER, 0x28) + FIELD(TIMESTAMP_REGISTER, CTS, 0, 1) +REG32(WIR, 0x2c) + FIELD(WIR, EW, 8, 8) + FIELD(WIR, FW, 0, 8) +REG32(TXFIFO_ID, 0x30) + FIELD(TXFIFO_ID, IDH, 21, 11) + FIELD(TXFIFO_ID, SRRRTR, 20, 1) + FIELD(TXFIFO_ID, IDE, 19, 1) + FIELD(TXFIFO_ID, IDL, 1, 18) + FIELD(TXFIFO_ID, RTR, 0, 1) +REG32(TXFIFO_DLC, 0x34) + FIELD(TXFIFO_DLC, DLC, 28, 4) +REG32(TXFIFO_DATA1, 0x38) + FIELD(TXFIFO_DATA1, DB0, 24, 8) + FIELD(TXFIFO_DATA1, DB1, 16, 8) + FIELD(TXFIFO_DATA1, DB2, 8, 8) + FIELD(TXFIFO_DATA1, DB3, 0, 8) +REG32(TXFIFO_DATA2, 0x3c) + FIELD(TXFIFO_DATA2, DB4, 24, 8) + FIELD(TXFIFO_DATA2, DB5, 16, 8) + FIELD(TXFIFO_DATA2, DB6, 8, 8) + FIELD(TXFIFO_DATA2, DB7, 0, 8) +REG32(TXHPB_ID, 0x40) + FIELD(TXHPB_ID, IDH, 21, 11) + FIELD(TXHPB_ID, SRRRTR, 20, 1) + FIELD(TXHPB_ID, IDE, 19, 1) + FIELD(TXHPB_ID, IDL, 1, 18) + FIELD(TXHPB_ID, RTR, 0, 1) +REG32(TXHPB_DLC, 0x44) + FIELD(TXHPB_DLC, DLC, 28, 4) +REG32(TXHPB_DATA1, 0x48) + FIELD(TXHPB_DATA1, DB0, 24, 8) + FIELD(TXHPB_DATA1, DB1, 16, 8) + FIELD(TXHPB_DATA1, DB2, 8, 8) + FIELD(TXHPB_DATA1, DB3, 0, 8) +REG32(TXHPB_DATA2, 0x4c) + FIELD(TXHPB_DATA2, DB4, 24, 8) + FIELD(TXHPB_DATA2, DB5, 16, 8) + FIELD(TXHPB_DATA2, DB6, 8, 8) + FIELD(TXHPB_DATA2, DB7, 0, 8) +REG32(RXFIFO_ID, 0x50) + FIELD(RXFIFO_ID, IDH, 21, 11) + FIELD(RXFIFO_ID, SRRRTR, 20, 1) + FIELD(RXFIFO_ID, IDE, 19, 1) + FIELD(RXFIFO_ID, IDL, 1, 18) + FIELD(RXFIFO_ID, RTR, 0, 1) +REG32(RXFIFO_DLC, 0x54) + FIELD(RXFIFO_DLC, DLC, 28, 4) + FIELD(RXFIFO_DLC, RXT, 0, 16) +REG32(RXFIFO_DATA1, 0x58) + FIELD(RXFIFO_DATA1, DB0, 24, 8) + FIELD(RXFIFO_DATA1, DB1, 16, 8) + FIELD(RXFIFO_DATA1, DB2, 8, 8) + FIELD(RXFIFO_DATA1, DB3, 0, 8) +REG32(RXFIFO_DATA2, 0x5c) + FIELD(RXFIFO_DATA2, DB4, 24, 8) + FIELD(RXFIFO_DATA2, DB5, 16, 8) + FIELD(RXFIFO_DATA2, DB6, 8, 8) + FIELD(RXFIFO_DATA2, DB7, 0, 8) +REG32(AFR, 0x60) + FIELD(AFR, UAF4, 3, 1) + FIELD(AFR, UAF3, 2, 1) + FIELD(AFR, UAF2, 1, 1) + FIELD(AFR, UAF1, 0, 1) +REG32(AFMR1, 0x64) + FIELD(AFMR1, AMIDH, 21, 11) + FIELD(AFMR1, AMSRR, 20, 1) + FIELD(AFMR1, AMIDE, 19, 1) + FIELD(AFMR1, AMIDL, 1, 18) + FIELD(AFMR1, AMRTR, 0, 1) +REG32(AFIR1, 0x68) + FIELD(AFIR1, AIIDH, 21, 11) + FIELD(AFIR1, AISRR, 20, 1) + FIELD(AFIR1, AIIDE, 19, 1) + FIELD(AFIR1, AIIDL, 1, 18) + FIELD(AFIR1, AIRTR, 0, 1) +REG32(AFMR2, 0x6c) + FIELD(AFMR2, AMIDH, 21, 11) + FIELD(AFMR2, AMSRR, 20, 1) + FIELD(AFMR2, AMIDE, 19, 1) + FIELD(AFMR2, AMIDL, 1, 18) + FIELD(AFMR2, AMRTR, 0, 1) +REG32(AFIR2, 0x70) + FIELD(AFIR2, AIIDH, 21, 11) + FIELD(AFIR2, AISRR, 20, 1) + FIELD(AFIR2, AIIDE, 19, 1) + FIELD(AFIR2, AIIDL, 1, 18) + FIELD(AFIR2, AIRTR, 0, 1) +REG32(AFMR3, 0x74) + FIELD(AFMR3, AMIDH, 21, 11) + FIELD(AFMR3, AMSRR, 20, 1) + FIELD(AFMR3, AMIDE, 19, 1) + FIELD(AFMR3, AMIDL, 1, 18) + FIELD(AFMR3, AMRTR, 0, 1) +REG32(AFIR3, 0x78) + FIELD(AFIR3, AIIDH, 21, 11) + FIELD(AFIR3, AISRR, 20, 1) + FIELD(AFIR3, AIIDE, 19, 1) + FIELD(AFIR3, AIIDL, 1, 18) + FIELD(AFIR3, AIRTR, 0, 1) +REG32(AFMR4, 0x7c) + FIELD(AFMR4, AMIDH, 21, 11) + FIELD(AFMR4, AMSRR, 20, 1) + FIELD(AFMR4, AMIDE, 19, 1) + FIELD(AFMR4, AMIDL, 1, 18) + FIELD(AFMR4, AMRTR, 0, 1) +REG32(AFIR4, 0x80) + FIELD(AFIR4, AIIDH, 21, 11) + FIELD(AFIR4, AISRR, 20, 1) + FIELD(AFIR4, AIIDE, 19, 1) + FIELD(AFIR4, AIIDL, 1, 18) + FIELD(AFIR4, AIRTR, 0, 1) + +static void can_update_irq(XlnxZynqMPCANState *s) +{ + uint32_t irq; + + /* Watermark register interrupts. */ + if ((fifo32_num_free(&s->tx_fifo) / CAN_FRAME_SIZE) > + ARRAY_FIELD_EX32(s->regs, WIR, EW)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXFWMEMP, 1); + } + + if ((fifo32_num_used(&s->rx_fifo) / CAN_FRAME_SIZE) > + ARRAY_FIELD_EX32(s->regs, WIR, FW)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXFWMFLL, 1); + } + + /* RX Interrupts. */ + if (fifo32_num_used(&s->rx_fifo) >= CAN_FRAME_SIZE) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXNEMP, 1); + } + + /* TX interrupts. */ + if (fifo32_is_empty(&s->tx_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXFEMP, 1); + } + + if (fifo32_is_full(&s->tx_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXFLL, 1); + } + + if (fifo32_is_full(&s->txhpb_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXBFLL, 1); + } + + irq = s->regs[R_INTERRUPT_STATUS_REGISTER]; + irq &= s->regs[R_INTERRUPT_ENABLE_REGISTER]; + + qemu_set_irq(s->irq, irq); +} + +static void can_ier_post_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + can_update_irq(s); +} + +static uint64_t can_icr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + + s->regs[R_INTERRUPT_STATUS_REGISTER] &= ~val; + can_update_irq(s); + + return 0; +} + +static void can_config_reset(XlnxZynqMPCANState *s) +{ + /* Reset all the configuration registers. */ + register_reset(&s->reg_info[R_SOFTWARE_RESET_REGISTER]); + register_reset(&s->reg_info[R_MODE_SELECT_REGISTER]); + register_reset( + &s->reg_info[R_ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER]); + register_reset(&s->reg_info[R_ARBITRATION_PHASE_BIT_TIMING_REGISTER]); + register_reset(&s->reg_info[R_STATUS_REGISTER]); + register_reset(&s->reg_info[R_INTERRUPT_STATUS_REGISTER]); + register_reset(&s->reg_info[R_INTERRUPT_ENABLE_REGISTER]); + register_reset(&s->reg_info[R_INTERRUPT_CLEAR_REGISTER]); + register_reset(&s->reg_info[R_WIR]); +} + +static void can_config_mode(XlnxZynqMPCANState *s) +{ + register_reset(&s->reg_info[R_ERROR_COUNTER_REGISTER]); + register_reset(&s->reg_info[R_ERROR_STATUS_REGISTER]); + + /* Put XlnxZynqMPCAN in configuration mode. */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, CONFIG, 1); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, WKUP, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, SLP, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, BSOFF, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, ERROR, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOFLW, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOK, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXOK, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, ARBLST, 0); + + can_update_irq(s); +} + +static void update_status_register_mode_bits(XlnxZynqMPCANState *s) +{ + bool sleep_status = ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP); + bool sleep_mode = ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SLEEP); + /* Wake up interrupt bit. */ + bool wakeup_irq_val = sleep_status && (sleep_mode == 0); + /* Sleep interrupt bit. */ + bool sleep_irq_val = sleep_mode && (sleep_status == 0); + + /* Clear previous core mode status bits. */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, LBACK, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SLEEP, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SNOOP, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, NORMAL, 0); + + /* set current mode bit and generate irqs accordingly. */ + if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, LBACK)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, LBACK, 1); + } else if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SLEEP)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SLEEP, 1); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, SLP, + sleep_irq_val); + } else if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SNOOP)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SNOOP, 1); + } else { + /* + * If all bits are zero then XlnxZynqMPCAN is set in normal mode. + */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, NORMAL, 1); + /* Set wakeup interrupt bit. */ + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, WKUP, + wakeup_irq_val); + } + + can_update_irq(s); +} + +static void can_exit_sleep_mode(XlnxZynqMPCANState *s) +{ + ARRAY_FIELD_DP32(s->regs, MODE_SELECT_REGISTER, SLEEP, 0); + update_status_register_mode_bits(s); +} + +static void generate_frame(qemu_can_frame *frame, uint32_t *data) +{ + frame->can_id = data[0]; + frame->can_dlc = FIELD_EX32(data[1], TXFIFO_DLC, DLC); + + frame->data[0] = FIELD_EX32(data[2], TXFIFO_DATA1, DB3); + frame->data[1] = FIELD_EX32(data[2], TXFIFO_DATA1, DB2); + frame->data[2] = FIELD_EX32(data[2], TXFIFO_DATA1, DB1); + frame->data[3] = FIELD_EX32(data[2], TXFIFO_DATA1, DB0); + + frame->data[4] = FIELD_EX32(data[3], TXFIFO_DATA2, DB7); + frame->data[5] = FIELD_EX32(data[3], TXFIFO_DATA2, DB6); + frame->data[6] = FIELD_EX32(data[3], TXFIFO_DATA2, DB5); + frame->data[7] = FIELD_EX32(data[3], TXFIFO_DATA2, DB4); +} + +static bool tx_ready_check(XlnxZynqMPCANState *s) +{ + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, SRST)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer data while" + " data while controller is in reset mode.\n", + path); + return false; + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer" + " data while controller is in configuration mode. Reset" + " the core so operations can start fresh.\n", + path); + return false; + } + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SNOOP)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer" + " data while controller is in SNOOP MODE.\n", + path); + return false; + } + + return true; +} + +static void transfer_fifo(XlnxZynqMPCANState *s, Fifo32 *fifo) +{ + qemu_can_frame frame; + uint32_t data[CAN_FRAME_SIZE]; + int i; + bool can_tx = tx_ready_check(s); + + if (can_tx) { + while (!fifo32_is_empty(fifo)) { + for (i = 0; i < CAN_FRAME_SIZE; i++) { + data[i] = fifo32_pop(fifo); + } + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, LBACK)) { + /* + * Controller is in loopback. In Loopback mode, the CAN core + * transmits a recessive bitstream on to the XlnxZynqMPCAN Bus. + * Any message transmitted is looped back to the RX line and + * acknowledged. The XlnxZynqMPCAN core receives any message + * that it transmits. + */ + if (fifo32_is_full(&s->rx_fifo)) { + DB_PRINT(s, "Loopback: RX FIFO is full." + " TX FIFO will be flushed.\n"); + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, + RXOFLW, 1); + } else { + for (i = 0; i < CAN_FRAME_SIZE; i++) { + fifo32_push(&s->rx_fifo, data[i]); + } + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, + RXOK, 1); + } + } else { + /* Normal mode Tx. */ + generate_frame(&frame, data); + + can_bus_client_send(&s->bus_client, &frame, 1); + } + } + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXOK, 1); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, TXBFLL, 0); + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP)) { + can_exit_sleep_mode(s); + } + } else { + DB_PRINT(s, "Not enabled for data transfer.\n"); + } + + can_update_irq(s); +} + +static uint64_t can_srr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + + ARRAY_FIELD_DP32(s->regs, SOFTWARE_RESET_REGISTER, CEN, + FIELD_EX32(val, SOFTWARE_RESET_REGISTER, CEN)); + + if (FIELD_EX32(val, SOFTWARE_RESET_REGISTER, SRST)) { + DB_PRINT(s, "Resetting controller.\n"); + + /* First, core will do software reset then will enter in config mode. */ + can_config_reset(s); + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + can_config_mode(s); + } else { + /* + * Leave config mode. Now XlnxZynqMPCAN core will enter normal, + * sleep, snoop or loopback mode depending upon LBACK, SLEEP, SNOOP + * register states. + */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, CONFIG, 0); + + ptimer_transaction_begin(s->can_timer); + ptimer_set_count(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); + + /* XlnxZynqMPCAN is out of config mode. It will send pending data. */ + transfer_fifo(s, &s->txhpb_fifo); + transfer_fifo(s, &s->tx_fifo); + } + + update_status_register_mode_bits(s); + + return s->regs[R_SOFTWARE_RESET_REGISTER]; +} + +static uint64_t can_msr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + uint8_t multi_mode; + + /* + * Multiple mode set check. This is done to make sure user doesn't set + * multiple modes. + */ + multi_mode = FIELD_EX32(val, MODE_SELECT_REGISTER, LBACK) + + FIELD_EX32(val, MODE_SELECT_REGISTER, SLEEP) + + FIELD_EX32(val, MODE_SELECT_REGISTER, SNOOP); + + if (multi_mode > 1) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to config" + " several modes simultaneously. One mode will be selected" + " according to their priority: LBACK > SLEEP > SNOOP.\n", + path); + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + /* We are in configuration mode, any mode can be selected. */ + s->regs[R_MODE_SELECT_REGISTER] = val; + } else { + bool sleep_mode_bit = FIELD_EX32(val, MODE_SELECT_REGISTER, SLEEP); + + ARRAY_FIELD_DP32(s->regs, MODE_SELECT_REGISTER, SLEEP, sleep_mode_bit); + + if (FIELD_EX32(val, MODE_SELECT_REGISTER, LBACK)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to set" + " LBACK mode without setting CEN bit as 0.\n", + path); + } else if (FIELD_EX32(val, MODE_SELECT_REGISTER, SNOOP)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to set" + " SNOOP mode without setting CEN bit as 0.\n", + path); + } + + update_status_register_mode_bits(s); + } + + return s->regs[R_MODE_SELECT_REGISTER]; +} + +static uint64_t can_brpr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + + /* Only allow writes when in config mode. */ + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) { + val = s->regs[R_ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER]; + } + + return val; +} + +static uint64_t can_btr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + + /* Only allow writes when in config mode. */ + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) { + val = s->regs[R_ARBITRATION_PHASE_BIT_TIMING_REGISTER]; + } + + return val; +} + +static uint64_t can_tcr_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + + if (FIELD_EX32(val, TIMESTAMP_REGISTER, CTS)) { + ptimer_transaction_begin(s->can_timer); + ptimer_set_count(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); + } + + return 0; +} + +static void update_rx_fifo(XlnxZynqMPCANState *s, const qemu_can_frame *frame) +{ + bool filter_pass = false; + uint16_t timestamp = 0; + + /* If no filter is enabled. Message will be stored in FIFO. */ + if (!((ARRAY_FIELD_EX32(s->regs, AFR, UAF1)) | + (ARRAY_FIELD_EX32(s->regs, AFR, UAF2)) | + (ARRAY_FIELD_EX32(s->regs, AFR, UAF3)) | + (ARRAY_FIELD_EX32(s->regs, AFR, UAF4)))) { + filter_pass = true; + } + + /* + * Messages that pass any of the acceptance filters will be stored in + * the RX FIFO. + */ + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF1)) { + uint32_t id_masked = s->regs[R_AFMR1] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR1] & s->regs[R_AFIR1]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF2)) { + uint32_t id_masked = s->regs[R_AFMR2] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR2] & s->regs[R_AFIR2]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF3)) { + uint32_t id_masked = s->regs[R_AFMR3] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR3] & s->regs[R_AFIR3]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF4)) { + uint32_t id_masked = s->regs[R_AFMR4] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR4] & s->regs[R_AFIR4]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + /* Store the message in fifo if it passed through any of the filters. */ + if (filter_pass && frame->can_dlc <= MAX_DLC) { + + if (fifo32_is_full(&s->rx_fifo)) { + DB_PRINT(s, "RX FIFO is full.\n"); + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOFLW, 1); + } else { + timestamp = CAN_TIMER_MAX - ptimer_get_count(s->can_timer); + + fifo32_push(&s->rx_fifo, frame->can_id); + + fifo32_push(&s->rx_fifo, deposit32(0, R_RXFIFO_DLC_DLC_SHIFT, + R_RXFIFO_DLC_DLC_LENGTH, + frame->can_dlc) | + deposit32(0, R_RXFIFO_DLC_RXT_SHIFT, + R_RXFIFO_DLC_RXT_LENGTH, + timestamp)); + + /* First 32 bit of the data. */ + fifo32_push(&s->rx_fifo, deposit32(0, R_TXFIFO_DATA1_DB3_SHIFT, + R_TXFIFO_DATA1_DB3_LENGTH, + frame->data[0]) | + deposit32(0, R_TXFIFO_DATA1_DB2_SHIFT, + R_TXFIFO_DATA1_DB2_LENGTH, + frame->data[1]) | + deposit32(0, R_TXFIFO_DATA1_DB1_SHIFT, + R_TXFIFO_DATA1_DB1_LENGTH, + frame->data[2]) | + deposit32(0, R_TXFIFO_DATA1_DB0_SHIFT, + R_TXFIFO_DATA1_DB0_LENGTH, + frame->data[3])); + /* Last 32 bit of the data. */ + fifo32_push(&s->rx_fifo, deposit32(0, R_TXFIFO_DATA2_DB7_SHIFT, + R_TXFIFO_DATA2_DB7_LENGTH, + frame->data[4]) | + deposit32(0, R_TXFIFO_DATA2_DB6_SHIFT, + R_TXFIFO_DATA2_DB6_LENGTH, + frame->data[5]) | + deposit32(0, R_TXFIFO_DATA2_DB5_SHIFT, + R_TXFIFO_DATA2_DB5_LENGTH, + frame->data[6]) | + deposit32(0, R_TXFIFO_DATA2_DB4_SHIFT, + R_TXFIFO_DATA2_DB4_LENGTH, + frame->data[7])); + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOK, 1); + } + + can_update_irq(s); + } else { + DB_PRINT(s, "Message didn't pass through any filter or dlc" + " is not in range.\n"); + } +} + +static uint64_t can_rxfifo_pre_read(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t r = 0; + + if (!fifo32_is_empty(&s->rx_fifo)) { + r = fifo32_pop(&s->rx_fifo); + } else { + DB_PRINT(s, "No message in RXFIFO.\n"); + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXUFLW, 1); + } + + can_update_irq(s); + return r; +} + +static void can_filter_enable_post_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF1) && + ARRAY_FIELD_EX32(s->regs, AFR, UAF2) && + ARRAY_FIELD_EX32(s->regs, AFR, UAF3) && + ARRAY_FIELD_EX32(s->regs, AFR, UAF4)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, ACFBSY, 1); + } else { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, ACFBSY, 0); + } +} + +static uint64_t can_filter_mask_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t reg_idx = (reg->access->addr) / 4; + uint32_t val = val64; + uint32_t filter_number = (reg_idx - R_AFMR1) / 2; + + /* modify an acceptance filter, the corresponding UAF bit should be '0.' */ + if (!(s->regs[R_AFR] & (1 << filter_number))) { + s->regs[reg_idx] = val; + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Acceptance filter %d" + " mask is not set as corresponding UAF bit is not 0.\n", + path, filter_number + 1); + } + + return s->regs[reg_idx]; +} + +static uint64_t can_filter_id_pre_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t reg_idx = (reg->access->addr) / 4; + uint32_t val = val64; + uint32_t filter_number = (reg_idx - R_AFIR1) / 2; + + if (!(s->regs[R_AFR] & (1 << filter_number))) { + s->regs[reg_idx] = val; + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Acceptance filter %d" + " id is not set as corresponding UAF bit is not 0.\n", + path, filter_number + 1); + } + + return s->regs[reg_idx]; +} + +static void can_tx_post_write(RegisterInfo *reg, uint64_t val64) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t val = val64; + + bool is_txhpb = reg->access->addr > A_TXFIFO_DATA2; + + bool initiate_transfer = (reg->access->addr == A_TXFIFO_DATA2) || + (reg->access->addr == A_TXHPB_DATA2); + + Fifo32 *f = is_txhpb ? &s->txhpb_fifo : &s->tx_fifo; + + DB_PRINT(s, "TX FIFO write.\n"); + + if (!fifo32_is_full(f)) { + fifo32_push(f, val); + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: TX FIFO is full.\n", path); + } + + /* Initiate the message send if TX register is written. */ + if (initiate_transfer && + ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) { + transfer_fifo(s, f); + } + + can_update_irq(s); +} + +static const RegisterAccessInfo can_regs_info[] = { + { .name = "SOFTWARE_RESET_REGISTER", + .addr = A_SOFTWARE_RESET_REGISTER, + .rsvd = 0xfffffffc, + .pre_write = can_srr_pre_write, + },{ .name = "MODE_SELECT_REGISTER", + .addr = A_MODE_SELECT_REGISTER, + .rsvd = 0xfffffff8, + .pre_write = can_msr_pre_write, + },{ .name = "ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER", + .addr = A_ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, + .rsvd = 0xffffff00, + .pre_write = can_brpr_pre_write, + },{ .name = "ARBITRATION_PHASE_BIT_TIMING_REGISTER", + .addr = A_ARBITRATION_PHASE_BIT_TIMING_REGISTER, + .rsvd = 0xfffffe00, + .pre_write = can_btr_pre_write, + },{ .name = "ERROR_COUNTER_REGISTER", + .addr = A_ERROR_COUNTER_REGISTER, + .rsvd = 0xffff0000, + .ro = 0xffffffff, + },{ .name = "ERROR_STATUS_REGISTER", + .addr = A_ERROR_STATUS_REGISTER, + .rsvd = 0xffffffe0, + .w1c = 0x1f, + },{ .name = "STATUS_REGISTER", .addr = A_STATUS_REGISTER, + .reset = 0x1, + .rsvd = 0xffffe000, + .ro = 0x1fff, + },{ .name = "INTERRUPT_STATUS_REGISTER", + .addr = A_INTERRUPT_STATUS_REGISTER, + .reset = 0x6000, + .rsvd = 0xffff8000, + .ro = 0x7fff, + },{ .name = "INTERRUPT_ENABLE_REGISTER", + .addr = A_INTERRUPT_ENABLE_REGISTER, + .rsvd = 0xffff8000, + .post_write = can_ier_post_write, + },{ .name = "INTERRUPT_CLEAR_REGISTER", + .addr = A_INTERRUPT_CLEAR_REGISTER, + .rsvd = 0xffff8000, + .pre_write = can_icr_pre_write, + },{ .name = "TIMESTAMP_REGISTER", + .addr = A_TIMESTAMP_REGISTER, + .rsvd = 0xfffffffe, + .pre_write = can_tcr_pre_write, + },{ .name = "WIR", .addr = A_WIR, + .reset = 0x3f3f, + .rsvd = 0xffff0000, + },{ .name = "TXFIFO_ID", .addr = A_TXFIFO_ID, + .post_write = can_tx_post_write, + },{ .name = "TXFIFO_DLC", .addr = A_TXFIFO_DLC, + .rsvd = 0xfffffff, + .post_write = can_tx_post_write, + },{ .name = "TXFIFO_DATA1", .addr = A_TXFIFO_DATA1, + .post_write = can_tx_post_write, + },{ .name = "TXFIFO_DATA2", .addr = A_TXFIFO_DATA2, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_ID", .addr = A_TXHPB_ID, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_DLC", .addr = A_TXHPB_DLC, + .rsvd = 0xfffffff, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_DATA1", .addr = A_TXHPB_DATA1, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_DATA2", .addr = A_TXHPB_DATA2, + .post_write = can_tx_post_write, + },{ .name = "RXFIFO_ID", .addr = A_RXFIFO_ID, + .ro = 0xffffffff, + .post_read = can_rxfifo_pre_read, + },{ .name = "RXFIFO_DLC", .addr = A_RXFIFO_DLC, + .rsvd = 0xfff0000, + .post_read = can_rxfifo_pre_read, + },{ .name = "RXFIFO_DATA1", .addr = A_RXFIFO_DATA1, + .post_read = can_rxfifo_pre_read, + },{ .name = "RXFIFO_DATA2", .addr = A_RXFIFO_DATA2, + .post_read = can_rxfifo_pre_read, + },{ .name = "AFR", .addr = A_AFR, + .rsvd = 0xfffffff0, + .post_write = can_filter_enable_post_write, + },{ .name = "AFMR1", .addr = A_AFMR1, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR1", .addr = A_AFIR1, + .pre_write = can_filter_id_pre_write, + },{ .name = "AFMR2", .addr = A_AFMR2, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR2", .addr = A_AFIR2, + .pre_write = can_filter_id_pre_write, + },{ .name = "AFMR3", .addr = A_AFMR3, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR3", .addr = A_AFIR3, + .pre_write = can_filter_id_pre_write, + },{ .name = "AFMR4", .addr = A_AFMR4, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR4", .addr = A_AFIR4, + .pre_write = can_filter_id_pre_write, + } +}; + +static void xlnx_zynqmp_can_ptimer_cb(void *opaque) +{ + /* No action required on the timer rollover. */ +} + +static const MemoryRegionOps can_ops = { + .read = register_read_memory, + .write = register_write_memory, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void xlnx_zynqmp_can_reset_init(Object *obj, ResetType type) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(obj); + unsigned int i; + + for (i = R_RXFIFO_ID; i < ARRAY_SIZE(s->reg_info); ++i) { + register_reset(&s->reg_info[i]); + } + + ptimer_transaction_begin(s->can_timer); + ptimer_set_count(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); +} + +static void xlnx_zynqmp_can_reset_hold(Object *obj) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(obj); + unsigned int i; + + for (i = 0; i < R_RXFIFO_ID; ++i) { + register_reset(&s->reg_info[i]); + } + + /* + * Reset FIFOs when CAN model is reset. This will clear the fifo writes + * done by post_write which gets called from register_reset function, + * post_write handle will not be able to trigger tx because CAN will be + * disabled when software_reset_register is cleared first. + */ + fifo32_reset(&s->rx_fifo); + fifo32_reset(&s->tx_fifo); + fifo32_reset(&s->txhpb_fifo); +} + +static bool xlnx_zynqmp_can_can_receive(CanBusClientState *client) +{ + XlnxZynqMPCANState *s = container_of(client, XlnxZynqMPCANState, + bus_client); + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, SRST)) { + DB_PRINT(s, "Controller is in reset.\n"); + return false; + } else if ((ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) == 0) { + DB_PRINT(s, "Controller is disabled. Incoming messages" + " will be discarded.\n"); + return false; + } else { + return true; + } +} + +static ssize_t xlnx_zynqmp_can_receive(CanBusClientState *client, + const qemu_can_frame *buf, size_t buf_size) { + XlnxZynqMPCANState *s = container_of(client, XlnxZynqMPCANState, + bus_client); + const qemu_can_frame *frame = buf; + + DB_PRINT(s, "Incoming data.\n"); + + if (buf_size <= 0) { + DB_PRINT(s, "Junk data received.\n"); + return 0; + } + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, LBACK)) { + /* + * XlnxZynqMPCAN will not participate in normal bus communication + * and will not receive any messages transmitted by other CAN nodes. + */ + DB_PRINT(s, "Controller is in loopback mode. It will not" + " receive data.\n"); + + } else if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SNOOP)) { + /* Snoop Mode: Just keep the data. no response back. */ + update_rx_fifo(s, frame); + } else if ((ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP))) { + /* + * XlnxZynqMPCAN is in sleep mode. Any data on bus will bring it to wake + * up state. + */ + can_exit_sleep_mode(s); + update_rx_fifo(s, frame); + } else if ((ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP)) == 0) { + update_rx_fifo(s, frame); + } else { + DB_PRINT(s, "Cannot receive data as controller is not configured" + " correctly.\n"); + } + + return 1; +} + +static CanBusClientInfo can_xilinx_bus_client_info = { + .can_receive = xlnx_zynqmp_can_can_receive, + .receive = xlnx_zynqmp_can_receive, +}; + +static int xlnx_zynqmp_can_connect_to_bus(XlnxZynqMPCANState *s, + CanBusState *bus) +{ + s->bus_client.info = &can_xilinx_bus_client_info; + + if (can_bus_insert_client(bus, &s->bus_client) < 0) { + return -1; + } + return 0; +} + +static void xlnx_zynqmp_can_realize(DeviceState *dev, Error **errp) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(dev); + + if (s->canbus) { + if (xlnx_zynqmp_can_connect_to_bus(s, s->canbus) < 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + error_setg(errp, "%s: xlnx_zynqmp_can_connect_to_bus" + " failed.", path); + return; + } + + } else { + /* If no bus is set. */ + DB_PRINT(s, "Canbus property is not set.\n"); + } + + /* Create RX FIFO, TXFIFO, TXHPB storage. */ + fifo32_create(&s->rx_fifo, RXFIFO_SIZE); + fifo32_create(&s->tx_fifo, RXFIFO_SIZE); + fifo32_create(&s->txhpb_fifo, CAN_FRAME_SIZE); + + /* Allocate a new timer. */ + s->can_timer = ptimer_init(xlnx_zynqmp_can_ptimer_cb, s, + PTIMER_POLICY_DEFAULT); + + ptimer_transaction_begin(s->can_timer); + + ptimer_set_freq(s->can_timer, s->cfg.ext_clk_freq); + ptimer_set_limit(s->can_timer, CAN_TIMER_MAX, 1); + ptimer_run(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); +} + +static void xlnx_zynqmp_can_init(Object *obj) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + RegisterInfoArray *reg_array; + + memory_region_init(&s->iomem, obj, TYPE_XLNX_ZYNQMP_CAN, + XLNX_ZYNQMP_CAN_R_MAX * 4); + reg_array = register_init_block32(DEVICE(obj), can_regs_info, + ARRAY_SIZE(can_regs_info), + s->reg_info, s->regs, + &can_ops, + XLNX_ZYNQMP_CAN_ERR_DEBUG, + XLNX_ZYNQMP_CAN_R_MAX * 4); + + memory_region_add_subregion(&s->iomem, 0x00, &reg_array->mem); + sysbus_init_mmio(sbd, &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq); +} + +static const VMStateDescription vmstate_can = { + .name = TYPE_XLNX_ZYNQMP_CAN, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_FIFO32(rx_fifo, XlnxZynqMPCANState), + VMSTATE_FIFO32(tx_fifo, XlnxZynqMPCANState), + VMSTATE_FIFO32(txhpb_fifo, XlnxZynqMPCANState), + VMSTATE_UINT32_ARRAY(regs, XlnxZynqMPCANState, XLNX_ZYNQMP_CAN_R_MAX), + VMSTATE_PTIMER(can_timer, XlnxZynqMPCANState), + VMSTATE_END_OF_LIST(), + } +}; + +static Property xlnx_zynqmp_can_properties[] = { + DEFINE_PROP_UINT32("ext_clk_freq", XlnxZynqMPCANState, cfg.ext_clk_freq, + CAN_DEFAULT_CLOCK), + DEFINE_PROP_LINK("canbus", XlnxZynqMPCANState, canbus, TYPE_CAN_BUS, + CanBusState *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void xlnx_zynqmp_can_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.enter = xlnx_zynqmp_can_reset_init; + rc->phases.hold = xlnx_zynqmp_can_reset_hold; + dc->realize = xlnx_zynqmp_can_realize; + device_class_set_props(dc, xlnx_zynqmp_can_properties); + dc->vmsd = &vmstate_can; +} + +static const TypeInfo can_info = { + .name = TYPE_XLNX_ZYNQMP_CAN, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(XlnxZynqMPCANState), + .class_init = xlnx_zynqmp_can_class_init, + .instance_init = xlnx_zynqmp_can_init, +}; + +static void can_register_types(void) +{ + type_register_static(&can_info); +} + +type_init(can_register_types) diff --git a/hw/net/can/meson.build b/hw/net/can/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/net/can/meson.build +++ b/hw/net/can/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_CAN_SJA1000', if_true: files('can_sja1000.c')) softmmu_ss.add(when: 'CONFIG_CAN_PCI', if_true: files('can_kvaser_pci.c')) softmmu_ss.add(when: 'CONFIG_CAN_PCI', if_true: files('can_pcm3680_pci.c')) softmmu_ss.add(when: 'CONFIG_CAN_PCI', if_true: files('can_mioe3680_pci.c')) +softmmu_ss.add(when: 'CONFIG_XLNX_ZYNQMP', if_true: files('xlnx-zynqmp-can.c')) -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> Connect CAN0 and CAN1 on the ZynqMP. Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1597278668-339715-3-git-send-email-fnu.vikram@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-zynqmp.h | 8 ++++++++ hw/arm/xlnx-zcu102.c | 20 ++++++++++++++++++++ hw/arm/xlnx-zynqmp.c | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 62 insertions(+) diff --git a/include/hw/arm/xlnx-zynqmp.h b/include/hw/arm/xlnx-zynqmp.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-zynqmp.h +++ b/include/hw/arm/xlnx-zynqmp.h @@ -XXX,XX +XXX,XX @@ #include "hw/intc/arm_gic.h" #include "hw/net/cadence_gem.h" #include "hw/char/cadence_uart.h" +#include "hw/net/xlnx-zynqmp-can.h" #include "hw/ide/ahci.h" #include "hw/sd/sdhci.h" #include "hw/ssi/xilinx_spips.h" @@ -XXX,XX +XXX,XX @@ #include "hw/cpu/cluster.h" #include "target/arm/cpu.h" #include "qom/object.h" +#include "net/can_emu.h" #define TYPE_XLNX_ZYNQMP "xlnx,zynqmp" typedef struct XlnxZynqMPState XlnxZynqMPState; @@ -XXX,XX +XXX,XX @@ DECLARE_INSTANCE_CHECKER(XlnxZynqMPState, XLNX_ZYNQMP, #define XLNX_ZYNQMP_NUM_RPU_CPUS 2 #define XLNX_ZYNQMP_NUM_GEMS 4 #define XLNX_ZYNQMP_NUM_UARTS 2 +#define XLNX_ZYNQMP_NUM_CAN 2 +#define XLNX_ZYNQMP_CAN_REF_CLK (24 * 1000 * 1000) #define XLNX_ZYNQMP_NUM_SDHCI 2 #define XLNX_ZYNQMP_NUM_SPIS 2 #define XLNX_ZYNQMP_NUM_GDMA_CH 8 @@ -XXX,XX +XXX,XX @@ struct XlnxZynqMPState { CadenceGEMState gem[XLNX_ZYNQMP_NUM_GEMS]; CadenceUARTState uart[XLNX_ZYNQMP_NUM_UARTS]; + XlnxZynqMPCANState can[XLNX_ZYNQMP_NUM_CAN]; SysbusAHCIState sata; SDHCIState sdhci[XLNX_ZYNQMP_NUM_SDHCI]; XilinxSPIPS spi[XLNX_ZYNQMP_NUM_SPIS]; @@ -XXX,XX +XXX,XX @@ struct XlnxZynqMPState { bool virt; /* Has the RPU subsystem? */ bool has_rpu; + + /* CAN bus. */ + CanBusState *canbus[XLNX_ZYNQMP_NUM_CAN]; }; #endif diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/qtest.h" #include "sysemu/device_tree.h" #include "qom/object.h" +#include "net/can_emu.h" struct XlnxZCU102 { MachineState parent_obj; @@ -XXX,XX +XXX,XX @@ struct XlnxZCU102 { bool secure; bool virt; + CanBusState *canbus[XLNX_ZYNQMP_NUM_CAN]; + struct arm_boot_info binfo; }; typedef struct XlnxZCU102 XlnxZCU102; @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_init(MachineState *machine) object_property_set_bool(OBJECT(&s->soc), "virtualization", s->virt, &error_fatal); + for (i = 0; i < XLNX_ZYNQMP_NUM_CAN; i++) { + gchar *bus_name = g_strdup_printf("canbus%d", i); + + object_property_set_link(OBJECT(&s->soc), bus_name, + OBJECT(s->canbus[i]), &error_fatal); + g_free(bus_name); + } + qdev_realize(DEVICE(&s->soc), NULL, &error_fatal); /* Create and plug in the SD cards */ @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_machine_instance_init(Object *obj) "Set on/off to enable/disable emulating a " "guest CPU which implements the ARM " "Virtualization Extensions"); + object_property_add_link(obj, "xlnx-zcu102.canbus0", TYPE_CAN_BUS, + (Object **)&s->canbus[0], + object_property_allow_set_link, + 0); + + object_property_add_link(obj, "xlnx-zcu102.canbus1", TYPE_CAN_BUS, + (Object **)&s->canbus[1], + object_property_allow_set_link, + 0); } static void xlnx_zcu102_machine_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/xlnx-zynqmp.c b/hw/arm/xlnx-zynqmp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zynqmp.c +++ b/hw/arm/xlnx-zynqmp.c @@ -XXX,XX +XXX,XX @@ static const int uart_intr[XLNX_ZYNQMP_NUM_UARTS] = { 21, 22, }; +static const uint64_t can_addr[XLNX_ZYNQMP_NUM_CAN] = { + 0xFF060000, 0xFF070000, +}; + +static const int can_intr[XLNX_ZYNQMP_NUM_CAN] = { + 23, 24, +}; + static const uint64_t sdhci_addr[XLNX_ZYNQMP_NUM_SDHCI] = { 0xFF160000, 0xFF170000, }; @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_init(Object *obj) TYPE_CADENCE_UART); } + for (i = 0; i < XLNX_ZYNQMP_NUM_CAN; i++) { + object_initialize_child(obj, "can[*]", &s->can[i], + TYPE_XLNX_ZYNQMP_CAN); + } + object_initialize_child(obj, "sata", &s->sata, TYPE_SYSBUS_AHCI); for (i = 0; i < XLNX_ZYNQMP_NUM_SDHCI; i++) { @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp) gic_spi[uart_intr[i]]); } + for (i = 0; i < XLNX_ZYNQMP_NUM_CAN; i++) { + object_property_set_int(OBJECT(&s->can[i]), "ext_clk_freq", + XLNX_ZYNQMP_CAN_REF_CLK, &error_abort); + + object_property_set_link(OBJECT(&s->can[i]), "canbus", + OBJECT(s->canbus[i]), &error_fatal); + + sysbus_realize(SYS_BUS_DEVICE(&s->can[i]), &err); + if (err) { + error_propagate(errp, err); + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->can[i]), 0, can_addr[i]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->can[i]), 0, + gic_spi[can_intr[i]]); + } + object_property_set_int(OBJECT(&s->sata), "num-ports", SATA_NUM_PORTS, &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->sata), errp)) { @@ -XXX,XX +XXX,XX @@ static Property xlnx_zynqmp_props[] = { DEFINE_PROP_BOOL("has_rpu", XlnxZynqMPState, has_rpu, false), DEFINE_PROP_LINK("ddr-ram", XlnxZynqMPState, ddr_ram, TYPE_MEMORY_REGION, MemoryRegion *), + DEFINE_PROP_LINK("canbus0", XlnxZynqMPState, canbus[0], TYPE_CAN_BUS, + CanBusState *), + DEFINE_PROP_LINK("canbus1", XlnxZynqMPState, canbus[1], TYPE_CAN_BUS, + CanBusState *), DEFINE_PROP_END_OF_LIST() }; -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> The QTests perform five tests on the Xilinx ZynqMP CAN controller: Tests the CAN controller in loopback, sleep and snoop mode. Tests filtering of incoming CAN messages. Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1597278668-339715-4-git-send-email-fnu.vikram@xilinx.com [PMM: updated to meson build system] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/xlnx-can-test.c | 359 ++++++++++++++++++++++++++++++++++++ tests/qtest/meson.build | 1 + 2 files changed, 360 insertions(+) create mode 100644 tests/qtest/xlnx-can-test.c diff --git a/tests/qtest/xlnx-can-test.c b/tests/qtest/xlnx-can-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/xlnx-can-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTests for the Xilinx ZynqMP CAN controller. + * + * Copyright (c) 2020 Xilinx Inc. + * + * Written-by: Vikram Garhwal<fnu.vikram@xilinx.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "libqos/libqtest.h" + +/* Base address. */ +#define CAN0_BASE_ADDR 0xFF060000 +#define CAN1_BASE_ADDR 0xFF070000 + +/* Register addresses. */ +#define R_SRR_OFFSET 0x00 +#define R_MSR_OFFSET 0x04 +#define R_SR_OFFSET 0x18 +#define R_ISR_OFFSET 0x1C +#define R_ICR_OFFSET 0x24 +#define R_TXID_OFFSET 0x30 +#define R_TXDLC_OFFSET 0x34 +#define R_TXDATA1_OFFSET 0x38 +#define R_TXDATA2_OFFSET 0x3C +#define R_RXID_OFFSET 0x50 +#define R_RXDLC_OFFSET 0x54 +#define R_RXDATA1_OFFSET 0x58 +#define R_RXDATA2_OFFSET 0x5C +#define R_AFR 0x60 +#define R_AFMR1 0x64 +#define R_AFIR1 0x68 +#define R_AFMR2 0x6C +#define R_AFIR2 0x70 +#define R_AFMR3 0x74 +#define R_AFIR3 0x78 +#define R_AFMR4 0x7C +#define R_AFIR4 0x80 + +/* CAN modes. */ +#define CONFIG_MODE 0x00 +#define NORMAL_MODE 0x00 +#define LOOPBACK_MODE 0x02 +#define SNOOP_MODE 0x04 +#define SLEEP_MODE 0x01 +#define ENABLE_CAN (1 << 1) +#define STATUS_NORMAL_MODE (1 << 3) +#define STATUS_LOOPBACK_MODE (1 << 1) +#define STATUS_SNOOP_MODE (1 << 12) +#define STATUS_SLEEP_MODE (1 << 2) +#define ISR_TXOK (1 << 1) +#define ISR_RXOK (1 << 4) + +static void match_rx_tx_data(uint32_t *buf_tx, uint32_t *buf_rx, + uint8_t can_timestamp) +{ + uint16_t size = 0; + uint8_t len = 4; + + while (size < len) { + if (R_RXID_OFFSET + 4 * size == R_RXDLC_OFFSET) { + g_assert_cmpint(buf_rx[size], ==, buf_tx[size] + can_timestamp); + } else { + g_assert_cmpint(buf_rx[size], ==, buf_tx[size]); + } + + size++; + } +} + +static void read_data(QTestState *qts, uint64_t can_base_addr, uint32_t *buf_rx) +{ + uint32_t int_status; + + /* Read the interrupt on CAN rx. */ + int_status = qtest_readl(qts, can_base_addr + R_ISR_OFFSET) & ISR_RXOK; + + g_assert_cmpint(int_status, ==, ISR_RXOK); + + /* Read the RX register data for CAN. */ + buf_rx[0] = qtest_readl(qts, can_base_addr + R_RXID_OFFSET); + buf_rx[1] = qtest_readl(qts, can_base_addr + R_RXDLC_OFFSET); + buf_rx[2] = qtest_readl(qts, can_base_addr + R_RXDATA1_OFFSET); + buf_rx[3] = qtest_readl(qts, can_base_addr + R_RXDATA2_OFFSET); + + /* Clear the RX interrupt. */ + qtest_writel(qts, CAN1_BASE_ADDR + R_ICR_OFFSET, ISR_RXOK); +} + +static void send_data(QTestState *qts, uint64_t can_base_addr, uint32_t *buf_tx) +{ + uint32_t int_status; + + /* Write the TX register data for CAN. */ + qtest_writel(qts, can_base_addr + R_TXID_OFFSET, buf_tx[0]); + qtest_writel(qts, can_base_addr + R_TXDLC_OFFSET, buf_tx[1]); + qtest_writel(qts, can_base_addr + R_TXDATA1_OFFSET, buf_tx[2]); + qtest_writel(qts, can_base_addr + R_TXDATA2_OFFSET, buf_tx[3]); + + /* Read the interrupt on CAN for tx. */ + int_status = qtest_readl(qts, can_base_addr + R_ISR_OFFSET) & ISR_TXOK; + + g_assert_cmpint(int_status, ==, ISR_TXOK); + + /* Clear the interrupt for tx. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_ICR_OFFSET, ISR_TXOK); +} + +/* + * This test will be transferring data from CAN0 and CAN1 through canbus. CAN0 + * initiate the data transfer to can-bus, CAN1 receives the data. Test compares + * the data sent from CAN0 with received on CAN1. + */ +static void test_can_bus(void) +{ + uint32_t buf_tx[4] = { 0xFF, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0 and CAN1. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 and CAN1 are in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + send_data(qts, CAN0_BASE_ADDR, buf_tx); + + read_data(qts, CAN1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +/* + * This test is performing loopback mode on CAN0 and CAN1. Data sent from TX of + * each CAN0 and CAN1 are compared with RX register data for respective CAN. + */ +static void test_can_loopback(void) +{ + uint32_t buf_tx[4] = { 0xFF, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0 in loopback mode. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, LOOPBACK_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + /* Check here if CAN0 is set in loopback mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + + g_assert_cmpint(status, ==, STATUS_LOOPBACK_MODE); + + send_data(qts, CAN0_BASE_ADDR, buf_tx); + read_data(qts, CAN0_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, 0); + + /* Configure the CAN1 in loopback mode. */ + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, LOOPBACK_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + /* Check here if CAN1 is set in loopback mode. */ + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + + g_assert_cmpint(status, ==, STATUS_LOOPBACK_MODE); + + send_data(qts, CAN1_BASE_ADDR, buf_tx); + read_data(qts, CAN1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, 0); + + qtest_quit(qts); +} + +/* + * Enable filters for CAN1. This will filter incoming messages with ID. In this + * test message will pass through filter 2. + */ +static void test_can_filter(void) +{ + uint32_t buf_tx[4] = { 0x14, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0 and CAN1. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 and CAN1 are in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + /* Set filter for CAN1 for incoming messages. */ + qtest_writel(qts, CAN1_BASE_ADDR + R_AFR, 0x0); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR1, 0xF7); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR1, 0x121F); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR2, 0x5431); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR2, 0x14); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR3, 0x1234); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR3, 0x5431); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR4, 0xFFF); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR4, 0x1234); + + qtest_writel(qts, CAN1_BASE_ADDR + R_AFR, 0xF); + + send_data(qts, CAN0_BASE_ADDR, buf_tx); + + read_data(qts, CAN1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +/* Testing sleep mode on CAN0 while CAN1 is in normal mode. */ +static void test_can_sleepmode(void) +{ + uint32_t buf_tx[4] = { 0x14, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, SLEEP_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 is in SLEEP mode and CAN1 in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_SLEEP_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + send_data(qts, CAN1_BASE_ADDR, buf_tx); + + /* + * Once CAN1 sends data on can-bus. CAN0 should exit sleep mode. + * Check the CAN0 status now. It should exit the sleep mode and receive the + * incoming data. + */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + read_data(qts, CAN0_BASE_ADDR, buf_rx); + + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +/* Testing Snoop mode on CAN0 while CAN1 is in normal mode. */ +static void test_can_snoopmode(void) +{ + uint32_t buf_tx[4] = { 0x14, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, SNOOP_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 is in SNOOP mode and CAN1 in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_SNOOP_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + send_data(qts, CAN1_BASE_ADDR, buf_tx); + + read_data(qts, CAN0_BASE_ADDR, buf_rx); + + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +int main(int argc, char **argv) +{ + g_test_init(&argc, &argv, NULL); + + qtest_add_func("/net/can/can_bus", test_can_bus); + qtest_add_func("/net/can/can_loopback", test_can_loopback); + qtest_add_func("/net/can/can_filter", test_can_filter); + qtest_add_func("/net/can/can_test_snoopmode", test_can_snoopmode); + qtest_add_func("/net/can/can_test_sleepmode", test_can_sleepmode); + + return g_test_run(); +} diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qtests_aarch64 = \ (config_all_devices.has_key('CONFIG_TPM_TIS_SYSBUS') ? ['tpm-tis-device-swtpm-test'] : []) + \ ['numa-test', 'boot-serial-test', + 'xlnx-can-test', 'migration-test'] qtests_s390x = \ -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1597278668-339715-5-git-send-email-fnu.vikram@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/net/opencores_eth.c Devices ------- +Xilinx CAN +M: Vikram Garhwal <fnu.vikram@xilinx.com> +M: Francisco Iglesias <francisco.iglesias@xilinx.com> +S: Maintained +F: hw/net/can/xlnx-* +F: include/hw/net/xlnx-* +F: tests/qtest/xlnx-can-test* + EDU M: Jiri Slaby <jslaby@suse.cz> S: Maintained -- 2.20.1