diff options
Diffstat (limited to 'target')
| -rw-r--r-- | target/arm/arm-qmp-cmds.c | 2 | ||||
| -rw-r--r-- | target/arm/cpu.c | 2 | ||||
| -rw-r--r-- | target/arm/cpu.h | 4 | ||||
| -rw-r--r-- | target/arm/cpu64.c | 38 | ||||
| -rw-r--r-- | target/arm/helper.c | 285 | ||||
| -rw-r--r-- | target/arm/kvm.c | 2 | ||||
| -rw-r--r-- | target/arm/tcg/arith_helper.c | 296 | ||||
| -rw-r--r-- | target/arm/tcg/meson.build | 1 | ||||
| -rw-r--r-- | target/arm/tcg/op_addsub.c.inc (renamed from target/arm/op_addsub.h) | 0 | ||||
| -rw-r--r-- | target/hppa/cpu.c | 22 | ||||
| -rw-r--r-- | target/hppa/cpu.h | 11 | ||||
| -rw-r--r-- | target/loongarch/cpu_helper.c | 94 | ||||
| -rw-r--r-- | target/loongarch/helper.h | 1 | ||||
| -rw-r--r-- | target/loongarch/internals.h | 4 | ||||
| -rw-r--r-- | target/loongarch/tcg/csr_helper.c | 21 | ||||
| -rw-r--r-- | target/loongarch/tcg/insn_trans/trans_privileged.c.inc | 2 | ||||
| -rw-r--r-- | target/loongarch/tcg/tlb_helper.c | 21 | ||||
| -rw-r--r-- | target/mips/cpu.c | 2 | ||||
| -rw-r--r-- | target/s390x/kvm/kvm.c | 16 | ||||
| -rw-r--r-- | target/xtensa/cpu.c | 2 |
20 files changed, 489 insertions, 337 deletions
diff --git a/target/arm/arm-qmp-cmds.c b/target/arm/arm-qmp-cmds.c index 3cc8cc738b..33cea080d1 100644 --- a/target/arm/arm-qmp-cmds.c +++ b/target/arm/arm-qmp-cmds.c @@ -94,7 +94,7 @@ 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-qarma3", + "pauth", "pauth-impdef", "pauth-qarma3", "pauth-qarma5", NULL }; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index dcedadc89e..dc0231233a 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -2653,6 +2653,8 @@ static const Property arm_cpu_properties[] = { DEFINE_PROP_INT32("core-count", ARMCPU, core_count, -1), /* True to default to the backward-compat old CNTFRQ rather than 1Ghz */ DEFINE_PROP_BOOL("backcompat-cntfrq", ARMCPU, backcompat_cntfrq, false), + DEFINE_PROP_BOOL("backcompat-pauth-default-use-qarma5", ARMCPU, + backcompat_pauth_default_use_qarma5, false), }; static const gchar *arm_gdb_arch_name(CPUState *cs) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 12b8466542..9a6e8e589c 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -972,6 +972,9 @@ struct ArchCPU { /* QOM property to indicate we should use the back-compat CNTFRQ default */ bool backcompat_cntfrq; + /* QOM property to indicate we should use the back-compat QARMA5 default */ + bool backcompat_pauth_default_use_qarma5; + /* Specify the number of cores in this CPU cluster. Used for the L2CTLR * register. */ @@ -1062,6 +1065,7 @@ struct ArchCPU { bool prop_pauth; bool prop_pauth_impdef; bool prop_pauth_qarma3; + bool prop_pauth_qarma5; 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 dca83e4518..8188ede5cc 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -520,25 +520,40 @@ void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp) } if (cpu->prop_pauth) { - if (cpu->prop_pauth_impdef && cpu->prop_pauth_qarma3) { + if ((cpu->prop_pauth_impdef && cpu->prop_pauth_qarma3) || + (cpu->prop_pauth_impdef && cpu->prop_pauth_qarma5) || + (cpu->prop_pauth_qarma3 && cpu->prop_pauth_qarma5)) { error_setg(errp, - "cannot enable both pauth-impdef and pauth-qarma3"); + "cannot enable pauth-impdef, pauth-qarma3 and " + "pauth-qarma5 at the same time"); return; } - if (cpu->prop_pauth_impdef) { - isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, API, features); - isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPI, 1); + bool use_default = !cpu->prop_pauth_qarma5 && + !cpu->prop_pauth_qarma3 && + !cpu->prop_pauth_impdef; + + if (cpu->prop_pauth_qarma5 || + (use_default && + cpu->backcompat_pauth_default_use_qarma5)) { + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, APA, features); + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPA, 1); } else if (cpu->prop_pauth_qarma3) { isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, APA3, features); isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, GPA3, 1); + } else if (cpu->prop_pauth_impdef || + (use_default && + !cpu->backcompat_pauth_default_use_qarma5)) { + 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); + g_assert_not_reached(); } - } else if (cpu->prop_pauth_impdef || cpu->prop_pauth_qarma3) { - error_setg(errp, "cannot enable pauth-impdef or " - "pauth-qarma3 without pauth"); + } else if (cpu->prop_pauth_impdef || + cpu->prop_pauth_qarma3 || + cpu->prop_pauth_qarma5) { + error_setg(errp, "cannot enable pauth-impdef, pauth-qarma3 or " + "pauth-qarma5 without pauth"); error_append_hint(errp, "Add pauth=on to the CPU property list.\n"); } } @@ -553,6 +568,8 @@ static const Property arm_cpu_pauth_impdef_property = DEFINE_PROP_BOOL("pauth-impdef", ARMCPU, prop_pauth_impdef, false); static const Property arm_cpu_pauth_qarma3_property = DEFINE_PROP_BOOL("pauth-qarma3", ARMCPU, prop_pauth_qarma3, false); +static Property arm_cpu_pauth_qarma5_property = + DEFINE_PROP_BOOL("pauth-qarma5", ARMCPU, prop_pauth_qarma5, false); void aarch64_add_pauth_properties(Object *obj) { @@ -573,6 +590,7 @@ void aarch64_add_pauth_properties(Object *obj) } else { qdev_property_add_static(DEVICE(obj), &arm_cpu_pauth_impdef_property); qdev_property_add_static(DEVICE(obj), &arm_cpu_pauth_qarma3_property); + qdev_property_add_static(DEVICE(obj), &arm_cpu_pauth_qarma5_property); } } diff --git a/target/arm/helper.c b/target/arm/helper.c index 5b595f951b..6399767851 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -17,11 +17,9 @@ #include "qemu/main-loop.h" #include "qemu/timer.h" #include "qemu/bitops.h" -#include "qemu/crc32c.h" #include "qemu/qemu-print.h" #include "exec/exec-all.h" #include "exec/translation-block.h" -#include <zlib.h> /* for crc32 */ #include "hw/irq.h" #include "system/cpu-timers.h" #include "system/kvm.h" @@ -10984,289 +10982,6 @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, }; } -/* - * Note that signed overflow is undefined in C. The following routines are - * careful to use unsigned types where modulo arithmetic is required. - * Failure to do so _will_ break on newer gcc. - */ - -/* Signed saturating arithmetic. */ - -/* Perform 16-bit signed saturating addition. */ -static inline uint16_t add16_sat(uint16_t a, uint16_t b) -{ - uint16_t res; - - res = a + b; - if (((res ^ a) & 0x8000) && !((a ^ b) & 0x8000)) { - if (a & 0x8000) { - res = 0x8000; - } else { - res = 0x7fff; - } - } - return res; -} - -/* Perform 8-bit signed saturating addition. */ -static inline uint8_t add8_sat(uint8_t a, uint8_t b) -{ - uint8_t res; - - res = a + b; - if (((res ^ a) & 0x80) && !((a ^ b) & 0x80)) { - if (a & 0x80) { - res = 0x80; - } else { - res = 0x7f; - } - } - return res; -} - -/* Perform 16-bit signed saturating subtraction. */ -static inline uint16_t sub16_sat(uint16_t a, uint16_t b) -{ - uint16_t res; - - res = a - b; - if (((res ^ a) & 0x8000) && ((a ^ b) & 0x8000)) { - if (a & 0x8000) { - res = 0x8000; - } else { - res = 0x7fff; - } - } - return res; -} - -/* Perform 8-bit signed saturating subtraction. */ -static inline uint8_t sub8_sat(uint8_t a, uint8_t b) -{ - uint8_t res; - - res = a - b; - if (((res ^ a) & 0x80) && ((a ^ b) & 0x80)) { - if (a & 0x80) { - res = 0x80; - } else { - res = 0x7f; - } - } - return res; -} - -#define ADD16(a, b, n) RESULT(add16_sat(a, b), n, 16); -#define SUB16(a, b, n) RESULT(sub16_sat(a, b), n, 16); -#define ADD8(a, b, n) RESULT(add8_sat(a, b), n, 8); -#define SUB8(a, b, n) RESULT(sub8_sat(a, b), n, 8); -#define PFX q - -#include "op_addsub.h" - -/* Unsigned saturating arithmetic. */ -static inline uint16_t add16_usat(uint16_t a, uint16_t b) -{ - uint16_t res; - res = a + b; - if (res < a) { - res = 0xffff; - } - return res; -} - -static inline uint16_t sub16_usat(uint16_t a, uint16_t b) -{ - if (a > b) { - return a - b; - } else { - return 0; - } -} - -static inline uint8_t add8_usat(uint8_t a, uint8_t b) -{ - uint8_t res; - res = a + b; - if (res < a) { - res = 0xff; - } - return res; -} - -static inline uint8_t sub8_usat(uint8_t a, uint8_t b) -{ - if (a > b) { - return a - b; - } else { - return 0; - } -} - -#define ADD16(a, b, n) RESULT(add16_usat(a, b), n, 16); -#define SUB16(a, b, n) RESULT(sub16_usat(a, b), n, 16); -#define ADD8(a, b, n) RESULT(add8_usat(a, b), n, 8); -#define SUB8(a, b, n) RESULT(sub8_usat(a, b), n, 8); -#define PFX uq - -#include "op_addsub.h" - -/* Signed modulo arithmetic. */ -#define SARITH16(a, b, n, op) do { \ - int32_t sum; \ - sum = (int32_t)(int16_t)(a) op (int32_t)(int16_t)(b); \ - RESULT(sum, n, 16); \ - if (sum >= 0) \ - ge |= 3 << (n * 2); \ - } while (0) - -#define SARITH8(a, b, n, op) do { \ - int32_t sum; \ - sum = (int32_t)(int8_t)(a) op (int32_t)(int8_t)(b); \ - RESULT(sum, n, 8); \ - if (sum >= 0) \ - ge |= 1 << n; \ - } while (0) - - -#define ADD16(a, b, n) SARITH16(a, b, n, +) -#define SUB16(a, b, n) SARITH16(a, b, n, -) -#define ADD8(a, b, n) SARITH8(a, b, n, +) -#define SUB8(a, b, n) SARITH8(a, b, n, -) -#define PFX s -#define ARITH_GE - -#include "op_addsub.h" - -/* Unsigned modulo arithmetic. */ -#define ADD16(a, b, n) do { \ - uint32_t sum; \ - sum = (uint32_t)(uint16_t)(a) + (uint32_t)(uint16_t)(b); \ - RESULT(sum, n, 16); \ - if ((sum >> 16) == 1) \ - ge |= 3 << (n * 2); \ - } while (0) - -#define ADD8(a, b, n) do { \ - uint32_t sum; \ - sum = (uint32_t)(uint8_t)(a) + (uint32_t)(uint8_t)(b); \ - RESULT(sum, n, 8); \ - if ((sum >> 8) == 1) \ - ge |= 1 << n; \ - } while (0) - -#define SUB16(a, b, n) do { \ - uint32_t sum; \ - sum = (uint32_t)(uint16_t)(a) - (uint32_t)(uint16_t)(b); \ - RESULT(sum, n, 16); \ - if ((sum >> 16) == 0) \ - ge |= 3 << (n * 2); \ - } while (0) - -#define SUB8(a, b, n) do { \ - uint32_t sum; \ - sum = (uint32_t)(uint8_t)(a) - (uint32_t)(uint8_t)(b); \ - RESULT(sum, n, 8); \ - if ((sum >> 8) == 0) \ - ge |= 1 << n; \ - } while (0) - -#define PFX u -#define ARITH_GE - -#include "op_addsub.h" - -/* Halved signed arithmetic. */ -#define ADD16(a, b, n) \ - RESULT(((int32_t)(int16_t)(a) + (int32_t)(int16_t)(b)) >> 1, n, 16) -#define SUB16(a, b, n) \ - RESULT(((int32_t)(int16_t)(a) - (int32_t)(int16_t)(b)) >> 1, n, 16) -#define ADD8(a, b, n) \ - RESULT(((int32_t)(int8_t)(a) + (int32_t)(int8_t)(b)) >> 1, n, 8) -#define SUB8(a, b, n) \ - RESULT(((int32_t)(int8_t)(a) - (int32_t)(int8_t)(b)) >> 1, n, 8) -#define PFX sh - -#include "op_addsub.h" - -/* Halved unsigned arithmetic. */ -#define ADD16(a, b, n) \ - RESULT(((uint32_t)(uint16_t)(a) + (uint32_t)(uint16_t)(b)) >> 1, n, 16) -#define SUB16(a, b, n) \ - RESULT(((uint32_t)(uint16_t)(a) - (uint32_t)(uint16_t)(b)) >> 1, n, 16) -#define ADD8(a, b, n) \ - RESULT(((uint32_t)(uint8_t)(a) + (uint32_t)(uint8_t)(b)) >> 1, n, 8) -#define SUB8(a, b, n) \ - RESULT(((uint32_t)(uint8_t)(a) - (uint32_t)(uint8_t)(b)) >> 1, n, 8) -#define PFX uh - -#include "op_addsub.h" - -static inline uint8_t do_usad(uint8_t a, uint8_t b) -{ - if (a > b) { - return a - b; - } else { - return b - a; - } -} - -/* Unsigned sum of absolute byte differences. */ -uint32_t HELPER(usad8)(uint32_t a, uint32_t b) -{ - uint32_t sum; - sum = do_usad(a, b); - sum += do_usad(a >> 8, b >> 8); - sum += do_usad(a >> 16, b >> 16); - sum += do_usad(a >> 24, b >> 24); - return sum; -} - -/* For ARMv6 SEL instruction. */ -uint32_t HELPER(sel_flags)(uint32_t flags, uint32_t a, uint32_t b) -{ - uint32_t mask; - - mask = 0; - if (flags & 1) { - mask |= 0xff; - } - if (flags & 2) { - mask |= 0xff00; - } - if (flags & 4) { - mask |= 0xff0000; - } - if (flags & 8) { - mask |= 0xff000000; - } - return (a & mask) | (b & ~mask); -} - -/* - * CRC helpers. - * The upper bytes of val (above the number specified by 'bytes') must have - * been zeroed out by the caller. - */ -uint32_t HELPER(crc32)(uint32_t acc, uint32_t val, uint32_t bytes) -{ - uint8_t buf[4]; - - stl_le_p(buf, val); - - /* zlib crc32 converts the accumulator and output to one's complement. */ - return crc32(acc ^ 0xffffffff, buf, bytes) ^ 0xffffffff; -} - -uint32_t HELPER(crc32c)(uint32_t acc, uint32_t val, uint32_t bytes) -{ - uint8_t buf[4]; - - stl_le_p(buf, val); - - /* Linux crc32c converts the output to one's complement. */ - return crc32c(acc, buf, bytes) ^ 0xffffffff; -} /* * Return the exception level to which FP-disabled exceptions should diff --git a/target/arm/kvm.c b/target/arm/kvm.c index a9444a2c7a..da30bdbb23 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -2387,7 +2387,7 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr) */ if (code == BUS_MCEERR_AR) { kvm_cpu_synchronize_state(c); - if (!acpi_ghes_record_errors(ACPI_HEST_SRC_ID_SEA, paddr)) { + if (!acpi_ghes_memory_errors(ACPI_HEST_SRC_ID_SEA, paddr)) { kvm_inject_arm_sea(c); } else { error_report("failed to record the error"); diff --git a/target/arm/tcg/arith_helper.c b/target/arm/tcg/arith_helper.c new file mode 100644 index 0000000000..9a555c7966 --- /dev/null +++ b/target/arm/tcg/arith_helper.c @@ -0,0 +1,296 @@ +/* + * ARM generic helpers for various arithmetical operations. + * + * This code is licensed under the GNU GPL v2 or later. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#include "qemu/osdep.h" +#include "cpu.h" +#include "exec/helper-proto.h" +#include "qemu/crc32c.h" +#include <zlib.h> /* for crc32 */ + +/* + * Note that signed overflow is undefined in C. The following routines are + * careful to use unsigned types where modulo arithmetic is required. + * Failure to do so _will_ break on newer gcc. + */ + +/* Signed saturating arithmetic. */ + +/* Perform 16-bit signed saturating addition. */ +static inline uint16_t add16_sat(uint16_t a, uint16_t b) +{ + uint16_t res; + + res = a + b; + if (((res ^ a) & 0x8000) && !((a ^ b) & 0x8000)) { + if (a & 0x8000) { + res = 0x8000; + } else { + res = 0x7fff; + } + } + return res; +} + +/* Perform 8-bit signed saturating addition. */ +static inline uint8_t add8_sat(uint8_t a, uint8_t b) +{ + uint8_t res; + + res = a + b; + if (((res ^ a) & 0x80) && !((a ^ b) & 0x80)) { + if (a & 0x80) { + res = 0x80; + } else { + res = 0x7f; + } + } + return res; +} + +/* Perform 16-bit signed saturating subtraction. */ +static inline uint16_t sub16_sat(uint16_t a, uint16_t b) +{ + uint16_t res; + + res = a - b; + if (((res ^ a) & 0x8000) && ((a ^ b) & 0x8000)) { + if (a & 0x8000) { + res = 0x8000; + } else { + res = 0x7fff; + } + } + return res; +} + +/* Perform 8-bit signed saturating subtraction. */ +static inline uint8_t sub8_sat(uint8_t a, uint8_t b) +{ + uint8_t res; + + res = a - b; + if (((res ^ a) & 0x80) && ((a ^ b) & 0x80)) { + if (a & 0x80) { + res = 0x80; + } else { + res = 0x7f; + } + } + return res; +} + +#define ADD16(a, b, n) RESULT(add16_sat(a, b), n, 16); +#define SUB16(a, b, n) RESULT(sub16_sat(a, b), n, 16); +#define ADD8(a, b, n) RESULT(add8_sat(a, b), n, 8); +#define SUB8(a, b, n) RESULT(sub8_sat(a, b), n, 8); +#define PFX q + +#include "op_addsub.c.inc" + +/* Unsigned saturating arithmetic. */ +static inline uint16_t add16_usat(uint16_t a, uint16_t b) +{ + uint16_t res; + res = a + b; + if (res < a) { + res = 0xffff; + } + return res; +} + +static inline uint16_t sub16_usat(uint16_t a, uint16_t b) +{ + if (a > b) { + return a - b; + } else { + return 0; + } +} + +static inline uint8_t add8_usat(uint8_t a, uint8_t b) +{ + uint8_t res; + res = a + b; + if (res < a) { + res = 0xff; + } + return res; +} + +static inline uint8_t sub8_usat(uint8_t a, uint8_t b) +{ + if (a > b) { + return a - b; + } else { + return 0; + } +} + +#define ADD16(a, b, n) RESULT(add16_usat(a, b), n, 16); +#define SUB16(a, b, n) RESULT(sub16_usat(a, b), n, 16); +#define ADD8(a, b, n) RESULT(add8_usat(a, b), n, 8); +#define SUB8(a, b, n) RESULT(sub8_usat(a, b), n, 8); +#define PFX uq + +#include "op_addsub.c.inc" + +/* Signed modulo arithmetic. */ +#define SARITH16(a, b, n, op) do { \ + int32_t sum; \ + sum = (int32_t)(int16_t)(a) op (int32_t)(int16_t)(b); \ + RESULT(sum, n, 16); \ + if (sum >= 0) \ + ge |= 3 << (n * 2); \ + } while (0) + +#define SARITH8(a, b, n, op) do { \ + int32_t sum; \ + sum = (int32_t)(int8_t)(a) op (int32_t)(int8_t)(b); \ + RESULT(sum, n, 8); \ + if (sum >= 0) \ + ge |= 1 << n; \ + } while (0) + + +#define ADD16(a, b, n) SARITH16(a, b, n, +) +#define SUB16(a, b, n) SARITH16(a, b, n, -) +#define ADD8(a, b, n) SARITH8(a, b, n, +) +#define SUB8(a, b, n) SARITH8(a, b, n, -) +#define PFX s +#define ARITH_GE + +#include "op_addsub.c.inc" + +/* Unsigned modulo arithmetic. */ +#define ADD16(a, b, n) do { \ + uint32_t sum; \ + sum = (uint32_t)(uint16_t)(a) + (uint32_t)(uint16_t)(b); \ + RESULT(sum, n, 16); \ + if ((sum >> 16) == 1) \ + ge |= 3 << (n * 2); \ + } while (0) + +#define ADD8(a, b, n) do { \ + uint32_t sum; \ + sum = (uint32_t)(uint8_t)(a) + (uint32_t)(uint8_t)(b); \ + RESULT(sum, n, 8); \ + if ((sum >> 8) == 1) \ + ge |= 1 << n; \ + } while (0) + +#define SUB16(a, b, n) do { \ + uint32_t sum; \ + sum = (uint32_t)(uint16_t)(a) - (uint32_t)(uint16_t)(b); \ + RESULT(sum, n, 16); \ + if ((sum >> 16) == 0) \ + ge |= 3 << (n * 2); \ + } while (0) + +#define SUB8(a, b, n) do { \ + uint32_t sum; \ + sum = (uint32_t)(uint8_t)(a) - (uint32_t)(uint8_t)(b); \ + RESULT(sum, n, 8); \ + if ((sum >> 8) == 0) \ + ge |= 1 << n; \ + } while (0) + +#define PFX u +#define ARITH_GE + +#include "op_addsub.c.inc" + +/* Halved signed arithmetic. */ +#define ADD16(a, b, n) \ + RESULT(((int32_t)(int16_t)(a) + (int32_t)(int16_t)(b)) >> 1, n, 16) +#define SUB16(a, b, n) \ + RESULT(((int32_t)(int16_t)(a) - (int32_t)(int16_t)(b)) >> 1, n, 16) +#define ADD8(a, b, n) \ + RESULT(((int32_t)(int8_t)(a) + (int32_t)(int8_t)(b)) >> 1, n, 8) +#define SUB8(a, b, n) \ + RESULT(((int32_t)(int8_t)(a) - (int32_t)(int8_t)(b)) >> 1, n, 8) +#define PFX sh + +#include "op_addsub.c.inc" + +/* Halved unsigned arithmetic. */ +#define ADD16(a, b, n) \ + RESULT(((uint32_t)(uint16_t)(a) + (uint32_t)(uint16_t)(b)) >> 1, n, 16) +#define SUB16(a, b, n) \ + RESULT(((uint32_t)(uint16_t)(a) - (uint32_t)(uint16_t)(b)) >> 1, n, 16) +#define ADD8(a, b, n) \ + RESULT(((uint32_t)(uint8_t)(a) + (uint32_t)(uint8_t)(b)) >> 1, n, 8) +#define SUB8(a, b, n) \ + RESULT(((uint32_t)(uint8_t)(a) - (uint32_t)(uint8_t)(b)) >> 1, n, 8) +#define PFX uh + +#include "op_addsub.c.inc" + +static inline uint8_t do_usad(uint8_t a, uint8_t b) +{ + if (a > b) { + return a - b; + } else { + return b - a; + } +} + +/* Unsigned sum of absolute byte differences. */ +uint32_t HELPER(usad8)(uint32_t a, uint32_t b) +{ + uint32_t sum; + sum = do_usad(a, b); + sum += do_usad(a >> 8, b >> 8); + sum += do_usad(a >> 16, b >> 16); + sum += do_usad(a >> 24, b >> 24); + return sum; +} + +/* For ARMv6 SEL instruction. */ +uint32_t HELPER(sel_flags)(uint32_t flags, uint32_t a, uint32_t b) +{ + uint32_t mask; + + mask = 0; + if (flags & 1) { + mask |= 0xff; + } + if (flags & 2) { + mask |= 0xff00; + } + if (flags & 4) { + mask |= 0xff0000; + } + if (flags & 8) { + mask |= 0xff000000; + } + return (a & mask) | (b & ~mask); +} + +/* + * CRC helpers. + * The upper bytes of val (above the number specified by 'bytes') must have + * been zeroed out by the caller. + */ +uint32_t HELPER(crc32)(uint32_t acc, uint32_t val, uint32_t bytes) +{ + uint8_t buf[4]; + + stl_le_p(buf, val); + + /* zlib crc32 converts the accumulator and output to one's complement. */ + return crc32(acc ^ 0xffffffff, buf, bytes) ^ 0xffffffff; +} + +uint32_t HELPER(crc32c)(uint32_t acc, uint32_t val, uint32_t bytes) +{ + uint8_t buf[4]; + + stl_le_p(buf, val); + + /* Linux crc32c converts the output to one's complement. */ + return crc32c(acc, buf, bytes) ^ 0xffffffff; +} diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build index 09238989c5..1f9077c372 100644 --- a/target/arm/tcg/meson.build +++ b/target/arm/tcg/meson.build @@ -40,6 +40,7 @@ arm_ss.add(files( 'tlb_helper.c', 'vec_helper.c', 'tlb-insns.c', + 'arith_helper.c', )) arm_ss.add(when: 'TARGET_AARCH64', if_true: files( diff --git a/target/arm/op_addsub.h b/target/arm/tcg/op_addsub.c.inc index ca4a1893c3..ca4a1893c3 100644 --- a/target/arm/op_addsub.h +++ b/target/arm/tcg/op_addsub.c.inc diff --git a/target/hppa/cpu.c b/target/hppa/cpu.c index 47d0160955..b0bc9d35e4 100644 --- a/target/hppa/cpu.c +++ b/target/hppa/cpu.c @@ -195,13 +195,29 @@ static void hppa_cpu_realizefn(DeviceState *dev, Error **errp) static void hppa_cpu_initfn(Object *obj) { + CPUHPPAState *env = cpu_env(CPU(obj)); + + env->is_pa20 = !!object_dynamic_cast(obj, TYPE_HPPA64_CPU); +} + +static void hppa_cpu_reset_hold(Object *obj, ResetType type) +{ + HPPACPUClass *scc = HPPA_CPU_GET_CLASS(obj); CPUState *cs = CPU(obj); HPPACPU *cpu = HPPA_CPU(obj); CPUHPPAState *env = &cpu->env; + if (scc->parent_phases.hold) { + scc->parent_phases.hold(obj, type); + } cs->exception_index = -1; + cs->halted = 0; + cpu_set_pc(cs, 0xf0000004); + + memset(env, 0, offsetof(CPUHPPAState, end_reset_fields)); + cpu_hppa_loaded_fr0(env); - cpu_hppa_put_psw(env, PSW_W); + cpu_hppa_put_psw(env, PSW_M); } static ObjectClass *hppa_cpu_class_by_name(const char *cpu_model) @@ -242,10 +258,14 @@ static void hppa_cpu_class_init(ObjectClass *oc, void *data) DeviceClass *dc = DEVICE_CLASS(oc); CPUClass *cc = CPU_CLASS(oc); HPPACPUClass *acc = HPPA_CPU_CLASS(oc); + ResettableClass *rc = RESETTABLE_CLASS(oc); device_class_set_parent_realize(dc, hppa_cpu_realizefn, &acc->parent_realize); + resettable_class_set_parent_phases(rc, NULL, hppa_cpu_reset_hold, NULL, + &acc->parent_phases); + cc->class_by_name = hppa_cpu_class_by_name; cc->has_work = hppa_cpu_has_work; cc->mmu_index = hppa_cpu_mmu_index; diff --git a/target/hppa/cpu.h b/target/hppa/cpu.h index 22a6510e08..083d4f5a56 100644 --- a/target/hppa/cpu.h +++ b/target/hppa/cpu.h @@ -263,6 +263,11 @@ typedef struct CPUArchState { IntervalTreeRoot tlb_root; HPPATLBEntry tlb[HPPA_TLB_ENTRIES]; + + /* Fields up to this point are cleared by a CPU reset */ + struct {} end_reset_fields; + + bool is_pa20; } CPUHPPAState; /** @@ -281,6 +286,7 @@ struct ArchCPU { /** * HPPACPUClass: * @parent_realize: The parent class' realize handler. + * @parent_phases: The parent class' reset phase handlers. * * An HPPA CPU model. */ @@ -288,13 +294,14 @@ struct HPPACPUClass { CPUClass parent_class; DeviceRealize parent_realize; + ResettablePhases parent_phases; }; #include "exec/cpu-all.h" -static inline bool hppa_is_pa20(CPUHPPAState *env) +static inline bool hppa_is_pa20(const CPUHPPAState *env) { - return object_dynamic_cast(OBJECT(env_cpu(env)), TYPE_HPPA64_CPU) != NULL; + return env->is_pa20; } static inline int HPPA_BTLB_ENTRIES(CPUHPPAState *env) diff --git a/target/loongarch/cpu_helper.c b/target/loongarch/cpu_helper.c index 580362ac3e..930466ca48 100644 --- a/target/loongarch/cpu_helper.c +++ b/target/loongarch/cpu_helper.c @@ -141,9 +141,85 @@ bool loongarch_tlb_search(CPULoongArchState *env, target_ulong vaddr, return false; } +static int loongarch_page_table_walker(CPULoongArchState *env, hwaddr *physical, + int *prot, target_ulong address) +{ + CPUState *cs = env_cpu(env); + target_ulong index, phys; + uint64_t dir_base, dir_width; + uint64_t base; + int level; + + if ((address >> 63) & 0x1) { + base = env->CSR_PGDH; + } else { + base = env->CSR_PGDL; + } + base &= TARGET_PHYS_MASK; + + for (level = 4; level > 0; level--) { + get_dir_base_width(env, &dir_base, &dir_width, level); + + if (dir_width == 0) { + continue; + } + + /* get next level page directory */ + index = (address >> dir_base) & ((1 << dir_width) - 1); + phys = base | index << 3; + base = ldq_phys(cs->as, phys) & TARGET_PHYS_MASK; + if (FIELD_EX64(base, TLBENTRY, HUGE)) { + /* base is a huge pte */ + break; + } + } + + /* pte */ + if (FIELD_EX64(base, TLBENTRY, HUGE)) { + /* Huge Page. base is pte */ + base = FIELD_DP64(base, TLBENTRY, LEVEL, 0); + base = FIELD_DP64(base, TLBENTRY, HUGE, 0); + if (FIELD_EX64(base, TLBENTRY, HGLOBAL)) { + base = FIELD_DP64(base, TLBENTRY, HGLOBAL, 0); + base = FIELD_DP64(base, TLBENTRY, G, 1); + } + } else { + /* Normal Page. base points to pte */ + get_dir_base_width(env, &dir_base, &dir_width, 0); + index = (address >> dir_base) & ((1 << dir_width) - 1); + phys = base | index << 3; + base = ldq_phys(cs->as, phys); + } + + /* TODO: check plv and other bits? */ + + /* base is pte, in normal pte format */ + if (!FIELD_EX64(base, TLBENTRY, V)) { + return TLBRET_NOMATCH; + } + + if (!FIELD_EX64(base, TLBENTRY, D)) { + *prot = PAGE_READ; + } else { + *prot = PAGE_READ | PAGE_WRITE; + } + + /* get TARGET_PAGE_SIZE aligned physical address */ + base += (address & TARGET_PHYS_MASK) & ((1 << dir_base) - 1); + /* mask RPLV, NX, NR bits */ + base = FIELD_DP64(base, TLBENTRY_64, RPLV, 0); + base = FIELD_DP64(base, TLBENTRY_64, NX, 0); + base = FIELD_DP64(base, TLBENTRY_64, NR, 0); + /* mask other attribute bits */ + *physical = base & TARGET_PAGE_MASK; + + return 0; +} + static int loongarch_map_address(CPULoongArchState *env, hwaddr *physical, int *prot, target_ulong address, - MMUAccessType access_type, int mmu_idx) + MMUAccessType access_type, int mmu_idx, + int is_debug) { int index, match; @@ -151,6 +227,13 @@ static int loongarch_map_address(CPULoongArchState *env, hwaddr *physical, if (match) { return loongarch_map_tlb_entry(env, physical, prot, address, access_type, index, mmu_idx); + } else if (is_debug) { + /* + * For debugger memory access, we want to do the map when there is a + * legal mapping, even if the mapping is not yet in TLB. return 0 if + * there is a valid map, else none zero. + */ + return loongarch_page_table_walker(env, physical, prot, address); } return TLBRET_NOMATCH; @@ -158,7 +241,8 @@ static int loongarch_map_address(CPULoongArchState *env, hwaddr *physical, #else static int loongarch_map_address(CPULoongArchState *env, hwaddr *physical, int *prot, target_ulong address, - MMUAccessType access_type, int mmu_idx) + MMUAccessType access_type, int mmu_idx, + int is_debug) { return TLBRET_NOMATCH; } @@ -178,7 +262,7 @@ static hwaddr dmw_va2pa(CPULoongArchState *env, target_ulong va, int get_physical_address(CPULoongArchState *env, hwaddr *physical, int *prot, target_ulong address, - MMUAccessType access_type, int mmu_idx) + MMUAccessType access_type, int mmu_idx, int is_debug) { int user_mode = mmu_idx == MMU_USER_IDX; int kernel_mode = mmu_idx == MMU_KERNEL_IDX; @@ -222,7 +306,7 @@ int get_physical_address(CPULoongArchState *env, hwaddr *physical, /* Mapped address */ return loongarch_map_address(env, physical, prot, address, - access_type, mmu_idx); + access_type, mmu_idx, is_debug); } hwaddr loongarch_cpu_get_phys_page_debug(CPUState *cs, vaddr addr) @@ -232,7 +316,7 @@ hwaddr loongarch_cpu_get_phys_page_debug(CPUState *cs, vaddr addr) int prot; if (get_physical_address(env, &phys_addr, &prot, addr, MMU_DATA_LOAD, - cpu_mmu_index(cs, false)) != 0) { + cpu_mmu_index(cs, false), 1) != 0) { return -1; } return phys_addr; diff --git a/target/loongarch/helper.h b/target/loongarch/helper.h index b3b64a0215..943517b5f2 100644 --- a/target/loongarch/helper.h +++ b/target/loongarch/helper.h @@ -104,6 +104,7 @@ DEF_HELPER_2(csrwr_estat, i64, env, tl) DEF_HELPER_2(csrwr_asid, i64, env, tl) DEF_HELPER_2(csrwr_tcfg, i64, env, tl) DEF_HELPER_2(csrwr_ticlr, i64, env, tl) +DEF_HELPER_2(csrwr_pwcl, i64, env, tl) DEF_HELPER_2(iocsrrd_b, i64, env, tl) DEF_HELPER_2(iocsrrd_h, i64, env, tl) DEF_HELPER_2(iocsrrd_w, i64, env, tl) diff --git a/target/loongarch/internals.h b/target/loongarch/internals.h index ad9cf4fc7a..7b254c5f49 100644 --- a/target/loongarch/internals.h +++ b/target/loongarch/internals.h @@ -56,7 +56,9 @@ bool loongarch_tlb_search(CPULoongArchState *env, target_ulong vaddr, int *index); int get_physical_address(CPULoongArchState *env, hwaddr *physical, int *prot, target_ulong address, - MMUAccessType access_type, int mmu_idx); + MMUAccessType access_type, int mmu_idx, int is_debug); +void get_dir_base_width(CPULoongArchState *env, uint64_t *dir_base, + uint64_t *dir_width, target_ulong level); hwaddr loongarch_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); #ifdef CONFIG_TCG diff --git a/target/loongarch/tcg/csr_helper.c b/target/loongarch/tcg/csr_helper.c index 15f94caefa..6c95be9910 100644 --- a/target/loongarch/tcg/csr_helper.c +++ b/target/loongarch/tcg/csr_helper.c @@ -6,6 +6,7 @@ */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "qemu/main-loop.h" #include "cpu.h" #include "internals.h" @@ -95,3 +96,23 @@ target_ulong helper_csrwr_ticlr(CPULoongArchState *env, target_ulong val) } return old_v; } + +target_ulong helper_csrwr_pwcl(CPULoongArchState *env, target_ulong val) +{ + int shift; + int64_t old_v = env->CSR_PWCL; + + /* + * The real hardware only supports 64bit PTE width now, 128bit or others + * treated as illegal. + */ + shift = FIELD_EX64(val, CSR_PWCL, PTEWIDTH); + if (shift) { + qemu_log_mask(LOG_GUEST_ERROR, + "Attempted set pte width with %d bit\n", 64 << shift); + val = FIELD_DP64(val, CSR_PWCL, PTEWIDTH, 0); + } + + env->CSR_PWCL = val; + return old_v; +} diff --git a/target/loongarch/tcg/insn_trans/trans_privileged.c.inc b/target/loongarch/tcg/insn_trans/trans_privileged.c.inc index 7e4ec93edb..30f9b83fb2 100644 --- a/target/loongarch/tcg/insn_trans/trans_privileged.c.inc +++ b/target/loongarch/tcg/insn_trans/trans_privileged.c.inc @@ -95,7 +95,7 @@ static const CSRInfo csr_info[] = { CSR_OFF(PGDL), CSR_OFF(PGDH), CSR_OFF_FUNCS(PGD, CSRFL_READONLY, gen_helper_csrrd_pgd, NULL), - CSR_OFF(PWCL), + CSR_OFF_FUNCS(PWCL, 0, NULL, gen_helper_csrwr_pwcl), CSR_OFF(PWCH), CSR_OFF(STLBPS), CSR_OFF(RVACFG), diff --git a/target/loongarch/tcg/tlb_helper.c b/target/loongarch/tcg/tlb_helper.c index 97f38fc391..a323606e5a 100644 --- a/target/loongarch/tcg/tlb_helper.c +++ b/target/loongarch/tcg/tlb_helper.c @@ -18,7 +18,7 @@ #include "exec/log.h" #include "cpu-csr.h" -static void get_dir_base_width(CPULoongArchState *env, uint64_t *dir_base, +void get_dir_base_width(CPULoongArchState *env, uint64_t *dir_base, uint64_t *dir_width, target_ulong level) { switch (level) { @@ -485,7 +485,7 @@ bool loongarch_cpu_tlb_fill(CPUState *cs, vaddr address, int size, /* Data access */ ret = get_physical_address(env, &physical, &prot, address, - access_type, mmu_idx); + access_type, mmu_idx, 0); if (ret == TLBRET_MATCH) { tlb_set_page(cs, address & TARGET_PAGE_MASK, @@ -512,7 +512,6 @@ target_ulong helper_lddir(CPULoongArchState *env, target_ulong base, { CPUState *cs = env_cpu(env); target_ulong badvaddr, index, phys, ret; - int shift; uint64_t dir_base, dir_width; if (unlikely((level == 0) || (level > 4))) { @@ -537,14 +536,9 @@ target_ulong helper_lddir(CPULoongArchState *env, target_ulong base, badvaddr = env->CSR_TLBRBADV; base = base & TARGET_PHYS_MASK; - - /* 0:64bit, 1:128bit, 2:192bit, 3:256bit */ - shift = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, PTEWIDTH); - shift = (shift + 1) * 3; - get_dir_base_width(env, &dir_base, &dir_width, level); index = (badvaddr >> dir_base) & ((1 << dir_width) - 1); - phys = base | index << shift; + phys = base | index << 3; ret = ldq_phys(cs->as, phys) & TARGET_PHYS_MASK; return ret; } @@ -554,7 +548,6 @@ void helper_ldpte(CPULoongArchState *env, target_ulong base, target_ulong odd, { CPUState *cs = env_cpu(env); target_ulong phys, tmp0, ptindex, ptoffset0, ptoffset1, ps, badv; - int shift; uint64_t ptbase = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, PTBASE); uint64_t ptwidth = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, PTWIDTH); uint64_t dir_base, dir_width; @@ -595,16 +588,12 @@ void helper_ldpte(CPULoongArchState *env, target_ulong base, target_ulong odd, tmp0 += MAKE_64BIT_MASK(ps, 1); } } else { - /* 0:64bit, 1:128bit, 2:192bit, 3:256bit */ - shift = FIELD_EX64(env->CSR_PWCL, CSR_PWCL, PTEWIDTH); - shift = (shift + 1) * 3; badv = env->CSR_TLBRBADV; ptindex = (badv >> ptbase) & ((1 << ptwidth) - 1); ptindex = ptindex & ~0x1; /* clear bit 0 */ - ptoffset0 = ptindex << shift; - ptoffset1 = (ptindex + 1) << shift; - + ptoffset0 = ptindex << 3; + ptoffset1 = (ptindex + 1) << 3; phys = base | (odd ? ptoffset1 : ptoffset0); tmp0 = ldq_phys(cs->as, phys) & TARGET_PHYS_MASK; ps = ptbase; diff --git a/target/mips/cpu.c b/target/mips/cpu.c index e3af02a4e6..47cd7cfdce 100644 --- a/target/mips/cpu.c +++ b/target/mips/cpu.c @@ -644,7 +644,7 @@ MIPSCPU *mips_cpu_create_with_clock(const char *cpu_type, Clock *cpu_refclk, { DeviceState *cpu; - cpu = DEVICE(object_new(cpu_type)); + cpu = qdev_new(cpu_type); qdev_connect_clock_in(cpu, "clk-in", cpu_refclk); object_property_set_bool(OBJECT(cpu), "big-endian", is_big_endian, &error_abort); diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c index db645a4813..4d56e653dd 100644 --- a/target/s390x/kvm/kvm.c +++ b/target/s390x/kvm/kvm.c @@ -374,13 +374,9 @@ int kvm_arch_init(MachineState *ms, KVMState *s) kvm_vm_enable_cap(s, KVM_CAP_S390_VECTOR_REGISTERS, 0); kvm_vm_enable_cap(s, KVM_CAP_S390_USER_STSI, 0); kvm_vm_enable_cap(s, KVM_CAP_S390_CPU_TOPOLOGY, 0); - if (ri_allowed()) { - if (kvm_vm_enable_cap(s, KVM_CAP_S390_RI, 0) == 0) { - cap_ri = 1; - } - } - if (cpu_model_allowed()) { - kvm_vm_enable_cap(s, KVM_CAP_S390_GS, 0); + kvm_vm_enable_cap(s, KVM_CAP_S390_GS, 0); + if (kvm_vm_enable_cap(s, KVM_CAP_S390_RI, 0) == 0) { + cap_ri = 1; } /* @@ -389,7 +385,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s) * support is considered necessary, we only try to enable this for * newer machine types if KVM_CAP_S390_AIS_MIGRATION is available. */ - if (cpu_model_allowed() && kvm_kernel_irqchip_allowed() && + if (kvm_kernel_irqchip_allowed() && kvm_check_extension(s, KVM_CAP_S390_AIS_MIGRATION)) { kvm_vm_enable_cap(s, KVM_CAP_S390_AIS, 0); } @@ -2354,10 +2350,6 @@ static int configure_cpu_feat(const S390FeatBitmap features) bool kvm_s390_cpu_models_supported(void) { - if (!cpu_model_allowed()) { - /* compatibility machines interfere with the cpu model */ - return false; - } return kvm_vm_check_attr(kvm_state, KVM_S390_VM_CPU_MODEL, KVM_S390_VM_CPU_MACHINE) && kvm_vm_check_attr(kvm_state, KVM_S390_VM_CPU_MODEL, diff --git a/target/xtensa/cpu.c b/target/xtensa/cpu.c index 0910a3d290..4eb699d1f4 100644 --- a/target/xtensa/cpu.c +++ b/target/xtensa/cpu.c @@ -208,7 +208,7 @@ XtensaCPU *xtensa_cpu_create_with_clock(const char *cpu_type, Clock *cpu_refclk) { DeviceState *cpu; - cpu = DEVICE(object_new(cpu_type)); + cpu = qdev_new(cpu_type); qdev_connect_clock_in(cpu, "clk-in", cpu_refclk); qdev_realize(cpu, NULL, &error_abort); |