Arm stuff, mostly patches from RTH. thanks -- PMM The following changes since commit 01a9a51ffaf4699827ea6425cb2b834a356e159d: Merge remote-tracking branch 'remotes/kraxel/tags/ui-20190205-pull-request' into staging (2019-02-05 14:01:29 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20190205 for you to fetch changes up to a15945d98d3a3390c3da344d1b47218e91e49d8b: target/arm: Make FPSCR/FPCR trapped-exception bits RAZ/WI (2019-02-05 16:52:42 +0000) ---------------------------------------------------------------- target-arm queue: * Implement Armv8.5-BTI extension for system emulation mode * Implement the PR_PAC_RESET_KEYS prctl() for linux-user mode's Armv8.3-PAuth support * Support TBI (top-byte-ignore) properly for linux-user mode * gdbstub: allow killing QEMU via vKill command * hw/arm/boot: Support DTB autoload for firmware-only boots * target/arm: Make FPSCR/FPCR trapped-exception bits RAZ/WI ---------------------------------------------------------------- Max Filippov (1): gdbstub: allow killing QEMU via vKill command Peter Maydell (7): target/arm: Compute TB_FLAGS for TBI for user-only hw/arm/boot: Fix block comment style in arm_load_kernel() hw/arm/boot: Factor out "direct kernel boot" code into its own function hw/arm/boot: Factor out "set up firmware boot" code hw/arm/boot: Clarify why arm_setup_firmware_boot() doesn't set env->boot_info hw/arm/boot: Support DTB autoload for firmware-only boots target/arm: Make FPSCR/FPCR trapped-exception bits RAZ/WI Richard Henderson (14): target/arm: Introduce isar_feature_aa64_bti target/arm: Add PSTATE.BTYPE target/arm: Add BT and BTYPE to tb->flags exec: Add target-specific tlb bits to MemTxAttrs target/arm: Cache the GP bit for a page in MemTxAttrs target/arm: Default handling of BTYPE during translation target/arm: Reset btype for direct branches target/arm: Set btype for indirect branches target/arm: Enable BTI for -cpu max linux-user: Implement PR_PAC_RESET_KEYS tests/tcg/aarch64: Add pauth smoke test target/arm: Add TBFLAG_A64_TBID, split out gen_top_byte_ignore target/arm: Clean TBI for data operations in the translator target/arm: Enable TBI for user-only tests/tcg/aarch64/Makefile.target | 6 +- include/exec/memattrs.h | 10 + linux-user/aarch64/target_syscall.h | 7 + target/arm/cpu.h | 27 +- target/arm/internals.h | 27 +- target/arm/translate.h | 12 +- gdbstub.c | 4 + hw/arm/boot.c | 166 +++++++------ linux-user/syscall.c | 36 +++ target/arm/cpu.c | 6 + target/arm/cpu64.c | 4 + target/arm/helper.c | 80 +++--- target/arm/translate-a64.c | 476 +++++++++++++++++++++++++----------- tests/tcg/aarch64/pauth-1.c | 23 ++ 14 files changed, 623 insertions(+), 261 deletions(-) create mode 100644 tests/tcg/aarch64/pauth-1.c From: Richard Henderson <richard.henderson@linaro.org> Also create field definitions for id_aa64pfr1 from ARMv8.5. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190128223118.5255-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 10 ++++++++++ 1 file changed, 10 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_AA64PFR0, GIC, 24, 4) FIELD(ID_AA64PFR0, RAS, 28, 4) FIELD(ID_AA64PFR0, SVE, 32, 4) +FIELD(ID_AA64PFR1, BT, 0, 4) +FIELD(ID_AA64PFR1, SBSS, 4, 4) +FIELD(ID_AA64PFR1, MTE, 8, 4) +FIELD(ID_AA64PFR1, RAS_FRAC, 12, 4) + FIELD(ID_AA64MMFR0, PARANGE, 0, 4) FIELD(ID_AA64MMFR0, ASIDBITS, 4, 4) FIELD(ID_AA64MMFR0, BIGEND, 8, 4) @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_lor(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, LO) != 0; } +static inline bool isar_feature_aa64_bti(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0; +} + /* * Forward to the above feature tests given an ARMCPU pointer. */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Place this in its own field within ENV, as that will make it easier to reset from within TCG generated code. With the change to pstate_read/write, exception entry and return are automatically handled. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190128223118.5255-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 8 ++++++-- target/arm/translate-a64.c | 3 +++ 2 files changed, 9 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 @@ typedef struct CPUARMState { * semantics as for AArch32, as described in the comments on each field) * nRW (also known as M[4]) is kept, inverted, in env->aarch64 * DAIF (exception masks) are kept in env->daif + * BTYPE is kept in env->btype * all other bits are stored in their correct places in env->pstate */ uint32_t pstate; @@ -XXX,XX +XXX,XX @@ typedef struct CPUARMState { 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 */ uint64_t elr_el[4]; /* AArch64 exception link regs */ @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define PSTATE_I (1U << 7) #define PSTATE_A (1U << 8) #define PSTATE_D (1U << 9) +#define PSTATE_BTYPE (3U << 10) #define PSTATE_IL (1U << 20) #define PSTATE_SS (1U << 21) #define PSTATE_V (1U << 28) @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define PSTATE_N (1U << 31) #define PSTATE_NZCV (PSTATE_N | PSTATE_Z | PSTATE_C | PSTATE_V) #define PSTATE_DAIF (PSTATE_D | PSTATE_A | PSTATE_I | PSTATE_F) -#define CACHED_PSTATE_BITS (PSTATE_NZCV | PSTATE_DAIF) +#define CACHED_PSTATE_BITS (PSTATE_NZCV | PSTATE_DAIF | PSTATE_BTYPE) /* Mode values for AArch64 */ #define PSTATE_MODE_EL3h 13 #define PSTATE_MODE_EL3t 12 @@ -XXX,XX +XXX,XX @@ static inline uint32_t pstate_read(CPUARMState *env) ZF = (env->ZF == 0); return (env->NF & 0x80000000) | (ZF << 30) | (env->CF << 29) | ((env->VF & 0x80000000) >> 3) - | env->pstate | env->daif; + | env->pstate | env->daif | (env->btype << 10); } static inline void pstate_write(CPUARMState *env, uint32_t val) @@ -XXX,XX +XXX,XX @@ static inline void pstate_write(CPUARMState *env, uint32_t val) env->CF = (val >> 29) & 1; env->VF = (val << 3) & 0x80000000; env->daif = val & PSTATE_DAIF; + env->btype = (val >> 10) & 3; env->pstate = val & ~CACHED_PSTATE_BITS; } 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 aarch64_cpu_dump_state(CPUState *cs, FILE *f, el, psr & PSTATE_SP ? 'h' : 't'); + if (cpu_isar_feature(aa64_bti, cpu)) { + cpu_fprintf(f, " BTYPE=%d", (psr & PSTATE_BTYPE) >> 10); + } if (!(flags & CPU_DUMP_FPU)) { cpu_fprintf(f, "\n"); return; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190128223118.5255-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 ++ target/arm/translate.h | 4 ++++ target/arm/helper.c | 22 +++++++++++++++------- target/arm/translate-a64.c | 2 ++ 4 files changed, 23 insertions(+), 7 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 @@ FIELD(TBFLAG_A64, TBII, 0, 2) FIELD(TBFLAG_A64, SVEEXC_EL, 2, 2) FIELD(TBFLAG_A64, ZCR_LEN, 4, 4) FIELD(TBFLAG_A64, PAUTH_ACTIVE, 8, 1) +FIELD(TBFLAG_A64, BT, 9, 1) +FIELD(TBFLAG_A64, BTYPE, 10, 2) static inline bool bswap_code(bool sctlr_b) { 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 ss_same_el; /* True if v8.3-PAuth is active. */ bool pauth_active; + /* True with v8.5-BTI and SCTLR_ELx.BT* set. */ + bool bt; + /* A copy of PSTATE.BTYPE, which will be 0 without v8.5-BTI. */ + uint8_t btype; /* Bottom two bits of XScale c15_cpar coprocessor access control reg */ int c15_cpar; /* TCG op of the current insn_start. */ 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 cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, if (is_a64(env)) { ARMCPU *cpu = arm_env_get_cpu(env); + uint64_t sctlr; *pc = env->pc; flags = FIELD_DP32(flags, TBFLAG_ANY, AARCH64_STATE, 1); @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, flags = FIELD_DP32(flags, TBFLAG_A64, ZCR_LEN, zcr_len); } + if (current_el == 0) { + /* FIXME: ARMv8.1-VHE S2 translation regime. */ + sctlr = env->cp15.sctlr_el[1]; + } else { + sctlr = env->cp15.sctlr_el[current_el]; + } if (cpu_isar_feature(aa64_pauth, cpu)) { /* * In order to save space in flags, we record only whether @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, * a nop, or "active" when some action must be performed. * The decision of which action to take is left to a helper. */ - uint64_t sctlr; - if (current_el == 0) { - /* FIXME: ARMv8.1-VHE S2 translation regime. */ - sctlr = env->cp15.sctlr_el[1]; - } else { - sctlr = env->cp15.sctlr_el[current_el]; - } if (sctlr & (SCTLR_EnIA | SCTLR_EnIB | SCTLR_EnDA | SCTLR_EnDB)) { flags = FIELD_DP32(flags, TBFLAG_A64, PAUTH_ACTIVE, 1); } } + + if (cpu_isar_feature(aa64_bti, cpu)) { + /* Note that SCTLR_EL[23].BT == SCTLR_BT1. */ + if (sctlr & (current_el == 0 ? SCTLR_BT0 : SCTLR_BT1)) { + flags = FIELD_DP32(flags, TBFLAG_A64, BT, 1); + } + flags = FIELD_DP32(flags, TBFLAG_A64, BTYPE, env->btype); + } } else { *pc = env->regs[15]; flags = FIELD_DP32(flags, TBFLAG_A32, THUMB, env->thumb); 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->sve_excp_el = FIELD_EX32(tb_flags, TBFLAG_A64, SVEEXC_EL); dc->sve_len = (FIELD_EX32(tb_flags, TBFLAG_A64, ZCR_LEN) + 1) * 16; dc->pauth_active = FIELD_EX32(tb_flags, TBFLAG_A64, PAUTH_ACTIVE); + dc->bt = FIELD_EX32(tb_flags, TBFLAG_A64, BT); + dc->btype = FIELD_EX32(tb_flags, TBFLAG_A64, BTYPE); dc->vec_len = 0; dc->vec_stride = 0; dc->cp_regs = arm_cpu->cp_regs; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> These bits can be used to cache target-specific data in cputlb read from the page tables. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190128223118.5255-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/exec/memattrs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/include/exec/memattrs.h b/include/exec/memattrs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memattrs.h +++ b/include/exec/memattrs.h @@ -XXX,XX +XXX,XX @@ typedef struct MemTxAttrs { unsigned int user:1; /* Requester ID (for MSI for example) */ unsigned int requester_id:16; + /* + * The following are target-specific page-table bits. These are not + * related to actual memory transactions at all. However, this structure + * is part of the tlb_fill interface, cached in the cputlb structure, + * and has unused bits. These fields will be read by target-specific + * helpers using env->iotlb[mmu_idx][tlb_index()].attrs.target_tlb_bitN. + */ + unsigned int target_tlb_bit0 : 1; + unsigned int target_tlb_bit1 : 1; + unsigned int target_tlb_bit2 : 1; } MemTxAttrs; /* Bus masters which don't specify any attributes will get this, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Caching the bit means that we will not have to re-walk the page tables to look up the bit during translation. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190128223118.5255-6-richard.henderson@linaro.org [PMM: no need to OR in guarded bit status] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 6 ++++++ 1 file changed, 6 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 bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, bool ttbr1_valid; uint64_t descaddrmask; bool aarch64 = arm_el_is_aa64(env, el); + bool guarded = false; /* TODO: * This code does not handle the different format TCR for VTCR_EL2. @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, } /* Merge in attributes from table descriptors */ attrs |= nstable << 3; /* NS */ + guarded = extract64(descriptor, 50, 1); /* GP */ if (param.hpd) { /* HPD disables all the table attributes except NSTable. */ break; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, */ txattrs->secure = false; } + /* When in aarch64 mode, and BTI is enabled, remember GP in the IOTLB. */ + if (aarch64 && guarded && cpu_isar_feature(aa64_bti, cpu)) { + txattrs->target_tlb_bit0 = true; + } if (cacheattrs != NULL) { if (mmu_idx == ARMMMUIdx_S2NS) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The branch target exception for guarded pages has high priority, and only 8 instructions are valid for that case. Perform this check before doing any other decode. Clear BTYPE after all insns that neither set BTYPE nor exit via exception (DISAS_NORETURN). Not yet handled are insns that exit via DISAS_NORETURN for some other reason, like direct branches. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190128223118.5255-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 6 ++ target/arm/translate.h | 9 ++- target/arm/translate-a64.c | 139 +++++++++++++++++++++++++++++++++++++ 3 files changed, 152 insertions(+), 2 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ enum arm_exception_class { EC_FPIDTRAP = 0x08, EC_PACTRAP = 0x09, EC_CP14RRTTRAP = 0x0c, + EC_BTITRAP = 0x0d, EC_ILLEGALSTATE = 0x0e, EC_AA32_SVC = 0x11, EC_AA32_HVC = 0x12, @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_pactrap(void) return EC_PACTRAP << ARM_EL_EC_SHIFT; } +static inline uint32_t syn_btitrap(int btype) +{ + return (EC_BTITRAP << ARM_EL_EC_SHIFT) | btype; +} + static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc) { return (EC_INSNABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) 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 pauth_active; /* True with v8.5-BTI and SCTLR_ELx.BT* set. */ bool bt; - /* A copy of PSTATE.BTYPE, which will be 0 without v8.5-BTI. */ - uint8_t btype; + /* + * >= 0, a copy of PSTATE.BTYPE, which will be 0 without v8.5-BTI. + * < 0, set by the current instruction. + */ + int8_t btype; + /* True if this page is guarded. */ + bool guarded_page; /* Bottom two bits of XScale c15_cpar coprocessor access control reg */ int c15_cpar; /* TCG op of the current insn_start. */ 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 inline int get_a64_user_mem_index(DisasContext *s) return arm_to_core_mmu_idx(useridx); } +static void reset_btype(DisasContext *s) +{ + 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; + } +} + void aarch64_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf, int flags) { @@ -XXX,XX +XXX,XX @@ static void disas_data_proc_simd_fp(DisasContext *s, uint32_t insn) } } +/** + * is_guarded_page: + * @env: The cpu environment + * @s: The DisasContext + * + * Return true if the page is guarded. + */ +static bool is_guarded_page(CPUARMState *env, DisasContext *s) +{ +#ifdef CONFIG_USER_ONLY + return false; /* FIXME */ +#else + uint64_t addr = s->base.pc_first; + int mmu_idx = arm_to_core_mmu_idx(s->mmu_idx); + unsigned int index = tlb_index(env, mmu_idx, addr); + CPUTLBEntry *entry = tlb_entry(env, mmu_idx, addr); + + /* + * We test this immediately after reading an insn, which means + * that any normal page must be in the TLB. The only exception + * would be for executing from flash or device memory, which + * does not retain the TLB entry. + * + * FIXME: Assume false for those, for now. We could use + * arm_cpu_get_phys_page_attrs_debug to re-read the page + * table entry even for that case. + */ + return (tlb_hit(entry->addr_code, addr) && + env->iotlb[mmu_idx][index].attrs.target_tlb_bit0); +#endif +} + +/** + * btype_destination_ok: + * @insn: The instruction at the branch destination + * @bt: SCTLR_ELx.BT + * @btype: PSTATE.BTYPE, and is non-zero + * + * On a guarded page, there are a limited number of insns + * that may be present at the branch target: + * - branch target identifiers, + * - paciasp, pacibsp, + * - BRK insn + * - HLT insn + * Anything else causes a Branch Target Exception. + * + * Return true if the branch is compatible, false to raise BTITRAP. + */ +static bool btype_destination_ok(uint32_t insn, bool bt, int btype) +{ + if ((insn & 0xfffff01fu) == 0xd503201fu) { + /* HINT space */ + switch (extract32(insn, 5, 7)) { + case 0b011001: /* PACIASP */ + case 0b011011: /* PACIBSP */ + /* + * If SCTLR_ELx.BT, then PACI*SP are not compatible + * with btype == 3. Otherwise all btype are ok. + */ + return !bt || btype != 3; + case 0b100000: /* BTI */ + /* Not compatible with any btype. */ + return false; + case 0b100010: /* BTI c */ + /* Not compatible with btype == 3 */ + return btype != 3; + case 0b100100: /* BTI j */ + /* Not compatible with btype == 2 */ + return btype != 2; + case 0b100110: /* BTI jc */ + /* Compatible with any btype. */ + return true; + } + } else { + switch (insn & 0xffe0001fu) { + case 0xd4200000u: /* BRK */ + case 0xd4400000u: /* HLT */ + /* Give priority to the breakpoint exception. */ + return true; + } + } + return false; +} + /* C3.1 A64 instruction index by encoding */ static void disas_a64_insn(CPUARMState *env, DisasContext *s) { @@ -XXX,XX +XXX,XX @@ static void disas_a64_insn(CPUARMState *env, DisasContext *s) s->fp_access_checked = false; + if (dc_isar_feature(aa64_bti, s)) { + if (s->base.num_insns == 1) { + /* + * At the first insn of the TB, compute s->guarded_page. + * We delayed computing this until successfully reading + * the first insn of the TB, above. This (mostly) ensures + * that the softmmu tlb entry has been populated, and the + * page table GP bit is available. + * + * Note that we need to compute this even if btype == 0, + * because this value is used for BR instructions later + * where ENV is not available. + */ + s->guarded_page = is_guarded_page(env, s); + + /* First insn can have btype set to non-zero. */ + tcg_debug_assert(s->btype >= 0); + + /* + * Note that the Branch Target Exception has fairly high + * priority -- below debugging exceptions but above most + * everything else. This allows us to handle this now + * instead of waiting until the insn is otherwise decoded. + */ + if (s->btype != 0 + && s->guarded_page + && !btype_destination_ok(insn, s->bt, s->btype)) { + gen_exception_insn(s, 4, EXCP_UDEF, syn_btitrap(s->btype), + default_exception_el(s)); + return; + } + } else { + /* Not the first insn: btype must be 0. */ + tcg_debug_assert(s->btype == 0); + } + } + switch (extract32(insn, 25, 4)) { case 0x0: case 0x1: case 0x3: /* UNALLOCATED */ unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_a64_insn(CPUARMState *env, DisasContext *s) /* if we allocated any temporaries, free them here */ free_tmp_a64(s); + + /* + * After execution of most insns, btype is reset to 0. + * Note that we set btype == -1 when the insn sets btype. + */ + if (s->btype > 0 && s->base.is_jmp != DISAS_NORETURN) { + reset_btype(s); + } } static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This is all of the non-exception cases of DISAS_NORETURN. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190128223118.5255-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 6 ++++++ 1 file changed, 6 insertions(+) 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 disas_uncond_b_imm(DisasContext *s, uint32_t insn) } /* B Branch / BL Branch with link */ + reset_btype(s); gen_goto_tb(s, 0, addr); } @@ -XXX,XX +XXX,XX @@ static void disas_comp_b_imm(DisasContext *s, uint32_t insn) tcg_cmp = read_cpu_reg(s, rt, sf); label_match = gen_new_label(); + reset_btype(s); tcg_gen_brcondi_i64(op ? TCG_COND_NE : TCG_COND_EQ, tcg_cmp, 0, label_match); @@ -XXX,XX +XXX,XX @@ static void disas_test_b_imm(DisasContext *s, uint32_t insn) tcg_cmp = tcg_temp_new_i64(); tcg_gen_andi_i64(tcg_cmp, cpu_reg(s, rt), (1ULL << bit_pos)); label_match = gen_new_label(); + + reset_btype(s); tcg_gen_brcondi_i64(op ? TCG_COND_NE : TCG_COND_EQ, tcg_cmp, 0, label_match); tcg_temp_free_i64(tcg_cmp); @@ -XXX,XX +XXX,XX @@ static void disas_cond_b_imm(DisasContext *s, uint32_t insn) addr = s->pc + sextract32(insn, 5, 19) * 4 - 4; cond = extract32(insn, 0, 4); + reset_btype(s); if (cond < 0x0e) { /* genuinely conditional branches */ TCGLabel *label_match = gen_new_label(); @@ -XXX,XX +XXX,XX @@ static void handle_sync(DisasContext *s, uint32_t insn, * a self-modified code correctly and also to take * any pending interrupts immediately. */ + reset_btype(s); gen_goto_tb(s, 0, s->pc); return; default: -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190128223118.5255-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 37 ++++++++++++++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) 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 reset_btype(DisasContext *s) } } +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); + s->btype = -1; +} + void aarch64_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf, int flags) { @@ -XXX,XX +XXX,XX @@ static void disas_exc(DisasContext *s, uint32_t insn) static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) { unsigned int opc, op2, op3, rn, op4; + unsigned btype_mod = 2; /* 0: BR, 1: BLR, 2: other */ TCGv_i64 dst; TCGv_i64 modifier; @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) case 0: /* BR */ case 1: /* BLR */ case 2: /* RET */ + btype_mod = opc; switch (op3) { case 0: /* BR, BLR, RET */ @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) default: goto do_unallocated; } - gen_a64_set_pc(s, dst); /* BLR also needs to load return address */ if (opc == 1) { @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) if ((op3 & ~1) != 2) { goto do_unallocated; } + btype_mod = opc & 1; if (s->pauth_active) { dst = new_tmp_a64(s); modifier = cpu_reg_sp(s, op4); @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) return; } + switch (btype_mod) { + case 0: /* BR */ + if (dc_isar_feature(aa64_bti, s)) { + /* BR to {x16,x17} or !guard -> 1, else 3. */ + set_btype(s, rn == 16 || rn == 17 || !s->guarded_page ? 1 : 3); + } + break; + + case 1: /* BLR */ + if (dc_isar_feature(aa64_bti, s)) { + /* BLR sets BTYPE to 2, regardless of source guarded page. */ + set_btype(s, 2); + } + break; + + default: /* RET or none of the above. */ + /* BTYPE will be set to 0 by normal end-of-insn processing. */ + break; + } + s->base.is_jmp = DISAS_JUMP; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190128223118.5255-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64PFR0, ADVSIMD, 1); cpu->isar.id_aa64pfr0 = t; + t = cpu->isar.id_aa64pfr1; + t = FIELD_DP64(t, ID_AA64PFR1, BT, 1); + cpu->isar.id_aa64pfr1 = t; + t = cpu->isar.id_aa64mmfr1; t = FIELD_DP64(t, ID_AA64MMFR1, HPDS, 1); /* HPD */ t = FIELD_DP64(t, ID_AA64MMFR1, LO, 1); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190201195404.30486-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/target_syscall.h | 7 ++++++ linux-user/syscall.c | 36 +++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+) diff --git a/linux-user/aarch64/target_syscall.h b/linux-user/aarch64/target_syscall.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/target_syscall.h +++ b/linux-user/aarch64/target_syscall.h @@ -XXX,XX +XXX,XX @@ struct target_pt_regs { #define TARGET_PR_SVE_SET_VL 50 #define TARGET_PR_SVE_GET_VL 51 +#define TARGET_PR_PAC_RESET_KEYS 54 +# define TARGET_PR_PAC_APIAKEY (1 << 0) +# define TARGET_PR_PAC_APIBKEY (1 << 1) +# define TARGET_PR_PAC_APDAKEY (1 << 2) +# define TARGET_PR_PAC_APDBKEY (1 << 3) +# define TARGET_PR_PAC_APGAKEY (1 << 4) + void arm_init_pauth_key(ARMPACKey *key); #endif /* AARCH64_TARGET_SYSCALL_H */ diff --git a/linux-user/syscall.c b/linux-user/syscall.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -XXX,XX +XXX,XX @@ static abi_long do_syscall1(void *cpu_env, int num, abi_long arg1, } } return ret; + case TARGET_PR_PAC_RESET_KEYS: + { + CPUARMState *env = cpu_env; + ARMCPU *cpu = arm_env_get_cpu(env); + + if (arg3 || arg4 || arg5) { + return -TARGET_EINVAL; + } + if (cpu_isar_feature(aa64_pauth, cpu)) { + int all = (TARGET_PR_PAC_APIAKEY | TARGET_PR_PAC_APIBKEY | + TARGET_PR_PAC_APDAKEY | TARGET_PR_PAC_APDBKEY | + TARGET_PR_PAC_APGAKEY); + if (arg2 == 0) { + arg2 = all; + } else if (arg2 & ~all) { + return -TARGET_EINVAL; + } + if (arg2 & TARGET_PR_PAC_APIAKEY) { + arm_init_pauth_key(&env->apia_key); + } + if (arg2 & TARGET_PR_PAC_APIBKEY) { + arm_init_pauth_key(&env->apib_key); + } + if (arg2 & TARGET_PR_PAC_APDAKEY) { + arm_init_pauth_key(&env->apda_key); + } + if (arg2 & TARGET_PR_PAC_APDBKEY) { + arm_init_pauth_key(&env->apdb_key); + } + if (arg2 & TARGET_PR_PAC_APGAKEY) { + arm_init_pauth_key(&env->apga_key); + } + return 0; + } + } + return -TARGET_EINVAL; #endif /* AARCH64 */ case PR_GET_SECCOMP: case PR_SET_SECCOMP: -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190201195404.30486-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/tcg/aarch64/Makefile.target | 6 +++++- tests/tcg/aarch64/pauth-1.c | 23 +++++++++++++++++++++++ 2 files changed, 28 insertions(+), 1 deletion(-) create mode 100644 tests/tcg/aarch64/pauth-1.c diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target index XXXXXXX..XXXXXXX 100644 --- a/tests/tcg/aarch64/Makefile.target +++ b/tests/tcg/aarch64/Makefile.target @@ -XXX,XX +XXX,XX @@ VPATH += $(AARCH64_SRC) # we don't build any of the ARM tests AARCH64_TESTS=$(filter-out $(ARM_TESTS), $(TESTS)) AARCH64_TESTS+=fcvt -TESTS:=$(AARCH64_TESTS) fcvt: LDFLAGS+=-lm run-fcvt: fcvt $(call run-test,$<,$(QEMU) $<, "$< on $(TARGET_NAME)") $(call diff-out,$<,$(AARCH64_SRC)/fcvt.ref) + +AARCH64_TESTS += pauth-1 +run-pauth-%: QEMU += -cpu max + +TESTS:=$(AARCH64_TESTS) diff --git a/tests/tcg/aarch64/pauth-1.c b/tests/tcg/aarch64/pauth-1.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/tcg/aarch64/pauth-1.c @@ -XXX,XX +XXX,XX @@ +#include <assert.h> +#include <sys/prctl.h> + +asm(".arch armv8.4-a"); + +#ifndef PR_PAC_RESET_KEYS +#define PR_PAC_RESET_KEYS 54 +#define PR_PAC_APDAKEY (1 << 2) +#endif + +int main() +{ + int x; + void *p0 = &x, *p1, *p2; + + asm volatile("pacdza %0" : "=r"(p1) : "0"(p0)); + prctl(PR_PAC_RESET_KEYS, PR_PAC_APDAKEY, 0, 0, 0); + asm volatile("pacdza %0" : "=r"(p2) : "0"(p0)); + + assert(p1 != p0); + assert(p1 != p2); + return 0; +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Split out gen_top_byte_ignore in preparation of handling these data accesses; the new tbflags field is not yet honored. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190204132126.3255-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 1 + target/arm/translate.h | 3 +- target/arm/helper.c | 1 + target/arm/translate-a64.c | 72 +++++++++++++++++++------------------- 4 files changed, 40 insertions(+), 37 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 @@ FIELD(TBFLAG_A64, ZCR_LEN, 4, 4) FIELD(TBFLAG_A64, PAUTH_ACTIVE, 8, 1) FIELD(TBFLAG_A64, BT, 9, 1) FIELD(TBFLAG_A64, BTYPE, 10, 2) +FIELD(TBFLAG_A64, TBID, 12, 2) static inline bool bswap_code(bool sctlr_b) { 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 { int user; #endif ARMMMUIdx mmu_idx; /* MMU index to use for normal loads/stores */ - uint8_t tbii; /* TBI1|TBI0 for EL0/1 or TBI for EL2/3 */ + uint8_t tbii; /* TBI1|TBI0 for insns */ + uint8_t tbid; /* TBI1|TBI0 for data */ bool ns; /* Use non-secure CPREG bank on access */ int fp_excp_el; /* FP exception EL or 0 if enabled */ int sve_excp_el; /* SVE exception EL or 0 if enabled */ 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 cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, } flags = FIELD_DP32(flags, TBFLAG_A64, TBII, tbii); + flags = FIELD_DP32(flags, TBFLAG_A64, TBID, tbid); } #endif 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 gen_a64_set_pc_im(uint64_t val) tcg_gen_movi_i64(cpu_pc, val); } -/* Load the PC from a generic TCG variable. +/* + * Handle Top Byte Ignore (TBI) bits. * - * If address tagging is enabled via the TCR TBI bits, then loading - * an address into the PC will clear out any tag in it: + * If address tagging is enabled via the TCR TBI bits: * + for EL2 and EL3 there is only one TBI bit, and if it is set * then the address is zero-extended, clearing bits [63:56] * + for EL0 and EL1, TBI0 controls addresses with bit 55 == 0 @@ -XXX,XX +XXX,XX @@ void gen_a64_set_pc_im(uint64_t val) * If the appropriate TBI bit is set for the address then * the address is sign-extended from bit 55 into bits [63:56] * - * We can avoid doing this for relative-branches, because the - * PC + offset can never overflow into the tag bits (assuming - * that virtual addresses are less than 56 bits wide, as they - * are currently), but we must handle it for branch-to-register. + * Here We have concatenated TBI{1,0} into tbi. */ -static void gen_a64_set_pc(DisasContext *s, TCGv_i64 src) +static void gen_top_byte_ignore(DisasContext *s, TCGv_i64 dst, + TCGv_i64 src, int tbi) { - /* Note that TBII is TBI1:TBI0. */ - int tbi = s->tbii; - - if (s->current_el <= 1) { - if (tbi != 0) { - /* Sign-extend from bit 55. */ - tcg_gen_sextract_i64(cpu_pc, src, 0, 56); - - if (tbi != 3) { - TCGv_i64 tcg_zero = tcg_const_i64(0); - - /* - * The two TBI bits differ. - * If tbi0, then !tbi1: only use the extension if positive. - * if !tbi0, then tbi1: only use the extension if negative. - */ - tcg_gen_movcond_i64(tbi == 1 ? TCG_COND_GE : TCG_COND_LT, - cpu_pc, cpu_pc, tcg_zero, cpu_pc, src); - tcg_temp_free_i64(tcg_zero); - } - return; - } + if (tbi == 0) { + /* Load unmodified address */ + tcg_gen_mov_i64(dst, src); + } else if (s->current_el >= 2) { + /* FIXME: ARMv8.1-VHE S2 translation regime. */ + /* Force tag byte to all zero */ + tcg_gen_extract_i64(dst, src, 0, 56); } else { - if (tbi != 0) { - /* Force tag byte to all zero */ - tcg_gen_extract_i64(cpu_pc, src, 0, 56); - return; + /* Sign-extend from bit 55. */ + tcg_gen_sextract_i64(dst, src, 0, 56); + + if (tbi != 3) { + TCGv_i64 tcg_zero = tcg_const_i64(0); + + /* + * The two TBI bits differ. + * If tbi0, then !tbi1: only use the extension if positive. + * if !tbi0, then tbi1: only use the extension if negative. + */ + tcg_gen_movcond_i64(tbi == 1 ? TCG_COND_GE : TCG_COND_LT, + dst, dst, tcg_zero, dst, src); + tcg_temp_free_i64(tcg_zero); } } +} - /* Load unmodified address */ - tcg_gen_mov_i64(cpu_pc, src); +static void gen_a64_set_pc(DisasContext *s, TCGv_i64 src) +{ + /* + * If address tagging is enabled for instructions via the TCR TBI bits, + * then loading an address into the PC will clear out any tag. + */ + gen_top_byte_ignore(s, cpu_pc, src, s->tbii); } typedef struct DisasCompare64 { @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, core_mmu_idx = FIELD_EX32(tb_flags, TBFLAG_ANY, MMUIDX); dc->mmu_idx = core_to_arm_mmu_idx(env, core_mmu_idx); dc->tbii = FIELD_EX32(tb_flags, TBFLAG_A64, TBII); + dc->tbid = FIELD_EX32(tb_flags, TBFLAG_A64, TBID); dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx); #if !defined(CONFIG_USER_ONLY) dc->user = (dc->current_el == 0); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This will allow TBI to be used in user-only mode, as well as avoid ping-ponging the softmmu TLB when TBI is in use. It will also enable other armv8 extensions. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190204132126.3255-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 217 ++++++++++++++++++++----------------- 1 file changed, 116 insertions(+), 101 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 gen_a64_set_pc(DisasContext *s, TCGv_i64 src) gen_top_byte_ignore(s, cpu_pc, src, s->tbii); } +/* + * Return a "clean" address for ADDR according to TBID. + * This is always a fresh temporary, as we need to be able to + * increment this independently of a dirty write-back address. + */ +static TCGv_i64 clean_data_tbi(DisasContext *s, TCGv_i64 addr) +{ + TCGv_i64 clean = new_tmp_a64(s); + gen_top_byte_ignore(s, clean, addr, s->tbid); + return clean; +} + typedef struct DisasCompare64 { TCGCond cond; TCGv_i64 value; @@ -XXX,XX +XXX,XX @@ static void gen_compare_and_swap(DisasContext *s, int rs, int rt, TCGv_i64 tcg_rs = cpu_reg(s, rs); TCGv_i64 tcg_rt = cpu_reg(s, rt); int memidx = get_mem_index(s); - TCGv_i64 addr = cpu_reg_sp(s, rn); + TCGv_i64 clean_addr; if (rn == 31) { gen_check_sp_alignment(s); } - tcg_gen_atomic_cmpxchg_i64(tcg_rs, addr, tcg_rs, tcg_rt, memidx, + clean_addr = clean_data_tbi(s, cpu_reg_sp(s, rn)); + tcg_gen_atomic_cmpxchg_i64(tcg_rs, clean_addr, tcg_rs, tcg_rt, memidx, size | MO_ALIGN | s->be_data); } @@ -XXX,XX +XXX,XX @@ static void gen_compare_and_swap_pair(DisasContext *s, int rs, int rt, TCGv_i64 s2 = cpu_reg(s, rs + 1); TCGv_i64 t1 = cpu_reg(s, rt); TCGv_i64 t2 = cpu_reg(s, rt + 1); - TCGv_i64 addr = cpu_reg_sp(s, rn); + TCGv_i64 clean_addr; int memidx = get_mem_index(s); if (rn == 31) { gen_check_sp_alignment(s); } + clean_addr = clean_data_tbi(s, cpu_reg_sp(s, rn)); if (size == 2) { TCGv_i64 cmp = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static void gen_compare_and_swap_pair(DisasContext *s, int rs, int rt, tcg_gen_concat32_i64(cmp, s2, s1); } - tcg_gen_atomic_cmpxchg_i64(cmp, addr, cmp, val, memidx, + tcg_gen_atomic_cmpxchg_i64(cmp, clean_addr, cmp, val, memidx, MO_64 | MO_ALIGN | s->be_data); tcg_temp_free_i64(val); @@ -XXX,XX +XXX,XX @@ static void gen_compare_and_swap_pair(DisasContext *s, int rs, int rt, if (HAVE_CMPXCHG128) { TCGv_i32 tcg_rs = tcg_const_i32(rs); if (s->be_data == MO_LE) { - gen_helper_casp_le_parallel(cpu_env, tcg_rs, addr, t1, t2); + gen_helper_casp_le_parallel(cpu_env, tcg_rs, + clean_addr, t1, t2); } else { - gen_helper_casp_be_parallel(cpu_env, tcg_rs, addr, t1, t2); + gen_helper_casp_be_parallel(cpu_env, tcg_rs, + clean_addr, t1, t2); } tcg_temp_free_i32(tcg_rs); } else { @@ -XXX,XX +XXX,XX @@ static void gen_compare_and_swap_pair(DisasContext *s, int rs, int rt, TCGv_i64 zero = tcg_const_i64(0); /* Load the two words, in memory order. */ - tcg_gen_qemu_ld_i64(d1, addr, memidx, + tcg_gen_qemu_ld_i64(d1, clean_addr, memidx, MO_64 | MO_ALIGN_16 | s->be_data); - tcg_gen_addi_i64(a2, addr, 8); - tcg_gen_qemu_ld_i64(d2, addr, memidx, MO_64 | s->be_data); + tcg_gen_addi_i64(a2, clean_addr, 8); + tcg_gen_qemu_ld_i64(d2, clean_addr, memidx, MO_64 | s->be_data); /* Compare the two words, also in memory order. */ tcg_gen_setcond_i64(TCG_COND_EQ, c1, d1, s1); @@ -XXX,XX +XXX,XX @@ static void gen_compare_and_swap_pair(DisasContext *s, int rs, int rt, /* If compare equal, write back new data, else write back old data. */ tcg_gen_movcond_i64(TCG_COND_NE, c1, c2, zero, t1, d1); tcg_gen_movcond_i64(TCG_COND_NE, c2, c2, zero, t2, d2); - tcg_gen_qemu_st_i64(c1, addr, memidx, MO_64 | s->be_data); + tcg_gen_qemu_st_i64(c1, clean_addr, memidx, MO_64 | s->be_data); tcg_gen_qemu_st_i64(c2, a2, memidx, MO_64 | s->be_data); tcg_temp_free_i64(a2); tcg_temp_free_i64(c1); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) int is_lasr = extract32(insn, 15, 1); int o2_L_o1_o0 = extract32(insn, 21, 3) * 2 | is_lasr; int size = extract32(insn, 30, 2); - TCGv_i64 tcg_addr; + TCGv_i64 clean_addr; switch (o2_L_o1_o0) { case 0x0: /* STXR */ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) if (is_lasr) { tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); } - tcg_addr = read_cpu_reg_sp(s, rn, 1); - gen_store_exclusive(s, rs, rt, rt2, tcg_addr, size, false); + clean_addr = clean_data_tbi(s, cpu_reg_sp(s, rn)); + gen_store_exclusive(s, rs, rt, rt2, clean_addr, size, false); return; case 0x4: /* LDXR */ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) if (rn == 31) { gen_check_sp_alignment(s); } - tcg_addr = read_cpu_reg_sp(s, rn, 1); + clean_addr = clean_data_tbi(s, cpu_reg_sp(s, rn)); s->is_ldex = true; - gen_load_exclusive(s, rt, rt2, tcg_addr, size, false); + gen_load_exclusive(s, rt, rt2, clean_addr, size, false); if (is_lasr) { tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) gen_check_sp_alignment(s); } tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); - tcg_addr = read_cpu_reg_sp(s, rn, 1); - do_gpr_st(s, cpu_reg(s, rt), tcg_addr, size, true, rt, + clean_addr = clean_data_tbi(s, cpu_reg_sp(s, rn)); + do_gpr_st(s, cpu_reg(s, rt), clean_addr, size, true, rt, disas_ldst_compute_iss_sf(size, false, 0), is_lasr); return; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) if (rn == 31) { gen_check_sp_alignment(s); } - tcg_addr = read_cpu_reg_sp(s, rn, 1); - do_gpr_ld(s, cpu_reg(s, rt), tcg_addr, size, false, false, true, rt, + clean_addr = clean_data_tbi(s, cpu_reg_sp(s, rn)); + do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size, false, false, true, rt, disas_ldst_compute_iss_sf(size, false, 0), is_lasr); tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); return; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) if (is_lasr) { tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); } - tcg_addr = read_cpu_reg_sp(s, rn, 1); - gen_store_exclusive(s, rs, rt, rt2, tcg_addr, size, true); + clean_addr = clean_data_tbi(s, cpu_reg_sp(s, rn)); + gen_store_exclusive(s, rs, rt, rt2, clean_addr, size, true); return; } if (rt2 == 31 @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) if (rn == 31) { gen_check_sp_alignment(s); } - tcg_addr = read_cpu_reg_sp(s, rn, 1); + clean_addr = clean_data_tbi(s, cpu_reg_sp(s, rn)); s->is_ldex = true; - gen_load_exclusive(s, rt, rt2, tcg_addr, size, true); + gen_load_exclusive(s, rt, rt2, clean_addr, size, true); if (is_lasr) { tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); } @@ -XXX,XX +XXX,XX @@ static void disas_ld_lit(DisasContext *s, uint32_t insn) int opc = extract32(insn, 30, 2); bool is_signed = false; int size = 2; - TCGv_i64 tcg_rt, tcg_addr; + TCGv_i64 tcg_rt, clean_addr; if (is_vector) { if (opc == 3) { @@ -XXX,XX +XXX,XX @@ static void disas_ld_lit(DisasContext *s, uint32_t insn) tcg_rt = cpu_reg(s, rt); - tcg_addr = tcg_const_i64((s->pc - 4) + imm); + clean_addr = tcg_const_i64((s->pc - 4) + imm); if (is_vector) { - do_fp_ld(s, rt, tcg_addr, size); + do_fp_ld(s, rt, clean_addr, size); } else { /* Only unsigned 32bit loads target 32bit registers. */ bool iss_sf = opc != 0; - do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, false, + do_gpr_ld(s, tcg_rt, clean_addr, size, is_signed, false, true, rt, iss_sf, false); } - tcg_temp_free_i64(tcg_addr); + tcg_temp_free_i64(clean_addr); } /* @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) bool postindex = false; bool wback = false; - TCGv_i64 tcg_addr; /* calculated address */ + TCGv_i64 clean_addr, dirty_addr; + int size; if (opc == 3) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) gen_check_sp_alignment(s); } - tcg_addr = read_cpu_reg_sp(s, rn, 1); - + dirty_addr = read_cpu_reg_sp(s, rn, 1); if (!postindex) { - tcg_gen_addi_i64(tcg_addr, tcg_addr, offset); + tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); } + clean_addr = clean_data_tbi(s, dirty_addr); if (is_vector) { if (is_load) { - do_fp_ld(s, rt, tcg_addr, size); + do_fp_ld(s, rt, clean_addr, size); } else { - do_fp_st(s, rt, tcg_addr, size); + do_fp_st(s, rt, clean_addr, size); } - tcg_gen_addi_i64(tcg_addr, tcg_addr, 1 << size); + tcg_gen_addi_i64(clean_addr, clean_addr, 1 << size); if (is_load) { - do_fp_ld(s, rt2, tcg_addr, size); + do_fp_ld(s, rt2, clean_addr, size); } else { - do_fp_st(s, rt2, tcg_addr, size); + do_fp_st(s, rt2, clean_addr, size); } } else { TCGv_i64 tcg_rt = cpu_reg(s, rt); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn) /* Do not modify tcg_rt before recognizing any exception * from the second load. */ - do_gpr_ld(s, tmp, tcg_addr, size, is_signed, false, + do_gpr_ld(s, tmp, clean_addr, size, is_signed, false, false, 0, false, false); - tcg_gen_addi_i64(tcg_addr, tcg_addr, 1 << size); - do_gpr_ld(s, tcg_rt2, tcg_addr, size, is_signed, false, + tcg_gen_addi_i64(clean_addr, clean_addr, 1 << size); + do_gpr_ld(s, tcg_rt2, clean_addr, size, is_signed, false, false, 0, false, false); tcg_gen_mov_i64(tcg_rt, tmp); tcg_temp_free_i64(tmp); } else { - do_gpr_st(s, tcg_rt, tcg_addr, size, + do_gpr_st(s, tcg_rt, clean_addr, size, false, 0, false, false); - tcg_gen_addi_i64(tcg_addr, tcg_addr, 1 << size); - do_gpr_st(s, tcg_rt2, tcg_addr, size, + tcg_gen_addi_i64(clean_addr, clean_addr, 1 << size); + do_gpr_st(s, tcg_rt2, clean_addr, size, false, 0, false, false); } } if (wback) { if (postindex) { - tcg_gen_addi_i64(tcg_addr, tcg_addr, offset - (1 << size)); - } else { - tcg_gen_subi_i64(tcg_addr, tcg_addr, 1 << size); + tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); } - tcg_gen_mov_i64(cpu_reg_sp(s, rn), tcg_addr); + tcg_gen_mov_i64(cpu_reg_sp(s, rn), dirty_addr); } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, bool post_index; bool writeback; - TCGv_i64 tcg_addr; + TCGv_i64 clean_addr, dirty_addr; if (is_vector) { size |= (opc & 2) << 1; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, if (rn == 31) { gen_check_sp_alignment(s); } - tcg_addr = read_cpu_reg_sp(s, rn, 1); + dirty_addr = read_cpu_reg_sp(s, rn, 1); if (!post_index) { - tcg_gen_addi_i64(tcg_addr, tcg_addr, imm9); + tcg_gen_addi_i64(dirty_addr, dirty_addr, imm9); } + clean_addr = clean_data_tbi(s, dirty_addr); if (is_vector) { if (is_store) { - do_fp_st(s, rt, tcg_addr, size); + do_fp_st(s, rt, clean_addr, size); } else { - do_fp_ld(s, rt, tcg_addr, size); + do_fp_ld(s, rt, clean_addr, size); } } else { TCGv_i64 tcg_rt = cpu_reg(s, rt); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, bool iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc); if (is_store) { - do_gpr_st_memidx(s, tcg_rt, tcg_addr, size, memidx, + do_gpr_st_memidx(s, tcg_rt, clean_addr, size, memidx, iss_valid, rt, iss_sf, false); } else { - do_gpr_ld_memidx(s, tcg_rt, tcg_addr, size, + do_gpr_ld_memidx(s, tcg_rt, clean_addr, size, is_signed, is_extended, memidx, iss_valid, rt, iss_sf, false); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, if (writeback) { TCGv_i64 tcg_rn = cpu_reg_sp(s, rn); if (post_index) { - tcg_gen_addi_i64(tcg_addr, tcg_addr, imm9); + tcg_gen_addi_i64(dirty_addr, dirty_addr, imm9); } - tcg_gen_mov_i64(tcg_rn, tcg_addr); + tcg_gen_mov_i64(tcg_rn, dirty_addr); } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, bool is_store = false; bool is_extended = false; - TCGv_i64 tcg_rm; - TCGv_i64 tcg_addr; + TCGv_i64 tcg_rm, clean_addr, dirty_addr; if (extract32(opt, 1, 1) == 0) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, if (rn == 31) { gen_check_sp_alignment(s); } - tcg_addr = read_cpu_reg_sp(s, rn, 1); + dirty_addr = read_cpu_reg_sp(s, rn, 1); tcg_rm = read_cpu_reg(s, rm, 1); ext_and_shift_reg(tcg_rm, tcg_rm, opt, shift ? size : 0); - tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_rm); + tcg_gen_add_i64(dirty_addr, dirty_addr, tcg_rm); + clean_addr = clean_data_tbi(s, dirty_addr); if (is_vector) { if (is_store) { - do_fp_st(s, rt, tcg_addr, size); + do_fp_st(s, rt, clean_addr, size); } else { - do_fp_ld(s, rt, tcg_addr, size); + do_fp_ld(s, rt, clean_addr, size); } } else { TCGv_i64 tcg_rt = cpu_reg(s, rt); bool iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc); if (is_store) { - do_gpr_st(s, tcg_rt, tcg_addr, size, + do_gpr_st(s, tcg_rt, clean_addr, size, true, rt, iss_sf, false); } else { - do_gpr_ld(s, tcg_rt, tcg_addr, size, + do_gpr_ld(s, tcg_rt, clean_addr, size, is_signed, is_extended, true, rt, iss_sf, false); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn, unsigned int imm12 = extract32(insn, 10, 12); unsigned int offset; - TCGv_i64 tcg_addr; + TCGv_i64 clean_addr, dirty_addr; bool is_store; bool is_signed = false; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn, if (rn == 31) { gen_check_sp_alignment(s); } - tcg_addr = read_cpu_reg_sp(s, rn, 1); + dirty_addr = read_cpu_reg_sp(s, rn, 1); offset = imm12 << size; - tcg_gen_addi_i64(tcg_addr, tcg_addr, offset); + tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); + clean_addr = clean_data_tbi(s, dirty_addr); if (is_vector) { if (is_store) { - do_fp_st(s, rt, tcg_addr, size); + do_fp_st(s, rt, clean_addr, size); } else { - do_fp_ld(s, rt, tcg_addr, size); + do_fp_ld(s, rt, clean_addr, size); } } else { TCGv_i64 tcg_rt = cpu_reg(s, rt); bool iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc); if (is_store) { - do_gpr_st(s, tcg_rt, tcg_addr, size, + do_gpr_st(s, tcg_rt, clean_addr, size, true, rt, iss_sf, false); } else { - do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, is_extended, + do_gpr_ld(s, tcg_rt, clean_addr, size, is_signed, is_extended, true, rt, iss_sf, false); } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, int rs = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int o3_opc = extract32(insn, 12, 4); - TCGv_i64 tcg_rn, tcg_rs; + TCGv_i64 tcg_rs, clean_addr; AtomicThreeOpFn *fn; if (is_vector || !dc_isar_feature(aa64_atomics, s)) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, if (rn == 31) { gen_check_sp_alignment(s); } - tcg_rn = cpu_reg_sp(s, rn); + clean_addr = clean_data_tbi(s, cpu_reg_sp(s, rn)); tcg_rs = read_cpu_reg(s, rs, true); if (o3_opc == 1) { /* LDCLR */ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, /* The tcg atomic primitives are all full barriers. Therefore we * can ignore the Acquire and Release bits of this instruction. */ - fn(cpu_reg(s, rt), tcg_rn, tcg_rs, get_mem_index(s), + fn(cpu_reg(s, rt), clean_addr, tcg_rs, get_mem_index(s), s->be_data | size | MO_ALIGN); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pac(DisasContext *s, uint32_t insn, bool is_wback = extract32(insn, 11, 1); bool use_key_a = !extract32(insn, 23, 1); int offset; - TCGv_i64 tcg_addr, tcg_rt; + TCGv_i64 clean_addr, dirty_addr, tcg_rt; if (size != 3 || is_vector || !dc_isar_feature(aa64_pauth, s)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pac(DisasContext *s, uint32_t insn, if (rn == 31) { gen_check_sp_alignment(s); } - tcg_addr = read_cpu_reg_sp(s, rn, 1); + dirty_addr = read_cpu_reg_sp(s, rn, 1); if (s->pauth_active) { if (use_key_a) { - gen_helper_autda(tcg_addr, cpu_env, tcg_addr, cpu_X[31]); + gen_helper_autda(dirty_addr, cpu_env, dirty_addr, cpu_X[31]); } else { - gen_helper_autdb(tcg_addr, cpu_env, tcg_addr, cpu_X[31]); + gen_helper_autdb(dirty_addr, cpu_env, dirty_addr, cpu_X[31]); } } /* Form the 10-bit signed, scaled offset. */ offset = (extract32(insn, 22, 1) << 9) | extract32(insn, 12, 9); offset = sextract32(offset << size, 0, 10 + size); - tcg_gen_addi_i64(tcg_addr, tcg_addr, offset); + tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); + + /* Note that "clean" and "dirty" here refer to TBI not PAC. */ + clean_addr = clean_data_tbi(s, dirty_addr); tcg_rt = cpu_reg(s, rt); - - do_gpr_ld(s, tcg_rt, tcg_addr, size, /* is_signed */ false, + do_gpr_ld(s, tcg_rt, clean_addr, size, /* is_signed */ false, /* extend */ false, /* iss_valid */ !is_wback, /* iss_srt */ rt, /* iss_sf */ true, /* iss_ar */ false); if (is_wback) { - tcg_gen_mov_i64(cpu_reg_sp(s, rn), tcg_addr); + tcg_gen_mov_i64(cpu_reg_sp(s, rn), dirty_addr); } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) bool is_store = !extract32(insn, 22, 1); bool is_postidx = extract32(insn, 23, 1); bool is_q = extract32(insn, 30, 1); - TCGv_i64 tcg_addr, tcg_rn, tcg_ebytes; + TCGv_i64 clean_addr, tcg_rn, tcg_ebytes; TCGMemOp endian = s->be_data; int ebytes; /* bytes per element */ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) elements = (is_q ? 16 : 8) / ebytes; tcg_rn = cpu_reg_sp(s, rn); - tcg_addr = tcg_temp_new_i64(); - tcg_gen_mov_i64(tcg_addr, tcg_rn); + clean_addr = clean_data_tbi(s, tcg_rn); tcg_ebytes = tcg_const_i64(ebytes); for (r = 0; r < rpt; r++) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) for (xs = 0; xs < selem; xs++) { int tt = (rt + r + xs) % 32; if (is_store) { - do_vec_st(s, tt, e, tcg_addr, size, endian); + do_vec_st(s, tt, e, clean_addr, size, endian); } else { - do_vec_ld(s, tt, e, tcg_addr, size, endian); + do_vec_ld(s, tt, e, clean_addr, size, endian); } - tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_ebytes); + tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes); } } } + tcg_temp_free_i64(tcg_ebytes); if (!is_store) { /* For non-quad operations, setting a slice of the low @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) if (is_postidx) { if (rm == 31) { - tcg_gen_mov_i64(tcg_rn, tcg_addr); + tcg_gen_addi_i64(tcg_rn, tcg_rn, rpt * elements * selem * ebytes); } else { tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm)); } } - tcg_temp_free_i64(tcg_ebytes); - tcg_temp_free_i64(tcg_addr); } /* AdvSIMD load/store single structure @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) bool replicate = false; int index = is_q << 3 | S << 2 | size; int ebytes, xs; - TCGv_i64 tcg_addr, tcg_rn, tcg_ebytes; + TCGv_i64 clean_addr, tcg_rn, tcg_ebytes; if (extract32(insn, 31, 1)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) } tcg_rn = cpu_reg_sp(s, rn); - tcg_addr = tcg_temp_new_i64(); - tcg_gen_mov_i64(tcg_addr, tcg_rn); + clean_addr = clean_data_tbi(s, tcg_rn); tcg_ebytes = tcg_const_i64(ebytes); for (xs = 0; xs < selem; xs++) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) /* Load and replicate to all elements */ TCGv_i64 tcg_tmp = tcg_temp_new_i64(); - tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, + tcg_gen_qemu_ld_i64(tcg_tmp, clean_addr, get_mem_index(s), s->be_data + scale); tcg_gen_gvec_dup_i64(scale, vec_full_reg_offset(s, rt), (is_q + 1) * 8, vec_full_reg_size(s), @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) } else { /* Load/store one element per register */ if (is_load) { - do_vec_ld(s, rt, index, tcg_addr, scale, s->be_data); + do_vec_ld(s, rt, index, clean_addr, scale, s->be_data); } else { - do_vec_st(s, rt, index, tcg_addr, scale, s->be_data); + do_vec_st(s, rt, index, clean_addr, scale, s->be_data); } } - tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_ebytes); + tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes); rt = (rt + 1) % 32; } + tcg_temp_free_i64(tcg_ebytes); if (is_postidx) { if (rm == 31) { - tcg_gen_mov_i64(tcg_rn, tcg_addr); + tcg_gen_addi_i64(tcg_rn, tcg_rn, selem * ebytes); } else { tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm)); } } - tcg_temp_free_i64(tcg_ebytes); - tcg_temp_free_i64(tcg_addr); } /* Loads and stores */ -- 2.20.1 Enables, but does not turn on, TBI for CONFIG_USER_ONLY. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190204132126.3255-4-richard.henderson@linaro.org [PMM: adjusted #ifdeffery to placate clang, which otherwise complains about static functions that are unused in the CONFIG_USER_ONLY build] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 21 -------------------- target/arm/helper.c | 45 ++++++++++++++++++++++-------------------- 2 files changed, 24 insertions(+), 42 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ typedef struct ARMVAParameters { bool using64k : 1; } ARMVAParameters; -#ifdef CONFIG_USER_ONLY -static inline ARMVAParameters aa64_va_parameters_both(CPUARMState *env, - uint64_t va, - ARMMMUIdx mmu_idx) -{ - return (ARMVAParameters) { - /* 48-bit address space */ - .tsz = 16, - /* We can't handle tagged addresses properly in user-only mode */ - .tbi = false, - }; -} - -static inline ARMVAParameters aa64_va_parameters(CPUARMState *env, - uint64_t va, - ARMMMUIdx mmu_idx, bool data) -{ - return aa64_va_parameters_both(env, va, mmu_idx); -} -#else ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, ARMMMUIdx mmu_idx); ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, ARMMMUIdx mmu_idx, bool data); -#endif #endif 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 @@ uint32_t HELPER(rbit)(uint32_t x) return revbit32(x); } -#if defined(CONFIG_USER_ONLY) +#ifdef CONFIG_USER_ONLY /* These should probably raise undefined insn exceptions. */ void HELPER(v7m_msr)(CPUARMState *env, uint32_t reg, uint32_t val) @@ -XXX,XX +XXX,XX @@ void arm_cpu_do_interrupt(CPUState *cs) cs->interrupt_request |= CPU_INTERRUPT_EXITTB; } } +#endif /* !CONFIG_USER_ONLY */ /* Return the exception level which controls this address translation regime */ static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx) @@ -XXX,XX +XXX,XX @@ static inline uint32_t regime_el(CPUARMState *env, ARMMMUIdx mmu_idx) } } +#ifndef CONFIG_USER_ONLY + /* Return the SCTLR value which controls this address translation regime */ static inline uint32_t regime_sctlr(CPUARMState *env, ARMMMUIdx mmu_idx) { @@ -XXX,XX +XXX,XX @@ static inline bool regime_translation_big_endian(CPUARMState *env, return (regime_sctlr(env, mmu_idx) & SCTLR_EE) != 0; } +/* Return the TTBR associated with this translation regime */ +static inline uint64_t regime_ttbr(CPUARMState *env, ARMMMUIdx mmu_idx, + int ttbrn) +{ + if (mmu_idx == ARMMMUIdx_S2NS) { + return env->cp15.vttbr_el2; + } + if (ttbrn == 0) { + return env->cp15.ttbr0_el[regime_el(env, mmu_idx)]; + } else { + return env->cp15.ttbr1_el[regime_el(env, mmu_idx)]; + } +} + +#endif /* !CONFIG_USER_ONLY */ + /* Return the TCR controlling this translation regime */ static inline TCR *regime_tcr(CPUARMState *env, ARMMMUIdx mmu_idx) { @@ -XXX,XX +XXX,XX @@ static inline ARMMMUIdx stage_1_mmu_idx(ARMMMUIdx mmu_idx) return mmu_idx; } -/* Return the TTBR associated with this translation regime */ -static inline uint64_t regime_ttbr(CPUARMState *env, ARMMMUIdx mmu_idx, - int ttbrn) -{ - if (mmu_idx == ARMMMUIdx_S2NS) { - return env->cp15.vttbr_el2; - } - if (ttbrn == 0) { - return env->cp15.ttbr0_el[regime_el(env, mmu_idx)]; - } else { - return env->cp15.ttbr1_el[regime_el(env, mmu_idx)]; - } -} - /* Return true if the translation regime is using LPAE format page tables */ static inline bool regime_using_lpae_format(CPUARMState *env, ARMMMUIdx mmu_idx) @@ -XXX,XX +XXX,XX @@ bool arm_s1_regime_using_lpae_format(CPUARMState *env, ARMMMUIdx mmu_idx) return regime_using_lpae_format(env, mmu_idx); } +#ifndef CONFIG_USER_ONLY static inline bool regime_is_user(CPUARMState *env, ARMMMUIdx mmu_idx) { switch (mmu_idx) { @@ -XXX,XX +XXX,XX @@ static uint8_t convert_stage2_attrs(CPUARMState *env, uint8_t s2attrs) return (hiattr << 6) | (hihint << 4) | (loattr << 2) | lohint; } +#endif /* !CONFIG_USER_ONLY */ ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, ARMMMUIdx mmu_idx) @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, return ret; } +#ifndef CONFIG_USER_ONLY static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va, ARMMMUIdx mmu_idx) { @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, *pc = env->pc; flags = FIELD_DP32(flags, TBFLAG_ANY, AARCH64_STATE, 1); -#ifndef CONFIG_USER_ONLY - /* - * Get control bits for tagged addresses. Note that the - * translator only uses this for instruction addresses. - */ + /* Get control bits for tagged addresses. */ { ARMMMUIdx stage1 = stage_1_mmu_idx(mmu_idx); ARMVAParameters p0 = aa64_va_parameters_both(env, 0, stage1); @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, flags = FIELD_DP32(flags, TBFLAG_A64, TBII, tbii); flags = FIELD_DP32(flags, TBFLAG_A64, TBID, tbid); } -#endif if (cpu_isar_feature(aa64_sve, cpu)) { int sve_el = sve_exception_el(env, current_el); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This has been enabled in the linux kernel since v3.11 (commit d50240a5f6cea, 2013-09-03, "arm64: mm: permit use of tagged pointers at EL0"). Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190204132126.3255-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 6 ++++++ 1 file changed, 6 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_reset(CPUState *s) env->vfp.zcr_el[1] = cpu->sve_max_vq - 1; env->vfp.zcr_el[2] = env->vfp.zcr_el[1]; env->vfp.zcr_el[3] = env->vfp.zcr_el[1]; + /* + * Enable TBI0 and TBI1. While the real kernel only enables TBI0, + * turning on both here will produce smaller code and otherwise + * make no difference to the user-level emulation. + */ + env->cp15.tcr_el[1].raw_tcr = (3ULL << 37); #else /* Reset into the highest available EL */ if (arm_feature(env, ARM_FEATURE_EL3)) { -- 2.20.1 From: Max Filippov <jcmvbkbc@gmail.com> With multiprocess extensions gdb uses 'vKill' packet instead of 'k' to kill the inferior. Handle 'vKill' the same way 'k' was handled in the presence of single process. Fixes: 7cf48f6752e5 ("gdbstub: add multiprocess support to (f|s)ThreadInfo and ThreadExtraInfo") Cc: Luc Michel <luc.michel@greensocs.com> Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Reviewed-by: KONRAD Frederic <frederic.konrad@adacore.com> Tested-by: KONRAD Frederic <frederic.konrad@adacore.com> Message-id: 20190130192403.13754-1-jcmvbkbc@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- gdbstub.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/gdbstub.c b/gdbstub.c index XXXXXXX..XXXXXXX 100644 --- a/gdbstub.c +++ b/gdbstub.c @@ -XXX,XX +XXX,XX @@ static int gdb_handle_packet(GDBState *s, const char *line_buf) put_packet(s, buf); break; + } else if (strncmp(p, "Kill;", 5) == 0) { + /* Kill the target */ + error_report("QEMU: Terminated via GDBstub"); + exit(0); } else { goto unknown_command; } -- 2.20.1 Fix the block comment style in arm_load_kernel() to QEMU's current style preferences. This will allow us to do some refactoring of this function without checkpatch complaining about the code-motion patches. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20190131112240.8395-2-peter.maydell@linaro.org --- hw/arm/boot.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) static const ARMInsnFixup *primary_loader; AddressSpace *as = arm_boot_address_space(cpu, info); - /* CPU objects (unlike devices) are not automatically reset on system + /* + * CPU objects (unlike devices) are not automatically reset on system * reset, so we must always register a handler to do so. If we're * actually loading a kernel, the handler is also responsible for * arranging that we start it correctly. @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) qemu_register_reset(do_cpu_reset, ARM_CPU(cs)); } - /* The board code is not supposed to set secure_board_setup unless + /* + * The board code is not supposed to set secure_board_setup unless * running its code in secure mode is actually possible, and KVM * doesn't support secure. */ @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) if (!info->kernel_filename || info->firmware_loaded) { if (have_dtb(info)) { - /* If we have a device tree blob, but no kernel to supply it to (or + /* + * If we have a device tree blob, but no kernel to supply it to (or * the kernel is supposed to be loaded by the bootloader), copy the * DTB to the base of RAM for the bootloader to pick up. */ @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) try_decompressing_kernel = arm_feature(&cpu->env, ARM_FEATURE_AARCH64); - /* Expose the kernel, the command line, and the initrd in fw_cfg. + /* + * Expose the kernel, the command line, and the initrd in fw_cfg. * We don't process them here at all, it's all left to the * firmware. */ @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) } } - /* We will start from address 0 (typically a boot ROM image) in the + /* + * We will start from address 0 (typically a boot ROM image) in the * same way as hardware. */ return; @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) if (info->nb_cpus == 0) info->nb_cpus = 1; - /* We want to put the initrd far enough into RAM that when the + /* + * We want to put the initrd far enough into RAM that when the * kernel is uncompressed it will not clobber the initrd. However * on boards without much RAM we must ensure that we still leave * enough room for a decent sized initrd, and on boards with large @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) kernel_size = arm_load_elf(info, &elf_entry, &elf_low_addr, &elf_high_addr, elf_machine, as); if (kernel_size > 0 && have_dtb(info)) { - /* If there is still some room left at the base of RAM, try and put + /* + * If there is still some room left at the base of RAM, try and put * the DTB there like we do for images loaded with -bios or -pflash. */ if (elf_low_addr > info->loader_start || elf_high_addr < info->loader_start) { - /* Set elf_low_addr as address limit for arm_load_dtb if it may be + /* + * Set elf_low_addr as address limit for arm_load_dtb if it may be * pointing into RAM, otherwise pass '0' (no limit) */ if (elf_low_addr < info->loader_start) { @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) fixupcontext[FIXUP_BOARDID] = info->board_id; fixupcontext[FIXUP_BOARD_SETUP] = info->board_setup_addr; - /* for device tree boot, we pass the DTB directly in r2. Otherwise + /* + * for device tree boot, we pass the DTB directly in r2. Otherwise * we point to the kernel args. */ if (have_dtb(info)) { @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) info->write_board_setup(cpu, info); } - /* Notify devices which need to fake up firmware initialization + /* + * Notify devices which need to fake up firmware initialization * that we're doing a direct kernel boot. */ object_child_foreach_recursive(object_get_root(), -- 2.20.1 Factor out the "direct kernel boot" code path from arm_load_kernel() into its own function; this function is getting long enough that the code flow is a bit confusing. This commit only moves code around; no semantic changes. We leave the "load the dtb" code in arm_load_kernel() -- this is currently only used by the "direct kernel boot" path, but this is a bug which we will fix shortly. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20190131112240.8395-3-peter.maydell@linaro.org --- hw/arm/boot.c | 150 +++++++++++++++++++++++++++----------------------- 1 file changed, 80 insertions(+), 70 deletions(-) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ static uint64_t load_aarch64_image(const char *filename, hwaddr mem_base, return size; } -void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) +static void arm_setup_direct_kernel_boot(ARMCPU *cpu, + struct arm_boot_info *info) { + /* Set up for a direct boot of a kernel image file. */ CPUState *cs; + AddressSpace *as = arm_boot_address_space(cpu, info); int kernel_size; int initrd_size; int is_linux = 0; @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) int elf_machine; hwaddr entry; static const ARMInsnFixup *primary_loader; - AddressSpace *as = arm_boot_address_space(cpu, info); - - /* - * CPU objects (unlike devices) are not automatically reset on system - * reset, so we must always register a handler to do so. If we're - * actually loading a kernel, the handler is also responsible for - * arranging that we start it correctly. - */ - for (cs = first_cpu; cs; cs = CPU_NEXT(cs)) { - qemu_register_reset(do_cpu_reset, ARM_CPU(cs)); - } - - /* - * The board code is not supposed to set secure_board_setup unless - * running its code in secure mode is actually possible, and KVM - * doesn't support secure. - */ - assert(!(info->secure_board_setup && kvm_enabled())); - - info->dtb_filename = qemu_opt_get(qemu_get_machine_opts(), "dtb"); - info->dtb_limit = 0; - - /* Load the kernel. */ - if (!info->kernel_filename || info->firmware_loaded) { - - if (have_dtb(info)) { - /* - * If we have a device tree blob, but no kernel to supply it to (or - * the kernel is supposed to be loaded by the bootloader), copy the - * DTB to the base of RAM for the bootloader to pick up. - */ - info->dtb_start = info->loader_start; - } - - if (info->kernel_filename) { - FWCfgState *fw_cfg; - bool try_decompressing_kernel; - - fw_cfg = fw_cfg_find(); - try_decompressing_kernel = arm_feature(&cpu->env, - ARM_FEATURE_AARCH64); - - /* - * Expose the kernel, the command line, and the initrd in fw_cfg. - * We don't process them here at all, it's all left to the - * firmware. - */ - load_image_to_fw_cfg(fw_cfg, - FW_CFG_KERNEL_SIZE, FW_CFG_KERNEL_DATA, - info->kernel_filename, - try_decompressing_kernel); - load_image_to_fw_cfg(fw_cfg, - FW_CFG_INITRD_SIZE, FW_CFG_INITRD_DATA, - info->initrd_filename, false); - - if (info->kernel_cmdline) { - fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, - strlen(info->kernel_cmdline) + 1); - fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, - info->kernel_cmdline); - } - } - - /* - * We will start from address 0 (typically a boot ROM image) in the - * same way as hardware. - */ - return; - } if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { primary_loader = bootloader_aarch64; @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) for (cs = first_cpu; cs; cs = CPU_NEXT(cs)) { ARM_CPU(cs)->env.boot_info = info; } +} + +void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) +{ + CPUState *cs; + AddressSpace *as = arm_boot_address_space(cpu, info); + + /* + * CPU objects (unlike devices) are not automatically reset on system + * reset, so we must always register a handler to do so. If we're + * actually loading a kernel, the handler is also responsible for + * arranging that we start it correctly. + */ + for (cs = first_cpu; cs; cs = CPU_NEXT(cs)) { + qemu_register_reset(do_cpu_reset, ARM_CPU(cs)); + } + + /* + * The board code is not supposed to set secure_board_setup unless + * running its code in secure mode is actually possible, and KVM + * doesn't support secure. + */ + assert(!(info->secure_board_setup && kvm_enabled())); + + info->dtb_filename = qemu_opt_get(qemu_get_machine_opts(), "dtb"); + info->dtb_limit = 0; + + /* Load the kernel. */ + if (!info->kernel_filename || info->firmware_loaded) { + + if (have_dtb(info)) { + /* + * If we have a device tree blob, but no kernel to supply it to (or + * the kernel is supposed to be loaded by the bootloader), copy the + * DTB to the base of RAM for the bootloader to pick up. + */ + info->dtb_start = info->loader_start; + } + + if (info->kernel_filename) { + FWCfgState *fw_cfg; + bool try_decompressing_kernel; + + fw_cfg = fw_cfg_find(); + try_decompressing_kernel = arm_feature(&cpu->env, + ARM_FEATURE_AARCH64); + + /* + * Expose the kernel, the command line, and the initrd in fw_cfg. + * We don't process them here at all, it's all left to the + * firmware. + */ + load_image_to_fw_cfg(fw_cfg, + FW_CFG_KERNEL_SIZE, FW_CFG_KERNEL_DATA, + info->kernel_filename, + try_decompressing_kernel); + load_image_to_fw_cfg(fw_cfg, + FW_CFG_INITRD_SIZE, FW_CFG_INITRD_DATA, + info->initrd_filename, false); + + if (info->kernel_cmdline) { + fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, + strlen(info->kernel_cmdline) + 1); + fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, + info->kernel_cmdline); + } + } + + /* + * We will start from address 0 (typically a boot ROM image) in the + * same way as hardware. + */ + return; + } else { + arm_setup_direct_kernel_boot(cpu, info); + } if (!info->skip_dtb_autoload && have_dtb(info)) { if (arm_load_dtb(info->dtb_start, info, info->dtb_limit, as) < 0) { -- 2.20.1 Factor out the "boot via firmware" code path from arm_load_kernel() into its own function. This commit only moves code around; no semantic changes. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20190131112240.8395-4-peter.maydell@linaro.org --- hw/arm/boot.c | 92 +++++++++++++++++++++++++++------------------------ 1 file changed, 49 insertions(+), 43 deletions(-) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ static void arm_setup_direct_kernel_boot(ARMCPU *cpu, } } +static void arm_setup_firmware_boot(ARMCPU *cpu, struct arm_boot_info *info) +{ + /* Set up for booting firmware (which might load a kernel via fw_cfg) */ + + if (have_dtb(info)) { + /* + * If we have a device tree blob, but no kernel to supply it to (or + * the kernel is supposed to be loaded by the bootloader), copy the + * DTB to the base of RAM for the bootloader to pick up. + */ + info->dtb_start = info->loader_start; + } + + if (info->kernel_filename) { + FWCfgState *fw_cfg; + bool try_decompressing_kernel; + + fw_cfg = fw_cfg_find(); + try_decompressing_kernel = arm_feature(&cpu->env, + ARM_FEATURE_AARCH64); + + /* + * Expose the kernel, the command line, and the initrd in fw_cfg. + * We don't process them here at all, it's all left to the + * firmware. + */ + load_image_to_fw_cfg(fw_cfg, + FW_CFG_KERNEL_SIZE, FW_CFG_KERNEL_DATA, + info->kernel_filename, + try_decompressing_kernel); + load_image_to_fw_cfg(fw_cfg, + FW_CFG_INITRD_SIZE, FW_CFG_INITRD_DATA, + info->initrd_filename, false); + + if (info->kernel_cmdline) { + fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, + strlen(info->kernel_cmdline) + 1); + fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, + info->kernel_cmdline); + } + } + + /* + * We will start from address 0 (typically a boot ROM image) in the + * same way as hardware. + */ +} + void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) { CPUState *cs; @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) /* Load the kernel. */ if (!info->kernel_filename || info->firmware_loaded) { - - if (have_dtb(info)) { - /* - * If we have a device tree blob, but no kernel to supply it to (or - * the kernel is supposed to be loaded by the bootloader), copy the - * DTB to the base of RAM for the bootloader to pick up. - */ - info->dtb_start = info->loader_start; - } - - if (info->kernel_filename) { - FWCfgState *fw_cfg; - bool try_decompressing_kernel; - - fw_cfg = fw_cfg_find(); - try_decompressing_kernel = arm_feature(&cpu->env, - ARM_FEATURE_AARCH64); - - /* - * Expose the kernel, the command line, and the initrd in fw_cfg. - * We don't process them here at all, it's all left to the - * firmware. - */ - load_image_to_fw_cfg(fw_cfg, - FW_CFG_KERNEL_SIZE, FW_CFG_KERNEL_DATA, - info->kernel_filename, - try_decompressing_kernel); - load_image_to_fw_cfg(fw_cfg, - FW_CFG_INITRD_SIZE, FW_CFG_INITRD_DATA, - info->initrd_filename, false); - - if (info->kernel_cmdline) { - fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, - strlen(info->kernel_cmdline) + 1); - fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, - info->kernel_cmdline); - } - } - - /* - * We will start from address 0 (typically a boot ROM image) in the - * same way as hardware. - */ + arm_setup_firmware_boot(cpu, info); return; } else { arm_setup_direct_kernel_boot(cpu, info); -- 2.20.1 The code path for booting firmware doesn't set env->boot_info. At first sight this looks odd, so add a comment saying why we don't. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20190131112240.8395-5-peter.maydell@linaro.org --- hw/arm/boot.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ static void arm_setup_firmware_boot(ARMCPU *cpu, struct arm_boot_info *info) /* * We will start from address 0 (typically a boot ROM image) in the - * same way as hardware. + * same way as hardware. Leave env->boot_info NULL, so that + * do_cpu_reset() knows it does not need to alter the PC on reset. */ } -- 2.20.1 The arm_boot_info struct has a skip_dtb_autoload flag: if this is set to true by the board code then arm_load_kernel() will not load the DTB itself, but will leave this for the board code to do itself later. However, the check for this is done in a code path which is only executed for the case where we load a kernel image file. If we're taking the "boot via firmware" code path then the flag isn't honoured and the DTB is never loaded. We didn't notice this because the only real user of "boot via firmware" that cares about the DTB is the virt board (for UEFI boot), and that always wants skip_dtb_autoload anyway. But the SBSA reference board model we're planning to add will want the flag to behave correctly. Now we've refactored the arm_load_kernel() function, the fix is simple: drop the early 'return' so we fall into the same "load the DTB" code the boot-direct-kernel path uses. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20190131112240.8395-6-peter.maydell@linaro.org --- hw/arm/boot.c | 1 - 1 file changed, 1 deletion(-) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) /* Load the kernel. */ if (!info->kernel_filename || info->firmware_loaded) { arm_setup_firmware_boot(cpu, info); - return; } else { arm_setup_direct_kernel_boot(cpu, info); } -- 2.20.1 The {IOE, DZE, OFE, UFE, IXE, IDE} bits in the FPSCR/FPCR are for enabling trapped IEEE floating point exceptions (where IEEE exception conditions cause a CPU exception rather than updating the FPSR status bits). QEMU doesn't implement this (and nor does the hardware we're modelling), but for implementations which don't implement trapped exception handling these control bits are supposed to be RAZ/WI. This allows guest code to test for whether the feature is present by trying to write to the bit and checking whether it sticks. QEMU is incorrectly making these bits read as written. Make them RAZ/WI as the architecture requires. In particular this was causing problems for the NetBSD automatic test suite. Reported-by: Martin Husemann <martin@netbsd.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190131130700.28392-1-peter.maydell@linaro.org --- target/arm/cpu.h | 6 ++++++ target/arm/helper.c | 6 ++++++ 2 files 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 @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val); #define FPSR_MASK 0xf800009f #define FPCR_MASK 0x07ff9f00 +#define FPCR_IOE (1 << 8) /* Invalid Operation exception trap enable */ +#define FPCR_DZE (1 << 9) /* Divide by Zero exception trap enable */ +#define FPCR_OFE (1 << 10) /* Overflow exception trap enable */ +#define FPCR_UFE (1 << 11) /* Underflow exception trap enable */ +#define FPCR_IXE (1 << 12) /* Inexact exception trap enable */ +#define FPCR_IDE (1 << 15) /* Input Denormal exception trap enable */ #define FPCR_FZ16 (1 << 19) /* ARMv8.2+, FP16 flush-to-zero */ #define FPCR_FZ (1 << 24) /* Flush-to-zero enable bit */ #define FPCR_DN (1 << 25) /* Default NaN enable bit */ 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 HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) val &= ~FPCR_FZ16; } + /* + * We don't implement trapped exception handling, so the + * trap enable bits are all RAZ/WI (not RES0!) + */ + val &= ~(FPCR_IDE | FPCR_IXE | FPCR_UFE | FPCR_OFE | FPCR_DZE | FPCR_IOE); + changed = env->vfp.xregs[ARM_VFP_FPSCR]; env->vfp.xregs[ARM_VFP_FPSCR] = (val & 0xffc8ffff); env->vfp.vec_len = (val >> 16) & 7; -- 2.20.1 v3->v4: Windows headers define an INT type which clashed with an enum value name in arm_gicv3_its.c... The following changes since commit eae587e8e3694b1aceab23239493fb4c7e1a80f5: Merge remote-tracking branch 'remotes/armbru/tags/pull-qapi-2021-09-13' into staging (2021-09-13 11:00:30 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210913-3 for you to fetch changes up to 28e987a7e7edaa3ca7feeac65edca26145df8814: hw/arm/mps2.c: Mark internal-only I2C buses as 'full' (2021-09-13 21:01:08 +0100) ---------------------------------------------------------------- target-arm queue: * mark MPS2/MPS3 board-internal i2c buses as 'full' so that command line user-created devices are not plugged into them * Take an exception if PSTATE.IL is set * Support an emulated ITS in the virt board * Add support for kudo-bmc board * Probe for KVM_CAP_ARM_VM_IPA_SIZE when creating scratch VM * cadence_uart: Fix clock handling issues that prevented u-boot from running ---------------------------------------------------------------- Bin Meng (6): hw/misc: zynq_slcr: Correctly compute output clocks in the reset exit phase hw/char: cadence_uart: Disable transmit when input clock is disabled hw/char: cadence_uart: Move clock/reset check to uart_can_receive() hw/char: cadence_uart: Convert to memop_with_attrs() ops hw/char: cadence_uart: Ignore access when unclocked or in reset for uart_{read, write}() hw/char: cadence_uart: Log a guest error when device is unclocked or in reset Chris Rauer (1): hw/arm: Add support for kudo-bmc board. Marc Zyngier (1): hw/arm/virt: KVM: Probe for KVM_CAP_ARM_VM_IPA_SIZE when creating scratch VM Peter Maydell (5): target/arm: Take an exception if PSTATE.IL is set qdev: Support marking individual buses as 'full' hw/arm/mps2-tz.c: Add extra data parameter to MakeDevFn hw/arm/mps2-tz.c: Mark internal-only I2C buses as 'full' hw/arm/mps2.c: Mark internal-only I2C buses as 'full' Richard Henderson (1): target/arm: Merge disas_a64_insn into aarch64_tr_translate_insn Shashi Mallela (9): hw/intc: GICv3 ITS initial framework hw/intc: GICv3 ITS register definitions added hw/intc: GICv3 ITS command queue framework hw/intc: GICv3 ITS Command processing hw/intc: GICv3 ITS Feature enablement hw/intc: GICv3 redistributor ITS processing tests/data/acpi/virt: Add IORT files for ITS hw/arm/virt: add ITS support in virt GIC tests/data/acpi/virt: Update IORT files for ITS docs/system/arm/nuvoton.rst | 1 + hw/intc/gicv3_internal.h | 188 ++++- include/hw/arm/virt.h | 2 + include/hw/intc/arm_gicv3_common.h | 13 + include/hw/intc/arm_gicv3_its_common.h | 32 +- include/hw/qdev-core.h | 24 + target/arm/cpu.h | 1 + target/arm/kvm_arm.h | 4 +- target/arm/syndrome.h | 5 + target/arm/translate.h | 2 + hw/arm/mps2-tz.c | 92 ++- hw/arm/mps2.c | 12 +- hw/arm/npcm7xx_boards.c | 34 + hw/arm/virt.c | 29 +- hw/char/cadence_uart.c | 61 +- hw/intc/arm_gicv3.c | 14 + hw/intc/arm_gicv3_common.c | 13 + hw/intc/arm_gicv3_cpuif.c | 7 +- hw/intc/arm_gicv3_dist.c | 5 +- hw/intc/arm_gicv3_its.c | 1322 ++++++++++++++++++++++++++++++++ hw/intc/arm_gicv3_its_common.c | 7 +- hw/intc/arm_gicv3_its_kvm.c | 2 +- hw/intc/arm_gicv3_redist.c | 153 +++- hw/misc/zynq_slcr.c | 31 +- softmmu/qdev-monitor.c | 7 +- target/arm/helper-a64.c | 1 + target/arm/helper.c | 8 + target/arm/kvm.c | 7 +- target/arm/translate-a64.c | 255 +++--- target/arm/translate.c | 21 + hw/intc/meson.build | 1 + tests/data/acpi/virt/IORT | Bin 0 -> 124 bytes tests/data/acpi/virt/IORT.memhp | Bin 0 -> 124 bytes tests/data/acpi/virt/IORT.numamem | Bin 0 -> 124 bytes tests/data/acpi/virt/IORT.pxb | Bin 0 -> 124 bytes 35 files changed, 2144 insertions(+), 210 deletions(-) create mode 100644 hw/intc/arm_gicv3_its.c create mode 100644 tests/data/acpi/virt/IORT create mode 100644 tests/data/acpi/virt/IORT.memhp create mode 100644 tests/data/acpi/virt/IORT.numamem create mode 100644 tests/data/acpi/virt/IORT.pxb