From 871a7f6a9a62df2908f69b43fde4baff36305e34 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 29 Aug 2023 16:23:24 -0700 Subject: [PATCH 01/26] tests/tcg/aarch64: Adjust pauth tests for FEAT_FPAC With FEAT_FPAC, AUT* instructions that fail authentication do not produce an error value but instead fault. For pauth-2, install a signal handler and verify it gets called. For pauth-4 and pauth-5, we are explicitly testing the error value, so there's nothing to test with FEAT_FPAC, so exit early. Adjust the makefile to use -cpu neoverse-v1, which has FEAT_EPAC but not FEAT_FPAC. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20230829232335.965414-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- tests/tcg/aarch64/Makefile.target | 6 +++- tests/tcg/aarch64/pauth-2.c | 54 ++++++++++++++++++++++++++----- tests/tcg/aarch64/pauth-4.c | 18 ++++++++--- tests/tcg/aarch64/pauth-5.c | 10 ++++++ tests/tcg/aarch64/pauth.h | 23 +++++++++++++ 5 files changed, 98 insertions(+), 13 deletions(-) create mode 100644 tests/tcg/aarch64/pauth.h diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target index b77bbd9b3c..2efacf9a5a 100644 --- a/tests/tcg/aarch64/Makefile.target +++ b/tests/tcg/aarch64/Makefile.target @@ -42,7 +42,11 @@ endif ifneq ($(CROSS_CC_HAS_ARMV8_3),) AARCH64_TESTS += pauth-1 pauth-2 pauth-4 pauth-5 pauth-%: CFLAGS += -march=armv8.3-a -run-pauth-%: QEMU_OPTS += -cpu max +run-pauth-1: QEMU_OPTS += -cpu max +run-pauth-2: QEMU_OPTS += -cpu max +# Choose a cpu with FEAT_Pauth but without FEAT_FPAC for pauth-[45]. +run-pauth-4: QEMU_OPTS += -cpu neoverse-v1 +run-pauth-5: QEMU_OPTS += -cpu neoverse-v1 endif # BTI Tests diff --git a/tests/tcg/aarch64/pauth-2.c b/tests/tcg/aarch64/pauth-2.c index 978652ede3..89ffdbf1df 100644 --- a/tests/tcg/aarch64/pauth-2.c +++ b/tests/tcg/aarch64/pauth-2.c @@ -1,5 +1,22 @@ #include +#include +#include #include +#include "pauth.h" + + +static void sigill(int sig, siginfo_t *info, void *vuc) +{ + ucontext_t *uc = vuc; + uint64_t test; + + /* There is only one insn below that is allowed to fault. */ + asm volatile("adr %0, auth2_insn" : "=r"(test)); + assert(test == uc->uc_mcontext.pc); + exit(0); +} + +static int pac_feature; void do_test(uint64_t value) { @@ -27,31 +44,52 @@ void do_test(uint64_t value) * An invalid salt usually fails authorization, but again there * is a chance of choosing another salt that works. * Iterate until we find another salt which does fail. + * + * With FEAT_FPAC, this will SIGILL instead of producing a result. */ for (salt2 = salt1 + 1; ; salt2++) { - asm volatile("autda %0, %2" : "=r"(decode) : "0"(encode), "r"(salt2)); + asm volatile("auth2_insn: autda %0, %2" + : "=r"(decode) : "0"(encode), "r"(salt2)); if (decode != value) { break; } } + assert(pac_feature < 4); /* No FEAT_FPAC */ + /* The VA bits, bit 55, and the TBI bits, should be unchanged. */ assert(((decode ^ value) & 0xff80ffffffffffffull) == 0); /* - * Bits [54:53] are an error indicator based on the key used; - * the DA key above is keynumber 0, so error == 0b01. Otherwise - * bit 55 of the original is sign-extended into the rest of the auth. + * Without FEAT_Pauth2, bits [54:53] are an error indicator based on + * the key used; the DA key above is keynumber 0, so error == 0b01. + * Otherwise, bit 55 of the original is sign-extended into the rest + * of the auth. */ - if ((value >> 55) & 1) { - assert(((decode >> 48) & 0xff) == 0b10111111); - } else { - assert(((decode >> 48) & 0xff) == 0b00100000); + if (pac_feature < 3) { + if ((value >> 55) & 1) { + assert(((decode >> 48) & 0xff) == 0b10111111); + } else { + assert(((decode >> 48) & 0xff) == 0b00100000); + } } } int main() { + static const struct sigaction sa = { + .sa_sigaction = sigill, + .sa_flags = SA_SIGINFO + }; + + pac_feature = get_pac_feature(); + assert(pac_feature != 0); + + if (pac_feature >= 4) { + /* FEAT_FPAC */ + sigaction(SIGILL, &sa, NULL); + } + do_test(0); do_test(0xda004acedeadbeefull); return 0; diff --git a/tests/tcg/aarch64/pauth-4.c b/tests/tcg/aarch64/pauth-4.c index 24a639e36c..b254f413af 100644 --- a/tests/tcg/aarch64/pauth-4.c +++ b/tests/tcg/aarch64/pauth-4.c @@ -2,14 +2,24 @@ #include #include #include +#include "pauth.h" #define TESTS 1000 int main() { + char base[TESTS]; int i, count = 0; float perc; - void *base = malloc(TESTS); + int pac_feature = get_pac_feature(); + + /* + * Exit if no PAuth or FEAT_FPAC, which will SIGILL on AUTIA failure + * rather than return an error for us to check below. + */ + if (pac_feature == 0 || pac_feature >= 4) { + return 0; + } for (i = 0; i < TESTS; i++) { uintptr_t in, x, y; @@ -17,7 +27,7 @@ int main() in = i + (uintptr_t) base; asm("mov %0, %[in]\n\t" - "pacia %0, sp\n\t" /* sigill if pauth not supported */ + "pacia %0, sp\n\t" "eor %0, %0, #4\n\t" /* corrupt single bit */ "mov %1, %0\n\t" "autia %1, sp\n\t" /* validate corrupted pointer */ @@ -36,10 +46,10 @@ int main() if (x != y) { count++; } - } + perc = (float) count / (float) TESTS; - printf("Checks Passed: %0.2f%%", perc * 100.0); + printf("Checks Passed: %0.2f%%\n", perc * 100.0); assert(perc > 0.95); return 0; } diff --git a/tests/tcg/aarch64/pauth-5.c b/tests/tcg/aarch64/pauth-5.c index 67c257918b..ed8d5a926b 100644 --- a/tests/tcg/aarch64/pauth-5.c +++ b/tests/tcg/aarch64/pauth-5.c @@ -1,4 +1,5 @@ #include +#include "pauth.h" static int x; @@ -6,6 +7,15 @@ int main() { int *p0 = &x, *p1, *p2, *p3; unsigned long salt = 0; + int pac_feature = get_pac_feature(); + + /* + * Exit if no PAuth or FEAT_FPAC, which will SIGILL on AUTDA failure + * rather than return an error for us to check below. + */ + if (pac_feature == 0 || pac_feature >= 4) { + return 0; + } /* * With TBI enabled and a 48-bit VA, there are 7 bits of auth, and so diff --git a/tests/tcg/aarch64/pauth.h b/tests/tcg/aarch64/pauth.h new file mode 100644 index 0000000000..543b234437 --- /dev/null +++ b/tests/tcg/aarch64/pauth.h @@ -0,0 +1,23 @@ +/* + * Helper for pauth test case + * + * Copyright (c) 2023 Linaro Ltd + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include +#include + +static int get_pac_feature(void) +{ + unsigned long isar1, isar2; + + assert(getauxval(AT_HWCAP) & HWCAP_CPUID); + + asm("mrs %0, id_aa64isar1_el1" : "=r"(isar1)); + asm("mrs %0, S3_0_C0_C6_2" : "=r"(isar2)); /* id_aa64isar2_el1 */ + + return ((isar1 >> 4) & 0xf) /* APA */ + | ((isar1 >> 8) & 0xf) /* API */ + | ((isar2 >> 12) & 0xf); /* APA3 */ +} From a969fe9755d9f6e6319b6eb308c8afeec1ccc969 Mon Sep 17 00:00:00 2001 From: Aaron Lindsay Date: Tue, 29 Aug 2023 16:23:25 -0700 Subject: [PATCH 02/26] target/arm: Add ID_AA64ISAR2_EL1 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reviewed-by: Philippe Mathieu-Daudé Reviewed-by: Richard Henderson Signed-off-by: Aaron Lindsay Signed-off-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20230829232335.965414-3-richard.henderson@linaro.org [PMM: drop the HVF part of the patch and just comment that we need to do something when the register appears in that API] Signed-off-by: Peter Maydell Signed-off-by: Richard Henderson Signed-off-by: Peter Maydell --- target/arm/cpu.h | 1 + target/arm/helper.c | 4 ++-- target/arm/hvf/hvf.c | 1 + target/arm/kvm64.c | 2 ++ 4 files changed, 6 insertions(+), 2 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 278cc135c2..9b76cc68c6 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -1033,6 +1033,7 @@ struct ArchCPU { uint32_t dbgdevid1; uint64_t id_aa64isar0; uint64_t id_aa64isar1; + uint64_t id_aa64isar2; uint64_t id_aa64pfr0; uint64_t id_aa64pfr1; uint64_t id_aa64mmfr0; diff --git a/target/arm/helper.c b/target/arm/helper.c index e3f5a7d2bd..f9f7c3c39e 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -8435,11 +8435,11 @@ void register_cp_regs_for_features(ARMCPU *cpu) .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa64_tid3, .resetvalue = cpu->isar.id_aa64isar1 }, - { .name = "ID_AA64ISAR2_EL1_RESERVED", .state = ARM_CP_STATE_AA64, + { .name = "ID_AA64ISAR2_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 6, .opc2 = 2, .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa64_tid3, - .resetvalue = 0 }, + .resetvalue = cpu->isar.id_aa64isar2 }, { .name = "ID_AA64ISAR3_EL1_RESERVED", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 6, .opc2 = 3, .access = PL1_R, .type = ARM_CP_CONST, diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c index 486f90be1d..546c0e817f 100644 --- a/target/arm/hvf/hvf.c +++ b/target/arm/hvf/hvf.c @@ -847,6 +847,7 @@ static bool hvf_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) { HV_SYS_REG_ID_AA64DFR1_EL1, &host_isar.id_aa64dfr1 }, { HV_SYS_REG_ID_AA64ISAR0_EL1, &host_isar.id_aa64isar0 }, { HV_SYS_REG_ID_AA64ISAR1_EL1, &host_isar.id_aa64isar1 }, + /* Add ID_AA64ISAR2_EL1 here when HVF supports it */ { HV_SYS_REG_ID_AA64MMFR0_EL1, &host_isar.id_aa64mmfr0 }, { HV_SYS_REG_ID_AA64MMFR1_EL1, &host_isar.id_aa64mmfr1 }, { HV_SYS_REG_ID_AA64MMFR2_EL1, &host_isar.id_aa64mmfr2 }, diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index 4d904a1d11..ac440c33f9 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -304,6 +304,8 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) ARM64_SYS_REG(3, 0, 0, 6, 0)); err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64isar1, ARM64_SYS_REG(3, 0, 0, 6, 1)); + err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64isar2, + ARM64_SYS_REG(3, 0, 0, 6, 2)); err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64mmfr0, ARM64_SYS_REG(3, 0, 0, 7, 0)); err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64mmfr1, From 0274bd7be7daf0e9e6a8743e1daebda5246f155f Mon Sep 17 00:00:00 2001 From: Aaron Lindsay Date: Tue, 29 Aug 2023 16:23:26 -0700 Subject: [PATCH 03/26] target/arm: Add feature detection for FEAT_Pauth2 and extensions Rename isar_feature_aa64_pauth_arch to isar_feature_aa64_pauth_qarma5 to distinguish the other architectural algorithm qarma3. Add ARMPauthFeature and isar_feature_pauth_feature to cover the other pauth conditions. Reviewed-by: Peter Maydell Signed-off-by: Aaron Lindsay Signed-off-by: Richard Henderson Message-id: 20230829232335.965414-4-richard.henderson@linaro.org Message-Id: <20230609172324.982888-3-aaron@os.amperecomputing.com> [rth: Add ARMPauthFeature and eliminate most other predicates] Signed-off-by: Richard Henderson Signed-off-by: Peter Maydell --- target/arm/cpu.h | 47 +++++++++++++++++++++++++++++------ target/arm/tcg/pauth_helper.c | 2 +- 2 files changed, 40 insertions(+), 9 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 9b76cc68c6..225a9b5af5 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -3804,28 +3804,59 @@ static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; } +/* + * These are the values from APA/API/APA3. + * In general these must be compared '>=', per the normal Arm ARM + * treatment of fields in ID registers. + */ +typedef enum { + PauthFeat_None = 0, + PauthFeat_1 = 1, + PauthFeat_EPAC = 2, + PauthFeat_2 = 3, + PauthFeat_FPAC = 4, + PauthFeat_FPACCOMBINED = 5, +} ARMPauthFeature; + +static inline ARMPauthFeature +isar_feature_pauth_feature(const ARMISARegisters *id) +{ + /* + * Architecturally, only one of {APA,API,APA3} may be active (non-zero) + * and the other two must be zero. Thus we may avoid conditionals. + */ + return (FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, APA) | + FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, API) | + FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, APA3)); +} + static inline bool isar_feature_aa64_pauth(const ARMISARegisters *id) { /* * Return true if any form of pauth is enabled, as this * predicate controls migration of the 128-bit keys. */ - return (id->id_aa64isar1 & - (FIELD_DP64(0, ID_AA64ISAR1, APA, 0xf) | - FIELD_DP64(0, ID_AA64ISAR1, API, 0xf) | - FIELD_DP64(0, ID_AA64ISAR1, GPA, 0xf) | - FIELD_DP64(0, ID_AA64ISAR1, GPI, 0xf))) != 0; + return isar_feature_pauth_feature(id) != PauthFeat_None; } -static inline bool isar_feature_aa64_pauth_arch(const ARMISARegisters *id) +static inline bool isar_feature_aa64_pauth_qarma5(const ARMISARegisters *id) { /* - * Return true if pauth is enabled with the architected QARMA algorithm. - * QEMU will always set APA+GPA to the same value. + * Return true if pauth is enabled with the architected QARMA5 algorithm. + * QEMU will always enable or disable both APA and GPA. */ return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, APA) != 0; } +static inline bool isar_feature_aa64_pauth_qarma3(const ARMISARegisters *id) +{ + /* + * Return true if pauth is enabled with the architected QARMA3 algorithm. + * QEMU will always enable or disable both APA3 and GPA3. + */ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, APA3) != 0; +} + static inline bool isar_feature_aa64_tlbirange(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) == 2; diff --git a/target/arm/tcg/pauth_helper.c b/target/arm/tcg/pauth_helper.c index 62af569341..6271a84ec9 100644 --- a/target/arm/tcg/pauth_helper.c +++ b/target/arm/tcg/pauth_helper.c @@ -282,7 +282,7 @@ static uint64_t pauth_computepac_impdef(uint64_t data, uint64_t modifier, static uint64_t pauth_computepac(CPUARMState *env, uint64_t data, uint64_t modifier, ARMPACKey key) { - if (cpu_isar_feature(aa64_pauth_arch, env_archcpu(env))) { + if (cpu_isar_feature(aa64_pauth_qarma5, env_archcpu(env))) { return pauth_computepac_architected(data, modifier, key); } else { return pauth_computepac_impdef(data, modifier, key); From 6c3427eec532d534fae05d8aa740a9dcca5826e8 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 29 Aug 2023 16:23:27 -0700 Subject: [PATCH 04/26] target/arm: Don't change pauth features when changing algorithm We have cpu properties to adjust the pauth algorithm for the purpose of speed of emulation. Retain the set of pauth features supported by the cpu even as the algorithm changes. This already affects the neoverse-v1 cpu, which has FEAT_EPAC. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20230829232335.965414-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/cpu64.c | 70 +++++++++++++++++++++++++++--------------- target/arm/tcg/cpu64.c | 2 ++ 2 files changed, 47 insertions(+), 25 deletions(-) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index 96158093cc..fd584a31da 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -473,37 +473,57 @@ void aarch64_add_sme_properties(Object *obj) void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp) { - int arch_val = 0, impdef_val = 0; - uint64_t t; + ARMPauthFeature features = cpu_isar_feature(pauth_feature, cpu); + uint64_t isar1; - /* Exit early if PAuth is enabled, and fall through to disable it */ - if ((kvm_enabled() || hvf_enabled()) && cpu->prop_pauth) { - if (!cpu_isar_feature(aa64_pauth, cpu)) { - error_setg(errp, "'pauth' feature not supported by %s on this host", - kvm_enabled() ? "KVM" : "hvf"); + /* + * These properties enable or disable Pauth as a whole, or change + * the pauth algorithm, but do not change the set of features that + * are present. We have saved a copy of those features above and + * will now place it into the field that chooses the algorithm. + * + * Begin by disabling all fields. + */ + isar1 = cpu->isar.id_aa64isar1; + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, APA, 0); + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPA, 0); + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, API, 0); + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPI, 0); + + if (kvm_enabled() || hvf_enabled()) { + /* + * Exit early if PAuth is enabled and fall through to disable it. + * The algorithm selection properties are not present. + */ + if (cpu->prop_pauth) { + if (features == 0) { + error_setg(errp, "'pauth' feature not supported by " + "%s on this host", current_accel_name()); + } + return; + } + } else { + /* Pauth properties are only present when the model supports it. */ + if (features == 0) { + assert(!cpu->prop_pauth); + return; } - return; - } - - /* TODO: Handle HaveEnhancedPAC, HaveEnhancedPAC2, HaveFPAC. */ - if (cpu->prop_pauth) { - if (cpu->prop_pauth_impdef) { - impdef_val = 1; - } else { - arch_val = 1; + if (cpu->prop_pauth) { + if (cpu->prop_pauth_impdef) { + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, API, features); + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPI, 1); + } else { + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, APA, features); + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPA, 1); + } + } else if (cpu->prop_pauth_impdef) { + error_setg(errp, "cannot enable pauth-impdef without pauth"); + error_append_hint(errp, "Add pauth=on to the CPU property list.\n"); } - } else if (cpu->prop_pauth_impdef) { - error_setg(errp, "cannot enable pauth-impdef without pauth"); - error_append_hint(errp, "Add pauth=on to the CPU property list.\n"); } - t = cpu->isar.id_aa64isar1; - t = FIELD_DP64(t, ID_AA64ISAR1, APA, arch_val); - t = FIELD_DP64(t, ID_AA64ISAR1, GPA, arch_val); - t = FIELD_DP64(t, ID_AA64ISAR1, API, impdef_val); - t = FIELD_DP64(t, ID_AA64ISAR1, GPI, impdef_val); - cpu->isar.id_aa64isar1 = t; + cpu->isar.id_aa64isar1 = isar1; } static Property arm_cpu_pauth_property = diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index 0f8972950d..4a1d9816df 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -803,6 +803,8 @@ void aarch64_max_tcg_initfn(Object *obj) t = cpu->isar.id_aa64isar1; t = FIELD_DP64(t, ID_AA64ISAR1, DPB, 2); /* FEAT_DPB2 */ + t = FIELD_DP64(t, ID_AA64ISAR1, APA, PauthFeat_1); + t = FIELD_DP64(t, ID_AA64ISAR1, API, 1); t = FIELD_DP64(t, ID_AA64ISAR1, JSCVT, 1); /* FEAT_JSCVT */ t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); /* FEAT_FCMA */ t = FIELD_DP64(t, ID_AA64ISAR1, LRCPC, 2); /* FEAT_LRCPC2 */ From 399e5e71253469630b4a41089ae5fde04d95ac68 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 29 Aug 2023 16:23:28 -0700 Subject: [PATCH 05/26] target/arm: Implement FEAT_PACQARMA3 Implement the QARMA3 cryptographic algorithm for PAC calculation. Implement a cpu feature to select the algorithm and document it. Signed-off-by: Aaron Lindsay Reviewed-by: Peter Maydell Reviewed-by: Richard Henderson Signed-off-by: Richard Henderson Message-id: 20230829232335.965414-6-richard.henderson@linaro.org Message-Id: <20230609172324.982888-4-aaron@os.amperecomputing.com> [rth: Merge cpu feature addition from another patch.] Signed-off-by: Richard Henderson Signed-off-by: Peter Maydell --- docs/system/arm/cpu-features.rst | 21 ++++++++----- docs/system/arm/emulation.rst | 3 ++ target/arm/arm-qmp-cmds.c | 2 +- target/arm/cpu.h | 1 + target/arm/cpu64.c | 24 ++++++++++++-- target/arm/tcg/pauth_helper.c | 54 ++++++++++++++++++++++++++------ tests/qtest/arm-cpu-features.c | 12 ++++++- 7 files changed, 94 insertions(+), 23 deletions(-) diff --git a/docs/system/arm/cpu-features.rst b/docs/system/arm/cpu-features.rst index 6bb88a40c7..a5fb929243 100644 --- a/docs/system/arm/cpu-features.rst +++ b/docs/system/arm/cpu-features.rst @@ -210,15 +210,20 @@ TCG VCPU Features TCG VCPU features are CPU features that are specific to TCG. Below is the list of TCG VCPU features and their descriptions. -``pauth-impdef`` - When ``FEAT_Pauth`` is enabled, either the *impdef* (Implementation - Defined) algorithm is enabled or the *architected* QARMA algorithm - is enabled. By default the impdef algorithm is disabled, and QARMA - is enabled. +``pauth`` + Enable or disable ``FEAT_Pauth`` entirely. - The architected QARMA algorithm has good cryptographic properties, - but can be quite slow to emulate. The impdef algorithm used by QEMU - is non-cryptographic but significantly faster. +``pauth-impdef`` + When ``pauth`` is enabled, select the QEMU implementation defined algorithm. + +``pauth-qarma3`` + When ``pauth`` is enabled, select the architected QARMA3 algorithm. + +Without either ``pauth-impdef`` or ``pauth-qarma3`` enabled, +the architected QARMA5 algorithm is used. The architected QARMA5 +and QARMA3 algorithms have good cryptographic properties, but can +be quite slow to emulate. The impdef algorithm used by QEMU is +non-cryptographic but significantly faster. SVE CPU Properties ================== diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index 2e6a7c8961..c4bc407486 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -57,6 +57,9 @@ the following architecture extensions: - FEAT_MTE (Memory Tagging Extension) - FEAT_MTE2 (Memory Tagging Extension) - FEAT_MTE3 (MTE Asymmetric Fault Handling) +- FEAT_PACIMP (Pointer authentication - IMPLEMENTATION DEFINED algorithm) +- FEAT_PACQARMA3 (Pointer authentication - QARMA3 algorithm) +- FEAT_PACQARMA5 (Pointer authentication - QARMA5 algorithm) - FEAT_PAN (Privileged access never) - FEAT_PAN2 (AT S1E1R and AT S1E1W instruction variants affected by PSTATE.PAN) - FEAT_PAN3 (Support for SCTLR_ELx.EPAN) diff --git a/target/arm/arm-qmp-cmds.c b/target/arm/arm-qmp-cmds.c index c8fa524002..b53d5efe13 100644 --- a/target/arm/arm-qmp-cmds.c +++ b/target/arm/arm-qmp-cmds.c @@ -95,7 +95,7 @@ static const char *cpu_model_advertised_features[] = { "sve640", "sve768", "sve896", "sve1024", "sve1152", "sve1280", "sve1408", "sve1536", "sve1664", "sve1792", "sve1920", "sve2048", "kvm-no-adjvtime", "kvm-steal-time", - "pauth", "pauth-impdef", + "pauth", "pauth-impdef", "pauth-qarma3", NULL }; diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 225a9b5af5..6f75ccfcef 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -1072,6 +1072,7 @@ struct ArchCPU { */ bool prop_pauth; bool prop_pauth_impdef; + bool prop_pauth_qarma3; bool prop_lpa2; /* DCZ blocksize, in log_2(words), ie low 4 bits of DCZID_EL0 */ diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index fd584a31da..f3d87e001f 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -474,7 +474,7 @@ void aarch64_add_sme_properties(Object *obj) void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp) { ARMPauthFeature features = cpu_isar_feature(pauth_feature, cpu); - uint64_t isar1; + uint64_t isar1, isar2; /* * These properties enable or disable Pauth as a whole, or change @@ -490,6 +490,10 @@ void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp) isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, API, 0); isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPI, 0); + isar2 = cpu->isar.id_aa64isar2; + isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, APA3, 0); + isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, GPA3, 0); + if (kvm_enabled() || hvf_enabled()) { /* * Exit early if PAuth is enabled and fall through to disable it. @@ -510,26 +514,39 @@ void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp) } if (cpu->prop_pauth) { + if (cpu->prop_pauth_impdef && cpu->prop_pauth_qarma3) { + error_setg(errp, + "cannot enable both pauth-impdef and pauth-qarma3"); + return; + } + if (cpu->prop_pauth_impdef) { isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, API, features); isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPI, 1); + } else if (cpu->prop_pauth_qarma3) { + isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, APA3, features); + isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, GPA3, 1); } else { isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, APA, features); isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPA, 1); } - } else if (cpu->prop_pauth_impdef) { - error_setg(errp, "cannot enable pauth-impdef without pauth"); + } else if (cpu->prop_pauth_impdef || cpu->prop_pauth_qarma3) { + error_setg(errp, "cannot enable pauth-impdef or " + "pauth-qarma3 without pauth"); error_append_hint(errp, "Add pauth=on to the CPU property list.\n"); } } cpu->isar.id_aa64isar1 = isar1; + cpu->isar.id_aa64isar2 = isar2; } static Property arm_cpu_pauth_property = DEFINE_PROP_BOOL("pauth", ARMCPU, prop_pauth, true); static Property arm_cpu_pauth_impdef_property = DEFINE_PROP_BOOL("pauth-impdef", ARMCPU, prop_pauth_impdef, false); +static Property arm_cpu_pauth_qarma3_property = + DEFINE_PROP_BOOL("pauth-qarma3", ARMCPU, prop_pauth_qarma3, false); void aarch64_add_pauth_properties(Object *obj) { @@ -549,6 +566,7 @@ void aarch64_add_pauth_properties(Object *obj) cpu->prop_pauth = cpu_isar_feature(aa64_pauth, cpu); } else { qdev_property_add_static(DEVICE(obj), &arm_cpu_pauth_impdef_property); + qdev_property_add_static(DEVICE(obj), &arm_cpu_pauth_qarma3_property); } } diff --git a/target/arm/tcg/pauth_helper.c b/target/arm/tcg/pauth_helper.c index 6271a84ec9..bb03409ee5 100644 --- a/target/arm/tcg/pauth_helper.c +++ b/target/arm/tcg/pauth_helper.c @@ -96,6 +96,21 @@ static uint64_t pac_sub(uint64_t i) return o; } +static uint64_t pac_sub1(uint64_t i) +{ + static const uint8_t sub1[16] = { + 0xa, 0xd, 0xe, 0x6, 0xf, 0x7, 0x3, 0x5, + 0x9, 0x8, 0x0, 0xc, 0xb, 0x1, 0x2, 0x4, + }; + uint64_t o = 0; + int b; + + for (b = 0; b < 64; b += 4) { + o |= (uint64_t)sub1[(i >> b) & 0xf] << b; + } + return o; +} + static uint64_t pac_inv_sub(uint64_t i) { static const uint8_t inv_sub[16] = { @@ -209,7 +224,7 @@ static uint64_t tweak_inv_shuffle(uint64_t i) } static uint64_t pauth_computepac_architected(uint64_t data, uint64_t modifier, - ARMPACKey key) + ARMPACKey key, bool isqarma3) { static const uint64_t RC[5] = { 0x0000000000000000ull, @@ -219,6 +234,7 @@ static uint64_t pauth_computepac_architected(uint64_t data, uint64_t modifier, 0x452821E638D01377ull, }; const uint64_t alpha = 0xC0AC29B7C97C50DDull; + int iterations = isqarma3 ? 2 : 4; /* * Note that in the ARM pseudocode, key0 contains bits <127:64> * and key1 contains bits <63:0> of the 128-bit key. @@ -231,7 +247,7 @@ static uint64_t pauth_computepac_architected(uint64_t data, uint64_t modifier, runningmod = modifier; workingval = data ^ key0; - for (i = 0; i <= 4; ++i) { + for (i = 0; i <= iterations; ++i) { roundkey = key1 ^ runningmod; workingval ^= roundkey; workingval ^= RC[i]; @@ -239,32 +255,48 @@ static uint64_t pauth_computepac_architected(uint64_t data, uint64_t modifier, workingval = pac_cell_shuffle(workingval); workingval = pac_mult(workingval); } - workingval = pac_sub(workingval); + if (isqarma3) { + workingval = pac_sub1(workingval); + } else { + workingval = pac_sub(workingval); + } runningmod = tweak_shuffle(runningmod); } roundkey = modk0 ^ runningmod; workingval ^= roundkey; workingval = pac_cell_shuffle(workingval); workingval = pac_mult(workingval); - workingval = pac_sub(workingval); + if (isqarma3) { + workingval = pac_sub1(workingval); + } else { + workingval = pac_sub(workingval); + } workingval = pac_cell_shuffle(workingval); workingval = pac_mult(workingval); workingval ^= key1; workingval = pac_cell_inv_shuffle(workingval); - workingval = pac_inv_sub(workingval); + if (isqarma3) { + workingval = pac_sub1(workingval); + } else { + workingval = pac_inv_sub(workingval); + } workingval = pac_mult(workingval); workingval = pac_cell_inv_shuffle(workingval); workingval ^= key0; workingval ^= runningmod; - for (i = 0; i <= 4; ++i) { - workingval = pac_inv_sub(workingval); - if (i < 4) { + for (i = 0; i <= iterations; ++i) { + if (isqarma3) { + workingval = pac_sub1(workingval); + } else { + workingval = pac_inv_sub(workingval); + } + if (i < iterations) { workingval = pac_mult(workingval); workingval = pac_cell_inv_shuffle(workingval); } runningmod = tweak_inv_shuffle(runningmod); roundkey = key1 ^ runningmod; - workingval ^= RC[4 - i]; + workingval ^= RC[iterations - i]; workingval ^= roundkey; workingval ^= alpha; } @@ -283,7 +315,9 @@ static uint64_t pauth_computepac(CPUARMState *env, uint64_t data, uint64_t modifier, ARMPACKey key) { if (cpu_isar_feature(aa64_pauth_qarma5, env_archcpu(env))) { - return pauth_computepac_architected(data, modifier, key); + return pauth_computepac_architected(data, modifier, key, false); + } else if (cpu_isar_feature(aa64_pauth_qarma3, env_archcpu(env))) { + return pauth_computepac_architected(data, modifier, key, true); } else { return pauth_computepac_impdef(data, modifier, key); } diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c index 3fc33fc24d..a8a4c668ad 100644 --- a/tests/qtest/arm-cpu-features.c +++ b/tests/qtest/arm-cpu-features.c @@ -417,12 +417,22 @@ static void pauth_tests_default(QTestState *qts, const char *cpu_type) { assert_has_feature_enabled(qts, cpu_type, "pauth"); assert_has_feature_disabled(qts, cpu_type, "pauth-impdef"); + assert_has_feature_disabled(qts, cpu_type, "pauth-qarma3"); assert_set_feature(qts, cpu_type, "pauth", false); assert_set_feature(qts, cpu_type, "pauth", true); assert_set_feature(qts, cpu_type, "pauth-impdef", true); assert_set_feature(qts, cpu_type, "pauth-impdef", false); - assert_error(qts, cpu_type, "cannot enable pauth-impdef without pauth", + assert_set_feature(qts, cpu_type, "pauth-qarma3", true); + assert_set_feature(qts, cpu_type, "pauth-qarma3", false); + assert_error(qts, cpu_type, + "cannot enable pauth-impdef or pauth-qarma3 without pauth", "{ 'pauth': false, 'pauth-impdef': true }"); + assert_error(qts, cpu_type, + "cannot enable pauth-impdef or pauth-qarma3 without pauth", + "{ 'pauth': false, 'pauth-qarma3': true }"); + assert_error(qts, cpu_type, + "cannot enable both pauth-impdef and pauth-qarma3", + "{ 'pauth': true, 'pauth-impdef': true, 'pauth-qarma3': true }"); } static void test_query_cpu_model_expansion(const void *data) From c3ccd5669e957d97b340a65295a8f072e218ca46 Mon Sep 17 00:00:00 2001 From: Aaron Lindsay Date: Tue, 29 Aug 2023 16:23:29 -0700 Subject: [PATCH 06/26] target/arm: Implement FEAT_EPAC Signed-off-by: Aaron Lindsay Reviewed-by: Peter Maydell Reviewed-by: Richard Henderson Signed-off-by: Richard Henderson Message-id: 20230829232335.965414-7-richard.henderson@linaro.org Message-Id: <20230609172324.982888-5-aaron@os.amperecomputing.com> Signed-off-by: Richard Henderson Signed-off-by: Peter Maydell --- docs/system/arm/emulation.rst | 1 + target/arm/tcg/cpu64.c | 2 +- target/arm/tcg/pauth_helper.c | 16 +++++++++++----- 3 files changed, 13 insertions(+), 6 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index c4bc407486..2e99888a6a 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -28,6 +28,7 @@ the following architecture extensions: - FEAT_DotProd (Advanced SIMD dot product instructions) - FEAT_DoubleFault (Double Fault Extension) - FEAT_E0PD (Preventing EL0 access to halves of address maps) +- FEAT_EPAC (Enhanced pointer authentication) - FEAT_ETS (Enhanced Translation Synchronization) - FEAT_EVT (Enhanced Virtualization Traps) - FEAT_FCMA (Floating-point complex number instructions) diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index 4a1d9816df..b6a820aae7 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -803,7 +803,7 @@ void aarch64_max_tcg_initfn(Object *obj) t = cpu->isar.id_aa64isar1; t = FIELD_DP64(t, ID_AA64ISAR1, DPB, 2); /* FEAT_DPB2 */ - t = FIELD_DP64(t, ID_AA64ISAR1, APA, PauthFeat_1); + t = FIELD_DP64(t, ID_AA64ISAR1, APA, PauthFeat_EPAC); t = FIELD_DP64(t, ID_AA64ISAR1, API, 1); t = FIELD_DP64(t, ID_AA64ISAR1, JSCVT, 1); /* FEAT_JSCVT */ t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); /* FEAT_FCMA */ diff --git a/target/arm/tcg/pauth_helper.c b/target/arm/tcg/pauth_helper.c index bb03409ee5..63e1009ea7 100644 --- a/target/arm/tcg/pauth_helper.c +++ b/target/arm/tcg/pauth_helper.c @@ -326,8 +326,10 @@ static uint64_t pauth_computepac(CPUARMState *env, uint64_t data, static uint64_t pauth_addpac(CPUARMState *env, uint64_t ptr, uint64_t modifier, ARMPACKey *key, bool data) { + ARMCPU *cpu = env_archcpu(env); ARMMMUIdx mmu_idx = arm_stage1_mmu_idx(env); ARMVAParameters param = aa64_va_parameters(env, ptr, mmu_idx, data, false); + ARMPauthFeature pauth_feature = cpu_isar_feature(pauth_feature, cpu); uint64_t pac, ext_ptr, ext, test; int bot_bit, top_bit; @@ -351,11 +353,15 @@ static uint64_t pauth_addpac(CPUARMState *env, uint64_t ptr, uint64_t modifier, */ test = sextract64(ptr, bot_bit, top_bit - bot_bit); if (test != 0 && test != -1) { - /* - * Note that our top_bit is one greater than the pseudocode's - * version, hence "- 2" here. - */ - pac ^= MAKE_64BIT_MASK(top_bit - 2, 1); + if (pauth_feature == PauthFeat_EPAC) { + pac = 0; + } else { + /* + * Note that our top_bit is one greater than the pseudocode's + * version, hence "- 2" here. + */ + pac ^= MAKE_64BIT_MASK(top_bit - 2, 1); + } } /* From c7c807f6dd6dbc382225d3e0eb35545ca3f50f86 Mon Sep 17 00:00:00 2001 From: Aaron Lindsay Date: Tue, 29 Aug 2023 16:23:30 -0700 Subject: [PATCH 07/26] target/arm: Implement FEAT_Pauth2 Signed-off-by: Aaron Lindsay Reviewed-by: Peter Maydell Reviewed-by: Richard Henderson Signed-off-by: Richard Henderson Message-id: 20230829232335.965414-8-richard.henderson@linaro.org Message-Id: <20230609172324.982888-6-aaron@os.amperecomputing.com> Signed-off-by: Richard Henderson Signed-off-by: Peter Maydell --- docs/system/arm/emulation.rst | 1 + target/arm/tcg/cpu64.c | 2 +- target/arm/tcg/pauth_helper.c | 21 +++++++++++++++++---- 3 files changed, 19 insertions(+), 5 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index 2e99888a6a..b5a667527b 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -65,6 +65,7 @@ the following architecture extensions: - FEAT_PAN2 (AT S1E1R and AT S1E1W instruction variants affected by PSTATE.PAN) - FEAT_PAN3 (Support for SCTLR_ELx.EPAN) - FEAT_PAuth (Pointer authentication) +- FEAT_PAuth2 (Enhacements to pointer authentication) - FEAT_PMULL (PMULL, PMULL2 instructions) - FEAT_PMUv3p1 (PMU Extensions v3.1) - FEAT_PMUv3p4 (PMU Extensions v3.4) diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index b6a820aae7..be10370250 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -803,7 +803,7 @@ void aarch64_max_tcg_initfn(Object *obj) t = cpu->isar.id_aa64isar1; t = FIELD_DP64(t, ID_AA64ISAR1, DPB, 2); /* FEAT_DPB2 */ - t = FIELD_DP64(t, ID_AA64ISAR1, APA, PauthFeat_EPAC); + t = FIELD_DP64(t, ID_AA64ISAR1, APA, PauthFeat_2); t = FIELD_DP64(t, ID_AA64ISAR1, API, 1); t = FIELD_DP64(t, ID_AA64ISAR1, JSCVT, 1); /* FEAT_JSCVT */ t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); /* FEAT_FCMA */ diff --git a/target/arm/tcg/pauth_helper.c b/target/arm/tcg/pauth_helper.c index 63e1009ea7..b6aeb90548 100644 --- a/target/arm/tcg/pauth_helper.c +++ b/target/arm/tcg/pauth_helper.c @@ -353,7 +353,9 @@ static uint64_t pauth_addpac(CPUARMState *env, uint64_t ptr, uint64_t modifier, */ test = sextract64(ptr, bot_bit, top_bit - bot_bit); if (test != 0 && test != -1) { - if (pauth_feature == PauthFeat_EPAC) { + if (pauth_feature >= PauthFeat_2) { + /* No action required */ + } else if (pauth_feature == PauthFeat_EPAC) { pac = 0; } else { /* @@ -368,6 +370,9 @@ static uint64_t pauth_addpac(CPUARMState *env, uint64_t ptr, uint64_t modifier, * Preserve the determination between upper and lower at bit 55, * and insert pointer authentication code. */ + if (pauth_feature >= PauthFeat_2) { + pac ^= ptr; + } if (param.tbi) { ptr &= ~MAKE_64BIT_MASK(bot_bit, 55 - bot_bit + 1); pac &= MAKE_64BIT_MASK(bot_bit, 54 - bot_bit + 1); @@ -394,18 +399,26 @@ static uint64_t pauth_original_ptr(uint64_t ptr, ARMVAParameters param) static uint64_t pauth_auth(CPUARMState *env, uint64_t ptr, uint64_t modifier, ARMPACKey *key, bool data, int keynumber) { + ARMCPU *cpu = env_archcpu(env); ARMMMUIdx mmu_idx = arm_stage1_mmu_idx(env); ARMVAParameters param = aa64_va_parameters(env, ptr, mmu_idx, data, false); + ARMPauthFeature pauth_feature = cpu_isar_feature(pauth_feature, cpu); int bot_bit, top_bit; - uint64_t pac, orig_ptr, test; + uint64_t pac, orig_ptr, cmp_mask; orig_ptr = pauth_original_ptr(ptr, param); pac = pauth_computepac(env, orig_ptr, modifier, *key); bot_bit = 64 - param.tsz; top_bit = 64 - 8 * param.tbi; - test = (pac ^ ptr) & ~MAKE_64BIT_MASK(55, 1); - if (unlikely(extract64(test, bot_bit, top_bit - bot_bit))) { + cmp_mask = MAKE_64BIT_MASK(bot_bit, top_bit - bot_bit); + cmp_mask &= ~MAKE_64BIT_MASK(55, 1); + + if (pauth_feature >= PauthFeat_2) { + return ptr ^ (pac & cmp_mask); + } + + if ((pac ^ ptr) & cmp_mask) { int error_code = (keynumber << 1) | (keynumber ^ 1); if (param.tbi) { return deposit64(orig_ptr, 53, 2, error_code); From 28b9dcb74bf709e4f18bc99da3e946849f9aef17 Mon Sep 17 00:00:00 2001 From: Aaron Lindsay Date: Tue, 29 Aug 2023 16:23:31 -0700 Subject: [PATCH 08/26] target/arm: Inform helpers whether a PAC instruction is 'combined' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit An instruction is a 'combined' Pointer Authentication instruction if it does something in addition to PAC -- for instance, branching to or loading an address from the authenticated pointer. Knowing whether a PAC operation is 'combined' is needed to implement FEAT_FPACCOMBINE. Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Aaron Lindsay Reviewed-by: Richard Henderson Signed-off-by: Richard Henderson Message-id: 20230829232335.965414-9-richard.henderson@linaro.org Message-Id: <20230609172324.982888-7-aaron@os.amperecomputing.com> Signed-off-by: Richard Henderson Signed-off-by: Peter Maydell --- target/arm/tcg/helper-a64.h | 4 ++ target/arm/tcg/pauth_helper.c | 71 +++++++++++++++++++++++++++------- target/arm/tcg/translate-a64.c | 12 +++--- 3 files changed, 68 insertions(+), 19 deletions(-) diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index 3d5957c11f..57cfd68569 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -90,9 +90,13 @@ DEF_HELPER_FLAGS_3(pacda, TCG_CALL_NO_WG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(pacdb, TCG_CALL_NO_WG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(pacga, TCG_CALL_NO_WG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(autia, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(autia_combined, TCG_CALL_NO_WG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(autib, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(autib_combined, TCG_CALL_NO_WG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(autda, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(autda_combined, TCG_CALL_NO_WG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(autdb, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(autdb_combined, TCG_CALL_NO_WG, i64, env, i64, i64) DEF_HELPER_FLAGS_2(xpaci, TCG_CALL_NO_RWG_SE, i64, env, i64) DEF_HELPER_FLAGS_2(xpacd, TCG_CALL_NO_RWG_SE, i64, env, i64) diff --git a/target/arm/tcg/pauth_helper.c b/target/arm/tcg/pauth_helper.c index b6aeb90548..c05c5b30ff 100644 --- a/target/arm/tcg/pauth_helper.c +++ b/target/arm/tcg/pauth_helper.c @@ -397,7 +397,8 @@ static uint64_t pauth_original_ptr(uint64_t ptr, ARMVAParameters param) } static uint64_t pauth_auth(CPUARMState *env, uint64_t ptr, uint64_t modifier, - ARMPACKey *key, bool data, int keynumber) + ARMPACKey *key, bool data, int keynumber, + uintptr_t ra, bool is_combined) { ARMCPU *cpu = env_archcpu(env); ARMMMUIdx mmu_idx = arm_stage1_mmu_idx(env); @@ -519,44 +520,88 @@ uint64_t HELPER(pacga)(CPUARMState *env, uint64_t x, uint64_t y) return pac & 0xffffffff00000000ull; } -uint64_t HELPER(autia)(CPUARMState *env, uint64_t x, uint64_t y) +static uint64_t pauth_autia(CPUARMState *env, uint64_t x, uint64_t y, + uintptr_t ra, bool is_combined) { int el = arm_current_el(env); if (!pauth_key_enabled(env, el, SCTLR_EnIA)) { return x; } - pauth_check_trap(env, el, GETPC()); - return pauth_auth(env, x, y, &env->keys.apia, false, 0); + pauth_check_trap(env, el, ra); + return pauth_auth(env, x, y, &env->keys.apia, false, 0, ra, is_combined); } -uint64_t HELPER(autib)(CPUARMState *env, uint64_t x, uint64_t y) +uint64_t HELPER(autia)(CPUARMState *env, uint64_t x, uint64_t y) +{ + return pauth_autia(env, x, y, GETPC(), false); +} + +uint64_t HELPER(autia_combined)(CPUARMState *env, uint64_t x, uint64_t y) +{ + return pauth_autia(env, x, y, GETPC(), true); +} + +static uint64_t pauth_autib(CPUARMState *env, uint64_t x, uint64_t y, + uintptr_t ra, bool is_combined) { int el = arm_current_el(env); if (!pauth_key_enabled(env, el, SCTLR_EnIB)) { return x; } - pauth_check_trap(env, el, GETPC()); - return pauth_auth(env, x, y, &env->keys.apib, false, 1); + pauth_check_trap(env, el, ra); + return pauth_auth(env, x, y, &env->keys.apib, false, 1, ra, is_combined); } -uint64_t HELPER(autda)(CPUARMState *env, uint64_t x, uint64_t y) +uint64_t HELPER(autib)(CPUARMState *env, uint64_t x, uint64_t y) +{ + return pauth_autib(env, x, y, GETPC(), false); +} + +uint64_t HELPER(autib_combined)(CPUARMState *env, uint64_t x, uint64_t y) +{ + return pauth_autib(env, x, y, GETPC(), true); +} + +static uint64_t pauth_autda(CPUARMState *env, uint64_t x, uint64_t y, + uintptr_t ra, bool is_combined) { int el = arm_current_el(env); if (!pauth_key_enabled(env, el, SCTLR_EnDA)) { return x; } - pauth_check_trap(env, el, GETPC()); - return pauth_auth(env, x, y, &env->keys.apda, true, 0); + pauth_check_trap(env, el, ra); + return pauth_auth(env, x, y, &env->keys.apda, true, 0, ra, is_combined); } -uint64_t HELPER(autdb)(CPUARMState *env, uint64_t x, uint64_t y) +uint64_t HELPER(autda)(CPUARMState *env, uint64_t x, uint64_t y) +{ + return pauth_autda(env, x, y, GETPC(), false); +} + +uint64_t HELPER(autda_combined)(CPUARMState *env, uint64_t x, uint64_t y) +{ + return pauth_autda(env, x, y, GETPC(), true); +} + +static uint64_t pauth_autdb(CPUARMState *env, uint64_t x, uint64_t y, + uintptr_t ra, bool is_combined) { int el = arm_current_el(env); if (!pauth_key_enabled(env, el, SCTLR_EnDB)) { return x; } - pauth_check_trap(env, el, GETPC()); - return pauth_auth(env, x, y, &env->keys.apdb, true, 1); + pauth_check_trap(env, el, ra); + return pauth_auth(env, x, y, &env->keys.apdb, true, 1, ra, is_combined); +} + +uint64_t HELPER(autdb)(CPUARMState *env, uint64_t x, uint64_t y) +{ + return pauth_autdb(env, x, y, GETPC(), false); +} + +uint64_t HELPER(autdb_combined)(CPUARMState *env, uint64_t x, uint64_t y) +{ + return pauth_autdb(env, x, y, GETPC(), true); } uint64_t HELPER(xpaci)(CPUARMState *env, uint64_t a) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 0b77c92437..c2bd96f5d4 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -1530,9 +1530,9 @@ static TCGv_i64 auth_branch_target(DisasContext *s, TCGv_i64 dst, truedst = tcg_temp_new_i64(); if (use_key_a) { - gen_helper_autia(truedst, cpu_env, dst, modifier); + gen_helper_autia_combined(truedst, cpu_env, dst, modifier); } else { - gen_helper_autib(truedst, cpu_env, dst, modifier); + gen_helper_autib_combined(truedst, cpu_env, dst, modifier); } return truedst; } @@ -3352,11 +3352,11 @@ static bool trans_LDRA(DisasContext *s, arg_LDRA *a) if (s->pauth_active) { if (!a->m) { - gen_helper_autda(dirty_addr, cpu_env, dirty_addr, - tcg_constant_i64(0)); + gen_helper_autda_combined(dirty_addr, cpu_env, dirty_addr, + tcg_constant_i64(0)); } else { - gen_helper_autdb(dirty_addr, cpu_env, dirty_addr, - tcg_constant_i64(0)); + gen_helper_autdb_combined(dirty_addr, cpu_env, dirty_addr, + tcg_constant_i64(0)); } } From 8a69a42340a5f6b0d6d4b3b68de9919b3e59e712 Mon Sep 17 00:00:00 2001 From: Aaron Lindsay Date: Tue, 29 Aug 2023 16:23:32 -0700 Subject: [PATCH 09/26] target/arm: Implement FEAT_FPAC and FEAT_FPACCOMBINE Signed-off-by: Aaron Lindsay Reviewed-by: Richard Henderson Signed-off-by: Richard Henderson Message-id: 20230829232335.965414-10-richard.henderson@linaro.org Message-Id: <20230609172324.982888-8-aaron@os.amperecomputing.com> [rth: Simplify fpac comparison, reusing cmp_mask] Signed-off-by: Richard Henderson Signed-off-by: Peter Maydell --- docs/system/arm/emulation.rst | 2 ++ target/arm/syndrome.h | 7 +++++++ target/arm/tcg/cpu64.c | 2 +- target/arm/tcg/pauth_helper.c | 18 +++++++++++++++++- 4 files changed, 27 insertions(+), 2 deletions(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index b5a667527b..305b36b19e 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -35,6 +35,8 @@ the following architecture extensions: - FEAT_FGT (Fine-Grained Traps) - FEAT_FHM (Floating-point half-precision multiplication instructions) - FEAT_FP16 (Half-precision floating-point data processing) +- FEAT_FPAC (Faulting on AUT* instructions) +- FEAT_FPACCOMBINE (Faulting on combined pointer authentication instructions) - FEAT_FRINTTS (Floating-point to integer instructions) - FEAT_FlagM (Flag manipulation instructions v2) - FEAT_FlagM2 (Enhancements to flag manipulation instructions) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index 62254d0e51..8a6b8f8162 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -49,6 +49,7 @@ enum arm_exception_class { EC_SYSTEMREGISTERTRAP = 0x18, EC_SVEACCESSTRAP = 0x19, EC_ERETTRAP = 0x1a, + EC_PACFAIL = 0x1c, EC_SMETRAP = 0x1d, EC_GPC = 0x1e, EC_INSNABORT = 0x20, @@ -232,6 +233,12 @@ static inline uint32_t syn_smetrap(SMEExceptionType etype, bool is_16bit) | (is_16bit ? 0 : ARM_EL_IL) | etype; } +static inline uint32_t syn_pacfail(bool data, int keynumber) +{ + int error_code = (data << 1) | keynumber; + return (EC_PACFAIL << ARM_EL_EC_SHIFT) | ARM_EL_IL | error_code; +} + static inline uint32_t syn_pactrap(void) { return EC_PACTRAP << ARM_EL_EC_SHIFT; diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index be10370250..ef222da57d 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -803,7 +803,7 @@ void aarch64_max_tcg_initfn(Object *obj) t = cpu->isar.id_aa64isar1; t = FIELD_DP64(t, ID_AA64ISAR1, DPB, 2); /* FEAT_DPB2 */ - t = FIELD_DP64(t, ID_AA64ISAR1, APA, PauthFeat_2); + t = FIELD_DP64(t, ID_AA64ISAR1, APA, PauthFeat_FPACCOMBINED); t = FIELD_DP64(t, ID_AA64ISAR1, API, 1); t = FIELD_DP64(t, ID_AA64ISAR1, JSCVT, 1); /* FEAT_JSCVT */ t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); /* FEAT_FCMA */ diff --git a/target/arm/tcg/pauth_helper.c b/target/arm/tcg/pauth_helper.c index c05c5b30ff..4da2962ad5 100644 --- a/target/arm/tcg/pauth_helper.c +++ b/target/arm/tcg/pauth_helper.c @@ -396,6 +396,14 @@ static uint64_t pauth_original_ptr(uint64_t ptr, ARMVAParameters param) } } +static G_NORETURN +void pauth_fail_exception(CPUARMState *env, bool data, + int keynumber, uintptr_t ra) +{ + raise_exception_ra(env, EXCP_UDEF, syn_pacfail(data, keynumber), + exception_target_el(env), ra); +} + static uint64_t pauth_auth(CPUARMState *env, uint64_t ptr, uint64_t modifier, ARMPACKey *key, bool data, int keynumber, uintptr_t ra, bool is_combined) @@ -416,7 +424,15 @@ static uint64_t pauth_auth(CPUARMState *env, uint64_t ptr, uint64_t modifier, cmp_mask &= ~MAKE_64BIT_MASK(55, 1); if (pauth_feature >= PauthFeat_2) { - return ptr ^ (pac & cmp_mask); + ARMPauthFeature fault_feature = + is_combined ? PauthFeat_FPACCOMBINED : PauthFeat_FPAC; + uint64_t result = ptr ^ (pac & cmp_mask); + + if (pauth_feature >= fault_feature + && ((result ^ sextract64(result, 55, 1)) & cmp_mask)) { + pauth_fail_exception(env, data, keynumber, ra); + } + return result; } if ((pac ^ ptr) & cmp_mask) { From 0df11497c206666d21715e42cc765d96b4f3413b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Philippe=20Mathieu-Daud=C3=A9?= Date: Thu, 31 Aug 2023 15:13:48 +0200 Subject: [PATCH 10/26] hw/intc/arm_gicv3_its: Avoid maybe-uninitialized error in get_vte() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix when using GCC v11.4 (Ubuntu 11.4.0-1ubuntu1~22.04) with CFLAGS=-Og: [4/6] Compiling C object libcommon.fa.p/hw_intc_arm_gicv3_its.c.o FAILED: libcommon.fa.p/hw_intc_arm_gicv3_its.c.o inlined from ‘lookup_vte’ at hw/intc/arm_gicv3_its.c:453:9, inlined from ‘vmovp_callback’ at hw/intc/arm_gicv3_its.c:1039:14: hw/intc/arm_gicv3_its.c:347:9: error: ‘vte.rdbase’ may be used uninitialized [-Werror=maybe-uninitialized] 347 | trace_gicv3_its_vte_read(vpeid, vte->valid, vte->vptsize, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 348 | vte->vptaddr, vte->rdbase); | ~~~~~~~~~~~~~~~~~~~~~~~~~~ hw/intc/arm_gicv3_its.c: In function ‘vmovp_callback’: hw/intc/arm_gicv3_its.c:1036:13: note: ‘vte’ declared here 1036 | VTEntry vte; | ^~~ Signed-off-by: Philippe Mathieu-Daudé Reviewed-by: Alex Bennée Message-id: 20230831131348.69032-1-philmd@linaro.org Signed-off-by: Peter Maydell --- hw/intc/arm_gicv3_its.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index 43dfd7a35c..5f552b4d37 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -330,23 +330,20 @@ static MemTxResult get_vte(GICv3ITSState *s, uint32_t vpeid, VTEntry *vte) if (entry_addr == -1) { /* No L2 table entry, i.e. no valid VTE, or a memory error */ vte->valid = false; - goto out; + trace_gicv3_its_vte_read_fault(vpeid); + return MEMTX_OK; } vteval = address_space_ldq_le(as, entry_addr, MEMTXATTRS_UNSPECIFIED, &res); if (res != MEMTX_OK) { - goto out; + trace_gicv3_its_vte_read_fault(vpeid); + return res; } 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); - } + trace_gicv3_its_vte_read(vpeid, vte->valid, vte->vptsize, + vte->vptaddr, vte->rdbase); return res; } From 5a8559e2cc07f56470be5709efd17e5514a6a217 Mon Sep 17 00:00:00 2001 From: Francisco Iglesias Date: Thu, 31 Aug 2023 17:56:54 +0100 Subject: [PATCH 11/26] hw/misc: Introduce the Xilinx CFI interface Introduce the Xilinx Configuration Frame Interface (CFI) for transmitting CFI data packets between the Xilinx Configuration Frame Unit models (CFU_APB, CFU_FDRO and CFU_SFR), the Xilinx CFRAME controller (CFRAME_REG) and the Xilinx CFRAME broadcast controller (CFRAME_BCAST_REG) models (when emulating bitstream programming and readback). Signed-off-by: Francisco Iglesias Reviewed-by: Sai Pavan Boddu Acked-by: Edgar E. Iglesias Message-id: 20230831165701.2016397-2-francisco.iglesias@amd.com Signed-off-by: Peter Maydell --- MAINTAINERS | 6 ++++ hw/misc/meson.build | 1 + hw/misc/xlnx-cfi-if.c | 34 ++++++++++++++++++++ include/hw/misc/xlnx-cfi-if.h | 59 +++++++++++++++++++++++++++++++++++ 4 files changed, 100 insertions(+) create mode 100644 hw/misc/xlnx-cfi-if.c create mode 100644 include/hw/misc/xlnx-cfi-if.h diff --git a/MAINTAINERS b/MAINTAINERS index b471973e1e..4b9512eda9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1026,6 +1026,12 @@ S: Maintained F: hw/ssi/xlnx-versal-ospi.c F: include/hw/ssi/xlnx-versal-ospi.h +Xilinx Versal CFI +M: Francisco Iglesias +S: Maintained +F: hw/misc/xlnx-cfi-if.c +F: include/hw/misc/xlnx-cfi-if.h + STM32F100 M: Alexandre Iooss L: qemu-arm@nongnu.org diff --git a/hw/misc/meson.build b/hw/misc/meson.build index d9a370c1de..593c7591fc 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -98,6 +98,7 @@ specific_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files('xlnx-versal-crl.c')) system_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files( 'xlnx-versal-xramc.c', 'xlnx-versal-pmc-iou-slcr.c', + 'xlnx-cfi-if.c', )) system_ss.add(when: 'CONFIG_STM32F2XX_SYSCFG', if_true: files('stm32f2xx_syscfg.c')) system_ss.add(when: 'CONFIG_STM32F4XX_SYSCFG', if_true: files('stm32f4xx_syscfg.c')) diff --git a/hw/misc/xlnx-cfi-if.c b/hw/misc/xlnx-cfi-if.c new file mode 100644 index 0000000000..c45f05c4aa --- /dev/null +++ b/hw/misc/xlnx-cfi-if.c @@ -0,0 +1,34 @@ +/* + * Xilinx CFI interface + * + * Copyright (C) 2023, Advanced Micro Devices, Inc. + * + * Written by Francisco Iglesias + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#include "qemu/osdep.h" +#include "hw/misc/xlnx-cfi-if.h" + +void xlnx_cfi_transfer_packet(XlnxCfiIf *cfi_if, XlnxCfiPacket *pkt) +{ + XlnxCfiIfClass *xcic = XLNX_CFI_IF_GET_CLASS(cfi_if); + + if (xcic->cfi_transfer_packet) { + xcic->cfi_transfer_packet(cfi_if, pkt); + } +} + +static const TypeInfo xlnx_cfi_if_info = { + .name = TYPE_XLNX_CFI_IF, + .parent = TYPE_INTERFACE, + .class_size = sizeof(XlnxCfiIfClass), +}; + +static void xlnx_cfi_if_register_types(void) +{ + type_register_static(&xlnx_cfi_if_info); +} + +type_init(xlnx_cfi_if_register_types) + diff --git a/include/hw/misc/xlnx-cfi-if.h b/include/hw/misc/xlnx-cfi-if.h new file mode 100644 index 0000000000..f9bd12292d --- /dev/null +++ b/include/hw/misc/xlnx-cfi-if.h @@ -0,0 +1,59 @@ +/* + * Xilinx CFI interface + * + * Copyright (C) 2023, Advanced Micro Devices, Inc. + * + * Written by Francisco Iglesias + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#ifndef XLNX_CFI_IF_H +#define XLNX_CFI_IF_H 1 + +#include "qemu/help-texts.h" +#include "hw/hw.h" +#include "qom/object.h" + +#define TYPE_XLNX_CFI_IF "xlnx-cfi-if" +typedef struct XlnxCfiIfClass XlnxCfiIfClass; +DECLARE_CLASS_CHECKERS(XlnxCfiIfClass, XLNX_CFI_IF, TYPE_XLNX_CFI_IF) + +#define XLNX_CFI_IF(obj) \ + INTERFACE_CHECK(XlnxCfiIf, (obj), TYPE_XLNX_CFI_IF) + +typedef enum { + PACKET_TYPE_CFU = 0x52, + PACKET_TYPE_CFRAME = 0xA1, +} xlnx_cfi_packet_type; + +typedef enum { + CFRAME_FAR = 1, + CFRAME_SFR = 2, + CFRAME_FDRI = 4, + CFRAME_CMD = 6, +} xlnx_cfi_reg_addr; + +typedef struct XlnxCfiPacket { + uint8_t reg_addr; + uint32_t data[4]; +} XlnxCfiPacket; + +typedef struct XlnxCfiIf { + Object Parent; +} XlnxCfiIf; + +typedef struct XlnxCfiIfClass { + InterfaceClass parent; + + void (*cfi_transfer_packet)(XlnxCfiIf *cfi_if, XlnxCfiPacket *pkt); +} XlnxCfiIfClass; + +/** + * Transfer a XlnxCfiPacket. + * + * @cfi_if: the object implementing this interface + * @XlnxCfiPacket: a pointer to the XlnxCfiPacket to transfer + */ +void xlnx_cfi_transfer_packet(XlnxCfiIf *cfi_if, XlnxCfiPacket *pkt); + +#endif /* XLNX_CFI_IF_H */ From 86d916c62145168120ec97a71404d91c0aa72835 Mon Sep 17 00:00:00 2001 From: Francisco Iglesias Date: Thu, 31 Aug 2023 17:56:55 +0100 Subject: [PATCH 12/26] hw/misc: Introduce a model of Xilinx Versal's CFU_APB Introduce a model of the software programming interface (CFU_APB) of Xilinx Versal's Configuration Frame Unit. Signed-off-by: Francisco Iglesias Reviewed-by: Peter Maydell Message-id: 20230831165701.2016397-3-francisco.iglesias@amd.com Signed-off-by: Peter Maydell --- MAINTAINERS | 2 + hw/misc/meson.build | 1 + hw/misc/xlnx-versal-cfu.c | 380 ++++++++++++++++++++++++++++++ include/hw/misc/xlnx-versal-cfu.h | 231 ++++++++++++++++++ 4 files changed, 614 insertions(+) create mode 100644 hw/misc/xlnx-versal-cfu.c create mode 100644 include/hw/misc/xlnx-versal-cfu.h diff --git a/MAINTAINERS b/MAINTAINERS index 4b9512eda9..5b01fbe065 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1031,6 +1031,8 @@ M: Francisco Iglesias S: Maintained F: hw/misc/xlnx-cfi-if.c F: include/hw/misc/xlnx-cfi-if.h +F: hw/misc/xlnx-versal-cfu.c +F: include/hw/misc/xlnx-versal-cfu.h STM32F100 M: Alexandre Iooss diff --git a/hw/misc/meson.build b/hw/misc/meson.build index 593c7591fc..3135697d74 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -98,6 +98,7 @@ specific_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files('xlnx-versal-crl.c')) system_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files( 'xlnx-versal-xramc.c', 'xlnx-versal-pmc-iou-slcr.c', + 'xlnx-versal-cfu.c', 'xlnx-cfi-if.c', )) system_ss.add(when: 'CONFIG_STM32F2XX_SYSCFG', if_true: files('stm32f2xx_syscfg.c')) diff --git a/hw/misc/xlnx-versal-cfu.c b/hw/misc/xlnx-versal-cfu.c new file mode 100644 index 0000000000..b2dc6ab211 --- /dev/null +++ b/hw/misc/xlnx-versal-cfu.c @@ -0,0 +1,380 @@ +/* + * QEMU model of the CFU Configuration Unit. + * + * Copyright (C) 2023, Advanced Micro Devices, Inc. + * + * Written by Edgar E. Iglesias , + * Sai Pavan Boddu , + * Francisco Iglesias + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "hw/sysbus.h" +#include "hw/register.h" +#include "hw/irq.h" +#include "qemu/bitops.h" +#include "qemu/log.h" +#include "qemu/units.h" +#include "migration/vmstate.h" +#include "hw/qdev-properties.h" +#include "hw/qdev-properties-system.h" +#include "hw/misc/xlnx-versal-cfu.h" + +#ifndef XLNX_VERSAL_CFU_APB_ERR_DEBUG +#define XLNX_VERSAL_CFU_APB_ERR_DEBUG 0 +#endif + +#define KEYHOLE_STREAM_4K (4 * KiB) +#define KEYHOLE_STREAM_256K (256 * KiB) +#define CFRAME_BROADCAST_ROW 0x1F + +bool update_wfifo(hwaddr addr, uint64_t value, + uint32_t *wfifo, uint32_t *wfifo_ret) +{ + unsigned int idx = extract32(addr, 2, 2); + + wfifo[idx] = value; + + if (idx == 3) { + memcpy(wfifo_ret, wfifo, WFIFO_SZ * sizeof(uint32_t)); + memset(wfifo, 0, WFIFO_SZ * sizeof(uint32_t)); + return true; + } + + return false; +} + +static void cfu_imr_update_irq(XlnxVersalCFUAPB *s) +{ + bool pending = s->regs[R_CFU_ISR] & ~s->regs[R_CFU_IMR]; + qemu_set_irq(s->irq_cfu_imr, pending); +} + +static void cfu_isr_postw(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCFUAPB *s = XLNX_VERSAL_CFU_APB(reg->opaque); + cfu_imr_update_irq(s); +} + +static uint64_t cfu_ier_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCFUAPB *s = XLNX_VERSAL_CFU_APB(reg->opaque); + uint32_t val = val64; + + s->regs[R_CFU_IMR] &= ~val; + cfu_imr_update_irq(s); + return 0; +} + +static uint64_t cfu_idr_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCFUAPB *s = XLNX_VERSAL_CFU_APB(reg->opaque); + uint32_t val = val64; + + s->regs[R_CFU_IMR] |= val; + cfu_imr_update_irq(s); + return 0; +} + +static uint64_t cfu_itr_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCFUAPB *s = XLNX_VERSAL_CFU_APB(reg->opaque); + uint32_t val = val64; + + s->regs[R_CFU_ISR] |= val; + cfu_imr_update_irq(s); + return 0; +} + +static void cfu_fgcr_postw(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCFUAPB *s = XLNX_VERSAL_CFU_APB(reg->opaque); + uint32_t val = (uint32_t)val64; + + /* Do a scan. It always looks good. */ + if (FIELD_EX32(val, CFU_FGCR, SC_HBC_TRIGGER)) { + ARRAY_FIELD_DP32(s->regs, CFU_STATUS, SCAN_CLEAR_PASS, 1); + ARRAY_FIELD_DP32(s->regs, CFU_STATUS, SCAN_CLEAR_DONE, 1); + } +} + +static const RegisterAccessInfo cfu_apb_regs_info[] = { + { .name = "CFU_ISR", .addr = A_CFU_ISR, + .rsvd = 0xfffffc00, + .w1c = 0x3ff, + .post_write = cfu_isr_postw, + },{ .name = "CFU_IMR", .addr = A_CFU_IMR, + .reset = 0x3ff, + .rsvd = 0xfffffc00, + .ro = 0x3ff, + },{ .name = "CFU_IER", .addr = A_CFU_IER, + .rsvd = 0xfffffc00, + .pre_write = cfu_ier_prew, + },{ .name = "CFU_IDR", .addr = A_CFU_IDR, + .rsvd = 0xfffffc00, + .pre_write = cfu_idr_prew, + },{ .name = "CFU_ITR", .addr = A_CFU_ITR, + .rsvd = 0xfffffc00, + .pre_write = cfu_itr_prew, + },{ .name = "CFU_PROTECT", .addr = A_CFU_PROTECT, + .reset = 0x1, + },{ .name = "CFU_FGCR", .addr = A_CFU_FGCR, + .rsvd = 0xffff8000, + .post_write = cfu_fgcr_postw, + },{ .name = "CFU_CTL", .addr = A_CFU_CTL, + .rsvd = 0xffff0000, + },{ .name = "CFU_CRAM_RW", .addr = A_CFU_CRAM_RW, + .reset = 0x401f7d9, + .rsvd = 0xf8000000, + },{ .name = "CFU_MASK", .addr = A_CFU_MASK, + },{ .name = "CFU_CRC_EXPECT", .addr = A_CFU_CRC_EXPECT, + },{ .name = "CFU_CFRAME_LEFT_T0", .addr = A_CFU_CFRAME_LEFT_T0, + .rsvd = 0xfff00000, + },{ .name = "CFU_CFRAME_LEFT_T1", .addr = A_CFU_CFRAME_LEFT_T1, + .rsvd = 0xfff00000, + },{ .name = "CFU_CFRAME_LEFT_T2", .addr = A_CFU_CFRAME_LEFT_T2, + .rsvd = 0xfff00000, + },{ .name = "CFU_ROW_RANGE", .addr = A_CFU_ROW_RANGE, + .rsvd = 0xffffffc0, + .ro = 0x3f, + },{ .name = "CFU_STATUS", .addr = A_CFU_STATUS, + .rsvd = 0x80000000, + .ro = 0x7fffffff, + },{ .name = "CFU_INTERNAL_STATUS", .addr = A_CFU_INTERNAL_STATUS, + .rsvd = 0xff800000, + .ro = 0x7fffff, + },{ .name = "CFU_QWORD_CNT", .addr = A_CFU_QWORD_CNT, + .ro = 0xffffffff, + },{ .name = "CFU_CRC_LIVE", .addr = A_CFU_CRC_LIVE, + .ro = 0xffffffff, + },{ .name = "CFU_PENDING_READ_CNT", .addr = A_CFU_PENDING_READ_CNT, + .rsvd = 0xfe000000, + .ro = 0x1ffffff, + },{ .name = "CFU_FDRI_CNT", .addr = A_CFU_FDRI_CNT, + .ro = 0xffffffff, + },{ .name = "CFU_ECO1", .addr = A_CFU_ECO1, + },{ .name = "CFU_ECO2", .addr = A_CFU_ECO2, + } +}; + +static void cfu_apb_reset(DeviceState *dev) +{ + XlnxVersalCFUAPB *s = XLNX_VERSAL_CFU_APB(dev); + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(s->regs_info); ++i) { + register_reset(&s->regs_info[i]); + } + memset(s->wfifo, 0, WFIFO_SZ * sizeof(uint32_t)); + + s->regs[R_CFU_STATUS] |= R_CFU_STATUS_HC_COMPLETE_MASK; + cfu_imr_update_irq(s); +} + +static const MemoryRegionOps cfu_apb_ops = { + .read = register_read_memory, + .write = register_write_memory, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void cfu_transfer_cfi_packet(XlnxVersalCFUAPB *s, uint8_t row_addr, + XlnxCfiPacket *pkt) +{ + if (row_addr == CFRAME_BROADCAST_ROW) { + for (int i = 0; i < ARRAY_SIZE(s->cfg.cframe); i++) { + if (s->cfg.cframe[i]) { + xlnx_cfi_transfer_packet(s->cfg.cframe[i], pkt); + } + } + } else { + assert(row_addr < ARRAY_SIZE(s->cfg.cframe)); + + if (s->cfg.cframe[row_addr]) { + xlnx_cfi_transfer_packet(s->cfg.cframe[row_addr], pkt); + } + } +} + +static uint64_t cfu_stream_read(void *opaque, hwaddr addr, unsigned size) +{ + qemu_log_mask(LOG_GUEST_ERROR, "%s: Unsupported read from addr=%" + HWADDR_PRIx "\n", __func__, addr); + return 0; +} + +static void cfu_stream_write(void *opaque, hwaddr addr, uint64_t value, + unsigned size) +{ + XlnxVersalCFUAPB *s = XLNX_VERSAL_CFU_APB(opaque); + uint32_t wfifo[WFIFO_SZ]; + + if (update_wfifo(addr, value, s->wfifo, wfifo)) { + uint8_t packet_type, row_addr, reg_addr; + + packet_type = extract32(wfifo[0], 24, 8); + row_addr = extract32(wfifo[0], 16, 5); + reg_addr = extract32(wfifo[0], 8, 6); + + /* Compressed bitstreams are not supported yet. */ + if (ARRAY_FIELD_EX32(s->regs, CFU_CTL, DECOMPRESS) == 0) { + if (s->regs[R_CFU_FDRI_CNT]) { + XlnxCfiPacket pkt = { + .reg_addr = CFRAME_FDRI, + .data[0] = wfifo[0], + .data[1] = wfifo[1], + .data[2] = wfifo[2], + .data[3] = wfifo[3] + }; + + cfu_transfer_cfi_packet(s, s->fdri_row_addr, &pkt); + + s->regs[R_CFU_FDRI_CNT]--; + + } else if (packet_type == PACKET_TYPE_CFU && + reg_addr == CFRAME_FDRI) { + + /* Load R_CFU_FDRI_CNT, must be multiple of 25 */ + s->regs[R_CFU_FDRI_CNT] = wfifo[1]; + + /* Store target row_addr */ + s->fdri_row_addr = row_addr; + + if (wfifo[1] % 25 != 0) { + qemu_log_mask(LOG_GUEST_ERROR, + "CFU FDRI_CNT is not loaded with " + "a multiple of 25 value\n"); + } + + } else if (packet_type == PACKET_TYPE_CFRAME) { + XlnxCfiPacket pkt = { + .reg_addr = reg_addr, + .data[0] = wfifo[1], + .data[1] = wfifo[2], + .data[2] = wfifo[3], + }; + cfu_transfer_cfi_packet(s, row_addr, &pkt); + } + } + } +} + +static const MemoryRegionOps cfu_stream_ops = { + .read = cfu_stream_read, + .write = cfu_stream_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 8, + }, +}; + +static void cfu_apb_init(Object *obj) +{ + XlnxVersalCFUAPB *s = XLNX_VERSAL_CFU_APB(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + RegisterInfoArray *reg_array; + unsigned int i; + char *name; + + memory_region_init(&s->iomem, obj, TYPE_XLNX_VERSAL_CFU_APB, R_MAX * 4); + reg_array = + register_init_block32(DEVICE(obj), cfu_apb_regs_info, + ARRAY_SIZE(cfu_apb_regs_info), + s->regs_info, s->regs, + &cfu_apb_ops, + XLNX_VERSAL_CFU_APB_ERR_DEBUG, + R_MAX * 4); + memory_region_add_subregion(&s->iomem, + 0x0, + ®_array->mem); + sysbus_init_mmio(sbd, &s->iomem); + for (i = 0; i < NUM_STREAM; i++) { + name = g_strdup_printf(TYPE_XLNX_VERSAL_CFU_APB "-stream%d", i); + memory_region_init_io(&s->iomem_stream[i], obj, &cfu_stream_ops, s, + name, i == 0 ? KEYHOLE_STREAM_4K : + KEYHOLE_STREAM_256K); + sysbus_init_mmio(sbd, &s->iomem_stream[i]); + g_free(name); + } + sysbus_init_irq(sbd, &s->irq_cfu_imr); +} + +static Property cfu_props[] = { + DEFINE_PROP_LINK("cframe0", XlnxVersalCFUAPB, cfg.cframe[0], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe1", XlnxVersalCFUAPB, cfg.cframe[1], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe2", XlnxVersalCFUAPB, cfg.cframe[2], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe3", XlnxVersalCFUAPB, cfg.cframe[3], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe4", XlnxVersalCFUAPB, cfg.cframe[4], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe5", XlnxVersalCFUAPB, cfg.cframe[5], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe6", XlnxVersalCFUAPB, cfg.cframe[6], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe7", XlnxVersalCFUAPB, cfg.cframe[7], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe8", XlnxVersalCFUAPB, cfg.cframe[8], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe9", XlnxVersalCFUAPB, cfg.cframe[9], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe10", XlnxVersalCFUAPB, cfg.cframe[10], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe11", XlnxVersalCFUAPB, cfg.cframe[11], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe12", XlnxVersalCFUAPB, cfg.cframe[12], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe13", XlnxVersalCFUAPB, cfg.cframe[13], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe14", XlnxVersalCFUAPB, cfg.cframe[14], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_END_OF_LIST(), +}; + +static const VMStateDescription vmstate_cfu_apb = { + .name = TYPE_XLNX_VERSAL_CFU_APB, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(wfifo, XlnxVersalCFUAPB, 4), + VMSTATE_UINT32_ARRAY(regs, XlnxVersalCFUAPB, R_MAX), + VMSTATE_UINT8(fdri_row_addr, XlnxVersalCFUAPB), + VMSTATE_END_OF_LIST(), + } +}; + +static void cfu_apb_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = cfu_apb_reset; + dc->vmsd = &vmstate_cfu_apb; + device_class_set_props(dc, cfu_props); +} + +static const TypeInfo cfu_apb_info = { + .name = TYPE_XLNX_VERSAL_CFU_APB, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(XlnxVersalCFUAPB), + .class_init = cfu_apb_class_init, + .instance_init = cfu_apb_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_XLNX_CFI_IF }, + { } + } +}; + +static void cfu_apb_register_types(void) +{ + type_register_static(&cfu_apb_info); +} + +type_init(cfu_apb_register_types) diff --git a/include/hw/misc/xlnx-versal-cfu.h b/include/hw/misc/xlnx-versal-cfu.h new file mode 100644 index 0000000000..62d10caf27 --- /dev/null +++ b/include/hw/misc/xlnx-versal-cfu.h @@ -0,0 +1,231 @@ +/* + * QEMU model of the CFU Configuration Unit. + * + * Copyright (C) 2023, Advanced Micro Devices, Inc. + * + * Written by Francisco Iglesias + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + * References: + * [1] Versal ACAP Technical Reference Manual, + * https://www.xilinx.com/support/documentation/architecture-manuals/am011-versal-acap-trm.pdf + * + * [2] Versal ACAP Register Reference, + * https://www.xilinx.com/htmldocs/registers/am012/am012-versal-register-reference.html + */ +#ifndef HW_MISC_XLNX_VERSAL_CFU_APB_H +#define HW_MISC_XLNX_VERSAL_CFU_APB_H + +#include "hw/sysbus.h" +#include "hw/register.h" +#include "hw/misc/xlnx-cfi-if.h" + +#define TYPE_XLNX_VERSAL_CFU_APB "xlnx,versal-cfu-apb" +OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersalCFUAPB, XLNX_VERSAL_CFU_APB) + +REG32(CFU_ISR, 0x0) + FIELD(CFU_ISR, USR_GTS_EVENT, 9, 1) + FIELD(CFU_ISR, USR_GSR_EVENT, 8, 1) + FIELD(CFU_ISR, SLVERR, 7, 1) + FIELD(CFU_ISR, DECOMP_ERROR, 6, 1) + FIELD(CFU_ISR, BAD_CFI_PACKET, 5, 1) + FIELD(CFU_ISR, AXI_ALIGN_ERROR, 4, 1) + FIELD(CFU_ISR, CFI_ROW_ERROR, 3, 1) + FIELD(CFU_ISR, CRC32_ERROR, 2, 1) + FIELD(CFU_ISR, CRC8_ERROR, 1, 1) + FIELD(CFU_ISR, SEU_ENDOFCALIB, 0, 1) +REG32(CFU_IMR, 0x4) + FIELD(CFU_IMR, USR_GTS_EVENT, 9, 1) + FIELD(CFU_IMR, USR_GSR_EVENT, 8, 1) + FIELD(CFU_IMR, SLVERR, 7, 1) + FIELD(CFU_IMR, DECOMP_ERROR, 6, 1) + FIELD(CFU_IMR, BAD_CFI_PACKET, 5, 1) + FIELD(CFU_IMR, AXI_ALIGN_ERROR, 4, 1) + FIELD(CFU_IMR, CFI_ROW_ERROR, 3, 1) + FIELD(CFU_IMR, CRC32_ERROR, 2, 1) + FIELD(CFU_IMR, CRC8_ERROR, 1, 1) + FIELD(CFU_IMR, SEU_ENDOFCALIB, 0, 1) +REG32(CFU_IER, 0x8) + FIELD(CFU_IER, USR_GTS_EVENT, 9, 1) + FIELD(CFU_IER, USR_GSR_EVENT, 8, 1) + FIELD(CFU_IER, SLVERR, 7, 1) + FIELD(CFU_IER, DECOMP_ERROR, 6, 1) + FIELD(CFU_IER, BAD_CFI_PACKET, 5, 1) + FIELD(CFU_IER, AXI_ALIGN_ERROR, 4, 1) + FIELD(CFU_IER, CFI_ROW_ERROR, 3, 1) + FIELD(CFU_IER, CRC32_ERROR, 2, 1) + FIELD(CFU_IER, CRC8_ERROR, 1, 1) + FIELD(CFU_IER, SEU_ENDOFCALIB, 0, 1) +REG32(CFU_IDR, 0xc) + FIELD(CFU_IDR, USR_GTS_EVENT, 9, 1) + FIELD(CFU_IDR, USR_GSR_EVENT, 8, 1) + FIELD(CFU_IDR, SLVERR, 7, 1) + FIELD(CFU_IDR, DECOMP_ERROR, 6, 1) + FIELD(CFU_IDR, BAD_CFI_PACKET, 5, 1) + FIELD(CFU_IDR, AXI_ALIGN_ERROR, 4, 1) + FIELD(CFU_IDR, CFI_ROW_ERROR, 3, 1) + FIELD(CFU_IDR, CRC32_ERROR, 2, 1) + FIELD(CFU_IDR, CRC8_ERROR, 1, 1) + FIELD(CFU_IDR, SEU_ENDOFCALIB, 0, 1) +REG32(CFU_ITR, 0x10) + FIELD(CFU_ITR, USR_GTS_EVENT, 9, 1) + FIELD(CFU_ITR, USR_GSR_EVENT, 8, 1) + FIELD(CFU_ITR, SLVERR, 7, 1) + FIELD(CFU_ITR, DECOMP_ERROR, 6, 1) + FIELD(CFU_ITR, BAD_CFI_PACKET, 5, 1) + FIELD(CFU_ITR, AXI_ALIGN_ERROR, 4, 1) + FIELD(CFU_ITR, CFI_ROW_ERROR, 3, 1) + FIELD(CFU_ITR, CRC32_ERROR, 2, 1) + FIELD(CFU_ITR, CRC8_ERROR, 1, 1) + FIELD(CFU_ITR, SEU_ENDOFCALIB, 0, 1) +REG32(CFU_PROTECT, 0x14) + FIELD(CFU_PROTECT, ACTIVE, 0, 1) +REG32(CFU_FGCR, 0x18) + FIELD(CFU_FGCR, GCLK_CAL, 14, 1) + FIELD(CFU_FGCR, SC_HBC_TRIGGER, 13, 1) + FIELD(CFU_FGCR, GLOW, 12, 1) + FIELD(CFU_FGCR, GPWRDWN, 11, 1) + FIELD(CFU_FGCR, GCAP, 10, 1) + FIELD(CFU_FGCR, GSCWE, 9, 1) + FIELD(CFU_FGCR, GHIGH_B, 8, 1) + FIELD(CFU_FGCR, GMC_B, 7, 1) + FIELD(CFU_FGCR, GWE, 6, 1) + FIELD(CFU_FGCR, GRESTORE, 5, 1) + FIELD(CFU_FGCR, GTS_CFG_B, 4, 1) + FIELD(CFU_FGCR, GLUTMASK, 3, 1) + FIELD(CFU_FGCR, EN_GLOBS_B, 2, 1) + FIELD(CFU_FGCR, EOS, 1, 1) + FIELD(CFU_FGCR, INIT_COMPLETE, 0, 1) +REG32(CFU_CTL, 0x1c) + FIELD(CFU_CTL, GSR_GSC, 15, 1) + FIELD(CFU_CTL, SLVERR_EN, 14, 1) + FIELD(CFU_CTL, CRC32_RESET, 13, 1) + FIELD(CFU_CTL, AXI_ERROR_EN, 12, 1) + FIELD(CFU_CTL, FLUSH_AXI, 11, 1) + FIELD(CFU_CTL, SSI_PER_SLR_PR, 10, 1) + FIELD(CFU_CTL, GCAP_CLK_EN, 9, 1) + FIELD(CFU_CTL, STATUS_SYNC_DISABLE, 8, 1) + FIELD(CFU_CTL, IGNORE_CFI_ERROR, 7, 1) + FIELD(CFU_CTL, CFRAME_DISABLE, 6, 1) + FIELD(CFU_CTL, QWORD_CNT_RESET, 5, 1) + FIELD(CFU_CTL, CRC8_DISABLE, 4, 1) + FIELD(CFU_CTL, CRC32_CHECK, 3, 1) + FIELD(CFU_CTL, DECOMPRESS, 2, 1) + FIELD(CFU_CTL, SEU_GO, 1, 1) + FIELD(CFU_CTL, CFI_LOCAL_RESET, 0, 1) +REG32(CFU_CRAM_RW, 0x20) + FIELD(CFU_CRAM_RW, RFIFO_AFULL_DEPTH, 18, 9) + FIELD(CFU_CRAM_RW, RD_WAVE_CNT_LEFT, 12, 6) + FIELD(CFU_CRAM_RW, RD_WAVE_CNT, 6, 6) + FIELD(CFU_CRAM_RW, WR_WAVE_CNT, 0, 6) +REG32(CFU_MASK, 0x28) +REG32(CFU_CRC_EXPECT, 0x2c) +REG32(CFU_CFRAME_LEFT_T0, 0x60) + FIELD(CFU_CFRAME_LEFT_T0, NUM, 0, 20) +REG32(CFU_CFRAME_LEFT_T1, 0x64) + FIELD(CFU_CFRAME_LEFT_T1, NUM, 0, 20) +REG32(CFU_CFRAME_LEFT_T2, 0x68) + FIELD(CFU_CFRAME_LEFT_T2, NUM, 0, 20) +REG32(CFU_ROW_RANGE, 0x6c) + FIELD(CFU_ROW_RANGE, HALF_FSR, 5, 1) + FIELD(CFU_ROW_RANGE, NUM, 0, 5) +REG32(CFU_STATUS, 0x100) + FIELD(CFU_STATUS, SEU_WRITE_ERROR, 30, 1) + FIELD(CFU_STATUS, FRCNT_ERROR, 29, 1) + FIELD(CFU_STATUS, RSVD_ERROR, 28, 1) + FIELD(CFU_STATUS, FDRO_ERROR, 27, 1) + FIELD(CFU_STATUS, FDRI_ERROR, 26, 1) + FIELD(CFU_STATUS, FDRI_READ_ERROR, 25, 1) + FIELD(CFU_STATUS, READ_FDRI_ERROR, 24, 1) + FIELD(CFU_STATUS, READ_SFR_ERROR, 23, 1) + FIELD(CFU_STATUS, READ_STREAM_ERROR, 22, 1) + FIELD(CFU_STATUS, UNKNOWN_STREAM_PKT, 21, 1) + FIELD(CFU_STATUS, USR_GTS, 20, 1) + FIELD(CFU_STATUS, USR_GSR, 19, 1) + FIELD(CFU_STATUS, AXI_BAD_WSTRB, 18, 1) + FIELD(CFU_STATUS, AXI_BAD_AR_SIZE, 17, 1) + FIELD(CFU_STATUS, AXI_BAD_AW_SIZE, 16, 1) + FIELD(CFU_STATUS, AXI_BAD_ARADDR, 15, 1) + FIELD(CFU_STATUS, AXI_BAD_AWADDR, 14, 1) + FIELD(CFU_STATUS, SCAN_CLEAR_PASS, 13, 1) + FIELD(CFU_STATUS, HC_SEC_ERROR, 12, 1) + FIELD(CFU_STATUS, GHIGH_B_ISHIGH, 11, 1) + FIELD(CFU_STATUS, GHIGH_B_ISLOW, 10, 1) + FIELD(CFU_STATUS, GMC_B_ISHIGH, 9, 1) + FIELD(CFU_STATUS, GMC_B_ISLOW, 8, 1) + FIELD(CFU_STATUS, GPWRDWN_B_ISHIGH, 7, 1) + FIELD(CFU_STATUS, CFI_SEU_CRC_ERROR, 6, 1) + FIELD(CFU_STATUS, CFI_SEU_ECC_ERROR, 5, 1) + FIELD(CFU_STATUS, CFI_SEU_HEARTBEAT, 4, 1) + FIELD(CFU_STATUS, SCAN_CLEAR_DONE, 3, 1) + FIELD(CFU_STATUS, HC_COMPLETE, 2, 1) + FIELD(CFU_STATUS, CFI_CFRAME_BUSY, 1, 1) + FIELD(CFU_STATUS, CFU_STREAM_BUSY, 0, 1) +REG32(CFU_INTERNAL_STATUS, 0x104) + FIELD(CFU_INTERNAL_STATUS, SSI_EOS, 22, 1) + FIELD(CFU_INTERNAL_STATUS, SSI_GWE, 21, 1) + FIELD(CFU_INTERNAL_STATUS, RFIFO_EMPTY, 20, 1) + FIELD(CFU_INTERNAL_STATUS, RFIFO_FULL, 19, 1) + FIELD(CFU_INTERNAL_STATUS, SEL_SFR, 18, 1) + FIELD(CFU_INTERNAL_STATUS, STREAM_CFRAME, 17, 1) + FIELD(CFU_INTERNAL_STATUS, FDRI_PHASE, 16, 1) + FIELD(CFU_INTERNAL_STATUS, CFI_PIPE_EN, 15, 1) + FIELD(CFU_INTERNAL_STATUS, AWFIFO_DCNT, 10, 5) + FIELD(CFU_INTERNAL_STATUS, WFIFO_DCNT, 5, 5) + FIELD(CFU_INTERNAL_STATUS, REPAIR_BUSY, 4, 1) + FIELD(CFU_INTERNAL_STATUS, TRIMU_BUSY, 3, 1) + FIELD(CFU_INTERNAL_STATUS, TRIMB_BUSY, 2, 1) + FIELD(CFU_INTERNAL_STATUS, HCLEANR_BUSY, 1, 1) + FIELD(CFU_INTERNAL_STATUS, HCLEAN_BUSY, 0, 1) +REG32(CFU_QWORD_CNT, 0x108) +REG32(CFU_CRC_LIVE, 0x10c) +REG32(CFU_PENDING_READ_CNT, 0x110) + FIELD(CFU_PENDING_READ_CNT, NUM, 0, 25) +REG32(CFU_FDRI_CNT, 0x114) +REG32(CFU_ECO1, 0x118) +REG32(CFU_ECO2, 0x11c) + +#define R_MAX (R_CFU_ECO2 + 1) + +#define NUM_STREAM 2 +#define WFIFO_SZ 4 + +struct XlnxVersalCFUAPB { + SysBusDevice parent_obj; + MemoryRegion iomem; + MemoryRegion iomem_stream[NUM_STREAM]; + qemu_irq irq_cfu_imr; + + /* 128-bit wfifo. */ + uint32_t wfifo[WFIFO_SZ]; + + uint32_t regs[R_MAX]; + RegisterInfo regs_info[R_MAX]; + + uint8_t fdri_row_addr; + + struct { + XlnxCfiIf *cframe[15]; + } cfg; +}; + +/** + * This is a helper function for updating a CFI data write fifo, an array of 4 + * uint32_t and 128 bits of data that are allowed to be written through 4 + * sequential 32 bit accesses. After the last index has been written into the + * write fifo (wfifo), the data is copied to and returned in a secondary fifo + * provided to the function (wfifo_ret), and the write fifo is cleared + * (zeroized). + * + * @addr: the address used when calculating the wfifo array index to update + * @value: the value to write into the wfifo array + * @wfifo: the wfifo to update + * @wfifo_out: will return the wfifo data when all 128 bits have been written + * + * @return: true if all 128 bits have been updated. + */ +bool update_wfifo(hwaddr addr, uint64_t value, + uint32_t *wfifo, uint32_t *wfifo_ret); + +#endif From ebfdc4942810905c44a59ee92f3d3809f40ee253 Mon Sep 17 00:00:00 2001 From: Francisco Iglesias Date: Thu, 31 Aug 2023 17:56:56 +0100 Subject: [PATCH 13/26] hw/misc/xlnx-versal-cfu: Introduce a model of Xilinx Versal CFU_FDRO Introduce a model of Xilinx Versal's Configuration Frame Unit's data out port (CFU_FDRO). Signed-off-by: Francisco Iglesias Reviewed-by: Peter Maydell Message-id: 20230831165701.2016397-4-francisco.iglesias@amd.com Signed-off-by: Peter Maydell --- hw/misc/xlnx-versal-cfu.c | 96 +++++++++++++++++++++++++++++++ include/hw/misc/xlnx-versal-cfu.h | 12 ++++ 2 files changed, 108 insertions(+) diff --git a/hw/misc/xlnx-versal-cfu.c b/hw/misc/xlnx-versal-cfu.c index b2dc6ab211..255c1bf4b8 100644 --- a/hw/misc/xlnx-versal-cfu.c +++ b/hw/misc/xlnx-versal-cfu.c @@ -264,6 +264,25 @@ static void cfu_stream_write(void *opaque, hwaddr addr, uint64_t value, } } +static uint64_t cfu_fdro_read(void *opaque, hwaddr addr, unsigned size) +{ + XlnxVersalCFUFDRO *s = XLNX_VERSAL_CFU_FDRO(opaque); + uint64_t ret = 0; + + if (!fifo32_is_empty(&s->fdro_data)) { + ret = fifo32_pop(&s->fdro_data); + } + + return ret; +} + +static void cfu_fdro_write(void *opaque, hwaddr addr, uint64_t value, + unsigned size) +{ + qemu_log_mask(LOG_GUEST_ERROR, "%s: Unsupported write from addr=%" + HWADDR_PRIx "\n", __func__, addr); +} + static const MemoryRegionOps cfu_stream_ops = { .read = cfu_stream_read, .write = cfu_stream_write, @@ -274,6 +293,16 @@ static const MemoryRegionOps cfu_stream_ops = { }, }; +static const MemoryRegionOps cfu_fdro_ops = { + .read = cfu_fdro_read, + .write = cfu_fdro_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + static void cfu_apb_init(Object *obj) { XlnxVersalCFUAPB *s = XLNX_VERSAL_CFU_APB(obj); @@ -305,6 +334,39 @@ static void cfu_apb_init(Object *obj) sysbus_init_irq(sbd, &s->irq_cfu_imr); } +static void cfu_fdro_init(Object *obj) +{ + XlnxVersalCFUFDRO *s = XLNX_VERSAL_CFU_FDRO(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + memory_region_init_io(&s->iomem_fdro, obj, &cfu_fdro_ops, s, + TYPE_XLNX_VERSAL_CFU_FDRO, KEYHOLE_STREAM_4K); + sysbus_init_mmio(sbd, &s->iomem_fdro); + fifo32_create(&s->fdro_data, 8 * KiB / sizeof(uint32_t)); +} + +static void cfu_fdro_reset_enter(Object *obj, ResetType type) +{ + XlnxVersalCFUFDRO *s = XLNX_VERSAL_CFU_FDRO(obj); + + fifo32_reset(&s->fdro_data); +} + +static void cfu_fdro_cfi_transfer_packet(XlnxCfiIf *cfi_if, XlnxCfiPacket *pkt) +{ + XlnxVersalCFUFDRO *s = XLNX_VERSAL_CFU_FDRO(cfi_if); + + if (fifo32_num_free(&s->fdro_data) >= ARRAY_SIZE(pkt->data)) { + for (int i = 0; i < ARRAY_SIZE(pkt->data); i++) { + fifo32_push(&s->fdro_data, pkt->data[i]); + } + } else { + /* It is a programming error to fill the fifo. */ + qemu_log_mask(LOG_GUEST_ERROR, + "CFU_FDRO: CFI data dropped due to full read fifo\n"); + } +} + static Property cfu_props[] = { DEFINE_PROP_LINK("cframe0", XlnxVersalCFUAPB, cfg.cframe[0], TYPE_XLNX_CFI_IF, XlnxCfiIf *), @@ -351,6 +413,16 @@ static const VMStateDescription vmstate_cfu_apb = { } }; +static const VMStateDescription vmstate_cfu_fdro = { + .name = TYPE_XLNX_VERSAL_CFU_FDRO, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_FIFO32(fdro_data, XlnxVersalCFUFDRO), + VMSTATE_END_OF_LIST(), + } +}; + static void cfu_apb_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); @@ -360,6 +432,17 @@ static void cfu_apb_class_init(ObjectClass *klass, void *data) device_class_set_props(dc, cfu_props); } +static void cfu_fdro_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + XlnxCfiIfClass *xcic = XLNX_CFI_IF_CLASS(klass); + + dc->vmsd = &vmstate_cfu_fdro; + xcic->cfi_transfer_packet = cfu_fdro_cfi_transfer_packet; + rc->phases.enter = cfu_fdro_reset_enter; +} + static const TypeInfo cfu_apb_info = { .name = TYPE_XLNX_VERSAL_CFU_APB, .parent = TYPE_SYS_BUS_DEVICE, @@ -372,9 +455,22 @@ static const TypeInfo cfu_apb_info = { } }; +static const TypeInfo cfu_fdro_info = { + .name = TYPE_XLNX_VERSAL_CFU_FDRO, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(XlnxVersalCFUFDRO), + .class_init = cfu_fdro_class_init, + .instance_init = cfu_fdro_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_XLNX_CFI_IF }, + { } + } +}; + static void cfu_apb_register_types(void) { type_register_static(&cfu_apb_info); + type_register_static(&cfu_fdro_info); } type_init(cfu_apb_register_types) diff --git a/include/hw/misc/xlnx-versal-cfu.h b/include/hw/misc/xlnx-versal-cfu.h index 62d10caf27..73e9a21af4 100644 --- a/include/hw/misc/xlnx-versal-cfu.h +++ b/include/hw/misc/xlnx-versal-cfu.h @@ -20,10 +20,14 @@ #include "hw/sysbus.h" #include "hw/register.h" #include "hw/misc/xlnx-cfi-if.h" +#include "qemu/fifo32.h" #define TYPE_XLNX_VERSAL_CFU_APB "xlnx,versal-cfu-apb" OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersalCFUAPB, XLNX_VERSAL_CFU_APB) +#define TYPE_XLNX_VERSAL_CFU_FDRO "xlnx,versal-cfu-fdro" +OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersalCFUFDRO, XLNX_VERSAL_CFU_FDRO) + REG32(CFU_ISR, 0x0) FIELD(CFU_ISR, USR_GTS_EVENT, 9, 1) FIELD(CFU_ISR, USR_GSR_EVENT, 8, 1) @@ -210,6 +214,14 @@ struct XlnxVersalCFUAPB { } cfg; }; + +struct XlnxVersalCFUFDRO { + SysBusDevice parent_obj; + MemoryRegion iomem_fdro; + + Fifo32 fdro_data; +}; + /** * This is a helper function for updating a CFI data write fifo, an array of 4 * uint32_t and 128 bits of data that are allowed to be written through 4 From 975dd496b5255c14ea46cf7d51a95703eeb1a2e3 Mon Sep 17 00:00:00 2001 From: Francisco Iglesias Date: Thu, 31 Aug 2023 17:56:57 +0100 Subject: [PATCH 14/26] hw/misc/xlnx-versal-cfu: Introduce a model of Xilinx Versal's CFU_SFR Introduce a model of Xilinx Versal's Configuration Frame Unit's Single Frame Read port (CFU_SFR). Signed-off-by: Francisco Iglesias Reviewed-by: Peter Maydell Message-id: 20230831165701.2016397-5-francisco.iglesias@amd.com Signed-off-by: Peter Maydell --- hw/misc/xlnx-versal-cfu.c | 87 +++++++++++++++++++++++++++++++ include/hw/misc/xlnx-versal-cfu.h | 15 ++++++ 2 files changed, 102 insertions(+) diff --git a/hw/misc/xlnx-versal-cfu.c b/hw/misc/xlnx-versal-cfu.c index 255c1bf4b8..8e588ac1d8 100644 --- a/hw/misc/xlnx-versal-cfu.c +++ b/hw/misc/xlnx-versal-cfu.c @@ -264,6 +264,31 @@ static void cfu_stream_write(void *opaque, hwaddr addr, uint64_t value, } } +static uint64_t cfu_sfr_read(void *opaque, hwaddr addr, unsigned size) +{ + qemu_log_mask(LOG_GUEST_ERROR, "%s: Unsupported read from addr=%" + HWADDR_PRIx "\n", __func__, addr); + return 0; +} + +static void cfu_sfr_write(void *opaque, hwaddr addr, uint64_t value, + unsigned size) +{ + XlnxVersalCFUSFR *s = XLNX_VERSAL_CFU_SFR(opaque); + uint32_t wfifo[WFIFO_SZ]; + + if (update_wfifo(addr, value, s->wfifo, wfifo)) { + uint8_t row_addr = extract32(wfifo[0], 23, 5); + uint32_t frame_addr = extract32(wfifo[0], 0, 23); + XlnxCfiPacket pkt = { .reg_addr = CFRAME_SFR, + .data[0] = frame_addr }; + + if (s->cfg.cfu) { + cfu_transfer_cfi_packet(s->cfg.cfu, row_addr, &pkt); + } + } +} + static uint64_t cfu_fdro_read(void *opaque, hwaddr addr, unsigned size) { XlnxVersalCFUFDRO *s = XLNX_VERSAL_CFU_FDRO(opaque); @@ -293,6 +318,16 @@ static const MemoryRegionOps cfu_stream_ops = { }, }; +static const MemoryRegionOps cfu_sfr_ops = { + .read = cfu_sfr_read, + .write = cfu_sfr_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + static const MemoryRegionOps cfu_fdro_ops = { .read = cfu_fdro_read, .write = cfu_fdro_write, @@ -334,6 +369,23 @@ static void cfu_apb_init(Object *obj) sysbus_init_irq(sbd, &s->irq_cfu_imr); } +static void cfu_sfr_init(Object *obj) +{ + XlnxVersalCFUSFR *s = XLNX_VERSAL_CFU_SFR(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + memory_region_init_io(&s->iomem_sfr, obj, &cfu_sfr_ops, s, + TYPE_XLNX_VERSAL_CFU_SFR, KEYHOLE_STREAM_4K); + sysbus_init_mmio(sbd, &s->iomem_sfr); +} + +static void cfu_sfr_reset_enter(Object *obj, ResetType type) +{ + XlnxVersalCFUSFR *s = XLNX_VERSAL_CFU_SFR(obj); + + memset(s->wfifo, 0, WFIFO_SZ * sizeof(uint32_t)); +} + static void cfu_fdro_init(Object *obj) { XlnxVersalCFUFDRO *s = XLNX_VERSAL_CFU_FDRO(obj); @@ -401,6 +453,12 @@ static Property cfu_props[] = { DEFINE_PROP_END_OF_LIST(), }; +static Property cfu_sfr_props[] = { + DEFINE_PROP_LINK("cfu", XlnxVersalCFUSFR, cfg.cfu, + TYPE_XLNX_VERSAL_CFU_APB, XlnxVersalCFUAPB *), + DEFINE_PROP_END_OF_LIST(), +}; + static const VMStateDescription vmstate_cfu_apb = { .name = TYPE_XLNX_VERSAL_CFU_APB, .version_id = 1, @@ -423,6 +481,16 @@ static const VMStateDescription vmstate_cfu_fdro = { } }; +static const VMStateDescription vmstate_cfu_sfr = { + .name = TYPE_XLNX_VERSAL_CFU_SFR, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(wfifo, XlnxVersalCFUSFR, 4), + VMSTATE_END_OF_LIST(), + } +}; + static void cfu_apb_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); @@ -443,6 +511,16 @@ static void cfu_fdro_class_init(ObjectClass *klass, void *data) rc->phases.enter = cfu_fdro_reset_enter; } +static void cfu_sfr_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + device_class_set_props(dc, cfu_sfr_props); + dc->vmsd = &vmstate_cfu_sfr; + rc->phases.enter = cfu_sfr_reset_enter; +} + static const TypeInfo cfu_apb_info = { .name = TYPE_XLNX_VERSAL_CFU_APB, .parent = TYPE_SYS_BUS_DEVICE, @@ -467,10 +545,19 @@ static const TypeInfo cfu_fdro_info = { } }; +static const TypeInfo cfu_sfr_info = { + .name = TYPE_XLNX_VERSAL_CFU_SFR, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(XlnxVersalCFUSFR), + .class_init = cfu_sfr_class_init, + .instance_init = cfu_sfr_init, +}; + static void cfu_apb_register_types(void) { type_register_static(&cfu_apb_info); type_register_static(&cfu_fdro_info); + type_register_static(&cfu_sfr_info); } type_init(cfu_apb_register_types) diff --git a/include/hw/misc/xlnx-versal-cfu.h b/include/hw/misc/xlnx-versal-cfu.h index 73e9a21af4..86fb841053 100644 --- a/include/hw/misc/xlnx-versal-cfu.h +++ b/include/hw/misc/xlnx-versal-cfu.h @@ -28,6 +28,9 @@ OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersalCFUAPB, XLNX_VERSAL_CFU_APB) #define TYPE_XLNX_VERSAL_CFU_FDRO "xlnx,versal-cfu-fdro" OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersalCFUFDRO, XLNX_VERSAL_CFU_FDRO) +#define TYPE_XLNX_VERSAL_CFU_SFR "xlnx,versal-cfu-sfr" +OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersalCFUSFR, XLNX_VERSAL_CFU_SFR) + REG32(CFU_ISR, 0x0) FIELD(CFU_ISR, USR_GTS_EVENT, 9, 1) FIELD(CFU_ISR, USR_GSR_EVENT, 8, 1) @@ -222,6 +225,18 @@ struct XlnxVersalCFUFDRO { Fifo32 fdro_data; }; +struct XlnxVersalCFUSFR { + SysBusDevice parent_obj; + MemoryRegion iomem_sfr; + + /* 128-bit wfifo. */ + uint32_t wfifo[WFIFO_SZ]; + + struct { + XlnxVersalCFUAPB *cfu; + } cfg; +}; + /** * This is a helper function for updating a CFI data write fifo, an array of 4 * uint32_t and 128 bits of data that are allowed to be written through 4 From c6766f5b751d042f03a4cfdbee145c97cf4eedb9 Mon Sep 17 00:00:00 2001 From: Francisco Iglesias Date: Thu, 31 Aug 2023 17:56:58 +0100 Subject: [PATCH 15/26] hw/misc: Introduce a model of Xilinx Versal's CFRAME_REG Introduce a model of Xilinx Versal's Configuration Frame controller (CFRAME_REG). Signed-off-by: Francisco Iglesias Message-id: 20230831165701.2016397-6-francisco.iglesias@amd.com Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- MAINTAINERS | 2 + hw/misc/meson.build | 1 + hw/misc/xlnx-versal-cframe-reg.c | 697 +++++++++++++++++++++++ include/hw/misc/xlnx-versal-cframe-reg.h | 286 ++++++++++ 4 files changed, 986 insertions(+) create mode 100644 hw/misc/xlnx-versal-cframe-reg.c create mode 100644 include/hw/misc/xlnx-versal-cframe-reg.h diff --git a/MAINTAINERS b/MAINTAINERS index 5b01fbe065..57c5533dcf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1033,6 +1033,8 @@ F: hw/misc/xlnx-cfi-if.c F: include/hw/misc/xlnx-cfi-if.h F: hw/misc/xlnx-versal-cfu.c F: include/hw/misc/xlnx-versal-cfu.h +F: hw/misc/xlnx-versal-cframe-reg.c +F: include/hw/misc/xlnx-versal-cframe-reg.h STM32F100 M: Alexandre Iooss diff --git a/hw/misc/meson.build b/hw/misc/meson.build index 3135697d74..88ecab8392 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -100,6 +100,7 @@ system_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files( 'xlnx-versal-pmc-iou-slcr.c', 'xlnx-versal-cfu.c', 'xlnx-cfi-if.c', + 'xlnx-versal-cframe-reg.c', )) system_ss.add(when: 'CONFIG_STM32F2XX_SYSCFG', if_true: files('stm32f2xx_syscfg.c')) system_ss.add(when: 'CONFIG_STM32F4XX_SYSCFG', if_true: files('stm32f4xx_syscfg.c')) diff --git a/hw/misc/xlnx-versal-cframe-reg.c b/hw/misc/xlnx-versal-cframe-reg.c new file mode 100644 index 0000000000..78db68f10c --- /dev/null +++ b/hw/misc/xlnx-versal-cframe-reg.c @@ -0,0 +1,697 @@ +/* + * QEMU model of the Configuration Frame Control module + * + * Copyright (C) 2023, Advanced Micro Devices, Inc. + * + * Written by Francisco Iglesias + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "hw/sysbus.h" +#include "hw/register.h" +#include "hw/registerfields.h" +#include "qemu/bitops.h" +#include "qemu/log.h" +#include "qemu/units.h" +#include "qapi/error.h" +#include "hw/qdev-properties.h" +#include "migration/vmstate.h" +#include "hw/irq.h" +#include "hw/misc/xlnx-versal-cframe-reg.h" + +#ifndef XLNX_VERSAL_CFRAME_REG_ERR_DEBUG +#define XLNX_VERSAL_CFRAME_REG_ERR_DEBUG 0 +#endif + +#define KEYHOLE_STREAM_4K (4 * KiB) +#define N_WORDS_128BIT 4 + +#define MAX_BLOCKTYPE 6 +#define MAX_BLOCKTYPE_FRAMES 0xFFFFF + +enum { + CFRAME_CMD_WCFG = 1, + CFRAME_CMD_ROWON = 2, + CFRAME_CMD_ROWOFF = 3, + CFRAME_CMD_RCFG = 4, + CFRAME_CMD_DLPARK = 5, +}; + +static gint int_cmp(gconstpointer a, gconstpointer b, gpointer user_data) +{ + guint ua = GPOINTER_TO_UINT(a); + guint ub = GPOINTER_TO_UINT(b); + return (ua > ub) - (ua < ub); +} + +static void cfrm_imr_update_irq(XlnxVersalCFrameReg *s) +{ + bool pending = s->regs[R_CFRM_ISR0] & ~s->regs[R_CFRM_IMR0]; + qemu_set_irq(s->irq_cfrm_imr, pending); +} + +static void cfrm_isr_postw(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(reg->opaque); + cfrm_imr_update_irq(s); +} + +static uint64_t cfrm_ier_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(reg->opaque); + + s->regs[R_CFRM_IMR0] &= ~s->regs[R_CFRM_IER0]; + s->regs[R_CFRM_IER0] = 0; + cfrm_imr_update_irq(s); + return 0; +} + +static uint64_t cfrm_idr_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(reg->opaque); + + s->regs[R_CFRM_IMR0] |= s->regs[R_CFRM_IDR0]; + s->regs[R_CFRM_IDR0] = 0; + cfrm_imr_update_irq(s); + return 0; +} + +static uint64_t cfrm_itr_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(reg->opaque); + + s->regs[R_CFRM_ISR0] |= s->regs[R_CFRM_ITR0]; + s->regs[R_CFRM_ITR0] = 0; + cfrm_imr_update_irq(s); + return 0; +} + +static void cframe_incr_far(XlnxVersalCFrameReg *s) +{ + uint32_t faddr = ARRAY_FIELD_EX32(s->regs, FAR0, FRAME_ADDR); + uint32_t blktype = ARRAY_FIELD_EX32(s->regs, FAR0, BLOCKTYPE); + + assert(blktype <= MAX_BLOCKTYPE); + + faddr++; + if (faddr > s->cfg.blktype_num_frames[blktype]) { + /* Restart from 0 and increment block type */ + faddr = 0; + blktype++; + + assert(blktype <= MAX_BLOCKTYPE); + + ARRAY_FIELD_DP32(s->regs, FAR0, BLOCKTYPE, blktype); + } + + ARRAY_FIELD_DP32(s->regs, FAR0, FRAME_ADDR, faddr); +} + +static void cfrm_fdri_post_write(RegisterInfo *reg, uint64_t val) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(reg->opaque); + + if (s->row_configured && s->rowon && s->wcfg) { + + if (fifo32_num_free(&s->new_f_data) >= N_WORDS_128BIT) { + fifo32_push(&s->new_f_data, s->regs[R_FDRI0]); + fifo32_push(&s->new_f_data, s->regs[R_FDRI1]); + fifo32_push(&s->new_f_data, s->regs[R_FDRI2]); + fifo32_push(&s->new_f_data, s->regs[R_FDRI3]); + } + + if (fifo32_is_full(&s->new_f_data)) { + uint32_t addr = extract32(s->regs[R_FAR0], 0, 23); + XlnxCFrame *f = g_new(XlnxCFrame, 1); + + for (int i = 0; i < FRAME_NUM_WORDS; i++) { + f->data[i] = fifo32_pop(&s->new_f_data); + } + + g_tree_replace(s->cframes, GUINT_TO_POINTER(addr), f); + + cframe_incr_far(s); + + fifo32_reset(&s->new_f_data); + } + } +} + +static void cfrm_readout_frames(XlnxVersalCFrameReg *s, uint32_t start_addr, + uint32_t end_addr) +{ + /* + * NB: when our minimum glib version is at least 2.68 we can improve the + * performance of the cframe traversal by using g_tree_lookup_node and + * g_tree_node_next (instead of calling g_tree_lookup for finding each + * cframe). + */ + for (uint32_t addr = start_addr; addr < end_addr; addr++) { + XlnxCFrame *f = g_tree_lookup(s->cframes, GUINT_TO_POINTER(addr)); + + /* Transmit the data if a frame was found */ + if (f) { + for (int i = 0; i < FRAME_NUM_WORDS; i += 4) { + XlnxCfiPacket pkt = {}; + + pkt.data[0] = f->data[i]; + pkt.data[1] = f->data[i + 1]; + pkt.data[2] = f->data[i + 2]; + pkt.data[3] = f->data[i + 3]; + + if (s->cfg.cfu_fdro) { + xlnx_cfi_transfer_packet(s->cfg.cfu_fdro, &pkt); + } + } + } + } +} + +static void cfrm_frcnt_post_write(RegisterInfo *reg, uint64_t val) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(reg->opaque); + + if (s->row_configured && s->rowon && s->rcfg) { + uint32_t start_addr = extract32(s->regs[R_FAR0], 0, 23); + uint32_t end_addr = start_addr + s->regs[R_FRCNT0] / FRAME_NUM_QWORDS; + + cfrm_readout_frames(s, start_addr, end_addr); + } +} + +static void cfrm_cmd_post_write(RegisterInfo *reg, uint64_t val) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(reg->opaque); + + if (s->row_configured) { + uint8_t cmd = ARRAY_FIELD_EX32(s->regs, CMD0, CMD); + + switch (cmd) { + case CFRAME_CMD_WCFG: + s->wcfg = true; + break; + case CFRAME_CMD_ROWON: + s->rowon = true; + break; + case CFRAME_CMD_ROWOFF: + s->rowon = false; + break; + case CFRAME_CMD_RCFG: + s->rcfg = true; + break; + case CFRAME_CMD_DLPARK: + s->wcfg = false; + s->rcfg = false; + break; + default: + break; + }; + } +} + +static uint64_t cfrm_last_frame_bot_post_read(RegisterInfo *reg, + uint64_t val64) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(reg->opaque); + uint64_t val = 0; + + switch (reg->access->addr) { + case A_LAST_FRAME_BOT0: + val = FIELD_DP32(val, LAST_FRAME_BOT0, BLOCKTYPE1_LAST_FRAME_LSB, + s->cfg.blktype_num_frames[1]); + val = FIELD_DP32(val, LAST_FRAME_BOT0, BLOCKTYPE0_LAST_FRAME, + s->cfg.blktype_num_frames[0]); + break; + case A_LAST_FRAME_BOT1: + val = FIELD_DP32(val, LAST_FRAME_BOT1, BLOCKTYPE3_LAST_FRAME_LSB, + s->cfg.blktype_num_frames[3]); + val = FIELD_DP32(val, LAST_FRAME_BOT1, BLOCKTYPE2_LAST_FRAME, + s->cfg.blktype_num_frames[2]); + val = FIELD_DP32(val, LAST_FRAME_BOT1, BLOCKTYPE1_LAST_FRAME_MSB, + (s->cfg.blktype_num_frames[1] >> 12)); + break; + case A_LAST_FRAME_BOT2: + val = FIELD_DP32(val, LAST_FRAME_BOT2, BLOCKTYPE3_LAST_FRAME_MSB, + (s->cfg.blktype_num_frames[3] >> 4)); + break; + case A_LAST_FRAME_BOT3: + default: + break; + } + + return val; +} + +static uint64_t cfrm_last_frame_top_post_read(RegisterInfo *reg, + uint64_t val64) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(reg->opaque); + uint64_t val = 0; + + switch (reg->access->addr) { + case A_LAST_FRAME_TOP0: + val = FIELD_DP32(val, LAST_FRAME_TOP0, BLOCKTYPE5_LAST_FRAME_LSB, + s->cfg.blktype_num_frames[5]); + val = FIELD_DP32(val, LAST_FRAME_TOP0, BLOCKTYPE4_LAST_FRAME, + s->cfg.blktype_num_frames[4]); + break; + case A_LAST_FRAME_TOP1: + val = FIELD_DP32(val, LAST_FRAME_TOP1, BLOCKTYPE6_LAST_FRAME, + s->cfg.blktype_num_frames[6]); + val = FIELD_DP32(val, LAST_FRAME_TOP1, BLOCKTYPE5_LAST_FRAME_MSB, + (s->cfg.blktype_num_frames[5] >> 12)); + break; + case A_LAST_FRAME_TOP2: + case A_LAST_FRAME_BOT3: + default: + break; + } + + return val; +} + +static void cfrm_far_sfr_post_write(RegisterInfo *reg, uint64_t val) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(reg->opaque); + + if (s->row_configured && s->rowon && s->rcfg) { + uint32_t start_addr = extract32(s->regs[R_FAR_SFR0], 0, 23); + + /* Readback 1 frame */ + cfrm_readout_frames(s, start_addr, start_addr + 1); + } +} + +static const RegisterAccessInfo cframe_reg_regs_info[] = { + { .name = "CRC0", .addr = A_CRC0, + .rsvd = 0x00000000, + },{ .name = "CRC1", .addr = A_CRC0, + .rsvd = 0xffffffff, + },{ .name = "CRC2", .addr = A_CRC0, + .rsvd = 0xffffffff, + },{ .name = "CRC3", .addr = A_CRC0, + .rsvd = 0xffffffff, + },{ .name = "FAR0", .addr = A_FAR0, + .rsvd = 0xfe000000, + },{ .name = "FAR1", .addr = A_FAR1, + .rsvd = 0xffffffff, + },{ .name = "FAR2", .addr = A_FAR2, + .rsvd = 0xffffffff, + },{ .name = "FAR3", .addr = A_FAR3, + .rsvd = 0xffffffff, + },{ .name = "FAR_SFR0", .addr = A_FAR_SFR0, + .rsvd = 0xff800000, + },{ .name = "FAR_SFR1", .addr = A_FAR_SFR1, + .rsvd = 0xffffffff, + },{ .name = "FAR_SFR2", .addr = A_FAR_SFR2, + .rsvd = 0xffffffff, + },{ .name = "FAR_SFR3", .addr = A_FAR_SFR3, + .rsvd = 0xffffffff, + .post_write = cfrm_far_sfr_post_write, + },{ .name = "FDRI0", .addr = A_FDRI0, + },{ .name = "FDRI1", .addr = A_FDRI1, + },{ .name = "FDRI2", .addr = A_FDRI2, + },{ .name = "FDRI3", .addr = A_FDRI3, + .post_write = cfrm_fdri_post_write, + },{ .name = "FRCNT0", .addr = A_FRCNT0, + .rsvd = 0x00000000, + },{ .name = "FRCNT1", .addr = A_FRCNT1, + .rsvd = 0xffffffff, + },{ .name = "FRCNT2", .addr = A_FRCNT2, + .rsvd = 0xffffffff, + },{ .name = "FRCNT3", .addr = A_FRCNT3, + .rsvd = 0xffffffff, + .post_write = cfrm_frcnt_post_write + },{ .name = "CMD0", .addr = A_CMD0, + .rsvd = 0xffffffe0, + },{ .name = "CMD1", .addr = A_CMD1, + .rsvd = 0xffffffff, + },{ .name = "CMD2", .addr = A_CMD2, + .rsvd = 0xffffffff, + },{ .name = "CMD3", .addr = A_CMD3, + .rsvd = 0xffffffff, + .post_write = cfrm_cmd_post_write + },{ .name = "CR_MASK0", .addr = A_CR_MASK0, + .rsvd = 0x00000000, + },{ .name = "CR_MASK1", .addr = A_CR_MASK1, + .rsvd = 0x00000000, + },{ .name = "CR_MASK2", .addr = A_CR_MASK2, + .rsvd = 0x00000000, + },{ .name = "CR_MASK3", .addr = A_CR_MASK3, + .rsvd = 0xffffffff, + },{ .name = "CTL0", .addr = A_CTL0, + .rsvd = 0xfffffff8, + },{ .name = "CTL1", .addr = A_CTL1, + .rsvd = 0xffffffff, + },{ .name = "CTL2", .addr = A_CTL2, + .rsvd = 0xffffffff, + },{ .name = "CTL3", .addr = A_CTL3, + .rsvd = 0xffffffff, + },{ .name = "CFRM_ISR0", .addr = A_CFRM_ISR0, + .rsvd = 0xffc04000, + .w1c = 0x3bfff, + },{ .name = "CFRM_ISR1", .addr = A_CFRM_ISR1, + .rsvd = 0xffffffff, + },{ .name = "CFRM_ISR2", .addr = A_CFRM_ISR2, + .rsvd = 0xffffffff, + },{ .name = "CFRM_ISR3", .addr = A_CFRM_ISR3, + .rsvd = 0xffffffff, + .post_write = cfrm_isr_postw, + },{ .name = "CFRM_IMR0", .addr = A_CFRM_IMR0, + .rsvd = 0xffc04000, + .ro = 0xfffff, + .reset = 0x3bfff, + },{ .name = "CFRM_IMR1", .addr = A_CFRM_IMR1, + .rsvd = 0xffffffff, + },{ .name = "CFRM_IMR2", .addr = A_CFRM_IMR2, + .rsvd = 0xffffffff, + },{ .name = "CFRM_IMR3", .addr = A_CFRM_IMR3, + .rsvd = 0xffffffff, + },{ .name = "CFRM_IER0", .addr = A_CFRM_IER0, + .rsvd = 0xffc04000, + },{ .name = "CFRM_IER1", .addr = A_CFRM_IER1, + .rsvd = 0xffffffff, + },{ .name = "CFRM_IER2", .addr = A_CFRM_IER2, + .rsvd = 0xffffffff, + },{ .name = "CFRM_IER3", .addr = A_CFRM_IER3, + .rsvd = 0xffffffff, + .pre_write = cfrm_ier_prew, + },{ .name = "CFRM_IDR0", .addr = A_CFRM_IDR0, + .rsvd = 0xffc04000, + },{ .name = "CFRM_IDR1", .addr = A_CFRM_IDR1, + .rsvd = 0xffffffff, + },{ .name = "CFRM_IDR2", .addr = A_CFRM_IDR2, + .rsvd = 0xffffffff, + },{ .name = "CFRM_IDR3", .addr = A_CFRM_IDR3, + .rsvd = 0xffffffff, + .pre_write = cfrm_idr_prew, + },{ .name = "CFRM_ITR0", .addr = A_CFRM_ITR0, + .rsvd = 0xffc04000, + },{ .name = "CFRM_ITR1", .addr = A_CFRM_ITR1, + .rsvd = 0xffffffff, + },{ .name = "CFRM_ITR2", .addr = A_CFRM_ITR2, + .rsvd = 0xffffffff, + },{ .name = "CFRM_ITR3", .addr = A_CFRM_ITR3, + .rsvd = 0xffffffff, + .pre_write = cfrm_itr_prew, + },{ .name = "SEU_SYNDRM00", .addr = A_SEU_SYNDRM00, + },{ .name = "SEU_SYNDRM01", .addr = A_SEU_SYNDRM01, + },{ .name = "SEU_SYNDRM02", .addr = A_SEU_SYNDRM02, + },{ .name = "SEU_SYNDRM03", .addr = A_SEU_SYNDRM03, + },{ .name = "SEU_SYNDRM10", .addr = A_SEU_SYNDRM10, + },{ .name = "SEU_SYNDRM11", .addr = A_SEU_SYNDRM11, + },{ .name = "SEU_SYNDRM12", .addr = A_SEU_SYNDRM12, + },{ .name = "SEU_SYNDRM13", .addr = A_SEU_SYNDRM13, + },{ .name = "SEU_SYNDRM20", .addr = A_SEU_SYNDRM20, + },{ .name = "SEU_SYNDRM21", .addr = A_SEU_SYNDRM21, + },{ .name = "SEU_SYNDRM22", .addr = A_SEU_SYNDRM22, + },{ .name = "SEU_SYNDRM23", .addr = A_SEU_SYNDRM23, + },{ .name = "SEU_SYNDRM30", .addr = A_SEU_SYNDRM30, + },{ .name = "SEU_SYNDRM31", .addr = A_SEU_SYNDRM31, + },{ .name = "SEU_SYNDRM32", .addr = A_SEU_SYNDRM32, + },{ .name = "SEU_SYNDRM33", .addr = A_SEU_SYNDRM33, + },{ .name = "SEU_VIRTUAL_SYNDRM0", .addr = A_SEU_VIRTUAL_SYNDRM0, + },{ .name = "SEU_VIRTUAL_SYNDRM1", .addr = A_SEU_VIRTUAL_SYNDRM1, + },{ .name = "SEU_VIRTUAL_SYNDRM2", .addr = A_SEU_VIRTUAL_SYNDRM2, + },{ .name = "SEU_VIRTUAL_SYNDRM3", .addr = A_SEU_VIRTUAL_SYNDRM3, + },{ .name = "SEU_CRC0", .addr = A_SEU_CRC0, + },{ .name = "SEU_CRC1", .addr = A_SEU_CRC1, + },{ .name = "SEU_CRC2", .addr = A_SEU_CRC2, + },{ .name = "SEU_CRC3", .addr = A_SEU_CRC3, + },{ .name = "CFRAME_FAR_BOT0", .addr = A_CFRAME_FAR_BOT0, + },{ .name = "CFRAME_FAR_BOT1", .addr = A_CFRAME_FAR_BOT1, + },{ .name = "CFRAME_FAR_BOT2", .addr = A_CFRAME_FAR_BOT2, + },{ .name = "CFRAME_FAR_BOT3", .addr = A_CFRAME_FAR_BOT3, + },{ .name = "CFRAME_FAR_TOP0", .addr = A_CFRAME_FAR_TOP0, + },{ .name = "CFRAME_FAR_TOP1", .addr = A_CFRAME_FAR_TOP1, + },{ .name = "CFRAME_FAR_TOP2", .addr = A_CFRAME_FAR_TOP2, + },{ .name = "CFRAME_FAR_TOP3", .addr = A_CFRAME_FAR_TOP3, + },{ .name = "LAST_FRAME_BOT0", .addr = A_LAST_FRAME_BOT0, + .ro = 0xffffffff, + .post_read = cfrm_last_frame_bot_post_read, + },{ .name = "LAST_FRAME_BOT1", .addr = A_LAST_FRAME_BOT1, + .ro = 0xffffffff, + .post_read = cfrm_last_frame_bot_post_read, + },{ .name = "LAST_FRAME_BOT2", .addr = A_LAST_FRAME_BOT2, + .ro = 0xffffffff, + .post_read = cfrm_last_frame_bot_post_read, + },{ .name = "LAST_FRAME_BOT3", .addr = A_LAST_FRAME_BOT3, + .ro = 0xffffffff, + .post_read = cfrm_last_frame_bot_post_read, + },{ .name = "LAST_FRAME_TOP0", .addr = A_LAST_FRAME_TOP0, + .ro = 0xffffffff, + .post_read = cfrm_last_frame_top_post_read, + },{ .name = "LAST_FRAME_TOP1", .addr = A_LAST_FRAME_TOP1, + .ro = 0xffffffff, + .post_read = cfrm_last_frame_top_post_read, + },{ .name = "LAST_FRAME_TOP2", .addr = A_LAST_FRAME_TOP2, + .ro = 0xffffffff, + .post_read = cfrm_last_frame_top_post_read, + },{ .name = "LAST_FRAME_TOP3", .addr = A_LAST_FRAME_TOP3, + .ro = 0xffffffff, + .post_read = cfrm_last_frame_top_post_read, + } +}; + +static void cframe_reg_cfi_transfer_packet(XlnxCfiIf *cfi_if, + XlnxCfiPacket *pkt) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(cfi_if); + uint64_t we = MAKE_64BIT_MASK(0, 4 * 8); + + if (!s->row_configured) { + return; + } + + switch (pkt->reg_addr) { + case CFRAME_FAR: + s->regs[R_FAR0] = pkt->data[0]; + break; + case CFRAME_SFR: + s->regs[R_FAR_SFR0] = pkt->data[0]; + register_write(&s->regs_info[R_FAR_SFR3], 0, + we, object_get_typename(OBJECT(s)), + XLNX_VERSAL_CFRAME_REG_ERR_DEBUG); + break; + case CFRAME_FDRI: + s->regs[R_FDRI0] = pkt->data[0]; + s->regs[R_FDRI1] = pkt->data[1]; + s->regs[R_FDRI2] = pkt->data[2]; + register_write(&s->regs_info[R_FDRI3], pkt->data[3], + we, object_get_typename(OBJECT(s)), + XLNX_VERSAL_CFRAME_REG_ERR_DEBUG); + break; + case CFRAME_CMD: + ARRAY_FIELD_DP32(s->regs, CMD0, CMD, pkt->data[0]); + + register_write(&s->regs_info[R_CMD3], 0, + we, object_get_typename(OBJECT(s)), + XLNX_VERSAL_CFRAME_REG_ERR_DEBUG); + break; + default: + break; + } +} + +static uint64_t cframe_reg_fdri_read(void *opaque, hwaddr addr, unsigned size) +{ + qemu_log_mask(LOG_GUEST_ERROR, "%s: Unsupported read from addr=%" + HWADDR_PRIx "\n", __func__, addr); + return 0; +} + +static void cframe_reg_fdri_write(void *opaque, hwaddr addr, uint64_t value, + unsigned size) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(opaque); + uint32_t wfifo[WFIFO_SZ]; + + if (update_wfifo(addr, value, s->wfifo, wfifo)) { + uint64_t we = MAKE_64BIT_MASK(0, 4 * 8); + + s->regs[R_FDRI0] = wfifo[0]; + s->regs[R_FDRI1] = wfifo[1]; + s->regs[R_FDRI2] = wfifo[2]; + register_write(&s->regs_info[R_FDRI3], wfifo[3], + we, object_get_typename(OBJECT(s)), + XLNX_VERSAL_CFRAME_REG_ERR_DEBUG); + } +} + +static void cframe_reg_reset_enter(Object *obj, ResetType type) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(obj); + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(s->regs_info); ++i) { + register_reset(&s->regs_info[i]); + } + memset(s->wfifo, 0, WFIFO_SZ * sizeof(uint32_t)); + fifo32_reset(&s->new_f_data); + + if (g_tree_nnodes(s->cframes)) { + /* + * Take a reference so when g_tree_destroy() unrefs it we keep the + * GTree and only destroy its contents. NB: when our minimum + * glib version is at least 2.70 we could use g_tree_remove_all(). + */ + g_tree_ref(s->cframes); + g_tree_destroy(s->cframes); + } +} + +static void cframe_reg_reset_hold(Object *obj) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(obj); + + cfrm_imr_update_irq(s); +} + +static const MemoryRegionOps cframe_reg_ops = { + .read = register_read_memory, + .write = register_write_memory, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static const MemoryRegionOps cframe_reg_fdri_ops = { + .read = cframe_reg_fdri_read, + .write = cframe_reg_fdri_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void cframe_reg_realize(DeviceState *dev, Error **errp) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(dev); + + for (int i = 0; i < ARRAY_SIZE(s->cfg.blktype_num_frames); i++) { + if (s->cfg.blktype_num_frames[i] > MAX_BLOCKTYPE_FRAMES) { + error_setg(errp, + "blktype-frames%d > 0xFFFFF (max frame per block)", + i); + return; + } + if (s->cfg.blktype_num_frames[i]) { + s->row_configured = true; + } + } +} + +static void cframe_reg_init(Object *obj) +{ + XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + RegisterInfoArray *reg_array; + + memory_region_init(&s->iomem, obj, TYPE_XLNX_VERSAL_CFRAME_REG, + CFRAME_REG_R_MAX * 4); + reg_array = + register_init_block32(DEVICE(obj), cframe_reg_regs_info, + ARRAY_SIZE(cframe_reg_regs_info), + s->regs_info, s->regs, + &cframe_reg_ops, + XLNX_VERSAL_CFRAME_REG_ERR_DEBUG, + CFRAME_REG_R_MAX * 4); + memory_region_add_subregion(&s->iomem, + 0x0, + ®_array->mem); + sysbus_init_mmio(sbd, &s->iomem); + memory_region_init_io(&s->iomem_fdri, obj, &cframe_reg_fdri_ops, s, + TYPE_XLNX_VERSAL_CFRAME_REG "-fdri", + KEYHOLE_STREAM_4K); + sysbus_init_mmio(sbd, &s->iomem_fdri); + sysbus_init_irq(sbd, &s->irq_cfrm_imr); + + s->cframes = g_tree_new_full((GCompareDataFunc)int_cmp, NULL, + NULL, (GDestroyNotify)g_free); + fifo32_create(&s->new_f_data, FRAME_NUM_WORDS); +} + +static const VMStateDescription vmstate_cframe = { + .name = "cframe", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(data, XlnxCFrame, FRAME_NUM_WORDS), + VMSTATE_END_OF_LIST() + } +}; + +static const VMStateDescription vmstate_cframe_reg = { + .name = TYPE_XLNX_VERSAL_CFRAME_REG, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(wfifo, XlnxVersalCFrameReg, 4), + VMSTATE_UINT32_ARRAY(regs, XlnxVersalCFrameReg, CFRAME_REG_R_MAX), + VMSTATE_BOOL(rowon, XlnxVersalCFrameReg), + VMSTATE_BOOL(wcfg, XlnxVersalCFrameReg), + VMSTATE_BOOL(rcfg, XlnxVersalCFrameReg), + VMSTATE_GTREE_DIRECT_KEY_V(cframes, XlnxVersalCFrameReg, 1, + &vmstate_cframe, XlnxCFrame), + VMSTATE_FIFO32(new_f_data, XlnxVersalCFrameReg), + VMSTATE_END_OF_LIST(), + } +}; + +static Property cframe_regs_props[] = { + DEFINE_PROP_LINK("cfu-fdro", XlnxVersalCFrameReg, cfg.cfu_fdro, + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_UINT32("blktype0-frames", XlnxVersalCFrameReg, + cfg.blktype_num_frames[0], 0), + DEFINE_PROP_UINT32("blktype1-frames", XlnxVersalCFrameReg, + cfg.blktype_num_frames[1], 0), + DEFINE_PROP_UINT32("blktype2-frames", XlnxVersalCFrameReg, + cfg.blktype_num_frames[2], 0), + DEFINE_PROP_UINT32("blktype3-frames", XlnxVersalCFrameReg, + cfg.blktype_num_frames[3], 0), + DEFINE_PROP_UINT32("blktype4-frames", XlnxVersalCFrameReg, + cfg.blktype_num_frames[4], 0), + DEFINE_PROP_UINT32("blktype5-frames", XlnxVersalCFrameReg, + cfg.blktype_num_frames[5], 0), + DEFINE_PROP_UINT32("blktype6-frames", XlnxVersalCFrameReg, + cfg.blktype_num_frames[6], 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static void cframe_reg_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + XlnxCfiIfClass *xcic = XLNX_CFI_IF_CLASS(klass); + + dc->vmsd = &vmstate_cframe_reg; + dc->realize = cframe_reg_realize; + rc->phases.enter = cframe_reg_reset_enter; + rc->phases.hold = cframe_reg_reset_hold; + device_class_set_props(dc, cframe_regs_props); + xcic->cfi_transfer_packet = cframe_reg_cfi_transfer_packet; +} + +static const TypeInfo cframe_reg_info = { + .name = TYPE_XLNX_VERSAL_CFRAME_REG, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(XlnxVersalCFrameReg), + .class_init = cframe_reg_class_init, + .instance_init = cframe_reg_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_XLNX_CFI_IF }, + { } + } +}; + +static void cframe_reg_register_types(void) +{ + type_register_static(&cframe_reg_info); +} + +type_init(cframe_reg_register_types) diff --git a/include/hw/misc/xlnx-versal-cframe-reg.h b/include/hw/misc/xlnx-versal-cframe-reg.h new file mode 100644 index 0000000000..f286d973bf --- /dev/null +++ b/include/hw/misc/xlnx-versal-cframe-reg.h @@ -0,0 +1,286 @@ +/* + * QEMU model of the Configuration Frame Control module + * + * Copyright (C) 2023, Advanced Micro Devices, Inc. + * + * Written by Francisco Iglesias + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + * References: + * [1] Versal ACAP Technical Reference Manual, + * https://www.xilinx.com/support/documentation/architecture-manuals/am011-versal-acap-trm.pdf + * + * [2] Versal ACAP Register Reference, + * https://www.xilinx.com/htmldocs/registers/am012/am012-versal-register-reference.html + */ +#ifndef HW_MISC_XLNX_VERSAL_CFRAME_REG_H +#define HW_MISC_XLNX_VERSAL_CFRAME_REG_H + +#include "hw/sysbus.h" +#include "hw/register.h" +#include "hw/misc/xlnx-cfi-if.h" +#include "hw/misc/xlnx-versal-cfu.h" +#include "qemu/fifo32.h" + +#define TYPE_XLNX_VERSAL_CFRAME_REG "xlnx,cframe-reg" +OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersalCFrameReg, XLNX_VERSAL_CFRAME_REG) + +/* + * The registers in this module are 128 bits wide but it is ok to write + * and read them through 4 sequential 32 bit accesses (address[3:2] = 0, + * 1, 2, 3). + */ +REG32(CRC0, 0x0) + FIELD(CRC, CRC, 0, 32) +REG32(CRC1, 0x4) +REG32(CRC2, 0x8) +REG32(CRC3, 0xc) +REG32(FAR0, 0x10) + FIELD(FAR0, SEGMENT, 23, 2) + FIELD(FAR0, BLOCKTYPE, 20, 3) + FIELD(FAR0, FRAME_ADDR, 0, 20) +REG32(FAR1, 0x14) +REG32(FAR2, 0x18) +REG32(FAR3, 0x1c) +REG32(FAR_SFR0, 0x20) + FIELD(FAR_SFR0, BLOCKTYPE, 20, 3) + FIELD(FAR_SFR0, FRAME_ADDR, 0, 20) +REG32(FAR_SFR1, 0x24) +REG32(FAR_SFR2, 0x28) +REG32(FAR_SFR3, 0x2c) +REG32(FDRI0, 0x40) +REG32(FDRI1, 0x44) +REG32(FDRI2, 0x48) +REG32(FDRI3, 0x4c) +REG32(FRCNT0, 0x50) + FIELD(FRCNT0, FRCNT, 0, 32) +REG32(FRCNT1, 0x54) +REG32(FRCNT2, 0x58) +REG32(FRCNT3, 0x5c) +REG32(CMD0, 0x60) + FIELD(CMD0, CMD, 0, 5) +REG32(CMD1, 0x64) +REG32(CMD2, 0x68) +REG32(CMD3, 0x6c) +REG32(CR_MASK0, 0x70) +REG32(CR_MASK1, 0x74) +REG32(CR_MASK2, 0x78) +REG32(CR_MASK3, 0x7c) +REG32(CTL0, 0x80) + FIELD(CTL, PER_FRAME_CRC, 0, 1) +REG32(CTL1, 0x84) +REG32(CTL2, 0x88) +REG32(CTL3, 0x8c) +REG32(CFRM_ISR0, 0x150) + FIELD(CFRM_ISR0, READ_BROADCAST_ERROR, 21, 1) + FIELD(CFRM_ISR0, CMD_MISSING_ERROR, 20, 1) + FIELD(CFRM_ISR0, RW_ROWOFF_ERROR, 19, 1) + FIELD(CFRM_ISR0, READ_REG_ADDR_ERROR, 18, 1) + FIELD(CFRM_ISR0, READ_BLK_TYPE_ERROR, 17, 1) + FIELD(CFRM_ISR0, READ_FRAME_ADDR_ERROR, 16, 1) + FIELD(CFRM_ISR0, WRITE_REG_ADDR_ERROR, 15, 1) + FIELD(CFRM_ISR0, WRITE_BLK_TYPE_ERROR, 13, 1) + FIELD(CFRM_ISR0, WRITE_FRAME_ADDR_ERROR, 12, 1) + FIELD(CFRM_ISR0, MFW_OVERRUN_ERROR, 11, 1) + FIELD(CFRM_ISR0, FAR_FIFO_UNDERFLOW, 10, 1) + FIELD(CFRM_ISR0, FAR_FIFO_OVERFLOW, 9, 1) + FIELD(CFRM_ISR0, PER_FRAME_SEQ_ERROR, 8, 1) + FIELD(CFRM_ISR0, CRC_ERROR, 7, 1) + FIELD(CFRM_ISR0, WRITE_OVERRUN_ERROR, 6, 1) + FIELD(CFRM_ISR0, READ_OVERRUN_ERROR, 5, 1) + FIELD(CFRM_ISR0, CMD_INTERRUPT_ERROR, 4, 1) + FIELD(CFRM_ISR0, WRITE_INTERRUPT_ERROR, 3, 1) + FIELD(CFRM_ISR0, READ_INTERRUPT_ERROR, 2, 1) + FIELD(CFRM_ISR0, SEU_CRC_ERROR, 1, 1) + FIELD(CFRM_ISR0, SEU_ECC_ERROR, 0, 1) +REG32(CFRM_ISR1, 0x154) +REG32(CFRM_ISR2, 0x158) +REG32(CFRM_ISR3, 0x15c) +REG32(CFRM_IMR0, 0x160) + FIELD(CFRM_IMR0, READ_BROADCAST_ERROR, 21, 1) + FIELD(CFRM_IMR0, CMD_MISSING_ERROR, 20, 1) + FIELD(CFRM_IMR0, RW_ROWOFF_ERROR, 19, 1) + FIELD(CFRM_IMR0, READ_REG_ADDR_ERROR, 18, 1) + FIELD(CFRM_IMR0, READ_BLK_TYPE_ERROR, 17, 1) + FIELD(CFRM_IMR0, READ_FRAME_ADDR_ERROR, 16, 1) + FIELD(CFRM_IMR0, WRITE_REG_ADDR_ERROR, 15, 1) + FIELD(CFRM_IMR0, WRITE_BLK_TYPE_ERROR, 13, 1) + FIELD(CFRM_IMR0, WRITE_FRAME_ADDR_ERROR, 12, 1) + FIELD(CFRM_IMR0, MFW_OVERRUN_ERROR, 11, 1) + FIELD(CFRM_IMR0, FAR_FIFO_UNDERFLOW, 10, 1) + FIELD(CFRM_IMR0, FAR_FIFO_OVERFLOW, 9, 1) + FIELD(CFRM_IMR0, PER_FRAME_SEQ_ERROR, 8, 1) + FIELD(CFRM_IMR0, CRC_ERROR, 7, 1) + FIELD(CFRM_IMR0, WRITE_OVERRUN_ERROR, 6, 1) + FIELD(CFRM_IMR0, READ_OVERRUN_ERROR, 5, 1) + FIELD(CFRM_IMR0, CMD_INTERRUPT_ERROR, 4, 1) + FIELD(CFRM_IMR0, WRITE_INTERRUPT_ERROR, 3, 1) + FIELD(CFRM_IMR0, READ_INTERRUPT_ERROR, 2, 1) + FIELD(CFRM_IMR0, SEU_CRC_ERROR, 1, 1) + FIELD(CFRM_IMR0, SEU_ECC_ERROR, 0, 1) +REG32(CFRM_IMR1, 0x164) +REG32(CFRM_IMR2, 0x168) +REG32(CFRM_IMR3, 0x16c) +REG32(CFRM_IER0, 0x170) + FIELD(CFRM_IER0, READ_BROADCAST_ERROR, 21, 1) + FIELD(CFRM_IER0, CMD_MISSING_ERROR, 20, 1) + FIELD(CFRM_IER0, RW_ROWOFF_ERROR, 19, 1) + FIELD(CFRM_IER0, READ_REG_ADDR_ERROR, 18, 1) + FIELD(CFRM_IER0, READ_BLK_TYPE_ERROR, 17, 1) + FIELD(CFRM_IER0, READ_FRAME_ADDR_ERROR, 16, 1) + FIELD(CFRM_IER0, WRITE_REG_ADDR_ERROR, 15, 1) + FIELD(CFRM_IER0, WRITE_BLK_TYPE_ERROR, 13, 1) + FIELD(CFRM_IER0, WRITE_FRAME_ADDR_ERROR, 12, 1) + FIELD(CFRM_IER0, MFW_OVERRUN_ERROR, 11, 1) + FIELD(CFRM_IER0, FAR_FIFO_UNDERFLOW, 10, 1) + FIELD(CFRM_IER0, FAR_FIFO_OVERFLOW, 9, 1) + FIELD(CFRM_IER0, PER_FRAME_SEQ_ERROR, 8, 1) + FIELD(CFRM_IER0, CRC_ERROR, 7, 1) + FIELD(CFRM_IER0, WRITE_OVERRUN_ERROR, 6, 1) + FIELD(CFRM_IER0, READ_OVERRUN_ERROR, 5, 1) + FIELD(CFRM_IER0, CMD_INTERRUPT_ERROR, 4, 1) + FIELD(CFRM_IER0, WRITE_INTERRUPT_ERROR, 3, 1) + FIELD(CFRM_IER0, READ_INTERRUPT_ERROR, 2, 1) + FIELD(CFRM_IER0, SEU_CRC_ERROR, 1, 1) + FIELD(CFRM_IER0, SEU_ECC_ERROR, 0, 1) +REG32(CFRM_IER1, 0x174) +REG32(CFRM_IER2, 0x178) +REG32(CFRM_IER3, 0x17c) +REG32(CFRM_IDR0, 0x180) + FIELD(CFRM_IDR0, READ_BROADCAST_ERROR, 21, 1) + FIELD(CFRM_IDR0, CMD_MISSING_ERROR, 20, 1) + FIELD(CFRM_IDR0, RW_ROWOFF_ERROR, 19, 1) + FIELD(CFRM_IDR0, READ_REG_ADDR_ERROR, 18, 1) + FIELD(CFRM_IDR0, READ_BLK_TYPE_ERROR, 17, 1) + FIELD(CFRM_IDR0, READ_FRAME_ADDR_ERROR, 16, 1) + FIELD(CFRM_IDR0, WRITE_REG_ADDR_ERROR, 15, 1) + FIELD(CFRM_IDR0, WRITE_BLK_TYPE_ERROR, 13, 1) + FIELD(CFRM_IDR0, WRITE_FRAME_ADDR_ERROR, 12, 1) + FIELD(CFRM_IDR0, MFW_OVERRUN_ERROR, 11, 1) + FIELD(CFRM_IDR0, FAR_FIFO_UNDERFLOW, 10, 1) + FIELD(CFRM_IDR0, FAR_FIFO_OVERFLOW, 9, 1) + FIELD(CFRM_IDR0, PER_FRAME_SEQ_ERROR, 8, 1) + FIELD(CFRM_IDR0, CRC_ERROR, 7, 1) + FIELD(CFRM_IDR0, WRITE_OVERRUN_ERROR, 6, 1) + FIELD(CFRM_IDR0, READ_OVERRUN_ERROR, 5, 1) + FIELD(CFRM_IDR0, CMD_INTERRUPT_ERROR, 4, 1) + FIELD(CFRM_IDR0, WRITE_INTERRUPT_ERROR, 3, 1) + FIELD(CFRM_IDR0, READ_INTERRUPT_ERROR, 2, 1) + FIELD(CFRM_IDR0, SEU_CRC_ERROR, 1, 1) + FIELD(CFRM_IDR0, SEU_ECC_ERROR, 0, 1) +REG32(CFRM_IDR1, 0x184) +REG32(CFRM_IDR2, 0x188) +REG32(CFRM_IDR3, 0x18c) +REG32(CFRM_ITR0, 0x190) + FIELD(CFRM_ITR0, READ_BROADCAST_ERROR, 21, 1) + FIELD(CFRM_ITR0, CMD_MISSING_ERROR, 20, 1) + FIELD(CFRM_ITR0, RW_ROWOFF_ERROR, 19, 1) + FIELD(CFRM_ITR0, READ_REG_ADDR_ERROR, 18, 1) + FIELD(CFRM_ITR0, READ_BLK_TYPE_ERROR, 17, 1) + FIELD(CFRM_ITR0, READ_FRAME_ADDR_ERROR, 16, 1) + FIELD(CFRM_ITR0, WRITE_REG_ADDR_ERROR, 15, 1) + FIELD(CFRM_ITR0, WRITE_BLK_TYPE_ERROR, 13, 1) + FIELD(CFRM_ITR0, WRITE_FRAME_ADDR_ERROR, 12, 1) + FIELD(CFRM_ITR0, MFW_OVERRUN_ERROR, 11, 1) + FIELD(CFRM_ITR0, FAR_FIFO_UNDERFLOW, 10, 1) + FIELD(CFRM_ITR0, FAR_FIFO_OVERFLOW, 9, 1) + FIELD(CFRM_ITR0, PER_FRAME_SEQ_ERROR, 8, 1) + FIELD(CFRM_ITR0, CRC_ERROR, 7, 1) + FIELD(CFRM_ITR0, WRITE_OVERRUN_ERROR, 6, 1) + FIELD(CFRM_ITR0, READ_OVERRUN_ERROR, 5, 1) + FIELD(CFRM_ITR0, CMD_INTERRUPT_ERROR, 4, 1) + FIELD(CFRM_ITR0, WRITE_INTERRUPT_ERROR, 3, 1) + FIELD(CFRM_ITR0, READ_INTERRUPT_ERROR, 2, 1) + FIELD(CFRM_ITR0, SEU_CRC_ERROR, 1, 1) + FIELD(CFRM_ITR0, SEU_ECC_ERROR, 0, 1) +REG32(CFRM_ITR1, 0x194) +REG32(CFRM_ITR2, 0x198) +REG32(CFRM_ITR3, 0x19c) +REG32(SEU_SYNDRM00, 0x1a0) +REG32(SEU_SYNDRM01, 0x1a4) +REG32(SEU_SYNDRM02, 0x1a8) +REG32(SEU_SYNDRM03, 0x1ac) +REG32(SEU_SYNDRM10, 0x1b0) +REG32(SEU_SYNDRM11, 0x1b4) +REG32(SEU_SYNDRM12, 0x1b8) +REG32(SEU_SYNDRM13, 0x1bc) +REG32(SEU_SYNDRM20, 0x1c0) +REG32(SEU_SYNDRM21, 0x1c4) +REG32(SEU_SYNDRM22, 0x1c8) +REG32(SEU_SYNDRM23, 0x1cc) +REG32(SEU_SYNDRM30, 0x1d0) +REG32(SEU_SYNDRM31, 0x1d4) +REG32(SEU_SYNDRM32, 0x1d8) +REG32(SEU_SYNDRM33, 0x1dc) +REG32(SEU_VIRTUAL_SYNDRM0, 0x1e0) +REG32(SEU_VIRTUAL_SYNDRM1, 0x1e4) +REG32(SEU_VIRTUAL_SYNDRM2, 0x1e8) +REG32(SEU_VIRTUAL_SYNDRM3, 0x1ec) +REG32(SEU_CRC0, 0x1f0) +REG32(SEU_CRC1, 0x1f4) +REG32(SEU_CRC2, 0x1f8) +REG32(SEU_CRC3, 0x1fc) +REG32(CFRAME_FAR_BOT0, 0x200) +REG32(CFRAME_FAR_BOT1, 0x204) +REG32(CFRAME_FAR_BOT2, 0x208) +REG32(CFRAME_FAR_BOT3, 0x20c) +REG32(CFRAME_FAR_TOP0, 0x210) +REG32(CFRAME_FAR_TOP1, 0x214) +REG32(CFRAME_FAR_TOP2, 0x218) +REG32(CFRAME_FAR_TOP3, 0x21c) +REG32(LAST_FRAME_BOT0, 0x220) + FIELD(LAST_FRAME_BOT0, BLOCKTYPE1_LAST_FRAME_LSB, 20, 12) + FIELD(LAST_FRAME_BOT0, BLOCKTYPE0_LAST_FRAME, 0, 20) +REG32(LAST_FRAME_BOT1, 0x224) + FIELD(LAST_FRAME_BOT1, BLOCKTYPE3_LAST_FRAME_LSB, 28, 4) + FIELD(LAST_FRAME_BOT1, BLOCKTYPE2_LAST_FRAME, 8, 20) + FIELD(LAST_FRAME_BOT1, BLOCKTYPE1_LAST_FRAME_MSB, 0, 8) +REG32(LAST_FRAME_BOT2, 0x228) + FIELD(LAST_FRAME_BOT2, BLOCKTYPE3_LAST_FRAME_MSB, 0, 16) +REG32(LAST_FRAME_BOT3, 0x22c) +REG32(LAST_FRAME_TOP0, 0x230) + FIELD(LAST_FRAME_TOP0, BLOCKTYPE5_LAST_FRAME_LSB, 20, 12) + FIELD(LAST_FRAME_TOP0, BLOCKTYPE4_LAST_FRAME, 0, 20) +REG32(LAST_FRAME_TOP1, 0x234) + FIELD(LAST_FRAME_TOP1, BLOCKTYPE6_LAST_FRAME, 8, 20) + FIELD(LAST_FRAME_TOP1, BLOCKTYPE5_LAST_FRAME_MSB, 0, 8) +REG32(LAST_FRAME_TOP2, 0x238) +REG32(LAST_FRAME_TOP3, 0x23c) + +#define CFRAME_REG_R_MAX (R_LAST_FRAME_TOP3 + 1) + +#define FRAME_NUM_QWORDS 25 +#define FRAME_NUM_WORDS (FRAME_NUM_QWORDS * 4) /* 25 * 128 bits */ + +typedef struct XlnxCFrame { + uint32_t data[FRAME_NUM_WORDS]; +} XlnxCFrame; + +struct XlnxVersalCFrameReg { + SysBusDevice parent_obj; + MemoryRegion iomem; + MemoryRegion iomem_fdri; + qemu_irq irq_cfrm_imr; + + /* 128-bit wfifo. */ + uint32_t wfifo[WFIFO_SZ]; + + uint32_t regs[CFRAME_REG_R_MAX]; + RegisterInfo regs_info[CFRAME_REG_R_MAX]; + + bool rowon; + bool wcfg; + bool rcfg; + + GTree *cframes; + Fifo32 new_f_data; + + struct { + XlnxCfiIf *cfu_fdro; + uint32_t blktype_num_frames[7]; + } cfg; + bool row_configured; +}; + +#endif From eadd3343c494379e68c18545c160a9f50b7239d0 Mon Sep 17 00:00:00 2001 From: Francisco Iglesias Date: Thu, 31 Aug 2023 17:56:59 +0100 Subject: [PATCH 16/26] hw/misc: Introduce a model of Xilinx Versal's CFRAME_BCAST_REG Introduce a model of Xilinx Versal's Configuration Frame broadcast controller (CFRAME_BCAST_REG). Signed-off-by: Francisco Iglesias Reviewed-by: Peter Maydell Message-id: 20230831165701.2016397-7-francisco.iglesias@amd.com Signed-off-by: Peter Maydell --- hw/misc/xlnx-versal-cframe-reg.c | 161 +++++++++++++++++++++++ include/hw/misc/xlnx-versal-cframe-reg.h | 17 +++ 2 files changed, 178 insertions(+) diff --git a/hw/misc/xlnx-versal-cframe-reg.c b/hw/misc/xlnx-versal-cframe-reg.c index 78db68f10c..8e8ec0715a 100644 --- a/hw/misc/xlnx-versal-cframe-reg.c +++ b/hw/misc/xlnx-versal-cframe-reg.c @@ -569,6 +569,83 @@ static const MemoryRegionOps cframe_reg_fdri_ops = { }, }; +static uint64_t cframes_bcast_reg_read(void *opaque, hwaddr addr, unsigned size) +{ + qemu_log_mask(LOG_GUEST_ERROR, "%s: Unsupported read from addr=%" + HWADDR_PRIx "\n", __func__, addr); + return 0; +} + +static void cframes_bcast_write(XlnxVersalCFrameBcastReg *s, uint8_t reg_addr, + uint32_t *wfifo) +{ + XlnxCfiPacket pkt = { + .reg_addr = reg_addr, + .data[0] = wfifo[0], + .data[1] = wfifo[1], + .data[2] = wfifo[2], + .data[3] = wfifo[3] + }; + + for (int i = 0; i < ARRAY_SIZE(s->cfg.cframe); i++) { + if (s->cfg.cframe[i]) { + xlnx_cfi_transfer_packet(s->cfg.cframe[i], &pkt); + } + } +} + +static void cframes_bcast_reg_write(void *opaque, hwaddr addr, uint64_t value, + unsigned size) +{ + XlnxVersalCFrameBcastReg *s = XLNX_VERSAL_CFRAME_BCAST_REG(opaque); + uint32_t wfifo[WFIFO_SZ]; + + if (update_wfifo(addr, value, s->wfifo, wfifo)) { + uint8_t reg_addr = extract32(addr, 4, 6); + + cframes_bcast_write(s, reg_addr, wfifo); + } +} + +static uint64_t cframes_bcast_fdri_read(void *opaque, hwaddr addr, + unsigned size) +{ + qemu_log_mask(LOG_GUEST_ERROR, "%s: Unsupported read from addr=%" + HWADDR_PRIx "\n", __func__, addr); + return 0; +} + +static void cframes_bcast_fdri_write(void *opaque, hwaddr addr, uint64_t value, + unsigned size) +{ + XlnxVersalCFrameBcastReg *s = XLNX_VERSAL_CFRAME_BCAST_REG(opaque); + uint32_t wfifo[WFIFO_SZ]; + + if (update_wfifo(addr, value, s->wfifo, wfifo)) { + cframes_bcast_write(s, CFRAME_FDRI, wfifo); + } +} + +static const MemoryRegionOps cframes_bcast_reg_reg_ops = { + .read = cframes_bcast_reg_read, + .write = cframes_bcast_reg_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static const MemoryRegionOps cframes_bcast_reg_fdri_ops = { + .read = cframes_bcast_fdri_read, + .write = cframes_bcast_fdri_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + static void cframe_reg_realize(DeviceState *dev, Error **errp) { XlnxVersalCFrameReg *s = XLNX_VERSAL_CFRAME_REG(dev); @@ -663,6 +740,71 @@ static Property cframe_regs_props[] = { DEFINE_PROP_END_OF_LIST(), }; +static void cframe_bcast_reg_init(Object *obj) +{ + XlnxVersalCFrameBcastReg *s = XLNX_VERSAL_CFRAME_BCAST_REG(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + memory_region_init_io(&s->iomem_reg, obj, &cframes_bcast_reg_reg_ops, s, + TYPE_XLNX_VERSAL_CFRAME_BCAST_REG, KEYHOLE_STREAM_4K); + memory_region_init_io(&s->iomem_fdri, obj, &cframes_bcast_reg_fdri_ops, s, + TYPE_XLNX_VERSAL_CFRAME_BCAST_REG "-fdri", + KEYHOLE_STREAM_4K); + sysbus_init_mmio(sbd, &s->iomem_reg); + sysbus_init_mmio(sbd, &s->iomem_fdri); +} + +static void cframe_bcast_reg_reset_enter(Object *obj, ResetType type) +{ + XlnxVersalCFrameBcastReg *s = XLNX_VERSAL_CFRAME_BCAST_REG(obj); + + memset(s->wfifo, 0, WFIFO_SZ * sizeof(uint32_t)); +} + +static const VMStateDescription vmstate_cframe_bcast_reg = { + .name = TYPE_XLNX_VERSAL_CFRAME_BCAST_REG, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(wfifo, XlnxVersalCFrameBcastReg, 4), + VMSTATE_END_OF_LIST(), + } +}; + +static Property cframe_bcast_regs_props[] = { + DEFINE_PROP_LINK("cframe0", XlnxVersalCFrameBcastReg, cfg.cframe[0], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe1", XlnxVersalCFrameBcastReg, cfg.cframe[1], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe2", XlnxVersalCFrameBcastReg, cfg.cframe[2], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe3", XlnxVersalCFrameBcastReg, cfg.cframe[3], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe4", XlnxVersalCFrameBcastReg, cfg.cframe[4], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe5", XlnxVersalCFrameBcastReg, cfg.cframe[5], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe6", XlnxVersalCFrameBcastReg, cfg.cframe[6], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe7", XlnxVersalCFrameBcastReg, cfg.cframe[7], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe8", XlnxVersalCFrameBcastReg, cfg.cframe[8], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe9", XlnxVersalCFrameBcastReg, cfg.cframe[9], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe10", XlnxVersalCFrameBcastReg, cfg.cframe[10], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe11", XlnxVersalCFrameBcastReg, cfg.cframe[11], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe12", XlnxVersalCFrameBcastReg, cfg.cframe[12], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe13", XlnxVersalCFrameBcastReg, cfg.cframe[13], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_LINK("cframe14", XlnxVersalCFrameBcastReg, cfg.cframe[14], + TYPE_XLNX_CFI_IF, XlnxCfiIf *), + DEFINE_PROP_END_OF_LIST(), +}; + static void cframe_reg_class_init(ObjectClass *klass, void *data) { ResettableClass *rc = RESETTABLE_CLASS(klass); @@ -677,6 +819,16 @@ static void cframe_reg_class_init(ObjectClass *klass, void *data) xcic->cfi_transfer_packet = cframe_reg_cfi_transfer_packet; } +static void cframe_bcast_reg_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + dc->vmsd = &vmstate_cframe_bcast_reg; + device_class_set_props(dc, cframe_bcast_regs_props); + rc->phases.enter = cframe_bcast_reg_reset_enter; +} + static const TypeInfo cframe_reg_info = { .name = TYPE_XLNX_VERSAL_CFRAME_REG, .parent = TYPE_SYS_BUS_DEVICE, @@ -689,9 +841,18 @@ static const TypeInfo cframe_reg_info = { } }; +static const TypeInfo cframe_bcast_reg_info = { + .name = TYPE_XLNX_VERSAL_CFRAME_BCAST_REG, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(XlnxVersalCFrameBcastReg), + .class_init = cframe_bcast_reg_class_init, + .instance_init = cframe_bcast_reg_init, +}; + static void cframe_reg_register_types(void) { type_register_static(&cframe_reg_info); + type_register_static(&cframe_bcast_reg_info); } type_init(cframe_reg_register_types) diff --git a/include/hw/misc/xlnx-versal-cframe-reg.h b/include/hw/misc/xlnx-versal-cframe-reg.h index f286d973bf..a14fbd7fe4 100644 --- a/include/hw/misc/xlnx-versal-cframe-reg.h +++ b/include/hw/misc/xlnx-versal-cframe-reg.h @@ -26,6 +26,10 @@ #define TYPE_XLNX_VERSAL_CFRAME_REG "xlnx,cframe-reg" OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersalCFrameReg, XLNX_VERSAL_CFRAME_REG) +#define TYPE_XLNX_VERSAL_CFRAME_BCAST_REG "xlnx.cframe-bcast-reg" +OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersalCFrameBcastReg, + XLNX_VERSAL_CFRAME_BCAST_REG) + /* * The registers in this module are 128 bits wide but it is ok to write * and read them through 4 sequential 32 bit accesses (address[3:2] = 0, @@ -283,4 +287,17 @@ struct XlnxVersalCFrameReg { bool row_configured; }; +struct XlnxVersalCFrameBcastReg { + SysBusDevice parent_obj; + MemoryRegion iomem_reg; + MemoryRegion iomem_fdri; + + /* 128-bit wfifo. */ + uint32_t wfifo[WFIFO_SZ]; + + struct { + XlnxCfiIf *cframe[15]; + } cfg; +}; + #endif From b286d08aa113e0480a65b8cc6c1979547decc183 Mon Sep 17 00:00:00 2001 From: Francisco Iglesias Date: Thu, 31 Aug 2023 17:57:00 +0100 Subject: [PATCH 17/26] hw/arm/xlnx-versal: Connect the CFU_APB, CFU_FDRO and CFU_SFR Connect the Configuration Frame Unit (CFU_APB, CFU_FDRO and CFU_SFR) to the Versal machine. Signed-off-by: Francisco Iglesias Acked-by: Edgar E. Iglesias Reviewed-by: Peter Maydell Message-id: 20230831165701.2016397-8-francisco.iglesias@amd.com Signed-off-by: Peter Maydell --- hw/arm/xlnx-versal.c | 42 ++++++++++++++++++++++++++++++++++++ include/hw/arm/xlnx-versal.h | 16 ++++++++++++++ 2 files changed, 58 insertions(+) diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index 60bf5fe657..3f4b4b1560 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -570,6 +570,47 @@ static void versal_create_ospi(Versal *s, qemu_irq *pic) qdev_connect_gpio_out(orgate, 0, pic[VERSAL_OSPI_IRQ]); } +static void versal_create_cfu(Versal *s, qemu_irq *pic) +{ + SysBusDevice *sbd; + + /* CFU FDRO */ + object_initialize_child(OBJECT(s), "cfu-fdro", &s->pmc.cfu_fdro, + TYPE_XLNX_VERSAL_CFU_FDRO); + sbd = SYS_BUS_DEVICE(&s->pmc.cfu_fdro); + + sysbus_realize(sbd, &error_fatal); + memory_region_add_subregion(&s->mr_ps, MM_PMC_CFU_FDRO, + sysbus_mmio_get_region(sbd, 0)); + + /* CFU APB */ + object_initialize_child(OBJECT(s), "cfu-apb", &s->pmc.cfu_apb, + TYPE_XLNX_VERSAL_CFU_APB); + sbd = SYS_BUS_DEVICE(&s->pmc.cfu_apb); + + sysbus_realize(sbd, &error_fatal); + memory_region_add_subregion(&s->mr_ps, MM_PMC_CFU_APB, + sysbus_mmio_get_region(sbd, 0)); + memory_region_add_subregion(&s->mr_ps, MM_PMC_CFU_STREAM, + sysbus_mmio_get_region(sbd, 1)); + memory_region_add_subregion(&s->mr_ps, MM_PMC_CFU_STREAM_2, + sysbus_mmio_get_region(sbd, 2)); + sysbus_connect_irq(sbd, 0, pic[VERSAL_CFU_IRQ_0]); + + /* CFU SFR */ + object_initialize_child(OBJECT(s), "cfu-sfr", &s->pmc.cfu_sfr, + TYPE_XLNX_VERSAL_CFU_SFR); + + sbd = SYS_BUS_DEVICE(&s->pmc.cfu_sfr); + + object_property_set_link(OBJECT(&s->pmc.cfu_sfr), + "cfu", OBJECT(&s->pmc.cfu_apb), &error_abort); + + sysbus_realize(sbd, &error_fatal); + memory_region_add_subregion(&s->mr_ps, MM_PMC_CFU_SFR, + sysbus_mmio_get_region(sbd, 0)); +} + static void versal_create_crl(Versal *s, qemu_irq *pic) { SysBusDevice *sbd; @@ -763,6 +804,7 @@ static void versal_realize(DeviceState *dev, Error **errp) versal_create_pmc_iou_slcr(s, pic); versal_create_ospi(s, pic); versal_create_crl(s, pic); + versal_create_cfu(s, pic); versal_map_ddr(s); versal_unimp(s); diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index 39ee31185c..29b9c60301 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -32,6 +32,7 @@ #include "hw/misc/xlnx-versal-crl.h" #include "hw/misc/xlnx-versal-pmc-iou-slcr.h" #include "hw/net/xlnx-versal-canfd.h" +#include "hw/misc/xlnx-versal-cfu.h" #define TYPE_XLNX_VERSAL "xlnx-versal" OBJECT_DECLARE_SIMPLE_TYPE(Versal, XLNX_VERSAL) @@ -117,6 +118,9 @@ struct Versal { XlnxEFuse efuse; XlnxVersalEFuseCtrl efuse_ctrl; XlnxVersalEFuseCache efuse_cache; + XlnxVersalCFUAPB cfu_apb; + XlnxVersalCFUFDRO cfu_fdro; + XlnxVersalCFUSFR cfu_sfr; OrIRQState apb_irq_orgate; } pmc; @@ -147,6 +151,7 @@ struct Versal { #define VERSAL_GEM1_WAKE_IRQ_0 59 #define VERSAL_ADMA_IRQ_0 60 #define VERSAL_XRAM_IRQ_0 79 +#define VERSAL_CFU_IRQ_0 120 #define VERSAL_PMC_APB_IRQ 121 #define VERSAL_OSPI_IRQ 124 #define VERSAL_SD0_IRQ_0 126 @@ -240,6 +245,17 @@ struct Versal { #define MM_PMC_EFUSE_CACHE 0xf1250000 #define MM_PMC_EFUSE_CACHE_SIZE 0x00C00 +#define MM_PMC_CFU_APB 0xf12b0000 +#define MM_PMC_CFU_APB_SIZE 0x10000 +#define MM_PMC_CFU_STREAM 0xf12c0000 +#define MM_PMC_CFU_STREAM_SIZE 0x1000 +#define MM_PMC_CFU_SFR 0xf12c1000 +#define MM_PMC_CFU_SFR_SIZE 0x1000 +#define MM_PMC_CFU_FDRO 0xf12c2000 +#define MM_PMC_CFU_FDRO_SIZE 0x1000 +#define MM_PMC_CFU_STREAM_2 0xf1f80000 +#define MM_PMC_CFU_STREAM_2_SIZE 0x40000 + #define MM_PMC_CRP 0xf1260000U #define MM_PMC_CRP_SIZE 0x10000 #define MM_PMC_RTC 0xf12a0000 From 4a0244b4b297f4790cd7cb3ea0468f4abe34766f Mon Sep 17 00:00:00 2001 From: Francisco Iglesias Date: Thu, 31 Aug 2023 17:57:01 +0100 Subject: [PATCH 18/26] hw/arm/versal: Connect the CFRAME_REG and CFRAME_BCAST_REG Connect the Configuration Frame controller (CFRAME_REG) and the Configuration Frame broadcast controller (CFRAME_BCAST_REG) to the Versal machine. Signed-off-by: Francisco Iglesias Reviewed-by: Peter Maydell Message-id: 20230831165701.2016397-9-francisco.iglesias@amd.com Signed-off-by: Peter Maydell --- hw/arm/xlnx-versal.c | 113 ++++++++++++++++++++++++++++++++++- include/hw/arm/xlnx-versal.h | 69 +++++++++++++++++++++ 2 files changed, 181 insertions(+), 1 deletion(-) diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index 3f4b4b1560..fa556d8764 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -27,7 +27,7 @@ #define XLNX_VERSAL_RCPU_TYPE ARM_CPU_TYPE_NAME("cortex-r5f") #define GEM_REVISION 0x40070106 -#define VERSAL_NUM_PMC_APB_IRQS 3 +#define VERSAL_NUM_PMC_APB_IRQS 18 #define NUM_OSPI_IRQ_LINES 3 static void versal_create_apu_cpus(Versal *s) @@ -341,6 +341,7 @@ static void versal_create_pmc_apb_irq_orgate(Versal *s, qemu_irq *pic) * - RTC * - BBRAM * - PMC SLCR + * - CFRAME regs (input 3 - 17 to the orgate) */ object_initialize_child(OBJECT(s), "pmc-apb-irq-orgate", &s->pmc.apb_irq_orgate, TYPE_OR_IRQ); @@ -573,6 +574,42 @@ static void versal_create_ospi(Versal *s, qemu_irq *pic) static void versal_create_cfu(Versal *s, qemu_irq *pic) { SysBusDevice *sbd; + DeviceState *dev; + int i; + const struct { + uint64_t reg_base; + uint64_t fdri_base; + } cframe_addr[] = { + { MM_PMC_CFRAME0_REG, MM_PMC_CFRAME0_FDRI }, + { MM_PMC_CFRAME1_REG, MM_PMC_CFRAME1_FDRI }, + { MM_PMC_CFRAME2_REG, MM_PMC_CFRAME2_FDRI }, + { MM_PMC_CFRAME3_REG, MM_PMC_CFRAME3_FDRI }, + { MM_PMC_CFRAME4_REG, MM_PMC_CFRAME4_FDRI }, + { MM_PMC_CFRAME5_REG, MM_PMC_CFRAME5_FDRI }, + { MM_PMC_CFRAME6_REG, MM_PMC_CFRAME6_FDRI }, + { MM_PMC_CFRAME7_REG, MM_PMC_CFRAME7_FDRI }, + { MM_PMC_CFRAME8_REG, MM_PMC_CFRAME8_FDRI }, + { MM_PMC_CFRAME9_REG, MM_PMC_CFRAME9_FDRI }, + { MM_PMC_CFRAME10_REG, MM_PMC_CFRAME10_FDRI }, + { MM_PMC_CFRAME11_REG, MM_PMC_CFRAME11_FDRI }, + { MM_PMC_CFRAME12_REG, MM_PMC_CFRAME12_FDRI }, + { MM_PMC_CFRAME13_REG, MM_PMC_CFRAME13_FDRI }, + { MM_PMC_CFRAME14_REG, MM_PMC_CFRAME14_FDRI }, + }; + const struct { + uint32_t blktype0_frames; + uint32_t blktype1_frames; + uint32_t blktype2_frames; + uint32_t blktype3_frames; + uint32_t blktype4_frames; + uint32_t blktype5_frames; + uint32_t blktype6_frames; + } cframe_cfg[] = { + [0] = { 34111, 3528, 12800, 11, 5, 1, 1 }, + [1] = { 38498, 3841, 15361, 13, 7, 3, 1 }, + [2] = { 38498, 3841, 15361, 13, 7, 3, 1 }, + [3] = { 38498, 3841, 15361, 13, 7, 3, 1 }, + }; /* CFU FDRO */ object_initialize_child(OBJECT(s), "cfu-fdro", &s->pmc.cfu_fdro, @@ -583,10 +620,84 @@ static void versal_create_cfu(Versal *s, qemu_irq *pic) memory_region_add_subregion(&s->mr_ps, MM_PMC_CFU_FDRO, sysbus_mmio_get_region(sbd, 0)); + /* CFRAME REG */ + for (i = 0; i < ARRAY_SIZE(s->pmc.cframe); i++) { + g_autofree char *name = g_strdup_printf("cframe%d", i); + + object_initialize_child(OBJECT(s), name, &s->pmc.cframe[i], + TYPE_XLNX_VERSAL_CFRAME_REG); + + sbd = SYS_BUS_DEVICE(&s->pmc.cframe[i]); + dev = DEVICE(&s->pmc.cframe[i]); + + if (i < ARRAY_SIZE(cframe_cfg)) { + object_property_set_int(OBJECT(dev), "blktype0-frames", + cframe_cfg[i].blktype0_frames, + &error_abort); + object_property_set_int(OBJECT(dev), "blktype1-frames", + cframe_cfg[i].blktype1_frames, + &error_abort); + object_property_set_int(OBJECT(dev), "blktype2-frames", + cframe_cfg[i].blktype2_frames, + &error_abort); + object_property_set_int(OBJECT(dev), "blktype3-frames", + cframe_cfg[i].blktype3_frames, + &error_abort); + object_property_set_int(OBJECT(dev), "blktype4-frames", + cframe_cfg[i].blktype4_frames, + &error_abort); + object_property_set_int(OBJECT(dev), "blktype5-frames", + cframe_cfg[i].blktype5_frames, + &error_abort); + object_property_set_int(OBJECT(dev), "blktype6-frames", + cframe_cfg[i].blktype6_frames, + &error_abort); + } + object_property_set_link(OBJECT(dev), "cfu-fdro", + OBJECT(&s->pmc.cfu_fdro), &error_fatal); + + sysbus_realize(SYS_BUS_DEVICE(dev), &error_fatal); + + memory_region_add_subregion(&s->mr_ps, cframe_addr[i].reg_base, + sysbus_mmio_get_region(sbd, 0)); + memory_region_add_subregion(&s->mr_ps, cframe_addr[i].fdri_base, + sysbus_mmio_get_region(sbd, 1)); + sysbus_connect_irq(sbd, 0, + qdev_get_gpio_in(DEVICE(&s->pmc.apb_irq_orgate), + 3 + i)); + } + + /* CFRAME BCAST */ + object_initialize_child(OBJECT(s), "cframe_bcast", &s->pmc.cframe_bcast, + TYPE_XLNX_VERSAL_CFRAME_BCAST_REG); + + sbd = SYS_BUS_DEVICE(&s->pmc.cframe_bcast); + dev = DEVICE(&s->pmc.cframe_bcast); + + for (i = 0; i < ARRAY_SIZE(s->pmc.cframe); i++) { + g_autofree char *propname = g_strdup_printf("cframe%d", i); + object_property_set_link(OBJECT(dev), propname, + OBJECT(&s->pmc.cframe[i]), &error_fatal); + } + + sysbus_realize(sbd, &error_fatal); + + memory_region_add_subregion(&s->mr_ps, MM_PMC_CFRAME_BCAST_REG, + sysbus_mmio_get_region(sbd, 0)); + memory_region_add_subregion(&s->mr_ps, MM_PMC_CFRAME_BCAST_FDRI, + sysbus_mmio_get_region(sbd, 1)); + /* CFU APB */ object_initialize_child(OBJECT(s), "cfu-apb", &s->pmc.cfu_apb, TYPE_XLNX_VERSAL_CFU_APB); sbd = SYS_BUS_DEVICE(&s->pmc.cfu_apb); + dev = DEVICE(&s->pmc.cfu_apb); + + for (i = 0; i < ARRAY_SIZE(s->pmc.cframe); i++) { + g_autofree char *propname = g_strdup_printf("cframe%d", i); + object_property_set_link(OBJECT(dev), propname, + OBJECT(&s->pmc.cframe[i]), &error_fatal); + } sysbus_realize(sbd, &error_fatal); memory_region_add_subregion(&s->mr_ps, MM_PMC_CFU_APB, diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index 29b9c60301..7b419f88c2 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -33,6 +33,7 @@ #include "hw/misc/xlnx-versal-pmc-iou-slcr.h" #include "hw/net/xlnx-versal-canfd.h" #include "hw/misc/xlnx-versal-cfu.h" +#include "hw/misc/xlnx-versal-cframe-reg.h" #define TYPE_XLNX_VERSAL "xlnx-versal" OBJECT_DECLARE_SIMPLE_TYPE(Versal, XLNX_VERSAL) @@ -47,6 +48,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(Versal, XLNX_VERSAL) #define XLNX_VERSAL_NR_IRQS 192 #define XLNX_VERSAL_NR_CANFD 2 #define XLNX_VERSAL_CANFD_REF_CLK (24 * 1000 * 1000) +#define XLNX_VERSAL_NR_CFRAME 15 struct Versal { /*< private >*/ @@ -121,6 +123,8 @@ struct Versal { XlnxVersalCFUAPB cfu_apb; XlnxVersalCFUFDRO cfu_fdro; XlnxVersalCFUSFR cfu_sfr; + XlnxVersalCFrameReg cframe[XLNX_VERSAL_NR_CFRAME]; + XlnxVersalCFrameBcastReg cframe_bcast; OrIRQState apb_irq_orgate; } pmc; @@ -256,6 +260,71 @@ struct Versal { #define MM_PMC_CFU_STREAM_2 0xf1f80000 #define MM_PMC_CFU_STREAM_2_SIZE 0x40000 +#define MM_PMC_CFRAME0_REG 0xf12d0000 +#define MM_PMC_CFRAME0_REG_SIZE 0x1000 +#define MM_PMC_CFRAME0_FDRI 0xf12d1000 +#define MM_PMC_CFRAME0_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME1_REG 0xf12d2000 +#define MM_PMC_CFRAME1_REG_SIZE 0x1000 +#define MM_PMC_CFRAME1_FDRI 0xf12d3000 +#define MM_PMC_CFRAME1_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME2_REG 0xf12d4000 +#define MM_PMC_CFRAME2_REG_SIZE 0x1000 +#define MM_PMC_CFRAME2_FDRI 0xf12d5000 +#define MM_PMC_CFRAME2_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME3_REG 0xf12d6000 +#define MM_PMC_CFRAME3_REG_SIZE 0x1000 +#define MM_PMC_CFRAME3_FDRI 0xf12d7000 +#define MM_PMC_CFRAME3_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME4_REG 0xf12d8000 +#define MM_PMC_CFRAME4_REG_SIZE 0x1000 +#define MM_PMC_CFRAME4_FDRI 0xf12d9000 +#define MM_PMC_CFRAME4_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME5_REG 0xf12da000 +#define MM_PMC_CFRAME5_REG_SIZE 0x1000 +#define MM_PMC_CFRAME5_FDRI 0xf12db000 +#define MM_PMC_CFRAME5_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME6_REG 0xf12dc000 +#define MM_PMC_CFRAME6_REG_SIZE 0x1000 +#define MM_PMC_CFRAME6_FDRI 0xf12dd000 +#define MM_PMC_CFRAME6_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME7_REG 0xf12de000 +#define MM_PMC_CFRAME7_REG_SIZE 0x1000 +#define MM_PMC_CFRAME7_FDRI 0xf12df000 +#define MM_PMC_CFRAME7_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME8_REG 0xf12e0000 +#define MM_PMC_CFRAME8_REG_SIZE 0x1000 +#define MM_PMC_CFRAME8_FDRI 0xf12e1000 +#define MM_PMC_CFRAME8_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME9_REG 0xf12e2000 +#define MM_PMC_CFRAME9_REG_SIZE 0x1000 +#define MM_PMC_CFRAME9_FDRI 0xf12e3000 +#define MM_PMC_CFRAME9_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME10_REG 0xf12e4000 +#define MM_PMC_CFRAME10_REG_SIZE 0x1000 +#define MM_PMC_CFRAME10_FDRI 0xf12e5000 +#define MM_PMC_CFRAME10_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME11_REG 0xf12e6000 +#define MM_PMC_CFRAME11_REG_SIZE 0x1000 +#define MM_PMC_CFRAME11_FDRI 0xf12e7000 +#define MM_PMC_CFRAME11_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME12_REG 0xf12e8000 +#define MM_PMC_CFRAME12_REG_SIZE 0x1000 +#define MM_PMC_CFRAME12_FDRI 0xf12e9000 +#define MM_PMC_CFRAME12_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME13_REG 0xf12ea000 +#define MM_PMC_CFRAME13_REG_SIZE 0x1000 +#define MM_PMC_CFRAME13_FDRI 0xf12eb000 +#define MM_PMC_CFRAME13_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME14_REG 0xf12ec000 +#define MM_PMC_CFRAME14_REG_SIZE 0x1000 +#define MM_PMC_CFRAME14_FDRI 0xf12ed000 +#define MM_PMC_CFRAME14_FDRI_SIZE 0x1000 +#define MM_PMC_CFRAME_BCAST_REG 0xf12ee000 +#define MM_PMC_CFRAME_BCAST_REG_SIZE 0x1000 +#define MM_PMC_CFRAME_BCAST_FDRI 0xf12ef000 +#define MM_PMC_CFRAME_BCAST_FDRI_SIZE 0x1000 + #define MM_PMC_CRP 0xf1260000U #define MM_PMC_CRP_SIZE 0x10000 #define MM_PMC_RTC 0xf12a0000 From 44e0ddee8e18459d99173096e6f22fc64f35f8e4 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Fri, 1 Sep 2023 13:31:03 -0700 Subject: [PATCH 19/26] target/arm: Do not use gen_mte_checkN in trans_STGP STGP writes to tag memory, it does not check it. This happened to work because we wrote tag memory first so that the check always succeeded. Signed-off-by: Richard Henderson Message-id: 20230901203103.136408-1-richard.henderson@linaro.org Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- target/arm/tcg/translate-a64.c | 41 +++++++++++++--------------------- 1 file changed, 15 insertions(+), 26 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index c2bd96f5d4..7d2f8026e6 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -3020,37 +3020,17 @@ static bool trans_STGP(DisasContext *s, arg_ldstpair *a) tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); } - if (!s->ata) { - /* - * TODO: We could rely on the stores below, at least for - * system mode, if we arrange to add MO_ALIGN_16. - */ - gen_helper_stg_stub(cpu_env, dirty_addr); - } else if (tb_cflags(s->base.tb) & CF_PARALLEL) { - gen_helper_stg_parallel(cpu_env, dirty_addr, dirty_addr); - } else { - gen_helper_stg(cpu_env, dirty_addr, dirty_addr); - } - - mop = finalize_memop(s, MO_64); - clean_addr = gen_mte_checkN(s, dirty_addr, true, false, 2 << MO_64, mop); - + clean_addr = clean_data_tbi(s, dirty_addr); tcg_rt = cpu_reg(s, a->rt); tcg_rt2 = cpu_reg(s, a->rt2); /* - * STGP is defined as two 8-byte memory operations and one tag operation. - * We implement it as one single 16-byte memory operation for convenience. - * Rebuild mop as for STP. - * TODO: The atomicity with LSE2 is stronger than required. - * Need a form of MO_ATOM_WITHIN16_PAIR that never requires - * 16-byte atomicity. + * STGP is defined as two 8-byte memory operations, aligned to TAG_GRANULE, + * and one tag operation. We implement it as one single aligned 16-byte + * memory operation for convenience. Note that the alignment ensures + * MO_ATOM_IFALIGN_PAIR produces 8-byte atomicity for the memory store. */ - mop = MO_128; - if (s->align_mem) { - mop |= MO_ALIGN_8; - } - mop = finalize_memop_pair(s, mop); + mop = finalize_memop_atom(s, MO_128 | MO_ALIGN, MO_ATOM_IFALIGN_PAIR); tmp = tcg_temp_new_i128(); if (s->be_data == MO_LE) { @@ -3060,6 +3040,15 @@ static bool trans_STGP(DisasContext *s, arg_ldstpair *a) } tcg_gen_qemu_st_i128(tmp, clean_addr, get_mem_index(s), mop); + /* Perform the tag store, if tag access enabled. */ + if (s->ata) { + if (tb_cflags(s->base.tb) & CF_PARALLEL) { + gen_helper_stg_parallel(cpu_env, dirty_addr, dirty_addr); + } else { + gen_helper_stg(cpu_env, dirty_addr, dirty_addr); + } + } + op_addr_ldstpair_post(s, a, dirty_addr, offset); return true; } From 682814e2a3c883b27f24b9e7cab47313c49acbd4 Mon Sep 17 00:00:00 2001 From: Colton Lewis Date: Thu, 31 Aug 2023 19:00:52 +0000 Subject: [PATCH 20/26] arm64: Restore trapless ptimer access Due to recent KVM changes, QEMU is setting a ptimer offset resulting in unintended trap and emulate access and a consequent performance hit. Filter out the PTIMER_CNT register to restore trapless ptimer access. Quoting Andrew Jones: Simply reading the CNT register and writing back the same value is enough to set an offset, since the timer will have certainly moved past whatever value was read by the time it's written. QEMU frequently saves and restores all registers in the get-reg-list array, unless they've been explicitly filtered out (with Linux commit 680232a94c12, KVM_REG_ARM_PTIMER_CNT is now in the array). So, to restore trapless ptimer accesses, we need a QEMU patch to filter out the register. See https://lore.kernel.org/kvmarm/gsntttsonus5.fsf@coltonlewis-kvm.c.googlers.com/T/#m0770023762a821db2a3f0dd0a7dc6aa54e0d0da9 for additional context. Cc: qemu-stable@nongnu.org Signed-off-by: Andrew Jones Signed-off-by: Colton Lewis Reviewed-by: Richard Henderson Tested-by: Colton Lewis Message-id: 20230831190052.129045-1-coltonlewis@google.com Signed-off-by: Peter Maydell --- target/arm/kvm64.c | 1 + 1 file changed, 1 insertion(+) diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index ac440c33f9..5e95c496bb 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -674,6 +674,7 @@ typedef struct CPRegStateLevel { */ static const CPRegStateLevel non_runtime_cpregs[] = { { KVM_REG_ARM_TIMER_CNT, KVM_PUT_FULL_STATE }, + { KVM_REG_ARM_PTIMER_CNT, KVM_PUT_FULL_STATE }, }; int kvm_arm_cpreg_level(uint64_t regidx) From 97198a7dd1379928a09f58dff8ac7ce11b8fb39e Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Thu, 31 Aug 2023 16:24:37 -0700 Subject: [PATCH 21/26] target/arm: Implement RMR_ELx Provide a stub implementation, as a write is a "request". Signed-off-by: Richard Henderson Message-id: 20230831232441.66020-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- target/arm/helper.c | 64 +++++++++++++++++++++++++++++---------------- 1 file changed, 41 insertions(+), 23 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index f9f7c3c39e..3b22596eab 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -8682,16 +8682,25 @@ void register_cp_regs_for_features(ARMCPU *cpu) }; modify_arm_cp_regs(v8_idregs, v8_user_idregs); #endif - /* RVBAR_EL1 is only implemented if EL1 is the highest EL */ + /* + * RVBAR_EL1 and RMR_EL1 only implemented if EL1 is the highest EL. + * TODO: For RMR, a write with bit 1 set should do something with + * cpu_reset(). In the meantime, "the bit is strictly a request", + * so we are in spec just ignoring writes. + */ if (!arm_feature(env, ARM_FEATURE_EL3) && !arm_feature(env, ARM_FEATURE_EL2)) { - ARMCPRegInfo rvbar = { - .name = "RVBAR_EL1", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 0, .opc2 = 1, - .access = PL1_R, - .fieldoffset = offsetof(CPUARMState, cp15.rvbar), + ARMCPRegInfo el1_reset_regs[] = { + { .name = "RVBAR_EL1", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 0, .opc2 = 1, + .access = PL1_R, + .fieldoffset = offsetof(CPUARMState, cp15.rvbar) }, + { .name = "RMR_EL1", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 0, .opc2 = 2, + .access = PL1_RW, .type = ARM_CP_CONST, + .resetvalue = arm_feature(env, ARM_FEATURE_AARCH64) } }; - define_one_arm_cp_reg(cpu, &rvbar); + define_arm_cp_regs(cpu, el1_reset_regs); } define_arm_cp_regs(cpu, v8_idregs); define_arm_cp_regs(cpu, v8_cp_reginfo); @@ -8775,22 +8784,25 @@ void register_cp_regs_for_features(ARMCPU *cpu) if (cpu_isar_feature(aa64_sel2, cpu)) { define_arm_cp_regs(cpu, el2_sec_cp_reginfo); } - /* RVBAR_EL2 is only implemented if EL2 is the highest EL */ + /* + * RVBAR_EL2 and RMR_EL2 only implemented if EL2 is the highest EL. + * See commentary near RMR_EL1. + */ if (!arm_feature(env, ARM_FEATURE_EL3)) { - ARMCPRegInfo rvbar[] = { - { - .name = "RVBAR_EL2", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 0, .opc2 = 1, - .access = PL2_R, - .fieldoffset = offsetof(CPUARMState, cp15.rvbar), - }, - { .name = "RVBAR", .type = ARM_CP_ALIAS, - .cp = 15, .opc1 = 0, .crn = 12, .crm = 0, .opc2 = 1, - .access = PL2_R, - .fieldoffset = offsetof(CPUARMState, cp15.rvbar), - }, + static const ARMCPRegInfo el2_reset_regs[] = { + { .name = "RVBAR_EL2", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 0, .opc2 = 1, + .access = PL2_R, + .fieldoffset = offsetof(CPUARMState, cp15.rvbar) }, + { .name = "RVBAR", .type = ARM_CP_ALIAS, + .cp = 15, .opc1 = 0, .crn = 12, .crm = 0, .opc2 = 1, + .access = PL2_R, + .fieldoffset = offsetof(CPUARMState, cp15.rvbar) }, + { .name = "RMR_EL2", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 4, .crn = 12, .crm = 0, .opc2 = 2, + .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 1 }, }; - define_arm_cp_regs(cpu, rvbar); + define_arm_cp_regs(cpu, el2_reset_regs); } } @@ -8801,8 +8813,14 @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "RVBAR_EL3", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 6, .crn = 12, .crm = 0, .opc2 = 1, .access = PL3_R, - .fieldoffset = offsetof(CPUARMState, cp15.rvbar), - }, + .fieldoffset = offsetof(CPUARMState, cp15.rvbar), }, + { .name = "RMR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 12, .crm = 0, .opc2 = 2, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 1 }, + { .name = "RMR", .state = ARM_CP_STATE_AA32, + .cp = 15, .opc1 = 0, .crn = 12, .crm = 0, .opc2 = 2, + .access = PL3_RW, .type = ARM_CP_CONST, + .resetvalue = arm_feature(env, ARM_FEATURE_AARCH64) }, { .name = "SCTLR_EL3", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 6, .crn = 1, .crm = 0, .opc2 = 0, .access = PL3_RW, From e3d45c0a895764203f489184d361fe4c74b2cd57 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Thu, 31 Aug 2023 16:24:38 -0700 Subject: [PATCH 22/26] target/arm: Implement cortex-a710 The cortex-a710 is a first generation ARMv9.0-A processor. Signed-off-by: Richard Henderson Message-id: 20230831232441.66020-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- docs/system/arm/virt.rst | 1 + hw/arm/virt.c | 1 + target/arm/tcg/cpu64.c | 212 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 214 insertions(+) diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst index 51cdac6841..e1697ac8f4 100644 --- a/docs/system/arm/virt.rst +++ b/docs/system/arm/virt.rst @@ -58,6 +58,7 @@ Supported guest CPU types: - ``cortex-a57`` (64-bit) - ``cortex-a72`` (64-bit) - ``cortex-a76`` (64-bit) +- ``cortex-a710`` (64-bit) - ``a64fx`` (64-bit) - ``host`` (with KVM only) - ``neoverse-n1`` (64-bit) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index a13c658bbf..8ad78b23c2 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -211,6 +211,7 @@ static const char *valid_cpus[] = { ARM_CPU_TYPE_NAME("cortex-a55"), ARM_CPU_TYPE_NAME("cortex-a72"), ARM_CPU_TYPE_NAME("cortex-a76"), + ARM_CPU_TYPE_NAME("cortex-a710"), ARM_CPU_TYPE_NAME("a64fx"), ARM_CPU_TYPE_NAME("neoverse-n1"), ARM_CPU_TYPE_NAME("neoverse-v1"), diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index ef222da57d..6e5192ebfc 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -745,6 +745,217 @@ static void aarch64_neoverse_v1_initfn(Object *obj) aarch64_add_sve_properties(obj); } +static const ARMCPRegInfo cortex_a710_cp_reginfo[] = { + { .name = "CPUACTLR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 0, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, + { .name = "CPUACTLR2_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 1, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, + { .name = "CPUACTLR3_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 2, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, + { .name = "CPUACTLR4_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 3, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, + { .name = "CPUECTLR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 4, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, + { .name = "CPUECTLR2_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 5, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, + { .name = "CPUPPMCR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 2, .opc2 = 4, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUPWRCTLR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 2, .opc2 = 7, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, + { .name = "ATCR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 7, .opc2 = 0, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUACTLR5_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 8, .opc2 = 0, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, + { .name = "CPUACTLR6_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 8, .opc2 = 1, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, + { .name = "CPUACTLR7_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 8, .opc2 = 2, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0, + .accessfn = access_actlr_w }, + { .name = "ATCR_EL2", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 4, .crn = 15, .crm = 7, .opc2 = 0, + .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "AVTCR_EL2", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 4, .crn = 15, .crm = 7, .opc2 = 1, + .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUPPMCR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 2, .opc2 = 0, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUPPMCR2_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 2, .opc2 = 1, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUPPMCR4_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 2, .opc2 = 4, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUPPMCR5_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 2, .opc2 = 5, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUPPMCR6_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 2, .opc2 = 6, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUACTLR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 4, .opc2 = 0, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "ATCR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 7, .opc2 = 0, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUPSELR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 0, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUPCR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 1, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUPOR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 2, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUPMR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 3, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUPOR2_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 4, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUPMR2_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 5, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUPFR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 6, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + + /* + * Stub RAMINDEX, as we don't actually implement caches, BTB, + * or anything else with cpu internal memory. + * "Read" zeros into the IDATA* and DDATA* output registers. + */ + { .name = "RAMINDEX_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 15, .crm = 0, .opc2 = 0, + .access = PL3_W, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "IDATA0_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 0, .opc2 = 0, + .access = PL3_R, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "IDATA1_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 0, .opc2 = 1, + .access = PL3_R, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "IDATA2_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 0, .opc2 = 2, + .access = PL3_R, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "DDATA0_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 1, .opc2 = 0, + .access = PL3_R, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "DDATA1_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 1, .opc2 = 1, + .access = PL3_R, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "DDATA2_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 1, .opc2 = 2, + .access = PL3_R, .type = ARM_CP_CONST, .resetvalue = 0 }, +}; + +static void aarch64_a710_initfn(Object *obj) +{ + ARMCPU *cpu = ARM_CPU(obj); + + cpu->dtb_compatible = "arm,cortex-a710"; + set_feature(&cpu->env, ARM_FEATURE_V8); + set_feature(&cpu->env, ARM_FEATURE_NEON); + set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_AARCH64); + set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); + set_feature(&cpu->env, ARM_FEATURE_EL2); + set_feature(&cpu->env, ARM_FEATURE_EL3); + set_feature(&cpu->env, ARM_FEATURE_PMU); + + /* Ordered by Section B.4: AArch64 registers */ + cpu->midr = 0x412FD471; /* r2p1 */ + cpu->revidr = 0; + cpu->isar.id_pfr0 = 0x21110131; + cpu->isar.id_pfr1 = 0x00010000; /* GIC filled in later */ + cpu->isar.id_dfr0 = 0x16011099; + cpu->id_afr0 = 0; + cpu->isar.id_mmfr0 = 0x10201105; + cpu->isar.id_mmfr1 = 0x40000000; + cpu->isar.id_mmfr2 = 0x01260000; + cpu->isar.id_mmfr3 = 0x02122211; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232042; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x00010142; + cpu->isar.id_isar5 = 0x11011121; /* with Crypto */ + cpu->isar.id_mmfr4 = 0x21021110; + cpu->isar.id_isar6 = 0x01111111; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x13211111; + cpu->isar.mvfr2 = 0x00000043; + cpu->isar.id_pfr2 = 0x00000011; + cpu->isar.id_aa64pfr0 = 0x1201111120111112ull; /* GIC filled in later */ + cpu->isar.id_aa64pfr1 = 0x0000000000000221ull; + cpu->isar.id_aa64zfr0 = 0x0000110100110021ull; /* with Crypto */ + cpu->isar.id_aa64dfr0 = 0x000011f010305611ull; + cpu->isar.id_aa64dfr1 = 0; + cpu->id_aa64afr0 = 0; + cpu->id_aa64afr1 = 0; + cpu->isar.id_aa64isar0 = 0x0221111110212120ull; /* with Crypto */ + cpu->isar.id_aa64isar1 = 0x0010111101211032ull; + cpu->isar.id_aa64mmfr0 = 0x0000022200101122ull; + cpu->isar.id_aa64mmfr1 = 0x0000000010212122ull; + cpu->isar.id_aa64mmfr2 = 0x1221011110101011ull; + cpu->clidr = 0x0000001482000023ull; + cpu->gm_blocksize = 4; + cpu->ctr = 0x000000049444c004ull; + cpu->dcz_blocksize = 4; + /* TODO FEAT_MPAM: mpamidr_el1 = 0x0000_0001_0006_003f */ + + /* Section B.5.2: PMCR_EL0 */ + cpu->isar.reset_pmcr_el0 = 0xa000; /* with 20 counters */ + + /* Section B.6.7: ICH_VTR_EL2 */ + cpu->gic_num_lrs = 4; + cpu->gic_vpribits = 5; + cpu->gic_vprebits = 5; + cpu->gic_pribits = 5; + + /* Section 14: Scalable Vector Extensions support */ + cpu->sve_vq.supported = 1 << 0; /* 128bit */ + + /* + * The cortex-a710 TRM does not list CCSIDR values. The layout of + * the caches are in text in Table 7-1, Table 8-1, and Table 9-1. + * + * L1: 4-way set associative 64-byte line size, total either 32K or 64K. + * L2: 8-way set associative 64 byte line size, total either 256K or 512K. + */ + cpu->ccsidr[0] = make_ccsidr64(4, 64, 64 * KiB); /* L1 dcache */ + cpu->ccsidr[1] = cpu->ccsidr[0]; /* L1 icache */ + cpu->ccsidr[2] = make_ccsidr64(8, 64, 512 * KiB); /* L2 cache */ + + /* FIXME: Not documented -- copied from neoverse-v1 */ + cpu->reset_sctlr = 0x30c50838; + + define_arm_cp_regs(cpu, cortex_a710_cp_reginfo); + + aarch64_add_pauth_properties(obj); + aarch64_add_sve_properties(obj); +} + /* * -cpu max: a CPU with as many features enabled as our emulation supports. * The version of '-cpu max' for qemu-system-arm is defined in cpu32.c; @@ -936,6 +1147,7 @@ static const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a55", .initfn = aarch64_a55_initfn }, { .name = "cortex-a72", .initfn = aarch64_a72_initfn }, { .name = "cortex-a76", .initfn = aarch64_a76_initfn }, + { .name = "cortex-a710", .initfn = aarch64_a710_initfn }, { .name = "a64fx", .initfn = aarch64_a64fx_initfn }, { .name = "neoverse-n1", .initfn = aarch64_neoverse_n1_initfn }, { .name = "neoverse-v1", .initfn = aarch64_neoverse_v1_initfn }, From 27920d3d1de2f2b0d5048030820eec4fa64b8b36 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Thu, 31 Aug 2023 16:24:39 -0700 Subject: [PATCH 23/26] target/arm: Implement HCR_EL2.TIDCP Perform the check for EL2 enabled in the security space and the TIDCP bit in an out-of-line helper. Signed-off-by: Richard Henderson Message-id: 20230831232441.66020-4-richard.henderson@linaro.org Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- target/arm/helper.h | 1 + target/arm/tcg/op_helper.c | 13 +++++++++++++ target/arm/tcg/translate-a64.c | 16 ++++++++++++++-- target/arm/tcg/translate.c | 27 +++++++++++++++++++++++++++ 4 files changed, 55 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 95e32a697a..cf5c55a12b 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -81,6 +81,7 @@ DEF_HELPER_FLAGS_2(check_bxj_trap, TCG_CALL_NO_WG, void, env, i32) DEF_HELPER_4(access_check_cp_reg, cptr, env, i32, i32, i32) DEF_HELPER_FLAGS_2(lookup_cp_reg, TCG_CALL_NO_RWG_SE, cptr, env, i32) +DEF_HELPER_FLAGS_2(tidcp_el1, TCG_CALL_NO_WG, void, env, i32) DEF_HELPER_3(set_cp_reg, void, env, cptr, i32) DEF_HELPER_2(get_cp_reg, i32, env, cptr) DEF_HELPER_3(set_cp_reg64, void, env, cptr, i64) diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c index 3baf8004f6..9014c3ca46 100644 --- a/target/arm/tcg/op_helper.c +++ b/target/arm/tcg/op_helper.c @@ -764,6 +764,19 @@ const void *HELPER(lookup_cp_reg)(CPUARMState *env, uint32_t key) return ri; } +/* + * Test for HCR_EL2.TIDCP at EL1. + * Since implementation defined registers are rare, and within QEMU + * most of them are no-op, do not waste HFLAGS space for this and + * always use a helper. + */ +void HELPER(tidcp_el1)(CPUARMState *env, uint32_t syndrome) +{ + if (arm_hcr_el2_eff(env) & HCR_TIDCP) { + raise_exception_ra(env, EXCP_UDEF, syndrome, 2, GETPC()); + } +} + void HELPER(set_cp_reg)(CPUARMState *env, const void *rip, uint32_t value) { const ARMCPRegInfo *ri = rip; diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 7d2f8026e6..cb5c42638c 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -2154,6 +2154,20 @@ static void handle_sys(DisasContext *s, bool isread, bool need_exit_tb = false; TCGv_ptr tcg_ri = NULL; TCGv_i64 tcg_rt; + uint32_t syndrome; + + if (crn == 11 || crn == 15) { + /* + * Check for TIDCP trap, which must take precedence over + * the UNDEF for "no such register" etc. + */ + syndrome = syn_aa64_sysregtrap(op0, op1, op2, crn, crm, rt, isread); + switch (s->current_el) { + case 1: + gen_helper_tidcp_el1(cpu_env, tcg_constant_i32(syndrome)); + break; + } + } if (!ri) { /* Unknown register; this might be a guest error or a QEMU @@ -2176,8 +2190,6 @@ static void handle_sys(DisasContext *s, bool isread, /* Emit code to perform further access permissions checks at * runtime; this may result in an exception. */ - uint32_t syndrome; - syndrome = syn_aa64_sysregtrap(op0, op1, op2, crn, crm, rt, isread); gen_a64_update_pc(s, 0); tcg_ri = tcg_temp_new_ptr(); diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index 38ad8dd4bd..47d3bc5fd5 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -4538,6 +4538,20 @@ void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } +static bool aa32_cpreg_encoding_in_impdef_space(uint8_t crn, uint8_t crm) +{ + static const uint16_t mask[3] = { + 0b0000000111100111, /* crn == 9, crm == {c0-c2, c5-c8} */ + 0b0000000100010011, /* crn == 10, crm == {c0, c1, c4, c8} */ + 0b1000000111111111, /* crn == 11, crm == {c0-c8, c15} */ + }; + + if (crn >= 9 && crn <= 11) { + return (mask[crn - 9] >> crm) & 1; + } + return false; +} + static void do_coproc_insn(DisasContext *s, int cpnum, int is64, int opc1, int crn, int crm, int opc2, bool isread, int rt, int rt2) @@ -4619,6 +4633,19 @@ static void do_coproc_insn(DisasContext *s, int cpnum, int is64, } } + if (cpnum == 15 && aa32_cpreg_encoding_in_impdef_space(crn, crm)) { + /* + * Check for TIDCP trap, which must take precedence over the UNDEF + * for "no such register" etc. It shares precedence with HSTR, + * but raises the same exception, so order doesn't matter. + */ + switch (s->current_el) { + case 1: + gen_helper_tidcp_el1(cpu_env, tcg_constant_i32(syndrome)); + break; + } + } + if (!ri) { /* * Unknown register; this might be a guest error or a QEMU From 9cd0c0dec97be99c0b42b589e63fad6f8c6488b8 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Thu, 31 Aug 2023 16:24:40 -0700 Subject: [PATCH 24/26] target/arm: Implement FEAT_TIDCP1 Signed-off-by: Richard Henderson Message-id: 20230831232441.66020-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- docs/system/arm/emulation.rst | 1 + target/arm/cpu.h | 5 +++++ target/arm/helper.h | 1 + target/arm/tcg/cpu64.c | 1 + target/arm/tcg/op_helper.c | 20 ++++++++++++++++++++ target/arm/tcg/translate-a64.c | 5 +++++ target/arm/tcg/translate.c | 6 ++++++ 7 files changed, 39 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index 305b36b19e..3df936fc35 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -92,6 +92,7 @@ the following architecture extensions: - FEAT_SME_I16I64 (16-bit to 64-bit integer widening outer product instructions) - FEAT_SPECRES (Speculation restriction instructions) - FEAT_SSBS (Speculative Store Bypass Safe) +- FEAT_TIDCP1 (EL0 use of IMPLEMENTATION DEFINED functionality) - FEAT_TLBIOS (TLB invalidate instructions in Outer Shareable domain) - FEAT_TLBIRANGE (TLB invalidate range instructions) - FEAT_TTCNP (Translation table Common not private translations) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 6f75ccfcef..d1aa3da38f 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -3980,6 +3980,11 @@ static inline bool isar_feature_aa64_hcx(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HCX) != 0; } +static inline bool isar_feature_aa64_tidcp1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR1, TIDCP1) != 0; +} + static inline bool isar_feature_aa64_uao(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, UAO) != 0; diff --git a/target/arm/helper.h b/target/arm/helper.h index cf5c55a12b..2b02733305 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -81,6 +81,7 @@ DEF_HELPER_FLAGS_2(check_bxj_trap, TCG_CALL_NO_WG, void, env, i32) DEF_HELPER_4(access_check_cp_reg, cptr, env, i32, i32, i32) DEF_HELPER_FLAGS_2(lookup_cp_reg, TCG_CALL_NO_RWG_SE, cptr, env, i32) +DEF_HELPER_FLAGS_2(tidcp_el0, TCG_CALL_NO_WG, void, env, i32) DEF_HELPER_FLAGS_2(tidcp_el1, TCG_CALL_NO_WG, void, env, i32) DEF_HELPER_3(set_cp_reg, void, env, cptr, i32) DEF_HELPER_2(get_cp_reg, i32, env, cptr) diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index 6e5192ebfc..7264ab5ead 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -1071,6 +1071,7 @@ void aarch64_max_tcg_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64MMFR1, XNX, 1); /* FEAT_XNX */ t = FIELD_DP64(t, ID_AA64MMFR1, ETS, 1); /* FEAT_ETS */ t = FIELD_DP64(t, ID_AA64MMFR1, HCX, 1); /* FEAT_HCX */ + t = FIELD_DP64(t, ID_AA64MMFR1, TIDCP1, 1); /* FEAT_TIDCP1 */ cpu->isar.id_aa64mmfr1 = t; t = cpu->isar.id_aa64mmfr2; diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c index 9014c3ca46..403f8b09d3 100644 --- a/target/arm/tcg/op_helper.c +++ b/target/arm/tcg/op_helper.c @@ -777,6 +777,26 @@ void HELPER(tidcp_el1)(CPUARMState *env, uint32_t syndrome) } } +/* + * Similarly, for FEAT_TIDCP1 at EL0. + * We have already checked for the presence of the feature. + */ +void HELPER(tidcp_el0)(CPUARMState *env, uint32_t syndrome) +{ + /* See arm_sctlr(), but we also need the sctlr el. */ + ARMMMUIdx mmu_idx = arm_mmu_idx_el(env, 0); + int target_el = mmu_idx == ARMMMUIdx_E20_0 ? 2 : 1; + + /* + * The bit is not valid unless the target el is aa64, but since the + * bit test is simpler perform that first and check validity after. + */ + if ((env->cp15.sctlr_el[target_el] & SCTLR_TIDCP) + && arm_el_is_aa64(env, target_el)) { + raise_exception_ra(env, EXCP_UDEF, syndrome, target_el, GETPC()); + } +} + void HELPER(set_cp_reg)(CPUARMState *env, const void *rip, uint32_t value) { const ARMCPRegInfo *ri = rip; diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index cb5c42638c..1b6fbb61e2 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -2163,6 +2163,11 @@ static void handle_sys(DisasContext *s, bool isread, */ syndrome = syn_aa64_sysregtrap(op0, op1, op2, crn, crm, rt, isread); switch (s->current_el) { + case 0: + if (dc_isar_feature(aa64_tidcp1, s)) { + gen_helper_tidcp_el0(cpu_env, tcg_constant_i32(syndrome)); + } + break; case 1: gen_helper_tidcp_el1(cpu_env, tcg_constant_i32(syndrome)); break; diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index 47d3bc5fd5..976b704200 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -4640,6 +4640,12 @@ static void do_coproc_insn(DisasContext *s, int cpnum, int is64, * but raises the same exception, so order doesn't matter. */ switch (s->current_el) { + case 0: + if (arm_dc_feature(s, ARM_FEATURE_AARCH64) + && dc_isar_feature(aa64_tidcp1, s)) { + gen_helper_tidcp_el0(cpu_env, tcg_constant_i32(syndrome)); + } + break; case 1: gen_helper_tidcp_el1(cpu_env, tcg_constant_i32(syndrome)); break; From d03396a8bb19b77d4d0fa2ad2143999510f0d44e Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Thu, 31 Aug 2023 16:24:41 -0700 Subject: [PATCH 25/26] target/arm: Enable SCTLR_EL1.TIDCP for user-only The linux kernel detects and enables this bit. Once trapped, EC_SYSTEMREGISTERTRAP is treated like EC_UNCATEGORIZED, so no changes required within linux-user/aarch64/cpu_loop.c. Signed-off-by: Richard Henderson Message-id: 20230831232441.66020-6-richard.henderson@linaro.org Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- target/arm/cpu.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index 0bb0585441..b9e09a702d 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -243,6 +243,10 @@ static void arm_cpu_reset_hold(Object *obj) SCTLR_EnDA | SCTLR_EnDB); /* Trap on btype=3 for PACIxSP. */ env->cp15.sctlr_el[1] |= SCTLR_BT0; + /* Trap on implementation defined registers. */ + if (cpu_isar_feature(aa64_tidcp1, cpu)) { + env->cp15.sctlr_el[1] |= SCTLR_TIDCP; + } /* and to the FP/Neon instructions */ env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1, CPACR_EL1, FPEN, 3); From c8f2eb5d414b788420b938f2ffdde891aa6c3ae8 Mon Sep 17 00:00:00 2001 From: Shameer Kolothum Date: Tue, 5 Sep 2023 10:12:46 +0100 Subject: [PATCH 26/26] arm/kvm: Enable support for KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE Now that we have Eager Page Split support added for ARM in the kernel, enable it in Qemu. This adds, -eager-split-size to -accel sub-options to set the eager page split chunk size. -enable KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE. The chunk size specifies how many pages to break at a time, using a single allocation. Bigger the chunk size, more pages need to be allocated ahead of time. Reviewed-by: Gavin Shan Signed-off-by: Shameer Kolothum Message-id: 20230905091246.1931-1-shameerali.kolothum.thodi@huawei.com Signed-off-by: Peter Maydell --- accel/kvm/kvm-all.c | 1 + include/sysemu/kvm_int.h | 1 + qemu-options.hx | 15 ++++++++++ target/arm/kvm.c | 61 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 78 insertions(+) diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index 2ba7521695..ff1578bb32 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -3763,6 +3763,7 @@ static void kvm_accel_instance_init(Object *obj) /* KVM dirty ring is by default off */ s->kvm_dirty_ring_size = 0; s->kvm_dirty_ring_with_bitmap = false; + s->kvm_eager_split_size = 0; s->notify_vmexit = NOTIFY_VMEXIT_OPTION_RUN; s->notify_window = 0; s->xen_version = 0; diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h index 511b42bde5..a5b9122cb8 100644 --- a/include/sysemu/kvm_int.h +++ b/include/sysemu/kvm_int.h @@ -116,6 +116,7 @@ struct KVMState uint64_t kvm_dirty_ring_bytes; /* Size of the per-vcpu dirty ring */ uint32_t kvm_dirty_ring_size; /* Number of dirty GFNs per ring */ bool kvm_dirty_ring_with_bitmap; + uint64_t kvm_eager_split_size; /* Eager Page Splitting chunk size */ struct KVMDirtyRingReaper reaper; NotifyVmexitOption notify_vmexit; uint32_t notify_window; diff --git a/qemu-options.hx b/qemu-options.hx index 463f520c57..93d106aa9c 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -186,6 +186,7 @@ DEF("accel", HAS_ARG, QEMU_OPTION_accel, " split-wx=on|off (enable TCG split w^x mapping)\n" " tb-size=n (TCG translation block cache size)\n" " dirty-ring-size=n (KVM dirty ring GFN count, default 0)\n" + " eager-split-size=n (KVM Eager Page Split chunk size, default 0, disabled. ARM only)\n" " notify-vmexit=run|internal-error|disable,notify-window=n (enable notify VM exit and set notify window, x86 only)\n" " thread=single|multi (enable multi-threaded TCG)\n", QEMU_ARCH_ALL) SRST @@ -244,6 +245,20 @@ SRST is disabled (dirty-ring-size=0). When enabled, KVM will instead record dirty pages in a bitmap. + ``eager-split-size=n`` + KVM implements dirty page logging at the PAGE_SIZE granularity and + enabling dirty-logging on a huge-page requires breaking it into + PAGE_SIZE pages in the first place. KVM on ARM does this splitting + lazily by default. There are performance benefits in doing huge-page + split eagerly, especially in situations where TLBI costs associated + with break-before-make sequences are considerable and also if guest + workloads are read intensive. The size here specifies how many pages + to break at a time and needs to be a valid block size which is + 1GB/2MB/4KB, 32MB/16KB and 512MB/64KB for 4KB/16KB/64KB PAGE_SIZE + respectively. Be wary of specifying a higher size as it will have an + impact on the memory. By default, this feature is disabled + (eager-split-size=0). + ``notify-vmexit=run|internal-error|disable,notify-window=n`` Enables or disables notify VM exit support on x86 host and specify the corresponding notify window to trigger the VM exit if enabled. diff --git a/target/arm/kvm.c b/target/arm/kvm.c index 23aeb09949..b66b936a95 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -30,6 +30,7 @@ #include "exec/address-spaces.h" #include "hw/boards.h" #include "hw/irq.h" +#include "qapi/visitor.h" #include "qemu/log.h" const KVMCapabilityInfo kvm_arch_required_capabilities[] = { @@ -287,6 +288,26 @@ int kvm_arch_init(MachineState *ms, KVMState *s) } } + if (s->kvm_eager_split_size) { + uint32_t sizes; + + sizes = kvm_vm_check_extension(s, KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES); + if (!sizes) { + s->kvm_eager_split_size = 0; + warn_report("Eager Page Split support not available"); + } else if (!(s->kvm_eager_split_size & sizes)) { + error_report("Eager Page Split requested chunk size not valid"); + ret = -EINVAL; + } else { + ret = kvm_vm_enable_cap(s, KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE, 0, + s->kvm_eager_split_size); + if (ret < 0) { + error_report("Enabling of Eager Page Split failed: %s", + strerror(-ret)); + } + } + } + kvm_arm_init_debug(s); return ret; @@ -1069,6 +1090,46 @@ bool kvm_arch_cpu_check_are_resettable(void) return true; } +static void kvm_arch_get_eager_split_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + KVMState *s = KVM_STATE(obj); + uint64_t value = s->kvm_eager_split_size; + + visit_type_size(v, name, &value, errp); +} + +static void kvm_arch_set_eager_split_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + KVMState *s = KVM_STATE(obj); + uint64_t value; + + if (s->fd != -1) { + error_setg(errp, "Unable to set early-split-size after KVM has been initialized"); + return; + } + + if (!visit_type_size(v, name, &value, errp)) { + return; + } + + if (value && !is_power_of_2(value)) { + error_setg(errp, "early-split-size must be a power of two"); + return; + } + + s->kvm_eager_split_size = value; +} + void kvm_arch_accel_class_init(ObjectClass *oc) { + object_class_property_add(oc, "eager-split-size", "size", + kvm_arch_get_eager_split_size, + kvm_arch_set_eager_split_size, NULL, NULL); + + object_class_property_set_description(oc, "eager-split-size", + "Eager Page Split chunk size for hugepages. (default: 0, disabled)"); }