ARM pullreq; contains some patches that arrived while I was on holiday, plus the series I sent off before going away, which got reviewed while I was away. thanks -- PMM The following changes since commit c077a998eb3fcae2d048e3baeb5bc592d30fddde: Merge remote-tracking branch 'remotes/riku/tags/pull-linux-user-20170531' into staging (2017-06-01 15:50:40 +0100) are available in the git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20170601 for you to fetch changes up to cdc58be430b0bdeaef282e2e70f8135ae531616d: hw/arm/virt: fdt: generate distance-map when needed (2017-06-01 17:27:07 +0100) ---------------------------------------------------------------- target-arm queue: * virt: numa: provide ACPI distance info when needed * aspeed: fix i2c controller bugs * aspeed: add temperature sensor device * M profile: support MPU * gicv3: fix mishandling of BPR1, VBPR1 * load_uboot_image: don't assume a full header read * libvixl: Correct build failures on NetBSD ---------------------------------------------------------------- Andrew Jones (3): load_uboot_image: don't assume a full header read hw/arm/virt-acpi-build: build SLIT when needed hw/arm/virt: fdt: generate distance-map when needed Cédric Le Goater (6): aspeed/i2c: improve command handling aspeed/i2c: handle LAST command under the RX command aspeed/i2c: introduce a state machine aspeed: add some I2C devices to the Aspeed machines hw/misc: add a TMP42{1,2,3} device model aspeed: add a temp sensor device on I2C bus 3 Kamil Rytarowski (1): libvixl: Correct build failures on NetBSD Michael Davidsaver (4): armv7m: Improve "-d mmu" tracing for PMSAv7 MPU armv7m: Implement M profile default memory map armv7m: Classify faults as MemManage or BusFault arm: add MPU support to M profile CPUs Peter Maydell (12): hw/intc/arm_gicv3_cpuif: Fix reset value for VMCR_EL2.VBPR1 hw/intc/arm_gicv3_cpuif: Don't let BPR be set below its minimum hw/intc/arm_gicv3_cpuif: Fix priority masking for NS BPR1 arm: Use the mmu_idx we're passed in arm_cpu_do_unaligned_access() arm: Add support for M profile CPUs having different MMU index semantics arm: Use different ARMMMUIdx values for M profile arm: Clean up handling of no-MPU PMSA CPUs arm: Don't clear ARM_FEATURE_PMSA for no-mpu configs arm: Don't let no-MPU PMSA cores write to SCTLR.M arm: Remove unnecessary check on cpu->pmsav7_dregion arm: All M profile cores are PMSA arm: Implement HFNMIENA support for M profile MPU Wei Huang (1): target/arm: clear PMUVER field of AA64DFR0 when vPMU=off disas/libvixl/Makefile.objs | 3 + hw/misc/Makefile.objs | 1 + target/arm/cpu.h | 118 ++++++++++-- target/arm/translate.h | 2 +- hw/arm/aspeed.c | 36 ++++ hw/arm/virt-acpi-build.c | 4 + hw/arm/virt.c | 21 +++ hw/core/loader.c | 3 +- hw/i2c/aspeed_i2c.c | 65 ++++++- hw/intc/arm_gicv3_cpuif.c | 50 ++++- hw/intc/armv7m_nvic.c | 104 +++++++++++ hw/misc/tmp421.c | 401 ++++++++++++++++++++++++++++++++++++++++ target/arm/cpu.c | 28 ++- target/arm/helper.c | 338 ++++++++++++++++++++++----------- target/arm/machine.c | 7 +- target/arm/op_helper.c | 3 +- target/arm/translate-a64.c | 18 +- target/arm/translate.c | 14 +- default-configs/arm-softmmu.mak | 1 + 19 files changed, 1060 insertions(+), 157 deletions(-) create mode 100644 hw/misc/tmp421.c From: Kamil Rytarowski <n54@gmx.com> Ensure that C99 macros are defined regardless of the inclusion order of headers in vixl. This is required at least on NetBSD. The vixl/globals.h headers defines __STDC_CONSTANT_MACROS and must be included before other system headers. This file defines unconditionally the following macros, without altering the original sources: - __STDC_CONSTANT_MACROS - __STDC_LIMIT_MACROS - __STDC_FORMAT_MACROS Signed-off-by: Kamil Rytarowski <n54@gmx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20170514051820.15985-1-n54@gmx.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- disas/libvixl/Makefile.objs | 3 +++ 1 file changed, 3 insertions(+) diff --git a/disas/libvixl/Makefile.objs b/disas/libvixl/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/disas/libvixl/Makefile.objs +++ b/disas/libvixl/Makefile.objs @@ -XXX,XX +XXX,XX @@ libvixl_OBJS = vixl/utils.o \ # The -Wno-sign-compare is needed only for gcc 4.6, which complains about # some signed-unsigned equality comparisons which later gcc versions do not. $(addprefix $(obj)/,$(libvixl_OBJS)): QEMU_CFLAGS := -I$(SRC_PATH)/disas/libvixl $(QEMU_CFLAGS) -Wno-sign-compare +# Ensure that C99 macros are defined regardless of the inclusion order of +# headers in vixl. This is required at least on NetBSD. +$(addprefix $(obj)/,$(libvixl_OBJS)): QEMU_CFLAGS += -D__STDC_CONSTANT_MACROS -D__STDC_LIMIT_MACROS -D__STDC_FORMAT_MACROS common-obj-$(CONFIG_ARM_A64_DIS) += $(libvixl_OBJS) -- 2.7.4 From: Andrew Jones <drjones@redhat.com> Don't allow load_uboot_image() to proceed when less bytes than header-size was read. Signed-off-by: Andrew Jones <drjones@redhat.com> Message-id: 20170524091315.20284-1-drjones@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/loader.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/core/loader.c b/hw/core/loader.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/loader.c +++ b/hw/core/loader.c @@ -XXX,XX +XXX,XX @@ static int load_uboot_image(const char *filename, hwaddr *ep, hwaddr *loadaddr, return -1; size = read(fd, hdr, sizeof(uboot_image_header_t)); - if (size < 0) + if (size < sizeof(uboot_image_header_t)) { goto out; + } bswap_uboot_header(hdr); -- 2.7.4 We were setting the VBPR1 field of VMCR_EL2 to icv_min_vbpr() on reset, but this is not correct. The field should reset to the minimum value of ICV_BPR0_EL1 plus one. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493226792-3237-2-git-send-email-peter.maydell@linaro.org --- hw/intc/arm_gicv3_cpuif.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static void icc_reset(CPUARMState *env, const ARMCPRegInfo *ri) cs->ich_hcr_el2 = 0; memset(cs->ich_lr_el2, 0, sizeof(cs->ich_lr_el2)); cs->ich_vmcr_el2 = ICH_VMCR_EL2_VFIQEN | - (icv_min_vbpr(cs) << ICH_VMCR_EL2_VBPR1_SHIFT) | + ((icv_min_vbpr(cs) + 1) << ICH_VMCR_EL2_VBPR1_SHIFT) | (icv_min_vbpr(cs) << ICH_VMCR_EL2_VBPR0_SHIFT); } -- 2.7.4 icc_bpr_write() was not enforcing that writing a value below the minimum for the BPR should behave as if the BPR was set to the minimum value. This doesn't make a difference for the secure BPRs (since we define the minimum for the QEMU implementation as zero) but did mean we were allowing the NS BPR1 to be set to 0 when 1 should be the lowest value. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493226792-3237-3-git-send-email-peter.maydell@linaro.org --- hw/intc/arm_gicv3_cpuif.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static void icc_bpr_write(CPUARMState *env, const ARMCPRegInfo *ri, { GICv3CPUState *cs = icc_cs_from_env(env); int grp = (ri->crm == 8) ? GICV3_G0 : GICV3_G1; + uint64_t minval; if (icv_access(env, grp == GICV3_G0 ? HCR_FMO : HCR_IMO)) { icv_bpr_write(env, ri, value); @@ -XXX,XX +XXX,XX @@ static void icc_bpr_write(CPUARMState *env, const ARMCPRegInfo *ri, return; } + minval = (grp == GICV3_G1NS) ? GIC_MIN_BPR_NS : GIC_MIN_BPR; + if (value < minval) { + value = minval; + } + cs->icc_bpr[grp] = value & 7; gicv3_cpuif_update(cs); } -- 2.7.4 When we calculate the mask to use to get the group priority from an interrupt priority, the way that NS BPR1 is handled differs from how BPR0 and S BPR1 work -- a BPR1 value of 1 means the group priority is in bits [7:1], whereas for BPR0 and S BPR1 this is indicated by a 0 BPR value. Subtract 1 from the BPR value before creating the mask if we're using the NS BPR value, for both hardware and virtual interrupts, as the GICv3 pseudocode does, and fix the comments accordingly. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493226792-3237-4-git-send-email-peter.maydell@linaro.org --- hw/intc/arm_gicv3_cpuif.c | 42 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 38 insertions(+), 4 deletions(-) diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static uint32_t icv_gprio_mask(GICv3CPUState *cs, int group) { /* Return a mask word which clears the subpriority bits from * a priority value for a virtual interrupt in the specified group. - * This depends on the VBPR value: + * This depends on the VBPR value. + * If using VBPR0 then: * a BPR of 0 means the group priority bits are [7:1]; * a BPR of 1 means they are [7:2], and so on down to * a BPR of 7 meaning no group priority bits at all. + * If using VBPR1 then: + * a BPR of 0 is impossible (the minimum value is 1) + * a BPR of 1 means the group priority bits are [7:1]; + * a BPR of 2 means they are [7:2], and so on down to + * a BPR of 7 meaning the group priority is [7]. + * * Which BPR to use depends on the group of the interrupt and * the current ICH_VMCR_EL2.VCBPR settings. + * + * This corresponds to the VGroupBits() pseudocode. */ + int bpr; + if (group == GICV3_G1NS && cs->ich_vmcr_el2 & ICH_VMCR_EL2_VCBPR) { group = GICV3_G0; } - return ~0U << (read_vbpr(cs, group) + 1); + bpr = read_vbpr(cs, group); + if (group == GICV3_G1NS) { + assert(bpr > 0); + bpr--; + } + + return ~0U << (bpr + 1); } static bool icv_hppi_can_preempt(GICv3CPUState *cs, uint64_t lr) @@ -XXX,XX +XXX,XX @@ static uint32_t icc_gprio_mask(GICv3CPUState *cs, int group) { /* Return a mask word which clears the subpriority bits from * a priority value for an interrupt in the specified group. - * This depends on the BPR value: + * This depends on the BPR value. For CBPR0 (S or NS): * a BPR of 0 means the group priority bits are [7:1]; * a BPR of 1 means they are [7:2], and so on down to * a BPR of 7 meaning no group priority bits at all. + * For CBPR1 NS: + * a BPR of 0 is impossible (the minimum value is 1) + * a BPR of 1 means the group priority bits are [7:1]; + * a BPR of 2 means they are [7:2], and so on down to + * a BPR of 7 meaning the group priority is [7]. + * * Which BPR to use depends on the group of the interrupt and * the current ICC_CTLR.CBPR settings. + * + * This corresponds to the GroupBits() pseudocode. */ + int bpr; + if ((group == GICV3_G1 && cs->icc_ctlr_el1[GICV3_S] & ICC_CTLR_EL1_CBPR) || (group == GICV3_G1NS && cs->icc_ctlr_el1[GICV3_NS] & ICC_CTLR_EL1_CBPR)) { group = GICV3_G0; } - return ~0U << ((cs->icc_bpr[group] & 7) + 1); + bpr = cs->icc_bpr[group] & 7; + + if (group == GICV3_G1NS) { + assert(bpr > 0); + bpr--; + } + + return ~0U << (bpr + 1); } static bool icc_no_enabled_hppi(GICv3CPUState *cs) -- 2.7.4 From: Wei Huang <wei@redhat.com> The PMUv3 driver of linux kernel (in arch/arm64/kernel/perf_event.c) relies on the PMUVER field of id_aa64dfr0_el1 to decide if PMU support is present or not. This patch clears the PMUVER field under TCG mode when vPMU=off. Without it, PMUv3 will init insider guest VMs even with vPMU=off. This patch also removes a redundant line inside the if-statement. Signed-off-by: Wei Huang <wei@redhat.com> Message-id: 1495123889-32301-1-git-send-email-wei@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) } if (!cpu->has_pmu) { - cpu->has_pmu = false; unset_feature(env, ARM_FEATURE_PMU); + cpu->id_aa64dfr0 &= ~0xf00; } if (!arm_feature(env, ARM_FEATURE_EL2)) { -- 2.7.4 When identifying the DFSR format for an alignment fault, use the mmu index that we are passed, rather than calling cpu_mmu_index() to get the mmu index for the current CPU state. This doesn't actually make any difference since the only cases where the current MMU index differs from the index used for the load are the "unprivileged load/store" instructions, and in that case the mmu index may differ but the translation regime is the same (apart from the "use from Hyp mode" case which is UNPREDICTABLE). However it's the more logical thing to do. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-2-git-send-email-peter.maydell@linaro.org --- target/arm/op_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr, /* the DFSR for an alignment fault depends on whether we're using * the LPAE long descriptor format, or the short descriptor format */ - if (arm_s1_regime_using_lpae_format(env, cpu_mmu_index(env, false))) { + if (arm_s1_regime_using_lpae_format(env, mmu_idx)) { env->exception.fsr = (1 << 9) | 0x21; } else { env->exception.fsr = 0x1; -- 2.7.4 The M profile CPU's MPU has an awkward corner case which we would like to implement with a different MMU index. We can avoid having to bump the number of MMU modes ARM uses, because some of our existing MMU indexes are only used by non-M-profile CPUs, so we can borrow one. To avoid that getting too confusing, clean up the code to try to keep the two meanings of the index separate. Instead of ARMMMUIdx enum values being identical to core QEMU MMU index values, they are now the core index values with some high bits set. Any particular CPU always uses the same high bits (so eventually A profile cores and M profile cores will use different bits). New functions arm_to_core_mmu_idx() and core_to_arm_mmu_idx() convert between the two. In general core index values are stored in 'int' types, and ARM values are stored in ARMMMUIdx types. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1493122030-32191-3-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 71 ++++++++++++++++----- target/arm/translate.h | 2 +- target/arm/helper.c | 151 ++++++++++++++++++++++++--------------------- target/arm/op_helper.c | 3 +- target/arm/translate-a64.c | 18 ++++-- target/arm/translate.c | 10 +-- 6 files changed, 156 insertions(+), 99 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, * for the accesses done as part of a stage 1 page table walk, rather than * having to walk the stage 2 page table over and over.) * + * The ARMMMUIdx and the mmu index value used by the core QEMU TLB code + * are not quite the same -- different CPU types (most notably M profile + * vs A/R profile) would like to use MMU indexes with different semantics, + * but since we don't ever need to use all of those in a single CPU we + * can avoid setting NB_MMU_MODES to more than 8. The lower bits of + * ARMMMUIdx are the core TLB mmu index, and the higher bits are always + * the same for any particular CPU. + * Variables of type ARMMUIdx are always full values, and the core + * index values are in variables of type 'int'. + * * Our enumeration includes at the end some entries which are not "true" * mmu_idx values in that they don't have corresponding TLBs and are only * valid for doing slow path page table walks. @@ -XXX,XX +XXX,XX @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, * of the AT/ATS operations. * The values used are carefully arranged to make mmu_idx => EL lookup easy. */ +#define ARM_MMU_IDX_A 0x10 /* A profile (and M profile, for the moment) */ +#define ARM_MMU_IDX_NOTLB 0x20 /* does not have a TLB */ + +#define ARM_MMU_IDX_TYPE_MASK (~0x7) +#define ARM_MMU_IDX_COREIDX_MASK 0x7 + typedef enum ARMMMUIdx { - ARMMMUIdx_S12NSE0 = 0, - ARMMMUIdx_S12NSE1 = 1, - ARMMMUIdx_S1E2 = 2, - ARMMMUIdx_S1E3 = 3, - ARMMMUIdx_S1SE0 = 4, - ARMMMUIdx_S1SE1 = 5, - ARMMMUIdx_S2NS = 6, + ARMMMUIdx_S12NSE0 = 0 | ARM_MMU_IDX_A, + ARMMMUIdx_S12NSE1 = 1 | ARM_MMU_IDX_A, + ARMMMUIdx_S1E2 = 2 | ARM_MMU_IDX_A, + ARMMMUIdx_S1E3 = 3 | ARM_MMU_IDX_A, + ARMMMUIdx_S1SE0 = 4 | ARM_MMU_IDX_A, + ARMMMUIdx_S1SE1 = 5 | ARM_MMU_IDX_A, + ARMMMUIdx_S2NS = 6 | ARM_MMU_IDX_A, /* Indexes below here don't have TLBs and are used only for AT system * instructions or for the first stage of an S12 page table walk. */ - ARMMMUIdx_S1NSE0 = 7, - ARMMMUIdx_S1NSE1 = 8, + ARMMMUIdx_S1NSE0 = 0 | ARM_MMU_IDX_NOTLB, + ARMMMUIdx_S1NSE1 = 1 | ARM_MMU_IDX_NOTLB, } ARMMMUIdx; +/* Bit macros for the core-mmu-index values for each index, + * for use when calling tlb_flush_by_mmuidx() and friends. + */ +typedef enum ARMMMUIdxBit { + ARMMMUIdxBit_S12NSE0 = 1 << 0, + ARMMMUIdxBit_S12NSE1 = 1 << 1, + ARMMMUIdxBit_S1E2 = 1 << 2, + ARMMMUIdxBit_S1E3 = 1 << 3, + ARMMMUIdxBit_S1SE0 = 1 << 4, + ARMMMUIdxBit_S1SE1 = 1 << 5, + ARMMMUIdxBit_S2NS = 1 << 6, +} ARMMMUIdxBit; + #define MMU_USER_IDX 0 +static inline int arm_to_core_mmu_idx(ARMMMUIdx mmu_idx) +{ + return mmu_idx & ARM_MMU_IDX_COREIDX_MASK; +} + +static inline ARMMMUIdx core_to_arm_mmu_idx(CPUARMState *env, int mmu_idx) +{ + return mmu_idx | ARM_MMU_IDX_A; +} + /* Return the exception level we're running at if this is our mmu_idx */ static inline int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx) { - assert(mmu_idx < ARMMMUIdx_S2NS); - return mmu_idx & 3; + switch (mmu_idx & ARM_MMU_IDX_TYPE_MASK) { + case ARM_MMU_IDX_A: + return mmu_idx & 3; + default: + g_assert_not_reached(); + } } /* Determine the current mmu_idx to use for normal loads/stores */ @@ -XXX,XX +XXX,XX @@ static inline int cpu_mmu_index(CPUARMState *env, bool ifetch) int el = arm_current_el(env); if (el < 2 && arm_is_secure_below_el3(env)) { - return ARMMMUIdx_S1SE0 + el; + return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0 + el); } return el; } @@ -XXX,XX +XXX,XX @@ static inline uint32_t arm_regime_tbi1(CPUARMState *env, ARMMMUIdx mmu_idx) static inline void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *flags) { - ARMMMUIdx mmu_idx = cpu_mmu_index(env, false); + ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); if (is_a64(env)) { *pc = env->pc; *flags = ARM_TBFLAG_AARCH64_STATE_MASK; @@ -XXX,XX +XXX,XX @@ static inline void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, << ARM_TBFLAG_XSCALE_CPAR_SHIFT); } - *flags |= (mmu_idx << ARM_TBFLAG_MMUIDX_SHIFT); + *flags |= (arm_to_core_mmu_idx(mmu_idx) << ARM_TBFLAG_MMUIDX_SHIFT); /* The SS_ACTIVE and PSTATE_SS bits correspond to the state machine * states defined in the ARM ARM for software singlestep: diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline int arm_dc_feature(DisasContext *dc, int feature) static inline int get_mem_index(DisasContext *s) { - return s->mmu_idx; + return arm_to_core_mmu_idx(s->mmu_idx); } /* Function used to determine the target exception EL when otherwise not known diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri, CPUState *cs = ENV_GET_CPU(env); tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0) | - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0 | + ARMMMUIdxBit_S2NS); } static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri, CPUState *cs = ENV_GET_CPU(env); tlb_flush_by_mmuidx_all_cpus_synced(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0) | - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0 | + ARMMMUIdxBit_S2NS); } static void tlbiipas2_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbiipas2_write(CPUARMState *env, const ARMCPRegInfo *ri, pageaddr = sextract64(value << 12, 0, 40); - tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S2NS)); + tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S2NS); } static void tlbiipas2_is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbiipas2_is_write(CPUARMState *env, const ARMCPRegInfo *ri, pageaddr = sextract64(value << 12, 0, 40); tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S2NS); } static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, { CPUState *cs = ENV_GET_CPU(env); - tlb_flush_by_mmuidx(cs, (1 << ARMMMUIdx_S1E2)); + tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_S1E2); } static void tlbiall_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbiall_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, { CPUState *cs = ENV_GET_CPU(env); - tlb_flush_by_mmuidx_all_cpus_synced(cs, (1 << ARMMMUIdx_S1E2)); + tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_S1E2); } static void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, CPUState *cs = ENV_GET_CPU(env); uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12); - tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S1E2)); + tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S1E2); } static void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12); tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S1E2)); + ARMMMUIdxBit_S1E2); } static const ARMCPRegInfo cp_reginfo[] = { @@ -XXX,XX +XXX,XX @@ static void vttbr_write(CPUARMState *env, const ARMCPRegInfo *ri, /* Accesses to VTTBR may change the VMID so we must flush the TLB. */ if (raw_read(env, ri) != value) { tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0) | - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0 | + ARMMMUIdxBit_S2NS); raw_write(env, ri, value); } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vmalle1_write(CPUARMState *env, const ARMCPRegInfo *ri, if (arm_is_secure_below_el3(env)) { tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S1SE1) | - (1 << ARMMMUIdx_S1SE0)); + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); } else { tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, if (sec) { tlb_flush_by_mmuidx_all_cpus_synced(cs, - (1 << ARMMMUIdx_S1SE1) | - (1 << ARMMMUIdx_S1SE0)); + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); } else { tlb_flush_by_mmuidx_all_cpus_synced(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle1_write(CPUARMState *env, const ARMCPRegInfo *ri, if (arm_is_secure_below_el3(env)) { tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S1SE1) | - (1 << ARMMMUIdx_S1SE0)); + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); } else { if (arm_feature(env, ARM_FEATURE_EL2)) { tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0) | - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0 | + ARMMMUIdxBit_S2NS); } else { tlb_flush_by_mmuidx(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); } } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle2_write(CPUARMState *env, const ARMCPRegInfo *ri, ARMCPU *cpu = arm_env_get_cpu(env); CPUState *cs = CPU(cpu); - tlb_flush_by_mmuidx(cs, (1 << ARMMMUIdx_S1E2)); + tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_S1E2); } static void tlbi_aa64_alle3_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle3_write(CPUARMState *env, const ARMCPRegInfo *ri, ARMCPU *cpu = arm_env_get_cpu(env); CPUState *cs = CPU(cpu); - tlb_flush_by_mmuidx(cs, (1 << ARMMMUIdx_S1E3)); + tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_S1E3); } static void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, if (sec) { tlb_flush_by_mmuidx_all_cpus_synced(cs, - (1 << ARMMMUIdx_S1SE1) | - (1 << ARMMMUIdx_S1SE0)); + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); } else if (has_el2) { tlb_flush_by_mmuidx_all_cpus_synced(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0) | - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0 | + ARMMMUIdxBit_S2NS); } else { tlb_flush_by_mmuidx_all_cpus_synced(cs, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle2is_write(CPUARMState *env, const ARMCPRegInfo *ri, { CPUState *cs = ENV_GET_CPU(env); - tlb_flush_by_mmuidx_all_cpus_synced(cs, (1 << ARMMMUIdx_S1E2)); + tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_S1E2); } static void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri, { CPUState *cs = ENV_GET_CPU(env); - tlb_flush_by_mmuidx_all_cpus_synced(cs, (1 << ARMMMUIdx_S1E3)); + tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_S1E3); } static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, if (arm_is_secure_below_el3(env)) { tlb_flush_page_by_mmuidx(cs, pageaddr, - (1 << ARMMMUIdx_S1SE1) | - (1 << ARMMMUIdx_S1SE0)); + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); } else { tlb_flush_page_by_mmuidx(cs, pageaddr, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri, CPUState *cs = CPU(cpu); uint64_t pageaddr = sextract64(value << 12, 0, 56); - tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S1E2)); + tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S1E2); } static void tlbi_aa64_vae3_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae3_write(CPUARMState *env, const ARMCPRegInfo *ri, CPUState *cs = CPU(cpu); uint64_t pageaddr = sextract64(value << 12, 0, 56); - tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S1E3)); + tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S1E3); } static void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, if (sec) { tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S1SE1) | - (1 << ARMMMUIdx_S1SE0)); + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); } else { tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S12NSE1) | - (1 << ARMMMUIdx_S12NSE0)); + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); } } @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t pageaddr = sextract64(value << 12, 0, 56); tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S1E2)); + ARMMMUIdxBit_S1E2); } static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t pageaddr = sextract64(value << 12, 0, 56); tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S1E3)); + ARMMMUIdxBit_S1E3); } static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri, pageaddr = sextract64(value << 12, 0, 48); - tlb_flush_page_by_mmuidx(cs, pageaddr, (1 << ARMMMUIdx_S2NS)); + tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_S2NS); } static void tlbi_aa64_ipas2e1is_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_ipas2e1is_write(CPUARMState *env, const ARMCPRegInfo *ri, pageaddr = sextract64(value << 12, 0, 48); tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - (1 << ARMMMUIdx_S2NS)); + ARMMMUIdxBit_S2NS); } static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static inline TCR *regime_tcr(CPUARMState *env, ARMMMUIdx mmu_idx) return &env->cp15.tcr_el[regime_el(env, mmu_idx)]; } +/* Convert a possible stage1+2 MMU index into the appropriate + * stage 1 MMU index + */ +static inline ARMMMUIdx stage_1_mmu_idx(ARMMMUIdx mmu_idx) +{ + if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) { + mmu_idx += (ARMMMUIdx_S1NSE0 - ARMMMUIdx_S12NSE0); + } + return mmu_idx; +} + /* Returns TBI0 value for current regime el */ uint32_t arm_regime_tbi0(CPUARMState *env, ARMMMUIdx mmu_idx) { @@ -XXX,XX +XXX,XX @@ uint32_t arm_regime_tbi0(CPUARMState *env, ARMMMUIdx mmu_idx) uint32_t el; /* For EL0 and EL1, TBI is controlled by stage 1's TCR, so convert - * a stage 1+2 mmu index into the appropriate stage 1 mmu index. - */ - if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) { - mmu_idx += ARMMMUIdx_S1NSE0; - } + * a stage 1+2 mmu index into the appropriate stage 1 mmu index. + */ + mmu_idx = stage_1_mmu_idx(mmu_idx); tcr = regime_tcr(env, mmu_idx); el = regime_el(env, mmu_idx); @@ -XXX,XX +XXX,XX @@ uint32_t arm_regime_tbi1(CPUARMState *env, ARMMMUIdx mmu_idx) uint32_t el; /* For EL0 and EL1, TBI is controlled by stage 1's TCR, so convert - * a stage 1+2 mmu index into the appropriate stage 1 mmu index. - */ - if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) { - mmu_idx += ARMMMUIdx_S1NSE0; - } + * a stage 1+2 mmu index into the appropriate stage 1 mmu index. + */ + mmu_idx = stage_1_mmu_idx(mmu_idx); tcr = regime_tcr(env, mmu_idx); el = regime_el(env, mmu_idx); @@ -XXX,XX +XXX,XX @@ static inline bool regime_using_lpae_format(CPUARMState *env, * on whether the long or short descriptor format is in use. */ bool arm_s1_regime_using_lpae_format(CPUARMState *env, ARMMMUIdx mmu_idx) { - if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) { - mmu_idx += ARMMMUIdx_S1NSE0; - } + mmu_idx = stage_1_mmu_idx(mmu_idx); return regime_using_lpae_format(env, mmu_idx); } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, int ret; ret = get_phys_addr(env, address, access_type, - mmu_idx + ARMMMUIdx_S1NSE0, &ipa, attrs, + stage_1_mmu_idx(mmu_idx), &ipa, attrs, prot, page_size, fsr, fi); /* If S1 fails or S2 is disabled, return early. */ @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, /* * For non-EL2 CPUs a stage1+stage2 translation is just stage 1. */ - mmu_idx += ARMMMUIdx_S1NSE0; + mmu_idx = stage_1_mmu_idx(mmu_idx); } } @@ -XXX,XX +XXX,XX @@ bool arm_tlb_fill(CPUState *cs, vaddr address, int ret; MemTxAttrs attrs = {}; - ret = get_phys_addr(env, address, access_type, mmu_idx, &phys_addr, + ret = get_phys_addr(env, address, access_type, + core_to_arm_mmu_idx(env, mmu_idx), &phys_addr, &attrs, &prot, &page_size, fsr, fi); if (!ret) { /* Map a single [sub]page. */ @@ -XXX,XX +XXX,XX @@ hwaddr arm_cpu_get_phys_page_attrs_debug(CPUState *cs, vaddr addr, bool ret; uint32_t fsr; ARMMMUFaultInfo fi = {}; + ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); *attrs = (MemTxAttrs) {}; - ret = get_phys_addr(env, addr, 0, cpu_mmu_index(env, false), &phys_addr, + ret = get_phys_addr(env, addr, 0, mmu_idx, &phys_addr, attrs, &prot, &page_size, &fsr, &fi); if (ret) { diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr, int target_el; bool same_el; uint32_t syn; + ARMMMUIdx arm_mmu_idx = core_to_arm_mmu_idx(env, mmu_idx); if (retaddr) { /* now we have a real cpu fault */ @@ -XXX,XX +XXX,XX @@ void arm_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr, /* the DFSR for an alignment fault depends on whether we're using * the LPAE long descriptor format, or the short descriptor format */ - if (arm_s1_regime_using_lpae_format(env, mmu_idx)) { + if (arm_s1_regime_using_lpae_format(env, arm_mmu_idx)) { env->exception.fsr = (1 << 9) | 0x21; } else { env->exception.fsr = 0x1; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ void a64_translate_init(void) offsetof(CPUARMState, exclusive_high), "exclusive_high"); } -static inline ARMMMUIdx get_a64_user_mem_index(DisasContext *s) +static inline int get_a64_user_mem_index(DisasContext *s) { - /* Return the mmu_idx to use for A64 "unprivileged load/store" insns: + /* Return the core mmu_idx to use for A64 "unprivileged load/store" insns: * if EL1, access as if EL0; otherwise access at current EL */ + ARMMMUIdx useridx; + switch (s->mmu_idx) { case ARMMMUIdx_S12NSE1: - return ARMMMUIdx_S12NSE0; + useridx = ARMMMUIdx_S12NSE0; + break; case ARMMMUIdx_S1SE1: - return ARMMMUIdx_S1SE0; + useridx = ARMMMUIdx_S1SE0; + break; case ARMMMUIdx_S2NS: g_assert_not_reached(); default: - return s->mmu_idx; + useridx = s->mmu_idx; + break; } + return arm_to_core_mmu_idx(useridx); } void aarch64_cpu_dump_state(CPUState *cs, FILE *f, @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code_a64(ARMCPU *cpu, TranslationBlock *tb) dc->be_data = ARM_TBFLAG_BE_DATA(tb->flags) ? MO_BE : MO_LE; dc->condexec_mask = 0; dc->condexec_cond = 0; - dc->mmu_idx = ARM_TBFLAG_MMUIDX(tb->flags); + dc->mmu_idx = core_to_arm_mmu_idx(env, ARM_TBFLAG_MMUIDX(tb->flags)); dc->tbi0 = ARM_TBFLAG_TBI0(tb->flags); dc->tbi1 = ARM_TBFLAG_TBI1(tb->flags); dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void disas_set_da_iss(DisasContext *s, TCGMemOp memop, ISSInfo issinfo) disas_set_insn_syndrome(s, syn); } -static inline ARMMMUIdx get_a32_user_mem_index(DisasContext *s) +static inline int get_a32_user_mem_index(DisasContext *s) { - /* Return the mmu_idx to use for A32/T32 "unprivileged load/store" + /* Return the core mmu_idx to use for A32/T32 "unprivileged load/store" * insns: * if PL2, UNPREDICTABLE (we choose to implement as if PL0) * otherwise, access as if at PL0. @@ -XXX,XX +XXX,XX @@ static inline ARMMMUIdx get_a32_user_mem_index(DisasContext *s) case ARMMMUIdx_S1E2: /* this one is UNPREDICTABLE */ case ARMMMUIdx_S12NSE0: case ARMMMUIdx_S12NSE1: - return ARMMMUIdx_S12NSE0; + return arm_to_core_mmu_idx(ARMMMUIdx_S12NSE0); case ARMMMUIdx_S1E3: case ARMMMUIdx_S1SE0: case ARMMMUIdx_S1SE1: - return ARMMMUIdx_S1SE0; + return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0); case ARMMMUIdx_S2NS: default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) dc->be_data = ARM_TBFLAG_BE_DATA(tb->flags) ? MO_BE : MO_LE; dc->condexec_mask = (ARM_TBFLAG_CONDEXEC(tb->flags) & 0xf) << 1; dc->condexec_cond = ARM_TBFLAG_CONDEXEC(tb->flags) >> 4; - dc->mmu_idx = ARM_TBFLAG_MMUIDX(tb->flags); + dc->mmu_idx = core_to_arm_mmu_idx(env, ARM_TBFLAG_MMUIDX(tb->flags)); dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx); #if !defined(CONFIG_USER_ONLY) dc->user = (dc->current_el == 0); -- 2.7.4 Make M profile use completely separate ARMMMUIdx values from those that A profile CPUs use. This is a prelude to adding support for the MPU and for v8M, which together will require 6 MMU indexes which don't map cleanly onto the A profile uses: non secure User non secure Privileged non secure Privileged, execution priority < 0 secure User secure Privileged secure Privileged, execution priority < 0 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1493122030-32191-4-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 21 +++++++++++++++++++-- target/arm/helper.c | 5 +++++ target/arm/translate.c | 3 +++ 3 files changed, 27 insertions(+), 2 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, * of the AT/ATS operations. * The values used are carefully arranged to make mmu_idx => EL lookup easy. */ -#define ARM_MMU_IDX_A 0x10 /* A profile (and M profile, for the moment) */ +#define ARM_MMU_IDX_A 0x10 /* A profile */ #define ARM_MMU_IDX_NOTLB 0x20 /* does not have a TLB */ +#define ARM_MMU_IDX_M 0x40 /* M profile */ #define ARM_MMU_IDX_TYPE_MASK (~0x7) #define ARM_MMU_IDX_COREIDX_MASK 0x7 @@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdx { ARMMMUIdx_S1SE0 = 4 | ARM_MMU_IDX_A, ARMMMUIdx_S1SE1 = 5 | ARM_MMU_IDX_A, ARMMMUIdx_S2NS = 6 | ARM_MMU_IDX_A, + ARMMMUIdx_MUser = 0 | ARM_MMU_IDX_M, + ARMMMUIdx_MPriv = 1 | ARM_MMU_IDX_M, /* Indexes below here don't have TLBs and are used only for AT system * instructions or for the first stage of an S12 page table walk. */ @@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdxBit { ARMMMUIdxBit_S1SE0 = 1 << 4, ARMMMUIdxBit_S1SE1 = 1 << 5, ARMMMUIdxBit_S2NS = 1 << 6, + ARMMMUIdxBit_MUser = 1 << 0, + ARMMMUIdxBit_MPriv = 1 << 1, } ARMMMUIdxBit; #define MMU_USER_IDX 0 @@ -XXX,XX +XXX,XX @@ static inline int arm_to_core_mmu_idx(ARMMMUIdx mmu_idx) static inline ARMMMUIdx core_to_arm_mmu_idx(CPUARMState *env, int mmu_idx) { - return mmu_idx | ARM_MMU_IDX_A; + if (arm_feature(env, ARM_FEATURE_M)) { + return mmu_idx | ARM_MMU_IDX_M; + } else { + return mmu_idx | ARM_MMU_IDX_A; + } } /* Return the exception level we're running at if this is our mmu_idx */ @@ -XXX,XX +XXX,XX @@ static inline int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx) switch (mmu_idx & ARM_MMU_IDX_TYPE_MASK) { case ARM_MMU_IDX_A: return mmu_idx & 3; + case ARM_MMU_IDX_M: + return mmu_idx & 1; default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static inline int cpu_mmu_index(CPUARMState *env, bool ifetch) { int el = arm_current_el(env); + if (arm_feature(env, ARM_FEATURE_M)) { + ARMMMUIdx mmu_idx = el == 0 ? ARMMMUIdx_MUser : ARMMMUIdx_MPriv; + + return arm_to_core_mmu_idx(mmu_idx); + } + if (el < 2 && arm_is_secure_below_el3(env)) { return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0 + el); } diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx) case ARMMMUIdx_S1SE1: case ARMMMUIdx_S1NSE0: case ARMMMUIdx_S1NSE1: + case ARMMMUIdx_MPriv: + case ARMMMUIdx_MUser: return 1; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static inline bool regime_is_secure(CPUARMState *env, ARMMMUIdx mmu_idx) case ARMMMUIdx_S1NSE1: case ARMMMUIdx_S1E2: case ARMMMUIdx_S2NS: + case ARMMMUIdx_MPriv: + case ARMMMUIdx_MUser: return false; case ARMMMUIdx_S1E3: case ARMMMUIdx_S1SE0: @@ -XXX,XX +XXX,XX @@ static inline bool regime_is_user(CPUARMState *env, ARMMMUIdx mmu_idx) switch (mmu_idx) { case ARMMMUIdx_S1SE0: case ARMMMUIdx_S1NSE0: + case ARMMMUIdx_MUser: return true; default: return false; diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline int get_a32_user_mem_index(DisasContext *s) case ARMMMUIdx_S1SE0: case ARMMMUIdx_S1SE1: return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0); + case ARMMMUIdx_MUser: + case ARMMMUIdx_MPriv: + return arm_to_core_mmu_idx(ARMMMUIdx_MUser); case ARMMMUIdx_S2NS: default: g_assert_not_reached(); -- 2.7.4 ARM CPUs come in two flavours: * proper MMU ("VMSA") * only an MPU ("PMSA") For PMSA, the MPU may be implemented, or not (in which case there is default "always acts the same" behaviour, but it isn't guest programmable). QEMU is a bit confused about how we indicate this: we have an ARM_FEATURE_MPU, but it's not clear whether this indicates "PMSA, not VMSA" or "PMSA and MPU present" , and sometimes we use it for one purpose and sometimes the other. Currently trying to implement a PMSA-without-MPU core won't work correctly because we turn off the ARM_FEATURE_MPU bit and then a lot of things which should still exist get turned off too. As the first step in cleaning this up, rename the feature bit to ARM_FEATURE_PMSA, which indicates a PMSA CPU (with or without MPU). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-5-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 2 +- target/arm/cpu.c | 12 ++++++------ target/arm/helper.c | 12 ++++++------ target/arm/machine.c | 2 +- 4 files changed, 14 insertions(+), 14 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_V6K, ARM_FEATURE_V7, ARM_FEATURE_THUMB2, - ARM_FEATURE_MPU, /* Only has Memory Protection Unit, not full MMU. */ + ARM_FEATURE_PMSA, /* no MMU; may have Memory Protection Unit */ ARM_FEATURE_VFP3, ARM_FEATURE_VFP_FP16, ARM_FEATURE_NEON, diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_post_init(Object *obj) &error_abort); } - if (arm_feature(&cpu->env, ARM_FEATURE_MPU)) { + if (arm_feature(&cpu->env, ARM_FEATURE_PMSA)) { qdev_property_add_static(DEVICE(obj), &arm_cpu_has_mpu_property, &error_abort); if (arm_feature(&cpu->env, ARM_FEATURE_V7)) { @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) if (arm_feature(env, ARM_FEATURE_V7) && !arm_feature(env, ARM_FEATURE_M) && - !arm_feature(env, ARM_FEATURE_MPU)) { + !arm_feature(env, ARM_FEATURE_PMSA)) { /* v7VMSA drops support for the old ARMv5 tiny pages, so we * can use 4K pages. */ @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) } if (!cpu->has_mpu) { - unset_feature(env, ARM_FEATURE_MPU); + unset_feature(env, ARM_FEATURE_PMSA); } - if (arm_feature(env, ARM_FEATURE_MPU) && + if (arm_feature(env, ARM_FEATURE_PMSA) && arm_feature(env, ARM_FEATURE_V7)) { uint32_t nr = cpu->pmsav7_dregion; @@ -XXX,XX +XXX,XX @@ static void arm946_initfn(Object *obj) cpu->dtb_compatible = "arm,arm946"; set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_MPU); + set_feature(&cpu->env, ARM_FEATURE_PMSA); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); cpu->midr = 0x41059461; cpu->ctr = 0x0f004006; @@ -XXX,XX +XXX,XX @@ static void cortex_r5_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_THUMB_DIV); set_feature(&cpu->env, ARM_FEATURE_ARM_DIV); set_feature(&cpu->env, ARM_FEATURE_V7MP); - set_feature(&cpu->env, ARM_FEATURE_MPU); + set_feature(&cpu->env, ARM_FEATURE_PMSA); cpu->midr = 0x411fc153; /* r1p3 */ cpu->id_pfr0 = 0x0131; cpu->id_pfr1 = 0x001; diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void contextidr_write(CPUARMState *env, const ARMCPRegInfo *ri, { ARMCPU *cpu = arm_env_get_cpu(env); - if (raw_read(env, ri) != value && !arm_feature(env, ARM_FEATURE_MPU) + if (raw_read(env, ri) != value && !arm_feature(env, ARM_FEATURE_PMSA) && !extended_addresses_enabled(env)) { /* For VMSA (when not using the LPAE long descriptor page table * format) this register includes the ASID, so do a TLB flush. @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_arm_cp_regs(cpu, v6k_cp_reginfo); } if (arm_feature(env, ARM_FEATURE_V7MP) && - !arm_feature(env, ARM_FEATURE_MPU)) { + !arm_feature(env, ARM_FEATURE_PMSA)) { define_arm_cp_regs(cpu, v7mp_cp_reginfo); } if (arm_feature(env, ARM_FEATURE_V7)) { @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) } } - if (arm_feature(env, ARM_FEATURE_MPU)) { + if (arm_feature(env, ARM_FEATURE_PMSA)) { if (arm_feature(env, ARM_FEATURE_V6)) { /* PMSAv6 not implemented */ assert(arm_feature(env, ARM_FEATURE_V7)); @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_arm_cp_regs(cpu, id_pre_v8_midr_cp_reginfo); } define_arm_cp_regs(cpu, id_cp_reginfo); - if (!arm_feature(env, ARM_FEATURE_MPU)) { + if (!arm_feature(env, ARM_FEATURE_PMSA)) { define_one_arm_cp_reg(cpu, &id_tlbtr_reginfo); } else if (arm_feature(env, ARM_FEATURE_V7)) { define_one_arm_cp_reg(cpu, &id_mpuir_reginfo); @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, /* pmsav7 has special handling for when MPU is disabled so call it before * the common MMU/MPU disabled check below. */ - if (arm_feature(env, ARM_FEATURE_MPU) && + if (arm_feature(env, ARM_FEATURE_PMSA) && arm_feature(env, ARM_FEATURE_V7)) { *page_size = TARGET_PAGE_SIZE; return get_phys_addr_pmsav7(env, address, access_type, mmu_idx, @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, return 0; } - if (arm_feature(env, ARM_FEATURE_MPU)) { + if (arm_feature(env, ARM_FEATURE_PMSA)) { /* Pre-v7 MPU */ *page_size = TARGET_PAGE_SIZE; return get_phys_addr_pmsav5(env, address, access_type, mmu_idx, diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static bool pmsav7_needed(void *opaque) ARMCPU *cpu = opaque; CPUARMState *env = &cpu->env; - return arm_feature(env, ARM_FEATURE_MPU) && + return arm_feature(env, ARM_FEATURE_PMSA) && arm_feature(env, ARM_FEATURE_V7); } -- 2.7.4 Fix the handling of QOM properties for PMSA CPUs with no MPU: Allow no-MPU to be specified by either: * has-mpu = false * pmsav7_dregion = 0 and make setting one imply the other. Don't clear the PMSA feature bit in this situation. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-6-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) cpu->id_pfr1 &= ~0xf000; } + /* MPU can be configured out of a PMSA CPU either by setting has-mpu + * to false or by setting pmsav7-dregion to 0. + */ if (!cpu->has_mpu) { - unset_feature(env, ARM_FEATURE_PMSA); + cpu->pmsav7_dregion = 0; + } + if (cpu->pmsav7_dregion == 0) { + cpu->has_mpu = false; } if (arm_feature(env, ARM_FEATURE_PMSA) && -- 2.7.4 If the CPU is a PMSA config with no MPU implemented, then the SCTLR.M bit should be RAZ/WI, so that the guest can never turn on the non-existent MPU. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-7-git-send-email-peter.maydell@linaro.org --- target/arm/helper.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void sctlr_write(CPUARMState *env, const ARMCPRegInfo *ri, return; } + if (arm_feature(env, ARM_FEATURE_PMSA) && !cpu->has_mpu) { + /* M bit is RAZ/WI for PMSA with no MPU implemented */ + value &= ~SCTLR_M; + } + raw_write(env, ri, value); /* ??? Lots of these bits are not implemented. */ /* This may enable/disable the MMU, so do a TLB flush. */ -- 2.7.4 Now that we enforce both: * pmsav7_dregion == 0 implies has_mpu == false * PMSA with has_mpu == false means SCTLR.M cannot be set we can remove a check on pmsav7_dregion from get_phys_addr_pmsav7(), because we can only reach this code path if the MPU is enabled (and so region_translation_disabled() returned false). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-8-git-send-email-peter.maydell@linaro.org --- target/arm/helper.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, } if (n == -1) { /* no hits */ - if (cpu->pmsav7_dregion && - (is_user || !(regime_sctlr(env, mmu_idx) & SCTLR_BR))) { + if (is_user || !(regime_sctlr(env, mmu_idx) & SCTLR_BR)) { /* background fault */ *fsr = 0; return true; -- 2.7.4 From: Michael Davidsaver <mdavidsaver@gmail.com> Improve the "-d mmu" tracing for the PMSAv7 MPU translation process as an aid in debugging guest MPU configurations: * fix a missing newline for a guest-error log * report the region number with guest-error or unimp logs of bad region register values * add a log message for the overall result of the lookup * print "0x" prefix for hex values Signed-off-by: Michael Davidsaver <mdavidsaver@gmail.com> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-9-git-send-email-peter.maydell@linaro.org [PMM: a little tidyup, report region number in all messages rather than just one] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 39 +++++++++++++++++++++++++++------------ 1 file changed, 27 insertions(+), 12 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, } if (!rsize) { - qemu_log_mask(LOG_GUEST_ERROR, "DRSR.Rsize field can not be 0"); + qemu_log_mask(LOG_GUEST_ERROR, + "DRSR[%d]: Rsize field cannot be 0\n", n); continue; } rsize++; rmask = (1ull << rsize) - 1; if (base & rmask) { - qemu_log_mask(LOG_GUEST_ERROR, "DRBAR %" PRIx32 " misaligned " - "to DRSR region size, mask = %" PRIx32, - base, rmask); + qemu_log_mask(LOG_GUEST_ERROR, + "DRBAR[%d]: 0x%" PRIx32 " misaligned " + "to DRSR region size, mask = 0x%" PRIx32 "\n", + n, base, rmask); continue; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, } } if (rsize < TARGET_PAGE_BITS) { - qemu_log_mask(LOG_UNIMP, "No support for MPU (sub)region" + qemu_log_mask(LOG_UNIMP, + "DRSR[%d]: No support for MPU (sub)region " "alignment of %" PRIu32 " bits. Minimum is %d\n", - rsize, TARGET_PAGE_BITS); + n, rsize, TARGET_PAGE_BITS); continue; } if (srdis) { @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, break; default: qemu_log_mask(LOG_GUEST_ERROR, - "Bad value for AP bits in DRACR %" - PRIx32 "\n", ap); + "DRACR[%d]: Bad value for AP bits: 0x%" + PRIx32 "\n", n, ap); } } else { /* Priv. mode AP bits decoding */ switch (ap) { @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, break; default: qemu_log_mask(LOG_GUEST_ERROR, - "Bad value for AP bits in DRACR %" - PRIx32 "\n", ap); + "DRACR[%d]: Bad value for AP bits: 0x%" + PRIx32 "\n", n, ap); } } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, */ if (arm_feature(env, ARM_FEATURE_PMSA) && arm_feature(env, ARM_FEATURE_V7)) { + bool ret; *page_size = TARGET_PAGE_SIZE; - return get_phys_addr_pmsav7(env, address, access_type, mmu_idx, - phys_ptr, prot, fsr); + ret = get_phys_addr_pmsav7(env, address, access_type, mmu_idx, + phys_ptr, prot, fsr); + qemu_log_mask(CPU_LOG_MMU, "PMSAv7 MPU lookup for %s at 0x%08" PRIx32 + " mmu_idx %u -> %s (prot %c%c%c)\n", + access_type == 1 ? "reading" : + (access_type == 2 ? "writing" : "execute"), + (uint32_t)address, mmu_idx, + ret ? "Miss" : "Hit", + *prot & PAGE_READ ? 'r' : '-', + *prot & PAGE_WRITE ? 'w' : '-', + *prot & PAGE_EXEC ? 'x' : '-'); + + return ret; } if (regime_translation_disabled(env, mmu_idx)) { -- 2.7.4 From: Michael Davidsaver <mdavidsaver@gmail.com> Add support for the M profile default memory map which is used if the MPU is not present or disabled. The main differences in behaviour from implementing this correctly are that we set the PAGE_EXEC attribute on the right regions of memory, such that device regions are not executable. Signed-off-by: Michael Davidsaver <mdavidsaver@gmail.com> Message-id: 1493122030-32191-10-git-send-email-peter.maydell@linaro.org [PMM: rephrased comment and commit message; don't mark the flash memory region as not-writable; list all the cases in the default map explicitly rather than using a 'default' case for the non-executable regions] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 41 ++++++++++++++++++++++++++++++++--------- 1 file changed, 32 insertions(+), 9 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static inline void get_phys_addr_pmsav7_default(CPUARMState *env, ARMMMUIdx mmu_idx, int32_t address, int *prot) { - *prot = PAGE_READ | PAGE_WRITE; - switch (address) { - case 0xF0000000 ... 0xFFFFFFFF: - if (regime_sctlr(env, mmu_idx) & SCTLR_V) { /* hivecs execing is ok */ + if (!arm_feature(env, ARM_FEATURE_M)) { + *prot = PAGE_READ | PAGE_WRITE; + switch (address) { + case 0xF0000000 ... 0xFFFFFFFF: + if (regime_sctlr(env, mmu_idx) & SCTLR_V) { + /* hivecs execing is ok */ + *prot |= PAGE_EXEC; + } + break; + case 0x00000000 ... 0x7FFFFFFF: *prot |= PAGE_EXEC; + break; + } + } else { + /* Default system address map for M profile cores. + * The architecture specifies which regions are execute-never; + * at the MPU level no other checks are defined. + */ + switch (address) { + case 0x00000000 ... 0x1fffffff: /* ROM */ + case 0x20000000 ... 0x3fffffff: /* SRAM */ + case 0x60000000 ... 0x7fffffff: /* RAM */ + case 0x80000000 ... 0x9fffffff: /* RAM */ + *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC; + break; + case 0x40000000 ... 0x5fffffff: /* Peripheral */ + case 0xa0000000 ... 0xbfffffff: /* Device */ + case 0xc0000000 ... 0xdfffffff: /* Device */ + case 0xe0000000 ... 0xffffffff: /* System */ + *prot = PAGE_READ | PAGE_WRITE; + break; + default: + g_assert_not_reached(); } - break; - case 0x00000000 ... 0x7FFFFFFF: - *prot |= PAGE_EXEC; - break; } - } static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, -- 2.7.4 All M profile CPUs are PMSA, so set the feature bit. (We haven't actually implemented the M profile MPU register interface yet, but setting this feature bit gives us closer to correct behaviour for the MPU-disabled case.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1493122030-32191-11-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_post_init(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); + /* M profile implies PMSA. We have to do this here rather than + * in realize with the other feature-implication checks because + * we look at the PMSA bit to see if we should add some properties. + */ + if (arm_feature(&cpu->env, ARM_FEATURE_M)) { + set_feature(&cpu->env, ARM_FEATURE_PMSA); + } + if (arm_feature(&cpu->env, ARM_FEATURE_CBAR) || arm_feature(&cpu->env, ARM_FEATURE_CBAR_RO)) { qdev_property_add_static(DEVICE(obj), &arm_cpu_reset_cbar_property, -- 2.7.4 From: Michael Davidsaver <mdavidsaver@gmail.com> General logic is that operations stopped by the MPU are MemManage, and those which go through the MPU and are caught by the unassigned handle are BusFault. Distinguish these by looking at the exception.fsr values, and set the CFSR bits and (if appropriate) fill in the BFAR or MMFAR with the exception address. Signed-off-by: Michael Davidsaver <mdavidsaver@gmail.com> Message-id: 1493122030-32191-12-git-send-email-peter.maydell@linaro.org [PMM: i-side faults do not set BFAR/MMFAR, only d-side; added some CPU_LOG_INT logging] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> --- target/arm/helper.c | 45 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 42 insertions(+), 3 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) break; case EXCP_PREFETCH_ABORT: case EXCP_DATA_ABORT: - /* TODO: if we implemented the MPU registers, this is where we - * should set the MMFAR, etc from exception.fsr and exception.vaddress. + /* Note that for M profile we don't have a guest facing FSR, but + * the env->exception.fsr will be populated by the code that + * raises the fault, in the A profile short-descriptor format. */ - armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_MEM); + switch (env->exception.fsr & 0xf) { + case 0x8: /* External Abort */ + switch (cs->exception_index) { + case EXCP_PREFETCH_ABORT: + env->v7m.cfsr |= R_V7M_CFSR_PRECISERR_MASK; + qemu_log_mask(CPU_LOG_INT, "...with CFSR.PRECISERR\n"); + break; + case EXCP_DATA_ABORT: + env->v7m.cfsr |= + (R_V7M_CFSR_IBUSERR_MASK | R_V7M_CFSR_BFARVALID_MASK); + env->v7m.bfar = env->exception.vaddress; + qemu_log_mask(CPU_LOG_INT, + "...with CFSR.IBUSERR and BFAR 0x%x\n", + env->v7m.bfar); + break; + } + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_BUS); + break; + default: + /* All other FSR values are either MPU faults or "can't happen + * for M profile" cases. + */ + switch (cs->exception_index) { + case EXCP_PREFETCH_ABORT: + env->v7m.cfsr |= R_V7M_CFSR_IACCVIOL_MASK; + qemu_log_mask(CPU_LOG_INT, "...with CFSR.IACCVIOL\n"); + break; + case EXCP_DATA_ABORT: + env->v7m.cfsr |= + (R_V7M_CFSR_DACCVIOL_MASK | R_V7M_CFSR_MMARVALID_MASK); + env->v7m.mmfar = env->exception.vaddress; + qemu_log_mask(CPU_LOG_INT, + "...with CFSR.DACCVIOL and MMFAR 0x%x\n", + env->v7m.mmfar); + break; + } + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_MEM); + break; + } break; case EXCP_BKPT: if (semihosting_enabled()) { -- 2.7.4 From: Michael Davidsaver <mdavidsaver@gmail.com> The M series MPU is almost the same as the already implemented R profile MPU (v7 PMSA). So all we need to implement here is the MPU register interface in the system register space. This implementation has the same restriction as the R profile MPU that it doesn't permit regions to be sized down smaller than 1K. We also do not yet implement support for MPU_CTRL.HFNMIENA; this bit should if zero disable use of the MPU when running HardFault, NMI or with FAULTMASK set to 1 (ie at an execution priority of less than zero) -- if the MPU is enabled we don't treat these cases any differently. Signed-off-by: Michael Davidsaver <mdavidsaver@gmail.com> Message-id: 1493122030-32191-13-git-send-email-peter.maydell@linaro.org [PMM: Keep all the bits in mpu_ctrl field, rather than using SCTLR bits for them; drop broken HFNMIENA support; various cleanup] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 6 +++ hw/intc/armv7m_nvic.c | 104 ++++++++++++++++++++++++++++++++++++++++++++++++++ target/arm/helper.c | 25 +++++++++++- target/arm/machine.c | 5 ++- 4 files changed, 137 insertions(+), 3 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUARMState { uint32_t dfsr; /* Debug Fault Status Register */ uint32_t mmfar; /* MemManage Fault Address */ uint32_t bfar; /* BusFault Address */ + unsigned mpu_ctrl; /* MPU_CTRL (some bits kept in sctlr_el[1]) */ int exception; } v7m; @@ -XXX,XX +XXX,XX @@ FIELD(V7M_DFSR, DWTTRAP, 2, 1) FIELD(V7M_DFSR, VCATCH, 3, 1) FIELD(V7M_DFSR, EXTERNAL, 4, 1) +/* v7M MPU_CTRL bits */ +FIELD(V7M_MPU_CTRL, ENABLE, 0, 1) +FIELD(V7M_MPU_CTRL, HFNMIENA, 1, 1) +FIELD(V7M_MPU_CTRL, PRIVDEFENA, 2, 1) + /* If adding a feature bit which corresponds to a Linux ELF * HWCAP bit, remember to update the feature-bit-to-hwcap * mapping in linux-user/elfload.c:get_elf_hwcap(). diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/arm.h" #include "hw/arm/armv7m_nvic.h" #include "target/arm/cpu.h" +#include "exec/exec-all.h" #include "qemu/log.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset) case 0xd70: /* ISAR4. */ return 0x01310102; /* TODO: Implement debug registers. */ + case 0xd90: /* MPU_TYPE */ + /* Unified MPU; if the MPU is not present this value is zero */ + return cpu->pmsav7_dregion << 8; + break; + case 0xd94: /* MPU_CTRL */ + return cpu->env.v7m.mpu_ctrl; + case 0xd98: /* MPU_RNR */ + return cpu->env.cp15.c6_rgnr; + case 0xd9c: /* MPU_RBAR */ + case 0xda4: /* MPU_RBAR_A1 */ + case 0xdac: /* MPU_RBAR_A2 */ + case 0xdb4: /* MPU_RBAR_A3 */ + { + int region = cpu->env.cp15.c6_rgnr; + + if (region >= cpu->pmsav7_dregion) { + return 0; + } + return (cpu->env.pmsav7.drbar[region] & 0x1f) | (region & 0xf); + } + case 0xda0: /* MPU_RASR */ + case 0xda8: /* MPU_RASR_A1 */ + case 0xdb0: /* MPU_RASR_A2 */ + case 0xdb8: /* MPU_RASR_A3 */ + { + int region = cpu->env.cp15.c6_rgnr; + + if (region >= cpu->pmsav7_dregion) { + return 0; + } + return ((cpu->env.pmsav7.dracr[region] & 0xffff) << 16) | + (cpu->env.pmsav7.drsr[region] & 0xffff); + } default: qemu_log_mask(LOG_GUEST_ERROR, "NVIC: Bad read offset 0x%x\n", offset); return 0; @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value) qemu_log_mask(LOG_UNIMP, "NVIC: Aux fault status registers unimplemented\n"); break; + case 0xd90: /* MPU_TYPE */ + return; /* RO */ + case 0xd94: /* MPU_CTRL */ + if ((value & + (R_V7M_MPU_CTRL_HFNMIENA_MASK | R_V7M_MPU_CTRL_ENABLE_MASK)) + == R_V7M_MPU_CTRL_HFNMIENA_MASK) { + qemu_log_mask(LOG_GUEST_ERROR, "MPU_CTRL: HFNMIENA and !ENABLE is " + "UNPREDICTABLE\n"); + } + cpu->env.v7m.mpu_ctrl = value & (R_V7M_MPU_CTRL_ENABLE_MASK | + R_V7M_MPU_CTRL_HFNMIENA_MASK | + R_V7M_MPU_CTRL_PRIVDEFENA_MASK); + tlb_flush(CPU(cpu)); + break; + case 0xd98: /* MPU_RNR */ + if (value >= cpu->pmsav7_dregion) { + qemu_log_mask(LOG_GUEST_ERROR, "MPU region out of range %" + PRIu32 "/%" PRIu32 "\n", + value, cpu->pmsav7_dregion); + } else { + cpu->env.cp15.c6_rgnr = value; + } + break; + case 0xd9c: /* MPU_RBAR */ + case 0xda4: /* MPU_RBAR_A1 */ + case 0xdac: /* MPU_RBAR_A2 */ + case 0xdb4: /* MPU_RBAR_A3 */ + { + int region; + + if (value & (1 << 4)) { + /* VALID bit means use the region number specified in this + * value and also update MPU_RNR.REGION with that value. + */ + region = extract32(value, 0, 4); + if (region >= cpu->pmsav7_dregion) { + qemu_log_mask(LOG_GUEST_ERROR, + "MPU region out of range %u/%" PRIu32 "\n", + region, cpu->pmsav7_dregion); + return; + } + cpu->env.cp15.c6_rgnr = region; + } else { + region = cpu->env.cp15.c6_rgnr; + } + + if (region >= cpu->pmsav7_dregion) { + return; + } + + cpu->env.pmsav7.drbar[region] = value & ~0x1f; + tlb_flush(CPU(cpu)); + break; + } + case 0xda0: /* MPU_RASR */ + case 0xda8: /* MPU_RASR_A1 */ + case 0xdb0: /* MPU_RASR_A2 */ + case 0xdb8: /* MPU_RASR_A3 */ + { + int region = cpu->env.cp15.c6_rgnr; + + if (region >= cpu->pmsav7_dregion) { + return; + } + + cpu->env.pmsav7.drsr[region] = value & 0xff3f; + cpu->env.pmsav7.dracr[region] = (value >> 16) & 0x173f; + tlb_flush(CPU(cpu)); + break; + } case 0xf00: /* Software Triggered Interrupt Register */ { /* user mode can only write to STIR if CCR.USERSETMPEND permits it */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t regime_sctlr(CPUARMState *env, ARMMMUIdx mmu_idx) static inline bool regime_translation_disabled(CPUARMState *env, ARMMMUIdx mmu_idx) { + if (arm_feature(env, ARM_FEATURE_M)) { + return !(env->v7m.mpu_ctrl & R_V7M_MPU_CTRL_ENABLE_MASK); + } + if (mmu_idx == ARMMMUIdx_S2NS) { return (env->cp15.hcr_el2 & HCR_VM) == 0; } @@ -XXX,XX +XXX,XX @@ static inline void get_phys_addr_pmsav7_default(CPUARMState *env, } } +static bool pmsav7_use_background_region(ARMCPU *cpu, + ARMMMUIdx mmu_idx, bool is_user) +{ + /* Return true if we should use the default memory map as a + * "background" region if there are no hits against any MPU regions. + */ + CPUARMState *env = &cpu->env; + + if (is_user) { + return false; + } + + if (arm_feature(env, ARM_FEATURE_M)) { + return env->v7m.mpu_ctrl & R_V7M_MPU_CTRL_PRIVDEFENA_MASK; + } else { + return regime_sctlr(env, mmu_idx) & SCTLR_BR; + } +} + static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, int access_type, ARMMMUIdx mmu_idx, hwaddr *phys_ptr, int *prot, uint32_t *fsr) @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, } if (n == -1) { /* no hits */ - if (is_user || !(regime_sctlr(env, mmu_idx) & SCTLR_BR)) { + if (!pmsav7_use_background_region(cpu, mmu_idx, is_user)) { /* background fault */ *fsr = 0; return true; diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static bool m_needed(void *opaque) static const VMStateDescription vmstate_m = { .name = "cpu/m", - .version_id = 3, - .minimum_version_id = 3, + .version_id = 4, + .minimum_version_id = 4, .needed = m_needed, .fields = (VMStateField[]) { VMSTATE_UINT32(env.v7m.vecbase, ARMCPU), @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_m = { VMSTATE_UINT32(env.v7m.dfsr, ARMCPU), VMSTATE_UINT32(env.v7m.mmfar, ARMCPU), VMSTATE_UINT32(env.v7m.bfar, ARMCPU), + VMSTATE_UINT32(env.v7m.mpu_ctrl, ARMCPU), VMSTATE_INT32(env.v7m.exception, ARMCPU), VMSTATE_END_OF_LIST() } -- 2.7.4 Implement HFNMIENA support for the M profile MPU. This bit controls whether the MPU is treated as enabled when executing at execution priorities of less than zero (in NMI, HardFault or with the FAULTMASK bit set). Doing this requires us to use a different MMU index for "running at execution priority < 0", because we will have different access permissions for that case versus the normal case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1493122030-32191-14-git-send-email-peter.maydell@linaro.org --- target/arm/cpu.h | 24 +++++++++++++++++++++++- target/arm/helper.c | 18 +++++++++++++++++- target/arm/translate.c | 1 + 3 files changed, 41 insertions(+), 2 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, * for the accesses done as part of a stage 1 page table walk, rather than * having to walk the stage 2 page table over and over.) * + * R profile CPUs have an MPU, but can use the same set of MMU indexes + * as A profile. They only need to distinguish NS EL0 and NS EL1 (and + * NS EL2 if we ever model a Cortex-R52). + * + * M profile CPUs are rather different as they do not have a true MMU. + * They have the following different MMU indexes: + * User + * Privileged + * Execution priority negative (this is like privileged, but the + * MPU HFNMIENA bit means that it may have different access permission + * check results to normal privileged code, so can't share a TLB). + * * The ARMMMUIdx and the mmu index value used by the core QEMU TLB code * are not quite the same -- different CPU types (most notably M profile * vs A/R profile) would like to use MMU indexes with different semantics, @@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdx { ARMMMUIdx_S2NS = 6 | ARM_MMU_IDX_A, ARMMMUIdx_MUser = 0 | ARM_MMU_IDX_M, ARMMMUIdx_MPriv = 1 | ARM_MMU_IDX_M, + ARMMMUIdx_MNegPri = 2 | ARM_MMU_IDX_M, /* Indexes below here don't have TLBs and are used only for AT system * instructions or for the first stage of an S12 page table walk. */ @@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdxBit { ARMMMUIdxBit_S2NS = 1 << 6, ARMMMUIdxBit_MUser = 1 << 0, ARMMMUIdxBit_MPriv = 1 << 1, + ARMMMUIdxBit_MNegPri = 1 << 2, } ARMMMUIdxBit; #define MMU_USER_IDX 0 @@ -XXX,XX +XXX,XX @@ static inline int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx) case ARM_MMU_IDX_A: return mmu_idx & 3; case ARM_MMU_IDX_M: - return mmu_idx & 1; + return mmu_idx == ARMMMUIdx_MUser ? 0 : 1; default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static inline int cpu_mmu_index(CPUARMState *env, bool ifetch) if (arm_feature(env, ARM_FEATURE_M)) { ARMMMUIdx mmu_idx = el == 0 ? ARMMMUIdx_MUser : ARMMMUIdx_MPriv; + /* Execution priority is negative if FAULTMASK is set or + * we're in a HardFault or NMI handler. + */ + if ((env->v7m.exception > 0 && env->v7m.exception <= 3) + || env->daif & PSTATE_F) { + return arm_to_core_mmu_idx(ARMMMUIdx_MNegPri); + } + return arm_to_core_mmu_idx(mmu_idx); } diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx) case ARMMMUIdx_S1NSE0: case ARMMMUIdx_S1NSE1: case ARMMMUIdx_MPriv: + case ARMMMUIdx_MNegPri: case ARMMMUIdx_MUser: return 1; default: @@ -XXX,XX +XXX,XX @@ static inline bool regime_is_secure(CPUARMState *env, ARMMMUIdx mmu_idx) case ARMMMUIdx_S1E2: case ARMMMUIdx_S2NS: case ARMMMUIdx_MPriv: + case ARMMMUIdx_MNegPri: case ARMMMUIdx_MUser: return false; case ARMMMUIdx_S1E3: @@ -XXX,XX +XXX,XX @@ static inline bool regime_translation_disabled(CPUARMState *env, ARMMMUIdx mmu_idx) { if (arm_feature(env, ARM_FEATURE_M)) { - return !(env->v7m.mpu_ctrl & R_V7M_MPU_CTRL_ENABLE_MASK); + switch (env->v7m.mpu_ctrl & + (R_V7M_MPU_CTRL_ENABLE_MASK | R_V7M_MPU_CTRL_HFNMIENA_MASK)) { + case R_V7M_MPU_CTRL_ENABLE_MASK: + /* Enabled, but not for HardFault and NMI */ + return mmu_idx == ARMMMUIdx_MNegPri; + case R_V7M_MPU_CTRL_ENABLE_MASK | R_V7M_MPU_CTRL_HFNMIENA_MASK: + /* Enabled for all cases */ + return false; + case 0: + default: + /* HFNMIENA set and ENABLE clear is UNPREDICTABLE, but + * we warned about that in armv7m_nvic.c when the guest set it. + */ + return true; + } } if (mmu_idx == ARMMMUIdx_S2NS) { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline int get_a32_user_mem_index(DisasContext *s) return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0); case ARMMMUIdx_MUser: case ARMMMUIdx_MPriv: + case ARMMMUIdx_MNegPri: return arm_to_core_mmu_idx(ARMMMUIdx_MUser); case ARMMMUIdx_S2NS: default: -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> Multiple I2C commands can be fired simultaneously and the controller execute the commands following these priorities: (1) Master Start Command (2) Master Transmit Command (3) Slave Transmit Command or Master Receive Command (4) Master Stop Command The current code is incorrect with respect to the above sequence and needs to be reworked to handle each individual command. Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 1494827476-1487-2-git-send-email-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/i2c/aspeed_i2c.c | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/hw/i2c/aspeed_i2c.c b/hw/i2c/aspeed_i2c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/aspeed_i2c.c +++ b/hw/i2c/aspeed_i2c.c @@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_i2c_bus_read(void *opaque, hwaddr offset, static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) { + bus->cmd &= ~0xFFFF; bus->cmd |= value & 0xFFFF; bus->intr_status = 0; @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) bus->intr_status |= I2CD_INTR_TX_ACK; } - } else if (bus->cmd & I2CD_M_TX_CMD) { + /* START command is also a TX command, as the slave address is + * sent on the bus */ + bus->cmd &= ~(I2CD_M_START_CMD | I2CD_M_TX_CMD); + + /* No slave found */ + if (!i2c_bus_busy(bus->bus)) { + return; + } + } + + if (bus->cmd & I2CD_M_TX_CMD) { if (i2c_send(bus->bus, bus->buf)) { bus->intr_status |= (I2CD_INTR_TX_NAK | I2CD_INTR_ABNORMAL); i2c_end_transfer(bus->bus); } else { bus->intr_status |= I2CD_INTR_TX_ACK; } + bus->cmd &= ~I2CD_M_TX_CMD; + } - } else if (bus->cmd & I2CD_M_RX_CMD) { + if (bus->cmd & I2CD_M_RX_CMD) { int ret = i2c_recv(bus->bus); if (ret < 0) { qemu_log_mask(LOG_GUEST_ERROR, "%s: read failed\n", __func__); @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) bus->intr_status |= I2CD_INTR_RX_DONE; } bus->buf = (ret & I2CD_BYTE_BUF_RX_MASK) << I2CD_BYTE_BUF_RX_SHIFT; + bus->cmd &= ~I2CD_M_RX_CMD; } if (bus->cmd & (I2CD_M_STOP_CMD | I2CD_M_S_RX_CMD_LAST)) { @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) i2c_end_transfer(bus->bus); bus->intr_status |= I2CD_INTR_NORMAL_STOP; } + bus->cmd &= ~I2CD_M_STOP_CMD; } - - /* command is handled, reset it and check for interrupts */ - bus->cmd &= ~0xFFFF; - aspeed_i2c_bus_raise_interrupt(bus); } static void aspeed_i2c_bus_write(void *opaque, hwaddr offset, @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_write(void *opaque, hwaddr offset, } aspeed_i2c_bus_handle_cmd(bus, value); + aspeed_i2c_bus_raise_interrupt(bus); break; default: -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> Today, the LAST command is handled with the STOP command but this is incorrect. Also nack the I2C bus when a LAST is issued. Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 1494827476-1487-3-git-send-email-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/i2c/aspeed_i2c.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/hw/i2c/aspeed_i2c.c b/hw/i2c/aspeed_i2c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/aspeed_i2c.c +++ b/hw/i2c/aspeed_i2c.c @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) bus->cmd &= ~I2CD_M_TX_CMD; } - if (bus->cmd & I2CD_M_RX_CMD) { + if (bus->cmd & (I2CD_M_RX_CMD | I2CD_M_S_RX_CMD_LAST)) { int ret = i2c_recv(bus->bus); if (ret < 0) { qemu_log_mask(LOG_GUEST_ERROR, "%s: read failed\n", __func__); @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) bus->intr_status |= I2CD_INTR_RX_DONE; } bus->buf = (ret & I2CD_BYTE_BUF_RX_MASK) << I2CD_BYTE_BUF_RX_SHIFT; - bus->cmd &= ~I2CD_M_RX_CMD; + if (bus->cmd & I2CD_M_S_RX_CMD_LAST) { + i2c_nack(bus->bus); + } + bus->cmd &= ~(I2CD_M_RX_CMD | I2CD_M_S_RX_CMD_LAST); } - if (bus->cmd & (I2CD_M_STOP_CMD | I2CD_M_S_RX_CMD_LAST)) { + if (bus->cmd & I2CD_M_STOP_CMD) { if (!i2c_bus_busy(bus->bus)) { bus->intr_status |= I2CD_INTR_ABNORMAL; } else { -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> The Aspeed I2C controller maintains a state machine in the command register, which is mostly used for debug. Let's start adding a few states to handle abnormal STOP commands. Today, the model uses the busy status of the bus as a condition to do so but it is not precise enough. Also remove the ABNORMAL bit for failing TX commands. This is incorrect with respect to the specs. Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 1494827476-1487-4-git-send-email-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/i2c/aspeed_i2c.c | 36 +++++++++++++++++++++++++++++++++--- 1 file changed, 33 insertions(+), 3 deletions(-) diff --git a/hw/i2c/aspeed_i2c.c b/hw/i2c/aspeed_i2c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/aspeed_i2c.c +++ b/hw/i2c/aspeed_i2c.c @@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_i2c_bus_read(void *opaque, hwaddr offset, } } +static void aspeed_i2c_set_state(AspeedI2CBus *bus, uint8_t state) +{ + bus->cmd &= ~(I2CD_TX_STATE_MASK << I2CD_TX_STATE_SHIFT); + bus->cmd |= (state & I2CD_TX_STATE_MASK) << I2CD_TX_STATE_SHIFT; +} + +static uint8_t aspeed_i2c_get_state(AspeedI2CBus *bus) +{ + return (bus->cmd >> I2CD_TX_STATE_SHIFT) & I2CD_TX_STATE_MASK; +} + +/* + * The state machine needs some refinement. It is only used to track + * invalid STOP commands for the moment. + */ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) { bus->cmd &= ~0xFFFF; @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) bus->intr_status = 0; if (bus->cmd & I2CD_M_START_CMD) { + uint8_t state = aspeed_i2c_get_state(bus) & I2CD_MACTIVE ? + I2CD_MSTARTR : I2CD_MSTART; + + aspeed_i2c_set_state(bus, state); + if (i2c_start_transfer(bus->bus, extract32(bus->buf, 1, 7), extract32(bus->buf, 0, 1))) { bus->intr_status |= I2CD_INTR_TX_NAK; @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) if (!i2c_bus_busy(bus->bus)) { return; } + aspeed_i2c_set_state(bus, I2CD_MACTIVE); } if (bus->cmd & I2CD_M_TX_CMD) { + aspeed_i2c_set_state(bus, I2CD_MTXD); if (i2c_send(bus->bus, bus->buf)) { - bus->intr_status |= (I2CD_INTR_TX_NAK | I2CD_INTR_ABNORMAL); + bus->intr_status |= (I2CD_INTR_TX_NAK); i2c_end_transfer(bus->bus); } else { bus->intr_status |= I2CD_INTR_TX_ACK; } bus->cmd &= ~I2CD_M_TX_CMD; + aspeed_i2c_set_state(bus, I2CD_MACTIVE); } if (bus->cmd & (I2CD_M_RX_CMD | I2CD_M_S_RX_CMD_LAST)) { - int ret = i2c_recv(bus->bus); + int ret; + + aspeed_i2c_set_state(bus, I2CD_MRXD); + ret = i2c_recv(bus->bus); if (ret < 0) { qemu_log_mask(LOG_GUEST_ERROR, "%s: read failed\n", __func__); ret = 0xff; @@ -XXX,XX +XXX,XX @@ static void aspeed_i2c_bus_handle_cmd(AspeedI2CBus *bus, uint64_t value) i2c_nack(bus->bus); } bus->cmd &= ~(I2CD_M_RX_CMD | I2CD_M_S_RX_CMD_LAST); + aspeed_i2c_set_state(bus, I2CD_MACTIVE); } if (bus->cmd & I2CD_M_STOP_CMD) { - if (!i2c_bus_busy(bus->bus)) { + if (!(aspeed_i2c_get_state(bus) & I2CD_MACTIVE)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: abnormal stop\n", __func__); bus->intr_status |= I2CD_INTR_ABNORMAL; } else { + aspeed_i2c_set_state(bus, I2CD_MSTOP); i2c_end_transfer(bus->bus); bus->intr_status |= I2CD_INTR_NORMAL_STOP; } bus->cmd &= ~I2CD_M_STOP_CMD; + aspeed_i2c_set_state(bus, I2CD_IDLE); } } -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> Let's add an RTC to the palmetto BMC and a LM75 temperature sensor to the AST2500 EVB to start with. Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 1494827476-1487-5-git-send-email-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ typedef struct AspeedBoardConfig { const char *fmc_model; const char *spi_model; uint32_t num_cs; + void (*i2c_init)(AspeedBoardState *bmc); } AspeedBoardConfig; enum { @@ -XXX,XX +XXX,XX @@ enum { SCU_AST2500_HW_STRAP_ACPI_ENABLE | \ SCU_HW_STRAP_SPI_MODE(SCU_HW_STRAP_SPI_MASTER)) +static void palmetto_bmc_i2c_init(AspeedBoardState *bmc); +static void ast2500_evb_i2c_init(AspeedBoardState *bmc); + static const AspeedBoardConfig aspeed_boards[] = { [PALMETTO_BMC] = { .soc_name = "ast2400-a1", @@ -XXX,XX +XXX,XX @@ static const AspeedBoardConfig aspeed_boards[] = { .fmc_model = "n25q256a", .spi_model = "mx25l25635e", .num_cs = 1, + .i2c_init = palmetto_bmc_i2c_init, }, [AST2500_EVB] = { .soc_name = "ast2500-a1", @@ -XXX,XX +XXX,XX @@ static const AspeedBoardConfig aspeed_boards[] = { .fmc_model = "n25q256a", .spi_model = "mx25l25635e", .num_cs = 1, + .i2c_init = ast2500_evb_i2c_init, }, [ROMULUS_BMC] = { .soc_name = "ast2500-a1", @@ -XXX,XX +XXX,XX @@ static void aspeed_board_init(MachineState *machine, aspeed_board_binfo.ram_size = ram_size; aspeed_board_binfo.loader_start = sc->info->sdram_base; + if (cfg->i2c_init) { + cfg->i2c_init(bmc); + } + arm_load_kernel(ARM_CPU(first_cpu), &aspeed_board_binfo); } +static void palmetto_bmc_i2c_init(AspeedBoardState *bmc) +{ + AspeedSoCState *soc = &bmc->soc; + + /* The palmetto platform expects a ds3231 RTC but a ds1338 is + * enough to provide basic RTC features. Alarms will be missing */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 0), "ds1338", 0x68); +} + static void palmetto_bmc_init(MachineState *machine) { aspeed_board_init(machine, &aspeed_boards[PALMETTO_BMC]); @@ -XXX,XX +XXX,XX @@ static const TypeInfo palmetto_bmc_type = { .class_init = palmetto_bmc_class_init, }; +static void ast2500_evb_i2c_init(AspeedBoardState *bmc) +{ + AspeedSoCState *soc = &bmc->soc; + + /* The AST2500 EVB expects a LM75 but a TMP105 is compatible */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 7), "tmp105", 0x4d); +} + static void ast2500_evb_init(MachineState *machine) { aspeed_board_init(machine, &aspeed_boards[AST2500_EVB]); -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> Largely inspired by the TMP105 temperature sensor, here is a model for the TMP42{1,2,3} temperature sensors. Specs can be found here : http://www.ti.com/lit/gpn/tmp421 Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 1494827476-1487-6-git-send-email-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + hw/misc/tmp421.c | 401 ++++++++++++++++++++++++++++++++++++++++ default-configs/arm-softmmu.mak | 1 + 3 files changed, 403 insertions(+) create mode 100644 hw/misc/tmp421.c diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_APPLESMC) += applesmc.o common-obj-$(CONFIG_MAX111X) += max111x.o common-obj-$(CONFIG_TMP105) += tmp105.o +common-obj-$(CONFIG_TMP421) += tmp421.o common-obj-$(CONFIG_ISA_DEBUG) += debugexit.o common-obj-$(CONFIG_SGA) += sga.o common-obj-$(CONFIG_ISA_TESTDEV) += pc-testdev.o diff --git a/hw/misc/tmp421.c b/hw/misc/tmp421.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/tmp421.c @@ -XXX,XX +XXX,XX @@ +/* + * Texas Instruments TMP421 temperature sensor. + * + * Copyright (c) 2016 IBM Corporation. + * + * Largely inspired by : + * + * Texas Instruments TMP105 temperature sensor. + * + * Copyright (C) 2008 Nokia Corporation + * Written by Andrzej Zaborowski <andrew@openedhand.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 or + * (at your option) version 3 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "hw/hw.h" +#include "hw/i2c/i2c.h" +#include "qapi/error.h" +#include "qapi/visitor.h" + +/* Manufacturer / Device ID's */ +#define TMP421_MANUFACTURER_ID 0x55 +#define TMP421_DEVICE_ID 0x21 +#define TMP422_DEVICE_ID 0x22 +#define TMP423_DEVICE_ID 0x23 + +typedef struct DeviceInfo { + int model; + const char *name; +} DeviceInfo; + +static const DeviceInfo devices[] = { + { TMP421_DEVICE_ID, "tmp421" }, + { TMP422_DEVICE_ID, "tmp422" }, + { TMP423_DEVICE_ID, "tmp423" }, +}; + +typedef struct TMP421State { + /*< private >*/ + I2CSlave i2c; + /*< public >*/ + + int16_t temperature[4]; + + uint8_t status; + uint8_t config[2]; + uint8_t rate; + + uint8_t len; + uint8_t buf[2]; + uint8_t pointer; + +} TMP421State; + +typedef struct TMP421Class { + I2CSlaveClass parent_class; + DeviceInfo *dev; +} TMP421Class; + +#define TYPE_TMP421 "tmp421-generic" +#define TMP421(obj) OBJECT_CHECK(TMP421State, (obj), TYPE_TMP421) + +#define TMP421_CLASS(klass) \ + OBJECT_CLASS_CHECK(TMP421Class, (klass), TYPE_TMP421) +#define TMP421_GET_CLASS(obj) \ + OBJECT_GET_CLASS(TMP421Class, (obj), TYPE_TMP421) + +/* the TMP421 registers */ +#define TMP421_STATUS_REG 0x08 +#define TMP421_STATUS_BUSY (1 << 7) +#define TMP421_CONFIG_REG_1 0x09 +#define TMP421_CONFIG_RANGE (1 << 2) +#define TMP421_CONFIG_SHUTDOWN (1 << 6) +#define TMP421_CONFIG_REG_2 0x0A +#define TMP421_CONFIG_RC (1 << 2) +#define TMP421_CONFIG_LEN (1 << 3) +#define TMP421_CONFIG_REN (1 << 4) +#define TMP421_CONFIG_REN2 (1 << 5) +#define TMP421_CONFIG_REN3 (1 << 6) + +#define TMP421_CONVERSION_RATE_REG 0x0B +#define TMP421_ONE_SHOT 0x0F + +#define TMP421_RESET 0xFC +#define TMP421_MANUFACTURER_ID_REG 0xFE +#define TMP421_DEVICE_ID_REG 0xFF + +#define TMP421_TEMP_MSB0 0x00 +#define TMP421_TEMP_MSB1 0x01 +#define TMP421_TEMP_MSB2 0x02 +#define TMP421_TEMP_MSB3 0x03 +#define TMP421_TEMP_LSB0 0x10 +#define TMP421_TEMP_LSB1 0x11 +#define TMP421_TEMP_LSB2 0x12 +#define TMP421_TEMP_LSB3 0x13 + +static const int32_t mins[2] = { -40000, -55000 }; +static const int32_t maxs[2] = { 127000, 150000 }; + +static void tmp421_get_temperature(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + TMP421State *s = TMP421(obj); + bool ext_range = (s->config[0] & TMP421_CONFIG_RANGE); + int offset = ext_range * 64 * 256; + int64_t value; + int tempid; + + if (sscanf(name, "temperature%d", &tempid) != 1) { + error_setg(errp, "error reading %s: %m", name); + return; + } + + if (tempid >= 4 || tempid < 0) { + error_setg(errp, "error reading %s", name); + return; + } + + value = ((s->temperature[tempid] - offset) * 1000 + 128) / 256; + + visit_type_int(v, name, &value, errp); +} + +/* Units are 0.001 centigrades relative to 0 C. s->temperature is 8.8 + * fixed point, so units are 1/256 centigrades. A simple ratio will do. + */ +static void tmp421_set_temperature(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + TMP421State *s = TMP421(obj); + Error *local_err = NULL; + int64_t temp; + bool ext_range = (s->config[0] & TMP421_CONFIG_RANGE); + int offset = ext_range * 64 * 256; + int tempid; + + visit_type_int(v, name, &temp, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + + if (temp >= maxs[ext_range] || temp < mins[ext_range]) { + error_setg(errp, "value %" PRId64 ".%03" PRIu64 " °C is out of range", + temp / 1000, temp % 1000); + return; + } + + if (sscanf(name, "temperature%d", &tempid) != 1) { + error_setg(errp, "error reading %s: %m", name); + return; + } + + if (tempid >= 4 || tempid < 0) { + error_setg(errp, "error reading %s", name); + return; + } + + s->temperature[tempid] = (int16_t) ((temp * 256 - 128) / 1000) + offset; +} + +static void tmp421_read(TMP421State *s) +{ + TMP421Class *sc = TMP421_GET_CLASS(s); + + s->len = 0; + + switch (s->pointer) { + case TMP421_MANUFACTURER_ID_REG: + s->buf[s->len++] = TMP421_MANUFACTURER_ID; + break; + case TMP421_DEVICE_ID_REG: + s->buf[s->len++] = sc->dev->model; + break; + case TMP421_CONFIG_REG_1: + s->buf[s->len++] = s->config[0]; + break; + case TMP421_CONFIG_REG_2: + s->buf[s->len++] = s->config[1]; + break; + case TMP421_CONVERSION_RATE_REG: + s->buf[s->len++] = s->rate; + break; + case TMP421_STATUS_REG: + s->buf[s->len++] = s->status; + break; + + /* FIXME: check for channel enablement in config registers */ + case TMP421_TEMP_MSB0: + s->buf[s->len++] = (((uint16_t) s->temperature[0]) >> 8); + s->buf[s->len++] = (((uint16_t) s->temperature[0]) >> 0) & 0xf0; + break; + case TMP421_TEMP_MSB1: + s->buf[s->len++] = (((uint16_t) s->temperature[1]) >> 8); + s->buf[s->len++] = (((uint16_t) s->temperature[1]) >> 0) & 0xf0; + break; + case TMP421_TEMP_MSB2: + s->buf[s->len++] = (((uint16_t) s->temperature[2]) >> 8); + s->buf[s->len++] = (((uint16_t) s->temperature[2]) >> 0) & 0xf0; + break; + case TMP421_TEMP_MSB3: + s->buf[s->len++] = (((uint16_t) s->temperature[3]) >> 8); + s->buf[s->len++] = (((uint16_t) s->temperature[3]) >> 0) & 0xf0; + break; + case TMP421_TEMP_LSB0: + s->buf[s->len++] = (((uint16_t) s->temperature[0]) >> 0) & 0xf0; + break; + case TMP421_TEMP_LSB1: + s->buf[s->len++] = (((uint16_t) s->temperature[1]) >> 0) & 0xf0; + break; + case TMP421_TEMP_LSB2: + s->buf[s->len++] = (((uint16_t) s->temperature[2]) >> 0) & 0xf0; + break; + case TMP421_TEMP_LSB3: + s->buf[s->len++] = (((uint16_t) s->temperature[3]) >> 0) & 0xf0; + break; + } +} + +static void tmp421_reset(I2CSlave *i2c); + +static void tmp421_write(TMP421State *s) +{ + switch (s->pointer) { + case TMP421_CONVERSION_RATE_REG: + s->rate = s->buf[0]; + break; + case TMP421_CONFIG_REG_1: + s->config[0] = s->buf[0]; + break; + case TMP421_CONFIG_REG_2: + s->config[1] = s->buf[0]; + break; + case TMP421_RESET: + tmp421_reset(I2C_SLAVE(s)); + break; + } +} + +static int tmp421_rx(I2CSlave *i2c) +{ + TMP421State *s = TMP421(i2c); + + if (s->len < 2) { + return s->buf[s->len++]; + } else { + return 0xff; + } +} + +static int tmp421_tx(I2CSlave *i2c, uint8_t data) +{ + TMP421State *s = TMP421(i2c); + + if (s->len == 0) { + /* first byte is the register pointer for a read or write + * operation */ + s->pointer = data; + s->len++; + } else if (s->len == 1) { + /* second byte is the data to write. The device only supports + * one byte writes */ + s->buf[0] = data; + tmp421_write(s); + } + + return 0; +} + +static int tmp421_event(I2CSlave *i2c, enum i2c_event event) +{ + TMP421State *s = TMP421(i2c); + + if (event == I2C_START_RECV) { + tmp421_read(s); + } + + s->len = 0; + return 0; +} + +static const VMStateDescription vmstate_tmp421 = { + .name = "TMP421", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT8(len, TMP421State), + VMSTATE_UINT8_ARRAY(buf, TMP421State, 2), + VMSTATE_UINT8(pointer, TMP421State), + VMSTATE_UINT8_ARRAY(config, TMP421State, 2), + VMSTATE_UINT8(status, TMP421State), + VMSTATE_UINT8(rate, TMP421State), + VMSTATE_INT16_ARRAY(temperature, TMP421State, 4), + VMSTATE_I2C_SLAVE(i2c, TMP421State), + VMSTATE_END_OF_LIST() + } +}; + +static void tmp421_reset(I2CSlave *i2c) +{ + TMP421State *s = TMP421(i2c); + TMP421Class *sc = TMP421_GET_CLASS(s); + + memset(s->temperature, 0, sizeof(s->temperature)); + s->pointer = 0; + + s->config[0] = 0; /* TMP421_CONFIG_RANGE */ + + /* resistance correction and channel enablement */ + switch (sc->dev->model) { + case TMP421_DEVICE_ID: + s->config[1] = 0x1c; + break; + case TMP422_DEVICE_ID: + s->config[1] = 0x3c; + break; + case TMP423_DEVICE_ID: + s->config[1] = 0x7c; + break; + } + + s->rate = 0x7; /* 8Hz */ + s->status = 0; +} + +static int tmp421_init(I2CSlave *i2c) +{ + TMP421State *s = TMP421(i2c); + + tmp421_reset(&s->i2c); + + return 0; +} + +static void tmp421_initfn(Object *obj) +{ + object_property_add(obj, "temperature0", "int", + tmp421_get_temperature, + tmp421_set_temperature, NULL, NULL, NULL); + object_property_add(obj, "temperature1", "int", + tmp421_get_temperature, + tmp421_set_temperature, NULL, NULL, NULL); + object_property_add(obj, "temperature2", "int", + tmp421_get_temperature, + tmp421_set_temperature, NULL, NULL, NULL); + object_property_add(obj, "temperature3", "int", + tmp421_get_temperature, + tmp421_set_temperature, NULL, NULL, NULL); +} + +static void tmp421_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + I2CSlaveClass *k = I2C_SLAVE_CLASS(klass); + TMP421Class *sc = TMP421_CLASS(klass); + + k->init = tmp421_init; + k->event = tmp421_event; + k->recv = tmp421_rx; + k->send = tmp421_tx; + dc->vmsd = &vmstate_tmp421; + sc->dev = (DeviceInfo *) data; +} + +static const TypeInfo tmp421_info = { + .name = TYPE_TMP421, + .parent = TYPE_I2C_SLAVE, + .instance_size = sizeof(TMP421State), + .instance_init = tmp421_initfn, + .class_init = tmp421_class_init, +}; + +static void tmp421_register_types(void) +{ + int i; + + type_register_static(&tmp421_info); + for (i = 0; i < ARRAY_SIZE(devices); ++i) { + TypeInfo ti = { + .name = devices[i].name, + .parent = TYPE_TMP421, + .class_init = tmp421_class_init, + .class_data = (void *) &devices[i], + }; + type_register(&ti); + } +} + +type_init(tmp421_register_types) diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/arm-softmmu.mak +++ b/default-configs/arm-softmmu.mak @@ -XXX,XX +XXX,XX @@ CONFIG_TWL92230=y CONFIG_TSC2005=y CONFIG_LM832X=y CONFIG_TMP105=y +CONFIG_TMP421=y CONFIG_STELLARIS=y CONFIG_STELLARIS_INPUT=y CONFIG_STELLARIS_ENET=y -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> Temperatures can be changed from the monitor with : (qemu) qom-set /machine/unattached/device[2] temperature0 12000 Signed-off-by: Cédric Le Goater <clg@kaod.org> Message-id: 1494827476-1487-7-git-send-email-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ static void aspeed_board_init(MachineState *machine, static void palmetto_bmc_i2c_init(AspeedBoardState *bmc) { AspeedSoCState *soc = &bmc->soc; + DeviceState *dev; /* The palmetto platform expects a ds3231 RTC but a ds1338 is * enough to provide basic RTC features. Alarms will be missing */ i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 0), "ds1338", 0x68); + + /* add a TMP423 temperature sensor */ + dev = i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 2), + "tmp423", 0x4c); + object_property_set_int(OBJECT(dev), 31000, "temperature0", &error_abort); + object_property_set_int(OBJECT(dev), 28000, "temperature1", &error_abort); + object_property_set_int(OBJECT(dev), 20000, "temperature2", &error_abort); + object_property_set_int(OBJECT(dev), 110000, "temperature3", &error_abort); } static void palmetto_bmc_init(MachineState *machine) -- 2.7.4 From: Andrew Jones <drjones@redhat.com> Cc: Shannon Zhao <zhaoshenglong@huawei.com> Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Reviewed-by: Shannon Zhao <shannon.zhao@linaro.org> Message-id: 20170529173751.3443-2-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt-acpi-build.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -XXX,XX +XXX,XX @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) if (nb_numa_nodes > 0) { acpi_add_table(table_offsets, tables_blob); build_srat(tables_blob, tables->linker, vms); + if (have_numa_distance) { + acpi_add_table(table_offsets, tables_blob); + build_slit(tables_blob, tables->linker); + } } if (its_class_name() && !vmc->no_its) { -- 2.7.4 From: Andrew Jones <drjones@redhat.com> This is based on patch Shannon Zhao originally posted. Cc: Shannon Zhao <zhaoshenglong@huawei.com> Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Shannon Zhao <shannon.zhao@linaro.org> Message-id: 20170529173751.3443-3-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void create_fdt(VirtMachineState *vms) "clk24mhz"); qemu_fdt_setprop_cell(fdt, "/apb-pclk", "phandle", vms->clock_phandle); + if (have_numa_distance) { + int size = nb_numa_nodes * nb_numa_nodes * 3 * sizeof(uint32_t); + uint32_t *matrix = g_malloc0(size); + int idx, i, j; + + for (i = 0; i < nb_numa_nodes; i++) { + for (j = 0; j < nb_numa_nodes; j++) { + idx = (i * nb_numa_nodes + j) * 3; + matrix[idx + 0] = cpu_to_be32(i); + matrix[idx + 1] = cpu_to_be32(j); + matrix[idx + 2] = cpu_to_be32(numa_info[i].distance[j]); + } + } + + qemu_fdt_add_subnode(fdt, "/distance-map"); + qemu_fdt_setprop_string(fdt, "/distance-map", "compatible", + "numa-distance-map-v1"); + qemu_fdt_setprop(fdt, "/distance-map", "distance-matrix", + matrix, size); + g_free(matrix); + } } static void fdt_add_psci_node(const VirtMachineState *vms) -- 2.7.4 This pullreq is (1) my GICv4 patches (2) most of the first third of RTH's cleanup patchset (3) one patch fixing an smmuv3 bug... thanks -- PMM The following changes since commit a74782936dc6e979ce371dabda4b1c05624ea87f: Merge tag 'pull-migration-20220421a' of https://gitlab.com/dagrh/qemu into staging (2022-04-21 18:48:18 -0700) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20220422 for you to fetch changes up to 9792130613191c1e0c34109918c5e07b9f1429a5: hw/arm/smmuv3: Pass the actual perm to returned IOMMUTLBEntry in smmuv3_translate() (2022-04-22 10:19:15 +0100) ---------------------------------------------------------------- target-arm queue: * Implement GICv4 emulation * Some cleanup patches in target/arm * hw/arm/smmuv3: Pass the actual perm to returned IOMMUTLBEntry in smmuv3_translate() ---------------------------------------------------------------- Peter Maydell (41): hw/intc/arm_gicv3_its: Add missing blank line hw/intc/arm_gicv3: Sanity-check num-cpu property hw/intc/arm_gicv3: Insist that redist region capacity matches CPU count hw/intc/arm_gicv3: Report correct PIDR0 values for ID registers target/arm/cpu.c: ignore VIRQ and VFIQ if no EL2 hw/intc/arm_gicv3_its: Factor out "is intid a valid LPI ID?" hw/intc/arm_gicv3_its: Implement GITS_BASER2 for GICv4 hw/intc/arm_gicv3_its: Implement VMAPI and VMAPTI hw/intc/arm_gicv3_its: Implement VMAPP hw/intc/arm_gicv3_its: Distinguish success and error cases of CMD_CONTINUE hw/intc/arm_gicv3_its: Factor out "find ITE given devid, eventid" hw/intc/arm_gicv3_its: Factor out CTE lookup sequence hw/intc/arm_gicv3_its: Split out process_its_cmd() physical interrupt code hw/intc/arm_gicv3_its: Handle virtual interrupts in process_its_cmd() hw/intc/arm_gicv3: Keep pointers to every connected ITS hw/intc/arm_gicv3_its: Implement VMOVP hw/intc/arm_gicv3_its: Implement VSYNC hw/intc/arm_gicv3_its: Implement INV command properly hw/intc/arm_gicv3_its: Implement INV for virtual interrupts hw/intc/arm_gicv3_its: Implement VMOVI hw/intc/arm_gicv3_its: Implement VINVALL hw/intc/arm_gicv3: Implement GICv4's new redistributor frame hw/intc/arm_gicv3: Implement new GICv4 redistributor registers hw/intc/arm_gicv3_cpuif: Split "update vIRQ/vFIQ" from gicv3_cpuif_virt_update() hw/intc/arm_gicv3_cpuif: Support vLPIs hw/intc/arm_gicv3_cpuif: Don't recalculate maintenance irq unnecessarily hw/intc/arm_gicv3_redist: Factor out "update hpplpi for one LPI" logic hw/intc/arm_gicv3_redist: Factor out "update hpplpi for all LPIs" logic hw/intc/arm_gicv3_redist: Recalculate hppvlpi on VPENDBASER writes hw/intc/arm_gicv3_redist: Factor out "update bit in pending table" code hw/intc/arm_gicv3_redist: Implement gicv3_redist_process_vlpi() hw/intc/arm_gicv3_redist: Implement gicv3_redist_vlpi_pending() hw/intc/arm_gicv3_redist: Use set_pending_table_bit() in mov handling hw/intc/arm_gicv3_redist: Implement gicv3_redist_mov_vlpi() hw/intc/arm_gicv3_redist: Implement gicv3_redist_vinvall() hw/intc/arm_gicv3_redist: Implement gicv3_redist_inv_vlpi() hw/intc/arm_gicv3: Update ID and feature registers for GICv4 hw/intc/arm_gicv3: Allow 'revision' property to be set to 4 hw/arm/virt: Use VIRT_GIC_VERSION_* enum values in create_gic() hw/arm/virt: Abstract out calculation of redistributor region capacity hw/arm/virt: Support TCG GICv4 Richard Henderson (19): target/arm: Update ISAR fields for ARMv8.8 target/arm: Update SCR_EL3 bits to ARMv8.8 target/arm: Update SCTLR bits to ARMv9.2 target/arm: Change DisasContext.aarch64 to bool target/arm: Change CPUArchState.aarch64 to bool target/arm: Extend store_cpu_offset to take field size target/arm: Change DisasContext.thumb to bool target/arm: Change CPUArchState.thumb to bool target/arm: Remove fpexc32_access target/arm: Split out set_btype_raw target/arm: Split out gen_rebuild_hflags target/arm: Simplify GEN_SHIFT in translate.c target/arm: Simplify gen_sar target/arm: Simplify aa32 DISAS_WFI target/arm: Use tcg_constant in translate-m-nocp.c target/arm: Use tcg_constant in translate-neon.c target/arm: Use smin/smax for do_sat_addsub_32 target/arm: Use tcg_constant in translate-vfp.c target/arm: Use tcg_constant_i32 in translate.h Xiang Chen (1): hw/arm/smmuv3: Pass the actual perm to returned IOMMUTLBEntry in smmuv3_translate() docs/system/arm/virt.rst | 5 +- hw/intc/gicv3_internal.h | 231 ++++++++- include/hw/arm/virt.h | 19 +- include/hw/intc/arm_gicv3_common.h | 13 + include/hw/intc/arm_gicv3_its_common.h | 1 + target/arm/cpu.h | 59 ++- target/arm/translate-a32.h | 13 +- target/arm/translate.h | 17 +- hw/arm/smmuv3.c | 2 +- hw/arm/virt.c | 102 +++- hw/intc/arm_gicv3_common.c | 54 +- hw/intc/arm_gicv3_cpuif.c | 195 ++++++-- hw/intc/arm_gicv3_dist.c | 7 +- hw/intc/arm_gicv3_its.c | 876 +++++++++++++++++++++++++++------ hw/intc/arm_gicv3_its_kvm.c | 2 + hw/intc/arm_gicv3_kvm.c | 5 + hw/intc/arm_gicv3_redist.c | 480 +++++++++++++++--- linux-user/arm/cpu_loop.c | 2 +- target/arm/cpu.c | 16 +- target/arm/helper-a64.c | 4 +- target/arm/helper.c | 19 +- target/arm/hvf/hvf.c | 2 +- target/arm/m_helper.c | 6 +- target/arm/op_helper.c | 13 - target/arm/translate-a64.c | 50 +- target/arm/translate-m-nocp.c | 12 +- target/arm/translate-neon.c | 21 +- target/arm/translate-sve.c | 9 +- target/arm/translate-vfp.c | 76 +-- target/arm/translate.c | 101 ++-- hw/intc/trace-events | 18 +- 31 files changed, 1890 insertions(+), 540 deletions(-) In commit b6f96009acc we split do_process_its_cmd() from process_its_cmd(), but forgot the usual blank line between function definitions. Add it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-2-peter.maydell@linaro.org --- hw/intc/arm_gicv3_its.c | 1 + 1 file changed, 1 insertion(+) diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static ItsCmdResult do_process_its_cmd(GICv3ITSState *s, uint32_t devid, } return CMD_CONTINUE; } + static ItsCmdResult process_its_cmd(GICv3ITSState *s, const uint64_t *cmdpkt, ItsCmdType cmd) { -- 2.25.1 In the GICv3 code we implicitly rely on there being at least one CPU and thus at least one redistributor and CPU interface. Sanity-check that the property the board code sets is not zero. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-3-peter.maydell@linaro.org --- hw/intc/arm_gicv3_common.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_realize(DeviceState *dev, Error **errp) s->num_irq, GIC_INTERNAL); return; } + if (s->num_cpu == 0) { + error_setg(errp, "num-cpu must be at least 1"); + return; + } /* ITLinesNumber is represented as (N / 32) - 1, so this is an * implementation imposed restriction, not an architectural one, -- 2.25.1 Boards using the GICv3 need to configure it with both the total number of CPUs and also the sizes of all the memory regions which contain redistributors (one redistributor per CPU). At the moment the GICv3 checks that the number of CPUs specified is not too many to fit in the defined redistributor regions, but in fact the code assumes that the two match exactly. For instance when we set the GICR_TYPER.Last bit on the final redistributor in each region, we assume that we don't need to consider the possibility of a region being only half full of redistributors or even completely empty. We also assume in gicv3_redist_read() and gicv3_redist_write() that we can calculate the CPU index from the offset within the MemoryRegion and that this will always be in range. Fortunately all the board code sets the redistributor region sizes to exactly match the CPU count, so this isn't a visible bug. We could in theory make the GIC code handle non-full redistributor regions, or have it automatically reduce the provided region sizes to match the CPU count, but the simplest thing is just to strengthen the error check and insist that the CPU count and redistributor region size settings match exactly, since all the board code does that anyway. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-4-peter.maydell@linaro.org --- hw/intc/arm_gicv3_common.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_realize(DeviceState *dev, Error **errp) for (i = 0; i < s->nb_redist_regions; i++) { rdist_capacity += s->redist_region_count[i]; } - if (rdist_capacity < s->num_cpu) { + if (rdist_capacity != s->num_cpu) { error_setg(errp, "Capacity of the redist regions(%d) " - "is less than number of vcpus(%d)", + "does not match the number of vcpus(%d)", rdist_capacity, s->num_cpu); return; } -- 2.25.1 We use the common function gicv3_idreg() to supply the CoreSight ID register values for the GICv3 for the copies of these ID registers in the distributor, redistributor and ITS register frames. This isn't quite correct, because while most of the register values are the same, the PIDR0 value should vary to indicate which of these three frames it is. (You can see this and also the correct values of these PIDR0 registers by looking at the GIC-600 or GIC-700 TRMs, for example.) Make gicv3_idreg() take an extra argument for the PIDR0 value. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-5-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 15 +++++++++++++-- hw/intc/arm_gicv3_dist.c | 2 +- hw/intc/arm_gicv3_its.c | 2 +- hw/intc/arm_gicv3_redist.c | 2 +- 4 files changed, 16 insertions(+), 5 deletions(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t gicv3_iidr(void) return 0x43b; } -static inline uint32_t gicv3_idreg(int regoffset) +/* CoreSight PIDR0 values for ARM GICv3 implementations */ +#define GICV3_PIDR0_DIST 0x92 +#define GICV3_PIDR0_REDIST 0x93 +#define GICV3_PIDR0_ITS 0x94 + +static inline uint32_t gicv3_idreg(int regoffset, uint8_t pidr0) { /* Return the value of the CoreSight ID register at the specified * offset from the first ID register (as found in the distributor @@ -XXX,XX +XXX,XX @@ static inline uint32_t gicv3_idreg(int regoffset) static const uint8_t gicd_ids[] = { 0x44, 0x00, 0x00, 0x00, 0x92, 0xB4, 0x3B, 0x00, 0x0D, 0xF0, 0x05, 0xB1 }; - return gicd_ids[regoffset / 4]; + + regoffset /= 4; + + if (regoffset == 4) { + return pidr0; + } + return gicd_ids[regoffset]; } /** diff --git a/hw/intc/arm_gicv3_dist.c b/hw/intc/arm_gicv3_dist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_dist.c +++ b/hw/intc/arm_gicv3_dist.c @@ -XXX,XX +XXX,XX @@ static bool gicd_readl(GICv3State *s, hwaddr offset, } case GICD_IDREGS ... GICD_IDREGS + 0x2f: /* ID registers */ - *data = gicv3_idreg(offset - GICD_IDREGS); + *data = gicv3_idreg(offset - GICD_IDREGS, GICV3_PIDR0_DIST); return true; case GICD_SGIR: /* WO registers, return unknown value */ diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static bool its_readl(GICv3ITSState *s, hwaddr offset, break; case GITS_IDREGS ... GITS_IDREGS + 0x2f: /* ID registers */ - *data = gicv3_idreg(offset - GITS_IDREGS); + *data = gicv3_idreg(offset - GITS_IDREGS, GICV3_PIDR0_ITS); break; case GITS_TYPER: *data = extract64(s->typer, 0, 32); diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_readl(GICv3CPUState *cs, hwaddr offset, *data = cs->gicr_nsacr; return MEMTX_OK; case GICR_IDREGS ... GICR_IDREGS + 0x2f: - *data = gicv3_idreg(offset - GICR_IDREGS); + *data = gicv3_idreg(offset - GICR_IDREGS, GICV3_PIDR0_REDIST); return MEMTX_OK; default: return MEMTX_ERROR; -- 2.25.1 In a GICv3, it is impossible for the GIC to deliver a VIRQ or VFIQ to the CPU unless the CPU has EL2, because VIRQ and VFIQ are only configurable via EL2-only system registers. Moreover, in our implementation we were only calculating and updating the state of the VIRQ and VFIQ lines in gicv3_cpuif_virt_irq_fiq_update() when those EL2 system registers changed. We were therefore able to assert in arm_cpu_set_irq() that we didn't see a VIRQ or VFIQ line update if EL2 wasn't present. This assumption no longer holds with GICv4: * even if the CPU does not have EL2 the guest is able to cause the GIC to deliver a virtual LPI by programming the ITS (which is a silly thing for it to do, but possible) * because we now need to recalculate the state of the VIRQ and VFIQ lines in more cases than just "some EL2 GIC sysreg was written", we will see calls to arm_cpu_set_irq() for "VIRQ is 0, VFIQ is 0" even if the guest is not using the virtual LPI parts of the ITS Remove the assertions, and instead simply ignore the state of the VIRQ and VFIQ lines if the CPU does not have EL2. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-6-peter.maydell@linaro.org --- target/arm/cpu.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_set_irq(void *opaque, int irq, int level) [ARM_CPU_VFIQ] = CPU_INTERRUPT_VFIQ }; + if (!arm_feature(env, ARM_FEATURE_EL2) && + (irq == ARM_CPU_VIRQ || irq == ARM_CPU_VFIQ)) { + /* + * The GIC might tell us about VIRQ and VFIQ state, but if we don't + * have EL2 support we don't care. (Unless the guest is doing something + * silly this will only be calls saying "level is still 0".) + */ + return; + } + if (level) { env->irq_line_state |= mask[irq]; } else { @@ -XXX,XX +XXX,XX @@ static void arm_cpu_set_irq(void *opaque, int irq, int level) switch (irq) { case ARM_CPU_VIRQ: - assert(arm_feature(env, ARM_FEATURE_EL2)); arm_cpu_update_virq(cpu); break; case ARM_CPU_VFIQ: - assert(arm_feature(env, ARM_FEATURE_EL2)); arm_cpu_update_vfiq(cpu); break; case ARM_CPU_IRQ: -- 2.25.1 In process_mapti() we check interrupt IDs to see whether they are in the valid LPI range. Factor this out into its own utility function, as we're going to want it elsewhere too for GICv4. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-7-peter.maydell@linaro.org --- hw/intc/arm_gicv3_its.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ typedef enum ItsCmdResult { CMD_CONTINUE = 1, } ItsCmdResult; +static inline bool intid_in_lpi_range(uint32_t id) +{ + return id >= GICV3_LPI_INTID_START && + id < (1 << (GICD_TYPER_IDBITS + 1)); +} + static uint64_t baser_base_addr(uint64_t value, uint32_t page_sz) { uint64_t result = 0; @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_mapti(GICv3ITSState *s, const uint64_t *cmdpkt, uint32_t devid, eventid; uint32_t pIntid = 0; uint64_t num_eventids; - uint32_t num_intids; uint16_t icid = 0; DTEntry dte; ITEntry ite; @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_mapti(GICv3ITSState *s, const uint64_t *cmdpkt, return CMD_STALL; } num_eventids = 1ULL << (dte.size + 1); - num_intids = 1ULL << (GICD_TYPER_IDBITS + 1); if (icid >= s->ct.num_entries) { qemu_log_mask(LOG_GUEST_ERROR, @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_mapti(GICv3ITSState *s, const uint64_t *cmdpkt, return CMD_CONTINUE; } - if (pIntid < GICV3_LPI_INTID_START || pIntid >= num_intids) { + if (!intid_in_lpi_range(pIntid)) { qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid interrupt ID 0x%x\n", __func__, pIntid); return CMD_CONTINUE; -- 2.25.1 The GICv4 defines a new in-guest-memory table for the ITS: this is the vPE table. Implement the new GITS_BASER2 register which the guest uses to tell the ITS where the vPE table is located, including the decode of the register fields into the TableDesc structure which we do for the GITS_BASER<n> when the guest enables the ITS. We guard provision of the new register with the its_feature_virtual() function, which does a check of the GITS_TYPER.Virtual bit which indicates presence of ITS support for virtual LPIs. Since this bit is currently always zero, GICv4-specific features will not be accessible to the guest yet. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-8-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 16 ++++++++++++++++ include/hw/intc/arm_gicv3_its_common.h | 1 + hw/intc/arm_gicv3_its.c | 25 +++++++++++++++++++++++++ 3 files changed, 42 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(GITS_CTLR, ENABLED, 0, 1) FIELD(GITS_CTLR, QUIESCENT, 31, 1) FIELD(GITS_TYPER, PHYSICAL, 0, 1) +FIELD(GITS_TYPER, VIRTUAL, 1, 1) FIELD(GITS_TYPER, ITT_ENTRY_SIZE, 4, 4) FIELD(GITS_TYPER, IDBITS, 8, 5) FIELD(GITS_TYPER, DEVBITS, 13, 5) @@ -XXX,XX +XXX,XX @@ FIELD(GITS_TYPER, CIL, 36, 1) #define GITS_BASER_PAGESIZE_64K 2 #define GITS_BASER_TYPE_DEVICE 1ULL +#define GITS_BASER_TYPE_VPE 2ULL #define GITS_BASER_TYPE_COLLECTION 4ULL #define GITS_PAGE_SIZE_4K 0x1000 @@ -XXX,XX +XXX,XX @@ FIELD(DTE, ITTADDR, 6, 44) FIELD(CTE, VALID, 0, 1) FIELD(CTE, RDBASE, 1, RDBASE_PROCNUM_LENGTH) +/* + * 8 bytes VPE table entry size: + * Valid = 1 bit, VPTsize = 5 bits, VPTaddr = 36 bits, RDbase = 16 bits + * + * Field sizes for Valid and size are mandated; field sizes for RDbase + * and VPT_addr are IMPDEF. + */ +#define GITS_VPE_SIZE 0x8ULL + +FIELD(VTE, VALID, 0, 1) +FIELD(VTE, VPTSIZE, 1, 5) +FIELD(VTE, VPTADDR, 6, 36) +FIELD(VTE, RDBASE, 42, RDBASE_PROCNUM_LENGTH) + /* Special interrupt IDs */ #define INTID_SECURE 1020 #define INTID_NONSECURE 1021 diff --git a/include/hw/intc/arm_gicv3_its_common.h b/include/hw/intc/arm_gicv3_its_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_its_common.h +++ b/include/hw/intc/arm_gicv3_its_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3ITSState { TableDesc dt; TableDesc ct; + TableDesc vpet; CmdQDesc cq; Error *migration_blocker; diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ typedef enum ItsCmdResult { CMD_CONTINUE = 1, } ItsCmdResult; +/* True if the ITS supports the GICv4 virtual LPI feature */ +static bool its_feature_virtual(GICv3ITSState *s) +{ + return s->typer & R_GITS_TYPER_VIRTUAL_MASK; +} + static inline bool intid_in_lpi_range(uint32_t id) { return id >= GICV3_LPI_INTID_START && @@ -XXX,XX +XXX,XX @@ static void extract_table_params(GICv3ITSState *s) idbits = 16; } break; + case GITS_BASER_TYPE_VPE: + td = &s->vpet; + /* + * For QEMU vPEIDs are always 16 bits. (GICv4.1 allows an + * implementation to implement fewer bits and report this + * via GICD_TYPER2.) + */ + idbits = 16; + break; default: /* * GITS_BASER<n>.TYPE is read-only, so GITS_BASER_RO_MASK @@ -XXX,XX +XXX,XX @@ static void gicv3_its_reset(DeviceState *dev) /* * setting GITS_BASER0.Type = 0b001 (Device) * GITS_BASER1.Type = 0b100 (Collection Table) + * GITS_BASER2.Type = 0b010 (vPE) for GICv4 and later * GITS_BASER<n>.Type,where n = 3 to 7 are 0b00 (Unimplemented) * GITS_BASER<0,1>.Page_Size = 64KB * and default translation table entry size to 16 bytes @@ -XXX,XX +XXX,XX @@ static void gicv3_its_reset(DeviceState *dev) GITS_BASER_PAGESIZE_64K); s->baser[1] = FIELD_DP64(s->baser[1], GITS_BASER, ENTRYSIZE, GITS_CTE_SIZE - 1); + + if (its_feature_virtual(s)) { + s->baser[2] = FIELD_DP64(s->baser[2], GITS_BASER, TYPE, + GITS_BASER_TYPE_VPE); + s->baser[2] = FIELD_DP64(s->baser[2], GITS_BASER, PAGESIZE, + GITS_BASER_PAGESIZE_64K); + s->baser[2] = FIELD_DP64(s->baser[2], GITS_BASER, ENTRYSIZE, + GITS_VPE_SIZE - 1); + } } static void gicv3_its_post_load(GICv3ITSState *s) -- 2.25.1 Implement the GICv4 VMAPI and VMAPTI commands. These write an interrupt translation table entry that maps (DeviceID,EventID) to (vPEID,vINTID,doorbell). The only difference between VMAPI and VMAPTI is that VMAPI assumes vINTID == EventID rather than both being specified in the command packet. (This code won't be reachable until we allow the GIC version to be set to 4. Support for reading this new virtual-interrupt DTE and handling it correctly will be implemented in a later commit.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-9-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 9 ++++ hw/intc/arm_gicv3_its.c | 91 ++++++++++++++++++++++++++++++++++++++++ hw/intc/trace-events | 2 + 3 files changed, 102 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(GITS_TYPER, CIL, 36, 1) #define GITS_CMD_INVALL 0x0D #define GITS_CMD_MOVALL 0x0E #define GITS_CMD_DISCARD 0x0F +#define GITS_CMD_VMAPTI 0x2A +#define GITS_CMD_VMAPI 0x2B /* MAPC command fields */ #define ICID_LENGTH 16 @@ -XXX,XX +XXX,XX @@ FIELD(MOVI_0, DEVICEID, 32, 32) FIELD(MOVI_1, EVENTID, 0, 32) FIELD(MOVI_2, ICID, 0, 16) +/* VMAPI, VMAPTI command fields */ +FIELD(VMAPTI_0, DEVICEID, 32, 32) +FIELD(VMAPTI_1, EVENTID, 0, 32) +FIELD(VMAPTI_1, VPEID, 32, 16) +FIELD(VMAPTI_2, VINTID, 0, 32) /* VMAPTI only */ +FIELD(VMAPTI_2, DOORBELL, 32, 32) + /* * 12 bytes Interrupt translation Table Entry size * as per Table 5.3 in GICv3 spec diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static inline bool intid_in_lpi_range(uint32_t id) id < (1 << (GICD_TYPER_IDBITS + 1)); } +static inline bool valid_doorbell(uint32_t id) +{ + /* Doorbell fields may be an LPI, or 1023 to mean "no doorbell" */ + return id == INTID_SPURIOUS || intid_in_lpi_range(id); +} + static uint64_t baser_base_addr(uint64_t value, uint32_t page_sz) { uint64_t result = 0; @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_mapti(GICv3ITSState *s, const uint64_t *cmdpkt, return update_ite(s, eventid, &dte, &ite) ? CMD_CONTINUE : CMD_STALL; } +static ItsCmdResult process_vmapti(GICv3ITSState *s, const uint64_t *cmdpkt, + bool ignore_vintid) +{ + uint32_t devid, eventid, vintid, doorbell, vpeid; + uint32_t num_eventids; + DTEntry dte; + ITEntry ite; + + if (!its_feature_virtual(s)) { + return CMD_CONTINUE; + } + + devid = FIELD_EX64(cmdpkt[0], VMAPTI_0, DEVICEID); + eventid = FIELD_EX64(cmdpkt[1], VMAPTI_1, EVENTID); + vpeid = FIELD_EX64(cmdpkt[1], VMAPTI_1, VPEID); + doorbell = FIELD_EX64(cmdpkt[2], VMAPTI_2, DOORBELL); + if (ignore_vintid) { + vintid = eventid; + trace_gicv3_its_cmd_vmapi(devid, eventid, vpeid, doorbell); + } else { + vintid = FIELD_EX64(cmdpkt[2], VMAPTI_2, VINTID); + trace_gicv3_its_cmd_vmapti(devid, eventid, vpeid, vintid, doorbell); + } + + if (devid >= s->dt.num_entries) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid DeviceID 0x%x (must be less than 0x%x)\n", + __func__, devid, s->dt.num_entries); + return CMD_CONTINUE; + } + + if (get_dte(s, devid, &dte) != MEMTX_OK) { + return CMD_STALL; + } + + if (!dte.valid) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: no entry in device table for DeviceID 0x%x\n", + __func__, devid); + return CMD_CONTINUE; + } + + num_eventids = 1ULL << (dte.size + 1); + + if (eventid >= num_eventids) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: EventID 0x%x too large for DeviceID 0x%x " + "(must be less than 0x%x)\n", + __func__, eventid, devid, num_eventids); + return CMD_CONTINUE; + } + if (!intid_in_lpi_range(vintid)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: VIntID 0x%x not a valid LPI\n", + __func__, vintid); + return CMD_CONTINUE; + } + if (!valid_doorbell(doorbell)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Doorbell %d not 1023 and not a valid LPI\n", + __func__, doorbell); + return CMD_CONTINUE; + } + if (vpeid >= s->vpet.num_entries) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: VPEID 0x%x out of range (must be less than 0x%x)\n", + __func__, vpeid, s->vpet.num_entries); + return CMD_CONTINUE; + } + /* add ite entry to interrupt translation table */ + ite.valid = true; + ite.inttype = ITE_INTTYPE_VIRTUAL; + ite.intid = vintid; + ite.icid = 0; + ite.doorbell = doorbell; + ite.vpeid = vpeid; + return update_ite(s, eventid, &dte, &ite) ? CMD_CONTINUE : CMD_STALL; +} + /* * Update the Collection Table entry for @icid to @cte. Returns true * on success, false if there was a memory access error. @@ -XXX,XX +XXX,XX @@ static void process_cmdq(GICv3ITSState *s) case GITS_CMD_MOVALL: result = process_movall(s, cmdpkt); break; + case GITS_CMD_VMAPTI: + result = process_vmapti(s, cmdpkt, false); + break; + case GITS_CMD_VMAPI: + result = process_vmapti(s, cmdpkt, true); + break; default: trace_gicv3_its_cmd_unknown(cmd); break; diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_its_cmd_mapti(uint32_t devid, uint32_t eventid, uint32_t icid, uint32_t in gicv3_its_cmd_inv(void) "GICv3 ITS: command INV or INVALL" gicv3_its_cmd_movall(uint64_t rd1, uint64_t rd2) "GICv3 ITS: command MOVALL RDbase1 0x%" PRIx64 " RDbase2 0x%" PRIx64 gicv3_its_cmd_movi(uint32_t devid, uint32_t eventid, uint32_t icid) "GICv3 ITS: command MOVI DeviceID 0x%x EventID 0x%x ICID 0x%x" +gicv3_its_cmd_vmapi(uint32_t devid, uint32_t eventid, uint32_t vpeid, uint32_t doorbell) "GICv3 ITS: command VMAPI DeviceID 0x%x EventID 0x%x vPEID 0x%x Dbell_pINTID 0x%x" +gicv3_its_cmd_vmapti(uint32_t devid, uint32_t eventid, uint32_t vpeid, uint32_t vintid, uint32_t doorbell) "GICv3 ITS: command VMAPI DeviceID 0x%x EventID 0x%x vPEID 0x%x vINTID 0x%x Dbell_pINTID 0x%x" gicv3_its_cmd_unknown(unsigned cmd) "GICv3 ITS: unknown command 0x%x" gicv3_its_cte_read(uint32_t icid, int valid, uint32_t rdbase) "GICv3 ITS: Collection Table read for ICID 0x%x: valid %d RDBase 0x%x" gicv3_its_cte_write(uint32_t icid, int valid, uint32_t rdbase) "GICv3 ITS: Collection Table write for ICID 0x%x: valid %d RDBase 0x%x" -- 2.25.1 Implement the GICv4 VMAPP command, which writes an entry to the vPE table. For GICv4.1 this command has extra fields in the command packet and additional behaviour. We define the 4.1-only fields with the FIELD macro, but only implement the GICv4.0 version of the command. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-10-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 12 ++++++ hw/intc/arm_gicv3_its.c | 88 ++++++++++++++++++++++++++++++++++++++++ hw/intc/trace-events | 2 + 3 files changed, 102 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(GITS_TYPER, CIL, 36, 1) #define GITS_CMD_INVALL 0x0D #define GITS_CMD_MOVALL 0x0E #define GITS_CMD_DISCARD 0x0F +#define GITS_CMD_VMAPP 0x29 #define GITS_CMD_VMAPTI 0x2A #define GITS_CMD_VMAPI 0x2B @@ -XXX,XX +XXX,XX @@ FIELD(VMAPTI_1, VPEID, 32, 16) FIELD(VMAPTI_2, VINTID, 0, 32) /* VMAPTI only */ FIELD(VMAPTI_2, DOORBELL, 32, 32) +/* VMAPP command fields */ +FIELD(VMAPP_0, ALLOC, 8, 1) /* GICv4.1 only */ +FIELD(VMAPP_0, PTZ, 9, 1) /* GICv4.1 only */ +FIELD(VMAPP_0, VCONFADDR, 16, 36) /* GICv4.1 only */ +FIELD(VMAPP_1, DEFAULT_DOORBELL, 0, 32) /* GICv4.1 only */ +FIELD(VMAPP_1, VPEID, 32, 16) +FIELD(VMAPP_2, RDBASE, 16, 36) +FIELD(VMAPP_2, V, 63, 1) +FIELD(VMAPP_3, VPTSIZE, 0, 8) /* For GICv4.0, bits [7:6] are RES0 */ +FIELD(VMAPP_3, VPTADDR, 16, 36) + /* * 12 bytes Interrupt translation Table Entry size * as per Table 5.3 in GICv3 spec diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ typedef struct ITEntry { uint32_t vpeid; } ITEntry; +typedef struct VTEntry { + bool valid; + unsigned vptsize; + uint32_t rdbase; + uint64_t vptaddr; +} VTEntry; /* * The ITS spec permits a range of CONSTRAINED UNPREDICTABLE options @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_movi(GICv3ITSState *s, const uint64_t *cmdpkt) return update_ite(s, eventid, &dte, &old_ite) ? CMD_CONTINUE : CMD_STALL; } +/* + * Update the vPE Table entry at index @vpeid with the entry @vte. + * Returns true on success, false if there was a memory access error. + */ +static bool update_vte(GICv3ITSState *s, uint32_t vpeid, const VTEntry *vte) +{ + AddressSpace *as = &s->gicv3->dma_as; + uint64_t entry_addr; + uint64_t vteval = 0; + MemTxResult res = MEMTX_OK; + + trace_gicv3_its_vte_write(vpeid, vte->valid, vte->vptsize, vte->vptaddr, + vte->rdbase); + + if (vte->valid) { + vteval = FIELD_DP64(vteval, VTE, VALID, 1); + vteval = FIELD_DP64(vteval, VTE, VPTSIZE, vte->vptsize); + vteval = FIELD_DP64(vteval, VTE, VPTADDR, vte->vptaddr); + vteval = FIELD_DP64(vteval, VTE, RDBASE, vte->rdbase); + } + + entry_addr = table_entry_addr(s, &s->vpet, vpeid, &res); + if (res != MEMTX_OK) { + return false; + } + if (entry_addr == -1) { + /* No L2 table for this index: discard write and continue */ + return true; + } + address_space_stq_le(as, entry_addr, vteval, MEMTXATTRS_UNSPECIFIED, &res); + return res == MEMTX_OK; +} + +static ItsCmdResult process_vmapp(GICv3ITSState *s, const uint64_t *cmdpkt) +{ + VTEntry vte; + uint32_t vpeid; + + if (!its_feature_virtual(s)) { + return CMD_CONTINUE; + } + + vpeid = FIELD_EX64(cmdpkt[1], VMAPP_1, VPEID); + vte.rdbase = FIELD_EX64(cmdpkt[2], VMAPP_2, RDBASE); + vte.valid = FIELD_EX64(cmdpkt[2], VMAPP_2, V); + vte.vptsize = FIELD_EX64(cmdpkt[3], VMAPP_3, VPTSIZE); + vte.vptaddr = FIELD_EX64(cmdpkt[3], VMAPP_3, VPTADDR); + + trace_gicv3_its_cmd_vmapp(vpeid, vte.rdbase, vte.valid, + vte.vptaddr, vte.vptsize); + + /* + * For GICv4.0 the VPT_size field is only 5 bits, whereas we + * define our field macros to include the full GICv4.1 8 bits. + * The range check on VPT_size will catch the cases where + * the guest set the RES0-in-GICv4.0 bits [7:6]. + */ + if (vte.vptsize > FIELD_EX64(s->typer, GITS_TYPER, IDBITS)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid VPT_size 0x%x\n", __func__, vte.vptsize); + return CMD_CONTINUE; + } + + if (vte.valid && vte.rdbase >= s->gicv3->num_cpu) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid rdbase 0x%x\n", __func__, vte.rdbase); + return CMD_CONTINUE; + } + + if (vpeid >= s->vpet.num_entries) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: VPEID 0x%x out of range (must be less than 0x%x)\n", + __func__, vpeid, s->vpet.num_entries); + return CMD_CONTINUE; + } + + return update_vte(s, vpeid, &vte) ? CMD_CONTINUE : CMD_STALL; +} + /* * Current implementation blocks until all * commands are processed @@ -XXX,XX +XXX,XX @@ static void process_cmdq(GICv3ITSState *s) case GITS_CMD_VMAPI: result = process_vmapti(s, cmdpkt, true); break; + case GITS_CMD_VMAPP: + result = process_vmapp(s, cmdpkt); + break; default: trace_gicv3_its_cmd_unknown(cmd); break; diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_its_cmd_movall(uint64_t rd1, uint64_t rd2) "GICv3 ITS: command MOVALL RDba gicv3_its_cmd_movi(uint32_t devid, uint32_t eventid, uint32_t icid) "GICv3 ITS: command MOVI DeviceID 0x%x EventID 0x%x ICID 0x%x" gicv3_its_cmd_vmapi(uint32_t devid, uint32_t eventid, uint32_t vpeid, uint32_t doorbell) "GICv3 ITS: command VMAPI DeviceID 0x%x EventID 0x%x vPEID 0x%x Dbell_pINTID 0x%x" gicv3_its_cmd_vmapti(uint32_t devid, uint32_t eventid, uint32_t vpeid, uint32_t vintid, uint32_t doorbell) "GICv3 ITS: command VMAPI DeviceID 0x%x EventID 0x%x vPEID 0x%x vINTID 0x%x Dbell_pINTID 0x%x" +gicv3_its_cmd_vmapp(uint32_t vpeid, uint64_t rdbase, int valid, uint64_t vptaddr, uint32_t vptsize) "GICv3 ITS: command VMAPP vPEID 0x%x RDbase 0x%" PRIx64 " V %d VPT_addr 0x%" PRIx64 " VPT_size 0x%x" gicv3_its_cmd_unknown(unsigned cmd) "GICv3 ITS: unknown command 0x%x" gicv3_its_cte_read(uint32_t icid, int valid, uint32_t rdbase) "GICv3 ITS: Collection Table read for ICID 0x%x: valid %d RDBase 0x%x" gicv3_its_cte_write(uint32_t icid, int valid, uint32_t rdbase) "GICv3 ITS: Collection Table write for ICID 0x%x: valid %d RDBase 0x%x" @@ -XXX,XX +XXX,XX @@ gicv3_its_ite_write(uint64_t ittaddr, uint32_t eventid, int valid, int inttype, gicv3_its_dte_read(uint32_t devid, int valid, uint32_t size, uint64_t ittaddr) "GICv3 ITS: Device Table read for DeviceID 0x%x: valid %d size 0x%x ITTaddr 0x%" PRIx64 gicv3_its_dte_write(uint32_t devid, int valid, uint32_t size, uint64_t ittaddr) "GICv3 ITS: Device Table write for DeviceID 0x%x: valid %d size 0x%x ITTaddr 0x%" PRIx64 gicv3_its_dte_read_fault(uint32_t devid) "GICv3 ITS: Device Table read for DeviceID 0x%x: faulted" +gicv3_its_vte_write(uint32_t vpeid, int valid, uint32_t vptsize, uint64_t vptaddr, uint32_t rdbase) "GICv3 ITS: vPE Table write for vPEID 0x%x: valid %d VPTsize 0x%x VPTaddr 0x%" PRIx64 " RDbase 0x%x" # armv7m_nvic.c nvic_recompute_state(int vectpending, int vectpending_prio, int exception_prio) "NVIC state recomputed: vectpending %d vectpending_prio %d exception_prio %d" -- 2.25.1 In the ItsCmdResult enum, we currently distinguish only CMD_STALL (failure, stall processing of the command queue) and CMD_CONTINUE (keep processing the queue), and we use the latter both for "there was a parameter error, go on to the next command" and "the command succeeded, go on to the next command". Sometimes we would like to distinguish those two cases, so add CMD_CONTINUE_OK to the enum to represent the success situation, and use it in the relevant places. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-11-peter.maydell@linaro.org --- hw/intc/arm_gicv3_its.c | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ typedef struct VTEntry { * and continue processing. * The process_* functions which handle individual ITS commands all * return an ItsCmdResult which tells process_cmdq() whether it should - * stall or keep going. + * stall, keep going because of an error, or keep going because the + * command was a success. */ typedef enum ItsCmdResult { CMD_STALL = 0, CMD_CONTINUE = 1, + CMD_CONTINUE_OK = 2, } ItsCmdResult; /* True if the ITS supports the GICv4 virtual LPI feature */ @@ -XXX,XX +XXX,XX @@ static ItsCmdResult do_process_its_cmd(GICv3ITSState *s, uint32_t devid, ITEntry ite = {}; /* remove mapping from interrupt translation table */ ite.valid = false; - return update_ite(s, eventid, &dte, &ite) ? CMD_CONTINUE : CMD_STALL; + return update_ite(s, eventid, &dte, &ite) ? CMD_CONTINUE_OK : CMD_STALL; } - return CMD_CONTINUE; + return CMD_CONTINUE_OK; } static ItsCmdResult process_its_cmd(GICv3ITSState *s, const uint64_t *cmdpkt, @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_mapti(GICv3ITSState *s, const uint64_t *cmdpkt, ite.icid = icid; ite.doorbell = INTID_SPURIOUS; ite.vpeid = 0; - return update_ite(s, eventid, &dte, &ite) ? CMD_CONTINUE : CMD_STALL; + return update_ite(s, eventid, &dte, &ite) ? CMD_CONTINUE_OK : CMD_STALL; } static ItsCmdResult process_vmapti(GICv3ITSState *s, const uint64_t *cmdpkt, @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_vmapti(GICv3ITSState *s, const uint64_t *cmdpkt, ite.icid = 0; ite.doorbell = doorbell; ite.vpeid = vpeid; - return update_ite(s, eventid, &dte, &ite) ? CMD_CONTINUE : CMD_STALL; + return update_ite(s, eventid, &dte, &ite) ? CMD_CONTINUE_OK : CMD_STALL; } /* @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_mapc(GICv3ITSState *s, const uint64_t *cmdpkt) return CMD_CONTINUE; } - return update_cte(s, icid, &cte) ? CMD_CONTINUE : CMD_STALL; + return update_cte(s, icid, &cte) ? CMD_CONTINUE_OK : CMD_STALL; } /* @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_mapd(GICv3ITSState *s, const uint64_t *cmdpkt) return CMD_CONTINUE; } - return update_dte(s, devid, &dte) ? CMD_CONTINUE : CMD_STALL; + return update_dte(s, devid, &dte) ? CMD_CONTINUE_OK : CMD_STALL; } static ItsCmdResult process_movall(GICv3ITSState *s, const uint64_t *cmdpkt) @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_movall(GICv3ITSState *s, const uint64_t *cmdpkt) if (rd1 == rd2) { /* Move to same target must succeed as a no-op */ - return CMD_CONTINUE; + return CMD_CONTINUE_OK; } /* Move all pending LPIs from redistributor 1 to redistributor 2 */ gicv3_redist_movall_lpis(&s->gicv3->cpu[rd1], &s->gicv3->cpu[rd2]); - return CMD_CONTINUE; + return CMD_CONTINUE_OK; } static ItsCmdResult process_movi(GICv3ITSState *s, const uint64_t *cmdpkt) @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_movi(GICv3ITSState *s, const uint64_t *cmdpkt) /* Update the ICID field in the interrupt translation table entry */ old_ite.icid = new_icid; - return update_ite(s, eventid, &dte, &old_ite) ? CMD_CONTINUE : CMD_STALL; + return update_ite(s, eventid, &dte, &old_ite) ? CMD_CONTINUE_OK : CMD_STALL; } /* @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_vmapp(GICv3ITSState *s, const uint64_t *cmdpkt) return CMD_CONTINUE; } - return update_vte(s, vpeid, &vte) ? CMD_CONTINUE : CMD_STALL; + return update_vte(s, vpeid, &vte) ? CMD_CONTINUE_OK : CMD_STALL; } /* @@ -XXX,XX +XXX,XX @@ static void process_cmdq(GICv3ITSState *s) } while (wr_offset != rd_offset) { - ItsCmdResult result = CMD_CONTINUE; + ItsCmdResult result = CMD_CONTINUE_OK; void *hostmem; hwaddr buflen; uint64_t cmdpkt[GITS_CMDQ_ENTRY_WORDS]; @@ -XXX,XX +XXX,XX @@ static void process_cmdq(GICv3ITSState *s) trace_gicv3_its_cmd_unknown(cmd); break; } - if (result == CMD_CONTINUE) { + if (result != CMD_STALL) { + /* CMD_CONTINUE or CMD_CONTINUE_OK */ rd_offset++; rd_offset %= s->cq.num_entries; s->creadr = FIELD_DP64(s->creadr, GITS_CREADR, OFFSET, rd_offset); -- 2.25.1 The operation of finding an interrupt table entry given a (DeviceID, EventID) pair is necessary in multiple different ITS commands. The process requires first using the DeviceID as an index into the device table to find the DTE, and then useng the EventID as an index into the interrupt table specified by that DTE to find the ITE. We also need to handle all the possible error cases: indexes out of range, table memory not readable, table entries not valid. Factor this out into a separate lookup_ite() function which we can then call from the places where we were previously open-coding this sequence. We'll also need this for some of the new GICv4.0 commands. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-12-peter.maydell@linaro.org --- hw/intc/arm_gicv3_its.c | 124 +++++++++++++++++++++------------------- 1 file changed, 64 insertions(+), 60 deletions(-) diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ out: return res; } +/* + * Given a (DeviceID, EventID), look up the corresponding ITE, including + * checking for the various invalid-value cases. If we find a valid ITE, + * fill in @ite and @dte and return CMD_CONTINUE_OK. Otherwise return + * CMD_STALL or CMD_CONTINUE as appropriate (and the contents of @ite + * should not be relied on). + * + * The string @who is purely for the LOG_GUEST_ERROR messages, + * and should indicate the name of the calling function or similar. + */ +static ItsCmdResult lookup_ite(GICv3ITSState *s, const char *who, + uint32_t devid, uint32_t eventid, ITEntry *ite, + DTEntry *dte) +{ + uint64_t num_eventids; + + if (devid >= s->dt.num_entries) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid command attributes: devid %d>=%d", + who, devid, s->dt.num_entries); + return CMD_CONTINUE; + } + + if (get_dte(s, devid, dte) != MEMTX_OK) { + return CMD_STALL; + } + if (!dte->valid) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid command attributes: " + "invalid dte for %d\n", who, devid); + return CMD_CONTINUE; + } + + num_eventids = 1ULL << (dte->size + 1); + if (eventid >= num_eventids) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid command attributes: eventid %d >= %" + PRId64 "\n", who, eventid, num_eventids); + return CMD_CONTINUE; + } + + if (get_ite(s, eventid, dte, ite) != MEMTX_OK) { + return CMD_STALL; + } + + if (!ite->valid) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid command attributes: invalid ITE\n", who); + return CMD_CONTINUE; + } + + return CMD_CONTINUE_OK; +} + /* * This function handles the processing of following commands based on * the ItsCmdType parameter passed:- @@ -XXX,XX +XXX,XX @@ out: static ItsCmdResult do_process_its_cmd(GICv3ITSState *s, uint32_t devid, uint32_t eventid, ItsCmdType cmd) { - uint64_t num_eventids; DTEntry dte; CTEntry cte; ITEntry ite; + ItsCmdResult cmdres; - if (devid >= s->dt.num_entries) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid command attributes: devid %d>=%d", - __func__, devid, s->dt.num_entries); - return CMD_CONTINUE; + cmdres = lookup_ite(s, __func__, devid, eventid, &ite, &dte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; } - if (get_dte(s, devid, &dte) != MEMTX_OK) { - return CMD_STALL; - } - if (!dte.valid) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid command attributes: " - "invalid dte for %d\n", __func__, devid); - return CMD_CONTINUE; - } - - num_eventids = 1ULL << (dte.size + 1); - if (eventid >= num_eventids) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid command attributes: eventid %d >= %" - PRId64 "\n", - __func__, eventid, num_eventids); - return CMD_CONTINUE; - } - - if (get_ite(s, eventid, &dte, &ite) != MEMTX_OK) { - return CMD_STALL; - } - - if (!ite.valid || ite.inttype != ITE_INTTYPE_PHYSICAL) { + if (ite.inttype != ITE_INTTYPE_PHYSICAL) { qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid command attributes: invalid ITE\n", __func__); @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_movi(GICv3ITSState *s, const uint64_t *cmdpkt) { uint32_t devid, eventid; uint16_t new_icid; - uint64_t num_eventids; DTEntry dte; CTEntry old_cte, new_cte; ITEntry old_ite; + ItsCmdResult cmdres; devid = FIELD_EX64(cmdpkt[0], MOVI_0, DEVICEID); eventid = FIELD_EX64(cmdpkt[1], MOVI_1, EVENTID); @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_movi(GICv3ITSState *s, const uint64_t *cmdpkt) trace_gicv3_its_cmd_movi(devid, eventid, new_icid); - if (devid >= s->dt.num_entries) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid command attributes: devid %d>=%d", - __func__, devid, s->dt.num_entries); - return CMD_CONTINUE; - } - if (get_dte(s, devid, &dte) != MEMTX_OK) { - return CMD_STALL; + cmdres = lookup_ite(s, __func__, devid, eventid, &old_ite, &dte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; } - if (!dte.valid) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid command attributes: " - "invalid dte for %d\n", __func__, devid); - return CMD_CONTINUE; - } - - num_eventids = 1ULL << (dte.size + 1); - if (eventid >= num_eventids) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid command attributes: eventid %d >= %" - PRId64 "\n", - __func__, eventid, num_eventids); - return CMD_CONTINUE; - } - - if (get_ite(s, eventid, &dte, &old_ite) != MEMTX_OK) { - return CMD_STALL; - } - - if (!old_ite.valid || old_ite.inttype != ITE_INTTYPE_PHYSICAL) { + if (old_ite.inttype != ITE_INTTYPE_PHYSICAL) { qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid command attributes: invalid ITE\n", __func__); -- 2.25.1 Factor out the sequence of looking up a CTE from an ICID including the validity and error checks. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-13-peter.maydell@linaro.org --- hw/intc/arm_gicv3_its.c | 109 ++++++++++++++-------------------------- 1 file changed, 39 insertions(+), 70 deletions(-) diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static ItsCmdResult lookup_ite(GICv3ITSState *s, const char *who, return CMD_CONTINUE_OK; } +/* + * Given an ICID, look up the corresponding CTE, including checking for various + * invalid-value cases. If we find a valid CTE, fill in @cte and return + * CMD_CONTINUE_OK; otherwise return CMD_STALL or CMD_CONTINUE (and the + * contents of @cte should not be relied on). + * + * The string @who is purely for the LOG_GUEST_ERROR messages, + * and should indicate the name of the calling function or similar. + */ +static ItsCmdResult lookup_cte(GICv3ITSState *s, const char *who, + uint32_t icid, CTEntry *cte) +{ + if (icid >= s->ct.num_entries) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid ICID 0x%x\n", who, icid); + return CMD_CONTINUE; + } + if (get_cte(s, icid, cte) != MEMTX_OK) { + return CMD_STALL; + } + if (!cte->valid) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid CTE\n", who); + return CMD_CONTINUE; + } + if (cte->rdbase >= s->gicv3->num_cpu) { + return CMD_CONTINUE; + } + return CMD_CONTINUE_OK; +} + + /* * This function handles the processing of following commands based on * the ItsCmdType parameter passed:- @@ -XXX,XX +XXX,XX @@ static ItsCmdResult do_process_its_cmd(GICv3ITSState *s, uint32_t devid, return CMD_CONTINUE; } - if (ite.icid >= s->ct.num_entries) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid ICID 0x%x in ITE (table corrupted?)\n", - __func__, ite.icid); - return CMD_CONTINUE; - } - - if (get_cte(s, ite.icid, &cte) != MEMTX_OK) { - return CMD_STALL; - } - if (!cte.valid) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid command attributes: invalid CTE\n", - __func__); - return CMD_CONTINUE; - } - - /* - * Current implementation only supports rdbase == procnum - * Hence rdbase physical address is ignored - */ - if (cte.rdbase >= s->gicv3->num_cpu) { - return CMD_CONTINUE; + cmdres = lookup_cte(s, __func__, ite.icid, &cte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; } if ((cmd == CLEAR) || (cmd == DISCARD)) { @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_movi(GICv3ITSState *s, const uint64_t *cmdpkt) return CMD_CONTINUE; } - if (old_ite.icid >= s->ct.num_entries) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid ICID 0x%x in ITE (table corrupted?)\n", - __func__, old_ite.icid); - return CMD_CONTINUE; + cmdres = lookup_cte(s, __func__, old_ite.icid, &old_cte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; } - - if (new_icid >= s->ct.num_entries) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid command attributes: ICID 0x%x\n", - __func__, new_icid); - return CMD_CONTINUE; - } - - if (get_cte(s, old_ite.icid, &old_cte) != MEMTX_OK) { - return CMD_STALL; - } - if (!old_cte.valid) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid command attributes: " - "invalid CTE for old ICID 0x%x\n", - __func__, old_ite.icid); - return CMD_CONTINUE; - } - - if (get_cte(s, new_icid, &new_cte) != MEMTX_OK) { - return CMD_STALL; - } - if (!new_cte.valid) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid command attributes: " - "invalid CTE for new ICID 0x%x\n", - __func__, new_icid); - return CMD_CONTINUE; - } - - if (old_cte.rdbase >= s->gicv3->num_cpu) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: CTE has invalid rdbase 0x%x\n", - __func__, old_cte.rdbase); - return CMD_CONTINUE; - } - - if (new_cte.rdbase >= s->gicv3->num_cpu) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: CTE has invalid rdbase 0x%x\n", - __func__, new_cte.rdbase); - return CMD_CONTINUE; + cmdres = lookup_cte(s, __func__, new_icid, &new_cte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; } if (old_cte.rdbase != new_cte.rdbase) { -- 2.25.1 Split the part of process_its_cmd() which is specific to physical interrupts into its own function. This is the part which starts by taking the ICID and looking it up in the collection table. The handling of virtual interrupts is significantly different (involving a lookup in the vPE table) so structuring the code with one sub-function for the physical interrupt case and one for the virtual interrupt case will be clearer than putting both cases in one large function. The code for handling the "remove mapping from ITE" for the DISCARD command remains in process_its_cmd() because it is common to both virtual and physical interrupts. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-14-peter.maydell@linaro.org --- hw/intc/arm_gicv3_its.c | 51 ++++++++++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 18 deletions(-) diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static ItsCmdResult lookup_cte(GICv3ITSState *s, const char *who, return CMD_CONTINUE_OK; } +static ItsCmdResult process_its_cmd_phys(GICv3ITSState *s, const ITEntry *ite, + int irqlevel) +{ + CTEntry cte; + ItsCmdResult cmdres; + + cmdres = lookup_cte(s, __func__, ite->icid, &cte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; + } + gicv3_redist_process_lpi(&s->gicv3->cpu[cte.rdbase], ite->intid, irqlevel); + return CMD_CONTINUE_OK; +} /* * This function handles the processing of following commands based on @@ -XXX,XX +XXX,XX @@ static ItsCmdResult do_process_its_cmd(GICv3ITSState *s, uint32_t devid, uint32_t eventid, ItsCmdType cmd) { DTEntry dte; - CTEntry cte; ITEntry ite; ItsCmdResult cmdres; + int irqlevel; cmdres = lookup_ite(s, __func__, devid, eventid, &ite, &dte); if (cmdres != CMD_CONTINUE_OK) { return cmdres; } - if (ite.inttype != ITE_INTTYPE_PHYSICAL) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: invalid command attributes: invalid ITE\n", - __func__); - return CMD_CONTINUE; + irqlevel = (cmd == CLEAR || cmd == DISCARD) ? 0 : 1; + + switch (ite.inttype) { + case ITE_INTTYPE_PHYSICAL: + cmdres = process_its_cmd_phys(s, &ite, irqlevel); + break; + case ITE_INTTYPE_VIRTUAL: + if (!its_feature_virtual(s)) { + /* Can't happen unless guest is illegally writing to table memory */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid type %d in ITE (table corrupted?)\n", + __func__, ite.inttype); + return CMD_CONTINUE; + } + /* The GICv4 virtual interrupt handling will go here */ + g_assert_not_reached(); + default: + g_assert_not_reached(); } - cmdres = lookup_cte(s, __func__, ite.icid, &cte); - if (cmdres != CMD_CONTINUE_OK) { - return cmdres; - } - - if ((cmd == CLEAR) || (cmd == DISCARD)) { - gicv3_redist_process_lpi(&s->gicv3->cpu[cte.rdbase], ite.intid, 0); - } else { - gicv3_redist_process_lpi(&s->gicv3->cpu[cte.rdbase], ite.intid, 1); - } - - if (cmd == DISCARD) { + if (cmdres == CMD_CONTINUE_OK && cmd == DISCARD) { ITEntry ite = {}; /* remove mapping from interrupt translation table */ ite.valid = false; -- 2.25.1 For GICv4, interrupt table entries read by process_its_cmd() may indicate virtual LPIs which are to be directly injected into a VM. Implement the ITS side of the code for handling this. This is similar to the existing handling of physical LPIs, but instead of looking up a collection ID in a collection table, we look up a vPEID in a vPE table. As with the physical LPIs, we leave the rest of the work to code in the redistributor device. The redistributor half will be implemented in a later commit; for now we just provide a stub function which does nothing. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-15-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 17 +++++++ hw/intc/arm_gicv3_its.c | 99 +++++++++++++++++++++++++++++++++++++- hw/intc/arm_gicv3_redist.c | 9 ++++ hw/intc/trace-events | 2 + 4 files changed, 125 insertions(+), 2 deletions(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ MemTxResult gicv3_redist_write(void *opaque, hwaddr offset, uint64_t data, void gicv3_dist_set_irq(GICv3State *s, int irq, int level); void gicv3_redist_set_irq(GICv3CPUState *cs, int irq, int level); void gicv3_redist_process_lpi(GICv3CPUState *cs, int irq, int level); +/** + * gicv3_redist_process_vlpi: + * @cs: GICv3CPUState + * @irq: (virtual) interrupt number + * @vptaddr: (guest) address of VLPI table + * @doorbell: doorbell (physical) interrupt number (1023 for "no doorbell") + * @level: level to set @irq to + * + * Process a virtual LPI being directly injected by the ITS. This function + * will update the VLPI table specified by @vptaddr and @vptsize. If the + * vCPU corresponding to that VLPI table is currently running on + * the CPU associated with this redistributor, directly inject the VLPI + * @irq. If the vCPU is not running on this CPU, raise the doorbell + * interrupt instead. + */ +void gicv3_redist_process_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr, + int doorbell, int level); void gicv3_redist_lpi_pending(GICv3CPUState *cs, int irq, int level); /** * gicv3_redist_update_lpi: diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ out: return res; } +/* + * Read the vPE Table entry at index @vpeid. On success (including + * successfully determining that there is no valid entry for this index), + * we return MEMTX_OK and populate the VTEntry struct accordingly. + * If there is an error reading memory then we return the error code. + */ +static MemTxResult get_vte(GICv3ITSState *s, uint32_t vpeid, VTEntry *vte) +{ + MemTxResult res = MEMTX_OK; + AddressSpace *as = &s->gicv3->dma_as; + uint64_t entry_addr = table_entry_addr(s, &s->vpet, vpeid, &res); + uint64_t vteval; + + if (entry_addr == -1) { + /* No L2 table entry, i.e. no valid VTE, or a memory error */ + vte->valid = false; + goto out; + } + vteval = address_space_ldq_le(as, entry_addr, MEMTXATTRS_UNSPECIFIED, &res); + if (res != MEMTX_OK) { + goto out; + } + vte->valid = FIELD_EX64(vteval, VTE, VALID); + vte->vptsize = FIELD_EX64(vteval, VTE, VPTSIZE); + vte->vptaddr = FIELD_EX64(vteval, VTE, VPTADDR); + vte->rdbase = FIELD_EX64(vteval, VTE, RDBASE); +out: + if (res != MEMTX_OK) { + trace_gicv3_its_vte_read_fault(vpeid); + } else { + trace_gicv3_its_vte_read(vpeid, vte->valid, vte->vptsize, + vte->vptaddr, vte->rdbase); + } + return res; +} + /* * Given a (DeviceID, EventID), look up the corresponding ITE, including * checking for the various invalid-value cases. If we find a valid ITE, @@ -XXX,XX +XXX,XX @@ static ItsCmdResult lookup_cte(GICv3ITSState *s, const char *who, return CMD_CONTINUE_OK; } +/* + * Given a VPEID, look up the corresponding VTE, including checking + * for various invalid-value cases. if we find a valid VTE, fill in @vte + * and return CMD_CONTINUE_OK; otherwise return CMD_STALL or CMD_CONTINUE + * (and the contents of @vte should not be relied on). + * + * The string @who is purely for the LOG_GUEST_ERROR messages, + * and should indicate the name of the calling function or similar. + */ +static ItsCmdResult lookup_vte(GICv3ITSState *s, const char *who, + uint32_t vpeid, VTEntry *vte) +{ + if (vpeid >= s->vpet.num_entries) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid VPEID 0x%x\n", who, vpeid); + return CMD_CONTINUE; + } + + if (get_vte(s, vpeid, vte) != MEMTX_OK) { + return CMD_STALL; + } + if (!vte->valid) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid VTE for VPEID 0x%x\n", who, vpeid); + return CMD_CONTINUE; + } + + if (vte->rdbase >= s->gicv3->num_cpu) { + return CMD_CONTINUE; + } + return CMD_CONTINUE_OK; +} + static ItsCmdResult process_its_cmd_phys(GICv3ITSState *s, const ITEntry *ite, int irqlevel) { @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_its_cmd_phys(GICv3ITSState *s, const ITEntry *ite, return CMD_CONTINUE_OK; } +static ItsCmdResult process_its_cmd_virt(GICv3ITSState *s, const ITEntry *ite, + int irqlevel) +{ + VTEntry vte; + ItsCmdResult cmdres; + + cmdres = lookup_vte(s, __func__, ite->vpeid, &vte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; + } + + if (!intid_in_lpi_range(ite->intid) || + ite->intid >= (1ULL << (vte.vptsize + 1))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: intid 0x%x out of range\n", + __func__, ite->intid); + return CMD_CONTINUE; + } + + /* + * For QEMU the actual pending of the vLPI is handled in the + * redistributor code + */ + gicv3_redist_process_vlpi(&s->gicv3->cpu[vte.rdbase], ite->intid, + vte.vptaddr << 16, ite->doorbell, irqlevel); + return CMD_CONTINUE_OK; +} + /* * This function handles the processing of following commands based on * the ItsCmdType parameter passed:- @@ -XXX,XX +XXX,XX @@ static ItsCmdResult do_process_its_cmd(GICv3ITSState *s, uint32_t devid, __func__, ite.inttype); return CMD_CONTINUE; } - /* The GICv4 virtual interrupt handling will go here */ - g_assert_not_reached(); + cmdres = process_its_cmd_virt(s, &ite, irqlevel); + break; default: g_assert_not_reached(); } diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ void gicv3_redist_movall_lpis(GICv3CPUState *src, GICv3CPUState *dest) gicv3_redist_update_lpi(dest); } +void gicv3_redist_process_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr, + int doorbell, int level) +{ + /* + * The redistributor handling for being handed a VLPI by the ITS + * will be added in a subsequent commit. + */ +} + void gicv3_redist_set_irq(GICv3CPUState *cs, int irq, int level) { /* Update redistributor state for a change in an external PPI input line */ diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_its_ite_write(uint64_t ittaddr, uint32_t eventid, int valid, int inttype, gicv3_its_dte_read(uint32_t devid, int valid, uint32_t size, uint64_t ittaddr) "GICv3 ITS: Device Table read for DeviceID 0x%x: valid %d size 0x%x ITTaddr 0x%" PRIx64 gicv3_its_dte_write(uint32_t devid, int valid, uint32_t size, uint64_t ittaddr) "GICv3 ITS: Device Table write for DeviceID 0x%x: valid %d size 0x%x ITTaddr 0x%" PRIx64 gicv3_its_dte_read_fault(uint32_t devid) "GICv3 ITS: Device Table read for DeviceID 0x%x: faulted" +gicv3_its_vte_read(uint32_t vpeid, int valid, uint32_t vptsize, uint64_t vptaddr, uint32_t rdbase) "GICv3 ITS: vPE Table read for vPEID 0x%x: valid %d VPTsize 0x%x VPTaddr 0x%" PRIx64 " RDbase 0x%x" +gicv3_its_vte_read_fault(uint32_t vpeid) "GICv3 ITS: vPE Table read for vPEID 0x%x: faulted" gicv3_its_vte_write(uint32_t vpeid, int valid, uint32_t vptsize, uint64_t vptaddr, uint32_t rdbase) "GICv3 ITS: vPE Table write for vPEID 0x%x: valid %d VPTsize 0x%x VPTaddr 0x%" PRIx64 " RDbase 0x%x" # armv7m_nvic.c -- 2.25.1 The GICv4 ITS VMOVP command's semantics require it to perform the operation on every ITS connected to the same GIC that the ITS that received the command is attached to. This means that the GIC object needs to keep a pointer to every ITS that is connected to it (previously it was sufficient for the ITS to have a pointer to its GIC). Add a glib ptrarray to the GICv3 object which holds pointers to every connected ITS, and make the ITS add itself to the array for the GIC it is connected to when it is realized. Note that currently all QEMU machine types with an ITS have exactly one ITS in the system, so typically the length of this ptrarray will be 1. Multiple ITSes are typically used to improve performance on real hardware, so we wouldn't need to have more than one unless we were modelling a real machine type that had multile ITSes. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-16-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 9 +++++++++ include/hw/intc/arm_gicv3_common.h | 2 ++ hw/intc/arm_gicv3_common.c | 2 ++ hw/intc/arm_gicv3_its.c | 2 ++ hw/intc/arm_gicv3_its_kvm.c | 2 ++ 5 files changed, 17 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ static inline void gicv3_cache_all_target_cpustates(GICv3State *s) void gicv3_set_gicv3state(CPUState *cpu, GICv3CPUState *s); +/* + * The ITS should call this when it is realized to add itself + * to its GIC's list of connected ITSes. + */ +static inline void gicv3_add_its(GICv3State *s, DeviceState *its) +{ + g_ptr_array_add(s->itslist, its); +} + #endif /* QEMU_ARM_GICV3_INTERNAL_H */ diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3State { uint32_t gicd_nsacr[DIV_ROUND_UP(GICV3_MAXIRQ, 16)]; GICv3CPUState *cpu; + /* List of all ITSes connected to this GIC */ + GPtrArray *itslist; }; #define GICV3_BITMAP_ACCESSORS(BMP) \ diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_realize(DeviceState *dev, Error **errp) cpuidx += s->redist_region_count[i]; s->cpu[cpuidx - 1].gicr_typer |= GICR_TYPER_LAST; } + + s->itslist = g_ptr_array_new(); } static void arm_gicv3_finalize(Object *obj) diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static void gicv3_arm_its_realize(DeviceState *dev, Error **errp) } } + gicv3_add_its(s->gicv3, dev); + gicv3_its_init_mmio(s, &gicv3_its_control_ops, &gicv3_its_translation_ops); /* set the ITS default features supported */ diff --git a/hw/intc/arm_gicv3_its_kvm.c b/hw/intc/arm_gicv3_its_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its_kvm.c +++ b/hw/intc/arm_gicv3_its_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_its_realize(DeviceState *dev, Error **errp) kvm_arm_register_device(&s->iomem_its_cntrl, -1, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_ITS_ADDR_TYPE, s->dev_fd, 0); + gicv3_add_its(s->gicv3, dev); + gicv3_its_init_mmio(s, NULL, NULL); if (!kvm_device_check_attr(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_ITS_REGS, -- 2.25.1 Implement the GICv4 VMOVP command, which updates an entry in the vPE table to change its rdbase field. This command is unique in the ITS command set because its effects must be propagated to all the other ITSes connected to the same GIC as the ITS which executes the VMOVP command. The GICv4 spec allows two implementation choices for handling the propagation to other ITSes: * If GITS_TYPER.VMOVP is 1, the guest only needs to issue the command on one ITS, and the implementation handles the propagation to all ITSes * If GITS_TYPER.VMOVP is 0, the guest must issue the command on every ITS, and arrange for the ITSes to synchronize the updates with each other by setting ITSList and Sequence Number fields in the command packets We choose the GITS_TYPER.VMOVP = 1 approach, and synchronously execute the update on every ITS. For GICv4.1 this command has extra fields in the command packet and additional behaviour. We define the 4.1-only fields with the FIELD macro, but only implement the GICv4.0 version of the command. Note that we don't update the reported GITS_TYPER value here; we'll do that later in a commit which updates all the reported feature bit and ID register values for GICv4. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-17-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 18 ++++++++++ hw/intc/arm_gicv3_its.c | 75 ++++++++++++++++++++++++++++++++++++++++ hw/intc/trace-events | 1 + 3 files changed, 94 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(GITS_TYPER, CIL, 36, 1) #define GITS_CMD_INVALL 0x0D #define GITS_CMD_MOVALL 0x0E #define GITS_CMD_DISCARD 0x0F +#define GITS_CMD_VMOVP 0x22 #define GITS_CMD_VMAPP 0x29 #define GITS_CMD_VMAPTI 0x2A #define GITS_CMD_VMAPI 0x2B @@ -XXX,XX +XXX,XX @@ FIELD(VMAPP_2, V, 63, 1) FIELD(VMAPP_3, VPTSIZE, 0, 8) /* For GICv4.0, bits [7:6] are RES0 */ FIELD(VMAPP_3, VPTADDR, 16, 36) +/* VMOVP command fields */ +FIELD(VMOVP_0, SEQNUM, 32, 16) /* not used for GITS_TYPER.VMOVP == 1 */ +FIELD(VMOVP_1, ITSLIST, 0, 16) /* not used for GITS_TYPER.VMOVP == 1 */ +FIELD(VMOVP_1, VPEID, 32, 16) +FIELD(VMOVP_2, RDBASE, 16, 36) +FIELD(VMOVP_2, DB, 63, 1) /* GICv4.1 only */ +FIELD(VMOVP_3, DEFAULT_DOORBELL, 0, 32) /* GICv4.1 only */ + /* * 12 bytes Interrupt translation Table Entry size * as per Table 5.3 in GICv3 spec @@ -XXX,XX +XXX,XX @@ static inline void gicv3_add_its(GICv3State *s, DeviceState *its) g_ptr_array_add(s->itslist, its); } +/* + * The ITS can use this for operations that must be performed on + * every ITS connected to the same GIC that it is + */ +static inline void gicv3_foreach_its(GICv3State *s, GFunc func, void *opaque) +{ + g_ptr_array_foreach(s->itslist, func, opaque); +} + #endif /* QEMU_ARM_GICV3_INTERNAL_H */ diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_vmapp(GICv3ITSState *s, const uint64_t *cmdpkt) return update_vte(s, vpeid, &vte) ? CMD_CONTINUE_OK : CMD_STALL; } +typedef struct VmovpCallbackData { + uint64_t rdbase; + uint32_t vpeid; + /* + * Overall command result. If more than one callback finds an + * error, STALL beats CONTINUE. + */ + ItsCmdResult result; +} VmovpCallbackData; + +static void vmovp_callback(gpointer data, gpointer opaque) +{ + /* + * This function is called to update the VPEID field in a VPE + * table entry for this ITS. This might be because of a VMOVP + * command executed on any ITS that is connected to the same GIC + * as this ITS. We need to read the VPE table entry for the VPEID + * and update its RDBASE field. + */ + GICv3ITSState *s = data; + VmovpCallbackData *cbdata = opaque; + VTEntry vte; + ItsCmdResult cmdres; + + cmdres = lookup_vte(s, __func__, cbdata->vpeid, &vte); + switch (cmdres) { + case CMD_STALL: + cbdata->result = CMD_STALL; + return; + case CMD_CONTINUE: + if (cbdata->result != CMD_STALL) { + cbdata->result = CMD_CONTINUE; + } + return; + case CMD_CONTINUE_OK: + break; + } + + vte.rdbase = cbdata->rdbase; + if (!update_vte(s, cbdata->vpeid, &vte)) { + cbdata->result = CMD_STALL; + } +} + +static ItsCmdResult process_vmovp(GICv3ITSState *s, const uint64_t *cmdpkt) +{ + VmovpCallbackData cbdata; + + if (!its_feature_virtual(s)) { + return CMD_CONTINUE; + } + + cbdata.vpeid = FIELD_EX64(cmdpkt[1], VMOVP_1, VPEID); + cbdata.rdbase = FIELD_EX64(cmdpkt[2], VMOVP_2, RDBASE); + + trace_gicv3_its_cmd_vmovp(cbdata.vpeid, cbdata.rdbase); + + if (cbdata.rdbase >= s->gicv3->num_cpu) { + return CMD_CONTINUE; + } + + /* + * Our ITS implementation reports GITS_TYPER.VMOVP == 1, which means + * that when the VMOVP command is executed on an ITS to change the + * VPEID field in a VPE table entry the change must be propagated + * to all the ITSes connected to the same GIC. + */ + cbdata.result = CMD_CONTINUE_OK; + gicv3_foreach_its(s->gicv3, vmovp_callback, &cbdata); + return cbdata.result; +} + /* * Current implementation blocks until all * commands are processed @@ -XXX,XX +XXX,XX @@ static void process_cmdq(GICv3ITSState *s) case GITS_CMD_VMAPP: result = process_vmapp(s, cmdpkt); break; + case GITS_CMD_VMOVP: + result = process_vmovp(s, cmdpkt); + break; default: trace_gicv3_its_cmd_unknown(cmd); break; diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_its_cmd_movi(uint32_t devid, uint32_t eventid, uint32_t icid) "GICv3 ITS: gicv3_its_cmd_vmapi(uint32_t devid, uint32_t eventid, uint32_t vpeid, uint32_t doorbell) "GICv3 ITS: command VMAPI DeviceID 0x%x EventID 0x%x vPEID 0x%x Dbell_pINTID 0x%x" gicv3_its_cmd_vmapti(uint32_t devid, uint32_t eventid, uint32_t vpeid, uint32_t vintid, uint32_t doorbell) "GICv3 ITS: command VMAPI DeviceID 0x%x EventID 0x%x vPEID 0x%x vINTID 0x%x Dbell_pINTID 0x%x" gicv3_its_cmd_vmapp(uint32_t vpeid, uint64_t rdbase, int valid, uint64_t vptaddr, uint32_t vptsize) "GICv3 ITS: command VMAPP vPEID 0x%x RDbase 0x%" PRIx64 " V %d VPT_addr 0x%" PRIx64 " VPT_size 0x%x" +gicv3_its_cmd_vmovp(uint32_t vpeid, uint64_t rdbase) "GICv3 ITS: command VMOVP vPEID 0x%x RDbase 0x%" PRIx64 gicv3_its_cmd_unknown(unsigned cmd) "GICv3 ITS: unknown command 0x%x" gicv3_its_cte_read(uint32_t icid, int valid, uint32_t rdbase) "GICv3 ITS: Collection Table read for ICID 0x%x: valid %d RDBase 0x%x" gicv3_its_cte_write(uint32_t icid, int valid, uint32_t rdbase) "GICv3 ITS: Collection Table write for ICID 0x%x: valid %d RDBase 0x%x" -- 2.25.1 The VSYNC command forces the ITS to synchronize all outstanding ITS operations for the specified vPEID, so that subsequent writes to GITS_TRANSLATER honour them. The QEMU implementation is always in sync, so for us this is a nop, like the existing SYNC command. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-18-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 1 + hw/intc/arm_gicv3_its.c | 11 +++++++++++ hw/intc/trace-events | 1 + 3 files changed, 13 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(GITS_TYPER, CIL, 36, 1) #define GITS_CMD_MOVALL 0x0E #define GITS_CMD_DISCARD 0x0F #define GITS_CMD_VMOVP 0x22 +#define GITS_CMD_VSYNC 0x25 #define GITS_CMD_VMAPP 0x29 #define GITS_CMD_VMAPTI 0x2A #define GITS_CMD_VMAPI 0x2B diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static void process_cmdq(GICv3ITSState *s) */ trace_gicv3_its_cmd_sync(); break; + case GITS_CMD_VSYNC: + /* + * VSYNC also is a nop, because our implementation is always + * in sync. + */ + if (!its_feature_virtual(s)) { + result = CMD_CONTINUE; + break; + } + trace_gicv3_its_cmd_vsync(); + break; case GITS_CMD_MAPD: result = process_mapd(s, cmdpkt); break; diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_its_cmd_vmapi(uint32_t devid, uint32_t eventid, uint32_t vpeid, uint32_t d gicv3_its_cmd_vmapti(uint32_t devid, uint32_t eventid, uint32_t vpeid, uint32_t vintid, uint32_t doorbell) "GICv3 ITS: command VMAPI DeviceID 0x%x EventID 0x%x vPEID 0x%x vINTID 0x%x Dbell_pINTID 0x%x" gicv3_its_cmd_vmapp(uint32_t vpeid, uint64_t rdbase, int valid, uint64_t vptaddr, uint32_t vptsize) "GICv3 ITS: command VMAPP vPEID 0x%x RDbase 0x%" PRIx64 " V %d VPT_addr 0x%" PRIx64 " VPT_size 0x%x" gicv3_its_cmd_vmovp(uint32_t vpeid, uint64_t rdbase) "GICv3 ITS: command VMOVP vPEID 0x%x RDbase 0x%" PRIx64 +gicv3_its_cmd_vsync(void) "GICv3 ITS: command VSYNC" gicv3_its_cmd_unknown(unsigned cmd) "GICv3 ITS: unknown command 0x%x" gicv3_its_cte_read(uint32_t icid, int valid, uint32_t rdbase) "GICv3 ITS: Collection Table read for ICID 0x%x: valid %d RDBase 0x%x" gicv3_its_cte_write(uint32_t icid, int valid, uint32_t rdbase) "GICv3 ITS: Collection Table write for ICID 0x%x: valid %d RDBase 0x%x" -- 2.25.1 We were previously implementing INV (like INVALL) to just blow away cached highest-priority-pending-LPI information on all connected redistributors. For GICv4.0, this isn't going to be sufficient, because the LPI we are invalidating cached information for might be either physical or virtual, and the required action is different for those two cases. So we need to do the full process of looking up the ITE from the devid and eventid. This also means we can do the error checks that the spec lists for this command. Split out INV handling into a process_inv() function like our other command-processing functions. For the moment, stick to handling only physical LPIs; we will add the vLPI parts later. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-19-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 12 +++++++++ hw/intc/arm_gicv3_its.c | 50 +++++++++++++++++++++++++++++++++++++- hw/intc/arm_gicv3_redist.c | 11 +++++++++ hw/intc/trace-events | 3 ++- 4 files changed, 74 insertions(+), 2 deletions(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(MOVI_0, DEVICEID, 32, 32) FIELD(MOVI_1, EVENTID, 0, 32) FIELD(MOVI_2, ICID, 0, 16) +/* INV command fields */ +FIELD(INV_0, DEVICEID, 32, 32) +FIELD(INV_1, EVENTID, 0, 32) + /* VMAPI, VMAPTI command fields */ FIELD(VMAPTI_0, DEVICEID, 32, 32) FIELD(VMAPTI_1, EVENTID, 0, 32) @@ -XXX,XX +XXX,XX @@ void gicv3_redist_update_lpi(GICv3CPUState *cs); * an incoming migration has loaded new state. */ void gicv3_redist_update_lpi_only(GICv3CPUState *cs); +/** + * gicv3_redist_inv_lpi: + * @cs: GICv3CPUState + * @irq: LPI to invalidate cached information for + * + * Forget or update any cached information associated with this LPI. + */ +void gicv3_redist_inv_lpi(GICv3CPUState *cs, int irq); /** * gicv3_redist_mov_lpi: * @src: source redistributor diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_vmovp(GICv3ITSState *s, const uint64_t *cmdpkt) return cbdata.result; } +static ItsCmdResult process_inv(GICv3ITSState *s, const uint64_t *cmdpkt) +{ + uint32_t devid, eventid; + ITEntry ite; + DTEntry dte; + CTEntry cte; + ItsCmdResult cmdres; + + devid = FIELD_EX64(cmdpkt[0], INV_0, DEVICEID); + eventid = FIELD_EX64(cmdpkt[1], INV_1, EVENTID); + + trace_gicv3_its_cmd_inv(devid, eventid); + + cmdres = lookup_ite(s, __func__, devid, eventid, &ite, &dte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; + } + + switch (ite.inttype) { + case ITE_INTTYPE_PHYSICAL: + cmdres = lookup_cte(s, __func__, ite.icid, &cte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; + } + gicv3_redist_inv_lpi(&s->gicv3->cpu[cte.rdbase], ite.intid); + break; + case ITE_INTTYPE_VIRTUAL: + if (!its_feature_virtual(s)) { + /* Can't happen unless guest is illegally writing to table memory */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid type %d in ITE (table corrupted?)\n", + __func__, ite.inttype); + return CMD_CONTINUE; + } + /* We will implement the vLPI invalidation in a later commit */ + g_assert_not_reached(); + break; + default: + g_assert_not_reached(); + } + + return CMD_CONTINUE_OK; +} + /* * Current implementation blocks until all * commands are processed @@ -XXX,XX +XXX,XX @@ static void process_cmdq(GICv3ITSState *s) result = process_its_cmd(s, cmdpkt, DISCARD); break; case GITS_CMD_INV: + result = process_inv(s, cmdpkt); + break; case GITS_CMD_INVALL: /* * Current implementation doesn't cache any ITS tables, * but the calculated lpi priority information. We only * need to trigger lpi priority re-calculation to be in * sync with LPI config table or pending table changes. + * INVALL operates on a collection specified by ICID so + * it only affects physical LPIs. */ - trace_gicv3_its_cmd_inv(); + trace_gicv3_its_cmd_invall(); for (i = 0; i < s->gicv3->num_cpu; i++) { gicv3_redist_update_lpi(&s->gicv3->cpu[i]); } diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ void gicv3_redist_process_lpi(GICv3CPUState *cs, int irq, int level) gicv3_redist_lpi_pending(cs, irq, level); } +void gicv3_redist_inv_lpi(GICv3CPUState *cs, int irq) +{ + /* + * The only cached information for LPIs we have is the HPPLPI. + * We could be cleverer about identifying when we don't need + * to do a full rescan of the pending table, but until we find + * this is a performance issue, just always recalculate. + */ + gicv3_redist_update_lpi(cs); +} + void gicv3_redist_mov_lpi(GICv3CPUState *src, GICv3CPUState *dest, int irq) { /* diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_its_cmd_mapd(uint32_t devid, uint32_t size, uint64_t ittaddr, int valid) " gicv3_its_cmd_mapc(uint32_t icid, uint64_t rdbase, int valid) "GICv3 ITS: command MAPC ICID 0x%x RDbase 0x%" PRIx64 " V %d" gicv3_its_cmd_mapi(uint32_t devid, uint32_t eventid, uint32_t icid) "GICv3 ITS: command MAPI DeviceID 0x%x EventID 0x%x ICID 0x%x" gicv3_its_cmd_mapti(uint32_t devid, uint32_t eventid, uint32_t icid, uint32_t intid) "GICv3 ITS: command MAPTI DeviceID 0x%x EventID 0x%x ICID 0x%x pINTID 0x%x" -gicv3_its_cmd_inv(void) "GICv3 ITS: command INV or INVALL" +gicv3_its_cmd_inv(uint32_t devid, uint32_t eventid) "GICv3 ITS: command INV DeviceID 0x%x EventID 0x%x" +gicv3_its_cmd_invall(void) "GICv3 ITS: command INVALL" gicv3_its_cmd_movall(uint64_t rd1, uint64_t rd2) "GICv3 ITS: command MOVALL RDbase1 0x%" PRIx64 " RDbase2 0x%" PRIx64 gicv3_its_cmd_movi(uint32_t devid, uint32_t eventid, uint32_t icid) "GICv3 ITS: command MOVI DeviceID 0x%x EventID 0x%x ICID 0x%x" gicv3_its_cmd_vmapi(uint32_t devid, uint32_t eventid, uint32_t vpeid, uint32_t doorbell) "GICv3 ITS: command VMAPI DeviceID 0x%x EventID 0x%x vPEID 0x%x Dbell_pINTID 0x%x" -- 2.25.1 Implement the ITS side of the handling of the INV command for virtual interrupts; as usual this calls into a redistributor function which we leave as a stub to fill in later. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-20-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 9 +++++++++ hw/intc/arm_gicv3_its.c | 16 ++++++++++++++-- hw/intc/arm_gicv3_redist.c | 8 ++++++++ 3 files changed, 31 insertions(+), 2 deletions(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ void gicv3_redist_update_lpi_only(GICv3CPUState *cs); * Forget or update any cached information associated with this LPI. */ void gicv3_redist_inv_lpi(GICv3CPUState *cs, int irq); +/** + * gicv3_redist_inv_vlpi: + * @cs: GICv3CPUState + * @irq: vLPI to invalidate cached information for + * @vptaddr: (guest) address of vLPI table + * + * Forget or update any cached information associated with this vLPI. + */ +void gicv3_redist_inv_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr); /** * gicv3_redist_mov_lpi: * @src: source redistributor diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_inv(GICv3ITSState *s, const uint64_t *cmdpkt) ITEntry ite; DTEntry dte; CTEntry cte; + VTEntry vte; ItsCmdResult cmdres; devid = FIELD_EX64(cmdpkt[0], INV_0, DEVICEID); @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_inv(GICv3ITSState *s, const uint64_t *cmdpkt) __func__, ite.inttype); return CMD_CONTINUE; } - /* We will implement the vLPI invalidation in a later commit */ - g_assert_not_reached(); + + cmdres = lookup_vte(s, __func__, ite.vpeid, &vte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; + } + if (!intid_in_lpi_range(ite.intid) || + ite.intid >= (1ULL << (vte.vptsize + 1))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: intid 0x%x out of range\n", + __func__, ite.intid); + return CMD_CONTINUE; + } + gicv3_redist_inv_vlpi(&s->gicv3->cpu[vte.rdbase], ite.intid, + vte.vptaddr << 16); break; default: g_assert_not_reached(); diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ void gicv3_redist_process_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr, */ } +void gicv3_redist_inv_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr) +{ + /* + * The redistributor handling for invalidating cached information + * about a VLPI will be added in a subsequent commit. + */ +} + void gicv3_redist_set_irq(GICv3CPUState *cs, int irq, int level) { /* Update redistributor state for a change in an external PPI input line */ -- 2.25.1 Implement the GICv4 VMOVI command, which moves the pending state of a virtual interrupt from one redistributor to another. As with MOVI, we handle the "parse and validate command arguments and table lookups" part in the ITS source file, and pass the final results to a function in the redistributor which will do the actual operation. As with the "make a VLPI pending" change, for the moment we leave that redistributor function as a stub, to be implemented in a later commit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-21-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 23 +++++++++++ hw/intc/arm_gicv3_its.c | 82 ++++++++++++++++++++++++++++++++++++++ hw/intc/arm_gicv3_redist.c | 10 +++++ hw/intc/trace-events | 1 + 4 files changed, 116 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(GITS_TYPER, CIL, 36, 1) #define GITS_CMD_INVALL 0x0D #define GITS_CMD_MOVALL 0x0E #define GITS_CMD_DISCARD 0x0F +#define GITS_CMD_VMOVI 0x21 #define GITS_CMD_VMOVP 0x22 #define GITS_CMD_VSYNC 0x25 #define GITS_CMD_VMAPP 0x29 @@ -XXX,XX +XXX,XX @@ FIELD(VMOVP_2, RDBASE, 16, 36) FIELD(VMOVP_2, DB, 63, 1) /* GICv4.1 only */ FIELD(VMOVP_3, DEFAULT_DOORBELL, 0, 32) /* GICv4.1 only */ +/* VMOVI command fields */ +FIELD(VMOVI_0, DEVICEID, 32, 32) +FIELD(VMOVI_1, EVENTID, 0, 32) +FIELD(VMOVI_1, VPEID, 32, 16) +FIELD(VMOVI_2, D, 0, 1) +FIELD(VMOVI_2, DOORBELL, 32, 32) + /* * 12 bytes Interrupt translation Table Entry size * as per Table 5.3 in GICv3 spec @@ -XXX,XX +XXX,XX @@ void gicv3_redist_mov_lpi(GICv3CPUState *src, GICv3CPUState *dest, int irq); * by the ITS MOVALL command. */ void gicv3_redist_movall_lpis(GICv3CPUState *src, GICv3CPUState *dest); +/** + * gicv3_redist_mov_vlpi: + * @src: source redistributor + * @src_vptaddr: (guest) address of source VLPI table + * @dest: destination redistributor + * @dest_vptaddr: (guest) address of destination VLPI table + * @irq: VLPI to update + * @doorbell: doorbell for destination (1023 for "no doorbell") + * + * Move the pending state of the specified VLPI from @src to @dest, + * as required by the ITS VMOVI command. + */ +void gicv3_redist_mov_vlpi(GICv3CPUState *src, uint64_t src_vptaddr, + GICv3CPUState *dest, uint64_t dest_vptaddr, + int irq, int doorbell); void gicv3_redist_send_sgi(GICv3CPUState *cs, int grp, int irq, bool ns); void gicv3_init_cpuif(GICv3State *s); diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_vmovp(GICv3ITSState *s, const uint64_t *cmdpkt) return cbdata.result; } +static ItsCmdResult process_vmovi(GICv3ITSState *s, const uint64_t *cmdpkt) +{ + uint32_t devid, eventid, vpeid, doorbell; + bool doorbell_valid; + DTEntry dte; + ITEntry ite; + VTEntry old_vte, new_vte; + ItsCmdResult cmdres; + + if (!its_feature_virtual(s)) { + return CMD_CONTINUE; + } + + devid = FIELD_EX64(cmdpkt[0], VMOVI_0, DEVICEID); + eventid = FIELD_EX64(cmdpkt[1], VMOVI_1, EVENTID); + vpeid = FIELD_EX64(cmdpkt[1], VMOVI_1, VPEID); + doorbell_valid = FIELD_EX64(cmdpkt[2], VMOVI_2, D); + doorbell = FIELD_EX64(cmdpkt[2], VMOVI_2, DOORBELL); + + trace_gicv3_its_cmd_vmovi(devid, eventid, vpeid, doorbell_valid, doorbell); + + if (doorbell_valid && !valid_doorbell(doorbell)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid doorbell 0x%x\n", __func__, doorbell); + return CMD_CONTINUE; + } + + cmdres = lookup_ite(s, __func__, devid, eventid, &ite, &dte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; + } + + if (ite.inttype != ITE_INTTYPE_VIRTUAL) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: ITE is not for virtual interrupt\n", + __func__); + return CMD_CONTINUE; + } + + cmdres = lookup_vte(s, __func__, ite.vpeid, &old_vte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; + } + cmdres = lookup_vte(s, __func__, vpeid, &new_vte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; + } + + if (!intid_in_lpi_range(ite.intid) || + ite.intid >= (1ULL << (old_vte.vptsize + 1)) || + ite.intid >= (1ULL << (new_vte.vptsize + 1))) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: ITE intid 0x%x out of range\n", + __func__, ite.intid); + return CMD_CONTINUE; + } + + ite.vpeid = vpeid; + if (doorbell_valid) { + ite.doorbell = doorbell; + } + + /* + * Move the LPI from the old redistributor to the new one. We don't + * need to do anything if the guest somehow specified the + * same pending table for source and destination. + */ + if (old_vte.vptaddr != new_vte.vptaddr) { + gicv3_redist_mov_vlpi(&s->gicv3->cpu[old_vte.rdbase], + old_vte.vptaddr << 16, + &s->gicv3->cpu[new_vte.rdbase], + new_vte.vptaddr << 16, + ite.intid, + ite.doorbell); + } + + /* Update the ITE to the new VPEID and possibly doorbell values */ + return update_ite(s, eventid, &dte, &ite) ? CMD_CONTINUE_OK : CMD_STALL; +} + static ItsCmdResult process_inv(GICv3ITSState *s, const uint64_t *cmdpkt) { uint32_t devid, eventid; @@ -XXX,XX +XXX,XX @@ static void process_cmdq(GICv3ITSState *s) case GITS_CMD_VMOVP: result = process_vmovp(s, cmdpkt); break; + case GITS_CMD_VMOVI: + result = process_vmovi(s, cmdpkt); + break; default: trace_gicv3_its_cmd_unknown(cmd); break; diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ void gicv3_redist_process_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr, */ } +void gicv3_redist_mov_vlpi(GICv3CPUState *src, uint64_t src_vptaddr, + GICv3CPUState *dest, uint64_t dest_vptaddr, + int irq, int doorbell) +{ + /* + * The redistributor handling for moving a VLPI will be added + * in a subsequent commit. + */ +} + void gicv3_redist_inv_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr) { /* diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_its_cmd_vmapti(uint32_t devid, uint32_t eventid, uint32_t vpeid, uint32_t gicv3_its_cmd_vmapp(uint32_t vpeid, uint64_t rdbase, int valid, uint64_t vptaddr, uint32_t vptsize) "GICv3 ITS: command VMAPP vPEID 0x%x RDbase 0x%" PRIx64 " V %d VPT_addr 0x%" PRIx64 " VPT_size 0x%x" gicv3_its_cmd_vmovp(uint32_t vpeid, uint64_t rdbase) "GICv3 ITS: command VMOVP vPEID 0x%x RDbase 0x%" PRIx64 gicv3_its_cmd_vsync(void) "GICv3 ITS: command VSYNC" +gicv3_its_cmd_vmovi(uint32_t devid, uint32_t eventid, uint32_t vpeid, int dbvalid, uint32_t doorbell) "GICv3 ITS: command VMOVI DeviceID 0x%x EventID 0x%x vPEID 0x%x D %d Dbell_pINTID 0x%x" gicv3_its_cmd_unknown(unsigned cmd) "GICv3 ITS: unknown command 0x%x" gicv3_its_cte_read(uint32_t icid, int valid, uint32_t rdbase) "GICv3 ITS: Collection Table read for ICID 0x%x: valid %d RDBase 0x%x" gicv3_its_cte_write(uint32_t icid, int valid, uint32_t rdbase) "GICv3 ITS: Collection Table write for ICID 0x%x: valid %d RDBase 0x%x" -- 2.25.1 The VINVALL command should cause any cached information in the ITS or redistributor for the specified vCPU to be dropped or otherwise made consistent with the in-memory LPI configuration tables. Here we implement the command and table parsing, leaving the redistributor part as a stub for the moment, as usual. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-22-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 13 +++++++++++++ hw/intc/arm_gicv3_its.c | 26 ++++++++++++++++++++++++++ hw/intc/arm_gicv3_redist.c | 5 +++++ hw/intc/trace-events | 1 + 4 files changed, 45 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(GITS_TYPER, CIL, 36, 1) #define GITS_CMD_VMAPP 0x29 #define GITS_CMD_VMAPTI 0x2A #define GITS_CMD_VMAPI 0x2B +#define GITS_CMD_VINVALL 0x2D /* MAPC command fields */ #define ICID_LENGTH 16 @@ -XXX,XX +XXX,XX @@ FIELD(VMOVI_1, VPEID, 32, 16) FIELD(VMOVI_2, D, 0, 1) FIELD(VMOVI_2, DOORBELL, 32, 32) +/* VINVALL command fields */ +FIELD(VINVALL_1, VPEID, 32, 16) + /* * 12 bytes Interrupt translation Table Entry size * as per Table 5.3 in GICv3 spec @@ -XXX,XX +XXX,XX @@ void gicv3_redist_movall_lpis(GICv3CPUState *src, GICv3CPUState *dest); void gicv3_redist_mov_vlpi(GICv3CPUState *src, uint64_t src_vptaddr, GICv3CPUState *dest, uint64_t dest_vptaddr, int irq, int doorbell); +/** + * gicv3_redist_vinvall: + * @cs: GICv3CPUState + * @vptaddr: address of VLPI pending table + * + * On redistributor @cs, invalidate all cached information associated + * with the vCPU defined by @vptaddr. + */ +void gicv3_redist_vinvall(GICv3CPUState *cs, uint64_t vptaddr); void gicv3_redist_send_sgi(GICv3CPUState *cs, int grp, int irq, bool ns); void gicv3_init_cpuif(GICv3State *s); diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_vmovi(GICv3ITSState *s, const uint64_t *cmdpkt) return update_ite(s, eventid, &dte, &ite) ? CMD_CONTINUE_OK : CMD_STALL; } +static ItsCmdResult process_vinvall(GICv3ITSState *s, const uint64_t *cmdpkt) +{ + VTEntry vte; + uint32_t vpeid; + ItsCmdResult cmdres; + + if (!its_feature_virtual(s)) { + return CMD_CONTINUE; + } + + vpeid = FIELD_EX64(cmdpkt[1], VINVALL_1, VPEID); + + trace_gicv3_its_cmd_vinvall(vpeid); + + cmdres = lookup_vte(s, __func__, vpeid, &vte); + if (cmdres != CMD_CONTINUE_OK) { + return cmdres; + } + + gicv3_redist_vinvall(&s->gicv3->cpu[vte.rdbase], vte.vptaddr << 16); + return CMD_CONTINUE_OK; +} + static ItsCmdResult process_inv(GICv3ITSState *s, const uint64_t *cmdpkt) { uint32_t devid, eventid; @@ -XXX,XX +XXX,XX @@ static void process_cmdq(GICv3ITSState *s) case GITS_CMD_VMOVI: result = process_vmovi(s, cmdpkt); break; + case GITS_CMD_VINVALL: + result = process_vinvall(s, cmdpkt); + break; default: trace_gicv3_its_cmd_unknown(cmd); break; diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ void gicv3_redist_mov_vlpi(GICv3CPUState *src, uint64_t src_vptaddr, */ } +void gicv3_redist_vinvall(GICv3CPUState *cs, uint64_t vptaddr) +{ + /* The redistributor handling will be added in a subsequent commit */ +} + void gicv3_redist_inv_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr) { /* diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_its_cmd_vmapp(uint32_t vpeid, uint64_t rdbase, int valid, uint64_t vptaddr gicv3_its_cmd_vmovp(uint32_t vpeid, uint64_t rdbase) "GICv3 ITS: command VMOVP vPEID 0x%x RDbase 0x%" PRIx64 gicv3_its_cmd_vsync(void) "GICv3 ITS: command VSYNC" gicv3_its_cmd_vmovi(uint32_t devid, uint32_t eventid, uint32_t vpeid, int dbvalid, uint32_t doorbell) "GICv3 ITS: command VMOVI DeviceID 0x%x EventID 0x%x vPEID 0x%x D %d Dbell_pINTID 0x%x" +gicv3_its_cmd_vinvall(uint32_t vpeid) "GICv3 ITS: command VINVALL vPEID 0x%x" gicv3_its_cmd_unknown(unsigned cmd) "GICv3 ITS: unknown command 0x%x" gicv3_its_cte_read(uint32_t icid, int valid, uint32_t rdbase) "GICv3 ITS: Collection Table read for ICID 0x%x: valid %d RDBase 0x%x" gicv3_its_cte_write(uint32_t icid, int valid, uint32_t rdbase) "GICv3 ITS: Collection Table write for ICID 0x%x: valid %d RDBase 0x%x" -- 2.25.1 The GICv4 extends the redistributor register map -- where GICv3 had two 64KB frames per CPU, GICv4 has four frames. Add support for the extra frame by using a new gicv3_redist_size() function in the places in the GIC implementation which currently use a fixed constant size for the redistributor register block. (Until we implement the extra registers they will RAZ/WI.) Any board that wants to use a GICv4 will need to also adjust to handle the different sized redistributor register block; that will be done separately. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-23-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 21 +++++++++++++++++++++ include/hw/intc/arm_gicv3_common.h | 5 +++++ hw/intc/arm_gicv3_common.c | 2 +- hw/intc/arm_gicv3_redist.c | 8 ++++---- 4 files changed, 31 insertions(+), 5 deletions(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(VTE, RDBASE, 42, RDBASE_PROCNUM_LENGTH) /* Functions internal to the emulated GICv3 */ +/** + * gicv3_redist_size: + * @s: GICv3State + * + * Return the size of the redistributor register frame in bytes + * (which depends on what GIC version this is) + */ +static inline int gicv3_redist_size(GICv3State *s) +{ + /* + * Redistributor size is controlled by the redistributor GICR_TYPER.VLPIS. + * It's the same for every redistributor in the GIC, so arbitrarily + * use the register field in the first one. + */ + if (s->cpu[0].gicr_typer & GICR_TYPER_VLPIS) { + return GICV4_REDIST_SIZE; + } else { + return GICV3_REDIST_SIZE; + } +} + /** * gicv3_intid_is_special: * @intid: interrupt ID diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ #define GICV3_LPI_INTID_START 8192 +/* + * The redistributor in GICv3 has two 64KB frames per CPU; in + * GICv4 it has four 64KB frames per CPU. + */ #define GICV3_REDIST_SIZE 0x20000 +#define GICV4_REDIST_SIZE 0x40000 /* Number of SGI target-list bits */ #define GICV3_TARGETLIST_BITS 16 diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ void gicv3_init_irqs_and_mmio(GICv3State *s, qemu_irq_handler handler, memory_region_init_io(&region->iomem, OBJECT(s), ops ? &ops[1] : NULL, region, name, - s->redist_region_count[i] * GICV3_REDIST_SIZE); + s->redist_region_count[i] * gicv3_redist_size(s)); sysbus_init_mmio(sbd, &region->iomem); g_free(name); } diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ MemTxResult gicv3_redist_read(void *opaque, hwaddr offset, uint64_t *data, * in the memory map); if so then the GIC has multiple MemoryRegions * for the redistributors. */ - cpuidx = region->cpuidx + offset / GICV3_REDIST_SIZE; - offset %= GICV3_REDIST_SIZE; + cpuidx = region->cpuidx + offset / gicv3_redist_size(s); + offset %= gicv3_redist_size(s); cs = &s->cpu[cpuidx]; @@ -XXX,XX +XXX,XX @@ MemTxResult gicv3_redist_write(void *opaque, hwaddr offset, uint64_t data, * in the memory map); if so then the GIC has multiple MemoryRegions * for the redistributors. */ - cpuidx = region->cpuidx + offset / GICV3_REDIST_SIZE; - offset %= GICV3_REDIST_SIZE; + cpuidx = region->cpuidx + offset / gicv3_redist_size(s); + offset %= gicv3_redist_size(s); cs = &s->cpu[cpuidx]; -- 2.25.1 Implement the new GICv4 redistributor registers: GICR_VPROPBASER and GICR_VPENDBASER; for the moment we implement these as simple reads-as-written stubs, together with the necessary migration and reset handling. We don't put ID-register checks on the handling of these registers, because they are all in the only-in-v4 extra register frames, so they're not accessible in a GICv3. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-24-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 21 +++++++++++ include/hw/intc/arm_gicv3_common.h | 3 ++ hw/intc/arm_gicv3_common.c | 22 ++++++++++++ hw/intc/arm_gicv3_redist.c | 56 ++++++++++++++++++++++++++++++ 4 files changed, 102 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ * Redistributor frame offsets from RD_base */ #define GICR_SGI_OFFSET 0x10000 +#define GICR_VLPI_OFFSET 0x20000 /* * Redistributor registers, offsets from RD_base @@ -XXX,XX +XXX,XX @@ #define GICR_IGRPMODR0 (GICR_SGI_OFFSET + 0x0D00) #define GICR_NSACR (GICR_SGI_OFFSET + 0x0E00) +/* VLPI redistributor registers, offsets from VLPI_base */ +#define GICR_VPROPBASER (GICR_VLPI_OFFSET + 0x70) +#define GICR_VPENDBASER (GICR_VLPI_OFFSET + 0x78) + #define GICR_CTLR_ENABLE_LPIS (1U << 0) #define GICR_CTLR_CES (1U << 1) #define GICR_CTLR_RWP (1U << 3) @@ -XXX,XX +XXX,XX @@ FIELD(GICR_PENDBASER, PTZ, 62, 1) #define GICR_PROPBASER_IDBITS_THRESHOLD 0xd +/* These are the GICv4 VPROPBASER and VPENDBASER layouts; v4.1 is different */ +FIELD(GICR_VPROPBASER, IDBITS, 0, 5) +FIELD(GICR_VPROPBASER, INNERCACHE, 7, 3) +FIELD(GICR_VPROPBASER, SHAREABILITY, 10, 2) +FIELD(GICR_VPROPBASER, PHYADDR, 12, 40) +FIELD(GICR_VPROPBASER, OUTERCACHE, 56, 3) + +FIELD(GICR_VPENDBASER, INNERCACHE, 7, 3) +FIELD(GICR_VPENDBASER, SHAREABILITY, 10, 2) +FIELD(GICR_VPENDBASER, PHYADDR, 16, 36) +FIELD(GICR_VPENDBASER, OUTERCACHE, 56, 3) +FIELD(GICR_VPENDBASER, DIRTY, 60, 1) +FIELD(GICR_VPENDBASER, PENDINGLAST, 61, 1) +FIELD(GICR_VPENDBASER, IDAI, 62, 1) +FIELD(GICR_VPENDBASER, VALID, 63, 1) + #define ICC_CTLR_EL1_CBPR (1U << 0) #define ICC_CTLR_EL1_EOIMODE (1U << 1) #define ICC_CTLR_EL1_PMHE (1U << 6) diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3CPUState { uint32_t gicr_igrpmodr0; uint32_t gicr_nsacr; uint8_t gicr_ipriorityr[GIC_INTERNAL]; + /* VLPI_base page registers */ + uint64_t gicr_vpropbaser; + uint64_t gicr_vpendbaser; /* CPU interface */ uint64_t icc_sre_el1; diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ const VMStateDescription vmstate_gicv3_cpu_sre_el1 = { } }; +static bool gicv4_needed(void *opaque) +{ + GICv3CPUState *cs = opaque; + + return cs->gic->revision > 3; +} + +const VMStateDescription vmstate_gicv3_gicv4 = { + .name = "arm_gicv3_cpu/gicv4", + .version_id = 1, + .minimum_version_id = 1, + .needed = gicv4_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT64(gicr_vpropbaser, GICv3CPUState), + VMSTATE_UINT64(gicr_vpendbaser, GICv3CPUState), + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_gicv3_cpu = { .name = "arm_gicv3_cpu", .version_id = 1, @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_gicv3_cpu = { .subsections = (const VMStateDescription * []) { &vmstate_gicv3_cpu_virt, &vmstate_gicv3_cpu_sre_el1, + &vmstate_gicv3_gicv4, NULL } }; @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_reset(DeviceState *dev) cs->gicr_waker = GICR_WAKER_ProcessorSleep | GICR_WAKER_ChildrenAsleep; cs->gicr_propbaser = 0; cs->gicr_pendbaser = 0; + cs->gicr_vpropbaser = 0; + cs->gicr_vpendbaser = 0; /* If we're resetting a TZ-aware GIC as if secure firmware * had set it up ready to start a kernel in non-secure, we * need to set interrupts to group 1 so the kernel can use them. diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_readl(GICv3CPUState *cs, hwaddr offset, case GICR_IDREGS ... GICR_IDREGS + 0x2f: *data = gicv3_idreg(offset - GICR_IDREGS, GICV3_PIDR0_REDIST); return MEMTX_OK; + /* + * VLPI frame registers. We don't need a version check for + * VPROPBASER and VPENDBASER because gicv3_redist_size() will + * prevent pre-v4 GIC from passing us offsets this high. + */ + case GICR_VPROPBASER: + *data = extract64(cs->gicr_vpropbaser, 0, 32); + return MEMTX_OK; + case GICR_VPROPBASER + 4: + *data = extract64(cs->gicr_vpropbaser, 32, 32); + return MEMTX_OK; + case GICR_VPENDBASER: + *data = extract64(cs->gicr_vpendbaser, 0, 32); + return MEMTX_OK; + case GICR_VPENDBASER + 4: + *data = extract64(cs->gicr_vpendbaser, 32, 32); + return MEMTX_OK; default: return MEMTX_ERROR; } @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_writel(GICv3CPUState *cs, hwaddr offset, "%s: invalid guest write to RO register at offset " TARGET_FMT_plx "\n", __func__, offset); return MEMTX_OK; + /* + * VLPI frame registers. We don't need a version check for + * VPROPBASER and VPENDBASER because gicv3_redist_size() will + * prevent pre-v4 GIC from passing us offsets this high. + */ + case GICR_VPROPBASER: + cs->gicr_vpropbaser = deposit64(cs->gicr_vpropbaser, 0, 32, value); + return MEMTX_OK; + case GICR_VPROPBASER + 4: + cs->gicr_vpropbaser = deposit64(cs->gicr_vpropbaser, 32, 32, value); + return MEMTX_OK; + case GICR_VPENDBASER: + cs->gicr_vpendbaser = deposit64(cs->gicr_vpendbaser, 0, 32, value); + return MEMTX_OK; + case GICR_VPENDBASER + 4: + cs->gicr_vpendbaser = deposit64(cs->gicr_vpendbaser, 32, 32, value); + return MEMTX_OK; default: return MEMTX_ERROR; } @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_readll(GICv3CPUState *cs, hwaddr offset, case GICR_PENDBASER: *data = cs->gicr_pendbaser; return MEMTX_OK; + /* + * VLPI frame registers. We don't need a version check for + * VPROPBASER and VPENDBASER because gicv3_redist_size() will + * prevent pre-v4 GIC from passing us offsets this high. + */ + case GICR_VPROPBASER: + *data = cs->gicr_vpropbaser; + return MEMTX_OK; + case GICR_VPENDBASER: + *data = cs->gicr_vpendbaser; + return MEMTX_OK; default: return MEMTX_ERROR; } @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_writell(GICv3CPUState *cs, hwaddr offset, "%s: invalid guest write to RO register at offset " TARGET_FMT_plx "\n", __func__, offset); return MEMTX_OK; + /* + * VLPI frame registers. We don't need a version check for + * VPROPBASER and VPENDBASER because gicv3_redist_size() will + * prevent pre-v4 GIC from passing us offsets this high. + */ + case GICR_VPROPBASER: + cs->gicr_vpropbaser = value; + return MEMTX_OK; + case GICR_VPENDBASER: + cs->gicr_vpendbaser = value; + return MEMTX_OK; default: return MEMTX_ERROR; } -- 2.25.1 The function gicv3_cpuif_virt_update() currently sets all of vIRQ, vFIQ and the maintenance interrupt. This implies that it has to be used quite carefully -- as the comment notes, setting the maintenance interrupt will typically cause the GIC code to be re-entered recursively. For handling vLPIs, we need the redistributor to be able to tell the cpuif to update the vIRQ and vFIQ lines when the highest priority pending vLPI changes. Since that change can't cause the maintenance interrupt state to change, we can pull the "update vIRQ/vFIQ" parts of gicv3_cpuif_virt_update() out into a separate function, which the redistributor can then call without having to worry about the reentrancy issue. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-25-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 11 +++++++ hw/intc/arm_gicv3_cpuif.c | 64 ++++++++++++++++++++++++--------------- hw/intc/trace-events | 3 +- 3 files changed, 53 insertions(+), 25 deletions(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ void gicv3_init_cpuif(GICv3State *s); */ void gicv3_cpuif_update(GICv3CPUState *cs); +/* + * gicv3_cpuif_virt_irq_fiq_update: + * @cs: GICv3CPUState for the CPU to update + * + * Recalculate whether to assert the virtual IRQ or FIQ lines after + * a change to the current highest priority pending virtual interrupt. + * Note that this does not recalculate and change the maintenance + * interrupt status (for that, see gicv3_cpuif_virt_update()). + */ +void gicv3_cpuif_virt_irq_fiq_update(GICv3CPUState *cs); + static inline uint32_t gicv3_iidr(void) { /* Return the Implementer Identification Register value diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static uint32_t maintenance_interrupt_state(GICv3CPUState *cs) return value; } -static void gicv3_cpuif_virt_update(GICv3CPUState *cs) +void gicv3_cpuif_virt_irq_fiq_update(GICv3CPUState *cs) { - /* Tell the CPU about any pending virtual interrupts or - * maintenance interrupts, following a change to the state - * of the CPU interface relevant to virtual interrupts. - * - * CAUTION: this function will call qemu_set_irq() on the - * CPU maintenance IRQ line, which is typically wired up - * to the GIC as a per-CPU interrupt. This means that it - * will recursively call back into the GIC code via - * gicv3_redist_set_irq() and thus into the CPU interface code's - * gicv3_cpuif_update(). It is therefore important that this - * function is only called as the final action of a CPU interface - * register write implementation, after all the GIC state - * fields have been updated. gicv3_cpuif_update() also must - * not cause this function to be called, but that happens - * naturally as a result of there being no architectural - * linkage between the physical and virtual GIC logic. + /* + * Tell the CPU about any pending virtual interrupts. + * This should only be called for changes that affect the + * vIRQ and vFIQ status and do not change the maintenance + * interrupt status. This means that unlike gicv3_cpuif_virt_update() + * this function won't recursively call back into the GIC code. + * The main use of this is when the redistributor has changed the + * highest priority pending virtual LPI. */ int idx; int irqlevel = 0; int fiqlevel = 0; - int maintlevel = 0; - ARMCPU *cpu = ARM_CPU(cs->cpu); idx = hppvi_index(cs); trace_gicv3_cpuif_virt_update(gicv3_redist_affid(cs), idx); @@ -XXX,XX +XXX,XX @@ static void gicv3_cpuif_virt_update(GICv3CPUState *cs) } } + trace_gicv3_cpuif_virt_set_irqs(gicv3_redist_affid(cs), fiqlevel, irqlevel); + qemu_set_irq(cs->parent_vfiq, fiqlevel); + qemu_set_irq(cs->parent_virq, irqlevel); +} + +static void gicv3_cpuif_virt_update(GICv3CPUState *cs) +{ + /* + * Tell the CPU about any pending virtual interrupts or + * maintenance interrupts, following a change to the state + * of the CPU interface relevant to virtual interrupts. + * + * CAUTION: this function will call qemu_set_irq() on the + * CPU maintenance IRQ line, which is typically wired up + * to the GIC as a per-CPU interrupt. This means that it + * will recursively call back into the GIC code via + * gicv3_redist_set_irq() and thus into the CPU interface code's + * gicv3_cpuif_update(). It is therefore important that this + * function is only called as the final action of a CPU interface + * register write implementation, after all the GIC state + * fields have been updated. gicv3_cpuif_update() also must + * not cause this function to be called, but that happens + * naturally as a result of there being no architectural + * linkage between the physical and virtual GIC logic. + */ + ARMCPU *cpu = ARM_CPU(cs->cpu); + int maintlevel = 0; + + gicv3_cpuif_virt_irq_fiq_update(cs); + if ((cs->ich_hcr_el2 & ICH_HCR_EL2_EN) && maintenance_interrupt_state(cs) != 0) { maintlevel = 1; } - trace_gicv3_cpuif_virt_set_irqs(gicv3_redist_affid(cs), fiqlevel, - irqlevel, maintlevel); - - qemu_set_irq(cs->parent_vfiq, fiqlevel); - qemu_set_irq(cs->parent_virq, irqlevel); + trace_gicv3_cpuif_virt_set_maint_irq(gicv3_redist_affid(cs), maintlevel); qemu_set_irq(cpu->gicv3_maintenance_interrupt, maintlevel); } diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_icv_dir_write(uint32_t cpu, uint64_t val) "GICv3 ICV_DIR write cpu 0x%x va gicv3_icv_iar_read(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_IAR%d read cpu 0x%x value 0x%" PRIx64 gicv3_icv_eoir_write(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_EOIR%d write cpu 0x%x value 0x%" PRIx64 gicv3_cpuif_virt_update(uint32_t cpuid, int idx) "GICv3 CPU i/f 0x%x virt HPPI update LR index %d" -gicv3_cpuif_virt_set_irqs(uint32_t cpuid, int fiqlevel, int irqlevel, int maintlevel) "GICv3 CPU i/f 0x%x virt HPPI update: setting FIQ %d IRQ %d maintenance-irq %d" +gicv3_cpuif_virt_set_irqs(uint32_t cpuid, int fiqlevel, int irqlevel) "GICv3 CPU i/f 0x%x virt HPPI update: setting FIQ %d IRQ %d" +gicv3_cpuif_virt_set_maint_irq(uint32_t cpuid, int maintlevel) "GICv3 CPU i/f 0x%x virt HPPI update: setting maintenance-irq %d" # arm_gicv3_dist.c gicv3_dist_read(uint64_t offset, uint64_t data, unsigned size, bool secure) "GICv3 distributor read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u secure %d" -- 2.25.1 The CPU interface changes to support vLPIs are fairly minor: in the parts of the code that currently look at the list registers to determine the highest priority pending virtual interrupt, we must also look at the highest priority pending vLPI. To do this we change hppvi_index() to check the vLPI and return a special-case value if that is the right virtual interrupt to take. The callsites (which handle HPPIR and IAR registers and the "raise vIRQ and vFIQ lines" code) then have to handle this special-case value. This commit includes two interfaces with the as-yet-unwritten redistributor code: * the new GICv3CPUState::hppvlpi will be set by the redistributor (in the same way as the existing hpplpi does for physical LPIs) * when the CPU interface acknowledges a vLPI it needs to set it to non-pending; the new gicv3_redist_vlpi_pending() function (which matches the existing gicv3_redist_lpi_pending() used for physical LPIs) is a stub that will be filled in later Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-26-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 13 ++++ include/hw/intc/arm_gicv3_common.h | 3 + hw/intc/arm_gicv3_common.c | 1 + hw/intc/arm_gicv3_cpuif.c | 119 +++++++++++++++++++++++++++-- hw/intc/arm_gicv3_redist.c | 8 ++ hw/intc/trace-events | 2 +- 6 files changed, 140 insertions(+), 6 deletions(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ void gicv3_redist_process_lpi(GICv3CPUState *cs, int irq, int level); */ void gicv3_redist_process_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr, int doorbell, int level); +/** + * gicv3_redist_vlpi_pending: + * @cs: GICv3CPUState + * @irq: (virtual) interrupt number + * @level: level to set @irq to + * + * Set/clear the pending status of a virtual LPI in the vLPI table + * that this redistributor is currently using. (The difference between + * this and gicv3_redist_process_vlpi() is that this is called from + * the cpuif and does not need to do the not-running-on-this-vcpu checks.) + */ +void gicv3_redist_vlpi_pending(GICv3CPUState *cs, int irq, int level); + void gicv3_redist_lpi_pending(GICv3CPUState *cs, int irq, int level); /** * gicv3_redist_update_lpi: diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3CPUState { */ PendingIrq hpplpi; + /* Cached information recalculated from vLPI tables in guest memory */ + PendingIrq hppvlpi; + /* This is temporary working state, to avoid a malloc in gicv3_update() */ bool seenbetter; }; diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_reset(DeviceState *dev) cs->hppi.prio = 0xff; cs->hpplpi.prio = 0xff; + cs->hppvlpi.prio = 0xff; /* State in the CPU interface must *not* be reset here, because it * is part of the CPU's reset domain, not the GIC device's. diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ #include "hw/irq.h" #include "cpu.h" +/* + * Special case return value from hppvi_index(); must be larger than + * the architecturally maximum possible list register index (which is 15) + */ +#define HPPVI_INDEX_VLPI 16 + static GICv3CPUState *icc_cs_from_env(CPUARMState *env) { return env->gicv3state; @@ -XXX,XX +XXX,XX @@ static int ich_highest_active_virt_prio(GICv3CPUState *cs) static int hppvi_index(GICv3CPUState *cs) { - /* Return the list register index of the highest priority pending + /* + * Return the list register index of the highest priority pending * virtual interrupt, as per the HighestPriorityVirtualInterrupt * pseudocode. If no pending virtual interrupts, return -1. + * If the highest priority pending virtual interrupt is a vLPI, + * return HPPVI_INDEX_VLPI. + * (The pseudocode handles checking whether the vLPI is higher + * priority than the highest priority list register at every + * callsite of HighestPriorityVirtualInterrupt; we check it here.) */ + ARMCPU *cpu = ARM_CPU(cs->cpu); + CPUARMState *env = &cpu->env; int idx = -1; int i; /* Note that a list register entry with a priority of 0xff will @@ -XXX,XX +XXX,XX @@ static int hppvi_index(GICv3CPUState *cs) } } + /* + * "no pending vLPI" is indicated with prio = 0xff, which always + * fails the priority check here. vLPIs are only considered + * when we are in Non-Secure state. + */ + if (cs->hppvlpi.prio < prio && !arm_is_secure(env)) { + if (cs->hppvlpi.grp == GICV3_G0) { + if (cs->ich_vmcr_el2 & ICH_VMCR_EL2_VENG0) { + return HPPVI_INDEX_VLPI; + } + } else { + if (cs->ich_vmcr_el2 & ICH_VMCR_EL2_VENG1) { + return HPPVI_INDEX_VLPI; + } + } + } + return idx; } @@ -XXX,XX +XXX,XX @@ static bool icv_hppi_can_preempt(GICv3CPUState *cs, uint64_t lr) return false; } +static bool icv_hppvlpi_can_preempt(GICv3CPUState *cs) +{ + /* + * Return true if we can signal the highest priority pending vLPI. + * We can assume we're Non-secure because hppvi_index() already + * tested for that. + */ + uint32_t mask, rprio, vpmr; + + if (!(cs->ich_hcr_el2 & ICH_HCR_EL2_EN)) { + /* Virtual interface disabled */ + return false; + } + + vpmr = extract64(cs->ich_vmcr_el2, ICH_VMCR_EL2_VPMR_SHIFT, + ICH_VMCR_EL2_VPMR_LENGTH); + + if (cs->hppvlpi.prio >= vpmr) { + /* Priority mask masks this interrupt */ + return false; + } + + rprio = ich_highest_active_virt_prio(cs); + if (rprio == 0xff) { + /* No running interrupt so we can preempt */ + return true; + } + + mask = icv_gprio_mask(cs, cs->hppvlpi.grp); + + /* + * We only preempt a running interrupt if the pending interrupt's + * group priority is sufficient (the subpriorities are not considered). + */ + if ((cs->hppvlpi.prio & mask) < (rprio & mask)) { + return true; + } + + return false; +} + static uint32_t eoi_maintenance_interrupt_state(GICv3CPUState *cs, uint32_t *misr) { @@ -XXX,XX +XXX,XX @@ void gicv3_cpuif_virt_irq_fiq_update(GICv3CPUState *cs) int fiqlevel = 0; idx = hppvi_index(cs); - trace_gicv3_cpuif_virt_update(gicv3_redist_affid(cs), idx); - if (idx >= 0) { + trace_gicv3_cpuif_virt_update(gicv3_redist_affid(cs), idx, + cs->hppvlpi.irq, cs->hppvlpi.grp, + cs->hppvlpi.prio); + if (idx == HPPVI_INDEX_VLPI) { + if (icv_hppvlpi_can_preempt(cs)) { + if (cs->hppvlpi.grp == GICV3_G0) { + fiqlevel = 1; + } else { + irqlevel = 1; + } + } + } else if (idx >= 0) { uint64_t lr = cs->ich_lr_el2[idx]; if (icv_hppi_can_preempt(cs, lr)) { @@ -XXX,XX +XXX,XX @@ static uint64_t icv_hppir_read(CPUARMState *env, const ARMCPRegInfo *ri) int idx = hppvi_index(cs); uint64_t value = INTID_SPURIOUS; - if (idx >= 0) { + if (idx == HPPVI_INDEX_VLPI) { + if (cs->hppvlpi.grp == grp) { + value = cs->hppvlpi.irq; + } + } else if (idx >= 0) { uint64_t lr = cs->ich_lr_el2[idx]; int thisgrp = (lr & ICH_LR_EL2_GROUP) ? GICV3_G1NS : GICV3_G0; @@ -XXX,XX +XXX,XX @@ static void icv_activate_irq(GICv3CPUState *cs, int idx, int grp) cs->ich_apr[grp][regno] |= (1 << regbit); } +static void icv_activate_vlpi(GICv3CPUState *cs) +{ + uint32_t mask = icv_gprio_mask(cs, cs->hppvlpi.grp); + int prio = cs->hppvlpi.prio & mask; + int aprbit = prio >> (8 - cs->vprebits); + int regno = aprbit / 32; + int regbit = aprbit % 32; + + cs->ich_apr[cs->hppvlpi.grp][regno] |= (1 << regbit); + gicv3_redist_vlpi_pending(cs, cs->hppvlpi.irq, 0); +} + static uint64_t icv_iar_read(CPUARMState *env, const ARMCPRegInfo *ri) { GICv3CPUState *cs = icc_cs_from_env(env); @@ -XXX,XX +XXX,XX @@ static uint64_t icv_iar_read(CPUARMState *env, const ARMCPRegInfo *ri) int idx = hppvi_index(cs); uint64_t intid = INTID_SPURIOUS; - if (idx >= 0) { + if (idx == HPPVI_INDEX_VLPI) { + if (cs->hppvlpi.grp == grp && icv_hppvlpi_can_preempt(cs)) { + intid = cs->hppvlpi.irq; + icv_activate_vlpi(cs); + } + } else if (idx >= 0) { uint64_t lr = cs->ich_lr_el2[idx]; int thisgrp = (lr & ICH_LR_EL2_GROUP) ? GICV3_G1NS : GICV3_G0; @@ -XXX,XX +XXX,XX @@ static void gicv3_cpuif_el_change_hook(ARMCPU *cpu, void *opaque) GICv3CPUState *cs = opaque; gicv3_cpuif_update(cs); + /* + * Because vLPIs are only pending in NonSecure state, + * an EL change can change the VIRQ/VFIQ status (but + * cannot affect the maintenance interrupt state) + */ + gicv3_cpuif_virt_irq_fiq_update(cs); } void gicv3_init_cpuif(GICv3State *s) diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ void gicv3_redist_movall_lpis(GICv3CPUState *src, GICv3CPUState *dest) gicv3_redist_update_lpi(dest); } +void gicv3_redist_vlpi_pending(GICv3CPUState *cs, int irq, int level) +{ + /* + * The redistributor handling for changing the pending state + * of a vLPI will be added in a subsequent commit. + */ +} + void gicv3_redist_process_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr, int doorbell, int level) { diff --git a/hw/intc/trace-events b/hw/intc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/trace-events +++ b/hw/intc/trace-events @@ -XXX,XX +XXX,XX @@ gicv3_icv_hppir_read(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_HPPIR%d rea gicv3_icv_dir_write(uint32_t cpu, uint64_t val) "GICv3 ICV_DIR write cpu 0x%x value 0x%" PRIx64 gicv3_icv_iar_read(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_IAR%d read cpu 0x%x value 0x%" PRIx64 gicv3_icv_eoir_write(int grp, uint32_t cpu, uint64_t val) "GICv3 ICV_EOIR%d write cpu 0x%x value 0x%" PRIx64 -gicv3_cpuif_virt_update(uint32_t cpuid, int idx) "GICv3 CPU i/f 0x%x virt HPPI update LR index %d" +gicv3_cpuif_virt_update(uint32_t cpuid, int idx, int hppvlpi, int grp, int prio) "GICv3 CPU i/f 0x%x virt HPPI update LR index %d HPPVLPI %d grp %d prio %d" gicv3_cpuif_virt_set_irqs(uint32_t cpuid, int fiqlevel, int irqlevel) "GICv3 CPU i/f 0x%x virt HPPI update: setting FIQ %d IRQ %d" gicv3_cpuif_virt_set_maint_irq(uint32_t cpuid, int maintlevel) "GICv3 CPU i/f 0x%x virt HPPI update: setting maintenance-irq %d" -- 2.25.1 The maintenance interrupt state depends only on: * ICH_HCR_EL2 * ICH_LR<n>_EL2 * ICH_VMCR_EL2 fields VENG0 and VENG1 Now we have a separate function that updates only the vIRQ and vFIQ lines, use that in places that only change state that affects vIRQ and vFIQ but not the maintenance interrupt. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-27-peter.maydell@linaro.org --- hw/intc/arm_gicv3_cpuif.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static void icv_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, cs->ich_apr[grp][regno] = value & 0xFFFFFFFFU; - gicv3_cpuif_virt_update(cs); + gicv3_cpuif_virt_irq_fiq_update(cs); return; } @@ -XXX,XX +XXX,XX @@ static void icv_bpr_write(CPUARMState *env, const ARMCPRegInfo *ri, write_vbpr(cs, grp, value); - gicv3_cpuif_virt_update(cs); + gicv3_cpuif_virt_irq_fiq_update(cs); } static uint64_t icv_pmr_read(CPUARMState *env, const ARMCPRegInfo *ri) @@ -XXX,XX +XXX,XX @@ static void icv_pmr_write(CPUARMState *env, const ARMCPRegInfo *ri, cs->ich_vmcr_el2 = deposit64(cs->ich_vmcr_el2, ICH_VMCR_EL2_VPMR_SHIFT, ICH_VMCR_EL2_VPMR_LENGTH, value); - gicv3_cpuif_virt_update(cs); + gicv3_cpuif_virt_irq_fiq_update(cs); } static uint64_t icv_igrpen_read(CPUARMState *env, const ARMCPRegInfo *ri) @@ -XXX,XX +XXX,XX @@ static void icv_ctlr_write(CPUARMState *env, const ARMCPRegInfo *ri, cs->ich_vmcr_el2 = deposit64(cs->ich_vmcr_el2, ICH_VMCR_EL2_VEOIM_SHIFT, 1, value & ICC_CTLR_EL1_EOIMODE ? 1 : 0); - gicv3_cpuif_virt_update(cs); + gicv3_cpuif_virt_irq_fiq_update(cs); } static uint64_t icv_rpr_read(CPUARMState *env, const ARMCPRegInfo *ri) @@ -XXX,XX +XXX,XX @@ static void ich_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, trace_gicv3_ich_ap_write(ri->crm & 1, regno, gicv3_redist_affid(cs), value); cs->ich_apr[grp][regno] = value & 0xFFFFFFFFU; - gicv3_cpuif_virt_update(cs); + gicv3_cpuif_virt_irq_fiq_update(cs); } static uint64_t ich_hcr_read(CPUARMState *env, const ARMCPRegInfo *ri) -- 2.25.1 Currently the functions which update the highest priority pending LPI information by looking at the LPI Pending and Configuration tables are hard-coded to use the physical LPI tables addressed by GICR_PENDBASER and GICR_PROPBASER. To support virtual LPIs we will need to do essentially the same job, but looking at the current virtual LPI Pending and Configuration tables and updating cs->hppvlpi instead of cs->hpplpi. Factor out the common part of the gicv3_redist_check_lpi_priority() function into a new update_for_one_lpi() function, which updates a PendingIrq struct if the specified LPI is higher priority than what is currently recorded there. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-28-peter.maydell@linaro.org --- hw/intc/arm_gicv3_redist.c | 74 ++++++++++++++++++++++++-------------- 1 file changed, 47 insertions(+), 27 deletions(-) diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ static uint32_t gicr_read_bitmap_reg(GICv3CPUState *cs, MemTxAttrs attrs, return reg; } +/** + * update_for_one_lpi: Update pending information if this LPI is better + * + * @cs: GICv3CPUState + * @irq: interrupt to look up in the LPI Configuration table + * @ctbase: physical address of the LPI Configuration table to use + * @ds: true if priority value should not be shifted + * @hpp: points to pending information to update + * + * Look up @irq in the Configuration table specified by @ctbase + * to see if it is enabled and what its priority is. If it is an + * enabled interrupt with a higher priority than that currently + * recorded in @hpp, update @hpp. + */ +static void update_for_one_lpi(GICv3CPUState *cs, int irq, + uint64_t ctbase, bool ds, PendingIrq *hpp) +{ + uint8_t lpite; + uint8_t prio; + + address_space_read(&cs->gic->dma_as, + ctbase + ((irq - GICV3_LPI_INTID_START) * sizeof(lpite)), + MEMTXATTRS_UNSPECIFIED, &lpite, sizeof(lpite)); + + if (!(lpite & LPI_CTE_ENABLED)) { + return; + } + + if (ds) { + prio = lpite & LPI_PRIORITY_MASK; + } else { + prio = ((lpite & LPI_PRIORITY_MASK) >> 1) | 0x80; + } + + if ((prio < hpp->prio) || + ((prio == hpp->prio) && (irq <= hpp->irq))) { + hpp->irq = irq; + hpp->prio = prio; + /* LPIs and vLPIs are always non-secure Grp1 interrupts */ + hpp->grp = GICV3_G1NS; + } +} + static uint8_t gicr_read_ipriorityr(GICv3CPUState *cs, MemTxAttrs attrs, int irq) { @@ -XXX,XX +XXX,XX @@ MemTxResult gicv3_redist_write(void *opaque, hwaddr offset, uint64_t data, static void gicv3_redist_check_lpi_priority(GICv3CPUState *cs, int irq) { - AddressSpace *as = &cs->gic->dma_as; - uint64_t lpict_baddr; - uint8_t lpite; - uint8_t prio; + uint64_t lpict_baddr = cs->gicr_propbaser & R_GICR_PROPBASER_PHYADDR_MASK; - lpict_baddr = cs->gicr_propbaser & R_GICR_PROPBASER_PHYADDR_MASK; - - address_space_read(as, lpict_baddr + ((irq - GICV3_LPI_INTID_START) * - sizeof(lpite)), MEMTXATTRS_UNSPECIFIED, &lpite, - sizeof(lpite)); - - if (!(lpite & LPI_CTE_ENABLED)) { - return; - } - - if (cs->gic->gicd_ctlr & GICD_CTLR_DS) { - prio = lpite & LPI_PRIORITY_MASK; - } else { - prio = ((lpite & LPI_PRIORITY_MASK) >> 1) | 0x80; - } - - if ((prio < cs->hpplpi.prio) || - ((prio == cs->hpplpi.prio) && (irq <= cs->hpplpi.irq))) { - cs->hpplpi.irq = irq; - cs->hpplpi.prio = prio; - /* LPIs are always non-secure Grp1 interrupts */ - cs->hpplpi.grp = GICV3_G1NS; - } + update_for_one_lpi(cs, irq, lpict_baddr, + cs->gic->gicd_ctlr & GICD_CTLR_DS, + &cs->hpplpi); } void gicv3_redist_update_lpi_only(GICv3CPUState *cs) -- 2.25.1 Factor out the common part of gicv3_redist_update_lpi_only() into a new function update_for_all_lpis(), which does a full rescan of an LPI Pending table and sets the specified PendingIrq struct with the highest priority pending enabled LPI it finds. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-29-peter.maydell@linaro.org --- hw/intc/arm_gicv3_redist.c | 66 ++++++++++++++++++++++++++------------ 1 file changed, 46 insertions(+), 20 deletions(-) diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ static void update_for_one_lpi(GICv3CPUState *cs, int irq, } } +/** + * update_for_all_lpis: Fully scan LPI tables and find best pending LPI + * + * @cs: GICv3CPUState + * @ptbase: physical address of LPI Pending table + * @ctbase: physical address of LPI Configuration table + * @ptsizebits: size of tables, specified as number of interrupt ID bits minus 1 + * @ds: true if priority value should not be shifted + * @hpp: points to pending information to set + * + * Recalculate the highest priority pending enabled LPI from scratch, + * and set @hpp accordingly. + * + * We scan the LPI pending table @ptbase; for each pending LPI, we read the + * corresponding entry in the LPI configuration table @ctbase to extract + * the priority and enabled information. + * + * We take @ptsizebits in the form idbits-1 because this is the way that + * LPI table sizes are architecturally specified in GICR_PROPBASER.IDBits + * and in the VMAPP command's VPT_size field. + */ +static void update_for_all_lpis(GICv3CPUState *cs, uint64_t ptbase, + uint64_t ctbase, unsigned ptsizebits, + bool ds, PendingIrq *hpp) +{ + AddressSpace *as = &cs->gic->dma_as; + uint8_t pend; + uint32_t pendt_size = (1ULL << (ptsizebits + 1)); + int i, bit; + + hpp->prio = 0xff; + + for (i = GICV3_LPI_INTID_START / 8; i < pendt_size / 8; i++) { + address_space_read(as, ptbase + i, MEMTXATTRS_UNSPECIFIED, &pend, 1); + while (pend) { + bit = ctz32(pend); + update_for_one_lpi(cs, i * 8 + bit, ctbase, ds, hpp); + pend &= ~(1 << bit); + } + } +} + static uint8_t gicr_read_ipriorityr(GICv3CPUState *cs, MemTxAttrs attrs, int irq) { @@ -XXX,XX +XXX,XX @@ void gicv3_redist_update_lpi_only(GICv3CPUState *cs) * priority is lower than the last computed high priority lpi interrupt. * If yes, replace current LPI as the new high priority lpi interrupt. */ - AddressSpace *as = &cs->gic->dma_as; - uint64_t lpipt_baddr; - uint32_t pendt_size = 0; - uint8_t pend; - int i, bit; + uint64_t lpipt_baddr, lpict_baddr; uint64_t idbits; idbits = MIN(FIELD_EX64(cs->gicr_propbaser, GICR_PROPBASER, IDBITS), @@ -XXX,XX +XXX,XX @@ void gicv3_redist_update_lpi_only(GICv3CPUState *cs) return; } - cs->hpplpi.prio = 0xff; - lpipt_baddr = cs->gicr_pendbaser & R_GICR_PENDBASER_PHYADDR_MASK; + lpict_baddr = cs->gicr_propbaser & R_GICR_PROPBASER_PHYADDR_MASK; - /* Determine the highest priority pending interrupt among LPIs */ - pendt_size = (1ULL << (idbits + 1)); - - for (i = GICV3_LPI_INTID_START / 8; i < pendt_size / 8; i++) { - address_space_read(as, lpipt_baddr + i, MEMTXATTRS_UNSPECIFIED, &pend, - sizeof(pend)); - - while (pend) { - bit = ctz32(pend); - gicv3_redist_check_lpi_priority(cs, i * 8 + bit); - pend &= ~(1 << bit); - } - } + update_for_all_lpis(cs, lpipt_baddr, lpict_baddr, idbits, + cs->gic->gicd_ctlr & GICD_CTLR_DS, &cs->hpplpi); } void gicv3_redist_update_lpi(GICv3CPUState *cs) -- 2.25.1 The guest uses GICR_VPENDBASER to tell the redistributor when it is scheduling or descheduling a vCPU. When it writes and changes the VALID bit from 0 to 1, it is scheduling a vCPU, and we must update our view of the current highest priority pending vLPI from the new Pending and Configuration tables. When it writes and changes the VALID bit from 1 to 0, it is descheduling, which means that there is no longer a highest priority pending vLPI. The specification allows the implementation to use part of the vLPI Pending table as an IMPDEF area where it can cache information when a vCPU is descheduled, so that it can avoid having to do a full rescan of the tables when the vCPU is scheduled again. For now, we don't take advantage of this, and simply do a complete rescan. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-30-peter.maydell@linaro.org --- hw/intc/arm_gicv3_redist.c | 87 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 84 insertions(+), 3 deletions(-) diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ static void gicr_write_ipriorityr(GICv3CPUState *cs, MemTxAttrs attrs, int irq, cs->gicr_ipriorityr[irq] = value; } +static void gicv3_redist_update_vlpi_only(GICv3CPUState *cs) +{ + uint64_t ptbase, ctbase, idbits; + + if (!FIELD_EX64(cs->gicr_vpendbaser, GICR_VPENDBASER, VALID)) { + cs->hppvlpi.prio = 0xff; + return; + } + + ptbase = cs->gicr_vpendbaser & R_GICR_VPENDBASER_PHYADDR_MASK; + ctbase = cs->gicr_vpropbaser & R_GICR_VPROPBASER_PHYADDR_MASK; + idbits = FIELD_EX64(cs->gicr_vpropbaser, GICR_VPROPBASER, IDBITS); + + update_for_all_lpis(cs, ptbase, ctbase, idbits, true, &cs->hppvlpi); +} + +static void gicv3_redist_update_vlpi(GICv3CPUState *cs) +{ + gicv3_redist_update_vlpi_only(cs); + gicv3_cpuif_virt_irq_fiq_update(cs); +} + +static void gicr_write_vpendbaser(GICv3CPUState *cs, uint64_t newval) +{ + /* Write @newval to GICR_VPENDBASER, handling its effects */ + bool oldvalid = FIELD_EX64(cs->gicr_vpendbaser, GICR_VPENDBASER, VALID); + bool newvalid = FIELD_EX64(newval, GICR_VPENDBASER, VALID); + bool pendinglast; + + /* + * The DIRTY bit is read-only and for us is always zero; + * other fields are writeable. + */ + newval &= R_GICR_VPENDBASER_INNERCACHE_MASK | + R_GICR_VPENDBASER_SHAREABILITY_MASK | + R_GICR_VPENDBASER_PHYADDR_MASK | + R_GICR_VPENDBASER_OUTERCACHE_MASK | + R_GICR_VPENDBASER_PENDINGLAST_MASK | + R_GICR_VPENDBASER_IDAI_MASK | + R_GICR_VPENDBASER_VALID_MASK; + + if (oldvalid && newvalid) { + /* + * Changing other fields while VALID is 1 is UNPREDICTABLE; + * we choose to log and ignore the write. + */ + if (cs->gicr_vpendbaser ^ newval) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Changing GICR_VPENDBASER when VALID=1 " + "is UNPREDICTABLE\n", __func__); + } + return; + } + if (!oldvalid && !newvalid) { + cs->gicr_vpendbaser = newval; + return; + } + + if (newvalid) { + /* + * Valid going from 0 to 1: update hppvlpi from tables. + * If IDAI is 0 we are allowed to use the info we cached in + * the IMPDEF area of the table. + * PendingLast is RES1 when we make this transition. + */ + pendinglast = true; + } else { + /* + * Valid going from 1 to 0: + * Set PendingLast if there was a pending enabled interrupt + * for the vPE that was just descheduled. + * If we cache info in the IMPDEF area, write it out here. + */ + pendinglast = cs->hppvlpi.prio != 0xff; + } + + newval = FIELD_DP64(newval, GICR_VPENDBASER, PENDINGLAST, pendinglast); + cs->gicr_vpendbaser = newval; + gicv3_redist_update_vlpi(cs); +} + static MemTxResult gicr_readb(GICv3CPUState *cs, hwaddr offset, uint64_t *data, MemTxAttrs attrs) { @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_writel(GICv3CPUState *cs, hwaddr offset, cs->gicr_vpropbaser = deposit64(cs->gicr_vpropbaser, 32, 32, value); return MEMTX_OK; case GICR_VPENDBASER: - cs->gicr_vpendbaser = deposit64(cs->gicr_vpendbaser, 0, 32, value); + gicr_write_vpendbaser(cs, deposit64(cs->gicr_vpendbaser, 0, 32, value)); return MEMTX_OK; case GICR_VPENDBASER + 4: - cs->gicr_vpendbaser = deposit64(cs->gicr_vpendbaser, 32, 32, value); + gicr_write_vpendbaser(cs, deposit64(cs->gicr_vpendbaser, 32, 32, value)); return MEMTX_OK; default: return MEMTX_ERROR; @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_writell(GICv3CPUState *cs, hwaddr offset, cs->gicr_vpropbaser = value; return MEMTX_OK; case GICR_VPENDBASER: - cs->gicr_vpendbaser = value; + gicr_write_vpendbaser(cs, value); return MEMTX_OK; default: return MEMTX_ERROR; -- 2.25.1 Factor out the code which sets a single bit in an LPI pending table. We're going to need this for handling vLPI tables, not just the physical LPI table. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-31-peter.maydell@linaro.org --- hw/intc/arm_gicv3_redist.c | 49 +++++++++++++++++++++++--------------- 1 file changed, 30 insertions(+), 19 deletions(-) diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ static void update_for_all_lpis(GICv3CPUState *cs, uint64_t ptbase, } } +/** + * set_lpi_pending_bit: Set or clear pending bit for an LPI + * + * @cs: GICv3CPUState + * @ptbase: physical address of LPI Pending table + * @irq: LPI to change pending state for + * @level: false to clear pending state, true to set + * + * Returns true if we needed to do something, false if the pending bit + * was already at @level. + */ +static bool set_pending_table_bit(GICv3CPUState *cs, uint64_t ptbase, + int irq, bool level) +{ + AddressSpace *as = &cs->gic->dma_as; + uint64_t addr = ptbase + irq / 8; + uint8_t pend; + + address_space_read(as, addr, MEMTXATTRS_UNSPECIFIED, &pend, 1); + if (extract32(pend, irq % 8, 1) == level) { + /* Bit already at requested state, no action required */ + return false; + } + pend = deposit32(pend, irq % 8, 1, level ? 1 : 0); + address_space_write(as, addr, MEMTXATTRS_UNSPECIFIED, &pend, 1); + return true; +} + static uint8_t gicr_read_ipriorityr(GICv3CPUState *cs, MemTxAttrs attrs, int irq) { @@ -XXX,XX +XXX,XX @@ void gicv3_redist_lpi_pending(GICv3CPUState *cs, int irq, int level) * This function updates the pending bit in lpi pending table for * the irq being activated or deactivated. */ - AddressSpace *as = &cs->gic->dma_as; uint64_t lpipt_baddr; - bool ispend = false; - uint8_t pend; - /* - * get the bit value corresponding to this irq in the - * lpi pending table - */ lpipt_baddr = cs->gicr_pendbaser & R_GICR_PENDBASER_PHYADDR_MASK; - - address_space_read(as, lpipt_baddr + ((irq / 8) * sizeof(pend)), - MEMTXATTRS_UNSPECIFIED, &pend, sizeof(pend)); - - ispend = extract32(pend, irq % 8, 1); - - /* no change in the value of pending bit, return */ - if (ispend == level) { + if (!set_pending_table_bit(cs, lpipt_baddr, irq, level)) { + /* no change in the value of pending bit, return */ return; } - pend = deposit32(pend, irq % 8, 1, level ? 1 : 0); - - address_space_write(as, lpipt_baddr + ((irq / 8) * sizeof(pend)), - MEMTXATTRS_UNSPECIFIED, &pend, sizeof(pend)); /* * check if this LPI is better than the current hpplpi, if yes -- 2.25.1 Implement the function gicv3_redist_process_vlpi(), which was left as just a stub earlier. This function deals with being handed a VLPI by the ITS. It must set the bit in the pending table. If the vCPU is currently resident we must recalculate the highest priority pending vLPI; otherwise we may need to ring a "doorbell" interrupt to let the hypervisor know it might want to reschedule the vCPU. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-32-peter.maydell@linaro.org --- hw/intc/arm_gicv3_redist.c | 48 ++++++++++++++++++++++++++++++++++---- 1 file changed, 44 insertions(+), 4 deletions(-) diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ static uint32_t gicr_read_bitmap_reg(GICv3CPUState *cs, MemTxAttrs attrs, return reg; } +static bool vcpu_resident(GICv3CPUState *cs, uint64_t vptaddr) +{ + /* + * Return true if a vCPU is resident, which is defined by + * whether the GICR_VPENDBASER register is marked VALID and + * has the right virtual pending table address. + */ + if (!FIELD_EX64(cs->gicr_vpendbaser, GICR_VPENDBASER, VALID)) { + return false; + } + return vptaddr == (cs->gicr_vpendbaser & R_GICR_VPENDBASER_PHYADDR_MASK); +} + /** * update_for_one_lpi: Update pending information if this LPI is better * @@ -XXX,XX +XXX,XX @@ void gicv3_redist_vlpi_pending(GICv3CPUState *cs, int irq, int level) void gicv3_redist_process_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr, int doorbell, int level) { - /* - * The redistributor handling for being handed a VLPI by the ITS - * will be added in a subsequent commit. - */ + bool bit_changed; + bool resident = vcpu_resident(cs, vptaddr); + uint64_t ctbase; + + if (resident) { + uint32_t idbits = FIELD_EX64(cs->gicr_vpropbaser, GICR_VPROPBASER, IDBITS); + if (irq >= (1ULL << (idbits + 1))) { + return; + } + } + + bit_changed = set_pending_table_bit(cs, vptaddr, irq, level); + if (resident && bit_changed) { + if (level) { + /* Check whether this vLPI is now the best */ + ctbase = cs->gicr_vpropbaser & R_GICR_VPROPBASER_PHYADDR_MASK; + update_for_one_lpi(cs, irq, ctbase, true, &cs->hppvlpi); + gicv3_cpuif_virt_irq_fiq_update(cs); + } else { + /* Only need to recalculate if this was previously the best vLPI */ + if (irq == cs->hppvlpi.irq) { + gicv3_redist_update_vlpi(cs); + } + } + } + + if (!resident && level && doorbell != INTID_SPURIOUS && + (cs->gicr_ctlr & GICR_CTLR_ENABLE_LPIS)) { + /* vCPU is not currently resident: ring the doorbell */ + gicv3_redist_process_lpi(cs, doorbell, 1); + } } void gicv3_redist_mov_vlpi(GICv3CPUState *src, uint64_t src_vptaddr, -- 2.25.1 Implement the function gicv3_redist_vlpi_pending(), which was previously left as a stub. This is the function that is called by the CPU interface when it changes the state of a vLPI. It's similar to gicv3_redist_process_vlpi(), but we know that the vCPU is definitely resident on the redistributor and the irq is in range, so it is a bit simpler. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-33-peter.maydell@linaro.org --- hw/intc/arm_gicv3_redist.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ void gicv3_redist_movall_lpis(GICv3CPUState *src, GICv3CPUState *dest) void gicv3_redist_vlpi_pending(GICv3CPUState *cs, int irq, int level) { /* - * The redistributor handling for changing the pending state - * of a vLPI will be added in a subsequent commit. + * Change the pending state of the specified vLPI. + * Unlike gicv3_redist_process_vlpi(), we know here that the + * vCPU is definitely resident on this redistributor, and that + * the irq is in range. */ + uint64_t vptbase, ctbase; + + vptbase = FIELD_EX64(cs->gicr_vpendbaser, GICR_VPENDBASER, PHYADDR) << 16; + + if (set_pending_table_bit(cs, vptbase, irq, level)) { + if (level) { + /* Check whether this vLPI is now the best */ + ctbase = cs->gicr_vpropbaser & R_GICR_VPROPBASER_PHYADDR_MASK; + update_for_one_lpi(cs, irq, ctbase, true, &cs->hppvlpi); + gicv3_cpuif_virt_irq_fiq_update(cs); + } else { + /* Only need to recalculate if this was previously the best vLPI */ + if (irq == cs->hppvlpi.irq) { + gicv3_redist_update_vlpi(cs); + } + } + } } void gicv3_redist_process_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr, -- 2.25.1 We can use our new set_pending_table_bit() utility function in gicv3_redist_mov_lpi() to clear the bit in the source pending table, rather than doing the "load, clear bit, store" ourselves. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-34-peter.maydell@linaro.org --- hw/intc/arm_gicv3_redist.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ void gicv3_redist_mov_lpi(GICv3CPUState *src, GICv3CPUState *dest, int irq) * we choose to NOP. If LPIs are disabled on source there's nothing * to be transferred anyway. */ - AddressSpace *as = &src->gic->dma_as; uint64_t idbits; uint32_t pendt_size; uint64_t src_baddr; - uint8_t src_pend; if (!(src->gicr_ctlr & GICR_CTLR_ENABLE_LPIS) || !(dest->gicr_ctlr & GICR_CTLR_ENABLE_LPIS)) { @@ -XXX,XX +XXX,XX @@ void gicv3_redist_mov_lpi(GICv3CPUState *src, GICv3CPUState *dest, int irq) src_baddr = src->gicr_pendbaser & R_GICR_PENDBASER_PHYADDR_MASK; - address_space_read(as, src_baddr + (irq / 8), - MEMTXATTRS_UNSPECIFIED, &src_pend, sizeof(src_pend)); - if (!extract32(src_pend, irq % 8, 1)) { + if (!set_pending_table_bit(src, src_baddr, irq, 0)) { /* Not pending on source, nothing to do */ return; } - src_pend &= ~(1 << (irq % 8)); - address_space_write(as, src_baddr + (irq / 8), - MEMTXATTRS_UNSPECIFIED, &src_pend, sizeof(src_pend)); if (irq == src->hpplpi.irq) { /* * We just made this LPI not-pending so only need to update -- 2.25.1 Implement the gicv3_redist_mov_vlpi() function (previously left as a stub). This function handles the work of a VMOVI command: it marks the vLPI not-pending on the source and pending on the destination. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-35-peter.maydell@linaro.org --- hw/intc/arm_gicv3_redist.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ void gicv3_redist_mov_vlpi(GICv3CPUState *src, uint64_t src_vptaddr, int irq, int doorbell) { /* - * The redistributor handling for moving a VLPI will be added - * in a subsequent commit. + * Move the specified vLPI's pending state from the source redistributor + * to the destination. */ + if (!set_pending_table_bit(src, src_vptaddr, irq, 0)) { + /* Not pending on source, nothing to do */ + return; + } + if (vcpu_resident(src, src_vptaddr) && irq == src->hppvlpi.irq) { + /* + * Update src's cached highest-priority pending vLPI if we just made + * it not-pending + */ + gicv3_redist_update_vlpi(src); + } + /* + * Mark the vLPI pending on the destination (ringing the doorbell + * if the vCPU isn't resident) + */ + gicv3_redist_process_vlpi(dest, irq, dest_vptaddr, doorbell, irq); } void gicv3_redist_vinvall(GICv3CPUState *cs, uint64_t vptaddr) -- 2.25.1 Implement the gicv3_redist_vinvall() function (previously left as a stub). This function handles the work of a VINVALL command: it must invalidate any cached information associated with a specific vCPU. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-36-peter.maydell@linaro.org --- hw/intc/arm_gicv3_redist.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ void gicv3_redist_mov_vlpi(GICv3CPUState *src, uint64_t src_vptaddr, void gicv3_redist_vinvall(GICv3CPUState *cs, uint64_t vptaddr) { - /* The redistributor handling will be added in a subsequent commit */ + if (!vcpu_resident(cs, vptaddr)) { + /* We don't have anything cached if the vCPU isn't resident */ + return; + } + + /* Otherwise, our only cached information is the HPPVLPI info */ + gicv3_redist_update_vlpi(cs); } void gicv3_redist_inv_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr) -- 2.25.1 Implement the function gicv3_redist_inv_vlpi(), which was previously left as a stub. This is the function that does the work of the INV command for a virtual interrupt. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-37-peter.maydell@linaro.org --- hw/intc/arm_gicv3_redist.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ void gicv3_redist_vinvall(GICv3CPUState *cs, uint64_t vptaddr) void gicv3_redist_inv_vlpi(GICv3CPUState *cs, int irq, uint64_t vptaddr) { /* - * The redistributor handling for invalidating cached information - * about a VLPI will be added in a subsequent commit. + * The only cached information for LPIs we have is the HPPLPI. + * We could be cleverer about identifying when we don't need + * to do a full rescan of the pending table, but until we find + * this is a performance issue, just always recalculate. */ + gicv3_redist_vinvall(cs, vptaddr); } void gicv3_redist_set_irq(GICv3CPUState *cs, int irq, int level) -- 2.25.1 Update the various GIC ID and feature registers for GICv4: * PIDR2 [7:4] is the GIC architecture revision * GICD_TYPER.DVIS is 1 to indicate direct vLPI injection support * GICR_TYPER.VLPIS is 1 to indicate redistributor support for vLPIs * GITS_TYPER.VIRTUAL is 1 to indicate vLPI support * GITS_TYPER.VMOVP is 1 to indicate that our VMOVP implementation handles cross-ITS synchronization for the guest * ICH_VTR_EL2.nV4 is 0 to indicate direct vLPI injection support Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-38-peter.maydell@linaro.org --- hw/intc/gicv3_internal.h | 15 +++++++++++---- hw/intc/arm_gicv3_common.c | 7 +++++-- hw/intc/arm_gicv3_cpuif.c | 6 +++++- hw/intc/arm_gicv3_dist.c | 7 ++++--- hw/intc/arm_gicv3_its.c | 7 ++++++- hw/intc/arm_gicv3_redist.c | 2 +- 6 files changed, 32 insertions(+), 12 deletions(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ FIELD(GITS_TYPER, SEIS, 18, 1) FIELD(GITS_TYPER, PTA, 19, 1) FIELD(GITS_TYPER, CIDBITS, 32, 4) FIELD(GITS_TYPER, CIL, 36, 1) +FIELD(GITS_TYPER, VMOVP, 37, 1) #define GITS_IDREGS 0xFFD0 @@ -XXX,XX +XXX,XX @@ static inline uint32_t gicv3_iidr(void) #define GICV3_PIDR0_REDIST 0x93 #define GICV3_PIDR0_ITS 0x94 -static inline uint32_t gicv3_idreg(int regoffset, uint8_t pidr0) +static inline uint32_t gicv3_idreg(GICv3State *s, int regoffset, uint8_t pidr0) { /* Return the value of the CoreSight ID register at the specified * offset from the first ID register (as found in the distributor * and redistributor register banks). - * These values indicate an ARM implementation of a GICv3. + * These values indicate an ARM implementation of a GICv3 or v4. */ static const uint8_t gicd_ids[] = { - 0x44, 0x00, 0x00, 0x00, 0x92, 0xB4, 0x3B, 0x00, 0x0D, 0xF0, 0x05, 0xB1 + 0x44, 0x00, 0x00, 0x00, 0x92, 0xB4, 0x0B, 0x00, 0x0D, 0xF0, 0x05, 0xB1 }; + uint32_t id; regoffset /= 4; if (regoffset == 4) { return pidr0; } - return gicd_ids[regoffset]; + id = gicd_ids[regoffset]; + if (regoffset == 6) { + /* PIDR2 bits [7:4] are the GIC architecture revision */ + id |= s->revision << 4; + } + return id; } /** diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_realize(DeviceState *dev, Error **errp) * Last == 1 if this is the last redistributor in a series of * contiguous redistributor pages * DirectLPI == 0 (direct injection of LPIs not supported) - * VLPIS == 0 (virtual LPIs not supported) - * PLPIS == 0 (physical LPIs not supported) + * VLPIS == 1 if vLPIs supported (GICv4 and up) + * PLPIS == 1 if LPIs supported */ cpu_affid = object_property_get_uint(OBJECT(cpu), "mp-affinity", NULL); @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_realize(DeviceState *dev, Error **errp) if (s->lpi_enable) { s->cpu[i].gicr_typer |= GICR_TYPER_PLPIS; + if (s->revision > 3) { + s->cpu[i].gicr_typer |= GICR_TYPER_VLPIS; + } } } diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static uint64_t ich_vtr_read(CPUARMState *env, const ARMCPRegInfo *ri) uint64_t value; value = ((cs->num_list_regs - 1) << ICH_VTR_EL2_LISTREGS_SHIFT) - | ICH_VTR_EL2_TDS | ICH_VTR_EL2_NV4 | ICH_VTR_EL2_A3V + | ICH_VTR_EL2_TDS | ICH_VTR_EL2_A3V | (1 << ICH_VTR_EL2_IDBITS_SHIFT) | ((cs->vprebits - 1) << ICH_VTR_EL2_PREBITS_SHIFT) | ((cs->vpribits - 1) << ICH_VTR_EL2_PRIBITS_SHIFT); + if (cs->gic->revision < 4) { + value |= ICH_VTR_EL2_NV4; + } + trace_gicv3_ich_vtr_read(gicv3_redist_affid(cs), value); return value; } diff --git a/hw/intc/arm_gicv3_dist.c b/hw/intc/arm_gicv3_dist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_dist.c +++ b/hw/intc/arm_gicv3_dist.c @@ -XXX,XX +XXX,XX @@ static bool gicd_readl(GICv3State *s, hwaddr offset, * No1N == 1 (1-of-N SPI interrupts not supported) * A3V == 1 (non-zero values of Affinity level 3 supported) * IDbits == 0xf (we support 16-bit interrupt identifiers) - * DVIS == 0 (Direct virtual LPI injection not supported) + * DVIS == 1 (Direct virtual LPI injection supported) if GICv4 * LPIS == 1 (LPIs are supported if affinity routing is enabled) * num_LPIs == 0b00000 (bits [15:11],Number of LPIs as indicated * by GICD_TYPER.IDbits) @@ -XXX,XX +XXX,XX @@ static bool gicd_readl(GICv3State *s, hwaddr offset, * so we only need to check the DS bit. */ bool sec_extn = !(s->gicd_ctlr & GICD_CTLR_DS); + bool dvis = s->revision >= 4; - *data = (1 << 25) | (1 << 24) | (sec_extn << 10) | + *data = (1 << 25) | (1 << 24) | (dvis << 18) | (sec_extn << 10) | (s->lpi_enable << GICD_TYPER_LPIS_SHIFT) | (0xf << 19) | itlinesnumber; return true; @@ -XXX,XX +XXX,XX @@ static bool gicd_readl(GICv3State *s, hwaddr offset, } case GICD_IDREGS ... GICD_IDREGS + 0x2f: /* ID registers */ - *data = gicv3_idreg(offset - GICD_IDREGS, GICV3_PIDR0_DIST); + *data = gicv3_idreg(s, offset - GICD_IDREGS, GICV3_PIDR0_DIST); return true; case GICD_SGIR: /* WO registers, return unknown value */ diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static bool its_readl(GICv3ITSState *s, hwaddr offset, break; case GITS_IDREGS ... GITS_IDREGS + 0x2f: /* ID registers */ - *data = gicv3_idreg(offset - GITS_IDREGS, GICV3_PIDR0_ITS); + *data = gicv3_idreg(s->gicv3, offset - GITS_IDREGS, GICV3_PIDR0_ITS); break; case GITS_TYPER: *data = extract64(s->typer, 0, 32); @@ -XXX,XX +XXX,XX @@ static void gicv3_arm_its_realize(DeviceState *dev, Error **errp) s->typer = FIELD_DP64(s->typer, GITS_TYPER, DEVBITS, ITS_DEVBITS); s->typer = FIELD_DP64(s->typer, GITS_TYPER, CIL, 1); s->typer = FIELD_DP64(s->typer, GITS_TYPER, CIDBITS, ITS_CIDBITS); + if (s->gicv3->revision >= 4) { + /* Our VMOVP handles cross-ITS synchronization itself */ + s->typer = FIELD_DP64(s->typer, GITS_TYPER, VMOVP, 1); + s->typer = FIELD_DP64(s->typer, GITS_TYPER, VIRTUAL, 1); + } } static void gicv3_its_reset(DeviceState *dev) diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_redist.c +++ b/hw/intc/arm_gicv3_redist.c @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_readl(GICv3CPUState *cs, hwaddr offset, *data = cs->gicr_nsacr; return MEMTX_OK; case GICR_IDREGS ... GICR_IDREGS + 0x2f: - *data = gicv3_idreg(offset - GICR_IDREGS, GICV3_PIDR0_REDIST); + *data = gicv3_idreg(cs->gic, offset - GICR_IDREGS, GICV3_PIDR0_REDIST); return MEMTX_OK; /* * VLPI frame registers. We don't need a version check for -- 2.25.1 Now that we have implemented all the GICv4 requirements, relax the error-checking on the GIC object's 'revision' property to allow a TCG GIC to be a GICv4, whilst still constraining the KVM GIC to GICv3. Our 'revision' property doesn't consider the possibility of wanting to specify the minor version of the GIC -- for instance there is a GICv3.1 which adds support for extended SPI and PPI ranges, among other things, and also GICv4.1. But since the QOM property is internal to QEMU, not user-facing, we can cross that bridge when we come to it. Within the GIC implementation itself code generally checks against the appropriate ID register feature bits, and the only use of s->revision is for setting those ID register bits. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-39-peter.maydell@linaro.org --- hw/intc/arm_gicv3_common.c | 12 +++++++----- hw/intc/arm_gicv3_kvm.c | 5 +++++ 2 files changed, 12 insertions(+), 5 deletions(-) diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_realize(DeviceState *dev, Error **errp) GICv3State *s = ARM_GICV3_COMMON(dev); int i, rdist_capacity, cpuidx; - /* revision property is actually reserved and currently used only in order - * to keep the interface compatible with GICv2 code, avoiding extra - * conditions. However, in future it could be used, for example, if we - * implement GICv4. + /* + * This GIC device supports only revisions 3 and 4. The GICv1/v2 + * is a separate device. + * Note that subclasses of this device may impose further restrictions + * on the GIC revision: notably, the in-kernel KVM GIC doesn't + * support GICv4. */ - if (s->revision != 3) { + if (s->revision != 3 && s->revision != 4) { error_setg(errp, "unsupported GIC revision %d", s->revision); return; } diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_kvm.c +++ b/hw/intc/arm_gicv3_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gicv3_realize(DeviceState *dev, Error **errp) return; } + if (s->revision != 3) { + error_setg(errp, "unsupported GIC revision %d for in-kernel GIC", + s->revision); + } + if (s->security_extn) { error_setg(errp, "the in-kernel VGICv3 does not implement the " "security extensions"); -- 2.25.1 Everywhere we need to check which GIC version we're using, we look at vms->gic_version and use the VIRT_GIC_VERSION_* enum values, except in create_gic(), which copies vms->gic_version into a local 'int' variable and makes direct comparisons against values 2 and 3. For consistency, change this function to check the GIC version the same way we do elsewhere. This includes not implicitly relying on the enumeration type values happening to match the integer 'revision' values the GIC device object wants. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-40-peter.maydell@linaro.org --- hw/arm/virt.c | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) /* We create a standalone GIC */ SysBusDevice *gicbusdev; const char *gictype; - int type = vms->gic_version, i; + int i; unsigned int smp_cpus = ms->smp.cpus; uint32_t nb_redist_regions = 0; + int revision; - gictype = (type == 3) ? gicv3_class_name() : gic_class_name(); + if (vms->gic_version == VIRT_GIC_VERSION_2) { + gictype = gic_class_name(); + } else { + gictype = gicv3_class_name(); + } + switch (vms->gic_version) { + case VIRT_GIC_VERSION_2: + revision = 2; + break; + case VIRT_GIC_VERSION_3: + revision = 3; + break; + default: + g_assert_not_reached(); + } vms->gic = qdev_new(gictype); - qdev_prop_set_uint32(vms->gic, "revision", type); + qdev_prop_set_uint32(vms->gic, "revision", revision); qdev_prop_set_uint32(vms->gic, "num-cpu", smp_cpus); /* Note that the num-irq property counts both internal and external * interrupts; there are always 32 of the former (mandated by GIC spec). @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) qdev_prop_set_bit(vms->gic, "has-security-extensions", vms->secure); } - if (type == 3) { + if (vms->gic_version == VIRT_GIC_VERSION_3) { uint32_t redist0_capacity = vms->memmap[VIRT_GIC_REDIST].size / GICV3_REDIST_SIZE; uint32_t redist0_count = MIN(smp_cpus, redist0_capacity); @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) gicbusdev = SYS_BUS_DEVICE(vms->gic); sysbus_realize_and_unref(gicbusdev, &error_fatal); sysbus_mmio_map(gicbusdev, 0, vms->memmap[VIRT_GIC_DIST].base); - if (type == 3) { + if (vms->gic_version == VIRT_GIC_VERSION_3) { sysbus_mmio_map(gicbusdev, 1, vms->memmap[VIRT_GIC_REDIST].base); if (nb_redist_regions == 2) { sysbus_mmio_map(gicbusdev, 2, @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) ppibase + timer_irq[irq])); } - if (type == 3) { + if (vms->gic_version == VIRT_GIC_VERSION_3) { qemu_irq irq = qdev_get_gpio_in(vms->gic, ppibase + ARCH_GIC_MAINT_IRQ); qdev_connect_gpio_out_named(cpudev, "gicv3-maintenance-interrupt", @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) fdt_add_gic_node(vms); - if (type == 3 && vms->its) { + if (vms->gic_version == VIRT_GIC_VERSION_3 && vms->its) { create_its(vms); - } else if (type == 2) { + } else if (vms->gic_version == VIRT_GIC_VERSION_2) { create_v2m(vms); } } -- 2.25.1 In several places in virt.c we calculate the number of redistributors that fit in a region of our memory map, which is the size of the region divided by the size of a single redistributor frame. For GICv4, the redistributor frame is a different size from that for GICv3. Abstract out the calculation of redistributor region capacity so that we have one place we need to change to handle GICv4 rather than several. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-41-peter.maydell@linaro.org --- include/hw/arm/virt.h | 9 +++++++-- hw/arm/virt.c | 11 ++++------- 2 files changed, 11 insertions(+), 9 deletions(-) diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_TYPE(VirtMachineState, VirtMachineClass, VIRT_MACHINE) void virt_acpi_setup(VirtMachineState *vms); bool virt_is_acpi_enabled(VirtMachineState *vms); +/* Return number of redistributors that fit in the specified region */ +static uint32_t virt_redist_capacity(VirtMachineState *vms, int region) +{ + return vms->memmap[region].size / GICV3_REDIST_SIZE; +} + /* Return the number of used redistributor regions */ static inline int virt_gicv3_redist_region_count(VirtMachineState *vms) { - uint32_t redist0_capacity = - vms->memmap[VIRT_GIC_REDIST].size / GICV3_REDIST_SIZE; + uint32_t redist0_capacity = virt_redist_capacity(vms, VIRT_GIC_REDIST); assert(vms->gic_version == VIRT_GIC_VERSION_3); diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) } if (vms->gic_version == VIRT_GIC_VERSION_3) { - uint32_t redist0_capacity = - vms->memmap[VIRT_GIC_REDIST].size / GICV3_REDIST_SIZE; + uint32_t redist0_capacity = virt_redist_capacity(vms, VIRT_GIC_REDIST); uint32_t redist0_count = MIN(smp_cpus, redist0_capacity); nb_redist_regions = virt_gicv3_redist_region_count(vms); @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) if (nb_redist_regions == 2) { uint32_t redist1_capacity = - vms->memmap[VIRT_HIGH_GIC_REDIST2].size / GICV3_REDIST_SIZE; + virt_redist_capacity(vms, VIRT_HIGH_GIC_REDIST2); qdev_prop_set_uint32(vms->gic, "redist-region-count[1]", MIN(smp_cpus - redist0_count, redist1_capacity)); @@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine) * many redistributors we can fit into the memory map. */ if (vms->gic_version == VIRT_GIC_VERSION_3) { - virt_max_cpus = - vms->memmap[VIRT_GIC_REDIST].size / GICV3_REDIST_SIZE; - virt_max_cpus += - vms->memmap[VIRT_HIGH_GIC_REDIST2].size / GICV3_REDIST_SIZE; + virt_max_cpus = virt_redist_capacity(vms, VIRT_GIC_REDIST) + + virt_redist_capacity(vms, VIRT_HIGH_GIC_REDIST2); } else { virt_max_cpus = GIC_NCPU; } -- 2.25.1 Add support for the TCG GICv4 to the virt board. For the board, the GICv4 is very similar to the GICv3, with the only difference being the size of the redistributor frame. The changes here are thus: * calculating virt_redist_capacity correctly for GICv4 * changing various places which were "if GICv3" to be "if not GICv2" * the commandline option handling Note that using GICv4 reduces the maximum possible number of CPUs on the virt board from 512 to 317, because we can now only fit half as many redistributors into the redistributor regions we have defined. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220408141550.1271295-42-peter.maydell@linaro.org --- docs/system/arm/virt.rst | 5 ++- include/hw/arm/virt.h | 12 +++++-- hw/arm/virt.c | 70 ++++++++++++++++++++++++++++++---------- 3 files changed, 67 insertions(+), 20 deletions(-) diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/virt.rst +++ b/docs/system/arm/virt.rst @@ -XXX,XX +XXX,XX @@ gic-version GICv2. Note that this limits the number of CPUs to 8. ``3`` GICv3. This allows up to 512 CPUs. + ``4`` + GICv4. Requires ``virtualization`` to be ``on``; allows up to 317 CPUs. ``host`` Use the same GIC version the host provides, when using KVM ``max`` Use the best GIC version possible (same as host when using KVM; - currently same as ``3``` for TCG, but this may change in future) + with TCG this is currently ``3`` if ``virtualization`` is ``off`` and + ``4`` if ``virtualization`` is ``on``, but this may change in future) its Set ``on``/``off`` to enable/disable ITS instantiation. The default is ``on`` diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -XXX,XX +XXX,XX @@ typedef enum VirtGICType { VIRT_GIC_VERSION_HOST, VIRT_GIC_VERSION_2, VIRT_GIC_VERSION_3, + VIRT_GIC_VERSION_4, VIRT_GIC_VERSION_NOSEL, } VirtGICType; @@ -XXX,XX +XXX,XX @@ bool virt_is_acpi_enabled(VirtMachineState *vms); /* Return number of redistributors that fit in the specified region */ static uint32_t virt_redist_capacity(VirtMachineState *vms, int region) { - return vms->memmap[region].size / GICV3_REDIST_SIZE; + uint32_t redist_size; + + if (vms->gic_version == VIRT_GIC_VERSION_3) { + redist_size = GICV3_REDIST_SIZE; + } else { + redist_size = GICV4_REDIST_SIZE; + } + return vms->memmap[region].size / redist_size; } /* Return the number of used redistributor regions */ @@ -XXX,XX +XXX,XX @@ static inline int virt_gicv3_redist_region_count(VirtMachineState *vms) { uint32_t redist0_capacity = virt_redist_capacity(vms, VIRT_GIC_REDIST); - assert(vms->gic_version == VIRT_GIC_VERSION_3); + assert(vms->gic_version != VIRT_GIC_VERSION_2); return (MACHINE(vms)->smp.cpus > redist0_capacity && vms->highmem_redists) ? 2 : 1; diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void fdt_add_gic_node(VirtMachineState *vms) qemu_fdt_setprop_cell(ms->fdt, nodename, "#address-cells", 0x2); qemu_fdt_setprop_cell(ms->fdt, nodename, "#size-cells", 0x2); qemu_fdt_setprop(ms->fdt, nodename, "ranges", NULL, 0); - if (vms->gic_version == VIRT_GIC_VERSION_3) { + if (vms->gic_version != VIRT_GIC_VERSION_2) { int nb_redist_regions = virt_gicv3_redist_region_count(vms); qemu_fdt_setprop_string(ms->fdt, nodename, "compatible", @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) case VIRT_GIC_VERSION_3: revision = 3; break; + case VIRT_GIC_VERSION_4: + revision = 4; + break; default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) qdev_prop_set_bit(vms->gic, "has-security-extensions", vms->secure); } - if (vms->gic_version == VIRT_GIC_VERSION_3) { + if (vms->gic_version != VIRT_GIC_VERSION_2) { uint32_t redist0_capacity = virt_redist_capacity(vms, VIRT_GIC_REDIST); uint32_t redist0_count = MIN(smp_cpus, redist0_capacity); @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) gicbusdev = SYS_BUS_DEVICE(vms->gic); sysbus_realize_and_unref(gicbusdev, &error_fatal); sysbus_mmio_map(gicbusdev, 0, vms->memmap[VIRT_GIC_DIST].base); - if (vms->gic_version == VIRT_GIC_VERSION_3) { + if (vms->gic_version != VIRT_GIC_VERSION_2) { sysbus_mmio_map(gicbusdev, 1, vms->memmap[VIRT_GIC_REDIST].base); if (nb_redist_regions == 2) { sysbus_mmio_map(gicbusdev, 2, @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) ppibase + timer_irq[irq])); } - if (vms->gic_version == VIRT_GIC_VERSION_3) { + if (vms->gic_version != VIRT_GIC_VERSION_2) { qemu_irq irq = qdev_get_gpio_in(vms->gic, ppibase + ARCH_GIC_MAINT_IRQ); qdev_connect_gpio_out_named(cpudev, "gicv3-maintenance-interrupt", @@ -XXX,XX +XXX,XX @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) fdt_add_gic_node(vms); - if (vms->gic_version == VIRT_GIC_VERSION_3 && vms->its) { + if (vms->gic_version != VIRT_GIC_VERSION_2 && vms->its) { create_its(vms); } else if (vms->gic_version == VIRT_GIC_VERSION_2) { create_v2m(vms); @@ -XXX,XX +XXX,XX @@ static uint64_t virt_cpu_mp_affinity(VirtMachineState *vms, int idx) * purposes are to make TCG consistent (with 64-bit KVM hosts) * and to improve SGI efficiency. */ - if (vms->gic_version == VIRT_GIC_VERSION_3) { - clustersz = GICV3_TARGETLIST_BITS; - } else { + if (vms->gic_version == VIRT_GIC_VERSION_2) { clustersz = GIC_TARGETLIST_BITS; + } else { + clustersz = GICV3_TARGETLIST_BITS; } } return arm_cpu_mp_affinity(idx, clustersz); @@ -XXX,XX +XXX,XX @@ static void finalize_gic_version(VirtMachineState *vms) error_report( "gic-version=3 is not supported with kernel-irqchip=off"); exit(1); + case VIRT_GIC_VERSION_4: + error_report( + "gic-version=4 is not supported with kernel-irqchip=off"); + exit(1); } } @@ -XXX,XX +XXX,XX @@ static void finalize_gic_version(VirtMachineState *vms) case VIRT_GIC_VERSION_2: case VIRT_GIC_VERSION_3: break; + case VIRT_GIC_VERSION_4: + error_report("gic-version=4 is not supported with KVM"); + exit(1); } /* Check chosen version is effectively supported by the host */ @@ -XXX,XX +XXX,XX @@ static void finalize_gic_version(VirtMachineState *vms) case VIRT_GIC_VERSION_MAX: if (module_object_class_by_name("arm-gicv3")) { /* CONFIG_ARM_GICV3_TCG was set */ - vms->gic_version = VIRT_GIC_VERSION_3; + if (vms->virt) { + /* GICv4 only makes sense if CPU has EL2 */ + vms->gic_version = VIRT_GIC_VERSION_4; + } else { + vms->gic_version = VIRT_GIC_VERSION_3; + } } else { vms->gic_version = VIRT_GIC_VERSION_2; } @@ -XXX,XX +XXX,XX @@ static void finalize_gic_version(VirtMachineState *vms) case VIRT_GIC_VERSION_HOST: error_report("gic-version=host requires KVM"); exit(1); + case VIRT_GIC_VERSION_4: + if (!vms->virt) { + error_report("gic-version=4 requires virtualization enabled"); + exit(1); + } + break; case VIRT_GIC_VERSION_2: case VIRT_GIC_VERSION_3: break; @@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine) vms->psci_conduit = QEMU_PSCI_CONDUIT_HVC; } - /* The maximum number of CPUs depends on the GIC version, or on how - * many redistributors we can fit into the memory map. + /* + * The maximum number of CPUs depends on the GIC version, or on how + * many redistributors we can fit into the memory map (which in turn + * depends on whether this is a GICv3 or v4). */ - if (vms->gic_version == VIRT_GIC_VERSION_3) { + if (vms->gic_version == VIRT_GIC_VERSION_2) { + virt_max_cpus = GIC_NCPU; + } else { virt_max_cpus = virt_redist_capacity(vms, VIRT_GIC_REDIST) + virt_redist_capacity(vms, VIRT_HIGH_GIC_REDIST2); - } else { - virt_max_cpus = GIC_NCPU; } if (max_cpus > virt_max_cpus) { @@ -XXX,XX +XXX,XX @@ static void virt_set_mte(Object *obj, bool value, Error **errp) static char *virt_get_gic_version(Object *obj, Error **errp) { VirtMachineState *vms = VIRT_MACHINE(obj); - const char *val = vms->gic_version == VIRT_GIC_VERSION_3 ? "3" : "2"; + const char *val; + switch (vms->gic_version) { + case VIRT_GIC_VERSION_4: + val = "4"; + break; + case VIRT_GIC_VERSION_3: + val = "3"; + break; + default: + val = "2"; + break; + } return g_strdup(val); } @@ -XXX,XX +XXX,XX @@ static void virt_set_gic_version(Object *obj, const char *value, Error **errp) { VirtMachineState *vms = VIRT_MACHINE(obj); - if (!strcmp(value, "3")) { + if (!strcmp(value, "4")) { + vms->gic_version = VIRT_GIC_VERSION_4; + } else if (!strcmp(value, "3")) { vms->gic_version = VIRT_GIC_VERSION_3; } else if (!strcmp(value, "2")) { vms->gic_version = VIRT_GIC_VERSION_2; @@ -XXX,XX +XXX,XX @@ static void virt_machine_class_init(ObjectClass *oc, void *data) virt_set_gic_version); object_class_property_set_description(oc, "gic-version", "Set GIC version. " - "Valid values are 2, 3, host and max"); + "Valid values are 2, 3, 4, host and max"); object_class_property_add_str(oc, "iommu", virt_get_iommu, virt_set_iommu); object_class_property_set_description(oc, "iommu", -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Update isar fields per ARM DDI0487 H.a. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(ID_MMFR4, CCIDX, 24, 4) FIELD(ID_MMFR4, EVT, 28, 4) FIELD(ID_MMFR5, ETS, 0, 4) +FIELD(ID_MMFR5, NTLBPA, 4, 4) FIELD(ID_PFR0, STATE0, 0, 4) FIELD(ID_PFR0, STATE1, 4, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64ISAR1, SPECRES, 40, 4) FIELD(ID_AA64ISAR1, BF16, 44, 4) FIELD(ID_AA64ISAR1, DGH, 48, 4) FIELD(ID_AA64ISAR1, I8MM, 52, 4) +FIELD(ID_AA64ISAR1, XS, 56, 4) +FIELD(ID_AA64ISAR1, LS64, 60, 4) + +FIELD(ID_AA64ISAR2, WFXT, 0, 4) +FIELD(ID_AA64ISAR2, RPRES, 4, 4) +FIELD(ID_AA64ISAR2, GPA3, 8, 4) +FIELD(ID_AA64ISAR2, APA3, 12, 4) +FIELD(ID_AA64ISAR2, MOPS, 16, 4) +FIELD(ID_AA64ISAR2, BC, 20, 4) +FIELD(ID_AA64ISAR2, PAC_FRAC, 24, 4) FIELD(ID_AA64PFR0, EL0, 0, 4) FIELD(ID_AA64PFR0, EL1, 4, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64PFR1, SSBS, 4, 4) FIELD(ID_AA64PFR1, MTE, 8, 4) FIELD(ID_AA64PFR1, RAS_FRAC, 12, 4) FIELD(ID_AA64PFR1, MPAM_FRAC, 16, 4) +FIELD(ID_AA64PFR1, SME, 24, 4) +FIELD(ID_AA64PFR1, RNDR_TRAP, 28, 4) +FIELD(ID_AA64PFR1, CSV2_FRAC, 32, 4) +FIELD(ID_AA64PFR1, NMI, 36, 4) FIELD(ID_AA64MMFR0, PARANGE, 0, 4) FIELD(ID_AA64MMFR0, ASIDBITS, 4, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64MMFR1, SPECSEI, 24, 4) FIELD(ID_AA64MMFR1, XNX, 28, 4) FIELD(ID_AA64MMFR1, TWED, 32, 4) FIELD(ID_AA64MMFR1, ETS, 36, 4) +FIELD(ID_AA64MMFR1, HCX, 40, 4) +FIELD(ID_AA64MMFR1, AFP, 44, 4) +FIELD(ID_AA64MMFR1, NTLBPA, 48, 4) +FIELD(ID_AA64MMFR1, TIDCP1, 52, 4) +FIELD(ID_AA64MMFR1, CMOW, 56, 4) FIELD(ID_AA64MMFR2, CNP, 0, 4) FIELD(ID_AA64MMFR2, UAO, 4, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64DFR0, CTX_CMPS, 28, 4) FIELD(ID_AA64DFR0, PMSVER, 32, 4) FIELD(ID_AA64DFR0, DOUBLELOCK, 36, 4) FIELD(ID_AA64DFR0, TRACEFILT, 40, 4) +FIELD(ID_AA64DFR0, TRACEBUFFER, 44, 4) FIELD(ID_AA64DFR0, MTPMU, 48, 4) +FIELD(ID_AA64DFR0, BRBE, 52, 4) +FIELD(ID_AA64DFR0, HPMN0, 60, 4) FIELD(ID_AA64ZFR0, SVEVER, 0, 4) FIELD(ID_AA64ZFR0, AES, 4, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_DFR0, PERFMON, 24, 4) FIELD(ID_DFR0, TRACEFILT, 28, 4) FIELD(ID_DFR1, MTPMU, 0, 4) +FIELD(ID_DFR1, HPMN0, 4, 4) FIELD(DBGDIDR, SE_IMP, 12, 1) FIELD(DBGDIDR, NSUHD_IMP, 14, 1) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Update SCR_EL3 fields per ARM DDI0487 H.a. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline void xpsr_write(CPUARMState *env, uint32_t val, uint32_t mask) #define SCR_FIEN (1U << 21) #define SCR_ENSCXT (1U << 25) #define SCR_ATA (1U << 26) +#define SCR_FGTEN (1U << 27) +#define SCR_ECVEN (1U << 28) +#define SCR_TWEDEN (1U << 29) +#define SCR_TWEDEL MAKE_64BIT_MASK(30, 4) +#define SCR_TME (1ULL << 34) +#define SCR_AMVOFFEN (1ULL << 35) +#define SCR_ENAS0 (1ULL << 36) +#define SCR_ADEN (1ULL << 37) +#define SCR_HXEN (1ULL << 38) +#define SCR_TRNDR (1ULL << 40) +#define SCR_ENTP2 (1ULL << 41) +#define SCR_GPF (1ULL << 48) #define HSTR_TTEE (1 << 16) #define HSTR_TJDBX (1 << 17) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Update SCTLR_ELx fields per ARM DDI0487 H.a. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define SCTLR_ATA0 (1ULL << 42) /* v8.5-MemTag */ #define SCTLR_ATA (1ULL << 43) /* v8.5-MemTag */ #define SCTLR_DSSBS_64 (1ULL << 44) /* v8.5, AArch64 only */ +#define SCTLR_TWEDEn (1ULL << 45) /* FEAT_TWED */ +#define SCTLR_TWEDEL MAKE_64_MASK(46, 4) /* FEAT_TWED */ +#define SCTLR_TMT0 (1ULL << 50) /* FEAT_TME */ +#define SCTLR_TMT (1ULL << 51) /* FEAT_TME */ +#define SCTLR_TME0 (1ULL << 52) /* FEAT_TME */ +#define SCTLR_TME (1ULL << 53) /* FEAT_TME */ +#define SCTLR_EnASR (1ULL << 54) /* FEAT_LS64_V */ +#define SCTLR_EnAS0 (1ULL << 55) /* FEAT_LS64_ACCDATA */ +#define SCTLR_EnALS (1ULL << 56) /* FEAT_LS64 */ +#define SCTLR_EPAN (1ULL << 57) /* FEAT_PAN3 */ +#define SCTLR_EnTP2 (1ULL << 60) /* FEAT_SME */ +#define SCTLR_NMI (1ULL << 61) /* FEAT_NMI */ +#define SCTLR_SPINTMASK (1ULL << 62) /* FEAT_NMI */ +#define SCTLR_TIDCP (1ULL << 63) /* FEAT_TIDCP1 */ #define CPTR_TCPAC (1U << 31) #define CPTR_TTA (1U << 20) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Bool is a more appropriate type for this value. Move the member down in the struct to keep the bool type members together and remove a hole. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 2 +- target/arm/translate-a64.c | 2 +- target/arm/translate.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { * so that top level loop can generate correct syndrome information. */ uint32_t svc_imm; - int aarch64; int current_el; /* Debug target exception level for single-step exceptions */ int debug_target_el; GHashTable *cp_regs; uint64_t features; /* CPU features bits */ + bool aarch64; /* Because unallocated encodings generate different exception syndrome * information from traps due to FP being disabled, we can't do a single * "is fp access disabled" check at a high level in the decode tree. diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->isar = &arm_cpu->isar; dc->condjmp = 0; - dc->aarch64 = 1; + dc->aarch64 = true; /* If we are coming from secure EL0 in a system with a 32-bit EL3, then * there is no secure EL1, so we route exceptions to EL3. */ diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) dc->isar = &cpu->isar; dc->condjmp = 0; - dc->aarch64 = 0; + dc->aarch64 = false; /* If we are coming from secure EL0 in a system with a 32-bit EL3, then * there is no secure EL1, so we route exceptions to EL3. */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Bool is a more appropriate type for this value. Adjust the assignments to use true/false. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 +- target/arm/cpu.c | 2 +- target/arm/helper-a64.c | 4 ++-- target/arm/helper.c | 2 +- target/arm/hvf/hvf.c | 2 +- 5 files changed, 6 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 @@ typedef struct CPUArchState { * all other bits are stored in their correct places in env->pstate */ uint32_t pstate; - uint32_t aarch64; /* 1 if CPU is in aarch64 state; inverse of PSTATE.nRW */ + bool aarch64; /* True if CPU is in aarch64 state; inverse of PSTATE.nRW */ /* Cached TBFLAGS state. See below for which bits are included. */ CPUARMTBFlags hflags; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(DeviceState *dev) if (arm_feature(env, ARM_FEATURE_AARCH64)) { /* 64 bit CPUs always start in 64 bit mode */ - env->aarch64 = 1; + env->aarch64 = true; #if defined(CONFIG_USER_ONLY) env->pstate = PSTATE_MODE_EL0t; /* Userspace expects access to DC ZVA, CTL_EL0 and the cache ops */ diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ void HELPER(exception_return)(CPUARMState *env, uint64_t new_pc) qemu_mutex_unlock_iothread(); if (!return_to_aa64) { - env->aarch64 = 0; + env->aarch64 = false; /* We do a raw CPSR write because aarch64_sync_64_to_32() * will sort the register banks out for us, and we've already * caught all the bad-mode cases in el_from_spsr(). @@ -XXX,XX +XXX,XX @@ void HELPER(exception_return)(CPUARMState *env, uint64_t new_pc) } else { int tbii; - env->aarch64 = 1; + env->aarch64 = true; spsr &= aarch64_pstate_valid_mask(&env_archcpu(env)->isar); pstate_write(env, spsr); if (!arm_singlestep_active(env)) { 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 arm_cpu_do_interrupt_aarch64(CPUState *cs) } pstate_write(env, PSTATE_DAIF | new_mode); - env->aarch64 = 1; + env->aarch64 = true; aarch64_restore_sp(env, new_el); helper_rebuild_hflags_a64(env, new_el); diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/hvf/hvf.c +++ b/target/arm/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ int hvf_arch_init_vcpu(CPUState *cpu) hv_return_t ret; int i; - env->aarch64 = 1; + env->aarch64 = true; asm volatile("mrs %0, cntfrq_el0" : "=r"(arm_cpu->gt_cntfrq_hz)); /* Allocate enough space for our sysreg sync */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Currently we assume all fields are 32-bit. Prepare for fields of a single byte, using sizeof_field(). Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: use sizeof_field() instead of raw sizeof()] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a32.h | 13 +++++-------- target/arm/translate.c | 21 ++++++++++++++++++++- 2 files changed, 25 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 load_cpu_offset(int offset) #define load_cpu_field(name) load_cpu_offset(offsetof(CPUARMState, name)) -static inline void store_cpu_offset(TCGv_i32 var, int offset) -{ - tcg_gen_st_i32(var, cpu_env, offset); - tcg_temp_free_i32(var); -} +void store_cpu_offset(TCGv_i32 var, int offset, int size); -#define store_cpu_field(var, name) \ - store_cpu_offset(var, offsetof(CPUARMState, name)) +#define store_cpu_field(var, name) \ + store_cpu_offset(var, offsetof(CPUARMState, name), \ + sizeof_field(CPUARMState, name)) #define store_cpu_field_constant(val, name) \ - tcg_gen_st_i32(tcg_constant_i32(val), cpu_env, offsetof(CPUARMState, name)) + store_cpu_field(tcg_constant_i32(val), name) /* Create a new temporary and set it to the value of a CPU register. */ static inline TCGv_i32 load_reg(DisasContext *s, int reg) 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 @@ typedef enum ISSInfo { ISSIs16Bit = (1 << 8), } ISSInfo; +/* + * Store var into env + offset to a member with size bytes. + * Free var after use. + */ +void store_cpu_offset(TCGv_i32 var, int offset, int size) +{ + switch (size) { + case 1: + tcg_gen_st8_i32(var, cpu_env, offset); + break; + case 4: + tcg_gen_st_i32(var, cpu_env, offset); + break; + default: + g_assert_not_reached(); + } + tcg_temp_free_i32(var); +} + /* Save the syndrome information for a Data Abort */ static void disas_set_da_iss(DisasContext *s, MemOp memop, ISSInfo issinfo) { @@ -XXX,XX +XXX,XX @@ static void do_coproc_insn(DisasContext *s, int cpnum, int is64, tcg_temp_free_i32(tmp); } else { TCGv_i32 tmp = load_reg(s, rt); - store_cpu_offset(tmp, ri->fieldoffset); + store_cpu_offset(tmp, ri->fieldoffset, 4); } } } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Bool is a more appropriate type for this value. Move the member down in the struct to keep the bool type members together and remove a hole. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 2 +- target/arm/translate-a64.c | 2 +- 2 files changed, 2 insertions(+), 2 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 struct DisasContext { bool eci_handled; /* TCG op to rewind to if this turns out to be an invalid ECI state */ TCGOp *insn_eci_rewind; - int thumb; int sctlr_b; MemOp be_data; #if !defined(CONFIG_USER_ONLY) @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { GHashTable *cp_regs; uint64_t features; /* CPU features bits */ bool aarch64; + bool thumb; /* Because unallocated encodings generate different exception syndrome * information from traps due to FP being disabled, we can't do a single * "is fp access disabled" check at a high level in the decode tree. diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, */ dc->secure_routed_to_el3 = arm_feature(env, ARM_FEATURE_EL3) && !arm_el_is_aa64(env, 3); - dc->thumb = 0; + dc->thumb = false; dc->sctlr_b = 0; dc->be_data = EX_TBFLAG_ANY(tb_flags, BE_DATA) ? MO_BE : MO_LE; dc->condexec_mask = 0; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Bool is a more appropriate type for this value. Adjust the assignments to use true/false. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 +- linux-user/arm/cpu_loop.c | 2 +- target/arm/cpu.c | 2 +- target/arm/m_helper.c | 6 +++--- 4 files changed, 6 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 @@ typedef struct CPUArchState { */ uint32_t pstate; bool aarch64; /* True if CPU is in aarch64 state; inverse of PSTATE.nRW */ + bool thumb; /* True if CPU is in thumb mode; cpsr[5] */ /* Cached TBFLAGS state. See below for which bits are included. */ CPUARMTBFlags hflags; @@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState { uint32_t ZF; /* Z set if zero. */ uint32_t QF; /* 0 or 1 */ uint32_t GE; /* cpsr[19:16] */ - uint32_t thumb; /* cpsr[5]. 0 = arm mode, 1 = thumb mode. */ uint32_t condexec_bits; /* IT bits. cpsr[15:10,26:25]. */ uint32_t btype; /* BTI branch type. spsr[11:10]. */ uint64_t daif; /* exception masks, in the bits they are in PSTATE */ diff --git a/linux-user/arm/cpu_loop.c b/linux-user/arm/cpu_loop.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/arm/cpu_loop.c +++ b/linux-user/arm/cpu_loop.c @@ -XXX,XX +XXX,XX @@ do_kernel_trap(CPUARMState *env) /* Jump back to the caller. */ addr = env->regs[14]; if (addr & 1) { - env->thumb = 1; + env->thumb = true; addr &= ~1; } env->regs[15] = addr; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_set_pc(CPUState *cs, vaddr value) if (is_a64(env)) { env->pc = value; - env->thumb = 0; + env->thumb = false; } else { env->regs[15] = value & ~1; env->thumb = value & 1; diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_bxns)(CPUARMState *env, uint32_t dest) env->v7m.control[M_REG_S] &= ~R_V7M_CONTROL_SFPA_MASK; } switch_v7m_security_state(env, dest & 1); - env->thumb = 1; + env->thumb = true; env->regs[15] = dest & ~1; arm_rebuild_hflags(env); } @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) * except that the low bit doesn't indicate Thumb/not. */ env->regs[14] = nextinst; - env->thumb = 1; + env->thumb = true; env->regs[15] = dest & ~1; return; } @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) } env->v7m.control[M_REG_S] &= ~R_V7M_CONTROL_SFPA_MASK; switch_v7m_security_state(env, 0); - env->thumb = 1; + env->thumb = true; env->regs[15] = dest; arm_rebuild_hflags(env); } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This function is incorrect in that it does not properly consider CPTR_EL2.FPEN. We've already got another mechanism for raising an FPU access trap: ARM_CP_FPU, so use that instead. Remove CP_ACCESS_TRAP_FP_EL{2,3}, which becomes unused. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 5 ----- target/arm/helper.c | 17 ++--------------- target/arm/op_helper.c | 13 ------------- 3 files changed, 2 insertions(+), 33 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef enum CPAccessResult { /* As CP_ACCESS_UNCATEGORIZED, but for traps directly to EL2 or EL3 */ CP_ACCESS_TRAP_UNCATEGORIZED_EL2 = 5, CP_ACCESS_TRAP_UNCATEGORIZED_EL3 = 6, - /* Access fails and results in an exception syndrome for an FP access, - * trapped directly to EL2 or EL3 - */ - CP_ACCESS_TRAP_FP_EL2 = 7, - CP_ACCESS_TRAP_FP_EL3 = 8, } CPAccessResult; /* Access functions for coprocessor registers. These cannot fail and diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void sctlr_write(CPUARMState *env, const ARMCPRegInfo *ri, } } -static CPAccessResult fpexc32_access(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread) -{ - if ((env->cp15.cptr_el[2] & CPTR_TFP) && arm_current_el(env) == 2) { - return CP_ACCESS_TRAP_FP_EL2; - } - if (env->cp15.cptr_el[3] & CPTR_TFP) { - return CP_ACCESS_TRAP_FP_EL3; - } - return CP_ACCESS_OK; -} - static void sdcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v8_cp_reginfo[] = { .access = PL1_RW, .readfn = spsel_read, .writefn = spsel_write }, { .name = "FPEXC32_EL2", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 4, .crn = 5, .crm = 3, .opc2 = 0, - .type = ARM_CP_ALIAS, - .fieldoffset = offsetof(CPUARMState, vfp.xregs[ARM_VFP_FPEXC]), - .access = PL2_RW, .accessfn = fpexc32_access }, + .access = PL2_RW, .type = ARM_CP_ALIAS | ARM_CP_FPU, + .fieldoffset = offsetof(CPUARMState, vfp.xregs[ARM_VFP_FPEXC]) }, { .name = "DACR32_EL2", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 4, .crn = 3, .crm = 0, .opc2 = 0, .access = PL2_RW, .resetvalue = 0, diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(access_check_cp_reg)(CPUARMState *env, void *rip, uint32_t syndrome, target_el = 3; syndrome = syn_uncategorized(); break; - case CP_ACCESS_TRAP_FP_EL2: - target_el = 2; - /* Since we are an implementation that takes exceptions on a trapped - * conditional insn only if the insn has passed its condition code - * check, we take the IMPDEF choice to always report CV=1 COND=0xe - * (which is also the required value for AArch64 traps). - */ - syndrome = syn_fp_access_trap(1, 0xe, false); - break; - case CP_ACCESS_TRAP_FP_EL3: - target_el = 3; - syndrome = syn_fp_access_trap(1, 0xe, false); - break; default: g_assert_not_reached(); } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Common code for reset_btype and set_btype. Use tcg_constant_i32. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static int get_a64_user_mem_index(DisasContext *s) return arm_to_core_mmu_idx(useridx); } -static void reset_btype(DisasContext *s) +static void set_btype_raw(int val) { - if (s->btype != 0) { - TCGv_i32 zero = tcg_const_i32(0); - tcg_gen_st_i32(zero, cpu_env, offsetof(CPUARMState, btype)); - tcg_temp_free_i32(zero); - s->btype = 0; - } + tcg_gen_st_i32(tcg_constant_i32(val), cpu_env, + offsetof(CPUARMState, btype)); } static void set_btype(DisasContext *s, int val) { - TCGv_i32 tcg_val; - /* BTYPE is a 2-bit field, and 0 should be done with reset_btype. */ tcg_debug_assert(val >= 1 && val <= 3); - - tcg_val = tcg_const_i32(val); - tcg_gen_st_i32(tcg_val, cpu_env, offsetof(CPUARMState, btype)); - tcg_temp_free_i32(tcg_val); + set_btype_raw(val); s->btype = -1; } +static void reset_btype(DisasContext *s) +{ + if (s->btype != 0) { + set_btype_raw(0); + s->btype = 0; + } +} + void gen_a64_set_pc_im(uint64_t val) { tcg_gen_movi_i64(cpu_pc, val); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> For aa32, the function has a parameter to use the new el. For aa64, that never happens. Use tcg_constant_i32 while we're at it. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 21 +++++++++----------- target/arm/translate.c | 40 +++++++++++++++++++++++--------------- 2 files changed, 33 insertions(+), 28 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void a64_free_cc(DisasCompare64 *c64) tcg_temp_free_i64(c64->value); } +static void gen_rebuild_hflags(DisasContext *s) +{ + gen_helper_rebuild_hflags_a64(cpu_env, tcg_constant_i32(s->current_el)); +} + static void gen_exception_internal(int excp) { TCGv_i32 tcg_excp = tcg_const_i32(excp); @@ -XXX,XX +XXX,XX @@ static void handle_msr_i(DisasContext *s, uint32_t insn, } else { clear_pstate_bits(PSTATE_UAO); } - t1 = tcg_const_i32(s->current_el); - gen_helper_rebuild_hflags_a64(cpu_env, t1); - tcg_temp_free_i32(t1); + gen_rebuild_hflags(s); break; case 0x04: /* PAN */ @@ -XXX,XX +XXX,XX @@ static void handle_msr_i(DisasContext *s, uint32_t insn, } else { clear_pstate_bits(PSTATE_PAN); } - t1 = tcg_const_i32(s->current_el); - gen_helper_rebuild_hflags_a64(cpu_env, t1); - tcg_temp_free_i32(t1); + gen_rebuild_hflags(s); break; case 0x05: /* SPSel */ @@ -XXX,XX +XXX,XX @@ static void handle_msr_i(DisasContext *s, uint32_t insn, } else { clear_pstate_bits(PSTATE_TCO); } - t1 = tcg_const_i32(s->current_el); - gen_helper_rebuild_hflags_a64(cpu_env, t1); - tcg_temp_free_i32(t1); + gen_rebuild_hflags(s); /* Many factors, including TCO, go into MTE_ACTIVE. */ s->base.is_jmp = DISAS_UPDATE_NOCHAIN; } else if (dc_isar_feature(aa64_mte_insn_reg, s)) { @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, * A write to any coprocessor regiser that ends a TB * must rebuild the hflags for the next TB. */ - TCGv_i32 tcg_el = tcg_const_i32(s->current_el); - gen_helper_rebuild_hflags_a64(cpu_env, tcg_el); - tcg_temp_free_i32(tcg_el); + gen_rebuild_hflags(s); /* * We default to ending the TB on a coprocessor register write, * but allow this to be suppressed by the register definition diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ void gen_set_cpsr(TCGv_i32 var, uint32_t mask) tcg_temp_free_i32(tmp_mask); } +static void gen_rebuild_hflags(DisasContext *s, bool new_el) +{ + bool m_profile = arm_dc_feature(s, ARM_FEATURE_M); + + if (new_el) { + if (m_profile) { + gen_helper_rebuild_hflags_m32_newel(cpu_env); + } else { + gen_helper_rebuild_hflags_a32_newel(cpu_env); + } + } else { + TCGv_i32 tcg_el = tcg_constant_i32(s->current_el); + if (m_profile) { + gen_helper_rebuild_hflags_m32(cpu_env, tcg_el); + } else { + gen_helper_rebuild_hflags_a32(cpu_env, tcg_el); + } + } +} + static void gen_exception_internal(int excp) { TCGv_i32 tcg_excp = tcg_const_i32(excp); @@ -XXX,XX +XXX,XX @@ static void do_coproc_insn(DisasContext *s, int cpnum, int is64, * A write to any coprocessor register that ends a TB * must rebuild the hflags for the next TB. */ - TCGv_i32 tcg_el = tcg_const_i32(s->current_el); - if (arm_dc_feature(s, ARM_FEATURE_M)) { - gen_helper_rebuild_hflags_m32(cpu_env, tcg_el); - } else { - if (ri->type & ARM_CP_NEWEL) { - gen_helper_rebuild_hflags_a32_newel(cpu_env); - } else { - gen_helper_rebuild_hflags_a32(cpu_env, tcg_el); - } - } - tcg_temp_free_i32(tcg_el); + gen_rebuild_hflags(s, ri->type & ARM_CP_NEWEL); /* * We default to ending the TB on a coprocessor register write, * but allow this to be suppressed by the register definition @@ -XXX,XX +XXX,XX @@ static bool trans_MSR_v7m(DisasContext *s, arg_MSR_v7m *a) tcg_temp_free_i32(addr); tcg_temp_free_i32(reg); /* If we wrote to CONTROL, the EL might have changed */ - gen_helper_rebuild_hflags_m32_newel(cpu_env); + gen_rebuild_hflags(s, true); gen_lookup_tb(s); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_CPS(DisasContext *s, arg_CPS *a) static bool trans_CPS_v7m(DisasContext *s, arg_CPS_v7m *a) { - TCGv_i32 tmp, addr, el; + TCGv_i32 tmp, addr; if (!arm_dc_feature(s, ARM_FEATURE_M)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_CPS_v7m(DisasContext *s, arg_CPS_v7m *a) gen_helper_v7m_msr(cpu_env, addr, tmp); tcg_temp_free_i32(addr); } - el = tcg_const_i32(s->current_el); - gen_helper_rebuild_hflags_m32(cpu_env, el); - tcg_temp_free_i32(el); + gen_rebuild_hflags(s, false); tcg_temp_free_i32(tmp); gen_lookup_tb(s); return true; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Instead of computing tmp1 = shift & 0xff; dest = (tmp1 > 0x1f ? 0 : value) << (tmp1 & 0x1f) use tmpd = value << (shift & 0x1f); dest = shift & 0xe0 ? 0 : tmpd; which has a flatter dependency tree. Use tcg_constant_i32 while we're at it. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_sbc_CC(TCGv_i32 dest, TCGv_i32 t0, TCGv_i32 t1) #define GEN_SHIFT(name) \ static void gen_##name(TCGv_i32 dest, TCGv_i32 t0, TCGv_i32 t1) \ { \ - TCGv_i32 tmp1, tmp2, tmp3; \ - tmp1 = tcg_temp_new_i32(); \ - tcg_gen_andi_i32(tmp1, t1, 0xff); \ - tmp2 = tcg_const_i32(0); \ - tmp3 = tcg_const_i32(0x1f); \ - tcg_gen_movcond_i32(TCG_COND_GTU, tmp2, tmp1, tmp3, tmp2, t0); \ - tcg_temp_free_i32(tmp3); \ - tcg_gen_andi_i32(tmp1, tmp1, 0x1f); \ - tcg_gen_##name##_i32(dest, tmp2, tmp1); \ - tcg_temp_free_i32(tmp2); \ + TCGv_i32 tmpd = tcg_temp_new_i32(); \ + TCGv_i32 tmp1 = tcg_temp_new_i32(); \ + TCGv_i32 zero = tcg_constant_i32(0); \ + tcg_gen_andi_i32(tmp1, t1, 0x1f); \ + tcg_gen_##name##_i32(tmpd, t0, tmp1); \ + tcg_gen_andi_i32(tmp1, t1, 0xe0); \ + tcg_gen_movcond_i32(TCG_COND_NE, dest, tmp1, zero, zero, tmpd); \ + tcg_temp_free_i32(tmpd); \ tcg_temp_free_i32(tmp1); \ } GEN_SHIFT(shl) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Use tcg_gen_umin_i32 instead of tcg_gen_movcond_i32. Use tcg_constant_i32 while we're at it. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 8 +++----- 1 file changed, 3 insertions(+), 5 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 @@ GEN_SHIFT(shr) static void gen_sar(TCGv_i32 dest, TCGv_i32 t0, TCGv_i32 t1) { - TCGv_i32 tmp1, tmp2; - tmp1 = tcg_temp_new_i32(); + TCGv_i32 tmp1 = tcg_temp_new_i32(); + tcg_gen_andi_i32(tmp1, t1, 0xff); - tmp2 = tcg_const_i32(0x1f); - tcg_gen_movcond_i32(TCG_COND_GTU, tmp1, tmp1, tmp2, tmp2, tmp1); - tcg_temp_free_i32(tmp2); + tcg_gen_umin_i32(tmp1, tmp1, tcg_constant_i32(31)); tcg_gen_sar_i32(dest, t0, tmp1); tcg_temp_free_i32(tmp1); } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> The length of the previous insn may be computed from the difference of start and end addresses. Use tcg_constant_i32 while we're at it. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 12 ++++-------- 1 file changed, 4 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 void arm_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu) /* nothing more to generate */ break; case DISAS_WFI: - { - TCGv_i32 tmp = tcg_const_i32((dc->thumb && - !(dc->insn & (1U << 31))) ? 2 : 4); - - gen_helper_wfi(cpu_env, tmp); - tcg_temp_free_i32(tmp); - /* The helper doesn't necessarily throw an exception, but we + gen_helper_wfi(cpu_env, + tcg_constant_i32(dc->base.pc_next - dc->pc_curr)); + /* + * The helper doesn't necessarily throw an exception, but we * must go back to the main loop to check for interrupts anyway. */ tcg_gen_exit_tb(NULL, 0); break; - } case DISAS_WFE: gen_helper_wfe(cpu_env); break; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Use tcg_constant_{i32,i64} as appropriate throughout. This fixes a bug in trans_VSCCLRM() where we were leaking a TCGv. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-m-nocp.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/target/arm/translate-m-nocp.c b/target/arm/translate-m-nocp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-m-nocp.c +++ b/target/arm/translate-m-nocp.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSCCLRM(DisasContext *s, arg_VSCCLRM *a) } /* Zero the Sregs from btmreg to topreg inclusive. */ - zero = tcg_const_i64(0); + zero = tcg_constant_i64(0); if (btmreg & 1) { write_neon_element64(zero, btmreg >> 1, 1, MO_32); btmreg++; @@ -XXX,XX +XXX,XX @@ static bool trans_VSCCLRM(DisasContext *s, arg_VSCCLRM *a) } assert(btmreg == topreg + 1); if (dc_isar_feature(aa32_mve, s)) { - TCGv_i32 z32 = tcg_const_i32(0); - store_cpu_field(z32, v7m.vpr); + store_cpu_field(tcg_constant_i32(0), v7m.vpr); } clear_eci_state(s); @@ -XXX,XX +XXX,XX @@ static bool gen_M_fp_sysreg_read(DisasContext *s, int regno, } case ARM_VFP_FPCXT_NS: { - TCGv_i32 control, sfpa, fpscr, fpdscr, zero; + TCGv_i32 control, sfpa, fpscr, fpdscr; TCGLabel *lab_active = gen_new_label(); lookup_tb = true; @@ -XXX,XX +XXX,XX @@ static bool gen_M_fp_sysreg_read(DisasContext *s, int regno, storefn(s, opaque, tmp, true); /* If SFPA is zero then set FPSCR from FPDSCR_NS */ fpdscr = load_cpu_field(v7m.fpdscr[M_REG_NS]); - zero = tcg_const_i32(0); - tcg_gen_movcond_i32(TCG_COND_EQ, fpscr, sfpa, zero, fpdscr, fpscr); + tcg_gen_movcond_i32(TCG_COND_EQ, fpscr, sfpa, tcg_constant_i32(0), + fpdscr, fpscr); gen_helper_vfp_set_fpscr(cpu_env, fpscr); - tcg_temp_free_i32(zero); tcg_temp_free_i32(sfpa); tcg_temp_free_i32(fpdscr); tcg_temp_free_i32(fpscr); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Use tcg_constant_{i32,i64} as appropriate throughout. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-neon.c | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c +++ b/target/arm/translate-neon.c @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a) int mmu_idx = get_mem_index(s); int size = a->size; TCGv_i64 tmp64; - TCGv_i32 addr, tmp; + TCGv_i32 addr; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a) tmp64 = tcg_temp_new_i64(); addr = tcg_temp_new_i32(); - tmp = tcg_const_i32(1 << size); load_reg_var(s, addr, a->rn); mop = endian | size | align; @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a) neon_load_element64(tmp64, tt, n, size); gen_aa32_st_internal_i64(s, tmp64, addr, mmu_idx, mop); } - tcg_gen_add_i32(addr, addr, tmp); + tcg_gen_addi_i32(addr, addr, 1 << size); /* Subsequent memory operations inherit alignment */ mop &= ~MO_AMASK; @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a) } } 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); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a, * To avoid excessive duplication of ops we implement shift * by immediate using the variable shift operations. */ - constimm = tcg_const_i64(dup_const(a->size, a->shift)); + constimm = tcg_constant_i64(dup_const(a->size, a->shift)); for (pass = 0; pass < a->q + 1; pass++) { TCGv_i64 tmp = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a, write_neon_element64(tmp, a->vd, pass, MO_64); tcg_temp_free_i64(tmp); } - tcg_temp_free_i64(constimm); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a, * To avoid excessive duplication of ops we implement shift * by immediate using the variable shift operations. */ - constimm = tcg_const_i32(dup_const(a->size, a->shift)); + constimm = tcg_constant_i32(dup_const(a->size, a->shift)); tmp = tcg_temp_new_i32(); for (pass = 0; pass < (a->q ? 4 : 2); pass++) { @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_32(DisasContext *s, arg_2reg_shift *a, write_neon_element32(tmp, a->vd, pass, MO_32); } tcg_temp_free_i32(tmp); - tcg_temp_free_i32(constimm); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a, * This is always a right shift, and the shiftfn is always a * left-shift helper, which thus needs the negated shift count. */ - constimm = tcg_const_i64(-a->shift); + constimm = tcg_constant_i64(-a->shift); rm1 = tcg_temp_new_i64(); rm2 = tcg_temp_new_i64(); rd = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_64(DisasContext *s, arg_2reg_shift *a, tcg_temp_free_i32(rd); tcg_temp_free_i64(rm1); tcg_temp_free_i64(rm2); - tcg_temp_free_i64(constimm); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a, /* size == 2 */ imm = -a->shift; } - constimm = tcg_const_i32(imm); + constimm = tcg_constant_i32(imm); /* Load all inputs first to avoid potential overwrite */ rm1 = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static bool do_2shift_narrow_32(DisasContext *s, arg_2reg_shift *a, shiftfn(rm3, rm3, constimm); shiftfn(rm4, rm4, constimm); - tcg_temp_free_i32(constimm); tcg_gen_concat_i32_i64(rtmp, rm3, rm4); tcg_temp_free_i32(rm4); @@ -XXX,XX +XXX,XX @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a) return true; } - desc = tcg_const_i32((a->vn << 2) | a->len); + desc = tcg_constant_i32((a->vn << 2) | a->len); def = tcg_temp_new_i64(); if (a->op) { read_neon_element64(def, a->vd, 0, MO_64); @@ -XXX,XX +XXX,XX @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a) tcg_temp_free_i64(def); tcg_temp_free_i64(val); - tcg_temp_free_i32(desc); return true; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> The operation we're performing with the movcond is either min/max depending on cond -- simplify. Use tcg_constant_i64 while we're at it. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_PNEXT(DisasContext *s, arg_rr_esz *a) static void do_sat_addsub_32(TCGv_i64 reg, TCGv_i64 val, bool u, bool d) { int64_t ibound; - TCGv_i64 bound; - TCGCond cond; /* Use normal 64-bit arithmetic to detect 32-bit overflow. */ if (u) { @@ -XXX,XX +XXX,XX @@ static void do_sat_addsub_32(TCGv_i64 reg, TCGv_i64 val, bool u, bool d) if (d) { tcg_gen_sub_i64(reg, reg, val); ibound = (u ? 0 : INT32_MIN); - cond = TCG_COND_LT; + tcg_gen_smax_i64(reg, reg, tcg_constant_i64(ibound)); } else { tcg_gen_add_i64(reg, reg, val); ibound = (u ? UINT32_MAX : INT32_MAX); - cond = TCG_COND_GT; + tcg_gen_smin_i64(reg, reg, tcg_constant_i64(ibound)); } - bound = tcg_const_i64(ibound); - tcg_gen_movcond_i64(cond, reg, reg, bound, bound, reg); - tcg_temp_free_i64(bound); } /* Similarly with 64-bit values. */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Use tcg_constant_{i32,i64} as appropriate throughout. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-vfp.c | 76 ++++++++++++-------------------------- 1 file changed, 23 insertions(+), 53 deletions(-) diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c +++ b/target/arm/translate-vfp.c @@ -XXX,XX +XXX,XX @@ static void gen_update_fp_context(DisasContext *s) gen_helper_vfp_set_fpscr(cpu_env, fpscr); tcg_temp_free_i32(fpscr); if (dc_isar_feature(aa32_mve, s)) { - TCGv_i32 z32 = tcg_const_i32(0); - store_cpu_field(z32, v7m.vpr); + store_cpu_field(tcg_constant_i32(0), v7m.vpr); } /* * We just updated the FPSCR and VPR. Some of this state is cached @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) TCGv_i64 frn, frm, dest; TCGv_i64 tmp, zero, zf, nf, vf; - zero = tcg_const_i64(0); + zero = tcg_constant_i64(0); frn = tcg_temp_new_i64(); frm = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) vfp_load_reg64(frm, rm); switch (a->cc) { case 0: /* eq: Z */ - tcg_gen_movcond_i64(TCG_COND_EQ, dest, zf, zero, - frn, frm); + tcg_gen_movcond_i64(TCG_COND_EQ, dest, zf, zero, frn, frm); break; case 1: /* vs: V */ - tcg_gen_movcond_i64(TCG_COND_LT, dest, vf, zero, - frn, frm); + tcg_gen_movcond_i64(TCG_COND_LT, dest, vf, zero, frn, frm); break; case 2: /* ge: N == V -> N ^ V == 0 */ tmp = tcg_temp_new_i64(); tcg_gen_xor_i64(tmp, vf, nf); - tcg_gen_movcond_i64(TCG_COND_GE, dest, tmp, zero, - frn, frm); + tcg_gen_movcond_i64(TCG_COND_GE, dest, tmp, zero, frn, frm); tcg_temp_free_i64(tmp); break; case 3: /* gt: !Z && N == V */ - tcg_gen_movcond_i64(TCG_COND_NE, dest, zf, zero, - frn, frm); + tcg_gen_movcond_i64(TCG_COND_NE, dest, zf, zero, frn, frm); tmp = tcg_temp_new_i64(); tcg_gen_xor_i64(tmp, vf, nf); - tcg_gen_movcond_i64(TCG_COND_GE, dest, tmp, zero, - dest, frm); + tcg_gen_movcond_i64(TCG_COND_GE, dest, tmp, zero, dest, frm); tcg_temp_free_i64(tmp); break; } @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) tcg_temp_free_i64(zf); tcg_temp_free_i64(nf); tcg_temp_free_i64(vf); - - tcg_temp_free_i64(zero); } else { TCGv_i32 frn, frm, dest; TCGv_i32 tmp, zero; - zero = tcg_const_i32(0); + zero = tcg_constant_i32(0); frn = tcg_temp_new_i32(); frm = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) vfp_load_reg32(frm, rm); switch (a->cc) { case 0: /* eq: Z */ - tcg_gen_movcond_i32(TCG_COND_EQ, dest, cpu_ZF, zero, - frn, frm); + tcg_gen_movcond_i32(TCG_COND_EQ, dest, cpu_ZF, zero, frn, frm); break; case 1: /* vs: V */ - tcg_gen_movcond_i32(TCG_COND_LT, dest, cpu_VF, zero, - frn, frm); + tcg_gen_movcond_i32(TCG_COND_LT, dest, cpu_VF, zero, frn, frm); break; case 2: /* ge: N == V -> N ^ V == 0 */ tmp = tcg_temp_new_i32(); tcg_gen_xor_i32(tmp, cpu_VF, cpu_NF); - tcg_gen_movcond_i32(TCG_COND_GE, dest, tmp, zero, - frn, frm); + tcg_gen_movcond_i32(TCG_COND_GE, dest, tmp, zero, frn, frm); tcg_temp_free_i32(tmp); break; case 3: /* gt: !Z && N == V */ - tcg_gen_movcond_i32(TCG_COND_NE, dest, cpu_ZF, zero, - frn, frm); + tcg_gen_movcond_i32(TCG_COND_NE, dest, cpu_ZF, zero, frn, frm); tmp = tcg_temp_new_i32(); tcg_gen_xor_i32(tmp, cpu_VF, cpu_NF); - tcg_gen_movcond_i32(TCG_COND_GE, dest, tmp, zero, - dest, frm); + tcg_gen_movcond_i32(TCG_COND_GE, dest, tmp, zero, dest, frm); tcg_temp_free_i32(tmp); break; } @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) tcg_temp_free_i32(frn); tcg_temp_free_i32(frm); tcg_temp_free_i32(dest); - - tcg_temp_free_i32(zero); } return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) fpst = fpstatus_ptr(FPST_FPCR); } - tcg_shift = tcg_const_i32(0); + tcg_shift = tcg_constant_i32(0); tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rounding)); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); tcg_temp_free_i32(tcg_rmode); - tcg_temp_free_i32(tcg_shift); - tcg_temp_free_ptr(fpst); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) case ARM_VFP_MVFR2: case ARM_VFP_FPSID: if (s->current_el == 1) { - TCGv_i32 tcg_reg, tcg_rt; - gen_set_condexec(s); gen_set_pc_im(s, s->pc_curr); - tcg_reg = tcg_const_i32(a->reg); - tcg_rt = tcg_const_i32(a->rt); - gen_helper_check_hcr_el2_trap(cpu_env, tcg_rt, tcg_reg); - tcg_temp_free_i32(tcg_reg); - tcg_temp_free_i32(tcg_rt); + gen_helper_check_hcr_el2_trap(cpu_env, + tcg_constant_i32(a->rt), + tcg_constant_i32(a->reg)); } /* fall through */ case ARM_VFP_FPEXC: @@ -XXX,XX +XXX,XX @@ MAKE_VFM_TRANS_FNS(dp) static bool trans_VMOV_imm_hp(DisasContext *s, arg_VMOV_imm_sp *a) { - TCGv_i32 fd; - if (!dc_isar_feature(aa32_fp16_arith, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_hp(DisasContext *s, arg_VMOV_imm_sp *a) return true; } - fd = tcg_const_i32(vfp_expand_imm(MO_16, a->imm)); - vfp_store_reg32(fd, a->vd); - tcg_temp_free_i32(fd); + vfp_store_reg32(tcg_constant_i32(vfp_expand_imm(MO_16, a->imm)), a->vd); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a) } } - fd = tcg_const_i32(vfp_expand_imm(MO_32, a->imm)); + fd = tcg_constant_i32(vfp_expand_imm(MO_32, a->imm)); for (;;) { vfp_store_reg32(fd, vd); @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a) vd = vfp_advance_sreg(vd, delta_d); } - tcg_temp_free_i32(fd); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) } } - fd = tcg_const_i64(vfp_expand_imm(MO_64, a->imm)); + fd = tcg_constant_i64(vfp_expand_imm(MO_64, a->imm)); for (;;) { vfp_store_reg64(fd, vd); @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) vd = vfp_advance_dreg(vd, delta_d); } - tcg_temp_free_i64(fd); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_hp(DisasContext *s, arg_VCVT_fix_sp *a) vfp_load_reg32(vd, a->vd); fpst = fpstatus_ptr(FPST_FPCR_F16); - shift = tcg_const_i32(frac_bits); + shift = tcg_constant_i32(frac_bits); /* Switch on op:U:sx bits */ switch (a->opc) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_hp(DisasContext *s, arg_VCVT_fix_sp *a) vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); - tcg_temp_free_i32(shift); tcg_temp_free_ptr(fpst); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a) vfp_load_reg32(vd, a->vd); fpst = fpstatus_ptr(FPST_FPCR); - shift = tcg_const_i32(frac_bits); + shift = tcg_constant_i32(frac_bits); /* Switch on op:U:sx bits */ switch (a->opc) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a) vfp_store_reg32(vd, a->vd); tcg_temp_free_i32(vd); - tcg_temp_free_i32(shift); tcg_temp_free_ptr(fpst); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) vfp_load_reg64(vd, a->vd); fpst = fpstatus_ptr(FPST_FPCR); - shift = tcg_const_i32(frac_bits); + shift = tcg_constant_i32(frac_bits); /* Switch on op:U:sx bits */ switch (a->opc) { @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) vfp_store_reg64(vd, a->vd); tcg_temp_free_i64(vd); - tcg_temp_free_i32(shift); tcg_temp_free_ptr(fpst); return true; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 13 +++---------- 1 file changed, 3 insertions(+), 10 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 @@ static inline void gen_ss_advance(DisasContext *s) static inline void gen_exception(int excp, uint32_t syndrome, uint32_t target_el) { - TCGv_i32 tcg_excp = tcg_const_i32(excp); - TCGv_i32 tcg_syn = tcg_const_i32(syndrome); - TCGv_i32 tcg_el = tcg_const_i32(target_el); - - gen_helper_exception_with_syndrome(cpu_env, tcg_excp, - tcg_syn, tcg_el); - - tcg_temp_free_i32(tcg_el); - tcg_temp_free_i32(tcg_syn); - tcg_temp_free_i32(tcg_excp); + gen_helper_exception_with_syndrome(cpu_env, tcg_constant_i32(excp), + tcg_constant_i32(syndrome), + tcg_constant_i32(target_el)); } /* Generate an architectural singlestep exception */ -- 2.25.1 From: Xiang Chen <chenxiang66@hisilicon.com> It always calls the IOMMU MR translate() callback with flag=IOMMU_NONE in memory_region_iommu_replay(). Currently, smmuv3_translate() return an IOMMUTLBEntry with perm set to IOMMU_NONE even if the translation success, whereas it is expected to return the actual permission set in the table entry. So pass the actual perm to returned IOMMUTLBEntry in the table entry. Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 1650094695-121918-1-git-send-email-chenxiang66@hisilicon.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/smmuv3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ epilogue: qemu_mutex_unlock(&s->mutex); switch (status) { case SMMU_TRANS_SUCCESS: - entry.perm = flag; + entry.perm = cached_entry->entry.perm; entry.translated_addr = cached_entry->entry.translated_addr + (addr & cached_entry->entry.addr_mask); entry.addr_mask = cached_entry->entry.addr_mask; -- 2.25.1